diff options
| author | Francesco Dolcini <francesco.dolcini@toradex.com> | 2024-03-14 08:58:18 +0100 |
|---|---|---|
| committer | Francesco Dolcini <francesco.dolcini@toradex.com> | 2024-03-14 08:58:18 +0100 |
| commit | b010b465886a57efc5e394dddc5aad8093591cde (patch) | |
| tree | 0e4f5e02dac9f748ec37ba45f9cf21666c1a4723 | |
| parent | 4a45b91c2a5391066ad769f3e023d00595b3d3f4 (diff) | |
| parent | a6174d6c4ff531039c677079321888a9a3f9951c (diff) | |
Merge tag '09.02.00.007' into toradex_ti-linux-6.1.y
RC Release 09.02.00.007
1638 files changed, 19861 insertions, 14478 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq index 5e6b74f30406..1e7e0bb4c14e 100644 --- a/Documentation/ABI/testing/sysfs-class-devfreq +++ b/Documentation/ABI/testing/sysfs-class-devfreq @@ -52,6 +52,9 @@ Description: echo 0 > /sys/class/devfreq/.../trans_stat + If the transition table is bigger than PAGE_SIZE, reading + this will return an -EFBIG error. + What: /sys/class/devfreq/.../available_frequencies Date: October 2012 Contact: Nishanth Menon <nm@ti.com> diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues index 978b76358661..40d5aab8452d 100644 --- a/Documentation/ABI/testing/sysfs-class-net-queues +++ b/Documentation/ABI/testing/sysfs-class-net-queues @@ -1,4 +1,4 @@ -What: /sys/class/<iface>/queues/rx-<queue>/rps_cpus +What: /sys/class/net/<iface>/queues/rx-<queue>/rps_cpus Date: March 2010 KernelVersion: 2.6.35 Contact: netdev@vger.kernel.org @@ -8,7 +8,7 @@ Description: network device queue. Possible values depend on the number of available CPU(s) in the system. -What: /sys/class/<iface>/queues/rx-<queue>/rps_flow_cnt +What: /sys/class/net/<iface>/queues/rx-<queue>/rps_flow_cnt Date: April 2010 KernelVersion: 2.6.35 Contact: netdev@vger.kernel.org @@ -16,7 +16,7 @@ Description: Number of Receive Packet Steering flows being currently processed by this particular network device receive queue. -What: /sys/class/<iface>/queues/tx-<queue>/tx_timeout +What: /sys/class/net/<iface>/queues/tx-<queue>/tx_timeout Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -24,7 +24,7 @@ Description: Indicates the number of transmit timeout events seen by this network interface transmit queue. -What: /sys/class/<iface>/queues/tx-<queue>/tx_maxrate +What: /sys/class/net/<iface>/queues/tx-<queue>/tx_maxrate Date: March 2015 KernelVersion: 4.1 Contact: netdev@vger.kernel.org @@ -32,7 +32,7 @@ Description: A Mbps max-rate set for the queue, a value of zero means disabled, default is disabled. -What: /sys/class/<iface>/queues/tx-<queue>/xps_cpus +What: /sys/class/net/<iface>/queues/tx-<queue>/xps_cpus Date: November 2010 KernelVersion: 2.6.38 Contact: netdev@vger.kernel.org @@ -42,7 +42,7 @@ Description: network device transmit queue. Possible vaules depend on the number of available CPU(s) in the system. -What: /sys/class/<iface>/queues/tx-<queue>/xps_rxqs +What: /sys/class/net/<iface>/queues/tx-<queue>/xps_rxqs Date: June 2018 KernelVersion: 4.18.0 Contact: netdev@vger.kernel.org @@ -53,7 +53,7 @@ Description: number of available receive queue(s) in the network device. Default is disabled. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -62,7 +62,7 @@ Description: of this particular network device transmit queue. Default value is 1000. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/inflight +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/inflight Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -70,7 +70,7 @@ Description: Indicates the number of bytes (objects) in flight on this network device transmit queue. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -79,7 +79,7 @@ Description: on this network device transmit queue. This value is clamped to be within the bounds defined by limit_max and limit_min. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -88,7 +88,7 @@ Description: queued on this network device transmit queue. See include/linux/dynamic_queue_limits.h for the default value. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics index 55db27815361..53e508c6936a 100644 --- a/Documentation/ABI/testing/sysfs-class-net-statistics +++ b/Documentation/ABI/testing/sysfs-class-net-statistics @@ -1,4 +1,4 @@ -What: /sys/class/<iface>/statistics/collisions +What: /sys/class/net/<iface>/statistics/collisions Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -6,7 +6,7 @@ Description: Indicates the number of collisions seen by this network device. This value might not be relevant with all MAC layers. -What: /sys/class/<iface>/statistics/multicast +What: /sys/class/net/<iface>/statistics/multicast Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -14,7 +14,7 @@ Description: Indicates the number of multicast packets received by this network device. -What: /sys/class/<iface>/statistics/rx_bytes +What: /sys/class/net/<iface>/statistics/rx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -23,7 +23,7 @@ Description: See the network driver for the exact meaning of when this value is incremented. -What: /sys/class/<iface>/statistics/rx_compressed +What: /sys/class/net/<iface>/statistics/rx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -32,7 +32,7 @@ Description: network device. This value might only be relevant for interfaces that support packet compression (e.g: PPP). -What: /sys/class/<iface>/statistics/rx_crc_errors +What: /sys/class/net/<iface>/statistics/rx_crc_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -41,7 +41,7 @@ Description: by this network device. Note that the specific meaning might depend on the MAC layer used by the interface. -What: /sys/class/<iface>/statistics/rx_dropped +What: /sys/class/net/<iface>/statistics/rx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -51,7 +51,7 @@ Description: packet processing. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_errors +What: /sys/class/net/<iface>/statistics/rx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -59,7 +59,7 @@ Description: Indicates the number of receive errors on this network device. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_fifo_errors +What: /sys/class/net/<iface>/statistics/rx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -68,7 +68,7 @@ Description: network device. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_frame_errors +What: /sys/class/net/<iface>/statistics/rx_frame_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -78,7 +78,7 @@ Description: on the MAC layer protocol used. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_length_errors +What: /sys/class/net/<iface>/statistics/rx_length_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -87,7 +87,7 @@ Description: error, oversized or undersized. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_missed_errors +What: /sys/class/net/<iface>/statistics/rx_missed_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -96,7 +96,7 @@ Description: due to lack of capacity in the receive side. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_nohandler +What: /sys/class/net/<iface>/statistics/rx_nohandler Date: February 2016 KernelVersion: 4.6 Contact: netdev@vger.kernel.org @@ -104,7 +104,7 @@ Description: Indicates the number of received packets that were dropped on an inactive device by the network core. -What: /sys/class/<iface>/statistics/rx_over_errors +What: /sys/class/net/<iface>/statistics/rx_over_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -114,7 +114,7 @@ Description: (e.g: larger than MTU). See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_packets +What: /sys/class/net/<iface>/statistics/rx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -122,7 +122,7 @@ Description: Indicates the total number of good packets received by this network device. -What: /sys/class/<iface>/statistics/tx_aborted_errors +What: /sys/class/net/<iface>/statistics/tx_aborted_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -132,7 +132,7 @@ Description: a medium collision). See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/tx_bytes +What: /sys/class/net/<iface>/statistics/tx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -143,7 +143,7 @@ Description: transmitted packets or all packets that have been queued for transmission. -What: /sys/class/<iface>/statistics/tx_carrier_errors +What: /sys/class/net/<iface>/statistics/tx_carrier_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -152,7 +152,7 @@ Description: because of carrier errors (e.g: physical link down). See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/tx_compressed +What: /sys/class/net/<iface>/statistics/tx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -161,7 +161,7 @@ Description: this might only be relevant for devices that support compression (e.g: PPP). -What: /sys/class/<iface>/statistics/tx_dropped +What: /sys/class/net/<iface>/statistics/tx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -170,7 +170,7 @@ Description: See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class/<iface>/statistics/tx_errors +What: /sys/class/net/<iface>/statistics/tx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -179,7 +179,7 @@ Description: a network device. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class/<iface>/statistics/tx_fifo_errors +What: /sys/class/net/<iface>/statistics/tx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -188,7 +188,7 @@ Description: FIFO error. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class/<iface>/statistics/tx_heartbeat_errors +What: /sys/class/net/<iface>/statistics/tx_heartbeat_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -197,7 +197,7 @@ Description: reported as heartbeat errors. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class/<iface>/statistics/tx_packets +What: /sys/class/net/<iface>/statistics/tx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -206,7 +206,7 @@ Description: device. See the driver for whether this reports the number of all attempted or successful transmissions. -What: /sys/class/<iface>/statistics/tx_window_errors +What: /sys/class/net/<iface>/statistics/tx_window_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org diff --git a/Documentation/admin-guide/abi-obsolete.rst b/Documentation/admin-guide/abi-obsolete.rst index d095867899c5..594e697aa1b2 100644 --- a/Documentation/admin-guide/abi-obsolete.rst +++ b/Documentation/admin-guide/abi-obsolete.rst @@ -7,5 +7,5 @@ marked to be removed at some later point in time. The description of the interface will document the reason why it is obsolete and when it can be expected to be removed. -.. kernel-abi:: $srctree/Documentation/ABI/obsolete +.. kernel-abi:: ABI/obsolete :rst: diff --git a/Documentation/admin-guide/abi-removed.rst b/Documentation/admin-guide/abi-removed.rst index f7e9e43023c1..f9e000c81828 100644 --- a/Documentation/admin-guide/abi-removed.rst +++ b/Documentation/admin-guide/abi-removed.rst @@ -1,5 +1,5 @@ ABI removed symbols =================== -.. kernel-abi:: $srctree/Documentation/ABI/removed +.. kernel-abi:: ABI/removed :rst: diff --git a/Documentation/admin-guide/abi-stable.rst b/Documentation/admin-guide/abi-stable.rst index 70490736e0d3..fc3361d847b1 100644 --- a/Documentation/admin-guide/abi-stable.rst +++ b/Documentation/admin-guide/abi-stable.rst @@ -10,5 +10,5 @@ for at least 2 years. Most interfaces (like syscalls) are expected to never change and always be available. -.. kernel-abi:: $srctree/Documentation/ABI/stable +.. kernel-abi:: ABI/stable :rst: diff --git a/Documentation/admin-guide/abi-testing.rst b/Documentation/admin-guide/abi-testing.rst index b205b16a72d0..19767926b344 100644 --- a/Documentation/admin-guide/abi-testing.rst +++ b/Documentation/admin-guide/abi-testing.rst @@ -16,5 +16,5 @@ Programs that use these interfaces are strongly encouraged to add their name to the description of these interfaces, so that the kernel developers can easily notify them if any changes occur. -.. kernel-abi:: $srctree/Documentation/ABI/testing +.. kernel-abi:: ABI/testing :rst: diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index d9fce65b2f04..27135b9c07ac 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -221,3 +221,10 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 | +----------------+-----------------+-----------------+-----------------------------+ ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2139208 | ARM64_ERRATUM_2139208 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2067961 | ARM64_ERRATUM_2067961 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2253138 | ARM64_ERRATUM_2253138 | ++----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml b/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml index f333ee2288e7..11ae8ec3c739 100644 --- a/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml +++ b/Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml @@ -126,7 +126,7 @@ examples: - | #include <dt-bindings/interrupt-controller/arm-gic.h> - gpio@e000a000 { + gpio@a0020000 { compatible = "xlnx,xps-gpio-1.00.a"; reg = <0xa0020000 0x10000>; #gpio-cells = <2>; diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml index 9cfc0c7d23e0..46730687c662 100644 --- a/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-rdma.yaml @@ -61,6 +61,9 @@ properties: - description: used for 1st data pipe from RDMA - description: used for 2nd data pipe from RDMA + '#dma-cells': + const: 1 + required: - compatible - reg @@ -70,6 +73,7 @@ required: - clocks - iommus - mboxes + - '#dma-cells' additionalProperties: false @@ -80,16 +84,17 @@ examples: #include <dt-bindings/power/mt8183-power.h> #include <dt-bindings/memory/mt8183-larb-port.h> - mdp3_rdma0: mdp3-rdma0@14001000 { - compatible = "mediatek,mt8183-mdp3-rdma"; - reg = <0x14001000 0x1000>; - mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; - mediatek,gce-events = <CMDQ_EVENT_MDP_RDMA0_SOF>, - <CMDQ_EVENT_MDP_RDMA0_EOF>; - power-domains = <&spm MT8183_POWER_DOMAIN_DISP>; - clocks = <&mmsys CLK_MM_MDP_RDMA0>, - <&mmsys CLK_MM_MDP_RSZ1>; - iommus = <&iommu>; - mboxes = <&gce 20 CMDQ_THR_PRIO_LOWEST>, - <&gce 21 CMDQ_THR_PRIO_LOWEST>; + dma-controller@14001000 { + compatible = "mediatek,mt8183-mdp3-rdma"; + reg = <0x14001000 0x1000>; + mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; + mediatek,gce-events = <CMDQ_EVENT_MDP_RDMA0_SOF>, + <CMDQ_EVENT_MDP_RDMA0_EOF>; + power-domains = <&spm MT8183_POWER_DOMAIN_DISP>; + clocks = <&mmsys CLK_MM_MDP_RDMA0>, + <&mmsys CLK_MM_MDP_RSZ1>; + iommus = <&iommu>; + mboxes = <&gce 20 CMDQ_THR_PRIO_LOWEST>, + <&gce 21 CMDQ_THR_PRIO_LOWEST>; + #dma-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml b/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml index 0baa77198fa2..64ea98aa0592 100644 --- a/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,mdp3-wrot.yaml @@ -50,6 +50,9 @@ properties: iommus: maxItems: 1 + '#dma-cells': + const: 1 + required: - compatible - reg @@ -58,6 +61,7 @@ required: - power-domains - clocks - iommus + - '#dma-cells' additionalProperties: false @@ -68,13 +72,14 @@ examples: #include <dt-bindings/power/mt8183-power.h> #include <dt-bindings/memory/mt8183-larb-port.h> - mdp3_wrot0: mdp3-wrot0@14005000 { - compatible = "mediatek,mt8183-mdp3-wrot"; - reg = <0x14005000 0x1000>; - mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x5000 0x1000>; - mediatek,gce-events = <CMDQ_EVENT_MDP_WROT0_SOF>, - <CMDQ_EVENT_MDP_WROT0_EOF>; - power-domains = <&spm MT8183_POWER_DOMAIN_DISP>; - clocks = <&mmsys CLK_MM_MDP_WROT0>; - iommus = <&iommu>; + dma-controller@14005000 { + compatible = "mediatek,mt8183-mdp3-wrot"; + reg = <0x14005000 0x1000>; + mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x5000 0x1000>; + mediatek,gce-events = <CMDQ_EVENT_MDP_WROT0_SOF>, + <CMDQ_EVENT_MDP_WROT0_EOF>; + power-domains = <&spm MT8183_POWER_DOMAIN_DISP>; + clocks = <&mmsys CLK_MM_MDP_WROT0>; + iommus = <&iommu>; + #dma-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/media/rockchip-isp1.yaml b/Documentation/devicetree/bindings/media/rockchip-isp1.yaml index b3661d7d4357..2a0ad332f5ce 100644 --- a/Documentation/devicetree/bindings/media/rockchip-isp1.yaml +++ b/Documentation/devicetree/bindings/media/rockchip-isp1.yaml @@ -90,15 +90,16 @@ properties: description: connection point for input on the parallel interface properties: - bus-type: - enum: [5, 6] - endpoint: $ref: video-interfaces.yaml# unevaluatedProperties: false - required: - - bus-type + properties: + bus-type: + enum: [5, 6] + + required: + - bus-type anyOf: - required: diff --git a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml index ff317fd7c15b..2e1fcff3c280 100644 --- a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml +++ b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml @@ -14,9 +14,11 @@ allOf: properties: compatible: - enum: - - fsl,imx23-ocotp - - fsl,imx28-ocotp + items: + - enum: + - fsl,imx23-ocotp + - fsl,imx28-ocotp + - const: fsl,ocotp "#address-cells": const: 1 @@ -40,7 +42,7 @@ additionalProperties: false examples: - | ocotp: efuse@8002c000 { - compatible = "fsl,imx28-ocotp"; + compatible = "fsl,imx28-ocotp", "fsl,ocotp"; #address-cells = <1>; #size-cells = <1>; reg = <0x8002c000 0x2000>; diff --git a/Documentation/driver-api/pci/p2pdma.rst b/Documentation/driver-api/pci/p2pdma.rst index 44deb52beeb4..d0b241628cf1 100644 --- a/Documentation/driver-api/pci/p2pdma.rst +++ b/Documentation/driver-api/pci/p2pdma.rst @@ -83,19 +83,9 @@ this to include other types of resources like doorbells. Client Drivers -------------- -A client driver typically only has to conditionally change its DMA map -routine to use the mapping function :c:func:`pci_p2pdma_map_sg()` instead -of the usual :c:func:`dma_map_sg()` function. Memory mapped in this -way does not need to be unmapped. - -The client may also, optionally, make use of -:c:func:`is_pci_p2pdma_page()` to determine when to use the P2P mapping -functions and when to use the regular mapping functions. In some -situations, it may be more appropriate to use a flag to indicate a -given request is P2P memory and map appropriately. It is important to -ensure that struct pages that back P2P memory stay out of code that -does not have support for them as other code may treat the pages as -regular memory which may not be appropriate. +A client driver only has to use the mapping API :c:func:`dma_map_sg()` +and :c:func:`dma_unmap_sg()` functions as usual, and the implementation +will do the right thing for the P2P capable memory. Orchestrator Drivers diff --git a/Documentation/filesystems/directory-locking.rst b/Documentation/filesystems/directory-locking.rst index dccd61c7c5c3..193c22687851 100644 --- a/Documentation/filesystems/directory-locking.rst +++ b/Documentation/filesystems/directory-locking.rst @@ -22,13 +22,16 @@ exclusive. 3) object removal. Locking rules: caller locks parent, finds victim, locks victim and calls the method. Locks are exclusive. -4) rename() that is _not_ cross-directory. Locking rules: caller locks the -parent and finds source and target. We lock both (provided they exist). If we -need to lock two inodes of different type (dir vs non-dir), we lock directory -first. If we need to lock two inodes of the same type, lock them in inode -pointer order. Then call the method. All locks are exclusive. -NB: we might get away with locking the source (and target in exchange -case) shared. +4) rename() that is _not_ cross-directory. Locking rules: caller locks +the parent and finds source and target. Then we decide which of the +source and target need to be locked. Source needs to be locked if it's a +non-directory; target - if it's a non-directory or about to be removed. +Take the locks that need to be taken, in inode pointer order if need +to take both (that can happen only when both source and target are +non-directories - the source because it wouldn't be locked otherwise +and the target because mixing directory and non-directory is allowed +only with RENAME_EXCHANGE, and that won't be removing the target). +After the locks had been taken, call the method. All locks are exclusive. 5) link creation. Locking rules: @@ -44,20 +47,17 @@ rules: * lock the filesystem * lock parents in "ancestors first" order. If one is not ancestor of - the other, lock them in inode pointer order. + the other, lock the parent of source first. * find source and target. * if old parent is equal to or is a descendent of target fail with -ENOTEMPTY * if new parent is equal to or is a descendent of source fail with -ELOOP - * Lock both the source and the target provided they exist. If we - need to lock two inodes of different type (dir vs non-dir), we lock - the directory first. If we need to lock two inodes of the same type, - lock them in inode pointer order. + * Lock subdirectories involved (source before target). + * Lock non-directories involved, in inode pointer order. * call the method. -All ->i_rwsem are taken exclusive. Again, we might get away with locking -the source (and target in exchange case) shared. +All ->i_rwsem are taken exclusive. The rules above obviously guarantee that all directories that are going to be read, modified or removed by method will be locked by caller. @@ -67,6 +67,7 @@ If no directory is its own ancestor, the scheme above is deadlock-free. Proof: +[XXX: will be updated once we are done massaging the lock_rename()] First of all, at any moment we have a linear ordering of the objects - A < B iff (A is an ancestor of B) or (B is not an ancestor of A and ptr(A) < ptr(B)). diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 8f737e76935c..555215c416d9 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -99,7 +99,7 @@ symlink: exclusive mkdir: exclusive unlink: exclusive (both) rmdir: exclusive (both)(see below) -rename: exclusive (all) (see below) +rename: exclusive (both parents, some children) (see below) readlink: no get_link: no setattr: exclusive @@ -119,6 +119,9 @@ fileattr_set: exclusive Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem exclusive on victim. cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. + ->unlink() and ->rename() have ->i_rwsem exclusive on all non-directories + involved. + ->rename() has ->i_rwsem exclusive on any subdirectory that changes parent. See Documentation/filesystems/directory-locking.rst for more detailed discussion of the locking scheme for directory operations. diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index df0dc37e6f58..c6aaf340f179 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -943,3 +943,21 @@ file pointer instead of struct dentry pointer. d_tmpfile() is similarly changed to simplify callers. The passed file is in a non-open state and on success must be opened before returning (e.g. by calling finish_open_simple()). + +--- + +**mandatory** + +If ->rename() update of .. on cross-directory move needs an exclusion with +directory modifications, do *not* lock the subdirectory in question in your +->rename() - it's done by the caller now [that item should've been added in +28eceeda130f "fs: Lock moved directories"]. + +--- + +**mandatory** + +On same-directory ->rename() the (tautological) update of .. is not protected +by any locks; just don't do it if the old parent is the same as the new one. +We really can't lock two subdirectories in same-directory rename - not without +deadlocks. diff --git a/Documentation/sound/soc/dapm.rst b/Documentation/sound/soc/dapm.rst index 8e44107933ab..c3154ce6e1b2 100644 --- a/Documentation/sound/soc/dapm.rst +++ b/Documentation/sound/soc/dapm.rst @@ -234,7 +234,7 @@ corresponding soft power control. In this case it is necessary to create a virtual widget - a widget with no control bits e.g. :: - SND_SOC_DAPM_MIXER("AC97 Mixer", SND_SOC_DAPM_NOPM, 0, 0, NULL, 0), + SND_SOC_DAPM_MIXER("AC97 Mixer", SND_SOC_NOPM, 0, 0, NULL, 0), This can be used to merge to signal paths together in software. diff --git a/Documentation/sphinx/kernel_abi.py b/Documentation/sphinx/kernel_abi.py index b5feb5b1d905..6d8a637ad566 100644 --- a/Documentation/sphinx/kernel_abi.py +++ b/Documentation/sphinx/kernel_abi.py @@ -39,8 +39,6 @@ import sys import re import kernellog -from os import path - from docutils import nodes, statemachine from docutils.statemachine import ViewList from docutils.parsers.rst import directives, Directive @@ -73,60 +71,26 @@ class KernelCmd(Directive): } def run(self): - doc = self.state.document if not doc.settings.file_insertion_enabled: raise self.warning("docutils: file insertion disabled") - env = doc.settings.env - cwd = path.dirname(doc.current_source) - cmd = "get_abi.pl rest --enable-lineno --dir " - cmd += self.arguments[0] - - if 'rst' in self.options: - cmd += " --rst-source" + srctree = os.path.abspath(os.environ["srctree"]) - srctree = path.abspath(os.environ["srctree"]) + args = [ + os.path.join(srctree, 'scripts/get_abi.pl'), + 'rest', + '--enable-lineno', + '--dir', os.path.join(srctree, 'Documentation', self.arguments[0]), + ] - fname = cmd - - # extend PATH with $(srctree)/scripts - path_env = os.pathsep.join([ - srctree + os.sep + "scripts", - os.environ["PATH"] - ]) - shell_env = os.environ.copy() - shell_env["PATH"] = path_env - shell_env["srctree"] = srctree + if 'rst' in self.options: + args.append('--rst-source') - lines = self.runCmd(cmd, shell=True, cwd=cwd, env=shell_env) + lines = subprocess.check_output(args, cwd=os.path.dirname(doc.current_source)).decode('utf-8') nodeList = self.nestedParse(lines, self.arguments[0]) return nodeList - def runCmd(self, cmd, **kwargs): - u"""Run command ``cmd`` and return its stdout as unicode.""" - - try: - proc = subprocess.Popen( - cmd - , stdout = subprocess.PIPE - , stderr = subprocess.PIPE - , **kwargs - ) - out, err = proc.communicate() - - out, err = codecs.decode(out, 'utf-8'), codecs.decode(err, 'utf-8') - - if proc.returncode != 0: - raise self.severe( - u"command '%s' failed with return code %d" - % (cmd, proc.returncode) - ) - except OSError as exc: - raise self.severe(u"problems with '%s' directive: %s." - % (self.name, ErrorString(exc))) - return out - def nestedParse(self, lines, fname): env = self.state.document.settings.env content = ViewList() diff --git a/MAINTAINERS b/MAINTAINERS index e93d8a90c0e1..73fb699e83d5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10825,6 +10825,8 @@ L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core F: kernel/irq/ +F: include/linux/group_cpus.h +F: lib/group_cpus.c IRQCHIP DRIVERS M: Thomas Gleixner <tglx@linutronix.de> @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 69 +SUBLEVEL = 80 EXTRAVERSION = NAME = Curry Ramen @@ -459,8 +459,7 @@ HOSTRUSTC = rustc HOSTPKG_CONFIG = pkg-config KBUILD_USERHOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes \ - -O2 -fomit-frame-pointer -std=gnu11 \ - -Wdeclaration-after-statement + -O2 -fomit-frame-pointer -std=gnu11 KBUILD_USERCFLAGS := $(KBUILD_USERHOSTCFLAGS) $(USERCFLAGS) KBUILD_USERLDFLAGS := $(USERLDFLAGS) @@ -1018,9 +1017,6 @@ endif # arch Makefile may override CC so keep this after arch Makefile is included NOSTDINC_FLAGS += -nostdinc -# warn about C99 declaration after statement -KBUILD_CFLAGS += -Wdeclaration-after-statement - # Variable Length Arrays (VLAs) should not be used anywhere in the kernel KBUILD_CFLAGS += -Wvla diff --git a/arch/Kconfig b/arch/Kconfig index b60d271bf76a..f99fd9a4ca77 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -34,6 +34,9 @@ config ARCH_HAS_SUBPAGE_FAULTS config HOTPLUG_SMT bool +config SMT_NUM_THREADS_DYNAMIC + bool + config GENERIC_ENTRY bool @@ -639,6 +642,7 @@ config SHADOW_CALL_STACK bool "Shadow Call Stack" depends on ARCH_SUPPORTS_SHADOW_CALL_STACK depends on DYNAMIC_FTRACE_WITH_ARGS || DYNAMIC_FTRACE_WITH_REGS || !FUNCTION_GRAPH_TRACER + depends on MMU help This option enables the compiler's Shadow Call Stack, which uses a shadow stack to protect function return addresses from diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c index fb3025396ac9..cfdf90bc8b3f 100644 --- a/arch/alpha/kernel/rtc.c +++ b/arch/alpha/kernel/rtc.c @@ -80,7 +80,7 @@ init_rtc_epoch(void) static int alpha_rtc_read_time(struct device *dev, struct rtc_time *tm) { - int ret = mc146818_get_time(tm); + int ret = mc146818_get_time(tm, 10); if (ret < 0) { dev_err_ratelimited(dev, "unable to read current time\n"); diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h index 9d9618079739..a339223d9e05 100644 --- a/arch/arc/include/asm/jump_label.h +++ b/arch/arc/include/asm/jump_label.h @@ -31,7 +31,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" "1: \n" "nop \n" ".pushsection __jump_table, \"aw\" \n" @@ -47,7 +47,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" "1: \n" "b %l[l_yes] \n" ".pushsection __jump_table, \"aw\" \n" diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 3c1590c27fae..723abcb10c80 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -61,7 +61,7 @@ struct rt_sigframe { unsigned int sigret_magic; }; -static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) +static int save_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs) { int err = 0; #ifndef CONFIG_ISA_ARCOMPACT @@ -74,12 +74,12 @@ static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) #else v2abi.r58 = v2abi.r59 = 0; #endif - err = __copy_to_user(&mctx->v2abi, &v2abi, sizeof(v2abi)); + err = __copy_to_user(&mctx->v2abi, (void const *)&v2abi, sizeof(v2abi)); #endif return err; } -static int restore_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) +static int restore_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs) { int err = 0; #ifndef CONFIG_ISA_ARCOMPACT diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index ad5b1050d4b1..42f282e55d65 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -349,6 +349,7 @@ <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; + ti,sysc-delay-us = <2>; clocks = <&l3s_clkctrl AM3_L3S_USB_OTG_HS_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 38737ca12541..287620d866b8 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -144,7 +144,7 @@ l3-noc@44000000 { compatible = "ti,dra7-l3-noc"; - reg = <0x44000000 0x1000>, + reg = <0x44000000 0x1000000>, <0x45000000 0x1000>; interrupts-extended = <&crossbar_mpu GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>, <&wakeupgen GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/exynos4210-i9100.dts b/arch/arm/boot/dts/exynos4210-i9100.dts index 53e023fc1cac..b4c7b642e456 100644 --- a/arch/arm/boot/dts/exynos4210-i9100.dts +++ b/arch/arm/boot/dts/exynos4210-i9100.dts @@ -521,6 +521,14 @@ regulator-name = "VT_CAM_1.8V"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + + /* + * Force-enable this regulator; otherwise the + * kernel hangs very early in the boot process + * for about 12 seconds, without apparent + * reason. + */ + regulator-always-on; }; vcclcd_reg: LDO13 { diff --git a/arch/arm/boot/dts/imx1-ads.dts b/arch/arm/boot/dts/imx1-ads.dts index 5833fb6f15d8..2c817c4a4c68 100644 --- a/arch/arm/boot/dts/imx1-ads.dts +++ b/arch/arm/boot/dts/imx1-ads.dts @@ -65,7 +65,7 @@ pinctrl-0 = <&pinctrl_weim>; status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { compatible = "cfi-flash"; reg = <0 0x00000000 0x02000000>; bank-width = <4>; diff --git a/arch/arm/boot/dts/imx1-apf9328.dts b/arch/arm/boot/dts/imx1-apf9328.dts index 77b21aa7a146..27e72b07b517 100644 --- a/arch/arm/boot/dts/imx1-apf9328.dts +++ b/arch/arm/boot/dts/imx1-apf9328.dts @@ -45,7 +45,7 @@ pinctrl-0 = <&pinctrl_weim>; status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { compatible = "cfi-flash"; reg = <0 0x00000000 0x02000000>; bank-width = <2>; diff --git a/arch/arm/boot/dts/imx1.dtsi b/arch/arm/boot/dts/imx1.dtsi index e312f1e74e2f..4aeb74479f44 100644 --- a/arch/arm/boot/dts/imx1.dtsi +++ b/arch/arm/boot/dts/imx1.dtsi @@ -268,9 +268,12 @@ status = "disabled"; }; - esram: esram@300000 { + esram: sram@300000 { compatible = "mmio-sram"; reg = <0x00300000 0x20000>; + ranges = <0 0x00300000 0x20000>; + #address-cells = <1>; + #size-cells = <1>; }; }; }; diff --git a/arch/arm/boot/dts/imx23-sansa.dts b/arch/arm/boot/dts/imx23-sansa.dts index 46057d9bf555..c2efcc20ae80 100644 --- a/arch/arm/boot/dts/imx23-sansa.dts +++ b/arch/arm/boot/dts/imx23-sansa.dts @@ -175,10 +175,8 @@ #address-cells = <1>; #size-cells = <0>; compatible = "i2c-gpio"; - gpios = < - &gpio1 24 0 /* SDA */ - &gpio1 22 0 /* SCL */ - >; + sda-gpios = <&gpio1 24 0>; + scl-gpios = <&gpio1 22 0>; i2c-gpio,delay-us = <2>; /* ~100 kHz */ }; @@ -186,10 +184,8 @@ #address-cells = <1>; #size-cells = <0>; compatible = "i2c-gpio"; - gpios = < - &gpio0 31 0 /* SDA */ - &gpio0 30 0 /* SCL */ - >; + sda-gpios = <&gpio0 31 0>; + scl-gpios = <&gpio0 30 0>; i2c-gpio,delay-us = <2>; /* ~100 kHz */ touch: touch@20 { diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi index 7f4c602454a5..ec476b159649 100644 --- a/arch/arm/boot/dts/imx23.dtsi +++ b/arch/arm/boot/dts/imx23.dtsi @@ -414,7 +414,7 @@ status = "disabled"; }; - dma_apbx: dma-apbx@80024000 { + dma_apbx: dma-controller@80024000 { compatible = "fsl,imx23-dma-apbx"; reg = <0x80024000 0x2000>; interrupts = <7 5 9 26 diff --git a/arch/arm/boot/dts/imx25-eukrea-cpuimx25.dtsi b/arch/arm/boot/dts/imx25-eukrea-cpuimx25.dtsi index 0703f62d10d1..93a6e4e680b4 100644 --- a/arch/arm/boot/dts/imx25-eukrea-cpuimx25.dtsi +++ b/arch/arm/boot/dts/imx25-eukrea-cpuimx25.dtsi @@ -27,7 +27,7 @@ pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; - pcf8563@51 { + rtc@51 { compatible = "nxp,pcf8563"; reg = <0x51>; }; diff --git a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts index 7d4301b22b90..1ed3fb7b9ce6 100644 --- a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts +++ b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts @@ -16,7 +16,7 @@ bus-width = <18>; display-timings { native-mode = <&qvga_timings>; - qvga_timings: 320x240 { + qvga_timings: timing0 { clock-frequency = <6500000>; hactive = <320>; vactive = <240>; diff --git a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts index 80a7f96de4c6..64b2ffac463b 100644 --- a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts +++ b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts @@ -16,7 +16,7 @@ bus-width = <18>; display-timings { native-mode = <&dvi_svga_timings>; - dvi_svga_timings: 800x600 { + dvi_svga_timings: timing0 { clock-frequency = <40000000>; hactive = <800>; vactive = <600>; diff --git a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts index 24027a1fb46d..fb074bfdaa8d 100644 --- a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts +++ b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts @@ -16,7 +16,7 @@ bus-width = <18>; display-timings { native-mode = <&dvi_vga_timings>; - dvi_vga_timings: 640x480 { + dvi_vga_timings: timing0 { clock-frequency = <31250000>; hactive = <640>; vactive = <480>; diff --git a/arch/arm/boot/dts/imx25-pdk.dts b/arch/arm/boot/dts/imx25-pdk.dts index fb66884d8a2f..59b40d13a640 100644 --- a/arch/arm/boot/dts/imx25-pdk.dts +++ b/arch/arm/boot/dts/imx25-pdk.dts @@ -78,7 +78,7 @@ bus-width = <18>; display-timings { native-mode = <&wvga_timings>; - wvga_timings: 640x480 { + wvga_timings: timing0 { hactive = <640>; vactive = <480>; hback-porch = <45>; diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index 5f90d72b840b..5ac4549286bd 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -543,7 +543,7 @@ }; iim: efuse@53ff0000 { - compatible = "fsl,imx25-iim", "fsl,imx27-iim"; + compatible = "fsl,imx25-iim"; reg = <0x53ff0000 0x4000>; interrupts = <19>; clocks = <&clks 99>; diff --git a/arch/arm/boot/dts/imx27-apf27dev.dts b/arch/arm/boot/dts/imx27-apf27dev.dts index 6f1e8ce9e76e..3d9bb7fc3be2 100644 --- a/arch/arm/boot/dts/imx27-apf27dev.dts +++ b/arch/arm/boot/dts/imx27-apf27dev.dts @@ -16,7 +16,7 @@ fsl,pcr = <0xfae80083>; /* non-standard but required */ display-timings { native-mode = <&timing0>; - timing0: 800x480 { + timing0: timing0 { clock-frequency = <33000033>; hactive = <800>; vactive = <480>; @@ -47,7 +47,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - user { + led-user { label = "Heartbeat"; gpios = <&gpio6 14 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi b/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi index 74110bbcd9d4..c7e923584878 100644 --- a/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi +++ b/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi @@ -33,7 +33,7 @@ pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; - pcf8563@51 { + rtc@51 { compatible = "nxp,pcf8563"; reg = <0x51>; }; @@ -90,7 +90,7 @@ &weim { status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { #address-cells = <1>; #size-cells = <1>; compatible = "cfi-flash"; diff --git a/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts b/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts index 9c3ec82ec7e5..50fa0bd4c8a1 100644 --- a/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts +++ b/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts @@ -16,7 +16,7 @@ display-timings { native-mode = <&timing0>; - timing0: 320x240 { + timing0: timing0 { clock-frequency = <6500000>; hactive = <320>; vactive = <240>; diff --git a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts index 188639738dc3..7f36af150a25 100644 --- a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts +++ b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts @@ -19,7 +19,7 @@ fsl,pcr = <0xf0c88080>; /* non-standard but required */ display-timings { native-mode = <&timing0>; - timing0: 640x480 { + timing0: timing0 { hactive = <640>; vactive = <480>; hback-porch = <112>; diff --git a/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts index 344e77790152..d133b9f08b3a 100644 --- a/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts +++ b/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts @@ -19,7 +19,7 @@ display-timings { native-mode = <&timing0>; - timing0: 240x320 { + timing0: timing0 { clock-frequency = <5500000>; hactive = <240>; vactive = <320>; diff --git a/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi b/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi index 3d10273177e9..a5fdc2fd4ce5 100644 --- a/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi +++ b/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi @@ -322,7 +322,7 @@ &weim { status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { compatible = "cfi-flash"; reg = <0 0x00000000 0x02000000>; bank-width = <2>; diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index e140307be2e7..eb6daf22486e 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -588,6 +588,9 @@ iram: sram@ffff4c00 { compatible = "mmio-sram"; reg = <0xffff4c00 0xb400>; + ranges = <0 0xffff4c00 0xb400>; + #address-cells = <1>; + #size-cells = <1>; }; }; }; diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index 130b4145af82..b15df16ecb01 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -994,7 +994,7 @@ status = "disabled"; }; - dma_apbx: dma-apbx@80024000 { + dma_apbx: dma-controller@80024000 { compatible = "fsl,imx28-dma-apbx"; reg = <0x80024000 0x2000>; interrupts = <78 79 66 0 diff --git a/arch/arm/boot/dts/imx6q-apalis-ixora-v1.2.dts b/arch/arm/boot/dts/imx6q-apalis-ixora-v1.2.dts index f9f7d99bd4db..76f3e07bc882 100644 --- a/arch/arm/boot/dts/imx6q-apalis-ixora-v1.2.dts +++ b/arch/arm/boot/dts/imx6q-apalis-ixora-v1.2.dts @@ -76,6 +76,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enable_can1_power>; regulator-name = "can1_supply"; + startup-delay-us = <1000>; }; reg_can2_supply: regulator-can2-supply { @@ -85,6 +86,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enable_can2_power>; regulator-name = "can2_supply"; + startup-delay-us = <1000>; }; }; diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi index 7ceb7c09f7ad..7ef685fdda55 100644 --- a/arch/arm/boot/dts/imx7d.dtsi +++ b/arch/arm/boot/dts/imx7d.dtsi @@ -208,9 +208,6 @@ }; &ca_funnel_in_ports { - #address-cells = <1>; - #size-cells = <0>; - port@1 { reg = <1>; ca_funnel_in_port1: endpoint { diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 45947707134b..4b23630fc738 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -190,7 +190,11 @@ clock-names = "apb_pclk"; ca_funnel_in_ports: in-ports { - port { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; ca_funnel_in_port0: endpoint { remote-endpoint = <&etm0_out_port>; }; @@ -814,7 +818,7 @@ }; lcdif: lcdif@30730000 { - compatible = "fsl,imx7d-lcdif", "fsl,imx28-lcdif"; + compatible = "fsl,imx7d-lcdif", "fsl,imx6sx-lcdif"; reg = <0x30730000 0x10000>; interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>, @@ -1279,7 +1283,7 @@ gpmi: nand-controller@33002000{ compatible = "fsl,imx7d-gpmi-nand"; #address-cells = <1>; - #size-cells = <1>; + #size-cells = <0>; reg = <0x33002000 0x2000>, <0x33004000 0x4000>; reg-names = "gpmi-nand", "bch"; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi index 4b57e9f5bc64..2b3927a829b7 100644 --- a/arch/arm/boot/dts/qcom-apq8064.dtsi +++ b/arch/arm/boot/dts/qcom-apq8064.dtsi @@ -750,7 +750,7 @@ xoadc: xoadc@197 { compatible = "qcom,pm8921-adc"; - reg = <197>; + reg = <0x197>; interrupts-extended = <&pmicintc 78 IRQ_TYPE_EDGE_RISING>; #address-cells = <2>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/qcom-sdx55.dtsi b/arch/arm/boot/dts/qcom-sdx55.dtsi index a4bf1d5ee206..b85820448b9d 100644 --- a/arch/arm/boot/dts/qcom-sdx55.dtsi +++ b/arch/arm/boot/dts/qcom-sdx55.dtsi @@ -495,10 +495,10 @@ <&gcc GCC_USB30_MASTER_CLK>; assigned-clock-rates = <19200000>, <200000000>; - interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 198 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 158 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 51 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 11 IRQ_TYPE_EDGE_BOTH>, + <&pdc 10 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -522,7 +522,7 @@ compatible = "qcom,sdx55-pdc", "qcom,pdc"; reg = <0x0b210000 0x30000>; qcom,pdc-ranges = <0 179 52>; - #interrupt-cells = <3>; + #interrupt-cells = <2>; interrupt-parent = <&intc>; interrupt-controller; }; diff --git a/arch/arm/boot/dts/qcom-sdx65.dtsi b/arch/arm/boot/dts/qcom-sdx65.dtsi index ecb9171e4da5..ebb78b489e63 100644 --- a/arch/arm/boot/dts/qcom-sdx65.dtsi +++ b/arch/arm/boot/dts/qcom-sdx65.dtsi @@ -401,7 +401,7 @@ reg = <0x0c264000 0x1000>; }; - spmi_bus: qcom,spmi@c440000 { + spmi_bus: spmi@c440000 { compatible = "qcom,spmi-pmic-arb"; reg = <0xc440000 0xd00>, <0xc600000 0x2000000>, diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi index 78686fc72ce6..c420c7c642cb 100644 --- a/arch/arm/boot/dts/rk3036.dtsi +++ b/arch/arm/boot/dts/rk3036.dtsi @@ -402,12 +402,20 @@ pinctrl-0 = <&hdmi_ctl>; status = "disabled"; - hdmi_in: port { + ports { #address-cells = <1>; #size-cells = <0>; - hdmi_in_vop: endpoint@0 { + + hdmi_in: port@0 { reg = <0>; - remote-endpoint = <&vop_out_hdmi>; + + hdmi_in_vop: endpoint { + remote-endpoint = <&vop_out_hdmi>; + }; + }; + + hdmi_out: port@1 { + reg = <1>; }; }; }; diff --git a/arch/arm/boot/dts/stm32mp157a-dk1-scmi.dts b/arch/arm/boot/dts/stm32mp157a-dk1-scmi.dts index e539cc80bef8..942a6ca38d97 100644 --- a/arch/arm/boot/dts/stm32mp157a-dk1-scmi.dts +++ b/arch/arm/boot/dts/stm32mp157a-dk1-scmi.dts @@ -11,7 +11,7 @@ / { model = "STMicroelectronics STM32MP157A-DK1 SCMI Discovery Board"; - compatible = "st,stm32mp157a-dk1-scmi", "st,stm32mp157a-dk1", "st,stm32mp157"; + compatible = "st,stm32mp157a-dk1-scmi", "st,stm32mp157"; reserved-memory { optee@de000000 { diff --git a/arch/arm/boot/dts/stm32mp157c-dk2-scmi.dts b/arch/arm/boot/dts/stm32mp157c-dk2-scmi.dts index 97e4f94b0a24..99c4ff1f5c21 100644 --- a/arch/arm/boot/dts/stm32mp157c-dk2-scmi.dts +++ b/arch/arm/boot/dts/stm32mp157c-dk2-scmi.dts @@ -11,7 +11,7 @@ / { model = "STMicroelectronics STM32MP157C-DK2 SCMI Discovery Board"; - compatible = "st,stm32mp157c-dk2-scmi", "st,stm32mp157c-dk2", "st,stm32mp157"; + compatible = "st,stm32mp157c-dk2-scmi", "st,stm32mp157"; reserved-memory { optee@de000000 { diff --git a/arch/arm/boot/dts/stm32mp157c-ed1-scmi.dts b/arch/arm/boot/dts/stm32mp157c-ed1-scmi.dts index 9cf0a44d2f47..21010458b36f 100644 --- a/arch/arm/boot/dts/stm32mp157c-ed1-scmi.dts +++ b/arch/arm/boot/dts/stm32mp157c-ed1-scmi.dts @@ -11,7 +11,7 @@ / { model = "STMicroelectronics STM32MP157C-ED1 SCMI eval daughter"; - compatible = "st,stm32mp157c-ed1-scmi", "st,stm32mp157c-ed1", "st,stm32mp157"; + compatible = "st,stm32mp157c-ed1-scmi", "st,stm32mp157"; reserved-memory { optee@fe000000 { diff --git a/arch/arm/boot/dts/stm32mp157c-ev1-scmi.dts b/arch/arm/boot/dts/stm32mp157c-ev1-scmi.dts index 3b9dd6f4ccc9..d37637149919 100644 --- a/arch/arm/boot/dts/stm32mp157c-ev1-scmi.dts +++ b/arch/arm/boot/dts/stm32mp157c-ev1-scmi.dts @@ -11,8 +11,7 @@ / { model = "STMicroelectronics STM32MP157C-EV1 SCMI eval daughter on eval mother"; - compatible = "st,stm32mp157c-ev1-scmi", "st,stm32mp157c-ev1", "st,stm32mp157c-ed1", - "st,stm32mp157"; + compatible = "st,stm32mp157c-ev1-scmi", "st,stm32mp157c-ed1", "st,stm32mp157"; reserved-memory { optee@fe000000 { diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 7de96783e5ed..c979fb22bf0e 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -1,3 +1,4 @@ +CONFIG_XFRM_USER=m CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_NO_HZ_IDLE=y @@ -149,6 +150,7 @@ CONFIG_CRYPTO_AES_ARM_CE=m CONFIG_CRYPTO_GHASH_ARM_CE=m CONFIG_CRYPTO_CRC32_ARM_CE=m CONFIG_CRYPTO_CHACHA20_NEON=m +CONFIG_CRYPTO_XCBC=m CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_PARTITION_ADVANCED=y @@ -157,6 +159,7 @@ CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_INET=y +CONFIG_INET_ESP=m CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y diff --git a/arch/arm/include/asm/irq_work.h b/arch/arm/include/asm/irq_work.h index 3149e4dc1b54..8895999834cc 100644 --- a/arch/arm/include/asm/irq_work.h +++ b/arch/arm/include/asm/irq_work.h @@ -9,6 +9,4 @@ static inline bool arch_irq_work_has_interrupt(void) return is_smp(); } -extern void arch_irq_work_raise(void); - #endif /* _ASM_ARM_IRQ_WORK_H */ diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h index e12d7d096fc0..e4eb54f6cd9f 100644 --- a/arch/arm/include/asm/jump_label.h +++ b/arch/arm/include/asm/jump_label.h @@ -11,7 +11,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" WASM(nop) "\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" @@ -25,7 +25,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" WASM(b) " %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig index c8cbd9a30791..672ffb0b5f3a 100644 --- a/arch/arm/mach-davinci/Kconfig +++ b/arch/arm/mach-davinci/Kconfig @@ -4,12 +4,14 @@ menuconfig ARCH_DAVINCI bool "TI DaVinci" depends on ARCH_MULTI_V5 depends on CPU_LITTLE_ENDIAN + select CPU_ARM926T select DAVINCI_TIMER select ZONE_DMA select PM_GENERIC_DOMAINS if PM select PM_GENERIC_DOMAINS_OF if PM && OF select REGMAP_MMIO select RESET_CONTROLLER + select PINCTRL select PINCTRL_SINGLE if ARCH_DAVINCI diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index 95e731676cea..961daac65326 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -339,6 +339,7 @@ static struct gpiod_lookup_table ep93xx_i2c_gpiod_table = { GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), GPIO_LOOKUP_IDX("G", 0, NULL, 1, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), + { } }, }; diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 59755b5a1ad7..75091aa7269a 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -793,11 +793,16 @@ void __init omap_soc_device_init(void) soc_dev_attr->machine = soc_name; soc_dev_attr->family = omap_get_family(); + if (!soc_dev_attr->family) { + kfree(soc_dev_attr); + return; + } soc_dev_attr->revision = soc_rev; soc_dev_attr->custom_attr_group = omap_soc_groups[0]; soc_dev = soc_device_register(soc_dev_attr); if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr->family); kfree(soc_dev_attr); return; } diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c index 26cbce135338..f779e386b6e7 100644 --- a/arch/arm/mach-sunxi/mc_smp.c +++ b/arch/arm/mach-sunxi/mc_smp.c @@ -804,16 +804,16 @@ static int __init sunxi_mc_smp_init(void) for (i = 0; i < ARRAY_SIZE(sunxi_mc_smp_data); i++) { ret = of_property_match_string(node, "enable-method", sunxi_mc_smp_data[i].enable_method); - if (!ret) + if (ret >= 0) break; } - is_a83t = sunxi_mc_smp_data[i].is_a83t; - of_node_put(node); - if (ret) + if (ret < 0) return -ENODEV; + is_a83t = sunxi_mc_smp_data[i].is_a83t; + if (!sunxi_mc_smp_cpu_table_init()) return -EINVAL; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index ea70eb960565..c15f71501c6c 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -983,8 +983,12 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. +config ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD + bool + config ARM64_ERRATUM_2966298 bool "Cortex-A520: 2966298: workaround for speculatively executed unprivileged load" + select ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD default y help This option adds the workaround for ARM Cortex-A520 erratum 2966298. diff --git a/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts b/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts index 8ffbcb2b1ac5..bbd3c05cbd90 100644 --- a/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts +++ b/arch/arm64/boot/dts/amlogic/meson-s4-s805x2-aq222.dts @@ -15,7 +15,7 @@ #size-cells = <2>; aliases { - serial0 = &uart_B; + serial0 = &uart_b; }; memory@0 { @@ -25,6 +25,6 @@ }; -&uart_B { +&uart_b { status = "okay"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi index ad50cba42d19..372a03762d69 100644 --- a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi @@ -118,14 +118,14 @@ <10 11 12 13 14 15 16 17 18 19 20 21>; }; - uart_B: serial@7a000 { + uart_b: serial@7a000 { compatible = "amlogic,meson-s4-uart", "amlogic,meson-ao-uart"; reg = <0x0 0x7a000 0x0 0x18>; interrupts = <GIC_SPI 169 IRQ_TYPE_EDGE_RISING>; - status = "disabled"; clocks = <&xtal>, <&xtal>, <&xtal>; clock-names = "xtal", "pclk", "baud"; + status = "disabled"; }; reset: reset-controller@2000 { diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index d583db18f74c..7a410d73600b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -1303,7 +1303,7 @@ assigned-clocks = <&clk IMX8MM_CLK_GPU3D_CORE>, <&clk IMX8MM_GPU_PLL_OUT>; assigned-clock-parents = <&clk IMX8MM_GPU_PLL_OUT>; - assigned-clock-rates = <0>, <1000000000>; + assigned-clock-rates = <0>, <800000000>; power-domains = <&pgc_gpu>; }; @@ -1318,7 +1318,7 @@ assigned-clocks = <&clk IMX8MM_CLK_GPU2D_CORE>, <&clk IMX8MM_GPU_PLL_OUT>; assigned-clock-parents = <&clk IMX8MM_GPU_PLL_OUT>; - assigned-clock-rates = <0>, <1000000000>; + assigned-clock-rates = <0>, <800000000>; power-domains = <&pgc_gpu>; }; diff --git a/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi b/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi index 970047f2dabd..c06e011a6c3f 100644 --- a/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hikey970-pmic.dtsi @@ -25,9 +25,6 @@ gpios = <&gpio28 0 0>; regulators { - #address-cells = <1>; - #size-cells = <0>; - ldo3: ldo3 { /* HDMI */ regulator-name = "ldo3"; regulator-min-microvolt = <1500000>; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts index 200f97e1c4c9..37350e5fa253 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts @@ -130,7 +130,7 @@ compatible = "microchip,mcp7940x"; reg = <0x6f>; interrupt-parent = <&gpiosb>; - interrupts = <5 0>; /* GPIO2_5 */ + interrupts = <5 IRQ_TYPE_EDGE_FALLING>; /* GPIO2_5 */ }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi index 10779a9947fe..d5d9b954c449 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi @@ -1586,7 +1586,7 @@ mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0 0x1000>; }; - mdp3-rdma0@14001000 { + dma-controller0@14001000 { compatible = "mediatek,mt8183-mdp3-rdma"; reg = <0 0x14001000 0 0x1000>; mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; @@ -1598,6 +1598,7 @@ iommus = <&iommu M4U_PORT_MDP_RDMA0>; mboxes = <&gce 20 CMDQ_THR_PRIO_LOWEST 0>, <&gce 21 CMDQ_THR_PRIO_LOWEST 0>; + #dma-cells = <1>; }; mdp3-rsz0@14003000 { @@ -1618,7 +1619,7 @@ clocks = <&mmsys CLK_MM_MDP_RSZ1>; }; - mdp3-wrot0@14005000 { + dma-controller@14005000 { compatible = "mediatek,mt8183-mdp3-wrot"; reg = <0 0x14005000 0 0x1000>; mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x5000 0x1000>; @@ -1627,6 +1628,7 @@ power-domains = <&spm MT8183_POWER_DOMAIN_DISP>; clocks = <&mmsys CLK_MM_MDP_WROT0>; iommus = <&iommu M4U_PORT_MDP_WROT0>; + #dma-cells = <1>; }; mdp3-wdma@14006000 { diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc.dts b/arch/arm64/boot/dts/qcom/apq8016-sbc.dts index 9d116e1fbe10..1ac4f8c24e23 100644 --- a/arch/arm64/boot/dts/qcom/apq8016-sbc.dts +++ b/arch/arm64/boot/dts/qcom/apq8016-sbc.dts @@ -169,10 +169,6 @@ }; }; -&blsp_dma { - status = "okay"; -}; - &blsp_i2c2 { /* On Low speed expansion */ status = "okay"; diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi index 43ff8f1f1475..1533c61cb106 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi @@ -146,7 +146,7 @@ ranges; rpm_msg_ram: memory@60000 { - reg = <0x0 0x60000 0x0 0x6000>; + reg = <0x0 0x00060000 0x0 0x6000>; no-map; }; @@ -181,7 +181,7 @@ prng: qrng@e1000 { compatible = "qcom,prng-ee"; - reg = <0x0 0xe3000 0x0 0x1000>; + reg = <0x0 0x000e3000 0x0 0x1000>; clocks = <&gcc GCC_PRNG_AHB_CLK>; clock-names = "core"; }; @@ -201,8 +201,8 @@ compatible = "qcom,crypto-v5.1"; reg = <0x0 0x0073a000 0x0 0x6000>; clocks = <&gcc GCC_CRYPTO_AHB_CLK>, - <&gcc GCC_CRYPTO_AXI_CLK>, - <&gcc GCC_CRYPTO_CLK>; + <&gcc GCC_CRYPTO_AXI_CLK>, + <&gcc GCC_CRYPTO_CLK>; clock-names = "iface", "bus", "core"; dmas = <&cryptobam 2>, <&cryptobam 3>; dma-names = "rx", "tx"; @@ -272,7 +272,7 @@ reg = <0x0 0x078b1000 0x0 0x200>; interrupts = <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_UART3_APPS_CLK>, - <&gcc GCC_BLSP1_AHB_CLK>; + <&gcc GCC_BLSP1_AHB_CLK>; clock-names = "core", "iface"; status = "disabled"; }; @@ -285,7 +285,7 @@ interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>; spi-max-frequency = <50000000>; clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>, - <&gcc GCC_BLSP1_AHB_CLK>; + <&gcc GCC_BLSP1_AHB_CLK>; clock-names = "core", "iface"; dmas = <&blsp_dma 12>, <&blsp_dma 13>; dma-names = "tx", "rx"; @@ -300,7 +300,7 @@ interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; spi-max-frequency = <50000000>; clocks = <&gcc GCC_BLSP1_QUP2_SPI_APPS_CLK>, - <&gcc GCC_BLSP1_AHB_CLK>; + <&gcc GCC_BLSP1_AHB_CLK>; clock-names = "core", "iface"; dmas = <&blsp_dma 14>, <&blsp_dma 15>; dma-names = "tx", "rx"; @@ -358,8 +358,8 @@ clock-names = "core", "aon"; dmas = <&qpic_bam 0>, - <&qpic_bam 1>, - <&qpic_bam 2>; + <&qpic_bam 1>, + <&qpic_bam 2>; dma-names = "tx", "rx", "cmd"; pinctrl-0 = <&qpic_pins>; pinctrl-names = "default"; @@ -372,10 +372,10 @@ #size-cells = <2>; interrupt-controller; #interrupt-cells = <0x3>; - reg = <0x0 0x0b000000 0x0 0x1000>, /*GICD*/ - <0x0 0x0b002000 0x0 0x1000>, /*GICC*/ - <0x0 0x0b001000 0x0 0x1000>, /*GICH*/ - <0x0 0x0b004000 0x0 0x1000>; /*GICV*/ + reg = <0x0 0x0b000000 0x0 0x1000>, /*GICD*/ + <0x0 0x0b002000 0x0 0x1000>, /*GICC*/ + <0x0 0x0b001000 0x0 0x1000>, /*GICH*/ + <0x0 0x0b004000 0x0 0x1000>; /*GICV*/ interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>; ranges = <0 0 0 0xb00a000 0 0xffd>; @@ -388,7 +388,7 @@ pcie_phy: phy@84000 { compatible = "qcom,ipq6018-qmp-pcie-phy"; - reg = <0x0 0x84000 0x0 0x1bc>; /* Serdes PLL */ + reg = <0x0 0x00084000 0x0 0x1bc>; /* Serdes PLL */ status = "disabled"; #address-cells = <2>; #size-cells = <2>; @@ -404,9 +404,10 @@ "common"; pcie_phy0: phy@84200 { - reg = <0x0 0x84200 0x0 0x16c>, /* Serdes Tx */ - <0x0 0x84400 0x0 0x200>, /* Serdes Rx */ - <0x0 0x84800 0x0 0x4f4>; /* PCS: Lane0, COM, PCIE */ + reg = <0x0 0x00084200 0x0 0x16c>, /* Serdes Tx */ + <0x0 0x00084400 0x0 0x200>, /* Serdes Rx */ + <0x0 0x00084800 0x0 0x1f0>, /* PCS: Lane0, COM, PCIE */ + <0x0 0x00084c00 0x0 0xf4>; /* pcs_misc */ #phy-cells = <0>; clocks = <&gcc GCC_PCIE0_PIPE_CLK>; @@ -628,7 +629,7 @@ #address-cells = <1>; #size-cells = <0>; compatible = "qcom,ipq6018-mdio", "qcom,ipq4019-mdio"; - reg = <0x0 0x90000 0x0 0x64>; + reg = <0x0 0x00090000 0x0 0x64>; clocks = <&gcc GCC_MDIO_AHB_CLK>; clock-names = "gcc_mdio_ahb_clk"; status = "disabled"; @@ -636,7 +637,7 @@ qusb_phy_1: qusb@59000 { compatible = "qcom,ipq6018-qusb2-phy"; - reg = <0x0 0x059000 0x0 0x180>; + reg = <0x0 0x00059000 0x0 0x180>; #phy-cells = <0>; clocks = <&gcc GCC_USB1_PHY_CFG_AHB_CLK>, @@ -668,23 +669,23 @@ status = "disabled"; dwc_1: usb@7000000 { - compatible = "snps,dwc3"; - reg = <0x0 0x7000000 0x0 0xcd00>; - interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>; - phys = <&qusb_phy_1>; - phy-names = "usb2-phy"; - tx-fifo-resize; - snps,is-utmi-l1-suspend; - snps,hird-threshold = /bits/ 8 <0x0>; - snps,dis_u2_susphy_quirk; - snps,dis_u3_susphy_quirk; - dr_mode = "host"; + compatible = "snps,dwc3"; + reg = <0x0 0x07000000 0x0 0xcd00>; + interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>; + phys = <&qusb_phy_1>; + phy-names = "usb2-phy"; + tx-fifo-resize; + snps,is-utmi-l1-suspend; + snps,hird-threshold = /bits/ 8 <0x0>; + snps,dis_u2_susphy_quirk; + snps,dis_u3_susphy_quirk; + dr_mode = "host"; }; }; ssphy_0: ssphy@78000 { compatible = "qcom,ipq6018-qmp-usb3-phy"; - reg = <0x0 0x78000 0x0 0x1C4>; + reg = <0x0 0x00078000 0x0 0x1c4>; #address-cells = <2>; #size-cells = <2>; ranges; @@ -701,7 +702,7 @@ usb0_ssphy: phy@78200 { reg = <0x0 0x00078200 0x0 0x130>, /* Tx */ <0x0 0x00078400 0x0 0x200>, /* Rx */ - <0x0 0x00078800 0x0 0x1F8>, /* PCS */ + <0x0 0x00078800 0x0 0x1f8>, /* PCS */ <0x0 0x00078600 0x0 0x044>; /* PCS misc */ #phy-cells = <0>; #clock-cells = <0>; @@ -713,7 +714,7 @@ qusb_phy_0: qusb@79000 { compatible = "qcom,ipq6018-qusb2-phy"; - reg = <0x0 0x079000 0x0 0x180>; + reg = <0x0 0x00079000 0x0 0x180>; #phy-cells = <0>; clocks = <&gcc GCC_USB0_PHY_CFG_AHB_CLK>, @@ -726,7 +727,7 @@ usb3: usb@8af8800 { compatible = "qcom,ipq6018-dwc3", "qcom,dwc3"; - reg = <0x0 0x8AF8800 0x0 0x400>; + reg = <0x0 0x8af8800 0x0 0x400>; #address-cells = <2>; #size-cells = <2>; ranges; @@ -745,14 +746,14 @@ <&gcc GCC_USB0_MOCK_UTMI_CLK>; assigned-clock-rates = <133330000>, <133330000>, - <20000000>; + <24000000>; resets = <&gcc GCC_USB0_BCR>; status = "disabled"; dwc_0: usb@8a00000 { compatible = "snps,dwc3"; - reg = <0x0 0x8A00000 0x0 0xcd00>; + reg = <0x0 0x8a00000 0x0 0xcd00>; interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>; phys = <&qusb_phy_0>, <&usb0_ssphy>; phy-names = "usb2-phy", "usb3-phy"; diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index bafac2cf7e3d..987cebbda057 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -1522,7 +1522,7 @@ clock-names = "bam_clk"; #dma-cells = <1>; qcom,ee = <0>; - status = "disabled"; + qcom,controlled-remotely; }; blsp1_uart1: serial@78af000 { diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 9de2248a385a..789121171a11 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -390,6 +390,19 @@ reg = <0x0 0x80000000 0x0 0x0>; }; + etm { + compatible = "qcom,coresight-remote-etm"; + + out-ports { + port { + modem_etm_out_funnel_in2: endpoint { + remote-endpoint = + <&funnel_in2_in_modem_etm>; + }; + }; + }; + }; + psci { compatible = "arm,psci-1.0"; method = "smc"; @@ -2565,6 +2578,14 @@ clocks = <&rpmcc RPM_QDSS_CLK>, <&rpmcc RPM_QDSS_A_CLK>; clock-names = "apb_pclk", "atclk"; + in-ports { + port { + funnel_in2_in_modem_etm: endpoint { + remote-endpoint = + <&modem_etm_out_funnel_in2>; + }; + }; + }; out-ports { port { diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index b00b8164c4aa..7a41250539ff 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -1903,9 +1903,11 @@ cpu = <&CPU4>; - port{ - etm4_out: endpoint { - remote-endpoint = <&apss_funnel_in4>; + out-ports { + port{ + etm4_out: endpoint { + remote-endpoint = <&apss_funnel_in4>; + }; }; }; }; @@ -1920,9 +1922,11 @@ cpu = <&CPU5>; - port{ - etm5_out: endpoint { - remote-endpoint = <&apss_funnel_in5>; + out-ports { + port{ + etm5_out: endpoint { + remote-endpoint = <&apss_funnel_in5>; + }; }; }; }; @@ -1937,9 +1941,11 @@ cpu = <&CPU6>; - port{ - etm6_out: endpoint { - remote-endpoint = <&apss_funnel_in6>; + out-ports { + port{ + etm6_out: endpoint { + remote-endpoint = <&apss_funnel_in6>; + }; }; }; }; @@ -1954,9 +1960,11 @@ cpu = <&CPU7>; - port{ - etm7_out: endpoint { - remote-endpoint = <&apss_funnel_in7>; + out-ports { + port{ + etm7_out: endpoint { + remote-endpoint = <&apss_funnel_in7>; + }; }; }; }; diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts index 9731a7c63d53..1defbe0404e2 100644 --- a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts +++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts @@ -63,8 +63,8 @@ function = LED_FUNCTION_INDICATOR; color = <LED_COLOR_ID_GREEN>; gpios = <&pm8150_gpios 10 GPIO_ACTIVE_HIGH>; - linux,default-trigger = "panic-indicator"; default-state = "off"; + panic-indicator; }; led-wlan { diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index 6f0ee4e13ef1..13fe1c92bf35 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -2769,8 +2769,8 @@ interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 8 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 9 IRQ_TYPE_LEVEL_HIGH>; + <&pdc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -3378,7 +3378,7 @@ compatible = "qcom,apss-wdt-sc7180", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>; }; timer@17c20000{ diff --git a/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi b/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi index 25f31c81b2b7..efe6ea538ad2 100644 --- a/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi @@ -56,6 +56,26 @@ }; }; +&lpass_aon { + status = "okay"; +}; + +&lpass_core { + status = "okay"; +}; + +&lpass_hm { + status = "okay"; +}; + +&lpasscc { + status = "okay"; +}; + +&pdc_reset { + status = "okay"; +}; + /* The PMIC PON code isn't compatible w/ how Chrome EC/BIOS handle things. */ &pmk8350_pon { status = "disabled"; @@ -93,6 +113,10 @@ reg = <0x0 0x9c900000 0x0 0x800000>; }; +&watchdog { + status = "okay"; +}; + &wifi { status = "okay"; diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index aea356c63b9a..04106d725400 100644 --- a/arch/arm64/boot/dts/qcom/sc7280.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi @@ -888,6 +888,7 @@ bus-width = <8>; supports-cqe; + dma-coherent; qcom,dll-config = <0x0007642c>; qcom,ddr-config = <0x80040868>; @@ -2187,6 +2188,7 @@ clocks = <&gcc GCC_CFG_NOC_LPASS_CLK>; clock-names = "iface"; #clock-cells = <1>; + status = "reserved"; /* Owned by ADSP firmware */ }; lpass_rx_macro: codec@3200000 { @@ -2339,6 +2341,7 @@ clock-names = "bi_tcxo", "bi_tcxo_ao", "iface"; #clock-cells = <1>; #power-domain-cells = <1>; + status = "reserved"; /* Owned by ADSP firmware */ }; lpass_core: clock-controller@3900000 { @@ -2349,6 +2352,7 @@ power-domains = <&lpass_hm LPASS_CORE_CC_LPASS_CORE_HM_GDSC>; #clock-cells = <1>; #power-domain-cells = <1>; + status = "reserved"; /* Owned by ADSP firmware */ }; lpass_cpu: audio@3987000 { @@ -2419,6 +2423,7 @@ clock-names = "bi_tcxo"; #clock-cells = <1>; #power-domain-cells = <1>; + status = "reserved"; /* Owned by ADSP firmware */ }; lpass_ag_noc: interconnect@3c40000 { @@ -2529,7 +2534,8 @@ "cx_mem", "cx_dbgc"; interrupts = <GIC_SPI 300 IRQ_TYPE_LEVEL_HIGH>; - iommus = <&adreno_smmu 0 0x401>; + iommus = <&adreno_smmu 0 0x400>, + <&adreno_smmu 1 0x400>; operating-points-v2 = <&gpu_opp_table>; qcom,gmu = <&gmu>; interconnects = <&gem_noc MASTER_GFX3D 0 &mc_virt SLAVE_EBI1 0>; @@ -2696,6 +2702,7 @@ "gpu_cc_hub_aon_clk"; power-domains = <&gpucc GPU_CC_CX_GDSC>; + dma-coherent; }; remoteproc_mpss: remoteproc@4080000 { @@ -3265,6 +3272,7 @@ operating-points-v2 = <&sdhc2_opp_table>; bus-width = <4>; + dma-coherent; qcom,dll-config = <0x0007642c>; @@ -3386,8 +3394,8 @@ assigned-clock-rates = <19200000>, <200000000>; interrupts-extended = <&intc GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 12 IRQ_TYPE_EDGE_RISING>, - <&pdc 13 IRQ_TYPE_EDGE_RISING>; + <&pdc 12 IRQ_TYPE_EDGE_BOTH>, + <&pdc 13 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "dp_hs_phy_irq", "dm_hs_phy_irq"; @@ -3656,9 +3664,9 @@ assigned-clock-rates = <19200000>, <200000000>; interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 14 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 14 IRQ_TYPE_EDGE_BOTH>, <&pdc 15 IRQ_TYPE_EDGE_BOTH>, - <&pdc 17 IRQ_TYPE_EDGE_BOTH>; + <&pdc 17 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "hs_phy_irq", "dp_hs_phy_irq", "dm_hs_phy_irq", @@ -4195,6 +4203,7 @@ compatible = "qcom,sc7280-pdc-global"; reg = <0 0x0b5e0000 0 0x20000>; #reset-cells = <1>; + status = "reserved"; /* Owned by firmware */ }; tsens0: thermal-sensor@c263000 { @@ -5186,11 +5195,12 @@ }; }; - watchdog@17c10000 { + watchdog: watchdog@17c10000 { compatible = "qcom,apss-wdt-sc7280", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>; + status = "reserved"; /* Owned by Gunyah hyp */ }; timer@17c20000 { diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index 405835ad28bc..7e3aaf5de3f5 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -1653,7 +1653,7 @@ compatible = "qcom,apss-wdt-sc8280xp", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>; }; timer@17c20000 { diff --git a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi index a5c0c788969f..43ee28db61aa 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi @@ -150,15 +150,15 @@ }; &psci { - /delete-node/ cpu0; - /delete-node/ cpu1; - /delete-node/ cpu2; - /delete-node/ cpu3; - /delete-node/ cpu4; - /delete-node/ cpu5; - /delete-node/ cpu6; - /delete-node/ cpu7; - /delete-node/ cpu-cluster0; + /delete-node/ power-domain-cpu0; + /delete-node/ power-domain-cpu1; + /delete-node/ power-domain-cpu2; + /delete-node/ power-domain-cpu3; + /delete-node/ power-domain-cpu4; + /delete-node/ power-domain-cpu5; + /delete-node/ power-domain-cpu6; + /delete-node/ power-domain-cpu7; + /delete-node/ power-domain-cluster; }; &cpus { @@ -351,7 +351,9 @@ &apps_rsc { - pm8998-rpmh-regulators { + /delete-property/ power-domains; + + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -633,7 +635,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-1 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index c9efcb894a52..135ff4368c4a 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -66,8 +66,8 @@ function = LED_FUNCTION_INDICATOR; color = <LED_COLOR_ID_GREEN>; gpios = <&pm8998_gpio 13 GPIO_ACTIVE_HIGH>; - linux,default-trigger = "panic-indicator"; default-state = "off"; + panic-indicator; }; led-1 { @@ -271,7 +271,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; vdd-s1-supply = <&vph_pwr>; @@ -396,7 +396,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-lg-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-lg-common.dtsi index 20f275f8694d..e2921640880a 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-lg-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-lg-common.dtsi @@ -166,7 +166,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -419,7 +419,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -433,7 +433,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-mtp.dts b/arch/arm64/boot/dts/qcom/sdm845-mtp.dts index 64958dee17d8..b47e333aa351 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-mtp.dts @@ -117,7 +117,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -382,7 +382,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -396,7 +396,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi index 392461c29e76..0713b774a97b 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi @@ -144,7 +144,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -280,7 +280,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -294,7 +294,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts index 83261c9bb4f2..b65c35865dab 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts @@ -110,7 +110,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -375,7 +375,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -389,7 +389,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi b/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi index d6918e6d1979..249a715d5aae 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi @@ -78,7 +78,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -308,7 +308,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -319,7 +319,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium.dts b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium.dts index 0f470cf1ed1c..6d6b3dd69947 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium.dts @@ -125,7 +125,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-polaris.dts b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-polaris.dts index 093b04359ec3..ffbe45a99b74 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-polaris.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-polaris.dts @@ -143,7 +143,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -343,7 +343,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -355,7 +355,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 52c9f5639f8a..95c515da9f2e 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -4048,10 +4048,10 @@ <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>; - interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 6 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc_intc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -4099,10 +4099,10 @@ <&gcc GCC_USB30_SEC_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>; - interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 490 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 491 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 7 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 10 IRQ_TYPE_EDGE_BOTH>, + <&pdc_intc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -5019,7 +5019,7 @@ compatible = "qcom,apss-wdt-sdm845", "qcom,kpss-wdt"; reg = <0 0x17980000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>; }; apss_shared: mailbox@17990000 { diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index 74f43da51fa5..48a41ace8fc5 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -99,7 +99,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; diff --git a/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts b/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts index d028a7eb364a..c169d2870bdf 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts @@ -129,7 +129,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi index cea7ca3f326f..9da373090593 100644 --- a/arch/arm64/boot/dts/qcom/sm6350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi @@ -1462,7 +1462,7 @@ compatible = "qcom,apss-wdt-sm6350", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>; }; timer@17c20000 { diff --git a/arch/arm64/boot/dts/qcom/sm8150-hdk.dts b/arch/arm64/boot/dts/qcom/sm8150-hdk.dts index 3331ee957d64..368da4c7f41b 100644 --- a/arch/arm64/boot/dts/qcom/sm8150-hdk.dts +++ b/arch/arm64/boot/dts/qcom/sm8150-hdk.dts @@ -126,8 +126,6 @@ vdda_sp_sensor: vdda_ufs_2ln_core_1: vdda_ufs_2ln_core_2: - vdda_usb_ss_dp_core_1: - vdda_usb_ss_dp_core_2: vdda_qlink_lv: vdda_qlink_lv_ck: vreg_l5a_0p875: ldo5 { @@ -209,6 +207,12 @@ regulator-max-microvolt = <3008000>; regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>; }; + + vreg_l18a_0p8: ldo18 { + regulator-min-microvolt = <880000>; + regulator-max-microvolt = <880000>; + regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>; + }; }; pm8150l-rpmh-regulators { @@ -439,13 +443,13 @@ &usb_1_qmpphy { status = "okay"; vdda-phy-supply = <&vreg_l3c_1p2>; - vdda-pll-supply = <&vdda_usb_ss_dp_core_1>; + vdda-pll-supply = <&vreg_l18a_0p8>; }; &usb_2_qmpphy { status = "okay"; vdda-phy-supply = <&vreg_l3c_1p2>; - vdda-pll-supply = <&vdda_usb_ss_dp_core_1>; + vdda-pll-supply = <&vreg_l5a_0p875>; }; &usb_1 { diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi index c586378fc6bc..eb1a9369926d 100644 --- a/arch/arm64/boot/dts/qcom/sm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi @@ -3628,10 +3628,10 @@ <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <200000000>; - interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -3677,10 +3677,10 @@ <&gcc GCC_USB30_SEC_MASTER_CLK>; assigned-clock-rates = <19200000>, <200000000>; - interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 490 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 491 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 7 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 10 IRQ_TYPE_EDGE_BOTH>, + <&pdc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -3940,7 +3940,7 @@ compatible = "qcom,apss-wdt-sm8150", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>; }; timer@17c20000 { diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index 4d9b30f0b284..3d02adbc0b62 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -4879,7 +4879,7 @@ compatible = "qcom,apss-wdt-sm8250", "qcom,kpss-wdt"; reg = <0 0x17c10000 0 0x1000>; clocks = <&sleep_clk>; - interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 0 IRQ_TYPE_EDGE_RISING>; }; timer@17c20000 { diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index 793768a2c9e1..888bf4cd73c3 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -903,9 +903,9 @@ }; }; - gpi_dma0: dma-controller@9800000 { + gpi_dma0: dma-controller@900000 { compatible = "qcom,sm8350-gpi-dma", "qcom,sm6350-gpi-dma"; - reg = <0 0x09800000 0 0x60000>; + reg = <0 0x00900000 0 0x60000>; interrupts = <GIC_SPI 244 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 245 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi index 895f0bd9f754..541b1e73b65e 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi @@ -125,6 +125,9 @@ }; &hscif0 { + pinctrl-0 = <&hscif0_pins>; + pinctrl-names = "default"; + status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi index bfa3580429d1..61f0186447da 100644 --- a/arch/arm64/boot/dts/rockchip/px30.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30.dtsi @@ -607,6 +607,7 @@ clock-names = "spiclk", "apb_pclk"; dmas = <&dmac 12>, <&dmac 13>; dma-names = "tx", "rx"; + num-cs = <2>; pinctrl-names = "default"; pinctrl-0 = <&spi0_clk &spi0_csn &spi0_miso &spi0_mosi>; #address-cells = <1>; @@ -622,6 +623,7 @@ clock-names = "spiclk", "apb_pclk"; dmas = <&dmac 14>, <&dmac 15>; dma-names = "tx", "rx"; + num-cs = <2>; pinctrl-names = "default"; pinctrl-0 = <&spi1_clk &spi1_csn0 &spi1_csn1 &spi1_miso &spi1_mosi>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi index ee6095baba4d..7d9b8064ad2e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi @@ -510,8 +510,7 @@ ap_i2c_tp: &i2c5 { &pci_rootport { mvl_wifi: wifi@0,0 { compatible = "pci1b4b,2b42"; - reg = <0x83010000 0x0 0x00000000 0x0 0x00100000 - 0x83010000 0x0 0x00100000 0x0 0x00100000>; + reg = <0x0000 0x0 0x0 0x0 0x0>; interrupt-parent = <&gpio0>; interrupts = <8 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts index 853e88455e75..9e4b12ed62cb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts @@ -34,8 +34,8 @@ &pci_rootport { wifi@0,0 { compatible = "qcom,ath10k"; - reg = <0x00010000 0x0 0x00000000 0x0 0x00000000>, - <0x03010010 0x0 0x00000000 0x0 0x00200000>; + reg = <0x00000000 0x0 0x00000000 0x0 0x00000000>, + <0x03000010 0x0 0x00000000 0x0 0x00200000>; qcom,ath10k-calibration-variant = "GO_DUMO"; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi index 23bfba86daab..7ba25315dd9a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi @@ -489,6 +489,7 @@ ap_i2c_audio: &i2c8 { #address-cells = <3>; #size-cells = <2>; ranges; + device_type = "pci"; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi index 234b5bbda120..f4d6dbbbddcd 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi @@ -958,7 +958,7 @@ <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "sys", "pmc", "msi", "legacy", "err"; + interrupt-names = "sys", "pmc", "msg", "legacy", "err"; bus-range = <0x0 0xf>; clocks = <&cru ACLK_PCIE20_MST>, <&cru ACLK_PCIE20_SLV>, <&cru ACLK_PCIE20_DBI>, <&cru PCLK_PCIE20>, diff --git a/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi index a3a2ab24a9f1..e96910af341b 100644 --- a/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi @@ -5,6 +5,8 @@ * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/ */ +#include <dt-bindings/bus/ti-sysc.h> + &cbass_wakeup { wkup_conf: syscon@43000000 { compatible = "ti,j721e-system-controller", "syscon", "simple-mfd"; @@ -29,14 +31,34 @@ }; }; - wkup_uart0: serial@2b300000 { - compatible = "ti,am64-uart", "ti,am654-uart"; - reg = <0x00 0x2b300000 0x00 0x100>; - interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>; + target-module@2b300050 { + compatible = "ti,sysc-omap2", "ti,sysc"; + reg = <0 0x2b300050 0 0x4>, + <0 0x2b300054 0 0x4>, + <0 0x2b300058 0 0x4>; + reg-names = "rev", "sysc", "syss"; + ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP | + SYSC_OMAP2_SOFTRESET | + SYSC_OMAP2_AUTOIDLE)>; + ti,sysc-sidle = <SYSC_IDLE_FORCE>, + <SYSC_IDLE_NO>, + <SYSC_IDLE_SMART>, + <SYSC_IDLE_SMART_WKUP>; + ti,syss-mask = <1>; + ti,no-reset-on-init; power-domains = <&k3_pds 114 TI_SCI_PD_EXCLUSIVE>; clocks = <&k3_clks 114 0>; - clock-names = "fclk"; - status = "disabled"; + clock-names = "fck"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0 0x2b300000 0x100000>; + + wkup_uart0: serial@0 { + compatible = "ti,am64-uart", "ti,am654-uart"; + reg = <0 0x100>; + interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; }; wkup_i2c0: i2c@2b200000 { diff --git a/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi index 34efe4876175..e46dc1d29f7e 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi @@ -609,7 +609,7 @@ mmc-hs200-1_8v; mmc-hs400-1_8v; ti,clkbuf-sel = <0x7>; - ti,strobe-sel = <0x77>; + ti,strobe-sel = <0x55>; ti,trm-icp = <0x8>; ti,otap-del-sel-legacy = <0x1>; ti,otap-del-sel-mmc-hs = <0x1>; diff --git a/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi index d6bf0d4a15d3..6c9f5d3bd756 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi @@ -174,6 +174,7 @@ interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "int0", "int1"; + wakeup-source; status = "disabled"; }; @@ -189,6 +190,7 @@ interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "int0", "int1"; + wakeup-source; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi index 2883bea20104..5fd201ce401a 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi @@ -4,8 +4,10 @@ * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/ */ +#include <dt-bindings/bus/ti-sysc.h> + &cbass_wakeup { - wkup_conf: bus@43000000 { + wkup_conf: syscon@43000000 { compatible = "syscon", "simple-mfd"; reg = <0x00 0x43000000 0x00 0x20000>; #address-cells = <1>; @@ -20,14 +22,34 @@ }; }; - wkup_uart0: serial@2b300000 { - compatible = "ti,am64-uart", "ti,am654-uart"; - reg = <0x00 0x2b300000 0x00 0x100>; - interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>; + target-module@2b300050 { + compatible = "ti,sysc-omap2", "ti,sysc"; + reg = <0 0x2b300050 0 0x4>, + <0 0x2b300054 0 0x4>, + <0 0x2b300058 0 0x4>; + reg-names = "rev", "sysc", "syss"; + ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP | + SYSC_OMAP2_SOFTRESET | + SYSC_OMAP2_AUTOIDLE)>; + ti,sysc-sidle = <SYSC_IDLE_FORCE>, + <SYSC_IDLE_NO>, + <SYSC_IDLE_SMART>, + <SYSC_IDLE_SMART_WKUP>; + ti,syss-mask = <1>; + ti,no-reset-on-init; power-domains = <&k3_pds 114 TI_SCI_PD_EXCLUSIVE>; clocks = <&k3_clks 114 0>; - clock-names = "fclk"; - status = "disabled"; + clock-names = "fck"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0 0x2b300000 0x100000>; + + wkup_uart0: serial@0 { + compatible = "ti,am64-uart", "ti,am654-uart"; + reg = <0 0x100>; + interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; }; wkup_i2c0: i2c@2b200000 { diff --git a/arch/arm64/boot/dts/ti/k3-am62p.dtsi b/arch/arm64/boot/dts/ti/k3-am62p.dtsi index 6a3534b86ae3..61c5b553008d 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p.dtsi @@ -127,3 +127,7 @@ #include "k3-am62p-main.dtsi" #include "k3-am62p-mcu.dtsi" #include "k3-am62p-wakeup.dtsi" + +&dmsc { + ti,partial-io-wakeup-sources = <&mcu_mcan0>, <&mcu_mcan1>, <&mcu_uart0>, <&wkup_uart0>; +}; diff --git a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts index d5cfff9c14af..4b8e7964ca4d 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts @@ -19,6 +19,7 @@ aliases { serial0 = &wkup_uart0; + serial1 = &mcu_uart0; serial2 = &main_uart0; serial3 = &main_uart1; mmc0 = &sdhci0; @@ -38,18 +39,14 @@ stdout-path = &main_uart0; - framebuffer0: framebuffer@ff700000 { + framebuffer0: framebuffer@0 { compatible = "simple-framebuffer"; power-domains = <&k3_pds 186 TI_SCI_PD_EXCLUSIVE>; clocks = <&k3_clks 186 6>, <&k3_clks 186 0>, <&k3_clks 186 2>; display = <&dss0>; - reg = <0x00 0xff700000 0x00 0x008ca000>; - width = <1920>; - height = <1200>; - stride = <(1920 * 4)>; - format = "x8r8g8b8"; + status = "disabled"; }; }; @@ -112,11 +109,6 @@ reg = <0x00 0x9e800000 0x00 0x01800000>; /* for OP-TEE */ no-map; }; - - framebuffer: framebuffer@ff700000 { - reg = <0x00 0xff700000 0x00 0x008ca000>; - no-map; - }; }; vmain_pd: regulator-0 { @@ -817,8 +809,6 @@ wkup_uart0_pins_default: wkup-uart0-default-pins { pinctrl-single,pins = < - AM62PX_MCU_IOPAD(0x02c, PIN_INPUT, 0) /* (C7) WKUP_UART0_CTSn */ - AM62PX_MCU_IOPAD(0x030, PIN_OUTPUT, 0) /* (C6) WKUP_UART0_RTSn */ AM62PX_MCU_IOPAD(0x024, PIN_INPUT, 0) /* (D8) WKUP_UART0_RXD */ AM62PX_MCU_IOPAD(0x028, PIN_OUTPUT, 0) /* (D7) WKUP_UART0_TXD */ >; diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi index 167e2b52e572..b1980b85cfc2 100644 --- a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi @@ -40,11 +40,7 @@ <&k3_clks 186 0>, <&k3_clks 186 2>; display = <&dss>; - reg = <0x00 0xff700000 0x00 0x008ca000>; - width = <1920>; - height = <1200>; - stride = <(1920 * 4)>; - format = "x8r8g8b8"; + status = "disabled"; }; }; @@ -118,11 +114,6 @@ alignment = <0x1000>; no-map; }; - - framebuffer: framebuffer@ff700000 { - reg = <0x00 0xff700000 0x00 0x008ca000>; - no-map; - }; }; leds { diff --git a/arch/arm64/boot/dts/ti/k3-am642-evm-icssg1-dualemac-mii.dtso b/arch/arm64/boot/dts/ti/k3-am642-evm-icssg1-dualemac-mii.dtso index 0d35b55a293e..4078f1950fac 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-evm-icssg1-dualemac-mii.dtso +++ b/arch/arm64/boot/dts/ti/k3-am642-evm-icssg1-dualemac-mii.dtso @@ -76,7 +76,7 @@ }; &cpsw3g { - pinctrl-0 = <&mdio1_pins_default &rgmii1_pins_default>; + pinctrl-0 = <&rgmii1_pins_default>; }; &cpsw_port2 { diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi index 7e1531e35239..60e60cd76740 100644 --- a/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi @@ -456,7 +456,7 @@ reg = <0x0 0x42040000 0x0 0x350>, <0x0 0x42050000 0x0 0x350>, <0x0 0x43000300 0x0 0x10>; - power-domains = <&k3_pds 154 TI_SCI_PD_SHARED>; + power-domains = <&k3_pds 180 TI_SCI_PD_SHARED>; #thermal-sensor-cells = <1>; }; diff --git a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts index dc27ae9a078c..85340a77fef6 100644 --- a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts +++ b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts @@ -249,8 +249,10 @@ main_uart0_pins_default: main-uart0-default-pins { pinctrl-single,pins = < - J722S_IOPAD(0x01c8, PIN_INPUT, 0) /* (A22) UART0_RXD */ - J722S_IOPAD(0x01cc, PIN_OUTPUT, 0) /* (B22) UART0_TXD */ + J722S_IOPAD(0x01c8, PIN_INPUT, 0) /* (F19) UART0_RXD */ + J722S_IOPAD(0x01cc, PIN_OUTPUT, 0) /* (F20) UART0_TXD */ + J722S_IOPAD(0x01d4, PIN_OUTPUT, 0) /* (B21) UART0_RTSn */ + J722S_IOPAD(0x01d0, PIN_INPUT, 0) /* (E22) UART0_CTSn */ >; bootph-all; }; diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi index 26f070196328..4f6b9774500d 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi @@ -416,7 +416,7 @@ reg = <0x0 0x42040000 0x0 0x350>, <0x0 0x42050000 0x0 0x350>, <0x0 0x43000300 0x0 0x10>; - power-domains = <&k3_pds 154 TI_SCI_PD_SHARED>; + power-domains = <&k3_pds 243 TI_SCI_PD_SHARED>; #thermal-sensor-cells = <1>; }; diff --git a/arch/arm64/boot/install.sh b/arch/arm64/boot/install.sh index 7399d706967a..9b7a09808a3d 100755 --- a/arch/arm64/boot/install.sh +++ b/arch/arm64/boot/install.sh @@ -17,7 +17,8 @@ # $3 - kernel map file # $4 - default install path (blank if root directory) -if [ "$(basename $2)" = "Image.gz" ]; then +if [ "$(basename $2)" = "Image.gz" ] || [ "$(basename $2)" = "vmlinuz.efi" ] +then # Compressed install echo "Installing compressed kernel" base=vmlinuz diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h index 3622e9f4fb44..51738c56e96c 100644 --- a/arch/arm64/include/asm/alternative-macros.h +++ b/arch/arm64/include/asm/alternative-macros.h @@ -229,7 +229,7 @@ alternative_has_feature_likely(unsigned long feature) compiletime_assert(feature < ARM64_NCAPS, "feature must be < ARM64_NCAPS"); - asm_volatile_goto( + asm goto( ALTERNATIVE_CB("b %l[l_no]", %[feature], alt_cb_patch_nops) : : [feature] "i" (feature) @@ -247,7 +247,7 @@ alternative_has_feature_unlikely(unsigned long feature) compiletime_assert(feature < ARM64_NCAPS, "feature must be < ARM64_NCAPS"); - asm_volatile_goto( + asm goto( ALTERNATIVE("nop", "b %l[l_yes]", %[feature]) : : [feature] "i" (feature) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 7dce9c0aa783..af3a678a76b3 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -61,6 +61,7 @@ #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 #define ARM_CPU_IMP_AMPERE 0xC0 +#define ARM_CPU_IMP_MICROSOFT 0x6D #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -128,6 +129,8 @@ #define AMPERE_CPU_PART_AMPERE1 0xAC3 +#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */ + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -179,6 +182,7 @@ #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) +#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index d720b6f7e5f9..da18413712c0 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -343,6 +343,7 @@ extern void sme_alloc(struct task_struct *task, bool flush); extern unsigned int sme_get_vl(void); extern int sme_set_current_vl(unsigned long arg); extern int sme_get_current_vl(void); +extern void sme_suspend_exit(void); /* * Return how many bytes of memory are required to store the full SME @@ -372,6 +373,7 @@ static inline int sme_max_vl(void) { return 0; } static inline int sme_max_virtualisable_vl(void) { return 0; } static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sme_get_current_vl(void) { return -EINVAL; } +static inline void sme_suspend_exit(void) { } static inline size_t za_state_size(struct task_struct const *task) { diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h index 81bbfa3a035b..a1020285ea75 100644 --- a/arch/arm64/include/asm/irq_work.h +++ b/arch/arm64/include/asm/irq_work.h @@ -2,8 +2,6 @@ #ifndef __ASM_IRQ_WORK_H #define __ASM_IRQ_WORK_H -extern void arch_irq_work_raise(void); - static inline bool arch_irq_work_has_interrupt(void) { return true; diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index cea441b6aa5d..b5bd3c38a01b 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -18,7 +18,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: nop \n\t" " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" @@ -35,7 +35,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: b %l[l_yes] \n\t" " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 3f917124684c..74584597bfb8 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -390,6 +390,7 @@ static const struct midr_range erratum_1463225[] = { static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2139208 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2119858 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -403,6 +404,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { static const struct midr_range tsb_flush_fail_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2067961 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2054223 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -415,6 +417,7 @@ static const struct midr_range tsb_flush_fail_cpus[] = { static struct midr_range trbe_write_out_of_range_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2253138 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2224489 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -723,10 +726,10 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .cpu_enable = cpu_clear_bf16_from_user_emulation, }, #endif -#ifdef CONFIG_ARM64_ERRATUM_2966298 +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD { .desc = "ARM erratum 2966298", - .capability = ARM64_WORKAROUND_2966298, + .capability = ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD, /* Cortex-A520 r0p0 - r0p1 */ ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1), }, diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index de16fa917e1b..62146d48dba7 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -419,7 +419,7 @@ alternative_else_nop_endif ldp x28, x29, [sp, #16 * 14] .if \el == 0 -alternative_if ARM64_WORKAROUND_2966298 +alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD tlbi vale1, xzr dsb nsh alternative_else_nop_endif diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 8c226d79abdf..59b5a16bab5d 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1347,6 +1347,20 @@ void __init sme_setup(void) get_sme_default_vl()); } +void sme_suspend_exit(void) +{ + u64 smcr = 0; + + if (!system_supports_sme()) + return; + + if (system_supports_fa64()) + smcr |= SMCR_ELx_FA64; + + write_sysreg_s(smcr, SYS_SMCR_EL1); + write_sysreg_s(0, SYS_SMPRI_EL1); +} + #endif /* CONFIG_ARM64_SME */ static void sve_init_regs(void) diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 38dbd3828f13..d2850b49a371 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -22,6 +22,7 @@ #include <linux/vmalloc.h> #include <asm/daifflags.h> #include <asm/exception.h> +#include <asm/numa.h> #include <asm/vmap_stack.h> #include <asm/softirq_stack.h> @@ -46,17 +47,17 @@ static void init_irq_scs(void) for_each_possible_cpu(cpu) per_cpu(irq_shadow_call_stack_ptr, cpu) = - scs_alloc(cpu_to_node(cpu)); + scs_alloc(early_cpu_to_node(cpu)); } #ifdef CONFIG_VMAP_STACK -static void init_irq_stacks(void) +static void __init init_irq_stacks(void) { int cpu; unsigned long *p; for_each_possible_cpu(cpu) { - p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu)); + p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu)); per_cpu(irq_stack_ptr, cpu) = p; } } diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 7b0643fe2f13..214b1805e536 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -168,7 +168,11 @@ armv8pmu_events_sysfs_show(struct device *dev, PMU_EVENT_ATTR_ID(name, armv8pmu_events_sysfs_show, config) static struct attribute *armv8_pmuv3_event_attrs[] = { - ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR), + /* + * Don't expose the sw_incr event in /sys. It's not usable as writes to + * PMSWINC_EL0 will trap as PMUSERENR.{SW,EN}=={0,0} and event rotation + * means we don't have a fixed event<->counter relationship regardless. + */ ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL), ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL), ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL), diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 8b02d310838f..064d996cc55b 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -11,6 +11,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/exec.h> +#include <asm/fpsimd.h> #include <asm/mte.h> #include <asm/memory.h> #include <asm/mmu_context.h> @@ -77,6 +78,8 @@ void notrace __cpu_suspend_exit(void) */ spectre_v4_enable_mitigation(NULL); + sme_suspend_exit(); + /* Restore additional feature-specific configuration */ ptrauth_suspend_exit(); } diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 36c8f66cad25..d513533cc922 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -68,11 +68,9 @@ VDSO_CFLAGS += -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -fno-common \ -Werror-implicit-function-declaration \ -Wno-format-security \ - -Wdeclaration-after-statement \ -std=gnu11 VDSO_CFLAGS += -O2 # Some useful compiler-dependent flags from top-level Makefile -VDSO_CFLAGS += $(call cc32-option,-Wdeclaration-after-statement,) VDSO_CFLAGS += $(call cc32-option,-Wno-pointer-sign) VDSO_CFLAGS += -fno-strict-overflow VDSO_CFLAGS += $(call cc32-option,-Werror=strict-prototypes) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 6cc380a15eb7..de94515fb17c 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -386,7 +386,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); kvm_timer_vcpu_terminate(vcpu); kvm_pmu_vcpu_destroy(vcpu); - + kvm_vgic_vcpu_destroy(vcpu); kvm_arm_vcpu_destroy(vcpu); } diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index f2f3bf4a04b0..0919e3b8f46e 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -368,7 +368,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) vgic_v4_teardown(kvm); } -void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) +static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; @@ -379,29 +379,39 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) vgic_flush_pending_lpis(vcpu); INIT_LIST_HEAD(&vgic_cpu->ap_list_head); - vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + vgic_unregister_redist_iodev(vcpu); + vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + } } -static void __kvm_vgic_destroy(struct kvm *kvm) +void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + mutex_lock(&kvm->slots_lock); + __kvm_vgic_vcpu_destroy(vcpu); + mutex_unlock(&kvm->slots_lock); +} + +void kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; - lockdep_assert_held(&kvm->arch.config_lock); + mutex_lock(&kvm->slots_lock); vgic_debug_destroy(kvm); kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vgic_vcpu_destroy(vcpu); + __kvm_vgic_vcpu_destroy(vcpu); + + mutex_lock(&kvm->arch.config_lock); kvm_vgic_dist_destroy(kvm); -} -void kvm_vgic_destroy(struct kvm *kvm) -{ - mutex_lock(&kvm->arch.config_lock); - __kvm_vgic_destroy(kvm); mutex_unlock(&kvm->arch.config_lock); + mutex_unlock(&kvm->slots_lock); } /** @@ -469,25 +479,26 @@ int kvm_vgic_map_resources(struct kvm *kvm) type = VGIC_V3; } - if (ret) { - __kvm_vgic_destroy(kvm); + if (ret) goto out; - } + dist->ready = true; dist_base = dist->vgic_dist_base; mutex_unlock(&kvm->arch.config_lock); ret = vgic_register_dist_iodev(kvm, dist_base, type); - if (ret) { + if (ret) kvm_err("Unable to register VGIC dist MMIO regions\n"); - kvm_vgic_destroy(kvm); - } - mutex_unlock(&kvm->slots_lock); - return ret; + goto out_slots; out: mutex_unlock(&kvm->arch.config_lock); +out_slots: mutex_unlock(&kvm->slots_lock); + + if (ret) + kvm_vgic_destroy(kvm); + return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 00ad6587bee9..092327665a6e 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -462,6 +462,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) } irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); + if (!irq) + continue; + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); @@ -584,7 +587,11 @@ static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db, unsigned long flags; raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); + irq = __vgic_its_check_cache(dist, db, devid, eventid); + if (irq) + vgic_get_irq_kref(irq); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return irq; @@ -763,6 +770,7 @@ int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi) raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); + vgic_put_irq(kvm, irq); return 0; } @@ -1422,6 +1430,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, for (i = 0; i < irq_count; i++) { irq = vgic_get_irq(kvm, NULL, intids[i]); + if (!irq) + continue; update_affinity(irq, vcpu2); diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 188d2187eede..ae5a3a717655 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -365,19 +365,26 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (test_bit(i, &val)) { - /* - * pending_latch is set irrespective of irq type - * (level or edge) to avoid dependency that VM should - * restore irq config before pending info. - */ - irq->pending_latch = true; - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - } else { + + /* + * pending_latch is set irrespective of irq type + * (level or edge) to avoid dependency that VM should + * restore irq config before pending info. + */ + irq->pending_latch = test_bit(i, &val); + + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + irq->pending_latch); irq->pending_latch = false; - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } + if (irq->pending_latch) + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + else + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); } @@ -820,7 +827,7 @@ out_unlock: return ret; } -static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) +void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) { struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 23e280fa0a16..9f80a580ca77 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -229,6 +229,7 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq); int vgic_v3_save_pending_tables(struct kvm *kvm); int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count); int vgic_register_redist_iodev(struct kvm_vcpu *vcpu); +void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu); bool vgic_v3_check_base(struct kvm *kvm); void vgic_v3_load(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index e73830d9f136..2dc7ddee5f04 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -71,7 +71,6 @@ WORKAROUND_2064142 WORKAROUND_2077057 WORKAROUND_2457168 WORKAROUND_2658417 -WORKAROUND_2966298 WORKAROUND_AMPERE_AC03_CPU_38 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE @@ -87,3 +86,4 @@ WORKAROUND_NVIDIA_CARMEL_CNP WORKAROUND_QCOM_FALKOR_E1003 WORKAROUND_REPEAT_TLBI WORKAROUND_SPECULATIVE_AT +WORKAROUND_SPECULATIVE_UNPRIV_LOAD diff --git a/arch/csky/include/asm/irq_work.h b/arch/csky/include/asm/irq_work.h index 33aaf39d6f94..d39fcc1f5395 100644 --- a/arch/csky/include/asm/irq_work.h +++ b/arch/csky/include/asm/irq_work.h @@ -7,5 +7,5 @@ static inline bool arch_irq_work_has_interrupt(void) { return true; } -extern void arch_irq_work_raise(void); + #endif /* __ASM_CSKY_IRQ_WORK_H */ diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h index d488ba6084bc..ef2e37a10a0f 100644 --- a/arch/csky/include/asm/jump_label.h +++ b/arch/csky/include/asm/jump_label.h @@ -12,7 +12,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: nop32 \n" " .pushsection __jump_table, \"aw\" \n" " .align 2 \n" @@ -29,7 +29,7 @@ label: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: bsr32 %l[label] \n" " .pushsection __jump_table, \"aw\" \n" " .align 2 \n" @@ -43,5 +43,10 @@ label: return true; } +enum jump_label_type; +void arch_jump_label_transform_static(struct jump_entry *entry, + enum jump_label_type type); +#define arch_jump_label_transform_static arch_jump_label_transform_static + #endif /* __ASSEMBLY__ */ #endif /* __ASM_CSKY_JUMP_LABEL_H */ diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index e737dc8cd660..fa3171f56327 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -9,6 +9,7 @@ config LOONGARCH select ARCH_BINFMT_ELF_STATE select ARCH_ENABLE_MEMORY_HOTPLUG select ARCH_ENABLE_MEMORY_HOTREMOVE + select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL @@ -80,6 +81,7 @@ config LOONGARCH select GPIOLIB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_SECCOMP select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE @@ -461,23 +463,6 @@ config PHYSICAL_START specified in the "crashkernel=YM@XM" command line boot parameter passed to the panic-ed kernel). -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - default y - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc/<pid>/seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - endmenu config ARCH_SELECT_MEMORY_MODEL @@ -495,10 +480,6 @@ config ARCH_SPARSEMEM_ENABLE or have huge holes in the physical address space for other reasons. See <file:Documentation/mm/numa.rst> for more. -config ARCH_ENABLE_THP_MIGRATION - def_bool y - depends on TRANSPARENT_HUGEPAGE - config ARCH_MEMORY_PROBE def_bool y depends on MEMORY_HOTPLUG diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h index b9a4ab54285c..f16bd42456e4 100644 --- a/arch/loongarch/include/asm/elf.h +++ b/arch/loongarch/include/asm/elf.h @@ -241,8 +241,6 @@ void loongarch_dump_regs64(u64 *uregs, const struct pt_regs *regs); do { \ current->thread.vdso = &vdso_info; \ \ - loongarch_set_personality_fcsr(state); \ - \ if (personality(current->personality) != PER_LINUX) \ set_personality(PER_LINUX); \ } while (0) @@ -259,7 +257,6 @@ do { \ clear_thread_flag(TIF_32BIT_ADDR); \ \ current->thread.vdso = &vdso_info; \ - loongarch_set_personality_fcsr(state); \ \ p = personality(current->personality); \ if (p != PER_LINUX32 && p != PER_LINUX) \ @@ -293,7 +290,7 @@ extern const char *__elf_platform; #define ELF_PLAT_INIT(_r, load_addr) do { \ _r->regs[1] = _r->regs[2] = _r->regs[3] = _r->regs[4] = 0; \ _r->regs[5] = _r->regs[6] = _r->regs[7] = _r->regs[8] = 0; \ - _r->regs[9] = _r->regs[10] = _r->regs[11] = _r->regs[12] = 0; \ + _r->regs[9] = _r->regs[10] /* syscall n */ = _r->regs[12] = 0; \ _r->regs[13] = _r->regs[14] = _r->regs[15] = _r->regs[16] = 0; \ _r->regs[17] = _r->regs[18] = _r->regs[19] = _r->regs[20] = 0; \ _r->regs[21] = _r->regs[22] = _r->regs[23] = _r->regs[24] = 0; \ @@ -340,6 +337,4 @@ extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf, extern int arch_check_elf(void *ehdr, bool has_interpreter, void *interp_ehdr, struct arch_elf_state *state); -extern void loongarch_set_personality_fcsr(struct arch_elf_state *state); - #endif /* _ASM_ELF_H */ diff --git a/arch/loongarch/kernel/elf.c b/arch/loongarch/kernel/elf.c index 183e94fc9c69..0fa81ced28dc 100644 --- a/arch/loongarch/kernel/elf.c +++ b/arch/loongarch/kernel/elf.c @@ -23,8 +23,3 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, void *_interp_ehdr, { return 0; } - -void loongarch_set_personality_fcsr(struct arch_elf_state *state) -{ - current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0; -} diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 90a5de746332..1259bc312979 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -82,6 +82,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) euen = regs->csr_euen & ~(CSR_EUEN_FPEN); regs->csr_euen = euen; lose_fpu(0); + current->thread.fpu.fcsr = boot_cpu_data.fpu_csr0; clear_thread_flag(TIF_LSX_CTX_LIVE); clear_thread_flag(TIF_LASX_CTX_LIVE); diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 14508d429ffa..18a2b37f4aea 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -297,6 +297,7 @@ void play_dead(void) addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0); } while (addr == 0); + local_irq_disable(); init_fn = (void *)TO_CACHE(addr); iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR); @@ -471,7 +472,7 @@ asmlinkage void start_secondary(void) unsigned int cpu; sync_counter(); - cpu = smp_processor_id(); + cpu = raw_smp_processor_id(); set_my_cpu_offset(per_cpu_offset(cpu)); cpu_probe(); diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c index da3681f131c8..eeb2d815cfa2 100644 --- a/arch/loongarch/mm/tlb.c +++ b/arch/loongarch/mm/tlb.c @@ -271,12 +271,16 @@ void setup_tlb_handler(int cpu) set_handler(EXCCODE_TLBNR * VECSIZE, handle_tlb_protect, VECSIZE); set_handler(EXCCODE_TLBNX * VECSIZE, handle_tlb_protect, VECSIZE); set_handler(EXCCODE_TLBPE * VECSIZE, handle_tlb_protect, VECSIZE); - } + } else { + int vec_sz __maybe_unused; + void *addr __maybe_unused; + struct page *page __maybe_unused; + + /* Avoid lockdep warning */ + rcu_cpu_starting(cpu); + #ifdef CONFIG_NUMA - else { - void *addr; - struct page *page; - const int vec_sz = sizeof(exception_handlers); + vec_sz = sizeof(exception_handlers); if (pcpu_handlers[cpu]) return; @@ -292,8 +296,8 @@ void setup_tlb_handler(int cpu) csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_EENTRY); csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_MERRENTRY); csr_write64(pcpu_handlers[cpu] + 80*VECSIZE, LOONGARCH_CSR_TLBRENTRY); - } #endif + } } void tlb_init(int cpu) diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 40ed49d9adff..4e86441e6319 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -402,7 +402,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext const u8 dst = regmap[insn->dst_reg]; const s16 off = insn->off; const s32 imm = insn->imm; - const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm; const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || BPF_CLASS(insn->code) == BPF_JMP32; switch (code) { @@ -806,8 +805,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* dst = imm64 */ case BPF_LD | BPF_IMM | BPF_DW: + { + const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm; + move_imm(ctx, dst, imm64, is32); return 1; + } /* dst = *(size *)(src + off) */ case BPF_LDX | BPF_MEM | BPF_B: diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c index f521874ebb07..67f067706af2 100644 --- a/arch/mips/alchemy/devboards/db1200.c +++ b/arch/mips/alchemy/devboards/db1200.c @@ -847,7 +847,7 @@ int __init db1200_dev_setup(void) i2c_register_board_info(0, db1200_i2c_devs, ARRAY_SIZE(db1200_i2c_devs)); spi_register_board_info(db1200_spi_devs, - ARRAY_SIZE(db1200_i2c_devs)); + ARRAY_SIZE(db1200_spi_devs)); /* SWITCHES: S6.8 I2C/SPI selector (OFF=I2C ON=SPI) * S6.7 AC97/I2S selector (OFF=AC97 ON=I2S) diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c index fd91d9c9a252..6c6837181f55 100644 --- a/arch/mips/alchemy/devboards/db1550.c +++ b/arch/mips/alchemy/devboards/db1550.c @@ -589,7 +589,7 @@ int __init db1550_dev_setup(void) i2c_register_board_info(0, db1550_i2c_devs, ARRAY_SIZE(db1550_i2c_devs)); spi_register_board_info(db1550_spi_devs, - ARRAY_SIZE(db1550_i2c_devs)); + ARRAY_SIZE(db1550_spi_devs)); c = clk_get(NULL, "psc0_intclk"); if (!IS_ERR(c)) { diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi index 8143a61111e3..c16b521308cb 100644 --- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi +++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi @@ -123,8 +123,7 @@ compatible = "pci0014,7a03.0", "pci0014,7a03", "pciclass0c0320", - "pciclass0c03", - "loongson, pci-gmac"; + "pciclass0c03"; reg = <0x1800 0x0 0x0 0x0 0x0>; interrupts = <12 IRQ_TYPE_LEVEL_LOW>, diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi index 2f45fce2cdc4..ed99ee316feb 100644 --- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi +++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi @@ -186,8 +186,7 @@ compatible = "pci0014,7a03.0", "pci0014,7a03", "pciclass020000", - "pciclass0200", - "loongson, pci-gmac"; + "pciclass0200"; reg = <0x1800 0x0 0x0 0x0 0x0>; interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h index 4044eaf989ac..0921ddda11a4 100644 --- a/arch/mips/include/asm/checksum.h +++ b/arch/mips/include/asm/checksum.h @@ -241,7 +241,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " .set pop" : "=&r" (sum), "=&r" (tmp) : "r" (saddr), "r" (daddr), - "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)); + "0" (htonl(len)), "r" (htonl(proto)), "r" (sum) + : "memory"); return csum_fold(sum); } diff --git a/arch/mips/include/asm/dmi.h b/arch/mips/include/asm/dmi.h index 27415a288adf..dc397f630c66 100644 --- a/arch/mips/include/asm/dmi.h +++ b/arch/mips/include/asm/dmi.h @@ -5,7 +5,7 @@ #include <linux/io.h> #include <linux/memblock.h> -#define dmi_early_remap(x, l) ioremap_cache(x, l) +#define dmi_early_remap(x, l) ioremap(x, l) #define dmi_early_unmap(x, l) iounmap(x) #define dmi_remap(x, l) ioremap_cache(x, l) #define dmi_unmap(x) iounmap(x) diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h index c5c6864e64bc..405c85173f2c 100644 --- a/arch/mips/include/asm/jump_label.h +++ b/arch/mips/include/asm/jump_label.h @@ -36,7 +36,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\t" B_INSN " 2f\n\t" + asm goto("1:\t" B_INSN " 2f\n\t" "2:\t.insn\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" @@ -50,7 +50,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t" + asm goto("1:\t" J_INSN " %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" ".popsection\n\t" diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index 5582a4ca1e9e..7aa2c2360ff6 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -11,6 +11,7 @@ #include <asm/cpu-features.h> #include <asm/cpu-info.h> +#include <asm/fpu.h> #ifdef CONFIG_MIPS_FP_SUPPORT @@ -309,6 +310,11 @@ void mips_set_personality_nan(struct arch_elf_state *state) struct cpuinfo_mips *c = &boot_cpu_data; struct task_struct *t = current; + /* Do this early so t->thread.fpu.fcr31 won't be clobbered in case + * we are preempted before the lose_fpu(0) in start_thread. + */ + lose_fpu(0); + t->thread.fpu.fcr31 = c->fpu_csr31; switch (state->nan_2008) { case 0: diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 7c540572f1f7..e46e7ec76b4f 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -326,11 +326,11 @@ static void __init bootmem_init(void) panic("Incorrect memory mapping !!!"); if (max_pfn > PFN_DOWN(HIGHMEM_START)) { + max_low_pfn = PFN_DOWN(HIGHMEM_START); #ifdef CONFIG_HIGHMEM - highstart_pfn = PFN_DOWN(HIGHMEM_START); + highstart_pfn = max_low_pfn; highend_pfn = max_pfn; #else - max_low_pfn = PFN_DOWN(HIGHMEM_START); max_pfn = max_low_pfn; #endif } diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 1d93b85271ba..002c91fcb842 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -333,10 +333,11 @@ early_initcall(mips_smp_ipi_init); */ asmlinkage void start_secondary(void) { - unsigned int cpu; + unsigned int cpu = raw_smp_processor_id(); cpu_probe(); per_cpu_trap_init(false); + rcu_cpu_starting(cpu); mips_clockevent_init(); mp_ops->init_secondary(); cpu_report(); @@ -348,7 +349,6 @@ asmlinkage void start_secondary(void) */ calibrate_delay(); - cpu = smp_processor_id(); cpu_data[cpu].udelay_val = loops_per_jiffy; set_cpu_sibling_map(cpu); diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 246c6a6b0261..5b778995d448 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -2007,7 +2007,13 @@ unsigned long vi_handlers[64]; void reserve_exception_space(phys_addr_t addr, unsigned long size) { - memblock_reserve(addr, size); + /* + * reserve exception space on CPUs other than CPU0 + * is too late, since memblock is unavailable when APs + * up + */ + if (smp_processor_id() == 0) + memblock_reserve(addr, size); } void __init *set_except_vector(int n, void *addr) diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c index be4829cc7a3a..28da4e720d17 100644 --- a/arch/mips/lantiq/prom.c +++ b/arch/mips/lantiq/prom.c @@ -114,10 +114,9 @@ void __init prom_init(void) prom_init_cmdline(); #if defined(CONFIG_MIPS_MT_SMP) - if (cpu_has_mipsmt) { - lantiq_smp_ops = vsmp_smp_ops; + lantiq_smp_ops = vsmp_smp_ops; + if (cpu_has_mipsmt) lantiq_smp_ops.init_secondary = lantiq_init_secondary; - register_smp_ops(&lantiq_smp_ops); - } + register_smp_ops(&lantiq_smp_ops); #endif } diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 5a8002839550..e8660d06f663 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -417,7 +417,12 @@ void __init paging_init(void) (highend_pfn - max_low_pfn) << (PAGE_SHIFT - 10)); max_zone_pfns[ZONE_HIGHMEM] = max_low_pfn; } + + max_mapnr = highend_pfn ? highend_pfn : max_low_pfn; +#else + max_mapnr = max_low_pfn; #endif + high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); free_area_init(max_zone_pfns); } @@ -453,13 +458,6 @@ void __init mem_init(void) */ BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (_PFN_SHIFT > PAGE_SHIFT)); -#ifdef CONFIG_HIGHMEM - max_mapnr = highend_pfn ? highend_pfn : max_low_pfn; -#else - max_mapnr = max_low_pfn; -#endif - high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); - maar_init(); memblock_free_all(); setup_zero_pages(); /* Setup zeroed pages. */ diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 345d5e021484..abf39ecda6fb 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -24,7 +24,6 @@ config PARISC select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE select BUG - select BUILDTIME_TABLE_SORT select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_KERNEL_BZIP2 diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 74d17d7e759d..5937d5edaba1 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -576,6 +576,7 @@ .section __ex_table,"aw" ! \ .align 4 ! \ .word (fault_addr - .), (except_addr - .) ! \ + or %r0,%r0,%r0 ! \ .previous diff --git a/arch/parisc/include/asm/extable.h b/arch/parisc/include/asm/extable.h new file mode 100644 index 000000000000..4ea23e3d79dc --- /dev/null +++ b/arch/parisc/include/asm/extable.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PARISC_EXTABLE_H +#define __PARISC_EXTABLE_H + +#include <asm/ptrace.h> +#include <linux/compiler.h> + +/* + * The exception table consists of three addresses: + * + * - A relative address to the instruction that is allowed to fault. + * - A relative address at which the program should continue (fixup routine) + * - An asm statement which specifies which CPU register will + * receive -EFAULT when an exception happens if the lowest bit in + * the fixup address is set. + * + * Note: The register specified in the err_opcode instruction will be + * modified at runtime if a fault happens. Register %r0 will be ignored. + * + * Since relative addresses are used, 32bit values are sufficient even on + * 64bit kernel. + */ + +struct pt_regs; +int fixup_exception(struct pt_regs *regs); + +#define ARCH_HAS_RELATIVE_EXTABLE +struct exception_table_entry { + int insn; /* relative address of insn that is allowed to fault. */ + int fixup; /* relative address of fixup routine */ + int err_opcode; /* sample opcode with register which holds error code */ +}; + +#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr, opcode )\ + ".section __ex_table,\"aw\"\n" \ + ".align 4\n" \ + ".word (" #fault_addr " - .), (" #except_addr " - .)\n" \ + opcode "\n" \ + ".previous\n" + +/* + * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry + * (with lowest bit set) for which the fault handler in fixup_exception() will + * load -EFAULT on fault into the register specified by the err_opcode instruction, + * and zeroes the target register in case of a read fault in get_user(). + */ +#define ASM_EXCEPTIONTABLE_VAR(__err_var) \ + int __err_var = 0 +#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr, register )\ + ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1, "or %%r0,%%r0," register) + +static inline void swap_ex_entry_fixup(struct exception_table_entry *a, + struct exception_table_entry *b, + struct exception_table_entry tmp, + int delta) +{ + a->fixup = b->fixup + delta; + b->fixup = tmp.fixup - delta; + a->err_opcode = b->err_opcode; + b->err_opcode = tmp.err_opcode; +} +#define swap_ex_entry_fixup swap_ex_entry_fixup + +#endif diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h index 94428798b6aa..317ebc5edc9f 100644 --- a/arch/parisc/include/asm/jump_label.h +++ b/arch/parisc/include/asm/jump_label.h @@ -12,7 +12,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align %1\n\t" @@ -29,7 +29,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b,n %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align %1\n\t" diff --git a/arch/parisc/include/asm/special_insns.h b/arch/parisc/include/asm/special_insns.h index c822bd0c0e3c..51f40eaf7780 100644 --- a/arch/parisc/include/asm/special_insns.h +++ b/arch/parisc/include/asm/special_insns.h @@ -8,7 +8,8 @@ "copy %%r0,%0\n" \ "8:\tlpa %%r0(%1),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY(8b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY(8b, 9b, \ + "or %%r0,%%r0,%%r0") \ : "=&r" (pa) \ : "r" (va) \ : "memory" \ @@ -22,7 +23,8 @@ "copy %%r0,%0\n" \ "8:\tlpa %%r0(%%sr3,%1),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY(8b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY(8b, 9b, \ + "or %%r0,%%r0,%%r0") \ : "=&r" (pa) \ : "r" (va) \ : "memory" \ diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 4165079898d9..88d0ae5769dd 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -7,6 +7,7 @@ */ #include <asm/page.h> #include <asm/cache.h> +#include <asm/extable.h> #include <linux/bug.h> #include <linux/string.h> @@ -26,37 +27,6 @@ #define STD_USER(sr, x, ptr) __put_user_asm(sr, "std", x, ptr) #endif -/* - * The exception table contains two values: the first is the relative offset to - * the address of the instruction that is allowed to fault, and the second is - * the relative offset to the address of the fixup routine. Since relative - * addresses are used, 32bit values are sufficient even on 64bit kernel. - */ - -#define ARCH_HAS_RELATIVE_EXTABLE -struct exception_table_entry { - int insn; /* relative address of insn that is allowed to fault. */ - int fixup; /* relative address of fixup routine */ -}; - -#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\ - ".section __ex_table,\"aw\"\n" \ - ".align 4\n" \ - ".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \ - ".previous\n" - -/* - * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry - * (with lowest bit set) for which the fault handler in fixup_exception() will - * load -EFAULT into %r29 for a read or write fault, and zeroes the target - * register in case of a read fault in get_user(). - */ -#define ASM_EXCEPTIONTABLE_REG 29 -#define ASM_EXCEPTIONTABLE_VAR(__variable) \ - register long __variable __asm__ ("r29") = 0 -#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\ - ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1) - #define __get_user_internal(sr, val, ptr) \ ({ \ ASM_EXCEPTIONTABLE_VAR(__gu_err); \ @@ -83,7 +53,7 @@ struct exception_table_entry { \ __asm__("1: " ldx " 0(%%sr%2,%3),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1") \ : "=r"(__gu_val), "+r"(__gu_err) \ : "i"(sr), "r"(ptr)); \ \ @@ -115,8 +85,8 @@ struct exception_table_entry { "1: ldw 0(%%sr%2,%3),%0\n" \ "2: ldw 4(%%sr%2,%3),%R0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1") \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%1") \ : "=&r"(__gu_tmp.l), "+r"(__gu_err) \ : "i"(sr), "r"(ptr)); \ \ @@ -174,7 +144,7 @@ struct exception_table_entry { __asm__ __volatile__ ( \ "1: " stx " %1,0(%%sr%2,%3)\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0") \ : "+r"(__pu_err) \ : "r"(x), "i"(sr), "r"(ptr)) @@ -186,15 +156,14 @@ struct exception_table_entry { "1: stw %1,0(%%sr%2,%3)\n" \ "2: stw %R1,4(%%sr%2,%3)\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0") \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%0") \ : "+r"(__pu_err) \ : "r"(__val), "i"(sr), "r"(ptr)); \ } while (0) #endif /* !defined(CONFIG_64BIT) */ - /* * Complex access routines -- external declarations */ @@ -216,7 +185,4 @@ unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src, #define INLINE_COPY_TO_USER #define INLINE_COPY_FROM_USER -struct pt_regs; -int fixup_exception(struct pt_regs *regs); - #endif /* __PARISC_UACCESS_H */ diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index 8f12b9f318ae..a582928739dd 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -1003,6 +1003,9 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data) pr_info("\n"); + /* Prevent hung task messages when printing on serial console */ + cond_resched(); + pr_info("#define HPA_%08lx_DESCRIPTION \"%s\"\n", hpa, parisc_hardware_description(&dev->id)); diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 3e051a973e9b..92276bcf19d7 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -123,10 +123,10 @@ static unsigned long f_extend(unsigned long address) #ifdef CONFIG_64BIT if(unlikely(parisc_narrow_firmware)) { if((address & 0xff000000) == 0xf0000000) - return 0xf0f0f0f000000000UL | (u32)address; + return (0xfffffff0UL << 32) | (u32)address; if((address & 0xf0000000) == 0xf0000000) - return 0xffffffff00000000UL | (u32)address; + return (0xffffffffUL << 32) | (u32)address; } #endif return address; diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 1f6c776d8081..c67883487ecd 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -171,7 +171,6 @@ static int __init processor_probe(struct parisc_device *dev) p->cpu_num = cpu_info.cpu_num; p->cpu_loc = cpu_info.cpu_loc; - set_cpu_possible(cpuid, true); store_cpu_topology(cpuid); #ifdef CONFIG_SMP @@ -466,13 +465,6 @@ static struct parisc_driver cpu_driver __refdata = { */ void __init processor_init(void) { - unsigned int cpu; - reset_cpu_topology(); - - /* reset possible mask. We will mark those which are possible. */ - for_each_possible_cpu(cpu) - set_cpu_possible(cpu, false); - register_parisc_driver(&cpu_driver); } diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index e8a4d77cff53..8a8e7d7224a2 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -118,8 +118,8 @@ static int emulate_ldh(struct pt_regs *regs, int toreg) "2: ldbs 1(%%sr1,%3), %0\n" " depw %2, 23, 24, %0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") : "+r" (val), "+r" (ret), "=&r" (temp1) : "r" (saddr), "r" (regs->isr) ); @@ -150,8 +150,8 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop) " mtctl %2,11\n" " vshd %0,%3,%0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") : "+r" (val), "+r" (ret), "=&r" (temp1), "=&r" (temp2) : "r" (saddr), "r" (regs->isr) ); @@ -187,8 +187,8 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) " mtsar %%r19\n" " shrpd %0,%%r20,%%sar,%0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") : "=r" (val), "+r" (ret) : "0" (val), "r" (saddr), "r" (regs->isr) : "r19", "r20" ); @@ -207,9 +207,9 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) " vshd %0,%R0,%0\n" " vshd %R0,%4,%R0\n" "4: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b, "%1") : "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1) : "r" (regs->isr) ); } @@ -242,8 +242,8 @@ static int emulate_sth(struct pt_regs *regs, int frreg) "1: stb %1, 0(%%sr1, %3)\n" "2: stb %2, 1(%%sr1, %3)\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0") : "+r" (ret), "=&r" (temp1) : "r" (val), "r" (regs->ior), "r" (regs->isr) ); @@ -283,8 +283,8 @@ static int emulate_stw(struct pt_regs *regs, int frreg, int flop) " stw %%r20,0(%%sr1,%2)\n" " stw %%r21,4(%%sr1,%2)\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0") : "+r" (ret) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r22", "r1" ); @@ -327,10 +327,10 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) "3: std %%r20,0(%%sr1,%2)\n" "4: std %%r21,8(%%sr1,%2)\n" "5: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b, "%0") : "+r" (ret) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r22", "r1" ); @@ -356,11 +356,11 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) "4: stw %%r1,4(%%sr1,%3)\n" "5: stw %2,8(%%sr1,%3)\n" "6: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b, "%0") : "+r" (ret) : "r" (valh), "r" (vall), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r1" ); diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index b00aa98b582c..fbd9ada5e527 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -150,11 +150,16 @@ int fixup_exception(struct pt_regs *regs) * Fix up get_user() and put_user(). * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant * bit in the relative address of the fixup routine to indicate - * that gr[ASM_EXCEPTIONTABLE_REG] should be loaded with - * -EFAULT to report a userspace access error. + * that the register encoded in the "or %r0,%r0,register" + * opcode should be loaded with -EFAULT to report a userspace + * access error. */ if (fix->fixup & 1) { - regs->gr[ASM_EXCEPTIONTABLE_REG] = -EFAULT; + int fault_error_reg = fix->err_opcode & 0x1f; + if (!WARN_ON(!fault_error_reg)) + regs->gr[fault_error_reg] = -EFAULT; + pr_debug("Unalignment fixup of register %d at %pS\n", + fault_error_reg, (void*)regs->iaoq[0]); /* zero target register for get_user() */ if (parisc_acctyp(0, regs->iir) == VM_READ) { diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 98001784c46c..3d11bfa40b3b 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -42,18 +42,13 @@ machine-$(CONFIG_PPC64) += 64 machine-$(CONFIG_CPU_LITTLE_ENDIAN) += le UTS_MACHINE := $(subst $(space),,$(machine-y)) -# XXX This needs to be before we override LD below -ifdef CONFIG_PPC32 -KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o -else -ifeq ($(call ld-ifversion, -ge, 22500, y),y) +ifeq ($(CONFIG_PPC64)$(CONFIG_LD_IS_BFD),yy) # Have the linker provide sfpr if possible. # There is a corresponding test in arch/powerpc/lib/Makefile KBUILD_LDFLAGS_MODULE += --save-restore-funcs else KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o endif -endif ifdef CONFIG_CPU_LITTLE_ENDIAN KBUILD_CFLAGS += -mlittle-endian @@ -381,17 +376,7 @@ endif endif PHONY += checkbin -# Check toolchain versions: -# - gcc-4.6 is the minimum kernel-wide version so nothing required. checkbin: - @if test "x${CONFIG_LD_IS_LLD}" != "xy" -a \ - "x$(call ld-ifversion, -le, 22400, y)" = "xy" ; then \ - echo -n '*** binutils 2.24 miscompiles weak symbols ' ; \ - echo 'in some circumstances.' ; \ - echo '*** binutils 2.23 do not define the TOC symbol ' ; \ - echo -n '*** Please use a different binutils version.' ; \ - false ; \ - fi @if test "x${CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT}" = "xy" -a \ "x${CONFIG_LD_IS_BFD}" = "xy" -a \ "${CONFIG_LD_VERSION}" = "23700" ; then \ diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index 61a4736355c2..20d5052e2292 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -74,7 +74,7 @@ ##__VA_ARGS__) #define WARN_ENTRY(insn, flags, label, ...) \ - asm_volatile_goto( \ + asm goto( \ "1: " insn "\n" \ EX_TABLE(1b, %l[label]) \ _EMIT_BUG_ENTRY \ diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h index b8b0be8f1a07..c6d3078bd8c3 100644 --- a/arch/powerpc/include/asm/irq_work.h +++ b/arch/powerpc/include/asm/irq_work.h @@ -6,6 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void) { return true; } -extern void arch_irq_work_raise(void); #endif /* _ASM_POWERPC_IRQ_WORK_H */ diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 93ce3ec25387..2f2a86ed2280 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop # arch_static_branch\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" @@ -32,7 +32,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes] # arch_static_branch_jump\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 94b981152667..07fabb054aea 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -417,5 +417,9 @@ extern void *abatron_pteptrs[2]; #include <asm/nohash/mmu.h> #endif +#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) +#define __HAVE_ARCH_RESERVED_KERNEL_PAGES +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MMU_H_ */ diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 4c6c6dbd182f..da827d2d0866 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -42,14 +42,6 @@ u64 memory_hotplug_max(void); #else #define memory_hotplug_max() memblock_end_of_DRAM() #endif /* CONFIG_NUMA */ -#ifdef CONFIG_FA_DUMP -#define __HAVE_ARCH_RESERVED_KERNEL_PAGES -#endif - -#ifdef CONFIG_MEMORY_HOTPLUG -extern int create_section_mapping(unsigned long start, unsigned long end, - int nid, pgprot_t prot); -#endif #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index af58f1ed3952..c4b798aa6ce8 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -14,7 +14,7 @@ #ifdef __KERNEL__ -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15 #define MIN_THREAD_SHIFT (CONFIG_THREAD_SHIFT + 1) #else #define MIN_THREAD_SHIFT CONFIG_THREAD_SHIFT diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 3ddc65c63a49..45d4c9cf3f3a 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -72,7 +72,7 @@ __pu_failed: \ * are no aliasing issues. */ #define __put_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -85,7 +85,7 @@ __pu_failed: \ __put_user_asm_goto(x, ptr, label, "std") #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm goto( \ "1: stw%X1 %0, %1\n" \ "2: stw%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ @@ -132,7 +132,7 @@ do { \ #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: "op"%U1%X1 %0, %1 # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ @@ -145,7 +145,7 @@ do { \ __get_user_asm_goto(x, addr, label, "ld") #else /* __powerpc64__ */ #define __get_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: lwz%X1 %0, %1\n" \ "2: lwz%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h index ceb06b109f83..2ae8e9a7b461 100644 --- a/arch/powerpc/kernel/cpu_specs_e500mc.h +++ b/arch/powerpc/kernel/cpu_specs_e500mc.h @@ -8,7 +8,8 @@ #ifdef CONFIG_PPC64 #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ - PPC_FEATURE_HAS_FPU | PPC_FEATURE_64) + PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \ + PPC_FEATURE_BOOKE) #else #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ PPC_FEATURE_BOOKE) diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index a019ed6fc839..26c151e2a794 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) - std r11,_NIP(r1) + std r11,_LINK(r1) + std r11,_NIP(r1) /* Saved LR is also the next instruction */ std r12,_MSR(r1) std r0,GPR0(r1) std r10,GPR1(r1) @@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) std r9,GPR13(r1) SAVE_NVGPRS(r1) std r11,_XER(r1) - std r11,_LINK(r1) std r11,_CTR(r1) li r11,\trapnr diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c index 9dc0ad3c533a..5a6e44e4d36f 100644 --- a/arch/powerpc/kernel/irq_64.c +++ b/arch/powerpc/kernel/irq_64.c @@ -230,7 +230,7 @@ again: * This allows interrupts to be unmasked without hard disabling, and * also without new hard interrupts coming in ahead of pending ones. */ - asm_volatile_goto( + asm goto( "1: \n" " lbz 9,%0(13) \n" " cmpwi 9,0 \n" diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 3956f32682c6..362b712386f6 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1439,10 +1439,12 @@ static int emulate_instruction(struct pt_regs *regs) return -EINVAL; } +#ifdef CONFIG_GENERIC_BUG int is_valid_bugaddr(unsigned long addr) { return is_kernel_addr(addr); } +#endif #ifdef CONFIG_MATH_EMULATION static int emulate_math(struct pt_regs *regs) diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 8560c912186d..9b394bab17eb 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -42,8 +42,8 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o # 64-bit linker creates .sfpr on demand for final link (vmlinux), # so it is only needed for modules, and only for older linkers which # do not support --save-restore-funcs -ifeq ($(call ld-ifversion, -lt, 22500, y),y) -extra-$(CONFIG_PPC64) += crtsavres.o +ifndef CONFIG_LD_IS_BFD +always-$(CONFIG_PPC64) += crtsavres.o endif obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \ diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 398b5694aeb7..ec30af8eadb7 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -586,6 +586,8 @@ static int do_fp_load(struct instruction_op *op, unsigned long ea, } u; nb = GETSIZE(op->type); + if (nb > sizeof(u)) + return -EINVAL; if (!address_ok(regs, ea, nb)) return -EFAULT; rn = op->reg; @@ -636,6 +638,8 @@ static int do_fp_store(struct instruction_op *op, unsigned long ea, } u; nb = GETSIZE(op->type); + if (nb > sizeof(u)) + return -EINVAL; if (!address_ok(regs, ea, nb)) return -EFAULT; rn = op->reg; @@ -680,6 +684,9 @@ static nokprobe_inline int do_vec_load(int rn, unsigned long ea, u8 b[sizeof(__vector128)]; } u = {}; + if (size > sizeof(u)) + return -EINVAL; + if (!address_ok(regs, ea & ~0xfUL, 16)) return -EFAULT; /* align to multiple of size */ @@ -707,6 +714,9 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea, u8 b[sizeof(__vector128)]; } u; + if (size > sizeof(u)) + return -EINVAL; + if (!address_ok(regs, ea & ~0xfUL, 16)) return -EFAULT; /* align to multiple of size */ diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index f6151a589298..87aa76c73799 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -463,6 +463,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, set_pte_at(vma->vm_mm, addr, ptep, pte); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * For hash translation mode, we use the deposited table to store hash slot * information and they are stored at PTRS_PER_PMD offset from related pmd @@ -484,6 +485,7 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, return true; } +#endif /* * Does the CPU support tlbie? diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index 119ef491f797..d3a7726ecf51 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -126,7 +126,7 @@ void pgtable_cache_add(unsigned int shift) * as to leave enough 0 bits in the address to contain it. */ unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1, HUGEPD_SHIFT_MASK + 1); - struct kmem_cache *new; + struct kmem_cache *new = NULL; /* It would be nice if this was a BUILD_BUG_ON(), but at the * moment, gcc doesn't seem to recognize is_power_of_2 as a @@ -139,7 +139,8 @@ void pgtable_cache_add(unsigned int shift) align = max_t(unsigned long, align, minalign); name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift); - new = kmem_cache_create(name, table_size, align, 0, ctor(shift)); + if (name) + new = kmem_cache_create(name, table_size, align, 0, ctor(shift)); if (!new) panic("Could not allocate pgtable cache for order %d", shift); diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c index a70828a6d935..aa9aa11927b2 100644 --- a/arch/powerpc/mm/kasan/init_32.c +++ b/arch/powerpc/mm/kasan/init_32.c @@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size) if (ret) return ret; + k_start = k_start & PAGE_MASK; block = memblock_alloc(k_end - k_start, PAGE_SIZE); if (!block) return -ENOMEM; diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index bd9784f77f2e..71250605b784 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -179,3 +179,8 @@ static inline bool debug_pagealloc_enabled_or_kfence(void) { return IS_ENABLED(CONFIG_KFENCE) || debug_pagealloc_enabled(); } + +#ifdef CONFIG_MEMORY_HOTPLUG +int create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); +#endif diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index ada817c49b72..56d82f7f9734 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -299,6 +299,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu) attr_group->attrs = attrs; do { ev_val_str = kasprintf(GFP_KERNEL, "event=0x%x", pmu->events[i].value); + if (!ev_val_str) + continue; dev_str = device_str_attr_create(pmu->events[i].name, ev_val_str); if (!dev_str) continue; @@ -306,6 +308,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu) attrs[j++] = dev_str; if (pmu->events[i].scale) { ev_scale_str = kasprintf(GFP_KERNEL, "%s.scale", pmu->events[i].name); + if (!ev_scale_str) + continue; dev_str = device_str_attr_create(ev_scale_str, pmu->events[i].scale); if (!dev_str) continue; @@ -315,6 +319,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu) if (pmu->events[i].unit) { ev_unit_str = kasprintf(GFP_KERNEL, "%s.unit", pmu->events[i].name); + if (!ev_unit_str) + continue; dev_str = device_str_attr_create(ev_unit_str, pmu->events[i].unit); if (!dev_str) continue; diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index 25b80cd558f8..fc79f8466933 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -173,6 +173,7 @@ config ISS4xx config CURRITUCK bool "IBM Currituck (476fpe) Support" depends on PPC_47x + select I2C select SWIOTLB select 476FPE select FORCE_PCI diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index d55652b5f6fa..391f50535200 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -275,6 +275,8 @@ int __init opal_event_init(void) else name = kasprintf(GFP_KERNEL, "opal"); + if (!name) + continue; /* Install interrupt handler */ rc = request_irq(r->start, opal_interrupt, r->flags & IRQD_TRIGGER_MASK, name, NULL); diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c index 7bfe4cbeb35a..ea917266aa17 100644 --- a/arch/powerpc/platforms/powernv/opal-powercap.c +++ b/arch/powerpc/platforms/powernv/opal-powercap.c @@ -196,6 +196,12 @@ void __init opal_powercap_init(void) j = 0; pcaps[i].pg.name = kasprintf(GFP_KERNEL, "%pOFn", node); + if (!pcaps[i].pg.name) { + kfree(pcaps[i].pattrs); + kfree(pcaps[i].pg.attrs); + goto out_pcaps_pattrs; + } + if (has_min) { powercap_add_attr(min, "powercap-min", &pcaps[i].pattrs[j]); diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 6b4eed2ef4fa..f67235d1ba2c 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -165,6 +165,11 @@ static int scom_debug_init_one(struct dentry *root, struct device_node *dn, ent->chip = chip; snprintf(ent->name, 16, "%08x", chip); ent->path.data = (void *)kasprintf(GFP_KERNEL, "%pOF", dn); + if (!ent->path.data) { + kfree(ent); + return -ENOMEM; + } + ent->path.size = strlen((char *)ent->path.data); dir = debugfs_create_dir(ent->name, root); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2e3a317722a8..051a777ba1b2 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -500,14 +500,15 @@ static int dlpar_memory_remove_by_index(u32 drc_index) } } - if (!lmb_found) + if (!lmb_found) { + pr_debug("Failed to look up LMB for drc index %x\n", drc_index); rc = -EINVAL; - - if (rc) + } else if (rc) { pr_debug("Failed to hot-remove memory at %llx\n", lmb->base_addr); - else + } else { pr_debug("Memory at %llx was hot-removed\n", lmb->base_addr); + } return rc; } diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 541199c6a587..5186d65d772e 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -660,8 +660,12 @@ u64 pseries_paravirt_steal_clock(int cpu) { struct lppaca *lppaca = &lppaca_of(cpu); - return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + - be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)); + /* + * VPA steal time counters are reported at TB frequency. Hence do a + * conversion to ns before returning + */ + return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + + be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb))); } #endif diff --git a/arch/riscv/include/asm/irq_work.h b/arch/riscv/include/asm/irq_work.h index b53891964ae0..b27a4d64fc6a 100644 --- a/arch/riscv/include/asm/irq_work.h +++ b/arch/riscv/include/asm/irq_work.h @@ -6,5 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void) { return IS_ENABLED(CONFIG_SMP); } -extern void arch_irq_work_raise(void); + #endif /* _ASM_RISCV_IRQ_WORK_H */ diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h index 14a5ea8d8ef0..4a35d787c019 100644 --- a/arch/riscv/include/asm/jump_label.h +++ b/arch/riscv/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" @@ -39,7 +39,7 @@ label: static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h index 32336e8a17cb..a393d5035c54 100644 --- a/arch/riscv/include/asm/sections.h +++ b/arch/riscv/include/asm/sections.h @@ -13,6 +13,7 @@ extern char _start_kernel[]; extern char __init_data_begin[], __init_data_end[]; extern char __init_text_begin[], __init_text_end[]; extern char __alt_start[], __alt_end[]; +extern char __exittext_begin[], __exittext_end[]; static inline bool is_va_kernel_text(uintptr_t va) { diff --git a/arch/riscv/include/asm/signal.h b/arch/riscv/include/asm/signal.h index 532c29ef0376..956ae0a01bad 100644 --- a/arch/riscv/include/asm/signal.h +++ b/arch/riscv/include/asm/signal.h @@ -7,6 +7,6 @@ #include <uapi/asm/ptrace.h> asmlinkage __visible -void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags); +void do_work_pending(struct pt_regs *regs, unsigned long thread_info_flags); #endif diff --git a/arch/riscv/include/asm/xip_fixup.h b/arch/riscv/include/asm/xip_fixup.h index d4ffc3c37649..b65bf6306f69 100644 --- a/arch/riscv/include/asm/xip_fixup.h +++ b/arch/riscv/include/asm/xip_fixup.h @@ -13,7 +13,7 @@ add \reg, \reg, t0 .endm .macro XIP_FIXUP_FLASH_OFFSET reg - la t1, __data_loc + la t0, __data_loc REG_L t1, _xip_phys_offset sub \reg, \reg, t1 add \reg, \reg, t0 diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 91fe16bfaa07..a331001e33e6 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -424,7 +424,8 @@ void *module_alloc(unsigned long size) { return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL, - PAGE_KERNEL, 0, NUMA_NO_NODE, + PAGE_KERNEL, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __builtin_return_address(0)); } #endif diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index e099961453cc..160e5c1caa9c 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -13,6 +13,7 @@ #include <asm/fixmap.h> #include <asm/ftrace.h> #include <asm/patch.h> +#include <asm/sections.h> struct patch_insn { void *addr; @@ -23,6 +24,14 @@ struct patch_insn { int riscv_patch_in_stop_machine = false; #ifdef CONFIG_MMU + +static inline bool is_kernel_exittext(uintptr_t addr) +{ + return system_state < SYSTEM_RUNNING && + addr >= (uintptr_t)__exittext_begin && + addr < (uintptr_t)__exittext_end; +} + /* * The fix_to_virt(, idx) needs a const value (not a dynamic variable of * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses". @@ -33,7 +42,7 @@ static __always_inline void *patch_map(void *addr, const unsigned int fixmap) uintptr_t uintaddr = (uintptr_t) addr; struct page *page; - if (core_kernel_text(uintaddr)) + if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr)) page = phys_to_page(__pa_symbol(addr)); else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) page = vmalloc_to_page(addr); diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S index 75e0fa8a700a..24a2fdd3be6a 100644 --- a/arch/riscv/kernel/vmlinux-xip.lds.S +++ b/arch/riscv/kernel/vmlinux-xip.lds.S @@ -29,10 +29,12 @@ SECTIONS HEAD_TEXT_SECTION INIT_TEXT_SECTION(PAGE_SIZE) /* we have to discard exit text and such at runtime, not link time */ + __exittext_begin = .; .exit.text : { EXIT_TEXT } + __exittext_end = .; .text : { _text = .; diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 4e6c88aa4d87..d478e063b878 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -72,10 +72,12 @@ SECTIONS __soc_builtin_dtb_table_end = .; } /* we have to discard exit text and such at runtime, not link time */ + __exittext_begin = .; .exit.text : { EXIT_TEXT } + __exittext_end = .; __init_text_end = .; . = ALIGN(SECTION_ALIGN); diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index ea3d61de065b..9587e4487415 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -5,6 +5,7 @@ #include <linux/pagewalk.h> #include <linux/pgtable.h> +#include <linux/vmalloc.h> #include <asm/tlbflush.h> #include <asm/bitops.h> #include <asm/set_memory.h> @@ -25,19 +26,6 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk) return new_val; } -static int pageattr_pgd_entry(pgd_t *pgd, unsigned long addr, - unsigned long next, struct mm_walk *walk) -{ - pgd_t val = READ_ONCE(*pgd); - - if (pgd_leaf(val)) { - val = __pgd(set_pageattr_masks(pgd_val(val), walk)); - set_pgd(pgd, val); - } - - return 0; -} - static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr, unsigned long next, struct mm_walk *walk) { @@ -96,7 +84,6 @@ static int pageattr_pte_hole(unsigned long addr, unsigned long next, } static const struct mm_walk_ops pageattr_ops = { - .pgd_entry = pageattr_pgd_entry, .p4d_entry = pageattr_p4d_entry, .pud_entry = pageattr_pud_entry, .pmd_entry = pageattr_pmd_entry, @@ -104,12 +91,181 @@ static const struct mm_walk_ops pageattr_ops = { .pte_hole = pageattr_pte_hole, }; +#ifdef CONFIG_64BIT +static int __split_linear_mapping_pmd(pud_t *pudp, + unsigned long vaddr, unsigned long end) +{ + pmd_t *pmdp; + unsigned long next; + + pmdp = pmd_offset(pudp, vaddr); + + do { + next = pmd_addr_end(vaddr, end); + + if (next - vaddr >= PMD_SIZE && + vaddr <= (vaddr & PMD_MASK) && end >= next) + continue; + + if (pmd_leaf(*pmdp)) { + struct page *pte_page; + unsigned long pfn = _pmd_pfn(*pmdp); + pgprot_t prot = __pgprot(pmd_val(*pmdp) & ~_PAGE_PFN_MASK); + pte_t *ptep_new; + int i; + + pte_page = alloc_page(GFP_KERNEL); + if (!pte_page) + return -ENOMEM; + + ptep_new = (pte_t *)page_address(pte_page); + for (i = 0; i < PTRS_PER_PTE; ++i, ++ptep_new) + set_pte(ptep_new, pfn_pte(pfn + i, prot)); + + smp_wmb(); + + set_pmd(pmdp, pfn_pmd(page_to_pfn(pte_page), PAGE_TABLE)); + } + } while (pmdp++, vaddr = next, vaddr != end); + + return 0; +} + +static int __split_linear_mapping_pud(p4d_t *p4dp, + unsigned long vaddr, unsigned long end) +{ + pud_t *pudp; + unsigned long next; + int ret; + + pudp = pud_offset(p4dp, vaddr); + + do { + next = pud_addr_end(vaddr, end); + + if (next - vaddr >= PUD_SIZE && + vaddr <= (vaddr & PUD_MASK) && end >= next) + continue; + + if (pud_leaf(*pudp)) { + struct page *pmd_page; + unsigned long pfn = _pud_pfn(*pudp); + pgprot_t prot = __pgprot(pud_val(*pudp) & ~_PAGE_PFN_MASK); + pmd_t *pmdp_new; + int i; + + pmd_page = alloc_page(GFP_KERNEL); + if (!pmd_page) + return -ENOMEM; + + pmdp_new = (pmd_t *)page_address(pmd_page); + for (i = 0; i < PTRS_PER_PMD; ++i, ++pmdp_new) + set_pmd(pmdp_new, + pfn_pmd(pfn + ((i * PMD_SIZE) >> PAGE_SHIFT), prot)); + + smp_wmb(); + + set_pud(pudp, pfn_pud(page_to_pfn(pmd_page), PAGE_TABLE)); + } + + ret = __split_linear_mapping_pmd(pudp, vaddr, next); + if (ret) + return ret; + } while (pudp++, vaddr = next, vaddr != end); + + return 0; +} + +static int __split_linear_mapping_p4d(pgd_t *pgdp, + unsigned long vaddr, unsigned long end) +{ + p4d_t *p4dp; + unsigned long next; + int ret; + + p4dp = p4d_offset(pgdp, vaddr); + + do { + next = p4d_addr_end(vaddr, end); + + /* + * If [vaddr; end] contains [vaddr & P4D_MASK; next], we don't + * need to split, we'll change the protections on the whole P4D. + */ + if (next - vaddr >= P4D_SIZE && + vaddr <= (vaddr & P4D_MASK) && end >= next) + continue; + + if (p4d_leaf(*p4dp)) { + struct page *pud_page; + unsigned long pfn = _p4d_pfn(*p4dp); + pgprot_t prot = __pgprot(p4d_val(*p4dp) & ~_PAGE_PFN_MASK); + pud_t *pudp_new; + int i; + + pud_page = alloc_page(GFP_KERNEL); + if (!pud_page) + return -ENOMEM; + + /* + * Fill the pud level with leaf puds that have the same + * protections as the leaf p4d. + */ + pudp_new = (pud_t *)page_address(pud_page); + for (i = 0; i < PTRS_PER_PUD; ++i, ++pudp_new) + set_pud(pudp_new, + pfn_pud(pfn + ((i * PUD_SIZE) >> PAGE_SHIFT), prot)); + + /* + * Make sure the pud filling is not reordered with the + * p4d store which could result in seeing a partially + * filled pud level. + */ + smp_wmb(); + + set_p4d(p4dp, pfn_p4d(page_to_pfn(pud_page), PAGE_TABLE)); + } + + ret = __split_linear_mapping_pud(p4dp, vaddr, next); + if (ret) + return ret; + } while (p4dp++, vaddr = next, vaddr != end); + + return 0; +} + +static int __split_linear_mapping_pgd(pgd_t *pgdp, + unsigned long vaddr, + unsigned long end) +{ + unsigned long next; + int ret; + + do { + next = pgd_addr_end(vaddr, end); + /* We never use PGD mappings for the linear mapping */ + ret = __split_linear_mapping_p4d(pgdp, vaddr, next); + if (ret) + return ret; + } while (pgdp++, vaddr = next, vaddr != end); + + return 0; +} + +static int split_linear_mapping(unsigned long start, unsigned long end) +{ + return __split_linear_mapping_pgd(pgd_offset_k(start), start, end); +} +#endif /* CONFIG_64BIT */ + static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, pgprot_t clear_mask) { int ret; unsigned long start = addr; unsigned long end = start + PAGE_SIZE * numpages; + unsigned long __maybe_unused lm_start; + unsigned long __maybe_unused lm_end; struct pageattr_masks masks = { .set_mask = set_mask, .clear_mask = clear_mask @@ -119,11 +275,72 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, return 0; mmap_write_lock(&init_mm); + +#ifdef CONFIG_64BIT + /* + * We are about to change the permissions of a kernel mapping, we must + * apply the same changes to its linear mapping alias, which may imply + * splitting a huge mapping. + */ + + if (is_vmalloc_or_module_addr((void *)start)) { + struct vm_struct *area = NULL; + int i, page_start; + + area = find_vm_area((void *)start); + page_start = (start - (unsigned long)area->addr) >> PAGE_SHIFT; + + for (i = page_start; i < page_start + numpages; ++i) { + lm_start = (unsigned long)page_address(area->pages[i]); + lm_end = lm_start + PAGE_SIZE; + + ret = split_linear_mapping(lm_start, lm_end); + if (ret) + goto unlock; + + ret = walk_page_range_novma(&init_mm, lm_start, lm_end, + &pageattr_ops, NULL, &masks); + if (ret) + goto unlock; + } + } else if (is_kernel_mapping(start) || is_linear_mapping(start)) { + if (is_kernel_mapping(start)) { + lm_start = (unsigned long)lm_alias(start); + lm_end = (unsigned long)lm_alias(end); + } else { + lm_start = start; + lm_end = end; + } + + ret = split_linear_mapping(lm_start, lm_end); + if (ret) + goto unlock; + + ret = walk_page_range_novma(&init_mm, lm_start, lm_end, + &pageattr_ops, NULL, &masks); + if (ret) + goto unlock; + } + ret = walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL, &masks); + +unlock: + mmap_write_unlock(&init_mm); + + /* + * We can't use flush_tlb_kernel_range() here as we may have split a + * hugepage that is larger than that, so let's flush everything. + */ + flush_tlb_all(); +#else + ret = walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL, + &masks); + mmap_write_unlock(&init_mm); flush_tlb_kernel_range(start, end); +#endif return ret; } @@ -158,36 +375,14 @@ int set_memory_nx(unsigned long addr, int numpages) int set_direct_map_invalid_noflush(struct page *page) { - int ret; - unsigned long start = (unsigned long)page_address(page); - unsigned long end = start + PAGE_SIZE; - struct pageattr_masks masks = { - .set_mask = __pgprot(0), - .clear_mask = __pgprot(_PAGE_PRESENT) - }; - - mmap_read_lock(&init_mm); - ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); - mmap_read_unlock(&init_mm); - - return ret; + return __set_memory((unsigned long)page_address(page), 1, + __pgprot(0), __pgprot(_PAGE_PRESENT)); } int set_direct_map_default_noflush(struct page *page) { - int ret; - unsigned long start = (unsigned long)page_address(page); - unsigned long end = start + PAGE_SIZE; - struct pageattr_masks masks = { - .set_mask = PAGE_KERNEL, - .clear_mask = __pgprot(0) - }; - - mmap_read_lock(&init_mm); - ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); - mmap_read_unlock(&init_mm); - - return ret; + return __set_memory((unsigned long)page_address(page), 1, + PAGE_KERNEL, __pgprot(_PAGE_EXEC)); } #ifdef CONFIG_DEBUG_PAGEALLOC diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 526c3f40f6a2..7b66e81e5f87 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -601,7 +601,9 @@ static int ctr_aes_crypt(struct skcipher_request *req) * final block may be < AES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { - cpacf_kmctr(sctx->fc, sctx->key, buf, walk.src.virt.addr, + memset(buf, 0, AES_BLOCK_SIZE); + memcpy(buf, walk.src.virt.addr, nbytes); + cpacf_kmctr(sctx->fc, sctx->key, buf, buf, AES_BLOCK_SIZE, walk.iv); memcpy(walk.dst.virt.addr, buf, nbytes); crypto_inc(walk.iv, AES_BLOCK_SIZE); diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 621322eb0e68..d84d87349718 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -688,9 +688,11 @@ static int ctr_paes_crypt(struct skcipher_request *req) * final block may be < AES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { + memset(buf, 0, AES_BLOCK_SIZE); + memcpy(buf, walk.src.virt.addr, nbytes); while (1) { if (cpacf_kmctr(ctx->fc, ¶m, buf, - walk.src.virt.addr, AES_BLOCK_SIZE, + buf, AES_BLOCK_SIZE, walk.iv) == AES_BLOCK_SIZE) break; if (__paes_convert_key(ctx)) diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index b714ed0ef688..9acf48e53a87 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -79,7 +79,7 @@ static inline int test_fp_ctl(u32 fpc) #define KERNEL_VXR_HIGH (KERNEL_VXR_V16V23|KERNEL_VXR_V24V31) #define KERNEL_VXR (KERNEL_VXR_LOW|KERNEL_VXR_HIGH) -#define KERNEL_FPR (KERNEL_FPC|KERNEL_VXR_V0V7) +#define KERNEL_FPR (KERNEL_FPC|KERNEL_VXR_LOW) struct kernel_fpu; diff --git a/arch/s390/include/asm/irq_work.h b/arch/s390/include/asm/irq_work.h index 603783766d0a..f00c9f610d5a 100644 --- a/arch/s390/include/asm/irq_work.h +++ b/arch/s390/include/asm/irq_work.h @@ -7,6 +7,4 @@ static inline bool arch_irq_work_has_interrupt(void) return true; } -void arch_irq_work_raise(void); - #endif /* _ASM_S390_IRQ_WORK_H */ diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 895f774bbcc5..bf78cf381dfc 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -25,7 +25,7 @@ */ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 0,%l[label]\n" + asm goto("0: brcl 0,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" @@ -39,7 +39,7 @@ label: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 15,%l[label]\n" + asm goto("0: brcl 15,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index 287bb88f7698..2686bee800e3 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -11,6 +11,8 @@ /* I/O size constraints */ #define ZPCI_MAX_READ_SIZE 8 #define ZPCI_MAX_WRITE_SIZE 128 +#define ZPCI_BOUNDARY_SIZE (1 << 12) +#define ZPCI_BOUNDARY_MASK (ZPCI_BOUNDARY_SIZE - 1) /* I/O Map */ #define ZPCI_IOMAP_SHIFT 48 @@ -125,16 +127,18 @@ out: int zpci_write_block(volatile void __iomem *dst, const void *src, unsigned long len); -static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max) +static inline int zpci_get_max_io_size(u64 src, u64 dst, int len, int max) { - int count = len > max ? max : len, size = 1; + int offset = dst & ZPCI_BOUNDARY_MASK; + int size; - while (!(src & 0x1) && !(dst & 0x1) && ((size << 1) <= count)) { - dst = dst >> 1; - src = src >> 1; - size = size << 1; - } - return size; + size = min3(len, ZPCI_BOUNDARY_SIZE - offset, max); + if (IS_ALIGNED(src, 8) && IS_ALIGNED(dst, 8) && IS_ALIGNED(size, 8)) + return size; + + if (size >= 8) + return 8; + return rounddown_pow_of_two(size); } static inline int zpci_memcpy_fromio(void *dst, @@ -144,9 +148,9 @@ static inline int zpci_memcpy_fromio(void *dst, int size, rc = 0; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) src, - (u64) dst, n, - ZPCI_MAX_READ_SIZE); + size = zpci_get_max_io_size((u64 __force) src, + (u64) dst, n, + ZPCI_MAX_READ_SIZE); rc = zpci_read_single(dst, src, size); if (rc) break; @@ -166,9 +170,9 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst, return -EINVAL; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) dst, - (u64) src, n, - ZPCI_MAX_WRITE_SIZE); + size = zpci_get_max_io_size((u64 __force) dst, + (u64) src, n, + ZPCI_MAX_WRITE_SIZE); if (size > 8) /* main path */ rc = zpci_write_block(dst, src, size); else diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index f043a7ff220b..28fa80fd69fa 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -2,7 +2,7 @@ /* * Performance event support for s390x - CPU-measurement Counter Facility * - * Copyright IBM Corp. 2012, 2021 + * Copyright IBM Corp. 2012, 2022 * Author(s): Hendrik Brueckner <brueckner@linux.ibm.com> * Thomas Richter <tmricht@linux.ibm.com> */ @@ -434,6 +434,12 @@ static void cpumf_hw_inuse(void) mutex_unlock(&pmc_reserve_mutex); } +static int is_userspace_event(u64 ev) +{ + return cpumf_generic_events_user[PERF_COUNT_HW_CPU_CYCLES] == ev || + cpumf_generic_events_user[PERF_COUNT_HW_INSTRUCTIONS] == ev; +} + static int __hw_perf_event_init(struct perf_event *event, unsigned int type) { struct perf_event_attr *attr = &event->attr; @@ -456,19 +462,26 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) if (is_sampling_event(event)) /* No sampling support */ return -ENOENT; ev = attr->config; - /* Count user space (problem-state) only */ if (!attr->exclude_user && attr->exclude_kernel) { - if (ev >= ARRAY_SIZE(cpumf_generic_events_user)) - return -EOPNOTSUPP; - ev = cpumf_generic_events_user[ev]; - - /* No support for kernel space counters only */ + /* + * Count user space (problem-state) only + * Handle events 32 and 33 as 0:u and 1:u + */ + if (!is_userspace_event(ev)) { + if (ev >= ARRAY_SIZE(cpumf_generic_events_user)) + return -EOPNOTSUPP; + ev = cpumf_generic_events_user[ev]; + } } else if (!attr->exclude_kernel && attr->exclude_user) { + /* No support for kernel space counters only */ return -EOPNOTSUPP; - } else { /* Count user and kernel space */ - if (ev >= ARRAY_SIZE(cpumf_generic_events_basic)) - return -EOPNOTSUPP; - ev = cpumf_generic_events_basic[ev]; + } else { + /* Count user and kernel space, incl. events 32 + 33 */ + if (!is_userspace_event(ev)) { + if (ev >= ARRAY_SIZE(cpumf_generic_events_basic)) + return -EOPNOTSUPP; + ev = cpumf_generic_events_basic[ev]; + } } break; diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 092b16b4dd4f..6b442edb3857 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -385,6 +385,7 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* * floating point control reg. is in the thread structure */ + save_fpu_regs(); if ((unsigned int) data != 0 || test_fp_ctl(data >> (BITS_PER_LONG - 32))) return -EINVAL; @@ -741,6 +742,7 @@ static int __poke_user_compat(struct task_struct *child, /* * floating point control reg. is in the thread structure */ + save_fpu_regs(); if (test_fp_ctl(tmp)) return -EINVAL; child->thread.fpu.fpc = data; @@ -904,9 +906,7 @@ static int s390_fpregs_set(struct task_struct *target, int rc = 0; freg_t fprs[__NUM_FPRS]; - if (target == current) - save_fpu_regs(); - + save_fpu_regs(); if (MACHINE_HAS_VX) convert_vx_to_fp(fprs, target->thread.fpu.vxrs); else diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 3775363471f0..f604946ab2c8 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4138,10 +4138,6 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) vcpu_load(vcpu); - if (test_fp_ctl(fpu->fpc)) { - ret = -EINVAL; - goto out; - } vcpu->run->s.regs.fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs, @@ -4149,7 +4145,6 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) else memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs)); -out: vcpu_put(vcpu); return ret; } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 9a0ce5315f36..3cbb46182066 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -11,6 +11,7 @@ #include <linux/list.h> #include <linux/hugetlb.h> #include <linux/slab.h> +#include <asm/page-states.h> #include <asm/cacheflush.h> #include <asm/nospec-branch.h> #include <asm/pgalloc.h> @@ -44,8 +45,11 @@ void *vmem_crst_alloc(unsigned long val) unsigned long *table; table = vmem_alloc_pages(CRST_ALLOC_ORDER); - if (table) - crst_table_init(table, val); + if (!table) + return NULL; + crst_table_init(table, val); + if (slab_is_available()) + arch_set_page_dat(virt_to_page(table), CRST_ALLOC_ORDER); return table; } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 2c99f9552b2f..394c69fda399 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -241,7 +241,7 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, /* combine single writes by using store-block insn */ void __iowrite64_copy(void __iomem *to, const void *from, size_t count) { - zpci_memcpy_toio(to, from, count); + zpci_memcpy_toio(to, from, count * 8); } static void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot) diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 588089332931..a90499c087f0 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -97,9 +97,9 @@ static inline int __memcpy_toio_inuser(void __iomem *dst, return -EINVAL; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) dst, - (u64 __force) src, n, - ZPCI_MAX_WRITE_SIZE); + size = zpci_get_max_io_size((u64 __force) dst, + (u64 __force) src, n, + ZPCI_MAX_WRITE_SIZE); if (size > 8) /* main path */ rc = __pcistb_mio_inuser(dst, src, size, &status); else @@ -242,9 +242,9 @@ static inline int __memcpy_fromio_inuser(void __user *dst, u8 status; while (n > 0) { - size = zpci_get_max_write_size((u64 __force) src, - (u64 __force) dst, n, - ZPCI_MAX_READ_SIZE); + size = zpci_get_max_io_size((u64 __force) src, + (u64 __force) dst, n, + ZPCI_MAX_READ_SIZE); rc = __pcilg_mio_inuser(dst, src, size, &status); if (rc) break; diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h index 94eb529dcb77..2718cbea826a 100644 --- a/arch/sparc/include/asm/jump_label.h +++ b/arch/sparc/include/asm/jump_label.h @@ -10,7 +10,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" @@ -26,7 +26,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes]\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" diff --git a/arch/um/Makefile b/arch/um/Makefile index 3dbd0e3b660e..778c50f27399 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -118,7 +118,9 @@ archprepare: $(Q)$(MAKE) $(build)=$(HOST_DIR)/um include/generated/user_constants.h LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static -LINK-$(CONFIG_LD_SCRIPT_DYN) += $(call cc-option, -no-pie) +ifdef CONFIG_LD_SCRIPT_DYN +LINK-$(call gcc-min-version, 60100)$(CONFIG_CC_IS_CLANG) += -no-pie +endif LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \ diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 3d7836c46507..cabcc501b448 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -204,7 +204,7 @@ static int uml_net_close(struct net_device *dev) return 0; } -static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct uml_net_private *lp = netdev_priv(dev); unsigned long flags; diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h index 4b6d1b526bc1..66fe06db872f 100644 --- a/arch/um/include/asm/cpufeature.h +++ b/arch/um/include/asm/cpufeature.h @@ -75,7 +75,7 @@ extern void setup_clear_cpu_cap(unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" + asm goto("1: jmp 6f\n" "2:\n" ".skip -(((5f-4f) - (2b-1b)) > 0) * " "((5f-4f) - (2b-1b)),0x90\n" diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index d8b8b4f07e42..444bae755b16 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -50,7 +50,7 @@ extern void do_uml_exitcalls(void); * Are we disallowed to sleep? Used to choose between GFP_KERNEL and * GFP_ATOMIC. */ -extern int __cant_sleep(void); +extern int __uml_cant_sleep(void); extern int get_current_pid(void); extern int copy_from_user_proc(void *to, void *from, int size); extern char *uml_strdup(const char *string); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 010bc422a09d..a351c87db248 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -220,7 +220,7 @@ void arch_cpu_idle(void) raw_local_irq_enable(); } -int __cant_sleep(void) { +int __uml_cant_sleep(void) { return in_atomic() || irqs_disabled() || in_interrupt(); /* Is in_interrupt() really needed? */ } diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index fddd1dec27e6..3e270da6b6f6 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -432,9 +432,29 @@ static void time_travel_update_time(unsigned long long next, bool idle) time_travel_del_event(&ne); } +static void time_travel_update_time_rel(unsigned long long offs) +{ + unsigned long flags; + + /* + * Disable interrupts before calculating the new time so + * that a real timer interrupt (signal) can't happen at + * a bad time e.g. after we read time_travel_time but + * before we've completed updating the time. + */ + local_irq_save(flags); + time_travel_update_time(time_travel_time + offs, false); + local_irq_restore(flags); +} + void time_travel_ndelay(unsigned long nsec) { - time_travel_update_time(time_travel_time + nsec, false); + /* + * Not strictly needed to use _rel() version since this is + * only used in INFCPU/EXT modes, but it doesn't hurt and + * is more readable too. + */ + time_travel_update_time_rel(nsec); } EXPORT_SYMBOL(time_travel_ndelay); @@ -568,7 +588,11 @@ static void time_travel_set_start(void) #define time_travel_time 0 #define time_travel_ext_waiting 0 -static inline void time_travel_update_time(unsigned long long ns, bool retearly) +static inline void time_travel_update_time(unsigned long long ns, bool idle) +{ +} + +static inline void time_travel_update_time_rel(unsigned long long offs) { } @@ -720,9 +744,7 @@ static u64 timer_read(struct clocksource *cs) */ if (!irqs_disabled() && !in_interrupt() && !in_softirq() && !time_travel_ext_waiting) - time_travel_update_time(time_travel_time + - TIMER_MULTIPLIER, - false); + time_travel_update_time_rel(TIMER_MULTIPLIER); return time_travel_time / TIMER_MULTIPLIER; } diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index b459745f52e2..3cb8ac63be6e 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -46,7 +46,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) unsigned long stack, sp; int pid, fds[2], ret, n; - stack = alloc_stack(0, __cant_sleep()); + stack = alloc_stack(0, __uml_cant_sleep()); if (stack == 0) return -ENOMEM; @@ -70,7 +70,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) data.pre_data = pre_data; data.argv = argv; data.fd = fds[1]; - data.buf = __cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) : + data.buf = __uml_cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) : uml_kmalloc(PATH_MAX, UM_GFP_KERNEL); pid = clone(helper_child, (void *) sp, CLONE_VM, &data); if (pid < 0) { @@ -121,7 +121,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, unsigned long stack, sp; int pid, status, err; - stack = alloc_stack(0, __cant_sleep()); + stack = alloc_stack(0, __uml_cant_sleep()); if (stack == 0) return -ENOMEM; diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index fc0f2a9dee5a..1dca4ffbd572 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -173,23 +173,38 @@ __uml_setup("quiet", quiet_cmd_param, "quiet\n" " Turns off information messages during boot.\n\n"); +/* + * The os_info/os_warn functions will be called by helper threads. These + * have a very limited stack size and using the libc formatting functions + * may overflow the stack. + * So pull in the kernel vscnprintf and use that instead with a fixed + * on-stack buffer. + */ +int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); + void os_info(const char *fmt, ...) { + char buf[256]; va_list list; + int len; if (quiet_info) return; va_start(list, fmt); - vfprintf(stderr, fmt, list); + len = vscnprintf(buf, sizeof(buf), fmt, list); + fwrite(buf, len, 1, stderr); va_end(list); } void os_warn(const char *fmt, ...) { + char buf[256]; va_list list; + int len; va_start(list, fmt); - vfprintf(stderr, fmt, list); + len = vscnprintf(buf, sizeof(buf), fmt, list); + fwrite(buf, len, 1, stderr); va_end(list); } diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 542377cd419d..ce5ed2c2db0c 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -375,7 +375,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index b4155273df89..d34222816c9f 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -393,3 +393,8 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) */ kernel_add_identity_map(address, end); } + +void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code) +{ + /* Empty handler to ignore NMI during early boot */ +} diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 3cdf94b41456..d100284bbef4 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -61,6 +61,7 @@ void load_stage2_idt(void) boot_idt_desc.address = (unsigned long)boot_idt; set_idt_entry(X86_TRAP_PF, boot_page_fault); + set_idt_entry(X86_TRAP_NMI, boot_nmi_trap); #ifdef CONFIG_AMD_MEM_ENCRYPT /* diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index 22890e199f5b..4d03c8562f63 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -70,6 +70,7 @@ SYM_FUNC_END(\name) .code64 EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1 +EXCEPTION_HANDLER boot_nmi_trap do_boot_nmi_trap error_code=0 #ifdef CONFIG_AMD_MEM_ENCRYPT EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1 diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 20118fb7c53b..a49d9219c06e 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -190,6 +190,7 @@ static inline void cleanup_exception_handling(void) { } /* IDT Entry Points */ void boot_page_fault(void); +void boot_nmi_trap(void); void boot_stage1_vc(void); void boot_stage2_vc(void); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2fb5e1541efc..949129443b1c 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4033,12 +4033,17 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) u64 pebs_mask = cpuc->pebs_enabled & x86_pmu.pebs_capable; int global_ctrl, pebs_enable; + /* + * In addition to obeying exclude_guest/exclude_host, remove bits being + * used for PEBS when running a guest, because PEBS writes to virtual + * addresses (not physical addresses). + */ *nr = 0; global_ctrl = (*nr)++; arr[global_ctrl] = (struct perf_guest_switch_msr){ .msr = MSR_CORE_PERF_GLOBAL_CTRL, .host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask, - .guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask), + .guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask & ~pebs_mask, }; if (!x86_pmu.pebs) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index ce0c8f7d3218..f835b328ba24 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -173,7 +173,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto( + asm goto( ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index 800ffce0db29..6b4d36c95165 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -9,7 +9,6 @@ static inline bool arch_irq_work_has_interrupt(void) { return boot_cpu_has(X86_FEATURE_APIC); } -extern void arch_irq_work_raise(void); #else static inline bool arch_irq_work_has_interrupt(void) { diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 071572e23d3a..cbbef32517f0 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -24,7 +24,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:" + asm goto("1:" "jmp %l[l_yes] # objtool NOPs this \n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (2 | branch) : : l_yes); @@ -38,7 +38,7 @@ l_yes: static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto("1:" + asm goto("1:" ".byte " __stringify(BYTES_NOP5) "\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); @@ -52,7 +52,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto("1:" + asm goto("1:" "jmp %l[l_yes]\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); diff --git a/arch/x86/include/asm/kmsan.h b/arch/x86/include/asm/kmsan.h index 8fa6ac0e2d76..d91b37f5b4bb 100644 --- a/arch/x86/include/asm/kmsan.h +++ b/arch/x86/include/asm/kmsan.h @@ -64,6 +64,7 @@ static inline bool kmsan_virt_addr_valid(void *addr) { unsigned long x = (unsigned long)addr; unsigned long y = x - __START_KERNEL_map; + bool ret; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { @@ -79,7 +80,21 @@ static inline bool kmsan_virt_addr_valid(void *addr) return false; } - return pfn_valid(x >> PAGE_SHIFT); + /* + * pfn_valid() relies on RCU, and may call into the scheduler on exiting + * the critical section. However, this would result in recursion with + * KMSAN. Therefore, disable preemption here, and re-enable preemption + * below while suppressing reschedules to avoid recursion. + * + * Note, this sacrifices occasionally breaking scheduling guarantees. + * Although, a kernel compiled with KMSAN has already given up on any + * performance guarantees due to being heavily instrumented. + */ + preempt_disable(); + ret = pfn_valid(x >> PAGE_SHIFT); + preempt_enable_no_resched(); + + return ret; } #endif /* !MODULE */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 2f123d4fb85b..d3706de91a93 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -222,6 +222,8 @@ extern void srso_alias_untrain_ret(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); +extern void (*x86_return_thunk)(void); + #ifdef CONFIG_RETPOLINE #define GEN(reg) \ diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 7fa611216417..1919ccf493cd 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -18,7 +18,7 @@ #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \ ({ \ bool c = false; \ - asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \ + asm goto (fullop "; j" #cc " %l[cc_label]" \ : : [var] "m" (_var), ## __VA_ARGS__ \ : clobbers : cc_label); \ if (0) { \ diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index fd2669b1cb2d..e3323a9dc911 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -58,12 +58,29 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); ,,regs->di,,regs->si,,regs->dx \ ,,regs->r10,,regs->r8,,regs->r9) \ + +/* SYSCALL_PT_ARGS is Adapted from s390x */ +#define SYSCALL_PT_ARG6(m, t1, t2, t3, t4, t5, t6) \ + SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5), m(t6, (regs->bp)) +#define SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5) \ + SYSCALL_PT_ARG4(m, t1, t2, t3, t4), m(t5, (regs->di)) +#define SYSCALL_PT_ARG4(m, t1, t2, t3, t4) \ + SYSCALL_PT_ARG3(m, t1, t2, t3), m(t4, (regs->si)) +#define SYSCALL_PT_ARG3(m, t1, t2, t3) \ + SYSCALL_PT_ARG2(m, t1, t2), m(t3, (regs->dx)) +#define SYSCALL_PT_ARG2(m, t1, t2) \ + SYSCALL_PT_ARG1(m, t1), m(t2, (regs->cx)) +#define SYSCALL_PT_ARG1(m, t1) m(t1, (regs->bx)) +#define SYSCALL_PT_ARGS(x, ...) SYSCALL_PT_ARG##x(__VA_ARGS__) + +#define __SC_COMPAT_CAST(t, a) \ + (__typeof(__builtin_choose_expr(__TYPE_IS_L(t), 0, 0U))) \ + (unsigned int)a + /* Mapping of registers to parameters for syscalls on i386 */ #define SC_IA32_REGS_TO_ARGS(x, ...) \ - __MAP(x,__SC_ARGS \ - ,,(unsigned int)regs->bx,,(unsigned int)regs->cx \ - ,,(unsigned int)regs->dx,,(unsigned int)regs->si \ - ,,(unsigned int)regs->di,,(unsigned int)regs->bp) + SYSCALL_PT_ARGS(x, __SC_COMPAT_CAST, \ + __MAP(x, __SC_TYPE, __VA_ARGS__)) \ #define __SYS_STUB0(abi, name) \ long __##abi##_##name(const struct pt_regs *regs); \ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 6ca0c661cb63..c638535eedd5 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -155,7 +155,7 @@ extern int __get_user_bad(void); #ifdef CONFIG_X86_32 #define __put_user_goto_u64(x, addr, label) \ - asm_volatile_goto("\n" \ + asm goto("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ _ASM_EXTABLE_UA(1b, %l2) \ @@ -317,7 +317,7 @@ do { \ } while (0) #define __get_user_asm(x, addr, itype, ltype, label) \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: mov"itype" %[umem],%[output]\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : [output] ltype(x) \ @@ -397,7 +397,7 @@ do { \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ @@ -416,7 +416,7 @@ do { \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ @@ -499,7 +499,7 @@ struct __large_struct { unsigned long buf[100]; }; * aliasing issues. */ #define __put_user_goto(x, addr, itype, ltype, label) \ - asm_volatile_goto("\n" \ + asm goto("\n" \ "1: mov"itype" %0,%1\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 6c2e3ff3cb28..724ce44809ed 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -43,9 +43,9 @@ static inline int cpu_has_vmx(void) */ static inline int cpu_vmxoff(void) { - asm_volatile_goto("1: vmxoff\n\t" - _ASM_EXTABLE(1b, %l[fault]) - ::: "cc", "memory" : fault); + asm goto("1: vmxoff\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "cc", "memory" : fault); cr4_clear_bits(X86_CR4_VMXE); return 0; @@ -129,9 +129,9 @@ static inline void cpu_svm_disable(void) * case, GIF must already be set, otherwise the NMI would have * been blocked, so just eat the fault. */ - asm_volatile_goto("1: stgi\n\t" - _ASM_EXTABLE(1b, %l[fault]) - ::: "memory" : fault); + asm goto("1: stgi\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "memory" : fault); fault: wrmsrl(MSR_EFER, efer & ~EFER_SVME); } diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 46b7ee0ab01a..69f85e274611 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -536,6 +536,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) } #ifdef CONFIG_RETHUNK + /* * Rewrite the compiler generated return thunk tail-calls. * @@ -551,14 +552,18 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) { int i = 0; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - return -1; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (x86_return_thunk == __x86_return_thunk) + return -1; - bytes[i++] = RET_INSN_OPCODE; + i = JMP32_INSN_SIZE; + __text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i); + } else { + bytes[i++] = RET_INSN_OPCODE; + } for (; i < insn->length;) bytes[i++] = INT3_INSN_OPCODE; - return i; } @@ -1015,8 +1020,8 @@ void __init_or_module text_poke_early(void *addr, const void *opcode, } else { local_irq_save(flags); memcpy(addr, opcode, len); - local_irq_restore(flags); sync_core(); + local_irq_restore(flags); /* * Could also do a CLFLUSH here to speed up CPU recovery; but diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index f1a748da5fab..cad6ea1911e9 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -44,6 +44,7 @@ #include <linux/sync_core.h> #include <linux/task_work.h> #include <linux/hardirq.h> +#include <linux/kexec.h> #include <asm/intel-family.h> #include <asm/processor.h> @@ -239,6 +240,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) struct llist_node *pending; struct mce_evt_llist *l; int apei_err = 0; + struct page *p; /* * Allow instrumentation around external facilities usage. Not that it @@ -292,6 +294,20 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) if (!fake_panic) { if (panic_timeout == 0) panic_timeout = mca_cfg.panic_timeout; + + /* + * Kdump skips the poisoned page in order to avoid + * touching the error bits again. Poison the page even + * if the error is fatal and the machine is about to + * panic. + */ + if (kexec_crash_loaded()) { + if (final && (final->status & MCI_STATUS_ADDRV)) { + p = pfn_to_online_page(final->addr >> PAGE_SHIFT); + if (p) + SetPageHWPoison(p); + } + } panic(msg); } else pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 12cf2e7ca33c..87c15ab89651 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -747,6 +747,7 @@ static void check_hw_inj_possible(void) wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status); rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status); + wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), 0); if (!status) { hw_injection_possible = false; diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 558076dbde5b..247f2225aa9f 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures, * Attempt to restore the FPU registers directly from user memory. * Pagefaults are handled and any errors returned are fatal. */ -static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, - bool fx_only, unsigned int size) +static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) { struct fpu *fpu = ¤t->thread.fpu; int ret; + /* Restore enabled features only. */ + xrestore &= fpu->fpstate->user_xfeatures; retry: fpregs_lock(); /* Ensure that XFD is up to date */ @@ -309,7 +310,7 @@ retry: if (ret != X86_TRAP_PF) return false; - if (!fault_in_readable(buf, size)) + if (!fault_in_readable(buf, fpu->fpstate->user_size)) goto retry; return false; } @@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, struct user_i387_ia32_struct env; bool success, fx_only = false; union fpregs_state *fpregs; - unsigned int state_size; u64 user_xfeatures = 0; if (use_xsave()) { @@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, return false; fx_only = !fx_sw_user.magic1; - state_size = fx_sw_user.xstate_size; user_xfeatures = fx_sw_user.xfeatures; } else { user_xfeatures = XFEATURE_MASK_FPSSE; - state_size = fpu->fpstate->user_size; } if (likely(!ia32_fxstate)) { /* Restore the FPU registers directly from user memory. */ - return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only, - state_size); + return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); } /* diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index e07234ec7e23..ec51ce713dea 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -361,7 +361,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) ip = trampoline + size; if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, &__x86_return_thunk, JMP32_INSN_SIZE); + __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE); else memcpy(ip, retq, sizeof(retq)); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 71f336425e58..54732da52dc1 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1436,7 +1436,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) memset(&curr_time, 0, sizeof(struct rtc_time)); if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) { - if (unlikely(mc146818_get_time(&curr_time) < 0)) { + if (unlikely(mc146818_get_time(&curr_time, 10) < 0)) { pr_err_ratelimited("unable to read current time from RTC\n"); return IRQ_HANDLED; } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index ea155f0cf545..6120f25b0d5c 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -549,7 +549,8 @@ static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs) { unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg]; - int3_emulate_call(regs, regs_get_register(regs, offs)); + int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + p->ainsn.size); + int3_emulate_jmp(regs, regs_get_register(regs, offs)); } NOKPROBE_SYMBOL(kprobe_emulate_call_indirect); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 16333ba1904b..c067887d42df 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -24,8 +24,8 @@ static int kvmclock __initdata = 1; static int kvmclock_vsyscall __initdata = 1; -static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME; -static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK; +static int msr_kvm_system_time __ro_after_init; +static int msr_kvm_wall_clock __ro_after_init; static u64 kvm_sched_clock_offset __ro_after_init; static int __init parse_no_kvmclock(char *arg) @@ -195,7 +195,8 @@ static void kvm_setup_secondary_clock(void) void kvmclock_disable(void) { - native_write_msr(msr_kvm_system_time, 0, 0); + if (msr_kvm_system_time) + native_write_msr(msr_kvm_system_time, 0, 0); } static void __init kvmclock_init_mem(void) @@ -294,7 +295,10 @@ void __init kvmclock_init(void) if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) { msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW; msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW; - } else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { + } else if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { + msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; + msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; + } else { return; } diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 349046434513..344c141133e4 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -67,7 +67,7 @@ void mach_get_cmos_time(struct timespec64 *now) return; } - if (mc146818_get_time(&tm)) { + if (mc146818_get_time(&tm, 1000)) { pr_err("Unable to read current time from RTC\n"); now->tv_sec = now->tv_nsec = 0; return; diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 3fbb49168827..b32134b093ec 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -80,7 +80,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, case RET: if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk); + code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk); else code = &retinsn; break; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index bc288e6bde64..5d4d78c9a787 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -239,18 +239,6 @@ static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size) kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1); } -static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl) -{ - /* Nested FLUSHBYASID is not supported yet. */ - switch(tlb_ctl) { - case TLB_CONTROL_DO_NOTHING: - case TLB_CONTROL_FLUSH_ALL_ASID: - return true; - default: - return false; - } -} - static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, struct vmcb_ctrl_area_cached *control) { @@ -270,8 +258,6 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, IOPM_SIZE))) return false; - if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl))) - return false; return true; } diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h index 36c8af87a707..4e725854c63a 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -8,7 +8,7 @@ #define svm_asm(insn, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) "\n\t" \ + asm goto("1: " __stringify(insn) "\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ ::: clobber : fault); \ return; \ @@ -18,7 +18,7 @@ fault: \ #define svm_asm1(insn, op1, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1 : clobber : fault); \ return; \ @@ -28,7 +28,7 @@ fault: \ #define svm_asm2(insn, op1, op2, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1, op2 : clobber : fault); \ return; \ diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 9a75a0d5deae..220cdbe1e286 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -38,7 +38,7 @@ static int fixed_pmc_events[] = {1, 0, 7}; static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) { struct kvm_pmc *pmc; - u8 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl; + u64 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl; int i; pmu->fixed_ctr_ctrl = data; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 98d732b9418f..57c1374fdfd4 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2469,10 +2469,10 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) cr4_set_bits(X86_CR4_VMXE); - asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" - _ASM_EXTABLE(1b, %l[fault]) - : : [vmxon_pointer] "m"(vmxon_pointer) - : : fault); + asm goto("1: vmxon %[vmxon_pointer]\n\t" + _ASM_EXTABLE(1b, %l[fault]) + : : [vmxon_pointer] "m"(vmxon_pointer) + : : fault); return 0; fault: diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index ec268df83ed6..5edab28dfb2e 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -73,7 +73,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT - asm_volatile_goto("1: vmread %[field], %[output]\n\t" + asm_goto_output("1: vmread %[field], %[output]\n\t" "jna %l[do_fail]\n\t" _ASM_EXTABLE(1b, %l[do_exception]) @@ -166,7 +166,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) #define vmx_asm1(insn, op1, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ @@ -183,7 +183,7 @@ fault: \ #define vmx_asm2(insn, op1, op2, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c index a018ec4fba53..c97be9a1430a 100644 --- a/arch/x86/lib/misc.c +++ b/arch/x86/lib/misc.c @@ -6,7 +6,7 @@ */ int num_digits(int val) { - int m = 10; + long long m = 10; int d = 1; if (val < 0) { diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index 968d7005f4a7..f50cc210a981 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, for (; addr < end; addr = next) { pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; + bool use_gbpage; next = (addr & PUD_MASK) + PUD_SIZE; if (next > end) next = end; - if (info->direct_gbpages) { - pud_t pudval; + /* if this is already a gbpage, this portion is already mapped */ + if (pud_large(*pud)) + continue; + + /* Is using a gbpage allowed? */ + use_gbpage = info->direct_gbpages; - if (pud_present(*pud)) - continue; + /* Don't use gbpage if it maps more than the requested region. */ + /* at the begining: */ + use_gbpage &= ((addr & ~PUD_MASK) == 0); + /* ... or at the end: */ + use_gbpage &= ((next & ~PUD_MASK) == 0); + + /* Never overwrite existing mappings */ + use_gbpage &= !pud_present(*pud); + + if (use_gbpage) { + pud_t pudval; - addr &= PUD_MASK; pudval = __pud((addr - info->offset) | info->page_flag); set_pud(pud, pudval); continue; diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index aa39d678fe81..dae5c952735c 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -961,7 +961,7 @@ static int __init cmp_memblk(const void *a, const void *b) const struct numa_memblk *ma = *(const struct numa_memblk **)a; const struct numa_memblk *mb = *(const struct numa_memblk **)b; - return ma->start - mb->start; + return (ma->start > mb->start) - (ma->start < mb->start); } static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; @@ -971,14 +971,12 @@ static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; * @start: address to begin fill * @end: address to end fill * - * Find and extend numa_meminfo memblks to cover the @start-@end - * physical address range, such that the first memblk includes - * @start, the last memblk includes @end, and any gaps in between - * are filled. + * Find and extend numa_meminfo memblks to cover the physical + * address range @start-@end * * RETURNS: * 0 : Success - * NUMA_NO_MEMBLK : No memblk exists in @start-@end range + * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end */ int __init numa_fill_memblks(u64 start, u64 end) @@ -990,17 +988,14 @@ int __init numa_fill_memblks(u64 start, u64 end) /* * Create a list of pointers to numa_meminfo memblks that - * overlap start, end. Exclude (start == bi->end) since - * end addresses in both a CFMWS range and a memblk range - * are exclusive. - * - * This list of pointers is used to make in-place changes - * that fill out the numa_meminfo memblks. + * overlap start, end. The list is used to make in-place + * changes that fill out the numa_meminfo memblks. */ for (int i = 0; i < mi->nr_blks; i++) { struct numa_memblk *bi = &mi->blk[i]; - if (start < bi->end && end >= bi->start) { + if (memblock_addrs_overlap(start, end - start, bi->start, + bi->end - bi->start)) { blk[count] = &mi->blk[i]; count++; } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 5e680e039d0e..7913440c0fd4 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -432,7 +432,7 @@ static void emit_return(u8 **pprog, u8 *ip) u8 *prog = *pprog; if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { - emit_jump(&prog, &__x86_return_thunk, ip); + emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ if (IS_ENABLED(CONFIG_SLS)) @@ -893,6 +893,10 @@ static void emit_nops(u8 **pprog, int len) #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) +/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ +#define RESTORE_TAIL_CALL_CNT(stack) \ + EMIT3_off32(0x48, 0x8B, 0x85, -round_up(stack, 8) - 8) + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { @@ -1436,9 +1440,7 @@ st: if (is_imm8(insn->off)) case BPF_JMP | BPF_CALL: func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { - /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ - EMIT3_off32(0x48, 0x8B, 0x85, - -round_up(bpf_prog->aux->stack_depth, 8) - 8); + RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth); if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7)) return -EINVAL; } else { @@ -1623,16 +1625,24 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ break; case BPF_JMP | BPF_JA: - if (insn->off == -1) - /* -1 jmp instructions will always jump - * backwards two bytes. Explicitly handling - * this case avoids wasting too many passes - * when there are long sequences of replaced - * dead code. - */ - jmp_offset = -2; - else - jmp_offset = addrs[i + insn->off] - addrs[i]; + case BPF_JMP32 | BPF_JA: + if (BPF_CLASS(insn->code) == BPF_JMP) { + if (insn->off == -1) + /* -1 jmp instructions will always jump + * backwards two bytes. Explicitly handling + * this case avoids wasting too many passes + * when there are long sequences of replaced + * dead code. + */ + jmp_offset = -2; + else + jmp_offset = addrs[i + insn->off] - addrs[i]; + } else { + if (insn->imm == -1) + jmp_offset = -2; + else + jmp_offset = addrs[i + insn->imm] - addrs[i]; + } if (!jmp_offset) { /* @@ -1750,63 +1760,37 @@ emit_jmp: return proglen; } -static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_args, +static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_regs, int stack_size) { - int i, j, arg_size, nr_regs; + int i; + /* Store function arguments to stack. * For a function that accepts two pointers the sequence will be: * mov QWORD PTR [rbp-0x10],rdi * mov QWORD PTR [rbp-0x8],rsi */ - for (i = 0, j = 0; i < min(nr_args, 6); i++) { - if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) { - nr_regs = (m->arg_size[i] + 7) / 8; - arg_size = 8; - } else { - nr_regs = 1; - arg_size = m->arg_size[i]; - } - - while (nr_regs) { - emit_stx(prog, bytes_to_bpf_size(arg_size), - BPF_REG_FP, - j == 5 ? X86_REG_R9 : BPF_REG_1 + j, - -(stack_size - j * 8)); - nr_regs--; - j++; - } - } + for (i = 0; i < min(nr_regs, 6); i++) + emit_stx(prog, BPF_DW, BPF_REG_FP, + i == 5 ? X86_REG_R9 : BPF_REG_1 + i, + -(stack_size - i * 8)); } -static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, +static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_regs, int stack_size) { - int i, j, arg_size, nr_regs; + int i; /* Restore function arguments from stack. * For a function that accepts two pointers the sequence will be: * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10] * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8] */ - for (i = 0, j = 0; i < min(nr_args, 6); i++) { - if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) { - nr_regs = (m->arg_size[i] + 7) / 8; - arg_size = 8; - } else { - nr_regs = 1; - arg_size = m->arg_size[i]; - } - - while (nr_regs) { - emit_ldx(prog, bytes_to_bpf_size(arg_size), - j == 5 ? X86_REG_R9 : BPF_REG_1 + j, - BPF_REG_FP, - -(stack_size - j * 8)); - nr_regs--; - j++; - } - } + for (i = 0; i < min(nr_regs, 6); i++) + emit_ldx(prog, BPF_DW, + i == 5 ? X86_REG_R9 : BPF_REG_1 + i, + BPF_REG_FP, + -(stack_size - i * 8)); } static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, @@ -2031,8 +2015,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i struct bpf_tramp_links *tlinks, void *func_addr) { - int ret, i, nr_args = m->nr_args, extra_nregs = 0; - int regs_off, ip_off, args_off, stack_size = nr_args * 8, run_ctx_off; + int i, ret, nr_regs = m->nr_args, stack_size = 0; + int regs_off, nregs_off, ip_off, run_ctx_off; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; @@ -2041,17 +2025,14 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i u8 *prog; bool save_ret; - /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ - if (nr_args > 6) - return -ENOTSUPP; - - for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) { + /* extra registers for struct arguments */ + for (i = 0; i < m->nr_args; i++) if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) - extra_nregs += (m->arg_size[i] + 7) / 8 - 1; - } - if (nr_args + extra_nregs > 6) + nr_regs += (m->arg_size[i] + 7) / 8 - 1; + + /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ + if (nr_regs > 6) return -ENOTSUPP; - stack_size += extra_nregs * 8; /* Generated trampoline stack layout: * @@ -2065,11 +2046,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * [ ... ] * RBP - regs_off [ reg_arg1 ] program's ctx pointer * - * RBP - args_off [ arg regs count ] always + * RBP - nregs_off [ regs count ] always * * RBP - ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag * * RBP - run_ctx_off [ bpf_tramp_run_ctx ] + * RSP [ tail_call_cnt ] BPF_TRAMP_F_TAIL_CALL_CTX */ /* room for return value of orig_call or fentry prog */ @@ -2077,11 +2059,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (save_ret) stack_size += 8; + stack_size += nr_regs * 8; regs_off = stack_size; - /* args count */ + /* regs count */ stack_size += 8; - args_off = stack_size; + nregs_off = stack_size; if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ @@ -2106,14 +2089,16 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + EMIT1(0x50); /* push rax */ EMIT1(0x53); /* push rbx */ /* Store number of argument registers of the traced function: - * mov rax, nr_args + extra_nregs - * mov QWORD PTR [rbp - args_off], rax + * mov rax, nr_regs + * mov QWORD PTR [rbp - nregs_off], rax */ - emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args + extra_nregs); - emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -args_off); + emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_regs); + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -nregs_off); if (flags & BPF_TRAMP_F_IP_ARG) { /* Store IP address of the traced function: @@ -2124,7 +2109,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off); } - save_regs(m, &prog, nr_args, regs_off); + save_regs(m, &prog, nr_regs, regs_off); if (flags & BPF_TRAMP_F_CALL_ORIG) { /* arg1: mov rdi, im */ @@ -2154,11 +2139,17 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (flags & BPF_TRAMP_F_CALL_ORIG) { - restore_regs(m, &prog, nr_args, regs_off); + restore_regs(m, &prog, nr_regs, regs_off); + + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + /* Before calling the original function, restore the + * tail_call_cnt from stack to rax. + */ + RESTORE_TAIL_CALL_CNT(stack_size); if (flags & BPF_TRAMP_F_ORIG_STACK) { - emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8); - EMIT2(0xff, 0xd0); /* call *rax */ + emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8); + EMIT2(0xff, 0xd3); /* call *rbx */ } else { /* call original function */ if (emit_call(&prog, orig_call, prog)) { @@ -2195,7 +2186,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (flags & BPF_TRAMP_F_RESTORE_REGS) - restore_regs(m, &prog, nr_args, regs_off); + restore_regs(m, &prog, nr_regs, regs_off); /* This needs to be done regardless. If there were fmod_ret programs, * the return value is only updated on the stack and still needs to be @@ -2209,7 +2200,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i ret = -EINVAL; goto cleanup; } - } + } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + /* Before running the original function, restore the + * tail_call_cnt from stack to rax. + */ + RESTORE_TAIL_CALL_CNT(stack_size); + /* restore return value of orig_call or fentry prog back into RAX */ if (save_ret) emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); @@ -2553,3 +2549,49 @@ void bpf_jit_free(struct bpf_prog *prog) bpf_prog_unlock_free(prog); } + +void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old) +{ + u8 *old_addr, *new_addr, *old_bypass_addr; + int ret; + + old_bypass_addr = old ? NULL : poke->bypass_addr; + old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; + new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; + + /* + * On program loading or teardown, the program's kallsym entry + * might not be in place, so we use __bpf_arch_text_poke to skip + * the kallsyms check. + */ + if (new) { + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, + old_addr, new_addr); + BUG_ON(ret < 0); + if (!old) { + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + poke->bypass_addr, + NULL); + BUG_ON(ret < 0); + } + } else { + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + old_bypass_addr, + poke->bypass_addr); + BUG_ON(ret < 0); + /* let other CPUs finish the execution of program + * so that it will not possible to expose them + * to invalid nop, stack unwind, nop state + */ + if (!ret) + synchronize_rcu(); + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, + old_addr, NULL); + BUG_ON(ret < 0); + } +} diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 9b1ec5d8c99c..a65fc2ae15b4 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -9,6 +9,7 @@ config XEN select PARAVIRT_CLOCK select X86_HV_CALLBACK_VECTOR depends on X86_64 || (X86_32 && X86_PAE) + depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8) depends on X86_LOCAL_APIC && X86_TSC help This is the Linux Xen port. Enabling this will allow the diff --git a/arch/xtensa/include/asm/jump_label.h b/arch/xtensa/include/asm/jump_label.h index c812bf85021c..46c8596259d2 100644 --- a/arch/xtensa/include/asm/jump_label.h +++ b/arch/xtensa/include/asm/jump_label.h @@ -13,7 +13,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "_nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" @@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, * make it reachable and wrap both into a no-transform block * to avoid any assembler interference with this. */ - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" ".begin no-transform\n\t" "_j %l[l_yes]\n\t" "2:\n\t" diff --git a/block/bdev.c b/block/bdev.c index d699ecdb3260..b61502ec8da0 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -507,6 +507,8 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) void bdev_add(struct block_device *bdev, dev_t dev) { + if (bdev_stable_writes(bdev)) + mapping_set_stable_writes(bdev->bd_inode->i_mapping); bdev->bd_dev = dev; bdev->bd_inode->i_rdev = dev; bdev->bd_inode->i_ino = dev; diff --git a/block/bio.c b/block/bio.c index 9ec72a78f114..74c2818c7ec9 100644 --- a/block/bio.c +++ b/block/bio.c @@ -927,7 +927,7 @@ static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio, if ((addr1 | mask) != (addr2 | mask)) return false; - if (bv->bv_len + len > queue_max_segment_size(q)) + if (len > queue_max_segment_size(q) - bv->bv_len) return false; return __bio_try_merge_page(bio, page, len, offset, same_page); } @@ -1109,13 +1109,22 @@ bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len, void __bio_release_pages(struct bio *bio, bool mark_dirty) { - struct bvec_iter_all iter_all; - struct bio_vec *bvec; + struct folio_iter fi; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (mark_dirty && !PageCompound(bvec->bv_page)) - set_page_dirty_lock(bvec->bv_page); - put_page(bvec->bv_page); + bio_for_each_folio_all(fi, bio) { + struct page *page; + size_t done = 0; + + if (mark_dirty) { + folio_lock(fi.folio); + folio_mark_dirty(fi.folio); + folio_unlock(fi.folio); + } + page = folio_page(fi.folio, fi.offset / PAGE_SIZE); + do { + folio_put(fi.folio); + done += PAGE_SIZE; + } while (done < fi.length); } } EXPORT_SYMBOL_GPL(__bio_release_pages); @@ -1414,12 +1423,12 @@ EXPORT_SYMBOL(bio_free_pages); */ void bio_set_pages_dirty(struct bio *bio) { - struct bio_vec *bvec; - struct bvec_iter_all iter_all; + struct folio_iter fi; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (!PageCompound(bvec->bv_page)) - set_page_dirty_lock(bvec->bv_page); + bio_for_each_folio_all(fi, bio) { + folio_lock(fi.folio); + folio_mark_dirty(fi.folio); + folio_unlock(fi.folio); } } @@ -1462,12 +1471,11 @@ static void bio_dirty_fn(struct work_struct *work) void bio_check_pages_dirty(struct bio *bio) { - struct bio_vec *bvec; + struct folio_iter fi; unsigned long flags; - struct bvec_iter_all iter_all; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page)) + bio_for_each_folio_all(fi, bio) { + if (!folio_test_dirty(fi.folio)) goto defer; } diff --git a/block/blk-core.c b/block/blk-core.c index 6eaf2b0ad7cc..aefdf07bdc2c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -864,7 +864,16 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) */ blk_flush_plug(current->plug, false); - if (bio_queue_enter(bio)) + /* + * We need to be able to enter a frozen queue, similar to how + * timeouts also need to do that. If that is blocked, then we can + * have pending IO when a queue freeze is started, and then the + * wait for the freeze to finish will wait for polled requests to + * timeout as the poller is preventer from entering the queue and + * completing them. As long as we prevent new IO from being queued, + * that should be all that matters. + */ + if (!percpu_ref_tryget(&q->q_usage_counter)) return 0; if (queue_is_mq(q)) { ret = blk_mq_poll(q, cookie, iob, flags); diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 7dd6a33e1d6a..e6557024e3da 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1337,6 +1337,13 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) lockdep_assert_held(&iocg->waitq.lock); + /* + * If the delay is set by another CPU, we may be in the past. No need to + * change anything if so. This avoids decay calculation underflow. + */ + if (time_before64(now->now, iocg->delay_at)) + return false; + /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; if (iocg->delay) diff --git a/block/blk-map.c b/block/blk-map.c index 66da9e2b19ab..b337ae347bfa 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -203,12 +203,19 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, /* * success */ - if ((iov_iter_rw(iter) == WRITE && - (!map_data || !map_data->null_mapped)) || - (map_data && map_data->from_user)) { + if (iov_iter_rw(iter) == WRITE && + (!map_data || !map_data->null_mapped)) { ret = bio_copy_from_iter(bio, iter); if (ret) goto cleanup; + } else if (map_data && map_data->from_user) { + struct iov_iter iter2 = *iter; + + /* This is the copy-in part of SG_DXFER_TO_FROM_DEV. */ + iter2.data_source = ITER_SOURCE; + ret = bio_copy_from_iter(bio, &iter2); + if (ret) + goto cleanup; } else { if (bmd->is_our_pages) zero_fill_bio(bio); diff --git a/block/blk-mq.c b/block/blk-mq.c index 100fb0c3114f..7ed6b9469f97 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -747,11 +747,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio, /* * Partial zone append completions cannot be supported as the * BIO fragments may end up not being written sequentially. + * For such case, force the completed nbytes to be equal to + * the BIO size so that bio_advance() sets the BIO remaining + * size to 0 and we end up calling bio_endio() before returning. */ - if (bio->bi_iter.bi_size != nbytes) + if (bio->bi_iter.bi_size != nbytes) { bio->bi_status = BLK_STS_IOERR; - else + nbytes = bio->bi_iter.bi_size; + } else { bio->bi_iter.bi_sector = rq->__sector; + } } bio_advance(bio, nbytes); @@ -1500,14 +1505,26 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q, } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); +static bool blk_is_flush_data_rq(struct request *rq) +{ + return (rq->rq_flags & RQF_FLUSH_SEQ) && !is_flush_rq(rq); +} + static bool blk_mq_rq_inflight(struct request *rq, void *priv) { /* * If we find a request that isn't idle we know the queue is busy * as it's checked in the iter. * Return false to stop the iteration. + * + * In case of queue quiesce, if one flush data request is completed, + * don't count it as inflight given the flush sequence is suspended, + * and the original flush data request is invisible to driver, just + * like other pending requests because of quiesce */ - if (blk_mq_request_started(rq)) { + if (blk_mq_request_started(rq) && !(blk_queue_quiesced(rq->q) && + blk_is_flush_data_rq(rq) && + blk_mq_request_completed(rq))) { bool *busy = priv; *busy = true; @@ -1848,6 +1865,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, __add_wait_queue(wq, wait); /* + * Add one explicit barrier since blk_mq_get_driver_tag() may + * not imply barrier in case of failure. + * + * Order adding us to wait queue and allocating driver tag. + * + * The pair is the one implied in sbitmap_queue_wake_up() which + * orders clearing sbitmap tag bits and waitqueue_active() in + * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless + * + * Otherwise, re-order of adding wait queue and getting driver tag + * may cause __sbitmap_queue_wake_up() to wake up nothing because + * the waitqueue_active() may not observe us in wait queue. + */ + smp_mb(); + + /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. @@ -2855,11 +2888,8 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, }; struct request *rq; - if (unlikely(bio_queue_enter(bio))) - return NULL; - if (blk_mq_attempt_bio_merge(q, bio, nsegs)) - goto queue_exit; + return NULL; rq_qos_throttle(q, bio); @@ -2875,35 +2905,23 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); -queue_exit: - blk_queue_exit(q); return NULL; } -static inline struct request *blk_mq_get_cached_request(struct request_queue *q, - struct blk_plug *plug, struct bio **bio, unsigned int nsegs) +/* return true if this @rq can be used for @bio */ +static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug, + struct bio *bio) { - struct request *rq; - enum hctx_type type, hctx_type; - - if (!plug) - return NULL; - rq = rq_list_peek(&plug->cached_rq); - if (!rq || rq->q != q) - return NULL; + enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf); + enum hctx_type hctx_type = rq->mq_hctx->type; - if (blk_mq_attempt_bio_merge(q, *bio, nsegs)) { - *bio = NULL; - return NULL; - } + WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq); - type = blk_mq_get_hctx_type((*bio)->bi_opf); - hctx_type = rq->mq_hctx->type; if (type != hctx_type && !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT)) - return NULL; - if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf)) - return NULL; + return false; + if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf)) + return false; /* * If any qos ->throttle() end up blocking, we will have flushed the @@ -2911,11 +2929,11 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, * before we throttle. */ plug->cached_rq = rq_list_next(rq); - rq_qos_throttle(q, *bio); + rq_qos_throttle(rq->q, bio); - rq->cmd_flags = (*bio)->bi_opf; + rq->cmd_flags = bio->bi_opf; INIT_LIST_HEAD(&rq->queuelist); - return rq; + return true; } static void bio_set_ioprio(struct bio *bio) @@ -2944,31 +2962,51 @@ void blk_mq_submit_bio(struct bio *bio) struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct blk_plug *plug = blk_mq_plug(bio); const int is_sync = op_is_sync(bio->bi_opf); - struct request *rq; + struct request *rq = NULL; unsigned int nr_segs = 1; blk_status_t ret; bio = blk_queue_bounce(bio, q); - if (bio_may_exceed_limits(bio, &q->limits)) { - bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); - if (!bio) - return; - } - - if (!bio_integrity_prep(bio)) - return; - bio_set_ioprio(bio); - rq = blk_mq_get_cached_request(q, plug, &bio, nr_segs); - if (!rq) { - if (!bio) + if (plug) { + rq = rq_list_peek(&plug->cached_rq); + if (rq && rq->q != q) + rq = NULL; + } + if (rq) { + if (unlikely(bio_may_exceed_limits(bio, &q->limits))) { + bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); + if (!bio) + return; + } + if (!bio_integrity_prep(bio)) return; - rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); - if (unlikely(!rq)) + if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) return; + if (blk_mq_can_use_cached_rq(rq, plug, bio)) + goto done; + percpu_ref_get(&q->q_usage_counter); + } else { + if (unlikely(bio_queue_enter(bio))) + return; + if (unlikely(bio_may_exceed_limits(bio, &q->limits))) { + bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); + if (!bio) + goto fail; + } + if (!bio_integrity_prep(bio)) + goto fail; + } + + rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); + if (unlikely(!rq)) { +fail: + blk_queue_exit(q); + return; } +done: trace_block_getrq(bio); rq_qos_track(q, rq, bio); diff --git a/block/blk-settings.c b/block/blk-settings.c index 86ff375c00ce..bbca4ce77a2d 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -135,7 +135,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto limits->max_hw_sectors = max_hw_sectors; max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors); - max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS); + max_sectors = min(max_sectors, BLK_DEF_MAX_SECTORS); max_sectors = round_down(max_sectors, limits->logical_block_size >> SECTOR_SHIFT); limits->max_sectors = max_sectors; diff --git a/block/fops.c b/block/fops.c index 6197d1c41652..01cb6260fa24 100644 --- a/block/fops.c +++ b/block/fops.c @@ -655,24 +655,35 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, filemap_invalidate_lock(inode->i_mapping); - /* Invalidate the page cache, including dirty pages. */ - error = truncate_bdev_range(bdev, file->f_mode, start, end); - if (error) - goto fail; - + /* + * Invalidate the page cache, including dirty pages, for valid + * de-allocate mode calls to fallocate(). + */ switch (mode) { case FALLOC_FL_ZERO_RANGE: case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: + error = truncate_bdev_range(bdev, file->f_mode, start, end); + if (error) + goto fail; + error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT, len >> SECTOR_SHIFT, GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: + error = truncate_bdev_range(bdev, file->f_mode, start, end); + if (error) + goto fail; + error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT, len >> SECTOR_SHIFT, GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: + error = truncate_bdev_range(bdev, file->f_mode, start, end); + if (error) + goto fail; + error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT, len >> SECTOR_SHIFT, GFP_KERNEL); break; diff --git a/block/genhd.c b/block/genhd.c index afab646d12c8..ddb17c4adc8a 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -444,7 +444,9 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, DISK_MAX_PARTS); disk->minors = DISK_MAX_PARTS; } - if (disk->first_minor + disk->minors > MINORMASK + 1) + if (disk->first_minor > MINORMASK || + disk->minors > MINORMASK + 1 || + disk->first_minor + disk->minors > MINORMASK + 1) goto out_exit_elevator; } else { if (WARN_ON(disk->minors)) @@ -567,6 +569,7 @@ out_del_integrity: out_del_block_link: if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(ddev)); + pm_runtime_set_memalloc_noio(ddev, false); out_device_del: device_del(ddev); out_free_ext_minor: diff --git a/block/ioctl.c b/block/ioctl.c index 3c475e4166e9..47567ba1185a 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -18,10 +18,8 @@ static int blkpg_do_ioctl(struct block_device *bdev, { struct gendisk *disk = bdev->bd_disk; struct blkpg_partition p; - long long start, length; + sector_t start, length; - if (disk->flags & GENHD_FL_NO_PART) - return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (copy_from_user(&p, upart, sizeof(struct blkpg_partition))) @@ -35,14 +33,17 @@ static int blkpg_do_ioctl(struct block_device *bdev, if (op == BLKPG_DEL_PARTITION) return bdev_del_partition(disk, p.pno); + if (p.start < 0 || p.length <= 0 || p.start + p.length < 0) + return -EINVAL; + /* Check that the partition is aligned to the block size */ + if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev))) + return -EINVAL; + start = p.start >> SECTOR_SHIFT; length = p.length >> SECTOR_SHIFT; switch (op) { case BLKPG_ADD_PARTITION: - /* check if partition is aligned to blocksize */ - if (p.start & (bdev_logical_block_size(bdev) - 1)) - return -EINVAL; return bdev_add_partition(disk, p.pno, start, length); case BLKPG_RESIZE_PARTITION: return bdev_resize_partition(disk, p.pno, start, length); diff --git a/block/partitions/core.c b/block/partitions/core.c index b8112f52d388..3927f4283f6b 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -453,6 +453,11 @@ int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, goto out; } + if (disk->flags & GENHD_FL_NO_PART) { + ret = -EINVAL; + goto out; + } + if (partition_overlaps(disk, start, length, -1)) { ret = -EBUSY; goto out; diff --git a/crypto/af_alg.c b/crypto/af_alg.c index e893c0f6c879..fef69d2a6b18 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1045,9 +1045,13 @@ EXPORT_SYMBOL_GPL(af_alg_sendpage); void af_alg_free_resources(struct af_alg_async_req *areq) { struct sock *sk = areq->sk; + struct af_alg_ctx *ctx; af_alg_free_areq_sgls(areq); sock_kfree_s(sk, areq, areq->areqlen); + + ctx = alg_sk(sk)->private; + ctx->inflight = false; } EXPORT_SYMBOL_GPL(af_alg_free_resources); @@ -1117,11 +1121,19 @@ EXPORT_SYMBOL_GPL(af_alg_poll); struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk, unsigned int areqlen) { - struct af_alg_async_req *areq = sock_kmalloc(sk, areqlen, GFP_KERNEL); + struct af_alg_ctx *ctx = alg_sk(sk)->private; + struct af_alg_async_req *areq; + + /* Only one AIO request can be in flight. */ + if (ctx->inflight) + return ERR_PTR(-EBUSY); + areq = sock_kmalloc(sk, areqlen, GFP_KERNEL); if (unlikely(!areq)) return ERR_PTR(-ENOMEM); + ctx->inflight = true; + areq->areqlen = areqlen; areq->sk = sk; areq->last_rsgl = NULL; diff --git a/crypto/algapi.c b/crypto/algapi.c index 5dc9ccdd5a51..c73d1359b9d4 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -290,6 +290,7 @@ static struct crypto_larval *__crypto_register_alg(struct crypto_alg *alg) } if (!strcmp(q->cra_driver_name, alg->cra_name) || + !strcmp(q->cra_driver_name, alg->cra_driver_name) || !strcmp(q->cra_name, alg->cra_driver_name)) goto err; } diff --git a/crypto/scompress.c b/crypto/scompress.c index 738f4f8f0f41..4d6366a44400 100644 --- a/crypto/scompress.c +++ b/crypto/scompress.c @@ -124,6 +124,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) struct crypto_scomp *scomp = *tfm_ctx; void **ctx = acomp_request_ctx(req); struct scomp_scratch *scratch; + unsigned int dlen; int ret; if (!req->src || !req->slen || req->slen > SCOMP_SCRATCH_SIZE) @@ -135,6 +136,8 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) if (!req->dlen || req->dlen > SCOMP_SCRATCH_SIZE) req->dlen = SCOMP_SCRATCH_SIZE; + dlen = req->dlen; + scratch = raw_cpu_ptr(&scomp_scratch); spin_lock(&scratch->lock); @@ -152,6 +155,9 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) ret = -ENOMEM; goto out; } + } else if (req->dlen > dlen) { + ret = -ENOSPC; + goto out; } scatterwalk_map_and_copy(scratch->dst, req->dst, 0, req->dlen, 1); diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index e648158368a7..0a84d5afd37c 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -145,9 +145,14 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, static u32 err_seq; estatus = extlog_elog_entry_check(cpu, bank); - if (estatus == NULL || (mce->kflags & MCE_HANDLED_CEC)) + if (!estatus) return NOTIFY_DONE; + if (mce->kflags & MCE_HANDLED_CEC) { + estatus->block_status = 0; + return NOTIFY_DONE; + } + memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN); /* clear record status to enable BIOS to update it again */ estatus->block_status = 0; @@ -303,9 +308,10 @@ err: static void __exit extlog_exit(void) { mce_unregister_decode_chain(&extlog_mce_dec); - ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; - if (extlog_l1_addr) + if (extlog_l1_addr) { + ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; acpi_os_unmap_iomem(extlog_l1_addr, l1_size); + } if (elog_addr) acpi_os_unmap_iomem(elog_addr, elog_size); release_mem_region(elog_base, elog_size); diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c index 50540d4d4948..2c015ecf7185 100644 --- a/drivers/acpi/acpi_lpit.c +++ b/drivers/acpi/acpi_lpit.c @@ -98,7 +98,7 @@ static void lpit_update_residency(struct lpit_residency_info *info, struct acpi_lpit_native *lpit_native) { info->frequency = lpit_native->counter_frequency ? - lpit_native->counter_frequency : tsc_khz * 1000; + lpit_native->counter_frequency : mul_u32_u32(tsc_khz, 1000U); if (!info->frequency) info->frequency = 1; diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index f08ffa75f4a7..8b44743945c8 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -450,8 +450,9 @@ static int register_device_clock(struct acpi_device *adev, if (!clk_name) return -ENOMEM; clk = clk_register_fractional_divider(NULL, clk_name, parent, + 0, prv_base, 1, 15, 16, 15, CLK_FRAC_DIVIDER_POWER_OF_TWO_PS, - prv_base, 1, 15, 16, 15, 0, NULL); + NULL); parent = clk_name; clk_name = kasprintf(GFP_KERNEL, "%s-update", devname); diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index ed318485eb19..756ab8edde83 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -513,6 +513,15 @@ static const struct dmi_system_id video_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 3350"), }, }, + { + .callback = video_set_report_key_events, + .driver_data = (void *)((uintptr_t)REPORT_BRIGHTNESS_KEY_EVENTS), + .ident = "COLORFUL X15 AT 23", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "COLORFUL"), + DMI_MATCH(DMI_PRODUCT_NAME, "X15 AT 23"), + }, + }, /* * Some machines change the brightness themselves when a brightness * hotkey gets pressed, despite us telling them not to. In this case @@ -1726,12 +1735,12 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device) return; count++; - acpi_get_parent(device->dev->handle, &acpi_parent); - - pdev = acpi_get_pci_dev(acpi_parent); - if (pdev) { - parent = &pdev->dev; - pci_dev_put(pdev); + if (ACPI_SUCCESS(acpi_get_parent(device->dev->handle, &acpi_parent))) { + pdev = acpi_get_pci_dev(acpi_parent); + if (pdev) { + parent = &pdev->dev; + pci_dev_put(pdev); + } } memset(&props, 0, sizeof(struct backlight_properties)); diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 9952f3a792ba..dd808cf65c84 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -100,6 +100,20 @@ static inline bool is_hest_type_generic_v2(struct ghes *ghes) } /* + * A platform may describe one error source for the handling of synchronous + * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI + * or External Interrupt). On x86, the HEST notifications are always + * asynchronous, so only SEA on ARM is delivered as a synchronous + * notification. + */ +static inline bool is_hest_sync_notify(struct ghes *ghes) +{ + u8 notify_type = ghes->generic->notify.type; + + return notify_type == ACPI_HEST_NOTIFY_SEA; +} + +/* * This driver isn't really modular, however for the time being, * continuing to use module_param is the easiest way to remain * compatible with existing boot arg use cases. @@ -461,7 +475,7 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags) } static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, - int sev) + int sev, bool sync) { int flags = -1; int sec_sev = ghes_severity(gdata->error_severity); @@ -475,7 +489,7 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED)) flags = MF_SOFT_OFFLINE; if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE) - flags = 0; + flags = sync ? MF_ACTION_REQUIRED : 0; if (flags != -1) return ghes_do_memory_failure(mem_err->physical_addr, flags); @@ -483,9 +497,11 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, return false; } -static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev) +static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, + int sev, bool sync) { struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata); + int flags = sync ? MF_ACTION_REQUIRED : 0; bool queued = false; int sec_sev, i; char *p; @@ -510,7 +526,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int s * and don't filter out 'corrected' error here. */ if (is_cache && has_pa) { - queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0); + queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags); p += err_info->length; continue; } @@ -631,6 +647,7 @@ static bool ghes_do_proc(struct ghes *ghes, const guid_t *fru_id = &guid_null; char *fru_text = ""; bool queued = false; + bool sync = is_hest_sync_notify(ghes); sev = ghes_severity(estatus->error_severity); apei_estatus_for_each_section(estatus, gdata) { @@ -648,13 +665,13 @@ static bool ghes_do_proc(struct ghes *ghes, ghes_edac_report_mem_error(sev, mem_err); arch_apei_report_mem_error(sev, mem_err); - queued = ghes_handle_memory_failure(gdata, sev); + queued = ghes_handle_memory_failure(gdata, sev, sync); } else if (guid_equal(sec_type, &CPER_SEC_PCIE)) { ghes_handle_aer(gdata); } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { - queued = ghes_handle_arm_hw_error(gdata, sev); + queued = ghes_handle_arm_hw_error(gdata, sev, sync); } else { void *err = acpi_hest_get_payload(gdata); diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 12f330b0eac0..b57de78fbf14 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -183,7 +183,7 @@ static int __init slit_valid(struct acpi_table_slit *slit) int i, j; int d = slit->locality_count; for (i = 0; i < d; i++) { - for (j = 0; j < d; j++) { + for (j = 0; j < d; j++) { u8 val = slit->entry[d*i + j]; if (i == j) { if (val != LOCAL_DISTANCE) @@ -532,7 +532,7 @@ int __init acpi_numa_init(void) */ /* fake_pxm is the next unused PXM value after SRAT parsing */ - for (i = 0, fake_pxm = -1; i < MAX_NUMNODES - 1; i++) { + for (i = 0, fake_pxm = -1; i < MAX_NUMNODES; i++) { if (node_to_pxm_map[i] > fake_pxm) fake_pxm = node_to_pxm_map[i]; } diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 0565c18c2ee3..62aee900af3d 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -851,6 +851,7 @@ static int acpi_get_ref_args(struct fwnode_reference_args *args, * @index: Index of the reference to return * @num_args: Maximum number of arguments after each reference * @args: Location to store the returned reference with optional arguments + * (may be NULL) * * Find property with @name, verifify that it is a package containing at least * one object reference and if so, store the ACPI device object pointer to the @@ -907,6 +908,9 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, if (!device) return -EINVAL; + if (!args) + return 0; + args->fwnode = acpi_fwnode_handle(device); args->nargs = 0; return 0; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index c297e40c5bdc..5ebeb0d7b6be 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -513,6 +513,13 @@ static const struct dmi_system_id maingear_laptop[] = { }, }, { + /* TongFang GMxXGxx sold as Eluktronics Inc. RP-15 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Eluktronics Inc."), + DMI_MATCH(DMI_BOARD_NAME, "RP-15"), + }, + }, + { /* TongFang GM6XGxX/TUXEDO Stellaris 16 Gen5 AMD */ .matches = { DMI_MATCH(DMI_BOARD_NAME, "GM6XGxX"), diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 9cc3a2b1b4fc..55cd17a13e75 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -477,6 +477,16 @@ binder_enqueue_thread_work_ilocked(struct binder_thread *thread, { WARN_ON(!list_empty(&thread->waiting_thread_node)); binder_enqueue_work_ilocked(work, &thread->todo); + + /* (e)poll-based threads require an explicit wakeup signal when + * queuing their own work; they rely on these events to consume + * messages without I/O block. Without it, threads risk waiting + * indefinitely without handling the work. + */ + if (thread->looper & BINDER_LOOPER_STATE_POLL && + thread->pid == current->pid && !thread->process_todo) + wake_up_interruptible_sync(&thread->wait); + thread->process_todo = true; } @@ -5005,7 +5015,7 @@ static __poll_t binder_poll(struct file *filp, thread = binder_get_thread(proc); if (!thread) - return POLLERR; + return EPOLLERR; binder_inner_proc_lock(thread->proc); thread->looper |= BINDER_LOOPER_STATE_POLL; diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index cd87f12733f2..fcbb750b1ccc 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -271,7 +271,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, } if (mm) { mmap_write_unlock(mm); - mmput(mm); + mmput_async(mm); } return 0; @@ -304,7 +304,7 @@ err_page_ptr_cleared: err_no_vma: if (mm) { mmap_write_unlock(mm); - mmput(mm); + mmput_async(mm); } return vma ? -ENOMEM : -ESRCH; } @@ -344,8 +344,7 @@ static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid) continue; if (!buffer->async_transaction) continue; - total_alloc_size += binder_alloc_buffer_size(alloc, buffer) - + sizeof(struct binder_buffer); + total_alloc_size += binder_alloc_buffer_size(alloc, buffer); num_buffers++; } @@ -407,17 +406,17 @@ static struct binder_buffer *binder_alloc_new_buf_locked( alloc->pid, extra_buffers_size); return ERR_PTR(-EINVAL); } - if (is_async && - alloc->free_async_space < size + sizeof(struct binder_buffer)) { + + /* Pad 0-size buffers so they get assigned unique addresses */ + size = max(size, sizeof(void *)); + + if (is_async && alloc->free_async_space < size) { binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, "%d: binder_alloc_buf size %zd failed, no async space left\n", alloc->pid, size); return ERR_PTR(-ENOSPC); } - /* Pad 0-size buffers so they get assigned unique addresses */ - size = max(size, sizeof(void *)); - while (n) { buffer = rb_entry(n, struct binder_buffer, rb_node); BUG_ON(!buffer->free); @@ -519,7 +518,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked( buffer->pid = pid; buffer->oneway_spam_suspect = false; if (is_async) { - alloc->free_async_space -= size + sizeof(struct binder_buffer); + alloc->free_async_space -= size; binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC, "%d: binder_alloc_buf size %zd async free %zd\n", alloc->pid, size, alloc->free_async_space); @@ -557,7 +556,7 @@ err_alloc_buf_struct_failed: * is the sum of the three given sizes (each rounded up to * pointer-sized boundary) * - * Return: The allocated buffer or %NULL if error + * Return: The allocated buffer or %ERR_PTR(-errno) if error */ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, size_t data_size, @@ -657,8 +656,7 @@ static void binder_free_buf_locked(struct binder_alloc *alloc, BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size); if (buffer->async_transaction) { - alloc->free_async_space += buffer_size + sizeof(struct binder_buffer); - + alloc->free_async_space += buffer_size; binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC, "%d: binder_free_buf size %zd async free %zd\n", alloc->pid, size, alloc->free_async_space); @@ -706,7 +704,7 @@ void binder_alloc_free_buf(struct binder_alloc *alloc, /* * We could eliminate the call to binder_alloc_clear_buf() * from binder_alloc_deferred_release() by moving this to - * binder_alloc_free_buf_locked(). However, that could + * binder_free_buf_locked(). However, that could * increase contention for the alloc mutex if clear_on_free * is used frequently for large buffers. The mutex is not * needed for correctness here. @@ -1005,7 +1003,9 @@ enum lru_status binder_alloc_free_page(struct list_head *item, goto err_mmget; if (!mmap_read_trylock(mm)) goto err_mmap_read_lock_failed; - vma = binder_alloc_get_vma(alloc); + vma = vma_lookup(mm, page_addr); + if (vma && vma != binder_alloc_get_vma(alloc)) + goto err_invalid_vma; list_lru_isolate(lru, item); spin_unlock(lock); @@ -1031,6 +1031,8 @@ enum lru_status binder_alloc_free_page(struct list_head *item, mutex_unlock(&alloc->mutex); return LRU_REMOVED_RETRY; +err_invalid_vma: + mmap_read_unlock(mm); err_mmap_read_lock_failed: mmput_async(mm); err_mmget: diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 805645efb3cc..1790a2ecb9fa 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -49,6 +49,7 @@ enum { enum board_ids { /* board IDs by feature in alphabetical order */ board_ahci, + board_ahci_43bit_dma, board_ahci_ign_iferr, board_ahci_low_power, board_ahci_no_debounce_delay, @@ -129,6 +130,13 @@ static const struct ata_port_info ahci_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &ahci_ops, }, + [board_ahci_43bit_dma] = { + AHCI_HFLAGS (AHCI_HFLAG_43BIT_ONLY), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_ign_iferr] = { AHCI_HFLAGS (AHCI_HFLAG_IGN_IRQ_IF_ERR), .flags = AHCI_FLAG_COMMON, @@ -597,14 +605,19 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(PROMISE, 0x3f20), board_ahci }, /* PDC42819 */ { PCI_VDEVICE(PROMISE, 0x3781), board_ahci }, /* FastTrak TX8660 ahci-mode */ - /* Asmedia */ - { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci }, /* ASM1060 */ - { PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci }, /* ASM1060 */ - { PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci }, /* ASM1061 */ - { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */ - { PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci }, /* ASM1061R */ - { PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci }, /* ASM1062R */ - { PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci }, /* ASM1062+JMB575 */ + /* ASMedia */ + { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci_43bit_dma }, /* ASM1060 */ + { PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci_43bit_dma }, /* ASM1060 */ + { PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci_43bit_dma }, /* ASM1061 */ + { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci_43bit_dma }, /* ASM1061/1062 */ + { PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci_43bit_dma }, /* ASM1061R */ + { PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci_43bit_dma }, /* ASM1062R */ + { PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci_43bit_dma }, /* ASM1062+JMB575 */ + { PCI_VDEVICE(ASMEDIA, 0x1062), board_ahci }, /* ASM1062A */ + { PCI_VDEVICE(ASMEDIA, 0x1064), board_ahci }, /* ASM1064 */ + { PCI_VDEVICE(ASMEDIA, 0x1164), board_ahci }, /* ASM1164 */ + { PCI_VDEVICE(ASMEDIA, 0x1165), board_ahci }, /* ASM1165 */ + { PCI_VDEVICE(ASMEDIA, 0x1166), board_ahci }, /* ASM1166 */ /* * Samsung SSDs found on some macbooks. NCQ times out if MSI is @@ -658,6 +671,11 @@ MODULE_PARM_DESC(mobile_lpm_policy, "Default LPM policy for mobile chipsets"); static void ahci_pci_save_initial_config(struct pci_dev *pdev, struct ahci_host_priv *hpriv) { + if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == 0x1166) { + dev_info(&pdev->dev, "ASM1166 has only six ports\n"); + hpriv->saved_port_map = 0x3f; + } + if (pdev->vendor == PCI_VENDOR_ID_JMICRON && pdev->device == 0x2361) { dev_info(&pdev->dev, "JMB361 has only one port\n"); hpriv->saved_port_map = 1; @@ -944,11 +962,20 @@ static int ahci_pci_device_resume(struct device *dev) #endif /* CONFIG_PM */ -static int ahci_configure_dma_masks(struct pci_dev *pdev, int using_dac) +static int ahci_configure_dma_masks(struct pci_dev *pdev, + struct ahci_host_priv *hpriv) { - const int dma_bits = using_dac ? 64 : 32; + int dma_bits; int rc; + if (hpriv->cap & HOST_CAP_64) { + dma_bits = 64; + if (hpriv->flags & AHCI_HFLAG_43BIT_ONLY) + dma_bits = 43; + } else { + dma_bits = 32; + } + /* * If the device fixup already set the dma_mask to some non-standard * value, don't extend it here. This happens on STA2X11, for example. @@ -1921,7 +1948,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) ahci_gtf_filter_workaround(host); /* initialize adapter */ - rc = ahci_configure_dma_masks(pdev, hpriv->cap & HOST_CAP_64); + rc = ahci_configure_dma_masks(pdev, hpriv); if (rc) return rc; diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index ff8e6ae1c636..f9c5906a8afa 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -247,6 +247,7 @@ enum { AHCI_HFLAG_SUSPEND_PHYS = BIT(26), /* handle PHYs during suspend/resume */ AHCI_HFLAG_NO_SXS = BIT(28), /* SXS not supported */ + AHCI_HFLAG_43BIT_ONLY = BIT(29), /* 43bit DMA addr limit */ /* ap->flags bits */ diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c index cb24ecf36faf..50e07ea60e45 100644 --- a/drivers/ata/ahci_ceva.c +++ b/drivers/ata/ahci_ceva.c @@ -88,7 +88,6 @@ struct ceva_ahci_priv { u32 axicc; bool is_cci_enabled; int flags; - struct reset_control *rst; }; static unsigned int ceva_ahci_read_id(struct ata_device *dev, @@ -189,6 +188,60 @@ static struct scsi_host_template ahci_platform_sht = { AHCI_SHT(DRV_NAME), }; +static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv) +{ + int rc, i; + + rc = ahci_platform_enable_regulators(hpriv); + if (rc) + return rc; + + rc = ahci_platform_enable_clks(hpriv); + if (rc) + goto disable_regulator; + + /* Assert the controller reset */ + rc = ahci_platform_assert_rsts(hpriv); + if (rc) + goto disable_clks; + + for (i = 0; i < hpriv->nports; i++) { + rc = phy_init(hpriv->phys[i]); + if (rc) + goto disable_rsts; + } + + /* De-assert the controller reset */ + ahci_platform_deassert_rsts(hpriv); + + for (i = 0; i < hpriv->nports; i++) { + rc = phy_power_on(hpriv->phys[i]); + if (rc) { + phy_exit(hpriv->phys[i]); + goto disable_phys; + } + } + + return 0; + +disable_rsts: + ahci_platform_deassert_rsts(hpriv); + +disable_phys: + while (--i >= 0) { + phy_power_off(hpriv->phys[i]); + phy_exit(hpriv->phys[i]); + } + +disable_clks: + ahci_platform_disable_clks(hpriv); + +disable_regulator: + ahci_platform_disable_regulators(hpriv); + + return rc; +} + static int ceva_ahci_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; @@ -203,47 +256,19 @@ static int ceva_ahci_probe(struct platform_device *pdev) return -ENOMEM; cevapriv->ahci_pdev = pdev; - - cevapriv->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, - NULL); - if (IS_ERR(cevapriv->rst)) - dev_err_probe(&pdev->dev, PTR_ERR(cevapriv->rst), - "failed to get reset\n"); - hpriv = ahci_platform_get_resources(pdev, 0); if (IS_ERR(hpriv)) return PTR_ERR(hpriv); - if (!cevapriv->rst) { - rc = ahci_platform_enable_resources(hpriv); - if (rc) - return rc; - } else { - int i; + hpriv->rsts = devm_reset_control_get_optional_exclusive(&pdev->dev, + NULL); + if (IS_ERR(hpriv->rsts)) + return dev_err_probe(&pdev->dev, PTR_ERR(hpriv->rsts), + "failed to get reset\n"); - rc = ahci_platform_enable_clks(hpriv); - if (rc) - return rc; - /* Assert the controller reset */ - reset_control_assert(cevapriv->rst); - - for (i = 0; i < hpriv->nports; i++) { - rc = phy_init(hpriv->phys[i]); - if (rc) - return rc; - } - - /* De-assert the controller reset */ - reset_control_deassert(cevapriv->rst); - - for (i = 0; i < hpriv->nports; i++) { - rc = phy_power_on(hpriv->phys[i]); - if (rc) { - phy_exit(hpriv->phys[i]); - return rc; - } - } - } + rc = ceva_ahci_platform_enable_resources(hpriv); + if (rc) + return rc; if (of_property_read_bool(np, "ceva,broken-gen2")) cevapriv->flags = CEVA_FLAG_BROKEN_GEN2; @@ -252,52 +277,60 @@ static int ceva_ahci_probe(struct platform_device *pdev) if (of_property_read_u8_array(np, "ceva,p0-cominit-params", (u8 *)&cevapriv->pp2c[0], 4) < 0) { dev_warn(dev, "ceva,p0-cominit-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u8_array(np, "ceva,p1-cominit-params", (u8 *)&cevapriv->pp2c[1], 4) < 0) { dev_warn(dev, "ceva,p1-cominit-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* Read OOB timing value for COMWAKE from device-tree*/ if (of_property_read_u8_array(np, "ceva,p0-comwake-params", (u8 *)&cevapriv->pp3c[0], 4) < 0) { dev_warn(dev, "ceva,p0-comwake-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u8_array(np, "ceva,p1-comwake-params", (u8 *)&cevapriv->pp3c[1], 4) < 0) { dev_warn(dev, "ceva,p1-comwake-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* Read phy BURST timing value from device-tree */ if (of_property_read_u8_array(np, "ceva,p0-burst-params", (u8 *)&cevapriv->pp4c[0], 4) < 0) { dev_warn(dev, "ceva,p0-burst-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u8_array(np, "ceva,p1-burst-params", (u8 *)&cevapriv->pp4c[1], 4) < 0) { dev_warn(dev, "ceva,p1-burst-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* Read phy RETRY interval timing value from device-tree */ if (of_property_read_u16_array(np, "ceva,p0-retry-params", (u16 *)&cevapriv->pp5c[0], 2) < 0) { dev_warn(dev, "ceva,p0-retry-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u16_array(np, "ceva,p1-retry-params", (u16 *)&cevapriv->pp5c[1], 2) < 0) { dev_warn(dev, "ceva,p1-retry-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* @@ -335,7 +368,7 @@ static int __maybe_unused ceva_ahci_resume(struct device *dev) struct ahci_host_priv *hpriv = host->private_data; int rc; - rc = ahci_platform_enable_resources(hpriv); + rc = ceva_ahci_platform_enable_resources(hpriv); if (rc) return rc; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index fa2fc1953fc2..f14e56a5cff6 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2005,6 +2005,10 @@ void ata_dev_power_set_active(struct ata_device *dev) struct ata_taskfile tf; unsigned int err_mask; + /* If the device is already sleeping, do nothing. */ + if (dev->flags & ATA_DFLAG_SLEEPING) + return; + /* * Issue READ VERIFY SECTORS command for 1 sector at lba=0 only * if supported by the device. diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 49cb4537344a..2daf50d4cd47 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -2930,6 +2930,8 @@ open_card_ubr0(struct idt77252_dev *card) vc->scq = alloc_scq(card, vc->class); if (!vc->scq) { printk("%s: can't get SCQ.\n", card->name); + kfree(card->vcs[0]); + card->vcs[0] = NULL; return -ENOMEM; } diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index eaa31e567d1e..5b59d133b6af 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -144,7 +144,7 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid) unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); -static int __init early_cpu_to_node(int cpu) +int __init early_cpu_to_node(int cpu) { return cpu_to_node_map[cpu]; } diff --git a/drivers/base/core.c b/drivers/base/core.c index af90bfb0cc3d..3078f44dc186 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -337,10 +337,12 @@ static bool device_is_ancestor(struct device *dev, struct device *target) return false; } +#define DL_MARKER_FLAGS (DL_FLAG_INFERRED | \ + DL_FLAG_CYCLE | \ + DL_FLAG_MANAGED) static inline bool device_link_flag_is_sync_state_only(u32 flags) { - return (flags & ~(DL_FLAG_INFERRED | DL_FLAG_CYCLE)) == - (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED); + return (flags & ~DL_MARKER_FLAGS) == DL_FLAG_SYNC_STATE_ONLY; } /** @@ -2054,9 +2056,14 @@ static int fw_devlink_create_devlink(struct device *con, /* * SYNC_STATE_ONLY device links don't block probing and supports cycles. - * So cycle detection isn't necessary and shouldn't be done. + * So, one might expect that cycle detection isn't necessary for them. + * However, if the device link was marked as SYNC_STATE_ONLY because + * it's part of a cycle, then we still need to do cycle detection. This + * is because the consumer and supplier might be part of multiple cycles + * and we need to detect all those cycles. */ - if (!(flags & DL_FLAG_SYNC_STATE_ONLY)) { + if (!device_link_flag_is_sync_state_only(flags) || + flags & DL_FLAG_CYCLE) { device_links_write_lock(); if (__fw_devlink_relax_cycles(con, sup_handle)) { __fwnode_link_cycle(link); diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 9aa0da991cfb..5d39f3e374da 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -175,6 +175,9 @@ int memory_notify(unsigned long val, void *v) return blocking_notifier_call_chain(&memory_chain, val, v); } +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_online(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -193,10 +196,11 @@ static int memory_block_online(struct memory_block *mem) * stage helps to keep accounting easier to follow - e.g vmemmaps * belong to the same zone as the memory they backed. */ + mem_hotplug_begin(); if (nr_vmemmap_pages) { ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); if (ret) - return ret; + goto out; } ret = online_pages(start_pfn + nr_vmemmap_pages, @@ -204,7 +208,7 @@ static int memory_block_online(struct memory_block *mem) if (ret) { if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); - return ret; + goto out; } /* @@ -216,9 +220,14 @@ static int memory_block_online(struct memory_block *mem) nr_vmemmap_pages); mem->zone = zone; +out: + mem_hotplug_done(); return ret; } +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_offline(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -233,6 +242,7 @@ static int memory_block_offline(struct memory_block *mem) * Unaccount before offlining, such that unpopulated zone and kthreads * can properly be torn down in offline_pages(). */ + mem_hotplug_begin(); if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, -nr_vmemmap_pages); @@ -244,13 +254,15 @@ static int memory_block_offline(struct memory_block *mem) if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, nr_vmemmap_pages); - return ret; + goto out; } if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); mem->zone = NULL; +out: + mem_hotplug_done(); return ret; } diff --git a/drivers/base/node.c b/drivers/base/node.c index faf3597a96da..a4141b57b147 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -859,11 +859,15 @@ int __register_one_node(int nid) { int error; int cpu; + struct node *node; - node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL); - if (!node_devices[nid]) + node = kzalloc(sizeof(struct node), GFP_KERNEL); + if (!node) return -ENOMEM; + INIT_LIST_HEAD(&node->access_list); + node_devices[nid] = node; + error = register_node(node_devices[nid], nid); /* link cpu under this node */ @@ -872,7 +876,6 @@ int __register_one_node(int nid) register_cpu_under_node(cpu, nid); } - INIT_LIST_HEAD(&node_devices[nid]->access_list); node_init_caches(nid); return error; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 56ceba469802..d238b47f74c3 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1052,7 +1052,7 @@ static int __init genpd_power_off_unused(void) return 0; } -late_initcall(genpd_power_off_unused); +late_initcall_sync(genpd_power_off_unused); #ifdef CONFIG_PM_SLEEP diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index c50139207794..9c5a5f4dba5a 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -579,7 +579,7 @@ bool dev_pm_skip_resume(struct device *dev) } /** - * device_resume_noirq - Execute a "noirq resume" callback for given device. + * __device_resume_noirq - Execute a "noirq resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. @@ -587,7 +587,7 @@ bool dev_pm_skip_resume(struct device *dev) * The driver of @dev will not receive interrupts while this function is being * executed. */ -static int device_resume_noirq(struct device *dev, pm_message_t state, bool async) +static void __device_resume_noirq(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -655,7 +655,13 @@ Skip: Out: complete_all(&dev->power.completion); TRACE_RESUME(error); - return error; + + if (error) { + suspend_stats.failed_resume_noirq++; + dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); + } } static bool is_async(struct device *dev) @@ -668,27 +674,35 @@ static bool dpm_async_fn(struct device *dev, async_func_t func) { reinit_completion(&dev->power.completion); - if (is_async(dev)) { - get_device(dev); - async_schedule_dev(func, dev); + if (!is_async(dev)) + return false; + + get_device(dev); + + if (async_schedule_dev_nocall(func, dev)) return true; - } + + put_device(dev); return false; } static void async_resume_noirq(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; - int error; - - error = device_resume_noirq(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + struct device *dev = data; + __device_resume_noirq(dev, pm_transition, true); put_device(dev); } +static void device_resume_noirq(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume_noirq)) + return; + + __device_resume_noirq(dev, pm_transition, false); +} + static void dpm_noirq_resume_devices(pm_message_t state) { struct device *dev; @@ -698,14 +712,6 @@ static void dpm_noirq_resume_devices(pm_message_t state) mutex_lock(&dpm_list_mtx); pm_transition = state; - /* - * Advanced the async threads upfront, - * in case the starting of async threads is - * delayed by non-async resuming devices. - */ - list_for_each_entry(dev, &dpm_noirq_list, power.entry) - dpm_async_fn(dev, async_resume_noirq); - while (!list_empty(&dpm_noirq_list)) { dev = to_device(dpm_noirq_list.next); get_device(dev); @@ -713,17 +719,7 @@ static void dpm_noirq_resume_devices(pm_message_t state) mutex_unlock(&dpm_list_mtx); - if (!is_async(dev)) { - int error; - - error = device_resume_noirq(dev, state, false); - if (error) { - suspend_stats.failed_resume_noirq++; - dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, " noirq", error); - } - } + device_resume_noirq(dev); put_device(dev); @@ -751,14 +747,14 @@ void dpm_resume_noirq(pm_message_t state) } /** - * device_resume_early - Execute an "early resume" callback for given device. + * __device_resume_early - Execute an "early resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. * * Runtime PM is disabled for @dev while this function is being executed. */ -static int device_resume_early(struct device *dev, pm_message_t state, bool async) +static void __device_resume_early(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -811,21 +807,31 @@ Out: pm_runtime_enable(dev); complete_all(&dev->power.completion); - return error; + + if (error) { + suspend_stats.failed_resume_early++; + dpm_save_failed_step(SUSPEND_RESUME_EARLY); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async early" : " early", error); + } } static void async_resume_early(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; - int error; - - error = device_resume_early(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + struct device *dev = data; + __device_resume_early(dev, pm_transition, true); put_device(dev); } +static void device_resume_early(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume_early)) + return; + + __device_resume_early(dev, pm_transition, false); +} + /** * dpm_resume_early - Execute "early resume" callbacks for all devices. * @state: PM transition of the system being carried out. @@ -839,14 +845,6 @@ void dpm_resume_early(pm_message_t state) mutex_lock(&dpm_list_mtx); pm_transition = state; - /* - * Advanced the async threads upfront, - * in case the starting of async threads is - * delayed by non-async resuming devices. - */ - list_for_each_entry(dev, &dpm_late_early_list, power.entry) - dpm_async_fn(dev, async_resume_early); - while (!list_empty(&dpm_late_early_list)) { dev = to_device(dpm_late_early_list.next); get_device(dev); @@ -854,17 +852,7 @@ void dpm_resume_early(pm_message_t state) mutex_unlock(&dpm_list_mtx); - if (!is_async(dev)) { - int error; - - error = device_resume_early(dev, state, false); - if (error) { - suspend_stats.failed_resume_early++; - dpm_save_failed_step(SUSPEND_RESUME_EARLY); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, " early", error); - } - } + device_resume_early(dev); put_device(dev); @@ -888,12 +876,12 @@ void dpm_resume_start(pm_message_t state) EXPORT_SYMBOL_GPL(dpm_resume_start); /** - * device_resume - Execute "resume" callbacks for given device. + * __device_resume - Execute "resume" callbacks for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. */ -static int device_resume(struct device *dev, pm_message_t state, bool async) +static void __device_resume(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -975,20 +963,30 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) TRACE_RESUME(error); - return error; + if (error) { + suspend_stats.failed_resume++; + dpm_save_failed_step(SUSPEND_RESUME); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async" : "", error); + } } static void async_resume(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; - int error; + struct device *dev = data; - error = device_resume(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + __device_resume(dev, pm_transition, true); put_device(dev); } +static void device_resume(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume)) + return; + + __device_resume(dev, pm_transition, false); +} + /** * dpm_resume - Execute "resume" callbacks for non-sysdev devices. * @state: PM transition of the system being carried out. @@ -1008,27 +1006,17 @@ void dpm_resume(pm_message_t state) pm_transition = state; async_error = 0; - list_for_each_entry(dev, &dpm_suspended_list, power.entry) - dpm_async_fn(dev, async_resume); - while (!list_empty(&dpm_suspended_list)) { dev = to_device(dpm_suspended_list.next); + get_device(dev); - if (!is_async(dev)) { - int error; - mutex_unlock(&dpm_list_mtx); + mutex_unlock(&dpm_list_mtx); + + device_resume(dev); - error = device_resume(dev, state, false); - if (error) { - suspend_stats.failed_resume++; - dpm_save_failed_step(SUSPEND_RESUME); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, "", error); - } + mutex_lock(&dpm_list_mtx); - mutex_lock(&dpm_list_mtx); - } if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list); @@ -1269,7 +1257,7 @@ Complete: static void async_suspend_noirq(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; + struct device *dev = data; int error; error = __device_suspend_noirq(dev, pm_transition, true); @@ -1450,7 +1438,7 @@ Complete: static void async_suspend_late(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; + struct device *dev = data; int error; error = __device_suspend_late(dev, pm_transition, true); @@ -1727,7 +1715,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) static void async_suspend(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; + struct device *dev = data; int error; error = __device_suspend(dev, pm_transition, true); diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index 72b7a92337b1..cd6e559648b2 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -120,7 +120,7 @@ static unsigned int read_magic_time(void) struct rtc_time time; unsigned int val; - if (mc146818_get_time(&time) < 0) { + if (mc146818_get_time(&time, 1000) < 0) { pr_err("Unable to read current time from RTC\n"); return 0; } diff --git a/drivers/base/property.c b/drivers/base/property.c index b0c40d973484..eb9b01c2ff1d 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -17,12 +17,19 @@ #include <linux/property.h> #include <linux/phy.h> -struct fwnode_handle *dev_fwnode(const struct device *dev) +struct fwnode_handle *__dev_fwnode(struct device *dev) { return IS_ENABLED(CONFIG_OF) && dev->of_node ? of_fwnode_handle(dev->of_node) : dev->fwnode; } -EXPORT_SYMBOL_GPL(dev_fwnode); +EXPORT_SYMBOL_GPL(__dev_fwnode); + +const struct fwnode_handle *__dev_fwnode_const(const struct device *dev) +{ + return IS_ENABLED(CONFIG_OF) && dev->of_node ? + of_fwnode_handle(dev->of_node) : dev->fwnode; +} +EXPORT_SYMBOL_GPL(__dev_fwnode_const); /** * device_property_present - check if a property of a device is present diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index 0a482212c7e8..44153caa893a 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -541,6 +541,9 @@ software_node_get_reference_args(const struct fwnode_handle *fwnode, if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; + if (!args) + return 0; + args->fwnode = software_node_get(refnode); args->nargs = nargs; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 128722cf6c3c..827802e418dd 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -333,6 +333,7 @@ aoeblk_gdalloc(void *vp) struct gendisk *gd; mempool_t *mp; struct blk_mq_tag_set *set; + sector_t ssize; ulong flags; int late = 0; int err; @@ -395,7 +396,7 @@ aoeblk_gdalloc(void *vp) gd->minors = AOE_PARTITIONS; gd->fops = &aoe_bdops; gd->private_data = d; - set_capacity(gd, d->ssize); + ssize = d->ssize; snprintf(gd->disk_name, sizeof gd->disk_name, "etherd/e%ld.%d", d->aoemajor, d->aoeminor); @@ -404,6 +405,8 @@ aoeblk_gdalloc(void *vp) spin_unlock_irqrestore(&d->lock, flags); + set_capacity(gd, ssize); + err = device_add_disk(NULL, gd, aoe_attr_groups); if (err) goto out_disk_cleanup; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 426d0b42685a..12ff6f58b8a9 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -165,39 +165,37 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file) return get_size(lo->lo_offset, lo->lo_sizelimit, file); } +/* + * We support direct I/O only if lo_offset is aligned with the logical I/O size + * of backing device, and the logical block size of loop is bigger than that of + * the backing device. + */ +static bool lo_bdev_can_use_dio(struct loop_device *lo, + struct block_device *backing_bdev) +{ + unsigned short sb_bsize = bdev_logical_block_size(backing_bdev); + + if (queue_logical_block_size(lo->lo_queue) < sb_bsize) + return false; + if (lo->lo_offset & (sb_bsize - 1)) + return false; + return true; +} + static void __loop_update_dio(struct loop_device *lo, bool dio) { struct file *file = lo->lo_backing_file; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - unsigned short sb_bsize = 0; - unsigned dio_align = 0; + struct inode *inode = file->f_mapping->host; + struct block_device *backing_bdev = NULL; bool use_dio; - if (inode->i_sb->s_bdev) { - sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev); - dio_align = sb_bsize - 1; - } + if (S_ISBLK(inode->i_mode)) + backing_bdev = I_BDEV(inode); + else if (inode->i_sb->s_bdev) + backing_bdev = inode->i_sb->s_bdev; - /* - * We support direct I/O only if lo_offset is aligned with the - * logical I/O size of backing device, and the logical block - * size of loop is bigger than the backing device's. - * - * TODO: the above condition may be loosed in the future, and - * direct I/O may be switched runtime at that time because most - * of requests in sane applications should be PAGE_SIZE aligned - */ - if (dio) { - if (queue_logical_block_size(lo->lo_queue) >= sb_bsize && - !(lo->lo_offset & dio_align) && - (file->f_mode & FMODE_CAN_ODIRECT)) - use_dio = true; - else - use_dio = false; - } else { - use_dio = false; - } + use_dio = dio && (file->f_mode & FMODE_CAN_ODIRECT) && + (!backing_bdev || lo_bdev_can_use_dio(lo, backing_bdev)); if (lo->use_dio == use_dio) return; @@ -1777,14 +1775,43 @@ static const struct block_device_operations lo_fops = { /* * If max_loop is specified, create that many devices upfront. * This also becomes a hard limit. If max_loop is not specified, + * the default isn't a hard limit (as before commit 85c50197716c + * changed the default value from 0 for max_loop=0 reasons), just * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module * init time. Loop devices can be requested on-demand with the * /dev/loop-control interface, or be instantiated by accessing * a 'dead' device node. */ static int max_loop = CONFIG_BLK_DEV_LOOP_MIN_COUNT; -module_param(max_loop, int, 0444); + +#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD +static bool max_loop_specified; + +static int max_loop_param_set_int(const char *val, + const struct kernel_param *kp) +{ + int ret; + + ret = param_set_int(val, kp); + if (ret < 0) + return ret; + + max_loop_specified = true; + return 0; +} + +static const struct kernel_param_ops max_loop_param_ops = { + .set = max_loop_param_set_int, + .get = param_get_int, +}; + +module_param_cb(max_loop, &max_loop_param_ops, &max_loop, 0444); MODULE_PARM_DESC(max_loop, "Maximum number of loop devices"); +#else +module_param(max_loop, int, 0444); +MODULE_PARM_DESC(max_loop, "Initial number of loop devices"); +#endif + module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device"); @@ -2089,14 +2116,18 @@ static void loop_remove(struct loop_device *lo) put_disk(lo->lo_disk); } +#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD static void loop_probe(dev_t dev) { int idx = MINOR(dev) >> part_shift; - if (max_loop && idx >= max_loop) + if (max_loop_specified && max_loop && idx >= max_loop) return; loop_add(idx); } +#else +#define loop_probe NULL +#endif /* !CONFIG_BLOCK_LEGACY_AUTOLOAD */ static int loop_control_remove(int idx) { @@ -2277,6 +2308,9 @@ module_exit(loop_exit); static int __init max_loop_setup(char *str) { max_loop = simple_strtol(str, NULL, 0); +#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD + max_loop_specified = true; +#endif return 1; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 8037aaefeb2e..9a53165de4ce 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -494,7 +494,7 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, struct iov_iter *iter, int msg_flags, int *sent) { int result; - struct msghdr msg; + struct msghdr msg = { }; unsigned int noreclaim_flag; if (unlikely(!sock)) { @@ -509,10 +509,6 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, noreclaim_flag = memalloc_noreclaim_save(); do { sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC; - msg.msg_name = NULL; - msg.msg_namelen = 0; - msg.msg_control = NULL; - msg.msg_controllen = 0; msg.msg_flags = msg_flags | MSG_NOSIGNAL; if (send) diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index e9f38eba2f13..959952e8ede3 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -2114,11 +2114,8 @@ static int null_add_dev(struct nullb_device *dev) blk_queue_logical_block_size(nullb->q, dev->blocksize); blk_queue_physical_block_size(nullb->q, dev->blocksize); - if (!dev->max_sectors) - dev->max_sectors = queue_max_hw_sectors(nullb->q); - dev->max_sectors = min_t(unsigned int, dev->max_sectors, - BLK_DEF_MAX_SECTORS); - blk_queue_max_hw_sectors(nullb->q, dev->max_sectors); + if (dev->max_sectors) + blk_queue_max_hw_sectors(nullb->q, dev->max_sectors); if (dev->virt_boundary) blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1); @@ -2218,12 +2215,6 @@ static int __init null_init(void) g_bs = PAGE_SIZE; } - if (g_max_sectors > BLK_DEF_MAX_SECTORS) { - pr_warn("invalid max sectors\n"); - pr_warn("defaults max sectors to %u\n", BLK_DEF_MAX_SECTORS); - g_max_sectors = BLK_DEF_MAX_SECTORS; - } - if (g_home_node != NUMA_NO_NODE && g_home_node >= nr_online_nodes) { pr_err("invalid home_node value\n"); g_home_node = NUMA_NO_NODE; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index afc92869cba4..f58ca9ce3503 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3453,14 +3453,15 @@ static bool rbd_lock_add_request(struct rbd_img_request *img_req) static void rbd_lock_del_request(struct rbd_img_request *img_req) { struct rbd_device *rbd_dev = img_req->rbd_dev; - bool need_wakeup; + bool need_wakeup = false; lockdep_assert_held(&rbd_dev->lock_rwsem); spin_lock(&rbd_dev->lock_lists_lock); - rbd_assert(!list_empty(&img_req->lock_item)); - list_del_init(&img_req->lock_item); - need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING && - list_empty(&rbd_dev->running_list)); + if (!list_empty(&img_req->lock_item)) { + list_del_init(&img_req->lock_item); + need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING && + list_empty(&rbd_dev->running_list)); + } spin_unlock(&rbd_dev->lock_lists_lock); if (need_wakeup) complete(&rbd_dev->releasing_wait); @@ -3843,14 +3844,19 @@ static void wake_lock_waiters(struct rbd_device *rbd_dev, int result) return; } - list_for_each_entry(img_req, &rbd_dev->acquiring_list, lock_item) { + while (!list_empty(&rbd_dev->acquiring_list)) { + img_req = list_first_entry(&rbd_dev->acquiring_list, + struct rbd_img_request, lock_item); mutex_lock(&img_req->state_mutex); rbd_assert(img_req->state == RBD_IMG_EXCLUSIVE_LOCK); + if (!result) + list_move_tail(&img_req->lock_item, + &rbd_dev->running_list); + else + list_del_init(&img_req->lock_item); rbd_img_schedule(img_req, result); mutex_unlock(&img_req->state_mutex); } - - list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list); } static bool locker_equal(const struct ceph_locker *lhs, diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index 2cfed2e58d64..ad451224e663 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -587,6 +587,7 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess, { char *full_path; char *a, *b; + int len; full_path = kmalloc(PATH_MAX, GFP_KERNEL); if (!full_path) @@ -598,19 +599,19 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess, */ a = strnstr(dev_search_path, "%SESSNAME%", sizeof(dev_search_path)); if (a) { - int len = a - dev_search_path; + len = a - dev_search_path; len = snprintf(full_path, PATH_MAX, "%.*s/%s/%s", len, dev_search_path, srv_sess->sessname, dev_name); - if (len >= PATH_MAX) { - pr_err("Too long path: %s, %s, %s\n", - dev_search_path, srv_sess->sessname, dev_name); - kfree(full_path); - return ERR_PTR(-EINVAL); - } } else { - snprintf(full_path, PATH_MAX, "%s/%s", - dev_search_path, dev_name); + len = snprintf(full_path, PATH_MAX, "%s/%s", + dev_search_path, dev_name); + } + if (len >= PATH_MAX) { + pr_err("Too long path: %s, %s, %s\n", + dev_search_path, srv_sess->sessname, dev_name); + kfree(full_path); + return ERR_PTR(-EINVAL); } /* eliminitate duplicated slashes */ diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c2f0f74193f0..3fa74051f31b 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -103,6 +103,9 @@ struct ublk_uring_cmd_pdu { */ #define UBLK_IO_FLAG_NEED_GET_DATA 0x08 +/* atomic RW with ubq->cancel_lock */ +#define UBLK_IO_FLAG_CANCELED 0x80000000 + struct ublk_io { /* userspace buffer address from io cmd */ __u64 addr; @@ -126,6 +129,7 @@ struct ublk_queue { unsigned int max_io_sz; bool force_abort; unsigned short nr_io_ready; /* how many ios setup */ + spinlock_t cancel_lock; struct ublk_device *dev; struct ublk_io ios[]; }; @@ -1045,28 +1049,28 @@ static inline bool ublk_queue_ready(struct ublk_queue *ubq) return ubq->nr_io_ready == ubq->q_depth; } -static void ublk_cmd_cancel_cb(struct io_uring_cmd *cmd, unsigned issue_flags) -{ - io_uring_cmd_done(cmd, UBLK_IO_RES_ABORT, 0, issue_flags); -} - static void ublk_cancel_queue(struct ublk_queue *ubq) { int i; - if (!ublk_queue_ready(ubq)) - return; - for (i = 0; i < ubq->q_depth; i++) { struct ublk_io *io = &ubq->ios[i]; - if (io->flags & UBLK_IO_FLAG_ACTIVE) - io_uring_cmd_complete_in_task(io->cmd, - ublk_cmd_cancel_cb); - } + if (io->flags & UBLK_IO_FLAG_ACTIVE) { + bool done; - /* all io commands are canceled */ - ubq->nr_io_ready = 0; + spin_lock(&ubq->cancel_lock); + done = !!(io->flags & UBLK_IO_FLAG_CANCELED); + if (!done) + io->flags |= UBLK_IO_FLAG_CANCELED; + spin_unlock(&ubq->cancel_lock); + + if (!done) + io_uring_cmd_done(io->cmd, + UBLK_IO_RES_ABORT, 0, + IO_URING_F_UNLOCKED); + } + } } /* Cancel all pending commands, must be called after del_gendisk() returns */ @@ -1113,7 +1117,6 @@ static void __ublk_quiesce_dev(struct ublk_device *ub) blk_mq_quiesce_queue(ub->ub_disk->queue); ublk_wait_tagset_rqs_idle(ub); ub->dev_info.state = UBLK_S_DEV_QUIESCED; - ublk_cancel_dev(ub); /* we are going to release task_struct of ubq_daemon and resets * ->ubq_daemon to NULL. So in monitor_work, check on ubq_daemon causes UAF. * Besides, monitor_work is not necessary in QUIESCED state since we have @@ -1136,6 +1139,7 @@ static void ublk_quiesce_work_fn(struct work_struct *work) __ublk_quiesce_dev(ub); unlock: mutex_unlock(&ub->mutex); + ublk_cancel_dev(ub); } static void ublk_unquiesce_dev(struct ublk_device *ub) @@ -1175,8 +1179,8 @@ static void ublk_stop_dev(struct ublk_device *ub) put_disk(ub->ub_disk); ub->ub_disk = NULL; unlock: - ublk_cancel_dev(ub); mutex_unlock(&ub->mutex); + ublk_cancel_dev(ub); cancel_delayed_work_sync(&ub->monitor_work); } @@ -1353,6 +1357,7 @@ static int ublk_init_queue(struct ublk_device *ub, int q_id) void *ptr; int size; + spin_lock_init(&ubq->cancel_lock); ubq->flags = ub->dev_info.flags; ubq->q_id = q_id; ubq->q_depth = ub->dev_info.queue_depth; @@ -1882,8 +1887,9 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) int i; WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq))); + /* All old ioucmds have to be completed */ - WARN_ON_ONCE(ubq->nr_io_ready); + ubq->nr_io_ready = 0; /* old daemon is PF_EXITING, put it now */ put_task_struct(ubq->ubq_daemon); /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */ diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index efa5535a8e1d..505026f0025c 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -609,12 +609,12 @@ static void virtblk_config_changed(struct virtio_device *vdev) static int init_vq(struct virtio_blk *vblk) { int err; - int i; + unsigned short i; vq_callback_t **callbacks; const char **names; struct virtqueue **vqs; unsigned short num_vqs; - unsigned int num_poll_vqs; + unsigned short num_poll_vqs; struct virtio_device *vdev = vblk->vdev; struct irq_affinity desc = { 0, }; @@ -658,13 +658,13 @@ static int init_vq(struct virtio_blk *vblk) for (i = 0; i < num_vqs - num_poll_vqs; i++) { callbacks[i] = virtblk_done; - snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%d", i); + snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%u", i); names[i] = vblk->vqs[i].name; } for (; i < num_vqs; i++) { callbacks[i] = NULL; - snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%d", i); + snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%u", i); names[i] = vblk->vqs[i].name; } @@ -1206,14 +1206,15 @@ static int virtblk_freeze(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; + /* Ensure no requests in virtqueues before deleting vqs. */ + blk_mq_freeze_queue(vblk->disk->queue); + /* Ensure we don't receive any more interrupts */ virtio_reset_device(vdev); /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); - blk_mq_quiesce_queue(vblk->disk->queue); - vdev->config->del_vqs(vdev); kfree(vblk->vqs); @@ -1231,7 +1232,7 @@ static int virtblk_restore(struct virtio_device *vdev) virtio_device_ready(vdev); - blk_mq_unquiesce_queue(vblk->disk->queue); + blk_mq_unfreeze_queue(vblk->disk->queue); return 0; } #endif diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c index c98691cdbbd5..04b72394dda5 100644 --- a/drivers/bluetooth/btmtkuart.c +++ b/drivers/bluetooth/btmtkuart.c @@ -337,7 +337,7 @@ mtk_stp_split(struct btmtkuart_dev *bdev, const unsigned char *data, int count, return data; } -static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count) +static void btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count) { struct btmtkuart_dev *bdev = hci_get_drvdata(hdev); const unsigned char *p_left = data, *p_h4; @@ -376,25 +376,20 @@ static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count) bt_dev_err(bdev->hdev, "Frame reassembly failed (%d)", err); bdev->rx_skb = NULL; - return err; + return; } sz_left -= sz_h4; p_left += sz_h4; } - - return 0; } static int btmtkuart_receive_buf(struct serdev_device *serdev, const u8 *data, size_t count) { struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev); - int err; - err = btmtkuart_recv(bdev->hdev, data, count); - if (err < 0) - return err; + btmtkuart_recv(bdev->hdev, data, count); bdev->hdev->stat.byte_rx += count; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 45dffd2cbc71..76ceb8a0183d 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -1861,6 +1861,7 @@ static const struct qca_device_data qca_soc_data_wcn3998 = { static const struct qca_device_data qca_soc_data_qca6390 = { .soc_type = QCA_QCA6390, .num_vregs = 0, + .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, }; static const struct qca_device_data qca_soc_data_wcn6750 = { diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index 4415d850d698..44dc91555aa0 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <asm/unaligned.h> +#include <linux/atomic.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/slab.h> @@ -44,6 +45,7 @@ struct vhci_data { bool wakeup; __u16 msft_opcode; bool aosp_capable; + atomic_t initialized; }; static int vhci_open_dev(struct hci_dev *hdev) @@ -75,11 +77,10 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1); - mutex_lock(&data->open_mutex); skb_queue_tail(&data->readq, skb); - mutex_unlock(&data->open_mutex); - wake_up_interruptible(&data->read_wait); + if (atomic_read(&data->initialized)) + wake_up_interruptible(&data->read_wait); return 0; } @@ -363,7 +364,8 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) skb_put_u8(skb, 0xff); skb_put_u8(skb, opcode); put_unaligned_le16(hdev->id, skb_put(skb, 2)); - skb_queue_tail(&data->readq, skb); + skb_queue_head(&data->readq, skb); + atomic_inc(&data->initialized); wake_up_interruptible(&data->read_wait); return 0; diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c index edd153dda40c..34e0ba6f52d0 100644 --- a/drivers/bus/mhi/ep/main.c +++ b/drivers/bus/mhi/ep/main.c @@ -71,45 +71,77 @@ err_unlock: static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring, struct mhi_ring_element *tre, u32 len, enum mhi_ev_ccs code) { - struct mhi_ring_element event = {}; + struct mhi_ring_element *event; + int ret; + + event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL); + if (!event) + return -ENOMEM; - event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre)); - event.dword[0] = MHI_TRE_EV_DWORD0(code, len); - event.dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT); + event->ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre)); + event->dword[0] = MHI_TRE_EV_DWORD0(code, len); + event->dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT); - return mhi_ep_send_event(mhi_cntrl, ring->er_index, &event, MHI_TRE_DATA_GET_BEI(tre)); + ret = mhi_ep_send_event(mhi_cntrl, ring->er_index, event, MHI_TRE_DATA_GET_BEI(tre)); + kfree(event); + + return ret; } int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state state) { - struct mhi_ring_element event = {}; + struct mhi_ring_element *event; + int ret; + + event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL); + if (!event) + return -ENOMEM; - event.dword[0] = MHI_SC_EV_DWORD0(state); - event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT); + event->dword[0] = MHI_SC_EV_DWORD0(state); + event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT); - return mhi_ep_send_event(mhi_cntrl, 0, &event, 0); + ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0); + kfree(event); + + return ret; } int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_env) { - struct mhi_ring_element event = {}; + struct mhi_ring_element *event; + int ret; + + event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL); + if (!event) + return -ENOMEM; - event.dword[0] = MHI_EE_EV_DWORD0(exec_env); - event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT); + event->dword[0] = MHI_EE_EV_DWORD0(exec_env); + event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT); - return mhi_ep_send_event(mhi_cntrl, 0, &event, 0); + ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0); + kfree(event); + + return ret; } static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ev_ccs code) { struct mhi_ep_ring *ring = &mhi_cntrl->mhi_cmd->ring; - struct mhi_ring_element event = {}; + struct mhi_ring_element *event; + int ret; + + event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL); + if (!event) + return -ENOMEM; - event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element)); - event.dword[0] = MHI_CC_EV_DWORD0(code); - event.dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT); + event->ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element)); + event->dword[0] = MHI_CC_EV_DWORD0(code); + event->dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT); - return mhi_ep_send_event(mhi_cntrl, 0, &event, 0); + ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0); + kfree(event); + + return ret; } static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_element *el) diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c index 0c3a009ed9bb..8378c3319cd5 100644 --- a/drivers/bus/mhi/host/main.c +++ b/drivers/bus/mhi/host/main.c @@ -268,7 +268,8 @@ static void mhi_del_ring_element(struct mhi_controller *mhi_cntrl, static bool is_valid_ring_ptr(struct mhi_ring *ring, dma_addr_t addr) { - return addr >= ring->iommu_base && addr < ring->iommu_base + ring->len; + return addr >= ring->iommu_base && addr < ring->iommu_base + ring->len && + !(addr & (sizeof(struct mhi_ring_element) - 1)); } int mhi_destroy_device(struct device *dev, void *data) @@ -642,6 +643,8 @@ static int parse_xfer_event(struct mhi_controller *mhi_cntrl, mhi_del_ring_element(mhi_cntrl, tre_ring); local_rp = tre_ring->rp; + read_unlock_bh(&mhi_chan->lock); + /* notify client */ mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result); @@ -667,6 +670,8 @@ static int parse_xfer_event(struct mhi_controller *mhi_cntrl, kfree(buf_info->cb_buf); } } + + read_lock_bh(&mhi_chan->lock); } break; } /* CC_EOT */ @@ -1119,17 +1124,15 @@ static int mhi_queue(struct mhi_device *mhi_dev, struct mhi_buf_info *buf_info, if (unlikely(MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state))) return -EIO; - read_lock_irqsave(&mhi_cntrl->pm_lock, flags); - ret = mhi_is_ring_full(mhi_cntrl, tre_ring); - if (unlikely(ret)) { - ret = -EAGAIN; - goto exit_unlock; - } + if (unlikely(ret)) + return -EAGAIN; ret = mhi_gen_tre(mhi_cntrl, mhi_chan, buf_info, mflags); if (unlikely(ret)) - goto exit_unlock; + return ret; + + read_lock_irqsave(&mhi_cntrl->pm_lock, flags); /* Packet is queued, take a usage ref to exit M3 if necessary * for host->device buffer, balanced put is done on buffer completion @@ -1149,7 +1152,6 @@ static int mhi_queue(struct mhi_device *mhi_dev, struct mhi_buf_info *buf_info, if (dir == DMA_FROM_DEVICE) mhi_cntrl->runtime_put(mhi_cntrl); -exit_unlock: read_unlock_irqrestore(&mhi_cntrl->pm_lock, flags); return ret; @@ -1201,6 +1203,9 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan, int eot, eob, chain, bei; int ret; + /* Protect accesses for reading and incrementing WP */ + write_lock_bh(&mhi_chan->lock); + buf_ring = &mhi_chan->buf_ring; tre_ring = &mhi_chan->tre_ring; @@ -1218,8 +1223,10 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan, if (!info->pre_mapped) { ret = mhi_cntrl->map_single(mhi_cntrl, buf_info); - if (ret) + if (ret) { + write_unlock_bh(&mhi_chan->lock); return ret; + } } eob = !!(flags & MHI_EOB); @@ -1236,6 +1243,8 @@ int mhi_gen_tre(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan, mhi_add_ring_element(mhi_cntrl, tre_ring); mhi_add_ring_element(mhi_cntrl, buf_ring); + write_unlock_bh(&mhi_chan->lock); + return 0; } diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c index 5eb0fe73ddc4..79fc96c8d836 100644 --- a/drivers/bus/moxtet.c +++ b/drivers/bus/moxtet.c @@ -830,6 +830,12 @@ static void moxtet_remove(struct spi_device *spi) mutex_destroy(&moxtet->lock); } +static const struct spi_device_id moxtet_spi_ids[] = { + { "moxtet" }, + { }, +}; +MODULE_DEVICE_TABLE(spi, moxtet_spi_ids); + static const struct of_device_id moxtet_dt_ids[] = { { .compatible = "cznic,moxtet" }, {}, @@ -841,6 +847,7 @@ static struct spi_driver moxtet_spi_driver = { .name = "moxtet", .of_match_table = moxtet_dt_ids, }, + .id_table = moxtet_spi_ids, .probe = moxtet_probe, .remove = moxtet_remove, }; diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 59a2fe2448f1..15c6b85b125d 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -2174,13 +2174,23 @@ static int sysc_reset(struct sysc *ddata) sysc_val = sysc_read_sysconfig(ddata); sysc_val |= sysc_mask; sysc_write(ddata, sysc_offset, sysc_val); - /* Flush posted write */ + + /* + * Some devices need a delay before reading registers + * after reset. Presumably a srst_udelay is not needed + * for devices that use a rstctrl register reset. + */ + if (ddata->cfg.srst_udelay) + fsleep(ddata->cfg.srst_udelay); + + /* + * Flush posted write. For devices needing srst_udelay + * this should trigger an interconnect error if the + * srst_udelay value is needed but not configured. + */ sysc_val = sysc_read_sysconfig(ddata); } - if (ddata->cfg.srst_udelay) - fsleep(ddata->cfg.srst_udelay); - if (ddata->post_reset_quirk) ddata->post_reset_quirk(ddata); diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 8f31f9d81030..c319f9937709 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -24,10 +24,13 @@ #include <linux/random.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/string.h> #include <linux/uaccess.h> #define RNG_MODULE_NAME "hw_random" +#define RNG_BUFFER_SIZE (SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES) + static struct hwrng *current_rng; /* the current rng has been explicitly chosen by user via sysfs */ static int cur_rng_set_by_user; @@ -59,7 +62,7 @@ static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size, static size_t rng_buffer_size(void) { - return SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES; + return RNG_BUFFER_SIZE; } static void add_early_randomness(struct hwrng *rng) @@ -211,6 +214,7 @@ static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size, static ssize_t rng_dev_read(struct file *filp, char __user *buf, size_t size, loff_t *offp) { + u8 buffer[RNG_BUFFER_SIZE]; ssize_t ret = 0; int err = 0; int bytes_read, len; @@ -238,34 +242,37 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, if (bytes_read < 0) { err = bytes_read; goto out_unlock_reading; + } else if (bytes_read == 0 && + (filp->f_flags & O_NONBLOCK)) { + err = -EAGAIN; + goto out_unlock_reading; } + data_avail = bytes_read; } - if (!data_avail) { - if (filp->f_flags & O_NONBLOCK) { - err = -EAGAIN; - goto out_unlock_reading; - } - } else { - len = data_avail; + len = data_avail; + if (len) { if (len > size) len = size; data_avail -= len; - if (copy_to_user(buf + ret, rng_buffer + data_avail, - len)) { + memcpy(buffer, rng_buffer + data_avail, len); + } + mutex_unlock(&reading_mutex); + put_rng(rng); + + if (len) { + if (copy_to_user(buf + ret, buffer, len)) { err = -EFAULT; - goto out_unlock_reading; + goto out; } size -= len; ret += len; } - mutex_unlock(&reading_mutex); - put_rng(rng); if (need_resched()) schedule_timeout_interruptible(1); @@ -276,6 +283,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, } } out: + memzero_explicit(buffer, sizeof(buffer)); return ret ? : err; out_unlock_reading: diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c index c7d8cbd22bac..5acb35236c58 100644 --- a/drivers/clk/clk-si5341.c +++ b/drivers/clk/clk-si5341.c @@ -892,10 +892,8 @@ static int si5341_output_clk_set_rate(struct clk_hw *hw, unsigned long rate, r[0] = r_div ? (r_div & 0xff) : 1; r[1] = (r_div >> 8) & 0xff; r[2] = (r_div >> 16) & 0xff; - err = regmap_bulk_write(output->data->regmap, + return regmap_bulk_write(output->data->regmap, SI5341_OUT_R_REG(output), r, 3); - - return 0; } static int si5341_output_reparent(struct clk_si5341_output *output, u8 index) diff --git a/drivers/clk/hisilicon/clk-hi3620.c b/drivers/clk/hisilicon/clk-hi3620.c index a3d04c7c3da8..eb9c139babc3 100644 --- a/drivers/clk/hisilicon/clk-hi3620.c +++ b/drivers/clk/hisilicon/clk-hi3620.c @@ -467,8 +467,10 @@ static void __init hi3620_mmc_clk_init(struct device_node *node) return; clk_data->clks = kcalloc(num, sizeof(*clk_data->clks), GFP_KERNEL); - if (!clk_data->clks) + if (!clk_data->clks) { + kfree(clk_data); return; + } for (i = 0; i < num; i++) { struct hisi_mmc_clock *mmc_clk = &hi3620_mmc_clks[i]; diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c index 273de1f29307..1066ea16de62 100644 --- a/drivers/clk/imx/clk-imx8qxp.c +++ b/drivers/clk/imx/clk-imx8qxp.c @@ -67,6 +67,22 @@ static const char * const lcd_pxl_sels[] = { "lcd_pxl_bypass_div_clk", }; +static const char *const lvds0_sels[] = { + "clk_dummy", + "clk_dummy", + "clk_dummy", + "clk_dummy", + "mipi0_lvds_bypass_clk", +}; + +static const char *const lvds1_sels[] = { + "clk_dummy", + "clk_dummy", + "clk_dummy", + "clk_dummy", + "mipi1_lvds_bypass_clk", +}; + static const char * const mipi_sels[] = { "clk_dummy", "clk_dummy", @@ -201,9 +217,9 @@ static int imx8qxp_clk_probe(struct platform_device *pdev) /* MIPI-LVDS SS */ imx_clk_scu("mipi0_bypass_clk", IMX_SC_R_MIPI_0, IMX_SC_PM_CLK_BYPASS); imx_clk_scu("mipi0_pixel_clk", IMX_SC_R_MIPI_0, IMX_SC_PM_CLK_PER); - imx_clk_scu("mipi0_lvds_pixel_clk", IMX_SC_R_LVDS_0, IMX_SC_PM_CLK_MISC2); imx_clk_scu("mipi0_lvds_bypass_clk", IMX_SC_R_LVDS_0, IMX_SC_PM_CLK_BYPASS); - imx_clk_scu("mipi0_lvds_phy_clk", IMX_SC_R_LVDS_0, IMX_SC_PM_CLK_MISC3); + imx_clk_scu2("mipi0_lvds_pixel_clk", lvds0_sels, ARRAY_SIZE(lvds0_sels), IMX_SC_R_LVDS_0, IMX_SC_PM_CLK_MISC2); + imx_clk_scu2("mipi0_lvds_phy_clk", lvds0_sels, ARRAY_SIZE(lvds0_sels), IMX_SC_R_LVDS_0, IMX_SC_PM_CLK_MISC3); imx_clk_scu2("mipi0_dsi_tx_esc_clk", mipi_sels, ARRAY_SIZE(mipi_sels), IMX_SC_R_MIPI_0, IMX_SC_PM_CLK_MST_BUS); imx_clk_scu2("mipi0_dsi_rx_esc_clk", mipi_sels, ARRAY_SIZE(mipi_sels), IMX_SC_R_MIPI_0, IMX_SC_PM_CLK_SLV_BUS); imx_clk_scu2("mipi0_dsi_phy_clk", mipi_sels, ARRAY_SIZE(mipi_sels), IMX_SC_R_MIPI_0, IMX_SC_PM_CLK_PHY); @@ -213,9 +229,9 @@ static int imx8qxp_clk_probe(struct platform_device *pdev) imx_clk_scu("mipi1_bypass_clk", IMX_SC_R_MIPI_1, IMX_SC_PM_CLK_BYPASS); imx_clk_scu("mipi1_pixel_clk", IMX_SC_R_MIPI_1, IMX_SC_PM_CLK_PER); - imx_clk_scu("mipi1_lvds_pixel_clk", IMX_SC_R_LVDS_1, IMX_SC_PM_CLK_MISC2); imx_clk_scu("mipi1_lvds_bypass_clk", IMX_SC_R_LVDS_1, IMX_SC_PM_CLK_BYPASS); - imx_clk_scu("mipi1_lvds_phy_clk", IMX_SC_R_LVDS_1, IMX_SC_PM_CLK_MISC3); + imx_clk_scu2("mipi1_lvds_pixel_clk", lvds1_sels, ARRAY_SIZE(lvds1_sels), IMX_SC_R_LVDS_1, IMX_SC_PM_CLK_MISC2); + imx_clk_scu2("mipi1_lvds_phy_clk", lvds1_sels, ARRAY_SIZE(lvds1_sels), IMX_SC_R_LVDS_1, IMX_SC_PM_CLK_MISC3); imx_clk_scu2("mipi1_dsi_tx_esc_clk", mipi_sels, ARRAY_SIZE(mipi_sels), IMX_SC_R_MIPI_1, IMX_SC_PM_CLK_MST_BUS); imx_clk_scu2("mipi1_dsi_rx_esc_clk", mipi_sels, ARRAY_SIZE(mipi_sels), IMX_SC_R_MIPI_1, IMX_SC_PM_CLK_SLV_BUS); diff --git a/drivers/clk/mmp/clk-of-pxa168.c b/drivers/clk/mmp/clk-of-pxa168.c index 130d1a723879..cb0ebbd82038 100644 --- a/drivers/clk/mmp/clk-of-pxa168.c +++ b/drivers/clk/mmp/clk-of-pxa168.c @@ -306,18 +306,21 @@ static void __init pxa168_clk_init(struct device_node *np) pxa_unit->mpmu_base = of_iomap(np, 0); if (!pxa_unit->mpmu_base) { pr_err("failed to map mpmu registers\n"); + kfree(pxa_unit); return; } pxa_unit->apmu_base = of_iomap(np, 1); if (!pxa_unit->apmu_base) { pr_err("failed to map apmu registers\n"); + kfree(pxa_unit); return; } pxa_unit->apbc_base = of_iomap(np, 2); if (!pxa_unit->apbc_base) { pr_err("failed to map apbc registers\n"); + kfree(pxa_unit); return; } diff --git a/drivers/clk/qcom/gpucc-sm8150.c b/drivers/clk/qcom/gpucc-sm8150.c index 8422fd047493..c89a5b59ddb7 100644 --- a/drivers/clk/qcom/gpucc-sm8150.c +++ b/drivers/clk/qcom/gpucc-sm8150.c @@ -37,8 +37,8 @@ static struct alpha_pll_config gpu_cc_pll1_config = { .config_ctl_hi_val = 0x00002267, .config_ctl_hi1_val = 0x00000024, .test_ctl_val = 0x00000000, - .test_ctl_hi_val = 0x00000002, - .test_ctl_hi1_val = 0x00000000, + .test_ctl_hi_val = 0x00000000, + .test_ctl_hi1_val = 0x00000020, .user_ctl_val = 0x00000000, .user_ctl_hi_val = 0x00000805, .user_ctl_hi1_val = 0x000000d0, diff --git a/drivers/clk/qcom/videocc-sm8150.c b/drivers/clk/qcom/videocc-sm8150.c index 1afdbe4a249d..52a9a453a143 100644 --- a/drivers/clk/qcom/videocc-sm8150.c +++ b/drivers/clk/qcom/videocc-sm8150.c @@ -33,6 +33,7 @@ static struct alpha_pll_config video_pll0_config = { .config_ctl_val = 0x20485699, .config_ctl_hi_val = 0x00002267, .config_ctl_hi1_val = 0x00000024, + .test_ctl_hi1_val = 0x00000020, .user_ctl_val = 0x00000000, .user_ctl_hi_val = 0x00000805, .user_ctl_hi1_val = 0x000000D0, @@ -214,6 +215,10 @@ static const struct regmap_config video_cc_sm8150_regmap_config = { static const struct qcom_reset_map video_cc_sm8150_resets[] = { [VIDEO_CC_MVSC_CORE_CLK_BCR] = { 0x850, 2 }, + [VIDEO_CC_INTERFACE_BCR] = { 0x8f0 }, + [VIDEO_CC_MVS0_BCR] = { 0x870 }, + [VIDEO_CC_MVS1_BCR] = { 0x8b0 }, + [VIDEO_CC_MVSC_BCR] = { 0x810 }, }; static const struct qcom_cc_desc video_cc_sm8150_desc = { diff --git a/drivers/clk/renesas/rzg2l-cpg.c b/drivers/clk/renesas/rzg2l-cpg.c index 84767cfc1e73..473feb36a38f 100644 --- a/drivers/clk/renesas/rzg2l-cpg.c +++ b/drivers/clk/renesas/rzg2l-cpg.c @@ -1115,41 +1115,33 @@ fail: #define rcdev_to_priv(x) container_of(x, struct rzg2l_cpg_priv, rcdev) -static int rzg2l_cpg_reset(struct reset_controller_dev *rcdev, - unsigned long id) -{ - struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); - const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->resets[id].off; - u32 dis = BIT(info->resets[id].bit); - u32 we = dis << 16; - - dev_dbg(rcdev->dev, "reset id:%ld offset:0x%x\n", id, CLK_RST_R(reg)); - - /* Reset module */ - writel(we, priv->base + CLK_RST_R(reg)); - - /* Wait for at least one cycle of the RCLK clock (@ ca. 32 kHz) */ - udelay(35); - - /* Release module from reset state */ - writel(we | dis, priv->base + CLK_RST_R(reg)); - - return 0; -} - static int rzg2l_cpg_assert(struct reset_controller_dev *rcdev, unsigned long id) { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; unsigned int reg = info->resets[id].off; - u32 value = BIT(info->resets[id].bit) << 16; + u32 mask = BIT(info->resets[id].bit); + s8 monbit = info->resets[id].monbit; + u32 value = mask << 16; dev_dbg(rcdev->dev, "assert id:%ld offset:0x%x\n", id, CLK_RST_R(reg)); writel(value, priv->base + CLK_RST_R(reg)); - return 0; + + if (info->has_clk_mon_regs) { + reg = CLK_MRST_R(reg); + } else if (monbit >= 0) { + reg = CPG_RST_MON; + mask = BIT(monbit); + } else { + /* Wait for at least one cycle of the RCLK clock (@ ca. 32 kHz) */ + udelay(35); + return 0; + } + + return readl_poll_timeout_atomic(priv->base + reg, value, + value & mask, 10, 200); } static int rzg2l_cpg_deassert(struct reset_controller_dev *rcdev, @@ -1158,14 +1150,40 @@ static int rzg2l_cpg_deassert(struct reset_controller_dev *rcdev, struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; unsigned int reg = info->resets[id].off; - u32 dis = BIT(info->resets[id].bit); - u32 value = (dis << 16) | dis; + u32 mask = BIT(info->resets[id].bit); + s8 monbit = info->resets[id].monbit; + u32 value = (mask << 16) | mask; dev_dbg(rcdev->dev, "deassert id:%ld offset:0x%x\n", id, CLK_RST_R(reg)); writel(value, priv->base + CLK_RST_R(reg)); - return 0; + + if (info->has_clk_mon_regs) { + reg = CLK_MRST_R(reg); + } else if (monbit >= 0) { + reg = CPG_RST_MON; + mask = BIT(monbit); + } else { + /* Wait for at least one cycle of the RCLK clock (@ ca. 32 kHz) */ + udelay(35); + return 0; + } + + return readl_poll_timeout_atomic(priv->base + reg, value, + !(value & mask), 10, 200); +} + +static int rzg2l_cpg_reset(struct reset_controller_dev *rcdev, + unsigned long id) +{ + int ret; + + ret = rzg2l_cpg_assert(rcdev, id); + if (ret) + return ret; + + return rzg2l_cpg_deassert(rcdev, id); } static int rzg2l_cpg_status(struct reset_controller_dev *rcdev, @@ -1173,18 +1191,21 @@ static int rzg2l_cpg_status(struct reset_controller_dev *rcdev, { struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev); const struct rzg2l_cpg_info *info = priv->info; - unsigned int reg = info->resets[id].off; - u32 bitmask = BIT(info->resets[id].bit); s8 monbit = info->resets[id].monbit; + unsigned int reg; + u32 bitmask; if (info->has_clk_mon_regs) { - return !!(readl(priv->base + CLK_MRST_R(reg)) & bitmask); + reg = CLK_MRST_R(info->resets[id].off); + bitmask = BIT(info->resets[id].bit); } else if (monbit >= 0) { - u32 monbitmask = BIT(monbit); - - return !!(readl(priv->base + CPG_RST_MON) & monbitmask); + reg = CPG_RST_MON; + bitmask = BIT(monbit); + } else { + return -ENOTSUPP; } - return -ENOTSUPP; + + return !!(readl(priv->base + reg) & bitmask); } static const struct reset_control_ops rzg2l_cpg_reset_ops = { diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c index aa53797dbfc1..7782785a86e6 100644 --- a/drivers/clk/rockchip/clk-rk3128.c +++ b/drivers/clk/rockchip/clk-rk3128.c @@ -490,7 +490,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { GATE(HCLK_I2S_2CH, "hclk_i2s_2ch", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS), GATE(0, "hclk_usb_peri", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 13, GFLAGS), GATE(HCLK_HOST2, "hclk_host2", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS), - GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(3), 13, GFLAGS), + GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 13, GFLAGS), GATE(0, "hclk_peri_ahb", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 14, GFLAGS), GATE(HCLK_SPDIF, "hclk_spdif", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 9, GFLAGS), GATE(HCLK_TSP, "hclk_tsp", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 12, GFLAGS), diff --git a/drivers/clk/rockchip/clk-rk3568.c b/drivers/clk/rockchip/clk-rk3568.c index 2f54f630c8b6..1ffb755feea4 100644 --- a/drivers/clk/rockchip/clk-rk3568.c +++ b/drivers/clk/rockchip/clk-rk3568.c @@ -72,6 +72,7 @@ static struct rockchip_pll_rate_table rk3568_pll_rates[] = { RK3036_PLL_RATE(408000000, 1, 68, 2, 2, 1, 0), RK3036_PLL_RATE(312000000, 1, 78, 6, 1, 1, 0), RK3036_PLL_RATE(297000000, 2, 99, 4, 1, 1, 0), + RK3036_PLL_RATE(292500000, 1, 195, 4, 4, 1, 0), RK3036_PLL_RATE(241500000, 2, 161, 4, 2, 1, 0), RK3036_PLL_RATE(216000000, 1, 72, 4, 2, 1, 0), RK3036_PLL_RATE(200000000, 1, 100, 3, 4, 1, 0), diff --git a/drivers/clk/zynqmp/clk-mux-zynqmp.c b/drivers/clk/zynqmp/clk-mux-zynqmp.c index 60359333f26d..9b5d3050b742 100644 --- a/drivers/clk/zynqmp/clk-mux-zynqmp.c +++ b/drivers/clk/zynqmp/clk-mux-zynqmp.c @@ -89,7 +89,7 @@ static int zynqmp_clk_mux_set_parent(struct clk_hw *hw, u8 index) static const struct clk_ops zynqmp_clk_mux_ops = { .get_parent = zynqmp_clk_mux_get_parent, .set_parent = zynqmp_clk_mux_set_parent, - .determine_rate = __clk_mux_determine_rate, + .determine_rate = __clk_mux_determine_rate_closest, }; static const struct clk_ops zynqmp_clk_mux_ro_ops = { diff --git a/drivers/clk/zynqmp/divider.c b/drivers/clk/zynqmp/divider.c index 33a3b2a22659..5a00487ae408 100644 --- a/drivers/clk/zynqmp/divider.c +++ b/drivers/clk/zynqmp/divider.c @@ -110,52 +110,6 @@ static unsigned long zynqmp_clk_divider_recalc_rate(struct clk_hw *hw, return DIV_ROUND_UP_ULL(parent_rate, value); } -static void zynqmp_get_divider2_val(struct clk_hw *hw, - unsigned long rate, - struct zynqmp_clk_divider *divider, - u32 *bestdiv) -{ - int div1; - int div2; - long error = LONG_MAX; - unsigned long div1_prate; - struct clk_hw *div1_parent_hw; - struct zynqmp_clk_divider *pdivider; - struct clk_hw *div2_parent_hw = clk_hw_get_parent(hw); - - if (!div2_parent_hw) - return; - - pdivider = to_zynqmp_clk_divider(div2_parent_hw); - if (!pdivider) - return; - - div1_parent_hw = clk_hw_get_parent(div2_parent_hw); - if (!div1_parent_hw) - return; - - div1_prate = clk_hw_get_rate(div1_parent_hw); - *bestdiv = 1; - for (div1 = 1; div1 <= pdivider->max_div;) { - for (div2 = 1; div2 <= divider->max_div;) { - long new_error = ((div1_prate / div1) / div2) - rate; - - if (abs(new_error) < abs(error)) { - *bestdiv = div2; - error = new_error; - } - if (divider->flags & CLK_DIVIDER_POWER_OF_TWO) - div2 = div2 << 1; - else - div2++; - } - if (pdivider->flags & CLK_DIVIDER_POWER_OF_TWO) - div1 = div1 << 1; - else - div1++; - } -} - /** * zynqmp_clk_divider_round_rate() - Round rate of divider clock * @hw: handle between common and hardware-specific interfaces @@ -174,6 +128,7 @@ static long zynqmp_clk_divider_round_rate(struct clk_hw *hw, u32 div_type = divider->div_type; u32 bestdiv; int ret; + u8 width; /* if read only, just return current value */ if (divider->flags & CLK_DIVIDER_READ_ONLY) { @@ -193,23 +148,12 @@ static long zynqmp_clk_divider_round_rate(struct clk_hw *hw, return DIV_ROUND_UP_ULL((u64)*prate, bestdiv); } - bestdiv = zynqmp_divider_get_val(*prate, rate, divider->flags); - - /* - * In case of two divisors, compute best divider values and return - * divider2 value based on compute value. div1 will be automatically - * set to optimum based on required total divider value. - */ - if (div_type == TYPE_DIV2 && - (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) { - zynqmp_get_divider2_val(hw, rate, divider, &bestdiv); - } + width = fls(divider->max_div); - if ((clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) && divider->is_frac) - bestdiv = rate % *prate ? 1 : bestdiv; + rate = divider_round_rate(hw, rate, prate, NULL, width, divider->flags); - bestdiv = min_t(u32, bestdiv, divider->max_div); - *prate = rate * bestdiv; + if (divider->is_frac && (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) && (rate % *prate)) + *prate = rate; return rate; } diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index ec86aecb748f..7f9c1f58a947 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -184,7 +184,7 @@ static inline u32 dmtimer_read(struct dmtimer *timer, u32 reg) * dmtimer_write - write timer registers in posted and non-posted mode * @timer: timer pointer over which write operation is to perform * @reg: lowest byte holds the register offset - * @value: data to write into the register + * @val: data to write into the register * * The posted mode bit is encoded in reg. Note that in posted mode, the write * pending bit must be checked. Otherwise a write on a register which has a @@ -937,7 +937,7 @@ static int omap_dm_timer_set_int_enable(struct omap_dm_timer *cookie, /** * omap_dm_timer_set_int_disable - disable timer interrupts - * @timer: pointer to timer handle + * @cookie: pointer to timer cookie * @mask: bit mask of interrupts to be disabled * * Disables the specified timer interrupts for a timer. diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index e2f9038b66d1..60bd56190579 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -179,7 +179,7 @@ static bool __init cpu0_node_has_opp_v2_prop(void) struct device_node *np = of_cpu_device_node_get(0); bool ret = false; - if (of_get_property(np, "operating-points-v2", NULL)) + if (of_property_present(np, "operating-points-v2")) ret = true; of_node_put(np); diff --git a/drivers/cpufreq/imx-cpufreq-dt.c b/drivers/cpufreq/imx-cpufreq-dt.c index 76e553af2071..535867a7dfdd 100644 --- a/drivers/cpufreq/imx-cpufreq-dt.c +++ b/drivers/cpufreq/imx-cpufreq-dt.c @@ -89,7 +89,7 @@ static int imx_cpufreq_dt_probe(struct platform_device *pdev) cpu_dev = get_cpu_device(0); - if (!of_find_property(cpu_dev->of_node, "cpu-supply", NULL)) + if (!of_property_present(cpu_dev->of_node, "cpu-supply")) return -ENODEV; if (of_machine_is_compatible("fsl,imx7ulp")) { diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 925fc17eaacb..39b0362a3b9a 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -230,7 +230,7 @@ static int imx6q_opp_check_speed_grading(struct device *dev) u32 val; int ret; - if (of_find_property(dev->of_node, "nvmem-cells", NULL)) { + if (of_property_present(dev->of_node, "nvmem-cells")) { ret = nvmem_cell_read_u32(dev, "speed_grade", &val); if (ret) return ret; @@ -285,7 +285,7 @@ static int imx6ul_opp_check_speed_grading(struct device *dev) u32 val; int ret = 0; - if (of_find_property(dev->of_node, "nvmem-cells", NULL)) { + if (of_property_present(dev->of_node, "nvmem-cells")) { ret = nvmem_cell_read_u32(dev, "speed_grade", &val); if (ret) return ret; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index fbe3a4098743..abdd26f7d04c 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -493,6 +493,30 @@ static inline int intel_pstate_get_cppc_guaranteed(int cpu) } #endif /* CONFIG_ACPI_CPPC_LIB */ +static int intel_pstate_freq_to_hwp_rel(struct cpudata *cpu, int freq, + unsigned int relation) +{ + if (freq == cpu->pstate.turbo_freq) + return cpu->pstate.turbo_pstate; + + if (freq == cpu->pstate.max_freq) + return cpu->pstate.max_pstate; + + switch (relation) { + case CPUFREQ_RELATION_H: + return freq / cpu->pstate.scaling; + case CPUFREQ_RELATION_C: + return DIV_ROUND_CLOSEST(freq, cpu->pstate.scaling); + } + + return DIV_ROUND_UP(freq, cpu->pstate.scaling); +} + +static int intel_pstate_freq_to_hwp(struct cpudata *cpu, int freq) +{ + return intel_pstate_freq_to_hwp_rel(cpu, freq, CPUFREQ_RELATION_L); +} + /** * intel_pstate_hybrid_hwp_adjust - Calibrate HWP performance levels. * @cpu: Target CPU. @@ -510,6 +534,7 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu) int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling; int perf_ctl_turbo = pstate_funcs.get_turbo(cpu->cpu); int scaling = cpu->pstate.scaling; + int freq; pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys); pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo); @@ -523,16 +548,16 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu) cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling, perf_ctl_scaling); - cpu->pstate.max_pstate_physical = - DIV_ROUND_UP(perf_ctl_max_phys * perf_ctl_scaling, - scaling); + freq = perf_ctl_max_phys * perf_ctl_scaling; + cpu->pstate.max_pstate_physical = intel_pstate_freq_to_hwp(cpu, freq); - cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling; + freq = cpu->pstate.min_pstate * perf_ctl_scaling; + cpu->pstate.min_freq = freq; /* * Cast the min P-state value retrieved via pstate_funcs.get_min() to * the effective range of HWP performance levels. */ - cpu->pstate.min_pstate = DIV_ROUND_UP(cpu->pstate.min_freq, scaling); + cpu->pstate.min_pstate = intel_pstate_freq_to_hwp(cpu, freq); } static inline void update_turbo_state(void) @@ -2493,13 +2518,12 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu, * abstract values to represent performance rather than pure ratios. */ if (hwp_active && cpu->pstate.scaling != perf_ctl_scaling) { - int scaling = cpu->pstate.scaling; int freq; freq = max_policy_perf * perf_ctl_scaling; - max_policy_perf = DIV_ROUND_UP(freq, scaling); + max_policy_perf = intel_pstate_freq_to_hwp(cpu, freq); freq = min_policy_perf * perf_ctl_scaling; - min_policy_perf = DIV_ROUND_UP(freq, scaling); + min_policy_perf = intel_pstate_freq_to_hwp(cpu, freq); } pr_debug("cpu:%d min_policy_perf:%d max_policy_perf:%d\n", @@ -2873,18 +2897,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy, cpufreq_freq_transition_begin(policy, &freqs); - switch (relation) { - case CPUFREQ_RELATION_L: - target_pstate = DIV_ROUND_UP(freqs.new, cpu->pstate.scaling); - break; - case CPUFREQ_RELATION_H: - target_pstate = freqs.new / cpu->pstate.scaling; - break; - default: - target_pstate = DIV_ROUND_CLOSEST(freqs.new, cpu->pstate.scaling); - break; - } - + target_pstate = intel_pstate_freq_to_hwp_rel(cpu, freqs.new, relation); target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false); freqs.new = target_pstate * cpu->pstate.scaling; @@ -2902,7 +2915,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, update_turbo_state(); - target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling); + target_pstate = intel_pstate_freq_to_hwp(cpu, target_freq); target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true); diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 513a071845c2..028df8a5f537 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -310,8 +310,11 @@ static int scmi_cpufreq_probe(struct scmi_device *sdev) #ifdef CONFIG_COMMON_CLK /* dummy clock provider as needed by OPP if clocks property is used */ - if (of_find_property(dev->of_node, "#clock-cells", NULL)) - devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL); + if (of_property_present(dev->of_node, "#clock-cells")) { + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL); + if (ret) + return dev_err_probe(dev, ret, "%s: registering clock provider failed\n", __func__); + } #endif ret = cpufreq_register_driver(&scmi_cpufreq_driver); diff --git a/drivers/cpufreq/tegra20-cpufreq.c b/drivers/cpufreq/tegra20-cpufreq.c index ab7ac7df9e62..dfd2de4f8e07 100644 --- a/drivers/cpufreq/tegra20-cpufreq.c +++ b/drivers/cpufreq/tegra20-cpufreq.c @@ -25,7 +25,7 @@ static bool cpu0_node_has_opp_v2_prop(void) struct device_node *np = of_cpu_device_node_get(0); bool ret = false; - if (of_get_property(np, "operating-points-v2", NULL)) + if (of_property_present(np, "operating-points-v2")) ret = true; of_node_put(np); diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c index aa4e1a500691..cb8e99936abb 100644 --- a/drivers/crypto/ccp/ccp-ops.c +++ b/drivers/crypto/ccp/ccp-ops.c @@ -179,8 +179,11 @@ static int ccp_init_dm_workarea(struct ccp_dm_workarea *wa, wa->dma.address = dma_map_single(wa->dev, wa->address, len, dir); - if (dma_mapping_error(wa->dev, wa->dma.address)) + if (dma_mapping_error(wa->dev, wa->dma.address)) { + kfree(wa->address); + wa->address = NULL; return -ENOMEM; + } wa->dma.length = len; } diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index b8e02c3a1961..bbfb0f288dc3 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -515,10 +515,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init); static int __sev_platform_shutdown_locked(int *error) { - struct sev_device *sev = psp_master->sev_data; + struct psp_device *psp = psp_master; + struct sev_device *sev; int ret; - if (!sev || sev->state == SEV_STATE_UNINIT) + if (!psp || !psp->sev_data) + return 0; + + sev = psp->sev_data; + + if (sev->state == SEV_STATE_UNINIT) return 0; ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index ff8a5f20a5df..269df4ec148b 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -118,8 +118,6 @@ #define HPRE_DFX_COMMON2_LEN 0xE #define HPRE_DFX_CORE_LEN 0x43 -#define HPRE_DEV_ALG_MAX_LEN 256 - static const char hpre_name[] = "hisi_hpre"; static struct dentry *hpre_debugfs_root; static const struct pci_device_id hpre_dev_ids[] = { @@ -135,12 +133,7 @@ struct hpre_hw_error { const char *msg; }; -struct hpre_dev_alg { - u32 alg_msk; - const char *alg; -}; - -static const struct hpre_dev_alg hpre_dev_algs[] = { +static const struct qm_dev_alg hpre_dev_algs[] = { { .alg_msk = BIT(0), .alg = "rsa\n" @@ -233,6 +226,20 @@ static const struct hisi_qm_cap_info hpre_basic_info[] = { {HPRE_CORE10_ALG_BITMAP_CAP, 0x3170, 0, GENMASK(31, 0), 0x0, 0x10, 0x10} }; +enum hpre_pre_store_cap_idx { + HPRE_CLUSTER_NUM_CAP_IDX = 0x0, + HPRE_CORE_ENABLE_BITMAP_CAP_IDX, + HPRE_DRV_ALG_BITMAP_CAP_IDX, + HPRE_DEV_ALG_BITMAP_CAP_IDX, +}; + +static const u32 hpre_pre_store_caps[] = { + HPRE_CLUSTER_NUM_CAP, + HPRE_CORE_ENABLE_BITMAP_CAP, + HPRE_DRV_ALG_BITMAP_CAP, + HPRE_DEV_ALG_BITMAP_CAP, +}; + static const struct hpre_hw_error hpre_hw_errors[] = { { .int_msk = BIT(0), @@ -352,42 +359,13 @@ bool hpre_check_alg_support(struct hisi_qm *qm, u32 alg) { u32 cap_val; - cap_val = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_DRV_ALG_BITMAP_CAP, qm->cap_ver); + cap_val = qm->cap_tables.dev_cap_table[HPRE_DRV_ALG_BITMAP_CAP_IDX].cap_val; if (alg & cap_val) return true; return false; } -static int hpre_set_qm_algs(struct hisi_qm *qm) -{ - struct device *dev = &qm->pdev->dev; - char *algs, *ptr; - u32 alg_msk; - int i; - - if (!qm->use_sva) - return 0; - - algs = devm_kzalloc(dev, HPRE_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); - if (!algs) - return -ENOMEM; - - alg_msk = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_DEV_ALG_BITMAP_CAP, qm->cap_ver); - - for (i = 0; i < ARRAY_SIZE(hpre_dev_algs); i++) - if (alg_msk & hpre_dev_algs[i].alg_msk) - strcat(algs, hpre_dev_algs[i].alg); - - ptr = strrchr(algs, '\n'); - if (ptr) - *ptr = '\0'; - - qm->uacce->algs = algs; - - return 0; -} - static int hpre_diff_regs_show(struct seq_file *s, void *unused) { struct hisi_qm *qm = s->private; @@ -457,16 +435,6 @@ static u32 vfs_num; module_param_cb(vfs_num, &vfs_num_ops, &vfs_num, 0444); MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)"); -static inline int hpre_cluster_num(struct hisi_qm *qm) -{ - return hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CLUSTER_NUM_CAP, qm->cap_ver); -} - -static inline int hpre_cluster_core_mask(struct hisi_qm *qm) -{ - return hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CORE_ENABLE_BITMAP_CAP, qm->cap_ver); -} - struct hisi_qp *hpre_create_qp(u8 type) { int node = cpu_to_node(smp_processor_id()); @@ -533,13 +501,15 @@ static int hpre_cfg_by_dsm(struct hisi_qm *qm) static int hpre_set_cluster(struct hisi_qm *qm) { - u32 cluster_core_mask = hpre_cluster_core_mask(qm); - u8 clusters_num = hpre_cluster_num(qm); struct device *dev = &qm->pdev->dev; unsigned long offset; + u32 cluster_core_mask; + u8 clusters_num; u32 val = 0; int ret, i; + cluster_core_mask = qm->cap_tables.dev_cap_table[HPRE_CORE_ENABLE_BITMAP_CAP_IDX].cap_val; + clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val; for (i = 0; i < clusters_num; i++) { offset = i * HPRE_CLSTR_ADDR_INTRVL; @@ -734,11 +704,12 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm) static void hpre_cnt_regs_clear(struct hisi_qm *qm) { - u8 clusters_num = hpre_cluster_num(qm); unsigned long offset; + u8 clusters_num; int i; /* clear clusterX/cluster_ctrl */ + clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val; for (i = 0; i < clusters_num; i++) { offset = HPRE_CLSTR_BASE + i * HPRE_CLSTR_ADDR_INTRVL; writel(0x0, qm->io_base + offset + HPRE_CLUSTER_INQURY); @@ -1025,13 +996,14 @@ static int hpre_pf_comm_regs_debugfs_init(struct hisi_qm *qm) static int hpre_cluster_debugfs_init(struct hisi_qm *qm) { - u8 clusters_num = hpre_cluster_num(qm); struct device *dev = &qm->pdev->dev; char buf[HPRE_DBGFS_VAL_MAX_LEN]; struct debugfs_regset32 *regset; struct dentry *tmp_d; + u8 clusters_num; int i, ret; + clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val; for (i = 0; i < clusters_num; i++) { ret = snprintf(buf, HPRE_DBGFS_VAL_MAX_LEN, "cluster%d", i); if (ret >= HPRE_DBGFS_VAL_MAX_LEN) @@ -1136,8 +1108,37 @@ static void hpre_debugfs_exit(struct hisi_qm *qm) debugfs_remove_recursive(qm->debug.debug_root); } +static int hpre_pre_store_cap_reg(struct hisi_qm *qm) +{ + struct hisi_qm_cap_record *hpre_cap; + struct device *dev = &qm->pdev->dev; + size_t i, size; + + size = ARRAY_SIZE(hpre_pre_store_caps); + hpre_cap = devm_kzalloc(dev, sizeof(*hpre_cap) * size, GFP_KERNEL); + if (!hpre_cap) + return -ENOMEM; + + for (i = 0; i < size; i++) { + hpre_cap[i].type = hpre_pre_store_caps[i]; + hpre_cap[i].cap_val = hisi_qm_get_hw_info(qm, hpre_basic_info, + hpre_pre_store_caps[i], qm->cap_ver); + } + + if (hpre_cap[HPRE_CLUSTER_NUM_CAP_IDX].cap_val > HPRE_CLUSTERS_NUM_MAX) { + dev_err(dev, "Device cluster num %u is out of range for driver supports %d!\n", + hpre_cap[HPRE_CLUSTER_NUM_CAP_IDX].cap_val, HPRE_CLUSTERS_NUM_MAX); + return -EINVAL; + } + + qm->cap_tables.dev_cap_table = hpre_cap; + + return 0; +} + static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) { + u64 alg_msk; int ret; if (pdev->revision == QM_HW_V1) { @@ -1168,7 +1169,16 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) return ret; } - ret = hpre_set_qm_algs(qm); + /* Fetch and save the value of capability registers */ + ret = hpre_pre_store_cap_reg(qm); + if (ret) { + pci_err(pdev, "Failed to pre-store capability registers!\n"); + hisi_qm_uninit(qm); + return ret; + } + + alg_msk = qm->cap_tables.dev_cap_table[HPRE_DEV_ALG_BITMAP_CAP_IDX].cap_val; + ret = hisi_qm_set_algs(qm, alg_msk, hpre_dev_algs, ARRAY_SIZE(hpre_dev_algs)); if (ret) { pci_err(pdev, "Failed to set hpre algs!\n"); hisi_qm_uninit(qm); @@ -1181,11 +1191,12 @@ static int hpre_show_last_regs_init(struct hisi_qm *qm) { int cluster_dfx_regs_num = ARRAY_SIZE(hpre_cluster_dfx_regs); int com_dfx_regs_num = ARRAY_SIZE(hpre_com_dfx_regs); - u8 clusters_num = hpre_cluster_num(qm); struct qm_debug *debug = &qm->debug; void __iomem *io_base; + u8 clusters_num; int i, j, idx; + clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val; debug->last_words = kcalloc(cluster_dfx_regs_num * clusters_num + com_dfx_regs_num, sizeof(unsigned int), GFP_KERNEL); if (!debug->last_words) @@ -1222,10 +1233,10 @@ static void hpre_show_last_dfx_regs(struct hisi_qm *qm) { int cluster_dfx_regs_num = ARRAY_SIZE(hpre_cluster_dfx_regs); int com_dfx_regs_num = ARRAY_SIZE(hpre_com_dfx_regs); - u8 clusters_num = hpre_cluster_num(qm); struct qm_debug *debug = &qm->debug; struct pci_dev *pdev = qm->pdev; void __iomem *io_base; + u8 clusters_num; int i, j, idx; u32 val; @@ -1240,6 +1251,7 @@ static void hpre_show_last_dfx_regs(struct hisi_qm *qm) hpre_com_dfx_regs[i].name, debug->last_words[i], val); } + clusters_num = qm->cap_tables.dev_cap_table[HPRE_CLUSTER_NUM_CAP_IDX].cap_val; for (i = 0; i < clusters_num; i++) { io_base = qm->io_base + hpre_cluster_offsets[i]; for (j = 0; j < cluster_dfx_regs_num; j++) { diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index f9acf7ecc41b..5539be1bfb40 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -237,6 +237,8 @@ #define QM_QOS_MAX_CIR_S 11 #define QM_AUTOSUSPEND_DELAY 3000 +#define QM_DEV_ALG_MAX_LEN 256 + #define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \ (((hop_num) << QM_CQ_HOP_NUM_SHIFT) | \ ((pg_sz) << QM_CQ_PAGE_SIZE_SHIFT) | \ @@ -315,6 +317,13 @@ enum qm_basic_type { QM_VF_IRQ_NUM_CAP, }; +enum qm_pre_store_cap_idx { + QM_EQ_IRQ_TYPE_CAP_IDX = 0x0, + QM_AEQ_IRQ_TYPE_CAP_IDX, + QM_ABN_IRQ_TYPE_CAP_IDX, + QM_PF2VF_IRQ_TYPE_CAP_IDX, +}; + static const struct hisi_qm_cap_info qm_cap_info_comm[] = { {QM_SUPPORT_DB_ISOLATION, 0x30, 0, BIT(0), 0x0, 0x0, 0x0}, {QM_SUPPORT_FUNC_QOS, 0x3100, 0, BIT(8), 0x0, 0x0, 0x1}, @@ -344,6 +353,13 @@ static const struct hisi_qm_cap_info qm_basic_info[] = { {QM_VF_IRQ_NUM_CAP, 0x311c, 0, GENMASK(15, 0), 0x1, 0x2, 0x3}, }; +static const u32 qm_pre_store_caps[] = { + QM_EQ_IRQ_TYPE_CAP, + QM_AEQ_IRQ_TYPE_CAP, + QM_ABN_IRQ_TYPE_CAP, + QM_PF2VF_IRQ_TYPE_CAP, +}; + struct qm_mailbox { __le16 w0; __le16 queue_num; @@ -781,6 +797,40 @@ static void qm_get_xqc_depth(struct hisi_qm *qm, u16 *low_bits, *high_bits = (depth >> QM_XQ_DEPTH_SHIFT) & QM_XQ_DEPTH_MASK; } +int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs, + u32 dev_algs_size) +{ + struct device *dev = &qm->pdev->dev; + char *algs, *ptr; + int i; + + if (!qm->uacce) + return 0; + + if (dev_algs_size >= QM_DEV_ALG_MAX_LEN) { + dev_err(dev, "algs size %u is equal or larger than %d.\n", + dev_algs_size, QM_DEV_ALG_MAX_LEN); + return -EINVAL; + } + + algs = devm_kzalloc(dev, QM_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); + if (!algs) + return -ENOMEM; + + for (i = 0; i < dev_algs_size; i++) + if (alg_msk & dev_algs[i].alg_msk) + strcat(algs, dev_algs[i].alg); + + ptr = strrchr(algs, '\n'); + if (ptr) { + *ptr = '\0'; + qm->uacce->algs = algs; + } + + return 0; +} +EXPORT_SYMBOL_GPL(hisi_qm_set_algs); + static u32 qm_get_irq_num(struct hisi_qm *qm) { if (qm->fun_type == QM_HW_PF) @@ -4804,7 +4854,7 @@ static void qm_unregister_abnormal_irq(struct hisi_qm *qm) if (qm->fun_type == QM_HW_VF) return; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_ABN_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_ABN_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_ABN_IRQ_TYPE_MASK)) return; @@ -4821,7 +4871,7 @@ static int qm_register_abnormal_irq(struct hisi_qm *qm) if (qm->fun_type == QM_HW_VF) return 0; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_ABN_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_ABN_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_ABN_IRQ_TYPE_MASK)) return 0; @@ -4838,7 +4888,7 @@ static void qm_unregister_mb_cmd_irq(struct hisi_qm *qm) struct pci_dev *pdev = qm->pdev; u32 irq_vector, val; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF2VF_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_PF2VF_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return; @@ -4852,7 +4902,7 @@ static int qm_register_mb_cmd_irq(struct hisi_qm *qm) u32 irq_vector, val; int ret; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF2VF_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_PF2VF_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return 0; @@ -4869,7 +4919,7 @@ static void qm_unregister_aeq_irq(struct hisi_qm *qm) struct pci_dev *pdev = qm->pdev; u32 irq_vector, val; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_AEQ_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_AEQ_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return; @@ -4883,7 +4933,7 @@ static int qm_register_aeq_irq(struct hisi_qm *qm) u32 irq_vector, val; int ret; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_AEQ_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_AEQ_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return 0; @@ -4901,7 +4951,7 @@ static void qm_unregister_eq_irq(struct hisi_qm *qm) struct pci_dev *pdev = qm->pdev; u32 irq_vector, val; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_EQ_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_EQ_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return; @@ -4915,7 +4965,7 @@ static int qm_register_eq_irq(struct hisi_qm *qm) u32 irq_vector, val; int ret; - val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_EQ_IRQ_TYPE_CAP, qm->cap_ver); + val = qm->cap_tables.qm_cap_table[QM_EQ_IRQ_TYPE_CAP_IDX].cap_val; if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK)) return 0; @@ -5003,7 +5053,29 @@ static int qm_get_qp_num(struct hisi_qm *qm) return 0; } -static void qm_get_hw_caps(struct hisi_qm *qm) +static int qm_pre_store_irq_type_caps(struct hisi_qm *qm) +{ + struct hisi_qm_cap_record *qm_cap; + struct pci_dev *pdev = qm->pdev; + size_t i, size; + + size = ARRAY_SIZE(qm_pre_store_caps); + qm_cap = devm_kzalloc(&pdev->dev, sizeof(*qm_cap) * size, GFP_KERNEL); + if (!qm_cap) + return -ENOMEM; + + for (i = 0; i < size; i++) { + qm_cap[i].type = qm_pre_store_caps[i]; + qm_cap[i].cap_val = hisi_qm_get_hw_info(qm, qm_basic_info, + qm_pre_store_caps[i], qm->cap_ver); + } + + qm->cap_tables.qm_cap_table = qm_cap; + + return 0; +} + +static int qm_get_hw_caps(struct hisi_qm *qm) { const struct hisi_qm_cap_info *cap_info = qm->fun_type == QM_HW_PF ? qm_cap_info_pf : qm_cap_info_vf; @@ -5034,6 +5106,9 @@ static void qm_get_hw_caps(struct hisi_qm *qm) if (val) set_bit(cap_info[i].type, &qm->caps); } + + /* Fetch and save the value of irq type related capability registers */ + return qm_pre_store_irq_type_caps(qm); } static int qm_get_pci_res(struct hisi_qm *qm) @@ -5055,7 +5130,10 @@ static int qm_get_pci_res(struct hisi_qm *qm) goto err_request_mem_regions; } - qm_get_hw_caps(qm); + ret = qm_get_hw_caps(qm); + if (ret) + goto err_ioremap; + if (test_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps)) { qm->db_interval = QM_QP_DB_INTERVAL; qm->db_phys_base = pci_resource_start(pdev, PCI_BAR_4); diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h index 3e57fc04b377..410c83712e28 100644 --- a/drivers/crypto/hisilicon/sec2/sec.h +++ b/drivers/crypto/hisilicon/sec2/sec.h @@ -220,6 +220,13 @@ enum sec_cap_type { SEC_CORE4_ALG_BITMAP_HIGH, }; +enum sec_cap_reg_record_idx { + SEC_DRV_ALG_BITMAP_LOW_IDX = 0x0, + SEC_DRV_ALG_BITMAP_HIGH_IDX, + SEC_DEV_ALG_BITMAP_LOW_IDX, + SEC_DEV_ALG_BITMAP_HIGH_IDX, +}; + void sec_destroy_qps(struct hisi_qp **qps, int qp_num); struct hisi_qp **sec_create_qps(void); int sec_register_to_crypto(struct hisi_qm *qm); diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c index 84ae8ddd1a13..cae7c414bdaf 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.c +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c @@ -2546,8 +2546,12 @@ err: int sec_register_to_crypto(struct hisi_qm *qm) { - u64 alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH, SEC_DRV_ALG_BITMAP_LOW); - int ret; + u64 alg_mask; + int ret = 0; + + alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH_IDX, + SEC_DRV_ALG_BITMAP_LOW_IDX); + ret = sec_register_skcipher(alg_mask); if (ret) @@ -2562,7 +2566,10 @@ int sec_register_to_crypto(struct hisi_qm *qm) void sec_unregister_from_crypto(struct hisi_qm *qm) { - u64 alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH, SEC_DRV_ALG_BITMAP_LOW); + u64 alg_mask; + + alg_mask = sec_get_alg_bitmap(qm, SEC_DRV_ALG_BITMAP_HIGH_IDX, + SEC_DRV_ALG_BITMAP_LOW_IDX); sec_unregister_aead(alg_mask, ARRAY_SIZE(sec_aeads)); sec_unregister_skcipher(alg_mask, ARRAY_SIZE(sec_skciphers)); diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index e384988bda91..4bab5000a13e 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -121,7 +121,6 @@ GENMASK_ULL(42, 25)) #define SEC_AEAD_BITMAP (GENMASK_ULL(7, 6) | GENMASK_ULL(18, 17) | \ GENMASK_ULL(45, 43)) -#define SEC_DEV_ALG_MAX_LEN 256 struct sec_hw_error { u32 int_msk; @@ -133,11 +132,6 @@ struct sec_dfx_item { u32 offset; }; -struct sec_dev_alg { - u64 alg_msk; - const char *algs; -}; - static const char sec_name[] = "hisi_sec2"; static struct dentry *sec_debugfs_root; @@ -174,15 +168,22 @@ static const struct hisi_qm_cap_info sec_basic_info[] = { {SEC_CORE4_ALG_BITMAP_HIGH, 0x3170, 0, GENMASK(31, 0), 0x3FFF, 0x3FFF, 0x3FFF}, }; -static const struct sec_dev_alg sec_dev_algs[] = { { +static const u32 sec_pre_store_caps[] = { + SEC_DRV_ALG_BITMAP_LOW, + SEC_DRV_ALG_BITMAP_HIGH, + SEC_DEV_ALG_BITMAP_LOW, + SEC_DEV_ALG_BITMAP_HIGH, +}; + +static const struct qm_dev_alg sec_dev_algs[] = { { .alg_msk = SEC_CIPHER_BITMAP, - .algs = "cipher\n", + .alg = "cipher\n", }, { .alg_msk = SEC_DIGEST_BITMAP, - .algs = "digest\n", + .alg = "digest\n", }, { .alg_msk = SEC_AEAD_BITMAP, - .algs = "aead\n", + .alg = "aead\n", }, }; @@ -395,8 +396,8 @@ u64 sec_get_alg_bitmap(struct hisi_qm *qm, u32 high, u32 low) { u32 cap_val_h, cap_val_l; - cap_val_h = hisi_qm_get_hw_info(qm, sec_basic_info, high, qm->cap_ver); - cap_val_l = hisi_qm_get_hw_info(qm, sec_basic_info, low, qm->cap_ver); + cap_val_h = qm->cap_tables.dev_cap_table[high].cap_val; + cap_val_l = qm->cap_tables.dev_cap_table[low].cap_val; return ((u64)cap_val_h << SEC_ALG_BITMAP_SHIFT) | (u64)cap_val_l; } @@ -1079,37 +1080,31 @@ static int sec_pf_probe_init(struct sec_dev *sec) return ret; } -static int sec_set_qm_algs(struct hisi_qm *qm) +static int sec_pre_store_cap_reg(struct hisi_qm *qm) { - struct device *dev = &qm->pdev->dev; - char *algs, *ptr; - u64 alg_mask; - int i; - - if (!qm->use_sva) - return 0; + struct hisi_qm_cap_record *sec_cap; + struct pci_dev *pdev = qm->pdev; + size_t i, size; - algs = devm_kzalloc(dev, SEC_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); - if (!algs) + size = ARRAY_SIZE(sec_pre_store_caps); + sec_cap = devm_kzalloc(&pdev->dev, sizeof(*sec_cap) * size, GFP_KERNEL); + if (!sec_cap) return -ENOMEM; - alg_mask = sec_get_alg_bitmap(qm, SEC_DEV_ALG_BITMAP_HIGH, SEC_DEV_ALG_BITMAP_LOW); - - for (i = 0; i < ARRAY_SIZE(sec_dev_algs); i++) - if (alg_mask & sec_dev_algs[i].alg_msk) - strcat(algs, sec_dev_algs[i].algs); - - ptr = strrchr(algs, '\n'); - if (ptr) - *ptr = '\0'; + for (i = 0; i < size; i++) { + sec_cap[i].type = sec_pre_store_caps[i]; + sec_cap[i].cap_val = hisi_qm_get_hw_info(qm, sec_basic_info, + sec_pre_store_caps[i], qm->cap_ver); + } - qm->uacce->algs = algs; + qm->cap_tables.dev_cap_table = sec_cap; return 0; } static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) { + u64 alg_msk; int ret; qm->pdev = pdev; @@ -1144,7 +1139,16 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) return ret; } - ret = sec_set_qm_algs(qm); + /* Fetch and save the value of capability registers */ + ret = sec_pre_store_cap_reg(qm); + if (ret) { + pci_err(qm->pdev, "Failed to pre-store capability registers!\n"); + hisi_qm_uninit(qm); + return ret; + } + + alg_msk = sec_get_alg_bitmap(qm, SEC_DEV_ALG_BITMAP_HIGH_IDX, SEC_DEV_ALG_BITMAP_LOW_IDX); + ret = hisi_qm_set_algs(qm, alg_msk, sec_dev_algs, ARRAY_SIZE(sec_dev_algs)); if (ret) { pci_err(qm->pdev, "Failed to set sec algs!\n"); hisi_qm_uninit(qm); diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 190b4fecfc74..9e3f5bca27de 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -74,7 +74,6 @@ #define HZIP_AXI_SHUTDOWN_ENABLE BIT(14) #define HZIP_WR_PORT BIT(11) -#define HZIP_DEV_ALG_MAX_LEN 256 #define HZIP_ALG_ZLIB_BIT GENMASK(1, 0) #define HZIP_ALG_GZIP_BIT GENMASK(3, 2) #define HZIP_ALG_DEFLATE_BIT GENMASK(5, 4) @@ -107,6 +106,14 @@ #define HZIP_CLOCK_GATED_EN (HZIP_CORE_GATED_EN | \ HZIP_CORE_GATED_OOO_EN) +/* zip comp high performance */ +#define HZIP_HIGH_PERF_OFFSET 0x301208 + +enum { + HZIP_HIGH_COMP_RATE, + HZIP_HIGH_COMP_PERF, +}; + static const char hisi_zip_name[] = "hisi_zip"; static struct dentry *hzip_debugfs_root; @@ -120,23 +127,18 @@ struct zip_dfx_item { u32 offset; }; -struct zip_dev_alg { - u32 alg_msk; - const char *algs; -}; - -static const struct zip_dev_alg zip_dev_algs[] = { { +static const struct qm_dev_alg zip_dev_algs[] = { { .alg_msk = HZIP_ALG_ZLIB_BIT, - .algs = "zlib\n", + .alg = "zlib\n", }, { .alg_msk = HZIP_ALG_GZIP_BIT, - .algs = "gzip\n", + .alg = "gzip\n", }, { .alg_msk = HZIP_ALG_DEFLATE_BIT, - .algs = "deflate\n", + .alg = "deflate\n", }, { .alg_msk = HZIP_ALG_LZ77_BIT, - .algs = "lz77_zstd\n", + .alg = "lz77_zstd\n", }, }; @@ -247,6 +249,26 @@ static struct hisi_qm_cap_info zip_basic_cap_info[] = { {ZIP_CAP_MAX, 0x317c, 0, GENMASK(0, 0), 0x0, 0x0, 0x0} }; +enum zip_pre_store_cap_idx { + ZIP_CORE_NUM_CAP_IDX = 0x0, + ZIP_CLUSTER_COMP_NUM_CAP_IDX, + ZIP_CLUSTER_DECOMP_NUM_CAP_IDX, + ZIP_DECOMP_ENABLE_BITMAP_IDX, + ZIP_COMP_ENABLE_BITMAP_IDX, + ZIP_DRV_ALG_BITMAP_IDX, + ZIP_DEV_ALG_BITMAP_IDX, +}; + +static const u32 zip_pre_store_caps[] = { + ZIP_CORE_NUM_CAP, + ZIP_CLUSTER_COMP_NUM_CAP, + ZIP_CLUSTER_DECOMP_NUM_CAP, + ZIP_DECOMP_ENABLE_BITMAP, + ZIP_COMP_ENABLE_BITMAP, + ZIP_DRV_ALG_BITMAP, + ZIP_DEV_ALG_BITMAP, +}; + enum { HZIP_COMP_CORE0, HZIP_COMP_CORE1, @@ -352,6 +374,37 @@ static int hzip_diff_regs_show(struct seq_file *s, void *unused) return 0; } DEFINE_SHOW_ATTRIBUTE(hzip_diff_regs); + +static int perf_mode_set(const char *val, const struct kernel_param *kp) +{ + int ret; + u32 n; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret != 0 || (n != HZIP_HIGH_COMP_PERF && + n != HZIP_HIGH_COMP_RATE)) + return -EINVAL; + + return param_set_int(val, kp); +} + +static const struct kernel_param_ops zip_com_perf_ops = { + .set = perf_mode_set, + .get = param_get_int, +}; + +/* + * perf_mode = 0 means enable high compression rate mode, + * perf_mode = 1 means enable high compression performance mode. + * These two modes only apply to the compression direction. + */ +static u32 perf_mode = HZIP_HIGH_COMP_RATE; +module_param_cb(perf_mode, &zip_com_perf_ops, &perf_mode, 0444); +MODULE_PARM_DESC(perf_mode, "ZIP high perf mode 0(default), 1(enable)"); + static const struct kernel_param_ops zip_uacce_mode_ops = { .set = uacce_mode_set, .get = param_get_int, @@ -410,40 +463,33 @@ bool hisi_zip_alg_support(struct hisi_qm *qm, u32 alg) { u32 cap_val; - cap_val = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_DRV_ALG_BITMAP, qm->cap_ver); + cap_val = qm->cap_tables.dev_cap_table[ZIP_DRV_ALG_BITMAP_IDX].cap_val; if ((alg & cap_val) == alg) return true; return false; } -static int hisi_zip_set_qm_algs(struct hisi_qm *qm) +static int hisi_zip_set_high_perf(struct hisi_qm *qm) { - struct device *dev = &qm->pdev->dev; - char *algs, *ptr; - u32 alg_mask; - int i; - - if (!qm->use_sva) - return 0; - - algs = devm_kzalloc(dev, HZIP_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL); - if (!algs) - return -ENOMEM; - - alg_mask = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_DEV_ALG_BITMAP, qm->cap_ver); - - for (i = 0; i < ARRAY_SIZE(zip_dev_algs); i++) - if (alg_mask & zip_dev_algs[i].alg_msk) - strcat(algs, zip_dev_algs[i].algs); - - ptr = strrchr(algs, '\n'); - if (ptr) - *ptr = '\0'; + u32 val; + int ret; - qm->uacce->algs = algs; + val = readl_relaxed(qm->io_base + HZIP_HIGH_PERF_OFFSET); + if (perf_mode == HZIP_HIGH_COMP_PERF) + val |= HZIP_HIGH_COMP_PERF; + else + val &= ~HZIP_HIGH_COMP_PERF; + + /* Set perf mode */ + writel(val, qm->io_base + HZIP_HIGH_PERF_OFFSET); + ret = readl_relaxed_poll_timeout(qm->io_base + HZIP_HIGH_PERF_OFFSET, + val, val == perf_mode, HZIP_DELAY_1_US, + HZIP_POLL_TIMEOUT_US); + if (ret) + pci_err(qm->pdev, "failed to set perf mode\n"); - return 0; + return ret; } static void hisi_zip_open_sva_prefetch(struct hisi_qm *qm) @@ -542,10 +588,8 @@ static int hisi_zip_set_user_domain_and_cache(struct hisi_qm *qm) } /* let's open all compression/decompression cores */ - dcomp_bm = hisi_qm_get_hw_info(qm, zip_basic_cap_info, - ZIP_DECOMP_ENABLE_BITMAP, qm->cap_ver); - comp_bm = hisi_qm_get_hw_info(qm, zip_basic_cap_info, - ZIP_COMP_ENABLE_BITMAP, qm->cap_ver); + dcomp_bm = qm->cap_tables.dev_cap_table[ZIP_DECOMP_ENABLE_BITMAP_IDX].cap_val; + comp_bm = qm->cap_tables.dev_cap_table[ZIP_COMP_ENABLE_BITMAP_IDX].cap_val; writel(HZIP_DECOMP_CHECK_ENABLE | dcomp_bm | comp_bm, base + HZIP_CLOCK_GATE_CTRL); /* enable sqc,cqc writeback */ @@ -772,9 +816,8 @@ static int hisi_zip_core_debug_init(struct hisi_qm *qm) char buf[HZIP_BUF_SIZE]; int i; - zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver); - zip_comp_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CLUSTER_COMP_NUM_CAP, - qm->cap_ver); + zip_core_num = qm->cap_tables.dev_cap_table[ZIP_CORE_NUM_CAP_IDX].cap_val; + zip_comp_core_num = qm->cap_tables.dev_cap_table[ZIP_CLUSTER_COMP_NUM_CAP_IDX].cap_val; for (i = 0; i < zip_core_num; i++) { if (i < zip_comp_core_num) @@ -916,7 +959,7 @@ static int hisi_zip_show_last_regs_init(struct hisi_qm *qm) u32 zip_core_num; int i, j, idx; - zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver); + zip_core_num = qm->cap_tables.dev_cap_table[ZIP_CORE_NUM_CAP_IDX].cap_val; debug->last_words = kcalloc(core_dfx_regs_num * zip_core_num + com_dfx_regs_num, sizeof(unsigned int), GFP_KERNEL); @@ -972,9 +1015,9 @@ static void hisi_zip_show_last_dfx_regs(struct hisi_qm *qm) hzip_com_dfx_regs[i].name, debug->last_words[i], val); } - zip_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CORE_NUM_CAP, qm->cap_ver); - zip_comp_core_num = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_CLUSTER_COMP_NUM_CAP, - qm->cap_ver); + zip_core_num = qm->cap_tables.dev_cap_table[ZIP_CORE_NUM_CAP_IDX].cap_val; + zip_comp_core_num = qm->cap_tables.dev_cap_table[ZIP_CLUSTER_COMP_NUM_CAP_IDX].cap_val; + for (i = 0; i < zip_core_num; i++) { if (i < zip_comp_core_num) scnprintf(buf, sizeof(buf), "Comp_core-%d", i); @@ -1115,6 +1158,10 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) if (ret) return ret; + ret = hisi_zip_set_high_perf(qm); + if (ret) + return ret; + hisi_zip_open_sva_prefetch(qm); hisi_qm_dev_err_init(qm); hisi_zip_debug_regs_clear(qm); @@ -1126,8 +1173,31 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) return ret; } +static int zip_pre_store_cap_reg(struct hisi_qm *qm) +{ + struct hisi_qm_cap_record *zip_cap; + struct pci_dev *pdev = qm->pdev; + size_t i, size; + + size = ARRAY_SIZE(zip_pre_store_caps); + zip_cap = devm_kzalloc(&pdev->dev, sizeof(*zip_cap) * size, GFP_KERNEL); + if (!zip_cap) + return -ENOMEM; + + for (i = 0; i < size; i++) { + zip_cap[i].type = zip_pre_store_caps[i]; + zip_cap[i].cap_val = hisi_qm_get_hw_info(qm, zip_basic_cap_info, + zip_pre_store_caps[i], qm->cap_ver); + } + + qm->cap_tables.dev_cap_table = zip_cap; + + return 0; +} + static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) { + u64 alg_msk; int ret; qm->pdev = pdev; @@ -1163,7 +1233,16 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) return ret; } - ret = hisi_zip_set_qm_algs(qm); + /* Fetch and save the value of capability registers */ + ret = zip_pre_store_cap_reg(qm); + if (ret) { + pci_err(qm->pdev, "Failed to pre-store capability registers!\n"); + hisi_qm_uninit(qm); + return ret; + } + + alg_msk = qm->cap_tables.dev_cap_table[ZIP_DEV_ALG_BITMAP_IDX].cap_val; + ret = hisi_qm_set_algs(qm, alg_msk, zip_dev_algs, ARRAY_SIZE(zip_dev_algs)); if (ret) { pci_err(qm->pdev, "Failed to set zip algs!\n"); hisi_qm_uninit(qm); diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c index 32a37e3850c5..f59e32115268 100644 --- a/drivers/crypto/inside-secure/safexcel_cipher.c +++ b/drivers/crypto/inside-secure/safexcel_cipher.c @@ -742,9 +742,9 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring, max(totlen_src, totlen_dst)); return -EINVAL; } - if (sreq->nr_src > 0) - dma_map_sg(priv->dev, src, sreq->nr_src, - DMA_BIDIRECTIONAL); + if (sreq->nr_src > 0 && + !dma_map_sg(priv->dev, src, sreq->nr_src, DMA_BIDIRECTIONAL)) + return -EIO; } else { if (unlikely(totlen_src && (sreq->nr_src <= 0))) { dev_err(priv->dev, "Source buffer not large enough (need %d bytes)!", @@ -752,8 +752,9 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring, return -EINVAL; } - if (sreq->nr_src > 0) - dma_map_sg(priv->dev, src, sreq->nr_src, DMA_TO_DEVICE); + if (sreq->nr_src > 0 && + !dma_map_sg(priv->dev, src, sreq->nr_src, DMA_TO_DEVICE)) + return -EIO; if (unlikely(totlen_dst && (sreq->nr_dst <= 0))) { dev_err(priv->dev, "Dest buffer not large enough (need %d bytes)!", @@ -762,9 +763,11 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring, goto unmap; } - if (sreq->nr_dst > 0) - dma_map_sg(priv->dev, dst, sreq->nr_dst, - DMA_FROM_DEVICE); + if (sreq->nr_dst > 0 && + !dma_map_sg(priv->dev, dst, sreq->nr_dst, DMA_FROM_DEVICE)) { + ret = -EIO; + goto unmap; + } } memcpy(ctx->base.ctxr->data, ctx->key, ctx->key_len); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c index 71e5f79431af..6e4a78e1f3ce 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c @@ -419,8 +419,8 @@ int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_mask, int pri, return 0; free_iq: - otx2_cpt_free_instruction_queues(lfs); cptlf_hw_cleanup(lfs); + otx2_cpt_free_instruction_queues(lfs); detach_rsrcs: otx2_cpt_detach_rsrcs_msg(lfs); clear_lfs_num: @@ -431,11 +431,13 @@ EXPORT_SYMBOL_NS_GPL(otx2_cptlf_init, CRYPTO_DEV_OCTEONTX2_CPT); void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs) { - lfs->lfs_num = 0; /* Cleanup LFs hardware side */ cptlf_hw_cleanup(lfs); + /* Free instruction queues */ + otx2_cpt_free_instruction_queues(lfs); /* Send request to detach LFs */ otx2_cpt_detach_rsrcs_msg(lfs); + lfs->lfs_num = 0; } EXPORT_SYMBOL_NS_GPL(otx2_cptlf_shutdown, CRYPTO_DEV_OCTEONTX2_CPT); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c index 392e9fee05e8..6f3373f9928c 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c @@ -249,8 +249,11 @@ static void cptvf_lf_shutdown(struct otx2_cptlfs_info *lfs) otx2_cptlf_unregister_interrupts(lfs); /* Cleanup LFs software side */ lf_sw_cleanup(lfs); + /* Free instruction queues */ + otx2_cpt_free_instruction_queues(lfs); /* Send request to detach LFs */ otx2_cpt_detach_rsrcs_msg(lfs); + lfs->lfs_num = 0; } static int cptvf_lf_init(struct otx2_cptvf_dev *cptvf) diff --git a/drivers/crypto/sa2ul.c b/drivers/crypto/sa2ul.c index f4bc06c24ad8..e7efebf8127f 100644 --- a/drivers/crypto/sa2ul.c +++ b/drivers/crypto/sa2ul.c @@ -1868,9 +1868,8 @@ static int sa_aead_setkey(struct crypto_aead *authenc, crypto_aead_set_flags(ctx->fallback.aead, crypto_aead_get_flags(authenc) & CRYPTO_TFM_REQ_MASK); - crypto_aead_setkey(ctx->fallback.aead, key, keylen); - return 0; + return crypto_aead_setkey(ctx->fallback.aead, key, keylen); } static int sa_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize) diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c index 7ab20fb95166..3b946f1313ed 100644 --- a/drivers/crypto/sahara.c +++ b/drivers/crypto/sahara.c @@ -44,7 +44,6 @@ #define FLAGS_MODE_MASK 0x000f #define FLAGS_ENCRYPT BIT(0) #define FLAGS_CBC BIT(1) -#define FLAGS_NEW_KEY BIT(3) #define SAHARA_HDR_BASE 0x00800000 #define SAHARA_HDR_SKHA_ALG_AES 0 @@ -142,8 +141,6 @@ struct sahara_hw_link { }; struct sahara_ctx { - unsigned long flags; - /* AES-specific context */ int keylen; u8 key[AES_KEYSIZE_128]; @@ -152,6 +149,7 @@ struct sahara_ctx { struct sahara_aes_reqctx { unsigned long mode; + u8 iv_out[AES_BLOCK_SIZE]; struct skcipher_request fallback_req; // keep at the end }; @@ -447,27 +445,24 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev) int ret; int i, j; int idx = 0; + u32 len; - /* Copy new key if necessary */ - if (ctx->flags & FLAGS_NEW_KEY) { - memcpy(dev->key_base, ctx->key, ctx->keylen); - ctx->flags &= ~FLAGS_NEW_KEY; + memcpy(dev->key_base, ctx->key, ctx->keylen); - if (dev->flags & FLAGS_CBC) { - dev->hw_desc[idx]->len1 = AES_BLOCK_SIZE; - dev->hw_desc[idx]->p1 = dev->iv_phys_base; - } else { - dev->hw_desc[idx]->len1 = 0; - dev->hw_desc[idx]->p1 = 0; - } - dev->hw_desc[idx]->len2 = ctx->keylen; - dev->hw_desc[idx]->p2 = dev->key_phys_base; - dev->hw_desc[idx]->next = dev->hw_phys_desc[1]; + if (dev->flags & FLAGS_CBC) { + dev->hw_desc[idx]->len1 = AES_BLOCK_SIZE; + dev->hw_desc[idx]->p1 = dev->iv_phys_base; + } else { + dev->hw_desc[idx]->len1 = 0; + dev->hw_desc[idx]->p1 = 0; + } + dev->hw_desc[idx]->len2 = ctx->keylen; + dev->hw_desc[idx]->p2 = dev->key_phys_base; + dev->hw_desc[idx]->next = dev->hw_phys_desc[1]; + dev->hw_desc[idx]->hdr = sahara_aes_key_hdr(dev); - dev->hw_desc[idx]->hdr = sahara_aes_key_hdr(dev); + idx++; - idx++; - } dev->nb_in_sg = sg_nents_for_len(dev->in_sg, dev->total); if (dev->nb_in_sg < 0) { @@ -489,24 +484,27 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev) DMA_TO_DEVICE); if (!ret) { dev_err(dev->device, "couldn't map in sg\n"); - goto unmap_in; + return -EINVAL; } + ret = dma_map_sg(dev->device, dev->out_sg, dev->nb_out_sg, DMA_FROM_DEVICE); if (!ret) { dev_err(dev->device, "couldn't map out sg\n"); - goto unmap_out; + goto unmap_in; } /* Create input links */ dev->hw_desc[idx]->p1 = dev->hw_phys_link[0]; sg = dev->in_sg; + len = dev->total; for (i = 0; i < dev->nb_in_sg; i++) { - dev->hw_link[i]->len = sg->length; + dev->hw_link[i]->len = min(len, sg->length); dev->hw_link[i]->p = sg->dma_address; if (i == (dev->nb_in_sg - 1)) { dev->hw_link[i]->next = 0; } else { + len -= min(len, sg->length); dev->hw_link[i]->next = dev->hw_phys_link[i + 1]; sg = sg_next(sg); } @@ -515,12 +513,14 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev) /* Create output links */ dev->hw_desc[idx]->p2 = dev->hw_phys_link[i]; sg = dev->out_sg; + len = dev->total; for (j = i; j < dev->nb_out_sg + i; j++) { - dev->hw_link[j]->len = sg->length; + dev->hw_link[j]->len = min(len, sg->length); dev->hw_link[j]->p = sg->dma_address; if (j == (dev->nb_out_sg + i - 1)) { dev->hw_link[j]->next = 0; } else { + len -= min(len, sg->length); dev->hw_link[j]->next = dev->hw_phys_link[j + 1]; sg = sg_next(sg); } @@ -539,9 +539,6 @@ static int sahara_hw_descriptor_create(struct sahara_dev *dev) return 0; -unmap_out: - dma_unmap_sg(dev->device, dev->out_sg, dev->nb_out_sg, - DMA_FROM_DEVICE); unmap_in: dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg, DMA_TO_DEVICE); @@ -549,8 +546,24 @@ unmap_in: return -EINVAL; } +static void sahara_aes_cbc_update_iv(struct skcipher_request *req) +{ + struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); + struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); + unsigned int ivsize = crypto_skcipher_ivsize(skcipher); + + /* Update IV buffer to contain the last ciphertext block */ + if (rctx->mode & FLAGS_ENCRYPT) { + sg_pcopy_to_buffer(req->dst, sg_nents(req->dst), req->iv, + ivsize, req->cryptlen - ivsize); + } else { + memcpy(req->iv, rctx->iv_out, ivsize); + } +} + static int sahara_aes_process(struct skcipher_request *req) { + struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); struct sahara_dev *dev = dev_ptr; struct sahara_ctx *ctx; struct sahara_aes_reqctx *rctx; @@ -572,8 +585,17 @@ static int sahara_aes_process(struct skcipher_request *req) rctx->mode &= FLAGS_MODE_MASK; dev->flags = (dev->flags & ~FLAGS_MODE_MASK) | rctx->mode; - if ((dev->flags & FLAGS_CBC) && req->iv) - memcpy(dev->iv_base, req->iv, AES_KEYSIZE_128); + if ((dev->flags & FLAGS_CBC) && req->iv) { + unsigned int ivsize = crypto_skcipher_ivsize(skcipher); + + memcpy(dev->iv_base, req->iv, ivsize); + + if (!(dev->flags & FLAGS_ENCRYPT)) { + sg_pcopy_to_buffer(req->src, sg_nents(req->src), + rctx->iv_out, ivsize, + req->cryptlen - ivsize); + } + } /* assign new context to device */ dev->ctx = ctx; @@ -586,16 +608,20 @@ static int sahara_aes_process(struct skcipher_request *req) timeout = wait_for_completion_timeout(&dev->dma_completion, msecs_to_jiffies(SAHARA_TIMEOUT_MS)); - if (!timeout) { - dev_err(dev->device, "AES timeout\n"); - return -ETIMEDOUT; - } dma_unmap_sg(dev->device, dev->out_sg, dev->nb_out_sg, DMA_FROM_DEVICE); dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg, DMA_TO_DEVICE); + if (!timeout) { + dev_err(dev->device, "AES timeout\n"); + return -ETIMEDOUT; + } + + if ((dev->flags & FLAGS_CBC) && req->iv) + sahara_aes_cbc_update_iv(req); + return 0; } @@ -609,7 +635,6 @@ static int sahara_aes_setkey(struct crypto_skcipher *tfm, const u8 *key, /* SAHARA only supports 128bit keys */ if (keylen == AES_KEYSIZE_128) { memcpy(ctx->key, key, keylen); - ctx->flags |= FLAGS_NEW_KEY; return 0; } @@ -625,12 +650,40 @@ static int sahara_aes_setkey(struct crypto_skcipher *tfm, const u8 *key, return crypto_skcipher_setkey(ctx->fallback, key, keylen); } +static int sahara_aes_fallback(struct skcipher_request *req, unsigned long mode) +{ + struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); + struct sahara_ctx *ctx = crypto_skcipher_ctx( + crypto_skcipher_reqtfm(req)); + + skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); + skcipher_request_set_callback(&rctx->fallback_req, + req->base.flags, + req->base.complete, + req->base.data); + skcipher_request_set_crypt(&rctx->fallback_req, req->src, + req->dst, req->cryptlen, req->iv); + + if (mode & FLAGS_ENCRYPT) + return crypto_skcipher_encrypt(&rctx->fallback_req); + + return crypto_skcipher_decrypt(&rctx->fallback_req); +} + static int sahara_aes_crypt(struct skcipher_request *req, unsigned long mode) { struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); + struct sahara_ctx *ctx = crypto_skcipher_ctx( + crypto_skcipher_reqtfm(req)); struct sahara_dev *dev = dev_ptr; int err = 0; + if (!req->cryptlen) + return 0; + + if (unlikely(ctx->keylen != AES_KEYSIZE_128)) + return sahara_aes_fallback(req, mode); + dev_dbg(dev->device, "nbytes: %d, enc: %d, cbc: %d\n", req->cryptlen, !!(mode & FLAGS_ENCRYPT), !!(mode & FLAGS_CBC)); @@ -653,81 +706,21 @@ static int sahara_aes_crypt(struct skcipher_request *req, unsigned long mode) static int sahara_aes_ecb_encrypt(struct skcipher_request *req) { - struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); - struct sahara_ctx *ctx = crypto_skcipher_ctx( - crypto_skcipher_reqtfm(req)); - - if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { - skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); - skcipher_request_set_callback(&rctx->fallback_req, - req->base.flags, - req->base.complete, - req->base.data); - skcipher_request_set_crypt(&rctx->fallback_req, req->src, - req->dst, req->cryptlen, req->iv); - return crypto_skcipher_encrypt(&rctx->fallback_req); - } - return sahara_aes_crypt(req, FLAGS_ENCRYPT); } static int sahara_aes_ecb_decrypt(struct skcipher_request *req) { - struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); - struct sahara_ctx *ctx = crypto_skcipher_ctx( - crypto_skcipher_reqtfm(req)); - - if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { - skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); - skcipher_request_set_callback(&rctx->fallback_req, - req->base.flags, - req->base.complete, - req->base.data); - skcipher_request_set_crypt(&rctx->fallback_req, req->src, - req->dst, req->cryptlen, req->iv); - return crypto_skcipher_decrypt(&rctx->fallback_req); - } - return sahara_aes_crypt(req, 0); } static int sahara_aes_cbc_encrypt(struct skcipher_request *req) { - struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); - struct sahara_ctx *ctx = crypto_skcipher_ctx( - crypto_skcipher_reqtfm(req)); - - if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { - skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); - skcipher_request_set_callback(&rctx->fallback_req, - req->base.flags, - req->base.complete, - req->base.data); - skcipher_request_set_crypt(&rctx->fallback_req, req->src, - req->dst, req->cryptlen, req->iv); - return crypto_skcipher_encrypt(&rctx->fallback_req); - } - return sahara_aes_crypt(req, FLAGS_ENCRYPT | FLAGS_CBC); } static int sahara_aes_cbc_decrypt(struct skcipher_request *req) { - struct sahara_aes_reqctx *rctx = skcipher_request_ctx(req); - struct sahara_ctx *ctx = crypto_skcipher_ctx( - crypto_skcipher_reqtfm(req)); - - if (unlikely(ctx->keylen != AES_KEYSIZE_128)) { - skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); - skcipher_request_set_callback(&rctx->fallback_req, - req->base.flags, - req->base.complete, - req->base.data); - skcipher_request_set_crypt(&rctx->fallback_req, req->src, - req->dst, req->cryptlen, req->iv); - return crypto_skcipher_decrypt(&rctx->fallback_req); - } - return sahara_aes_crypt(req, FLAGS_CBC); } @@ -784,6 +777,7 @@ static int sahara_sha_hw_links_create(struct sahara_dev *dev, int start) { struct scatterlist *sg; + unsigned int len; unsigned int i; int ret; @@ -805,12 +799,14 @@ static int sahara_sha_hw_links_create(struct sahara_dev *dev, if (!ret) return -EFAULT; + len = rctx->total; for (i = start; i < dev->nb_in_sg + start; i++) { - dev->hw_link[i]->len = sg->length; + dev->hw_link[i]->len = min(len, sg->length); dev->hw_link[i]->p = sg->dma_address; if (i == (dev->nb_in_sg + start - 1)) { dev->hw_link[i]->next = 0; } else { + len -= min(len, sg->length); dev->hw_link[i]->next = dev->hw_phys_link[i + 1]; sg = sg_next(sg); } @@ -891,24 +887,6 @@ static int sahara_sha_hw_context_descriptor_create(struct sahara_dev *dev, return 0; } -static int sahara_walk_and_recalc(struct scatterlist *sg, unsigned int nbytes) -{ - if (!sg || !sg->length) - return nbytes; - - while (nbytes && sg) { - if (nbytes <= sg->length) { - sg->length = nbytes; - sg_mark_end(sg); - break; - } - nbytes -= sg->length; - sg = sg_next(sg); - } - - return nbytes; -} - static int sahara_sha_prepare_request(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); @@ -945,36 +923,20 @@ static int sahara_sha_prepare_request(struct ahash_request *req) hash_later, 0); } - /* nbytes should now be multiple of blocksize */ - req->nbytes = req->nbytes - hash_later; - - sahara_walk_and_recalc(req->src, req->nbytes); - + rctx->total = len - hash_later; /* have data from previous operation and current */ if (rctx->buf_cnt && req->nbytes) { sg_init_table(rctx->in_sg_chain, 2); sg_set_buf(rctx->in_sg_chain, rctx->rembuf, rctx->buf_cnt); - sg_chain(rctx->in_sg_chain, 2, req->src); - - rctx->total = req->nbytes + rctx->buf_cnt; rctx->in_sg = rctx->in_sg_chain; - - req->src = rctx->in_sg_chain; /* only data from previous operation */ } else if (rctx->buf_cnt) { - if (req->src) - rctx->in_sg = req->src; - else - rctx->in_sg = rctx->in_sg_chain; - /* buf was copied into rembuf above */ + rctx->in_sg = rctx->in_sg_chain; sg_init_one(rctx->in_sg, rctx->rembuf, rctx->buf_cnt); - rctx->total = rctx->buf_cnt; /* no data from previous operation */ } else { rctx->in_sg = req->src; - rctx->total = req->nbytes; - req->src = rctx->in_sg; } /* on next call, we only have the remaining data in the buffer */ @@ -995,7 +957,10 @@ static int sahara_sha_process(struct ahash_request *req) return ret; if (rctx->first) { - sahara_sha_hw_data_descriptor_create(dev, rctx, req, 0); + ret = sahara_sha_hw_data_descriptor_create(dev, rctx, req, 0); + if (ret) + return ret; + dev->hw_desc[0]->next = 0; rctx->first = 0; } else { @@ -1003,7 +968,10 @@ static int sahara_sha_process(struct ahash_request *req) sahara_sha_hw_context_descriptor_create(dev, rctx, req, 0); dev->hw_desc[0]->next = dev->hw_phys_desc[1]; - sahara_sha_hw_data_descriptor_create(dev, rctx, req, 1); + ret = sahara_sha_hw_data_descriptor_create(dev, rctx, req, 1); + if (ret) + return ret; + dev->hw_desc[1]->next = 0; } @@ -1016,18 +984,19 @@ static int sahara_sha_process(struct ahash_request *req) timeout = wait_for_completion_timeout(&dev->dma_completion, msecs_to_jiffies(SAHARA_TIMEOUT_MS)); - if (!timeout) { - dev_err(dev->device, "SHA timeout\n"); - return -ETIMEDOUT; - } if (rctx->sg_in_idx) dma_unmap_sg(dev->device, dev->in_sg, dev->nb_in_sg, DMA_TO_DEVICE); + if (!timeout) { + dev_err(dev->device, "SHA timeout\n"); + return -ETIMEDOUT; + } + memcpy(rctx->context, dev->context_base, rctx->context_size); - if (req->result) + if (req->result && rctx->last) memcpy(req->result, rctx->context, rctx->digest_size); return 0; @@ -1171,8 +1140,7 @@ static int sahara_sha_import(struct ahash_request *req, const void *in) static int sahara_sha_cra_init(struct crypto_tfm *tfm) { crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), - sizeof(struct sahara_sha_reqctx) + - SHA_BUFFER_LEN + SHA256_BLOCK_SIZE); + sizeof(struct sahara_sha_reqctx)); return 0; } diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c index 90a920e7f664..c439be1650c8 100644 --- a/drivers/crypto/stm32/stm32-crc32.c +++ b/drivers/crypto/stm32/stm32-crc32.c @@ -104,7 +104,7 @@ static struct stm32_crc *stm32_crc_get_next_crc(void) struct stm32_crc *crc; spin_lock_bh(&crc_list.lock); - crc = list_first_entry(&crc_list.dev_list, struct stm32_crc, list); + crc = list_first_entry_or_null(&crc_list.dev_list, struct stm32_crc, list); if (crc) list_move_tail(&crc->list, &crc_list.dev_list); spin_unlock_bh(&crc_list.lock); diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c index 168195672e2e..d2df97cfcb29 100644 --- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -104,7 +104,8 @@ static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request * } static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx, - struct virtio_crypto_ctrl_header *header, void *para, + struct virtio_crypto_ctrl_header *header, + struct virtio_crypto_akcipher_session_para *para, const uint8_t *key, unsigned int keylen) { struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3]; @@ -128,7 +129,7 @@ static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher ctrl = &vc_ctrl_req->ctrl; memcpy(&ctrl->header, header, sizeof(ctrl->header)); - memcpy(&ctrl->u, para, sizeof(ctrl->u)); + memcpy(&ctrl->u.akcipher_create_session.para, para, sizeof(*para)); input = &vc_ctrl_req->input; input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR); diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h index 154590e1f764..7059bbe5a2eb 100644 --- a/drivers/crypto/virtio/virtio_crypto_common.h +++ b/drivers/crypto/virtio/virtio_crypto_common.h @@ -10,6 +10,7 @@ #include <linux/virtio.h> #include <linux/crypto.h> #include <linux/spinlock.h> +#include <linux/interrupt.h> #include <crypto/aead.h> #include <crypto/aes.h> #include <crypto/engine.h> @@ -28,6 +29,7 @@ struct data_queue { char name[32]; struct crypto_engine *engine; + struct tasklet_struct done_task; }; struct virtio_crypto { diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index 3842915ea743..56dc0935c774 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -72,27 +72,28 @@ int virtio_crypto_ctrl_vq_request(struct virtio_crypto *vcrypto, struct scatterl return 0; } -static void virtcrypto_dataq_callback(struct virtqueue *vq) +static void virtcrypto_done_task(unsigned long data) { - struct virtio_crypto *vcrypto = vq->vdev->priv; + struct data_queue *data_vq = (struct data_queue *)data; + struct virtqueue *vq = data_vq->vq; struct virtio_crypto_request *vc_req; - unsigned long flags; unsigned int len; - unsigned int qid = vq->index; - spin_lock_irqsave(&vcrypto->data_vq[qid].lock, flags); do { virtqueue_disable_cb(vq); while ((vc_req = virtqueue_get_buf(vq, &len)) != NULL) { - spin_unlock_irqrestore( - &vcrypto->data_vq[qid].lock, flags); if (vc_req->alg_cb) vc_req->alg_cb(vc_req, len); - spin_lock_irqsave( - &vcrypto->data_vq[qid].lock, flags); } } while (!virtqueue_enable_cb(vq)); - spin_unlock_irqrestore(&vcrypto->data_vq[qid].lock, flags); +} + +static void virtcrypto_dataq_callback(struct virtqueue *vq) +{ + struct virtio_crypto *vcrypto = vq->vdev->priv; + struct data_queue *dq = &vcrypto->data_vq[vq->index]; + + tasklet_schedule(&dq->done_task); } static int virtcrypto_find_vqs(struct virtio_crypto *vi) @@ -150,6 +151,8 @@ static int virtcrypto_find_vqs(struct virtio_crypto *vi) ret = -ENOMEM; goto err_engine; } + tasklet_init(&vi->data_vq[i].done_task, virtcrypto_done_task, + (unsigned long)&vi->data_vq[i]); } kfree(names); @@ -496,12 +499,15 @@ static void virtcrypto_free_unused_reqs(struct virtio_crypto *vcrypto) static void virtcrypto_remove(struct virtio_device *vdev) { struct virtio_crypto *vcrypto = vdev->priv; + int i; dev_info(&vdev->dev, "Start virtcrypto_remove.\n"); flush_work(&vcrypto->config_work); if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); + for (i = 0; i < vcrypto->max_data_queues; i++) + tasklet_kill(&vcrypto->data_vq[i].done_task); virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); virtcrypto_clear_crypto_engines(vcrypto); diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 003a44132418..5584af15300a 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -376,9 +376,9 @@ static bool __cxl_hdm_decode_init(struct cxl_dev_state *cxlds, allowed++; } - if (!allowed) { - cxl_set_mem_enable(cxlds, 0); - info->mem_enabled = 0; + if (!allowed && info->mem_enabled) { + dev_err(dev, "Range register decodes outside platform defined CXL ranges.\n"); + return -ENXIO; } /* diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index bd4142431980..1f1483a9e525 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -1403,7 +1403,7 @@ static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd, return -EINVAL; write_seqlock(&cxlsd->target_lock); - for (i = 0; i < cxlsd->nr_targets; i++) { + for (i = 0; i < cxlsd->cxld.interleave_ways; i++) { struct cxl_dport *dport = find_dport(port, target_map[i]); if (!dport) { diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index ebc1b028555c..5b7d848a6f01 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -331,7 +331,7 @@ static ssize_t interleave_ways_store(struct device *dev, return rc; /* - * Even for x3, x9, and x12 interleaves the region interleave must be a + * Even for x3, x6, and x12 interleaves the region interleave must be a * power of 2 multiple of the host bridge interleave. */ if (!is_power_of_2(val / cxld->interleave_ways) || @@ -450,7 +450,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size) struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent); struct cxl_region_params *p = &cxlr->params; struct resource *res; - u32 remainder = 0; + u64 remainder = 0; lockdep_assert_held_write(&cxl_region_rwsem); @@ -470,7 +470,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size) (cxlr->mode == CXL_DECODER_PMEM && uuid_is_null(&p->uuid))) return -ENXIO; - div_u64_rem(size, SZ_256M * p->interleave_ways, &remainder); + div64_u64_rem(size, (u64)SZ_256M * p->interleave_ways, &remainder); if (remainder) return -EINVAL; diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index fe6644f99887..344e276165e4 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -461,10 +461,14 @@ static void devfreq_monitor(struct work_struct *work) if (err) dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err); + if (devfreq->stop_polling) + goto out; + queue_delayed_work(devfreq_wq, &devfreq->work, msecs_to_jiffies(devfreq->profile->polling_ms)); - mutex_unlock(&devfreq->lock); +out: + mutex_unlock(&devfreq->lock); trace_devfreq_monitor(devfreq); } @@ -482,6 +486,10 @@ void devfreq_monitor_start(struct devfreq *devfreq) if (IS_SUPPORTED_FLAG(devfreq->governor->flags, IRQ_DRIVEN)) return; + mutex_lock(&devfreq->lock); + if (delayed_work_pending(&devfreq->work)) + goto out; + switch (devfreq->profile->timer) { case DEVFREQ_TIMER_DEFERRABLE: INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor); @@ -490,12 +498,16 @@ void devfreq_monitor_start(struct devfreq *devfreq) INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor); break; default: - return; + goto out; } if (devfreq->profile->polling_ms) queue_delayed_work(devfreq_wq, &devfreq->work, msecs_to_jiffies(devfreq->profile->polling_ms)); + +out: + devfreq->stop_polling = false; + mutex_unlock(&devfreq->lock); } EXPORT_SYMBOL(devfreq_monitor_start); @@ -512,6 +524,14 @@ void devfreq_monitor_stop(struct devfreq *devfreq) if (IS_SUPPORTED_FLAG(devfreq->governor->flags, IRQ_DRIVEN)) return; + mutex_lock(&devfreq->lock); + if (devfreq->stop_polling) { + mutex_unlock(&devfreq->lock); + return; + } + + devfreq->stop_polling = true; + mutex_unlock(&devfreq->lock); cancel_delayed_work_sync(&devfreq->work); } EXPORT_SYMBOL(devfreq_monitor_stop); @@ -1687,7 +1707,7 @@ static ssize_t trans_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { struct devfreq *df = to_devfreq(dev); - ssize_t len; + ssize_t len = 0; int i, j; unsigned int max_state; @@ -1696,7 +1716,7 @@ static ssize_t trans_stat_show(struct device *dev, max_state = df->max_state; if (max_state == 0) - return sprintf(buf, "Not Supported.\n"); + return scnprintf(buf, PAGE_SIZE, "Not Supported.\n"); mutex_lock(&df->lock); if (!df->stop_polling && @@ -1706,31 +1726,52 @@ static ssize_t trans_stat_show(struct device *dev, } mutex_unlock(&df->lock); - len = sprintf(buf, " From : To\n"); - len += sprintf(buf + len, " :"); - for (i = 0; i < max_state; i++) - len += sprintf(buf + len, "%10lu", - df->freq_table[i]); + len += scnprintf(buf + len, PAGE_SIZE - len, " From : To\n"); + len += scnprintf(buf + len, PAGE_SIZE - len, " :"); + for (i = 0; i < max_state; i++) { + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10lu", + df->freq_table[i]); + } + if (len >= PAGE_SIZE - 1) + return PAGE_SIZE - 1; - len += sprintf(buf + len, " time(ms)\n"); + len += scnprintf(buf + len, PAGE_SIZE - len, " time(ms)\n"); for (i = 0; i < max_state; i++) { + if (len >= PAGE_SIZE - 1) + break; if (df->freq_table[i] == df->previous_freq) - len += sprintf(buf + len, "*"); + len += scnprintf(buf + len, PAGE_SIZE - len, "*"); else - len += sprintf(buf + len, " "); + len += scnprintf(buf + len, PAGE_SIZE - len, " "); + if (len >= PAGE_SIZE - 1) + break; + + len += scnprintf(buf + len, PAGE_SIZE - len, "%10lu:", + df->freq_table[i]); + for (j = 0; j < max_state; j++) { + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10u", + df->stats.trans_table[(i * max_state) + j]); + } + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10llu\n", (u64) + jiffies64_to_msecs(df->stats.time_in_state[i])); + } - len += sprintf(buf + len, "%10lu:", df->freq_table[i]); - for (j = 0; j < max_state; j++) - len += sprintf(buf + len, "%10u", - df->stats.trans_table[(i * max_state) + j]); + if (len < PAGE_SIZE - 1) + len += scnprintf(buf + len, PAGE_SIZE - len, "Total transition : %u\n", + df->stats.total_trans); - len += sprintf(buf + len, "%10llu\n", (u64) - jiffies64_to_msecs(df->stats.time_in_state[i])); + if (len >= PAGE_SIZE - 1) { + pr_warn_once("devfreq transition table exceeds PAGE_SIZE. Disabling\n"); + return -EFBIG; } - len += sprintf(buf + len, "Total transition : %u\n", - df->stats.total_trans); return len; } diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index 4cf8da77bdd9..cac4532fe23a 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -56,6 +56,8 @@ #define REG_BUS_WIDTH(ch) (0x8040 + (ch) * 0x200) +#define BUS_WIDTH_WORD_SIZE GENMASK(3, 0) +#define BUS_WIDTH_FRAME_SIZE GENMASK(7, 4) #define BUS_WIDTH_8BIT 0x00 #define BUS_WIDTH_16BIT 0x01 #define BUS_WIDTH_32BIT 0x02 @@ -739,7 +741,8 @@ static int admac_device_config(struct dma_chan *chan, struct admac_data *ad = adchan->host; bool is_tx = admac_chan_direction(adchan->no) == DMA_MEM_TO_DEV; int wordsize = 0; - u32 bus_width = 0; + u32 bus_width = readl_relaxed(ad->base + REG_BUS_WIDTH(adchan->no)) & + ~(BUS_WIDTH_WORD_SIZE | BUS_WIDTH_FRAME_SIZE); switch (is_tx ? config->dst_addr_width : config->src_addr_width) { case DMA_SLAVE_BUSWIDTH_1_BYTE: diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 8a6e6b60d66f..892e8389232e 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1103,6 +1103,9 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_register); static void __dma_async_device_channel_unregister(struct dma_device *device, struct dma_chan *chan) { + if (chan->local == NULL) + return; + WARN_ONCE(!device->device_release && chan->client_count, "%s called while %d clients hold a reference\n", __func__, chan->client_count); diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c index 8dd40d00a672..6b829d347417 100644 --- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c +++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c @@ -38,15 +38,17 @@ static int dpaa2_qdma_alloc_chan_resources(struct dma_chan *chan) if (!dpaa2_chan->fd_pool) goto err; - dpaa2_chan->fl_pool = dma_pool_create("fl_pool", dev, - sizeof(struct dpaa2_fl_entry), - sizeof(struct dpaa2_fl_entry), 0); + dpaa2_chan->fl_pool = + dma_pool_create("fl_pool", dev, + sizeof(struct dpaa2_fl_entry) * 3, + sizeof(struct dpaa2_fl_entry), 0); + if (!dpaa2_chan->fl_pool) goto err_fd; dpaa2_chan->sdd_pool = dma_pool_create("sdd_pool", dev, - sizeof(struct dpaa2_qdma_sd_d), + sizeof(struct dpaa2_qdma_sd_d) * 2, sizeof(struct dpaa2_qdma_sd_d), 0); if (!dpaa2_chan->sdd_pool) goto err_fl; diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c index 045ead46ec8f..f383f219ed00 100644 --- a/drivers/dma/fsl-qdma.c +++ b/drivers/dma/fsl-qdma.c @@ -514,11 +514,11 @@ static struct fsl_qdma_queue queue_temp = queue_head + i + (j * queue_num); queue_temp->cq = - dma_alloc_coherent(&pdev->dev, - sizeof(struct fsl_qdma_format) * - queue_size[i], - &queue_temp->bus_addr, - GFP_KERNEL); + dmam_alloc_coherent(&pdev->dev, + sizeof(struct fsl_qdma_format) * + queue_size[i], + &queue_temp->bus_addr, + GFP_KERNEL); if (!queue_temp->cq) return NULL; queue_temp->block_base = fsl_qdma->block_base + @@ -563,11 +563,11 @@ static struct fsl_qdma_queue /* * Buffer for queue command */ - status_head->cq = dma_alloc_coherent(&pdev->dev, - sizeof(struct fsl_qdma_format) * - status_size, - &status_head->bus_addr, - GFP_KERNEL); + status_head->cq = dmam_alloc_coherent(&pdev->dev, + sizeof(struct fsl_qdma_format) * + status_size, + &status_head->bus_addr, + GFP_KERNEL); if (!status_head->cq) { devm_kfree(&pdev->dev, status_head); return NULL; @@ -805,7 +805,7 @@ fsl_qdma_irq_init(struct platform_device *pdev, int i; int cpu; int ret; - char irq_name[20]; + char irq_name[32]; fsl_qdma->error_irq = platform_get_irq_byname(pdev, "qdma-error"); @@ -1272,8 +1272,6 @@ static void fsl_qdma_cleanup_vchan(struct dma_device *dmadev) static int fsl_qdma_remove(struct platform_device *pdev) { - int i; - struct fsl_qdma_queue *status; struct device_node *np = pdev->dev.of_node; struct fsl_qdma_engine *fsl_qdma = platform_get_drvdata(pdev); @@ -1282,11 +1280,6 @@ static int fsl_qdma_remove(struct platform_device *pdev) of_dma_controller_free(np); dma_async_device_unregister(&fsl_qdma->dma_dev); - for (i = 0; i < fsl_qdma->block_number; i++) { - status = fsl_qdma->status[i]; - dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_format) * - status->n_cq, status->cq, status->bus_addr); - } return 0; } diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index e2070df6cad2..0b846c605d4b 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -584,11 +584,11 @@ desc_get_errstat(struct ioatdma_chan *ioat_chan, struct ioat_ring_ent *desc) } /** - * __cleanup - reclaim used descriptors + * __ioat_cleanup - reclaim used descriptors * @ioat_chan: channel (ring) to clean * @phys_complete: zeroed (or not) completion address (from status) */ -static void __cleanup(struct ioatdma_chan *ioat_chan, dma_addr_t phys_complete) +static void __ioat_cleanup(struct ioatdma_chan *ioat_chan, dma_addr_t phys_complete) { struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma; struct ioat_ring_ent *desc; @@ -675,7 +675,7 @@ static void ioat_cleanup(struct ioatdma_chan *ioat_chan) spin_lock_bh(&ioat_chan->cleanup_lock); if (ioat_cleanup_preamble(ioat_chan, &phys_complete)) - __cleanup(ioat_chan, phys_complete); + __ioat_cleanup(ioat_chan, phys_complete); if (is_ioat_halted(*ioat_chan->completion)) { u32 chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET); @@ -712,7 +712,7 @@ static void ioat_restart_channel(struct ioatdma_chan *ioat_chan) ioat_quiesce(ioat_chan, 0); if (ioat_cleanup_preamble(ioat_chan, &phys_complete)) - __cleanup(ioat_chan, phys_complete); + __ioat_cleanup(ioat_chan, phys_complete); __ioat_restart_chan(ioat_chan); } @@ -786,7 +786,7 @@ static void ioat_eh(struct ioatdma_chan *ioat_chan) /* cleanup so tail points to descriptor that caused the error */ if (ioat_cleanup_preamble(ioat_chan, &phys_complete)) - __cleanup(ioat_chan, phys_complete); + __ioat_cleanup(ioat_chan, phys_complete); chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET); pci_read_config_dword(pdev, IOAT_PCI_CHANERR_INT_OFFSET, &chanerr_int); @@ -943,7 +943,7 @@ void ioat_timer_event(struct timer_list *t) /* timer restarted in ioat_cleanup_preamble * and IOAT_COMPLETION_ACK cleared */ - __cleanup(ioat_chan, phys_complete); + __ioat_cleanup(ioat_chan, phys_complete); goto unlock_out; } diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h index 9c121a4b33ad..f97d80343aea 100644 --- a/drivers/dma/sh/shdma.h +++ b/drivers/dma/sh/shdma.h @@ -25,7 +25,7 @@ struct sh_dmae_chan { const struct sh_dmae_slave_config *config; /* Slave DMA configuration */ int xmit_shift; /* log_2(bytes_per_xfer) */ void __iomem *base; - char dev_id[16]; /* unique name per DMAC of channel */ + char dev_id[32]; /* unique name per DMAC of channel */ int pm_error; dma_addr_t slave_addr; }; diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index 7ec6e5d728b0..9212ac9f978f 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -2413,6 +2413,11 @@ static int edma_probe(struct platform_device *pdev) if (irq > 0) { irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccint", dev_name(dev)); + if (!irq_name) { + ret = -ENOMEM; + goto err_disable_pm; + } + ret = devm_request_irq(dev, irq, dma_irq_handler, 0, irq_name, ecc); if (ret) { @@ -2429,6 +2434,11 @@ static int edma_probe(struct platform_device *pdev) if (irq > 0) { irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccerrint", dev_name(dev)); + if (!irq_name) { + ret = -ENOMEM; + goto err_disable_pm; + } + ret = devm_request_irq(dev, irq, dma_ccerr_handler, 0, irq_name, ecc); if (ret) { diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index f13674081cb6..4dca21b39bf7 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -1133,7 +1133,7 @@ static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id) decode_register(other, OCX_OTHER_SIZE, ocx_com_errors, ctx->reg_com_int); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); for (lane = 0; lane < OCX_RX_LANES; lane++) if (ctx->reg_com_int & BIT(lane)) { @@ -1142,12 +1142,12 @@ static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id) lane, ctx->reg_lane_int[lane], lane, ctx->reg_lane_stat11[lane]); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); decode_register(other, OCX_OTHER_SIZE, ocx_lane_errors, ctx->reg_lane_int[lane]); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); } if (ctx->reg_com_int & OCX_COM_INT_CE) @@ -1217,7 +1217,7 @@ static irqreturn_t thunderx_ocx_lnk_threaded_isr(int irq, void *irq_id) decode_register(other, OCX_OTHER_SIZE, ocx_com_link_errors, ctx->reg_com_link_int); - strncat(msg, other, OCX_MESSAGE_SIZE); + strlcat(msg, other, OCX_MESSAGE_SIZE); if (ctx->reg_com_link_int & OCX_COM_LINK_INT_UE) edac_device_handle_ue(ocx->edac_dev, 0, 0, msg); @@ -1896,7 +1896,7 @@ static irqreturn_t thunderx_l2c_threaded_isr(int irq, void *irq_id) decode_register(other, L2C_OTHER_SIZE, l2_errors, ctx->reg_int); - strncat(msg, other, L2C_MESSAGE_SIZE); + strlcat(msg, other, L2C_MESSAGE_SIZE); if (ctx->reg_int & mask_ue) edac_device_handle_ue(l2c->edac_dev, 0, 0, msg); diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 6ac5ff20a2fe..8aaa7fcb2630 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -429,7 +429,23 @@ static void bm_work(struct work_struct *work) */ card->bm_generation = generation; - if (root_device == NULL) { + if (card->gap_count == 0) { + /* + * If self IDs have inconsistent gap counts, do a + * bus reset ASAP. The config rom read might never + * complete, so don't wait for it. However, still + * send a PHY configuration packet prior to the + * bus reset. The PHY configuration packet might + * fail, but 1394-2008 8.4.5.2 explicitly permits + * it in this case, so it should be safe to try. + */ + new_root_id = local_id; + /* + * We must always send a bus reset if the gap count + * is inconsistent, so bypass the 5-reset limit. + */ + card->bm_retries = 0; + } else if (root_device == NULL) { /* * Either link_on is false, or we failed to read the * config rom. In either case, pick another root. diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 74bab06283b7..1879ec27c023 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -100,10 +100,9 @@ static int textual_leaf_to_string(const u32 *block, char *buf, size_t size) * @buf: where to put the string * @size: size of @buf, in bytes * - * The string is taken from a minimal ASCII text descriptor leaf after - * the immediate entry with @key. The string is zero-terminated. - * An overlong string is silently truncated such that it and the - * zero byte fit into @size. + * The string is taken from a minimal ASCII text descriptor leaf just after the entry with the + * @key. The string is zero-terminated. An overlong string is silently truncated such that it + * and the zero byte fit into @size. * * Returns strlen(buf) or a negative error code. */ diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 17c9d825188b..667ff40f3935 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -279,6 +279,51 @@ static char ohci_driver_name[] = KBUILD_MODNAME; #define QUIRK_TI_SLLZ059 0x20 #define QUIRK_IR_WAKE 0x40 +// On PCI Express Root Complex in any type of AMD Ryzen machine, VIA VT6306/6307/6308 with Asmedia +// ASM1083/1085 brings an inconvenience that the read accesses to 'Isochronous Cycle Timer' register +// (at offset 0xf0 in PCI I/O space) often causes unexpected system reboot. The mechanism is not +// clear, since the read access to the other registers is enough safe; e.g. 'Node ID' register, +// while it is probable due to detection of any type of PCIe error. +#define QUIRK_REBOOT_BY_CYCLE_TIMER_READ 0x80000000 + +#if IS_ENABLED(CONFIG_X86) + +static bool has_reboot_by_cycle_timer_read_quirk(const struct fw_ohci *ohci) +{ + return !!(ohci->quirks & QUIRK_REBOOT_BY_CYCLE_TIMER_READ); +} + +#define PCI_DEVICE_ID_ASMEDIA_ASM108X 0x1080 + +static bool detect_vt630x_with_asm1083_on_amd_ryzen_machine(const struct pci_dev *pdev) +{ + const struct pci_dev *pcie_to_pci_bridge; + + // Detect any type of AMD Ryzen machine. + if (!static_cpu_has(X86_FEATURE_ZEN)) + return false; + + // Detect VIA VT6306/6307/6308. + if (pdev->vendor != PCI_VENDOR_ID_VIA) + return false; + if (pdev->device != PCI_DEVICE_ID_VIA_VT630X) + return false; + + // Detect Asmedia ASM1083/1085. + pcie_to_pci_bridge = pdev->bus->self; + if (pcie_to_pci_bridge->vendor != PCI_VENDOR_ID_ASMEDIA) + return false; + if (pcie_to_pci_bridge->device != PCI_DEVICE_ID_ASMEDIA_ASM108X) + return false; + + return true; +} + +#else +#define has_reboot_by_cycle_timer_read_quirk(ohci) false +#define detect_vt630x_with_asm1083_on_amd_ryzen_machine(pdev) false +#endif + /* In case of multiple matches in ohci_quirks[], only the first one is used. */ static const struct { unsigned short vendor, device, revision, flags; @@ -1713,6 +1758,9 @@ static u32 get_cycle_time(struct fw_ohci *ohci) s32 diff01, diff12; int i; + if (has_reboot_by_cycle_timer_read_quirk(ohci)) + return 0; + c2 = reg_read(ohci, OHCI1394_IsochronousCycleTimer); if (ohci->quirks & QUIRK_CYCLE_TIMER) { @@ -3615,6 +3663,9 @@ static int pci_probe(struct pci_dev *dev, if (param_quirks) ohci->quirks = param_quirks; + if (detect_vt630x_with_asm1083_on_amd_ryzen_machine(dev)) + ohci->quirks |= QUIRK_REBOOT_BY_CYCLE_TIMER_READ; + /* * Because dma_alloc_coherent() allocates at least one page, * we save space by using a common buffer for the AR request/ diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index a1c0154c31c6..4ac72754c255 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -244,6 +244,7 @@ void shmem_fetch_notification(struct scmi_shared_mem __iomem *shmem, void shmem_clear_channel(struct scmi_shared_mem __iomem *shmem); bool shmem_poll_done(struct scmi_shared_mem __iomem *shmem, struct scmi_xfer *xfer); +bool shmem_channel_free(struct scmi_shared_mem __iomem *shmem); /* declarations for message passing transports */ struct scmi_msg_payld; diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c index 25d31dfdad15..81c902672a30 100644 --- a/drivers/firmware/arm_scmi/mailbox.c +++ b/drivers/firmware/arm_scmi/mailbox.c @@ -43,6 +43,20 @@ static void rx_callback(struct mbox_client *cl, void *m) { struct scmi_mailbox *smbox = client_to_scmi_mailbox(cl); + /* + * An A2P IRQ is NOT valid when received while the platform still has + * the ownership of the channel, because the platform at first releases + * the SMT channel and then sends the completion interrupt. + * + * This addresses a possible race condition in which a spurious IRQ from + * a previous timed-out reply which arrived late could be wrongly + * associated with the next pending transaction. + */ + if (cl->knows_txdone && !shmem_channel_free(smbox->shmem)) { + dev_warn(smbox->cinfo->dev, "Ignoring spurious A2P IRQ !\n"); + return; + } + scmi_rx_callback(smbox->cinfo, shmem_read_header(smbox->shmem), NULL); } diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 431bda9165c3..2775bcafe40f 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -131,7 +131,7 @@ struct perf_dom_info { u32 opp_count; u32 sustained_freq_khz; u32 sustained_perf_level; - u32 mult_factor; + unsigned long mult_factor; char name[SCMI_MAX_STR_SIZE]; struct scmi_opp opp[MAX_OPPS]; struct scmi_fc_info *fc_info; @@ -223,8 +223,8 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph, dom_info->mult_factor = 1000; else dom_info->mult_factor = - (dom_info->sustained_freq_khz * 1000) / - dom_info->sustained_perf_level; + (dom_info->sustained_freq_khz * 1000UL) + / dom_info->sustained_perf_level; strscpy(dom_info->name, attr->name, SCMI_SHORT_NAME_MAX_SIZE); } diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c index 87b4f4d35f06..517d52fb3bcb 100644 --- a/drivers/firmware/arm_scmi/shmem.c +++ b/drivers/firmware/arm_scmi/shmem.c @@ -122,3 +122,9 @@ bool shmem_poll_done(struct scmi_shared_mem __iomem *shmem, (SCMI_SHMEM_CHAN_STAT_CHANNEL_ERROR | SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE); } + +bool shmem_channel_free(struct scmi_shared_mem __iomem *shmem) +{ + return (ioread32(&shmem->channel_status) & + SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE); +} diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 7c48c380d722..1995f0a2e0fc 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -107,7 +107,7 @@ static int __init arm_enable_runtime_services(void) efi_memory_desc_t *md; for_each_efi_memory_desc(md) { - int md_size = md->num_pages << EFI_PAGE_SHIFT; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; struct resource *res; if (!(md->attribute & EFI_MEMORY_SP)) diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index 2fd770b499a3..ff9791ce2e15 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -117,15 +117,6 @@ static __init int is_usable_memory(efi_memory_desc_t *md) case EFI_CONVENTIONAL_MEMORY: case EFI_PERSISTENT_MEMORY: /* - * Special purpose memory is 'soft reserved', which means it - * is set aside initially, but can be hotplugged back in or - * be assigned to the dax driver after boot. - */ - if (efi_soft_reserve_enabled() && - (md->attribute & EFI_MEMORY_SP)) - return false; - - /* * According to the spec, these regions are no longer reserved * after calling ExitBootServices(). However, we can only use * them as System RAM if they can be mapped writeback cacheable. @@ -169,6 +160,16 @@ static __init void reserve_regions(void) size = npages << PAGE_SHIFT; if (is_memory(md)) { + /* + * Special purpose memory is 'soft reserved', which + * means it is set aside initially. Don't add a memblock + * for it now so that it can be hotplugged back in or + * be assigned to the dax driver after boot. + */ + if (efi_soft_reserve_enabled() && + (md->attribute & EFI_MEMORY_SP)) + continue; + early_init_dt_add_memory_arch(paddr, size); if (!is_usable_memory(md)) diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index ef5045a53ce0..b6e1dcb98a64 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -25,7 +25,7 @@ cflags-$(CONFIG_ARM) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \ -fno-builtin -fpic \ $(call cc-option,-mno-single-pic-base) cflags-$(CONFIG_RISCV) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \ - -fpic + -fpic -mno-relax cflags-$(CONFIG_LOONGARCH) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \ -fpie diff --git a/drivers/firmware/efi/riscv-runtime.c b/drivers/firmware/efi/riscv-runtime.c index d0daacd2c903..6b142aa35389 100644 --- a/drivers/firmware/efi/riscv-runtime.c +++ b/drivers/firmware/efi/riscv-runtime.c @@ -85,7 +85,7 @@ static int __init riscv_enable_runtime_services(void) efi_memory_desc_t *md; for_each_efi_memory_desc(md) { - int md_size = md->num_pages << EFI_PAGE_SHIFT; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; struct resource *res; if (!(md->attribute & EFI_MEMORY_SP)) diff --git a/drivers/firmware/meson/meson_sm.c b/drivers/firmware/meson/meson_sm.c index d081a6312627..bf19dd66c213 100644 --- a/drivers/firmware/meson/meson_sm.c +++ b/drivers/firmware/meson/meson_sm.c @@ -313,11 +313,14 @@ static int __init meson_sm_probe(struct platform_device *pdev) platform_set_drvdata(pdev, fw); - pr_info("secure-monitor enabled\n"); + if (devm_of_platform_populate(dev)) + goto out_in_base; if (sysfs_create_group(&pdev->dev.kobj, &meson_sm_sysfs_attr_group)) goto out_in_base; + pr_info("secure-monitor enabled\n"); + return 0; out_in_base: diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c index 8e03488ccc5f..ae1ef599df71 100644 --- a/drivers/firmware/ti_sci.c +++ b/drivers/firmware/ti_sci.c @@ -178,7 +178,7 @@ static int ti_sci_debugfs_create(struct platform_device *pdev, { struct device *dev = &pdev->dev; struct resource *res; - char debug_name[50] = "ti_sci_debug@"; + char debug_name[50]; /* Debug region is optional */ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, @@ -195,10 +195,10 @@ static int ti_sci_debugfs_create(struct platform_device *pdev, /* Setup NULL termination */ info->debug_buffer[info->debug_region_size] = 0; - info->d = debugfs_create_file(strncat(debug_name, dev_name(dev), - sizeof(debug_name) - - sizeof("ti_sci_debug@")), - 0444, NULL, info, &ti_sci_debug_fops); + snprintf(debug_name, sizeof(debug_name), "ti_sci_debug@%s", + dev_name(dev)); + info->d = debugfs_create_file(debug_name, 0444, NULL, info, + &ti_sci_debug_fops); if (IS_ERR(info->d)) return PTR_ERR(info->d); diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index c22fcaa44a61..6b7d47a52b10 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -283,13 +283,15 @@ static void dwapb_irq_enable(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct dwapb_gpio *gpio = to_dwapb_gpio(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); unsigned long flags; u32 val; raw_spin_lock_irqsave(&gc->bgpio_lock, flags); - val = dwapb_read(gpio, GPIO_INTEN); - val |= BIT(irqd_to_hwirq(d)); + val = dwapb_read(gpio, GPIO_INTEN) | BIT(hwirq); dwapb_write(gpio, GPIO_INTEN, val); + val = dwapb_read(gpio, GPIO_INTMASK) & ~BIT(hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags); } @@ -297,12 +299,14 @@ static void dwapb_irq_disable(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct dwapb_gpio *gpio = to_dwapb_gpio(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); unsigned long flags; u32 val; raw_spin_lock_irqsave(&gc->bgpio_lock, flags); - val = dwapb_read(gpio, GPIO_INTEN); - val &= ~BIT(irqd_to_hwirq(d)); + val = dwapb_read(gpio, GPIO_INTMASK) | BIT(hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + val = dwapb_read(gpio, GPIO_INTEN) & ~BIT(hwirq); dwapb_write(gpio, GPIO_INTEN, val); raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags); } diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index 8d722e026e9c..c2857ed0c78a 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -318,20 +318,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) switch (flow_type) { case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 1); + sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 0); + sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1); break; case IRQ_TYPE_EDGE_RISING: case IRQ_TYPE_EDGE_FALLING: case IRQ_TYPE_EDGE_BOTH: state = sprd_eic_get(chip, offset); - if (state) + if (state) { sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 0); - else + sprd_eic_update(chip, offset, + SPRD_EIC_DBNC_IC, 1); + } else { sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 1); + sprd_eic_update(chip, offset, + SPRD_EIC_DBNC_IC, 1); + } break; default: return -ENOTSUPP; @@ -343,20 +350,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) switch (flow_type) { case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1); break; case IRQ_TYPE_EDGE_RISING: case IRQ_TYPE_EDGE_FALLING: case IRQ_TYPE_EDGE_BOTH: state = sprd_eic_get(chip, offset); - if (state) + if (state) { sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 0); - else + sprd_eic_update(chip, offset, + SPRD_EIC_LATCH_INTCLR, 1); + } else { sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 1); + sprd_eic_update(chip, offset, + SPRD_EIC_LATCH_INTCLR, 1); + } break; default: return -ENOTSUPP; @@ -370,29 +384,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_FALLING: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; default: @@ -405,29 +424,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_FALLING: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; default: diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 787d47e667ad..33d73687e463 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1626,6 +1626,20 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_wake = "ELAN0415:00@9", }, }, + { + /* + * Spurious wakeups from TP_ATTN# pin + * Found in BIOS 0.35 + * https://gitlab.freedesktop.org/drm/amd/-/issues/3073 + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GPD"), + DMI_MATCH(DMI_PRODUCT_NAME, "G1619-04"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_wake = "PNP0C50:00@8", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 6ab1cf489d03..e40c93f0960b 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -2444,10 +2444,7 @@ static int lineinfo_unwatch(struct gpio_chardev_data *cdev, void __user *ip) return 0; } -/* - * gpio_ioctl() - ioctl handler for the GPIO chardev - */ -static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long gpio_ioctl_unlocked(struct file *file, unsigned int cmd, unsigned long arg) { struct gpio_chardev_data *cdev = file->private_data; struct gpio_device *gdev = cdev->gdev; @@ -2484,6 +2481,17 @@ static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } } +/* + * gpio_ioctl() - ioctl handler for the GPIO chardev + */ +static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct gpio_chardev_data *cdev = file->private_data; + + return call_ioctl_locked(file, cmd, arg, cdev->gdev, + gpio_ioctl_unlocked); +} + #ifdef CONFIG_COMPAT static long gpio_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c index 2b97b8a96fb4..fa6193535d48 100644 --- a/drivers/gpu/drm/amd/amdgpu/aldebaran.c +++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.c @@ -333,6 +333,7 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl, { struct list_head *reset_device_list = reset_context->reset_device_list; struct amdgpu_device *tmp_adev = NULL; + struct amdgpu_ras *con; int r; if (reset_device_list == NULL) @@ -358,7 +359,30 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl, */ amdgpu_register_gpu_instance(tmp_adev); - /* Resume RAS */ + /* Resume RAS, ecc_irq */ + con = amdgpu_ras_get_context(tmp_adev); + if (!amdgpu_sriov_vf(tmp_adev) && con) { + if (tmp_adev->sdma.ras && + tmp_adev->sdma.ras->ras_block.ras_late_init) { + r = tmp_adev->sdma.ras->ras_block.ras_late_init(tmp_adev, + &tmp_adev->sdma.ras->ras_block.ras_comm); + if (r) { + dev_err(tmp_adev->dev, "SDMA failed to execute ras_late_init! ret:%d\n", r); + goto end; + } + } + + if (tmp_adev->gfx.ras && + tmp_adev->gfx.ras->ras_block.ras_late_init) { + r = tmp_adev->gfx.ras->ras_block.ras_late_init(tmp_adev, + &tmp_adev->gfx.ras->ras_block.ras_comm); + if (r) { + dev_err(tmp_adev->dev, "GFX failed to execute ras_late_init! ret:%d\n", r); + goto end; + } + } + } + amdgpu_ras_resume(tmp_adev); /* Update PSP FW topology after reset */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index c46c6fbd235e..e636c7850f77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -999,6 +999,8 @@ struct amdgpu_device { bool in_s3; bool in_s4; bool in_s0ix; + /* indicate amdgpu suspension status */ + bool suspend_complete; enum pp_mp1_state mp1_state; struct amdgpu_doorbell_index doorbell_index; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c index 469785d33791..1ef758ac5076 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c @@ -90,7 +90,7 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f) return NULL; fence = container_of(f, struct amdgpu_amdkfd_fence, base); - if (fence && f->ops == &amdkfd_fence_ops) + if (f->ops == &amdkfd_fence_ops) return fence; return NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index fd796574f87a..06ab6066da61 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -479,6 +479,9 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf, if (size & 0x3 || *pos & 0x3) return -EINVAL; + if (!adev->didt_rreg) + return -EOPNOTSUPP; + r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); @@ -535,6 +538,9 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user if (size & 0x3 || *pos & 0x3) return -EINVAL; + if (!adev->didt_wreg) + return -EOPNOTSUPP; + r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); @@ -590,7 +596,7 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf, int r; if (!adev->smc_rreg) - return -EPERM; + return -EOPNOTSUPP; if (size & 0x3 || *pos & 0x3) return -EINVAL; @@ -649,7 +655,7 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user * int r; if (!adev->smc_wreg) - return -EPERM; + return -EOPNOTSUPP; if (size & 0x3 || *pos & 0x3) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 8a1b84aaaf71..6a4749c0c5a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1310,6 +1310,7 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev) return true; fw_ver = *((uint32_t *)adev->pm.fw->data + 69); + release_firmware(adev->pm.fw); if (fw_ver < 0x00160e00) return true; } @@ -1976,15 +1977,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) adev->firmware.gpu_info_fw = NULL; - if (adev->mman.discovery_bin) { - /* - * FIXME: The bounding box is still needed by Navi12, so - * temporarily read it from gpu_info firmware. Should be dropped - * when DAL no longer needs it. - */ - if (adev->asic_type != CHIP_NAVI12) - return 0; - } + if (adev->mman.discovery_bin) + return 0; switch (adev->asic_type) { default: @@ -4209,7 +4203,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true); cancel_delayed_work_sync(&adev->delayed_init_work); - flush_delayed_work(&adev->gfx.gfx_off_delay_work); amdgpu_ras_suspend(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b9983ca99eb7..f24c3a20e901 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2414,6 +2414,7 @@ static int amdgpu_pmops_suspend(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); + adev->suspend_complete = false; if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; else if (amdgpu_acpi_is_s3_active(adev)) @@ -2428,6 +2429,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); + adev->suspend_complete = true; if (amdgpu_acpi_should_gpu_reset(adev)) return amdgpu_asic_reset(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 23f0067f92e4..b803e785d3af 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -585,8 +585,15 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable) if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state) { - schedule_delayed_work(&adev->gfx.gfx_off_delay_work, + /* If going to s2idle, no need to wait */ + if (adev->in_s0ix) { + if (!amdgpu_dpm_set_powergating_by_smu(adev, + AMD_IP_BLOCK_TYPE_GFX, true)) + adev->gfx.gfx_off_state = true; + } else { + schedule_delayed_work(&adev->gfx.gfx_off_delay_work, delay); + } } } else { if (adev->gfx.gfx_off_req_count == 0) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 2bc791ed8830..ea0fb079f942 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -808,19 +808,26 @@ int amdgpu_gmc_vram_checking(struct amdgpu_device *adev) * seconds, so here, we just pick up three parts for emulation. */ ret = memcmp(vram_ptr, cptr, 10); - if (ret) - return ret; + if (ret) { + ret = -EIO; + goto release_buffer; + } ret = memcmp(vram_ptr + (size / 2), cptr, 10); - if (ret) - return ret; + if (ret) { + ret = -EIO; + goto release_buffer; + } ret = memcmp(vram_ptr + size - 10, cptr, 10); - if (ret) - return ret; + if (ret) { + ret = -EIO; + goto release_buffer; + } +release_buffer: amdgpu_bo_free_kernel(&vram_bo, &vram_gpu, &vram_ptr); - return 0; + return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 0ee7c935fba1..cde2fd2f7117 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1222,19 +1222,15 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, * amdgpu_bo_move_notify - notification about a memory move * @bo: pointer to a buffer object * @evict: if this move is evicting the buffer from the graphics address space - * @new_mem: new information of the bufer object * * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs * bookkeeping. * TTM driver callback which is called when ttm moves a buffer. */ -void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, - bool evict, - struct ttm_resource *new_mem) +void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct amdgpu_bo *abo; - struct ttm_resource *old_mem = bo->resource; if (!amdgpu_bo_is_amdgpu_bo(bo)) return; @@ -1251,13 +1247,6 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, /* remember the eviction */ if (evict) atomic64_inc(&adev->num_evictions); - - /* update statistics */ - if (!new_mem) - return; - - /* move_notify is called before move happens */ - trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type); } void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 6dcd7bab42fb..2ada421e79e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -312,9 +312,7 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, size_t buffer_size, uint32_t *metadata_size, uint64_t *flags); -void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, - bool evict, - struct ttm_resource *new_mem); +void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict); void amdgpu_bo_release_notify(struct ttm_buffer_object *bo); vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo); void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 090e66a1b284..54bdbd83a8cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -191,7 +191,8 @@ static bool amdgpu_sync_test_fence(struct amdgpu_device *adev, /* Never sync to VM updates either. */ if (fence_owner == AMDGPU_FENCE_OWNER_VM && - owner != AMDGPU_FENCE_OWNER_UNDEFINED) + owner != AMDGPU_FENCE_OWNER_UNDEFINED && + owner != AMDGPU_FENCE_OWNER_KFD) return false; /* Ignore fences depending on the sync mode */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 10469f20a10c..158b791883f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -555,10 +555,11 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; } + trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type); out: /* update statistics */ atomic64_add(bo->base.size, &adev->num_bytes_moved); - amdgpu_bo_move_notify(bo, evict, new_mem); + amdgpu_bo_move_notify(bo, evict); return 0; } @@ -1503,7 +1504,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo, static void amdgpu_bo_delete_mem_notify(struct ttm_buffer_object *bo) { - amdgpu_bo_move_notify(bo, false, NULL); + amdgpu_bo_move_notify(bo, false); } static struct ttm_device_funcs amdgpu_bo_driver = { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index 6e7058a2d1c8..779707f19c88 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -1110,9 +1110,13 @@ int amdgpu_ucode_request(struct amdgpu_device *adev, const struct firmware **fw, if (err) return -ENODEV; + err = amdgpu_ucode_validate(*fw); - if (err) + if (err) { dev_dbg(adev->dev, "\"%s\" failed to validate\n", fw_name); + release_firmware(*fw); + *fw = NULL; + } return err; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 84ca601f7d5f..195b29892354 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3064,6 +3064,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev) gfx_v9_0_cp_gfx_enable(adev, true); + /* Now only limit the quirk on the APU gfx9 series and already + * confirmed that the APU gfx10/gfx11 needn't such update. + */ + if (adev->flags & AMD_IS_APU && + adev->in_s3 && !adev->suspend_complete) { + DRM_INFO(" Will skip the CSB packet resubmit\n"); + return 0; + } r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3); if (r) { DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index d96ee48e1706..35921b41fc27 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1144,6 +1144,10 @@ static int gmc_v10_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); + if (adev->gmc.ecc_irq.funcs && + amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC)) + amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index 7124347d2b6c..310a5607d83b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -951,6 +951,11 @@ static int gmc_v11_0_hw_fini(void *handle) } amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); + + if (adev->gmc.ecc_irq.funcs && + amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC)) + amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); + gmc_v11_0_gart_disable(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index ec291d28edff..345f0c9f551c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -921,8 +921,8 @@ static int gmc_v6_0_hw_init(void *handle) if (amdgpu_emu_mode == 1) return amdgpu_gmc_vram_checking(adev); - else - return r; + + return 0; } static int gmc_v6_0_hw_fini(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 979da6f510e8..12411f4c1b9a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -1110,8 +1110,8 @@ static int gmc_v7_0_hw_init(void *handle) if (amdgpu_emu_mode == 1) return amdgpu_gmc_vram_checking(adev); - else - return r; + + return 0; } static int gmc_v7_0_hw_fini(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 382dde1ce74c..cec9926e8bdd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -1240,8 +1240,8 @@ static int gmc_v8_0_hw_init(void *handle) if (amdgpu_emu_mode == 1) return amdgpu_gmc_vram_checking(adev); - else - return r; + + return 0; } static int gmc_v8_0_hw_fini(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 0d9e9d9dd4a1..3e631aefa791 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1861,8 +1861,8 @@ static int gmc_v9_0_hw_init(void *handle) if (amdgpu_emu_mode == 1) return amdgpu_gmc_vram_checking(adev); - else - return r; + + return 0; } /** @@ -1900,6 +1900,10 @@ static int gmc_v9_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); + if (adev->gmc.ecc_irq.funcs && + amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC)) + amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 2eddd7f6cd41..489c89465c78 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1285,10 +1285,32 @@ static int soc15_common_suspend(void *handle) return soc15_common_hw_fini(adev); } +static bool soc15_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg; + + sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); + + /* Will reset for the following suspend abort cases. + * 1) Only reset limit on APU side, dGPU hasn't checked yet. + * 2) S3 suspend abort and TOS already launched. + */ + if (adev->flags & AMD_IS_APU && adev->in_s3 && + !adev->suspend_complete && + sol_reg) + return true; + + return false; +} + static int soc15_common_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (soc15_need_reset_on_resume(adev)) { + dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n"); + soc15_asic_reset(adev); + } return soc15_common_hw_init(adev); } @@ -1411,9 +1433,11 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags) if (amdgpu_sriov_vf(adev)) *flags = 0; - adev->nbio.funcs->get_clockgating_state(adev, flags); + if (adev->nbio.funcs && adev->nbio.funcs->get_clockgating_state) + adev->nbio.funcs->get_clockgating_state(adev, flags); - adev->hdp.funcs->get_clock_gating_state(adev, flags); + if (adev->hdp.funcs && adev->hdp.funcs->get_clock_gating_state) + adev->hdp.funcs->get_clock_gating_state(adev, flags); if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(13, 0, 2)) { @@ -1429,9 +1453,11 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags) } /* AMD_CG_SUPPORT_ROM_MGCG */ - adev->smuio.funcs->get_clock_gating_state(adev, flags); + if (adev->smuio.funcs && adev->smuio.funcs->get_clock_gating_state) + adev->smuio.funcs->get_clock_gating_state(adev, flags); - adev->df.funcs->get_clockgating_state(adev, flags); + if (adev->df.funcs && adev->df.funcs->get_clockgating_state) + adev->df.funcs->get_clockgating_state(adev, flags); } static int soc15_common_set_powergating_state(void *handle, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 88bf6221d4be..8a7705db0b9a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -1019,7 +1019,7 @@ int svm_migrate_init(struct amdgpu_device *adev) } else { res = devm_request_free_mem_region(adev->dev, &iomem_resource, size); if (IS_ERR(res)) - return -ENOMEM; + return PTR_ERR(res); pgmap->range.start = res->start; pgmap->range.end = res->end; pgmap->type = MEMORY_DEVICE_PRIVATE; @@ -1035,11 +1035,10 @@ int svm_migrate_init(struct amdgpu_device *adev) r = devm_memremap_pages(adev->dev, pgmap); if (IS_ERR(r)) { pr_err("failed to register HMM device memory\n"); + if (pgmap->type == MEMORY_DEVICE_PRIVATE) + devm_release_mem_region(adev->dev, res->start, resource_size(res)); /* Disable SVM support capability */ pgmap->type = 0; - if (pgmap->type == MEMORY_DEVICE_PRIVATE) - devm_release_mem_region(adev->dev, res->start, - res->end - res->start + 1); return PTR_ERR(r); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 208812512d8a..7fa5e70f1aac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -380,14 +380,9 @@ static void svm_range_bo_release(struct kref *kref) spin_lock(&svm_bo->list_lock); } spin_unlock(&svm_bo->list_lock); - if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) { - /* We're not in the eviction worker. - * Signal the fence and synchronize with any - * pending eviction work. - */ + if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) + /* We're not in the eviction worker. Signal the fence. */ dma_fence_signal(&svm_bo->eviction_fence->base); - cancel_work_sync(&svm_bo->eviction_work); - } dma_fence_put(&svm_bo->eviction_fence->base); amdgpu_bo_unref(&svm_bo->bo); kfree(svm_bo); @@ -2246,8 +2241,10 @@ retry: mutex_unlock(&svms->lock); mmap_write_unlock(mm); - /* Pairs with mmget in svm_range_add_list_work */ - mmput(mm); + /* Pairs with mmget in svm_range_add_list_work. If dropping the + * last mm refcount, schedule release work to avoid circular locking + */ + mmput_async(mm); spin_lock(&svms->deferred_list_lock); } @@ -2556,6 +2553,7 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, { struct vm_area_struct *vma; struct interval_tree_node *node; + struct rb_node *rb_node; unsigned long start_limit, end_limit; vma = find_vma(p->mm, addr << PAGE_SHIFT); @@ -2578,16 +2576,15 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, if (node) { end_limit = min(end_limit, node->start); /* Last range that ends before the fault address */ - node = container_of(rb_prev(&node->rb), - struct interval_tree_node, rb); + rb_node = rb_prev(&node->rb); } else { /* Last range must end before addr because * there was no range after addr */ - node = container_of(rb_last(&p->svms.objects.rb_root), - struct interval_tree_node, rb); + rb_node = rb_last(&p->svms.objects.rb_root); } - if (node) { + if (rb_node) { + node = container_of(rb_node, struct interval_tree_node, rb); if (node->last >= addr) { WARN(1, "Overlap with prev node and page fault addr\n"); return -EFAULT; @@ -3310,13 +3307,14 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence) { - if (!fence) - return -EINVAL; - - if (dma_fence_is_signaled(&fence->base)) - return 0; - - if (fence->svm_bo) { + /* Dereferencing fence->svm_bo is safe here because the fence hasn't + * signaled yet and we're under the protection of the fence->lock. + * After the fence is signaled in svm_range_bo_release, we cannot get + * here any more. + * + * Reference is dropped in svm_range_evict_svm_bo_worker. + */ + if (svm_bo_ref_unless_zero(fence->svm_bo)) { WRITE_ONCE(fence->svm_bo->evicting, 1); schedule_work(&fence->svm_bo->eviction_work); } @@ -3331,8 +3329,6 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) int r = 0; svm_bo = container_of(work, struct svm_range_bo, eviction_work); - if (!svm_bo_ref_unless_zero(svm_bo)) - return; /* svm_bo was freed while eviction was pending */ if (mmget_not_zero(svm_bo->eviction_fence->mm)) { mm = svm_bo->eviction_fence->mm; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 713f893d2530..029916971bf6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -1403,10 +1403,11 @@ static int kfd_create_indirect_link_prop(struct kfd_topology_device *kdev, int g num_cpu++; } + if (list_empty(&kdev->io_link_props)) + return -ENODATA; + gpu_link = list_first_entry(&kdev->io_link_props, - struct kfd_iolink_properties, list); - if (!gpu_link) - return -ENOMEM; + struct kfd_iolink_properties, list); for (i = 0; i < num_cpu; i++) { /* CPU <--> GPU */ @@ -1484,15 +1485,17 @@ static int kfd_add_peer_prop(struct kfd_topology_device *kdev, peer->gpu->adev)) return ret; + if (list_empty(&kdev->io_link_props)) + return -ENODATA; + iolink1 = list_first_entry(&kdev->io_link_props, - struct kfd_iolink_properties, list); - if (!iolink1) - return -ENOMEM; + struct kfd_iolink_properties, list); + + if (list_empty(&peer->io_link_props)) + return -ENODATA; iolink2 = list_first_entry(&peer->io_link_props, - struct kfd_iolink_properties, list); - if (!iolink2) - return -ENOMEM; + struct kfd_iolink_properties, list); props = kfd_alloc_struct(props); if (!props) @@ -1510,17 +1513,19 @@ static int kfd_add_peer_prop(struct kfd_topology_device *kdev, /* CPU->CPU link*/ cpu_dev = kfd_topology_device_by_proximity_domain(iolink1->node_to); if (cpu_dev) { - list_for_each_entry(iolink3, &cpu_dev->io_link_props, list) - if (iolink3->node_to == iolink2->node_to) - break; - - props->weight += iolink3->weight; - props->min_latency += iolink3->min_latency; - props->max_latency += iolink3->max_latency; - props->min_bandwidth = min(props->min_bandwidth, - iolink3->min_bandwidth); - props->max_bandwidth = min(props->max_bandwidth, - iolink3->max_bandwidth); + list_for_each_entry(iolink3, &cpu_dev->io_link_props, list) { + if (iolink3->node_to != iolink2->node_to) + continue; + + props->weight += iolink3->weight; + props->min_latency += iolink3->min_latency; + props->max_latency += iolink3->max_latency; + props->min_bandwidth = min(props->min_bandwidth, + iolink3->min_bandwidth); + props->max_bandwidth = min(props->max_bandwidth, + iolink3->max_bandwidth); + break; + } } else { WARN(1, "CPU node not found"); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 6d5f3c5fb4a6..da16048bf100 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2255,6 +2255,7 @@ static int dm_sw_fini(void *handle) if (adev->dm.dmub_srv) { dmub_srv_destroy(adev->dm.dmub_srv); + kfree(adev->dm.dmub_srv); adev->dm.dmub_srv = NULL; } @@ -5104,6 +5105,9 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, if (plane->type == DRM_PLANE_TYPE_CURSOR) return; + if (new_plane_state->rotation != DRM_MODE_ROTATE_0) + goto ffu; + num_clips = drm_plane_get_damage_clips_count(new_plane_state); clips = drm_plane_get_damage_clips(new_plane_state); @@ -5998,7 +6002,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (recalculate_timing) { freesync_mode = get_highest_refresh_rate_mode(aconnector, false); drm_mode_copy(&saved_mode, &mode); + saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio; drm_mode_copy(&mode, freesync_mode); + mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio; } else { decide_crtc_timing_for_drm_display_mode( &mode, preferred_mode, scale); @@ -6674,8 +6680,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder, if (IS_ERR(mst_state)) return PTR_ERR(mst_state); - if (!mst_state->pbn_div) - mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_port->dc_link); + mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_port->dc_link); if (!state->duplicated) { int max_bpc = conn_state->max_requested_bpc; diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index e507d2e1410b..93e40e0a1508 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1018,13 +1018,20 @@ static enum bp_result get_ss_info_v4_5( DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_DISPLAY_PORT: - ss_info->spread_spectrum_percentage = + if (bp->base.integrated_info) { + DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", bp->base.integrated_info->gpuclk_ss_percentage); + ss_info->spread_spectrum_percentage = + bp->base.integrated_info->gpuclk_ss_percentage; + ss_info->type.CENTER_MODE = + bp->base.integrated_info->gpuclk_ss_type; + } else { + ss_info->spread_spectrum_percentage = disp_cntl_tbl->dp_ss_percentage; - ss_info->spread_spectrum_range = + ss_info->spread_spectrum_range = disp_cntl_tbl->dp_ss_rate_10hz * 10; - if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) - ss_info->type.CENTER_MODE = true; - + if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) + ss_info->type.CENTER_MODE = true; + } DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT ss_percentage: %d\n", ss_info->spread_spectrum_percentage); break; case AS_SIGNAL_TYPE_GPU_PLL: @@ -2830,6 +2837,8 @@ static enum bp_result get_integrated_info_v2_2( info->ma_channel_number = info_v2_2->umachannelnumber; info->dp_ss_control = le16_to_cpu(info_v2_2->reserved1); + info->gpuclk_ss_percentage = info_v2_2->gpuclk_ss_percentage; + info->gpuclk_ss_type = info_v2_2->gpuclk_ss_type; for (i = 0; i < NUMBER_OF_UCHAR_FOR_GUID; ++i) { info->ext_disp_conn_info.gu_id[i] = diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index e43b4d7dc60e..c8136a05a8d3 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -131,30 +131,27 @@ static int dcn314_get_active_display_cnt_wa( return display_count; } -static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) +static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, + bool safe_to_lower, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; for (i = 0; i < dc->res_pool->pipe_count; ++i) { - struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + struct pipe_ctx *pipe = safe_to_lower + ? &context->res_ctx.pipe_ctx[i] + : &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->top_pipe || pipe->prev_odm_pipe) continue; if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) { - struct stream_encoder *stream_enc = pipe->stream_res.stream_enc; - if (disable) { - if (stream_enc && stream_enc->funcs->disable_fifo) - pipe->stream_res.stream_enc->funcs->disable_fifo(stream_enc); + if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc) + pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); reset_sync_context_for_pipe(dc, context, i); } else { pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); - - if (stream_enc && stream_enc->funcs->enable_fifo) - pipe->stream_res.stream_enc->funcs->enable_fifo(stream_enc); } } } @@ -254,11 +251,11 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn314_disable_otg_wa(clk_mgr_base, context, true); + dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn314_disable_otg_wa(clk_mgr_base, context, false); + dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index 893991a0eb97..28b83133db91 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -324,7 +324,7 @@ static struct wm_table lpddr5_wm_table = { { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -332,7 +332,7 @@ static struct wm_table lpddr5_wm_table = { { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -340,7 +340,7 @@ static struct wm_table lpddr5_wm_table = { { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -348,7 +348,7 @@ static struct wm_table lpddr5_wm_table = { { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 11.65333, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 7a309547c2b3..f415733f1a97 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1903,6 +1903,10 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c wait_for_no_pipes_pending(dc, context); /* pplib is notified if disp_num changed */ dc->hwss.optimize_bandwidth(dc, context); + /* Need to do otg sync again as otg could be out of sync due to otg + * workaround applied during clock update + */ + dc_trigger_sync(dc, context); } if (dc->hwss.update_dsc_pg) diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index 848db8676adf..811c117665e7 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -244,7 +244,7 @@ enum pixel_format { #define DC_MAX_DIRTY_RECTS 3 struct dc_flip_addrs { struct dc_plane_address address; - unsigned int flip_timestamp_in_us; + unsigned long long flip_timestamp_in_us; bool flip_immediate; /* TODO: add flip duration for FreeSync */ bool triplebuffer_flips; @@ -465,6 +465,7 @@ struct dc_cursor_mi_param { struct fixed31_32 v_scale_ratio; enum dc_rotation_angle rotation; bool mirror; + struct dc_stream_state *stream; }; /* IPP related types */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index d84579da6400..009b5861a3fe 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -3427,7 +3427,8 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz, .v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert, .rotation = pipe_ctx->plane_state->rotation, - .mirror = pipe_ctx->plane_state->horizontal_mirror + .mirror = pipe_ctx->plane_state->horizontal_mirror, + .stream = pipe_ctx->stream, }; bool pipe_split_on = false; bool odm_combine_on = (pipe_ctx->next_odm_pipe != NULL) || diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index 4566bc7abf17..aa252dc26326 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -1075,8 +1075,16 @@ void hubp2_cursor_set_position( if (src_y_offset < 0) src_y_offset = 0; /* Save necessary cursor info x, y position. w, h is saved in attribute func. */ - hubp->cur_rect.x = src_x_offset + param->viewport.x; - hubp->cur_rect.y = src_y_offset + param->viewport.y; + if (param->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 && + param->rotation != ROTATION_ANGLE_0) { + hubp->cur_rect.x = 0; + hubp->cur_rect.y = 0; + hubp->cur_rect.w = param->stream->timing.h_addressable; + hubp->cur_rect.h = param->stream->timing.v_addressable; + } else { + hubp->cur_rect.x = src_x_offset + param->viewport.x; + hubp->cur_rect.y = src_y_offset + param->viewport.y; + } } void hubp2_clk_cntl(struct hubp *hubp, bool enable) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 53262f6bc40b..72bec33e371f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -994,5 +994,8 @@ void dcn30_prepare_bandwidth(struct dc *dc, dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz); dcn20_prepare_bandwidth(dc, context); + + dc_dmub_srv_p_state_delegate(dc, + context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching, context); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index f04595b750ab..5ec3f50a72ac 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -1014,7 +1014,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id vpg = dcn301_vpg_create(ctx, vpg_inst); afmt = dcn301_afmt_create(ctx, afmt_inst); - if (!enc1 || !vpg || !afmt) { + if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) { kfree(enc1); kfree(vpg); kfree(afmt); diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index ca7d24000621..6fdf87a6e240 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -60,11 +60,11 @@ ifdef CONFIG_DRM_AMD_DC_DCN CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 9d224bb2b3df..ce893fe1c69f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -438,7 +438,115 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { .use_urgent_burst_bw = 0 }; -struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 }; +struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { + .clock_limits = { + { + .state = 0, + .dcfclk_mhz = 560.0, + .fabricclk_mhz = 560.0, + .dispclk_mhz = 513.0, + .dppclk_mhz = 513.0, + .phyclk_mhz = 540.0, + .socclk_mhz = 560.0, + .dscclk_mhz = 171.0, + .dram_speed_mts = 1069.0, + }, + { + .state = 1, + .dcfclk_mhz = 694.0, + .fabricclk_mhz = 694.0, + .dispclk_mhz = 642.0, + .dppclk_mhz = 642.0, + .phyclk_mhz = 600.0, + .socclk_mhz = 694.0, + .dscclk_mhz = 214.0, + .dram_speed_mts = 1324.0, + }, + { + .state = 2, + .dcfclk_mhz = 875.0, + .fabricclk_mhz = 875.0, + .dispclk_mhz = 734.0, + .dppclk_mhz = 734.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 875.0, + .dscclk_mhz = 245.0, + .dram_speed_mts = 1670.0, + }, + { + .state = 3, + .dcfclk_mhz = 1000.0, + .fabricclk_mhz = 1000.0, + .dispclk_mhz = 1100.0, + .dppclk_mhz = 1100.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1000.0, + .dscclk_mhz = 367.0, + .dram_speed_mts = 2000.0, + }, + { + .state = 4, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 2000.0, + }, + { + .state = 5, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 2000.0, + }, + }, + + .num_states = 5, + .sr_exit_time_us = 1.9, + .sr_enter_plus_exit_time_us = 4.4, + .urgent_latency_us = 3.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 40.0, + .max_avg_dram_bw_use_normal_percent = 40.0, + .writeback_latency_us = 12.0, + .ideal_dram_bw_after_urgent_percent = 40.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 16, + .fabric_datapath_to_dcn_data_return_bytes = 64, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.5, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 131, + .urgent_out_of_order_return_per_channel_bytes = 4096, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 16, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 45.0, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3850, + .xfc_bus_transport_time_us = 20, + .xfc_xbuf_latency_tolerance_us = 50, + .use_urgent_burst_bw = 0, +}; struct _vcs_dpi_ip_params_st dcn2_1_ip = { .odm_capable = 1, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 19f55657272e..cc8c1a48c5c4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -810,6 +810,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman (v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKPerState[mode_lib->vba.VoltageLevel] <= DCFCLK_FREQ_EXTRA_PREFETCH_REQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, + mode_lib->vba.PrefetchModePerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] > 0 || mode_lib->vba.DRAMClockChangeRequirementFinal == false, + /* Output */ &v->DSTXAfterScaler[k], &v->DSTYAfterScaler[k], @@ -3291,6 +3293,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->SwathHeightCThisState[k], v->TWait, (v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKState[i][j] <= DCFCLK_FREQ_EXTRA_PREFETCH_REQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, + mode_lib->vba.PrefetchModePerState[i][j] > 0 || mode_lib->vba.DRAMClockChangeRequirementFinal == false, /* Output */ &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler[k], diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 23e4be2ad63f..7f4fc49be35c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -3418,6 +3418,7 @@ bool dml32_CalculatePrefetchSchedule( unsigned int SwathHeightC, double TWait, double TPreReq, + bool ExtendPrefetchIfPossible, /* Output */ double *DSTXAfterScaler, double *DSTYAfterScaler, @@ -3887,12 +3888,32 @@ bool dml32_CalculatePrefetchSchedule( /* Clamp to oto for bandwidth calculation */ LinesForPrefetchBandwidth = dst_y_prefetch_oto; } else { - *DestinationLinesForPrefetch = dst_y_prefetch_equ; - TimeForFetchingMetaPTE = Tvm_equ; - TimeForFetchingRowInVBlank = Tr0_equ; - *PrefetchBandwidth = prefetch_bw_equ; - /* Clamp to equ for bandwidth calculation */ - LinesForPrefetchBandwidth = dst_y_prefetch_equ; + /* For mode programming we want to extend the prefetch as much as possible + * (up to oto, or as long as we can for equ) if we're not already applying + * the 60us prefetch requirement. This is to avoid intermittent underflow + * issues during prefetch. + * + * The prefetch extension is applied under the following scenarios: + * 1. We're in prefetch mode > 0 (i.e. we don't support MCLK switch in blank) + * 2. We're using subvp or drr methods of p-state switch, in which case we + * we don't care if prefetch takes up more of the blanking time + * + * Mode programming typically chooses the smallest prefetch time possible + * (i.e. highest bandwidth during prefetch) presumably to create margin between + * p-states / c-states that happen in vblank and prefetch. Therefore we only + * apply this prefetch extension when p-state in vblank is not required (UCLK + * p-states take up the most vblank time). + */ + if (ExtendPrefetchIfPossible && TPreReq == 0 && VStartup < MaxVStartup) { + MyError = true; + } else { + *DestinationLinesForPrefetch = dst_y_prefetch_equ; + TimeForFetchingMetaPTE = Tvm_equ; + TimeForFetchingRowInVBlank = Tr0_equ; + *PrefetchBandwidth = prefetch_bw_equ; + /* Clamp to equ for bandwidth calculation */ + LinesForPrefetchBandwidth = dst_y_prefetch_equ; + } } *DestinationLinesToRequestVMInVBlank = dml_ceil(4.0 * TimeForFetchingMetaPTE / LineTime, 1.0) / 4.0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h index 779c6805f599..1823434d8ede 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h @@ -744,6 +744,7 @@ bool dml32_CalculatePrefetchSchedule( unsigned int SwathHeightC, double TWait, double TPreReq, + bool ExtendPrefetchIfPossible, /* Output */ double *DSTXAfterScaler, double *DSTYAfterScaler, diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h index bc96d0211360..813463ffe15c 100644 --- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h +++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h @@ -417,6 +417,8 @@ struct integrated_info { /* V2.1 */ struct edp_info edp1_info; struct edp_info edp2_info; + uint32_t gpuclk_ss_percentage; + uint32_t gpuclk_ss_type; }; /* diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c index f5e08b60f66e..d17bfa111aa7 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -2748,10 +2748,8 @@ static int kv_parse_power_table(struct amdgpu_device *adev) non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *) &non_clock_info_array->nonClockInfo[non_clock_array_index]; ps = kzalloc(sizeof(struct kv_ps), GFP_KERNEL); - if (ps == NULL) { - kfree(adev->pm.dpm.ps); + if (ps == NULL) return -ENOMEM; - } adev->pm.dpm.ps[i].ps_priv = ps; k = 0; idx = (u8 *)&power_state->v2.clockInfoIndex[0]; diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c index d3fe149d8476..291223ea7ba7 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c @@ -272,10 +272,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) le16_to_cpu(power_info->pplib4.usVddcDependencyOnSCLKOffset)); ret = amdgpu_parse_clk_voltage_dep_table(&adev->pm.dpm.dyn_state.vddc_dependency_on_sclk, dep_table); - if (ret) { - amdgpu_free_extended_power_table(adev); + if (ret) return ret; - } } if (power_info->pplib4.usVddciDependencyOnMCLKOffset) { dep_table = (ATOM_PPLIB_Clock_Voltage_Dependency_Table *) @@ -283,10 +281,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) le16_to_cpu(power_info->pplib4.usVddciDependencyOnMCLKOffset)); ret = amdgpu_parse_clk_voltage_dep_table(&adev->pm.dpm.dyn_state.vddci_dependency_on_mclk, dep_table); - if (ret) { - amdgpu_free_extended_power_table(adev); + if (ret) return ret; - } } if (power_info->pplib4.usVddcDependencyOnMCLKOffset) { dep_table = (ATOM_PPLIB_Clock_Voltage_Dependency_Table *) @@ -294,10 +290,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) le16_to_cpu(power_info->pplib4.usVddcDependencyOnMCLKOffset)); ret = amdgpu_parse_clk_voltage_dep_table(&adev->pm.dpm.dyn_state.vddc_dependency_on_mclk, dep_table); - if (ret) { - amdgpu_free_extended_power_table(adev); + if (ret) return ret; - } } if (power_info->pplib4.usMvddDependencyOnMCLKOffset) { dep_table = (ATOM_PPLIB_Clock_Voltage_Dependency_Table *) @@ -305,10 +299,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) le16_to_cpu(power_info->pplib4.usMvddDependencyOnMCLKOffset)); ret = amdgpu_parse_clk_voltage_dep_table(&adev->pm.dpm.dyn_state.mvdd_dependency_on_mclk, dep_table); - if (ret) { - amdgpu_free_extended_power_table(adev); + if (ret) return ret; - } } if (power_info->pplib4.usMaxClockVoltageOnDCOffset) { ATOM_PPLIB_Clock_Voltage_Limit_Table *clk_v = @@ -339,10 +331,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) kcalloc(psl->ucNumEntries, sizeof(struct amdgpu_phase_shedding_limits_entry), GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.phase_shedding_limits_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.phase_shedding_limits_table.entries) return -ENOMEM; - } entry = &psl->entries[0]; for (i = 0; i < psl->ucNumEntries; i++) { @@ -383,10 +373,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) ATOM_PPLIB_CAC_Leakage_Record *entry; u32 size = cac_table->ucNumEntries * sizeof(struct amdgpu_cac_leakage_table); adev->pm.dpm.dyn_state.cac_leakage_table.entries = kzalloc(size, GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.cac_leakage_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.cac_leakage_table.entries) return -ENOMEM; - } entry = &cac_table->entries[0]; for (i = 0; i < cac_table->ucNumEntries; i++) { if (adev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_EVV) { @@ -438,10 +426,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) sizeof(struct amdgpu_vce_clock_voltage_dependency_entry); adev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries = kzalloc(size, GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries) return -ENOMEM; - } adev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.count = limits->numEntries; entry = &limits->entries[0]; @@ -493,10 +479,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) sizeof(struct amdgpu_uvd_clock_voltage_dependency_entry); adev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries = kzalloc(size, GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries) return -ENOMEM; - } adev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.count = limits->numEntries; entry = &limits->entries[0]; @@ -525,10 +509,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) sizeof(struct amdgpu_clock_voltage_dependency_entry); adev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries = kzalloc(size, GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries) return -ENOMEM; - } adev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.count = limits->numEntries; entry = &limits->entries[0]; @@ -548,10 +530,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) le16_to_cpu(ext_hdr->usPPMTableOffset)); adev->pm.dpm.dyn_state.ppm_table = kzalloc(sizeof(struct amdgpu_ppm_table), GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.ppm_table) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.ppm_table) return -ENOMEM; - } adev->pm.dpm.dyn_state.ppm_table->ppm_design = ppm->ucPpmDesign; adev->pm.dpm.dyn_state.ppm_table->cpu_core_number = le16_to_cpu(ppm->usCpuCoreNumber); @@ -583,10 +563,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) sizeof(struct amdgpu_clock_voltage_dependency_entry); adev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries = kzalloc(size, GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries) return -ENOMEM; - } adev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.count = limits->numEntries; entry = &limits->entries[0]; @@ -606,10 +584,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) ATOM_PowerTune_Table *pt; adev->pm.dpm.dyn_state.cac_tdp_table = kzalloc(sizeof(struct amdgpu_cac_tdp_table), GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.cac_tdp_table) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.cac_tdp_table) return -ENOMEM; - } if (rev > 0) { ATOM_PPLIB_POWERTUNE_Table_V1 *ppt = (ATOM_PPLIB_POWERTUNE_Table_V1 *) (mode_info->atom_context->bios + data_offset + @@ -645,10 +621,8 @@ int amdgpu_parse_extended_power_table(struct amdgpu_device *adev) ret = amdgpu_parse_clk_voltage_dep_table( &adev->pm.dpm.dyn_state.vddgfx_dependency_on_sclk, dep_table); - if (ret) { - kfree(adev->pm.dpm.dyn_state.vddgfx_dependency_on_sclk.entries); + if (ret) return ret; - } } } diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index c89cfef7cafa..dc0a6fba7050 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -7379,10 +7379,9 @@ static int si_dpm_init(struct amdgpu_device *adev) kcalloc(4, sizeof(struct amdgpu_clock_voltage_dependency_entry), GFP_KERNEL); - if (!adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries) { - amdgpu_free_extended_power_table(adev); + if (!adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries) return -ENOMEM; - } + adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.count = 4; adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[0].clk = 0; adev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[0].v = 0; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c index f2a55c1413f5..17882f8dfdd3 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c @@ -200,7 +200,7 @@ static int get_platform_power_management_table( struct pp_hwmgr *hwmgr, ATOM_Tonga_PPM_Table *atom_ppm_table) { - struct phm_ppm_table *ptr = kzalloc(sizeof(ATOM_Tonga_PPM_Table), GFP_KERNEL); + struct phm_ppm_table *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL); struct phm_ppt_v1_information *pp_table_information = (struct phm_ppt_v1_information *)(hwmgr->pptable); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index a31a62a1ce0b..5e9410117712 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -2987,6 +2987,8 @@ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) result = smu7_get_evv_voltages(hwmgr); if (result) { pr_info("Get EVV Voltage Failed. Abort Driver loading!\n"); + kfree(hwmgr->backend); + hwmgr->backend = NULL; return -EINVAL; } } else { @@ -3032,8 +3034,10 @@ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) } result = smu7_update_edc_leakage_table(hwmgr); - if (result) + if (result) { + smu7_hwmgr_backend_fini(hwmgr); return result; + } return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 47ff3694ffa5..1d0693dad818 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -24,6 +24,7 @@ #include <linux/firmware.h> #include <linux/pci.h> +#include <linux/power_supply.h> #include <linux/reboot.h> #include "amdgpu.h" @@ -731,16 +732,8 @@ static int smu_late_init(void *handle) * handle the switch automatically. Driver involvement * is unnecessary. */ - if (!smu->dc_controlled_by_gpio) { - ret = smu_set_power_source(smu, - adev->pm.ac_power ? SMU_POWER_SOURCE_AC : - SMU_POWER_SOURCE_DC); - if (ret) { - dev_err(adev->dev, "Failed to switch to %s mode!\n", - adev->pm.ac_power ? "AC" : "DC"); - return ret; - } - } + adev->pm.ac_power = power_supply_is_system_supplied() > 0; + smu_set_ac_dc(smu); if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 1)) || (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 3))) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index d490b571c8ff..2e061a74a0b7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1467,10 +1467,12 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev, case 0x3: dev_dbg(adev->dev, "Switched to AC mode!\n"); schedule_work(&smu->interrupt_work); + adev->pm.ac_power = true; break; case 0x4: dev_dbg(adev->dev, "Switched to DC mode!\n"); schedule_work(&smu->interrupt_work); + adev->pm.ac_power = false; break; case 0x7: /* diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 1b0fb93539ec..f3257cf4b06f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1415,10 +1415,12 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, case 0x3: dev_dbg(adev->dev, "Switched to AC mode!\n"); smu_v13_0_ack_ac_dc_interrupt(smu); + adev->pm.ac_power = true; break; case 0x4: dev_dbg(adev->dev, "Switched to DC mode!\n"); smu_v13_0_ack_ac_dc_interrupt(smu); + adev->pm.ac_power = false; break; case 0x7: /* diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index cf86cc05b7fc..77a304ac4d75 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -1300,10 +1300,32 @@ static void anx7625_config(struct anx7625_data *ctx) XTAL_FRQ_SEL, XTAL_FRQ_27M); } +static int anx7625_hpd_timer_config(struct anx7625_data *ctx) +{ + int ret; + + /* Set irq detect window to 2ms */ + ret = anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, + HPD_DET_TIMER_BIT0_7, HPD_TIME & 0xFF); + ret |= anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, + HPD_DET_TIMER_BIT8_15, + (HPD_TIME >> 8) & 0xFF); + ret |= anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, + HPD_DET_TIMER_BIT16_23, + (HPD_TIME >> 16) & 0xFF); + + return ret; +} + +static int anx7625_read_hpd_gpio_config_status(struct anx7625_data *ctx) +{ + return anx7625_reg_read(ctx, ctx->i2c.rx_p0_client, GPIO_CTRL_2); +} + static void anx7625_disable_pd_protocol(struct anx7625_data *ctx) { struct device *dev = &ctx->client->dev; - int ret; + int ret, val; /* Reset main ocm */ ret = anx7625_reg_write(ctx, ctx->i2c.rx_p0_client, 0x88, 0x40); @@ -1317,6 +1339,19 @@ static void anx7625_disable_pd_protocol(struct anx7625_data *ctx) DRM_DEV_DEBUG_DRIVER(dev, "disable PD feature fail.\n"); else DRM_DEV_DEBUG_DRIVER(dev, "disable PD feature succeeded.\n"); + + /* + * Make sure the HPD GPIO already be configured after OCM release before + * setting HPD detect window register. Here we poll the status register + * at maximum 40ms, then config HPD irq detect window register + */ + readx_poll_timeout(anx7625_read_hpd_gpio_config_status, + ctx, val, + ((val & HPD_SOURCE) || (val < 0)), + 2000, 2000 * 20); + + /* Set HPD irq detect window to 2ms */ + anx7625_hpd_timer_config(ctx); } static int anx7625_ocm_loading_check(struct anx7625_data *ctx) @@ -1440,20 +1475,6 @@ static void anx7625_start_dp_work(struct anx7625_data *ctx) static int anx7625_read_hpd_status_p0(struct anx7625_data *ctx) { - int ret; - - /* Set irq detect window to 2ms */ - ret = anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, - HPD_DET_TIMER_BIT0_7, HPD_TIME & 0xFF); - ret |= anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, - HPD_DET_TIMER_BIT8_15, - (HPD_TIME >> 8) & 0xFF); - ret |= anx7625_reg_write(ctx, ctx->i2c.tx_p2_client, - HPD_DET_TIMER_BIT16_23, - (HPD_TIME >> 16) & 0xFF); - if (ret < 0) - return ret; - return anx7625_reg_read(ctx, ctx->i2c.rx_p0_client, SYSTEM_STSTUS); } @@ -1742,6 +1763,7 @@ static ssize_t anx7625_aux_transfer(struct drm_dp_aux *aux, u8 request = msg->request & ~DP_AUX_I2C_MOT; int ret = 0; + mutex_lock(&ctx->aux_lock); pm_runtime_get_sync(dev); msg->reply = 0; switch (request) { @@ -1758,6 +1780,7 @@ static ssize_t anx7625_aux_transfer(struct drm_dp_aux *aux, msg->size, msg->buffer); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); + mutex_unlock(&ctx->aux_lock); return ret; } @@ -2454,7 +2477,9 @@ static void anx7625_bridge_atomic_disable(struct drm_bridge *bridge, ctx->connector = NULL; anx7625_dp_stop(ctx); - pm_runtime_put_sync(dev); + mutex_lock(&ctx->aux_lock); + pm_runtime_put_sync_suspend(dev); + mutex_unlock(&ctx->aux_lock); } static enum drm_connector_status @@ -2648,6 +2673,7 @@ static int anx7625_i2c_probe(struct i2c_client *client) mutex_init(&platform->lock); mutex_init(&platform->hdcp_wq_lock); + mutex_init(&platform->aux_lock); INIT_DELAYED_WORK(&platform->hdcp_work, hdcp_check_work_func); platform->hdcp_workqueue = create_workqueue("hdcp workqueue"); diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.h b/drivers/gpu/drm/bridge/analogix/anx7625.h index 14f33d6be289..164250c8c8b6 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.h +++ b/drivers/gpu/drm/bridge/analogix/anx7625.h @@ -259,6 +259,10 @@ #define AP_MIPI_RX_EN BIT(5) /* 1: MIPI RX input in 0: no RX in */ #define AP_DISABLE_PD BIT(6) #define AP_DISABLE_DISPLAY BIT(7) + +#define GPIO_CTRL_2 0x49 +#define HPD_SOURCE BIT(6) + /***************************************************************/ /* Register definition of device address 0x84 */ #define MIPI_PHY_CONTROL_3 0x03 @@ -471,6 +475,8 @@ struct anx7625_data { struct workqueue_struct *hdcp_workqueue; /* Lock for hdcp work queue */ struct mutex hdcp_wq_lock; + /* Lock for aux transfer and disable */ + struct mutex aux_lock; char edid_block; struct display_timing dt; u8 display_timing_valid; diff --git a/drivers/gpu/drm/bridge/cadence/cdns-dsi-core.c b/drivers/gpu/drm/bridge/cadence/cdns-dsi-core.c index faed98919b34..6a8bff639568 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-dsi-core.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-dsi-core.c @@ -656,7 +656,7 @@ cdns_dsi_bridge_mode_valid(struct drm_bridge *bridge, return MODE_OK; } -static void cdns_dsi_bridge_disable(struct drm_bridge *bridge) +static void cdns_dsi_bridge_late_disable(struct drm_bridge *bridge) { struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge); struct cdns_dsi *dsi = input_to_dsi(input); @@ -676,14 +676,6 @@ static void cdns_dsi_bridge_disable(struct drm_bridge *bridge) pm_runtime_put(dsi->base.dev); } -static void cdns_dsi_bridge_post_disable(struct drm_bridge *bridge) -{ - struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge); - struct cdns_dsi *dsi = input_to_dsi(input); - - pm_runtime_put(dsi->base.dev); -} - static void cdns_dsi_hs_init(struct cdns_dsi *dsi) { struct cdns_dsi_output *output = &dsi->output; @@ -753,7 +745,7 @@ static void cdns_dsi_init_link(struct cdns_dsi *dsi) dsi->link_initialized = true; } -static void cdns_dsi_bridge_enable(struct drm_bridge *bridge) +static void cdns_dsi_bridge_early_enable(struct drm_bridge *bridge) { struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge); struct cdns_dsi *dsi = input_to_dsi(input); @@ -893,25 +885,11 @@ static void cdns_dsi_bridge_enable(struct drm_bridge *bridge) writel(tmp, dsi->regs + MCTL_MAIN_EN); } -static void cdns_dsi_bridge_pre_enable(struct drm_bridge *bridge) -{ - struct cdns_dsi_input *input = bridge_to_cdns_dsi_input(bridge); - struct cdns_dsi *dsi = input_to_dsi(input); - - if (WARN_ON(pm_runtime_get_sync(dsi->base.dev) < 0)) - return; - - cdns_dsi_init_link(dsi); - cdns_dsi_hs_init(dsi); -} - static const struct drm_bridge_funcs cdns_dsi_bridge_funcs = { .attach = cdns_dsi_bridge_attach, .mode_valid = cdns_dsi_bridge_mode_valid, - .disable = cdns_dsi_bridge_disable, - .pre_enable = cdns_dsi_bridge_pre_enable, - .enable = cdns_dsi_bridge_enable, - .post_disable = cdns_dsi_bridge_post_disable, + .early_enable = cdns_dsi_bridge_early_enable, + .late_disable = cdns_dsi_bridge_late_disable, }; static int cdns_dsi_attach(struct mipi_dsi_host *host, diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c index 946212a95598..5e3b8edcf794 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-hdcp.c @@ -403,7 +403,8 @@ static int _cdns_mhdp_hdcp_disable(struct cdns_mhdp_device *mhdp) static int _cdns_mhdp_hdcp_enable(struct cdns_mhdp_device *mhdp, u8 content_type) { - int ret, tries = 3; + int ret = -EINVAL; + int tries = 3; u32 i; for (i = 0; i < tries; i++) { diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c index 0851101a8c72..8686b20ac317 100644 --- a/drivers/gpu/drm/bridge/nxp-ptn3460.c +++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c @@ -54,13 +54,13 @@ static int ptn3460_read_bytes(struct ptn3460_bridge *ptn_bridge, char addr, int ret; ret = i2c_master_send(ptn_bridge->client, &addr, 1); - if (ret <= 0) { + if (ret < 0) { DRM_ERROR("Failed to send i2c command, ret=%d\n", ret); return ret; } ret = i2c_master_recv(ptn_bridge->client, buf, len); - if (ret <= 0) { + if (ret < 0) { DRM_ERROR("Failed to recv i2c data, ret=%d\n", ret); return ret; } @@ -78,7 +78,7 @@ static int ptn3460_write_byte(struct ptn3460_bridge *ptn_bridge, char addr, buf[1] = val; ret = i2c_master_send(ptn_bridge->client, buf, ARRAY_SIZE(buf)); - if (ret <= 0) { + if (ret < 0) { DRM_ERROR("Failed to send i2c command, ret=%d\n", ret); return ret; } diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c index 083337a27966..09737acc2cf4 100644 --- a/drivers/gpu/drm/bridge/parade-ps8640.c +++ b/drivers/gpu/drm/bridge/parade-ps8640.c @@ -106,6 +106,7 @@ struct ps8640 { struct device_link *link; bool pre_enabled; bool need_post_hpd_delay; + struct mutex aux_lock; }; static const struct regmap_config ps8640_regmap_config[] = { @@ -353,11 +354,20 @@ static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux, struct device *dev = &ps_bridge->page[PAGE0_DP_CNTL]->dev; int ret; + mutex_lock(&ps_bridge->aux_lock); pm_runtime_get_sync(dev); + ret = _ps8640_wait_hpd_asserted(ps_bridge, 200 * 1000); + if (ret) { + pm_runtime_put_sync_suspend(dev); + goto exit; + } ret = ps8640_aux_transfer_msg(aux, msg); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); +exit: + mutex_unlock(&ps_bridge->aux_lock); + return ret; } @@ -476,7 +486,18 @@ static void ps8640_post_disable(struct drm_bridge *bridge) ps_bridge->pre_enabled = false; ps8640_bridge_vdo_control(ps_bridge, DISABLE); + + /* + * The bridge seems to expect everything to be power cycled at the + * disable process, so grab a lock here to make sure + * ps8640_aux_transfer() is not holding a runtime PM reference and + * preventing the bridge from suspend. + */ + mutex_lock(&ps_bridge->aux_lock); + pm_runtime_put_sync_suspend(&ps_bridge->page[PAGE0_DP_CNTL]->dev); + + mutex_unlock(&ps_bridge->aux_lock); } static int ps8640_bridge_attach(struct drm_bridge *bridge, @@ -657,6 +678,8 @@ static int ps8640_probe(struct i2c_client *client) if (!ps_bridge) return -ENOMEM; + mutex_init(&ps_bridge->aux_lock); + ps_bridge->supplies[0].supply = "vdd12"; ps_bridge->supplies[1].supply = "vdd33"; ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(ps_bridge->supplies), diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c index 8f09adceeb7b..bc48919b0a16 100644 --- a/drivers/gpu/drm/bridge/sii902x.c +++ b/drivers/gpu/drm/bridge/sii902x.c @@ -1128,6 +1128,26 @@ static int sii902x_init(struct sii902x *sii902x) return ret; } + ret = sii902x_audio_codec_init(sii902x, dev); + if (ret) + return ret; + + i2c_set_clientdata(sii902x->i2c, sii902x); + + sii902x->i2cmux = i2c_mux_alloc(sii902x->i2c->adapter, dev, + 1, 0, I2C_MUX_GATE, + sii902x_i2c_bypass_select, + sii902x_i2c_bypass_deselect); + if (!sii902x->i2cmux) { + ret = -ENOMEM; + goto err_unreg_audio; + } + + sii902x->i2cmux->priv = sii902x; + ret = i2c_mux_add_adapter(sii902x->i2cmux, 0, 0, 0); + if (ret) + goto err_unreg_audio; + sii902x->bridge.funcs = &sii902x_bridge_funcs; sii902x->bridge.of_node = dev->of_node; sii902x->bridge.timings = &default_sii902x_timings; @@ -1138,19 +1158,13 @@ static int sii902x_init(struct sii902x *sii902x) drm_bridge_add(&sii902x->bridge); - sii902x_audio_codec_init(sii902x, dev); - - i2c_set_clientdata(sii902x->i2c, sii902x); + return 0; - sii902x->i2cmux = i2c_mux_alloc(sii902x->i2c->adapter, dev, - 1, 0, I2C_MUX_GATE, - sii902x_i2c_bypass_select, - sii902x_i2c_bypass_deselect); - if (!sii902x->i2cmux) - return -ENOMEM; +err_unreg_audio: + if (!PTR_ERR_OR_ZERO(sii902x->audio.pdev)) + platform_device_unregister(sii902x->audio.pdev); - sii902x->i2cmux->priv = sii902x; - return i2c_mux_add_adapter(sii902x->i2cmux, 0, 0, 0); + return ret; } static int sii902x_probe(struct i2c_client *client, @@ -1233,18 +1247,20 @@ static int sii902x_probe(struct i2c_client *client, } static void sii902x_remove(struct i2c_client *client) - { struct sii902x *sii902x = i2c_get_clientdata(client); + drm_bridge_remove(&sii902x->bridge); i2c_mux_del_adapters(sii902x->i2cmux); if (sii902x->link) device_link_del(sii902x->link); - drm_bridge_remove(&sii902x->bridge); regulator_bulk_disable(ARRAY_SIZE(sii902x->supplies), sii902x->supplies); + + if (!PTR_ERR_OR_ZERO(sii902x->audio.pdev)) + platform_device_unregister(sii902x->audio.pdev); } static const struct of_device_id sii902x_dt_ids[] = { diff --git a/drivers/gpu/drm/bridge/tc358762.c b/drivers/gpu/drm/bridge/tc358762.c index 8f4e9570f272..984d7b44651d 100644 --- a/drivers/gpu/drm/bridge/tc358762.c +++ b/drivers/gpu/drm/bridge/tc358762.c @@ -124,7 +124,7 @@ static int tc358762_init(struct tc358762 *ctx) return tc358762_clear_error(ctx); } -static void tc358762_post_disable(struct drm_bridge *bridge) +static void tc358762_late_disable(struct drm_bridge *bridge) { struct tc358762 *ctx = bridge_to_tc358762(bridge); int ret; @@ -143,7 +143,7 @@ static void tc358762_post_disable(struct drm_bridge *bridge) dev_err(ctx->dev, "error disabling regulators (%d)\n", ret); } -static void tc358762_pre_enable(struct drm_bridge *bridge) +static void tc358762_early_enable(struct drm_bridge *bridge) { struct tc358762 *ctx = bridge_to_tc358762(bridge); int ret; @@ -169,8 +169,8 @@ static int tc358762_attach(struct drm_bridge *bridge, } static const struct drm_bridge_funcs tc358762_bridge_funcs = { - .post_disable = tc358762_post_disable, - .pre_enable = tc358762_pre_enable, + .late_disable = tc358762_late_disable, + .early_enable = tc358762_early_enable, .attach = tc358762_attach, }; diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index 7ef78283e3d3..926ab5c3c31a 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -2097,7 +2097,7 @@ static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id) } else { if (tc->hpd_pin < 0 || tc->hpd_pin > 1) { dev_err(dev, "failed to parse HPD number\n"); - return ret; + return -EINVAL; } } diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 88a54ca35697..9603345feadf 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -529,6 +529,7 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, u32 request_val = AUX_CMD_REQ(msg->request); u8 *buf = msg->buffer; unsigned int len = msg->size; + unsigned int short_len; unsigned int val; int ret; u8 addr_len[SN_AUX_LENGTH_REG + 1 - SN_AUX_ADDR_19_16_REG]; @@ -602,7 +603,8 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, } if (val & AUX_IRQ_STATUS_AUX_SHORT) { - ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &len); + ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &short_len); + len = min(len, short_len); if (ret) goto exit; } else if (val & AUX_IRQ_STATUS_NAT_I2C_FAIL) { diff --git a/drivers/gpu/drm/bridge/ti-tpd12s015.c b/drivers/gpu/drm/bridge/ti-tpd12s015.c index e0e015243a60..b588fea12502 100644 --- a/drivers/gpu/drm/bridge/ti-tpd12s015.c +++ b/drivers/gpu/drm/bridge/ti-tpd12s015.c @@ -179,7 +179,7 @@ static int tpd12s015_probe(struct platform_device *pdev) return 0; } -static int __exit tpd12s015_remove(struct platform_device *pdev) +static int tpd12s015_remove(struct platform_device *pdev) { struct tpd12s015_device *tpd = platform_get_drvdata(pdev); @@ -197,7 +197,7 @@ MODULE_DEVICE_TABLE(of, tpd12s015_of_match); static struct platform_driver tpd12s015_driver = { .probe = tpd12s015_probe, - .remove = __exit_p(tpd12s015_remove), + .remove = tpd12s015_remove, .driver = { .name = "tpd12s015", .of_match_table = tpd12s015_of_match, diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index b097bff1cd18..385af7c95ff4 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1247,6 +1247,48 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state) if (ret == 0) drm_crtc_vblank_put(crtc); } + + for_each_oldnew_connector_in_state(old_state, connector, old_conn_state, new_conn_state, i) { + struct drm_encoder *encoder; + struct drm_bridge *bridge; + + /* + * Shut down everything that's in the changeset and currently + * still on. So need to check the old, saved state. + */ + if (!old_conn_state->crtc) + continue; + + old_crtc_state = drm_atomic_get_old_crtc_state(old_state, old_conn_state->crtc); + + if (new_conn_state->crtc) + new_crtc_state = drm_atomic_get_new_crtc_state(old_state, + new_conn_state->crtc); + else + new_crtc_state = NULL; + + if (!crtc_needs_disable(old_crtc_state, new_crtc_state) || + !drm_atomic_crtc_needs_modeset(old_conn_state->crtc->state)) + continue; + + encoder = old_conn_state->best_encoder; + + /* We shouldn't get this far if we didn't previously have + * an encoder.. but WARN_ON() rather than explode. + */ + if (WARN_ON(!encoder)) + continue; + + drm_dbg_atomic(dev, "disabling [ENCODER:%d:%s]\n", + encoder->base.id, encoder->name); + + /* + * Each encoder has at most one connector (since we always steal + * it away), so we won't call disable hooks twice. + */ + bridge = drm_bridge_chain_get_first_bridge(encoder); + drm_atomic_bridge_chain_late_disable(bridge, old_state); + } } /** @@ -1482,6 +1524,30 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, struct drm_connector_state *new_conn_state; int i; + for_each_new_connector_in_state(old_state, connector, new_conn_state, i) { + struct drm_encoder *encoder; + struct drm_bridge *bridge; + + if (!new_conn_state->best_encoder) + continue; + + if (!new_conn_state->crtc->state->active || + !drm_atomic_crtc_needs_modeset(new_conn_state->crtc->state)) + continue; + + encoder = new_conn_state->best_encoder; + + drm_dbg_atomic(dev, "enabling [ENCODER:%d:%s]\n", + encoder->base.id, encoder->name); + + /* + * Each encoder has at most one connector (since we always steal + * it away), so we won't call enable hooks twice. + */ + bridge = drm_bridge_chain_get_first_bridge(encoder); + drm_atomic_bridge_chain_early_enable(bridge, old_state); + } + for_each_oldnew_crtc_in_state(old_state, crtc, old_crtc_state, new_crtc_state, i) { const struct drm_crtc_helper_funcs *funcs; diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c index 7044e339a82c..9efdf50ab5f8 100644 --- a/drivers/gpu/drm/drm_bridge.c +++ b/drivers/gpu/drm/drm_bridge.c @@ -691,6 +691,49 @@ void drm_atomic_bridge_chain_disable(struct drm_bridge *bridge, } EXPORT_SYMBOL(drm_atomic_bridge_chain_disable); +/** + * drm_atomic_bridge_chain_late_disable - disables all bridges in the encoder chain + * after crtc is disabled. + * @bridge: bridge control structure + * @old_state: old atomic state + * + * Calls &drm_bridge_funcs.atomic_late_disable op for all the bridges in the + * encoder chain, starting from the last bridge to the first. These are called + * after calling &drm_crtc_helper_funcs.atomic_late_disable + * + * Note: the bridge passed should be the one closest to the encoder + */ +void drm_atomic_bridge_chain_late_disable(struct drm_bridge *bridge, + struct drm_atomic_state *old_state) +{ + struct drm_encoder *encoder; + struct drm_bridge *iter; + + if (!bridge) + return; + + encoder = bridge->encoder; + list_for_each_entry_reverse(iter, &encoder->bridge_chain, chain_node) { + if (iter->funcs->atomic_late_disable) { + struct drm_bridge_state *old_bridge_state; + + old_bridge_state = + drm_atomic_get_old_bridge_state(old_state, + iter); + if (WARN_ON(!old_bridge_state)) + return; + + iter->funcs->atomic_late_disable(iter, old_bridge_state); + } else if (iter->funcs->late_disable) { + iter->funcs->late_disable(iter); + } + + if (iter == bridge) + break; + } +} +EXPORT_SYMBOL(drm_atomic_bridge_chain_late_disable); + static void drm_atomic_bridge_call_post_disable(struct drm_bridge *bridge, struct drm_atomic_state *old_state) { @@ -783,6 +826,45 @@ void drm_atomic_bridge_chain_post_disable(struct drm_bridge *bridge, } EXPORT_SYMBOL(drm_atomic_bridge_chain_post_disable); +/** + * drm_atomic_bridge_chain_early_enable - enables all bridges in the encoder + * chain before it's crtc is enabled + * @bridge: bridge control structure + * @old_state: old atomic state + * + * Calls &drm_bridge_funcs.atomic_early_enable op for all the bridges in the + * encoder chain, starting from the first bridge to the last. These are called + * before even the &drm_crtc_helper_funcs.atomic_enable is called. + * + * Note: the bridge passed should be the one closest to the encoder + */ +void drm_atomic_bridge_chain_early_enable(struct drm_bridge *bridge, + struct drm_atomic_state *old_state) +{ + struct drm_encoder *encoder; + + if (!bridge) + return; + + encoder = bridge->encoder; + list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) { + if (bridge->funcs->atomic_early_enable) { + struct drm_bridge_state *old_bridge_state; + + old_bridge_state = + drm_atomic_get_old_bridge_state(old_state, + bridge); + if (WARN_ON(!old_bridge_state)) + return; + + bridge->funcs->atomic_early_enable(bridge, old_bridge_state); + } else if (bridge->funcs->early_enable) { + bridge->funcs->early_enable(bridge); + } + } +} +EXPORT_SYMBOL(drm_atomic_bridge_chain_early_enable); + static void drm_atomic_bridge_call_pre_enable(struct drm_bridge *bridge, struct drm_atomic_state *old_state) { diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index df9bf3c9206e..cb90e70d85e8 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -715,8 +715,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, struct drm_mode_set set; uint32_t __user *set_connectors_ptr; struct drm_modeset_acquire_ctx ctx; - int ret; - int i; + int ret, i, num_connectors = 0; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; @@ -871,6 +870,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, connector->name); connector_set[i] = connector; + num_connectors++; } } @@ -879,7 +879,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, set.y = crtc_req->y; set.mode = mode; set.connectors = connector_set; - set.num_connectors = crtc_req->count_connectors; + set.num_connectors = num_connectors; set.fb = fb; if (drm_drv_uses_atomic_modeset(dev)) @@ -892,7 +892,7 @@ out: drm_framebuffer_put(fb); if (connector_set) { - for (i = 0; i < crtc_req->count_connectors; i++) { + for (i = 0; i < num_connectors; i++) { if (connector_set[i]) drm_connector_put(connector_set[i]); } diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 203bf8d6c34c..d41a5eaa3e89 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -895,8 +895,11 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags) goto err_minors; } - if (drm_core_check_feature(dev, DRIVER_MODESET)) - drm_modeset_register_all(dev); + if (drm_core_check_feature(dev, DRIVER_MODESET)) { + ret = drm_modeset_register_all(dev); + if (ret) + goto err_unload; + } DRM_INFO("Initialized %s %d.%d.%d %s for %s on minor %d\n", driver->name, driver->major, driver->minor, @@ -906,6 +909,9 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags) goto out_unlock; +err_unload: + if (dev->driver->unload) + dev->driver->unload(dev); err_minors: remove_compat_control_link(dev); drm_minor_unregister(dev, DRM_MINOR_PRIMARY); diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index a8b4d918e9a3..d6a0572984b5 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -406,7 +406,7 @@ int drm_open(struct inode *inode, struct file *filp) { struct drm_device *dev; struct drm_minor *minor; - int retcode; + int retcode = 0; int need_setup = 0; minor = drm_minor_acquire(iminor(inode)); diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index 2dd97473ca10..72ad1715f8e7 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -570,7 +570,7 @@ int drm_mode_getfb2_ioctl(struct drm_device *dev, struct drm_mode_fb_cmd2 *r = data; struct drm_framebuffer *fb; unsigned int i; - int ret; + int ret = 0; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EINVAL; diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 853208e8dd73..ef7ec68867df 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -346,7 +346,8 @@ static int mipi_dsi_remove_device_fn(struct device *dev, void *priv) { struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev); - mipi_dsi_detach(dsi); + if (dsi->attached) + mipi_dsi_detach(dsi); mipi_dsi_device_unregister(dsi); return 0; @@ -369,11 +370,18 @@ EXPORT_SYMBOL(mipi_dsi_host_unregister); int mipi_dsi_attach(struct mipi_dsi_device *dsi) { const struct mipi_dsi_host_ops *ops = dsi->host->ops; + int ret; if (!ops || !ops->attach) return -ENOSYS; - return ops->attach(dsi->host, dsi); + ret = ops->attach(dsi->host, dsi); + if (ret) + return ret; + + dsi->attached = true; + + return 0; } EXPORT_SYMBOL(mipi_dsi_attach); @@ -385,9 +393,14 @@ int mipi_dsi_detach(struct mipi_dsi_device *dsi) { const struct mipi_dsi_host_ops *ops = dsi->host->ops; + if (WARN_ON(!dsi->attached)) + return -EINVAL; + if (!ops || !ops->detach) return -ENOSYS; + dsi->attached = false; + return ops->detach(dsi->host, dsi); } EXPORT_SYMBOL(mipi_dsi_detach); diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 33357629a7f5..7a4af43e2cd1 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -1382,6 +1382,7 @@ retry: out: if (fb) drm_framebuffer_put(fb); + fb = NULL; if (plane->old_fb) drm_framebuffer_put(plane->old_fb); plane->old_fb = NULL; diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index eb09e86044c6..68a6d4b0ead7 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -828,7 +828,7 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, if (max_segment == 0) max_segment = UINT_MAX; err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0, - nr_pages << PAGE_SHIFT, + (unsigned long)nr_pages << PAGE_SHIFT, max_segment, GFP_KERNEL); if (err) { kfree(sg); diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index da0145bc104a..8f2737075dc2 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -980,7 +980,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, uint64_t *points; uint32_t signaled_count, i; - if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) + if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) lockdep_assert_none_held_once(); points = kmalloc_array(count, sizeof(*points), GFP_KERNEL); @@ -1049,7 +1050,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, * fallthough and try a 0 timeout wait! */ - if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { + if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) { for (i = 0; i < count; ++i) drm_syncobj_fence_add_wait(syncobjs[i], &entries[i]); } diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 8155d7e650f1..4bc5d9470acd 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -319,9 +319,9 @@ static void decon_win_set_bldmod(struct decon_context *ctx, unsigned int win, static void decon_win_set_pixfmt(struct decon_context *ctx, unsigned int win, struct drm_framebuffer *fb) { - struct exynos_drm_plane plane = ctx->planes[win]; + struct exynos_drm_plane *plane = &ctx->planes[win]; struct exynos_drm_plane_state *state = - to_exynos_plane_state(plane.base.state); + to_exynos_plane_state(plane->base.state); unsigned int alpha = state->base.alpha; unsigned int pixel_alpha; unsigned long val; diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c index a971590b8132..e2c7373f20c6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dma.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c @@ -107,18 +107,16 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev, return 0; if (!priv->mapping) { - void *mapping; + void *mapping = NULL; if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) mapping = arm_iommu_create_mapping(&platform_bus_type, EXYNOS_DEV_ADDR_START, EXYNOS_DEV_ADDR_SIZE); else if (IS_ENABLED(CONFIG_IOMMU_DMA)) mapping = iommu_get_domain_for_dev(priv->dma_dev); - else - mapping = ERR_PTR(-ENODEV); - if (IS_ERR(mapping)) - return PTR_ERR(mapping); + if (!mapping) + return -ENODEV; priv->mapping = mapping; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 16c539657f73..4095b0d3ac2e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -309,6 +309,7 @@ err_mode_config_cleanup: drm_mode_config_cleanup(drm); exynos_drm_cleanup_dma(drm); kfree(private); + dev_set_drvdata(dev, NULL); err_free_drm: drm_dev_put(drm); @@ -323,6 +324,7 @@ static void exynos_drm_unbind(struct device *dev) exynos_drm_fbdev_fini(drm); drm_kms_helper_poll_fini(drm); + drm_atomic_helper_shutdown(drm); component_unbind_all(drm->dev, drm); drm_mode_config_cleanup(drm); @@ -360,9 +362,18 @@ static int exynos_drm_platform_remove(struct platform_device *pdev) return 0; } +static void exynos_drm_platform_shutdown(struct platform_device *pdev) +{ + struct drm_device *drm = platform_get_drvdata(pdev); + + if (drm) + drm_atomic_helper_shutdown(drm); +} + static struct platform_driver exynos_drm_platform_driver = { .probe = exynos_drm_platform_probe, .remove = exynos_drm_platform_remove, + .shutdown = exynos_drm_platform_shutdown, .driver = { .name = "exynos-drm", .pm = &exynos_drm_pm_ops, diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index ae6636e6658e..529033b980b2 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -662,9 +662,9 @@ static void fimd_win_set_bldmod(struct fimd_context *ctx, unsigned int win, static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win, struct drm_framebuffer *fb, int width) { - struct exynos_drm_plane plane = ctx->planes[win]; + struct exynos_drm_plane *plane = &ctx->planes[win]; struct exynos_drm_plane_state *state = - to_exynos_plane_state(plane.base.state); + to_exynos_plane_state(plane->base.state); uint32_t pixel_format = fb->format->format; unsigned int alpha = state->base.alpha; u32 val = WINCONx_ENWIN; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 964dceb28c1e..68ea92742b06 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -1342,7 +1342,7 @@ static int __maybe_unused gsc_runtime_resume(struct device *dev) for (i = 0; i < ctx->num_clocks; i++) { ret = clk_prepare_enable(ctx->clocks[i]); if (ret) { - while (--i > 0) + while (--i >= 0) clk_disable_unprepare(ctx->clocks[i]); return ret; } diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index b7c11bdce2c8..1a7194a653ae 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1861,6 +1861,8 @@ static int hdmi_bind(struct device *dev, struct device *master, void *data) return ret; crtc = exynos_drm_crtc_get_by_type(drm_dev, EXYNOS_DISPLAY_TYPE_HDMI); + if (IS_ERR(crtc)) + return PTR_ERR(crtc); crtc->pipe_clk = &hdata->phy_clk; ret = hdmi_create_connector(encoder); diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c index 18f0a5ae3bac..a502af0b6dd4 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.c +++ b/drivers/gpu/drm/i915/display/intel_atomic.c @@ -41,6 +41,7 @@ #include "intel_global_state.h" #include "intel_hdcp.h" #include "intel_psr.h" +#include "intel_fb.h" #include "skl_universal_plane.h" /** @@ -302,198 +303,6 @@ intel_crtc_destroy_state(struct drm_crtc *crtc, kfree(crtc_state); } -static void intel_atomic_setup_scaler(struct intel_crtc_scaler_state *scaler_state, - int num_scalers_need, struct intel_crtc *intel_crtc, - const char *name, int idx, - struct intel_plane_state *plane_state, - int *scaler_id) -{ - struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev); - int j; - u32 mode; - - if (*scaler_id < 0) { - /* find a free scaler */ - for (j = 0; j < intel_crtc->num_scalers; j++) { - if (scaler_state->scalers[j].in_use) - continue; - - *scaler_id = j; - scaler_state->scalers[*scaler_id].in_use = 1; - break; - } - } - - if (drm_WARN(&dev_priv->drm, *scaler_id < 0, - "Cannot find scaler for %s:%d\n", name, idx)) - return; - - /* set scaler mode */ - if (plane_state && plane_state->hw.fb && - plane_state->hw.fb->format->is_yuv && - plane_state->hw.fb->format->num_planes > 1) { - struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); - if (DISPLAY_VER(dev_priv) == 9) { - mode = SKL_PS_SCALER_MODE_NV12; - } else if (icl_is_hdr_plane(dev_priv, plane->id)) { - /* - * On gen11+'s HDR planes we only use the scaler for - * scaling. They have a dedicated chroma upsampler, so - * we don't need the scaler to upsample the UV plane. - */ - mode = PS_SCALER_MODE_NORMAL; - } else { - struct intel_plane *linked = - plane_state->planar_linked_plane; - - mode = PS_SCALER_MODE_PLANAR; - - if (linked) - mode |= PS_PLANE_Y_SEL(linked->id); - } - } else if (DISPLAY_VER(dev_priv) >= 10) { - mode = PS_SCALER_MODE_NORMAL; - } else if (num_scalers_need == 1 && intel_crtc->num_scalers > 1) { - /* - * when only 1 scaler is in use on a pipe with 2 scalers - * scaler 0 operates in high quality (HQ) mode. - * In this case use scaler 0 to take advantage of HQ mode - */ - scaler_state->scalers[*scaler_id].in_use = 0; - *scaler_id = 0; - scaler_state->scalers[0].in_use = 1; - mode = SKL_PS_SCALER_MODE_HQ; - } else { - mode = SKL_PS_SCALER_MODE_DYN; - } - - drm_dbg_kms(&dev_priv->drm, "Attached scaler id %u.%u to %s:%d\n", - intel_crtc->pipe, *scaler_id, name, idx); - scaler_state->scalers[*scaler_id].mode = mode; -} - -/** - * intel_atomic_setup_scalers() - setup scalers for crtc per staged requests - * @dev_priv: i915 device - * @intel_crtc: intel crtc - * @crtc_state: incoming crtc_state to validate and setup scalers - * - * This function sets up scalers based on staged scaling requests for - * a @crtc and its planes. It is called from crtc level check path. If request - * is a supportable request, it attaches scalers to requested planes and crtc. - * - * This function takes into account the current scaler(s) in use by any planes - * not being part of this atomic state - * - * Returns: - * 0 - scalers were setup succesfully - * error code - otherwise - */ -int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, - struct intel_crtc *intel_crtc, - struct intel_crtc_state *crtc_state) -{ - struct drm_plane *plane = NULL; - struct intel_plane *intel_plane; - struct intel_plane_state *plane_state = NULL; - struct intel_crtc_scaler_state *scaler_state = - &crtc_state->scaler_state; - struct drm_atomic_state *drm_state = crtc_state->uapi.state; - struct intel_atomic_state *intel_state = to_intel_atomic_state(drm_state); - int num_scalers_need; - int i; - - num_scalers_need = hweight32(scaler_state->scaler_users); - - /* - * High level flow: - * - staged scaler requests are already in scaler_state->scaler_users - * - check whether staged scaling requests can be supported - * - add planes using scalers that aren't in current transaction - * - assign scalers to requested users - * - as part of plane commit, scalers will be committed - * (i.e., either attached or detached) to respective planes in hw - * - as part of crtc_commit, scaler will be either attached or detached - * to crtc in hw - */ - - /* fail if required scalers > available scalers */ - if (num_scalers_need > intel_crtc->num_scalers){ - drm_dbg_kms(&dev_priv->drm, - "Too many scaling requests %d > %d\n", - num_scalers_need, intel_crtc->num_scalers); - return -EINVAL; - } - - /* walkthrough scaler_users bits and start assigning scalers */ - for (i = 0; i < sizeof(scaler_state->scaler_users) * 8; i++) { - int *scaler_id; - const char *name; - int idx; - - /* skip if scaler not required */ - if (!(scaler_state->scaler_users & (1 << i))) - continue; - - if (i == SKL_CRTC_INDEX) { - name = "CRTC"; - idx = intel_crtc->base.base.id; - - /* panel fitter case: assign as a crtc scaler */ - scaler_id = &scaler_state->scaler_id; - } else { - name = "PLANE"; - - /* plane scaler case: assign as a plane scaler */ - /* find the plane that set the bit as scaler_user */ - plane = drm_state->planes[i].ptr; - - /* - * to enable/disable hq mode, add planes that are using scaler - * into this transaction - */ - if (!plane) { - struct drm_plane_state *state; - - /* - * GLK+ scalers don't have a HQ mode so it - * isn't necessary to change between HQ and dyn mode - * on those platforms. - */ - if (DISPLAY_VER(dev_priv) >= 10) - continue; - - plane = drm_plane_from_index(&dev_priv->drm, i); - state = drm_atomic_get_plane_state(drm_state, plane); - if (IS_ERR(state)) { - drm_dbg_kms(&dev_priv->drm, - "Failed to add [PLANE:%d] to drm_state\n", - plane->base.id); - return PTR_ERR(state); - } - } - - intel_plane = to_intel_plane(plane); - idx = plane->base.id; - - /* plane on different crtc cannot be a scaler user of this crtc */ - if (drm_WARN_ON(&dev_priv->drm, - intel_plane->pipe != intel_crtc->pipe)) - continue; - - plane_state = intel_atomic_get_new_plane_state(intel_state, - intel_plane); - scaler_id = &plane_state->scaler_id; - } - - intel_atomic_setup_scaler(scaler_state, num_scalers_need, - intel_crtc, name, idx, - plane_state, scaler_id); - } - - return 0; -} - struct drm_atomic_state * intel_atomic_state_alloc(struct drm_device *dev) { diff --git a/drivers/gpu/drm/i915/display/intel_atomic.h b/drivers/gpu/drm/i915/display/intel_atomic.h index 1dc439983dd9..e506f6a87344 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.h +++ b/drivers/gpu/drm/i915/display/intel_atomic.h @@ -52,8 +52,4 @@ struct intel_crtc_state * intel_atomic_get_crtc_state(struct drm_atomic_state *state, struct intel_crtc *crtc); -int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, - struct intel_crtc *intel_crtc, - struct intel_crtc_state *crtc_state); - #endif /* __INTEL_ATOMIC_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 1777a12f2f42..fb8d1d63407a 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -6481,6 +6481,17 @@ static int intel_async_flip_check_uapi(struct intel_atomic_state *state, return -EINVAL; } + /* + * FIXME: Bigjoiner+async flip is busted currently. + * Remove this check once the issues are fixed. + */ + if (new_crtc_state->bigjoiner_pipes) { + drm_dbg_kms(&i915->drm, + "[CRTC:%d:%s] async flip disallowed with bigjoiner\n", + crtc->base.base.id, crtc->base.name); + return -EINVAL; + } + for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { if (plane->pipe != crtc->pipe) diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 5970f4149090..4699c2110226 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -3707,7 +3707,7 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp, intel_dp->train_set, crtc_state->lane_count); drm_dp_set_phy_test_pattern(&intel_dp->aux, data, - link_status[DP_DPCD_REV]); + intel_dp->dpcd[DP_DPCD_REV]); } static u8 intel_dp_autotest_phy_pattern(struct intel_dp *intel_dp) diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index 23d854bd73b7..c69a638796c6 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -1176,7 +1176,8 @@ bool intel_fb_needs_pot_stride_remap(const struct intel_framebuffer *fb) { struct drm_i915_private *i915 = to_i915(fb->base.dev); - return IS_ALDERLAKE_P(i915) && fb->base.modifier != DRM_FORMAT_MOD_LINEAR; + return (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) && + intel_fb_uses_dpt(&fb->base); } static int intel_fb_pitch(const struct intel_framebuffer *fb, int color_plane, unsigned int rotation) @@ -1312,9 +1313,11 @@ plane_view_scanout_stride(const struct intel_framebuffer *fb, int color_plane, unsigned int tile_width, unsigned int src_stride_tiles, unsigned int dst_stride_tiles) { + struct drm_i915_private *i915 = to_i915(fb->base.dev); unsigned int stride_tiles; - if (IS_ALDERLAKE_P(to_i915(fb->base.dev))) + if ((IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) && + src_stride_tiles < dst_stride_tiles) stride_tiles = src_stride_tiles; else stride_tiles = dst_stride_tiles; @@ -1520,7 +1523,8 @@ static void intel_fb_view_init(struct drm_i915_private *i915, struct intel_fb_vi memset(view, 0, sizeof(*view)); view->gtt.type = view_type; - if (view_type == I915_GTT_VIEW_REMAPPED && IS_ALDERLAKE_P(i915)) + if (view_type == I915_GTT_VIEW_REMAPPED && + (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14)) view->gtt.remapped.plane_alignment = SZ_2M / PAGE_SIZE; } diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c index 90f42f63128e..0b74f91e865d 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.c +++ b/drivers/gpu/drm/i915/display/skl_scaler.c @@ -337,6 +337,263 @@ int skl_update_scaler_plane(struct intel_crtc_state *crtc_state, return 0; } +static int intel_atomic_setup_scaler(struct intel_crtc_scaler_state *scaler_state, + int num_scalers_need, struct intel_crtc *intel_crtc, + const char *name, int idx, + struct intel_plane_state *plane_state, + int *scaler_id) +{ + struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev); + int j; + u32 mode; + + if (*scaler_id < 0) { + /* find a free scaler */ + for (j = 0; j < intel_crtc->num_scalers; j++) { + if (scaler_state->scalers[j].in_use) + continue; + + *scaler_id = j; + scaler_state->scalers[*scaler_id].in_use = 1; + break; + } + } + + if (drm_WARN(&dev_priv->drm, *scaler_id < 0, + "Cannot find scaler for %s:%d\n", name, idx)) + return -EINVAL; + + /* set scaler mode */ + if (plane_state && plane_state->hw.fb && + plane_state->hw.fb->format->is_yuv && + plane_state->hw.fb->format->num_planes > 1) { + struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + + if (DISPLAY_VER(dev_priv) == 9) { + mode = SKL_PS_SCALER_MODE_NV12; + } else if (icl_is_hdr_plane(dev_priv, plane->id)) { + /* + * On gen11+'s HDR planes we only use the scaler for + * scaling. They have a dedicated chroma upsampler, so + * we don't need the scaler to upsample the UV plane. + */ + mode = PS_SCALER_MODE_NORMAL; + } else { + struct intel_plane *linked = + plane_state->planar_linked_plane; + + mode = PS_SCALER_MODE_PLANAR; + + if (linked) + mode |= PS_PLANE_Y_SEL(linked->id); + } + } else if (DISPLAY_VER(dev_priv) >= 10) { + mode = PS_SCALER_MODE_NORMAL; + } else if (num_scalers_need == 1 && intel_crtc->num_scalers > 1) { + /* + * when only 1 scaler is in use on a pipe with 2 scalers + * scaler 0 operates in high quality (HQ) mode. + * In this case use scaler 0 to take advantage of HQ mode + */ + scaler_state->scalers[*scaler_id].in_use = 0; + *scaler_id = 0; + scaler_state->scalers[0].in_use = 1; + mode = SKL_PS_SCALER_MODE_HQ; + } else { + mode = SKL_PS_SCALER_MODE_DYN; + } + + /* + * FIXME: we should also check the scaler factors for pfit, so + * this shouldn't be tied directly to planes. + */ + if (plane_state && plane_state->hw.fb) { + const struct drm_framebuffer *fb = plane_state->hw.fb; + const struct drm_rect *src = &plane_state->uapi.src; + const struct drm_rect *dst = &plane_state->uapi.dst; + int hscale, vscale, max_vscale, max_hscale; + + /* + * FIXME: When two scalers are needed, but only one of + * them needs to downscale, we should make sure that + * the one that needs downscaling support is assigned + * as the first scaler, so we don't reject downscaling + * unnecessarily. + */ + + if (DISPLAY_VER(dev_priv) >= 14) { + /* + * On versions 14 and up, only the first + * scaler supports a vertical scaling factor + * of more than 1.0, while a horizontal + * scaling factor of 3.0 is supported. + */ + max_hscale = 0x30000 - 1; + if (*scaler_id == 0) + max_vscale = 0x30000 - 1; + else + max_vscale = 0x10000; + + } else if (DISPLAY_VER(dev_priv) >= 10 || + !intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier)) { + max_hscale = 0x30000 - 1; + max_vscale = 0x30000 - 1; + } else { + max_hscale = 0x20000 - 1; + max_vscale = 0x20000 - 1; + } + + /* + * FIXME: We should change the if-else block above to + * support HQ vs dynamic scaler properly. + */ + + /* Check if required scaling is within limits */ + hscale = drm_rect_calc_hscale(src, dst, 1, max_hscale); + vscale = drm_rect_calc_vscale(src, dst, 1, max_vscale); + + if (hscale < 0 || vscale < 0) { + drm_dbg_kms(&dev_priv->drm, + "Scaler %d doesn't support required plane scaling\n", + *scaler_id); + drm_rect_debug_print("src: ", src, true); + drm_rect_debug_print("dst: ", dst, false); + + return -EINVAL; + } + } + + drm_dbg_kms(&dev_priv->drm, "Attached scaler id %u.%u to %s:%d\n", + intel_crtc->pipe, *scaler_id, name, idx); + scaler_state->scalers[*scaler_id].mode = mode; + + return 0; +} + +/** + * intel_atomic_setup_scalers() - setup scalers for crtc per staged requests + * @dev_priv: i915 device + * @intel_crtc: intel crtc + * @crtc_state: incoming crtc_state to validate and setup scalers + * + * This function sets up scalers based on staged scaling requests for + * a @crtc and its planes. It is called from crtc level check path. If request + * is a supportable request, it attaches scalers to requested planes and crtc. + * + * This function takes into account the current scaler(s) in use by any planes + * not being part of this atomic state + * + * Returns: + * 0 - scalers were setup successfully + * error code - otherwise + */ +int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, + struct intel_crtc *intel_crtc, + struct intel_crtc_state *crtc_state) +{ + struct drm_plane *plane = NULL; + struct intel_plane *intel_plane; + struct intel_crtc_scaler_state *scaler_state = + &crtc_state->scaler_state; + struct drm_atomic_state *drm_state = crtc_state->uapi.state; + struct intel_atomic_state *intel_state = to_intel_atomic_state(drm_state); + int num_scalers_need; + int i; + + num_scalers_need = hweight32(scaler_state->scaler_users); + + /* + * High level flow: + * - staged scaler requests are already in scaler_state->scaler_users + * - check whether staged scaling requests can be supported + * - add planes using scalers that aren't in current transaction + * - assign scalers to requested users + * - as part of plane commit, scalers will be committed + * (i.e., either attached or detached) to respective planes in hw + * - as part of crtc_commit, scaler will be either attached or detached + * to crtc in hw + */ + + /* fail if required scalers > available scalers */ + if (num_scalers_need > intel_crtc->num_scalers) { + drm_dbg_kms(&dev_priv->drm, + "Too many scaling requests %d > %d\n", + num_scalers_need, intel_crtc->num_scalers); + return -EINVAL; + } + + /* walkthrough scaler_users bits and start assigning scalers */ + for (i = 0; i < sizeof(scaler_state->scaler_users) * 8; i++) { + struct intel_plane_state *plane_state = NULL; + int *scaler_id; + const char *name; + int idx, ret; + + /* skip if scaler not required */ + if (!(scaler_state->scaler_users & (1 << i))) + continue; + + if (i == SKL_CRTC_INDEX) { + name = "CRTC"; + idx = intel_crtc->base.base.id; + + /* panel fitter case: assign as a crtc scaler */ + scaler_id = &scaler_state->scaler_id; + } else { + name = "PLANE"; + + /* plane scaler case: assign as a plane scaler */ + /* find the plane that set the bit as scaler_user */ + plane = drm_state->planes[i].ptr; + + /* + * to enable/disable hq mode, add planes that are using scaler + * into this transaction + */ + if (!plane) { + struct drm_plane_state *state; + + /* + * GLK+ scalers don't have a HQ mode so it + * isn't necessary to change between HQ and dyn mode + * on those platforms. + */ + if (DISPLAY_VER(dev_priv) >= 10) + continue; + + plane = drm_plane_from_index(&dev_priv->drm, i); + state = drm_atomic_get_plane_state(drm_state, plane); + if (IS_ERR(state)) { + drm_dbg_kms(&dev_priv->drm, + "Failed to add [PLANE:%d] to drm_state\n", + plane->base.id); + return PTR_ERR(state); + } + } + + intel_plane = to_intel_plane(plane); + idx = plane->base.id; + + /* plane on different crtc cannot be a scaler user of this crtc */ + if (drm_WARN_ON(&dev_priv->drm, + intel_plane->pipe != intel_crtc->pipe)) + continue; + + plane_state = intel_atomic_get_new_plane_state(intel_state, + intel_plane); + scaler_id = &plane_state->scaler_id; + } + + ret = intel_atomic_setup_scaler(scaler_state, num_scalers_need, + intel_crtc, name, idx, + plane_state, scaler_id); + if (ret < 0) + return ret; + } + + return 0; +} + static int glk_coef_tap(int i) { return i % 7; diff --git a/drivers/gpu/drm/i915/display/skl_scaler.h b/drivers/gpu/drm/i915/display/skl_scaler.h index 0097d5d08e10..f040f6ac061f 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.h +++ b/drivers/gpu/drm/i915/display/skl_scaler.h @@ -8,17 +8,22 @@ #include <linux/types.h> enum drm_scaling_filter; +enum pipe; struct drm_i915_private; +struct intel_crtc; struct intel_crtc_state; -struct intel_plane_state; struct intel_plane; -enum pipe; +struct intel_plane_state; int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state); int skl_update_scaler_plane(struct intel_crtc_state *crtc_state, struct intel_plane_state *plane_state); +int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, + struct intel_crtc *intel_crtc, + struct intel_crtc_state *crtc_state); + void skl_pfit_enable(const struct intel_crtc_state *crtc_state); void skl_program_plane_scaler(struct intel_plane *plane, @@ -26,4 +31,5 @@ void skl_program_plane_scaler(struct intel_plane *plane, const struct intel_plane_state *plane_state); void skl_detach_scalers(const struct intel_crtc_state *crtc_state); void skl_scaler_disable(const struct intel_crtc_state *old_crtc_state); + #endif diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index daac2050d77d..6f531bb61f7e 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -2844,8 +2844,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset, for (i = start; i < end; i += 4) { p = intel_gvt_find_mmio_info(gvt, i); if (p) { - WARN(1, "dup mmio definition offset %x\n", - info->offset); + WARN(1, "dup mmio definition offset %x\n", i); /* We return -EEXIST here to make GVT-g load fail. * So duplicated MMIO can be found as soon as diff --git a/drivers/gpu/drm/mediatek/mtk_disp_merge.c b/drivers/gpu/drm/mediatek/mtk_disp_merge.c index 6428b6203ffe..211140e87568 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_merge.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_merge.c @@ -104,7 +104,7 @@ void mtk_merge_stop_cmdq(struct device *dev, struct cmdq_pkt *cmdq_pkt) mtk_ddp_write(cmdq_pkt, 0, &priv->cmdq_reg, priv->regs, DISP_REG_MERGE_CTRL); - if (priv->async_clk) + if (!cmdq_pkt && priv->async_clk) reset_control_reset(priv->reset_ctl); } diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index 2c850b6d945b..519e23a2a017 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -2669,3 +2669,4 @@ MODULE_AUTHOR("Markus Schneider-Pargmann <msp@baylibre.com>"); MODULE_AUTHOR("Bo-Chen Chen <rex-bc.chen@mediatek.com>"); MODULE_DESCRIPTION("MediaTek DisplayPort Driver"); MODULE_LICENSE("GPL"); +MODULE_SOFTDEP("pre: phy_mtk_dp"); diff --git a/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c b/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c index eecfa98ff52e..b288bb6eeecc 100644 --- a/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c +++ b/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c @@ -223,8 +223,7 @@ int mtk_mdp_rdma_clk_enable(struct device *dev) { struct mtk_mdp_rdma *rdma = dev_get_drvdata(dev); - clk_prepare_enable(rdma->clk); - return 0; + return clk_prepare_enable(rdma->clk); } void mtk_mdp_rdma_clk_disable(struct device *dev) diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index f0c2349404b4..aebd09e2d408 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -390,6 +390,11 @@ void mgag200_primary_plane_helper_atomic_disable(struct drm_plane *plane, .destroy = drm_plane_cleanup, \ DRM_GEM_SHADOW_PLANE_FUNCS +void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, const struct drm_format_info *format); +void mgag200_crtc_set_gamma(struct mga_device *mdev, + const struct drm_format_info *format, + struct drm_color_lut *lut); + enum drm_mode_status mgag200_crtc_helper_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode); int mgag200_crtc_helper_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *new_state); diff --git a/drivers/gpu/drm/mgag200/mgag200_g200er.c b/drivers/gpu/drm/mgag200/mgag200_g200er.c index bce267e0f7de..8d4538b71047 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200er.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200er.c @@ -202,6 +202,11 @@ static void mgag200_g200er_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200er_reset_tagfifo(mdev); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_g200ev.c b/drivers/gpu/drm/mgag200/mgag200_g200ev.c index ac957f42abe1..56e6f986bff3 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200ev.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200ev.c @@ -203,6 +203,11 @@ static void mgag200_g200ev_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200ev_set_hiprilvl(mdev); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_g200se.c b/drivers/gpu/drm/mgag200/mgag200_g200se.c index bd6e573c9a1a..ff2b3c6622e7 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200se.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200se.c @@ -334,6 +334,11 @@ static void mgag200_g200se_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200se_set_hiprilvl(mdev, adjusted_mode, format); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index ae90b260312a..554adf05e073 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -28,8 +28,8 @@ * This file contains setup code for the CRTC. */ -static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, - const struct drm_format_info *format) +void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, + const struct drm_format_info *format) { int i; @@ -65,9 +65,9 @@ static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, } } -static void mgag200_crtc_set_gamma(struct mga_device *mdev, - const struct drm_format_info *format, - struct drm_color_lut *lut) +void mgag200_crtc_set_gamma(struct mga_device *mdev, + const struct drm_format_info *format, + struct drm_color_lut *lut) { int i; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 6c0ffe8e4adb..5a5821e59dc1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2014-2021 The Linux Foundation. All rights reserved. * Copyright (C) 2013 Red Hat * Author: Rob Clark <robdclark@gmail.com> @@ -124,7 +124,7 @@ static void dpu_crtc_setup_lm_misr(struct dpu_crtc_state *crtc_state) continue; /* Calculate MISR over 1 frame */ - m->hw_lm->ops.setup_misr(m->hw_lm, true, 1); + m->hw_lm->ops.setup_misr(m->hw_lm); } } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 547f9f2b9fcb..25245ef386db 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2013 Red Hat * Copyright (c) 2014-2018, 2020-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * * Author: Rob Clark <robdclark@gmail.com> */ @@ -38,6 +38,9 @@ #define DPU_ERROR_ENC(e, fmt, ...) DPU_ERROR("enc%d " fmt,\ (e) ? (e)->base.base.id : -1, ##__VA_ARGS__) +#define DPU_ERROR_ENC_RATELIMITED(e, fmt, ...) DPU_ERROR_RATELIMITED("enc%d " fmt,\ + (e) ? (e)->base.base.id : -1, ##__VA_ARGS__) + /* * Two to anticipate panels that can do cmd/vid dynamic switching * plan is to create all possible physical encoder types, and switch between @@ -257,7 +260,7 @@ void dpu_encoder_setup_misr(const struct drm_encoder *drm_enc) if (!phys->hw_intf || !phys->hw_intf->ops.setup_misr) continue; - phys->hw_intf->ops.setup_misr(phys->hw_intf, true, 1); + phys->hw_intf->ops.setup_misr(phys->hw_intf); } } @@ -2050,7 +2053,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) } /* reset the merge 3D HW block */ - if (phys_enc->hw_pp->merge_3d) { + if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) { phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d, BLEND_3D_NONE); if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d) @@ -2066,7 +2069,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) if (phys_enc->hw_wb) intf_cfg.wb = phys_enc->hw_wb->idx; - if (phys_enc->hw_pp->merge_3d) + if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx; if (ctl->ops.reset_intf_cfg) @@ -2385,7 +2388,7 @@ static void dpu_encoder_frame_done_timeout(struct timer_list *t) return; } - DPU_ERROR_ENC(dpu_enc, "frame done timeout\n"); + DPU_ERROR_ENC_RATELIMITED(dpu_enc, "frame done timeout\n"); event = DPU_ENCODER_FRAME_EVENT_ERROR; trace_dpu_enc_frame_done_timeout(DRMID(drm_enc), event); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index b9dddf576c02..384558d2f960 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. */ @@ -322,9 +322,9 @@ static u32 dpu_hw_intf_get_line_count(struct dpu_hw_intf *intf) return DPU_REG_READ(c, INTF_LINE_COUNT); } -static void dpu_hw_intf_setup_misr(struct dpu_hw_intf *intf, bool enable, u32 frame_count) +static void dpu_hw_intf_setup_misr(struct dpu_hw_intf *intf) { - dpu_hw_setup_misr(&intf->hw, INTF_MISR_CTRL, enable, frame_count); + dpu_hw_setup_misr(&intf->hw, INTF_MISR_CTRL, 0x1); } static int dpu_hw_intf_collect_misr(struct dpu_hw_intf *intf, u32 *misr_value) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h index 643dd10bc030..e75339b96a1d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. */ @@ -80,7 +80,7 @@ struct dpu_hw_intf_ops { void (*bind_pingpong_blk)(struct dpu_hw_intf *intf, bool enable, const enum dpu_pingpong pp); - void (*setup_misr)(struct dpu_hw_intf *intf, bool enable, u32 frame_count); + void (*setup_misr)(struct dpu_hw_intf *intf); int (*collect_misr)(struct dpu_hw_intf *intf, u32 *misr_value); }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c index f5120ea91ede..cc04fb979fb5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved. */ @@ -99,9 +99,9 @@ static void dpu_hw_lm_setup_border_color(struct dpu_hw_mixer *ctx, } } -static void dpu_hw_lm_setup_misr(struct dpu_hw_mixer *ctx, bool enable, u32 frame_count) +static void dpu_hw_lm_setup_misr(struct dpu_hw_mixer *ctx) { - dpu_hw_setup_misr(&ctx->hw, LM_MISR_CTRL, enable, frame_count); + dpu_hw_setup_misr(&ctx->hw, LM_MISR_CTRL, 0x0); } static int dpu_hw_lm_collect_misr(struct dpu_hw_mixer *ctx, u32 *misr_value) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h index 652ddfdedec3..0a050eb247b9 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved. */ @@ -57,7 +58,7 @@ struct dpu_hw_lm_ops { /** * setup_misr: Enable/disable MISR */ - void (*setup_misr)(struct dpu_hw_mixer *ctx, bool enable, u32 frame_count); + void (*setup_misr)(struct dpu_hw_mixer *ctx); /** * collect_misr: Read MISR signature diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c index 8062228eada6..1b7439ae686a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. */ #define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ @@ -450,9 +450,11 @@ u64 _dpu_hw_get_qos_lut(const struct dpu_qos_lut_tbl *tbl, return 0; } +/* + * note: Aside from encoders, input_sel should be set to 0x0 by default + */ void dpu_hw_setup_misr(struct dpu_hw_blk_reg_map *c, - u32 misr_ctrl_offset, - bool enable, u32 frame_count) + u32 misr_ctrl_offset, u8 input_sel) { u32 config = 0; @@ -461,15 +463,9 @@ void dpu_hw_setup_misr(struct dpu_hw_blk_reg_map *c, /* Clear old MISR value (in case it's read before a new value is calculated)*/ wmb(); - if (enable) { - config = (frame_count & MISR_FRAME_COUNT_MASK) | - MISR_CTRL_ENABLE | MISR_CTRL_FREE_RUN_MASK; - - DPU_REG_WRITE(c, misr_ctrl_offset, config); - } else { - DPU_REG_WRITE(c, misr_ctrl_offset, 0); - } - + config = MISR_FRAME_COUNT | MISR_CTRL_ENABLE | MISR_CTRL_FREE_RUN_MASK | + ((input_sel & 0xF) << 24); + DPU_REG_WRITE(c, misr_ctrl_offset, config); } int dpu_hw_collect_misr(struct dpu_hw_blk_reg_map *c, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h index 27f4c39e35ab..4ae2a434372c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved. */ @@ -13,7 +13,7 @@ #include "dpu_hw_catalog.h" #define REG_MASK(n) ((BIT(n)) - 1) -#define MISR_FRAME_COUNT_MASK 0xFF +#define MISR_FRAME_COUNT 0x1 #define MISR_CTRL_ENABLE BIT(8) #define MISR_CTRL_STATUS BIT(9) #define MISR_CTRL_STATUS_CLEAR BIT(10) @@ -350,9 +350,7 @@ u64 _dpu_hw_get_qos_lut(const struct dpu_qos_lut_tbl *tbl, u32 total_fl); void dpu_hw_setup_misr(struct dpu_hw_blk_reg_map *c, - u32 misr_ctrl_offset, - bool enable, - u32 frame_count); + u32 misr_ctrl_offset, u8 input_sel); int dpu_hw_collect_misr(struct dpu_hw_blk_reg_map *c, u32 misr_ctrl_offset, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c index a3e413d27717..63dc2ee446d4 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c @@ -105,6 +105,9 @@ static void dpu_hw_wb_setup_format(struct dpu_hw_wb *ctx, dst_format |= BIT(14); /* DST_ALPHA_X */ } + if (DPU_FORMAT_IS_YUV(fmt)) + dst_format |= BIT(15); + pattern = (fmt->element[3] << 24) | (fmt->element[2] << 16) | (fmt->element[1] << 8) | diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index ed80ed6784ee..bb35aa5f5709 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -51,6 +51,7 @@ } while (0) #define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__) +#define DPU_ERROR_RATELIMITED(fmt, ...) pr_err_ratelimited("[dpu error]" fmt, ##__VA_ARGS__) /** * ktime_compare_safe - compare two ktime structures diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c index 169f9de4a12a..3100957225a7 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c @@ -269,6 +269,7 @@ static void mdp4_crtc_atomic_disable(struct drm_crtc *crtc, { struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); struct mdp4_kms *mdp4_kms = get_kms(crtc); + unsigned long flags; DBG("%s", mdp4_crtc->name); @@ -281,6 +282,14 @@ static void mdp4_crtc_atomic_disable(struct drm_crtc *crtc, mdp_irq_unregister(&mdp4_kms->base, &mdp4_crtc->err); mdp4_disable(mdp4_kms); + if (crtc->state->event && !crtc->state->active) { + WARN_ON(mdp4_crtc->event); + spin_lock_irqsave(&mdp4_kms->dev->event_lock, flags); + drm_crtc_send_vblank_event(crtc, crtc->state->event); + crtc->state->event = NULL; + spin_unlock_irqrestore(&mdp4_kms->dev->event_lock, flags); + } + mdp4_crtc->enabled = false; } diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 103eef9f059a..b20701893e5b 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -133,11 +133,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl) tbd = dp_link_get_test_bits_depth(ctrl->link, ctrl->panel->dp_mode.bpp); - if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) { - pr_debug("BIT_DEPTH not set. Configure default\n"); - tbd = DP_TEST_BIT_DEPTH_8; - } - config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT; /* Num of Lanes */ diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index cb66d1126ea9..ceb382fa56d5 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -7,6 +7,7 @@ #include <drm/drm_print.h> +#include "dp_reg.h" #include "dp_link.h" #include "dp_panel.h" @@ -1075,7 +1076,7 @@ int dp_link_process_request(struct dp_link *dp_link) int dp_link_get_colorimetry_config(struct dp_link *dp_link) { - u32 cc; + u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB; struct dp_link_private *link; if (!dp_link) { @@ -1089,10 +1090,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link) * Unless a video pattern CTS test is ongoing, use RGB_VESA * Only RGB_VESA and RGB_CEA supported for now */ - if (dp_link_is_video_pattern_requested(link)) - cc = link->dp_link.test_video.test_dyn_range; - else - cc = DP_TEST_DYNAMIC_RANGE_VESA; + if (dp_link_is_video_pattern_requested(link)) { + if (link->dp_link.test_video.test_dyn_range & + DP_TEST_DYNAMIC_RANGE_CEA) + cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB; + } return cc; } @@ -1172,6 +1174,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link) u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp) { u32 tbd; + struct dp_link_private *link; + + link = container_of(dp_link, struct dp_link_private, dp_link); /* * Few simplistic rules and assumptions made here: @@ -1189,12 +1194,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp) tbd = DP_TEST_BIT_DEPTH_10; break; default: - tbd = DP_TEST_BIT_DEPTH_UNKNOWN; + drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n", + bpp); + tbd = DP_TEST_BIT_DEPTH_8; break; } - if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN) - tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT); + tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT); return tbd; } diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h index 268602803d9a..176a503ece9c 100644 --- a/drivers/gpu/drm/msm/dp/dp_reg.h +++ b/drivers/gpu/drm/msm/dp/dp_reg.h @@ -129,6 +129,9 @@ #define DP_MISC0_COLORIMETRY_CFG_SHIFT (0x00000001) #define DP_MISC0_TEST_BITS_DEPTH_SHIFT (0x00000005) +#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB (0) +#define DP_MISC0_COLORIMERY_CFG_CEA_RGB (0x04) + #define REG_DP_VALID_BOUNDARY (0x00000030) #define REG_DP_VALID_BOUNDARY_2 (0x00000034) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 7fc0975cb869..c0bcf020ef66 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -512,7 +512,9 @@ static int dsi_phy_enable_resource(struct msm_dsi_phy *phy) struct device *dev = &phy->pdev->dev; int ret; - pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); + if (ret) + return ret; ret = clk_prepare_enable(phy->ahb_clk); if (ret) { @@ -671,6 +673,10 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(phy->ahb_clk), "Unable to get ahb clk\n"); + ret = devm_pm_runtime_enable(&pdev->dev); + if (ret) + return ret; + /* PLL init will call into clk_register which requires * register access, so we need to enable power and ahb clock. */ diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index d12ba47b37c4..0de3612135e9 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -21,6 +21,8 @@ struct msm_iommu_pagetable { struct msm_mmu base; struct msm_mmu *parent; struct io_pgtable_ops *pgtbl_ops; + const struct iommu_flush_ops *tlb; + struct device *iommu_dev; unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ phys_addr_t ttbr; u32 asid; @@ -194,11 +196,33 @@ static const struct msm_mmu_funcs pagetable_funcs = { static void msm_iommu_tlb_flush_all(void *cookie) { + struct msm_iommu_pagetable *pagetable = cookie; + struct adreno_smmu_priv *adreno_smmu; + + if (!pm_runtime_get_if_in_use(pagetable->iommu_dev)) + return; + + adreno_smmu = dev_get_drvdata(pagetable->parent->dev); + + pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie); + + pm_runtime_put_autosuspend(pagetable->iommu_dev); } static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule, void *cookie) { + struct msm_iommu_pagetable *pagetable = cookie; + struct adreno_smmu_priv *adreno_smmu; + + if (!pm_runtime_get_if_in_use(pagetable->iommu_dev)) + return; + + adreno_smmu = dev_get_drvdata(pagetable->parent->dev); + + pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie); + + pm_runtime_put_autosuspend(pagetable->iommu_dev); } static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, @@ -206,7 +230,7 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, { } -static const struct iommu_flush_ops null_tlb_ops = { +static const struct iommu_flush_ops tlb_ops = { .tlb_flush_all = msm_iommu_tlb_flush_all, .tlb_flush_walk = msm_iommu_tlb_flush_walk, .tlb_add_page = msm_iommu_tlb_add_page, @@ -254,10 +278,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* The incoming cfg will have the TTBR1 quirk enabled */ ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1; - ttbr0_cfg.tlb = &null_tlb_ops; + ttbr0_cfg.tlb = &tlb_ops; pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1, - &ttbr0_cfg, iommu->domain); + &ttbr0_cfg, pagetable); if (!pagetable->pgtbl_ops) { kfree(pagetable); @@ -282,6 +306,8 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* Needed later for TLB flush */ pagetable->parent = parent; + pagetable->tlb = ttbr1_cfg->tlb; + pagetable->iommu_dev = ttbr1_cfg->iommu_dev; pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap; pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr; diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 31a5b81ee9fc..be6674fb1af7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -997,7 +997,7 @@ nouveau_svm_fault_buffer_ctor(struct nouveau_svm *svm, s32 oclass, int id) if (ret) return ret; - buffer->fault = kvcalloc(sizeof(*buffer->fault), buffer->entries, GFP_KERNEL); + buffer->fault = kvcalloc(buffer->entries, sizeof(*buffer->fault), GFP_KERNEL); if (!buffer->fault) return -ENOMEM; diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c index 67d6619fcd5e..29b5dedf6db8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c @@ -108,6 +108,9 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm, } else { ret = nvif_vmm_get(&vmm->vmm, PTES, false, mem->mem.page, 0, mem->mem.size, &tmp); + if (ret) + goto done; + vma->addr = tmp.addr; } diff --git a/drivers/gpu/drm/nouveau/nv04_fence.c b/drivers/gpu/drm/nouveau/nv04_fence.c index 5b71a5a5cd85..cdbc75e3d1f6 100644 --- a/drivers/gpu/drm/nouveau/nv04_fence.c +++ b/drivers/gpu/drm/nouveau/nv04_fence.c @@ -39,7 +39,7 @@ struct nv04_fence_priv { static int nv04_fence_emit(struct nouveau_fence *fence) { - struct nvif_push *push = fence->channel->chan.push; + struct nvif_push *push = unrcu_pointer(fence->channel)->chan.push; int ret = PUSH_WAIT(push, 2); if (ret == 0) { PUSH_NVSQ(push, NV_SW, 0x0150, fence->base.seqno); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c index 19188683c8fc..8c2bf1c16f2a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c @@ -154,11 +154,17 @@ shadow_fw_init(struct nvkm_bios *bios, const char *name) return (void *)fw; } +static void +shadow_fw_release(void *fw) +{ + release_firmware(fw); +} + static const struct nvbios_source shadow_fw = { .name = "firmware", .init = shadow_fw_init, - .fini = (void(*)(void *))release_firmware, + .fini = shadow_fw_release, .read = shadow_fw_read, .rw = false, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c index 6cb5eefa45e9..5a08458fe1b7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c @@ -31,7 +31,7 @@ tu102_vmm_flush(struct nvkm_vmm *vmm, int depth) type |= 0x00000001; /* PAGE_ALL */ if (atomic_read(&vmm->engref[NVKM_SUBDEV_BAR])) - type |= 0x00000004; /* HUB_ONLY */ + type |= 0x00000006; /* HUB_ONLY | ALL PDB (hack) */ mutex_lock(&vmm->mmu->mutex); diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c index eaf67b9e5f12..5b6d1668f405 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.c +++ b/drivers/gpu/drm/omapdrm/omap_drv.c @@ -68,7 +68,6 @@ static void omap_atomic_commit_tail(struct drm_atomic_state *old_state) { struct drm_device *dev = old_state->dev; struct omap_drm_private *priv = dev->dev_private; - bool fence_cookie = dma_fence_begin_signalling(); dispc_runtime_get(priv->dispc); @@ -91,6 +90,8 @@ static void omap_atomic_commit_tail(struct drm_atomic_state *old_state) omap_atomic_wait_for_completion(dev, old_state); drm_atomic_helper_commit_planes(dev, old_state, 0); + + drm_atomic_helper_commit_hw_done(old_state); } else { /* * OMAP3 DSS seems to have issues with the work-around above, @@ -100,11 +101,9 @@ static void omap_atomic_commit_tail(struct drm_atomic_state *old_state) drm_atomic_helper_commit_planes(dev, old_state, 0); drm_atomic_helper_commit_modeset_enables(dev, old_state); - } - drm_atomic_helper_commit_hw_done(old_state); - - dma_fence_end_signalling(fence_cookie); + drm_atomic_helper_commit_hw_done(old_state); + } /* * Wait for completion of the page flips to ensure that old buffers diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index 8542e391d3f4..d9d15ed41e0f 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -207,6 +207,9 @@ struct edp_panel_entry { /** @name: Name of this panel (for printing to logs). */ const char *name; + + /** @override_edid_mode: Override the mode obtained by edid. */ + const struct drm_display_mode *override_edid_mode; }; struct panel_edp { @@ -305,6 +308,24 @@ static unsigned int panel_edp_get_display_modes(struct panel_edp *panel, return num; } +static int panel_edp_override_edid_mode(struct panel_edp *panel, + struct drm_connector *connector, + const struct drm_display_mode *override_mode) +{ + struct drm_display_mode *mode; + + mode = drm_mode_duplicate(connector->dev, override_mode); + if (!mode) { + dev_err(panel->base.dev, "failed to add additional mode\n"); + return 0; + } + + mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; + drm_mode_set_name(mode); + drm_mode_probed_add(connector, mode); + return 1; +} + static int panel_edp_get_non_edid_modes(struct panel_edp *panel, struct drm_connector *connector) { @@ -575,6 +596,9 @@ static int panel_edp_get_modes(struct drm_panel *panel, { struct panel_edp *p = to_panel_edp(panel); int num = 0; + bool has_override_edid_mode = p->detected_panel && + p->detected_panel != ERR_PTR(-EINVAL) && + p->detected_panel->override_edid_mode; /* probe EDID if a DDC bus is available */ if (p->ddc) { @@ -582,9 +606,18 @@ static int panel_edp_get_modes(struct drm_panel *panel, if (!p->edid) p->edid = drm_get_edid(connector, p->ddc); - - if (p->edid) - num += drm_add_edid_modes(connector, p->edid); + if (p->edid) { + if (has_override_edid_mode) { + /* + * override_edid_mode is specified. Use + * override_edid_mode instead of from edid. + */ + num += panel_edp_override_edid_mode(p, connector, + p->detected_panel->override_edid_mode); + } else { + num += drm_add_edid_modes(connector, p->edid); + } + } pm_runtime_mark_last_busy(panel->dev); pm_runtime_put_autosuspend(panel->dev); @@ -984,6 +1017,8 @@ static const struct panel_desc auo_b116xak01 = { }, .delay = { .hpd_absent = 200, + .unprepare = 500, + .enable = 50, }, }; @@ -1902,6 +1937,15 @@ static const struct panel_delay delay_200_500_e200 = { .delay = _delay \ } +#define EDP_PANEL_ENTRY2(vend_chr_0, vend_chr_1, vend_chr_2, product_id, _delay, _name, _mode) \ +{ \ + .name = _name, \ + .panel_id = drm_edid_encode_panel_id(vend_chr_0, vend_chr_1, vend_chr_2, \ + product_id), \ + .delay = _delay, \ + .override_edid_mode = _mode \ +} + /* * This table is used to figure out power sequencing delays for panels that * are detected by EDID. Entries here may point to entries in the @@ -1913,7 +1957,7 @@ static const struct edp_panel_entry edp_panels[] = { EDP_PANEL_ENTRY('A', 'U', 'O', 0x1062, &delay_200_500_e50, "B120XAN01.0"), EDP_PANEL_ENTRY('A', 'U', 'O', 0x1e9b, &delay_200_500_e50, "B133UAN02.1"), EDP_PANEL_ENTRY('A', 'U', 'O', 0x1ea5, &delay_200_500_e50, "B116XAK01.6"), - EDP_PANEL_ENTRY('A', 'U', 'O', 0x405c, &auo_b116xak01.delay, "B116XAK01"), + EDP_PANEL_ENTRY('A', 'U', 'O', 0x405c, &auo_b116xak01.delay, "B116XAK01.0"), EDP_PANEL_ENTRY('A', 'U', 'O', 0x615c, &delay_200_500_e50, "B116XAN06.1"), EDP_PANEL_ENTRY('A', 'U', 'O', 0x8594, &delay_200_500_e50, "B133UAN01.0"), diff --git a/drivers/gpu/drm/panel/panel-elida-kd35t133.c b/drivers/gpu/drm/panel/panel-elida-kd35t133.c index eee714cf3f49..3a7fc3ca6a6f 100644 --- a/drivers/gpu/drm/panel/panel-elida-kd35t133.c +++ b/drivers/gpu/drm/panel/panel-elida-kd35t133.c @@ -112,6 +112,8 @@ static int kd35t133_unprepare(struct drm_panel *panel) return ret; } + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + regulator_disable(ctx->iovcc); regulator_disable(ctx->vdd); diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index f772b6eb6bf8..68ff69e8272a 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -3726,6 +3726,7 @@ static const struct panel_desc tianma_tm070jdhg30 = { }, .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, .connector_type = DRM_MODE_CONNECTOR_LVDS, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, }; static const struct panel_desc tianma_tm070jvhg33 = { @@ -3738,6 +3739,7 @@ static const struct panel_desc tianma_tm070jvhg33 = { }, .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, .connector_type = DRM_MODE_CONNECTOR_LVDS, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, }; static const struct display_timing tianma_tm070rvhg71_timing = { diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c index 225b9884f61a..54b28992db5d 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c @@ -288,7 +288,7 @@ static void st7701_init_sequence(struct st7701 *st7701) FIELD_PREP(DSI_CMD2_BK1_PWRCTRL2_AVDD_MASK, DIV_ROUND_CLOSEST(desc->avdd_mv - 6200, 200)) | FIELD_PREP(DSI_CMD2_BK1_PWRCTRL2_AVCL_MASK, - DIV_ROUND_CLOSEST(-4400 + desc->avcl_mv, 200))); + DIV_ROUND_CLOSEST(-4400 - desc->avcl_mv, 200))); /* T2D = 0.2us * T2D[3:0] */ ST7701_DSI(st7701, DSI_CMD2_BK1_SPD1, diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index 6452e4e900dd..55d243048516 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -71,7 +71,12 @@ int panfrost_gpu_soft_reset(struct panfrost_device *pfdev) } gpu_write(pfdev, GPU_INT_CLEAR, GPU_IRQ_MASK_ALL); - gpu_write(pfdev, GPU_INT_MASK, GPU_IRQ_MASK_ALL); + + /* Only enable the interrupts we care about */ + gpu_write(pfdev, GPU_INT_MASK, + GPU_IRQ_MASK_ERROR | + GPU_IRQ_PERFCNT_SAMPLE_COMPLETED | + GPU_IRQ_CLEAN_CACHES_COMPLETED); return 0; } @@ -313,28 +318,38 @@ static void panfrost_gpu_init_features(struct panfrost_device *pfdev) pfdev->features.shader_present, pfdev->features.l2_present); } +static u64 panfrost_get_core_mask(struct panfrost_device *pfdev) +{ + u64 core_mask; + + if (pfdev->features.l2_present == 1) + return U64_MAX; + + /* + * Only support one core group now. + * ~(l2_present - 1) unsets all bits in l2_present except + * the bottom bit. (l2_present - 2) has all the bits in + * the first core group set. AND them together to generate + * a mask of cores in the first core group. + */ + core_mask = ~(pfdev->features.l2_present - 1) & + (pfdev->features.l2_present - 2); + dev_info_once(pfdev->dev, "using only 1st core group (%lu cores from %lu)\n", + hweight64(core_mask), + hweight64(pfdev->features.shader_present)); + + return core_mask; +} + void panfrost_gpu_power_on(struct panfrost_device *pfdev) { int ret; u32 val; - u64 core_mask = U64_MAX; + u64 core_mask; panfrost_gpu_init_quirks(pfdev); + core_mask = panfrost_get_core_mask(pfdev); - if (pfdev->features.l2_present != 1) { - /* - * Only support one core group now. - * ~(l2_present - 1) unsets all bits in l2_present except - * the bottom bit. (l2_present - 2) has all the bits in - * the first core group set. AND them together to generate - * a mask of cores in the first core group. - */ - core_mask = ~(pfdev->features.l2_present - 1) & - (pfdev->features.l2_present - 2); - dev_info_once(pfdev->dev, "using only 1st core group (%lu cores from %lu)\n", - hweight64(core_mask), - hweight64(pfdev->features.shader_present)); - } gpu_write(pfdev, L2_PWRON_LO, pfdev->features.l2_present & core_mask); ret = readl_relaxed_poll_timeout(pfdev->iomem + L2_READY_LO, val, val == (pfdev->features.l2_present & core_mask), @@ -359,9 +374,26 @@ void panfrost_gpu_power_on(struct panfrost_device *pfdev) void panfrost_gpu_power_off(struct panfrost_device *pfdev) { - gpu_write(pfdev, TILER_PWROFF_LO, 0); - gpu_write(pfdev, SHADER_PWROFF_LO, 0); - gpu_write(pfdev, L2_PWROFF_LO, 0); + int ret; + u32 val; + + gpu_write(pfdev, SHADER_PWROFF_LO, pfdev->features.shader_present); + ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_PWRTRANS_LO, + val, !val, 1, 1000); + if (ret) + dev_err(pfdev->dev, "shader power transition timeout"); + + gpu_write(pfdev, TILER_PWROFF_LO, pfdev->features.tiler_present); + ret = readl_relaxed_poll_timeout(pfdev->iomem + TILER_PWRTRANS_LO, + val, !val, 1, 1000); + if (ret) + dev_err(pfdev->dev, "tiler power transition timeout"); + + gpu_write(pfdev, L2_PWROFF_LO, pfdev->features.l2_present); + ret = readl_poll_timeout(pfdev->iomem + L2_PWRTRANS_LO, + val, !val, 0, 1000); + if (ret) + dev_err(pfdev->dev, "l2 power transition timeout"); } int panfrost_gpu_init(struct panfrost_device *pfdev) diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index d4f09ecc3d22..f336b5b3b11f 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -2321,7 +2321,7 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) switch (prim_walk) { case 1: for (i = 0; i < track->num_arrays; i++) { - size = track->arrays[i].esize * track->max_indx * 4; + size = track->arrays[i].esize * track->max_indx * 4UL; if (track->arrays[i].robj == NULL) { DRM_ERROR("(PW %u) Vertex array %u no buffer " "bound\n", prim_walk, i); @@ -2340,7 +2340,7 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) break; case 2: for (i = 0; i < track->num_arrays; i++) { - size = track->arrays[i].esize * (nverts - 1) * 4; + size = track->arrays[i].esize * (nverts - 1) * 4UL; if (track->arrays[i].robj == NULL) { DRM_ERROR("(PW %u) Vertex array %u no buffer " "bound\n", prim_walk, i); diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 638f861af80f..6cf54a747749 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -1275,7 +1275,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) return -EINVAL; } tmp = (reg - CB_COLOR0_BASE) / 4; - track->cb_color_bo_offset[tmp] = radeon_get_ib_value(p, idx) << 8; + track->cb_color_bo_offset[tmp] = (u64)radeon_get_ib_value(p, idx) << 8; ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); track->cb_color_base_last[tmp] = ib[idx]; track->cb_color_bo[tmp] = reloc->robj; @@ -1302,7 +1302,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) "0x%04X\n", reg); return -EINVAL; } - track->htile_offset = radeon_get_ib_value(p, idx) << 8; + track->htile_offset = (u64)radeon_get_ib_value(p, idx) << 8; ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff); track->htile_bo = reloc->robj; track->db_dirty = true; diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index ca5598ae8bfc..1814bb8e14f1 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -687,11 +687,16 @@ static void radeon_crtc_init(struct drm_device *dev, int index) if (radeon_crtc == NULL) return; + radeon_crtc->flip_queue = alloc_workqueue("radeon-crtc", WQ_HIGHPRI, 0); + if (!radeon_crtc->flip_queue) { + kfree(radeon_crtc); + return; + } + drm_crtc_init(dev, &radeon_crtc->base, &radeon_crtc_funcs); drm_mode_crtc_set_gamma_size(&radeon_crtc->base, 256); radeon_crtc->crtc_id = index; - radeon_crtc->flip_queue = alloc_workqueue("radeon-crtc", WQ_HIGHPRI, 0); rdev->mode_info.crtcs[index] = radeon_crtc; if (rdev->family >= CHIP_BONAIRE) { diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index 987cabbf1318..c38b4d5d6a14 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -1204,13 +1204,17 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm) r = radeon_bo_create(rdev, pd_size, align, true, RADEON_GEM_DOMAIN_VRAM, 0, NULL, NULL, &vm->page_directory); - if (r) + if (r) { + kfree(vm->page_tables); + vm->page_tables = NULL; return r; - + } r = radeon_vm_clear_bo(rdev, vm->page_directory); if (r) { radeon_bo_unref(&vm->page_directory); vm->page_directory = NULL; + kfree(vm->page_tables); + vm->page_tables = NULL; return r; } diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index a91012447b56..85e9cba49cec 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -3611,6 +3611,10 @@ static int si_cp_start(struct radeon_device *rdev) for (i = RADEON_RING_TYPE_GFX_INDEX; i <= CAYMAN_RING_TYPE_CP2_INDEX; ++i) { ring = &rdev->ring[i]; r = radeon_ring_lock(rdev, ring, 2); + if (r) { + DRM_ERROR("radeon: cp failed to lock ring (%d).\n", r); + return r; + } /* clear the compute context state */ radeon_ring_write(ring, PACKET3_COMPUTE(PACKET3_CLEAR_STATE, 0)); diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c index f74f381af05f..d49c145db437 100644 --- a/drivers/gpu/drm/radeon/sumo_dpm.c +++ b/drivers/gpu/drm/radeon/sumo_dpm.c @@ -1493,8 +1493,10 @@ static int sumo_parse_power_table(struct radeon_device *rdev) non_clock_array_index = power_state->v2.nonClockInfoIndex; non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *) &non_clock_info_array->nonClockInfo[non_clock_array_index]; - if (!rdev->pm.power_state[i].clock_info) + if (!rdev->pm.power_state[i].clock_info) { + kfree(rdev->pm.dpm.ps); return -EINVAL; + } ps = kzalloc(sizeof(struct sumo_ps), GFP_KERNEL); if (ps == NULL) { kfree(rdev->pm.dpm.ps); diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c index 08ea1c864cb2..ef1cc7bad20a 100644 --- a/drivers/gpu/drm/radeon/trinity_dpm.c +++ b/drivers/gpu/drm/radeon/trinity_dpm.c @@ -1726,8 +1726,10 @@ static int trinity_parse_power_table(struct radeon_device *rdev) non_clock_array_index = power_state->v2.nonClockInfoIndex; non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *) &non_clock_info_array->nonClockInfo[non_clock_array_index]; - if (!rdev->pm.power_state[i].clock_info) + if (!rdev->pm.power_state[i].clock_info) { + kfree(rdev->pm.dpm.ps); return -EINVAL; + } ps = kzalloc(sizeof(struct sumo_ps), GFP_KERNEL); if (ps == NULL) { kfree(rdev->pm.dpm.ps); diff --git a/drivers/gpu/drm/tidss/tidss_crtc.c b/drivers/gpu/drm/tidss/tidss_crtc.c index 662353f81835..1f578079aa82 100644 --- a/drivers/gpu/drm/tidss/tidss_crtc.c +++ b/drivers/gpu/drm/tidss/tidss_crtc.c @@ -181,6 +181,10 @@ static void tidss_crtc_atomic_flush(struct drm_crtc *crtc, drm_atomic_crtc_needs_modeset(crtc->state) ? "needs" : "doesn't need", crtc->state->event); + /* There is nothing to do if CRTC is not going to be enabled. */ + if (!crtc->state->active) + return; + /* * Flush CRTC changes with go bit only if new modeset is not * coming, so CRTC is enabled trough out the commit. @@ -329,6 +333,16 @@ static void tidss_crtc_atomic_disable(struct drm_crtc *crtc, dev_dbg(ddev->dev, "%s, event %p\n", __func__, crtc->state->event); + /* + * If a layer is left enabled when the videoport is disabled, and the + * vid pipeline that was used for the layer is taken into use on + * another videoport, the DSS will report sync lost issues. Disable all + * the layers here as a work-around. + */ + for (u32 layer = 0; layer < tidss->feat->num_planes; layer++) + dispc_ovr_enable_layer(tidss->dispc, tcrtc->vp_idx, layer, + false); + reinit_completion(&tcrtc->framedone_completion); dispc_vp_disable(tidss->dispc, tcrtc->vp_idx); diff --git a/drivers/gpu/drm/tidss/tidss_dispc.c b/drivers/gpu/drm/tidss/tidss_dispc.c index 079104b03440..109bdf5ae4d3 100644 --- a/drivers/gpu/drm/tidss/tidss_dispc.c +++ b/drivers/gpu/drm/tidss/tidss_dispc.c @@ -3357,7 +3357,12 @@ static int dispc_init_hw(struct dispc_device *dispc) dispc->tidss->boot_enabled_vp_mask = 0; - if (dispc_is_idle(dispc)) { + /* HACK: If simple-framebuffer device is absent, then soft reset dispc even if it is not + * idle. This is to avoid powering-off of DSS (which can happen due + * to probe deferral waiting for child drivers) while DSS is active thus leading to system + * hang. + */ + if (dispc_is_idle(dispc) || !dispc->tidss->simplefb_enabled) { ret = dispc_softreset(dispc); if (ret) goto err_clk_disable; diff --git a/drivers/gpu/drm/tidss/tidss_drv.c b/drivers/gpu/drm/tidss/tidss_drv.c index e06f6ed98338..fff3883a355a 100644 --- a/drivers/gpu/drm/tidss/tidss_drv.c +++ b/drivers/gpu/drm/tidss/tidss_drv.c @@ -206,6 +206,29 @@ fail: return ret; } +static void check_for_simplefb_device(struct tidss_device *tidss) +{ + if (IS_ENABLED(CONFIG_FB_SIMPLE)) { + struct device *simplefb_dev; + struct device_node *simplefb_node; + + simplefb_node = of_find_compatible_node(NULL, NULL, "simple-framebuffer"); + if (!simplefb_node) + return; + + simplefb_dev = bus_find_device_by_of_node(&platform_bus_type, simplefb_node); + if (!simplefb_dev) { + of_node_put(simplefb_node); + return; + } + + tidss->simplefb_enabled = true; + dev_dbg(tidss->dev, "simple-framebuffer detected\n"); + put_device(simplefb_dev); + of_node_put(simplefb_node); + } +} + static int tidss_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -230,6 +253,7 @@ static int tidss_probe(struct platform_device *pdev) spin_lock_init(&tidss->wait_lock); + check_for_simplefb_device(tidss); tidss->shared_mode = device_property_read_bool(dev, "ti,dss-shared-mode"); /* powering up associated OLDI domains */ diff --git a/drivers/gpu/drm/tidss/tidss_drv.h b/drivers/gpu/drm/tidss/tidss_drv.h index 9bdd5c2cf0fc..25116ac968db 100644 --- a/drivers/gpu/drm/tidss/tidss_drv.h +++ b/drivers/gpu/drm/tidss/tidss_drv.h @@ -48,6 +48,7 @@ struct tidss_device { struct device_link **pd_link; u32 boot_enabled_vp_mask; + bool simplefb_enabled; bool shared_mode; /* DSS resources shared between remote core and Linux */ diff --git a/drivers/gpu/drm/tidss/tidss_plane.c b/drivers/gpu/drm/tidss/tidss_plane.c index 5328d8b8cff0..5d7c7d37606a 100644 --- a/drivers/gpu/drm/tidss/tidss_plane.c +++ b/drivers/gpu/drm/tidss/tidss_plane.c @@ -211,7 +211,7 @@ struct tidss_plane *tidss_plane_create(struct tidss_device *tidss, drm_plane_helper_add(&tplane->plane, &tidss_plane_helper_funcs); - drm_plane_create_zpos_property(&tplane->plane, hw_plane_id, 0, + drm_plane_create_zpos_property(&tplane->plane, tidss->num_planes, 0, num_planes - 1); ret = drm_plane_create_color_properties(&tplane->plane, diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c index f72755b8ea14..86d34b77b37d 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c @@ -138,7 +138,7 @@ static int tilcdc_irq_install(struct drm_device *dev, unsigned int irq) if (ret) return ret; - priv->irq_enabled = false; + priv->irq_enabled = true; return 0; } diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 86affe987a1c..393b97b4a991 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -383,7 +383,7 @@ static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt, enum ttm_caching caching, pgoff_t start_page, pgoff_t end_page) { - struct page **pages = tt->pages; + struct page **pages = &tt->pages[start_page]; unsigned int order; pgoff_t i, nr; diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 0035affc3e59..9b2d235168bb 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -93,6 +93,7 @@ static int virtio_gpu_probe(struct virtio_device *vdev) goto err_free; } + dma_set_max_seg_size(dev->dev, dma_max_mapping_size(dev->dev) ?: UINT_MAX); ret = virtio_gpu_init(vdev, dev); if (ret) goto err_free; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index ae01d22b8f84..c46f380d9149 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -595,10 +595,9 @@ static int vmw_user_bo_synccpu_release(struct drm_file *filp, if (!(flags & drm_vmw_synccpu_allow_cs)) { atomic_dec(&vmw_bo->cpu_writers); } - ttm_bo_put(&vmw_bo->base); + vmw_user_bo_unref(&vmw_bo); } - drm_gem_object_put(&vmw_bo->base.base); return ret; } @@ -638,8 +637,7 @@ int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data, return ret; ret = vmw_user_bo_synccpu_grab(vbo, arg->flags); - vmw_bo_unreference(&vbo); - drm_gem_object_put(&vbo->base.base); + vmw_user_bo_unref(&vbo); if (unlikely(ret != 0)) { if (ret == -ERESTARTSYS || ret == -EBUSY) return -EBUSY; @@ -713,7 +711,6 @@ int vmw_user_bo_lookup(struct drm_file *filp, } *out = gem_to_vmw_bo(gobj); - ttm_bo_get(&(*out)->base); return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index 79b30dc9d825..97e56a94eaf8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -407,8 +407,8 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) * for the new COTable. Initially pin the buffer object to make sure * we can use tryreserve without failure. */ - ret = vmw_bo_create(dev_priv, new_size, &vmw_mob_placement, - true, true, vmw_bo_bo_free, &buf); + ret = vmw_gem_object_create(dev_priv, new_size, &vmw_mob_placement, + true, true, vmw_bo_bo_free, &buf); if (ret) { DRM_ERROR("Failed initializing new cotable MOB.\n"); return ret; @@ -475,7 +475,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) vmw_resource_mob_attach(res); /* Let go of the old mob. */ - vmw_bo_unreference(&old_buf); + vmw_user_bo_unref(&old_buf); res->id = vcotbl->type; ret = dma_resv_reserve_fences(bo->base.resv, 1); @@ -492,7 +492,7 @@ out_map_new: out_wait: ttm_bo_unpin(bo); ttm_bo_unreserve(bo); - vmw_bo_unreference(&buf); + vmw_user_bo_unref(&buf); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 8459fab9d979..136f1cdcf8cd 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -969,6 +969,11 @@ static inline void vmw_bo_prio_del(struct vmw_buffer_object *vbo, int prio) /** * GEM related functionality - vmwgfx_gem.c */ +extern int vmw_gem_object_create(struct vmw_private *dev_priv, + size_t size, struct ttm_placement *placement, + bool interruptible, bool pin, + void (*bo_free)(struct ttm_buffer_object *bo), + struct vmw_buffer_object **p_bo); extern int vmw_gem_object_create_with_handle(struct vmw_private *dev_priv, struct drm_file *filp, uint32_t size, @@ -1600,6 +1605,21 @@ vmw_bo_reference(struct vmw_buffer_object *buf) return buf; } +static inline struct vmw_buffer_object *vmw_user_bo_ref(struct vmw_buffer_object *vbo) +{ + drm_gem_object_get(&vbo->base.base); + return vbo; +} + +static inline void vmw_user_bo_unref(struct vmw_buffer_object **buf) +{ + struct vmw_buffer_object *tmp_buf = *buf; + + *buf = NULL; + if (tmp_buf) + drm_gem_object_put(&tmp_buf->base.base); +} + static inline void vmw_fifo_resource_inc(struct vmw_private *dev_priv) { atomic_inc(&dev_priv->num_fifo_resources); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 7e59469e1cb9..bc7f02e4eceb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1147,7 +1147,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, SVGAMobId *id, struct vmw_buffer_object **vmw_bo_p) { - struct vmw_buffer_object *vmw_bo; + struct vmw_buffer_object *vmw_bo, *tmp_bo; uint32_t handle = *id; struct vmw_relocation *reloc; int ret; @@ -1159,8 +1159,8 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, return PTR_ERR(vmw_bo); } ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, true, false); - ttm_bo_put(&vmw_bo->base); - drm_gem_object_put(&vmw_bo->base.base); + tmp_bo = vmw_bo; + vmw_user_bo_unref(&tmp_bo); if (unlikely(ret != 0)) return ret; @@ -1202,7 +1202,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, SVGAGuestPtr *ptr, struct vmw_buffer_object **vmw_bo_p) { - struct vmw_buffer_object *vmw_bo; + struct vmw_buffer_object *vmw_bo, *tmp_bo; uint32_t handle = ptr->gmrId; struct vmw_relocation *reloc; int ret; @@ -1214,8 +1214,8 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, return PTR_ERR(vmw_bo); } ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, false, false); - ttm_bo_put(&vmw_bo->base); - drm_gem_object_put(&vmw_bo->base.base); + tmp_bo = vmw_bo; + vmw_user_bo_unref(&tmp_bo); if (unlikely(ret != 0)) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index 4d2c28e39f4e..e7a533e39155 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -133,6 +133,22 @@ void vmw_gem_destroy(struct ttm_buffer_object *bo) kfree(vbo); } +int vmw_gem_object_create(struct vmw_private *vmw, + size_t size, struct ttm_placement *placement, + bool interruptible, bool pin, + void (*bo_free)(struct ttm_buffer_object *bo), + struct vmw_buffer_object **p_bo) +{ + int ret = vmw_bo_create(vmw, size, placement, interruptible, pin, bo_free, p_bo); + + if (ret != 0) + goto out_no_bo; + + (*p_bo)->base.base.funcs = &vmw_gem_object_funcs; +out_no_bo: + return ret; +} + int vmw_gem_object_create_with_handle(struct vmw_private *dev_priv, struct drm_file *filp, uint32_t size, @@ -141,16 +157,14 @@ int vmw_gem_object_create_with_handle(struct vmw_private *dev_priv, { int ret; - ret = vmw_bo_create(dev_priv, size, - (dev_priv->has_mob) ? + ret = vmw_gem_object_create(dev_priv, size, + (dev_priv->has_mob) ? &vmw_sys_placement : &vmw_vram_sys_placement, - true, false, &vmw_gem_destroy, p_vbo); + true, false, &vmw_gem_destroy, p_vbo); if (ret != 0) goto out_no_bo; - (*p_vbo)->base.base.funcs = &vmw_gem_object_funcs; - ret = drm_gem_handle_create(filp, &(*p_vbo)->base.base, handle); out_no_bo: return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index aab6389cb4aa..aa571b75cd07 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1402,8 +1402,8 @@ static int vmw_create_bo_proxy(struct drm_device *dev, /* Reserve and switch the backing mob. */ mutex_lock(&res->dev_priv->cmdbuf_mutex); (void) vmw_resource_reserve(res, false, true); - vmw_bo_unreference(&res->backup); - res->backup = vmw_bo_reference(bo_mob); + vmw_user_bo_unref(&res->backup); + res->backup = vmw_user_bo_ref(bo_mob); res->backup_offset = 0; vmw_resource_unreserve(res, false, false, false, NULL, 0); mutex_unlock(&res->dev_priv->cmdbuf_mutex); @@ -1599,10 +1599,8 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, err_out: /* vmw_user_lookup_handle takes one ref so does new_fb */ - if (bo) { - vmw_bo_unreference(&bo); - drm_gem_object_put(&bo->base.base); - } + if (bo) + vmw_user_bo_unref(&bo); if (surface) vmw_surface_unreference(&surface); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c index b5b311f2a91a..abc354ead4e8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c @@ -457,8 +457,7 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data, ret = vmw_overlay_update_stream(dev_priv, buf, arg, true); - vmw_bo_unreference(&buf); - drm_gem_object_put(&buf->base.base); + vmw_user_bo_unref(&buf); out_unlock: mutex_unlock(&overlay->mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index c7d645e5ec7b..30d1c1918bb4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -140,7 +140,7 @@ static void vmw_resource_release(struct kref *kref) if (res->coherent) vmw_bo_dirty_release(res->backup); ttm_bo_unreserve(bo); - vmw_bo_unreference(&res->backup); + vmw_user_bo_unref(&res->backup); } if (likely(res->hw_destroy != NULL)) { @@ -330,10 +330,10 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res, return 0; } - ret = vmw_bo_create(res->dev_priv, res->backup_size, - res->func->backup_placement, - interruptible, false, - &vmw_bo_bo_free, &backup); + ret = vmw_gem_object_create(res->dev_priv, res->backup_size, + res->func->backup_placement, + interruptible, false, + &vmw_bo_bo_free, &backup); if (unlikely(ret != 0)) goto out_no_bo; @@ -452,11 +452,11 @@ void vmw_resource_unreserve(struct vmw_resource *res, vmw_resource_mob_detach(res); if (res->coherent) vmw_bo_dirty_release(res->backup); - vmw_bo_unreference(&res->backup); + vmw_user_bo_unref(&res->backup); } if (new_backup) { - res->backup = vmw_bo_reference(new_backup); + res->backup = vmw_user_bo_ref(new_backup); /* * The validation code should already have added a @@ -544,7 +544,7 @@ out_no_reserve: ttm_bo_put(val_buf->bo); val_buf->bo = NULL; if (backup_dirty) - vmw_bo_unreference(&res->backup); + vmw_user_bo_unref(&res->backup); return ret; } @@ -719,7 +719,7 @@ int vmw_resource_validate(struct vmw_resource *res, bool intr, goto out_no_validate; else if (!res->func->needs_backup && res->backup) { WARN_ON_ONCE(vmw_resource_mob_attached(res)); - vmw_bo_unreference(&res->backup); + vmw_user_bo_unref(&res->backup); } return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index 51e83dfa1cac..303f7a82f350 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -177,7 +177,7 @@ static int vmw_gb_shader_init(struct vmw_private *dev_priv, res->backup_size = size; if (byte_code) { - res->backup = vmw_bo_reference(byte_code); + res->backup = vmw_user_bo_ref(byte_code); res->backup_offset = offset; } shader->size = size; @@ -806,8 +806,7 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv, shader_type, num_input_sig, num_output_sig, tfile, shader_handle); out_bad_arg: - vmw_bo_unreference(&buffer); - drm_gem_object_put(&buffer->base.base); + vmw_user_bo_unref(&buffer); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 1a1a286bc749..50769528c3f3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -683,9 +683,6 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base) container_of(base, struct vmw_user_surface, prime.base); struct vmw_resource *res = &user_srf->srf.res; - if (res && res->backup) - drm_gem_object_put(&res->backup->base.base); - *p_base = NULL; vmw_resource_unreference(&res); } @@ -848,23 +845,17 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, * expect a backup buffer to be present. */ if (dev_priv->has_mob && req->shareable) { - uint32_t backup_handle; - - ret = vmw_gem_object_create_with_handle(dev_priv, - file_priv, - res->backup_size, - &backup_handle, - &res->backup); + ret = vmw_gem_object_create(dev_priv, + res->backup_size, + &vmw_sys_placement, + true, + false, + &vmw_gem_destroy, + &res->backup); if (unlikely(ret != 0)) { vmw_resource_unreference(&res); goto out_unlock; } - vmw_bo_reference(res->backup); - /* - * We don't expose the handle to the userspace and surface - * already holds a gem reference - */ - drm_gem_handle_delete(file_priv, backup_handle); } tmp = vmw_resource_reference(&srf->res); @@ -1505,7 +1496,7 @@ vmw_gb_surface_define_internal(struct drm_device *dev, if (ret == 0) { if (res->backup->base.base.size < res->backup_size) { VMW_DEBUG_USER("Surface backup buffer too small.\n"); - vmw_bo_unreference(&res->backup); + vmw_user_bo_unref(&res->backup); ret = -EINVAL; goto out_unlock; } else { @@ -1519,8 +1510,6 @@ vmw_gb_surface_define_internal(struct drm_device *dev, res->backup_size, &backup_handle, &res->backup); - if (ret == 0) - vmw_bo_reference(res->backup); } if (unlikely(ret != 0)) { diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index 8a8a3dd8af0c..df07e3ae0ffb 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -325,28 +325,28 @@ struct joycon_imu_cal { * All the controller's button values are stored in a u32. * They can be accessed with bitwise ANDs. */ -static const u32 JC_BTN_Y = BIT(0); -static const u32 JC_BTN_X = BIT(1); -static const u32 JC_BTN_B = BIT(2); -static const u32 JC_BTN_A = BIT(3); -static const u32 JC_BTN_SR_R = BIT(4); -static const u32 JC_BTN_SL_R = BIT(5); -static const u32 JC_BTN_R = BIT(6); -static const u32 JC_BTN_ZR = BIT(7); -static const u32 JC_BTN_MINUS = BIT(8); -static const u32 JC_BTN_PLUS = BIT(9); -static const u32 JC_BTN_RSTICK = BIT(10); -static const u32 JC_BTN_LSTICK = BIT(11); -static const u32 JC_BTN_HOME = BIT(12); -static const u32 JC_BTN_CAP = BIT(13); /* capture button */ -static const u32 JC_BTN_DOWN = BIT(16); -static const u32 JC_BTN_UP = BIT(17); -static const u32 JC_BTN_RIGHT = BIT(18); -static const u32 JC_BTN_LEFT = BIT(19); -static const u32 JC_BTN_SR_L = BIT(20); -static const u32 JC_BTN_SL_L = BIT(21); -static const u32 JC_BTN_L = BIT(22); -static const u32 JC_BTN_ZL = BIT(23); +#define JC_BTN_Y BIT(0) +#define JC_BTN_X BIT(1) +#define JC_BTN_B BIT(2) +#define JC_BTN_A BIT(3) +#define JC_BTN_SR_R BIT(4) +#define JC_BTN_SL_R BIT(5) +#define JC_BTN_R BIT(6) +#define JC_BTN_ZR BIT(7) +#define JC_BTN_MINUS BIT(8) +#define JC_BTN_PLUS BIT(9) +#define JC_BTN_RSTICK BIT(10) +#define JC_BTN_LSTICK BIT(11) +#define JC_BTN_HOME BIT(12) +#define JC_BTN_CAP BIT(13) /* capture button */ +#define JC_BTN_DOWN BIT(16) +#define JC_BTN_UP BIT(17) +#define JC_BTN_RIGHT BIT(18) +#define JC_BTN_LEFT BIT(19) +#define JC_BTN_SR_L BIT(20) +#define JC_BTN_SL_L BIT(21) +#define JC_BTN_L BIT(22) +#define JC_BTN_ZL BIT(23) enum joycon_msg_type { JOYCON_MSG_TYPE_NONE, @@ -859,14 +859,27 @@ static int joycon_request_calibration(struct joycon_ctlr *ctlr) */ static void joycon_calc_imu_cal_divisors(struct joycon_ctlr *ctlr) { - int i; + int i, divz = 0; for (i = 0; i < 3; i++) { ctlr->imu_cal_accel_divisor[i] = ctlr->accel_cal.scale[i] - ctlr->accel_cal.offset[i]; ctlr->imu_cal_gyro_divisor[i] = ctlr->gyro_cal.scale[i] - ctlr->gyro_cal.offset[i]; + + if (ctlr->imu_cal_accel_divisor[i] == 0) { + ctlr->imu_cal_accel_divisor[i] = 1; + divz++; + } + + if (ctlr->imu_cal_gyro_divisor[i] == 0) { + ctlr->imu_cal_gyro_divisor[i] = 1; + divz++; + } } + + if (divz) + hid_warn(ctlr->hdev, "inaccurate IMU divisors (%d)\n", divz); } static const s16 DFLT_ACCEL_OFFSET /*= 0*/; @@ -1095,16 +1108,16 @@ static void joycon_parse_imu_report(struct joycon_ctlr *ctlr, JC_IMU_SAMPLES_PER_DELTA_AVG) { ctlr->imu_avg_delta_ms = ctlr->imu_delta_samples_sum / ctlr->imu_delta_samples_count; - /* don't ever want divide by zero shenanigans */ - if (ctlr->imu_avg_delta_ms == 0) { - ctlr->imu_avg_delta_ms = 1; - hid_warn(ctlr->hdev, - "calculated avg imu delta of 0\n"); - } ctlr->imu_delta_samples_count = 0; ctlr->imu_delta_samples_sum = 0; } + /* don't ever want divide by zero shenanigans */ + if (ctlr->imu_avg_delta_ms == 0) { + ctlr->imu_avg_delta_ms = 1; + hid_warn(ctlr->hdev, "calculated avg imu delta of 0\n"); + } + /* useful for debugging IMU sample rate */ hid_dbg(ctlr->hdev, "imu_report: ms=%u last_ms=%u delta=%u avg_delta=%u\n", diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index b617aada50b0..7b097ab2170c 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -355,8 +355,11 @@ static int hidraw_release(struct inode * inode, struct file * file) down_write(&minors_rwsem); spin_lock_irqsave(&hidraw_table[minor]->list_lock, flags); - for (int i = list->tail; i < list->head; i++) - kfree(list->buffer[i].value); + while (list->tail != list->head) { + kfree(list->buffer[list->tail].value); + list->buffer[list->tail].value = NULL; + list->tail = (list->tail + 1) & (HIDRAW_BUFFER_SIZE - 1); + } list_del(&list->node); spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags); kfree(list); diff --git a/drivers/hid/i2c-hid/i2c-hid-acpi.c b/drivers/hid/i2c-hid/i2c-hid-acpi.c index b96ae15e0ad9..6d35bb397481 100644 --- a/drivers/hid/i2c-hid/i2c-hid-acpi.c +++ b/drivers/hid/i2c-hid/i2c-hid-acpi.c @@ -39,8 +39,13 @@ static const struct acpi_device_id i2c_hid_acpi_blacklist[] = { * The CHPN0001 ACPI device, which is used to describe the Chipone * ICN8505 controller, has a _CID of PNP0C50 but is not HID compatible. */ - {"CHPN0001", 0 }, - { }, + { "CHPN0001" }, + /* + * The IDEA5002 ACPI device causes high interrupt usage and spurious + * wakeups from suspend. + */ + { "IDEA5002" }, + { } }; /* HID I²C Device: 3cdff6f7-4267-4555-ad05-b30a3d8938de */ @@ -115,9 +120,9 @@ static int i2c_hid_acpi_probe(struct i2c_client *client) } static const struct acpi_device_id i2c_hid_acpi_match[] = { - {"ACPI0C50", 0 }, - {"PNP0C50", 0 }, - { }, + { "ACPI0C50" }, + { "PNP0C50" }, + { } }; MODULE_DEVICE_TABLE(acpi, i2c_hid_acpi_match); diff --git a/drivers/hid/i2c-hid/i2c-hid-of.c b/drivers/hid/i2c-hid/i2c-hid-of.c index 97a27a803f58..6feb812fce37 100644 --- a/drivers/hid/i2c-hid/i2c-hid-of.c +++ b/drivers/hid/i2c-hid/i2c-hid-of.c @@ -80,6 +80,7 @@ static int i2c_hid_of_probe(struct i2c_client *client, if (!ihid_of) return -ENOMEM; + ihid_of->client = client; ihid_of->ops.power_up = i2c_hid_of_power_up; ihid_of->ops.power_down = i2c_hid_of_power_down; diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index af163e8dfec0..12d4c28741d7 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2080,7 +2080,7 @@ static int wacom_allocate_inputs(struct wacom *wacom) return 0; } -static int wacom_register_inputs(struct wacom *wacom) +static int wacom_setup_inputs(struct wacom *wacom) { struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev; struct wacom_wac *wacom_wac = &(wacom->wacom_wac); @@ -2099,10 +2099,6 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(pen_input_dev); wacom_wac->pen_input = NULL; pen_input_dev = NULL; - } else { - error = input_register_device(pen_input_dev); - if (error) - goto fail; } error = wacom_setup_touch_input_capabilities(touch_input_dev, wacom_wac); @@ -2111,10 +2107,6 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(touch_input_dev); wacom_wac->touch_input = NULL; touch_input_dev = NULL; - } else { - error = input_register_device(touch_input_dev); - if (error) - goto fail; } error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac); @@ -2123,7 +2115,34 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(pad_input_dev); wacom_wac->pad_input = NULL; pad_input_dev = NULL; - } else { + } + + return 0; +} + +static int wacom_register_inputs(struct wacom *wacom) +{ + struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev; + struct wacom_wac *wacom_wac = &(wacom->wacom_wac); + int error = 0; + + pen_input_dev = wacom_wac->pen_input; + touch_input_dev = wacom_wac->touch_input; + pad_input_dev = wacom_wac->pad_input; + + if (pen_input_dev) { + error = input_register_device(pen_input_dev); + if (error) + goto fail; + } + + if (touch_input_dev) { + error = input_register_device(touch_input_dev); + if (error) + goto fail; + } + + if (pad_input_dev) { error = input_register_device(pad_input_dev); if (error) goto fail; @@ -2379,6 +2398,20 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail; } + error = wacom_setup_inputs(wacom); + if (error) + goto fail; + + if (features->type == HID_GENERIC) + connect_mask |= HID_CONNECT_DRIVER; + + /* Regular HID work starts now */ + error = hid_hw_start(hdev, connect_mask); + if (error) { + hid_err(hdev, "hw start failed\n"); + goto fail; + } + error = wacom_register_inputs(wacom); if (error) goto fail; @@ -2393,16 +2426,6 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail; } - if (features->type == HID_GENERIC) - connect_mask |= HID_CONNECT_DRIVER; - - /* Regular HID work starts now */ - error = hid_hw_start(hdev, connect_mask); - if (error) { - hid_err(hdev, "hw start failed\n"); - goto fail; - } - if (!wireless) { /* Note that if query fails it is not a hard failure */ wacom_query_tablet_data(wacom); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index c1270db12178..53235b276bb2 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2571,7 +2571,14 @@ static void wacom_wac_pen_report(struct hid_device *hdev, wacom_wac->hid_data.tipswitch); input_report_key(input, wacom_wac->tool[0], sense); if (wacom_wac->serial[0]) { - input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]); + /* + * xf86-input-wacom does not accept a serial number + * of '0'. Report the low 32 bits if possible, but + * if they are zero, report the upper ones instead. + */ + __u32 serial_lo = wacom_wac->serial[0] & 0xFFFFFFFFu; + __u32 serial_hi = wacom_wac->serial[0] >> 32; + input_event(input, EV_MSC, MSC_SERIAL, (int)(serial_lo ? serial_lo : serial_hi)); input_report_abs(input, ABS_MISC, sense ? id : 0); } @@ -2646,8 +2653,8 @@ static void wacom_wac_finger_slot(struct wacom_wac *wacom_wac, { struct hid_data *hid_data = &wacom_wac->hid_data; bool mt = wacom_wac->features.touch_max > 1; - bool prox = hid_data->tipswitch && - report_touch_events(wacom_wac); + bool touch_down = hid_data->tipswitch && hid_data->confidence; + bool prox = touch_down && report_touch_events(wacom_wac); if (touch_is_muted(wacom_wac)) { if (!wacom_wac->shared->touch_down) @@ -2697,24 +2704,6 @@ static void wacom_wac_finger_slot(struct wacom_wac *wacom_wac, } } -static bool wacom_wac_slot_is_active(struct input_dev *dev, int key) -{ - struct input_mt *mt = dev->mt; - struct input_mt_slot *s; - - if (!mt) - return false; - - for (s = mt->slots; s != mt->slots + mt->num_slots; s++) { - if (s->key == key && - input_mt_get_value(s, ABS_MT_TRACKING_ID) >= 0) { - return true; - } - } - - return false; -} - static void wacom_wac_finger_event(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value) { @@ -2765,14 +2754,8 @@ static void wacom_wac_finger_event(struct hid_device *hdev, } if (usage->usage_index + 1 == field->report_count) { - if (equivalent_usage == wacom_wac->hid_data.last_slot_field) { - bool touch_removed = wacom_wac_slot_is_active(wacom_wac->touch_input, - wacom_wac->hid_data.id) && !wacom_wac->hid_data.tipswitch; - - if (wacom_wac->hid_data.confidence || touch_removed) { - wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input); - } - } + if (equivalent_usage == wacom_wac->hid_data.last_slot_field) + wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input); } } diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c index d11f674e3dc3..51f321bcd778 100644 --- a/drivers/hwmon/aspeed-pwm-tacho.c +++ b/drivers/hwmon/aspeed-pwm-tacho.c @@ -194,6 +194,8 @@ struct aspeed_pwm_tacho_data { u8 fan_tach_ch_source[16]; struct aspeed_cooling_device *cdev[8]; const struct attribute_group *groups[3]; + /* protects access to shared ASPEED_PTCR_RESULT */ + struct mutex tach_lock; }; enum type { TYPEM, TYPEN, TYPEO }; @@ -528,6 +530,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv, u8 fan_tach_ch_source, type, mode, both; int ret; + mutex_lock(&priv->tach_lock); + regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0); regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0x1 << fan_tach_ch); @@ -545,6 +549,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv, ASPEED_RPM_STATUS_SLEEP_USEC, usec); + mutex_unlock(&priv->tach_lock); + /* return -ETIMEDOUT if we didn't get an answer. */ if (ret) return ret; @@ -904,6 +910,7 @@ static int aspeed_pwm_tacho_probe(struct platform_device *pdev) priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + mutex_init(&priv->tach_lock); priv->regmap = devm_regmap_init(dev, NULL, (__force void *)regs, &aspeed_pwm_tacho_regmap_config); if (IS_ERR(priv->regmap)) diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 09aab5859fa7..c0aa6bfa66b2 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -40,7 +40,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius"); #define PKG_SYSFS_ATTR_NO 1 /* Sysfs attribute for package temp */ #define BASE_SYSFS_ATTR_NO 2 /* Sysfs Base attr no for coretemp */ -#define NUM_REAL_CORES 128 /* Number of Real cores per cpu */ +#define NUM_REAL_CORES 512 /* Number of Real cores per cpu */ #define CORETEMP_NAME_LENGTH 28 /* String Length of attrs */ #define MAX_CORE_ATTRS 4 /* Maximum no of basic attrs */ #define TOTAL_ATTRS (MAX_CORE_ATTRS + 1) @@ -380,7 +380,7 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev) } static int create_core_attrs(struct temp_data *tdata, struct device *dev, - int attr_no) + int index) { int i; static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev, @@ -392,13 +392,20 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev, }; for (i = 0; i < tdata->attr_size; i++) { + /* + * We map the attr number to core id of the CPU + * The attr number is always core id + 2 + * The Pkgtemp will always show up as temp1_*, if available + */ + int attr_no = tdata->is_pkg_data ? 1 : tdata->cpu_core_id + 2; + snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH, "temp%d_%s", attr_no, suffixes[i]); sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr); tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i]; tdata->sd_attrs[i].dev_attr.attr.mode = 0444; tdata->sd_attrs[i].dev_attr.show = rd_ptr[i]; - tdata->sd_attrs[i].index = attr_no; + tdata->sd_attrs[i].index = index; tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr; } tdata->attr_group.attrs = tdata->attrs; @@ -456,27 +463,22 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, struct platform_data *pdata = platform_get_drvdata(pdev); struct cpuinfo_x86 *c = &cpu_data(cpu); u32 eax, edx; - int err, index, attr_no; + int err, index; /* - * Find attr number for sysfs: - * We map the attr number to core id of the CPU - * The attr number is always core id + 2 - * The Pkgtemp will always show up as temp1_*, if available + * Get the index of tdata in pdata->core_data[] + * tdata for package: pdata->core_data[1] + * tdata for core: pdata->core_data[2] .. pdata->core_data[NUM_REAL_CORES + 1] */ if (pkg_flag) { - attr_no = PKG_SYSFS_ATTR_NO; + index = PKG_SYSFS_ATTR_NO; } else { - index = ida_alloc(&pdata->ida, GFP_KERNEL); + index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL); if (index < 0) return index; - pdata->cpu_map[index] = topology_core_id(cpu); - attr_no = index + BASE_SYSFS_ATTR_NO; - } - if (attr_no > MAX_CORE_DATA - 1) { - err = -ERANGE; - goto ida_free; + pdata->cpu_map[index] = topology_core_id(cpu); + index += BASE_SYSFS_ATTR_NO; } tdata = init_temp_data(cpu, pkg_flag); @@ -508,20 +510,20 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, } } - pdata->core_data[attr_no] = tdata; + pdata->core_data[index] = tdata; /* Create sysfs interfaces */ - err = create_core_attrs(tdata, pdata->hwmon_dev, attr_no); + err = create_core_attrs(tdata, pdata->hwmon_dev, index); if (err) goto exit_free; return 0; exit_free: - pdata->core_data[attr_no] = NULL; + pdata->core_data[index] = NULL; kfree(tdata); ida_free: if (!pkg_flag) - ida_free(&pdata->ida, index); + ida_free(&pdata->ida, index - BASE_SYSFS_ATTR_NO); return err; } diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c index 2210aa62e3d0..ec7f27a6ce01 100644 --- a/drivers/hwmon/corsair-psu.c +++ b/drivers/hwmon/corsair-psu.c @@ -837,7 +837,23 @@ static struct hid_driver corsairpsu_driver = { .reset_resume = corsairpsu_resume, #endif }; -module_hid_driver(corsairpsu_driver); + +static int __init corsair_init(void) +{ + return hid_register_driver(&corsairpsu_driver); +} + +static void __exit corsair_exit(void) +{ + hid_unregister_driver(&corsairpsu_driver); +} + +/* + * With module_init() the driver would load before the HID bus when + * built-in, so use late_initcall() instead. + */ +late_initcall(corsair_init); +module_exit(corsair_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Wilken Gottwalt <wilken.gottwalt@posteo.net>"); diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c index 80310845fb99..9720ad214c20 100644 --- a/drivers/hwmon/nct6775-core.c +++ b/drivers/hwmon/nct6775-core.c @@ -2462,6 +2462,13 @@ store_pwm(struct device *dev, struct device_attribute *attr, const char *buf, int err; u16 reg; + /* + * The fan control mode should be set to manual if the user wants to adjust + * the fan speed. Otherwise, it will fail to set. + */ + if (index == 0 && data->pwm_enable[nr] > manual) + return -EBUSY; + err = kstrtoul(buf, 10, &val); if (err < 0) return err; diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 0174fbf1a963..d8e4d902b01a 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -1032,7 +1032,7 @@ struct etmv4_drvdata { u8 ctxid_size; u8 vmid_size; u8 ccsize; - u8 ccitmin; + u16 ccitmin; u8 s_ex_level; u8 ns_ex_level; u8 q_support; diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c index 016220ba0add..8d8fa8e8afe0 100644 --- a/drivers/hwtracing/ptt/hisi_ptt.c +++ b/drivers/hwtracing/ptt/hisi_ptt.c @@ -342,9 +342,9 @@ static int hisi_ptt_register_irq(struct hisi_ptt *hisi_ptt) return ret; hisi_ptt->trace_irq = pci_irq_vector(pdev, HISI_PTT_TRACE_DMA_IRQ); - ret = devm_request_threaded_irq(&pdev->dev, hisi_ptt->trace_irq, - NULL, hisi_ptt_isr, 0, - DRV_NAME, hisi_ptt); + ret = devm_request_irq(&pdev->dev, hisi_ptt->trace_irq, hisi_ptt_isr, + IRQF_NOBALANCING | IRQF_NO_THREAD, DRV_NAME, + hisi_ptt); if (ret) { pci_err(pdev, "failed to request irq %d, ret = %d\n", hisi_ptt->trace_irq, ret); @@ -659,6 +659,9 @@ static int hisi_ptt_pmu_event_init(struct perf_event *event) return -EOPNOTSUPP; } + if (event->attach_state & PERF_ATTACH_TASK) + return -EOPNOTSUPP; + if (event->attr.type != hisi_ptt->hisi_ptt_pmu.type) return -ENOENT; diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile index e73cdb1d2b5a..784a803279d9 100644 --- a/drivers/i2c/busses/Makefile +++ b/drivers/i2c/busses/Makefile @@ -89,10 +89,8 @@ obj-$(CONFIG_I2C_NPCM) += i2c-npcm7xx.o obj-$(CONFIG_I2C_OCORES) += i2c-ocores.o obj-$(CONFIG_I2C_OMAP) += i2c-omap.o obj-$(CONFIG_I2C_OWL) += i2c-owl.o -i2c-pasemi-objs := i2c-pasemi-core.o i2c-pasemi-pci.o -obj-$(CONFIG_I2C_PASEMI) += i2c-pasemi.o -i2c-apple-objs := i2c-pasemi-core.o i2c-pasemi-platform.o -obj-$(CONFIG_I2C_APPLE) += i2c-apple.o +obj-$(CONFIG_I2C_PASEMI) += i2c-pasemi-core.o i2c-pasemi-pci.o +obj-$(CONFIG_I2C_APPLE) += i2c-pasemi-core.o i2c-pasemi-platform.o obj-$(CONFIG_I2C_PCA_PLATFORM) += i2c-pca-platform.o obj-$(CONFIG_I2C_PNX) += i2c-pnx.o obj-$(CONFIG_I2C_PXA) += i2c-pxa.o diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index 6adf3b141316..86daf791aa27 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -249,18 +249,46 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status) if (!slave) return 0; - command = readl(bus->base + ASPEED_I2C_CMD_REG); + /* + * Handle stop conditions early, prior to SLAVE_MATCH. Some masters may drive + * transfers with low enough latency between the nak/stop phase of the current + * command and the start/address phase of the following command that the + * interrupts are coalesced by the time we process them. + */ + if (irq_status & ASPEED_I2CD_INTR_NORMAL_STOP) { + irq_handled |= ASPEED_I2CD_INTR_NORMAL_STOP; + bus->slave_state = ASPEED_I2C_SLAVE_STOP; + } + + if (irq_status & ASPEED_I2CD_INTR_TX_NAK && + bus->slave_state == ASPEED_I2C_SLAVE_READ_PROCESSED) { + irq_handled |= ASPEED_I2CD_INTR_TX_NAK; + bus->slave_state = ASPEED_I2C_SLAVE_STOP; + } + + /* Propagate any stop conditions to the slave implementation. */ + if (bus->slave_state == ASPEED_I2C_SLAVE_STOP) { + i2c_slave_event(slave, I2C_SLAVE_STOP, &value); + bus->slave_state = ASPEED_I2C_SLAVE_INACTIVE; + } - /* Slave was requested, restart state machine. */ + /* + * Now that we've dealt with any potentially coalesced stop conditions, + * address any start conditions. + */ if (irq_status & ASPEED_I2CD_INTR_SLAVE_MATCH) { irq_handled |= ASPEED_I2CD_INTR_SLAVE_MATCH; bus->slave_state = ASPEED_I2C_SLAVE_START; } - /* Slave is not currently active, irq was for someone else. */ + /* + * If the slave has been stopped and not started then slave interrupt + * handling is complete. + */ if (bus->slave_state == ASPEED_I2C_SLAVE_INACTIVE) return irq_handled; + command = readl(bus->base + ASPEED_I2C_CMD_REG); dev_dbg(bus->dev, "slave irq status 0x%08x, cmd 0x%08x\n", irq_status, command); @@ -279,17 +307,6 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status) irq_handled |= ASPEED_I2CD_INTR_RX_DONE; } - /* Slave was asked to stop. */ - if (irq_status & ASPEED_I2CD_INTR_NORMAL_STOP) { - irq_handled |= ASPEED_I2CD_INTR_NORMAL_STOP; - bus->slave_state = ASPEED_I2C_SLAVE_STOP; - } - if (irq_status & ASPEED_I2CD_INTR_TX_NAK && - bus->slave_state == ASPEED_I2C_SLAVE_READ_PROCESSED) { - irq_handled |= ASPEED_I2CD_INTR_TX_NAK; - bus->slave_state = ASPEED_I2C_SLAVE_STOP; - } - switch (bus->slave_state) { case ASPEED_I2C_SLAVE_READ_REQUESTED: if (unlikely(irq_status & ASPEED_I2CD_INTR_TX_ACK)) @@ -324,8 +341,7 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status) i2c_slave_event(slave, I2C_SLAVE_WRITE_RECEIVED, &value); break; case ASPEED_I2C_SLAVE_STOP: - i2c_slave_event(slave, I2C_SLAVE_STOP, &value); - bus->slave_state = ASPEED_I2C_SLAVE_INACTIVE; + /* Stop event handling is done early. Unreachable. */ break; case ASPEED_I2C_SLAVE_START: /* Slave was just started. Waiting for the next event. */; diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 3159ffbb77a2..9a4e9bf304c2 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -500,11 +500,10 @@ static int i801_block_transaction_by_block(struct i801_priv *priv, /* Set block buffer mode */ outb_p(inb_p(SMBAUXCTL(priv)) | SMBAUXCTL_E32B, SMBAUXCTL(priv)); - inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ - if (read_write == I2C_SMBUS_WRITE) { len = data->block[0]; outb_p(len, SMBHSTDAT0(priv)); + inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ for (i = 0; i < len; i++) outb_p(data->block[i+1], SMBBLKDAT(priv)); } @@ -520,6 +519,7 @@ static int i801_block_transaction_by_block(struct i801_priv *priv, return -EPROTO; data->block[0] = len; + inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ for (i = 0; i < len; i++) data->block[i + 1] = inb_p(SMBBLKDAT(priv)); } diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index fc70920c4dda..0c203c614197 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -804,6 +804,11 @@ static irqreturn_t i2c_imx_slave_handle(struct imx_i2c_struct *i2c_imx, ctl &= ~I2CR_MTX; imx_i2c_write_reg(ctl, i2c_imx, IMX_I2C_I2CR); imx_i2c_read_reg(i2c_imx, IMX_I2C_I2DR); + + /* flag the last byte as processed */ + i2c_imx_slave_event(i2c_imx, + I2C_SLAVE_READ_PROCESSED, &value); + i2c_imx_slave_finish_op(i2c_imx); return IRQ_HANDLED; } diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c index 9028ffb58cc0..f297e41352e7 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -356,3 +356,8 @@ int pasemi_i2c_common_probe(struct pasemi_smbus *smbus) return 0; } +EXPORT_SYMBOL_GPL(pasemi_i2c_common_probe); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Olof Johansson <olof@lixom.net>"); +MODULE_DESCRIPTION("PA Semi PWRficient SMBus driver"); diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 8fce98bb77ff..75b9c3f26bba 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -605,20 +605,20 @@ static int geni_i2c_gpi_xfer(struct geni_i2c_dev *gi2c, struct i2c_msg msgs[], i peripheral.addr = msgs[i].addr; + ret = geni_i2c_gpi(gi2c, &msgs[i], &config, + &tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c); + if (ret) + goto err; + if (msgs[i].flags & I2C_M_RD) { ret = geni_i2c_gpi(gi2c, &msgs[i], &config, &rx_addr, &rx_buf, I2C_READ, gi2c->rx_c); if (ret) goto err; - } - - ret = geni_i2c_gpi(gi2c, &msgs[i], &config, - &tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c); - if (ret) - goto err; - if (msgs[i].flags & I2C_M_RD) dma_async_issue_pending(gi2c->rx_c); + } + dma_async_issue_pending(gi2c->tx_c); timeout = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT); diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index b31cf4f18f85..6aa4f1f06240 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -178,6 +178,7 @@ struct rk3x_i2c_soc_data { * @clk: function clk for rk3399 or function & Bus clks for others * @pclk: Bus clk for rk3399 * @clk_rate_nb: i2c clk rate change notify + * @irq: irq number * @t: I2C known timing information * @lock: spinlock for the i2c bus * @wait: the waitqueue to wait for i2c transfer @@ -200,6 +201,7 @@ struct rk3x_i2c { struct clk *clk; struct clk *pclk; struct notifier_block clk_rate_nb; + int irq; /* Settings */ struct i2c_timings t; @@ -1087,13 +1089,18 @@ static int rk3x_i2c_xfer_common(struct i2c_adapter *adap, spin_unlock_irqrestore(&i2c->lock, flags); - rk3x_i2c_start(i2c); - if (!polling) { + rk3x_i2c_start(i2c); + timeout = wait_event_timeout(i2c->wait, !i2c->busy, msecs_to_jiffies(WAIT_TIMEOUT)); } else { + disable_irq(i2c->irq); + rk3x_i2c_start(i2c); + timeout = rk3x_i2c_wait_xfer_poll(i2c); + + enable_irq(i2c->irq); } spin_lock_irqsave(&i2c->lock, flags); @@ -1310,6 +1317,8 @@ static int rk3x_i2c_probe(struct platform_device *pdev) return ret; } + i2c->irq = irq; + platform_set_drvdata(pdev, i2c); if (i2c->soc_data->calc_timings == rk3x_i2c_v0_calc_timings) { diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index 36dab9cd208c..8e3838c42a8c 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -220,8 +220,17 @@ static bool is_ack(struct s3c24xx_i2c *i2c) int tries; for (tries = 50; tries; --tries) { - if (readl(i2c->regs + S3C2410_IICCON) - & S3C2410_IICCON_IRQPEND) { + unsigned long tmp = readl(i2c->regs + S3C2410_IICCON); + + if (!(tmp & S3C2410_IICCON_ACKEN)) { + /* + * Wait a bit for the bus to stabilize, + * delay estimated experimentally. + */ + usleep_range(100, 200); + return true; + } + if (tmp & S3C2410_IICCON_IRQPEND) { if (!(readl(i2c->regs + S3C2410_IICSTAT) & S3C2410_IICSTAT_LASTBIT)) return true; @@ -274,16 +283,6 @@ static void s3c24xx_i2c_message_start(struct s3c24xx_i2c *i2c, stat |= S3C2410_IICSTAT_START; writel(stat, i2c->regs + S3C2410_IICSTAT); - - if (i2c->quirks & QUIRK_POLL) { - while ((i2c->msg_num != 0) && is_ack(i2c)) { - i2c_s3c_irq_nextbyte(i2c, stat); - stat = readl(i2c->regs + S3C2410_IICSTAT); - - if (stat & S3C2410_IICSTAT_ARBITR) - dev_err(i2c->dev, "deal with arbitration loss\n"); - } - } } static inline void s3c24xx_i2c_stop(struct s3c24xx_i2c *i2c, int ret) @@ -690,7 +689,7 @@ static void s3c24xx_i2c_wait_idle(struct s3c24xx_i2c *i2c) static int s3c24xx_i2c_doxfer(struct s3c24xx_i2c *i2c, struct i2c_msg *msgs, int num) { - unsigned long timeout; + unsigned long timeout = 0; int ret; ret = s3c24xx_i2c_set_master(i2c); @@ -710,16 +709,19 @@ static int s3c24xx_i2c_doxfer(struct s3c24xx_i2c *i2c, s3c24xx_i2c_message_start(i2c, msgs); if (i2c->quirks & QUIRK_POLL) { - ret = i2c->msg_idx; + while ((i2c->msg_num != 0) && is_ack(i2c)) { + unsigned long stat = readl(i2c->regs + S3C2410_IICSTAT); - if (ret != num) - dev_dbg(i2c->dev, "incomplete xfer (%d)\n", ret); + i2c_s3c_irq_nextbyte(i2c, stat); - goto out; + stat = readl(i2c->regs + S3C2410_IICSTAT); + if (stat & S3C2410_IICSTAT_ARBITR) + dev_err(i2c->dev, "deal with arbitration loss\n"); + } + } else { + timeout = wait_event_timeout(i2c->wait, i2c->msg_num == 0, HZ * 5); } - timeout = wait_event_timeout(i2c->wait, i2c->msg_num == 0, HZ * 5); - ret = i2c->msg_idx; /* diff --git a/drivers/i2c/i2c-core.h b/drivers/i2c/i2c-core.h index 05b8b8dfa9bd..36587f38dff3 100644 --- a/drivers/i2c/i2c-core.h +++ b/drivers/i2c/i2c-core.h @@ -3,6 +3,7 @@ * i2c-core.h - interfaces internal to the I2C framework */ +#include <linux/kconfig.h> #include <linux/rwsem.h> struct i2c_devinfo { @@ -29,7 +30,8 @@ int i2c_dev_irq_from_resources(const struct resource *resources, */ static inline bool i2c_in_atomic_xfer_mode(void) { - return system_state > SYSTEM_RUNNING && !preemptible(); + return system_state > SYSTEM_RUNNING && + (IS_ENABLED(CONFIG_PREEMPT_COUNT) ? !preemptible() : irqs_disabled()); } static inline int __i2c_lock_bus_helper(struct i2c_adapter *adap) diff --git a/drivers/i3c/master/i3c-master-cdns.c b/drivers/i3c/master/i3c-master-cdns.c index 4a49c75a9408..b9cfda6ae9ae 100644 --- a/drivers/i3c/master/i3c-master-cdns.c +++ b/drivers/i3c/master/i3c-master-cdns.c @@ -77,7 +77,8 @@ #define PRESCL_CTRL0 0x14 #define PRESCL_CTRL0_I2C(x) ((x) << 16) #define PRESCL_CTRL0_I3C(x) (x) -#define PRESCL_CTRL0_MAX GENMASK(9, 0) +#define PRESCL_CTRL0_I3C_MAX GENMASK(9, 0) +#define PRESCL_CTRL0_I2C_MAX GENMASK(15, 0) #define PRESCL_CTRL1 0x18 #define PRESCL_CTRL1_PP_LOW_MASK GENMASK(15, 8) @@ -1234,7 +1235,7 @@ static int cdns_i3c_master_bus_init(struct i3c_master_controller *m) return -EINVAL; pres = DIV_ROUND_UP(sysclk_rate, (bus->scl_rate.i3c * 4)) - 1; - if (pres > PRESCL_CTRL0_MAX) + if (pres > PRESCL_CTRL0_I3C_MAX) return -ERANGE; bus->scl_rate.i3c = sysclk_rate / ((pres + 1) * 4); @@ -1247,7 +1248,7 @@ static int cdns_i3c_master_bus_init(struct i3c_master_controller *m) max_i2cfreq = bus->scl_rate.i2c; pres = (sysclk_rate / (max_i2cfreq * 5)) - 1; - if (pres > PRESCL_CTRL0_MAX) + if (pres > PRESCL_CTRL0_I2C_MAX) return -ERANGE; bus->scl_rate.i2c = sysclk_rate / ((pres + 1) * 5); diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index ffac66db7ac9..1f34747a68bf 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -219,10 +219,12 @@ config BMA400 config BMA400_I2C tristate + select REGMAP_I2C depends on BMA400 config BMA400_SPI tristate + select REGMAP_SPI depends on BMA400 config BMC150_ACCEL diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c index 8e252cde735b..76002b91c86a 100644 --- a/drivers/iio/adc/ad7091r-base.c +++ b/drivers/iio/adc/ad7091r-base.c @@ -6,6 +6,7 @@ */ #include <linux/bitops.h> +#include <linux/bitfield.h> #include <linux/iio/events.h> #include <linux/iio/iio.h> #include <linux/interrupt.h> @@ -28,6 +29,7 @@ #define AD7091R_REG_RESULT_CONV_RESULT(x) ((x) & 0xfff) /* AD7091R_REG_CONF */ +#define AD7091R_REG_CONF_ALERT_EN BIT(4) #define AD7091R_REG_CONF_AUTO BIT(8) #define AD7091R_REG_CONF_CMD BIT(10) @@ -49,6 +51,27 @@ struct ad7091r_state { struct mutex lock; /*lock to prevent concurent reads */ }; +const struct iio_event_spec ad7091r_events[] = { + { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_RISING, + .mask_separate = BIT(IIO_EV_INFO_VALUE) | + BIT(IIO_EV_INFO_ENABLE), + }, + { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_FALLING, + .mask_separate = BIT(IIO_EV_INFO_VALUE) | + BIT(IIO_EV_INFO_ENABLE), + }, + { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_EITHER, + .mask_separate = BIT(IIO_EV_INFO_HYSTERESIS), + }, +}; +EXPORT_SYMBOL_NS_GPL(ad7091r_events, IIO_AD7091R); + static int ad7091r_set_mode(struct ad7091r_state *st, enum ad7091r_mode mode) { int ret, conf; @@ -168,14 +191,148 @@ unlock: return ret; } +static int ad7091r_read_event_config(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir) +{ + struct ad7091r_state *st = iio_priv(indio_dev); + int val, ret; + + switch (dir) { + case IIO_EV_DIR_RISING: + ret = regmap_read(st->map, + AD7091R_REG_CH_HIGH_LIMIT(chan->channel), + &val); + if (ret) + return ret; + return val != AD7091R_HIGH_LIMIT; + case IIO_EV_DIR_FALLING: + ret = regmap_read(st->map, + AD7091R_REG_CH_LOW_LIMIT(chan->channel), + &val); + if (ret) + return ret; + return val != AD7091R_LOW_LIMIT; + default: + return -EINVAL; + } +} + +static int ad7091r_write_event_config(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, int state) +{ + struct ad7091r_state *st = iio_priv(indio_dev); + + if (state) { + return regmap_set_bits(st->map, AD7091R_REG_CONF, + AD7091R_REG_CONF_ALERT_EN); + } else { + /* + * Set thresholds either to 0 or to 2^12 - 1 as appropriate to + * prevent alerts and thus disable event generation. + */ + switch (dir) { + case IIO_EV_DIR_RISING: + return regmap_write(st->map, + AD7091R_REG_CH_HIGH_LIMIT(chan->channel), + AD7091R_HIGH_LIMIT); + case IIO_EV_DIR_FALLING: + return regmap_write(st->map, + AD7091R_REG_CH_LOW_LIMIT(chan->channel), + AD7091R_LOW_LIMIT); + default: + return -EINVAL; + } + } +} + +static int ad7091r_read_event_value(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, + enum iio_event_info info, int *val, int *val2) +{ + struct ad7091r_state *st = iio_priv(indio_dev); + int ret; + + switch (info) { + case IIO_EV_INFO_VALUE: + switch (dir) { + case IIO_EV_DIR_RISING: + ret = regmap_read(st->map, + AD7091R_REG_CH_HIGH_LIMIT(chan->channel), + val); + if (ret) + return ret; + return IIO_VAL_INT; + case IIO_EV_DIR_FALLING: + ret = regmap_read(st->map, + AD7091R_REG_CH_LOW_LIMIT(chan->channel), + val); + if (ret) + return ret; + return IIO_VAL_INT; + default: + return -EINVAL; + } + case IIO_EV_INFO_HYSTERESIS: + ret = regmap_read(st->map, + AD7091R_REG_CH_HYSTERESIS(chan->channel), + val); + if (ret) + return ret; + return IIO_VAL_INT; + default: + return -EINVAL; + } +} + +static int ad7091r_write_event_value(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, + enum iio_event_info info, int val, int val2) +{ + struct ad7091r_state *st = iio_priv(indio_dev); + + switch (info) { + case IIO_EV_INFO_VALUE: + switch (dir) { + case IIO_EV_DIR_RISING: + return regmap_write(st->map, + AD7091R_REG_CH_HIGH_LIMIT(chan->channel), + val); + case IIO_EV_DIR_FALLING: + return regmap_write(st->map, + AD7091R_REG_CH_LOW_LIMIT(chan->channel), + val); + default: + return -EINVAL; + } + case IIO_EV_INFO_HYSTERESIS: + return regmap_write(st->map, + AD7091R_REG_CH_HYSTERESIS(chan->channel), + val); + default: + return -EINVAL; + } +} + static const struct iio_info ad7091r_info = { .read_raw = ad7091r_read_raw, + .read_event_config = &ad7091r_read_event_config, + .write_event_config = &ad7091r_write_event_config, + .read_event_value = &ad7091r_read_event_value, + .write_event_value = &ad7091r_write_event_value, }; static irqreturn_t ad7091r_event_handler(int irq, void *private) { - struct ad7091r_state *st = (struct ad7091r_state *) private; - struct iio_dev *iio_dev = dev_get_drvdata(st->dev); + struct iio_dev *iio_dev = private; + struct ad7091r_state *st = iio_priv(iio_dev); unsigned int i, read_val; int ret; s64 timestamp = iio_get_time_ns(iio_dev); @@ -232,9 +389,14 @@ int ad7091r_probe(struct device *dev, const char *name, iio_dev->channels = chip_info->channels; if (irq) { + ret = regmap_update_bits(st->map, AD7091R_REG_CONF, + AD7091R_REG_CONF_ALERT_EN, BIT(4)); + if (ret) + return ret; + ret = devm_request_threaded_irq(dev, irq, NULL, ad7091r_event_handler, - IRQF_TRIGGER_FALLING | IRQF_ONESHOT, name, st); + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, name, iio_dev); if (ret) return ret; } @@ -243,7 +405,14 @@ int ad7091r_probe(struct device *dev, const char *name, if (IS_ERR(st->vref)) { if (PTR_ERR(st->vref) == -EPROBE_DEFER) return -EPROBE_DEFER; + st->vref = NULL; + /* Enable internal vref */ + ret = regmap_set_bits(st->map, AD7091R_REG_CONF, + AD7091R_REG_CONF_INT_VREF); + if (ret) + return dev_err_probe(st->dev, ret, + "Error on enable internal reference\n"); } else { ret = regulator_enable(st->vref); if (ret) diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h index 509748aef9b1..b9e1c8bf3440 100644 --- a/drivers/iio/adc/ad7091r-base.h +++ b/drivers/iio/adc/ad7091r-base.h @@ -8,6 +8,12 @@ #ifndef __DRIVERS_IIO_ADC_AD7091R_BASE_H__ #define __DRIVERS_IIO_ADC_AD7091R_BASE_H__ +#define AD7091R_REG_CONF_INT_VREF BIT(0) + +/* AD7091R_REG_CH_LIMIT */ +#define AD7091R_HIGH_LIMIT 0xFFF +#define AD7091R_LOW_LIMIT 0x0 + struct device; struct ad7091r_state; @@ -17,6 +23,8 @@ struct ad7091r_chip_info { unsigned int vref_mV; }; +extern const struct iio_event_spec ad7091r_events[3]; + extern const struct regmap_config ad7091r_regmap_config; int ad7091r_probe(struct device *dev, const char *name, diff --git a/drivers/iio/adc/ad7091r5.c b/drivers/iio/adc/ad7091r5.c index 47f5763023a4..12d475463945 100644 --- a/drivers/iio/adc/ad7091r5.c +++ b/drivers/iio/adc/ad7091r5.c @@ -12,26 +12,6 @@ #include "ad7091r-base.h" -static const struct iio_event_spec ad7091r5_events[] = { - { - .type = IIO_EV_TYPE_THRESH, - .dir = IIO_EV_DIR_RISING, - .mask_separate = BIT(IIO_EV_INFO_VALUE) | - BIT(IIO_EV_INFO_ENABLE), - }, - { - .type = IIO_EV_TYPE_THRESH, - .dir = IIO_EV_DIR_FALLING, - .mask_separate = BIT(IIO_EV_INFO_VALUE) | - BIT(IIO_EV_INFO_ENABLE), - }, - { - .type = IIO_EV_TYPE_THRESH, - .dir = IIO_EV_DIR_EITHER, - .mask_separate = BIT(IIO_EV_INFO_HYSTERESIS), - }, -}; - #define AD7091R_CHANNEL(idx, bits, ev, num_ev) { \ .type = IIO_VOLTAGE, \ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \ @@ -44,10 +24,10 @@ static const struct iio_event_spec ad7091r5_events[] = { .scan_type.realbits = bits, \ } static const struct iio_chan_spec ad7091r5_channels_irq[] = { - AD7091R_CHANNEL(0, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)), - AD7091R_CHANNEL(1, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)), - AD7091R_CHANNEL(2, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)), - AD7091R_CHANNEL(3, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)), + AD7091R_CHANNEL(0, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)), + AD7091R_CHANNEL(1, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)), + AD7091R_CHANNEL(2, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)), + AD7091R_CHANNEL(3, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)), }; static const struct iio_chan_spec ad7091r5_channels_noirq[] = { diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c index 7534572f7475..811525857d29 100644 --- a/drivers/iio/adc/ad9467.c +++ b/drivers/iio/adc/ad9467.c @@ -119,9 +119,9 @@ struct ad9467_state { struct spi_device *spi; struct clk *clk; unsigned int output_mode; + unsigned int (*scales)[2]; struct gpio_desc *pwrdown_gpio; - struct gpio_desc *reset_gpio; }; static int ad9467_spi_read(struct spi_device *spi, unsigned int reg) @@ -163,9 +163,10 @@ static int ad9467_reg_access(struct adi_axi_adc_conv *conv, unsigned int reg, if (readval == NULL) { ret = ad9467_spi_write(spi, reg, writeval); - ad9467_spi_write(spi, AN877_ADC_REG_TRANSFER, - AN877_ADC_TRANSFER_SYNC); - return ret; + if (ret) + return ret; + return ad9467_spi_write(spi, AN877_ADC_REG_TRANSFER, + AN877_ADC_TRANSFER_SYNC); } ret = ad9467_spi_read(spi, reg); @@ -212,6 +213,7 @@ static void __ad9467_get_scale(struct adi_axi_adc_conv *conv, int index, .channel = _chan, \ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE) | \ BIT(IIO_CHAN_INFO_SAMP_FREQ), \ + .info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE), \ .scan_index = _si, \ .scan_type = { \ .sign = _sign, \ @@ -273,10 +275,13 @@ static int ad9467_get_scale(struct adi_axi_adc_conv *conv, int *val, int *val2) const struct ad9467_chip_info *info1 = to_ad9467_chip_info(info); struct ad9467_state *st = adi_axi_adc_conv_priv(conv); unsigned int i, vref_val; + int ret; - vref_val = ad9467_spi_read(st->spi, AN877_ADC_REG_VREF); + ret = ad9467_spi_read(st->spi, AN877_ADC_REG_VREF); + if (ret < 0) + return ret; - vref_val &= info1->vref_mask; + vref_val = ret & info1->vref_mask; for (i = 0; i < info->num_scales; i++) { if (vref_val == info->scale_table[i][1]) @@ -297,6 +302,7 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2) struct ad9467_state *st = adi_axi_adc_conv_priv(conv); unsigned int scale_val[2]; unsigned int i; + int ret; if (val != 0) return -EINVAL; @@ -306,11 +312,13 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2) if (scale_val[0] != val || scale_val[1] != val2) continue; - ad9467_spi_write(st->spi, AN877_ADC_REG_VREF, - info->scale_table[i][1]); - ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER, - AN877_ADC_TRANSFER_SYNC); - return 0; + ret = ad9467_spi_write(st->spi, AN877_ADC_REG_VREF, + info->scale_table[i][1]); + if (ret < 0) + return ret; + + return ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER, + AN877_ADC_TRANSFER_SYNC); } return -EINVAL; @@ -359,6 +367,26 @@ static int ad9467_write_raw(struct adi_axi_adc_conv *conv, } } +static int ad9467_read_avail(struct adi_axi_adc_conv *conv, + struct iio_chan_spec const *chan, + const int **vals, int *type, int *length, + long mask) +{ + const struct adi_axi_adc_chip_info *info = conv->chip_info; + struct ad9467_state *st = adi_axi_adc_conv_priv(conv); + + switch (mask) { + case IIO_CHAN_INFO_SCALE: + *vals = (const int *)st->scales; + *type = IIO_VAL_INT_PLUS_MICRO; + /* Values are stored in a 2D matrix */ + *length = info->num_scales * 2; + return IIO_AVAIL_LIST; + default: + return -EINVAL; + } +} + static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode) { int ret; @@ -371,6 +399,26 @@ static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode) AN877_ADC_TRANSFER_SYNC); } +static int ad9467_scale_fill(struct adi_axi_adc_conv *conv) +{ + const struct adi_axi_adc_chip_info *info = conv->chip_info; + struct ad9467_state *st = adi_axi_adc_conv_priv(conv); + unsigned int i, val1, val2; + + st->scales = devm_kmalloc_array(&st->spi->dev, info->num_scales, + sizeof(*st->scales), GFP_KERNEL); + if (!st->scales) + return -ENOMEM; + + for (i = 0; i < info->num_scales; i++) { + __ad9467_get_scale(conv, i, &val1, &val2); + st->scales[i][0] = val1; + st->scales[i][1] = val2; + } + + return 0; +} + static int ad9467_preenable_setup(struct adi_axi_adc_conv *conv) { struct ad9467_state *st = adi_axi_adc_conv_priv(conv); @@ -378,6 +426,21 @@ static int ad9467_preenable_setup(struct adi_axi_adc_conv *conv) return ad9467_outputmode_set(st->spi, st->output_mode); } +static int ad9467_reset(struct device *dev) +{ + struct gpio_desc *gpio; + + gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR_OR_NULL(gpio)) + return PTR_ERR_OR_ZERO(gpio); + + fsleep(1); + gpiod_set_value_cansleep(gpio, 0); + fsleep(10 * USEC_PER_MSEC); + + return 0; +} + static int ad9467_probe(struct spi_device *spi) { const struct ad9467_chip_info *info; @@ -406,21 +469,16 @@ static int ad9467_probe(struct spi_device *spi) if (IS_ERR(st->pwrdown_gpio)) return PTR_ERR(st->pwrdown_gpio); - st->reset_gpio = devm_gpiod_get_optional(&spi->dev, "reset", - GPIOD_OUT_LOW); - if (IS_ERR(st->reset_gpio)) - return PTR_ERR(st->reset_gpio); - - if (st->reset_gpio) { - udelay(1); - ret = gpiod_direction_output(st->reset_gpio, 1); - if (ret) - return ret; - mdelay(10); - } + ret = ad9467_reset(&spi->dev); + if (ret) + return ret; conv->chip_info = &info->axi_adc_info; + ret = ad9467_scale_fill(conv); + if (ret) + return ret; + id = ad9467_spi_read(spi, AN877_ADC_REG_CHIP_ID); if (id != conv->chip_info->id) { dev_err(&spi->dev, "Mismatch CHIP_ID, got 0x%X, expected 0x%X\n", @@ -431,6 +489,7 @@ static int ad9467_probe(struct spi_device *spi) conv->reg_access = ad9467_reg_access; conv->write_raw = ad9467_write_raw; conv->read_raw = ad9467_read_raw; + conv->read_avail = ad9467_read_avail; conv->preenable_setup = ad9467_preenable_setup; st->output_mode = info->default_output_mode | diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c index e8a8ea4140f1..ad386ac7f03c 100644 --- a/drivers/iio/adc/adi-axi-adc.c +++ b/drivers/iio/adc/adi-axi-adc.c @@ -143,6 +143,20 @@ static int adi_axi_adc_write_raw(struct iio_dev *indio_dev, return conv->write_raw(conv, chan, val, val2, mask); } +static int adi_axi_adc_read_avail(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + const int **vals, int *type, int *length, + long mask) +{ + struct adi_axi_adc_state *st = iio_priv(indio_dev); + struct adi_axi_adc_conv *conv = &st->client->conv; + + if (!conv->read_avail) + return -EOPNOTSUPP; + + return conv->read_avail(conv, chan, vals, type, length, mask); +} + static int adi_axi_adc_update_scan_mode(struct iio_dev *indio_dev, const unsigned long *scan_mask) { @@ -227,69 +241,11 @@ struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev, } EXPORT_SYMBOL_NS_GPL(devm_adi_axi_adc_conv_register, IIO_ADI_AXI); -static ssize_t in_voltage_scale_available_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct adi_axi_adc_state *st = iio_priv(indio_dev); - struct adi_axi_adc_conv *conv = &st->client->conv; - size_t len = 0; - int i; - - for (i = 0; i < conv->chip_info->num_scales; i++) { - const unsigned int *s = conv->chip_info->scale_table[i]; - - len += scnprintf(buf + len, PAGE_SIZE - len, - "%u.%06u ", s[0], s[1]); - } - buf[len - 1] = '\n'; - - return len; -} - -static IIO_DEVICE_ATTR_RO(in_voltage_scale_available, 0); - -enum { - ADI_AXI_ATTR_SCALE_AVAIL, -}; - -#define ADI_AXI_ATTR(_en_, _file_) \ - [ADI_AXI_ATTR_##_en_] = &iio_dev_attr_##_file_.dev_attr.attr - -static struct attribute *adi_axi_adc_attributes[] = { - ADI_AXI_ATTR(SCALE_AVAIL, in_voltage_scale_available), - NULL -}; - -static umode_t axi_adc_attr_is_visible(struct kobject *kobj, - struct attribute *attr, int n) -{ - struct device *dev = kobj_to_dev(kobj); - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct adi_axi_adc_state *st = iio_priv(indio_dev); - struct adi_axi_adc_conv *conv = &st->client->conv; - - switch (n) { - case ADI_AXI_ATTR_SCALE_AVAIL: - if (!conv->chip_info->num_scales) - return 0; - return attr->mode; - default: - return attr->mode; - } -} - -static const struct attribute_group adi_axi_adc_attribute_group = { - .attrs = adi_axi_adc_attributes, - .is_visible = axi_adc_attr_is_visible, -}; - static const struct iio_info adi_axi_adc_info = { .read_raw = &adi_axi_adc_read_raw, .write_raw = &adi_axi_adc_write_raw, - .attrs = &adi_axi_adc_attribute_group, .update_scan_mode = &adi_axi_adc_update_scan_mode, + .read_avail = &adi_axi_adc_read_avail, }; static const struct adi_axi_adc_core_info adi_axi_adc_10_0_a_info = { diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 642c5c4895e3..3ac253a27dd9 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -671,8 +671,10 @@ static int tiadc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, indio_dev); err = tiadc_request_dma(pdev, adc_dev); - if (err && err == -EPROBE_DEFER) + if (err && err != -ENODEV) { + dev_err_probe(&pdev->dev, err, "DMA request failed\n"); goto err_dma; + } return 0; diff --git a/drivers/iio/buffer/industrialio-triggered-buffer.c b/drivers/iio/buffer/industrialio-triggered-buffer.c index 8d4fc97d1005..2b7873e8a959 100644 --- a/drivers/iio/buffer/industrialio-triggered-buffer.c +++ b/drivers/iio/buffer/industrialio-triggered-buffer.c @@ -46,6 +46,16 @@ int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev, struct iio_buffer *buffer; int ret; + /* + * iio_triggered_buffer_cleanup() assumes that the buffer allocated here + * is assigned to indio_dev->buffer but this is only the case if this + * function is the first caller to iio_device_attach_buffer(). If + * indio_dev->buffer is already set then we can't proceed otherwise the + * cleanup function will try to free a buffer that was not allocated here. + */ + if (indio_dev->buffer) + return -EADDRINUSE; + buffer = iio_kfifo_allocate(); if (!buffer) { ret = -ENOMEM; diff --git a/drivers/iio/common/ms_sensors/ms_sensors_i2c.c b/drivers/iio/common/ms_sensors/ms_sensors_i2c.c index 6633b35a94e6..9c9bc77003c7 100644 --- a/drivers/iio/common/ms_sensors/ms_sensors_i2c.c +++ b/drivers/iio/common/ms_sensors/ms_sensors_i2c.c @@ -15,8 +15,8 @@ /* Conversion times in us */ static const u16 ms_sensors_ht_t_conversion_time[] = { 50000, 25000, 13000, 7000 }; -static const u16 ms_sensors_ht_h_conversion_time[] = { 16000, 3000, - 5000, 8000 }; +static const u16 ms_sensors_ht_h_conversion_time[] = { 16000, 5000, + 3000, 8000 }; static const u16 ms_sensors_tp_conversion_time[] = { 500, 1100, 2100, 4100, 8220, 16440 }; diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c index aec55f7e1f26..2d939773445d 100644 --- a/drivers/iio/imu/adis16475.c +++ b/drivers/iio/imu/adis16475.c @@ -1243,50 +1243,6 @@ static int adis16475_config_irq_pin(struct adis16475 *st) return 0; } -static const struct of_device_id adis16475_of_match[] = { - { .compatible = "adi,adis16470", - .data = &adis16475_chip_info[ADIS16470] }, - { .compatible = "adi,adis16475-1", - .data = &adis16475_chip_info[ADIS16475_1] }, - { .compatible = "adi,adis16475-2", - .data = &adis16475_chip_info[ADIS16475_2] }, - { .compatible = "adi,adis16475-3", - .data = &adis16475_chip_info[ADIS16475_3] }, - { .compatible = "adi,adis16477-1", - .data = &adis16475_chip_info[ADIS16477_1] }, - { .compatible = "adi,adis16477-2", - .data = &adis16475_chip_info[ADIS16477_2] }, - { .compatible = "adi,adis16477-3", - .data = &adis16475_chip_info[ADIS16477_3] }, - { .compatible = "adi,adis16465-1", - .data = &adis16475_chip_info[ADIS16465_1] }, - { .compatible = "adi,adis16465-2", - .data = &adis16475_chip_info[ADIS16465_2] }, - { .compatible = "adi,adis16465-3", - .data = &adis16475_chip_info[ADIS16465_3] }, - { .compatible = "adi,adis16467-1", - .data = &adis16475_chip_info[ADIS16467_1] }, - { .compatible = "adi,adis16467-2", - .data = &adis16475_chip_info[ADIS16467_2] }, - { .compatible = "adi,adis16467-3", - .data = &adis16475_chip_info[ADIS16467_3] }, - { .compatible = "adi,adis16500", - .data = &adis16475_chip_info[ADIS16500] }, - { .compatible = "adi,adis16505-1", - .data = &adis16475_chip_info[ADIS16505_1] }, - { .compatible = "adi,adis16505-2", - .data = &adis16475_chip_info[ADIS16505_2] }, - { .compatible = "adi,adis16505-3", - .data = &adis16475_chip_info[ADIS16505_3] }, - { .compatible = "adi,adis16507-1", - .data = &adis16475_chip_info[ADIS16507_1] }, - { .compatible = "adi,adis16507-2", - .data = &adis16475_chip_info[ADIS16507_2] }, - { .compatible = "adi,adis16507-3", - .data = &adis16475_chip_info[ADIS16507_3] }, - { }, -}; -MODULE_DEVICE_TABLE(of, adis16475_of_match); static int adis16475_probe(struct spi_device *spi) { @@ -1300,7 +1256,7 @@ static int adis16475_probe(struct spi_device *spi) st = iio_priv(indio_dev); - st->info = device_get_match_data(&spi->dev); + st->info = spi_get_device_match_data(spi); if (!st->info) return -EINVAL; @@ -1340,12 +1296,83 @@ static int adis16475_probe(struct spi_device *spi) return 0; } +static const struct of_device_id adis16475_of_match[] = { + { .compatible = "adi,adis16470", + .data = &adis16475_chip_info[ADIS16470] }, + { .compatible = "adi,adis16475-1", + .data = &adis16475_chip_info[ADIS16475_1] }, + { .compatible = "adi,adis16475-2", + .data = &adis16475_chip_info[ADIS16475_2] }, + { .compatible = "adi,adis16475-3", + .data = &adis16475_chip_info[ADIS16475_3] }, + { .compatible = "adi,adis16477-1", + .data = &adis16475_chip_info[ADIS16477_1] }, + { .compatible = "adi,adis16477-2", + .data = &adis16475_chip_info[ADIS16477_2] }, + { .compatible = "adi,adis16477-3", + .data = &adis16475_chip_info[ADIS16477_3] }, + { .compatible = "adi,adis16465-1", + .data = &adis16475_chip_info[ADIS16465_1] }, + { .compatible = "adi,adis16465-2", + .data = &adis16475_chip_info[ADIS16465_2] }, + { .compatible = "adi,adis16465-3", + .data = &adis16475_chip_info[ADIS16465_3] }, + { .compatible = "adi,adis16467-1", + .data = &adis16475_chip_info[ADIS16467_1] }, + { .compatible = "adi,adis16467-2", + .data = &adis16475_chip_info[ADIS16467_2] }, + { .compatible = "adi,adis16467-3", + .data = &adis16475_chip_info[ADIS16467_3] }, + { .compatible = "adi,adis16500", + .data = &adis16475_chip_info[ADIS16500] }, + { .compatible = "adi,adis16505-1", + .data = &adis16475_chip_info[ADIS16505_1] }, + { .compatible = "adi,adis16505-2", + .data = &adis16475_chip_info[ADIS16505_2] }, + { .compatible = "adi,adis16505-3", + .data = &adis16475_chip_info[ADIS16505_3] }, + { .compatible = "adi,adis16507-1", + .data = &adis16475_chip_info[ADIS16507_1] }, + { .compatible = "adi,adis16507-2", + .data = &adis16475_chip_info[ADIS16507_2] }, + { .compatible = "adi,adis16507-3", + .data = &adis16475_chip_info[ADIS16507_3] }, + { }, +}; +MODULE_DEVICE_TABLE(of, adis16475_of_match); + +static const struct spi_device_id adis16475_ids[] = { + { "adis16470", (kernel_ulong_t)&adis16475_chip_info[ADIS16470] }, + { "adis16475-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_1] }, + { "adis16475-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_2] }, + { "adis16475-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_3] }, + { "adis16477-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_1] }, + { "adis16477-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_2] }, + { "adis16477-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_3] }, + { "adis16465-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_1] }, + { "adis16465-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_2] }, + { "adis16465-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_3] }, + { "adis16467-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_1] }, + { "adis16467-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_2] }, + { "adis16467-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_3] }, + { "adis16500", (kernel_ulong_t)&adis16475_chip_info[ADIS16500] }, + { "adis16505-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_1] }, + { "adis16505-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_2] }, + { "adis16505-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_3] }, + { "adis16507-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_1] }, + { "adis16507-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_2] }, + { "adis16507-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_3] }, + { } +}; +MODULE_DEVICE_TABLE(spi, adis16475_ids); + static struct spi_driver adis16475_driver = { .driver = { .name = "adis16475", .of_match_table = adis16475_of_match, }, .probe = adis16475_probe, + .id_table = adis16475_ids, }; module_spi_driver(adis16475_driver); diff --git a/drivers/iio/imu/bno055/Kconfig b/drivers/iio/imu/bno055/Kconfig index 83e53acfbe88..c7f5866a177d 100644 --- a/drivers/iio/imu/bno055/Kconfig +++ b/drivers/iio/imu/bno055/Kconfig @@ -8,6 +8,7 @@ config BOSCH_BNO055 config BOSCH_BNO055_SERIAL tristate "Bosch BNO055 attached via UART" depends on SERIAL_DEV_BUS + select REGMAP select BOSCH_BNO055 help Enable this to support Bosch BNO055 IMUs attached via UART. diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c index 86fbbe904050..19a1ef5351d2 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c @@ -736,13 +736,13 @@ inv_mpu6050_read_raw(struct iio_dev *indio_dev, ret = inv_mpu6050_sensor_show(st, st->reg->gyro_offset, chan->channel2, val); mutex_unlock(&st->lock); - return IIO_VAL_INT; + return ret; case IIO_ACCEL: mutex_lock(&st->lock); ret = inv_mpu6050_sensor_show(st, st->reg->accl_offset, chan->channel2, val); mutex_unlock(&st->lock); - return IIO_VAL_INT; + return ret; default: return -EINVAL; diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index c9614982cb67..a2f8278f0085 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1601,10 +1601,13 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev) ret = iio_device_register_sysfs_group(indio_dev, &iio_dev_opaque->chan_attr_group); if (ret) - goto error_clear_attrs; + goto error_free_chan_attrs; return 0; +error_free_chan_attrs: + kfree(iio_dev_opaque->chan_attr_group.attrs); + iio_dev_opaque->chan_attr_group.attrs = NULL; error_clear_attrs: iio_free_chan_devattr_list(&iio_dev_opaque->channel_attr_list); diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c index 5a1a625d8d16..85097b769c20 100644 --- a/drivers/iio/light/hid-sensor-als.c +++ b/drivers/iio/light/hid-sensor-als.c @@ -228,6 +228,7 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev, case HID_USAGE_SENSOR_TIME_TIMESTAMP: als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes, *(s64 *)raw_data); + ret = 0; break; default: break; diff --git a/drivers/iio/magnetometer/rm3100-core.c b/drivers/iio/magnetometer/rm3100-core.c index 69938204456f..42b70cd42b39 100644 --- a/drivers/iio/magnetometer/rm3100-core.c +++ b/drivers/iio/magnetometer/rm3100-core.c @@ -530,6 +530,7 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq) struct rm3100_data *data; unsigned int tmp; int ret; + int samp_rate_index; indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); if (!indio_dev) @@ -586,9 +587,14 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq) ret = regmap_read(regmap, RM3100_REG_TMRC, &tmp); if (ret < 0) return ret; + + samp_rate_index = tmp - RM3100_TMRC_OFFSET; + if (samp_rate_index < 0 || samp_rate_index >= RM3100_SAMP_NUM) { + dev_err(dev, "The value read from RM3100_REG_TMRC is invalid!\n"); + return -EINVAL; + } /* Initializing max wait time, which is double conversion time. */ - data->conversion_time = rm3100_samp_rates[tmp - RM3100_TMRC_OFFSET][2] - * 2; + data->conversion_time = rm3100_samp_rates[samp_rate_index][2] * 2; /* Cycle count values may not be what we want. */ if ((tmp - RM3100_TMRC_OFFSET) == 0) diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 4ed8814efde6..6ed0568747ea 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -1710,7 +1710,7 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, switch (srq_attr_mask) { case IB_SRQ_MAX_WR: /* SRQ resize is not supported */ - break; + return -EINVAL; case IB_SRQ_LIMIT: /* Change the SRQ threshold */ if (srq_attr->srq_limit > srq->qplib_srq.max_wqe) @@ -1725,13 +1725,12 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, /* On success, update the shadow */ srq->srq_limit = srq_attr->srq_limit; /* No need to Build and send response back to udata */ - break; + return 0; default: ibdev_err(&rdev->ibdev, "Unsupported srq_attr_mask 0x%x", srq_attr_mask); return -EINVAL; } - return 0; } int bnxt_re_query_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr) diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 51ae58c02b15..802b0e5801a7 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -2089,7 +2089,7 @@ int init_credit_return(struct hfi1_devdata *dd) "Unable to allocate credit return DMA range for NUMA %d\n", i); ret = -ENOMEM; - goto done; + goto free_cr_base; } } set_dev_node(&dd->pcidev->dev, dd->node); @@ -2097,6 +2097,10 @@ int init_credit_return(struct hfi1_devdata *dd) ret = 0; done: return ret; + +free_cr_base: + free_credit_return(dd); + goto done; } void free_credit_return(struct hfi1_devdata *dd) diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 26c62162759b..969c5c3ab859 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -3158,7 +3158,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) { int rval = 0; - if ((unlikely(tx->num_desc + 1 == tx->desc_limit))) { + if ((unlikely(tx->num_desc == tx->desc_limit))) { rval = _extend_sdma_tx_descs(dd, tx); if (rval) { __sdma_txclean(dd, tx); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index c2ee80546d12..58fbb1d3b7f4 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -2819,6 +2819,10 @@ static int free_mr_alloc_res(struct hns_roce_dev *hr_dev) return 0; create_failed_qp: + for (i--; i >= 0; i--) { + hns_roce_v2_destroy_qp(&free_mr->rsv_qp[i]->ibqp, NULL); + kfree(free_mr->rsv_qp[i]); + } hns_roce_destroy_cq(cq, NULL); kfree(cq); @@ -5791,7 +5795,7 @@ static int hns_roce_v2_modify_srq(struct ib_srq *ibsrq, /* Resizing SRQs is not supported yet */ if (srq_attr_mask & IB_SRQ_MAX_WR) - return -EINVAL; + return -EOPNOTSUPP; if (srq_attr_mask & IB_SRQ_LIMIT) { if (srq_attr->srq_limit > srq->wqe_cnt) diff --git a/drivers/infiniband/hw/hns/hns_roce_pd.c b/drivers/infiniband/hw/hns/hns_roce_pd.c index 783e71852c50..bd1fe89ca205 100644 --- a/drivers/infiniband/hw/hns/hns_roce_pd.c +++ b/drivers/infiniband/hw/hns/hns_roce_pd.c @@ -150,7 +150,7 @@ int hns_roce_alloc_xrcd(struct ib_xrcd *ib_xrcd, struct ib_udata *udata) int ret; if (!(hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)) - return -EINVAL; + return -EOPNOTSUPP; ret = hns_roce_xrcd_alloc(hr_dev, &xrcd->xrcdn); if (ret) diff --git a/drivers/infiniband/hw/irdma/defs.h b/drivers/infiniband/hw/irdma/defs.h index ad54260cb58c..ebe98fa2b1cd 100644 --- a/drivers/infiniband/hw/irdma/defs.h +++ b/drivers/infiniband/hw/irdma/defs.h @@ -345,6 +345,7 @@ enum irdma_cqp_op_type { #define IRDMA_AE_LLP_TOO_MANY_KEEPALIVE_RETRIES 0x050b #define IRDMA_AE_LLP_DOUBT_REACHABILITY 0x050c #define IRDMA_AE_LLP_CONNECTION_ESTABLISHED 0x050e +#define IRDMA_AE_LLP_TOO_MANY_RNRS 0x050f #define IRDMA_AE_RESOURCE_EXHAUSTION 0x0520 #define IRDMA_AE_RESET_SENT 0x0601 #define IRDMA_AE_TERMINATE_SENT 0x0602 diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 311a1138e838..918a2d783141 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -379,6 +379,7 @@ static void irdma_process_aeq(struct irdma_pci_f *rf) case IRDMA_AE_LLP_TOO_MANY_RETRIES: case IRDMA_AE_LCE_QP_CATASTROPHIC: case IRDMA_AE_LCE_FUNCTION_CATASTROPHIC: + case IRDMA_AE_LLP_TOO_MANY_RNRS: case IRDMA_AE_LCE_CQ_CATASTROPHIC: case IRDMA_AE_UDA_XMIT_DGRAM_TOO_LONG: default: @@ -562,6 +563,13 @@ static void irdma_destroy_irq(struct irdma_pci_f *rf, dev->irq_ops->irdma_dis_irq(dev, msix_vec->idx); irq_update_affinity_hint(msix_vec->irq, NULL); free_irq(msix_vec->irq, dev_id); + if (rf == dev_id) { + tasklet_kill(&rf->dpc_tasklet); + } else { + struct irdma_ceq *iwceq = (struct irdma_ceq *)dev_id; + + tasklet_kill(&iwceq->dpc_tasklet); + } } /** diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 447e1bcc82a3..42c671f20923 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -762,7 +762,9 @@ static int irdma_validate_qp_attrs(struct ib_qp_init_attr *init_attr, if (init_attr->cap.max_inline_data > uk_attrs->max_hw_inline || init_attr->cap.max_send_sge > uk_attrs->max_hw_wq_frags || - init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags) + init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags || + init_attr->cap.max_send_wr > uk_attrs->max_hw_wq_quanta || + init_attr->cap.max_recv_wr > uk_attrs->max_hw_rq_quanta) return -EINVAL; if (rdma_protocol_roce(&iwdev->ibdev, 1)) { @@ -2119,9 +2121,8 @@ static int irdma_create_cq(struct ib_cq *ibcq, info.cq_base_pa = iwcq->kmem.pa; } - if (dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2) - info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2, - (u32)IRDMA_MAX_CQ_READ_THRESH); + info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2, + (u32)IRDMA_MAX_CQ_READ_THRESH); if (irdma_sc_cq_init(cq, &info)) { ibdev_dbg(&iwdev->ibdev, "VERBS: init cq fail\n"); @@ -2825,7 +2826,7 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len, iwmr->ibmr.pd = pd; iwmr->ibmr.device = pd->device; iwmr->ibmr.iova = virt; - iwmr->page_size = PAGE_SIZE; + iwmr->page_size = SZ_4K; if (req.reg_type == IRDMA_MEMREG_TYPE_MEM) { iwmr->page_size = ib_umem_find_best_pgsz(region, @@ -2845,6 +2846,13 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len, switch (req.reg_type) { case IRDMA_MEMREG_TYPE_QP: + /* iWarp: Catch page not starting on OS page boundary */ + if (!rdma_protocol_roce(&iwdev->ibdev, 1) && + ib_umem_offset(iwmr->region)) { + err = -EINVAL; + goto error; + } + total = req.sq_pages + req.rq_pages + shadow_pgcnt; if (total > iwmr->page_cnt) { err = -EINVAL; diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c index f330ce895d88..8fe0cef7e2be 100644 --- a/drivers/infiniband/hw/mthca/mthca_cmd.c +++ b/drivers/infiniband/hw/mthca/mthca_cmd.c @@ -635,7 +635,7 @@ void mthca_free_mailbox(struct mthca_dev *dev, struct mthca_mailbox *mailbox) int mthca_SYS_EN(struct mthca_dev *dev) { - u64 out; + u64 out = 0; int ret; ret = mthca_cmd_imm(dev, 0, &out, 0, 0, CMD_SYS_EN, CMD_TIME_CLASS_D); @@ -1955,7 +1955,7 @@ int mthca_WRITE_MGM(struct mthca_dev *dev, int index, int mthca_MGID_HASH(struct mthca_dev *dev, struct mthca_mailbox *mailbox, u16 *hash) { - u64 imm; + u64 imm = 0; int err; err = mthca_cmd_imm(dev, mailbox->dma, &imm, 0, 0, CMD_MGID_HASH, diff --git a/drivers/infiniband/hw/mthca/mthca_main.c b/drivers/infiniband/hw/mthca/mthca_main.c index b54bc8865dae..1ab268b77096 100644 --- a/drivers/infiniband/hw/mthca/mthca_main.c +++ b/drivers/infiniband/hw/mthca/mthca_main.c @@ -382,7 +382,7 @@ static int mthca_init_icm(struct mthca_dev *mdev, struct mthca_init_hca_param *init_hca, u64 icm_size) { - u64 aux_pages; + u64 aux_pages = 0; int err; err = mthca_SET_ICM_SIZE(mdev, icm_size, &aux_pages); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index d745ce9dc88a..61755b5f3e20 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1879,8 +1879,17 @@ static int qedr_create_user_qp(struct qedr_dev *dev, /* RQ - read access only (0) */ rc = qedr_init_user_queue(udata, dev, &qp->urq, ureq.rq_addr, ureq.rq_len, true, 0, alloc_and_init); - if (rc) + if (rc) { + ib_umem_release(qp->usq.umem); + qp->usq.umem = NULL; + if (rdma_protocol_roce(&dev->ibdev, 1)) { + qedr_free_pbl(dev, &qp->usq.pbl_info, + qp->usq.pbl_tbl); + } else { + kfree(qp->usq.pbl_tbl); + } return rc; + } } memset(&in_params, 0, sizeof(in_params)); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 5b3154503bf4..319d4288eddd 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -531,21 +531,18 @@ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) rec.join_state = SENDONLY_FULLMEMBER_JOIN; } - spin_unlock_irq(&priv->lock); multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port, - &rec, comp_mask, GFP_KERNEL, + &rec, comp_mask, GFP_ATOMIC, ipoib_mcast_join_complete, mcast); - spin_lock_irq(&priv->lock); if (IS_ERR(multicast)) { ret = PTR_ERR(multicast); ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret); /* Requeue this join task with a backoff delay */ __ipoib_mcast_schedule_join_thread(priv, mcast, 1); clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - spin_unlock_irq(&priv->lock); complete(&mcast->done); - spin_lock_irq(&priv->lock); + return ret; } return 0; } diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h index dee8c97ff056..d967d5532459 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.h +++ b/drivers/infiniband/ulp/iser/iscsi_iser.h @@ -317,12 +317,10 @@ struct iser_device { * * @mr: memory region * @sig_mr: signature memory region - * @mr_valid: is mr valid indicator */ struct iser_reg_resources { struct ib_mr *mr; struct ib_mr *sig_mr; - u8 mr_valid:1; }; /** diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c index 7b83f48f60c5..8ec470c519e8 100644 --- a/drivers/infiniband/ulp/iser/iser_initiator.c +++ b/drivers/infiniband/ulp/iser/iser_initiator.c @@ -580,7 +580,10 @@ static inline int iser_inv_desc(struct iser_fr_desc *desc, u32 rkey) return -EINVAL; } - desc->rsc.mr_valid = 0; + if (desc->sig_protected) + desc->rsc.sig_mr->need_inval = false; + else + desc->rsc.mr->need_inval = false; return 0; } diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 29ae2c6a250a..6efcb79c8efe 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -264,7 +264,7 @@ static int iser_reg_sig_mr(struct iscsi_iser_task *iser_task, iser_set_prot_checks(iser_task->sc, &sig_attrs->check_mask); - if (rsc->mr_valid) + if (rsc->sig_mr->need_inval) iser_inv_rkey(&tx_desc->inv_wr, mr, cqe, &wr->wr); ib_update_fast_reg_key(mr, ib_inc_rkey(mr->rkey)); @@ -288,7 +288,7 @@ static int iser_reg_sig_mr(struct iscsi_iser_task *iser_task, wr->access = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ | IB_ACCESS_REMOTE_WRITE; - rsc->mr_valid = 1; + rsc->sig_mr->need_inval = true; sig_reg->sge.lkey = mr->lkey; sig_reg->rkey = mr->rkey; @@ -313,7 +313,7 @@ static int iser_fast_reg_mr(struct iscsi_iser_task *iser_task, struct ib_reg_wr *wr = &tx_desc->reg_wr; int n; - if (rsc->mr_valid) + if (rsc->mr->need_inval) iser_inv_rkey(&tx_desc->inv_wr, mr, cqe, &wr->wr); ib_update_fast_reg_key(mr, ib_inc_rkey(mr->rkey)); @@ -336,7 +336,7 @@ static int iser_fast_reg_mr(struct iscsi_iser_task *iser_task, IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ; - rsc->mr_valid = 1; + rsc->mr->need_inval = true; reg->sge.lkey = mr->lkey; reg->rkey = mr->rkey; diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index a00ca117303a..057e69164e6d 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -135,7 +135,6 @@ iser_create_fastreg_desc(struct iser_device *device, goto err_alloc_mr_integrity; } } - desc->rsc.mr_valid = 0; return desc; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 25e799dba999..cffa93f114a7 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -79,12 +79,16 @@ module_param(srpt_srq_size, int, 0444); MODULE_PARM_DESC(srpt_srq_size, "Shared receive queue (SRQ) size."); +static int srpt_set_u64_x(const char *buffer, const struct kernel_param *kp) +{ + return kstrtou64(buffer, 16, (u64 *)kp->arg); +} static int srpt_get_u64_x(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "0x%016llx\n", *(u64 *)kp->arg); } -module_param_call(srpt_service_guid, NULL, srpt_get_u64_x, &srpt_service_guid, - 0444); +module_param_call(srpt_service_guid, srpt_set_u64_x, srpt_get_u64_x, + &srpt_service_guid, 0444); MODULE_PARM_DESC(srpt_service_guid, "Using this value for ioc_guid, id_ext, and cm_listen_id instead of using the node_guid of the first HCA."); @@ -210,10 +214,12 @@ static const char *get_ch_state_name(enum rdma_ch_state s) /** * srpt_qp_event - QP event callback function * @event: Description of the event that occurred. - * @ch: SRPT RDMA channel. + * @ptr: SRPT RDMA channel. */ -static void srpt_qp_event(struct ib_event *event, struct srpt_rdma_ch *ch) +static void srpt_qp_event(struct ib_event *event, void *ptr) { + struct srpt_rdma_ch *ch = ptr; + pr_debug("QP event %d on ch=%p sess_name=%s-%d state=%s\n", event->event, ch, ch->sess_name, ch->qp->qp_num, get_ch_state_name(ch->state)); @@ -1807,8 +1813,7 @@ retry: ch->cq_size = ch->rq_size + sq_size; qp_init->qp_context = (void *)ch; - qp_init->event_handler - = (void(*)(struct ib_event *, void*))srpt_qp_event; + qp_init->event_handler = srpt_qp_event; qp_init->send_cq = ch->cq; qp_init->recv_cq = ch->cq; qp_init->sq_sig_type = IB_SIGNAL_REQ_WR; diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 8404286302b0..02f3bc4e4895 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -286,6 +286,7 @@ static const struct xpad_device { { 0x146b, 0x0604, "Bigben Interactive DAIJA Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x1532, 0x0a00, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE }, { 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE }, + { 0x1532, 0x0a29, "Razer Wolverine V2", 0, XTYPE_XBOXONE }, { 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 }, { 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 }, { 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 }, @@ -293,6 +294,7 @@ static const struct xpad_device { { 0x1689, 0xfd00, "Razer Onza Tournament Edition", 0, XTYPE_XBOX360 }, { 0x1689, 0xfd01, "Razer Onza Classic Edition", 0, XTYPE_XBOX360 }, { 0x1689, 0xfe00, "Razer Sabertooth", 0, XTYPE_XBOX360 }, + { 0x17ef, 0x6182, "Lenovo Legion Controller for Windows", 0, XTYPE_XBOX360 }, { 0x1949, 0x041a, "Amazon Game Controller", 0, XTYPE_XBOX360 }, { 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 }, { 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, @@ -488,6 +490,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x15e4), /* Numark X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x162e), /* Joytech X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */ + XPAD_XBOX360_VENDOR(0x17ef), /* Lenovo */ XPAD_XBOX360_VENDOR(0x1949), /* Amazon controllers */ XPAD_XBOX360_VENDOR(0x1bad), /* Harminix Rock Band Guitar and Drums */ XPAD_XBOX360_VENDOR(0x20d6), /* PowerA Controllers */ diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index 246958795f60..661d6c8b059b 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -746,6 +746,44 @@ static void atkbd_deactivate(struct atkbd *atkbd) ps2dev->serio->phys); } +#ifdef CONFIG_X86 +static bool atkbd_is_portable_device(void) +{ + static const char * const chassis_types[] = { + "8", /* Portable */ + "9", /* Laptop */ + "10", /* Notebook */ + "14", /* Sub-Notebook */ + "31", /* Convertible */ + "32", /* Detachable */ + }; + int i; + + for (i = 0; i < ARRAY_SIZE(chassis_types); i++) + if (dmi_match(DMI_CHASSIS_TYPE, chassis_types[i])) + return true; + + return false; +} + +/* + * On many modern laptops ATKBD_CMD_GETID may cause problems, on these laptops + * the controller is always in translated mode. In this mode mice/touchpads will + * not work. So in this case simply assume a keyboard is connected to avoid + * confusing some laptop keyboards. + * + * Skipping ATKBD_CMD_GETID ends up using a fake keyboard id. Using the standard + * 0xab83 id is ok in translated mode, only atkbd_select_set() checks atkbd->id + * and in translated mode that is a no-op. + */ +static bool atkbd_skip_getid(struct atkbd *atkbd) +{ + return atkbd->translated && atkbd_is_portable_device(); +} +#else +static inline bool atkbd_skip_getid(struct atkbd *atkbd) { return false; } +#endif + /* * atkbd_probe() probes for an AT keyboard on a serio port. */ @@ -767,6 +805,11 @@ static int atkbd_probe(struct atkbd *atkbd) "keyboard reset failed on %s\n", ps2dev->serio->phys); + if (atkbd_skip_getid(atkbd)) { + atkbd->id = 0xab83; + return 0; + } + /* * Then we check the keyboard ID. We should get 0xab83 under normal conditions. * Some keyboards report different values, but the first byte is always 0xab or @@ -778,9 +821,9 @@ static int atkbd_probe(struct atkbd *atkbd) if (ps2_command(ps2dev, param, ATKBD_CMD_GETID)) { /* - * If the get ID command failed, we check if we can at least set the LEDs on - * the keyboard. This should work on every keyboard out there. It also turns - * the LEDs off, which we want anyway. + * If the get ID command failed, we check if we can at least set + * the LEDs on the keyboard. This should work on every keyboard out there. + * It also turns the LEDs off, which we want anyway. */ param[0] = 0; if (ps2_command(ps2dev, param, ATKBD_CMD_SETLEDS)) diff --git a/drivers/input/keyboard/ipaq-micro-keys.c b/drivers/input/keyboard/ipaq-micro-keys.c index 13a66a8e3411..e0c51189e329 100644 --- a/drivers/input/keyboard/ipaq-micro-keys.c +++ b/drivers/input/keyboard/ipaq-micro-keys.c @@ -105,6 +105,9 @@ static int micro_key_probe(struct platform_device *pdev) keys->codes = devm_kmemdup(&pdev->dev, micro_keycodes, keys->input->keycodesize * keys->input->keycodemax, GFP_KERNEL); + if (!keys->codes) + return -ENOMEM; + keys->input->keycode = keys->codes; __set_bit(EV_KEY, keys->input->evbit); diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index e79f5497948b..9116f4248fd0 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -299,6 +299,11 @@ static int soc_button_parse_btn_desc(struct device *dev, info->name = "power"; info->event_code = KEY_POWER; info->wakeup = true; + } else if (upage == 0x01 && usage == 0xc6) { + info->name = "airplane mode switch"; + info->event_type = EV_SW; + info->event_code = SW_RFKILL_ALL; + info->active_low = false; } else if (upage == 0x01 && usage == 0xca) { info->name = "rotation lock switch"; info->event_type = EV_SW; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index e43e93ac2798..b6749af46262 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -183,6 +183,7 @@ static const char * const smbus_pnp_ids[] = { "LEN009b", /* T580 */ "LEN0402", /* X1 Extreme Gen 2 / P1 Gen 2 */ "LEN040f", /* P1 Gen 3 */ + "LEN0411", /* L14 Gen 1 */ "LEN200f", /* T450s */ "LEN2044", /* L470 */ "LEN2054", /* E480 */ diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 9c39553d30fa..dfc6c581873b 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -361,6 +361,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { + /* Acer TravelMate P459-G2-M */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate P459-G2-M"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { /* Amoi M636/A737 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."), @@ -627,6 +635,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOAUX) }, { + /* Fujitsu Lifebook U728 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U728"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX) + }, + { /* Gigabyte M912 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), @@ -1202,6 +1218,12 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "NS5x_7xPU"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX) + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"), }, .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 3f0732db7bf5..6de64b3f900f 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -884,7 +884,8 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts) } } - if (ts->gpio_count == 2 && ts->gpio_int_idx == 0) { + /* Some devices with gpio_int_idx 0 list a third unused GPIO */ + if ((ts->gpio_count == 2 || ts->gpio_count == 3) && ts->gpio_int_idx == 0) { ts->irq_pin_access_method = IRQ_PIN_ACCESS_ACPI_GPIO; gpio_mapping = acpi_goodix_int_first_gpios; } else if (ts->gpio_count == 2 && ts->gpio_int_idx == 1) { diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 0c6fc954e729..1d9494f64a21 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -381,6 +381,9 @@ struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec) } mutex_unlock(&icc_lock); + if (!node) + return ERR_PTR(-EINVAL); + if (IS_ERR(node)) return ERR_CAST(node); diff --git a/drivers/interconnect/qcom/sc8180x.c b/drivers/interconnect/qcom/sc8180x.c index 83461e31774e..d9ee193fb18b 100644 --- a/drivers/interconnect/qcom/sc8180x.c +++ b/drivers/interconnect/qcom/sc8180x.c @@ -1387,6 +1387,7 @@ static struct qcom_icc_bcm bcm_mm0 = { static struct qcom_icc_bcm bcm_co0 = { .name = "CO0", + .keepalive = true, .num_nodes = 1, .nodes = { &slv_qns_cdsp_mem_noc } }; diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index b2708de25ea3..d80065c8105a 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -243,6 +243,7 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain, static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = { { .compatible = "qcom,adreno" }, + { .compatible = "qcom,adreno-gmu" }, { .compatible = "qcom,mdp4" }, { .compatible = "qcom,mdss" }, { .compatible = "qcom,sc7180-mdss" }, diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 9297b741f5e8..aa6d62cc567a 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -28,6 +28,7 @@ #include <linux/spinlock.h> #include <linux/swiotlb.h> #include <linux/vmalloc.h> +#include <trace/events/swiotlb.h> #include "dma-iommu.h" @@ -999,6 +1000,8 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, return DMA_MAPPING_ERROR; } + trace_swiotlb_bounced(dev, phys, size); + aligned_size = iova_align(iovad, size); phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size, iova_mask(iovad), dir, attrs); diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index 091b0fe7e324..5d4421f75b43 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -2,7 +2,7 @@ /* * Generic Broadcom Set Top Box Level 2 Interrupt controller driver * - * Copyright (C) 2014-2017 Broadcom + * Copyright (C) 2014-2024 Broadcom */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -113,6 +113,9 @@ static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc) generic_handle_domain_irq(b->domain, irq); } while (status); out: + /* Don't ack parent before all device writes are done */ + wmb(); + chained_irq_exit(chip, desc); } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 8956881503d9..4d03fb3a8246 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3161,6 +3161,7 @@ static void its_cpu_init_lpis(void) val |= GICR_CTLR_ENABLE_LPIS; writel_relaxed(val, rbase + GICR_CTLR); +out: if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); @@ -3196,7 +3197,6 @@ static void its_cpu_init_lpis(void) /* Make sure the GIC has seen the above */ dsb(sy); -out: gic_data_rdist()->flags |= RD_LOCAL_LPI_ENABLED; pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n", smp_processor_id(), @@ -3805,8 +3805,9 @@ static int its_vpe_set_affinity(struct irq_data *d, bool force) { struct its_vpe *vpe = irq_data_get_irq_chip_data(d); - int from, cpu = cpumask_first(mask_val); + struct cpumask common, *table_mask; unsigned long flags; + int from, cpu; /* * Changing affinity is mega expensive, so let's be as lazy as @@ -3822,19 +3823,22 @@ static int its_vpe_set_affinity(struct irq_data *d, * taken on any vLPI handling path that evaluates vpe->col_idx. */ from = vpe_to_cpuid_lock(vpe, &flags); - if (from == cpu) - goto out; - - vpe->col_idx = cpu; + table_mask = gic_data_rdist_cpu(from)->vpe_table_mask; /* - * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD - * is sharing its VPE table with the current one. + * If we are offered another CPU in the same GICv4.1 ITS + * affinity, pick this one. Otherwise, any CPU will do. */ - if (gic_data_rdist_cpu(cpu)->vpe_table_mask && - cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask)) + if (table_mask && cpumask_and(&common, mask_val, table_mask)) + cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common); + else + cpu = cpumask_first(mask_val); + + if (from == cpu) goto out; + vpe->col_idx = cpu; + its_send_vmovp(vpe); its_vpe_db_proxy_move(vpe, from, cpu); diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index 3d99b8bdd8ef..de115ee6e9ec 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -242,7 +242,7 @@ static int eiointc_domain_alloc(struct irq_domain *domain, unsigned int virq, int ret; unsigned int i, type; unsigned long hwirq = 0; - struct eiointc *priv = domain->host_data; + struct eiointc_priv *priv = domain->host_data; ret = irq_domain_translate_onecell(domain, arg, &hwirq, &type); if (ret) diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index 2f4784860df5..be5e19a86ac3 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -144,7 +144,13 @@ static void plic_irq_eoi(struct irq_data *d) { struct plic_handler *handler = this_cpu_ptr(&plic_handlers); - writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); + if (unlikely(irqd_irq_disabled(d))) { + plic_toggle(handler, d->hwirq, 1); + writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); + plic_toggle(handler, d->hwirq, 0); + } else { + writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); + } } #ifdef CONFIG_SMP diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 2378cfb7443e..509d03eb3e8d 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -97,6 +97,7 @@ config LEDS_ARIEL config LEDS_AW2013 tristate "LED support for Awinic AW2013" depends on LEDS_CLASS && I2C && OF + select REGMAP_I2C help This option enables support for the AW2013 3-channel LED driver. diff --git a/drivers/leds/trigger/ledtrig-panic.c b/drivers/leds/trigger/ledtrig-panic.c index 64abf2e91608..5a6b21bfeb9a 100644 --- a/drivers/leds/trigger/ledtrig-panic.c +++ b/drivers/leds/trigger/ledtrig-panic.c @@ -64,10 +64,13 @@ static long led_panic_blink(int state) static int __init ledtrig_panic_init(void) { + led_trigger_register_simple("panic", &trigger); + if (!trigger) + return -ENOMEM; + atomic_notifier_chain_register(&panic_notifier_list, &led_trigger_panic_nb); - led_trigger_register_simple("panic", &trigger); panic_blink = led_panic_blink; return 0; } diff --git a/drivers/leds/trigger/ledtrig-tty.c b/drivers/leds/trigger/ledtrig-tty.c index 8ae0d2d284af..3e69a7bde928 100644 --- a/drivers/leds/trigger/ledtrig-tty.c +++ b/drivers/leds/trigger/ledtrig-tty.c @@ -168,6 +168,10 @@ static void ledtrig_tty_deactivate(struct led_classdev *led_cdev) cancel_delayed_work_sync(&trigger_data->dwork); + kfree(trigger_data->ttyname); + tty_kref_put(trigger_data->tty); + trigger_data->tty = NULL; + kfree(trigger_data); } diff --git a/drivers/mailbox/arm_mhuv2.c b/drivers/mailbox/arm_mhuv2.c index c6d4957c4da8..0ec21dcdbde7 100644 --- a/drivers/mailbox/arm_mhuv2.c +++ b/drivers/mailbox/arm_mhuv2.c @@ -553,7 +553,8 @@ static irqreturn_t mhuv2_sender_interrupt(int irq, void *data) priv = chan->con_priv; if (!IS_PROTOCOL_DOORBELL(priv)) { - writel_relaxed(1, &mhu->send->ch_wn[priv->ch_wn_idx + priv->windows - 1].int_clr); + for (i = 0; i < priv->windows; i++) + writel_relaxed(1, &mhu->send->ch_wn[priv->ch_wn_idx + i].int_clr); if (chan->cl) { mbox_chan_txdone(chan, 0); diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 662d219c39bf..db0e97020256 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -650,6 +650,7 @@ config DM_ZONED config DM_AUDIT bool "DM audit events" + depends on BLK_DEV_DM depends on AUDIT help Generate audit events for device-mapper. diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 382c5cc47195..100a6a236d92 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1914,6 +1914,13 @@ void dm_bufio_client_destroy(struct dm_bufio_client *c) } EXPORT_SYMBOL_GPL(dm_bufio_client_destroy); +void dm_bufio_client_reset(struct dm_bufio_client *c) +{ + drop_buffers(c); + flush_work(&c->shrink_work); +} +EXPORT_SYMBOL_GPL(dm_bufio_client_reset); + void dm_bufio_set_sector_offset(struct dm_bufio_client *c, sector_t start) { c->start = start; diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 71dcd8fd4050..6314210d3697 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -21,6 +21,8 @@ #include "dm-ima.h" #define DM_RESERVED_MAX_IOS 1024 +#define DM_MAX_TARGETS 1048576 +#define DM_MAX_TARGET_PARAMS 1024 struct dm_io; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index ff515437d81e..3e215aa85b99 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -61,6 +61,8 @@ struct convert_context { struct skcipher_request *req; struct aead_request *req_aead; } r; + bool aead_recheck; + bool aead_failed; }; @@ -72,10 +74,8 @@ struct dm_crypt_io { struct bio *base_bio; u8 *integrity_metadata; bool integrity_metadata_from_pool:1; - bool in_tasklet:1; struct work_struct work; - struct tasklet_struct tasklet; struct convert_context ctx; @@ -83,6 +83,8 @@ struct dm_crypt_io { blk_status_t error; sector_t sector; + struct bvec_iter saved_bi_iter; + struct rb_node rb_node; } CRYPTO_MINALIGN_ATTR; @@ -1367,10 +1369,13 @@ static int crypt_convert_block_aead(struct crypt_config *cc, if (r == -EBADMSG) { sector_t s = le64_to_cpu(*sector); - DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", - ctx->bio_in->bi_bdev, s); - dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", - ctx->bio_in, s, 0); + ctx->aead_failed = true; + if (ctx->aead_recheck) { + DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", + ctx->bio_in->bi_bdev, s); + dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", + ctx->bio_in, s, 0); + } } if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post) @@ -1726,10 +1731,11 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc, io->base_bio = bio; io->sector = sector; io->error = 0; + io->ctx.aead_recheck = false; + io->ctx.aead_failed = false; io->ctx.r.req = NULL; io->integrity_metadata = NULL; io->integrity_metadata_from_pool = false; - io->in_tasklet = false; atomic_set(&io->io_pending, 0); } @@ -1738,11 +1744,7 @@ static void crypt_inc_pending(struct dm_crypt_io *io) atomic_inc(&io->io_pending); } -static void kcryptd_io_bio_endio(struct work_struct *work) -{ - struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); - bio_endio(io->base_bio); -} +static void kcryptd_queue_read(struct dm_crypt_io *io); /* * One of the bios was finished. Check for completion of @@ -1757,6 +1759,15 @@ static void crypt_dec_pending(struct dm_crypt_io *io) if (!atomic_dec_and_test(&io->io_pending)) return; + if (likely(!io->ctx.aead_recheck) && unlikely(io->ctx.aead_failed) && + cc->on_disk_tag_size && bio_data_dir(base_bio) == READ) { + io->ctx.aead_recheck = true; + io->ctx.aead_failed = false; + io->error = 0; + kcryptd_queue_read(io); + return; + } + if (io->ctx.r.req) crypt_free_req(cc, io->ctx.r.req, base_bio); @@ -1767,20 +1778,6 @@ static void crypt_dec_pending(struct dm_crypt_io *io) base_bio->bi_status = error; - /* - * If we are running this function from our tasklet, - * we can't call bio_endio() here, because it will call - * clone_endio() from dm.c, which in turn will - * free the current struct dm_crypt_io structure with - * our tasklet. In this case we need to delay bio_endio() - * execution to after the tasklet is done and dequeued. - */ - if (io->in_tasklet) { - INIT_WORK(&io->work, kcryptd_io_bio_endio); - queue_work(cc->io_queue, &io->work); - return; - } - bio_endio(base_bio); } @@ -1806,15 +1803,19 @@ static void crypt_endio(struct bio *clone) struct dm_crypt_io *io = clone->bi_private; struct crypt_config *cc = io->cc; unsigned int rw = bio_data_dir(clone); - blk_status_t error; + blk_status_t error = clone->bi_status; + + if (io->ctx.aead_recheck && !error) { + kcryptd_queue_crypt(io); + return; + } /* * free the processed pages */ - if (rw == WRITE) + if (rw == WRITE || io->ctx.aead_recheck) crypt_free_buffer_pages(cc, clone); - error = clone->bi_status; bio_put(clone); if (rw == READ && !error) { @@ -1835,6 +1836,22 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) struct crypt_config *cc = io->cc; struct bio *clone; + if (io->ctx.aead_recheck) { + if (!(gfp & __GFP_DIRECT_RECLAIM)) + return 1; + crypt_inc_pending(io); + clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size); + if (unlikely(!clone)) { + crypt_dec_pending(io); + return 1; + } + clone->bi_iter.bi_sector = cc->start + io->sector; + crypt_convert_init(cc, &io->ctx, clone, clone, io->sector); + io->saved_bi_iter = clone->bi_iter; + dm_submit_bio_remap(io->base_bio, clone); + return 0; + } + /* * We need the original biovec array in order to decrypt the whole bio * data *afterwards* -- thanks to immutable biovecs we don't need to @@ -2061,6 +2078,12 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) io->ctx.bio_out = clone; io->ctx.iter_out = clone->bi_iter; + if (crypt_integrity_aead(cc)) { + bio_copy_data(clone, io->base_bio); + io->ctx.bio_in = clone; + io->ctx.iter_in = clone->bi_iter; + } + sector += bio_sectors(clone); crypt_inc_pending(io); @@ -2097,6 +2120,14 @@ dec: static void kcryptd_crypt_read_done(struct dm_crypt_io *io) { + if (io->ctx.aead_recheck) { + if (!io->error) { + io->ctx.bio_in->bi_iter = io->saved_bi_iter; + bio_copy_data(io->base_bio, io->ctx.bio_in); + } + crypt_free_buffer_pages(io->cc, io->ctx.bio_in); + bio_put(io->ctx.bio_in); + } crypt_dec_pending(io); } @@ -2126,11 +2157,17 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) crypt_inc_pending(io); - crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio, - io->sector); + if (io->ctx.aead_recheck) { + io->ctx.cc_sector = io->sector + cc->iv_offset; + r = crypt_convert(cc, &io->ctx, + test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); + } else { + crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio, + io->sector); - r = crypt_convert(cc, &io->ctx, - test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); + r = crypt_convert(cc, &io->ctx, + test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); + } /* * Crypto API backlogged the request, because its queue was full * and we're in softirq context, so continue from a workqueue @@ -2173,10 +2210,13 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, if (error == -EBADMSG) { sector_t s = le64_to_cpu(*org_sector_of_dmreq(cc, dmreq)); - DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", - ctx->bio_in->bi_bdev, s); - dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", - ctx->bio_in, s, 0); + ctx->aead_failed = true; + if (ctx->aead_recheck) { + DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", + ctx->bio_in->bi_bdev, s); + dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", + ctx->bio_in, s, 0); + } io->error = BLK_STS_PROTECTION; } else if (error < 0) io->error = BLK_STS_IOERR; @@ -2213,11 +2253,6 @@ static void kcryptd_crypt(struct work_struct *work) kcryptd_crypt_write_convert(io); } -static void kcryptd_crypt_tasklet(unsigned long work) -{ - kcryptd_crypt((struct work_struct *)work); -} - static void kcryptd_queue_crypt(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; @@ -2229,15 +2264,10 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io) * irqs_disabled(): the kernel may run some IO completion from the idle thread, but * it is being executed with irqs disabled. */ - if (in_hardirq() || irqs_disabled()) { - io->in_tasklet = true; - tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work); - tasklet_schedule(&io->tasklet); + if (!(in_hardirq() || irqs_disabled())) { + kcryptd_crypt(&io->work); return; } - - kcryptd_crypt(&io->work); - return; } INIT_WORK(&io->work, kcryptd_crypt); @@ -3112,7 +3142,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar sval = strchr(opt_string + strlen("integrity:"), ':') + 1; if (!strcasecmp(sval, "aead")) { set_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags); - } else if (strcasecmp(sval, "none")) { + } else if (strcasecmp(sval, "none")) { ti->error = "Unknown integrity profile"; return -EINVAL; } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index fe7dad3ffa75..3da4359f5164 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -279,6 +279,8 @@ struct dm_integrity_c { atomic64_t number_of_mismatches; + mempool_t recheck_pool; + struct notifier_block reboot_notifier; }; @@ -1699,6 +1701,77 @@ failed: get_random_bytes(result, ic->tag_size); } +static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checksum) +{ + struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io)); + struct dm_integrity_c *ic = dio->ic; + struct bvec_iter iter; + struct bio_vec bv; + sector_t sector, logical_sector, area, offset; + struct page *page; + void *buffer; + + get_area_and_offset(ic, dio->range.logical_sector, &area, &offset); + dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset, + &dio->metadata_offset); + sector = get_data_sector(ic, area, offset); + logical_sector = dio->range.logical_sector; + + page = mempool_alloc(&ic->recheck_pool, GFP_NOIO); + buffer = page_to_virt(page); + + __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) { + unsigned pos = 0; + + do { + char *mem; + int r; + struct dm_io_request io_req; + struct dm_io_region io_loc; + io_req.bi_opf = REQ_OP_READ; + io_req.mem.type = DM_IO_KMEM; + io_req.mem.ptr.addr = buffer; + io_req.notify.fn = NULL; + io_req.client = ic->io; + io_loc.bdev = ic->dev->bdev; + io_loc.sector = sector; + io_loc.count = ic->sectors_per_block; + + r = dm_io(&io_req, 1, &io_loc, NULL); + if (unlikely(r)) { + dio->bi_status = errno_to_blk_status(r); + goto free_ret; + } + + integrity_sector_checksum(ic, logical_sector, buffer, checksum); + r = dm_integrity_rw_tag(ic, checksum, &dio->metadata_block, + &dio->metadata_offset, ic->tag_size, TAG_CMP); + if (r) { + if (r > 0) { + DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx", + bio->bi_bdev, logical_sector); + atomic64_inc(&ic->number_of_mismatches); + dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum", + bio, logical_sector, 0); + r = -EILSEQ; + } + dio->bi_status = errno_to_blk_status(r); + goto free_ret; + } + + mem = bvec_kmap_local(&bv); + memcpy(mem + pos, buffer, ic->sectors_per_block << SECTOR_SHIFT); + kunmap_local(mem); + + pos += ic->sectors_per_block << SECTOR_SHIFT; + sector += ic->sectors_per_block; + logical_sector += ic->sectors_per_block; + } while (pos < bv.bv_len); + } +free_ret: + mempool_free(page, &ic->recheck_pool); +} + static void integrity_metadata(struct work_struct *w) { struct dm_integrity_io *dio = container_of(w, struct dm_integrity_io, work); @@ -1763,11 +1836,12 @@ static void integrity_metadata(struct work_struct *w) sectors_to_process = dio->range.n_sectors; __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) { + struct bio_vec bv_copy = bv; unsigned int pos; char *mem, *checksums_ptr; again: - mem = bvec_kmap_local(&bv); + mem = bvec_kmap_local(&bv_copy); pos = 0; checksums_ptr = checksums; do { @@ -1776,22 +1850,15 @@ again: sectors_to_process -= ic->sectors_per_block; pos += ic->sectors_per_block << SECTOR_SHIFT; sector += ic->sectors_per_block; - } while (pos < bv.bv_len && sectors_to_process && checksums != checksums_onstack); + } while (pos < bv_copy.bv_len && sectors_to_process && checksums != checksums_onstack); kunmap_local(mem); r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset, checksums_ptr - checksums, dio->op == REQ_OP_READ ? TAG_CMP : TAG_WRITE); if (unlikely(r)) { if (r > 0) { - sector_t s; - - s = sector - ((r + ic->tag_size - 1) / ic->tag_size); - DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx", - bio->bi_bdev, s); - r = -EILSEQ; - atomic64_inc(&ic->number_of_mismatches); - dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum", - bio, s, 0); + integrity_recheck(dio, checksums); + goto skip_io; } if (likely(checksums != checksums_onstack)) kfree(checksums); @@ -1801,9 +1868,9 @@ again: if (!sectors_to_process) break; - if (unlikely(pos < bv.bv_len)) { - bv.bv_offset += pos; - bv.bv_len -= pos; + if (unlikely(pos < bv_copy.bv_len)) { + bv_copy.bv_offset += pos; + bv_copy.bv_len -= pos; goto again; } } @@ -4207,6 +4274,12 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv goto bad; } + r = mempool_init_page_pool(&ic->recheck_pool, 1, 0); + if (r) { + ti->error = "Cannot allocate mempool"; + goto bad; + } + ic->metadata_wq = alloc_workqueue("dm-integrity-metadata", WQ_MEM_RECLAIM, METADATA_WORKQUEUE_MAX_ACTIVE); if (!ic->metadata_wq) { @@ -4571,6 +4644,7 @@ static void dm_integrity_dtr(struct dm_target *ti) kvfree(ic->bbs); if (ic->bufio) dm_bufio_client_destroy(ic->bufio); + mempool_exit(&ic->recheck_pool); mempool_exit(&ic->journal_io_mempool); if (ic->io) dm_io_client_destroy(ic->io); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 206e6ce554dc..4376754816ab 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1877,7 +1877,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern minimum_data_size - sizeof(param_kernel->version))) return -EFAULT; - if (param_kernel->data_size < minimum_data_size) { + if (unlikely(param_kernel->data_size < minimum_data_size) || + unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) { DMERR("Invalid data size in the ioctl structure: %u", param_kernel->data_size); return -EINVAL; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index dac6a5f25f2b..e0367a672eab 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -128,7 +128,12 @@ static int alloc_targets(struct dm_table *t, unsigned int num) int dm_table_create(struct dm_table **result, fmode_t mode, unsigned int num_targets, struct mapped_device *md) { - struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL); + struct dm_table *t; + + if (num_targets > DM_MAX_TARGETS) + return -EOVERFLOW; + + t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) return -ENOMEM; @@ -143,7 +148,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode, if (!num_targets) { kfree(t); - return -ENOMEM; + return -EOVERFLOW; } if (alloc_targets(t, num_targets)) { diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 4a0e15109997..bb0e0a270f62 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -597,6 +597,8 @@ static int __format_metadata(struct dm_pool_metadata *pmd) r = dm_tm_create_with_sm(pmd->bm, THIN_SUPERBLOCK_LOCATION, &pmd->tm, &pmd->metadata_sm); if (r < 0) { + pmd->tm = NULL; + pmd->metadata_sm = NULL; DMERR("tm_create_with_sm failed"); return r; } @@ -605,6 +607,7 @@ static int __format_metadata(struct dm_pool_metadata *pmd) if (IS_ERR(pmd->data_sm)) { DMERR("sm_disk_create failed"); r = PTR_ERR(pmd->data_sm); + pmd->data_sm = NULL; goto bad_cleanup_tm; } @@ -635,11 +638,15 @@ static int __format_metadata(struct dm_pool_metadata *pmd) bad_cleanup_nb_tm: dm_tm_destroy(pmd->nb_tm); + pmd->nb_tm = NULL; bad_cleanup_data_sm: dm_sm_destroy(pmd->data_sm); + pmd->data_sm = NULL; bad_cleanup_tm: dm_tm_destroy(pmd->tm); + pmd->tm = NULL; dm_sm_destroy(pmd->metadata_sm); + pmd->metadata_sm = NULL; return r; } @@ -705,6 +712,8 @@ static int __open_metadata(struct dm_pool_metadata *pmd) sizeof(disk_super->metadata_space_map_root), &pmd->tm, &pmd->metadata_sm); if (r < 0) { + pmd->tm = NULL; + pmd->metadata_sm = NULL; DMERR("tm_open_with_sm failed"); goto bad_unlock_sblock; } @@ -714,6 +723,7 @@ static int __open_metadata(struct dm_pool_metadata *pmd) if (IS_ERR(pmd->data_sm)) { DMERR("sm_disk_open failed"); r = PTR_ERR(pmd->data_sm); + pmd->data_sm = NULL; goto bad_cleanup_tm; } @@ -740,9 +750,12 @@ static int __open_metadata(struct dm_pool_metadata *pmd) bad_cleanup_data_sm: dm_sm_destroy(pmd->data_sm); + pmd->data_sm = NULL; bad_cleanup_tm: dm_tm_destroy(pmd->tm); + pmd->tm = NULL; dm_sm_destroy(pmd->metadata_sm); + pmd->metadata_sm = NULL; bad_unlock_sblock: dm_bm_unlock(sblock); @@ -789,9 +802,13 @@ static void __destroy_persistent_data_objects(struct dm_pool_metadata *pmd, bool destroy_bm) { dm_sm_destroy(pmd->data_sm); + pmd->data_sm = NULL; dm_sm_destroy(pmd->metadata_sm); + pmd->metadata_sm = NULL; dm_tm_destroy(pmd->nb_tm); + pmd->nb_tm = NULL; dm_tm_destroy(pmd->tm); + pmd->tm = NULL; if (destroy_bm) dm_block_manager_destroy(pmd->bm); } @@ -999,8 +1016,7 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd) __func__, r); } pmd_write_unlock(pmd); - if (!pmd->fail_io) - __destroy_persistent_data_objects(pmd, true); + __destroy_persistent_data_objects(pmd, true); kfree(pmd); return 0; @@ -1875,53 +1891,29 @@ static void __set_abort_with_changes_flags(struct dm_pool_metadata *pmd) int dm_pool_abort_metadata(struct dm_pool_metadata *pmd) { int r = -EINVAL; - struct dm_block_manager *old_bm = NULL, *new_bm = NULL; /* fail_io is double-checked with pmd->root_lock held below */ if (unlikely(pmd->fail_io)) return r; - /* - * Replacement block manager (new_bm) is created and old_bm destroyed outside of - * pmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of - * shrinker associated with the block manager's bufio client vs pmd root_lock). - * - must take shrinker_rwsem without holding pmd->root_lock - */ - new_bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT, - THIN_MAX_CONCURRENT_LOCKS); - pmd_write_lock(pmd); if (pmd->fail_io) { pmd_write_unlock(pmd); - goto out; + return r; } - __set_abort_with_changes_flags(pmd); + + /* destroy data_sm/metadata_sm/nb_tm/tm */ __destroy_persistent_data_objects(pmd, false); - old_bm = pmd->bm; - if (IS_ERR(new_bm)) { - DMERR("could not create block manager during abort"); - pmd->bm = NULL; - r = PTR_ERR(new_bm); - goto out_unlock; - } - pmd->bm = new_bm; + /* reset bm */ + dm_block_manager_reset(pmd->bm); + + /* rebuild data_sm/metadata_sm/nb_tm/tm */ r = __open_or_format_metadata(pmd, false); - if (r) { - pmd->bm = NULL; - goto out_unlock; - } - new_bm = NULL; -out_unlock: if (r) pmd->fail_io = true; pmd_write_unlock(pmd); - dm_block_manager_destroy(old_bm); -out: - if (new_bm && !IS_ERR(new_bm)) - dm_block_manager_destroy(new_bm); - return r; } diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 24df610a2c43..b48e1b59e6da 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -474,6 +474,63 @@ int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, return 0; } +static int verity_recheck_copy(struct dm_verity *v, struct dm_verity_io *io, + u8 *data, size_t len) +{ + memcpy(data, io->recheck_buffer, len); + io->recheck_buffer += len; + + return 0; +} + +static noinline int verity_recheck(struct dm_verity *v, struct dm_verity_io *io, + struct bvec_iter start, sector_t cur_block) +{ + struct page *page; + void *buffer; + int r; + struct dm_io_request io_req; + struct dm_io_region io_loc; + + page = mempool_alloc(&v->recheck_pool, GFP_NOIO); + buffer = page_to_virt(page); + + io_req.bi_opf = REQ_OP_READ; + io_req.mem.type = DM_IO_KMEM; + io_req.mem.ptr.addr = buffer; + io_req.notify.fn = NULL; + io_req.client = v->io; + io_loc.bdev = v->data_dev->bdev; + io_loc.sector = cur_block << (v->data_dev_block_bits - SECTOR_SHIFT); + io_loc.count = 1 << (v->data_dev_block_bits - SECTOR_SHIFT); + r = dm_io(&io_req, 1, &io_loc, NULL); + if (unlikely(r)) + goto free_ret; + + r = verity_hash(v, verity_io_hash_req(v, io), buffer, + 1 << v->data_dev_block_bits, + verity_io_real_digest(v, io), true); + if (unlikely(r)) + goto free_ret; + + if (memcmp(verity_io_real_digest(v, io), + verity_io_want_digest(v, io), v->digest_size)) { + r = -EIO; + goto free_ret; + } + + io->recheck_buffer = buffer; + r = verity_for_bv_block(v, io, &start, verity_recheck_copy); + if (unlikely(r)) + goto free_ret; + + r = 0; +free_ret: + mempool_free(page, &v->recheck_pool); + + return r; +} + static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io, u8 *data, size_t len) { @@ -500,9 +557,7 @@ static int verity_verify_io(struct dm_verity_io *io) { bool is_zero; struct dm_verity *v = io->v; -#if defined(CONFIG_DM_VERITY_FEC) struct bvec_iter start; -#endif struct bvec_iter iter_copy; struct bvec_iter *iter; struct crypto_wait wait; @@ -553,10 +608,7 @@ static int verity_verify_io(struct dm_verity_io *io) if (unlikely(r < 0)) return r; -#if defined(CONFIG_DM_VERITY_FEC) - if (verity_fec_is_enabled(v)) - start = *iter; -#endif + start = *iter; r = verity_for_io_block(v, io, iter, &wait); if (unlikely(r < 0)) return r; @@ -578,6 +630,10 @@ static int verity_verify_io(struct dm_verity_io *io) * tasklet since it may sleep, so fallback to work-queue. */ return -EAGAIN; + } else if (verity_recheck(v, io, start, cur_block) == 0) { + if (v->validated_blocks) + set_bit(cur_block, v->validated_blocks); + continue; #if defined(CONFIG_DM_VERITY_FEC) } else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA, cur_block, NULL, &start) == 0) { @@ -634,23 +690,6 @@ static void verity_work(struct work_struct *w) verity_finish_io(io, errno_to_blk_status(verity_verify_io(io))); } -static void verity_tasklet(unsigned long data) -{ - struct dm_verity_io *io = (struct dm_verity_io *)data; - int err; - - io->in_tasklet = true; - err = verity_verify_io(io); - if (err == -EAGAIN || err == -ENOMEM) { - /* fallback to retrying with work-queue */ - INIT_WORK(&io->work, verity_work); - queue_work(io->v->verify_wq, &io->work); - return; - } - - verity_finish_io(io, errno_to_blk_status(err)); -} - static void verity_end_io(struct bio *bio) { struct dm_verity_io *io = bio->bi_private; @@ -663,13 +702,8 @@ static void verity_end_io(struct bio *bio) return; } - if (static_branch_unlikely(&use_tasklet_enabled) && io->v->use_tasklet) { - tasklet_init(&io->tasklet, verity_tasklet, (unsigned long)io); - tasklet_schedule(&io->tasklet); - } else { - INIT_WORK(&io->work, verity_work); - queue_work(io->v->verify_wq, &io->work); - } + INIT_WORK(&io->work, verity_work); + queue_work(io->v->verify_wq, &io->work); } /* @@ -950,6 +984,10 @@ static void verity_dtr(struct dm_target *ti) if (v->verify_wq) destroy_workqueue(v->verify_wq); + mempool_exit(&v->recheck_pool); + if (v->io) + dm_io_client_destroy(v->io); + if (v->bufio) dm_bufio_client_destroy(v->bufio); @@ -1386,6 +1424,20 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) } v->hash_blocks = hash_position; + r = mempool_init_page_pool(&v->recheck_pool, 1, 0); + if (unlikely(r)) { + ti->error = "Cannot allocate mempool"; + goto bad; + } + + v->io = dm_io_client_create(); + if (IS_ERR(v->io)) { + r = PTR_ERR(v->io); + v->io = NULL; + ti->error = "Cannot allocate dm io"; + goto bad; + } + v->bufio = dm_bufio_client_create(v->hash_dev->bdev, 1 << v->hash_dev_block_bits, 1, sizeof(struct buffer_aux), dm_bufio_alloc_callback, NULL, diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index f9d522c870e6..4620a98c9956 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -11,6 +11,7 @@ #ifndef DM_VERITY_H #define DM_VERITY_H +#include <linux/dm-io.h> #include <linux/dm-bufio.h> #include <linux/device-mapper.h> #include <linux/interrupt.h> @@ -68,6 +69,9 @@ struct dm_verity { unsigned long *validated_blocks; /* bitset blocks validated */ char *signature_key_desc; /* signature keyring reference */ + + struct dm_io_client *io; + mempool_t recheck_pool; }; struct dm_verity_io { @@ -83,7 +87,8 @@ struct dm_verity_io { struct bvec_iter iter; struct work_struct work; - struct tasklet_struct tasklet; + + char *recheck_buffer; /* * Three variably-size fields follow this struct: diff --git a/drivers/md/md.c b/drivers/md/md.c index 0c2801d77090..846bdee4daa0 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -528,6 +528,9 @@ static void md_end_flush(struct bio *bio) rdev_dec_pending(rdev, mddev); if (atomic_dec_and_test(&mddev->flush_pending)) { + /* The pair is percpu_ref_get() from md_flush_request() */ + percpu_ref_put(&mddev->active_io); + /* The pre-request flush has finished */ queue_work(md_wq, &mddev->flush_work); } @@ -547,12 +550,8 @@ static void submit_flushes(struct work_struct *ws) rdev_for_each_rcu(rdev, mddev) if (rdev->raid_disk >= 0 && !test_bit(Faulty, &rdev->flags)) { - /* Take two references, one is dropped - * when request finishes, one after - * we reclaim rcu_read_lock - */ struct bio *bi; - atomic_inc(&rdev->nr_pending); + atomic_inc(&rdev->nr_pending); rcu_read_unlock(); bi = bio_alloc_bioset(rdev->bdev, 0, @@ -563,11 +562,14 @@ static void submit_flushes(struct work_struct *ws) atomic_inc(&mddev->flush_pending); submit_bio(bi); rcu_read_lock(); - rdev_dec_pending(rdev, mddev); } rcu_read_unlock(); - if (atomic_dec_and_test(&mddev->flush_pending)) + if (atomic_dec_and_test(&mddev->flush_pending)) { + /* The pair is percpu_ref_get() from md_flush_request() */ + percpu_ref_put(&mddev->active_io); + queue_work(md_wq, &mddev->flush_work); + } } static void md_submit_flush_data(struct work_struct *ws) @@ -616,6 +618,18 @@ bool md_flush_request(struct mddev *mddev, struct bio *bio) /* new request after previous flush is completed */ if (ktime_after(req_start, mddev->prev_flush_start)) { WARN_ON(mddev->flush_bio); + /* + * Grab a reference to make sure mddev_suspend() will wait for + * this flush to be done. + * + * md_flush_reqeust() is called under md_handle_request() and + * 'active_io' is already grabbed, hence percpu_ref_is_zero() + * won't pass, percpu_ref_tryget_live() can't be used because + * percpu_ref_kill() can be called by mddev_suspend() + * concurrently. + */ + WARN_ON(percpu_ref_is_zero(&mddev->active_io)); + percpu_ref_get(&mddev->active_io); mddev->flush_bio = bio; bio = NULL; } @@ -953,9 +967,10 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, return; bio = bio_alloc_bioset(rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev, - 1, - REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA, - GFP_NOIO, &mddev->sync_set); + 1, + REQ_OP_WRITE | REQ_SYNC | REQ_IDLE | REQ_META + | REQ_PREFLUSH | REQ_FUA, + GFP_NOIO, &mddev->sync_set); atomic_inc(&rdev->nr_pending); @@ -1135,6 +1150,7 @@ struct super_type { struct md_rdev *refdev, int minor_version); int (*validate_super)(struct mddev *mddev, + struct md_rdev *freshest, struct md_rdev *rdev); void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); @@ -1272,8 +1288,9 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor /* * validate_super for 0.90.0 + * note: we are not using "freshest" for 0.9 superblock */ -static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev) +static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev) { mdp_disk_t *desc; mdp_super_t *sb = page_address(rdev->sb_page); @@ -1785,7 +1802,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ return ret; } -static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) +static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev) { struct mdp_superblock_1 *sb = page_address(rdev->sb_page); __u64 ev1 = le64_to_cpu(sb->events); @@ -1881,13 +1898,15 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) } } else if (mddev->pers == NULL) { /* Insist of good event counter while assembling, except for - * spares (which don't need an event count) */ - ++ev1; + * spares (which don't need an event count). + * Similar to mdadm, we allow event counter difference of 1 + * from the freshest device. + */ if (rdev->desc_nr >= 0 && rdev->desc_nr < le32_to_cpu(sb->max_dev) && (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX || le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)) - if (ev1 < mddev->events) + if (ev1 + 1 < mddev->events) return -EINVAL; } else if (mddev->bitmap) { /* If adding to array with a bitmap, then we can accept an @@ -1908,8 +1927,38 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) rdev->desc_nr >= le32_to_cpu(sb->max_dev)) { role = MD_DISK_ROLE_SPARE; rdev->desc_nr = -1; - } else + } else if (mddev->pers == NULL && freshest && ev1 < mddev->events) { + /* + * If we are assembling, and our event counter is smaller than the + * highest event counter, we cannot trust our superblock about the role. + * It could happen that our rdev was marked as Faulty, and all other + * superblocks were updated with +1 event counter. + * Then, before the next superblock update, which typically happens when + * remove_and_add_spares() removes the device from the array, there was + * a crash or reboot. + * If we allow current rdev without consulting the freshest superblock, + * we could cause data corruption. + * Note that in this case our event counter is smaller by 1 than the + * highest, otherwise, this rdev would not be allowed into array; + * both kernel and mdadm allow event counter difference of 1. + */ + struct mdp_superblock_1 *freshest_sb = page_address(freshest->sb_page); + u32 freshest_max_dev = le32_to_cpu(freshest_sb->max_dev); + + if (rdev->desc_nr >= freshest_max_dev) { + /* this is unexpected, better not proceed */ + pr_warn("md: %s: rdev[%pg]: desc_nr(%d) >= freshest(%pg)->sb->max_dev(%u)\n", + mdname(mddev), rdev->bdev, rdev->desc_nr, + freshest->bdev, freshest_max_dev); + return -EUCLEAN; + } + + role = le16_to_cpu(freshest_sb->dev_roles[rdev->desc_nr]); + pr_debug("md: %s: rdev[%pg]: role=%d(0x%x) according to freshest %pg\n", + mdname(mddev), rdev->bdev, role, role, freshest->bdev); + } else { role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); + } switch(role) { case MD_DISK_ROLE_SPARE: /* spare */ break; @@ -2851,7 +2900,7 @@ static int add_bound_rdev(struct md_rdev *rdev) * and should be added immediately. */ super_types[mddev->major_version]. - validate_super(mddev, rdev); + validate_super(mddev, NULL/*freshest*/, rdev); if (add_journal) mddev_suspend(mddev); err = mddev->pers->hot_add_disk(mddev, rdev); @@ -3765,7 +3814,7 @@ static int analyze_sbs(struct mddev *mddev) } super_types[mddev->major_version]. - validate_super(mddev, freshest); + validate_super(mddev, NULL/*freshest*/, freshest); i = 0; rdev_for_each_safe(rdev, tmp, mddev) { @@ -3780,7 +3829,7 @@ static int analyze_sbs(struct mddev *mddev) } if (rdev != freshest) { if (super_types[mddev->major_version]. - validate_super(mddev, rdev)) { + validate_super(mddev, freshest, rdev)) { pr_warn("md: kicking non-fresh %pg from array!\n", rdev->bdev); md_kick_rdev_from_array(rdev); @@ -6794,7 +6843,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) rdev->saved_raid_disk = rdev->raid_disk; } else super_types[mddev->major_version]. - validate_super(mddev, rdev); + validate_super(mddev, NULL/*freshest*/, rdev); if ((info->state & (1<<MD_DISK_SYNC)) && rdev->raid_disk != info->raid_disk) { /* This was a hot-add request, but events doesn't diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index 1f40100908d7..2bbfbb704c75 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -415,6 +415,12 @@ void dm_block_manager_destroy(struct dm_block_manager *bm) } EXPORT_SYMBOL_GPL(dm_block_manager_destroy); +void dm_block_manager_reset(struct dm_block_manager *bm) +{ + dm_bufio_client_reset(bm->bufio); +} +EXPORT_SYMBOL_GPL(dm_block_manager_reset); + unsigned int dm_bm_block_size(struct dm_block_manager *bm) { return dm_bufio_get_block_size(bm->bufio); diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h index 58a23b8ec190..4371d85d3c25 100644 --- a/drivers/md/persistent-data/dm-block-manager.h +++ b/drivers/md/persistent-data/dm-block-manager.h @@ -35,6 +35,7 @@ struct dm_block_manager *dm_block_manager_create( struct block_device *bdev, unsigned int block_size, unsigned int max_held_per_thread); void dm_block_manager_destroy(struct dm_block_manager *bm); +void dm_block_manager_reset(struct dm_block_manager *bm); unsigned int dm_bm_block_size(struct dm_block_manager *bm); dm_block_t dm_bm_nr_blocks(struct dm_block_manager *bm); diff --git a/drivers/md/persistent-data/dm-space-map.h b/drivers/md/persistent-data/dm-space-map.h index a015cd11f6e9..85aa0a3974fe 100644 --- a/drivers/md/persistent-data/dm-space-map.h +++ b/drivers/md/persistent-data/dm-space-map.h @@ -76,7 +76,8 @@ struct dm_space_map { static inline void dm_sm_destroy(struct dm_space_map *sm) { - sm->destroy(sm); + if (sm) + sm->destroy(sm); } static inline int dm_sm_extend(struct dm_space_map *sm, dm_block_t extra_blocks) diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c index 39885f835584..557a3ecfe75a 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.c +++ b/drivers/md/persistent-data/dm-transaction-manager.c @@ -197,6 +197,9 @@ EXPORT_SYMBOL_GPL(dm_tm_create_non_blocking_clone); void dm_tm_destroy(struct dm_transaction_manager *tm) { + if (!tm) + return; + if (!tm->is_clone) wipe_shadow_table(tm); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 30f906a67def..76f7ca53d812 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1972,12 +1972,12 @@ static void end_sync_write(struct bio *bio) } static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector, - int sectors, struct page *page, int rw) + int sectors, struct page *page, blk_opf_t rw) { if (sync_page_io(rdev, sector, sectors << 9, page, rw, false)) /* success */ return 1; - if (rw == WRITE) { + if (rw == REQ_OP_WRITE) { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) @@ -2094,7 +2094,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio) rdev = conf->mirrors[d].rdev; if (r1_sync_page_io(rdev, sect, s, pages[idx], - WRITE) == 0) { + REQ_OP_WRITE) == 0) { r1_bio->bios[d]->bi_end_io = NULL; rdev_dec_pending(rdev, mddev); } @@ -2109,7 +2109,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio) rdev = conf->mirrors[d].rdev; if (r1_sync_page_io(rdev, sect, s, pages[idx], - READ) != 0) + REQ_OP_READ) != 0) atomic_add(s, &rdev->corrected_errors); } sectors -= s; @@ -2321,7 +2321,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk, atomic_inc(&rdev->nr_pending); rcu_read_unlock(); r1_sync_page_io(rdev, sect, s, - conf->tmppage, WRITE); + conf->tmppage, REQ_OP_WRITE); rdev_dec_pending(rdev, mddev); } else rcu_read_unlock(); @@ -2338,7 +2338,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk, atomic_inc(&rdev->nr_pending); rcu_read_unlock(); if (r1_sync_page_io(rdev, sect, s, - conf->tmppage, READ)) { + conf->tmppage, REQ_OP_READ)) { atomic_add(s, &rdev->corrected_errors); pr_info("md/raid1:%s: read error corrected (%d sectors at %llu on %pg)\n", mdname(mddev), s, diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index fa69158a65b1..cb1e4bc69dba 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -494,9 +494,15 @@ vb2_dma_sg_dmabuf_ops_end_cpu_access(struct dma_buf *dbuf, static int vb2_dma_sg_dmabuf_ops_vmap(struct dma_buf *dbuf, struct iosys_map *map) { - struct vb2_dma_sg_buf *buf = dbuf->priv; + struct vb2_dma_sg_buf *buf; + void *vaddr; + + buf = dbuf->priv; + vaddr = vb2_dma_sg_vaddr(buf->vb, buf); + if (!vaddr) + return -EINVAL; - iosys_map_set_vaddr(map, buf->vaddr); + iosys_map_set_vaddr(map, vaddr); return 0; } diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index 9f9a97652708..d352e028491a 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -104,6 +104,8 @@ static int dvb_device_open(struct inode *inode, struct file *file) err = file->f_op->open(inode, file); up_read(&minor_rwsem); mutex_unlock(&dvbdev_mutex); + if (err) + dvb_device_put(dvbdev); return err; } fail: diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c index 9a0d43c7ba9e..ce99f7dfb5a5 100644 --- a/drivers/media/dvb-frontends/m88ds3103.c +++ b/drivers/media/dvb-frontends/m88ds3103.c @@ -1894,7 +1894,7 @@ static int m88ds3103_probe(struct i2c_client *client, /* get frontend address */ ret = regmap_read(dev->regmap, 0x29, &utmp); if (ret) - goto err_kfree; + goto err_del_adapters; dev->dt_addr = ((utmp & 0x80) == 0) ? 0x42 >> 1 : 0x40 >> 1; dev_dbg(&client->dev, "dt addr is 0x%02x\n", dev->dt_addr); @@ -1902,11 +1902,14 @@ static int m88ds3103_probe(struct i2c_client *client, dev->dt_addr); if (IS_ERR(dev->dt_client)) { ret = PTR_ERR(dev->dt_client); - goto err_kfree; + goto err_del_adapters; } } return 0; + +err_del_adapters: + i2c_mux_del_adapters(dev->muxc); err_kfree: kfree(dev); err: diff --git a/drivers/media/i2c/imx335.c b/drivers/media/i2c/imx335.c index 078ede2b7a00..8e91767d6130 100644 --- a/drivers/media/i2c/imx335.c +++ b/drivers/media/i2c/imx335.c @@ -971,8 +971,8 @@ static int imx335_init_controls(struct imx335 *imx335) imx335->hblank_ctrl = v4l2_ctrl_new_std(ctrl_hdlr, &imx335_ctrl_ops, V4L2_CID_HBLANK, - IMX335_REG_MIN, - IMX335_REG_MAX, + mode->hblank, + mode->hblank, 1, mode->hblank); if (imx335->hblank_ctrl) imx335->hblank_ctrl->flags |= V4L2_CTRL_FLAG_READ_ONLY; diff --git a/drivers/media/i2c/imx355.c b/drivers/media/i2c/imx355.c index b46178681c05..7fb02ba56012 100644 --- a/drivers/media/i2c/imx355.c +++ b/drivers/media/i2c/imx355.c @@ -1784,10 +1784,6 @@ static int imx355_probe(struct i2c_client *client) goto error_handler_free; } - ret = v4l2_async_register_subdev_sensor(&imx355->sd); - if (ret < 0) - goto error_media_entity; - /* * Device is already turned on by i2c-core with ACPI domain PM. * Enable runtime PM and turn off the device. @@ -1796,9 +1792,15 @@ static int imx355_probe(struct i2c_client *client) pm_runtime_enable(&client->dev); pm_runtime_idle(&client->dev); + ret = v4l2_async_register_subdev_sensor(&imx355->sd); + if (ret < 0) + goto error_media_entity_runtime_pm; + return 0; -error_media_entity: +error_media_entity_runtime_pm: + pm_runtime_disable(&client->dev); + pm_runtime_set_suspended(&client->dev); media_entity_cleanup(&imx355->sd.entity); error_handler_free: diff --git a/drivers/media/i2c/ov13b10.c b/drivers/media/i2c/ov13b10.c index 549e5d93e568..368a3c2bfe34 100644 --- a/drivers/media/i2c/ov13b10.c +++ b/drivers/media/i2c/ov13b10.c @@ -589,6 +589,9 @@ struct ov13b10 { /* Streaming on/off */ bool streaming; + + /* True if the device has been identified */ + bool identified; }; #define to_ov13b10(_sd) container_of(_sd, struct ov13b10, sd) @@ -1023,12 +1026,42 @@ ov13b10_set_pad_format(struct v4l2_subdev *sd, return 0; } +/* Verify chip ID */ +static int ov13b10_identify_module(struct ov13b10 *ov13b) +{ + struct i2c_client *client = v4l2_get_subdevdata(&ov13b->sd); + int ret; + u32 val; + + if (ov13b->identified) + return 0; + + ret = ov13b10_read_reg(ov13b, OV13B10_REG_CHIP_ID, + OV13B10_REG_VALUE_24BIT, &val); + if (ret) + return ret; + + if (val != OV13B10_CHIP_ID) { + dev_err(&client->dev, "chip id mismatch: %x!=%x\n", + OV13B10_CHIP_ID, val); + return -EIO; + } + + ov13b->identified = true; + + return 0; +} + static int ov13b10_start_streaming(struct ov13b10 *ov13b) { struct i2c_client *client = v4l2_get_subdevdata(&ov13b->sd); const struct ov13b10_reg_list *reg_list; int ret, link_freq_index; + ret = ov13b10_identify_module(ov13b); + if (ret) + return ret; + /* Get out of from software reset */ ret = ov13b10_write_reg(ov13b, OV13B10_REG_SOFTWARE_RST, OV13B10_REG_VALUE_08BIT, OV13B10_SOFTWARE_RST); @@ -1144,27 +1177,6 @@ error: return ret; } -/* Verify chip ID */ -static int ov13b10_identify_module(struct ov13b10 *ov13b) -{ - struct i2c_client *client = v4l2_get_subdevdata(&ov13b->sd); - int ret; - u32 val; - - ret = ov13b10_read_reg(ov13b, OV13B10_REG_CHIP_ID, - OV13B10_REG_VALUE_24BIT, &val); - if (ret) - return ret; - - if (val != OV13B10_CHIP_ID) { - dev_err(&client->dev, "chip id mismatch: %x!=%x\n", - OV13B10_CHIP_ID, val); - return -EIO; - } - - return 0; -} - static const struct v4l2_subdev_video_ops ov13b10_video_ops = { .s_stream = ov13b10_set_stream, }; @@ -1379,6 +1391,7 @@ out_err: static int ov13b10_probe(struct i2c_client *client) { struct ov13b10 *ov13b; + bool full_power; int ret; /* Check HW config */ @@ -1395,11 +1408,14 @@ static int ov13b10_probe(struct i2c_client *client) /* Initialize subdev */ v4l2_i2c_subdev_init(&ov13b->sd, client, &ov13b10_subdev_ops); - /* Check module identity */ - ret = ov13b10_identify_module(ov13b); - if (ret) { - dev_err(&client->dev, "failed to find sensor: %d\n", ret); - return ret; + full_power = acpi_dev_state_d0(&client->dev); + if (full_power) { + /* Check module identity */ + ret = ov13b10_identify_module(ov13b); + if (ret) { + dev_err(&client->dev, "failed to find sensor: %d\n", ret); + return ret; + } } /* Set default mode to max resolution */ @@ -1423,21 +1439,27 @@ static int ov13b10_probe(struct i2c_client *client) goto error_handler_free; } - ret = v4l2_async_register_subdev_sensor(&ov13b->sd); - if (ret < 0) - goto error_media_entity; /* * Device is already turned on by i2c-core with ACPI domain PM. * Enable runtime PM and turn off the device. */ - pm_runtime_set_active(&client->dev); + /* Set the device's state to active if it's in D0 state. */ + if (full_power) + pm_runtime_set_active(&client->dev); pm_runtime_enable(&client->dev); pm_runtime_idle(&client->dev); + ret = v4l2_async_register_subdev_sensor(&ov13b->sd); + if (ret < 0) + goto error_media_entity_runtime_pm; + return 0; -error_media_entity: +error_media_entity_runtime_pm: + pm_runtime_disable(&client->dev); + if (full_power) + pm_runtime_set_suspended(&client->dev); media_entity_cleanup(&ov13b->sd.entity); error_handler_free: @@ -1457,6 +1479,7 @@ static void ov13b10_remove(struct i2c_client *client) ov13b10_free_controls(ov13b); pm_runtime_disable(&client->dev); + pm_runtime_set_suspended(&client->dev); } static const struct dev_pm_ops ov13b10_pm_ops = { @@ -1480,6 +1503,7 @@ static struct i2c_driver ov13b10_i2c_driver = { }, .probe_new = ov13b10_probe, .remove = ov13b10_remove, + .flags = I2C_DRV_ACPI_WAIVE_D0_PROBE, }; module_i2c_driver(ov13b10_i2c_driver); diff --git a/drivers/media/i2c/ov9734.c b/drivers/media/i2c/ov9734.c index 8b0a158cb297..c5592ddb0cff 100644 --- a/drivers/media/i2c/ov9734.c +++ b/drivers/media/i2c/ov9734.c @@ -939,6 +939,7 @@ static void ov9734_remove(struct i2c_client *client) media_entity_cleanup(&sd->entity); v4l2_ctrl_handler_free(sd->ctrl_handler); pm_runtime_disable(&client->dev); + pm_runtime_set_suspended(&client->dev); mutex_destroy(&ov9734->mutex); } @@ -984,13 +985,6 @@ static int ov9734_probe(struct i2c_client *client) goto probe_error_v4l2_ctrl_handler_free; } - ret = v4l2_async_register_subdev_sensor(&ov9734->sd); - if (ret < 0) { - dev_err(&client->dev, "failed to register V4L2 subdev: %d", - ret); - goto probe_error_media_entity_cleanup; - } - /* * Device is already turned on by i2c-core with ACPI domain PM. * Enable runtime PM and turn off the device. @@ -999,9 +993,18 @@ static int ov9734_probe(struct i2c_client *client) pm_runtime_enable(&client->dev); pm_runtime_idle(&client->dev); + ret = v4l2_async_register_subdev_sensor(&ov9734->sd); + if (ret < 0) { + dev_err(&client->dev, "failed to register V4L2 subdev: %d", + ret); + goto probe_error_media_entity_cleanup_pm; + } + return 0; -probe_error_media_entity_cleanup: +probe_error_media_entity_cleanup_pm: + pm_runtime_disable(&client->dev); + pm_runtime_set_suspended(&client->dev); media_entity_cleanup(&ov9734->sd.entity); probe_error_v4l2_ctrl_handler_free: diff --git a/drivers/media/pci/ddbridge/ddbridge-main.c b/drivers/media/pci/ddbridge/ddbridge-main.c index 91733ab9f58c..363badab7cf0 100644 --- a/drivers/media/pci/ddbridge/ddbridge-main.c +++ b/drivers/media/pci/ddbridge/ddbridge-main.c @@ -238,7 +238,7 @@ fail: ddb_unmap(dev); pci_set_drvdata(pdev, NULL); pci_disable_device(pdev); - return -1; + return stat; } /****************************************************************************/ diff --git a/drivers/media/platform/amphion/vpu.h b/drivers/media/platform/amphion/vpu.h index deb2288d4290..4f3d23b55b6d 100644 --- a/drivers/media/platform/amphion/vpu.h +++ b/drivers/media/platform/amphion/vpu.h @@ -152,7 +152,6 @@ struct vpu_core { struct vpu_mbox tx_type; struct vpu_mbox tx_data; struct vpu_mbox rx; - unsigned long cmd_seq; wait_queue_head_t ack_wq; struct completion cmp; @@ -251,6 +250,8 @@ struct vpu_inst { struct list_head cmd_q; void *pending; + unsigned long cmd_seq; + atomic_long_t last_response_cmd; struct vpu_inst_ops *ops; const struct vpu_format *formats; diff --git a/drivers/media/platform/amphion/vpu_cmds.c b/drivers/media/platform/amphion/vpu_cmds.c index 235b71398d40..c68163af29dc 100644 --- a/drivers/media/platform/amphion/vpu_cmds.c +++ b/drivers/media/platform/amphion/vpu_cmds.c @@ -34,6 +34,7 @@ struct vpu_cmd_t { struct vpu_cmd_request *request; struct vpu_rpc_event *pkt; unsigned long key; + atomic_long_t *last_response_cmd; }; static struct vpu_cmd_request vpu_cmd_requests[] = { @@ -117,6 +118,8 @@ static void vpu_free_cmd(struct vpu_cmd_t *cmd) { if (!cmd) return; + if (cmd->last_response_cmd) + atomic_long_set(cmd->last_response_cmd, cmd->key); vfree(cmd->pkt); vfree(cmd); } @@ -174,7 +177,8 @@ static int vpu_request_cmd(struct vpu_inst *inst, u32 id, void *data, return -ENOMEM; mutex_lock(&core->cmd_lock); - cmd->key = core->cmd_seq++; + cmd->key = ++inst->cmd_seq; + cmd->last_response_cmd = &inst->last_response_cmd; if (key) *key = cmd->key; if (sync) @@ -248,26 +252,12 @@ void vpu_clear_request(struct vpu_inst *inst) static bool check_is_responsed(struct vpu_inst *inst, unsigned long key) { - struct vpu_core *core = inst->core; - struct vpu_cmd_t *cmd; - bool flag = true; + unsigned long last_response = atomic_long_read(&inst->last_response_cmd); - mutex_lock(&core->cmd_lock); - cmd = inst->pending; - if (cmd && key == cmd->key) { - flag = false; - goto exit; - } - list_for_each_entry(cmd, &inst->cmd_q, list) { - if (key == cmd->key) { - flag = false; - break; - } - } -exit: - mutex_unlock(&core->cmd_lock); + if (key <= last_response && (last_response - key) < (ULONG_MAX >> 1)) + return true; - return flag; + return false; } static int sync_session_response(struct vpu_inst *inst, unsigned long key, long timeout, int try) diff --git a/drivers/media/platform/amphion/vpu_v4l2.c b/drivers/media/platform/amphion/vpu_v4l2.c index e5c8e1a753cc..e7a18948c4ab 100644 --- a/drivers/media/platform/amphion/vpu_v4l2.c +++ b/drivers/media/platform/amphion/vpu_v4l2.c @@ -631,6 +631,7 @@ int vpu_v4l2_open(struct file *file, struct vpu_inst *inst) func = &vpu->decoder; atomic_set(&inst->ref_count, 0); + atomic_long_set(&inst->last_response_cmd, 0); vpu_inst_get(inst); inst->vpu = vpu; inst->core = vpu_request_core(vpu, inst->type); diff --git a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c index e9a4f8abd21c..f911d3c7dd86 100644 --- a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c +++ b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c @@ -974,13 +974,13 @@ static void mtk_jpeg_dec_device_run(void *priv) if (ret < 0) goto dec_end; - schedule_delayed_work(&jpeg->job_timeout_work, - msecs_to_jiffies(MTK_JPEG_HW_TIMEOUT_MSEC)); - mtk_jpeg_set_dec_src(ctx, &src_buf->vb2_buf, &bs); if (mtk_jpeg_set_dec_dst(ctx, &jpeg_src_buf->dec_param, &dst_buf->vb2_buf, &fb)) goto dec_end; + schedule_delayed_work(&jpeg->job_timeout_work, + msecs_to_jiffies(MTK_JPEG_HW_TIMEOUT_MSEC)); + spin_lock_irqsave(&jpeg->hw_lock, flags); mtk_jpeg_dec_reset(jpeg->reg_base); mtk_jpeg_dec_set_config(jpeg->reg_base, @@ -1412,7 +1412,6 @@ static int mtk_jpeg_remove(struct platform_device *pdev) { struct mtk_jpeg_dev *jpeg = platform_get_drvdata(pdev); - cancel_delayed_work_sync(&jpeg->job_timeout_work); pm_runtime_disable(&pdev->dev); video_unregister_device(jpeg->vdev); v4l2_m2m_release(jpeg->m2m_dev); diff --git a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_dec_hw.c b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_dec_hw.c index afbbfd5d02bc..6d200e23754e 100644 --- a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_dec_hw.c +++ b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_dec_hw.c @@ -188,6 +188,7 @@ int mtk_jpeg_dec_fill_param(struct mtk_jpeg_dec_param *param) return 0; } +EXPORT_SYMBOL_GPL(mtk_jpeg_dec_fill_param); u32 mtk_jpeg_dec_get_int_status(void __iomem *base) { @@ -199,6 +200,7 @@ u32 mtk_jpeg_dec_get_int_status(void __iomem *base) return ret; } +EXPORT_SYMBOL_GPL(mtk_jpeg_dec_get_int_status); u32 mtk_jpeg_dec_enum_result(u32 irq_result) { @@ -215,11 +217,13 @@ u32 mtk_jpeg_dec_enum_result(u32 irq_result) return MTK_JPEG_DEC_RESULT_ERROR_UNKNOWN; } +EXPORT_SYMBOL_GPL(mtk_jpeg_dec_enum_result); void mtk_jpeg_dec_start(void __iomem *base) { writel(0, base + JPGDEC_REG_TRIG); } +EXPORT_SYMBOL_GPL(mtk_jpeg_dec_start); static void mtk_jpeg_dec_soft_reset(void __iomem *base) { @@ -239,6 +243,7 @@ void mtk_jpeg_dec_reset(void __iomem *base) mtk_jpeg_dec_soft_reset(base); mtk_jpeg_dec_hard_reset(base); } +EXPORT_SYMBOL_GPL(mtk_jpeg_dec_reset); static void mtk_jpeg_dec_set_brz_factor(void __iomem *base, u8 yscale_w, u8 yscale_h, u8 uvscale_w, u8 uvscale_h) @@ -407,3 +412,4 @@ void mtk_jpeg_dec_set_config(void __iomem *base, config->dma_last_mcu); mtk_jpeg_dec_set_pause_mcu_idx(base, config->total_mcu); } +EXPORT_SYMBOL_GPL(mtk_jpeg_dec_set_config); diff --git a/drivers/media/platform/nxp/imx-mipi-csis.c b/drivers/media/platform/nxp/imx-mipi-csis.c index 905072871ed2..196f2bba419f 100644 --- a/drivers/media/platform/nxp/imx-mipi-csis.c +++ b/drivers/media/platform/nxp/imx-mipi-csis.c @@ -1553,8 +1553,10 @@ static int mipi_csis_remove(struct platform_device *pdev) v4l2_async_nf_cleanup(&csis->notifier); v4l2_async_unregister_subdev(&csis->sd); + if (!pm_runtime_enabled(&pdev->dev)) + mipi_csis_runtime_suspend(&pdev->dev); + pm_runtime_disable(&pdev->dev); - mipi_csis_runtime_suspend(&pdev->dev); mipi_csis_clk_disable(csis); media_entity_cleanup(&csis->sd.entity); fwnode_handle_put(csis->sd.fwnode); diff --git a/drivers/media/platform/qcom/camss/camss-csid-gen2.c b/drivers/media/platform/qcom/camss/camss-csid-gen2.c index 904208f6f954..0147cc062e1a 100644 --- a/drivers/media/platform/qcom/camss/camss-csid-gen2.c +++ b/drivers/media/platform/qcom/camss/camss-csid-gen2.c @@ -334,13 +334,14 @@ static const struct csid_format csid_formats[] = { }, }; -static void csid_configure_stream(struct csid_device *csid, u8 enable) +static void __csid_configure_stream(struct csid_device *csid, u8 enable, u8 vc) { struct csid_testgen_config *tg = &csid->testgen; u32 val; u32 phy_sel = 0; u8 lane_cnt = csid->phy.lane_cnt; - struct v4l2_mbus_framefmt *input_format = &csid->fmt[MSM_CSID_PAD_SRC]; + /* Source pads matching RDI channels on hardware. Pad 1 -> RDI0, Pad 2 -> RDI1, etc. */ + struct v4l2_mbus_framefmt *input_format = &csid->fmt[MSM_CSID_PAD_FIRST_SRC + vc]; const struct csid_format *format = csid_get_fmt_entry(csid->formats, csid->nformats, input_format->code); @@ -351,8 +352,19 @@ static void csid_configure_stream(struct csid_device *csid, u8 enable) phy_sel = csid->phy.csiphy_id; if (enable) { - u8 vc = 0; /* Virtual Channel 0 */ - u8 dt_id = vc * 4; + /* + * DT_ID is a two bit bitfield that is concatenated with + * the four least significant bits of the five bit VC + * bitfield to generate an internal CID value. + * + * CSID_RDI_CFG0(vc) + * DT_ID : 28:27 + * VC : 26:22 + * DT : 21:16 + * + * CID : VC 3:0 << 2 | DT_ID 1:0 + */ + u8 dt_id = vc & 0x03; if (tg->enabled) { /* configure one DT, infinite frames */ @@ -392,42 +404,42 @@ static void csid_configure_stream(struct csid_device *csid, u8 enable) val |= format->data_type << RDI_CFG0_DATA_TYPE; val |= vc << RDI_CFG0_VIRTUAL_CHANNEL; val |= dt_id << RDI_CFG0_DT_ID; - writel_relaxed(val, csid->base + CSID_RDI_CFG0(0)); + writel_relaxed(val, csid->base + CSID_RDI_CFG0(vc)); /* CSID_TIMESTAMP_STB_POST_IRQ */ val = 2 << RDI_CFG1_TIMESTAMP_STB_SEL; - writel_relaxed(val, csid->base + CSID_RDI_CFG1(0)); + writel_relaxed(val, csid->base + CSID_RDI_CFG1(vc)); val = 1; - writel_relaxed(val, csid->base + CSID_RDI_FRM_DROP_PERIOD(0)); + writel_relaxed(val, csid->base + CSID_RDI_FRM_DROP_PERIOD(vc)); val = 0; - writel_relaxed(val, csid->base + CSID_RDI_FRM_DROP_PATTERN(0)); + writel_relaxed(val, csid->base + CSID_RDI_FRM_DROP_PATTERN(vc)); val = 1; - writel_relaxed(val, csid->base + CSID_RDI_IRQ_SUBSAMPLE_PERIOD(0)); + writel_relaxed(val, csid->base + CSID_RDI_IRQ_SUBSAMPLE_PERIOD(vc)); val = 0; - writel_relaxed(val, csid->base + CSID_RDI_IRQ_SUBSAMPLE_PATTERN(0)); + writel_relaxed(val, csid->base + CSID_RDI_IRQ_SUBSAMPLE_PATTERN(vc)); val = 1; - writel_relaxed(val, csid->base + CSID_RDI_RPP_PIX_DROP_PERIOD(0)); + writel_relaxed(val, csid->base + CSID_RDI_RPP_PIX_DROP_PERIOD(vc)); val = 0; - writel_relaxed(val, csid->base + CSID_RDI_RPP_PIX_DROP_PATTERN(0)); + writel_relaxed(val, csid->base + CSID_RDI_RPP_PIX_DROP_PATTERN(vc)); val = 1; - writel_relaxed(val, csid->base + CSID_RDI_RPP_LINE_DROP_PERIOD(0)); + writel_relaxed(val, csid->base + CSID_RDI_RPP_LINE_DROP_PERIOD(vc)); val = 0; - writel_relaxed(val, csid->base + CSID_RDI_RPP_LINE_DROP_PATTERN(0)); + writel_relaxed(val, csid->base + CSID_RDI_RPP_LINE_DROP_PATTERN(vc)); val = 0; - writel_relaxed(val, csid->base + CSID_RDI_CTRL(0)); + writel_relaxed(val, csid->base + CSID_RDI_CTRL(vc)); - val = readl_relaxed(csid->base + CSID_RDI_CFG0(0)); + val = readl_relaxed(csid->base + CSID_RDI_CFG0(vc)); val |= 1 << RDI_CFG0_ENABLE; - writel_relaxed(val, csid->base + CSID_RDI_CFG0(0)); + writel_relaxed(val, csid->base + CSID_RDI_CFG0(vc)); } if (tg->enabled) { @@ -446,6 +458,8 @@ static void csid_configure_stream(struct csid_device *csid, u8 enable) writel_relaxed(val, csid->base + CSID_CSI2_RX_CFG0); val = 1 << CSI2_RX_CFG1_PACKET_ECC_CORRECTION_EN; + if (vc > 3) + val |= 1 << CSI2_RX_CFG1_VC_MODE; val |= 1 << CSI2_RX_CFG1_MISR_EN; writel_relaxed(val, csid->base + CSID_CSI2_RX_CFG1); @@ -453,7 +467,16 @@ static void csid_configure_stream(struct csid_device *csid, u8 enable) val = HALT_CMD_RESUME_AT_FRAME_BOUNDARY << RDI_CTRL_HALT_CMD; else val = HALT_CMD_HALT_AT_FRAME_BOUNDARY << RDI_CTRL_HALT_CMD; - writel_relaxed(val, csid->base + CSID_RDI_CTRL(0)); + writel_relaxed(val, csid->base + CSID_RDI_CTRL(vc)); +} + +static void csid_configure_stream(struct csid_device *csid, u8 enable) +{ + u8 i; + /* Loop through all enabled VCs and configure stream for each */ + for (i = 0; i < MSM_CSID_MAX_SRC_STREAMS; i++) + if (csid->phy.en_vc & BIT(i)) + __csid_configure_stream(csid, enable, i); } static int csid_configure_testgen_pattern(struct csid_device *csid, s32 val) @@ -499,6 +522,7 @@ static irqreturn_t csid_isr(int irq, void *dev) struct csid_device *csid = dev; u32 val; u8 reset_done; + int i; val = readl_relaxed(csid->base + CSID_TOP_IRQ_STATUS); writel_relaxed(val, csid->base + CSID_TOP_IRQ_CLEAR); @@ -507,8 +531,12 @@ static irqreturn_t csid_isr(int irq, void *dev) val = readl_relaxed(csid->base + CSID_CSI2_RX_IRQ_STATUS); writel_relaxed(val, csid->base + CSID_CSI2_RX_IRQ_CLEAR); - val = readl_relaxed(csid->base + CSID_CSI2_RDIN_IRQ_STATUS(0)); - writel_relaxed(val, csid->base + CSID_CSI2_RDIN_IRQ_CLEAR(0)); + /* Read and clear IRQ status for each enabled RDI channel */ + for (i = 0; i < MSM_CSID_MAX_SRC_STREAMS; i++) + if (csid->phy.en_vc & BIT(i)) { + val = readl_relaxed(csid->base + CSID_CSI2_RDIN_IRQ_STATUS(i)); + writel_relaxed(val, csid->base + CSID_CSI2_RDIN_IRQ_CLEAR(i)); + } val = 1 << IRQ_CMD_CLEAR; writel_relaxed(val, csid->base + CSID_IRQ_CMD); diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c index 88f188e0f750..6360314f04a6 100644 --- a/drivers/media/platform/qcom/camss/camss-csid.c +++ b/drivers/media/platform/qcom/camss/camss-csid.c @@ -196,6 +196,8 @@ static int csid_set_power(struct v4l2_subdev *sd, int on) return ret; } + csid->phy.need_vc_update = true; + enable_irq(csid->irq); ret = csid->ops->reset(csid); @@ -249,7 +251,10 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable) return -ENOLINK; } - csid->ops->configure_stream(csid, enable); + if (csid->phy.need_vc_update) { + csid->ops->configure_stream(csid, enable); + csid->phy.need_vc_update = false; + } return 0; } @@ -460,6 +465,7 @@ static int csid_set_format(struct v4l2_subdev *sd, { struct csid_device *csid = v4l2_get_subdevdata(sd); struct v4l2_mbus_framefmt *format; + int i; format = __csid_get_format(csid, sd_state, fmt->pad, fmt->which); if (format == NULL) @@ -468,14 +474,14 @@ static int csid_set_format(struct v4l2_subdev *sd, csid_try_format(csid, sd_state, fmt->pad, &fmt->format, fmt->which); *format = fmt->format; - /* Propagate the format from sink to source */ + /* Propagate the format from sink to source pads */ if (fmt->pad == MSM_CSID_PAD_SINK) { - format = __csid_get_format(csid, sd_state, MSM_CSID_PAD_SRC, - fmt->which); + for (i = MSM_CSID_PAD_FIRST_SRC; i < MSM_CSID_PADS_NUM; ++i) { + format = __csid_get_format(csid, sd_state, i, fmt->which); - *format = fmt->format; - csid_try_format(csid, sd_state, MSM_CSID_PAD_SRC, format, - fmt->which); + *format = fmt->format; + csid_try_format(csid, sd_state, i, format, fmt->which); + } } return 0; @@ -738,7 +744,6 @@ static int csid_link_setup(struct media_entity *entity, struct csid_device *csid; struct csiphy_device *csiphy; struct csiphy_lanes_cfg *lane_cfg; - struct v4l2_subdev_format format = { 0 }; sd = media_entity_to_v4l2_subdev(entity); csid = v4l2_get_subdevdata(sd); @@ -761,11 +766,22 @@ static int csid_link_setup(struct media_entity *entity, lane_cfg = &csiphy->cfg.csi2->lane_cfg; csid->phy.lane_cnt = lane_cfg->num_data; csid->phy.lane_assign = csid_get_lane_assign(lane_cfg); + } + /* Decide which virtual channels to enable based on which source pads are enabled */ + if (local->flags & MEDIA_PAD_FL_SOURCE) { + struct v4l2_subdev *sd = media_entity_to_v4l2_subdev(entity); + struct csid_device *csid = v4l2_get_subdevdata(sd); + struct device *dev = csid->camss->dev; + + if (flags & MEDIA_LNK_FL_ENABLED) + csid->phy.en_vc |= BIT(local->index - 1); + else + csid->phy.en_vc &= ~BIT(local->index - 1); - /* Reset format on source pad to sink pad format */ - format.pad = MSM_CSID_PAD_SRC; - format.which = V4L2_SUBDEV_FORMAT_ACTIVE; - csid_set_format(&csid->subdev, NULL, &format); + csid->phy.need_vc_update = true; + + dev_dbg(dev, "%s: Enabled CSID virtual channels mask 0x%x\n", + __func__, csid->phy.en_vc); } return 0; @@ -816,6 +832,7 @@ int msm_csid_register_entity(struct csid_device *csid, struct v4l2_subdev *sd = &csid->subdev; struct media_pad *pads = csid->pads; struct device *dev = csid->camss->dev; + int i; int ret; v4l2_subdev_init(sd, &csid_v4l2_ops); @@ -852,7 +869,8 @@ int msm_csid_register_entity(struct csid_device *csid, } pads[MSM_CSID_PAD_SINK].flags = MEDIA_PAD_FL_SINK; - pads[MSM_CSID_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE; + for (i = MSM_CSID_PAD_FIRST_SRC; i < MSM_CSID_PADS_NUM; ++i) + pads[i].flags = MEDIA_PAD_FL_SOURCE; sd->entity.function = MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER; sd->entity.ops = &csid_media_ops; diff --git a/drivers/media/platform/qcom/camss/camss-csid.h b/drivers/media/platform/qcom/camss/camss-csid.h index f06040e44c51..d4b48432a097 100644 --- a/drivers/media/platform/qcom/camss/camss-csid.h +++ b/drivers/media/platform/qcom/camss/camss-csid.h @@ -19,8 +19,13 @@ #include <media/v4l2-subdev.h> #define MSM_CSID_PAD_SINK 0 -#define MSM_CSID_PAD_SRC 1 -#define MSM_CSID_PADS_NUM 2 +#define MSM_CSID_PAD_FIRST_SRC 1 +#define MSM_CSID_PADS_NUM 5 + +#define MSM_CSID_PAD_SRC (MSM_CSID_PAD_FIRST_SRC) + +/* CSID hardware can demultiplex up to 4 outputs */ +#define MSM_CSID_MAX_SRC_STREAMS 4 #define DATA_TYPE_EMBEDDED_DATA_8BIT 0x12 #define DATA_TYPE_YUV420_8BIT 0x18 @@ -81,6 +86,8 @@ struct csid_phy_config { u8 csiphy_id; u8 lane_cnt; u32 lane_assign; + u32 en_vc; + u8 need_vc_update; }; struct csid_device; diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c index 61b25fcf826e..9b20cef5afc6 100644 --- a/drivers/media/platform/rockchip/rga/rga.c +++ b/drivers/media/platform/rockchip/rga/rga.c @@ -187,7 +187,7 @@ static int rga_setup_ctrls(struct rga_ctx *ctx) static struct rga_fmt formats[] = { { .fourcc = V4L2_PIX_FMT_ARGB32, - .color_swap = RGA_COLOR_RB_SWAP, + .color_swap = RGA_COLOR_ALPHA_SWAP, .hw_format = RGA_COLOR_FMT_ABGR8888, .depth = 32, .uv_factor = 1, @@ -195,17 +195,8 @@ static struct rga_fmt formats[] = { .x_div = 1, }, { - .fourcc = V4L2_PIX_FMT_XRGB32, - .color_swap = RGA_COLOR_RB_SWAP, - .hw_format = RGA_COLOR_FMT_XBGR8888, - .depth = 32, - .uv_factor = 1, - .y_div = 1, - .x_div = 1, - }, - { .fourcc = V4L2_PIX_FMT_ABGR32, - .color_swap = RGA_COLOR_ALPHA_SWAP, + .color_swap = RGA_COLOR_RB_SWAP, .hw_format = RGA_COLOR_FMT_ABGR8888, .depth = 32, .uv_factor = 1, @@ -214,7 +205,7 @@ static struct rga_fmt formats[] = { }, { .fourcc = V4L2_PIX_FMT_XBGR32, - .color_swap = RGA_COLOR_ALPHA_SWAP, + .color_swap = RGA_COLOR_RB_SWAP, .hw_format = RGA_COLOR_FMT_XBGR8888, .depth = 32, .uv_factor = 1, diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h b/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h index a1293c45aae1..f9ec1c613894 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h @@ -61,6 +61,14 @@ struct dentry; RKISP1_CIF_ISP_EXP_END | \ RKISP1_CIF_ISP_HIST_MEASURE_RDY) +/* IRQ lines */ +enum rkisp1_irq_line { + RKISP1_IRQ_ISP = 0, + RKISP1_IRQ_MI, + RKISP1_IRQ_MIPI, + RKISP1_NUM_IRQS, +}; + /* enum for the resizer pads */ enum rkisp1_rsz_pad { RKISP1_RSZ_PAD_SINK, @@ -441,7 +449,6 @@ struct rkisp1_debug { * struct rkisp1_device - ISP platform device * * @base_addr: base register address - * @irq: the irq number * @dev: a pointer to the struct device * @clk_size: number of clocks * @clks: array of clocks @@ -459,6 +466,7 @@ struct rkisp1_debug { * @stream_lock: serializes {start/stop}_streaming callbacks between the capture devices. * @debug: debug params to be exposed on debugfs * @info: version-specific ISP information + * @irqs: IRQ line numbers */ struct rkisp1_device { void __iomem *base_addr; @@ -479,6 +487,7 @@ struct rkisp1_device { struct mutex stream_lock; /* serialize {start/stop}_streaming cb between capture devices */ struct rkisp1_debug debug; const struct rkisp1_info *info; + int irqs[RKISP1_NUM_IRQS]; }; /* diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c index d7acc94e10f8..e862f515cc6d 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c @@ -141,8 +141,20 @@ static void rkisp1_csi_disable(struct rkisp1_csi *csi) struct rkisp1_device *rkisp1 = csi->rkisp1; u32 val; - /* Mask and clear interrupts. */ + /* Mask MIPI interrupts. */ rkisp1_write(rkisp1, RKISP1_CIF_MIPI_IMSC, 0); + + /* Flush posted writes */ + rkisp1_read(rkisp1, RKISP1_CIF_MIPI_IMSC); + + /* + * Wait until the IRQ handler has ended. The IRQ handler may get called + * even after this, but it will return immediately as the MIPI + * interrupts have been masked. + */ + synchronize_irq(rkisp1->irqs[RKISP1_IRQ_MIPI]); + + /* Clear MIPI interrupt status */ rkisp1_write(rkisp1, RKISP1_CIF_MIPI_ICR, ~0); val = rkisp1_read(rkisp1, RKISP1_CIF_MIPI_CTRL); diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c index f2475c6235ea..41abb18b00ac 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c @@ -114,6 +114,7 @@ struct rkisp1_isr_data { const char *name; irqreturn_t (*isr)(int irq, void *ctx); + u32 line_mask; }; /* ---------------------------------------------------------------------------- @@ -442,17 +443,25 @@ error: static irqreturn_t rkisp1_isr(int irq, void *ctx) { + irqreturn_t ret = IRQ_NONE; + /* * Call rkisp1_capture_isr() first to handle the frame that * potentially completed using the current frame_sequence number before * it is potentially incremented by rkisp1_isp_isr() in the vertical * sync. */ - rkisp1_capture_isr(irq, ctx); - rkisp1_isp_isr(irq, ctx); - rkisp1_csi_isr(irq, ctx); - return IRQ_HANDLED; + if (rkisp1_capture_isr(irq, ctx) == IRQ_HANDLED) + ret = IRQ_HANDLED; + + if (rkisp1_isp_isr(irq, ctx) == IRQ_HANDLED) + ret = IRQ_HANDLED; + + if (rkisp1_csi_isr(irq, ctx) == IRQ_HANDLED) + ret = IRQ_HANDLED; + + return ret; } static const char * const px30_isp_clks[] = { @@ -463,9 +472,9 @@ static const char * const px30_isp_clks[] = { }; static const struct rkisp1_isr_data px30_isp_isrs[] = { - { "isp", rkisp1_isp_isr }, - { "mi", rkisp1_capture_isr }, - { "mipi", rkisp1_csi_isr }, + { "isp", rkisp1_isp_isr, BIT(RKISP1_IRQ_ISP) }, + { "mi", rkisp1_capture_isr, BIT(RKISP1_IRQ_MI) }, + { "mipi", rkisp1_csi_isr, BIT(RKISP1_IRQ_MIPI) }, }; static const struct rkisp1_info px30_isp_info = { @@ -484,7 +493,7 @@ static const char * const rk3399_isp_clks[] = { }; static const struct rkisp1_isr_data rk3399_isp_isrs[] = { - { NULL, rkisp1_isr }, + { NULL, rkisp1_isr, BIT(RKISP1_IRQ_ISP) | BIT(RKISP1_IRQ_MI) | BIT(RKISP1_IRQ_MIPI) }, }; static const struct rkisp1_info rk3399_isp_info = { @@ -535,6 +544,9 @@ static int rkisp1_probe(struct platform_device *pdev) if (IS_ERR(rkisp1->base_addr)) return PTR_ERR(rkisp1->base_addr); + for (unsigned int il = 0; il < ARRAY_SIZE(rkisp1->irqs); ++il) + rkisp1->irqs[il] = -1; + for (i = 0; i < info->isr_size; i++) { irq = info->isrs[i].name ? platform_get_irq_byname(pdev, info->isrs[i].name) @@ -542,6 +554,11 @@ static int rkisp1_probe(struct platform_device *pdev) if (irq < 0) return irq; + for (unsigned int il = 0; il < ARRAY_SIZE(rkisp1->irqs); ++il) { + if (info->isrs[i].line_mask & BIT(il)) + rkisp1->irqs[il] = irq; + } + ret = devm_request_irq(dev, irq, info->isrs[i].isr, IRQF_SHARED, dev_driver_string(dev), dev); if (ret) { @@ -582,7 +599,7 @@ static int rkisp1_probe(struct platform_device *pdev) ret = v4l2_device_register(rkisp1->dev, &rkisp1->v4l2_dev); if (ret) - goto err_pm_runtime_disable; + goto err_media_dev_cleanup; ret = media_device_register(&rkisp1->media_dev); if (ret) { @@ -617,6 +634,8 @@ err_unreg_media_dev: media_device_unregister(&rkisp1->media_dev); err_unreg_v4l2_dev: v4l2_device_unregister(&rkisp1->v4l2_dev); +err_media_dev_cleanup: + media_device_cleanup(&rkisp1->media_dev); err_pm_runtime_disable: pm_runtime_disable(&pdev->dev); return ret; @@ -637,6 +656,8 @@ static int rkisp1_remove(struct platform_device *pdev) media_device_unregister(&rkisp1->media_dev); v4l2_device_unregister(&rkisp1->v4l2_dev); + media_device_cleanup(&rkisp1->media_dev); + pm_runtime_disable(&pdev->dev); return 0; diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c index 585cf3f53469..00dca284c122 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c @@ -281,11 +281,25 @@ static void rkisp1_isp_stop(struct rkisp1_isp *isp) * ISP(mi) stop in mi frame end -> Stop ISP(mipi) -> * Stop ISP(isp) ->wait for ISP isp off */ - /* stop and clear MI and ISP interrupts */ - rkisp1_write(rkisp1, RKISP1_CIF_ISP_IMSC, 0); - rkisp1_write(rkisp1, RKISP1_CIF_ISP_ICR, ~0); + /* Mask MI and ISP interrupts */ + rkisp1_write(rkisp1, RKISP1_CIF_ISP_IMSC, 0); rkisp1_write(rkisp1, RKISP1_CIF_MI_IMSC, 0); + + /* Flush posted writes */ + rkisp1_read(rkisp1, RKISP1_CIF_MI_IMSC); + + /* + * Wait until the IRQ handler has ended. The IRQ handler may get called + * even after this, but it will return immediately as the MI and ISP + * interrupts have been masked. + */ + synchronize_irq(rkisp1->irqs[RKISP1_IRQ_ISP]); + if (rkisp1->irqs[RKISP1_IRQ_ISP] != rkisp1->irqs[RKISP1_IRQ_MI]) + synchronize_irq(rkisp1->irqs[RKISP1_IRQ_MI]); + + /* Clear MI and ISP interrupt status */ + rkisp1_write(rkisp1, RKISP1_CIF_ISP_ICR, ~0); rkisp1_write(rkisp1, RKISP1_CIF_MI_ICR, ~0); /* stop ISP */ diff --git a/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c b/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c index 6c0a33a83dcb..e5bcd8423dc5 100644 --- a/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c +++ b/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c @@ -1330,80 +1330,6 @@ static int ti_csi2rx_init_vb2q(struct ti_csi2rx_ctx *ctx) return 0; } -static int ti_csi2rx_link_validate_get_fmt(struct media_pad *pad, - struct v4l2_subdev_format *fmt) -{ - if (is_media_entity_v4l2_subdev(pad->entity)) { - struct v4l2_subdev *sd = - media_entity_to_v4l2_subdev(pad->entity); - - fmt->which = V4L2_SUBDEV_FORMAT_ACTIVE; - fmt->pad = pad->index; - return v4l2_subdev_call(sd, pad, get_fmt, NULL, fmt); - } - - WARN(pad->entity->function != MEDIA_ENT_F_IO_V4L, - "Driver bug! Wrong media entity type 0x%08x, entity %s\n", - pad->entity->function, pad->entity->name); - - return -EINVAL; -} - -static int ti_csi2rx_link_validate(struct media_link *link) -{ - struct media_entity *entity = link->sink->entity; - struct video_device *vdev = media_entity_to_video_device(entity); - struct ti_csi2rx_ctx *ctx = container_of(vdev, struct ti_csi2rx_ctx, vdev); - struct ti_csi2rx_dev *csi = ctx->csi; - struct v4l2_pix_format *csi_fmt = &ctx->v_fmt.fmt.pix; - struct v4l2_subdev_format source_fmt; - const struct ti_csi2rx_fmt *ti_fmt; - int ret; - - ret = ti_csi2rx_link_validate_get_fmt(link->source, &source_fmt); - if (ret) - return ret; - - if (source_fmt.format.width != csi_fmt->width) { - dev_dbg(csi->dev, "Width does not match (source %u, sink %u)\n", - source_fmt.format.width, csi_fmt->width); - return -EPIPE; - } - - if (source_fmt.format.height != csi_fmt->height) { - dev_dbg(csi->dev, "Height does not match (source %u, sink %u)\n", - source_fmt.format.height, csi_fmt->height); - return -EPIPE; - } - - if (source_fmt.format.field != csi_fmt->field && - csi_fmt->field != V4L2_FIELD_NONE) { - dev_dbg(csi->dev, "Field does not match (source %u, sink %u)\n", - source_fmt.format.field, csi_fmt->field); - return -EPIPE; - } - - ti_fmt = find_format_by_code(source_fmt.format.code); - if (!ti_fmt) { - dev_dbg(csi->dev, "Media bus format 0x%x not supported\n", - source_fmt.format.code); - return -EPIPE; - } - - if (ctx->v_fmt.fmt.pix.pixelformat != ti_fmt->fourcc) { - dev_dbg(csi->dev, - "Cannot transform source fmt 0x%x to sink fmt 0x%x\n", - ctx->v_fmt.fmt.pix.pixelformat, ti_fmt->fourcc); - return -EPIPE; - } - - return 0; -} - -static const struct media_entity_operations ti_csi2rx_video_entity_ops = { - .link_validate = ti_csi2rx_link_validate, -}; - static int ti_csi2rx_init_dma(struct ti_csi2rx_ctx *ctx) { struct dma_slave_config cfg = { diff --git a/drivers/media/platform/verisilicon/hantro_drv.c b/drivers/media/platform/verisilicon/hantro_drv.c index 08840ba313e7..69a2442f3122 100644 --- a/drivers/media/platform/verisilicon/hantro_drv.c +++ b/drivers/media/platform/verisilicon/hantro_drv.c @@ -813,6 +813,8 @@ static int hantro_add_func(struct hantro_dev *vpu, unsigned int funcid) if (funcid == MEDIA_ENT_F_PROC_VIDEO_ENCODER) { vpu->encoder = func; + v4l2_disable_ioctl(vfd, VIDIOC_TRY_DECODER_CMD); + v4l2_disable_ioctl(vfd, VIDIOC_DECODER_CMD); } else { vpu->decoder = func; v4l2_disable_ioctl(vfd, VIDIOC_TRY_ENCODER_CMD); diff --git a/drivers/media/platform/verisilicon/hantro_v4l2.c b/drivers/media/platform/verisilicon/hantro_v4l2.c index 30e650edaea8..b2da48936e3f 100644 --- a/drivers/media/platform/verisilicon/hantro_v4l2.c +++ b/drivers/media/platform/verisilicon/hantro_v4l2.c @@ -759,6 +759,9 @@ const struct v4l2_ioctl_ops hantro_ioctl_ops = { .vidioc_g_selection = vidioc_g_selection, .vidioc_s_selection = vidioc_s_selection, + .vidioc_decoder_cmd = v4l2_m2m_ioctl_stateless_decoder_cmd, + .vidioc_try_decoder_cmd = v4l2_m2m_ioctl_stateless_try_decoder_cmd, + .vidioc_try_encoder_cmd = v4l2_m2m_ioctl_try_encoder_cmd, .vidioc_encoder_cmd = vidioc_encoder_cmd, }; diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fe17c7f98e81..52d82cbe7685 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -253,7 +253,7 @@ int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) if (attr->attach_flags) return -EINVAL; - rcdev = rc_dev_get_from_fd(attr->target_fd); + rcdev = rc_dev_get_from_fd(attr->target_fd, true); if (IS_ERR(rcdev)) return PTR_ERR(rcdev); @@ -278,7 +278,7 @@ int lirc_prog_detach(const union bpf_attr *attr) if (IS_ERR(prog)) return PTR_ERR(prog); - rcdev = rc_dev_get_from_fd(attr->target_fd); + rcdev = rc_dev_get_from_fd(attr->target_fd, true); if (IS_ERR(rcdev)) { bpf_prog_put(prog); return PTR_ERR(rcdev); @@ -303,7 +303,7 @@ int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) if (attr->query.query_flags) return -EINVAL; - rcdev = rc_dev_get_from_fd(attr->query.target_fd); + rcdev = rc_dev_get_from_fd(attr->query.target_fd, false); if (IS_ERR(rcdev)) return PTR_ERR(rcdev); diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c index 196806709259..69e630d85262 100644 --- a/drivers/media/rc/ir_toy.c +++ b/drivers/media/rc/ir_toy.c @@ -332,6 +332,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count) sizeof(COMMAND_SMODE_EXIT), STATE_COMMAND_NO_RESP); if (err) { dev_err(irtoy->dev, "exit sample mode: %d\n", err); + kfree(buf); return err; } @@ -339,6 +340,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count) sizeof(COMMAND_SMODE_ENTER), STATE_COMMAND); if (err) { dev_err(irtoy->dev, "enter sample mode: %d\n", err); + kfree(buf); return err; } diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index 184e0b35744f..adb8c794a2d7 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -814,7 +814,7 @@ void __exit lirc_dev_exit(void) unregister_chrdev_region(lirc_base_dev, RC_DEV_MAX); } -struct rc_dev *rc_dev_get_from_fd(int fd) +struct rc_dev *rc_dev_get_from_fd(int fd, bool write) { struct fd f = fdget(fd); struct lirc_fh *fh; @@ -828,6 +828,9 @@ struct rc_dev *rc_dev_get_from_fd(int fd) return ERR_PTR(-EINVAL); } + if (write && !(f.file->f_mode & FMODE_WRITE)) + return ERR_PTR(-EPERM); + fh = f.file->private_data; dev = fh->rc; diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h index ef1e95e1af7f..7df949fc65e2 100644 --- a/drivers/media/rc/rc-core-priv.h +++ b/drivers/media/rc/rc-core-priv.h @@ -325,7 +325,7 @@ void lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev); void lirc_scancode_event(struct rc_dev *dev, struct lirc_scancode *lsc); int lirc_register(struct rc_dev *dev); void lirc_unregister(struct rc_dev *dev); -struct rc_dev *rc_dev_get_from_fd(int fd); +struct rc_dev *rc_dev_get_from_fd(int fd, bool write); #else static inline int lirc_dev_init(void) { return 0; } static inline void lirc_dev_exit(void) {} diff --git a/drivers/media/usb/cx231xx/cx231xx-core.c b/drivers/media/usb/cx231xx/cx231xx-core.c index 727e6268567f..f1feccc28bf0 100644 --- a/drivers/media/usb/cx231xx/cx231xx-core.c +++ b/drivers/media/usb/cx231xx/cx231xx-core.c @@ -1024,6 +1024,7 @@ int cx231xx_init_isoc(struct cx231xx *dev, int max_packets, if (!dev->video_mode.isoc_ctl.urb) { dev_err(dev->dev, "cannot alloc memory for usb buffers\n"); + kfree(dma_q->p_left_data); return -ENOMEM; } @@ -1033,6 +1034,7 @@ int cx231xx_init_isoc(struct cx231xx *dev, int max_packets, dev_err(dev->dev, "cannot allocate memory for usbtransfer\n"); kfree(dev->video_mode.isoc_ctl.urb); + kfree(dma_q->p_left_data); return -ENOMEM; } diff --git a/drivers/media/usb/pvrusb2/pvrusb2-context.c b/drivers/media/usb/pvrusb2/pvrusb2-context.c index 14170a5d72b3..1764674de98b 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-context.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-context.c @@ -268,7 +268,8 @@ void pvr2_context_disconnect(struct pvr2_context *mp) { pvr2_hdw_disconnect(mp->hdw); mp->disconnect_flag = !0; - pvr2_context_notify(mp); + if (!pvr2_context_shutok()) + pvr2_context_notify(mp); } diff --git a/drivers/media/usb/stk1160/stk1160-video.c b/drivers/media/usb/stk1160/stk1160-video.c index 4e966f6bf608..366f0e4a5dc0 100644 --- a/drivers/media/usb/stk1160/stk1160-video.c +++ b/drivers/media/usb/stk1160/stk1160-video.c @@ -107,8 +107,7 @@ void stk1160_copy_video(struct stk1160 *dev, u8 *src, int len) /* * TODO: These stk1160_dbg are very spammy! - * We should 1) check why we are getting them - * and 2) add ratelimit. + * We should check why we are getting them. * * UPDATE: One of the reasons (the only one?) for getting these * is incorrect standard (mismatch between expected and configured). @@ -151,7 +150,7 @@ void stk1160_copy_video(struct stk1160 *dev, u8 *src, int len) /* Let the bug hunt begin! sanity checks! */ if (lencopy < 0) { - stk1160_dbg("copy skipped: negative lencopy\n"); + printk_ratelimited(KERN_DEBUG "copy skipped: negative lencopy\n"); return; } diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index e71d269b10af..9f3b6cdf05e5 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1440,6 +1440,7 @@ config MFD_DAVINCI_VOICECODEC config MFD_TI_AM335X_TSCADC tristate "TI ADC / Touch Screen chip support" + depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST select MFD_CORE select REGMAP select REGMAP_MMIO diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c index cfbee2cfba6b..c50387600b81 100644 --- a/drivers/mfd/intel-lpss.c +++ b/drivers/mfd/intel-lpss.c @@ -301,8 +301,8 @@ static int intel_lpss_register_clock_divider(struct intel_lpss *lpss, snprintf(name, sizeof(name), "%s-div", devname); tmp = clk_register_fractional_divider(NULL, name, __clk_get_name(tmp), + 0, lpss->priv, 1, 15, 16, 15, CLK_FRAC_DIVIDER_POWER_OF_TWO_PS, - lpss->priv, 1, 15, 16, 15, 0, NULL); if (IS_ERR(tmp)) return PTR_ERR(tmp); diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c index bdb2ce7ff03b..6196724ef39b 100644 --- a/drivers/mfd/syscon.c +++ b/drivers/mfd/syscon.c @@ -102,6 +102,10 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_clk) } syscon_config.name = kasprintf(GFP_KERNEL, "%pOFn@%pa", np, &res.start); + if (!syscon_config.name) { + ret = -ENOMEM; + goto err_regmap; + } syscon_config.reg_stride = reg_io_width; syscon_config.val_bits = reg_io_width * 8; syscon_config.max_register = resource_size(&res) - reg_io_width; diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index cc57cc820432..69cc24962706 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1990,7 +1990,7 @@ static int fastrpc_cb_remove(struct platform_device *pdev) int i; spin_lock_irqsave(&cctx->lock, flags); - for (i = 1; i < FASTRPC_MAX_SESSIONS; i++) { + for (i = 0; i < FASTRPC_MAX_SESSIONS; i++) { if (cctx->session[i].sid == sess->sid) { cctx->session[i].valid = false; cctx->sesscount--; diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index 43afe40966e5..1ea1ae34b7a7 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -677,7 +677,7 @@ static int sec_attest_info(struct hl_fpriv *hpriv, struct hl_info_args *args) if (!sec_attest_info) return -ENOMEM; - info = kmalloc(sizeof(*info), GFP_KERNEL); + info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { rc = -ENOMEM; goto free_sec_attest_info; diff --git a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c index d7daa01fe7ca..fdec2c30eb16 100644 --- a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c +++ b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c @@ -151,6 +151,7 @@ static int lis3lv02d_i2c_probe(struct i2c_client *client, lis3_dev.init = lis3_i2c_init; lis3_dev.read = lis3_i2c_read; lis3_dev.write = lis3_i2c_write; + lis3_dev.reg_ctrl = lis3_reg_ctrl; lis3_dev.irq = client->irq; lis3_dev.ac = lis3lv02d_axis_map; lis3_dev.pm_dev = &client->dev; diff --git a/drivers/misc/open-dice.c b/drivers/misc/open-dice.c index c61be3404c6f..504b836a7abf 100644 --- a/drivers/misc/open-dice.c +++ b/drivers/misc/open-dice.c @@ -142,7 +142,6 @@ static int __init open_dice_probe(struct platform_device *pdev) return -ENOMEM; *drvdata = (struct open_dice_drvdata){ - .lock = __MUTEX_INITIALIZER(drvdata->lock), .rmem = rmem, .misc = (struct miscdevice){ .parent = dev, @@ -152,6 +151,7 @@ static int __init open_dice_probe(struct platform_device *pdev) .mode = 0600, }, }; + mutex_init(&drvdata->lock); /* Index overflow check not needed, misc_register() will fail. */ snprintf(drvdata->name, sizeof(drvdata->name), DRIVER_NAME"%u", dev_idx++); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 770490234c87..ea60efaecb0d 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -402,6 +402,10 @@ struct mmc_blk_ioc_data { struct mmc_ioc_cmd ic; unsigned char *buf; u64 buf_bytes; + unsigned int flags; +#define MMC_BLK_IOC_DROP BIT(0) /* drop this mrq */ +#define MMC_BLK_IOC_SBC BIT(1) /* use mrq.sbc */ + struct mmc_rpmb_data *rpmb; }; @@ -467,7 +471,7 @@ static int mmc_blk_ioctl_copy_to_user(struct mmc_ioc_cmd __user *ic_ptr, } static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, - struct mmc_blk_ioc_data *idata) + struct mmc_blk_ioc_data **idatas, int i) { struct mmc_command cmd = {}, sbc = {}; struct mmc_data data = {}; @@ -477,10 +481,18 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, unsigned int busy_timeout_ms; int err; unsigned int target_part; + struct mmc_blk_ioc_data *idata = idatas[i]; + struct mmc_blk_ioc_data *prev_idata = NULL; if (!card || !md || !idata) return -EINVAL; + if (idata->flags & MMC_BLK_IOC_DROP) + return 0; + + if (idata->flags & MMC_BLK_IOC_SBC) + prev_idata = idatas[i - 1]; + /* * The RPMB accesses comes in from the character device, so we * need to target these explicitly. Else we just target the @@ -547,7 +559,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, return err; } - if (idata->rpmb) { + if (idata->rpmb || prev_idata) { sbc.opcode = MMC_SET_BLOCK_COUNT; /* * We don't do any blockcount validation because the max size @@ -555,6 +567,8 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, * 'Reliable Write' bit here. */ sbc.arg = data.blocks | (idata->ic.write_flag & BIT(31)); + if (prev_idata) + sbc.arg = prev_idata->ic.arg; sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; mrq.sbc = &sbc; } @@ -572,6 +586,15 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, mmc_wait_for_req(card->host, &mrq); memcpy(&idata->ic.response, cmd.resp, sizeof(cmd.resp)); + if (prev_idata) { + memcpy(&prev_idata->ic.response, sbc.resp, sizeof(sbc.resp)); + if (sbc.error) { + dev_err(mmc_dev(card->host), "%s: sbc error %d\n", + __func__, sbc.error); + return sbc.error; + } + } + if (cmd.error) { dev_err(mmc_dev(card->host), "%s: cmd error %d\n", __func__, cmd.error); @@ -866,9 +889,10 @@ static const struct block_device_operations mmc_bdops = { static int mmc_blk_part_switch_pre(struct mmc_card *card, unsigned int part_type) { + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) { + if ((part_type & mask) == mask) { if (card->ext_csd.cmdq_en) { ret = mmc_cmdq_disable(card); if (ret) @@ -883,9 +907,10 @@ static int mmc_blk_part_switch_pre(struct mmc_card *card, static int mmc_blk_part_switch_post(struct mmc_card *card, unsigned int part_type) { + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) { + if ((part_type & mask) == mask) { mmc_retune_unpause(card->host); if (card->reenable_cmdq && !card->ext_csd.cmdq_en) ret = mmc_cmdq_enable(card); @@ -1055,6 +1080,20 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type) md->reset_done &= ~type; } +static void mmc_blk_check_sbc(struct mmc_queue_req *mq_rq) +{ + struct mmc_blk_ioc_data **idata = mq_rq->drv_op_data; + int i; + + for (i = 1; i < mq_rq->ioc_count; i++) { + if (idata[i - 1]->ic.opcode == MMC_SET_BLOCK_COUNT && + mmc_op_multi(idata[i]->ic.opcode)) { + idata[i - 1]->flags |= MMC_BLK_IOC_DROP; + idata[i]->flags |= MMC_BLK_IOC_SBC; + } + } +} + /* * The non-block commands come back from the block layer after it queued it and * processed it with all other requests and then they get issued in this @@ -1082,11 +1121,14 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req) if (ret) break; } + + mmc_blk_check_sbc(mq_rq); + fallthrough; case MMC_DRV_OP_IOCTL_RPMB: idata = mq_rq->drv_op_data; for (i = 0, ret = 0; i < mq_rq->ioc_count; i++) { - ret = __mmc_blk_ioctl_cmd(card, md, idata[i]); + ret = __mmc_blk_ioctl_cmd(card, md, idata, i); if (ret) break; } @@ -3180,4 +3222,3 @@ module_exit(mmc_blk_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Multimedia Card (MMC) block device driver"); - diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index b89dca1f15e9..25c152ef5d60 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -670,6 +670,7 @@ EXPORT_SYMBOL(mmc_remove_host); */ void mmc_free_host(struct mmc_host *host) { + cancel_delayed_work_sync(&host->detect); mmc_pwrseq_free(host); put_device(&host->class_dev); } diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index dd2a4b6ab6ad..e3c69c6b85a6 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -62,11 +62,15 @@ int mmc_gpio_alloc(struct mmc_host *host) int mmc_gpio_get_ro(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; + int cansleep; if (!ctx || !ctx->ro_gpio) return -ENOSYS; - return gpiod_get_value_cansleep(ctx->ro_gpio); + cansleep = gpiod_cansleep(ctx->ro_gpio); + return cansleep ? + gpiod_get_value_cansleep(ctx->ro_gpio) : + gpiod_get_value(ctx->ro_gpio); } EXPORT_SYMBOL(mmc_gpio_get_ro); diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 9b5a2cb110b3..d84bdb69f56b 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -1061,14 +1061,15 @@ config MMC_SDHCI_XENON config MMC_SDHCI_OMAP tristate "TI SDHCI Controller Support" + depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST depends on MMC_SDHCI_PLTFM && OF select THERMAL imply TI_SOC_THERMAL select MMC_SDHCI_EXTERNAL_DMA if DMA_ENGINE help This selects the Secure Digital Host Controller Interface (SDHCI) - support present in TI's DRA7 SOCs. The controller supports - SD/MMC/SDIO devices. + support present in TI's Keystone/OMAP2+/DRA7 SOCs. The controller + supports SD/MMC/SDIO devices. If you have a controller with this interface, say Y or M here. @@ -1076,14 +1077,15 @@ config MMC_SDHCI_OMAP config MMC_SDHCI_AM654 tristate "Support for the SDHCI Controller in TI's AM654 SOCs" + depends on ARCH_K3 || COMPILE_TEST depends on MMC_SDHCI_PLTFM && OF select MMC_SDHCI_IO_ACCESSORS select MMC_CQHCI select REGMAP_MMIO help This selects the Secure Digital Host Controller Interface (SDHCI) - support present in TI's AM654 SOCs. The controller supports - SD/MMC/SDIO devices. + support present in TI's AM65x/AM64x/AM62x/J721E SOCs. The controller + supports SD/MMC/SDIO devices. If you have a controller with this interface, say Y or M here. diff --git a/drivers/mmc/host/meson-mx-sdhc-mmc.c b/drivers/mmc/host/meson-mx-sdhc-mmc.c index da85c2f2acb8..c0e3b1634a88 100644 --- a/drivers/mmc/host/meson-mx-sdhc-mmc.c +++ b/drivers/mmc/host/meson-mx-sdhc-mmc.c @@ -269,7 +269,7 @@ static int meson_mx_sdhc_enable_clks(struct mmc_host *mmc) static int meson_mx_sdhc_set_clk(struct mmc_host *mmc, struct mmc_ios *ios) { struct meson_mx_sdhc_host *host = mmc_priv(mmc); - u32 rx_clk_phase; + u32 val, rx_clk_phase; int ret; meson_mx_sdhc_disable_clks(mmc); @@ -290,27 +290,11 @@ static int meson_mx_sdhc_set_clk(struct mmc_host *mmc, struct mmc_ios *ios) mmc->actual_clock = clk_get_rate(host->sd_clk); /* - * according to Amlogic the following latching points are - * selected with empirical values, there is no (known) formula - * to calculate these. + * Phase 90 should work in most cases. For data transmission, + * meson_mx_sdhc_execute_tuning() will find a accurate value */ - if (mmc->actual_clock > 100000000) { - rx_clk_phase = 1; - } else if (mmc->actual_clock > 45000000) { - if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) - rx_clk_phase = 15; - else - rx_clk_phase = 11; - } else if (mmc->actual_clock >= 25000000) { - rx_clk_phase = 15; - } else if (mmc->actual_clock > 5000000) { - rx_clk_phase = 23; - } else if (mmc->actual_clock > 1000000) { - rx_clk_phase = 55; - } else { - rx_clk_phase = 1061; - } - + regmap_read(host->regmap, MESON_SDHC_CLKC, &val); + rx_clk_phase = FIELD_GET(MESON_SDHC_CLKC_CLK_DIV, val) / 4; regmap_update_bits(host->regmap, MESON_SDHC_CLK2, MESON_SDHC_CLK2_RX_CLK_PHASE, FIELD_PREP(MESON_SDHC_CLK2_RX_CLK_PHASE, diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index cc333ad67cac..2a99ffb61f8c 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -15,7 +15,7 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/bio.h> -#include <linux/dma-mapping.h> +#include <linux/dma-direction.h> #include <linux/crc7.h> #include <linux/crc-itu-t.h> #include <linux/scatterlist.h> @@ -119,19 +119,14 @@ struct mmc_spi_host { struct spi_transfer status; struct spi_message readback; - /* underlying DMA-aware controller, or null */ - struct device *dma_dev; - /* buffer used for commands and for message "overhead" */ struct scratch *data; - dma_addr_t data_dma; /* Specs say to write ones most of the time, even when the card * has no need to read its input data; and many cards won't care. * This is our source of those ones. */ void *ones; - dma_addr_t ones_dma; }; @@ -147,11 +142,8 @@ static inline int mmc_cs_off(struct mmc_spi_host *host) return spi_setup(host->spi); } -static int -mmc_spi_readbytes(struct mmc_spi_host *host, unsigned len) +static int mmc_spi_readbytes(struct mmc_spi_host *host, unsigned int len) { - int status; - if (len > sizeof(*host->data)) { WARN_ON(1); return -EIO; @@ -159,19 +151,7 @@ mmc_spi_readbytes(struct mmc_spi_host *host, unsigned len) host->status.len = len; - if (host->dma_dev) - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_FROM_DEVICE); - - status = spi_sync_locked(host->spi, &host->readback); - - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_FROM_DEVICE); - - return status; + return spi_sync_locked(host->spi, &host->readback); } static int mmc_spi_skip(struct mmc_spi_host *host, unsigned long timeout, @@ -506,23 +486,11 @@ mmc_spi_command_send(struct mmc_spi_host *host, t = &host->t; memset(t, 0, sizeof(*t)); t->tx_buf = t->rx_buf = data->status; - t->tx_dma = t->rx_dma = host->data_dma; t->len = cp - data->status; t->cs_change = 1; spi_message_add_tail(t, &host->m); - if (host->dma_dev) { - host->m.is_dma_mapped = 1; - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); - } status = spi_sync_locked(host->spi, &host->m); - - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); if (status < 0) { dev_dbg(&host->spi->dev, " ... write returned %d\n", status); cmd->error = status; @@ -540,9 +508,6 @@ mmc_spi_command_send(struct mmc_spi_host *host, * We always provide TX data for data and CRC. The MMC/SD protocol * requires us to write ones; but Linux defaults to writing zeroes; * so we explicitly initialize it to all ones on RX paths. - * - * We also handle DMA mapping, so the underlying SPI controller does - * not need to (re)do it for each message. */ static void mmc_spi_setup_data_message( @@ -552,11 +517,8 @@ mmc_spi_setup_data_message( { struct spi_transfer *t; struct scratch *scratch = host->data; - dma_addr_t dma = host->data_dma; spi_message_init(&host->m); - if (dma) - host->m.is_dma_mapped = 1; /* for reads, readblock() skips 0xff bytes before finding * the token; for writes, this transfer issues that token. @@ -570,8 +532,6 @@ mmc_spi_setup_data_message( else scratch->data_token = SPI_TOKEN_SINGLE; t->tx_buf = &scratch->data_token; - if (dma) - t->tx_dma = dma + offsetof(struct scratch, data_token); spi_message_add_tail(t, &host->m); } @@ -581,7 +541,6 @@ mmc_spi_setup_data_message( t = &host->t; memset(t, 0, sizeof(*t)); t->tx_buf = host->ones; - t->tx_dma = host->ones_dma; /* length and actual buffer info are written later */ spi_message_add_tail(t, &host->m); @@ -591,14 +550,9 @@ mmc_spi_setup_data_message( if (direction == DMA_TO_DEVICE) { /* the actual CRC may get written later */ t->tx_buf = &scratch->crc_val; - if (dma) - t->tx_dma = dma + offsetof(struct scratch, crc_val); } else { t->tx_buf = host->ones; - t->tx_dma = host->ones_dma; t->rx_buf = &scratch->crc_val; - if (dma) - t->rx_dma = dma + offsetof(struct scratch, crc_val); } spi_message_add_tail(t, &host->m); @@ -621,10 +575,7 @@ mmc_spi_setup_data_message( memset(t, 0, sizeof(*t)); t->len = (direction == DMA_TO_DEVICE) ? sizeof(scratch->status) : 1; t->tx_buf = host->ones; - t->tx_dma = host->ones_dma; t->rx_buf = scratch->status; - if (dma) - t->rx_dma = dma + offsetof(struct scratch, status); t->cs_change = 1; spi_message_add_tail(t, &host->m); } @@ -653,23 +604,13 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t, if (host->mmc->use_spi_crc) scratch->crc_val = cpu_to_be16(crc_itu_t(0, t->tx_buf, t->len)); - if (host->dma_dev) - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); status = spi_sync_locked(spi, &host->m); - if (status != 0) { dev_dbg(&spi->dev, "write error (%d)\n", status); return status; } - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - /* * Get the transmission data-response reply. It must follow * immediately after the data block we transferred. This reply @@ -718,8 +659,6 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t, } t->tx_buf += t->len; - if (host->dma_dev) - t->tx_dma += t->len; /* Return when not busy. If we didn't collect that status yet, * we'll need some more I/O. @@ -783,30 +722,12 @@ mmc_spi_readblock(struct mmc_spi_host *host, struct spi_transfer *t, } leftover = status << 1; - if (host->dma_dev) { - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - dma_sync_single_for_device(host->dma_dev, - t->rx_dma, t->len, - DMA_FROM_DEVICE); - } - status = spi_sync_locked(spi, &host->m); if (status < 0) { dev_dbg(&spi->dev, "read error %d\n", status); return status; } - if (host->dma_dev) { - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - dma_sync_single_for_cpu(host->dma_dev, - t->rx_dma, t->len, - DMA_FROM_DEVICE); - } - if (bitshift) { /* Walk through the data and the crc and do * all the magic to get byte-aligned data. @@ -841,8 +762,6 @@ mmc_spi_readblock(struct mmc_spi_host *host, struct spi_transfer *t, } t->rx_buf += t->len; - if (host->dma_dev) - t->rx_dma += t->len; return 0; } @@ -857,7 +776,6 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd, struct mmc_data *data, u32 blk_size) { struct spi_device *spi = host->spi; - struct device *dma_dev = host->dma_dev; struct spi_transfer *t; enum dma_data_direction direction = mmc_get_dma_dir(data); struct scatterlist *sg; @@ -884,31 +802,8 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd, */ for_each_sg(data->sg, sg, data->sg_len, n_sg) { int status = 0; - dma_addr_t dma_addr = 0; void *kmap_addr; unsigned length = sg->length; - enum dma_data_direction dir = direction; - - /* set up dma mapping for controller drivers that might - * use DMA ... though they may fall back to PIO - */ - if (dma_dev) { - /* never invalidate whole *shared* pages ... */ - if ((sg->offset != 0 || length != PAGE_SIZE) - && dir == DMA_FROM_DEVICE) - dir = DMA_BIDIRECTIONAL; - - dma_addr = dma_map_page(dma_dev, sg_page(sg), 0, - PAGE_SIZE, dir); - if (dma_mapping_error(dma_dev, dma_addr)) { - data->error = -EFAULT; - break; - } - if (direction == DMA_TO_DEVICE) - t->tx_dma = dma_addr + sg->offset; - else - t->rx_dma = dma_addr + sg->offset; - } /* allow pio too; we don't allow highmem */ kmap_addr = kmap(sg_page(sg)); @@ -941,8 +836,6 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd, if (direction == DMA_FROM_DEVICE) flush_dcache_page(sg_page(sg)); kunmap(sg_page(sg)); - if (dma_dev) - dma_unmap_page(dma_dev, dma_addr, PAGE_SIZE, dir); if (status < 0) { data->error = status; @@ -977,21 +870,9 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd, scratch->status[0] = SPI_TOKEN_STOP_TRAN; host->early_status.tx_buf = host->early_status.rx_buf; - host->early_status.tx_dma = host->early_status.rx_dma; host->early_status.len = statlen; - if (host->dma_dev) - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - tmp = spi_sync_locked(spi, &host->m); - - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - if (tmp < 0) { if (!data->error) data->error = tmp; @@ -1265,52 +1146,6 @@ mmc_spi_detect_irq(int irq, void *mmc) return IRQ_HANDLED; } -#ifdef CONFIG_HAS_DMA -static int mmc_spi_dma_alloc(struct mmc_spi_host *host) -{ - struct spi_device *spi = host->spi; - struct device *dev; - - if (!spi->master->dev.parent->dma_mask) - return 0; - - dev = spi->master->dev.parent; - - host->ones_dma = dma_map_single(dev, host->ones, MMC_SPI_BLOCKSIZE, - DMA_TO_DEVICE); - if (dma_mapping_error(dev, host->ones_dma)) - return -ENOMEM; - - host->data_dma = dma_map_single(dev, host->data, sizeof(*host->data), - DMA_BIDIRECTIONAL); - if (dma_mapping_error(dev, host->data_dma)) { - dma_unmap_single(dev, host->ones_dma, MMC_SPI_BLOCKSIZE, - DMA_TO_DEVICE); - return -ENOMEM; - } - - dma_sync_single_for_cpu(dev, host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); - - host->dma_dev = dev; - return 0; -} - -static void mmc_spi_dma_free(struct mmc_spi_host *host) -{ - if (!host->dma_dev) - return; - - dma_unmap_single(host->dma_dev, host->ones_dma, MMC_SPI_BLOCKSIZE, - DMA_TO_DEVICE); - dma_unmap_single(host->dma_dev, host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); -} -#else -static inline int mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; } -static inline void mmc_spi_dma_free(struct mmc_spi_host *host) {} -#endif - static int mmc_spi_probe(struct spi_device *spi) { void *ones; @@ -1402,24 +1237,17 @@ static int mmc_spi_probe(struct spi_device *spi) host->powerup_msecs = 250; } - /* preallocate dma buffers */ + /* Preallocate buffers */ host->data = kmalloc(sizeof(*host->data), GFP_KERNEL); if (!host->data) goto fail_nobuf1; - status = mmc_spi_dma_alloc(host); - if (status) - goto fail_dma; - /* setup message for status/busy readback */ spi_message_init(&host->readback); - host->readback.is_dma_mapped = (host->dma_dev != NULL); spi_message_add_tail(&host->status, &host->readback); host->status.tx_buf = host->ones; - host->status.tx_dma = host->ones_dma; host->status.rx_buf = &host->data->status; - host->status.rx_dma = host->data_dma + offsetof(struct scratch, status); host->status.cs_change = 1; /* register card detect irq */ @@ -1464,9 +1292,8 @@ static int mmc_spi_probe(struct spi_device *spi) if (!status) has_ro = true; - dev_info(&spi->dev, "SD/MMC host %s%s%s%s%s\n", + dev_info(&spi->dev, "SD/MMC host %s%s%s%s\n", dev_name(&mmc->class_dev), - host->dma_dev ? "" : ", no DMA", has_ro ? "" : ", no WP", (host->pdata && host->pdata->setpower) ? "" : ", no poweroff", @@ -1477,8 +1304,6 @@ static int mmc_spi_probe(struct spi_device *spi) fail_gpiod_request: mmc_remove_host(mmc); fail_glue_init: - mmc_spi_dma_free(host); -fail_dma: kfree(host->data); fail_nobuf1: mmc_spi_put_pdata(spi); @@ -1500,7 +1325,6 @@ static void mmc_spi_remove(struct spi_device *spi) mmc_remove_host(mmc); - mmc_spi_dma_free(host); kfree(host->data); kfree(host->ones); diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c index bca1d095b759..24bb0e9809e7 100644 --- a/drivers/mmc/host/sdhci-pci-o2micro.c +++ b/drivers/mmc/host/sdhci-pci-o2micro.c @@ -602,6 +602,35 @@ static void sdhci_pci_o2_set_clock(struct sdhci_host *host, unsigned int clock) sdhci_o2_enable_clk(host, clk); } +static void sdhci_pci_o2_set_power(struct sdhci_host *host, unsigned char mode, unsigned short vdd) +{ + struct sdhci_pci_chip *chip; + struct sdhci_pci_slot *slot = sdhci_priv(host); + u32 scratch_32 = 0; + u8 scratch_8 = 0; + + chip = slot->chip; + + if (mode == MMC_POWER_OFF) { + /* UnLock WP */ + pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8); + scratch_8 &= 0x7f; + pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8); + + /* Set PCR 0x354[16] to switch Clock Source back to OPE Clock */ + pci_read_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, &scratch_32); + scratch_32 &= ~(O2_SD_SEL_DLL); + pci_write_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, scratch_32); + + /* Lock WP */ + pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8); + scratch_8 |= 0x80; + pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8); + } + + sdhci_set_power(host, mode, vdd); +} + static int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot) { struct sdhci_pci_chip *chip; @@ -911,6 +940,7 @@ static const struct sdhci_ops sdhci_pci_o2_ops = { .set_bus_width = sdhci_set_bus_width, .reset = sdhci_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, + .set_power = sdhci_pci_o2_set_power, }; const struct sdhci_pci_fixes sdhci_o2 = { diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 2101b6e794c0..66c1782823d8 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -228,15 +228,19 @@ static inline void _sdhci_sprd_set_clock(struct sdhci_host *host, div = ((div & 0x300) >> 2) | ((div & 0xFF) << 8); sdhci_enable_clk(host, div); + val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI); + mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN; /* Enable CLK_AUTO when the clock is greater than 400K. */ if (clk > 400000) { - val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI); - mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | - SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN; if (mask != (val & mask)) { val |= mask; sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI); } + } else { + if (val & mask) { + val &= ~mask; + sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI); + } } } diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 60b222799871..8ee60605a6dc 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -463,7 +463,7 @@ static void blktrans_notify_add(struct mtd_info *mtd) { struct mtd_blktrans_ops *tr; - if (mtd->type == MTD_ABSENT) + if (mtd->type == MTD_ABSENT || mtd->type == MTD_UBIVOLUME) return; list_for_each_entry(tr, &blktrans_majors, list) @@ -503,7 +503,7 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr) mutex_lock(&mtd_table_mutex); list_add(&tr->list, &blktrans_majors); mtd_for_each_device(mtd) - if (mtd->type != MTD_ABSENT) + if (mtd->type != MTD_ABSENT && mtd->type != MTD_UBIVOLUME) tr->add_mtd(tr, mtd); mutex_unlock(&mtd_table_mutex); return 0; diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c index 02d500176838..bea1a7d3edd7 100644 --- a/drivers/mtd/nand/raw/fsl_ifc_nand.c +++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c @@ -20,7 +20,7 @@ #define ERR_BYTE 0xFF /* Value returned for read bytes when read failed */ -#define IFC_TIMEOUT_MSECS 500 /* Maximum number of mSecs to wait +#define IFC_TIMEOUT_MSECS 1000 /* Maximum timeout to wait for IFC NAND Machine */ struct fsl_ifc_ctrl; diff --git a/drivers/mtd/parsers/ofpart_core.c b/drivers/mtd/parsers/ofpart_core.c index 192190c42fc8..e7b8e9d0a910 100644 --- a/drivers/mtd/parsers/ofpart_core.c +++ b/drivers/mtd/parsers/ofpart_core.c @@ -122,6 +122,25 @@ static int parse_fixed_partitions(struct mtd_info *master, a_cells = of_n_addr_cells(pp); s_cells = of_n_size_cells(pp); + if (!dedicated && s_cells == 0) { + /* + * This is a ugly workaround to not create + * regression on devices that are still creating + * partitions as direct children of the nand controller. + * This can happen in case the nand controller node has + * #size-cells equal to 0 and the firmware (e.g. + * U-Boot) just add the partitions there assuming + * 32-bit addressing. + * + * If you get this warning your firmware and/or DTS + * should be really fixed. + * + * This is working only for devices smaller than 4GiB. + */ + pr_warn("%s: ofpart partition %pOF (%pOF) #size-cells is wrongly set to <0>, assuming <1> for parsing partitions.\n", + master->name, pp, mtd_node); + s_cells = 1; + } if (len / 4 != a_cells + s_cells) { pr_debug("%s: ofpart partition %pOF (%pOF) error parsing reg property.\n", master->name, pp, diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 2d20be6ffb7e..ddd087c2c3ed 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -11,7 +11,7 @@ #include <linux/net.h> #include <linux/igmp.h> #include <linux/workqueue.h> -#include <net/sch_generic.h> +#include <net/pkt_sched.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/udp.h> @@ -80,11 +80,11 @@ static struct mld2_grec mldv2_zero_grec; static struct amt_skb_cb *amt_skb_cb(struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct qdisc_skb_cb) > + BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct tc_skb_cb) > sizeof_field(struct sk_buff, cb)); return (struct amt_skb_cb *)((void *)skb->cb + - sizeof(struct qdisc_skb_cb)); + sizeof(struct tc_skb_cb)); } static void __amt_source_gc_work(void) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index fc5da5d7744d..9c4c2c7d90ef 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -985,7 +985,8 @@ static int alb_upper_dev_walk(struct net_device *upper, if (netif_is_macvlan(upper) && !strict_match) { tags = bond_verify_device_path(bond->dev, upper, 0); if (IS_ERR_OR_NULL(tags)) - BUG(); + return -ENOMEM; + alb_send_lp_vid(slave, upper->dev_addr, tags[0].vlan_proto, tags[0].vlan_id); kfree(tags); diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 8efa22d9f214..053d375eae4f 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -311,7 +311,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], /* Neither of TDC parameters nor TDC flags are * provided: do calculation */ - can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming, + can_calc_tdco(&priv->tdc, priv->tdc_const, &dbt, &priv->ctrlmode, priv->ctrlmode_supported); } /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly * turned off. TDC is disabled: do nothing diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index e693154cf803..97a47d8743fd 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -601,8 +601,8 @@ struct mv88e6xxx_ops { int (*serdes_get_sset_count)(struct mv88e6xxx_chip *chip, int port); int (*serdes_get_strings)(struct mv88e6xxx_chip *chip, int port, uint8_t *data); - int (*serdes_get_stats)(struct mv88e6xxx_chip *chip, int port, - uint64_t *data); + size_t (*serdes_get_stats)(struct mv88e6xxx_chip *chip, int port, + uint64_t *data); /* SERDES registers for ethtool */ int (*serdes_get_regs_len)(struct mv88e6xxx_chip *chip, int port); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index d94150d8f3f4..4c38df4982bf 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -342,8 +342,8 @@ static uint64_t mv88e6352_serdes_get_stat(struct mv88e6xxx_chip *chip, return val; } -int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data) +size_t mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data) { struct mv88e6xxx_port *mv88e6xxx_port = &chip->ports[port]; struct mv88e6352_serdes_hw_stat *stat; @@ -352,7 +352,7 @@ int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, err = mv88e6352_g2_scratch_port_has_serdes(chip, port); if (err <= 0) - return err; + return 0; BUILD_BUG_ON(ARRAY_SIZE(mv88e6352_serdes_hw_stats) > ARRAY_SIZE(mv88e6xxx_port->serdes_stats)); @@ -798,8 +798,8 @@ static uint64_t mv88e6390_serdes_get_stat(struct mv88e6xxx_chip *chip, int lane, return reg[0] | ((u64)reg[1] << 16) | ((u64)reg[2] << 32); } -int mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data) +size_t mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data) { struct mv88e6390_serdes_hw_stat *stat; int lane; diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index 29bb4e91e2f6..67369054951f 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -165,13 +165,13 @@ irqreturn_t mv88e6393x_serdes_irq_status(struct mv88e6xxx_chip *chip, int port, int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port); int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, int port, uint8_t *data); -int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data); +size_t mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data); int mv88e6390_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port); int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip, int port, uint8_t *data); -int mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data); +size_t mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data); int mv88e6352_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port); void mv88e6352_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p); diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 1e94ba1031ec..641692f716f8 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -842,10 +842,15 @@ qca8k_mdio_register(struct qca8k_priv *priv) struct dsa_switch *ds = priv->ds; struct device_node *mdio; struct mii_bus *bus; + int err; + + mdio = of_get_child_by_name(priv->dev->of_node, "mdio"); bus = devm_mdiobus_alloc(ds->dev); - if (!bus) - return -ENOMEM; + if (!bus) { + err = -ENOMEM; + goto out_put_node; + } bus->priv = (void *)priv; snprintf(bus->id, MII_BUS_ID_SIZE, "qca8k-%d.%d", @@ -855,12 +860,12 @@ qca8k_mdio_register(struct qca8k_priv *priv) ds->slave_mii_bus = bus; /* Check if the devicetree declare the port:phy mapping */ - mdio = of_get_child_by_name(priv->dev->of_node, "mdio"); if (of_device_is_available(mdio)) { bus->name = "qca8k slave mii"; bus->read = qca8k_internal_mdio_read; bus->write = qca8k_internal_mdio_write; - return devm_of_mdiobus_register(priv->dev, bus, mdio); + err = devm_of_mdiobus_register(priv->dev, bus, mdio); + goto out_put_node; } /* If a mapping can't be found the legacy mapping is used, @@ -869,7 +874,13 @@ qca8k_mdio_register(struct qca8k_priv *priv) bus->name = "qca8k-legacy slave mii"; bus->read = qca8k_legacy_mdio_read; bus->write = qca8k_legacy_mdio_write; - return devm_mdiobus_register(priv->dev, bus); + + err = devm_mdiobus_register(priv->dev, bus); + +out_put_node: + of_node_put(mdio); + + return err; } static int @@ -1924,12 +1935,11 @@ qca8k_sw_probe(struct mdio_device *mdiodev) priv->info = of_device_get_match_data(priv->dev); priv->reset_gpio = devm_gpiod_get_optional(priv->dev, "reset", - GPIOD_ASIS); + GPIOD_OUT_HIGH); if (IS_ERR(priv->reset_gpio)) return PTR_ERR(priv->reset_gpio); if (priv->reset_gpio) { - gpiod_set_value_cansleep(priv->reset_gpio, 1); /* The active low duration must be greater than 10 ms * and checkpatch.pl wants 20 ms. */ diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index ef1a4a7c47b2..3efd55669056 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -1119,6 +1119,8 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc) vsc->gc.label = devm_kasprintf(vsc->dev, GFP_KERNEL, "VSC%04x", vsc->chipid); + if (!vsc->gc.label) + return -ENOMEM; vsc->gc.ngpio = 4; vsc->gc.owner = THIS_MODULE; vsc->gc.parent = vsc->dev; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c index 28c9b6f1a54f..5acb3e16b567 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c @@ -953,8 +953,6 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic) { struct aq_ptp_s *aq_ptp = aq_nic->aq_ptp; unsigned int tx_ring_idx, rx_ring_idx; - struct aq_ring_s *hwts; - struct aq_ring_s *ring; int err; if (!aq_ptp) @@ -962,29 +960,23 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic) tx_ring_idx = aq_ptp_ring_idx(aq_nic->aq_nic_cfg.tc_mode); - ring = aq_ring_tx_alloc(&aq_ptp->ptp_tx, aq_nic, - tx_ring_idx, &aq_nic->aq_nic_cfg); - if (!ring) { - err = -ENOMEM; + err = aq_ring_tx_alloc(&aq_ptp->ptp_tx, aq_nic, + tx_ring_idx, &aq_nic->aq_nic_cfg); + if (err) goto err_exit; - } rx_ring_idx = aq_ptp_ring_idx(aq_nic->aq_nic_cfg.tc_mode); - ring = aq_ring_rx_alloc(&aq_ptp->ptp_rx, aq_nic, - rx_ring_idx, &aq_nic->aq_nic_cfg); - if (!ring) { - err = -ENOMEM; + err = aq_ring_rx_alloc(&aq_ptp->ptp_rx, aq_nic, + rx_ring_idx, &aq_nic->aq_nic_cfg); + if (err) goto err_exit_ptp_tx; - } - hwts = aq_ring_hwts_rx_alloc(&aq_ptp->hwts_rx, aq_nic, PTP_HWST_RING_IDX, - aq_nic->aq_nic_cfg.rxds, - aq_nic->aq_nic_cfg.aq_hw_caps->rxd_size); - if (!hwts) { - err = -ENOMEM; + err = aq_ring_hwts_rx_alloc(&aq_ptp->hwts_rx, aq_nic, PTP_HWST_RING_IDX, + aq_nic->aq_nic_cfg.rxds, + aq_nic->aq_nic_cfg.aq_hw_caps->rxd_size); + if (err) goto err_exit_ptp_rx; - } err = aq_ptp_skb_ring_init(&aq_ptp->skb_ring, aq_nic->aq_nic_cfg.rxds); if (err != 0) { @@ -1001,7 +993,7 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic) return 0; err_exit_hwts_rx: - aq_ring_free(&aq_ptp->hwts_rx); + aq_ring_hwts_rx_free(&aq_ptp->hwts_rx); err_exit_ptp_rx: aq_ring_free(&aq_ptp->ptp_rx); err_exit_ptp_tx: @@ -1019,7 +1011,7 @@ void aq_ptp_ring_free(struct aq_nic_s *aq_nic) aq_ring_free(&aq_ptp->ptp_tx); aq_ring_free(&aq_ptp->ptp_rx); - aq_ring_free(&aq_ptp->hwts_rx); + aq_ring_hwts_rx_free(&aq_ptp->hwts_rx); aq_ptp_skb_ring_release(&aq_ptp->skb_ring); } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 4d9d7d1edb9b..0eaaba3a18ee 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -132,8 +132,8 @@ static int aq_get_rxpages(struct aq_ring_s *self, struct aq_ring_buff_s *rxbuf) return 0; } -static struct aq_ring_s *aq_ring_alloc(struct aq_ring_s *self, - struct aq_nic_s *aq_nic) +static int aq_ring_alloc(struct aq_ring_s *self, + struct aq_nic_s *aq_nic) { int err = 0; @@ -156,46 +156,29 @@ static struct aq_ring_s *aq_ring_alloc(struct aq_ring_s *self, err_exit: if (err < 0) { aq_ring_free(self); - self = NULL; } - return self; + return err; } -struct aq_ring_s *aq_ring_tx_alloc(struct aq_ring_s *self, - struct aq_nic_s *aq_nic, - unsigned int idx, - struct aq_nic_cfg_s *aq_nic_cfg) +int aq_ring_tx_alloc(struct aq_ring_s *self, + struct aq_nic_s *aq_nic, + unsigned int idx, + struct aq_nic_cfg_s *aq_nic_cfg) { - int err = 0; - self->aq_nic = aq_nic; self->idx = idx; self->size = aq_nic_cfg->txds; self->dx_size = aq_nic_cfg->aq_hw_caps->txd_size; - self = aq_ring_alloc(self, aq_nic); - if (!self) { - err = -ENOMEM; - goto err_exit; - } - -err_exit: - if (err < 0) { - aq_ring_free(self); - self = NULL; - } - - return self; + return aq_ring_alloc(self, aq_nic); } -struct aq_ring_s *aq_ring_rx_alloc(struct aq_ring_s *self, - struct aq_nic_s *aq_nic, - unsigned int idx, - struct aq_nic_cfg_s *aq_nic_cfg) +int aq_ring_rx_alloc(struct aq_ring_s *self, + struct aq_nic_s *aq_nic, + unsigned int idx, + struct aq_nic_cfg_s *aq_nic_cfg) { - int err = 0; - self->aq_nic = aq_nic; self->idx = idx; self->size = aq_nic_cfg->rxds; @@ -217,22 +200,10 @@ struct aq_ring_s *aq_ring_rx_alloc(struct aq_ring_s *self, self->tail_size = 0; } - self = aq_ring_alloc(self, aq_nic); - if (!self) { - err = -ENOMEM; - goto err_exit; - } - -err_exit: - if (err < 0) { - aq_ring_free(self); - self = NULL; - } - - return self; + return aq_ring_alloc(self, aq_nic); } -struct aq_ring_s * +int aq_ring_hwts_rx_alloc(struct aq_ring_s *self, struct aq_nic_s *aq_nic, unsigned int idx, unsigned int size, unsigned int dx_size) { @@ -250,10 +221,10 @@ aq_ring_hwts_rx_alloc(struct aq_ring_s *self, struct aq_nic_s *aq_nic, GFP_KERNEL); if (!self->dx_ring) { aq_ring_free(self); - return NULL; + return -ENOMEM; } - return self; + return 0; } int aq_ring_init(struct aq_ring_s *self, const enum atl_ring_type ring_type) @@ -948,6 +919,19 @@ void aq_ring_free(struct aq_ring_s *self) } } +void aq_ring_hwts_rx_free(struct aq_ring_s *self) +{ + if (!self) + return; + + if (self->dx_ring) { + dma_free_coherent(aq_nic_get_dev(self->aq_nic), + self->size * self->dx_size + AQ_CFG_RXDS_DEF, + self->dx_ring, self->dx_ring_pa); + self->dx_ring = NULL; + } +} + unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data) { unsigned int count; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 0a6c34438c1d..d627ace850ff 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -183,14 +183,14 @@ static inline unsigned int aq_ring_avail_dx(struct aq_ring_s *self) self->sw_head - self->sw_tail - 1); } -struct aq_ring_s *aq_ring_tx_alloc(struct aq_ring_s *self, - struct aq_nic_s *aq_nic, - unsigned int idx, - struct aq_nic_cfg_s *aq_nic_cfg); -struct aq_ring_s *aq_ring_rx_alloc(struct aq_ring_s *self, - struct aq_nic_s *aq_nic, - unsigned int idx, - struct aq_nic_cfg_s *aq_nic_cfg); +int aq_ring_tx_alloc(struct aq_ring_s *self, + struct aq_nic_s *aq_nic, + unsigned int idx, + struct aq_nic_cfg_s *aq_nic_cfg); +int aq_ring_rx_alloc(struct aq_ring_s *self, + struct aq_nic_s *aq_nic, + unsigned int idx, + struct aq_nic_cfg_s *aq_nic_cfg); int aq_ring_init(struct aq_ring_s *self, const enum atl_ring_type ring_type); void aq_ring_rx_deinit(struct aq_ring_s *self); @@ -207,9 +207,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self, int budget); int aq_ring_rx_fill(struct aq_ring_s *self); -struct aq_ring_s *aq_ring_hwts_rx_alloc(struct aq_ring_s *self, - struct aq_nic_s *aq_nic, unsigned int idx, - unsigned int size, unsigned int dx_size); +int aq_ring_hwts_rx_alloc(struct aq_ring_s *self, + struct aq_nic_s *aq_nic, unsigned int idx, + unsigned int size, unsigned int dx_size); +void aq_ring_hwts_rx_free(struct aq_ring_s *self); void aq_ring_hwts_rx_clean(struct aq_ring_s *self, struct aq_nic_s *aq_nic); unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index f5db1c44e9b9..9769ab4f9bef 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -136,35 +136,32 @@ int aq_vec_ring_alloc(struct aq_vec_s *self, struct aq_nic_s *aq_nic, const unsigned int idx_ring = AQ_NIC_CFG_TCVEC2RING(aq_nic_cfg, i, idx); - ring = aq_ring_tx_alloc(&self->ring[i][AQ_VEC_TX_ID], aq_nic, - idx_ring, aq_nic_cfg); - if (!ring) { - err = -ENOMEM; + ring = &self->ring[i][AQ_VEC_TX_ID]; + err = aq_ring_tx_alloc(ring, aq_nic, idx_ring, aq_nic_cfg); + if (err) goto err_exit; - } ++self->tx_rings; aq_nic_set_tx_ring(aq_nic, idx_ring, ring); - if (xdp_rxq_info_reg(&self->ring[i][AQ_VEC_RX_ID].xdp_rxq, + ring = &self->ring[i][AQ_VEC_RX_ID]; + if (xdp_rxq_info_reg(&ring->xdp_rxq, aq_nic->ndev, idx, self->napi.napi_id) < 0) { err = -ENOMEM; goto err_exit; } - if (xdp_rxq_info_reg_mem_model(&self->ring[i][AQ_VEC_RX_ID].xdp_rxq, + if (xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL) < 0) { - xdp_rxq_info_unreg(&self->ring[i][AQ_VEC_RX_ID].xdp_rxq); + xdp_rxq_info_unreg(&ring->xdp_rxq); err = -ENOMEM; goto err_exit; } - ring = aq_ring_rx_alloc(&self->ring[i][AQ_VEC_RX_ID], aq_nic, - idx_ring, aq_nic_cfg); - if (!ring) { - xdp_rxq_info_unreg(&self->ring[i][AQ_VEC_RX_ID].xdp_rxq); - err = -ENOMEM; + err = aq_ring_rx_alloc(ring, aq_nic, idx_ring, aq_nic_cfg); + if (err) { + xdp_rxq_info_unreg(&ring->xdp_rxq); goto err_exit; } diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 5935be190b9e..5f2a6fcba967 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -866,10 +866,13 @@ static int atl1e_setup_ring_resources(struct atl1e_adapter *adapter) netdev_err(adapter->netdev, "offset(%d) > ring size(%d) !!\n", offset, adapter->ring_size); err = -1; - goto failed; + goto free_buffer; } return 0; +free_buffer: + kfree(tx_ring->tx_buffer); + tx_ring->tx_buffer = NULL; failed: if (adapter->ring_vir_addr != NULL) { dma_free_coherent(&pdev->dev, adapter->ring_size, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 623cdeb29ed9..f810b5dc25f0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12081,6 +12081,8 @@ static void bnxt_sp_task(struct work_struct *work) bnxt_cfg_ntp_filters(bp); if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event)) bnxt_hwrm_exec_fwd_req(bp); + if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) + netdev_info(bp->dev, "Receive PF driver unload event!\n"); if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) { bnxt_hwrm_port_qstats(bp, 0); bnxt_hwrm_port_qstats_ext(bp, 0); @@ -12267,6 +12269,11 @@ static int bnxt_fw_init_one_p1(struct bnxt *bp) bp->fw_cap = 0; rc = bnxt_hwrm_ver_get(bp); + /* FW may be unresponsive after FLR. FLR must complete within 100 msec + * so wait before continuing with recovery. + */ + if (rc) + msleep(100); bnxt_try_map_fw_health_reg(bp); if (rc) { rc = bnxt_try_recover_fw(bp); @@ -13059,8 +13066,6 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp) } } } - if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) - netdev_info(bp->dev, "Receive PF driver unload event!\n"); } #else diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 1ae082eb9e90..c2a991308215 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2131,8 +2131,10 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) /* Note: if we ever change from DMA_TX_APPEND_CRC below we * will need to restore software padding of "runt" packets */ + len_stat |= DMA_TX_APPEND_CRC; + if (!i) { - len_stat |= DMA_TX_APPEND_CRC | DMA_SOP; + len_stat |= DMA_SOP; if (skb->ip_summed == CHECKSUM_PARTIAL) len_stat |= DMA_TX_DO_CSUM; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index f60a16de565e..0c694ab3c110 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6447,6 +6447,14 @@ static void tg3_dump_state(struct tg3 *tp) int i; u32 *regs; + /* If it is a PCI error, all registers will be 0xffff, + * we don't dump them out, just report the error and return + */ + if (tp->pdev->error_state != pci_channel_io_normal) { + netdev_err(tp->dev, "PCI channel ERROR!\n"); + return; + } + regs = kzalloc(TG3_REG_BLK_SIZE, GFP_ATOMIC); if (!regs) return; @@ -11184,7 +11192,8 @@ static void tg3_reset_task(struct work_struct *work) rtnl_lock(); tg3_full_lock(tp, 0); - if (tp->pcierr_recovery || !netif_running(tp->dev)) { + if (tp->pcierr_recovery || !netif_running(tp->dev) || + tp->pdev->error_state != pci_channel_io_normal) { tg3_flag_clear(tp, RESET_TASK_PENDING); tg3_full_unlock(tp); rtnl_unlock(); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index b58162ce81d8..de62eee58a00 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -509,8 +509,6 @@ static struct sk_buff *dpaa2_eth_copybreak(struct dpaa2_eth_channel *ch, memcpy(skb->data, fd_vaddr + fd_offset, fd_length); - dpaa2_eth_recycle_buf(priv, ch, dpaa2_fd_get_addr(fd)); - return skb; } @@ -528,6 +526,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, struct dpaa2_eth_drv_stats *percpu_extras; struct device *dev = priv->net_dev->dev.parent; struct dpaa2_fas *fas; + bool recycle_rx_buf = false; void *buf_data; u32 status = 0; u32 xdp_act; @@ -560,6 +559,8 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); skb = dpaa2_eth_build_linear_skb(ch, fd, vaddr); + } else { + recycle_rx_buf = true; } } else if (fd_format == dpaa2_fd_sg) { WARN_ON(priv->xdp_prog); @@ -607,6 +608,8 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, list_add_tail(&skb->list, ch->rx_list); + if (recycle_rx_buf) + dpaa2_eth_recycle_buf(priv, ch, dpaa2_fd_get_addr(fd)); return; err_build_skb: diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index eea7d7a07c00..59888826469b 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -227,17 +227,8 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, struct ethtool_stats *stats, u64 *data) { - int i = 0; - int j, k, err; - int num_cnt; - union dpni_statistics dpni_stats; - u32 fcnt, bcnt; - u32 fcnt_rx_total = 0, fcnt_tx_total = 0; - u32 bcnt_rx_total = 0, bcnt_tx_total = 0; - u32 buf_cnt; struct dpaa2_eth_priv *priv = netdev_priv(net_dev); - struct dpaa2_eth_drv_stats *extras; - struct dpaa2_eth_ch_stats *ch_stats; + union dpni_statistics dpni_stats; int dpni_stats_page_size[DPNI_STATISTICS_CNT] = { sizeof(dpni_stats.page_0), sizeof(dpni_stats.page_1), @@ -247,6 +238,13 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, sizeof(dpni_stats.page_5), sizeof(dpni_stats.page_6), }; + u32 fcnt_rx_total = 0, fcnt_tx_total = 0; + u32 bcnt_rx_total = 0, bcnt_tx_total = 0; + struct dpaa2_eth_ch_stats *ch_stats; + struct dpaa2_eth_drv_stats *extras; + int j, k, err, num_cnt, i = 0; + u32 fcnt, bcnt; + u32 buf_cnt; memset(data, 0, sizeof(u64) * (DPAA2_ETH_NUM_STATS + DPAA2_ETH_NUM_EXTRA_STATS)); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 6d1b76002282..97d12c7eea77 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1917,6 +1917,7 @@ static void fec_enet_adjust_link(struct net_device *ndev) /* if any of the above changed restart the FEC */ if (status_change) { + netif_stop_queue(ndev); napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); @@ -1926,6 +1927,7 @@ static void fec_enet_adjust_link(struct net_device *ndev) } } else { if (fep->link) { + netif_stop_queue(ndev); napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_stop(ndev); diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index 588d64819ed5..e84e944d751d 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -350,6 +350,7 @@ static void gve_tx_fill_pkt_desc_dqo(struct gve_tx_ring *tx, u32 *desc_idx, /* Validates and prepares `skb` for TSO. * * Returns header length, or < 0 if invalid. + * Warning : Might change skb->head (and thus skb_shinfo). */ static int gve_prep_tso(struct sk_buff *skb) { @@ -451,8 +452,8 @@ gve_tx_fill_general_ctx_desc(struct gve_tx_general_context_desc_dqo *desc, static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, struct sk_buff *skb) { - const struct skb_shared_info *shinfo = skb_shinfo(skb); const bool is_gso = skb_is_gso(skb); + struct skb_shared_info *shinfo; u32 desc_idx = tx->dqo_tx.tail; struct gve_tx_pending_packet_dqo *pkt; @@ -477,6 +478,8 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, desc_idx = (desc_idx + 1) & tx->mask; } + /* Must get after gve_prep_tso(), which can change shinfo. */ + shinfo = skb_shinfo(skb); gve_tx_fill_general_ctx_desc(&tx->dqo.tx_ring[desc_idx].general_ctx, &metadata); desc_idx = (desc_idx + 1) & tx->mask; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b4157ff370a3..76455405a6d8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -104,12 +104,18 @@ static struct workqueue_struct *i40e_wq; static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f, struct net_device *netdev, int delta) { + struct netdev_hw_addr_list *ha_list; struct netdev_hw_addr *ha; if (!f || !netdev) return; - netdev_for_each_mc_addr(ha, netdev) { + if (is_unicast_ether_addr(f->macaddr) || is_link_local_ether_addr(f->macaddr)) + ha_list = &netdev->uc; + else + ha_list = &netdev->mc; + + netdev_hw_addr_list_for_each(ha, ha_list) { if (ether_addr_equal(ha->addr, f->macaddr)) { ha->refcount += delta; if (ha->refcount <= 0) @@ -5327,7 +5333,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf) { int v, ret = 0; - for (v = 0; v < pf->hw.func_caps.num_vsis; v++) { + for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v]) { ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]); if (ret) @@ -16444,6 +16450,9 @@ static void i40e_pci_error_reset_done(struct pci_dev *pdev) return; i40e_reset_and_rebuild(pf, false, false); +#ifdef CONFIG_PCI_IOV + i40e_restore_all_vfs_msi_state(pdev); +#endif /* CONFIG_PCI_IOV */ } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index cb925baf72ce..ed4be80fec2a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -152,6 +152,32 @@ void i40e_vc_notify_reset(struct i40e_pf *pf) (u8 *)&pfe, sizeof(struct virtchnl_pf_event)); } +#ifdef CONFIG_PCI_IOV +void i40e_restore_all_vfs_msi_state(struct pci_dev *pdev) +{ + u16 vf_id; + u16 pos; + + /* Continue only if this is a PF */ + if (!pdev->is_physfn) + return; + + if (!pci_num_vf(pdev)) + return; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + if (pos) { + struct pci_dev *vf_dev = NULL; + + pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_id); + while ((vf_dev = pci_get_device(pdev->vendor, vf_id, vf_dev))) { + if (vf_dev->is_virtfn && vf_dev->physfn == pdev) + pci_restore_msi_state(vf_dev); + } + } +} +#endif /* CONFIG_PCI_IOV */ + /** * i40e_vc_notify_vf_reset * @vf: pointer to the VF structure @@ -2577,6 +2603,14 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) int aq_ret = 0; int i; + if (vf->is_disabled_from_host) { + aq_ret = -EPERM; + dev_info(&pf->pdev->dev, + "Admin has disabled VF %d, will not enable queues\n", + vf->vf_id); + goto error_param; + } + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; @@ -2812,6 +2846,24 @@ error_param: (u8 *)&stats, sizeof(stats)); } +/** + * i40e_can_vf_change_mac + * @vf: pointer to the VF info + * + * Return true if the VF is allowed to change its MAC filters, false otherwise + */ +static bool i40e_can_vf_change_mac(struct i40e_vf *vf) +{ + /* If the VF MAC address has been set administratively (via the + * ndo_set_vf_mac command), then deny permission to the VF to + * add/delete unicast MAC addresses, unless the VF is trusted + */ + if (vf->pf_set_mac && !vf->trusted) + return false; + + return true; +} + #define I40E_MAX_MACVLAN_PER_HW 3072 #define I40E_MAX_MACVLAN_PER_PF(num_ports) (I40E_MAX_MACVLAN_PER_HW / \ (num_ports)) @@ -2871,8 +2923,8 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, * The VF may request to set the MAC address filter already * assigned to it so do not return an error in that case. */ - if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) && - !is_multicast_ether_addr(addr) && vf->pf_set_mac && + if (!i40e_can_vf_change_mac(vf) && + !is_multicast_ether_addr(addr) && !ether_addr_equal(addr, vf->default_lan_addr.addr)) { dev_err(&pf->pdev->dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); @@ -3015,19 +3067,29 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) ret = I40E_ERR_INVALID_MAC_ADDR; goto error_param; } - if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr)) - was_unimac_deleted = true; } vsi = pf->vsi[vf->lan_vsi_idx]; spin_lock_bh(&vsi->mac_filter_hash_lock); /* delete addresses from the list */ - for (i = 0; i < al->num_elements; i++) + for (i = 0; i < al->num_elements; i++) { + const u8 *addr = al->list[i].addr; + + /* Allow to delete VF primary MAC only if it was not set + * administratively by PF or if VF is trusted. + */ + if (ether_addr_equal(addr, vf->default_lan_addr.addr) && + i40e_can_vf_change_mac(vf)) + was_unimac_deleted = true; + else + continue; + if (i40e_del_mac_filter(vsi, al->list[i].addr)) { ret = I40E_ERR_INVALID_MAC_ADDR; spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } + } spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -3451,16 +3513,16 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf, bool found = false; int bkt; - if (!tc_filter->action) { + if (tc_filter->action != VIRTCHNL_ACTION_TC_REDIRECT) { dev_info(&pf->pdev->dev, - "VF %d: Currently ADq doesn't support Drop Action\n", - vf->vf_id); + "VF %d: ADQ doesn't support this action (%d)\n", + vf->vf_id, tc_filter->action); goto err; } /* action_meta is TC number here to which the filter is applied */ if (!tc_filter->action_meta || - tc_filter->action_meta > I40E_MAX_VF_VSI) { + tc_filter->action_meta > vf->num_tc) { dev_info(&pf->pdev->dev, "VF %d: Invalid TC number %u\n", vf->vf_id, tc_filter->action_meta); goto err; @@ -4630,9 +4692,12 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) struct i40e_link_status *ls = &pf->hw.phy.link_info; struct virtchnl_pf_event pfe; struct i40e_hw *hw = &pf->hw; + struct i40e_vsi *vsi; + unsigned long q_map; struct i40e_vf *vf; int abs_vf_id; int ret = 0; + int tmp; if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); @@ -4655,17 +4720,38 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) switch (link) { case IFLA_VF_LINK_STATE_AUTO: vf->link_forced = false; + vf->is_disabled_from_host = false; + /* reset needed to reinit VF resources */ + i40e_vc_reset_vf(vf, true); i40e_set_vf_link_state(vf, &pfe, ls); break; case IFLA_VF_LINK_STATE_ENABLE: vf->link_forced = true; vf->link_up = true; + vf->is_disabled_from_host = false; + /* reset needed to reinit VF resources */ + i40e_vc_reset_vf(vf, true); i40e_set_vf_link_state(vf, &pfe, ls); break; case IFLA_VF_LINK_STATE_DISABLE: vf->link_forced = true; vf->link_up = false; i40e_set_vf_link_state(vf, &pfe, ls); + + vsi = pf->vsi[vf->lan_vsi_idx]; + q_map = BIT(vsi->num_queue_pairs) - 1; + + vf->is_disabled_from_host = true; + + /* Try to stop both Tx&Rx rings even if one of the calls fails + * to ensure we stop the rings even in case of errors. + * If any of them returns with an error then the first + * error that occurred will be returned. + */ + tmp = i40e_ctrl_vf_tx_rings(vsi, q_map, false); + ret = i40e_ctrl_vf_rx_rings(vsi, q_map, false); + + ret = tmp ? tmp : ret; break; default: ret = -EINVAL; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 358bbdb58795..97e9c34d7c6c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -98,6 +98,7 @@ struct i40e_vf { bool link_forced; bool link_up; /* only valid if VF link is forced */ bool spoofchk; + bool is_disabled_from_host; /* PF ctrl of VF enable/disable */ u16 num_vlan; /* ADq related variables */ @@ -135,6 +136,9 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable); void i40e_vc_notify_link_state(struct i40e_pf *pf); void i40e_vc_notify_reset(struct i40e_pf *pf); +#ifdef CONFIG_PCI_IOV +void i40e_restore_all_vfs_msi_state(struct pci_dev *pdev); +#endif /* CONFIG_PCI_IOV */ int i40e_get_vf_stats(struct net_device *netdev, int vf_id, struct ifla_vf_stats *vf_stats); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 1bdc70aa979d..fe48164dce1e 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -413,10 +413,10 @@ struct ice_aqc_vsi_props { #define ICE_AQ_VSI_INNER_VLAN_INSERT_PVID BIT(2) #define ICE_AQ_VSI_INNER_VLAN_EMODE_S 3 #define ICE_AQ_VSI_INNER_VLAN_EMODE_M (0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH (0x0 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_UP (0x1 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR (0x2 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) -#define ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING (0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH 0x0U +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_UP 0x1U +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR 0x2U +#define ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING 0x3U u8 inner_vlan_reserved2[3]; /* ingress egress up sections */ __le32 ingress_table; /* bitmap, 3 bits per up */ @@ -482,11 +482,11 @@ struct ice_aqc_vsi_props { #define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S 2 #define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M (0xF << ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S) #define ICE_AQ_VSI_Q_OPT_RSS_HASH_S 6 -#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_TPLZ (0x0 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_SYM_TPLZ (0x1 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_XOR (0x2 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_JHASH (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M GENMASK(7, 6) +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ 0x0U +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ 0x1U +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR 0x2U +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_JHASH 0x3U u8 q_opt_tc; #define ICE_AQ_VSI_Q_OPT_TC_OVR_S 0 #define ICE_AQ_VSI_Q_OPT_TC_OVR_M (0x1F << ICE_AQ_VSI_Q_OPT_TC_OVR_S) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index c051503c3a89..cc6c04a69b28 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -878,7 +878,8 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) */ if (ice_is_dvm_ena(hw)) { ctxt->info.inner_vlan_flags |= - ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING); ctxt->info.outer_vlan_flags = (ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & @@ -1085,12 +1086,12 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) case ICE_VSI_PF: /* PF VSI will inherit RSS instance of PF */ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF; - hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + hash_type = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; break; case ICE_VSI_VF: /* VF VSI will gets a small RSS table which is a VSI LUT type */ lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; - hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + hash_type = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; break; default: dev_dbg(dev, "Unsupported VSI type %s\n", diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f0f39364819a..ab46cfca4028 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2138,7 +2138,7 @@ static int ice_configure_phy(struct ice_vsi *vsi) /* Ensure we have media as we cannot configure a medialess port */ if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) - return -EPERM; + return -ENOMEDIUM; ice_print_topo_conflict(vsi); @@ -9065,8 +9065,14 @@ int ice_stop(struct net_device *netdev) int link_err = ice_force_phys_link_state(vsi, false); if (link_err) { - netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", - vsi->vsi_num, link_err); + if (link_err == -ENOMEDIUM) + netdev_info(vsi->netdev, "Skipping link reconfig - no media attached, VSI %d\n", + vsi->vsi_num); + else + netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", + vsi->vsi_num, link_err); + + ice_vsi_close(vsi); return -EIO; } } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 2b4c791b6cba..6c03ebf81ffd 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -817,8 +817,8 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) int status; lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; - hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_XOR : - ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR : + ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) { @@ -826,11 +826,9 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) goto error_param; } - ctx->info.q_opt_rss = ((lut_type << - ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & - ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | - (hash_type & - ICE_AQ_VSI_Q_OPT_RSS_HASH_M); + ctx->info.q_opt_rss = + FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_LUT_M, lut_type) | + FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hash_type); /* Preserve existing queueing option setting */ ctx->info.q_opt_rss |= (vsi->info.q_opt_rss & diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c index 5b4a0abb4607..239266e9d5f1 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -131,6 +131,7 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) { struct ice_hw *hw = &vsi->back->hw; struct ice_vsi_ctx *ctxt; + u8 *ivf; int err; /* do not allow modifying VLAN stripping when a port VLAN is configured @@ -143,19 +144,24 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) if (!ctxt) return -ENOMEM; + ivf = &ctxt->info.inner_vlan_flags; + /* Here we are configuring what the VSI should do with the VLAN tag in * the Rx packet. We can either leave the tag in the packet or put it in * the Rx descriptor. */ - if (ena) + if (ena) { /* Strip VLAN tag from Rx packet and put it in the desc */ - ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH; - else + *ivf = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH); + } else { /* Disable stripping. Leave tag in packet */ - ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + *ivf = FIELD_PREP(ICE_AQ_VSI_INNER_VLAN_EMODE_M, + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING); + } /* Allow all packets untagged/tagged */ - ctxt->info.inner_vlan_flags |= ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL; + *ivf |= ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL; ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 43c05b41627f..2a894ca49d93 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -538,6 +538,7 @@ struct igc_nfc_filter { u16 etype; __be16 vlan_etype; u16 vlan_tci; + u16 vlan_tci_mask; u8 src_addr[ETH_ALEN]; u8 dst_addr[ETH_ALEN]; u8 user_data[8]; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 81897f7a90a9..2bee9cace598 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -957,6 +957,7 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev, } #define ETHER_TYPE_FULL_MASK ((__force __be16)~0) +#define VLAN_TCI_FULL_MASK ((__force __be16)~0) static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter, struct ethtool_rxnfc *cmd) { @@ -979,10 +980,16 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter, fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK; } + if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) { + fsp->flow_type |= FLOW_EXT; + fsp->h_ext.vlan_etype = rule->filter.vlan_etype; + fsp->m_ext.vlan_etype = ETHER_TYPE_FULL_MASK; + } + if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) { fsp->flow_type |= FLOW_EXT; fsp->h_ext.vlan_tci = htons(rule->filter.vlan_tci); - fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK); + fsp->m_ext.vlan_tci = htons(rule->filter.vlan_tci_mask); } if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) { @@ -1217,6 +1224,7 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule, if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) { rule->filter.vlan_tci = ntohs(fsp->h_ext.vlan_tci); + rule->filter.vlan_tci_mask = ntohs(fsp->m_ext.vlan_tci); rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI; } @@ -1254,11 +1262,19 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule, memcpy(rule->filter.user_mask, fsp->m_ext.data, sizeof(fsp->m_ext.data)); } - /* When multiple filter options or user data or vlan etype is set, use a - * flex filter. + /* The i225/i226 has various different filters. Flex filters provide a + * way to match up to the first 128 bytes of a packet. Use them for: + * a) For specific user data + * b) For VLAN EtherType + * c) For full TCI match + * d) Or in case multiple filter criteria are set + * + * Otherwise, use the simple MAC, VLAN PRIO or EtherType filters. */ if ((rule->filter.match_flags & IGC_FILTER_FLAG_USER_DATA) || (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) || + ((rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) && + rule->filter.vlan_tci_mask == ntohs(VLAN_TCI_FULL_MASK)) || (rule->filter.match_flags & (rule->filter.match_flags - 1))) rule->flex = true; else @@ -1328,6 +1344,26 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter, return -EINVAL; } + /* There are two ways to match the VLAN TCI: + * 1. Match on PCP field and use vlan prio filter for it + * 2. Match on complete TCI field and use flex filter for it + */ + if ((fsp->flow_type & FLOW_EXT) && + fsp->m_ext.vlan_tci && + fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK) && + fsp->m_ext.vlan_tci != VLAN_TCI_FULL_MASK) { + netdev_dbg(netdev, "VLAN mask not supported\n"); + return -EOPNOTSUPP; + } + + /* VLAN EtherType can only be matched by full mask. */ + if ((fsp->flow_type & FLOW_EXT) && + fsp->m_ext.vlan_etype && + fsp->m_ext.vlan_etype != ETHER_TYPE_FULL_MASK) { + netdev_dbg(netdev, "VLAN EtherType mask not supported\n"); + return -EOPNOTSUPP; + } + if (fsp->location >= IGC_MAX_RXNFC_RULES) { netdev_dbg(netdev, "Invalid location\n"); return -EINVAL; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 725db36e399d..31ea0781b65e 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -178,7 +178,7 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_TQAVCC(i), tqavcc); wr32(IGC_TQAVHC(i), - 0x80000000 + ring->hicredit * 0x7735); + 0x80000000 + ring->hicredit * 0x7736); } else { /* Disable any CBS for the queue */ txqctl &= ~(IGC_TXQCTL_QAV_SEL_MASK); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 100388968e4d..3d56481e16bc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -123,14 +123,14 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) if (ret_val) return ret_val; if (hw->phy.sfp_type == ixgbe_sfp_type_unknown) - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; /* Check to see if SFP+ module is supported */ ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, &list_offset, &data_offset); if (ret_val) - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; break; default: break; @@ -213,7 +213,7 @@ static s32 ixgbe_get_link_capabilities_82598(struct ixgbe_hw *hw, break; default: - return IXGBE_ERR_LINK_SETUP; + return -EIO; } return 0; @@ -283,7 +283,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) /* Validate the water mark configuration */ if (!hw->fc.pause_time) - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; /* Low water mark of zero causes XOFF floods */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { @@ -292,7 +292,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) if (!hw->fc.low_water[i] || hw->fc.low_water[i] >= hw->fc.high_water[i]) { hw_dbg(hw, "Invalid water mark configuration\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } } } @@ -369,7 +369,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) break; default: hw_dbg(hw, "Flow control param set incorrectly\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } /* Set 802.3x based flow control settings. */ @@ -438,7 +438,7 @@ static s32 ixgbe_start_mac_link_82598(struct ixgbe_hw *hw, msleep(100); } if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { - status = IXGBE_ERR_AUTONEG_NOT_COMPLETE; + status = -EIO; hw_dbg(hw, "Autonegotiation did not complete.\n"); } } @@ -478,7 +478,7 @@ static s32 ixgbe_validate_link_ready(struct ixgbe_hw *hw) if (timeout == IXGBE_VALIDATE_LINK_READY_TIMEOUT) { hw_dbg(hw, "Link was indicated but link is down\n"); - return IXGBE_ERR_LINK_SETUP; + return -EIO; } return 0; @@ -594,7 +594,7 @@ static s32 ixgbe_setup_mac_link_82598(struct ixgbe_hw *hw, speed &= link_capabilities; if (speed == IXGBE_LINK_SPEED_UNKNOWN) - return IXGBE_ERR_LINK_SETUP; + return -EINVAL; /* Set KX4/KX support according to speed requested */ else if (link_mode == IXGBE_AUTOC_LMS_KX4_AN || @@ -701,9 +701,9 @@ static s32 ixgbe_reset_hw_82598(struct ixgbe_hw *hw) /* Init PHY and function pointers, perform SFP setup */ phy_status = hw->phy.ops.init(hw); - if (phy_status == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (phy_status == -EOPNOTSUPP) return phy_status; - if (phy_status == IXGBE_ERR_SFP_NOT_PRESENT) + if (phy_status == -ENOENT) goto mac_reset_top; hw->phy.ops.reset(hw); @@ -727,7 +727,7 @@ mac_reset_top: udelay(1); } if (ctrl & IXGBE_CTRL_RST) { - status = IXGBE_ERR_RESET_FAILED; + status = -EIO; hw_dbg(hw, "Reset polling failed to complete.\n"); } @@ -789,7 +789,7 @@ static s32 ixgbe_set_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq) /* Make sure we are using a valid rar index range */ if (rar >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", rar); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar)); @@ -814,7 +814,7 @@ static s32 ixgbe_clear_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq) /* Make sure we are using a valid rar index range */ if (rar >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", rar); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar)); @@ -845,7 +845,7 @@ static s32 ixgbe_set_vfta_82598(struct ixgbe_hw *hw, u32 vlan, u32 vind, u32 vftabyte; if (vlan > 4095) - return IXGBE_ERR_PARAM; + return -EINVAL; /* Determine 32-bit word position in array */ regindex = (vlan >> 5) & 0x7F; /* upper seven bits */ @@ -964,7 +964,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, gssr = IXGBE_GSSR_PHY0_SM; if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; if (hw->phy.type == ixgbe_phy_nl) { /* @@ -993,7 +993,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, if (sfp_stat != IXGBE_I2C_EEPROM_STATUS_PASS) { hw_dbg(hw, "EEPROM read did not pass.\n"); - status = IXGBE_ERR_SFP_NOT_PRESENT; + status = -ENOENT; goto out; } @@ -1003,7 +1003,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, *eeprom_data = (u8)(sfp_data >> 8); } else { - status = IXGBE_ERR_PHY; + status = -EIO; } out: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index 58ea959a4482..339e106a5732 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -117,7 +117,7 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) ret_val = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); if (ret_val) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; if (hw->eeprom.ops.read(hw, ++data_offset, &data_value)) goto setup_sfp_err; @@ -144,7 +144,7 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) if (ret_val) { hw_dbg(hw, " sfp module setup not complete\n"); - return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; + return -EIO; } } @@ -159,7 +159,7 @@ setup_sfp_err: usleep_range(hw->eeprom.semaphore_delay * 1000, hw->eeprom.semaphore_delay * 2000); hw_err(hw, "eeprom read at offset %d failed\n", data_offset); - return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; + return -EIO; } /** @@ -184,7 +184,7 @@ static s32 prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked, ret_val = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); if (ret_val) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; *locked = true; } @@ -219,7 +219,7 @@ static s32 prot_autoc_write_82599(struct ixgbe_hw *hw, u32 autoc, bool locked) ret_val = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); if (ret_val) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; locked = true; } @@ -400,7 +400,7 @@ static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, break; default: - return IXGBE_ERR_LINK_SETUP; + return -EIO; } if (hw->phy.multispeed_fiber) { @@ -541,7 +541,7 @@ static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw, msleep(100); } if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { - status = IXGBE_ERR_AUTONEG_NOT_COMPLETE; + status = -EIO; hw_dbg(hw, "Autoneg did not complete.\n"); } } @@ -794,7 +794,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, speed &= link_capabilities; if (speed == IXGBE_LINK_SPEED_UNKNOWN) - return IXGBE_ERR_LINK_SETUP; + return -EINVAL; /* Use stored value (EEPROM defaults) of AUTOC to find KR/KX4 support*/ if (hw->mac.orig_link_settings_stored) @@ -861,8 +861,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, msleep(100); } if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { - status = - IXGBE_ERR_AUTONEG_NOT_COMPLETE; + status = -EIO; hw_dbg(hw, "Autoneg did not complete.\n"); } } @@ -927,7 +926,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) /* Identify PHY and related function pointers */ status = hw->phy.ops.init(hw); - if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (status == -EOPNOTSUPP) return status; /* Setup SFP module if there is one present. */ @@ -936,7 +935,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) hw->phy.sfp_setup_needed = false; } - if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (status == -EOPNOTSUPP) return status; /* Reset PHY */ @@ -974,7 +973,7 @@ mac_reset_top: } if (ctrl & IXGBE_CTRL_RST_MASK) { - status = IXGBE_ERR_RESET_FAILED; + status = -EIO; hw_dbg(hw, "Reset polling failed to complete.\n"); } @@ -1093,7 +1092,7 @@ static s32 ixgbe_fdir_check_cmd_complete(struct ixgbe_hw *hw, u32 *fdircmd) udelay(10); } - return IXGBE_ERR_FDIR_CMD_INCOMPLETE; + return -EIO; } /** @@ -1155,7 +1154,7 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw) } if (i >= IXGBE_FDIR_INIT_DONE_POLL) { hw_dbg(hw, "Flow Director Signature poll time exceeded!\n"); - return IXGBE_ERR_FDIR_REINIT_FAILED; + return -EIO; } /* Clear FDIR statistics registers (read to clear) */ @@ -1387,7 +1386,7 @@ s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw, break; default: hw_dbg(hw, " Error on flow type input\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } /* configure FDIRCMD register */ @@ -1546,7 +1545,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, break; default: hw_dbg(hw, " Error on vm pool mask\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } switch (input_mask->formatted.flow_type & IXGBE_ATR_L4TYPE_MASK) { @@ -1555,14 +1554,14 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, if (input_mask->formatted.dst_port || input_mask->formatted.src_port) { hw_dbg(hw, " Error on src/dst port mask\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } break; case IXGBE_ATR_L4TYPE_MASK: break; default: hw_dbg(hw, " Error on flow type mask\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } switch (ntohs(input_mask->formatted.vlan_id) & 0xEFFF) { @@ -1583,7 +1582,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, break; default: hw_dbg(hw, " Error on VLAN mask\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } switch ((__force u16)input_mask->formatted.flex_bytes & 0xFFFF) { @@ -1595,7 +1594,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, break; default: hw_dbg(hw, " Error on flexible byte mask\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } /* Now mask VM pool and destination IPv6 - bits 5 and 2 */ @@ -1824,7 +1823,7 @@ static s32 ixgbe_identify_phy_82599(struct ixgbe_hw *hw) /* Return error if SFP module has been detected but is not supported */ if (hw->phy.type == ixgbe_phy_sfp_unsupported) - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; return status; } @@ -1863,13 +1862,13 @@ static s32 ixgbe_enable_rx_dma_82599(struct ixgbe_hw *hw, u32 regval) * Verifies that installed the firmware version is 0.6 or higher * for SFI devices. All 82599 SFI devices should have version 0.6 or higher. * - * Returns IXGBE_ERR_EEPROM_VERSION if the FW is not present or - * if the FW version is not supported. + * Return: -EACCES if the FW is not present or if the FW version is + * not supported. **/ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) { - s32 status = IXGBE_ERR_EEPROM_VERSION; u16 fw_offset, fw_ptp_cfg_offset; + s32 status = -EACCES; u16 offset; u16 fw_version = 0; @@ -1883,7 +1882,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) goto fw_version_err; if (fw_offset == 0 || fw_offset == 0xFFFF) - return IXGBE_ERR_EEPROM_VERSION; + return -EACCES; /* get the offset to the Pass Through Patch Configuration block */ offset = fw_offset + IXGBE_FW_PASSTHROUGH_PATCH_CONFIG_PTR; @@ -1891,7 +1890,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) goto fw_version_err; if (fw_ptp_cfg_offset == 0 || fw_ptp_cfg_offset == 0xFFFF) - return IXGBE_ERR_EEPROM_VERSION; + return -EACCES; /* get the firmware version */ offset = fw_ptp_cfg_offset + IXGBE_FW_PATCH_VERSION_4; @@ -1905,7 +1904,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) fw_version_err: hw_err(hw, "eeprom read at offset %d failed\n", offset); - return IXGBE_ERR_EEPROM_VERSION; + return -EACCES; } /** @@ -2038,7 +2037,7 @@ static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw) if (!(anlp1_reg & IXGBE_ANLP1_AN_STATE_MASK)) { hw_dbg(hw, "auto negotiation not completed\n"); - ret_val = IXGBE_ERR_RESET_FAILED; + ret_val = -EIO; goto reset_pipeline_out; } @@ -2087,7 +2086,7 @@ static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, if (!timeout) { hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); - status = IXGBE_ERR_I2C; + status = -EIO; goto release_i2c_access; } } @@ -2141,7 +2140,7 @@ static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, if (!timeout) { hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); - status = IXGBE_ERR_I2C; + status = -EIO; goto release_i2c_access; } } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 38c4609bd429..5688a6ad4b3b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -124,7 +124,7 @@ s32 ixgbe_setup_fc_generic(struct ixgbe_hw *hw) */ if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { hw_dbg(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } /* @@ -215,7 +215,7 @@ s32 ixgbe_setup_fc_generic(struct ixgbe_hw *hw) break; default: hw_dbg(hw, "Flow control param set incorrectly\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } if (hw->mac.type != ixgbe_mac_X540) { @@ -500,7 +500,7 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, if (pba_num == NULL) { hw_dbg(hw, "PBA string buffer was null\n"); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } ret_val = hw->eeprom.ops.read(hw, IXGBE_PBANUM0_PTR, &data); @@ -526,7 +526,7 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, /* we will need 11 characters to store the PBA */ if (pba_num_size < 11) { hw_dbg(hw, "PBA string buffer too small\n"); - return IXGBE_ERR_NO_SPACE; + return -ENOSPC; } /* extract hex string from data and pba_ptr */ @@ -563,13 +563,13 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, if (length == 0xFFFF || length == 0) { hw_dbg(hw, "NVM PBA number section invalid length\n"); - return IXGBE_ERR_PBA_SECTION; + return -EIO; } /* check if pba_num buffer is big enough */ if (pba_num_size < (((u32)length * 2) - 1)) { hw_dbg(hw, "PBA string buffer too small\n"); - return IXGBE_ERR_NO_SPACE; + return -ENOSPC; } /* trim pba length from start of string */ @@ -805,7 +805,7 @@ s32 ixgbe_led_on_generic(struct ixgbe_hw *hw, u32 index) u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; /* To turn on the LED, set mode to ON. */ led_reg &= ~IXGBE_LED_MODE_MASK(index); @@ -826,7 +826,7 @@ s32 ixgbe_led_off_generic(struct ixgbe_hw *hw, u32 index) u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; /* To turn off the LED, set mode to OFF. */ led_reg &= ~IXGBE_LED_MODE_MASK(index); @@ -904,11 +904,8 @@ s32 ixgbe_write_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, hw->eeprom.ops.init_params(hw); - if (words == 0) - return IXGBE_ERR_INVALID_ARGUMENT; - - if (offset + words > hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + if (words == 0 || (offset + words > hw->eeprom.word_size)) + return -EINVAL; /* * The EEPROM page size cannot be queried from the chip. We do lazy @@ -962,7 +959,7 @@ static s32 ixgbe_write_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, if (ixgbe_ready_eeprom(hw) != 0) { ixgbe_release_eeprom(hw); - return IXGBE_ERR_EEPROM; + return -EIO; } for (i = 0; i < words; i++) { @@ -1028,7 +1025,7 @@ s32 ixgbe_write_eeprom_generic(struct ixgbe_hw *hw, u16 offset, u16 data) hw->eeprom.ops.init_params(hw); if (offset >= hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + return -EINVAL; return ixgbe_write_eeprom_buffer_bit_bang(hw, offset, 1, &data); } @@ -1050,11 +1047,8 @@ s32 ixgbe_read_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, hw->eeprom.ops.init_params(hw); - if (words == 0) - return IXGBE_ERR_INVALID_ARGUMENT; - - if (offset + words > hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + if (words == 0 || (offset + words > hw->eeprom.word_size)) + return -EINVAL; /* * We cannot hold synchronization semaphores for too long @@ -1099,7 +1093,7 @@ static s32 ixgbe_read_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, if (ixgbe_ready_eeprom(hw) != 0) { ixgbe_release_eeprom(hw); - return IXGBE_ERR_EEPROM; + return -EIO; } for (i = 0; i < words; i++) { @@ -1142,7 +1136,7 @@ s32 ixgbe_read_eeprom_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, hw->eeprom.ops.init_params(hw); if (offset >= hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + return -EINVAL; return ixgbe_read_eeprom_buffer_bit_bang(hw, offset, 1, data); } @@ -1165,11 +1159,8 @@ s32 ixgbe_read_eerd_buffer_generic(struct ixgbe_hw *hw, u16 offset, hw->eeprom.ops.init_params(hw); - if (words == 0) - return IXGBE_ERR_INVALID_ARGUMENT; - - if (offset >= hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + if (words == 0 || offset >= hw->eeprom.word_size) + return -EINVAL; for (i = 0; i < words; i++) { eerd = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) | @@ -1262,11 +1253,8 @@ s32 ixgbe_write_eewr_buffer_generic(struct ixgbe_hw *hw, u16 offset, hw->eeprom.ops.init_params(hw); - if (words == 0) - return IXGBE_ERR_INVALID_ARGUMENT; - - if (offset >= hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + if (words == 0 || offset >= hw->eeprom.word_size) + return -EINVAL; for (i = 0; i < words; i++) { eewr = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) | @@ -1328,7 +1316,7 @@ static s32 ixgbe_poll_eerd_eewr_done(struct ixgbe_hw *hw, u32 ee_reg) } udelay(5); } - return IXGBE_ERR_EEPROM; + return -EIO; } /** @@ -1344,7 +1332,7 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw) u32 i; if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM) != 0) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); @@ -1366,7 +1354,7 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw) hw_dbg(hw, "Could not acquire EEPROM grant\n"); hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); - return IXGBE_ERR_EEPROM; + return -EIO; } /* Setup EEPROM for Read/Write */ @@ -1419,7 +1407,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw) swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw)); if (swsm & IXGBE_SWSM_SMBI) { hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } } @@ -1447,7 +1435,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw) if (i >= timeout) { hw_dbg(hw, "SWESMBI Software EEPROM semaphore not granted.\n"); ixgbe_release_eeprom_semaphore(hw); - return IXGBE_ERR_EEPROM; + return -EIO; } return 0; @@ -1503,7 +1491,7 @@ static s32 ixgbe_ready_eeprom(struct ixgbe_hw *hw) */ if (i >= IXGBE_EEPROM_MAX_RETRY_SPI) { hw_dbg(hw, "SPI EEPROM Status error\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } return 0; @@ -1715,7 +1703,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) for (i = IXGBE_PCIE_ANALOG_PTR; i < IXGBE_FW_PTR; i++) { if (hw->eeprom.ops.read(hw, i, &pointer)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } /* If the pointer seems invalid */ @@ -1724,7 +1712,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) if (hw->eeprom.ops.read(hw, pointer, &length)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } if (length == 0xFFFF || length == 0) @@ -1733,7 +1721,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) for (j = pointer + 1; j <= pointer + length; j++) { if (hw->eeprom.ops.read(hw, j, &word)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } checksum += word; } @@ -1786,7 +1774,7 @@ s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw, * calculated checksum */ if (read_checksum != checksum) - status = IXGBE_ERR_EEPROM_CHECKSUM; + status = -EIO; /* If the user cares, return the calculated checksum */ if (checksum_val) @@ -1845,7 +1833,7 @@ s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq, /* Make sure we are using a valid rar index range */ if (index >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", index); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } /* setup VMDq pool selection before this RAR gets enabled */ @@ -1897,7 +1885,7 @@ s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index) /* Make sure we are using a valid rar index range */ if (index >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", index); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } /* @@ -2146,7 +2134,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) /* Validate the water mark configuration. */ if (!hw->fc.pause_time) - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; /* Low water mark of zero causes XOFF floods */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { @@ -2155,7 +2143,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) if (!hw->fc.low_water[i] || hw->fc.low_water[i] >= hw->fc.high_water[i]) { hw_dbg(hw, "Invalid water mark configuration\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } } } @@ -2212,7 +2200,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) break; default: hw_dbg(hw, "Flow control param set incorrectly\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } /* Set 802.3x based flow control settings. */ @@ -2269,7 +2257,7 @@ s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg, u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm) { if ((!(adv_reg)) || (!(lp_reg))) - return IXGBE_ERR_FC_NOT_NEGOTIATED; + return -EINVAL; if ((adv_reg & adv_sym) && (lp_reg & lp_sym)) { /* @@ -2321,7 +2309,7 @@ static s32 ixgbe_fc_autoneg_fiber(struct ixgbe_hw *hw) linkstat = IXGBE_READ_REG(hw, IXGBE_PCS1GLSTA); if ((!!(linkstat & IXGBE_PCS1GLSTA_AN_COMPLETE) == 0) || (!!(linkstat & IXGBE_PCS1GLSTA_AN_TIMED_OUT) == 1)) - return IXGBE_ERR_FC_NOT_NEGOTIATED; + return -EIO; pcs_anadv_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); pcs_lpab_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANLP); @@ -2353,12 +2341,12 @@ static s32 ixgbe_fc_autoneg_backplane(struct ixgbe_hw *hw) */ links = IXGBE_READ_REG(hw, IXGBE_LINKS); if ((links & IXGBE_LINKS_KX_AN_COMP) == 0) - return IXGBE_ERR_FC_NOT_NEGOTIATED; + return -EIO; if (hw->mac.type == ixgbe_mac_82599EB) { links2 = IXGBE_READ_REG(hw, IXGBE_LINKS2); if ((links2 & IXGBE_LINKS2_AN_SUPPORTED) == 0) - return IXGBE_ERR_FC_NOT_NEGOTIATED; + return -EIO; } /* * Read the 10g AN autoc and LP ability registers and resolve @@ -2407,8 +2395,8 @@ static s32 ixgbe_fc_autoneg_copper(struct ixgbe_hw *hw) **/ void ixgbe_fc_autoneg(struct ixgbe_hw *hw) { - s32 ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; ixgbe_link_speed speed; + s32 ret_val = -EIO; bool link_up; /* @@ -2510,7 +2498,7 @@ static u32 ixgbe_pcie_timeout_poll(struct ixgbe_hw *hw) * @hw: pointer to hardware structure * * Disables PCI-Express primary access and verifies there are no pending - * requests. IXGBE_ERR_PRIMARY_REQUESTS_PENDING is returned if primary disable + * requests. -EALREADY is returned if primary disable * bit hasn't caused the primary requests to be disabled, else 0 * is returned signifying primary requests disabled. **/ @@ -2575,7 +2563,7 @@ gio_disable_fail: } hw_dbg(hw, "PCIe transaction pending bit also did not clear.\n"); - return IXGBE_ERR_PRIMARY_REQUESTS_PENDING; + return -EALREADY; } /** @@ -2600,7 +2588,7 @@ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u32 mask) * SW_FW_SYNC bits (not just NVM) */ if (ixgbe_get_eeprom_semaphore(hw)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; gssr = IXGBE_READ_REG(hw, IXGBE_GSSR); if (!(gssr & (fwmask | swmask))) { @@ -2620,7 +2608,7 @@ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u32 mask) ixgbe_release_swfw_sync(hw, gssr & (fwmask | swmask)); usleep_range(5000, 10000); - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } /** @@ -2757,7 +2745,7 @@ s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index) s32 ret_val; if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; /* * Link must be up to auto-blink the LEDs; @@ -2803,7 +2791,7 @@ s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index) s32 ret_val; if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg); if (ret_val) @@ -2963,7 +2951,7 @@ s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) /* Make sure we are using a valid rar index range */ if (rar >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", rar); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } mpsar_lo = IXGBE_READ_REG(hw, IXGBE_MPSAR_LO(rar)); @@ -3014,7 +3002,7 @@ s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) /* Make sure we are using a valid rar index range */ if (rar >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", rar); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } if (vmdq < 32) { @@ -3091,7 +3079,7 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan, bool vlvf_bypass) * will simply bypass the VLVF if there are no entries present in the * VLVF that contain our VLAN */ - first_empty_slot = vlvf_bypass ? IXGBE_ERR_NO_SPACE : 0; + first_empty_slot = vlvf_bypass ? -ENOSPC : 0; /* add VLAN enable bit for comparison */ vlan |= IXGBE_VLVF_VIEN; @@ -3115,7 +3103,7 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan, bool vlvf_bypass) if (!first_empty_slot) hw_dbg(hw, "No space in VLVF.\n"); - return first_empty_slot ? : IXGBE_ERR_NO_SPACE; + return first_empty_slot ? : -ENOSPC; } /** @@ -3135,7 +3123,7 @@ s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind, s32 vlvf_index; if ((vlan > 4095) || (vind > 63)) - return IXGBE_ERR_PARAM; + return -EINVAL; /* * this is a 2 part operation - first the VFTA, then the @@ -3596,7 +3584,8 @@ u8 ixgbe_calculate_checksum(u8 *buffer, u32 length) * * Communicates with the manageability block. On success return 0 * else returns semaphore error when encountering an error acquiring - * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + * semaphore, -EINVAL when incorrect parameters passed or -EIO when + * command fails. * * This function assumes that the IXGBE_GSSR_SW_MNG_SM semaphore is held * by the caller. @@ -3609,7 +3598,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length); - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EINVAL; } /* Set bit 9 of FWSTS clearing FW reset indication */ @@ -3620,13 +3609,13 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, hicr = IXGBE_READ_REG(hw, IXGBE_HICR); if (!(hicr & IXGBE_HICR_EN)) { hw_dbg(hw, "IXGBE_HOST_EN bit disabled.\n"); - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EIO; } /* Calculate length in DWORDs. We must be DWORD aligned */ if (length % sizeof(u32)) { hw_dbg(hw, "Buffer length failure, not aligned to dword"); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } dword_len = length >> 2; @@ -3651,7 +3640,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, /* Check command successful completion. */ if ((timeout && i == timeout) || !(IXGBE_READ_REG(hw, IXGBE_HICR) & IXGBE_HICR_SV)) - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EIO; return 0; } @@ -3671,7 +3660,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, * in these cases. * * Communicates with the manageability block. On success return 0 - * else return IXGBE_ERR_HOST_INTERFACE_COMMAND. + * else return -EIO or -EINVAL. **/ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, u32 length, u32 timeout, @@ -3686,7 +3675,7 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length); - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EINVAL; } /* Take management host interface semaphore */ status = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_SW_MNG_SM); @@ -3716,7 +3705,7 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, if (length < round_up(buf_len, 4) + hdr_size) { hw_dbg(hw, "Buffer not large enough for reply message.\n"); - status = IXGBE_ERR_HOST_INTERFACE_COMMAND; + status = -EIO; goto rel_out; } @@ -3747,8 +3736,8 @@ rel_out: * * Sends driver version number to firmware through the manageability * block. On success return 0 - * else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring - * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + * else returns -EBUSY when encountering an error acquiring + * semaphore or -EIO when command fails. **/ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, u8 build, u8 sub, __always_unused u16 len, @@ -3784,7 +3773,7 @@ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, FW_CEM_RESP_STATUS_SUCCESS) ret_val = 0; else - ret_val = IXGBE_ERR_HOST_INTERFACE_COMMAND; + ret_val = -EIO; break; } @@ -3882,14 +3871,14 @@ static s32 ixgbe_get_ets_data(struct ixgbe_hw *hw, u16 *ets_cfg, return status; if ((*ets_offset == 0x0000) || (*ets_offset == 0xFFFF)) - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; status = hw->eeprom.ops.read(hw, *ets_offset, ets_cfg); if (status) return status; if ((*ets_cfg & IXGBE_ETS_TYPE_MASK) != IXGBE_ETS_TYPE_EMC_SHIFTED) - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; return 0; } @@ -3912,7 +3901,7 @@ s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw) /* Only support thermal sensors attached to physical port 0 */ if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset); if (status) @@ -3972,7 +3961,7 @@ s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw) /* Only support thermal sensors attached to physical port 0 */ if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset); if (status) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 0051aa676e19..f8e65e18284e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3339,7 +3339,7 @@ static int ixgbe_get_module_eeprom(struct net_device *dev, { struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_hw *hw = &adapter->hw; - s32 status = IXGBE_ERR_PHY_ADDR_INVALID; + s32 status = -EFAULT; u8 databyte = 0xFF; int i = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 9e0e13638c46..6dc554e810a1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2764,7 +2764,6 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; u32 eicr = adapter->interrupt_event; - s32 rc; if (test_bit(__IXGBE_DOWN, &adapter->state)) return; @@ -2798,14 +2797,13 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) } /* Check if this is not due to overtemp */ - if (hw->phy.ops.check_overtemp(hw) != IXGBE_ERR_OVERTEMP) + if (!hw->phy.ops.check_overtemp(hw)) return; break; case IXGBE_DEV_ID_X550EM_A_1G_T: case IXGBE_DEV_ID_X550EM_A_1G_T_L: - rc = hw->phy.ops.check_overtemp(hw); - if (rc != IXGBE_ERR_OVERTEMP) + if (!hw->phy.ops.check_overtemp(hw)) return; break; default: @@ -5520,7 +5518,7 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) { u32 speed; bool autoneg, link_up = false; - int ret = IXGBE_ERR_LINK_SETUP; + int ret = -EIO; if (hw->mac.ops.check_link) ret = hw->mac.ops.check_link(hw, &speed, &link_up, false); @@ -5991,13 +5989,13 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) err = hw->mac.ops.init_hw(hw); switch (err) { case 0: - case IXGBE_ERR_SFP_NOT_PRESENT: - case IXGBE_ERR_SFP_NOT_SUPPORTED: + case -ENOENT: + case -EOPNOTSUPP: break; - case IXGBE_ERR_PRIMARY_REQUESTS_PENDING: + case -EALREADY: e_dev_err("primary disable timed out\n"); break; - case IXGBE_ERR_EEPROM_VERSION: + case -EACCES: /* We are running on a pre-production device, log a warning */ e_dev_warn("This device is a pre-production adapter/LOM. " "Please be aware there may be issues associated with " @@ -7837,10 +7835,10 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) adapter->sfp_poll_time = jiffies + IXGBE_SFP_POLL_JIFFIES - 1; err = hw->phy.ops.identify_sfp(hw); - if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (err == -EOPNOTSUPP) goto sfp_out; - if (err == IXGBE_ERR_SFP_NOT_PRESENT) { + if (err == -ENOENT) { /* If no cable is present, then we need to reset * the next time we find a good cable. */ adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET; @@ -7866,7 +7864,7 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) else err = hw->mac.ops.setup_sfp(hw); - if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (err == -EOPNOTSUPP) goto sfp_out; adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG; @@ -7875,8 +7873,8 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) sfp_out: clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); - if ((err == IXGBE_ERR_SFP_NOT_SUPPORTED) && - (adapter->netdev->reg_state == NETREG_REGISTERED)) { + if (err == -EOPNOTSUPP && + adapter->netdev->reg_state == NETREG_REGISTERED) { e_dev_err("failed to initialize because an unsupported " "SFP+ module type was detected.\n"); e_dev_err("Reload the driver after installing a " @@ -7946,7 +7944,7 @@ static void ixgbe_service_timer(struct timer_list *t) static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 status; + bool overtemp; if (!(adapter->flags2 & IXGBE_FLAG2_PHY_INTERRUPT)) return; @@ -7956,11 +7954,9 @@ static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter) if (!hw->phy.ops.handle_lasi) return; - status = hw->phy.ops.handle_lasi(&adapter->hw); - if (status != IXGBE_ERR_OVERTEMP) - return; - - e_crit(drv, "%s\n", ixgbe_overheat_msg); + hw->phy.ops.handle_lasi(&adapter->hw, &overtemp); + if (overtemp) + e_crit(drv, "%s\n", ixgbe_overheat_msg); } static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) @@ -10943,9 +10939,9 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = hw->mac.ops.reset_hw(hw); hw->phy.reset_if_overtemp = false; ixgbe_set_eee_capable(adapter); - if (err == IXGBE_ERR_SFP_NOT_PRESENT) { + if (err == -ENOENT) { err = 0; - } else if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { + } else if (err == -EOPNOTSUPP) { e_dev_err("failed to load because an unsupported SFP+ or QSFP module type was detected.\n"); e_dev_err("Reload the driver after installing a supported module.\n"); goto err_sw_init; @@ -11161,7 +11157,7 @@ skip_sriov: /* reset the hardware with the new settings */ err = hw->mac.ops.start_hw(hw); - if (err == IXGBE_ERR_EEPROM_VERSION) { + if (err == -EACCES) { /* We are running on a pre-production device, log a warning */ e_dev_warn("This device is a pre-production adapter/LOM. " "Please be aware there may be issues associated " diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c index 5679293e53f7..fe7ef5773369 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c @@ -24,7 +24,7 @@ s32 ixgbe_read_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id) size = mbx->size; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; return mbx->ops->read(hw, msg, size, mbx_id); } @@ -43,10 +43,10 @@ s32 ixgbe_write_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id) struct ixgbe_mbx_info *mbx = &hw->mbx; if (size > mbx->size) - return IXGBE_ERR_MBX; + return -EINVAL; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; return mbx->ops->write(hw, msg, size, mbx_id); } @@ -63,7 +63,7 @@ s32 ixgbe_check_for_msg(struct ixgbe_hw *hw, u16 mbx_id) struct ixgbe_mbx_info *mbx = &hw->mbx; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; return mbx->ops->check_for_msg(hw, mbx_id); } @@ -80,7 +80,7 @@ s32 ixgbe_check_for_ack(struct ixgbe_hw *hw, u16 mbx_id) struct ixgbe_mbx_info *mbx = &hw->mbx; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; return mbx->ops->check_for_ack(hw, mbx_id); } @@ -97,7 +97,7 @@ s32 ixgbe_check_for_rst(struct ixgbe_hw *hw, u16 mbx_id) struct ixgbe_mbx_info *mbx = &hw->mbx; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; return mbx->ops->check_for_rst(hw, mbx_id); } @@ -115,12 +115,12 @@ static s32 ixgbe_poll_for_msg(struct ixgbe_hw *hw, u16 mbx_id) int countdown = mbx->timeout; if (!countdown || !mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; while (mbx->ops->check_for_msg(hw, mbx_id)) { countdown--; if (!countdown) - return IXGBE_ERR_MBX; + return -EIO; udelay(mbx->usec_delay); } @@ -140,12 +140,12 @@ static s32 ixgbe_poll_for_ack(struct ixgbe_hw *hw, u16 mbx_id) int countdown = mbx->timeout; if (!countdown || !mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; while (mbx->ops->check_for_ack(hw, mbx_id)) { countdown--; if (!countdown) - return IXGBE_ERR_MBX; + return -EIO; udelay(mbx->usec_delay); } @@ -169,7 +169,7 @@ static s32 ixgbe_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, s32 ret_val; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; ret_val = ixgbe_poll_for_msg(hw, mbx_id); if (ret_val) @@ -197,7 +197,7 @@ static s32 ixgbe_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, /* exit if either we can't write or there isn't a defined timeout */ if (!mbx->ops || !mbx->timeout) - return IXGBE_ERR_MBX; + return -EIO; /* send msg */ ret_val = mbx->ops->write(hw, msg, size, mbx_id); @@ -217,7 +217,7 @@ static s32 ixgbe_check_for_bit_pf(struct ixgbe_hw *hw, u32 mask, s32 index) return 0; } - return IXGBE_ERR_MBX; + return -EIO; } /** @@ -238,7 +238,7 @@ static s32 ixgbe_check_for_msg_pf(struct ixgbe_hw *hw, u16 vf_number) return 0; } - return IXGBE_ERR_MBX; + return -EIO; } /** @@ -259,7 +259,7 @@ static s32 ixgbe_check_for_ack_pf(struct ixgbe_hw *hw, u16 vf_number) return 0; } - return IXGBE_ERR_MBX; + return -EIO; } /** @@ -295,7 +295,7 @@ static s32 ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number) return 0; } - return IXGBE_ERR_MBX; + return -EIO; } /** @@ -317,7 +317,7 @@ static s32 ixgbe_obtain_mbx_lock_pf(struct ixgbe_hw *hw, u16 vf_number) if (p2v_mailbox & IXGBE_PFMAILBOX_PFU) return 0; - return IXGBE_ERR_MBX; + return -EIO; } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h index 8f4316b19278..6434c190e7a4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h @@ -7,7 +7,6 @@ #include "ixgbe_type.h" #define IXGBE_VFMAILBOX_SIZE 16 /* 16 32 bit words - 64 bytes */ -#define IXGBE_ERR_MBX -100 #define IXGBE_VFMAILBOX 0x002FC #define IXGBE_VFMBMEM 0x00200 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 123dca9ce468..305afb82388b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -102,7 +102,7 @@ s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, csum = ~csum; do { if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; ixgbe_i2c_start(hw); /* Device Address and write indication */ if (ixgbe_out_i2c_byte_ack(hw, addr)) @@ -150,7 +150,7 @@ fail: hw_dbg(hw, "I2C byte read combined error.\n"); } while (retry < max_retry); - return IXGBE_ERR_I2C; + return -EIO; } /** @@ -179,7 +179,7 @@ s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, csum = ~csum; do { if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; ixgbe_i2c_start(hw); /* Device Address and write indication */ if (ixgbe_out_i2c_byte_ack(hw, addr)) @@ -215,7 +215,7 @@ fail: hw_dbg(hw, "I2C byte write combined error.\n"); } while (retry < max_retry); - return IXGBE_ERR_I2C; + return -EIO; } /** @@ -262,8 +262,8 @@ static bool ixgbe_probe_phy(struct ixgbe_hw *hw, u16 phy_addr) **/ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) { + u32 status = -EFAULT; u32 phy_addr; - u32 status = IXGBE_ERR_PHY_ADDR_INVALID; if (!hw->phy.phy_semaphore_mask) { if (hw->bus.lan_id) @@ -282,7 +282,7 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) if (ixgbe_probe_phy(hw, phy_addr)) return 0; else - return IXGBE_ERR_PHY_ADDR_INVALID; + return -EFAULT; } for (phy_addr = 0; phy_addr < IXGBE_MAX_PHY_ADDR; phy_addr++) { @@ -408,8 +408,7 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) return status; /* Don't reset PHY if it's shut down due to overtemp. */ - if (!hw->phy.reset_if_overtemp && - (IXGBE_ERR_OVERTEMP == hw->phy.ops.check_overtemp(hw))) + if (!hw->phy.reset_if_overtemp && hw->phy.ops.check_overtemp(hw)) return 0; /* Blocked by MNG FW so bail */ @@ -457,7 +456,7 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) if (ctrl & MDIO_CTRL1_RESET) { hw_dbg(hw, "PHY reset polling failed to complete.\n"); - return IXGBE_ERR_RESET_FAILED; + return -EIO; } return 0; @@ -500,7 +499,7 @@ s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { hw_dbg(hw, "PHY address command did not complete.\n"); - return IXGBE_ERR_PHY; + return -EIO; } /* Address cycle complete, setup and write the read @@ -527,7 +526,7 @@ s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { hw_dbg(hw, "PHY read command didn't complete\n"); - return IXGBE_ERR_PHY; + return -EIO; } /* Read operation is complete. Get the data @@ -559,7 +558,7 @@ s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, phy_data); hw->mac.ops.release_swfw_sync(hw, gssr); } else { - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } return status; @@ -604,7 +603,7 @@ s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { hw_dbg(hw, "PHY address cmd didn't complete\n"); - return IXGBE_ERR_PHY; + return -EIO; } /* @@ -632,7 +631,7 @@ s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { hw_dbg(hw, "PHY write cmd didn't complete\n"); - return IXGBE_ERR_PHY; + return -EIO; } return 0; @@ -657,7 +656,7 @@ s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, phy_data); hw->mac.ops.release_swfw_sync(hw, gssr); } else { - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } return status; @@ -1303,7 +1302,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) if ((phy_data & MDIO_CTRL1_RESET) != 0) { hw_dbg(hw, "PHY reset did not complete.\n"); - return IXGBE_ERR_PHY; + return -EIO; } /* Get init offsets */ @@ -1360,12 +1359,12 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) hw_dbg(hw, "SOL\n"); } else { hw_dbg(hw, "Bad control value\n"); - return IXGBE_ERR_PHY; + return -EIO; } break; default: hw_dbg(hw, "Bad control type\n"); - return IXGBE_ERR_PHY; + return -EIO; } } @@ -1373,7 +1372,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) err_eeprom: hw_err(hw, "eeprom read at offset %d failed\n", data_offset); - return IXGBE_ERR_PHY; + return -EIO; } /** @@ -1391,10 +1390,10 @@ s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw) return ixgbe_identify_qsfp_module_generic(hw); default: hw->phy.sfp_type = ixgbe_sfp_type_not_present; - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } /** @@ -1419,7 +1418,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber) { hw->phy.sfp_type = ixgbe_sfp_type_not_present; - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } /* LAN ID is needed for sfp_type determination */ @@ -1434,7 +1433,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) if (identifier != IXGBE_SFF_IDENTIFIER_SFP) { hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_1GBE_COMP_CODES, @@ -1625,7 +1624,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) { hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } /* Anything else 82598-based is supported */ @@ -1649,7 +1648,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) } hw_dbg(hw, "SFP+ module not supported\n"); hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } return 0; @@ -1659,7 +1658,7 @@ err_read_i2c_eeprom: hw->phy.id = 0; hw->phy.type = ixgbe_phy_unknown; } - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } /** @@ -1686,7 +1685,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber_qsfp) { hw->phy.sfp_type = ixgbe_sfp_type_not_present; - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } /* LAN ID is needed for sfp_type determination */ @@ -1700,7 +1699,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) if (identifier != IXGBE_SFF_IDENTIFIER_QSFP_PLUS) { hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } hw->phy.id = identifier; @@ -1768,7 +1767,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) } else { /* unsupported module type */ hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } } @@ -1828,7 +1827,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) } hw_dbg(hw, "QSFP module not supported\n"); hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } return 0; } @@ -1839,7 +1838,7 @@ err_read_i2c_eeprom: hw->phy.id = 0; hw->phy.type = ixgbe_phy_unknown; - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } /** @@ -1859,14 +1858,14 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, u16 sfp_type = hw->phy.sfp_type; if (hw->phy.sfp_type == ixgbe_sfp_type_unknown) - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; if (hw->phy.sfp_type == ixgbe_sfp_type_not_present) - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; if ((hw->device_id == IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM) && (hw->phy.sfp_type == ixgbe_sfp_type_da_cu)) - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; /* * Limiting active cables and 1G Phys must be initialized as @@ -1887,11 +1886,11 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, if (hw->eeprom.ops.read(hw, IXGBE_PHY_INIT_OFFSET_NL, list_offset)) { hw_err(hw, "eeprom read at %d failed\n", IXGBE_PHY_INIT_OFFSET_NL); - return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT; + return -EIO; } if ((!*list_offset) || (*list_offset == 0xFFFF)) - return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT; + return -EIO; /* Shift offset to first ID word */ (*list_offset)++; @@ -1910,7 +1909,7 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, goto err_phy; if ((!*data_offset) || (*data_offset == 0xFFFF)) { hw_dbg(hw, "SFP+ module not supported\n"); - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } else { break; } @@ -1923,14 +1922,14 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, if (sfp_id == IXGBE_PHY_INIT_END_NL) { hw_dbg(hw, "No matching SFP+ module found\n"); - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } return 0; err_phy: hw_err(hw, "eeprom read at offset %d failed\n", *list_offset); - return IXGBE_ERR_PHY; + return -EIO; } /** @@ -2025,7 +2024,7 @@ static s32 ixgbe_read_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, do { if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; ixgbe_i2c_start(hw); @@ -2141,7 +2140,7 @@ static s32 ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, u32 swfw_mask = hw->phy.phy_semaphore_mask; if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; do { ixgbe_i2c_start(hw); @@ -2383,7 +2382,7 @@ static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw) if (ack == 1) { hw_dbg(hw, "I2C ack was not received.\n"); - status = IXGBE_ERR_I2C; + status = -EIO; } ixgbe_lower_i2c_clk(hw, &i2cctl); @@ -2455,7 +2454,7 @@ static s32 ixgbe_clock_out_i2c_bit(struct ixgbe_hw *hw, bool data) udelay(IXGBE_I2C_T_LOW); } else { hw_dbg(hw, "I2C data was not set to %X\n", data); - return IXGBE_ERR_I2C; + return -EIO; } return 0; @@ -2551,7 +2550,7 @@ static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data) *i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); if (data != ixgbe_get_i2c_data(hw, i2cctl)) { hw_dbg(hw, "Error - I2C data was not set to %X.\n", data); - return IXGBE_ERR_I2C; + return -EIO; } return 0; @@ -2621,22 +2620,24 @@ static void ixgbe_i2c_bus_clear(struct ixgbe_hw *hw) * @hw: pointer to hardware structure * * Checks if the LASI temp alarm status was triggered due to overtemp + * + * Return true when an overtemp event detected, otherwise false. **/ -s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw) +bool ixgbe_tn_check_overtemp(struct ixgbe_hw *hw) { u16 phy_data = 0; + u32 status; if (hw->device_id != IXGBE_DEV_ID_82599_T3_LOM) - return 0; + return false; /* Check that the LASI temp alarm status was triggered */ - hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG, - MDIO_MMD_PMAPMD, &phy_data); - - if (!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM)) - return 0; + status = hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG, + MDIO_MMD_PMAPMD, &phy_data); + if (status) + return false; - return IXGBE_ERR_OVERTEMP; + return !!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM); } /** ixgbe_set_copper_phy_power - Control power for copper phy diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index 6544c4539c0d..ef72729d7c93 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -155,7 +155,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw); s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, u16 *list_offset, u16 *data_offset); -s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw); +bool ixgbe_tn_check_overtemp(struct ixgbe_hw *hw); s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, u8 dev_addr, u8 *data); s32 ixgbe_read_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index ea88ac04ab9a..198ab9d97618 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -1329,7 +1329,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) break; default: e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]); - retval = IXGBE_ERR_MBX; + retval = -EIO; break; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 2b00db92b08f..61b9774b3d31 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -3509,10 +3509,10 @@ struct ixgbe_phy_operations { s32 (*read_i2c_sff8472)(struct ixgbe_hw *, u8 , u8 *); s32 (*read_i2c_eeprom)(struct ixgbe_hw *, u8 , u8 *); s32 (*write_i2c_eeprom)(struct ixgbe_hw *, u8, u8); - s32 (*check_overtemp)(struct ixgbe_hw *); + bool (*check_overtemp)(struct ixgbe_hw *); s32 (*set_phy_power)(struct ixgbe_hw *, bool on); s32 (*enter_lplu)(struct ixgbe_hw *); - s32 (*handle_lasi)(struct ixgbe_hw *hw); + s32 (*handle_lasi)(struct ixgbe_hw *hw, bool *); s32 (*read_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr, u8 *value); s32 (*write_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr, @@ -3665,45 +3665,6 @@ struct ixgbe_info { const u32 *mvals; }; - -/* Error Codes */ -#define IXGBE_ERR_EEPROM -1 -#define IXGBE_ERR_EEPROM_CHECKSUM -2 -#define IXGBE_ERR_PHY -3 -#define IXGBE_ERR_CONFIG -4 -#define IXGBE_ERR_PARAM -5 -#define IXGBE_ERR_MAC_TYPE -6 -#define IXGBE_ERR_UNKNOWN_PHY -7 -#define IXGBE_ERR_LINK_SETUP -8 -#define IXGBE_ERR_ADAPTER_STOPPED -9 -#define IXGBE_ERR_INVALID_MAC_ADDR -10 -#define IXGBE_ERR_DEVICE_NOT_SUPPORTED -11 -#define IXGBE_ERR_PRIMARY_REQUESTS_PENDING -12 -#define IXGBE_ERR_INVALID_LINK_SETTINGS -13 -#define IXGBE_ERR_AUTONEG_NOT_COMPLETE -14 -#define IXGBE_ERR_RESET_FAILED -15 -#define IXGBE_ERR_SWFW_SYNC -16 -#define IXGBE_ERR_PHY_ADDR_INVALID -17 -#define IXGBE_ERR_I2C -18 -#define IXGBE_ERR_SFP_NOT_SUPPORTED -19 -#define IXGBE_ERR_SFP_NOT_PRESENT -20 -#define IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT -21 -#define IXGBE_ERR_NO_SAN_ADDR_PTR -22 -#define IXGBE_ERR_FDIR_REINIT_FAILED -23 -#define IXGBE_ERR_EEPROM_VERSION -24 -#define IXGBE_ERR_NO_SPACE -25 -#define IXGBE_ERR_OVERTEMP -26 -#define IXGBE_ERR_FC_NOT_NEGOTIATED -27 -#define IXGBE_ERR_FC_NOT_SUPPORTED -28 -#define IXGBE_ERR_SFP_SETUP_NOT_COMPLETE -30 -#define IXGBE_ERR_PBA_SECTION -31 -#define IXGBE_ERR_INVALID_ARGUMENT -32 -#define IXGBE_ERR_HOST_INTERFACE_COMMAND -33 -#define IXGBE_ERR_FDIR_CMD_INCOMPLETE -38 -#define IXGBE_ERR_FW_RESP_INVALID -39 -#define IXGBE_ERR_TOKEN_RETRY -40 -#define IXGBE_NOT_IMPLEMENTED 0x7FFFFFFF - #define IXGBE_FUSES0_GROUP(_i) (0x11158 + ((_i) * 4)) #define IXGBE_FUSES0_300MHZ BIT(5) #define IXGBE_FUSES0_REV_MASK (3u << 6) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index d5cfb51ff648..15325c549d9b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -84,7 +84,7 @@ mac_reset_top: status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); if (status) { hw_dbg(hw, "semaphore failed with %d", status); - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } ctrl = IXGBE_CTRL_RST; @@ -103,7 +103,7 @@ mac_reset_top: } if (ctrl & IXGBE_CTRL_RST_MASK) { - status = IXGBE_ERR_RESET_FAILED; + status = -EIO; hw_dbg(hw, "Reset polling failed to complete.\n"); } msleep(100); @@ -220,7 +220,7 @@ static s32 ixgbe_read_eerd_X540(struct ixgbe_hw *hw, u16 offset, u16 *data) s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = ixgbe_read_eerd_generic(hw, offset, data); @@ -243,7 +243,7 @@ static s32 ixgbe_read_eerd_buffer_X540(struct ixgbe_hw *hw, s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = ixgbe_read_eerd_buffer_generic(hw, offset, words, data); @@ -264,7 +264,7 @@ static s32 ixgbe_write_eewr_X540(struct ixgbe_hw *hw, u16 offset, u16 data) s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = ixgbe_write_eewr_generic(hw, offset, data); @@ -287,7 +287,7 @@ static s32 ixgbe_write_eewr_buffer_X540(struct ixgbe_hw *hw, s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = ixgbe_write_eewr_buffer_generic(hw, offset, words, data); @@ -324,7 +324,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw) for (i = 0; i < checksum_last_word; i++) { if (ixgbe_read_eerd_generic(hw, i, &word)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } checksum += word; } @@ -349,7 +349,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw) if (ixgbe_read_eerd_generic(hw, pointer, &length)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } /* Skip pointer section if length is invalid. */ @@ -360,7 +360,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw) for (j = pointer + 1; j <= pointer + length; j++) { if (ixgbe_read_eerd_generic(hw, j, &word)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } checksum += word; } @@ -397,7 +397,7 @@ static s32 ixgbe_validate_eeprom_checksum_X540(struct ixgbe_hw *hw, } if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = hw->eeprom.ops.calc_checksum(hw); if (status < 0) @@ -418,7 +418,7 @@ static s32 ixgbe_validate_eeprom_checksum_X540(struct ixgbe_hw *hw, */ if (read_checksum != checksum) { hw_dbg(hw, "Invalid EEPROM checksum"); - status = IXGBE_ERR_EEPROM_CHECKSUM; + status = -EIO; } /* If the user cares, return the calculated checksum */ @@ -455,7 +455,7 @@ static s32 ixgbe_update_eeprom_checksum_X540(struct ixgbe_hw *hw) } if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = hw->eeprom.ops.calc_checksum(hw); if (status < 0) @@ -490,7 +490,7 @@ static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw) s32 status; status = ixgbe_poll_flash_update_done_X540(hw); - if (status == IXGBE_ERR_EEPROM) { + if (status == -EIO) { hw_dbg(hw, "Flash update time out\n"); return status; } @@ -540,7 +540,7 @@ static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw) return 0; udelay(5); } - return IXGBE_ERR_EEPROM; + return -EIO; } /** @@ -575,7 +575,7 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) * SW_FW_SYNC bits (not just NVM) */ if (ixgbe_get_swfw_sync_semaphore(hw)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); if (!(swfw_sync & (fwmask | swmask | hwmask))) { @@ -599,7 +599,7 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) * bits in the SW_FW_SYNC register. */ if (ixgbe_get_swfw_sync_semaphore(hw)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); if (swfw_sync & (fwmask | hwmask)) { swfw_sync |= swmask; @@ -622,11 +622,11 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) rmask |= IXGBE_GSSR_I2C_MASK; ixgbe_release_swfw_sync_X540(hw, rmask); ixgbe_release_swfw_sync_semaphore(hw); - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } ixgbe_release_swfw_sync_semaphore(hw); - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } /** @@ -680,7 +680,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw) if (i == timeout) { hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } /* Now get the semaphore between SW/FW through the REGSMP bit */ @@ -697,7 +697,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw) */ hw_dbg(hw, "REGSMP Software NVM semaphore not granted\n"); ixgbe_release_swfw_sync_semaphore(hw); - return IXGBE_ERR_EEPROM; + return -EIO; } /** @@ -768,7 +768,7 @@ s32 ixgbe_blink_led_start_X540(struct ixgbe_hw *hw, u32 index) bool link_up; if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; /* Link should be up in order for the blink bit in the LED control * register to work. Force link and speed in the MAC if link is down. @@ -804,7 +804,7 @@ s32 ixgbe_blink_led_stop_X540(struct ixgbe_hw *hw, u32 index) u32 ledctl_reg; if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; /* Restore the LED to its default value. */ ledctl_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index aa4bf6c9a2f7..cdc912bba808 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -206,13 +206,13 @@ static s32 ixgbe_reset_cs4227(struct ixgbe_hw *hw) } if (retry == IXGBE_CS4227_RETRIES) { hw_err(hw, "CS4227 reset did not complete\n"); - return IXGBE_ERR_PHY; + return -EIO; } status = ixgbe_read_cs4227(hw, IXGBE_CS4227_EEPROM_STATUS, &value); if (status || !(value & IXGBE_CS4227_EEPROM_LOAD_OK)) { hw_err(hw, "CS4227 EEPROM did not load successfully\n"); - return IXGBE_ERR_PHY; + return -EIO; } return 0; @@ -350,13 +350,13 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw) static s32 ixgbe_read_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, u16 *phy_data) { - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; } static s32 ixgbe_write_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, u16 phy_data) { - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; } /** @@ -463,7 +463,7 @@ s32 ixgbe_fw_phy_activity(struct ixgbe_hw *hw, u16 activity, --retries; } while (retries > 0); - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EIO; } static const struct { @@ -511,7 +511,7 @@ static s32 ixgbe_get_phy_id_fw(struct ixgbe_hw *hw) hw->phy.id |= phy_id_lo & IXGBE_PHY_REVISION_MASK; hw->phy.revision = phy_id_lo & ~IXGBE_PHY_REVISION_MASK; if (!hw->phy.id || hw->phy.id == IXGBE_PHY_REVISION_MASK) - return IXGBE_ERR_PHY_ADDR_INVALID; + return -EFAULT; hw->phy.autoneg_advertised = hw->phy.speeds_supported; hw->phy.eee_speeds_supported = IXGBE_LINK_SPEED_100_FULL | @@ -568,7 +568,7 @@ static s32 ixgbe_setup_fw_link(struct ixgbe_hw *hw) if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { hw_err(hw, "rx_pause not valid in strict IEEE mode\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } switch (hw->fc.requested_mode) { @@ -600,8 +600,10 @@ static s32 ixgbe_setup_fw_link(struct ixgbe_hw *hw) rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_SETUP_LINK, &setup); if (rc) return rc; + if (setup[0] == FW_PHY_ACT_SETUP_LINK_RSP_DOWN) - return IXGBE_ERR_OVERTEMP; + return -EIO; + return 0; } @@ -675,7 +677,7 @@ static s32 ixgbe_iosf_wait(struct ixgbe_hw *hw, u32 *ctrl) *ctrl = command; if (i == IXGBE_MDIO_COMMAND_TIMEOUT) { hw_dbg(hw, "IOSF wait timed out\n"); - return IXGBE_ERR_PHY; + return -EIO; } return 0; @@ -715,7 +717,8 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; hw_dbg(hw, "Failed to read, error %x\n", error); - return IXGBE_ERR_PHY; + ret = -EIO; + goto out; } if (!ret) @@ -750,9 +753,9 @@ static s32 ixgbe_get_phy_token(struct ixgbe_hw *hw) if (token_cmd.hdr.cmd_or_resp.ret_status == FW_PHY_TOKEN_OK) return 0; if (token_cmd.hdr.cmd_or_resp.ret_status != FW_PHY_TOKEN_RETRY) - return IXGBE_ERR_FW_RESP_INVALID; + return -EIO; - return IXGBE_ERR_TOKEN_RETRY; + return -EAGAIN; } /** @@ -778,7 +781,7 @@ static s32 ixgbe_put_phy_token(struct ixgbe_hw *hw) return status; if (token_cmd.hdr.cmd_or_resp.ret_status == FW_PHY_TOKEN_OK) return 0; - return IXGBE_ERR_FW_RESP_INVALID; + return -EIO; } /** @@ -942,7 +945,7 @@ static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr, local_buffer = buf; } else { if (buffer_size < ptr) - return IXGBE_ERR_PARAM; + return -EINVAL; local_buffer = &buffer[ptr]; } @@ -960,7 +963,7 @@ static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr, } if (buffer && ((u32)start + (u32)length > buffer_size)) - return IXGBE_ERR_PARAM; + return -EINVAL; for (i = start; length; i++, length--) { if (i == bufsz && !buffer) { @@ -1012,7 +1015,7 @@ static s32 ixgbe_calc_checksum_X550(struct ixgbe_hw *hw, u16 *buffer, local_buffer = eeprom_ptrs; } else { if (buffer_size < IXGBE_EEPROM_LAST_WORD) - return IXGBE_ERR_PARAM; + return -EINVAL; local_buffer = buffer; } @@ -1148,7 +1151,7 @@ static s32 ixgbe_validate_eeprom_checksum_X550(struct ixgbe_hw *hw, * calculated checksum */ if (read_checksum != checksum) { - status = IXGBE_ERR_EEPROM_CHECKSUM; + status = -EIO; hw_dbg(hw, "Invalid EEPROM checksum"); } @@ -1203,7 +1206,7 @@ static s32 ixgbe_write_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 data) hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); } else { hw_dbg(hw, "write ee hostif failed to get semaphore"); - status = IXGBE_ERR_SWFW_SYNC; + status = -EBUSY; } return status; @@ -1415,7 +1418,7 @@ static s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; hw_dbg(hw, "Failed to write, error %x\n", error); - return IXGBE_ERR_PHY; + return -EIO; } out: @@ -1558,7 +1561,7 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) /* iXFI is only supported with X552 */ if (mac->type != ixgbe_mac_X550EM_x) - return IXGBE_ERR_LINK_SETUP; + return -EIO; /* Disable AN and force speed to 10G Serial. */ status = ixgbe_read_iosf_sb_reg_x550(hw, @@ -1580,7 +1583,7 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) break; default: /* Other link speeds are not supported by internal KR PHY. */ - return IXGBE_ERR_LINK_SETUP; + return -EINVAL; } status = ixgbe_write_iosf_sb_reg_x550(hw, @@ -1611,7 +1614,7 @@ static s32 ixgbe_supported_sfp_modules_X550em(struct ixgbe_hw *hw, bool *linear) { switch (hw->phy.sfp_type) { case ixgbe_sfp_type_not_present: - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; case ixgbe_sfp_type_da_cu_core0: case ixgbe_sfp_type_da_cu_core1: *linear = true; @@ -1630,7 +1633,7 @@ static s32 ixgbe_supported_sfp_modules_X550em(struct ixgbe_hw *hw, bool *linear) case ixgbe_sfp_type_1g_cu_core0: case ixgbe_sfp_type_1g_cu_core1: default: - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } return 0; @@ -1660,7 +1663,7 @@ ixgbe_setup_mac_link_sfp_x550em(struct ixgbe_hw *hw, * there is no reason to configure CS4227 and SFP not present error is * not accepted in the setup MAC link flow. */ - if (status == IXGBE_ERR_SFP_NOT_PRESENT) + if (status == -ENOENT) return 0; if (status) @@ -1718,7 +1721,7 @@ static s32 ixgbe_setup_sfi_x550a(struct ixgbe_hw *hw, ixgbe_link_speed *speed) break; default: /* Other link speeds are not supported by internal PHY. */ - return IXGBE_ERR_LINK_SETUP; + return -EINVAL; } (void)mac->ops.write_iosf_sb_reg(hw, @@ -1803,7 +1806,7 @@ ixgbe_setup_mac_link_sfp_n(struct ixgbe_hw *hw, ixgbe_link_speed speed, /* If no SFP module present, then return success. Return success since * SFP not present error is not excepted in the setup MAC link flow. */ - if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT) + if (ret_val == -ENOENT) return 0; if (ret_val) @@ -1853,7 +1856,7 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed, /* If no SFP module present, then return success. Return success since * SFP not present error is not excepted in the setup MAC link flow. */ - if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT) + if (ret_val == -ENOENT) return 0; if (ret_val) @@ -1863,7 +1866,7 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed, ixgbe_setup_kr_speed_x550em(hw, speed); if (hw->phy.mdio.prtad == MDIO_PRTAD_NONE) - return IXGBE_ERR_PHY_ADDR_INVALID; + return -EFAULT; /* Get external PHY SKU id */ ret_val = hw->phy.ops.read_reg(hw, IXGBE_CS4227_EFUSE_PDF_SKU, @@ -1962,7 +1965,7 @@ static s32 ixgbe_check_link_t_X550em(struct ixgbe_hw *hw, u16 i, autoneg_status; if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) - return IXGBE_ERR_CONFIG; + return -EIO; status = ixgbe_check_mac_link_generic(hw, speed, link_up, link_up_wait_to_complete); @@ -2145,9 +2148,9 @@ static s32 ixgbe_setup_sgmii_fw(struct ixgbe_hw *hw, ixgbe_link_speed speed, */ static void ixgbe_fc_autoneg_sgmii_x550em_a(struct ixgbe_hw *hw) { - s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED; u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 }; ixgbe_link_speed speed; + s32 status = -EIO; bool link_up; /* AN should have completed when the cable was plugged in. @@ -2165,7 +2168,7 @@ static void ixgbe_fc_autoneg_sgmii_x550em_a(struct ixgbe_hw *hw) /* Check if auto-negotiation has completed */ status = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &info); if (status || !(info[0] & FW_PHY_ACT_GET_LINK_INFO_AN_COMPLETE)) { - status = IXGBE_ERR_FC_NOT_NEGOTIATED; + status = -EIO; goto out; } @@ -2369,18 +2372,18 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, * @hw: pointer to hardware structure * @lsc: pointer to boolean flag which indicates whether external Base T * PHY interrupt is lsc + * @is_overtemp: indicate whether an overtemp event encountered * * Determime if external Base T PHY interrupt cause is high temperature * failure alarm or link status change. - * - * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature - * failure alarm, else return PHY access status. **/ -static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) +static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc, + bool *is_overtemp) { u32 status; u16 reg; + *is_overtemp = false; *lsc = false; /* Vendor alarm triggered */ @@ -2412,7 +2415,8 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) if (reg & IXGBE_MDIO_GLOBAL_ALM_1_HI_TMP_FAIL) { /* power down the PHY in case the PHY FW didn't already */ ixgbe_set_copper_phy_power(hw, false); - return IXGBE_ERR_OVERTEMP; + *is_overtemp = true; + return -EIO; } if (reg & IXGBE_MDIO_GLOBAL_ALM_1_DEV_FAULT) { /* device fault alarm triggered */ @@ -2426,7 +2430,8 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) if (reg == IXGBE_MDIO_GLOBAL_FAULT_MSG_HI_TMP) { /* power down the PHY in case the PHY FW didn't */ ixgbe_set_copper_phy_power(hw, false); - return IXGBE_ERR_OVERTEMP; + *is_overtemp = true; + return -EIO; } } @@ -2462,12 +2467,12 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) **/ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) { + bool lsc, overtemp; u32 status; u16 reg; - bool lsc; /* Clear interrupt flags */ - status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc); + status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc, &overtemp); /* Enable link status change alarm */ @@ -2546,21 +2551,20 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) /** * ixgbe_handle_lasi_ext_t_x550em - Handle external Base T PHY interrupt * @hw: pointer to hardware structure + * @is_overtemp: indicate whether an overtemp event encountered * * Handle external Base T PHY interrupt. If high temperature * failure alarm then return error, else if link status change * then setup internal/external PHY link - * - * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature - * failure alarm, else return PHY access status. **/ -static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw) +static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw, + bool *is_overtemp) { struct ixgbe_phy_info *phy = &hw->phy; bool lsc; u32 status; - status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc); + status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc, is_overtemp); if (status) return status; @@ -2692,7 +2696,7 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw) u16 speed; if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) - return IXGBE_ERR_CONFIG; + return -EIO; if (!(hw->mac.type == ixgbe_mac_X550EM_x && !(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE))) { @@ -2735,7 +2739,7 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw) break; default: /* Internal PHY does not support anything else */ - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } return ixgbe_setup_ixfi_x550em(hw, &force_speed); @@ -2767,7 +2771,7 @@ static s32 ixgbe_led_on_t_x550em(struct ixgbe_hw *hw, u32 led_idx) u16 phy_data; if (led_idx >= IXGBE_X557_MAX_LED_INDEX) - return IXGBE_ERR_PARAM; + return -EINVAL; /* To turn on the LED, set mode to ON. */ hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, @@ -2789,7 +2793,7 @@ static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx) u16 phy_data; if (led_idx >= IXGBE_X557_MAX_LED_INDEX) - return IXGBE_ERR_PARAM; + return -EINVAL; /* To turn on the LED, set mode to ON. */ hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, @@ -2813,8 +2817,9 @@ static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx) * * Sends driver version number to firmware through the manageability * block. On success return 0 - * else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring - * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + * else returns -EBUSY when encountering an error acquiring + * semaphore, -EIO when command fails or -ENIVAL when incorrect + * params passed. **/ static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, u8 build, u8 sub, u16 len, @@ -2825,7 +2830,7 @@ static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, int i; if (!len || !driver_ver || (len > sizeof(fw_cmd.driver_string))) - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; fw_cmd.hdr.cmd = FW_CEM_CMD_DRIVER_INFO; fw_cmd.hdr.buf_len = FW_CEM_CMD_DRIVER_INFO_LEN + len; @@ -2850,7 +2855,7 @@ static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, if (fw_cmd.hdr.cmd_or_resp.ret_status != FW_CEM_RESP_STATUS_SUCCESS) - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EIO; return 0; } @@ -2907,7 +2912,7 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) /* Validate the requested mode */ if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } /* 10gig parts do not have a word in the EEPROM to determine the @@ -2942,7 +2947,7 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) break; default: hw_err(hw, "Flow control param set incorrectly\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } switch (hw->device_id) { @@ -2986,8 +2991,8 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw) { u32 link_s1, lp_an_page_low, an_cntl_1; - s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED; ixgbe_link_speed speed; + s32 status = -EIO; bool link_up; /* AN should have completed when the cable was plugged in. @@ -3013,7 +3018,7 @@ static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw) if (status || (link_s1 & IXGBE_KRM_LINK_S1_MAC_AN_COMPLETE) == 0) { hw_dbg(hw, "Auto-Negotiation did not complete\n"); - status = IXGBE_ERR_FC_NOT_NEGOTIATED; + status = -EIO; goto out; } @@ -3187,21 +3192,23 @@ static s32 ixgbe_reset_phy_fw(struct ixgbe_hw *hw) /** * ixgbe_check_overtemp_fw - Check firmware-controlled PHYs for overtemp * @hw: pointer to hardware structure + * + * Return true when an overtemp event detected, otherwise false. */ -static s32 ixgbe_check_overtemp_fw(struct ixgbe_hw *hw) +static bool ixgbe_check_overtemp_fw(struct ixgbe_hw *hw) { u32 store[FW_PHY_ACT_DATA_COUNT] = { 0 }; s32 rc; rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &store); if (rc) - return rc; + return false; if (store[0] & FW_PHY_ACT_GET_LINK_INFO_TEMP) { ixgbe_shutdown_fw_phy(hw); - return IXGBE_ERR_OVERTEMP; + return true; } - return 0; + return false; } /** @@ -3251,8 +3258,7 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) /* Identify the PHY or SFP module */ ret_val = phy->ops.identify(hw); - if (ret_val == IXGBE_ERR_SFP_NOT_SUPPORTED || - ret_val == IXGBE_ERR_PHY_ADDR_INVALID) + if (ret_val == -EOPNOTSUPP || ret_val == -EFAULT) return ret_val; /* Setup function pointers based on detected hardware */ @@ -3460,8 +3466,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) /* PHY ops must be identified and initialized prior to reset */ status = hw->phy.ops.init(hw); - if (status == IXGBE_ERR_SFP_NOT_SUPPORTED || - status == IXGBE_ERR_PHY_ADDR_INVALID) + if (status == -EOPNOTSUPP || status == -EFAULT) return status; /* start the external PHY */ @@ -3477,7 +3482,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) hw->phy.sfp_setup_needed = false; } - if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (status == -EOPNOTSUPP) return status; /* Reset PHY */ @@ -3501,7 +3506,7 @@ mac_reset_top: status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); if (status) { hw_dbg(hw, "semaphore failed with %d", status); - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL); @@ -3519,7 +3524,7 @@ mac_reset_top: } if (ctrl & IXGBE_CTRL_RST_MASK) { - status = IXGBE_ERR_RESET_FAILED; + status = -EIO; hw_dbg(hw, "Reset polling failed to complete.\n"); } @@ -3615,7 +3620,7 @@ static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw) /* Validate the requested mode */ if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } if (hw->fc.requested_mode == ixgbe_fc_default) @@ -3672,7 +3677,7 @@ static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw) break; default: hw_err(hw, "Flow control param set incorrectly\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } status = hw->mac.ops.write_iosf_sb_reg(hw, @@ -3768,7 +3773,7 @@ static s32 ixgbe_acquire_swfw_sync_x550em_a(struct ixgbe_hw *hw, u32 mask) return 0; if (hmask) ixgbe_release_swfw_sync_X540(hw, hmask); - if (status != IXGBE_ERR_TOKEN_RETRY) + if (status != -EAGAIN) return status; msleep(FW_PHY_TOKEN_DELAY); } @@ -3812,7 +3817,7 @@ static s32 ixgbe_read_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = hw->phy.ops.read_reg_mdi(hw, reg_addr, device_type, phy_data); @@ -3838,7 +3843,7 @@ static s32 ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = ixgbe_write_phy_reg_mdi(hw, reg_addr, device_type, phy_data); hw->mac.ops.release_swfw_sync(hw, mask); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index f936640cca4e..2f80ee84c7ec 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -614,12 +614,38 @@ static void mvpp23_bm_set_8pool_mode(struct mvpp2 *priv) mvpp2_write(priv, MVPP22_BM_POOL_BASE_ADDR_HIGH_REG, val); } +/* Cleanup pool before actual initialization in the OS */ +static void mvpp2_bm_pool_cleanup(struct mvpp2 *priv, int pool_id) +{ + unsigned int thread = mvpp2_cpu_to_thread(priv, get_cpu()); + u32 val; + int i; + + /* Drain the BM from all possible residues left by firmware */ + for (i = 0; i < MVPP2_BM_POOL_SIZE_MAX; i++) + mvpp2_thread_read(priv, thread, MVPP2_BM_PHY_ALLOC_REG(pool_id)); + + put_cpu(); + + /* Stop the BM pool */ + val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(pool_id)); + val |= MVPP2_BM_STOP_MASK; + mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(pool_id), val); +} + static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv) { enum dma_data_direction dma_dir = DMA_FROM_DEVICE; int i, err, poolnum = MVPP2_BM_POOLS_NUM; struct mvpp2_port *port; + if (priv->percpu_pools) + poolnum = mvpp2_get_nrxqs(priv) * 2; + + /* Clean up the pool state in case it contains stale state */ + for (i = 0; i < poolnum; i++) + mvpp2_bm_pool_cleanup(priv, i); + if (priv->percpu_pools) { for (i = 0; i < priv->port_count; i++) { port = priv->port_list[i]; @@ -629,7 +655,6 @@ static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv) } } - poolnum = mvpp2_get_nrxqs(priv) * 2; for (i = 0; i < poolnum; i++) { /* the pool in use */ int pn = i / (poolnum / 2); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 65c0373d34d1..90be87dc105d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -78,7 +78,7 @@ static bool is_dev_rpm(void *cgxd) bool is_lmac_valid(struct cgx *cgx, int lmac_id) { - if (!cgx || lmac_id < 0 || lmac_id >= MAX_LMAC_PER_CGX) + if (!cgx || lmac_id < 0 || lmac_id >= cgx->max_lmac_per_mac) return false; return test_bit(lmac_id, &cgx->lmac_bmap); } @@ -90,7 +90,7 @@ static int get_sequence_id_of_lmac(struct cgx *cgx, int lmac_id) { int tmp, id = 0; - for_each_set_bit(tmp, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(tmp, &cgx->lmac_bmap, cgx->max_lmac_per_mac) { if (tmp == lmac_id) break; id++; @@ -121,7 +121,7 @@ u64 cgx_read(struct cgx *cgx, u64 lmac, u64 offset) struct lmac *lmac_pdata(u8 lmac_id, struct cgx *cgx) { - if (!cgx || lmac_id >= MAX_LMAC_PER_CGX) + if (!cgx || lmac_id >= cgx->max_lmac_per_mac) return NULL; return cgx->lmac_idmap[lmac_id]; @@ -1410,7 +1410,7 @@ int cgx_get_fwdata_base(u64 *base) if (!cgx) return -ENXIO; - first_lmac = find_first_bit(&cgx->lmac_bmap, MAX_LMAC_PER_CGX); + first_lmac = find_first_bit(&cgx->lmac_bmap, cgx->max_lmac_per_mac); req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_FWD_BASE, req); err = cgx_fwi_cmd_generic(req, &resp, cgx, first_lmac); if (!err) @@ -1499,7 +1499,7 @@ static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool enable) static inline int cgx_fwi_read_version(u64 *resp, struct cgx *cgx) { - int first_lmac = find_first_bit(&cgx->lmac_bmap, MAX_LMAC_PER_CGX); + int first_lmac = find_first_bit(&cgx->lmac_bmap, cgx->max_lmac_per_mac); u64 req = 0; req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_FW_VER, req); @@ -1537,7 +1537,7 @@ static void cgx_lmac_linkup_work(struct work_struct *work) int i, err; /* Do Link up for all the enabled lmacs */ - for_each_set_bit(i, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(i, &cgx->lmac_bmap, cgx->max_lmac_per_mac) { err = cgx_fwi_link_change(cgx, i, true); if (err) dev_info(dev, "cgx port %d:%d Link up command failed\n", @@ -1557,14 +1557,6 @@ int cgx_lmac_linkup_start(void *cgxd) return 0; } -static void cgx_lmac_get_fifolen(struct cgx *cgx) -{ - u64 cfg; - - cfg = cgx_read(cgx, 0, CGX_CONST); - cgx->mac_ops->fifo_len = FIELD_GET(CGX_CONST_RXFIFO_SIZE, cfg); -} - static int cgx_configure_interrupt(struct cgx *cgx, struct lmac *lmac, int cnt, bool req_free) { @@ -1619,17 +1611,14 @@ static int cgx_lmac_init(struct cgx *cgx) u64 lmac_list; int i, err; - cgx_lmac_get_fifolen(cgx); - - cgx->lmac_count = cgx->mac_ops->get_nr_lmacs(cgx); /* lmac_list specifies which lmacs are enabled * when bit n is set to 1, LMAC[n] is enabled */ if (cgx->mac_ops->non_contiguous_serdes_lane) lmac_list = cgx_read(cgx, 0, CGXX_CMRX_RX_LMACS) & 0xFULL; - if (cgx->lmac_count > MAX_LMAC_PER_CGX) - cgx->lmac_count = MAX_LMAC_PER_CGX; + if (cgx->lmac_count > cgx->max_lmac_per_mac) + cgx->lmac_count = cgx->max_lmac_per_mac; for (i = 0; i < cgx->lmac_count; i++) { lmac = kzalloc(sizeof(struct lmac), GFP_KERNEL); @@ -1707,7 +1696,7 @@ static int cgx_lmac_exit(struct cgx *cgx) } /* Free all lmac related resources */ - for_each_set_bit(i, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(i, &cgx->lmac_bmap, cgx->max_lmac_per_mac) { lmac = cgx->lmac_idmap[i]; if (!lmac) continue; @@ -1723,6 +1712,12 @@ static int cgx_lmac_exit(struct cgx *cgx) static void cgx_populate_features(struct cgx *cgx) { + u64 cfg; + + cfg = cgx_read(cgx, 0, CGX_CONST); + cgx->mac_ops->fifo_len = FIELD_GET(CGX_CONST_RXFIFO_SIZE, cfg); + cgx->max_lmac_per_mac = FIELD_GET(CGX_CONST_MAX_LMACS, cfg); + if (is_dev_rpm(cgx)) cgx->hw_features = (RVU_LMAC_FEAT_DMACF | RVU_MAC_RPM | RVU_LMAC_FEAT_FC | RVU_LMAC_FEAT_PTP); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 04338db38671..09ddb00f63cc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -18,11 +18,8 @@ /* PCI BAR nos */ #define PCI_CFG_REG_BAR_NUM 0 -#define CGX_ID_MASK 0x7 -#define MAX_LMAC_PER_CGX 4 +#define CGX_ID_MASK 0xF #define MAX_DMAC_ENTRIES_PER_CGX 32 -#define CGX_FIFO_LEN 65536 /* 64K for both Rx & Tx */ -#define CGX_OFFSET(x) ((x) * MAX_LMAC_PER_CGX) /* Registers */ #define CGXX_CMRX_CFG 0x00 @@ -56,6 +53,7 @@ #define CGXX_SCRATCH1_REG 0x1058 #define CGX_CONST 0x2000 #define CGX_CONST_RXFIFO_SIZE GENMASK_ULL(23, 0) +#define CGX_CONST_MAX_LMACS GENMASK_ULL(31, 24) #define CGXX_SPUX_CONTROL1 0x10000 #define CGXX_SPUX_LNX_FEC_CORR_BLOCKS 0x10700 #define CGXX_SPUX_LNX_FEC_UNCORR_BLOCKS 0x10800 diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h index 52b6016789fa..697cfec74aa1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h @@ -128,7 +128,10 @@ struct cgx { struct pci_dev *pdev; u8 cgx_id; u8 lmac_count; - struct lmac *lmac_idmap[MAX_LMAC_PER_CGX]; + /* number of LMACs per MAC could be 4 or 8 */ + u8 max_lmac_per_mac; +#define MAX_LMAC_COUNT 8 + struct lmac *lmac_idmap[MAX_LMAC_COUNT]; struct work_struct cgx_cmd_work; struct workqueue_struct *cgx_cmd_workq; struct list_head cgx_list; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index d027c23b8ef8..aaff91bc7415 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -514,7 +514,7 @@ struct npc_lt_def { u8 ltype_mask; u8 ltype_match; u8 lid; -}; +} __packed; struct npc_lt_def_ipsec { u8 ltype_mask; @@ -522,7 +522,7 @@ struct npc_lt_def_ipsec { u8 lid; u8 spi_offset; u8 spi_nz; -}; +} __packed; struct npc_lt_def_apad { u8 ltype_mask; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index a70e1153fa04..6b4792a942d8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -283,6 +283,11 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable) cfg = FIELD_SET(RPM_PFC_CLASS_MASK, 0, cfg); rpm_write(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL, cfg); + /* Disable forward pause to driver */ + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD; + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* Enable channel mask for all LMACS */ rpm_write(rpm, 0, RPMX_CMR_CHAN_MSK_OR, ~0ULL); } @@ -451,12 +456,10 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p if (rx_pause) { cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE); } else { cfg |= (RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE); } if (tx_pause) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 95a7bc396e8e..0b76dfa979d4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -480,7 +480,7 @@ struct rvu { u8 cgx_mapped_pfs; u8 cgx_cnt_max; /* CGX port count max */ u8 *pf2cgxlmac_map; /* pf to cgx_lmac map */ - u16 *cgxlmac2pf_map; /* bitmap of mapped pfs for + u64 *cgxlmac2pf_map; /* bitmap of mapped pfs for * every cgx lmac port */ unsigned long pf_notify_bmap; /* Flags for PF notification */ @@ -850,6 +850,7 @@ u32 rvu_cgx_get_fifolen(struct rvu *rvu); void *rvu_first_cgx_pdata(struct rvu *rvu); int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id); int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable); +int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable); int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause, u16 pfc_en); int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index c60b9580ca96..bcb4385d0621 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -55,8 +55,9 @@ bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature) return (cgx_features_get(cgxd) & feature); } +#define CGX_OFFSET(x) ((x) * rvu->hw->lmac_per_cgx) /* Returns bitmap of mapped PFs */ -static u16 cgxlmac_to_pfmap(struct rvu *rvu, u8 cgx_id, u8 lmac_id) +static u64 cgxlmac_to_pfmap(struct rvu *rvu, u8 cgx_id, u8 lmac_id) { return rvu->cgxlmac2pf_map[CGX_OFFSET(cgx_id) + lmac_id]; } @@ -71,7 +72,8 @@ int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id) if (!pfmap) return -ENODEV; else - return find_first_bit(&pfmap, 16); + return find_first_bit(&pfmap, + rvu->cgx_cnt_max * rvu->hw->lmac_per_cgx); } static u8 cgxlmac_id_to_bmap(u8 cgx_id, u8 lmac_id) @@ -129,14 +131,14 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) if (!cgx_cnt_max) return 0; - if (cgx_cnt_max > 0xF || MAX_LMAC_PER_CGX > 0xF) + if (cgx_cnt_max > 0xF || rvu->hw->lmac_per_cgx > 0xF) return -EINVAL; /* Alloc map table * An additional entry is required since PF id starts from 1 and * hence entry at offset 0 is invalid. */ - size = (cgx_cnt_max * MAX_LMAC_PER_CGX + 1) * sizeof(u8); + size = (cgx_cnt_max * rvu->hw->lmac_per_cgx + 1) * sizeof(u8); rvu->pf2cgxlmac_map = devm_kmalloc(rvu->dev, size, GFP_KERNEL); if (!rvu->pf2cgxlmac_map) return -ENOMEM; @@ -145,9 +147,10 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) memset(rvu->pf2cgxlmac_map, 0xFF, size); /* Reverse map table */ - rvu->cgxlmac2pf_map = devm_kzalloc(rvu->dev, - cgx_cnt_max * MAX_LMAC_PER_CGX * sizeof(u16), - GFP_KERNEL); + rvu->cgxlmac2pf_map = + devm_kzalloc(rvu->dev, + cgx_cnt_max * rvu->hw->lmac_per_cgx * sizeof(u64), + GFP_KERNEL); if (!rvu->cgxlmac2pf_map) return -ENOMEM; @@ -156,7 +159,7 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) if (!rvu_cgx_pdata(cgx, rvu)) continue; lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu)); - for_each_set_bit(iter, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) { lmac = cgx_get_lmacid(rvu_cgx_pdata(cgx, rvu), iter); rvu->pf2cgxlmac_map[pf] = cgxlmac_id_to_bmap(cgx, lmac); @@ -235,7 +238,8 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu) pfmap = cgxlmac_to_pfmap(rvu, event->cgx_id, event->lmac_id); do { - pfid = find_first_bit(&pfmap, 16); + pfid = find_first_bit(&pfmap, + rvu->cgx_cnt_max * rvu->hw->lmac_per_cgx); clear_bit(pfid, &pfmap); /* check if notification is enabled */ @@ -310,7 +314,7 @@ static int cgx_lmac_event_handler_init(struct rvu *rvu) if (!cgxd) continue; lmac_bmap = cgx_get_lmac_bmap(cgxd); - for_each_set_bit(lmac, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(lmac, &lmac_bmap, rvu->hw->lmac_per_cgx) { err = cgx_lmac_evh_register(&cb, cgxd, lmac); if (err) dev_err(rvu->dev, @@ -396,7 +400,7 @@ int rvu_cgx_exit(struct rvu *rvu) if (!cgxd) continue; lmac_bmap = cgx_get_lmac_bmap(cgxd); - for_each_set_bit(lmac, &lmac_bmap, MAX_LMAC_PER_CGX) + for_each_set_bit(lmac, &lmac_bmap, rvu->hw->lmac_per_cgx) cgx_lmac_evh_unregister(cgxd, lmac); } @@ -456,6 +460,23 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start) return mac_ops->mac_rx_tx_enable(cgxd, lmac_id, start); } +int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable) +{ + int pf = rvu_get_pf(pcifunc); + struct mac_ops *mac_ops; + u8 cgx_id, lmac_id; + void *cgxd; + + if (!is_cgx_config_permitted(rvu, pcifunc)) + return LMAC_AF_ERR_PERM_DENIED; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + mac_ops = get_mac_ops(cgxd); + + return mac_ops->mac_tx_enable(cgxd, lmac_id, enable); +} + int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable) { struct mac_ops *mac_ops; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 5c9dc3f9262f..cc5d342e026c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -2618,7 +2618,7 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) rvu->rvu_dbg.cgx = debugfs_create_dir(dname, rvu->rvu_dbg.cgx_root); - for_each_set_bit(lmac_id, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(lmac_id, &lmac_bmap, rvu->hw->lmac_per_cgx) { /* lmac debugfs dir */ sprintf(dname, "lmac%d", lmac_id); rvu->rvu_dbg.lmac = diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 959f36efdc4a..bb99302eab67 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -3923,90 +3923,18 @@ static void nix_find_link_frs(struct rvu *rvu, req->minlen = minlen; } -static int -nix_config_link_credits(struct rvu *rvu, int blkaddr, int link, - u16 pcifunc, u64 tx_credits) -{ - struct rvu_hwinfo *hw = rvu->hw; - int pf = rvu_get_pf(pcifunc); - u8 cgx_id = 0, lmac_id = 0; - unsigned long poll_tmo; - bool restore_tx_en = 0; - struct nix_hw *nix_hw; - u64 cfg, sw_xoff = 0; - u32 schq = 0; - u32 credits; - int rc; - - nix_hw = get_nix_hw(rvu->hw, blkaddr); - if (!nix_hw) - return NIX_AF_ERR_INVALID_NIXBLK; - - if (tx_credits == nix_hw->tx_credits[link]) - return 0; - - /* Enable cgx tx if disabled for credits to be back */ - if (is_pf_cgxmapped(rvu, pf)) { - rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); - restore_tx_en = !rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), - lmac_id, true); - } - - mutex_lock(&rvu->rsrc_lock); - /* Disable new traffic to link */ - if (hw->cap.nix_shaping) { - schq = nix_get_tx_link(rvu, pcifunc); - sw_xoff = rvu_read64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq)); - rvu_write64(rvu, blkaddr, - NIX_AF_TL1X_SW_XOFF(schq), BIT_ULL(0)); - } - - rc = NIX_AF_ERR_LINK_CREDITS; - poll_tmo = jiffies + usecs_to_jiffies(200000); - /* Wait for credits to return */ - do { - if (time_after(jiffies, poll_tmo)) - goto exit; - usleep_range(100, 200); - - cfg = rvu_read64(rvu, blkaddr, - NIX_AF_TX_LINKX_NORM_CREDIT(link)); - credits = (cfg >> 12) & 0xFFFFFULL; - } while (credits != nix_hw->tx_credits[link]); - - cfg &= ~(0xFFFFFULL << 12); - cfg |= (tx_credits << 12); - rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link), cfg); - rc = 0; - - nix_hw->tx_credits[link] = tx_credits; - -exit: - /* Enable traffic back */ - if (hw->cap.nix_shaping && !sw_xoff) - rvu_write64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq), 0); - - /* Restore state of cgx tx */ - if (restore_tx_en) - rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false); - - mutex_unlock(&rvu->rsrc_lock); - return rc; -} - int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, struct msg_rsp *rsp) { struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; int pf = rvu_get_pf(pcifunc); - int blkaddr, schq, link = -1; - struct nix_txsch *txsch; - u64 cfg, lmac_fifo_len; + int blkaddr, link = -1; struct nix_hw *nix_hw; struct rvu_pfvf *pfvf; u8 cgx = 0, lmac = 0; u16 max_mtu; + u64 cfg; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); if (blkaddr < 0) @@ -4027,25 +3955,6 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, if (req->update_minlen && req->minlen < NIC_HW_MIN_FRS) return NIX_AF_ERR_FRS_INVALID; - /* Check if requester wants to update SMQ's */ - if (!req->update_smq) - goto rx_frscfg; - - /* Update min/maxlen in each of the SMQ attached to this PF/VF */ - txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ]; - mutex_lock(&rvu->rsrc_lock); - for (schq = 0; schq < txsch->schq.max; schq++) { - if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc) - continue; - cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq)); - cfg = (cfg & ~(0xFFFFULL << 8)) | ((u64)req->maxlen << 8); - if (req->update_minlen) - cfg = (cfg & ~0x7FULL) | ((u64)req->minlen & 0x7F); - rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq), cfg); - } - mutex_unlock(&rvu->rsrc_lock); - -rx_frscfg: /* Check if config is for SDP link */ if (req->sdp_link) { if (!hw->sdp_links) @@ -4068,7 +3977,6 @@ rx_frscfg: if (link < 0) return NIX_AF_ERR_RX_LINK_INVALID; - linkcfg: nix_find_link_frs(rvu, req, pcifunc); @@ -4078,19 +3986,7 @@ linkcfg: cfg = (cfg & ~0xFFFFULL) | req->minlen; rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link), cfg); - if (req->sdp_link || pf == 0) - return 0; - - /* Update transmit credits for CGX links */ - lmac_fifo_len = rvu_cgx_get_lmac_fifolen(rvu, cgx, lmac); - if (!lmac_fifo_len) { - dev_err(rvu->dev, - "%s: Failed to get CGX/RPM%d:LMAC%d FIFO size\n", - __func__, cgx, lmac); - return 0; - } - return nix_config_link_credits(rvu, blkaddr, link, pcifunc, - (lmac_fifo_len - req->maxlen) / 16); + return 0; } int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req, @@ -4183,7 +4079,7 @@ static void nix_link_config(struct rvu *rvu, int blkaddr, /* Get LMAC id's from bitmap */ lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu)); - for_each_set_bit(iter, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) { lmac_fifo_len = rvu_cgx_get_lmac_fifolen(rvu, cgx, iter); if (!lmac_fifo_len) { dev_err(rvu->dev, @@ -4610,7 +4506,13 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, pfvf = rvu_get_pfvf(rvu, pcifunc); clear_bit(NIXLF_INITIALIZED, &pfvf->flags); - return rvu_cgx_start_stop_io(rvu, pcifunc, false); + err = rvu_cgx_start_stop_io(rvu, pcifunc, false); + if (err) + return err; + + rvu_cgx_tx_enable(rvu, pcifunc, true); + + return 0; } #define RX_SA_BASE GENMASK_ULL(52, 7) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 0bcf3e559280..55639c133dd0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -437,6 +437,10 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam, return; } + /* AF modifies given action iff PF/VF has requested for it */ + if ((entry->action & 0xFULL) != NIX_RX_ACTION_DEFAULT) + return; + /* copy VF default entry action to the VF mcam entry */ rx_action = npc_get_default_entry_action(rvu, mcam, blkaddr, target_func); @@ -2678,18 +2682,17 @@ int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu, rsp->entry = NPC_MCAM_ENTRY_INVALID; rsp->free_count = 0; - /* Check if ref_entry is within range */ - if (req->priority && req->ref_entry >= mcam->bmap_entries) { - dev_err(rvu->dev, "%s: reference entry %d is out of range\n", - __func__, req->ref_entry); - return NPC_MCAM_INVALID_REQ; - } + /* Check if ref_entry is greater that the range + * then set it to max value. + */ + if (req->ref_entry > mcam->bmap_entries) + req->ref_entry = mcam->bmap_entries; /* ref_entry can't be '0' if requested priority is high. * Can't be last entry if requested priority is low. */ if ((!req->ref_entry && req->priority == NPC_MCAM_HIGHER_PRIO) || - ((req->ref_entry == (mcam->bmap_entries - 1)) && + ((req->ref_entry == mcam->bmap_entries) && req->priority == NPC_MCAM_LOWER_PRIO)) return NPC_MCAM_INVALID_REQ; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c index 34fa59575fa9..54e0dfdc9d98 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c @@ -1999,7 +1999,9 @@ int rvu_npc_exact_init(struct rvu *rvu) /* Install SDP drop rule */ drop_mcam_idx = &table->num_drop_rules; - max_lmac_cnt = rvu->cgx_cnt_max * MAX_LMAC_PER_CGX + PF_CGXMAP_BASE; + max_lmac_cnt = rvu->cgx_cnt_max * rvu->hw->lmac_per_cgx + + PF_CGXMAP_BASE; + for (i = PF_CGXMAP_BASE; i < max_lmac_cnt; i++) { if (rvu->pf2cgxlmac_map[i] == 0xFF) continue; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 0f896f606c3e..c00d6d67db51 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -930,8 +930,11 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) if (pfvf->ptp && qidx < pfvf->hw.tx_queues) { err = qmem_alloc(pfvf->dev, &sq->timestamps, qset->sqe_cnt, sizeof(*sq->timestamps)); - if (err) + if (err) { + kfree(sq->sg); + sq->sg = NULL; return err; + } } sq->head = 0; @@ -947,7 +950,14 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) sq->stats.bytes = 0; sq->stats.pkts = 0; - return pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura); + err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura); + if (err) { + kfree(sq->sg); + sq->sg = NULL; + return err; + } + + return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c index bfddbff7bcdf..28fb643d2917 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -399,9 +399,10 @@ static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc) static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) { struct otx2_nic *pfvf = netdev_priv(dev); + u8 old_pfc_en; int err; - /* Save PFC configuration to interface */ + old_pfc_en = pfvf->pfc_en; pfvf->pfc_en = pfc->pfc_en; if (pfvf->hw.tx_queues >= NIX_PF_PFC_PRIO_MAX) @@ -411,13 +412,17 @@ static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) * supported by the tx queue configuration */ err = otx2_check_pfc_config(pfvf); - if (err) + if (err) { + pfvf->pfc_en = old_pfc_en; return err; + } process_pfc: err = otx2_config_priority_flow_ctrl(pfvf); - if (err) + if (err) { + pfvf->pfc_en = old_pfc_en; return err; + } /* Request Per channel Bpids */ if (pfc->pfc_en) @@ -425,6 +430,12 @@ process_pfc: err = otx2_pfc_txschq_update(pfvf); if (err) { + if (pfc->pfc_en) + otx2_nix_config_bp(pfvf, false); + + otx2_pfc_txschq_stop(pfvf); + pfvf->pfc_en = old_pfc_en; + otx2_config_priority_flow_ctrl(pfvf); dev_err(pfvf->dev, "%s failed to update TX schedulers\n", __func__); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index b3253e263ebc..ac6a0785b10d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -48,6 +48,25 @@ #define CREATE_TRACE_POINTS #include "diag/cmd_tracepoint.h" +struct mlx5_ifc_mbox_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_mbox_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + enum { CMD_IF_REV = 5, }; @@ -71,6 +90,26 @@ enum { MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR = 0x10, }; +static u16 in_to_opcode(void *in) +{ + return MLX5_GET(mbox_in, in, opcode); +} + +/* Returns true for opcodes that might be triggered very frequently and throttle + * the command interface. Limit their command slots usage. + */ +static bool mlx5_cmd_is_throttle_opcode(u16 op) +{ + switch (op) { + case MLX5_CMD_OP_CREATE_GENERAL_OBJECT: + case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT: + case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT: + case MLX5_CMD_OP_QUERY_GENERAL_OBJECT: + return true; + } + return false; +} + static struct mlx5_cmd_work_ent * cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in, struct mlx5_cmd_msg *out, void *uout, int uout_size, @@ -92,6 +131,7 @@ cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in, ent->context = context; ent->cmd = cmd; ent->page_queue = page_queue; + ent->op = in_to_opcode(in->first.data); refcount_set(&ent->refcnt, 1); return ent; @@ -116,24 +156,27 @@ static u8 alloc_token(struct mlx5_cmd *cmd) return token; } -static int cmd_alloc_index(struct mlx5_cmd *cmd) +static int cmd_alloc_index(struct mlx5_cmd *cmd, struct mlx5_cmd_work_ent *ent) { unsigned long flags; int ret; spin_lock_irqsave(&cmd->alloc_lock, flags); - ret = find_first_bit(&cmd->bitmask, cmd->max_reg_cmds); - if (ret < cmd->max_reg_cmds) - clear_bit(ret, &cmd->bitmask); + ret = find_first_bit(&cmd->vars.bitmask, cmd->vars.max_reg_cmds); + if (ret < cmd->vars.max_reg_cmds) { + clear_bit(ret, &cmd->vars.bitmask); + ent->idx = ret; + cmd->ent_arr[ent->idx] = ent; + } spin_unlock_irqrestore(&cmd->alloc_lock, flags); - return ret < cmd->max_reg_cmds ? ret : -ENOMEM; + return ret < cmd->vars.max_reg_cmds ? ret : -ENOMEM; } static void cmd_free_index(struct mlx5_cmd *cmd, int idx) { lockdep_assert_held(&cmd->alloc_lock); - set_bit(idx, &cmd->bitmask); + set_bit(idx, &cmd->vars.bitmask); } static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) @@ -152,7 +195,7 @@ static void cmd_ent_put(struct mlx5_cmd_work_ent *ent) if (ent->idx >= 0) { cmd_free_index(cmd, ent->idx); - up(ent->page_queue ? &cmd->pages_sem : &cmd->sem); + up(ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem); } cmd_free_ent(ent); @@ -162,7 +205,7 @@ out: static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) { - return cmd->cmd_buf + (idx << cmd->log_stride); + return cmd->cmd_buf + (idx << cmd->vars.log_stride); } static int mlx5_calc_cmd_blocks(struct mlx5_cmd_msg *msg) @@ -753,25 +796,6 @@ static int cmd_status_to_err(u8 status) } } -struct mlx5_ifc_mbox_out_bits { - u8 status[0x8]; - u8 reserved_at_8[0x18]; - - u8 syndrome[0x20]; - - u8 reserved_at_40[0x40]; -}; - -struct mlx5_ifc_mbox_in_bits { - u8 opcode[0x10]; - u8 uid[0x10]; - - u8 reserved_at_20[0x10]; - u8 op_mod[0x10]; - - u8 reserved_at_40[0x40]; -}; - void mlx5_cmd_out_err(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out) { u32 syndrome = MLX5_GET(mbox_out, out, syndrome); @@ -789,7 +813,7 @@ static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out) u16 opcode, op_mod; u16 uid; - opcode = MLX5_GET(mbox_in, in, opcode); + opcode = in_to_opcode(in); op_mod = MLX5_GET(mbox_in, in, op_mod); uid = MLX5_GET(mbox_in, in, uid); @@ -801,7 +825,7 @@ int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out) { /* aborted due to PCI error or via reset flow mlx5_cmd_trigger_completions() */ if (err == -ENXIO) { - u16 opcode = MLX5_GET(mbox_in, in, opcode); + u16 opcode = in_to_opcode(in); u32 syndrome; u8 status; @@ -830,9 +854,9 @@ static void dump_command(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent, int input) { struct mlx5_cmd_msg *msg = input ? ent->in : ent->out; - u16 op = MLX5_GET(mbox_in, ent->lay->in, opcode); struct mlx5_cmd_mailbox *next = msg->next; int n = mlx5_calc_cmd_blocks(msg); + u16 op = ent->op; int data_only; u32 offset = 0; int dump_len; @@ -884,11 +908,6 @@ static void dump_command(struct mlx5_core_dev *dev, mlx5_core_dbg(dev, "cmd[%d]: end dump\n", ent->idx); } -static u16 msg_to_opcode(struct mlx5_cmd_msg *in) -{ - return MLX5_GET(mbox_in, in->first.data, opcode); -} - static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced); static void cb_timeout_handler(struct work_struct *work) @@ -906,13 +925,13 @@ static void cb_timeout_handler(struct work_struct *work) /* Maybe got handled by eq recover ? */ if (!test_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state)) { mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, recovered after timeout\n", ent->idx, - mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + mlx5_command_str(ent->op), ent->op); goto out; /* phew, already handled */ } ent->ret = -ETIMEDOUT; mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n", - ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + ent->idx, mlx5_command_str(ent->op), ent->op); mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true); out: @@ -955,10 +974,10 @@ static void cmd_work_handler(struct work_struct *work) cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); complete(&ent->handling); - sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; + sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem; down(sem); if (!ent->page_queue) { - alloc_ret = cmd_alloc_index(cmd); + alloc_ret = cmd_alloc_index(cmd, ent); if (alloc_ret < 0) { mlx5_core_err_rl(dev, "failed to allocate command entry\n"); if (ent->callback) { @@ -973,20 +992,18 @@ static void cmd_work_handler(struct work_struct *work) up(sem); return; } - ent->idx = alloc_ret; } else { - ent->idx = cmd->max_reg_cmds; + ent->idx = cmd->vars.max_reg_cmds; spin_lock_irqsave(&cmd->alloc_lock, flags); - clear_bit(ent->idx, &cmd->bitmask); + clear_bit(ent->idx, &cmd->vars.bitmask); + cmd->ent_arr[ent->idx] = ent; spin_unlock_irqrestore(&cmd->alloc_lock, flags); } - cmd->ent_arr[ent->idx] = ent; lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); memcpy(lay->in, ent->in->first.data, sizeof(lay->in)); - ent->op = be32_to_cpu(lay->in[0]) >> 16; if (ent->in->next) lay->in_ptr = cpu_to_be64(ent->in->next->dma); lay->inlen = cpu_to_be32(ent->in->len); @@ -1099,12 +1116,12 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, */ if (wait_for_completion_timeout(&ent->done, timeout)) { mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) recovered after timeout\n", ent->idx, - mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + mlx5_command_str(ent->op), ent->op); return; } mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) No done completion\n", ent->idx, - mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + mlx5_command_str(ent->op), ent->op); ent->ret = -ETIMEDOUT; mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true); @@ -1131,12 +1148,10 @@ out_err: if (err == -ETIMEDOUT) { mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n", - mlx5_command_str(msg_to_opcode(ent->in)), - msg_to_opcode(ent->in)); + mlx5_command_str(ent->op), ent->op); } else if (err == -ECANCELED) { mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n", - mlx5_command_str(msg_to_opcode(ent->in)), - msg_to_opcode(ent->in)); + mlx5_command_str(ent->op), ent->op); } mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n", err, deliv_status_to_str(ent->status), ent->status); @@ -1170,7 +1185,6 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, u8 status = 0; int err = 0; s64 ds; - u16 op; if (callback && page_queue) return -EINVAL; @@ -1210,9 +1224,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, goto out_free; ds = ent->ts2 - ent->ts1; - op = MLX5_GET(mbox_in, in->first.data, opcode); - if (op < MLX5_CMD_OP_MAX) { - stats = &cmd->stats[op]; + if (ent->op < MLX5_CMD_OP_MAX) { + stats = &cmd->stats[ent->op]; spin_lock_irq(&stats->lock); stats->sum += ds; ++stats->n; @@ -1220,7 +1233,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, } mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME, "fw exec time for %s is %lld nsec\n", - mlx5_command_str(op), ds); + mlx5_command_str(ent->op), ds); out_free: status = ent->status; @@ -1558,15 +1571,15 @@ void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode) struct mlx5_cmd *cmd = &dev->cmd; int i; - for (i = 0; i < cmd->max_reg_cmds; i++) - down(&cmd->sem); - down(&cmd->pages_sem); + for (i = 0; i < cmd->vars.max_reg_cmds; i++) + down(&cmd->vars.sem); + down(&cmd->vars.pages_sem); cmd->allowed_opcode = opcode; - up(&cmd->pages_sem); - for (i = 0; i < cmd->max_reg_cmds; i++) - up(&cmd->sem); + up(&cmd->vars.pages_sem); + for (i = 0; i < cmd->vars.max_reg_cmds; i++) + up(&cmd->vars.sem); } static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode) @@ -1574,15 +1587,15 @@ static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode) struct mlx5_cmd *cmd = &dev->cmd; int i; - for (i = 0; i < cmd->max_reg_cmds; i++) - down(&cmd->sem); - down(&cmd->pages_sem); + for (i = 0; i < cmd->vars.max_reg_cmds; i++) + down(&cmd->vars.sem); + down(&cmd->vars.pages_sem); cmd->mode = mode; - up(&cmd->pages_sem); - for (i = 0; i < cmd->max_reg_cmds; i++) - up(&cmd->sem); + up(&cmd->vars.pages_sem); + for (i = 0; i < cmd->vars.max_reg_cmds; i++) + up(&cmd->vars.sem); } static int cmd_comp_notifier(struct notifier_block *nb, @@ -1641,7 +1654,7 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force /* there can be at most 32 command queues */ vector = vec & 0xffffffff; - for (i = 0; i < (1 << cmd->log_sz); i++) { + for (i = 0; i < (1 << cmd->vars.log_sz); i++) { if (test_bit(i, &vector)) { ent = cmd->ent_arr[i]; @@ -1730,7 +1743,7 @@ static void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) /* wait for pending handlers to complete */ mlx5_eq_synchronize_cmd_irq(dev); spin_lock_irqsave(&dev->cmd.alloc_lock, flags); - vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1); + vector = ~dev->cmd.vars.bitmask & ((1ul << (1 << dev->cmd.vars.log_sz)) - 1); if (!vector) goto no_trig; @@ -1739,14 +1752,14 @@ static void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) * to guarantee pending commands will not get freed in the meanwhile. * For that reason, it also has to be done inside the alloc_lock. */ - for_each_set_bit(i, &bitmask, (1 << cmd->log_sz)) + for_each_set_bit(i, &bitmask, (1 << cmd->vars.log_sz)) cmd_ent_get(cmd->ent_arr[i]); vector |= MLX5_TRIGGERED_CMD_COMP; spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); mlx5_core_dbg(dev, "vector 0x%llx\n", vector); mlx5_cmd_comp_handler(dev, vector, true); - for_each_set_bit(i, &bitmask, (1 << cmd->log_sz)) + for_each_set_bit(i, &bitmask, (1 << cmd->vars.log_sz)) cmd_ent_put(cmd->ent_arr[i]); return; @@ -1759,22 +1772,22 @@ void mlx5_cmd_flush(struct mlx5_core_dev *dev) struct mlx5_cmd *cmd = &dev->cmd; int i; - for (i = 0; i < cmd->max_reg_cmds; i++) { - while (down_trylock(&cmd->sem)) { + for (i = 0; i < cmd->vars.max_reg_cmds; i++) { + while (down_trylock(&cmd->vars.sem)) { mlx5_cmd_trigger_completions(dev); cond_resched(); } } - while (down_trylock(&cmd->pages_sem)) { + while (down_trylock(&cmd->vars.pages_sem)) { mlx5_cmd_trigger_completions(dev); cond_resched(); } /* Unlock cmdif */ - up(&cmd->pages_sem); - for (i = 0; i < cmd->max_reg_cmds; i++) - up(&cmd->sem); + up(&cmd->vars.pages_sem); + for (i = 0; i < cmd->vars.max_reg_cmds; i++) + up(&cmd->vars.sem); } static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size, @@ -1817,7 +1830,7 @@ cache_miss: static int is_manage_pages(void *in) { - return MLX5_GET(mbox_in, in, opcode) == MLX5_CMD_OP_MANAGE_PAGES; + return in_to_opcode(in) == MLX5_CMD_OP_MANAGE_PAGES; } /* Notes: @@ -1828,8 +1841,9 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size, mlx5_cmd_cbk_t callback, void *context, bool force_polling) { - u16 opcode = MLX5_GET(mbox_in, in, opcode); struct mlx5_cmd_msg *inb, *outb; + u16 opcode = in_to_opcode(in); + bool throttle_op; int pages_queue; gfp_t gfp; u8 token; @@ -1838,13 +1852,21 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode)) return -ENXIO; + throttle_op = mlx5_cmd_is_throttle_opcode(opcode); + if (throttle_op) { + /* atomic context may not sleep */ + if (callback) + return -EINVAL; + down(&dev->cmd.vars.throttle_sem); + } + pages_queue = is_manage_pages(in); gfp = callback ? GFP_ATOMIC : GFP_KERNEL; inb = alloc_msg(dev, in_size, gfp); if (IS_ERR(inb)) { err = PTR_ERR(inb); - return err; + goto out_up; } token = alloc_token(&dev->cmd); @@ -1878,6 +1900,9 @@ out_out: mlx5_free_cmd_msg(dev, outb); out_in: free_msg(dev, inb); +out_up: + if (throttle_op) + up(&dev->cmd.vars.throttle_sem); return err; } @@ -1952,8 +1977,8 @@ static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, u16 op int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size) { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false); - u16 opcode = MLX5_GET(mbox_in, in, opcode); u16 op_mod = MLX5_GET(mbox_in, in, op_mod); + u16 opcode = in_to_opcode(in); return cmd_status_err(dev, err, opcode, op_mod, out); } @@ -1998,8 +2023,8 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size) { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true); - u16 opcode = MLX5_GET(mbox_in, in, opcode); u16 op_mod = MLX5_GET(mbox_in, in, op_mod); + u16 opcode = in_to_opcode(in); err = cmd_status_err(dev, err, opcode, op_mod, out); return mlx5_cmd_check(dev, err, in, out); @@ -2051,7 +2076,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, work->ctx = ctx; work->user_callback = callback; - work->opcode = MLX5_GET(mbox_in, in, opcode); + work->opcode = in_to_opcode(in); work->op_mod = MLX5_GET(mbox_in, in, op_mod); work->out = out; if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight))) @@ -2187,16 +2212,16 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) goto err_free_pool; cmd_l = ioread32be(&dev->iseg->cmdq_addr_l_sz) & 0xff; - cmd->log_sz = cmd_l >> 4 & 0xf; - cmd->log_stride = cmd_l & 0xf; - if (1 << cmd->log_sz > MLX5_MAX_COMMANDS) { + cmd->vars.log_sz = cmd_l >> 4 & 0xf; + cmd->vars.log_stride = cmd_l & 0xf; + if (1 << cmd->vars.log_sz > MLX5_MAX_COMMANDS) { mlx5_core_err(dev, "firmware reports too many outstanding commands %d\n", - 1 << cmd->log_sz); + 1 << cmd->vars.log_sz); err = -EINVAL; goto err_free_page; } - if (cmd->log_sz + cmd->log_stride > MLX5_ADAPTER_PAGE_SHIFT) { + if (cmd->vars.log_sz + cmd->vars.log_stride > MLX5_ADAPTER_PAGE_SHIFT) { mlx5_core_err(dev, "command queue size overflow\n"); err = -EINVAL; goto err_free_page; @@ -2204,13 +2229,13 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) cmd->state = MLX5_CMDIF_STATE_DOWN; cmd->checksum_disabled = 1; - cmd->max_reg_cmds = (1 << cmd->log_sz) - 1; - cmd->bitmask = (1UL << cmd->max_reg_cmds) - 1; + cmd->vars.max_reg_cmds = (1 << cmd->vars.log_sz) - 1; + cmd->vars.bitmask = (1UL << cmd->vars.max_reg_cmds) - 1; - cmd->cmdif_rev = ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16; - if (cmd->cmdif_rev > CMD_IF_REV) { + cmd->vars.cmdif_rev = ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16; + if (cmd->vars.cmdif_rev > CMD_IF_REV) { mlx5_core_err(dev, "driver does not support command interface version. driver %d, firmware %d\n", - CMD_IF_REV, cmd->cmdif_rev); + CMD_IF_REV, cmd->vars.cmdif_rev); err = -EOPNOTSUPP; goto err_free_page; } @@ -2220,8 +2245,9 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) for (i = 0; i < MLX5_CMD_OP_MAX; i++) spin_lock_init(&cmd->stats[i].lock); - sema_init(&cmd->sem, cmd->max_reg_cmds); - sema_init(&cmd->pages_sem, 1); + sema_init(&cmd->vars.sem, cmd->vars.max_reg_cmds); + sema_init(&cmd->vars.pages_sem, 1); + sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2)); cmd_h = (u32)((u64)(cmd->dma) >> 32); cmd_l = (u32)(cmd->dma); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index bb95b40d25eb..e0b0729e238c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -176,8 +176,8 @@ static ssize_t slots_read(struct file *filp, char __user *buf, size_t count, int ret; cmd = filp->private_data; - weight = bitmap_weight(&cmd->bitmask, cmd->max_reg_cmds); - field = cmd->max_reg_cmds - weight; + weight = bitmap_weight(&cmd->vars.bitmask, cmd->vars.max_reg_cmds); + field = cmd->vars.max_reg_cmds - weight; ret = snprintf(tbuf, sizeof(tbuf), "%d\n", field); return simple_read_from_buffer(buf, count, pos, tbuf, ret); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 374c0011a127..3ba54ffa54bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -691,7 +691,7 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work) while (block_timestamp > tracer->last_timestamp) { /* Check block override if it's not the first block */ - if (!tracer->last_timestamp) { + if (tracer->last_timestamp) { u64 *ts_event; /* To avoid block override be the HW in case of buffer * wraparound, the time stamp of the previous block diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c index be83ad9db82a..671adbad0a40 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c @@ -154,6 +154,7 @@ static int fs_udp_create_groups(struct mlx5e_flow_table *ft, enum fs_udp_type ty in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } @@ -435,6 +436,7 @@ static int fs_any_create_groups(struct mlx5e_flow_table *ft) in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 29dd3a04c154..d3de1b7a80bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -990,8 +990,8 @@ void mlx5e_build_sq_param(struct mlx5_core_dev *mdev, void *wq = MLX5_ADDR_OF(sqc, sqc, wq); bool allow_swp; - allow_swp = - mlx5_geneve_tx_allowed(mdev) || !!mlx5_ipsec_device_caps(mdev); + allow_swp = mlx5_geneve_tx_allowed(mdev) || + (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_CRYPTO); mlx5e_build_sq_param_common(mdev, param); MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size); MLX5_SET(sqc, sqc, allow_swp, allow_swp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 4db0483c066a..83bb0811e774 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -300,6 +300,9 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, if (err) goto destroy_neigh_entry; + e->encap_size = ipv4_encap_size; + e->encap_header = encap_header; + if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event @@ -319,8 +322,6 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, goto destroy_neigh_entry; } - e->encap_size = ipv4_encap_size; - e->encap_header = encap_header; e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv4_put(&attr); @@ -403,12 +404,16 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, if (err) goto free_encap; + e->encap_size = ipv4_encap_size; + kfree(e->encap_header); + e->encap_header = encap_header; + if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event * and not used before that. */ - goto free_encap; + goto release_neigh; } memset(&reformat_params, 0, sizeof(reformat_params)); @@ -422,10 +427,6 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, goto free_encap; } - e->encap_size = ipv4_encap_size; - kfree(e->encap_header); - e->encap_header = encap_header; - e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv4_put(&attr); @@ -567,6 +568,9 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, if (err) goto destroy_neigh_entry; + e->encap_size = ipv6_encap_size; + e->encap_header = encap_header; + if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event @@ -586,8 +590,6 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, goto destroy_neigh_entry; } - e->encap_size = ipv6_encap_size; - e->encap_header = encap_header; e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv6_put(&attr); @@ -669,12 +671,16 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, if (err) goto free_encap; + e->encap_size = ipv6_encap_size; + kfree(e->encap_header); + e->encap_header = encap_header; + if (!(nud_state & NUD_VALID)) { neigh_event_send(attr.n, NULL); /* the encap entry will be made valid on neigh update event * and not used before that. */ - goto free_encap; + goto release_neigh; } memset(&reformat_params, 0, sizeof(reformat_params)); @@ -688,10 +694,6 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, goto free_encap; } - e->encap_size = ipv6_encap_size; - kfree(e->encap_header); - e->encap_header = encap_header; - e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(attr.out_dev)); mlx5e_route_lookup_ipv6_put(&attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 16bcceec16c4..785f188148d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -34,7 +34,6 @@ #ifndef __MLX5E_IPSEC_H__ #define __MLX5E_IPSEC_H__ -#ifdef CONFIG_MLX5_EN_IPSEC #include <linux/mlx5/device.h> #include <net/xfrm.h> @@ -146,6 +145,7 @@ struct mlx5e_ipsec_sa_entry { struct mlx5e_ipsec_modify_state_work modify_work; }; +#ifdef CONFIG_MLX5_EN_IPSEC int mlx5e_ipsec_init(struct mlx5e_priv *priv); void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv); void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index dc0a0a27ac84..58eacba6de8c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -255,11 +255,13 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, ft->g = kcalloc(MLX5E_ARFS_NUM_GROUPS, sizeof(*ft->g), GFP_KERNEL); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in || !ft->g) { - kfree(ft->g); - kvfree(in); + if (!ft->g) return -ENOMEM; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_free_g; } mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); @@ -279,7 +281,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, break; default: err = -EINVAL; - goto out; + goto err_free_in; } switch (type) { @@ -301,7 +303,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, break; default: err = -EINVAL; - goto out; + goto err_free_in; } MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); @@ -310,7 +312,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, MLX5_SET_CFG(in, end_flow_index, ix - 1); ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); if (IS_ERR(ft->g[ft->num_groups])) - goto err; + goto err_clean_group; ft->num_groups++; memset(in, 0, inlen); @@ -319,18 +321,20 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, MLX5_SET_CFG(in, end_flow_index, ix - 1); ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); if (IS_ERR(ft->g[ft->num_groups])) - goto err; + goto err_clean_group; ft->num_groups++; kvfree(in); return 0; -err: +err_clean_group: err = PTR_ERR(ft->g[ft->num_groups]); ft->g[ft->num_groups] = NULL; -out: +err_free_in: kvfree(in); - +err_free_g: + kfree(ft->g); + ft->g = NULL; return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index eeba91d9c521..ceeb23f478e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -49,7 +49,7 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id); - if (count == sizeof(drvinfo->fw_version)) + if (count >= sizeof(drvinfo->fw_version)) snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d", fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 2653cb96c310..5aeca9534f15 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -76,7 +76,7 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev, count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id); - if (count == sizeof(drvinfo->fw_version)) + if (count >= sizeof(drvinfo->fw_version)) snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d", fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c index c971ff04dd04..c215252f2f53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c @@ -98,7 +98,7 @@ static int create_aso_cq(struct mlx5_aso_cq *cq, void *cqc_data) mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas)); - MLX5_SET(cqc, cqc, cq_period_mode, DIM_CQ_PERIOD_MODE_START_FROM_EQE); + MLX5_SET(cqc, cqc, cq_period_mode, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index d136360ac6a9..a6d3fc96e168 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -25,7 +25,7 @@ struct mlx5_irq { struct atomic_notifier_head nh; cpumask_var_t mask; - char name[MLX5_MAX_IRQ_NAME]; + char name[MLX5_MAX_IRQ_FORMATTED_NAME]; struct mlx5_irq_pool *pool; int refcount; u32 index; @@ -236,8 +236,8 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i, else irq_sf_set_name(pool, name, i); ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh); - snprintf(irq->name, MLX5_MAX_IRQ_NAME, - "%s@pci:%s", name, pci_name(dev->pdev)); + snprintf(irq->name, MLX5_MAX_IRQ_FORMATTED_NAME, + MLX5_IRQ_NAME_FORMAT_STR, name, pci_name(dev->pdev)); err = request_irq(irq->irqn, irq_int_handler, 0, irq->name, &irq->nh); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h index 5c7e68bee43a..4047179307c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h @@ -7,6 +7,9 @@ #include <linux/mlx5/driver.h> #define MLX5_MAX_IRQ_NAME (32) +#define MLX5_IRQ_NAME_FORMAT_STR ("%s@pci:%s") +#define MLX5_MAX_IRQ_FORMATTED_NAME \ + (MLX5_MAX_IRQ_NAME + sizeof(MLX5_IRQ_NAME_FORMAT_STR)) /* max irq_index is 2047, so four chars */ #define MLX5_MAX_IRQ_IDX_CHARS (4) #define MLX5_EQ_REFS_PER_IRQ (2) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index a3e7602b044e..bf7517725d8c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -673,6 +673,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, switch (action_type) { case DR_ACTION_TYP_DROP: attr.final_icm_addr = nic_dmn->drop_icm_addr; + attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48; break; case DR_ACTION_TYP_FT: dest_action = action; @@ -761,11 +762,17 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, action->sampler->tx_icm_addr; break; case DR_ACTION_TYP_VPORT: - attr.hit_gvmi = action->vport->caps->vhca_gvmi; - dest_action = action; - attr.final_icm_addr = rx_rule ? - action->vport->caps->icm_address_rx : - action->vport->caps->icm_address_tx; + if (unlikely(rx_rule && action->vport->caps->num == MLX5_VPORT_UPLINK)) { + /* can't go to uplink on RX rule - dropping instead */ + attr.final_icm_addr = nic_dmn->drop_icm_addr; + attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48; + } else { + attr.hit_gvmi = action->vport->caps->vhca_gvmi; + dest_action = action; + attr.final_icm_addr = rx_rule ? + action->vport->caps->icm_address_rx : + action->vport->caps->icm_address_tx; + } break; case DR_ACTION_TYP_POP_VLAN: if (!rx_rule && !(dmn->ste_ctx->actions_caps & diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index d5c317325030..3f68e3198aa6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -277,7 +277,7 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, req_list_size = max_list_size; } - out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_in) + + out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_out) + req_list_size * MLX5_ST_SZ_BYTES(mac_address_layout); out = kvzalloc(out_sz, GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 2292d63a279c..83c4659390fd 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -130,9 +130,15 @@ static int mlxbf_gige_open(struct net_device *netdev) { struct mlxbf_gige *priv = netdev_priv(netdev); struct phy_device *phydev = netdev->phydev; + u64 control; u64 int_en; int err; + /* Perform general init of GigE block */ + control = readq(priv->base + MLXBF_GIGE_CONTROL); + control |= MLXBF_GIGE_CONTROL_PORT_EN; + writeq(control, priv->base + MLXBF_GIGE_CONTROL); + err = mlxbf_gige_request_irqs(priv); if (err) return err; @@ -147,14 +153,14 @@ static int mlxbf_gige_open(struct net_device *netdev) */ priv->valid_polarity = 0; - err = mlxbf_gige_rx_init(priv); + phy_start(phydev); + + err = mlxbf_gige_tx_init(priv); if (err) goto free_irqs; - err = mlxbf_gige_tx_init(priv); + err = mlxbf_gige_rx_init(priv); if (err) - goto rx_deinit; - - phy_start(phydev); + goto tx_deinit; netif_napi_add(netdev, &priv->napi, mlxbf_gige_poll); napi_enable(&priv->napi); @@ -176,8 +182,8 @@ static int mlxbf_gige_open(struct net_device *netdev) return 0; -rx_deinit: - mlxbf_gige_rx_deinit(priv); +tx_deinit: + mlxbf_gige_tx_deinit(priv); free_irqs: mlxbf_gige_free_irqs(priv); @@ -279,7 +285,6 @@ static int mlxbf_gige_probe(struct platform_device *pdev) void __iomem *plu_base; void __iomem *base; int addr, phy_irq; - u64 control; int err; base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC); @@ -294,11 +299,6 @@ static int mlxbf_gige_probe(struct platform_device *pdev) if (IS_ERR(plu_base)) return PTR_ERR(plu_base); - /* Perform general init of GigE block */ - control = readq(base + MLXBF_GIGE_CONTROL); - control |= MLXBF_GIGE_CONTROL_PORT_EN; - writeq(control, base + MLXBF_GIGE_CONTROL); - netdev = devm_alloc_etherdev(&pdev->dev, sizeof(*priv)); if (!netdev) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index 0d5a41a2ae01..699984358493 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -142,6 +142,9 @@ int mlxbf_gige_rx_init(struct mlxbf_gige *priv) writeq(MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS_EN, priv->base + MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS); + writeq(ilog2(priv->rx_q_entries), + priv->base + MLXBF_GIGE_RX_WQE_SIZE_LOG2); + /* Clear MLXBF_GIGE_INT_MASK 'receive pkt' bit to * indicate readiness to receive interrupts */ @@ -154,9 +157,6 @@ int mlxbf_gige_rx_init(struct mlxbf_gige *priv) data |= MLXBF_GIGE_RX_DMA_EN; writeq(data, priv->base + MLXBF_GIGE_RX_DMA); - writeq(ilog2(priv->rx_q_entries), - priv->base + MLXBF_GIGE_RX_WQE_SIZE_LOG2); - return 0; free_wqe_and_skb: @@ -267,6 +267,13 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) priv->stats.rx_truncate_errors++; } + /* Read receive consumer index before replenish so that this routine + * returns accurate return value even if packet is received into + * just-replenished buffer prior to exiting this routine. + */ + rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI); + rx_ci_rem = rx_ci % priv->rx_q_entries; + /* Let hardware know we've replenished one buffer */ rx_pi++; @@ -279,8 +286,6 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) rx_pi_rem = rx_pi % priv->rx_q_entries; if (rx_pi_rem == 0) priv->valid_polarity ^= 1; - rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI); - rx_ci_rem = rx_ci % priv->rx_q_entries; if (skb) netif_receive_skb(skb); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index 4c98950380d5..d231f4d2888b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -301,6 +301,7 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core, unsigned long *p_index) { unsigned int num_rows, entry_size; + unsigned long index; /* We only allow allocations of entire rows */ if (num_erps % erp_core->num_erp_banks != 0) @@ -309,10 +310,11 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core, entry_size = erp_core->erpt_entries_size[region_type]; num_rows = num_erps / erp_core->num_erp_banks; - *p_index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size); - if (*p_index == 0) + index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size); + if (!index) return -ENOBUFS; - *p_index -= MLXSW_SP_ACL_ERP_GENALLOC_OFFSET; + + *p_index = index - MLXSW_SP_ACL_ERP_GENALLOC_OFFSET; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 3b9ba8fa247a..dc2e204bcd72 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -65,6 +65,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, tcam->max_groups = max_groups; tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUP_SIZE); + tcam->max_group_size = min_t(unsigned int, tcam->max_group_size, + MLXSW_REG_PAGT_ACL_MAX_NUM); err = ops->init(mlxsw_sp, tcam->priv, tcam); if (err) diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h index fecd43754cea..e5ec0a363aff 100644 --- a/drivers/net/ethernet/micrel/ks8851.h +++ b/drivers/net/ethernet/micrel/ks8851.h @@ -350,6 +350,8 @@ union ks8851_tx_hdr { * @rxd: Space for receiving SPI data, in DMA-able space. * @txd: Space for transmitting SPI data, in DMA-able space. * @msg_enable: The message flags controlling driver output (see ethtool). + * @tx_space: Free space in the hardware TX buffer (cached copy of KS_TXMIR). + * @queued_len: Space required in hardware TX buffer for queued packets in txq. * @fid: Incrementing frame id tag. * @rc_ier: Cached copy of KS_IER. * @rc_ccr: Cached copy of KS_CCR. @@ -399,6 +401,7 @@ struct ks8851_net { struct work_struct rxctrl_work; struct sk_buff_head txq; + unsigned int queued_len; struct eeprom_93cx6 eeprom; struct regulator *vdd_reg; diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index cfbc900d4aeb..0bf13b38b8f5 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -362,16 +362,18 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) handled |= IRQ_RXPSI; if (status & IRQ_TXI) { - handled |= IRQ_TXI; + unsigned short tx_space = ks8851_rdreg16(ks, KS_TXMIR); - /* no lock here, tx queue should have been stopped */ + netif_dbg(ks, intr, ks->netdev, + "%s: txspace %d\n", __func__, tx_space); - /* update our idea of how much tx space is available to the - * system */ - ks->tx_space = ks8851_rdreg16(ks, KS_TXMIR); + spin_lock(&ks->statelock); + ks->tx_space = tx_space; + if (netif_queue_stopped(ks->netdev)) + netif_wake_queue(ks->netdev); + spin_unlock(&ks->statelock); - netif_dbg(ks, intr, ks->netdev, - "%s: txspace %d\n", __func__, ks->tx_space); + handled |= IRQ_TXI; } if (status & IRQ_RXI) @@ -414,9 +416,6 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) if (status & IRQ_LCI) mii_check_link(&ks->mii); - if (status & IRQ_TXI) - netif_wake_queue(ks->netdev); - return IRQ_HANDLED; } @@ -500,6 +499,7 @@ static int ks8851_net_open(struct net_device *dev) ks8851_wrreg16(ks, KS_ISR, ks->rc_ier); ks8851_wrreg16(ks, KS_IER, ks->rc_ier); + ks->queued_len = 0; netif_start_queue(ks->netdev); netif_dbg(ks, ifup, ks->netdev, "network device up\n"); diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c index 70bc7253454f..88e26c120b48 100644 --- a/drivers/net/ethernet/micrel/ks8851_spi.c +++ b/drivers/net/ethernet/micrel/ks8851_spi.c @@ -287,6 +287,18 @@ static void ks8851_wrfifo_spi(struct ks8851_net *ks, struct sk_buff *txp, } /** + * calc_txlen - calculate size of message to send packet + * @len: Length of data + * + * Returns the size of the TXFIFO message needed to send + * this packet. + */ +static unsigned int calc_txlen(unsigned int len) +{ + return ALIGN(len + 4, 4); +} + +/** * ks8851_rx_skb_spi - receive skbuff * @ks: The device state * @skb: The skbuff @@ -305,7 +317,9 @@ static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb) */ static void ks8851_tx_work(struct work_struct *work) { + unsigned int dequeued_len = 0; struct ks8851_net_spi *kss; + unsigned short tx_space; struct ks8851_net *ks; unsigned long flags; struct sk_buff *txb; @@ -322,6 +336,8 @@ static void ks8851_tx_work(struct work_struct *work) last = skb_queue_empty(&ks->txq); if (txb) { + dequeued_len += calc_txlen(txb->len); + ks8851_wrreg16_spi(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); ks8851_wrfifo_spi(ks, txb, last); @@ -332,6 +348,13 @@ static void ks8851_tx_work(struct work_struct *work) } } + tx_space = ks8851_rdreg16_spi(ks, KS_TXMIR); + + spin_lock(&ks->statelock); + ks->queued_len -= dequeued_len; + ks->tx_space = tx_space; + spin_unlock(&ks->statelock); + ks8851_unlock_spi(ks, &flags); } @@ -347,18 +370,6 @@ static void ks8851_flush_tx_work_spi(struct ks8851_net *ks) } /** - * calc_txlen - calculate size of message to send packet - * @len: Length of data - * - * Returns the size of the TXFIFO message needed to send - * this packet. - */ -static unsigned int calc_txlen(unsigned int len) -{ - return ALIGN(len + 4, 4); -} - -/** * ks8851_start_xmit_spi - transmit packet using SPI * @skb: The buffer to transmit * @dev: The device used to transmit the packet. @@ -386,16 +397,17 @@ static netdev_tx_t ks8851_start_xmit_spi(struct sk_buff *skb, spin_lock(&ks->statelock); - if (needed > ks->tx_space) { + if (ks->queued_len + needed > ks->tx_space) { netif_stop_queue(dev); ret = NETDEV_TX_BUSY; } else { - ks->tx_space -= needed; + ks->queued_len += needed; skb_queue_tail(&ks->txq, skb); } spin_unlock(&ks->statelock); - schedule_work(&kss->tx_work); + if (ret == NETDEV_TX_OK) + schedule_work(&kss->tx_work); return ret; } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c index 41fa2523d91d..5f2cd9a8cf8f 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c @@ -37,19 +37,24 @@ static void lan966x_lag_set_aggr_pgids(struct lan966x *lan966x) /* Now, set PGIDs for each active LAG */ for (lag = 0; lag < lan966x->num_phys_ports; ++lag) { - struct net_device *bond = lan966x->ports[lag]->bond; + struct lan966x_port *port = lan966x->ports[lag]; int num_active_ports = 0; + struct net_device *bond; unsigned long bond_mask; u8 aggr_idx[16]; - if (!bond || (visited & BIT(lag))) + if (!port || !port->bond || (visited & BIT(lag))) continue; + bond = port->bond; bond_mask = lan966x_lag_get_mask(lan966x, bond); for_each_set_bit(p, &bond_mask, lan966x->num_phys_ports) { struct lan966x_port *port = lan966x->ports[p]; + if (!port) + continue; + lan_wr(ANA_PGID_PGID_SET(bond_mask), lan966x, ANA_PGID(p)); if (port->lag_tx_active) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c index 0050fcb988b7..8cc5172833a9 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c @@ -168,9 +168,10 @@ static void lan966x_port_link_up(struct lan966x_port *port) lan966x_taprio_speed_set(port, config->speed); /* Also the GIGA_MODE_ENA(1) needs to be set regardless of the - * port speed for QSGMII ports. + * port speed for QSGMII or SGMII ports. */ - if (phy_interface_num_ports(config->portmode) == 4) + if (phy_interface_num_ports(config->portmode) == 4 || + config->portmode == PHY_INTERFACE_MODE_SGMII) mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA_SET(1); lan_wr(config->duplex | mode, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index 3423c95cc84a..7031f41287e0 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -744,6 +744,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev) platform_set_drvdata(pdev, sparx5); sparx5->pdev = pdev; sparx5->dev = &pdev->dev; + spin_lock_init(&sparx5->tx_lock); /* Do switch core reset if available */ reset = devm_reset_control_get_optional_shared(&pdev->dev, "switch"); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index 7a83222caa73..cb3173d2b0e8 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -278,6 +278,7 @@ struct sparx5 { int xtr_irq; /* Frame DMA */ int fdma_irq; + spinlock_t tx_lock; /* lock for frame transmission */ struct sparx5_rx rx; struct sparx5_tx tx; /* PTP */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index 6db6ac6a3bbc..ac7e1cffbcec 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -244,10 +244,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) } skb_tx_timestamp(skb); + spin_lock(&sparx5->tx_lock); if (sparx5->fdma_irq > 0) ret = sparx5_fdma_xmit(sparx5, ifh, skb); else ret = sparx5_inject(sparx5, ifh, skb, dev); + spin_unlock(&sparx5->tx_lock); if (ret == -EBUSY) goto busy; diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig index fe4e7a7d9c0b..8b6c4cc37c53 100644 --- a/drivers/net/ethernet/microsoft/Kconfig +++ b/drivers/net/ethernet/microsoft/Kconfig @@ -19,6 +19,7 @@ config MICROSOFT_MANA tristate "Microsoft Azure Network Adapter (MANA) support" depends on PCI_MSI && X86_64 depends on PCI_HYPERV + select PAGE_POOL help This driver supports Microsoft Azure Network Adapter (MANA). So far, the driver is only supported on X86_64. diff --git a/drivers/net/ethernet/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c index 0066219bb0e8..6b95262dad90 100644 --- a/drivers/net/ethernet/mscc/ocelot_stats.c +++ b/drivers/net/ethernet/mscc/ocelot_stats.c @@ -216,10 +216,10 @@ static void ocelot_port_rmon_stats_cb(struct ocelot *ocelot, int port, void *pri rmon_stats->hist_tx[0] = s[OCELOT_STAT_TX_64]; rmon_stats->hist_tx[1] = s[OCELOT_STAT_TX_65_127]; rmon_stats->hist_tx[2] = s[OCELOT_STAT_TX_128_255]; - rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_128_255]; - rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_256_511]; - rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_512_1023]; - rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_1024_1526]; + rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_256_511]; + rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_512_1023]; + rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_1024_1526]; + rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_1527_MAX]; } void ocelot_port_get_rmon_stats(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c index f7492be452ae..7af03b45555d 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -1379,10 +1379,30 @@ static void nfp_nft_ct_translate_mangle_action(struct flow_action_entry *mangle_ mangle_action->mangle.mask = (__force u32)cpu_to_be32(mangle_action->mangle.mask); return; + /* Both struct tcphdr and struct udphdr start with + * __be16 source; + * __be16 dest; + * so we can use the same code for both. + */ case FLOW_ACT_MANGLE_HDR_TYPE_TCP: case FLOW_ACT_MANGLE_HDR_TYPE_UDP: - mangle_action->mangle.val = (__force u16)cpu_to_be16(mangle_action->mangle.val); - mangle_action->mangle.mask = (__force u16)cpu_to_be16(mangle_action->mangle.mask); + if (mangle_action->mangle.offset == offsetof(struct tcphdr, source)) { + mangle_action->mangle.val = + (__force u32)cpu_to_be32(mangle_action->mangle.val << 16); + /* The mask of mangle action is inverse mask, + * so clear the dest tp port with 0xFFFF to + * instead of rotate-left operation. + */ + mangle_action->mangle.mask = + (__force u32)cpu_to_be32(mangle_action->mangle.mask << 16 | 0xFFFF); + } + if (mangle_action->mangle.offset == offsetof(struct tcphdr, dest)) { + mangle_action->mangle.offset = 0; + mangle_action->mangle.val = + (__force u32)cpu_to_be32(mangle_action->mangle.val); + mangle_action->mangle.mask = + (__force u32)cpu_to_be32(mangle_action->mangle.mask); + } return; default: diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 52f67157bd0f..a3c52c91a575 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -980,7 +980,7 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev, u16 nfp_mac_idx = 0; entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr); - if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) { + if (entry && (nfp_tunnel_is_mac_idx_global(entry->index) || netif_is_lag_port(netdev))) { if (entry->bridge_count || !nfp_flower_is_supported_bridge(netdev)) { nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c index 33b4c2856316..3f10c5365c80 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c @@ -537,11 +537,13 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface) const u32 barcfg_msix_general = NFP_PCIE_BAR_PCIE2CPP_MapType( NFP_PCIE_BAR_PCIE2CPP_MapType_GENERAL) | - NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT; + NFP_PCIE_BAR_PCIE2CPP_LengthSelect( + NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT); const u32 barcfg_msix_xpb = NFP_PCIE_BAR_PCIE2CPP_MapType( NFP_PCIE_BAR_PCIE2CPP_MapType_BULK) | - NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT | + NFP_PCIE_BAR_PCIE2CPP_LengthSelect( + NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT) | NFP_PCIE_BAR_PCIE2CPP_Target_BaseAddress( NFP_CPP_TARGET_ISLAND_XPB); const u32 barcfg_explicit[4] = { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index ce436e97324a..4b9caec6eb9b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -380,6 +380,10 @@ static void ionic_remove(struct pci_dev *pdev) del_timer_sync(&ionic->watchdog_timer); if (ionic->lif) { + /* prevent adminq cmds if already known as down */ + if (test_and_clear_bit(IONIC_LIF_F_FW_RESET, ionic->lif->state)) + set_bit(IONIC_LIF_F_FW_STOPPING, ionic->lif->state); + ionic_lif_unregister(ionic->lif); ionic_devlink_unregister(ionic); ionic_lif_deinit(ionic->lif); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 344a3924627d..7adfcd7c2f3a 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -293,6 +293,7 @@ void ionic_dev_cmd_comp(struct ionic_dev *idev, union ionic_dev_cmd_comp *comp) void ionic_dev_cmd_go(struct ionic_dev *idev, union ionic_dev_cmd *cmd) { + idev->opcode = cmd->cmd.opcode; memcpy_toio(&idev->dev_cmd_regs->cmd, cmd, sizeof(*cmd)); iowrite32(0, &idev->dev_cmd_regs->done); iowrite32(1, &idev->dev_cmd_regs->doorbell); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index 13dfcf9f75da..c10da629ef6e 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -150,6 +150,7 @@ struct ionic_dev { bool fw_hb_ready; bool fw_status_ready; u8 fw_generation; + u8 opcode; u64 __iomem *db_pages; dma_addr_t phy_db_pages; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index f7634884c750..fcc3faecb060 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3008,6 +3008,9 @@ static void ionic_lif_reset(struct ionic_lif *lif) { struct ionic_dev *idev = &lif->ionic->idev; + if (!ionic_is_fw_running(idev)) + return; + mutex_lock(&lif->ionic->dev_cmd_lock); ionic_dev_cmd_lif_reset(idev, lif->index); ionic_dev_cmd_wait(lif->ionic, DEVCMD_TIMEOUT); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 79272f5f380c..d2038ff316ca 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -410,22 +410,28 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, do_msg); } -int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) +static int __ionic_adminq_post_wait(struct ionic_lif *lif, + struct ionic_admin_ctx *ctx, + const bool do_msg) { int err; + if (!ionic_is_fw_running(&lif->ionic->idev)) + return 0; + err = ionic_adminq_post(lif, ctx); - return ionic_adminq_wait(lif, ctx, err, true); + return ionic_adminq_wait(lif, ctx, err, do_msg); } -int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) +int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) { - int err; - - err = ionic_adminq_post(lif, ctx); + return __ionic_adminq_post_wait(lif, ctx, true); +} - return ionic_adminq_wait(lif, ctx, err, false); +int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) +{ + return __ionic_adminq_post_wait(lif, ctx, false); } static void ionic_dev_cmd_clean(struct ionic *ionic) @@ -465,7 +471,7 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds, */ max_wait = jiffies + (max_seconds * HZ); try_again: - opcode = readb(&idev->dev_cmd_regs->cmd.cmd.opcode); + opcode = idev->opcode; start_time = jiffies; for (fw_up = ionic_is_fw_running(idev); !done && fw_up && time_before(jiffies, max_wait); diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 0d57ffcedf0c..fc78bc959ded 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2591,6 +2591,7 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev) if (qdev->lrg_buf_q_alloc_virt_addr == NULL) { netdev_err(qdev->ndev, "lBufQ failed\n"); + kfree(qdev->lrg_buf); return -ENOMEM; } qdev->lrg_buf_q_virt_addr = qdev->lrg_buf_q_alloc_virt_addr; @@ -2615,6 +2616,7 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev) qdev->lrg_buf_q_alloc_size, qdev->lrg_buf_q_alloc_virt_addr, qdev->lrg_buf_q_alloc_phy_addr); + kfree(qdev->lrg_buf); return -ENOMEM; } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 27b1663c476e..64b209a0ad21 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -391,7 +391,7 @@ nla_put_failure: struct rtnl_link_ops rmnet_link_ops __read_mostly = { .kind = "rmnet", - .maxtype = __IFLA_RMNET_MAX, + .maxtype = IFLA_RMNET_MAX, .priv_size = sizeof(struct rmnet_priv), .setup = rmnet_vnd_setup, .validate = rmnet_rtnl_validate, diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index d22457f2cf9c..06663c11ca96 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1145,7 +1145,7 @@ static void rtl8168ep_driver_start(struct rtl8169_private *tp) { r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START); r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01); - rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 10); + rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); } static void rtl8168_driver_start(struct rtl8169_private *tp) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 68cb5616ef99..e7b70006261f 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -68,16 +68,27 @@ int ravb_wait(struct net_device *ndev, enum ravb_reg reg, u32 mask, u32 value) return -ETIMEDOUT; } -static int ravb_config(struct net_device *ndev) +static int ravb_set_opmode(struct net_device *ndev, u32 opmode) { + u32 csr_ops = 1U << (opmode & CCC_OPC); + u32 ccc_mask = CCC_OPC; int error; - /* Set config mode */ - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); - /* Check if the operating mode is changed to the config mode */ - error = ravb_wait(ndev, CSR, CSR_OPS, CSR_OPS_CONFIG); - if (error) - netdev_err(ndev, "failed to switch device to config mode\n"); + /* If gPTP active in config mode is supported it needs to be configured + * along with CSEL and operating mode in the same access. This is a + * hardware limitation. + */ + if (opmode & CCC_GAC) + ccc_mask |= CCC_GAC | CCC_CSEL; + + /* Set operating mode */ + ravb_modify(ndev, CCC, ccc_mask, opmode); + /* Check if the operating mode is changed to the requested one */ + error = ravb_wait(ndev, CSR, CSR_OPS, csr_ops); + if (error) { + netdev_err(ndev, "failed to switch device to requested mode (%u)\n", + opmode & CCC_OPC); + } return error; } @@ -675,7 +686,7 @@ static int ravb_dmac_init(struct net_device *ndev) int error; /* Set CONFIG mode */ - error = ravb_config(ndev); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); if (error) return error; @@ -684,9 +695,7 @@ static int ravb_dmac_init(struct net_device *ndev) return error; /* Setting the control will start the AVB-DMAC process. */ - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_OPERATION); - - return 0; + return ravb_set_opmode(ndev, CCC_OPC_OPERATION); } static void ravb_get_tx_tstamp(struct net_device *ndev) @@ -1048,7 +1057,7 @@ static int ravb_stop_dma(struct net_device *ndev) return error; /* Stop AVB-DMAC process */ - return ravb_config(ndev); + return ravb_set_opmode(ndev, CCC_OPC_CONFIG); } /* E-MAC interrupt handler */ @@ -1956,7 +1965,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct ravb_tstamp_skb *ts_skb; struct ravb_tx_desc *desc; unsigned long flags; - u32 dma_addr; + dma_addr_t dma_addr; void *buffer; u32 entry; u32 len; @@ -2576,21 +2585,25 @@ static int ravb_set_gti(struct net_device *ndev) return 0; } -static void ravb_set_config_mode(struct net_device *ndev) +static int ravb_set_config_mode(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; + int error; if (info->gptp) { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); + if (error) + return error; /* Set CSEL value */ ravb_modify(ndev, CCC, CCC_CSEL, CCC_CSEL_HPB); } else if (info->ccc_gac) { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG | - CCC_GAC | CCC_CSEL_HPB); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG | CCC_GAC | CCC_CSEL_HPB); } else { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); } + + return error; } /* Set tx and rx clock internal delay modes */ @@ -2810,7 +2823,9 @@ static int ravb_probe(struct platform_device *pdev) ndev->ethtool_ops = &ravb_ethtool_ops; /* Set AVB config mode */ - ravb_set_config_mode(ndev); + error = ravb_set_config_mode(ndev); + if (error) + goto out_disable_gptp_clk; if (info->gptp || info->ccc_gac) { /* Set GTI value */ @@ -2933,8 +2948,7 @@ static int ravb_remove(struct platform_device *pdev) dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat, priv->desc_bat_dma); - /* Set reset mode */ - ravb_write(ndev, CCC_OPC_RESET, CCC); + ravb_set_opmode(ndev, CCC_OPC_RESET); clk_disable_unprepare(priv->gptp_clk); clk_disable_unprepare(priv->refclk); @@ -3018,8 +3032,11 @@ static int __maybe_unused ravb_resume(struct device *dev) int ret = 0; /* If WoL is enabled set reset mode to rearm the WoL logic */ - if (priv->wol_enabled) - ravb_write(ndev, CCC_OPC_RESET, CCC); + if (priv->wol_enabled) { + ret = ravb_set_opmode(ndev, CCC_OPC_RESET); + if (ret) + return ret; + } /* All register have been reset to default values. * Restore all registers which where setup at probe time and @@ -3027,7 +3044,9 @@ static int __maybe_unused ravb_resume(struct device *dev) */ /* Set AVB config mode */ - ravb_set_config_mode(ndev); + ret = ravb_set_config_mode(ndev); + if (ret) + return ret; if (info->gptp || info->ccc_gac) { /* Set GTI value */ diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 9220afeddee8..3f290791df1c 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -820,8 +820,10 @@ int efx_probe_filters(struct efx_nic *efx) } if (!success) { - efx_for_each_channel(channel, efx) + efx_for_each_channel(channel, efx) { kfree(channel->rps_flow_id); + channel->rps_flow_id = NULL; + } efx->type->filter_table_remove(efx); rc = -ENOMEM; goto out_unlock; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 54bb072aeb2d..c11d62685624 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -209,6 +209,7 @@ struct stmmac_safety_stats { unsigned long mac_errors[32]; unsigned long mtl_errors[32]; unsigned long dma_errors[32]; + unsigned long dma_dpp_errors[32]; }; /* Number of fields in Safety Stats */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 49c7aa86faaa..e129ee1020f0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -59,11 +59,6 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id return -ENODEV; } - if (!of_device_is_compatible(np, "loongson, pci-gmac")) { - pr_info("dwmac_loongson_pci: Incompatible OF node\n"); - return -ENODEV; - } - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) return -ENOMEM; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 880a75bf2eb1..8748c37e9dac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -282,6 +282,8 @@ #define XGMAC_RXCEIE BIT(4) #define XGMAC_TXCEIE BIT(0) #define XGMAC_MTL_ECC_INT_STATUS 0x000010cc +#define XGMAC_MTL_DPP_CONTROL 0x000010e0 +#define XGMAC_DPP_DISABLE BIT(0) #define XGMAC_MTL_TXQ_OPMODE(x) (0x00001100 + (0x80 * (x))) #define XGMAC_TQS GENMASK(25, 16) #define XGMAC_TQS_SHIFT 16 @@ -364,6 +366,7 @@ #define XGMAC_DCEIE BIT(1) #define XGMAC_TCEIE BIT(0) #define XGMAC_DMA_ECC_INT_STATUS 0x0000306c +#define XGMAC_DMA_DPP_INT_STATUS 0x00003074 #define XGMAC_DMA_CH_CONTROL(x) (0x00003100 + (0x80 * (x))) #define XGMAC_SPH BIT(24) #define XGMAC_PBLx8 BIT(16) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index c2181c277291..ec1616ffbfa7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -789,6 +789,44 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= { { false, "UNKNOWN", "Unknown Error" }, /* 31 */ }; +#define DPP_RX_ERR "Read Rx Descriptor Parity checker Error" +#define DPP_TX_ERR "Read Tx Descriptor Parity checker Error" + +static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = { + { true, "TDPES0", DPP_TX_ERR }, + { true, "TDPES1", DPP_TX_ERR }, + { true, "TDPES2", DPP_TX_ERR }, + { true, "TDPES3", DPP_TX_ERR }, + { true, "TDPES4", DPP_TX_ERR }, + { true, "TDPES5", DPP_TX_ERR }, + { true, "TDPES6", DPP_TX_ERR }, + { true, "TDPES7", DPP_TX_ERR }, + { true, "TDPES8", DPP_TX_ERR }, + { true, "TDPES9", DPP_TX_ERR }, + { true, "TDPES10", DPP_TX_ERR }, + { true, "TDPES11", DPP_TX_ERR }, + { true, "TDPES12", DPP_TX_ERR }, + { true, "TDPES13", DPP_TX_ERR }, + { true, "TDPES14", DPP_TX_ERR }, + { true, "TDPES15", DPP_TX_ERR }, + { true, "RDPES0", DPP_RX_ERR }, + { true, "RDPES1", DPP_RX_ERR }, + { true, "RDPES2", DPP_RX_ERR }, + { true, "RDPES3", DPP_RX_ERR }, + { true, "RDPES4", DPP_RX_ERR }, + { true, "RDPES5", DPP_RX_ERR }, + { true, "RDPES6", DPP_RX_ERR }, + { true, "RDPES7", DPP_RX_ERR }, + { true, "RDPES8", DPP_RX_ERR }, + { true, "RDPES9", DPP_RX_ERR }, + { true, "RDPES10", DPP_RX_ERR }, + { true, "RDPES11", DPP_RX_ERR }, + { true, "RDPES12", DPP_RX_ERR }, + { true, "RDPES13", DPP_RX_ERR }, + { true, "RDPES14", DPP_RX_ERR }, + { true, "RDPES15", DPP_RX_ERR }, +}; + static void dwxgmac3_handle_dma_err(struct net_device *ndev, void __iomem *ioaddr, bool correctable, struct stmmac_safety_stats *stats) @@ -800,6 +838,13 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev, dwxgmac3_log_error(ndev, value, correctable, "DMA", dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats); + + value = readl(ioaddr + XGMAC_DMA_DPP_INT_STATUS); + writel(value, ioaddr + XGMAC_DMA_DPP_INT_STATUS); + + dwxgmac3_log_error(ndev, value, false, "DMA_DPP", + dwxgmac3_dma_dpp_errors, + STAT_OFF(dma_dpp_errors), stats); } static int @@ -838,6 +883,12 @@ dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp, value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */ writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL); + /* 5. Enable Data Path Parity Protection */ + value = readl(ioaddr + XGMAC_MTL_DPP_CONTROL); + /* already enabled by default, explicit enable it again */ + value &= ~XGMAC_DPP_DISABLE; + writel(value, ioaddr + XGMAC_MTL_DPP_CONTROL); + return 0; } @@ -871,7 +922,11 @@ static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev, ret |= !corr; } - err = dma & (XGMAC_DEUIS | XGMAC_DECIS); + /* DMA_DPP_Interrupt_Status is indicated by MCSIS bit in + * DMA_Safety_Interrupt_Status, so we handle DMA Data Path + * Parity Errors here + */ + err = dma & (XGMAC_DEUIS | XGMAC_DECIS | XGMAC_MCSIS); corr = dma & XGMAC_DECIS; if (err) { dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats); @@ -887,6 +942,7 @@ static const struct dwxgmac3_error { { dwxgmac3_mac_errors }, { dwxgmac3_mtl_errors }, { dwxgmac3_dma_errors }, + { dwxgmac3_dma_dpp_errors }, }; static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index bdbf86cb102a..46944c02b45e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -247,6 +247,7 @@ struct stmmac_priv { u32 msg_enable; int wolopts; int wol_irq; + bool wol_irq_disabled; int clk_csr; struct timer_list eee_ctrl_timer; int lpi_irq; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 35c8dd92d369..f03aa8a0b895 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -761,10 +761,16 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) if (wol->wolopts) { pr_info("stmmac: wakeup enable\n"); device_set_wakeup_enable(priv->device, 1); - enable_irq_wake(priv->wol_irq); + /* Avoid unbalanced enable_irq_wake calls */ + if (priv->wol_irq_disabled) + enable_irq_wake(priv->wol_irq); + priv->wol_irq_disabled = false; } else { device_set_wakeup_enable(priv->device, 0); - disable_irq_wake(priv->wol_irq); + /* Avoid unbalanced disable_irq_wake calls */ + if (!priv->wol_irq_disabled) + disable_irq_wake(priv->wol_irq); + priv->wol_irq_disabled = true; } mutex_lock(&priv->lock); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index deb6e95a1bca..91b2aa81914b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3519,6 +3519,7 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev) /* Request the Wake IRQ in case of another line * is used for WoL */ + priv->wol_irq_disabled = true; if (priv->wol_irq > 0 && priv->wol_irq != dev->irq) { int_name = priv->int_name_wol; sprintf(int_name, "%s:%s", dev->name, "wol"); @@ -3825,6 +3826,9 @@ static int __stmmac_open(struct net_device *dev, priv->rx_copybreak = STMMAC_RX_COPYBREAK; buf_sz = dma_conf->dma_buf_sz; + for (int i = 0; i < MTL_MAX_TX_QUEUES; i++) + if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN) + dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs; memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf)); stmmac_reset_queues_param(priv); @@ -5819,11 +5823,6 @@ static irqreturn_t stmmac_mac_interrupt(int irq, void *dev_id) struct net_device *dev = (struct net_device *)dev_id; struct stmmac_priv *priv = netdev_priv(dev); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -5839,11 +5838,6 @@ static irqreturn_t stmmac_safety_interrupt(int irq, void *dev_id) struct net_device *dev = (struct net_device *)dev_id; struct stmmac_priv *priv = netdev_priv(dev); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -5865,11 +5859,6 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data) dma_conf = container_of(tx_q, struct stmmac_dma_conf, tx_queue[chan]); priv = container_of(dma_conf, struct stmmac_priv, dma_conf); - if (unlikely(!data)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -5896,11 +5885,6 @@ static irqreturn_t stmmac_msi_intr_rx(int irq, void *data) dma_conf = container_of(rx_q, struct stmmac_dma_conf, rx_queue[chan]); priv = container_of(dma_conf, struct stmmac_priv, dma_conf); - if (unlikely(!data)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -7165,6 +7149,9 @@ int stmmac_dvr_probe(struct device *device, dev_err(priv->device, "unable to bring out of ahb reset: %pe\n", ERR_PTR(ret)); + /* Wait a bit for the reset to take effect */ + udelay(10); + /* Init MAC and get the capabilities */ ret = stmmac_hw_init(priv); if (ret) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index cf7d6306fe07..cf76bade4ace 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -55,7 +55,7 @@ #define AM65_CPSW_MAX_PORTS 8 #define AM65_CPSW_MIN_PACKET_SIZE VLAN_ETH_ZLEN -#define AM65_CPSW_MAX_PACKET_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) +#define AM65_CPSW_MAX_PACKET_SIZE 2024 #define AM65_CPSW_REG_CTL 0x004 #define AM65_CPSW_REG_STAT_PORT_EN 0x014 @@ -2237,7 +2237,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) eth_hw_addr_set(port->ndev, port->slave.mac_addr); port->ndev->min_mtu = AM65_CPSW_MIN_PACKET_SIZE; - port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE; + port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE - + (VLAN_ETH_HLEN + ETH_FCS_LEN); port->ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM | diff --git a/drivers/net/ethernet/ti/cpsw-proxy-client.c b/drivers/net/ethernet/ti/cpsw-proxy-client.c index bda48cbb7c4d..de353db4be34 100644 --- a/drivers/net/ethernet/ti/cpsw-proxy-client.c +++ b/drivers/net/ethernet/ti/cpsw-proxy-client.c @@ -469,7 +469,7 @@ static int cpsw_proxy_client_cb(struct rpmsg_device *rpdev, void *data, u32 msg_type = msg->msg_hdr.msg_type; u32 notify_type, response_id, token; struct cpsw_virt_port *virt_port; - int response_status, ret = 0; + int ret = 0; switch (msg_type) { case ETHREMOTECFG_MSG_NOTIFY: @@ -519,7 +519,6 @@ static int cpsw_proxy_client_cb(struct rpmsg_device *rpdev, void *data, case ETHREMOTECFG_MSG_RESPONSE: response_msg_hdr = (struct response_message_header *)msg; response_id = response_msg_hdr->response_id; - response_status = response_msg_hdr->response_status; if (response_id == common->request_id - 1) { dev_info(common->dev, "ignoring delayed response for request: %u\n", @@ -1381,10 +1380,8 @@ static int cpsw_virt_port_tx_poll(struct napi_struct *napi_tx, int budget) } /* RX psdata[2] word format - checksum information */ -#define CPSW_RX_PSD_CSUM_ADD GENMASK(15, 0) #define CPSW_RX_PSD_CSUM_ERR BIT(16) #define CPSW_RX_PSD_IS_FRAGMENT BIT(17) -#define CPSW_RX_PSD_IS_TCP BIT(18) #define CPSW_RX_PSD_IPV6_VALID BIT(19) #define CPSW_RX_PSD_IPV4_VALID BIT(20) @@ -1750,8 +1747,7 @@ static void cpsw_proxy_client_detach(struct cpsw_proxy_common *common) /* Free TX DMA Channel */ for (j = 0; j < virt_port->num_tx_chan; j++) { - if (&virt_port->virt_port_tx_chan && - &virt_port->virt_port_tx_chan->is_valid) { + if (virt_port->virt_port_tx_chan->is_valid) { virt_port->curr_tx_chan_idx = j; ret = cpsw_proxy_client_send_request(common, virt_port, virt_port->virt_port_token, @@ -1767,8 +1763,7 @@ static void cpsw_proxy_client_detach(struct cpsw_proxy_common *common) /* Free RX DMA Flow */ for (j = 0; j < virt_port->num_rx_chan; j++) { - if (&virt_port->virt_port_rx_chan && - &virt_port->virt_port_rx_chan->is_valid) { + if (virt_port->virt_port_rx_chan->is_valid) { virt_port->curr_rx_chan_idx = j; ret = cpsw_proxy_client_send_request(common, virt_port, virt_port->virt_port_token, diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index 704e949484d0..b9b5554ea862 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -221,21 +221,25 @@ static int fjes_hw_setup(struct fjes_hw *hw) mem_size = FJES_DEV_REQ_BUF_SIZE(hw->max_epid); hw->hw_info.req_buf = kzalloc(mem_size, GFP_KERNEL); - if (!(hw->hw_info.req_buf)) - return -ENOMEM; + if (!(hw->hw_info.req_buf)) { + result = -ENOMEM; + goto free_ep_info; + } hw->hw_info.req_buf_size = mem_size; mem_size = FJES_DEV_RES_BUF_SIZE(hw->max_epid); hw->hw_info.res_buf = kzalloc(mem_size, GFP_KERNEL); - if (!(hw->hw_info.res_buf)) - return -ENOMEM; + if (!(hw->hw_info.res_buf)) { + result = -ENOMEM; + goto free_req_buf; + } hw->hw_info.res_buf_size = mem_size; result = fjes_hw_alloc_shared_status_region(hw); if (result) - return result; + goto free_res_buf; hw->hw_info.buffer_share_bit = 0; hw->hw_info.buffer_unshare_reserve_bit = 0; @@ -246,11 +250,11 @@ static int fjes_hw_setup(struct fjes_hw *hw) result = fjes_hw_alloc_epbuf(&buf_pair->tx); if (result) - return result; + goto free_epbuf; result = fjes_hw_alloc_epbuf(&buf_pair->rx); if (result) - return result; + goto free_epbuf; spin_lock_irqsave(&hw->rx_status_lock, flags); fjes_hw_setup_epbuf(&buf_pair->tx, mac, @@ -273,6 +277,25 @@ static int fjes_hw_setup(struct fjes_hw *hw) fjes_hw_init_command_registers(hw, ¶m); return 0; + +free_epbuf: + for (epidx = 0; epidx < hw->max_epid ; epidx++) { + if (epidx == hw->my_epid) + continue; + fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].tx); + fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].rx); + } + fjes_hw_free_shared_status_region(hw); +free_res_buf: + kfree(hw->hw_info.res_buf); + hw->hw_info.res_buf = NULL; +free_req_buf: + kfree(hw->hw_info.req_buf); + hw->hw_info.req_buf = NULL; +free_ep_info: + kfree(hw->ep_shm_info); + hw->ep_shm_info = NULL; + return result; } static void fjes_hw_cleanup(struct fjes_hw *hw) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 477b4d4f860b..937dd9cf4fba 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -629,7 +629,7 @@ static void __gtp_encap_destroy(struct sock *sk) gtp->sk0 = NULL; else gtp->sk1u = NULL; - udp_sk(sk)->encap_type = 0; + WRITE_ONCE(udp_sk(sk)->encap_type, 0); rcu_assign_sk_user_data(sk, NULL); release_sock(sk); sock_put(sk); @@ -681,7 +681,7 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk); - switch (udp_sk(sk)->encap_type) { + switch (READ_ONCE(udp_sk(sk)->encap_type)) { case UDP_ENCAP_GTP0: netdev_dbg(gtp->dev, "received GTP0 packet\n"); ret = gtp0_udp_encap_recv(gtp, skb); @@ -1906,20 +1906,20 @@ static int __init gtp_init(void) if (err < 0) goto error_out; - err = genl_register_family(>p_genl_family); + err = register_pernet_subsys(>p_net_ops); if (err < 0) goto unreg_rtnl_link; - err = register_pernet_subsys(>p_net_ops); + err = genl_register_family(>p_genl_family); if (err < 0) - goto unreg_genl_family; + goto unreg_pernet_subsys; pr_info("GTP module loaded (pdp ctx size %zd bytes)\n", sizeof(struct pdp_ctx)); return 0; -unreg_genl_family: - genl_unregister_family(>p_genl_family); +unreg_pernet_subsys: + unregister_pernet_subsys(>p_net_ops); unreg_rtnl_link: rtnl_link_unregister(>p_link_ops); error_out: diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index da737d959e81..3a834d4e1c84 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -740,7 +740,10 @@ void netvsc_device_remove(struct hv_device *device) /* Disable NAPI and disassociate its context from the device. */ for (i = 0; i < net_device->num_chn; i++) { /* See also vmbus_reset_channel_cb(). */ - napi_disable(&net_device->chan_table[i].napi); + /* only disable enabled NAPI channel */ + if (i < ndev->real_num_rx_queues) + napi_disable(&net_device->chan_table[i].napi); + netif_napi_del(&net_device->chan_table[i].napi); } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 0285894c892a..1b7405539984 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -42,9 +42,13 @@ #define LINKCHANGE_INT (2 * HZ) #define VF_TAKEOVER_INT (HZ / 10) +/* Macros to define the context of vf registration */ +#define VF_REG_IN_PROBE 1 +#define VF_REG_IN_NOTIFIER 2 + static unsigned int ring_size __ro_after_init = 128; module_param(ring_size, uint, 0444); -MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)"); +MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)"); unsigned int netvsc_ring_bytes __ro_after_init; static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE | @@ -2181,7 +2185,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb) } static int netvsc_vf_join(struct net_device *vf_netdev, - struct net_device *ndev) + struct net_device *ndev, int context) { struct net_device_context *ndev_ctx = netdev_priv(ndev); int ret; @@ -2204,7 +2208,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto upper_link_failed; } - schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); + /* If this registration is called from probe context vf_takeover + * is taken care of later in probe itself. + */ + if (context == VF_REG_IN_NOTIFIER) + schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); call_netdevice_notifiers(NETDEV_JOIN, vf_netdev); @@ -2342,7 +2350,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev) return NOTIFY_DONE; } -static int netvsc_register_vf(struct net_device *vf_netdev) +static int netvsc_register_vf(struct net_device *vf_netdev, int context) { struct net_device_context *net_device_ctx; struct netvsc_device *netvsc_dev; @@ -2382,7 +2390,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev) netdev_info(ndev, "VF registering: %s\n", vf_netdev->name); - if (netvsc_vf_join(vf_netdev, ndev) != 0) + if (netvsc_vf_join(vf_netdev, ndev, context) != 0) return NOTIFY_DONE; dev_hold(vf_netdev); @@ -2480,10 +2488,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) return NOTIFY_OK; } +static int check_dev_is_matching_vf(struct net_device *event_ndev) +{ + /* Skip NetVSC interfaces */ + if (event_ndev->netdev_ops == &device_ops) + return -ENODEV; + + /* Avoid non-Ethernet type devices */ + if (event_ndev->type != ARPHRD_ETHER) + return -ENODEV; + + /* Avoid Vlan dev with same MAC registering as VF */ + if (is_vlan_dev(event_ndev)) + return -ENODEV; + + /* Avoid Bonding master dev with same MAC registering as VF */ + if (netif_is_bond_master(event_ndev)) + return -ENODEV; + + return 0; +} + static int netvsc_probe(struct hv_device *dev, const struct hv_vmbus_device_id *dev_id) { - struct net_device *net = NULL; + struct net_device *net = NULL, *vf_netdev; struct net_device_context *net_device_ctx; struct netvsc_device_info *device_info = NULL; struct netvsc_device *nvdev; @@ -2592,6 +2621,30 @@ static int netvsc_probe(struct hv_device *dev, } list_add(&net_device_ctx->list, &netvsc_dev_list); + + /* When the hv_netvsc driver is unloaded and reloaded, the + * NET_DEVICE_REGISTER for the vf device is replayed before probe + * is complete. This is because register_netdevice_notifier() gets + * registered before vmbus_driver_register() so that callback func + * is set before probe and we don't miss events like NETDEV_POST_INIT + * So, in this section we try to register the matching vf device that + * is present as a netdevice, knowing that its register call is not + * processed in the netvsc_netdev_notifier(as probing is progress and + * get_netvsc_byslot fails). + */ + for_each_netdev(dev_net(net), vf_netdev) { + ret = check_dev_is_matching_vf(vf_netdev); + if (ret != 0) + continue; + + if (net != get_netvsc_byslot(vf_netdev)) + continue; + + netvsc_prepare_bonding(vf_netdev); + netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE); + __netvsc_vf_setup(net, vf_netdev); + break; + } rtnl_unlock(); netvsc_devinfo_put(device_info); @@ -2748,28 +2801,17 @@ static int netvsc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + int ret = 0; - /* Skip our own events */ - if (event_dev->netdev_ops == &device_ops) - return NOTIFY_DONE; - - /* Avoid non-Ethernet type devices */ - if (event_dev->type != ARPHRD_ETHER) - return NOTIFY_DONE; - - /* Avoid Vlan dev with same MAC registering as VF */ - if (is_vlan_dev(event_dev)) - return NOTIFY_DONE; - - /* Avoid Bonding master dev with same MAC registering as VF */ - if (netif_is_bond_master(event_dev)) + ret = check_dev_is_matching_vf(event_dev); + if (ret != 0) return NOTIFY_DONE; switch (event) { case NETDEV_POST_INIT: return netvsc_prepare_bonding(event_dev); case NETDEV_REGISTER: - return netvsc_register_vf(event_dev); + return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER); case NETDEV_UNREGISTER: return netvsc_unregister_vf(event_dev); case NETDEV_UP: @@ -2801,7 +2843,7 @@ static int __init netvsc_drv_init(void) pr_info("Increased ring_size to %u (min allowed)\n", ring_size); } - netvsc_ring_bytes = ring_size * PAGE_SIZE; + netvsc_ring_bytes = VMBUS_RING_SIZE(ring_size * 4096); register_netdevice_notifier(&netvsc_netdev_notifier); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index c3fbdd6b68ba..f3fa4bd12116 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -835,14 +835,14 @@ static void nsim_dev_trap_report_work(struct work_struct *work) trap_report_dw.work); nsim_dev = nsim_trap_data->nsim_dev; - /* For each running port and enabled packet trap, generate a UDP - * packet with a random 5-tuple and report it. - */ if (!devl_trylock(priv_to_devlink(nsim_dev))) { - schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 0); + schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 1); return; } + /* For each running port and enabled packet trap, generate a UDP + * packet with a random 5-tuple and report it. + */ list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list) { if (!netif_running(nsim_dev_port->ns->netdev)) continue; diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index edd4b1e58d96..75868e63b81b 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -2051,7 +2051,7 @@ static struct phy_driver at803x_driver[] = { .write_page = at803x_write_page, .get_features = at803x_get_features, .read_status = at803x_read_status, - .config_intr = &at803x_config_intr, + .config_intr = at803x_config_intr, .handle_interrupt = at803x_handle_interrupt, .get_tunable = at803x_get_tunable, .set_tunable = at803x_set_tunable, @@ -2081,7 +2081,7 @@ static struct phy_driver at803x_driver[] = { .resume = at803x_resume, .flags = PHY_POLL_CABLE_TEST, /* PHY_BASIC_FEATURES */ - .config_intr = &at803x_config_intr, + .config_intr = at803x_config_intr, .handle_interrupt = at803x_handle_interrupt, .cable_test_start = at803x_cable_test_start, .cable_test_get_status = at803x_cable_test_get_status, @@ -2097,7 +2097,7 @@ static struct phy_driver at803x_driver[] = { .resume = at803x_resume, .flags = PHY_POLL_CABLE_TEST, /* PHY_BASIC_FEATURES */ - .config_intr = &at803x_config_intr, + .config_intr = at803x_config_intr, .handle_interrupt = at803x_handle_interrupt, .cable_test_start = at803x_cable_test_start, .cable_test_get_status = at803x_cable_test_get_status, diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index fa8c6fdcf301..d7aaefb5226b 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -695,7 +695,8 @@ static int dp83869_configure_mode(struct phy_device *phydev, phy_ctrl_val = dp83869->mode; if (phydev->interface == PHY_INTERFACE_MODE_MII) { if (dp83869->mode == DP83869_100M_MEDIA_CONVERT || - dp83869->mode == DP83869_RGMII_100_BASE) { + dp83869->mode == DP83869_RGMII_100_BASE || + dp83869->mode == DP83869_RGMII_COPPER_ETHERNET) { phy_ctrl_val |= DP83869_OP_MODE_MII; } else { phydev_err(phydev, "selected op-mode is not valid with MII mode\n"); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 54a17b576eac..9481f172830f 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -120,6 +120,11 @@ */ #define LAN8814_1PPM_FORMAT 17179 +#define PTP_RX_VERSION 0x0248 +#define PTP_TX_VERSION 0x0288 +#define PTP_MAX_VERSION(x) (((x) & GENMASK(7, 0)) << 8) +#define PTP_MIN_VERSION(x) ((x) & GENMASK(7, 0)) + #define PTP_RX_MOD 0x024F #define PTP_RX_MOD_BAD_UDPV4_CHKSUM_FORCE_FCS_DIS_ BIT(3) #define PTP_RX_TIMESTAMP_EN 0x024D @@ -2922,6 +2927,12 @@ static void lan8814_ptp_init(struct phy_device *phydev) lanphy_write_page_reg(phydev, 5, PTP_TX_PARSE_IP_ADDR_EN, 0); lanphy_write_page_reg(phydev, 5, PTP_RX_PARSE_IP_ADDR_EN, 0); + /* Disable checking for minorVersionPTP field */ + lanphy_write_page_reg(phydev, 5, PTP_RX_VERSION, + PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0)); + lanphy_write_page_reg(phydev, 5, PTP_TX_VERSION, + PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0)); + skb_queue_head_init(&ptp_priv->tx_queue); skb_queue_head_init(&ptp_priv->rx_queue); INIT_LIST_HEAD(&ptp_priv->rx_ts_list); @@ -3302,6 +3313,7 @@ static struct phy_driver ksphy_driver[] = { .flags = PHY_POLL_CABLE_TEST, .driver_data = &ksz9021_type, .probe = kszphy_probe, + .soft_reset = genphy_soft_reset, .config_init = ksz9131_config_init, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 3d99fd6664d7..70e52d27064e 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -414,9 +414,11 @@ static int rtl8211f_config_init(struct phy_device *phydev) ERR_PTR(ret)); return ret; } + + return genphy_soft_reset(phydev); } - return genphy_soft_reset(phydev); + return 0; } static int rtl821x_resume(struct phy_device *phydev) diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 15a179631903..abc65c4d7a30 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -469,6 +469,10 @@ ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) case PPPIOCSMRU: if (get_user(val, p)) break; + if (val > U16_MAX) { + err = -EINVAL; + break; + } if (val < PPP_MRU) val = PPP_MRU; ap->mru = val; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d373953ddc30..367255bb44cd 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1622,13 +1622,19 @@ static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, switch (act) { case XDP_REDIRECT: err = xdp_do_redirect(tun->dev, xdp, xdp_prog); - if (err) + if (err) { + dev_core_stats_rx_dropped_inc(tun->dev); return err; + } + dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_TX: err = tun_xdp_tx(tun->dev, xdp); - if (err < 0) + if (err < 0) { + dev_core_stats_rx_dropped_inc(tun->dev); return err; + } + dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_PASS: break; diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 3777c7e2e6fc..e47bb125048d 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -161,7 +161,9 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) u8 buf[ETH_ALEN]; struct ax88172a_private *priv; - usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + return ret; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 4ea0e155bb0d..d837c1887416 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -173,6 +173,7 @@ struct ax88179_data { u8 in_pm; u32 wol_supported; u32 wolopts; + u8 disconnecting; }; struct ax88179_int_data { @@ -208,6 +209,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16); + struct ax88179_data *ax179_data = dev->driver_priv; BUG_ON(!dev); @@ -219,7 +221,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, ret = fn(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); - if (unlikely(ret < 0)) + if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting))) netdev_warn(dev->net, "Failed to read reg index 0x%04x: %d\n", index, ret); @@ -231,6 +233,7 @@ static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16); + struct ax88179_data *ax179_data = dev->driver_priv; BUG_ON(!dev); @@ -242,7 +245,7 @@ static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, ret = fn(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); - if (unlikely(ret < 0)) + if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting))) netdev_warn(dev->net, "Failed to write reg index 0x%04x: %d\n", index, ret); @@ -492,6 +495,20 @@ static int ax88179_resume(struct usb_interface *intf) return usbnet_resume(intf); } +static void ax88179_disconnect(struct usb_interface *intf) +{ + struct usbnet *dev = usb_get_intfdata(intf); + struct ax88179_data *ax179_data; + + if (!dev) + return; + + ax179_data = dev->driver_priv; + ax179_data->disconnecting = 1; + + usbnet_disconnect(intf); +} + static void ax88179_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) { @@ -1298,8 +1315,6 @@ static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf) netif_set_tso_max_size(dev->net, 16384); - ax88179_reset(dev); - return 0; } @@ -1906,7 +1921,7 @@ static struct usb_driver ax88179_178a_driver = { .suspend = ax88179_suspend, .resume = ax88179_resume, .reset_resume = ax88179_resume, - .disconnect = usbnet_disconnect, + .disconnect = ax88179_disconnect, .supports_autosuspend = 1, .disable_hub_initiated_lpm = 1, }; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 21d3461fb5d1..45f1a871b7da 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3474,10 +3474,11 @@ static int virtnet_find_vqs(struct virtnet_info *vi) { vq_callback_t **callbacks; struct virtqueue **vqs; - int ret = -ENOMEM; - int i, total_vqs; const char **names; + int ret = -ENOMEM; + int total_vqs; bool *ctx; + u16 i; /* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by @@ -3514,8 +3515,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { callbacks[rxq2vq(i)] = skb_recv_done; callbacks[txq2vq(i)] = skb_xmit_done; - sprintf(vi->rq[i].name, "input.%d", i); - sprintf(vi->sq[i].name, "output.%d", i); + sprintf(vi->rq[i].name, "input.%u", i); + sprintf(vi->sq[i].name, "output.%u", i); names[rxq2vq(i)] = vi->rq[i].name; names[txq2vq(i)] = vi->sq[i].name; if (ctx) diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c index 76f275ca53e9..70d468f01338 100644 --- a/drivers/net/wireless/ath/ath11k/ahb.c +++ b/drivers/net/wireless/ath/ath11k/ahb.c @@ -813,8 +813,8 @@ static int ath11k_core_get_rproc(struct ath11k_base *ab) prproc = rproc_get_by_phandle(rproc_phandle); if (!prproc) { - ath11k_err(ab, "failed to get rproc\n"); - return -EINVAL; + ath11k_dbg(ab, ATH11K_DBG_AHB, "failed to get rproc, deferring\n"); + return -EPROBE_DEFER; } ab_ahb->tgt_rproc = prproc; diff --git a/drivers/net/wireless/ath/ath11k/pcic.c b/drivers/net/wireless/ath/ath11k/pcic.c index 380f9d37b644..e3b65efcc868 100644 --- a/drivers/net/wireless/ath/ath11k/pcic.c +++ b/drivers/net/wireless/ath/ath11k/pcic.c @@ -453,8 +453,6 @@ void ath11k_pcic_ext_irq_enable(struct ath11k_base *ab) { int i; - set_bit(ATH11K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags); - for (i = 0; i < ATH11K_EXT_IRQ_GRP_NUM_MAX; i++) { struct ath11k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i]; @@ -465,6 +463,8 @@ void ath11k_pcic_ext_irq_enable(struct ath11k_base *ab) } ath11k_pcic_ext_grp_enable(irq_grp); } + + set_bit(ATH11K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags); } EXPORT_SYMBOL(ath11k_pcic_ext_irq_enable); diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c index 672789e3c55d..d6a3f001dacb 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c @@ -652,9 +652,10 @@ void ath9k_htc_txstatus(struct ath9k_htc_priv *priv, void *wmi_event) struct ath9k_htc_tx_event *tx_pend; int i; - for (i = 0; i < txs->cnt; i++) { - WARN_ON(txs->cnt > HTC_MAX_TX_STATUS); + if (WARN_ON_ONCE(txs->cnt > HTC_MAX_TX_STATUS)) + return; + for (i = 0; i < txs->cnt; i++) { __txs = &txs->txstatus[i]; skb = ath9k_htc_tx_get_packet(priv, __txs); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index 585e8cd2d332..f5fcc547de39 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -576,7 +576,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 2) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -592,7 +592,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 1) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -608,7 +608,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 0) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -665,7 +665,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 2) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -681,7 +681,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 1) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -697,7 +697,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 0) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -1044,6 +1044,9 @@ int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt) goto read_table; } + ret = PTR_ERR(wifi_pkg); + goto out_free; + read_table: fwrt->ppag_ver = tbl_rev; flags = &wifi_pkg->package.elements[1]; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index a1d34f3e7a9f..5979d904bbbd 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -1082,7 +1082,7 @@ static int iwl_dbg_tlv_override_trig_node(struct iwl_fw_runtime *fwrt, node_trig = (void *)node_tlv->data; } - memcpy(node_trig->data + offset, trig->data, trig_data_len); + memcpy((u8 *)node_trig->data + offset, trig->data, trig_data_len); node_tlv->length = cpu_to_le32(size); if (policy & IWL_FW_INI_APPLY_POLICY_OVERRIDE_CFG) { diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h index 157d1f31c487..c5a306b01fe2 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h @@ -348,8 +348,8 @@ #define RFIC_REG_RD 0xAD0470 #define WFPM_CTRL_REG 0xA03030 #define WFPM_OTP_CFG1_ADDR 0x00a03098 -#define WFPM_OTP_CFG1_IS_JACKET_BIT BIT(4) -#define WFPM_OTP_CFG1_IS_CDB_BIT BIT(5) +#define WFPM_OTP_CFG1_IS_JACKET_BIT BIT(5) +#define WFPM_OTP_CFG1_IS_CDB_BIT BIT(4) #define WFPM_GP2 0xA030B4 diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c index a3cefbc43e80..2c14188f34bb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c @@ -99,17 +99,6 @@ static void iwl_mvm_phy_ctxt_set_rxchain(struct iwl_mvm *mvm, active_cnt = 2; } - /* - * If the firmware requested it, then we know that it supports - * getting zero for the values to indicate "use one, but pick - * which one yourself", which means it can dynamically pick one - * that e.g. has better RSSI. - */ - if (mvm->fw_static_smps_request && active_cnt == 1 && idle_cnt == 1) { - idle_cnt = 0; - active_cnt = 0; - } - *rxchain_info = cpu_to_le32(iwl_mvm_get_valid_rx_ant(mvm) << PHY_RX_CHAIN_VALID_POS); *rxchain_info |= cpu_to_le32(idle_cnt << PHY_RX_CHAIN_CNT_POS); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index caaf4d52e2c6..76219486b9c2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -2200,7 +2200,7 @@ int iwl_mvm_flush_sta_tids(struct iwl_mvm *mvm, u32 sta_id, u16 tids) WARN_ON(!iwl_mvm_has_new_tx_api(mvm)); if (iwl_fw_lookup_notif_ver(mvm->fw, LONG_GROUP, TXPATH_FLUSH, 0) > 0) - cmd.flags |= CMD_WANT_SKB; + cmd.flags |= CMD_WANT_SKB | CMD_SEND_IN_RFKILL; IWL_DEBUG_TX_QUEUES(mvm, "flush for sta id %d tid mask 0x%x\n", sta_id, tids); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index 69b95ad5993b..2ec4ee8ab317 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -745,7 +745,7 @@ static inline void iwl_enable_rfkill_int(struct iwl_trans *trans) } } -void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans); +void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq); static inline bool iwl_is_rfkill_set(struct iwl_trans *trans) { @@ -792,7 +792,7 @@ static inline bool iwl_pcie_dbg_on(struct iwl_trans *trans) return (trans->dbg.dest_tlv || iwl_trans_dbg_ini_valid(trans)); } -void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state); +void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq); void iwl_trans_pcie_dump_regs(struct iwl_trans *trans); #ifdef CONFIG_IWLWIFI_DEBUGFS diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index 90a46faaaffd..91b73e7a4113 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1381,7 +1381,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans, * if it is true then one of the handlers took the page. */ - if (reclaim) { + if (reclaim && txq) { u16 sequence = le16_to_cpu(pkt->hdr.sequence); int index = SEQ_TO_INDEX(sequence); int cmd_index = iwl_txq_get_cmd_index(txq, index); @@ -1781,7 +1781,7 @@ static u32 iwl_pcie_int_cause_ict(struct iwl_trans *trans) return inta; } -void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans) +void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct isr_statistics *isr_stats = &trans_pcie->isr_stats; @@ -1805,7 +1805,7 @@ void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans) isr_stats->rfkill++; if (prev != report) - iwl_trans_pcie_rf_kill(trans, report); + iwl_trans_pcie_rf_kill(trans, report, from_irq); mutex_unlock(&trans_pcie->mutex); if (hw_rfkill) { @@ -1945,7 +1945,7 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id) /* HW RF KILL switch toggled */ if (inta & CSR_INT_BIT_RF_KILL) { - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, true); handled |= CSR_INT_BIT_RF_KILL; } @@ -2362,7 +2362,7 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id) /* HW RF KILL switch toggled */ if (inta_hw & MSIX_HW_INT_CAUSES_REG_RF_KILL) - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, true); if (inta_hw & MSIX_HW_INT_CAUSES_REG_HW_ERR) { IWL_ERR(trans, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 39ab6526e6b8..c7ed35b3dd8d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1080,7 +1080,7 @@ bool iwl_pcie_check_hw_rf_kill(struct iwl_trans *trans) report = test_bit(STATUS_RFKILL_OPMODE, &trans->status); if (prev != report) - iwl_trans_pcie_rf_kill(trans, report); + iwl_trans_pcie_rf_kill(trans, report, false); return hw_rfkill; } @@ -1234,7 +1234,7 @@ static void iwl_pcie_init_msix(struct iwl_trans_pcie *trans_pcie) trans_pcie->hw_mask = trans_pcie->hw_init_mask; } -static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans) +static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool from_irq) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1261,7 +1261,8 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans) if (test_and_clear_bit(STATUS_DEVICE_ENABLED, &trans->status)) { IWL_DEBUG_INFO(trans, "DEVICE_ENABLED bit was set and is now cleared\n"); - iwl_pcie_synchronize_irqs(trans); + if (!from_irq) + iwl_pcie_synchronize_irqs(trans); iwl_pcie_rx_napi_sync(trans); iwl_pcie_tx_stop(trans); iwl_pcie_rx_stop(trans); @@ -1451,7 +1452,7 @@ void iwl_trans_pcie_handle_stop_rfkill(struct iwl_trans *trans, clear_bit(STATUS_RFKILL_OPMODE, &trans->status); } if (hw_rfkill != was_in_rfkill) - iwl_trans_pcie_rf_kill(trans, hw_rfkill); + iwl_trans_pcie_rf_kill(trans, hw_rfkill, false); } static void iwl_trans_pcie_stop_device(struct iwl_trans *trans) @@ -1466,12 +1467,12 @@ static void iwl_trans_pcie_stop_device(struct iwl_trans *trans) mutex_lock(&trans_pcie->mutex); trans_pcie->opmode_down = true; was_in_rfkill = test_bit(STATUS_RFKILL_OPMODE, &trans->status); - _iwl_trans_pcie_stop_device(trans); + _iwl_trans_pcie_stop_device(trans, false); iwl_trans_pcie_handle_stop_rfkill(trans, was_in_rfkill); mutex_unlock(&trans_pcie->mutex); } -void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state) +void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq) { struct iwl_trans_pcie __maybe_unused *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1484,7 +1485,7 @@ void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state) if (trans->trans_cfg->gen2) _iwl_trans_pcie_gen2_stop_device(trans); else - _iwl_trans_pcie_stop_device(trans); + _iwl_trans_pcie_stop_device(trans, from_irq); } } @@ -2815,7 +2816,7 @@ static ssize_t iwl_dbgfs_rfkill_write(struct file *file, IWL_WARN(trans, "changing debug rfkill %d->%d\n", trans_pcie->debug_rfkill, new_value); trans_pcie->debug_rfkill = new_value; - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, false); return count; } @@ -3034,7 +3035,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans, struct iwl_rxq *rxq = &trans_pcie->rxq[0]; u32 i, r, j, rb_len = 0; - spin_lock(&rxq->lock); + spin_lock_bh(&rxq->lock); r = le16_to_cpu(iwl_get_closed_rb_stts(trans, rxq)) & 0x0FFF; @@ -3058,7 +3059,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans, *data = iwl_fw_error_next_data(*data); } - spin_unlock(&rxq->lock); + spin_unlock_bh(&rxq->lock); return rb_len; } diff --git a/drivers/net/wireless/marvell/libertas/Kconfig b/drivers/net/wireless/marvell/libertas/Kconfig index 6d62ab49aa8d..c7d02adb3eea 100644 --- a/drivers/net/wireless/marvell/libertas/Kconfig +++ b/drivers/net/wireless/marvell/libertas/Kconfig @@ -2,8 +2,6 @@ config LIBERTAS tristate "Marvell 8xxx Libertas WLAN driver support" depends on CFG80211 - select WIRELESS_EXT - select WEXT_SPY select LIB80211 select FW_LOADER help diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index e55747b50dbf..2c9b70e9a726 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -779,7 +779,7 @@ static int mwifiex_check_fw_status(struct mwifiex_adapter *adapter, { struct sdio_mmc_card *card = adapter->card; int ret = 0; - u16 firmware_stat; + u16 firmware_stat = 0; u32 tries; for (tries = 0; tries < poll_num; tries++) { diff --git a/drivers/net/wireless/mediatek/mt76/eeprom.c b/drivers/net/wireless/mediatek/mt76/eeprom.c index 9bc8758573fc..0a88048b8976 100644 --- a/drivers/net/wireless/mediatek/mt76/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/eeprom.c @@ -62,7 +62,7 @@ int mt76_get_of_eeprom(struct mt76_dev *dev, void *eep, int offset, int len) goto out_put_node; } - offset = be32_to_cpup(list); + offset += be32_to_cpup(list); ret = mtd_read(mtd, offset, len, &retlen, eep); put_mtd_device(mtd); if (mtd_is_bitflip(ret)) diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 9c753c6aabef..60c9f9c56a4f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -564,8 +564,7 @@ struct mt76_sdio { struct mt76_worker txrx_worker; struct mt76_worker status_worker; struct mt76_worker net_worker; - - struct work_struct stat_work; + struct mt76_worker stat_worker; u8 *xmit_buf; u32 xmit_buf_sz; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c index 304212f5f8da..d742b22428f0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c @@ -205,8 +205,8 @@ static int mt7663s_suspend(struct device *dev) mt76_worker_disable(&mdev->mt76.sdio.txrx_worker); mt76_worker_disable(&mdev->mt76.sdio.status_worker); mt76_worker_disable(&mdev->mt76.sdio.net_worker); + mt76_worker_disable(&mdev->mt76.sdio.stat_worker); - cancel_work_sync(&mdev->mt76.sdio.stat_work); clear_bit(MT76_READING_STATS, &mdev->mphy.state); mt76_tx_status_check(&mdev->mt76, true); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index 10dda1693d7d..19640ff76bdc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -1036,21 +1036,26 @@ int __mt7921_mcu_set_clc(struct mt7921_dev *dev, u8 *alpha2, u8 type[2]; u8 rsvd[64]; } __packed req = { + .ver = 1, .idx = idx, .env = env_cap, }; int ret, valid_cnt = 0; - u8 i, *pos; + u16 buf_len = 0; + u8 *pos; if (!clc) return 0; + buf_len = le16_to_cpu(clc->len) - sizeof(*clc); pos = clc->data; - for (i = 0; i < clc->nr_country; i++) { + while (buf_len > 16) { struct mt7921_clc_rule *rule = (struct mt7921_clc_rule *)pos; u16 len = le16_to_cpu(rule->len); + u16 offset = len + sizeof(*rule); - pos += len + sizeof(*rule); + pos += offset; + buf_len -= offset; if (rule->alpha2[0] != alpha2[0] || rule->alpha2[1] != alpha2[1]) continue; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c index 3b25a06fd946..8898ba69b8e9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c @@ -222,7 +222,7 @@ static int mt7921s_suspend(struct device *__dev) mt76_txq_schedule_all(&dev->mphy); mt76_worker_disable(&mdev->tx_worker); mt76_worker_disable(&mdev->sdio.status_worker); - cancel_work_sync(&mdev->sdio.stat_work); + mt76_worker_disable(&mdev->sdio.stat_worker); clear_bit(MT76_READING_STATS, &dev->mphy.state); mt76_tx_status_check(mdev, true); @@ -254,6 +254,7 @@ restore_txrx_worker: restore_worker: mt76_worker_enable(&mdev->tx_worker); mt76_worker_enable(&mdev->sdio.status_worker); + mt76_worker_enable(&mdev->sdio.stat_worker); if (!pm->ds_enable) mt76_connac_mcu_set_deep_sleep(mdev, false); @@ -286,6 +287,7 @@ static int mt7921s_resume(struct device *__dev) mt76_worker_enable(&mdev->sdio.txrx_worker); mt76_worker_enable(&mdev->sdio.status_worker); mt76_worker_enable(&mdev->sdio.net_worker); + mt76_worker_enable(&mdev->sdio.stat_worker); /* restore previous ds setting */ if (!pm->ds_enable) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c index 1b3adb3d91e8..fd07b6623392 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c @@ -107,7 +107,7 @@ int mt7921s_mac_reset(struct mt7921_dev *dev) mt76_worker_disable(&dev->mt76.sdio.txrx_worker); mt76_worker_disable(&dev->mt76.sdio.status_worker); mt76_worker_disable(&dev->mt76.sdio.net_worker); - cancel_work_sync(&dev->mt76.sdio.stat_work); + mt76_worker_disable(&dev->mt76.sdio.stat_worker); mt7921s_disable_irq(&dev->mt76); mt7921s_wfsys_reset(dev); @@ -115,6 +115,7 @@ int mt7921s_mac_reset(struct mt7921_dev *dev) mt76_worker_enable(&dev->mt76.sdio.txrx_worker); mt76_worker_enable(&dev->mt76.sdio.status_worker); mt76_worker_enable(&dev->mt76.sdio.net_worker); + mt76_worker_enable(&dev->mt76.sdio.stat_worker); dev->fw_assert = false; clear_bit(MT76_MCU_RESET, &dev->mphy.state); diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c index 176207f3177c..fc4fb9463564 100644 --- a/drivers/net/wireless/mediatek/mt76/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/sdio.c @@ -481,21 +481,21 @@ static void mt76s_status_worker(struct mt76_worker *w) if (dev->drv->tx_status_data && ndata_frames > 0 && !test_and_set_bit(MT76_READING_STATS, &dev->phy.state) && !test_bit(MT76_STATE_SUSPEND, &dev->phy.state)) - ieee80211_queue_work(dev->hw, &dev->sdio.stat_work); + mt76_worker_schedule(&sdio->stat_worker); } while (nframes > 0); if (resched) mt76_worker_schedule(&dev->tx_worker); } -static void mt76s_tx_status_data(struct work_struct *work) +static void mt76s_tx_status_data(struct mt76_worker *worker) { struct mt76_sdio *sdio; struct mt76_dev *dev; u8 update = 1; u16 count = 0; - sdio = container_of(work, struct mt76_sdio, stat_work); + sdio = container_of(worker, struct mt76_sdio, stat_worker); dev = container_of(sdio, struct mt76_dev, sdio); while (true) { @@ -508,7 +508,7 @@ static void mt76s_tx_status_data(struct work_struct *work) } if (count && test_bit(MT76_STATE_RUNNING, &dev->phy.state)) - ieee80211_queue_work(dev->hw, &sdio->stat_work); + mt76_worker_schedule(&sdio->status_worker); else clear_bit(MT76_READING_STATS, &dev->phy.state); } @@ -600,8 +600,8 @@ void mt76s_deinit(struct mt76_dev *dev) mt76_worker_teardown(&sdio->txrx_worker); mt76_worker_teardown(&sdio->status_worker); mt76_worker_teardown(&sdio->net_worker); + mt76_worker_teardown(&sdio->stat_worker); - cancel_work_sync(&sdio->stat_work); clear_bit(MT76_READING_STATS, &dev->phy.state); mt76_tx_status_check(dev, true); @@ -644,10 +644,14 @@ int mt76s_init(struct mt76_dev *dev, struct sdio_func *func, if (err) return err; + err = mt76_worker_setup(dev->hw, &sdio->stat_worker, mt76s_tx_status_data, + "sdio-sta"); + if (err) + return err; + sched_set_fifo_low(sdio->status_worker.task); sched_set_fifo_low(sdio->net_worker.task); - - INIT_WORK(&sdio->stat_work, mt76s_tx_status_data); + sched_set_fifo_low(sdio->stat_worker.task); dev->queue_ops = &sdio_queue_ops; dev->bus = bus_ops; diff --git a/drivers/net/wireless/purelifi/plfxlc/usb.c b/drivers/net/wireless/purelifi/plfxlc/usb.c index 76d0a778636a..311676c1ece0 100644 --- a/drivers/net/wireless/purelifi/plfxlc/usb.c +++ b/drivers/net/wireless/purelifi/plfxlc/usb.c @@ -493,9 +493,12 @@ int plfxlc_usb_wreq_async(struct plfxlc_usb *usb, const u8 *buffer, void *context) { struct usb_device *udev = interface_to_usbdev(usb->ez_usb); - struct urb *urb = usb_alloc_urb(0, GFP_ATOMIC); + struct urb *urb; int r; + urb = usb_alloc_urb(0, GFP_ATOMIC); + if (!urb) + return -ENOMEM; usb_fill_bulk_urb(urb, udev, usb_sndbulkpipe(udev, EP_DATA_OUT), (void *)buffer, buffer_len, complete_fn, context); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 12b700c7b9c3..517d9023aae3 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -8672,7 +8672,7 @@ static void rt2800_rxdcoc_calibration(struct rt2x00_dev *rt2x00dev) rt2800_rfcsr_write_bank(rt2x00dev, 5, 4, saverfb5r4); rt2800_rfcsr_write_bank(rt2x00dev, 7, 4, saverfb7r4); - rt2800_bbp_write(rt2x00dev, 158, 141); + rt2800_bbp_write(rt2x00dev, 158, 140); bbpreg = rt2800_bbp_read(rt2x00dev, 159); bbpreg = bbpreg & (~0x40); rt2800_bbp_write(rt2x00dev, 159, bbpreg); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c index 9a9cfd0ce402..00b945053e19 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c @@ -101,6 +101,7 @@ void rt2x00lib_disable_radio(struct rt2x00_dev *rt2x00dev) rt2x00link_stop_tuner(rt2x00dev); rt2x00queue_stop_queues(rt2x00dev); rt2x00queue_flush_queues(rt2x00dev, true); + rt2x00queue_stop_queue(rt2x00dev->bcn); /* * Disable radio. @@ -1286,6 +1287,7 @@ int rt2x00lib_start(struct rt2x00_dev *rt2x00dev) rt2x00dev->intf_ap_count = 0; rt2x00dev->intf_sta_count = 0; rt2x00dev->intf_associated = 0; + rt2x00dev->intf_beaconing = 0; /* Enable the radio */ retval = rt2x00lib_enable_radio(rt2x00dev); @@ -1312,6 +1314,7 @@ void rt2x00lib_stop(struct rt2x00_dev *rt2x00dev) rt2x00dev->intf_ap_count = 0; rt2x00dev->intf_sta_count = 0; rt2x00dev->intf_associated = 0; + rt2x00dev->intf_beaconing = 0; } static inline void rt2x00lib_set_if_combinations(struct rt2x00_dev *rt2x00dev) diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c index 4202c6517783..75fda72c14ca 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c @@ -598,6 +598,17 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw, */ if (changes & BSS_CHANGED_BEACON_ENABLED) { mutex_lock(&intf->beacon_skb_mutex); + + /* + * Clear the 'enable_beacon' flag and clear beacon because + * the beacon queue has been stopped after hardware reset. + */ + if (test_bit(DEVICE_STATE_RESET, &rt2x00dev->flags) && + intf->enable_beacon) { + intf->enable_beacon = false; + rt2x00queue_clear_beacon(rt2x00dev, vif); + } + if (!bss_conf->enable_beacon && intf->enable_beacon) { rt2x00dev->intf_beaconing--; intf->enable_beacon = false; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 3a9fa3ff37ac..6dd5ec1e4d8c 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -7030,6 +7030,18 @@ static const struct usb_device_id dev_table[] = { .driver_info = (unsigned long)&rtl8192eu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x818c, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192eu_fops}, +/* D-Link DWA-131 rev C1 */ +{USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3312, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192eu_fops}, +/* TP-Link TL-WN8200ND V2 */ +{USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x0126, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192eu_fops}, +/* Mercusys MW300UM */ +{USB_DEVICE_AND_INTERFACE_INFO(0x2c4e, 0x0100, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192eu_fops}, +/* Mercusys MW300UH */ +{USB_DEVICE_AND_INTERFACE_INFO(0x2c4e, 0x0104, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192eu_fops}, #endif { } }; diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index ca79f652fef3..6116c1bec155 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -164,21 +164,29 @@ static bool _rtl_pci_platform_switch_device_pci_aspm( struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); + value &= PCI_EXP_LNKCTL_ASPMC; + if (rtlhal->hw_type != HARDWARE_TYPE_RTL8192SE) - value |= 0x40; + value |= PCI_EXP_LNKCTL_CCC; - pci_write_config_byte(rtlpci->pdev, 0x80, value); + pcie_capability_clear_and_set_word(rtlpci->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_ASPMC | value, + value); return false; } -/*When we set 0x01 to enable clk request. Set 0x0 to disable clk req.*/ -static void _rtl_pci_switch_clk_req(struct ieee80211_hw *hw, u8 value) +/* @value is PCI_EXP_LNKCTL_CLKREQ_EN or 0 to enable/disable clk request. */ +static void _rtl_pci_switch_clk_req(struct ieee80211_hw *hw, u16 value) { struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); - pci_write_config_byte(rtlpci->pdev, 0x81, value); + value &= PCI_EXP_LNKCTL_CLKREQ_EN; + + pcie_capability_clear_and_set_word(rtlpci->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_CLKREQ_EN, + value); if (rtlhal->hw_type == HARDWARE_TYPE_RTL8192SE) udelay(100); @@ -192,11 +200,8 @@ static void rtl_pci_disable_aspm(struct ieee80211_hw *hw) struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); u8 pcibridge_vendor = pcipriv->ndis_adapter.pcibridge_vendor; - u8 num4bytes = pcipriv->ndis_adapter.num4bytes; /*Retrieve original configuration settings. */ u8 linkctrl_reg = pcipriv->ndis_adapter.linkctrl_reg; - u16 pcibridge_linkctrlreg = pcipriv->ndis_adapter. - pcibridge_linkctrlreg; u16 aspmlevel = 0; u8 tmp_u1b = 0; @@ -221,16 +226,8 @@ static void rtl_pci_disable_aspm(struct ieee80211_hw *hw) /*Set corresponding value. */ aspmlevel |= BIT(0) | BIT(1); linkctrl_reg &= ~aspmlevel; - pcibridge_linkctrlreg &= ~(BIT(0) | BIT(1)); _rtl_pci_platform_switch_device_pci_aspm(hw, linkctrl_reg); - udelay(50); - - /*4 Disable Pci Bridge ASPM */ - pci_write_config_byte(rtlpci->pdev, (num4bytes << 2), - pcibridge_linkctrlreg); - - udelay(50); } /*Enable RTL8192SE ASPM & Enable Pci Bridge ASPM for @@ -245,9 +242,7 @@ static void rtl_pci_enable_aspm(struct ieee80211_hw *hw) struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); u8 pcibridge_vendor = pcipriv->ndis_adapter.pcibridge_vendor; - u8 num4bytes = pcipriv->ndis_adapter.num4bytes; u16 aspmlevel; - u8 u_pcibridge_aspmsetting; u8 u_device_aspmsetting; if (!ppsc->support_aspm) @@ -259,25 +254,6 @@ static void rtl_pci_enable_aspm(struct ieee80211_hw *hw) return; } - /*4 Enable Pci Bridge ASPM */ - - u_pcibridge_aspmsetting = - pcipriv->ndis_adapter.pcibridge_linkctrlreg | - rtlpci->const_hostpci_aspm_setting; - - if (pcibridge_vendor == PCI_BRIDGE_VENDOR_INTEL) - u_pcibridge_aspmsetting &= ~BIT(0); - - pci_write_config_byte(rtlpci->pdev, (num4bytes << 2), - u_pcibridge_aspmsetting); - - rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD, - "PlatformEnableASPM(): Write reg[%x] = %x\n", - (pcipriv->ndis_adapter.pcibridge_pciehdr_offset + 0x10), - u_pcibridge_aspmsetting); - - udelay(50); - /*Get ASPM level (with/without Clock Req) */ aspmlevel = rtlpci->const_devicepci_aspm_setting; u_device_aspmsetting = pcipriv->ndis_adapter.linkctrl_reg; @@ -291,7 +267,8 @@ static void rtl_pci_enable_aspm(struct ieee80211_hw *hw) if (ppsc->reg_rfps_level & RT_RF_OFF_LEVL_CLK_REQ) { _rtl_pci_switch_clk_req(hw, (ppsc->reg_rfps_level & - RT_RF_OFF_LEVL_CLK_REQ) ? 1 : 0); + RT_RF_OFF_LEVL_CLK_REQ) ? + PCI_EXP_LNKCTL_CLKREQ_EN : 0); RT_SET_PS_LEVEL(ppsc, RT_RF_OFF_LEVL_CLK_REQ); } udelay(100); @@ -358,22 +335,6 @@ static bool rtl_pci_check_buddy_priv(struct ieee80211_hw *hw, return tpriv != NULL; } -static void rtl_pci_get_linkcontrol_field(struct ieee80211_hw *hw) -{ - struct rtl_pci_priv *pcipriv = rtl_pcipriv(hw); - struct rtl_pci *rtlpci = rtl_pcidev(pcipriv); - u8 capabilityoffset = pcipriv->ndis_adapter.pcibridge_pciehdr_offset; - u8 linkctrl_reg; - u8 num4bbytes; - - num4bbytes = (capabilityoffset + 0x10) / 4; - - /*Read Link Control Register */ - pci_read_config_byte(rtlpci->pdev, (num4bbytes << 2), &linkctrl_reg); - - pcipriv->ndis_adapter.pcibridge_linkctrlreg = linkctrl_reg; -} - static void rtl_pci_parse_configuration(struct pci_dev *pdev, struct ieee80211_hw *hw) { @@ -2033,12 +1994,6 @@ static bool _rtl_pci_find_adapter(struct pci_dev *pdev, PCI_SLOT(bridge_pdev->devfn); pcipriv->ndis_adapter.pcibridge_funcnum = PCI_FUNC(bridge_pdev->devfn); - pcipriv->ndis_adapter.pcibridge_pciehdr_offset = - pci_pcie_cap(bridge_pdev); - pcipriv->ndis_adapter.num4bytes = - (pcipriv->ndis_adapter.pcibridge_pciehdr_offset + 0x10) / 4; - - rtl_pci_get_linkcontrol_field(hw); if (pcipriv->ndis_adapter.pcibridge_vendor == PCI_BRIDGE_VENDOR_AMD) { @@ -2055,13 +2010,11 @@ static bool _rtl_pci_find_adapter(struct pci_dev *pdev, pdev->vendor, pcipriv->ndis_adapter.linkctrl_reg); rtl_dbg(rtlpriv, COMP_INIT, DBG_DMESG, - "pci_bridge busnumber:devnumber:funcnumber:vendor:pcie_cap:link_ctl_reg:amd %d:%d:%d:%x:%x:%x:%x\n", + "pci_bridge busnumber:devnumber:funcnumber:vendor:amd %d:%d:%d:%x:%x\n", pcipriv->ndis_adapter.pcibridge_busnum, pcipriv->ndis_adapter.pcibridge_devnum, pcipriv->ndis_adapter.pcibridge_funcnum, pcibridge_vendors[pcipriv->ndis_adapter.pcibridge_vendor], - pcipriv->ndis_adapter.pcibridge_pciehdr_offset, - pcipriv->ndis_adapter.pcibridge_linkctrlreg, pcipriv->ndis_adapter.amd_l1_patch); rtl_pci_parse_configuration(pdev, hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.h b/drivers/net/wireless/realtek/rtlwifi/pci.h index 866861626a0a..d6307197dfea 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.h +++ b/drivers/net/wireless/realtek/rtlwifi/pci.h @@ -236,11 +236,6 @@ struct mp_adapter { u16 pcibridge_vendorid; u16 pcibridge_deviceid; - u8 num4bytes; - - u8 pcibridge_pciehdr_offset; - u8 pcibridge_linkctrlreg; - bool amd_l1_patch; }; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c index 12d0b3a87af7..0fab3a0c7d49 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c @@ -16,12 +16,6 @@ static u32 _rtl88e_phy_rf_serial_read(struct ieee80211_hw *hw, static void _rtl88e_phy_rf_serial_write(struct ieee80211_hw *hw, enum radio_path rfpath, u32 offset, u32 data); -static u32 _rtl88e_phy_calculate_bit_shift(u32 bitmask) -{ - u32 i = ffs(bitmask); - - return i ? i - 1 : 32; -} static bool _rtl88e_phy_bb8188e_config_parafile(struct ieee80211_hw *hw); static bool _rtl88e_phy_config_mac_with_headerfile(struct ieee80211_hw *hw); static bool phy_config_bb_with_headerfile(struct ieee80211_hw *hw, @@ -51,7 +45,7 @@ u32 rtl88e_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask) rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "regaddr(%#x), bitmask(%#x)\n", regaddr, bitmask); originalvalue = rtl_read_dword(rtlpriv, regaddr); - bitshift = _rtl88e_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); returnvalue = (originalvalue & bitmask) >> bitshift; rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, @@ -74,7 +68,7 @@ void rtl88e_phy_set_bb_reg(struct ieee80211_hw *hw, if (bitmask != MASKDWORD) { originalvalue = rtl_read_dword(rtlpriv, regaddr); - bitshift = _rtl88e_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((originalvalue & (~bitmask)) | (data << bitshift)); } @@ -99,7 +93,7 @@ u32 rtl88e_phy_query_rf_reg(struct ieee80211_hw *hw, original_value = _rtl88e_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = _rtl88e_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); readback_value = (original_value & bitmask) >> bitshift; spin_unlock(&rtlpriv->locks.rf_lock); @@ -127,7 +121,7 @@ void rtl88e_phy_set_rf_reg(struct ieee80211_hw *hw, original_value = _rtl88e_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = _rtl88e_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c index 3d29c8dbb255..144ee780e1b6 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c @@ -17,7 +17,7 @@ u32 rtl92c_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask) rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "regaddr(%#x), bitmask(%#x)\n", regaddr, bitmask); originalvalue = rtl_read_dword(rtlpriv, regaddr); - bitshift = _rtl92c_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); returnvalue = (originalvalue & bitmask) >> bitshift; rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, @@ -40,7 +40,7 @@ void rtl92c_phy_set_bb_reg(struct ieee80211_hw *hw, if (bitmask != MASKDWORD) { originalvalue = rtl_read_dword(rtlpriv, regaddr); - bitshift = _rtl92c_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((originalvalue & (~bitmask)) | (data << bitshift)); } @@ -143,14 +143,6 @@ void _rtl92c_phy_rf_serial_write(struct ieee80211_hw *hw, } EXPORT_SYMBOL(_rtl92c_phy_rf_serial_write); -u32 _rtl92c_phy_calculate_bit_shift(u32 bitmask) -{ - u32 i = ffs(bitmask); - - return i ? i - 1 : 32; -} -EXPORT_SYMBOL(_rtl92c_phy_calculate_bit_shift); - static void _rtl92c_phy_bb_config_1t(struct ieee80211_hw *hw) { rtl_set_bbreg(hw, RFPGA0_TXINFO, 0x3, 0x2); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.h index 75afa6253ad0..e64d377dfe9e 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.h @@ -196,7 +196,6 @@ bool rtl92c_phy_set_rf_power_state(struct ieee80211_hw *hw, void rtl92ce_phy_set_rf_on(struct ieee80211_hw *hw); void rtl92c_phy_set_io(struct ieee80211_hw *hw); void rtl92c_bb_block_on(struct ieee80211_hw *hw); -u32 _rtl92c_phy_calculate_bit_shift(u32 bitmask); long _rtl92c_phy_txpwr_idx_to_dbm(struct ieee80211_hw *hw, enum wireless_mode wirelessmode, u8 txpwridx); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.c index da54e51badd3..fa70a7d5539f 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.c @@ -39,7 +39,7 @@ u32 rtl92c_phy_query_rf_reg(struct ieee80211_hw *hw, rfpath, regaddr); } - bitshift = _rtl92c_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); readback_value = (original_value & bitmask) >> bitshift; spin_unlock(&rtlpriv->locks.rf_lock); @@ -110,7 +110,7 @@ void rtl92ce_phy_set_rf_reg(struct ieee80211_hw *hw, original_value = _rtl92c_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = _rtl92c_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); @@ -122,7 +122,7 @@ void rtl92ce_phy_set_rf_reg(struct ieee80211_hw *hw, original_value = _rtl92c_phy_fw_rf_serial_read(hw, rfpath, regaddr); - bitshift = _rtl92c_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.h index 7582a162bd11..c7a0d4c776f0 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/phy.h @@ -94,7 +94,6 @@ u32 _rtl92c_phy_rf_serial_read(struct ieee80211_hw *hw, enum radio_path rfpath, u32 offset); u32 _rtl92c_phy_fw_rf_serial_read(struct ieee80211_hw *hw, enum radio_path rfpath, u32 offset); -u32 _rtl92c_phy_calculate_bit_shift(u32 bitmask); void _rtl92c_phy_rf_serial_write(struct ieee80211_hw *hw, enum radio_path rfpath, u32 offset, u32 data); void _rtl92c_phy_fw_rf_serial_write(struct ieee80211_hw *hw, diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/phy.c index a8d9fe269f31..0b8cb7e61fd8 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/phy.c @@ -32,7 +32,7 @@ u32 rtl92cu_phy_query_rf_reg(struct ieee80211_hw *hw, original_value = _rtl92c_phy_fw_rf_serial_read(hw, rfpath, regaddr); } - bitshift = _rtl92c_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); readback_value = (original_value & bitmask) >> bitshift; rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "regaddr(%#x), rfpath(%#x), bitmask(%#x), original_value(%#x)\n", @@ -56,7 +56,7 @@ void rtl92cu_phy_set_rf_reg(struct ieee80211_hw *hw, original_value = _rtl92c_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = _rtl92c_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); @@ -67,7 +67,7 @@ void rtl92cu_phy_set_rf_reg(struct ieee80211_hw *hw, original_value = _rtl92c_phy_fw_rf_serial_read(hw, rfpath, regaddr); - bitshift = _rtl92c_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c index d18c092b6142..d835a27429f0 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c @@ -169,13 +169,6 @@ static const u8 channel_all[59] = { 157, 159, 161, 163, 165 }; -static u32 _rtl92d_phy_calculate_bit_shift(u32 bitmask) -{ - u32 i = ffs(bitmask); - - return i ? i - 1 : 32; -} - u32 rtl92d_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask) { struct rtl_priv *rtlpriv = rtl_priv(hw); @@ -198,7 +191,7 @@ u32 rtl92d_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask) } else { originalvalue = rtl_read_dword(rtlpriv, regaddr); } - bitshift = _rtl92d_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); returnvalue = (originalvalue & bitmask) >> bitshift; rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "BBR MASK=0x%x Addr[0x%x]=0x%x\n", @@ -230,7 +223,7 @@ void rtl92d_phy_set_bb_reg(struct ieee80211_hw *hw, dbi_direct); else originalvalue = rtl_read_dword(rtlpriv, regaddr); - bitshift = _rtl92d_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((originalvalue & (~bitmask)) | (data << bitshift)); } if (rtlhal->during_mac1init_radioa || rtlhal->during_mac0init_radiob) @@ -317,7 +310,7 @@ u32 rtl92d_phy_query_rf_reg(struct ieee80211_hw *hw, regaddr, rfpath, bitmask); spin_lock(&rtlpriv->locks.rf_lock); original_value = _rtl92d_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = _rtl92d_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); readback_value = (original_value & bitmask) >> bitshift; spin_unlock(&rtlpriv->locks.rf_lock); rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, @@ -343,7 +336,7 @@ void rtl92d_phy_set_rf_reg(struct ieee80211_hw *hw, enum radio_path rfpath, if (bitmask != RFREG_OFFSET_MASK) { original_value = _rtl92d_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = _rtl92d_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c index cc0bcaf13e96..73ef602bfb01 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c @@ -16,7 +16,6 @@ static u32 _rtl92ee_phy_rf_serial_read(struct ieee80211_hw *hw, static void _rtl92ee_phy_rf_serial_write(struct ieee80211_hw *hw, enum radio_path rfpath, u32 offset, u32 data); -static u32 _rtl92ee_phy_calculate_bit_shift(u32 bitmask); static bool _rtl92ee_phy_bb8192ee_config_parafile(struct ieee80211_hw *hw); static bool _rtl92ee_phy_config_mac_with_headerfile(struct ieee80211_hw *hw); static bool phy_config_bb_with_hdr_file(struct ieee80211_hw *hw, @@ -46,7 +45,7 @@ u32 rtl92ee_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask) rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "regaddr(%#x), bitmask(%#x)\n", regaddr, bitmask); originalvalue = rtl_read_dword(rtlpriv, regaddr); - bitshift = _rtl92ee_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); returnvalue = (originalvalue & bitmask) >> bitshift; rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, @@ -68,7 +67,7 @@ void rtl92ee_phy_set_bb_reg(struct ieee80211_hw *hw, u32 regaddr, if (bitmask != MASKDWORD) { originalvalue = rtl_read_dword(rtlpriv, regaddr); - bitshift = _rtl92ee_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((originalvalue & (~bitmask)) | (data << bitshift)); } @@ -92,7 +91,7 @@ u32 rtl92ee_phy_query_rf_reg(struct ieee80211_hw *hw, spin_lock(&rtlpriv->locks.rf_lock); original_value = _rtl92ee_phy_rf_serial_read(hw , rfpath, regaddr); - bitshift = _rtl92ee_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); readback_value = (original_value & bitmask) >> bitshift; spin_unlock(&rtlpriv->locks.rf_lock); @@ -119,7 +118,7 @@ void rtl92ee_phy_set_rf_reg(struct ieee80211_hw *hw, if (bitmask != RFREG_OFFSET_MASK) { original_value = _rtl92ee_phy_rf_serial_read(hw, rfpath, addr); - bitshift = _rtl92ee_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = (original_value & (~bitmask)) | (data << bitshift); } @@ -201,13 +200,6 @@ static void _rtl92ee_phy_rf_serial_write(struct ieee80211_hw *hw, pphyreg->rf3wire_offset, data_and_addr); } -static u32 _rtl92ee_phy_calculate_bit_shift(u32 bitmask) -{ - u32 i = ffs(bitmask); - - return i ? i - 1 : 32; -} - bool rtl92ee_phy_mac_config(struct ieee80211_hw *hw) { return _rtl92ee_phy_config_mac_with_headerfile(hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c index aaa004d4d6d0..0e2b9698088b 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c @@ -14,13 +14,6 @@ #include "hw.h" #include "table.h" -static u32 _rtl92s_phy_calculate_bit_shift(u32 bitmask) -{ - u32 i = ffs(bitmask); - - return i ? i - 1 : 32; -} - u32 rtl92s_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask) { struct rtl_priv *rtlpriv = rtl_priv(hw); @@ -30,7 +23,7 @@ u32 rtl92s_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask) regaddr, bitmask); originalvalue = rtl_read_dword(rtlpriv, regaddr); - bitshift = _rtl92s_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); returnvalue = (originalvalue & bitmask) >> bitshift; rtl_dbg(rtlpriv, COMP_RF, DBG_TRACE, "BBR MASK=0x%x Addr[0x%x]=0x%x\n", @@ -52,7 +45,7 @@ void rtl92s_phy_set_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask, if (bitmask != MASKDWORD) { originalvalue = rtl_read_dword(rtlpriv, regaddr); - bitshift = _rtl92s_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((originalvalue & (~bitmask)) | (data << bitshift)); } @@ -160,7 +153,7 @@ u32 rtl92s_phy_query_rf_reg(struct ieee80211_hw *hw, enum radio_path rfpath, original_value = _rtl92s_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = _rtl92s_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); readback_value = (original_value & bitmask) >> bitshift; spin_unlock(&rtlpriv->locks.rf_lock); @@ -191,7 +184,7 @@ void rtl92s_phy_set_rf_reg(struct ieee80211_hw *hw, enum radio_path rfpath, if (bitmask != RFREG_OFFSET_MASK) { original_value = _rtl92s_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = _rtl92s_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c index fe9b407dc2af..71e29b103da5 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c @@ -49,7 +49,7 @@ u32 rtl8723e_phy_query_rf_reg(struct ieee80211_hw *hw, rfpath, regaddr); } - bitshift = rtl8723_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); readback_value = (original_value & bitmask) >> bitshift; spin_unlock(&rtlpriv->locks.rf_lock); @@ -80,7 +80,7 @@ void rtl8723e_phy_set_rf_reg(struct ieee80211_hw *hw, original_value = rtl8723_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = rtl8723_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); @@ -89,7 +89,7 @@ void rtl8723e_phy_set_rf_reg(struct ieee80211_hw *hw, rtl8723_phy_rf_serial_write(hw, rfpath, regaddr, data); } else { if (bitmask != RFREG_OFFSET_MASK) { - bitshift = rtl8723_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c index 2b9313cb93db..094cb36153f5 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c @@ -41,7 +41,7 @@ u32 rtl8723be_phy_query_rf_reg(struct ieee80211_hw *hw, enum radio_path rfpath, spin_lock(&rtlpriv->locks.rf_lock); original_value = rtl8723_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = rtl8723_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); readback_value = (original_value & bitmask) >> bitshift; spin_unlock(&rtlpriv->locks.rf_lock); @@ -68,7 +68,7 @@ void rtl8723be_phy_set_rf_reg(struct ieee80211_hw *hw, enum radio_path path, if (bitmask != RFREG_OFFSET_MASK) { original_value = rtl8723_phy_rf_serial_read(hw, path, regaddr); - bitshift = rtl8723_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c index 5323ead30db0..fa1839d8ee55 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c @@ -29,9 +29,10 @@ static void _rtl8821ae_phy_rf_serial_write(struct ieee80211_hw *hw, u32 data); static u32 _rtl8821ae_phy_calculate_bit_shift(u32 bitmask) { - u32 i = ffs(bitmask); + if (WARN_ON_ONCE(!bitmask)) + return 0; - return i ? i - 1 : 32; + return __ffs(bitmask); } static bool _rtl8821ae_phy_bb8821a_config_parafile(struct ieee80211_hw *hw); /*static bool _rtl8812ae_phy_config_mac_with_headerfile(struct ieee80211_hw *hw);*/ diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h index 31f9e9e5c680..0bac788ccd6e 100644 --- a/drivers/net/wireless/realtek/rtlwifi/wifi.h +++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h @@ -3105,4 +3105,11 @@ static inline struct ieee80211_sta *rtl_find_sta(struct ieee80211_hw *hw, return ieee80211_find_sta(mac->vif, mac_addr); } +static inline u32 calculate_bit_shift(u32 bitmask) +{ + if (WARN_ON_ONCE(!bitmask)) + return 0; + + return __ffs(bitmask); +} #endif diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c index fabca307867a..0970d6bcba43 100644 --- a/drivers/net/wireless/realtek/rtw88/mac80211.c +++ b/drivers/net/wireless/realtek/rtw88/mac80211.c @@ -266,9 +266,9 @@ static void rtw_ops_configure_filter(struct ieee80211_hw *hw, if (changed_flags & FIF_ALLMULTI) { if (*new_flags & FIF_ALLMULTI) - rtwdev->hal.rcr |= BIT_AM | BIT_AB; + rtwdev->hal.rcr |= BIT_AM; else - rtwdev->hal.rcr &= ~(BIT_AM | BIT_AB); + rtwdev->hal.rcr &= ~(BIT_AM); } if (changed_flags & FIF_FCSFAIL) { if (*new_flags & FIF_FCSFAIL) diff --git a/drivers/net/wireless/silabs/wfx/sta.c b/drivers/net/wireless/silabs/wfx/sta.c index 626dfb4b7a55..073e870b2641 100644 --- a/drivers/net/wireless/silabs/wfx/sta.c +++ b/drivers/net/wireless/silabs/wfx/sta.c @@ -354,29 +354,38 @@ static int wfx_upload_ap_templates(struct wfx_vif *wvif) return 0; } -static void wfx_set_mfp_ap(struct wfx_vif *wvif) +static int wfx_set_mfp_ap(struct wfx_vif *wvif) { struct ieee80211_vif *vif = wvif_to_vif(wvif); struct sk_buff *skb = ieee80211_beacon_get(wvif->wdev->hw, vif, 0); const int ieoffset = offsetof(struct ieee80211_mgmt, u.beacon.variable); - const u16 *ptr = (u16 *)cfg80211_find_ie(WLAN_EID_RSN, skb->data + ieoffset, - skb->len - ieoffset); const int pairwise_cipher_suite_count_offset = 8 / sizeof(u16); const int pairwise_cipher_suite_size = 4 / sizeof(u16); const int akm_suite_size = 4 / sizeof(u16); + const u16 *ptr; - if (ptr) { - ptr += pairwise_cipher_suite_count_offset; - if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) - return; - ptr += 1 + pairwise_cipher_suite_size * *ptr; - if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) - return; - ptr += 1 + akm_suite_size * *ptr; - if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) - return; - wfx_hif_set_mfp(wvif, *ptr & BIT(7), *ptr & BIT(6)); - } + if (unlikely(!skb)) + return -ENOMEM; + + ptr = (u16 *)cfg80211_find_ie(WLAN_EID_RSN, skb->data + ieoffset, + skb->len - ieoffset); + if (unlikely(!ptr)) + return -EINVAL; + + ptr += pairwise_cipher_suite_count_offset; + if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) + return -EINVAL; + + ptr += 1 + pairwise_cipher_suite_size * *ptr; + if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) + return -EINVAL; + + ptr += 1 + akm_suite_size * *ptr; + if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) + return -EINVAL; + + wfx_hif_set_mfp(wvif, *ptr & BIT(7), *ptr & BIT(6)); + return 0; } int wfx_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -394,8 +403,7 @@ int wfx_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif, ret = wfx_hif_start(wvif, &vif->bss_conf, wvif->channel); if (ret > 0) return -EIO; - wfx_set_mfp_ap(wvif); - return ret; + return wfx_set_mfp_ap(wvif); } void wfx_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif, diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index c3a8d78a41a7..0d51c900c553 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -104,13 +104,12 @@ bool provides_xdp_headroom = true; module_param(provides_xdp_headroom, bool, 0644); static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, - u8 status); + s8 status); static void make_tx_response(struct xenvif_queue *queue, - struct xen_netif_tx_request *txp, + const struct xen_netif_tx_request *txp, unsigned int extra_count, - s8 st); -static void push_tx_responses(struct xenvif_queue *queue); + s8 status); static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx); @@ -208,13 +207,9 @@ static void xenvif_tx_err(struct xenvif_queue *queue, unsigned int extra_count, RING_IDX end) { RING_IDX cons = queue->tx.req_cons; - unsigned long flags; do { - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, extra_count, XEN_NETIF_RSP_ERROR); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, flags); if (cons == end) break; RING_COPY_REQUEST(&queue->tx, cons++, txp); @@ -463,12 +458,20 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS; - shinfo->nr_frags++, gop++, nr_slots--) { + nr_slots--) { + if (unlikely(!txp->size)) { + make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY); + ++txp; + continue; + } + index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; xenvif_tx_create_map_op(queue, pending_idx, txp, txp == first ? extra_count : 0, gop); frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + ++shinfo->nr_frags; + ++gop; if (txp == first) txp = txfrags; @@ -481,20 +484,33 @@ static void xenvif_get_requests(struct xenvif_queue *queue, shinfo = skb_shinfo(nskb); frags = shinfo->frags; - for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; - shinfo->nr_frags++, txp++, gop++) { + for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) { + if (unlikely(!txp->size)) { + make_tx_response(queue, txp, 0, + XEN_NETIF_RSP_OKAY); + continue; + } + index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; xenvif_tx_create_map_op(queue, pending_idx, txp, 0, gop); frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + ++shinfo->nr_frags; + ++gop; + } + + if (shinfo->nr_frags) { + skb_shinfo(skb)->frag_list = nskb; + nskb = NULL; } + } - skb_shinfo(skb)->frag_list = nskb; - } else if (nskb) { + if (nskb) { /* A frag_list skb was allocated but it is no longer needed - * because enough slots were converted to copy ops above. + * because enough slots were converted to copy ops above or some + * were empty. */ kfree_skb(nskb); } @@ -965,7 +981,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, (ret == 0) ? XEN_NETIF_RSP_OKAY : XEN_NETIF_RSP_ERROR); - push_tx_responses(queue); continue; } @@ -977,7 +992,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, make_tx_response(queue, &txreq, extra_count, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); continue; } @@ -1412,8 +1426,35 @@ int xenvif_tx_action(struct xenvif_queue *queue, int budget) return work_done; } +static void _make_tx_response(struct xenvif_queue *queue, + const struct xen_netif_tx_request *txp, + unsigned int extra_count, + s8 status) +{ + RING_IDX i = queue->tx.rsp_prod_pvt; + struct xen_netif_tx_response *resp; + + resp = RING_GET_RESPONSE(&queue->tx, i); + resp->id = txp->id; + resp->status = status; + + while (extra_count-- != 0) + RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + + queue->tx.rsp_prod_pvt = ++i; +} + +static void push_tx_responses(struct xenvif_queue *queue) +{ + int notify; + + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); + if (notify) + notify_remote_via_irq(queue->tx_irq); +} + static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, - u8 status) + s8 status) { struct pending_tx_info *pending_tx_info; pending_ring_idx_t index; @@ -1423,8 +1464,8 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, spin_lock_irqsave(&queue->response_lock, flags); - make_tx_response(queue, &pending_tx_info->req, - pending_tx_info->extra_count, status); + _make_tx_response(queue, &pending_tx_info->req, + pending_tx_info->extra_count, status); /* Release the pending index before pusing the Tx response so * its available before a new Tx request is pushed by the @@ -1438,32 +1479,19 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, spin_unlock_irqrestore(&queue->response_lock, flags); } - static void make_tx_response(struct xenvif_queue *queue, - struct xen_netif_tx_request *txp, + const struct xen_netif_tx_request *txp, unsigned int extra_count, - s8 st) + s8 status) { - RING_IDX i = queue->tx.rsp_prod_pvt; - struct xen_netif_tx_response *resp; - - resp = RING_GET_RESPONSE(&queue->tx, i); - resp->id = txp->id; - resp->status = st; - - while (extra_count-- != 0) - RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + unsigned long flags; - queue->tx.rsp_prod_pvt = ++i; -} + spin_lock_irqsave(&queue->response_lock, flags); -static void push_tx_responses(struct xenvif_queue *queue) -{ - int notify; + _make_tx_response(queue, txp, extra_count, status); + push_tx_responses(queue); - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); - if (notify) - notify_remote_via_irq(queue->tx_irq); + spin_unlock_irqrestore(&queue->response_lock, flags); } static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index eb7c87b344b8..0c088db94470 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1511,7 +1511,8 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl, if (id->ncap == 0) { /* namespace not allocated or attached */ info->is_removed = true; - return -ENODEV; + ret = -ENODEV; + goto error; } info->anagrpid = id->anagrpid; @@ -1529,8 +1530,10 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl, !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) memcpy(ids->nguid, id->nguid, sizeof(ids->nguid)); } + +error: kfree(id); - return 0; + return ret; } static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl, @@ -1922,9 +1925,10 @@ static void nvme_update_disk_info(struct gendisk *disk, /* * The block layer can't support LBA sizes larger than the page size - * yet, so catch this early and don't allow block I/O. + * or smaller than a sector size yet, so catch this early and don't + * allow block I/O. */ - if (ns->lba_shift > PAGE_SHIFT) { + if (ns->lba_shift > PAGE_SHIFT || ns->lba_shift < SECTOR_SHIFT) { capacity = 0; bs = (1 << 9); } @@ -4835,6 +4839,8 @@ static void nvme_fw_act_work(struct work_struct *work) struct nvme_ctrl, fw_act_work); unsigned long fw_act_timeout; + nvme_auth_stop(ctrl); + if (ctrl->mtfa) fw_act_timeout = jiffies + msecs_to_jiffies(ctrl->mtfa * 100); @@ -4890,7 +4896,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) * firmware activation. */ if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) { - nvme_auth_stop(ctrl); requeue = false; queue_work(nvme_wq, &ctrl->fw_act_work); } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 177a365b8ec5..3dbf926fd99f 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -221,11 +221,6 @@ static LIST_HEAD(nvme_fc_lport_list); static DEFINE_IDA(nvme_fc_local_port_cnt); static DEFINE_IDA(nvme_fc_ctrl_cnt); -static struct workqueue_struct *nvme_fc_wq; - -static bool nvme_fc_waiting_to_unload; -static DECLARE_COMPLETION(nvme_fc_unload_proceed); - /* * These items are short-term. They will eventually be moved into * a generic FC class. See comments in module init. @@ -255,8 +250,6 @@ nvme_fc_free_lport(struct kref *ref) /* remove from transport list */ spin_lock_irqsave(&nvme_fc_lock, flags); list_del(&lport->port_list); - if (nvme_fc_waiting_to_unload && list_empty(&nvme_fc_lport_list)) - complete(&nvme_fc_unload_proceed); spin_unlock_irqrestore(&nvme_fc_lock, flags); ida_free(&nvme_fc_local_port_cnt, lport->localport.port_num); @@ -3869,10 +3862,6 @@ static int __init nvme_fc_init_module(void) { int ret; - nvme_fc_wq = alloc_workqueue("nvme_fc_wq", WQ_MEM_RECLAIM, 0); - if (!nvme_fc_wq) - return -ENOMEM; - /* * NOTE: * It is expected that in the future the kernel will combine @@ -3890,7 +3879,7 @@ static int __init nvme_fc_init_module(void) ret = class_register(&fc_class); if (ret) { pr_err("couldn't register class fc\n"); - goto out_destroy_wq; + return ret; } /* @@ -3914,8 +3903,6 @@ out_destroy_device: device_destroy(&fc_class, MKDEV(0, 0)); out_destroy_class: class_unregister(&fc_class); -out_destroy_wq: - destroy_workqueue(nvme_fc_wq); return ret; } @@ -3935,45 +3922,23 @@ nvme_fc_delete_controllers(struct nvme_fc_rport *rport) spin_unlock(&rport->lock); } -static void -nvme_fc_cleanup_for_unload(void) +static void __exit nvme_fc_exit_module(void) { struct nvme_fc_lport *lport; struct nvme_fc_rport *rport; - - list_for_each_entry(lport, &nvme_fc_lport_list, port_list) { - list_for_each_entry(rport, &lport->endp_list, endp_list) { - nvme_fc_delete_controllers(rport); - } - } -} - -static void __exit nvme_fc_exit_module(void) -{ unsigned long flags; - bool need_cleanup = false; spin_lock_irqsave(&nvme_fc_lock, flags); - nvme_fc_waiting_to_unload = true; - if (!list_empty(&nvme_fc_lport_list)) { - need_cleanup = true; - nvme_fc_cleanup_for_unload(); - } + list_for_each_entry(lport, &nvme_fc_lport_list, port_list) + list_for_each_entry(rport, &lport->endp_list, endp_list) + nvme_fc_delete_controllers(rport); spin_unlock_irqrestore(&nvme_fc_lock, flags); - if (need_cleanup) { - pr_info("%s: waiting for ctlr deletes\n", __func__); - wait_for_completion(&nvme_fc_unload_proceed); - pr_info("%s: ctrl deletes complete\n", __func__); - } + flush_workqueue(nvme_delete_wq); nvmf_unregister_transport(&nvme_fc_transport); - ida_destroy(&nvme_fc_local_port_cnt); - ida_destroy(&nvme_fc_ctrl_cnt); - device_destroy(&fc_class, MKDEV(0, 0)); class_unregister(&fc_class); - destroy_workqueue(nvme_fc_wq); } module_init(nvme_fc_init_module); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 118bf08a708b..a892d679e338 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -382,6 +382,11 @@ struct nvme_ctrl { enum nvme_dctype dctype; }; +static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl) +{ + return READ_ONCE(ctrl->state); +} + enum nvme_iopolicy { NVME_IOPOLICY_NUMA, NVME_IOPOLICY_RR, diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 6a2816f3b4e8..73ae16059a1c 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -16,6 +16,7 @@ #endif #include <crypto/hash.h> #include <crypto/kpp.h> +#include <linux/nospec.h> #include "nvmet.h" @@ -508,6 +509,7 @@ static ssize_t nvmet_ns_ana_grpid_store(struct config_item *item, down_write(&nvmet_ana_sem); oldgrpid = ns->anagrpid; + newgrpid = array_index_nospec(newgrpid, NVMET_MAX_ANAGRPS); nvmet_ana_group_enabled[newgrpid]++; ns->anagrpid = newgrpid; nvmet_ana_group_enabled[oldgrpid]--; @@ -1580,6 +1582,7 @@ static struct config_group *nvmet_ana_groups_make_group( grp->grpid = grpid; down_write(&nvmet_ana_sem); + grpid = array_index_nospec(grpid, NVMET_MAX_ANAGRPS); nvmet_ana_group_enabled[grpid]++; up_write(&nvmet_ana_sem); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 1ab6601fdd5c..8a02ed63b156 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -111,6 +111,8 @@ struct nvmet_fc_tgtport { struct nvmet_fc_port_entry *pe; struct kref ref; u32 max_sg_cnt; + + struct work_struct put_work; }; struct nvmet_fc_port_entry { @@ -165,7 +167,7 @@ struct nvmet_fc_tgt_assoc { struct nvmet_fc_hostport *hostport; struct nvmet_fc_ls_iod *rcv_disconn; struct list_head a_list; - struct nvmet_fc_tgt_queue __rcu *queues[NVMET_NR_QUEUES + 1]; + struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1]; struct kref ref; struct work_struct del_work; struct rcu_head rcu; @@ -248,6 +250,13 @@ static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc); static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue); static int nvmet_fc_tgt_q_get(struct nvmet_fc_tgt_queue *queue); static void nvmet_fc_tgtport_put(struct nvmet_fc_tgtport *tgtport); +static void nvmet_fc_put_tgtport_work(struct work_struct *work) +{ + struct nvmet_fc_tgtport *tgtport = + container_of(work, struct nvmet_fc_tgtport, put_work); + + nvmet_fc_tgtport_put(tgtport); +} static int nvmet_fc_tgtport_get(struct nvmet_fc_tgtport *tgtport); static void nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_fcp_iod *fod); @@ -359,7 +368,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop) if (!lsop->req_queued) { spin_unlock_irqrestore(&tgtport->lock, flags); - return; + goto out_putwork; } list_del(&lsop->lsreq_list); @@ -372,7 +381,8 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop) (lsreq->rqstlen + lsreq->rsplen), DMA_BIDIRECTIONAL); - nvmet_fc_tgtport_put(tgtport); +out_putwork: + queue_work(nvmet_wq, &tgtport->put_work); } static int @@ -801,14 +811,11 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, if (!queue) return NULL; - if (!nvmet_fc_tgt_a_get(assoc)) - goto out_free_queue; - queue->work_q = alloc_workqueue("ntfc%d.%d.%d", 0, 0, assoc->tgtport->fc_target_port.port_num, assoc->a_id, qid); if (!queue->work_q) - goto out_a_put; + goto out_free_queue; queue->qid = qid; queue->sqsize = sqsize; @@ -830,15 +837,13 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, goto out_fail_iodlist; WARN_ON(assoc->queues[qid]); - rcu_assign_pointer(assoc->queues[qid], queue); + assoc->queues[qid] = queue; return queue; out_fail_iodlist: nvmet_fc_destroy_fcp_iodlist(assoc->tgtport, queue); destroy_workqueue(queue->work_q); -out_a_put: - nvmet_fc_tgt_a_put(assoc); out_free_queue: kfree(queue); return NULL; @@ -851,12 +856,8 @@ nvmet_fc_tgt_queue_free(struct kref *ref) struct nvmet_fc_tgt_queue *queue = container_of(ref, struct nvmet_fc_tgt_queue, ref); - rcu_assign_pointer(queue->assoc->queues[queue->qid], NULL); - nvmet_fc_destroy_fcp_iodlist(queue->assoc->tgtport, queue); - nvmet_fc_tgt_a_put(queue->assoc); - destroy_workqueue(queue->work_q); kfree_rcu(queue, rcu); @@ -968,7 +969,7 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport, rcu_read_lock(); list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { if (association_id == assoc->association_id) { - queue = rcu_dereference(assoc->queues[qid]); + queue = assoc->queues[qid]; if (queue && (!atomic_read(&queue->connected) || !nvmet_fc_tgt_q_get(queue))) @@ -1077,8 +1078,6 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle) /* new allocation not needed */ kfree(newhost); newhost = match; - /* no new allocation - release reference */ - nvmet_fc_tgtport_put(tgtport); } else { newhost->tgtport = tgtport; newhost->hosthandle = hosthandle; @@ -1093,13 +1092,28 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle) } static void -nvmet_fc_delete_assoc(struct work_struct *work) +nvmet_fc_delete_assoc(struct nvmet_fc_tgt_assoc *assoc) +{ + nvmet_fc_delete_target_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); +} + +static void +nvmet_fc_delete_assoc_work(struct work_struct *work) { struct nvmet_fc_tgt_assoc *assoc = container_of(work, struct nvmet_fc_tgt_assoc, del_work); + struct nvmet_fc_tgtport *tgtport = assoc->tgtport; - nvmet_fc_delete_target_assoc(assoc); - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_delete_assoc(assoc); + nvmet_fc_tgtport_put(tgtport); +} + +static void +nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc) +{ + nvmet_fc_tgtport_get(assoc->tgtport); + queue_work(nvmet_wq, &assoc->del_work); } static struct nvmet_fc_tgt_assoc * @@ -1111,6 +1125,9 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle) int idx; bool needrandom = true; + if (!tgtport->pe) + return NULL; + assoc = kzalloc(sizeof(*assoc), GFP_KERNEL); if (!assoc) return NULL; @@ -1130,7 +1147,7 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle) assoc->a_id = idx; INIT_LIST_HEAD(&assoc->a_list); kref_init(&assoc->ref); - INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc); + INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc_work); atomic_set(&assoc->terminating, 0); while (needrandom) { @@ -1171,13 +1188,18 @@ nvmet_fc_target_assoc_free(struct kref *ref) struct nvmet_fc_tgtport *tgtport = assoc->tgtport; struct nvmet_fc_ls_iod *oldls; unsigned long flags; + int i; + + for (i = NVMET_NR_QUEUES; i >= 0; i--) { + if (assoc->queues[i]) + nvmet_fc_delete_target_queue(assoc->queues[i]); + } /* Send Disconnect now that all i/o has completed */ nvmet_fc_xmt_disconnect_assoc(assoc); nvmet_fc_free_hostport(assoc->hostport); spin_lock_irqsave(&tgtport->lock, flags); - list_del_rcu(&assoc->a_list); oldls = assoc->rcv_disconn; spin_unlock_irqrestore(&tgtport->lock, flags); /* if pending Rcv Disconnect Association LS, send rsp now */ @@ -1207,7 +1229,7 @@ static void nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) { struct nvmet_fc_tgtport *tgtport = assoc->tgtport; - struct nvmet_fc_tgt_queue *queue; + unsigned long flags; int i, terminating; terminating = atomic_xchg(&assoc->terminating, 1); @@ -1216,29 +1238,21 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) if (terminating) return; + spin_lock_irqsave(&tgtport->lock, flags); + list_del_rcu(&assoc->a_list); + spin_unlock_irqrestore(&tgtport->lock, flags); - for (i = NVMET_NR_QUEUES; i >= 0; i--) { - rcu_read_lock(); - queue = rcu_dereference(assoc->queues[i]); - if (!queue) { - rcu_read_unlock(); - continue; - } + synchronize_rcu(); - if (!nvmet_fc_tgt_q_get(queue)) { - rcu_read_unlock(); - continue; - } - rcu_read_unlock(); - nvmet_fc_delete_target_queue(queue); - nvmet_fc_tgt_q_put(queue); + /* ensure all in-flight I/Os have been processed */ + for (i = NVMET_NR_QUEUES; i >= 0; i--) { + if (assoc->queues[i]) + flush_workqueue(assoc->queues[i]->work_q); } dev_info(tgtport->dev, "{%d:%d} Association deleted\n", tgtport->fc_target_port.port_num, assoc->a_id); - - nvmet_fc_tgt_a_put(assoc); } static struct nvmet_fc_tgt_assoc * @@ -1414,6 +1428,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo, kref_init(&newrec->ref); ida_init(&newrec->assoc_cnt); newrec->max_sg_cnt = template->max_sgl_segments; + INIT_WORK(&newrec->put_work, nvmet_fc_put_tgtport_work); ret = nvmet_fc_alloc_ls_iodlist(newrec); if (ret) { @@ -1491,9 +1506,8 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport) list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { if (!nvmet_fc_tgt_a_get(assoc)) continue; - if (!queue_work(nvmet_wq, &assoc->del_work)) - /* already deleting - release local reference */ - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); } rcu_read_unlock(); } @@ -1546,9 +1560,8 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port, continue; assoc->hostport->invalid = 1; noassoc = false; - if (!queue_work(nvmet_wq, &assoc->del_work)) - /* already deleting - release local reference */ - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); } spin_unlock_irqrestore(&tgtport->lock, flags); @@ -1580,7 +1593,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl) rcu_read_lock(); list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { - queue = rcu_dereference(assoc->queues[0]); + queue = assoc->queues[0]; if (queue && queue->nvme_sq.ctrl == ctrl) { if (nvmet_fc_tgt_a_get(assoc)) found_ctrl = true; @@ -1592,9 +1605,8 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl) nvmet_fc_tgtport_put(tgtport); if (found_ctrl) { - if (!queue_work(nvmet_wq, &assoc->del_work)) - /* already deleting - release local reference */ - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); return; } @@ -1624,6 +1636,8 @@ nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *target_port) /* terminate any outstanding associations */ __nvmet_fc_free_assocs(tgtport); + flush_workqueue(nvmet_wq); + /* * should terminate LS's as well. However, LS's will be generated * at the tail end of association termination, so they likely don't @@ -1869,9 +1883,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, sizeof(struct fcnvme_ls_disconnect_assoc_acc)), FCNVME_LS_DISCONNECT_ASSOC); - /* release get taken in nvmet_fc_find_target_assoc */ - nvmet_fc_tgt_a_put(assoc); - /* * The rules for LS response says the response cannot * go back until ABTS's have been sent for all outstanding @@ -1886,8 +1897,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, assoc->rcv_disconn = iod; spin_unlock_irqrestore(&tgtport->lock, flags); - nvmet_fc_delete_target_assoc(assoc); - if (oldls) { dev_info(tgtport->dev, "{%d:%d} Multiple Disconnect Association LS's " @@ -1903,6 +1912,9 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, nvmet_fc_xmt_ls_rsp(tgtport, oldls); } + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); + return false; } @@ -2539,8 +2551,9 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, fod->req.cmd = &fod->cmdiubuf.sqe; fod->req.cqe = &fod->rspiubuf.cqe; - if (tgtport->pe) - fod->req.port = tgtport->pe->port; + if (!tgtport->pe) + goto transport_error; + fod->req.port = tgtport->pe->port; /* clear any response payload */ memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf)); @@ -2901,6 +2914,9 @@ nvmet_fc_remove_port(struct nvmet_port *port) nvmet_fc_portentry_unbind(pe); + /* terminate any outstanding associations */ + __nvmet_fc_free_assocs(pe->tgtport); + kfree(pe); } @@ -2932,6 +2948,9 @@ static int __init nvmet_fc_init_module(void) static void __exit nvmet_fc_exit_module(void) { + /* ensure any shutdown operation, e.g. delete ctrls have finished */ + flush_workqueue(nvmet_wq); + /* sanity check - all lports should be removed */ if (!list_empty(&nvmet_fc_target_list)) pr_warn("%s: targetport list not empty\n", __func__); diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index c780af36c1d4..f5b8442b653d 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -358,7 +358,7 @@ fcloop_h2t_ls_req(struct nvme_fc_local_port *localport, if (!rport->targetport) { tls_req->status = -ECONNREFUSED; spin_lock(&rport->lock); - list_add_tail(&rport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &rport->ls_list); spin_unlock(&rport->lock); queue_work(nvmet_wq, &rport->ls_work); return ret; @@ -391,7 +391,7 @@ fcloop_h2t_xmt_ls_rsp(struct nvmet_fc_target_port *targetport, if (remoteport) { rport = remoteport->private; spin_lock(&rport->lock); - list_add_tail(&rport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &rport->ls_list); spin_unlock(&rport->lock); queue_work(nvmet_wq, &rport->ls_work); } @@ -446,7 +446,7 @@ fcloop_t2h_ls_req(struct nvmet_fc_target_port *targetport, void *hosthandle, if (!tport->remoteport) { tls_req->status = -ECONNREFUSED; spin_lock(&tport->lock); - list_add_tail(&tport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &tport->ls_list); spin_unlock(&tport->lock); queue_work(nvmet_wq, &tport->ls_work); return ret; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 355d80323b83..348076827469 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -18,6 +18,7 @@ #include "nvmet.h" #define NVMET_TCP_DEF_INLINE_DATA_SIZE (4 * PAGE_SIZE) +#define NVMET_TCP_MAXH2CDATA 0x400000 /* 16M arbitrary limit */ /* Define the socket priority to use for connections were it is desirable * that the NIC consider performing optimized packet processing or filtering. @@ -861,7 +862,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) icresp->hdr.pdo = 0; icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen); icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0); - icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */ + icresp->maxdata = cpu_to_le32(NVMET_TCP_MAXH2CDATA); icresp->cpda = 0; if (queue->hdr_digest) icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE; @@ -914,6 +915,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) { struct nvme_tcp_data_pdu *data = &queue->pdu.data; struct nvmet_tcp_cmd *cmd; + unsigned int exp_data_len; if (likely(queue->nr_cmds)) { if (unlikely(data->ttag >= queue->nr_cmds)) { @@ -932,12 +934,24 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) data->ttag, le32_to_cpu(data->data_offset), cmd->rbytes_done); /* FIXME: use path and transport errors */ - nvmet_req_complete(&cmd->req, - NVME_SC_INVALID_FIELD | NVME_SC_DNR); + nvmet_tcp_fatal_error(queue); return -EPROTO; } + exp_data_len = le32_to_cpu(data->hdr.plen) - + nvmet_tcp_hdgst_len(queue) - + nvmet_tcp_ddgst_len(queue) - + sizeof(*data); + cmd->pdu_len = le32_to_cpu(data->data_length); + if (unlikely(cmd->pdu_len != exp_data_len || + cmd->pdu_len == 0 || + cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) { + pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len); + /* FIXME: use proper transport errors */ + nvmet_tcp_fatal_error(queue); + return -EPROTO; + } cmd->pdu_recv = 0; nvmet_tcp_build_pdu_iovec(cmd); queue->cmd = cmd; @@ -1870,6 +1884,7 @@ static void __exit nvmet_tcp_exit(void) flush_workqueue(nvmet_wq); destroy_workqueue(nvmet_tcp_wq); + ida_destroy(&nvmet_tcp_queue_ida); } module_init(nvmet_tcp_init); diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h index 6109b3806b12..974d99d47f51 100644 --- a/drivers/nvme/target/trace.h +++ b/drivers/nvme/target/trace.h @@ -53,8 +53,7 @@ static inline void __assign_req_name(char *name, struct nvmet_req *req) return; } - strncpy(name, req->ns->device_path, - min_t(size_t, DISK_NAME_LEN, strlen(req->ns->device_path))); + strscpy_pad(name, req->ns->device_path, DISK_NAME_LEN); } #endif @@ -85,7 +84,7 @@ TRACE_EVENT(nvmet_req_init, __entry->flags = cmd->common.flags; __entry->nsid = le32_to_cpu(cmd->common.nsid); __entry->metadata = le64_to_cpu(cmd->common.metadata); - memcpy(__entry->cdw10, &cmd->common.cdw10, + memcpy(__entry->cdw10, &cmd->common.cdws, sizeof(__entry->cdw10)); ), TP_printk("nvmet%s: %sqid=%d, cmdid=%u, nsid=%u, flags=%#x, " diff --git a/drivers/of/base.c b/drivers/of/base.c index d5a5c35eba72..f849bbb9ef8c 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1646,6 +1646,7 @@ int of_parse_phandle_with_args_map(const struct device_node *np, out_args->np = new; of_node_put(cur); cur = new; + new = NULL; } put: of_node_put(cur); diff --git a/drivers/of/property.c b/drivers/of/property.c index b636777e6f7c..33d5f16c8120 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -762,7 +762,9 @@ struct device_node *of_graph_get_port_parent(struct device_node *node) /* Walk 3 levels up only if there is 'ports' node. */ for (depth = 3; depth && node; depth--) { node = of_get_next_parent(node); - if (depth == 2 && !of_node_name_eq(node, "ports")) + if (depth == 2 && !of_node_name_eq(node, "ports") && + !of_node_name_eq(node, "in-ports") && + !of_node_name_eq(node, "out-ports")) break; } return node; @@ -1243,7 +1245,7 @@ DEFINE_SIMPLE_PROP(clocks, "clocks", "#clock-cells") DEFINE_SIMPLE_PROP(interconnects, "interconnects", "#interconnect-cells") DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells") DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells") -DEFINE_SIMPLE_PROP(io_channels, "io-channel", "#io-channel-cells") +DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells") DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL) DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") @@ -1261,7 +1263,6 @@ DEFINE_SIMPLE_PROP(pinctrl5, "pinctrl-5", NULL) DEFINE_SIMPLE_PROP(pinctrl6, "pinctrl-6", NULL) DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL) DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL) -DEFINE_SIMPLE_PROP(remote_endpoint, "remote-endpoint", NULL) DEFINE_SIMPLE_PROP(pwms, "pwms", "#pwm-cells") DEFINE_SIMPLE_PROP(resets, "resets", "#reset-cells") DEFINE_SIMPLE_PROP(leds, "leds", NULL) @@ -1326,6 +1327,17 @@ static struct device_node *parse_interrupts(struct device_node *np, return of_irq_parse_one(np, index, &sup_args) ? NULL : sup_args.np; } +static struct device_node *parse_remote_endpoint(struct device_node *np, + const char *prop_name, + int index) +{ + /* Return NULL for index > 0 to signify end of remote-endpoints. */ + if (!index || strcmp(prop_name, "remote-endpoint")) + return NULL; + + return of_graph_get_remote_port_parent(np); +} + static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_clocks, }, { .parse_prop = parse_interconnects, }, diff --git a/drivers/of/unittest-data/tests-phandle.dtsi b/drivers/of/unittest-data/tests-phandle.dtsi index 6b33be4c4416..aa0d7027ffa6 100644 --- a/drivers/of/unittest-data/tests-phandle.dtsi +++ b/drivers/of/unittest-data/tests-phandle.dtsi @@ -38,6 +38,13 @@ phandle-map-pass-thru = <0x0 0xf0>; }; + provider5: provider5 { + #phandle-cells = <2>; + phandle-map = <2 7 &provider4 2 3>; + phandle-map-mask = <0xff 0xf>; + phandle-map-pass-thru = <0x0 0xf0>; + }; + consumer-a { phandle-list = <&provider1 1>, <&provider2 2 0>, @@ -64,7 +71,8 @@ <&provider4 4 0x100>, <&provider4 0 0x61>, <&provider0>, - <&provider4 19 0x20>; + <&provider4 19 0x20>, + <&provider5 2 7>; phandle-list-bad-phandle = <12345678 0 0>; phandle-list-bad-args = <&provider2 1 0>, <&provider4 0>; diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index bff8c4d96235..2d59f8cfeb93 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -49,6 +49,12 @@ static struct unittest_results { failed; \ }) +#ifdef CONFIG_OF_KOBJ +#define OF_KREF_READ(NODE) kref_read(&(NODE)->kobj.kref) +#else +#define OF_KREF_READ(NODE) 1 +#endif + /* * Expected message may have a message level other than KERN_INFO. * Print the expected message only if the current loglevel will allow @@ -448,6 +454,9 @@ static void __init of_unittest_parse_phandle_with_args(void) unittest(passed, "index %i - data error on node %pOF rc=%i\n", i, args.np, rc); + + if (rc == 0) + of_node_put(args.np); } /* Check for missing list property */ @@ -537,8 +546,9 @@ static void __init of_unittest_parse_phandle_with_args(void) static void __init of_unittest_parse_phandle_with_args_map(void) { - struct device_node *np, *p0, *p1, *p2, *p3; + struct device_node *np, *p[6] = {}; struct of_phandle_args args; + unsigned int prefs[6]; int i, rc; np = of_find_node_by_path("/testcase-data/phandle-tests/consumer-b"); @@ -547,34 +557,24 @@ static void __init of_unittest_parse_phandle_with_args_map(void) return; } - p0 = of_find_node_by_path("/testcase-data/phandle-tests/provider0"); - if (!p0) { - pr_err("missing testcase data\n"); - return; - } - - p1 = of_find_node_by_path("/testcase-data/phandle-tests/provider1"); - if (!p1) { - pr_err("missing testcase data\n"); - return; - } - - p2 = of_find_node_by_path("/testcase-data/phandle-tests/provider2"); - if (!p2) { - pr_err("missing testcase data\n"); - return; - } - - p3 = of_find_node_by_path("/testcase-data/phandle-tests/provider3"); - if (!p3) { - pr_err("missing testcase data\n"); - return; + p[0] = of_find_node_by_path("/testcase-data/phandle-tests/provider0"); + p[1] = of_find_node_by_path("/testcase-data/phandle-tests/provider1"); + p[2] = of_find_node_by_path("/testcase-data/phandle-tests/provider2"); + p[3] = of_find_node_by_path("/testcase-data/phandle-tests/provider3"); + p[4] = of_find_node_by_path("/testcase-data/phandle-tests/provider4"); + p[5] = of_find_node_by_path("/testcase-data/phandle-tests/provider5"); + for (i = 0; i < ARRAY_SIZE(p); ++i) { + if (!p[i]) { + pr_err("missing testcase data\n"); + return; + } + prefs[i] = OF_KREF_READ(p[i]); } rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells"); - unittest(rc == 7, "of_count_phandle_with_args() returned %i, expected 7\n", rc); + unittest(rc == 8, "of_count_phandle_with_args() returned %i, expected 8\n", rc); - for (i = 0; i < 8; i++) { + for (i = 0; i < 9; i++) { bool passed = true; memset(&args, 0, sizeof(args)); @@ -585,13 +585,13 @@ static void __init of_unittest_parse_phandle_with_args_map(void) switch (i) { case 0: passed &= !rc; - passed &= (args.np == p1); + passed &= (args.np == p[1]); passed &= (args.args_count == 1); passed &= (args.args[0] == 1); break; case 1: passed &= !rc; - passed &= (args.np == p3); + passed &= (args.np == p[3]); passed &= (args.args_count == 3); passed &= (args.args[0] == 2); passed &= (args.args[1] == 5); @@ -602,28 +602,36 @@ static void __init of_unittest_parse_phandle_with_args_map(void) break; case 3: passed &= !rc; - passed &= (args.np == p0); + passed &= (args.np == p[0]); passed &= (args.args_count == 0); break; case 4: passed &= !rc; - passed &= (args.np == p1); + passed &= (args.np == p[1]); passed &= (args.args_count == 1); passed &= (args.args[0] == 3); break; case 5: passed &= !rc; - passed &= (args.np == p0); + passed &= (args.np == p[0]); passed &= (args.args_count == 0); break; case 6: passed &= !rc; - passed &= (args.np == p2); + passed &= (args.np == p[2]); passed &= (args.args_count == 2); passed &= (args.args[0] == 15); passed &= (args.args[1] == 0x20); break; case 7: + passed &= !rc; + passed &= (args.np == p[3]); + passed &= (args.args_count == 3); + passed &= (args.args[0] == 2); + passed &= (args.args[1] == 5); + passed &= (args.args[2] == 3); + break; + case 8: passed &= (rc == -ENOENT); break; default: @@ -632,6 +640,9 @@ static void __init of_unittest_parse_phandle_with_args_map(void) unittest(passed, "index %i - data error on node %s rc=%i\n", i, args.np->full_name, rc); + + if (rc == 0) + of_node_put(args.np); } /* Check for missing list property */ @@ -678,6 +689,13 @@ static void __init of_unittest_parse_phandle_with_args_map(void) "OF: /testcase-data/phandle-tests/consumer-b: #phandle-cells = 2 found 1"); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); + + for (i = 0; i < ARRAY_SIZE(p); ++i) { + unittest(prefs[i] == OF_KREF_READ(p[i]), + "provider%d: expected:%d got:%d\n", + i, prefs[i], OF_KREF_READ(p[i])); + of_node_put(p[i]); + } } static void __init of_unittest_property_string(void) diff --git a/drivers/opp/core.c b/drivers/opp/core.c index f0d70ecc0271..71d3e3ba909a 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -1226,12 +1226,12 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) * value of the frequency. In such a case, do not abort but * configure the hardware to the desired frequency forcefully. */ - forced = opp_table->rate_clk_single != target_freq; + forced = opp_table->rate_clk_single != freq; } - ret = _set_opp(dev, opp_table, opp, &target_freq, forced); + ret = _set_opp(dev, opp_table, opp, &freq, forced); - if (target_freq) + if (freq) dev_pm_opp_put(opp); put_opp_table: diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c index 332bcc0053a5..498bae2e3403 100644 --- a/drivers/parisc/power.c +++ b/drivers/parisc/power.c @@ -238,7 +238,7 @@ static int __init power_init(void) if (running_on_qemu && soft_power_reg) register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, SYS_OFF_PRIO_DEFAULT, qemu_power_off, (void *)soft_power_reg); - else + if (!running_on_qemu || soft_power_reg) power_task = kthread_run(kpowerswd, (void*)soft_power_reg, KTHREAD_NAME); if (IS_ERR(power_task)) { diff --git a/drivers/parport/parport_serial.c b/drivers/parport/parport_serial.c index 9f5d784cd95d..3644997a8342 100644 --- a/drivers/parport/parport_serial.c +++ b/drivers/parport/parport_serial.c @@ -65,6 +65,10 @@ enum parport_pc_pci_cards { sunix_5069a, sunix_5079a, sunix_5099a, + brainboxes_uc257, + brainboxes_is300, + brainboxes_uc414, + brainboxes_px263, }; /* each element directly indexed from enum list, above */ @@ -158,6 +162,10 @@ static struct parport_pc_pci cards[] = { /* sunix_5069a */ { 1, { { 1, 2 }, } }, /* sunix_5079a */ { 1, { { 1, 2 }, } }, /* sunix_5099a */ { 1, { { 1, 2 }, } }, + /* brainboxes_uc257 */ { 1, { { 3, -1 }, } }, + /* brainboxes_is300 */ { 1, { { 3, -1 }, } }, + /* brainboxes_uc414 */ { 1, { { 3, -1 }, } }, + /* brainboxes_px263 */ { 1, { { 3, -1 }, } }, }; static struct pci_device_id parport_serial_pci_tbl[] = { @@ -277,6 +285,38 @@ static struct pci_device_id parport_serial_pci_tbl[] = { { PCI_VENDOR_ID_SUNIX, PCI_DEVICE_ID_SUNIX_1999, PCI_VENDOR_ID_SUNIX, 0x0104, 0, 0, sunix_5099a }, + /* Brainboxes UC-203 */ + { PCI_VENDOR_ID_INTASHIELD, 0x0bc1, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 }, + { PCI_VENDOR_ID_INTASHIELD, 0x0bc2, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 }, + + /* Brainboxes UC-257 */ + { PCI_VENDOR_ID_INTASHIELD, 0x0861, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 }, + { PCI_VENDOR_ID_INTASHIELD, 0x0862, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 }, + { PCI_VENDOR_ID_INTASHIELD, 0x0863, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 }, + + /* Brainboxes UC-414 */ + { PCI_VENDOR_ID_INTASHIELD, 0x0e61, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc414 }, + + /* Brainboxes UC-475 */ + { PCI_VENDOR_ID_INTASHIELD, 0x0981, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 }, + { PCI_VENDOR_ID_INTASHIELD, 0x0982, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc257 }, + + /* Brainboxes IS-300/IS-500 */ + { PCI_VENDOR_ID_INTASHIELD, 0x0da0, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_is300 }, + + /* Brainboxes PX-263/PX-295 */ + { PCI_VENDOR_ID_INTASHIELD, 0x402c, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_px263 }, + { 0, } /* terminate list */ }; MODULE_DEVICE_TABLE(pci,parport_serial_pci_tbl); @@ -542,6 +582,30 @@ static struct pciserial_board pci_parport_serial_boards[] = { .base_baud = 921600, .uart_offset = 0x8, }, + [brainboxes_uc257] = { + .flags = FL_BASE2, + .num_ports = 2, + .base_baud = 115200, + .uart_offset = 8, + }, + [brainboxes_is300] = { + .flags = FL_BASE2, + .num_ports = 1, + .base_baud = 115200, + .uart_offset = 8, + }, + [brainboxes_uc414] = { + .flags = FL_BASE2, + .num_ports = 4, + .base_baud = 115200, + .uart_offset = 8, + }, + [brainboxes_px263] = { + .flags = FL_BASE2, + .num_ports = 4, + .base_baud = 921600, + .uart_offset = 8, + }, }; struct parport_serial_private { diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c index efa8131e2415..8d44cd88ae3f 100644 --- a/drivers/pci/controller/dwc/pci-keystone.c +++ b/drivers/pci/controller/dwc/pci-keystone.c @@ -1379,13 +1379,13 @@ static int ks_pcie_probe(struct platform_device *pdev) goto err_link; } - /* Obtain reference(s) to the phy(s) */ + /* Obtain references to the PHYs */ for (i = 0; i < num_lanes; i++) phy_pm_runtime_get_sync(ks_pcie->phy[i]); ret = ks_pcie_enable_phy(ks_pcie); - /* Release reference(s) to the phy(s) */ + /* Release references to the PHYs */ for (i = 0; i < num_lanes; i++) phy_pm_runtime_put_sync(ks_pcie->phy[i]); diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 83ddb190292e..4086a7818981 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -6,6 +6,7 @@ * Author: Kishon Vijay Abraham I <kishon@ti.com> */ +#include <linux/align.h> #include <linux/of.h> #include <linux/platform_device.h> @@ -600,6 +601,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, } aligned_offset = msg_addr & (epc->mem->window.page_size - 1); + msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size); ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, epc->mem->window.page_size); if (ret) diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c index b8612ce5f4d0..40c38ca5a42e 100644 --- a/drivers/pci/controller/pcie-mediatek-gen3.c +++ b/drivers/pci/controller/pcie-mediatek-gen3.c @@ -245,35 +245,60 @@ static int mtk_pcie_set_trans_table(struct mtk_gen3_pcie *pcie, resource_size_t cpu_addr, resource_size_t pci_addr, resource_size_t size, - unsigned long type, int num) + unsigned long type, int *num) { + resource_size_t remaining = size; + resource_size_t table_size; + resource_size_t addr_align; + const char *range_type; void __iomem *table; u32 val; - if (num >= PCIE_MAX_TRANS_TABLES) { - dev_err(pcie->dev, "not enough translate table for addr: %#llx, limited to [%d]\n", - (unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES); - return -ENODEV; - } + while (remaining && (*num < PCIE_MAX_TRANS_TABLES)) { + /* Table size needs to be a power of 2 */ + table_size = BIT(fls(remaining) - 1); + + if (cpu_addr > 0) { + addr_align = BIT(ffs(cpu_addr) - 1); + table_size = min(table_size, addr_align); + } + + /* Minimum size of translate table is 4KiB */ + if (table_size < 0x1000) { + dev_err(pcie->dev, "illegal table size %#llx\n", + (unsigned long long)table_size); + return -EINVAL; + } - table = pcie->base + PCIE_TRANS_TABLE_BASE_REG + - num * PCIE_ATR_TLB_SET_OFFSET; + table = pcie->base + PCIE_TRANS_TABLE_BASE_REG + *num * PCIE_ATR_TLB_SET_OFFSET; + writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(table_size) - 1), table); + writel_relaxed(upper_32_bits(cpu_addr), table + PCIE_ATR_SRC_ADDR_MSB_OFFSET); + writel_relaxed(lower_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET); + writel_relaxed(upper_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET); - writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(size) - 1), - table); - writel_relaxed(upper_32_bits(cpu_addr), - table + PCIE_ATR_SRC_ADDR_MSB_OFFSET); - writel_relaxed(lower_32_bits(pci_addr), - table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET); - writel_relaxed(upper_32_bits(pci_addr), - table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET); + if (type == IORESOURCE_IO) { + val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO; + range_type = "IO"; + } else { + val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM; + range_type = "MEM"; + } - if (type == IORESOURCE_IO) - val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO; - else - val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM; + writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET); - writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET); + dev_dbg(pcie->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n", + range_type, *num, (unsigned long long)cpu_addr, + (unsigned long long)pci_addr, (unsigned long long)table_size); + + cpu_addr += table_size; + pci_addr += table_size; + remaining -= table_size; + (*num)++; + } + + if (remaining) + dev_warn(pcie->dev, "not enough translate table for addr: %#llx, limited to [%d]\n", + (unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES); return 0; } @@ -380,30 +405,20 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie) resource_size_t cpu_addr; resource_size_t pci_addr; resource_size_t size; - const char *range_type; - if (type == IORESOURCE_IO) { + if (type == IORESOURCE_IO) cpu_addr = pci_pio_to_address(res->start); - range_type = "IO"; - } else if (type == IORESOURCE_MEM) { + else if (type == IORESOURCE_MEM) cpu_addr = res->start; - range_type = "MEM"; - } else { + else continue; - } pci_addr = res->start - entry->offset; size = resource_size(res); err = mtk_pcie_set_trans_table(pcie, cpu_addr, pci_addr, size, - type, table_index); + type, &table_index); if (err) return err; - - dev_dbg(pcie->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n", - range_type, table_index, (unsigned long long)cpu_addr, - (unsigned long long)pci_addr, (unsigned long long)size); - - table_index++; } return 0; diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index ae5ad05ddc1d..11bdef206d12 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -617,12 +617,18 @@ static void mtk_pcie_intr_handler(struct irq_desc *desc) if (status & MSI_STATUS){ unsigned long imsi_status; + /* + * The interrupt status can be cleared even if the + * MSI status remains pending. As such, given the + * edge-triggered interrupt type, its status should + * be cleared before being dispatched to the + * handler of the underlying device. + */ + writel(MSI_STATUS, port->base + PCIE_INT_STATUS); while ((imsi_status = readl(port->base + PCIE_IMSI_STATUS))) { for_each_set_bit(bit, &imsi_status, MTK_MSI_IRQS_NUM) generic_handle_domain_irq(port->inner_domain, bit); } - /* Clear MSI interrupt status */ - writel(MSI_STATUS, port->base + PCIE_INT_STATUS); } } diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index e9cf318e6670..34877a1f43a1 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -60,7 +60,7 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) return (irq_hw_number_t)desc->msi_index | pci_dev_id(dev) << 11 | - (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; + ((irq_hw_number_t)(pci_domain_nr(dev->bus) & 0xFFFFFFFF)) << 27; } static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 8df156c28aad..5368a37154cf 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1302,6 +1302,9 @@ static int pci_set_full_power_state(struct pci_dev *dev) pci_restore_bars(dev); } + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self); + return 0; } @@ -1396,6 +1399,9 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) pci_power_name(dev->current_state), pci_power_name(state)); + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self); + return 0; } diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index ffccb03933e2..e1d02b7c6029 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -274,7 +274,7 @@ void pci_bus_put(struct pci_bus *bus); /* PCIe speed to Mb/s reduced by encoding overhead */ #define PCIE_SPEED2MBS_ENC(speed) \ - ((speed) == PCIE_SPEED_64_0GT ? 64000*128/130 : \ + ((speed) == PCIE_SPEED_64_0GT ? 64000*1/1 : \ (speed) == PCIE_SPEED_32_0GT ? 32000*128/130 : \ (speed) == PCIE_SPEED_16_0GT ? 16000*128/130 : \ (speed) == PCIE_SPEED_8_0GT ? 8000*128/130 : \ @@ -561,10 +561,12 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); +void pcie_aspm_pm_state_change(struct pci_dev *pdev); void pcie_aspm_powersave_config_link(struct pci_dev *pdev); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } +static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } #endif diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index e2d8a74f83c3..5426f450ce91 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -748,7 +748,7 @@ static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info) u8 bus = info->id >> 8; u8 devfn = info->id & 0xff; - pci_info(dev, "%s%s error received: %04x:%02x:%02x.%d\n", + pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n", info->multi_error_valid ? "Multiple " : "", aer_error_severity_string[info->severity], pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn), @@ -936,7 +936,12 @@ static bool find_source_device(struct pci_dev *parent, pci_walk_bus(parent->subordinate, find_device_iter, e_info); if (!e_info->error_dev_num) { - pci_info(parent, "can't find device of ID%04x\n", e_info->id); + u8 bus = e_info->id >> 8; + u8 devfn = e_info->id & 0xff; + + pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n", + pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn), + PCI_FUNC(devfn)); return false; } return true; diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index f0b1e650a148..f74b9002d403 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1056,6 +1056,25 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) up_read(&pci_bus_sem); } +/* @pdev: the root port or switch downstream port */ +void pcie_aspm_pm_state_change(struct pci_dev *pdev) +{ + struct pcie_link_state *link = pdev->link_state; + + if (aspm_disabled || !link) + return; + /* + * Devices changed PM state, we should recheck if latency + * meets all functions' requirement + */ + down_read(&pci_bus_sem); + mutex_lock(&aspm_lock); + pcie_update_aspm_capable(link->root); + pcie_config_aspm_path(link); + mutex_unlock(&aspm_lock); + up_read(&pci_bus_sem); +} + void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { struct pcie_link_state *link = pdev->link_state; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index c132839d99dc..51d634fbdfb8 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -607,10 +607,13 @@ static void quirk_amd_dwc_class(struct pci_dev *pdev) { u32 class = pdev->class; - /* Use "USB Device (not host controller)" class */ - pdev->class = PCI_CLASS_SERIAL_USB_DEVICE; - pci_info(pdev, "PCI class overridden (%#08x -> %#08x) so dwc3 driver can claim this instead of xhci\n", - class, pdev->class); + if (class != PCI_CLASS_SERIAL_USB_DEVICE) { + /* Use "USB Device (not host controller)" class */ + pdev->class = PCI_CLASS_SERIAL_USB_DEVICE; + pci_info(pdev, + "PCI class overridden (%#08x -> %#08x) so dwc3 driver can claim this instead of xhci\n", + class, pdev->class); + } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB, quirk_amd_dwc_class); @@ -3692,6 +3695,19 @@ DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_ATI, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, 8, quirk_no_pm_reset); /* + * Spectrum-{1,2,3,4} devices report that a D3hot->D0 transition causes a reset + * (i.e., they advertise NoSoftRst-). However, this transition does not have + * any effect on the device: It continues to be operational and network ports + * remain up. Advertising this support makes it seem as if a PM reset is viable + * for these devices. Mark it as unavailable to skip it when testing reset + * methods. + */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcb84, quirk_no_pm_reset); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcf6c, quirk_no_pm_reset); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcf70, quirk_no_pm_reset); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcf80, quirk_no_pm_reset); + +/* * Thunderbolt controllers with broken MSI hotplug signaling: * Entire 1st generation (Light Ridge, Eagle Ridge, Light Peak) and part * of the 2nd generation (Cactus Ridge 4C up to revision 1, Port Ridge). @@ -4602,17 +4618,21 @@ static int pci_quirk_xgene_acs(struct pci_dev *dev, u16 acs_flags) * But the implementation could block peer-to-peer transactions between them * and provide ACS-like functionality. */ -static int pci_quirk_zhaoxin_pcie_ports_acs(struct pci_dev *dev, u16 acs_flags) +static int pci_quirk_zhaoxin_pcie_ports_acs(struct pci_dev *dev, u16 acs_flags) { if (!pci_is_pcie(dev) || ((pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) && (pci_pcie_type(dev) != PCI_EXP_TYPE_DOWNSTREAM))) return -ENOTTY; + /* + * Future Zhaoxin Root Ports and Switch Downstream Ports will + * implement ACS capability in accordance with the PCIe Spec. + */ switch (dev->device) { case 0x0710 ... 0x071e: case 0x0721: - case 0x0723 ... 0x0732: + case 0x0723 ... 0x0752: return pci_acs_ctrl_enabled(acs_flags, PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); } diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 0c1faa6c1973..3f3320d0a4f8 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -1308,13 +1308,6 @@ static void stdev_release(struct device *dev) { struct switchtec_dev *stdev = to_stdev(dev); - if (stdev->dma_mrpc) { - iowrite32(0, &stdev->mmio_mrpc->dma_en); - flush_wc_buf(stdev); - writeq(0, &stdev->mmio_mrpc->dma_addr); - dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc), - stdev->dma_mrpc, stdev->dma_mrpc_dma_addr); - } kfree(stdev); } @@ -1358,7 +1351,7 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev) return ERR_PTR(-ENOMEM); stdev->alive = true; - stdev->pdev = pdev; + stdev->pdev = pci_dev_get(pdev); INIT_LIST_HEAD(&stdev->mrpc_queue); mutex_init(&stdev->mrpc_mutex); stdev->mrpc_busy = 0; @@ -1391,6 +1384,7 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev) return stdev; err_put: + pci_dev_put(stdev->pdev); put_device(&stdev->dev); return ERR_PTR(rc); } @@ -1646,6 +1640,18 @@ static int switchtec_init_pci(struct switchtec_dev *stdev, return 0; } +static void switchtec_exit_pci(struct switchtec_dev *stdev) +{ + if (stdev->dma_mrpc) { + iowrite32(0, &stdev->mmio_mrpc->dma_en); + flush_wc_buf(stdev); + writeq(0, &stdev->mmio_mrpc->dma_addr); + dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc), + stdev->dma_mrpc, stdev->dma_mrpc_dma_addr); + stdev->dma_mrpc = NULL; + } +} + static int switchtec_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -1705,6 +1711,9 @@ static void switchtec_pci_remove(struct pci_dev *pdev) ida_free(&switchtec_minor_ida, MINOR(stdev->dev.devt)); dev_info(&stdev->dev, "unregistered.\n"); stdev_kill(stdev); + switchtec_exit_pci(stdev); + pci_dev_put(stdev->pdev); + stdev->pdev = NULL; put_device(&stdev->dev); } diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c index 9de617ca9daa..7e61c6b278a7 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c @@ -675,8 +675,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) channel->irq = platform_get_irq_optional(pdev, 0); channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node); if (channel->dr_mode != USB_DR_MODE_UNKNOWN) { - int ret; - channel->is_otg_channel = true; channel->uses_otg_pins = !of_property_read_bool(dev->of_node, "renesas,no-otg-pins"); @@ -740,8 +738,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) ret = PTR_ERR(provider); goto error; } else if (channel->is_otg_channel) { - int ret; - ret = device_create_file(dev, &dev_attr_role); if (ret < 0) goto error; diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index 31a775877f6e..63c45809943f 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -116,7 +116,7 @@ static int omap_usb_set_vbus(struct usb_otg *otg, bool enabled) { struct omap_usb *phy = phy_to_omapusb(otg->usb_phy); - if (!phy->comparator) + if (!phy->comparator || !phy->comparator->set_vbus) return -ENODEV; return phy->comparator->set_vbus(phy->comparator, enabled); @@ -126,7 +126,7 @@ static int omap_usb_start_srp(struct usb_otg *otg) { struct omap_usb *phy = phy_to_omapusb(otg->usb_phy); - if (!phy->comparator) + if (!phy->comparator || !phy->comparator->start_srp) return -ENODEV; return phy->comparator->start_srp(phy->comparator); diff --git a/drivers/pinctrl/cirrus/Kconfig b/drivers/pinctrl/cirrus/Kconfig index 530426a74f75..b3cea8d56c4f 100644 --- a/drivers/pinctrl/cirrus/Kconfig +++ b/drivers/pinctrl/cirrus/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only config PINCTRL_LOCHNAGAR tristate "Cirrus Logic Lochnagar pinctrl driver" - depends on MFD_LOCHNAGAR + # Avoid clash caused by MIPS defining RST, which is used in the driver + depends on MFD_LOCHNAGAR && !MIPS select GPIOLIB select PINMUX select PINCONF diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index f71c6457e350..2425d4813c3c 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -1033,6 +1033,13 @@ static const struct of_device_id atmel_pctrl_of_match[] = { } }; +/* + * This lock class allows to tell lockdep that parent IRQ and children IRQ do + * not share the same class so it does not raise false positive + */ +static struct lock_class_key atmel_lock_key; +static struct lock_class_key atmel_request_key; + static int atmel_pinctrl_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1185,6 +1192,7 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) irq_set_chip_and_handler(irq, &atmel_gpio_irq_chip, handle_simple_irq); irq_set_chip_data(irq, atmel_pioctrl); + irq_set_lockdep_class(irq, &atmel_lock_key, &atmel_request_key); dev_dbg(dev, "atmel gpio irq domain: hwirq: %d, linux irq: %d\n", i, irq); diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c index 68509a2301b8..5abab6bc763a 100644 --- a/drivers/pinctrl/pinctrl-cy8c95x0.c +++ b/drivers/pinctrl/pinctrl-cy8c95x0.c @@ -749,6 +749,8 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip, ret = regmap_read(chip->regmap, reg, ®_val); if (reg_val & bit) arg = 1; + if (param == PIN_CONFIG_OUTPUT_ENABLE) + arg = !arg; *config = pinconf_to_config_packed(param, (u16)arg); out: @@ -857,7 +859,7 @@ static int cy8c95x0_setup_gpiochip(struct cy8c95x0_pinctrl *chip) gc->get_direction = cy8c95x0_gpio_get_direction; gc->get_multiple = cy8c95x0_gpio_get_multiple; gc->set_multiple = cy8c95x0_gpio_set_multiple; - gc->set_config = gpiochip_generic_config, + gc->set_config = gpiochip_generic_config; gc->can_sleep = true; gc->add_pin_ranges = cy8c95x0_add_pin_ranges; diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c index 5b544fb7f3d8..3b18a03075f4 100644 --- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c +++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c @@ -489,7 +489,7 @@ static int starfive_dt_node_to_map(struct pinctrl_dev *pctldev, nmaps = 0; ngroups = 0; - for_each_child_of_node(np, child) { + for_each_available_child_of_node(np, child) { int npinmux = of_property_count_u32_elems(child, "pinmux"); int npins = of_property_count_u32_elems(child, "pins"); @@ -524,7 +524,7 @@ static int starfive_dt_node_to_map(struct pinctrl_dev *pctldev, nmaps = 0; ngroups = 0; mutex_lock(&sfp->mutex); - for_each_child_of_node(np, child) { + for_each_available_child_of_node(np, child) { int npins; int i; diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c index 9b12fe8e95c9..dd2e654daf4b 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c @@ -74,30 +74,30 @@ static ssize_t show_perf_status_freq_khz(struct uncore_data *data, char *buf) } #define store_uncore_min_max(name, min_max) \ - static ssize_t store_##name(struct device *dev, \ - struct device_attribute *attr, \ + static ssize_t store_##name(struct kobject *kobj, \ + struct kobj_attribute *attr, \ const char *buf, size_t count) \ { \ - struct uncore_data *data = container_of(attr, struct uncore_data, name##_dev_attr);\ + struct uncore_data *data = container_of(attr, struct uncore_data, name##_kobj_attr);\ \ return store_min_max_freq_khz(data, buf, count, \ min_max); \ } #define show_uncore_min_max(name, min_max) \ - static ssize_t show_##name(struct device *dev, \ - struct device_attribute *attr, char *buf)\ + static ssize_t show_##name(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf)\ { \ - struct uncore_data *data = container_of(attr, struct uncore_data, name##_dev_attr);\ + struct uncore_data *data = container_of(attr, struct uncore_data, name##_kobj_attr);\ \ return show_min_max_freq_khz(data, buf, min_max); \ } #define show_uncore_perf_status(name) \ - static ssize_t show_##name(struct device *dev, \ - struct device_attribute *attr, char *buf)\ + static ssize_t show_##name(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf)\ { \ - struct uncore_data *data = container_of(attr, struct uncore_data, name##_dev_attr);\ + struct uncore_data *data = container_of(attr, struct uncore_data, name##_kobj_attr);\ \ return show_perf_status_freq_khz(data, buf); \ } @@ -111,11 +111,11 @@ show_uncore_min_max(max_freq_khz, 1); show_uncore_perf_status(current_freq_khz); #define show_uncore_data(member_name) \ - static ssize_t show_##member_name(struct device *dev, \ - struct device_attribute *attr, char *buf)\ + static ssize_t show_##member_name(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf)\ { \ struct uncore_data *data = container_of(attr, struct uncore_data,\ - member_name##_dev_attr);\ + member_name##_kobj_attr);\ \ return sysfs_emit(buf, "%u\n", \ data->member_name); \ @@ -126,29 +126,29 @@ show_uncore_data(initial_max_freq_khz); #define init_attribute_rw(_name) \ do { \ - sysfs_attr_init(&data->_name##_dev_attr.attr); \ - data->_name##_dev_attr.show = show_##_name; \ - data->_name##_dev_attr.store = store_##_name; \ - data->_name##_dev_attr.attr.name = #_name; \ - data->_name##_dev_attr.attr.mode = 0644; \ + sysfs_attr_init(&data->_name##_kobj_attr.attr); \ + data->_name##_kobj_attr.show = show_##_name; \ + data->_name##_kobj_attr.store = store_##_name; \ + data->_name##_kobj_attr.attr.name = #_name; \ + data->_name##_kobj_attr.attr.mode = 0644; \ } while (0) #define init_attribute_ro(_name) \ do { \ - sysfs_attr_init(&data->_name##_dev_attr.attr); \ - data->_name##_dev_attr.show = show_##_name; \ - data->_name##_dev_attr.store = NULL; \ - data->_name##_dev_attr.attr.name = #_name; \ - data->_name##_dev_attr.attr.mode = 0444; \ + sysfs_attr_init(&data->_name##_kobj_attr.attr); \ + data->_name##_kobj_attr.show = show_##_name; \ + data->_name##_kobj_attr.store = NULL; \ + data->_name##_kobj_attr.attr.name = #_name; \ + data->_name##_kobj_attr.attr.mode = 0444; \ } while (0) #define init_attribute_root_ro(_name) \ do { \ - sysfs_attr_init(&data->_name##_dev_attr.attr); \ - data->_name##_dev_attr.show = show_##_name; \ - data->_name##_dev_attr.store = NULL; \ - data->_name##_dev_attr.attr.name = #_name; \ - data->_name##_dev_attr.attr.mode = 0400; \ + sysfs_attr_init(&data->_name##_kobj_attr.attr); \ + data->_name##_kobj_attr.show = show_##_name; \ + data->_name##_kobj_attr.store = NULL; \ + data->_name##_kobj_attr.attr.name = #_name; \ + data->_name##_kobj_attr.attr.mode = 0400; \ } while (0) static int create_attr_group(struct uncore_data *data, char *name) @@ -161,14 +161,14 @@ static int create_attr_group(struct uncore_data *data, char *name) init_attribute_ro(initial_max_freq_khz); init_attribute_root_ro(current_freq_khz); - data->uncore_attrs[index++] = &data->max_freq_khz_dev_attr.attr; - data->uncore_attrs[index++] = &data->min_freq_khz_dev_attr.attr; - data->uncore_attrs[index++] = &data->initial_min_freq_khz_dev_attr.attr; - data->uncore_attrs[index++] = &data->initial_max_freq_khz_dev_attr.attr; + data->uncore_attrs[index++] = &data->max_freq_khz_kobj_attr.attr; + data->uncore_attrs[index++] = &data->min_freq_khz_kobj_attr.attr; + data->uncore_attrs[index++] = &data->initial_min_freq_khz_kobj_attr.attr; + data->uncore_attrs[index++] = &data->initial_max_freq_khz_kobj_attr.attr; ret = uncore_read_freq(data, &freq); if (!ret) - data->uncore_attrs[index++] = &data->current_freq_khz_dev_attr.attr; + data->uncore_attrs[index++] = &data->current_freq_khz_kobj_attr.attr; data->uncore_attrs[index] = NULL; diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h index f5dcfa2fb285..2d9dc3151d6e 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h @@ -23,11 +23,11 @@ * @die_id: Die id for this instance * @name: Sysfs entry name for this instance * @uncore_attr_group: Attribute group storage - * @max_freq_khz_dev_attr: Storage for device attribute max_freq_khz - * @mix_freq_khz_dev_attr: Storage for device attribute min_freq_khz - * @initial_max_freq_khz_dev_attr: Storage for device attribute initial_max_freq_khz - * @initial_min_freq_khz_dev_attr: Storage for device attribute initial_min_freq_khz - * @current_freq_khz_dev_attr: Storage for device attribute current_freq_khz + * @max_freq_khz_dev_attr: Storage for kobject attribute max_freq_khz + * @mix_freq_khz_dev_attr: Storage for kobject attribute min_freq_khz + * @initial_max_freq_khz_dev_attr: Storage for kobject attribute initial_max_freq_khz + * @initial_min_freq_khz_dev_attr: Storage for kobject attribute initial_min_freq_khz + * @current_freq_khz_dev_attr: Storage for kobject attribute current_freq_khz * @uncore_attrs: Attribute storage for group creation * * This structure is used to encapsulate all data related to uncore sysfs @@ -44,11 +44,11 @@ struct uncore_data { char name[32]; struct attribute_group uncore_attr_group; - struct device_attribute max_freq_khz_dev_attr; - struct device_attribute min_freq_khz_dev_attr; - struct device_attribute initial_max_freq_khz_dev_attr; - struct device_attribute initial_min_freq_khz_dev_attr; - struct device_attribute current_freq_khz_dev_attr; + struct kobj_attribute max_freq_khz_kobj_attr; + struct kobj_attribute min_freq_khz_kobj_attr; + struct kobj_attribute initial_max_freq_khz_kobj_attr; + struct kobj_attribute initial_min_freq_khz_kobj_attr; + struct kobj_attribute current_freq_khz_kobj_attr; struct attribute *uncore_attrs[6]; }; diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c index c5e4e35c8d20..c10c99a31a90 100644 --- a/drivers/platform/x86/intel/vbtn.c +++ b/drivers/platform/x86/intel/vbtn.c @@ -73,10 +73,10 @@ struct intel_vbtn_priv { bool wakeup_mode; }; -static void detect_tablet_mode(struct platform_device *device) +static void detect_tablet_mode(struct device *dev) { - struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev); - acpi_handle handle = ACPI_HANDLE(&device->dev); + struct intel_vbtn_priv *priv = dev_get_drvdata(dev); + acpi_handle handle = ACPI_HANDLE(dev); unsigned long long vgbs; acpi_status status; int m; @@ -89,6 +89,8 @@ static void detect_tablet_mode(struct platform_device *device) input_report_switch(priv->switches_dev, SW_TABLET_MODE, m); m = (vgbs & VGBS_DOCK_MODE_FLAG) ? 1 : 0; input_report_switch(priv->switches_dev, SW_DOCK, m); + + input_sync(priv->switches_dev); } /* @@ -134,7 +136,7 @@ static int intel_vbtn_input_setup(struct platform_device *device) priv->switches_dev->id.bustype = BUS_HOST; if (priv->has_switches) { - detect_tablet_mode(device); + detect_tablet_mode(&device->dev); ret = input_register_device(priv->switches_dev); if (ret) @@ -358,7 +360,13 @@ static void intel_vbtn_pm_complete(struct device *dev) static int intel_vbtn_pm_resume(struct device *dev) { + struct intel_vbtn_priv *priv = dev_get_drvdata(dev); + intel_vbtn_pm_complete(dev); + + if (priv->has_switches) + detect_tablet_mode(dev); + return 0; } diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c index 483bb6565166..40477d1d41b5 100644 --- a/drivers/platform/x86/intel/vsec.c +++ b/drivers/platform/x86/intel/vsec.c @@ -124,36 +124,60 @@ static void intel_vsec_remove_aux(void *data) auxiliary_device_uninit(data); } +static DEFINE_MUTEX(vsec_ida_lock); + static void intel_vsec_dev_release(struct device *dev) { struct intel_vsec_device *intel_vsec_dev = dev_to_ivdev(dev); + xa_erase(&auxdev_array, intel_vsec_dev->id); + + mutex_lock(&vsec_ida_lock); ida_free(intel_vsec_dev->ida, intel_vsec_dev->auxdev.id); + mutex_unlock(&vsec_ida_lock); + kfree(intel_vsec_dev->resource); kfree(intel_vsec_dev); } -static int intel_vsec_add_aux(struct pci_dev *pdev, struct intel_vsec_device *intel_vsec_dev, - const char *name) +int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent, + struct intel_vsec_device *intel_vsec_dev, + const char *name) { struct auxiliary_device *auxdev = &intel_vsec_dev->auxdev; int ret, id; - ret = ida_alloc(intel_vsec_dev->ida, GFP_KERNEL); + ret = xa_alloc(&auxdev_array, &intel_vsec_dev->id, intel_vsec_dev, + PMT_XA_LIMIT, GFP_KERNEL); if (ret < 0) { kfree(intel_vsec_dev->resource); kfree(intel_vsec_dev); return ret; } - auxdev->id = ret; + mutex_lock(&vsec_ida_lock); + id = ida_alloc(intel_vsec_dev->ida, GFP_KERNEL); + mutex_unlock(&vsec_ida_lock); + if (id < 0) { + xa_erase(&auxdev_array, intel_vsec_dev->id); + kfree(intel_vsec_dev->resource); + kfree(intel_vsec_dev); + return id; + } + + if (!parent) + parent = &pdev->dev; + + auxdev->id = id; auxdev->name = name; - auxdev->dev.parent = &pdev->dev; + auxdev->dev.parent = parent; auxdev->dev.release = intel_vsec_dev_release; ret = auxiliary_device_init(auxdev); if (ret < 0) { + mutex_lock(&vsec_ida_lock); ida_free(intel_vsec_dev->ida, auxdev->id); + mutex_unlock(&vsec_ida_lock); kfree(intel_vsec_dev->resource); kfree(intel_vsec_dev); return ret; @@ -165,19 +189,14 @@ static int intel_vsec_add_aux(struct pci_dev *pdev, struct intel_vsec_device *in return ret; } - ret = devm_add_action_or_reset(&pdev->dev, intel_vsec_remove_aux, + ret = devm_add_action_or_reset(parent, intel_vsec_remove_aux, auxdev); if (ret < 0) return ret; - /* Add auxdev to list */ - ret = xa_alloc(&auxdev_array, &id, intel_vsec_dev, PMT_XA_LIMIT, - GFP_KERNEL); - if (ret) - return ret; - return 0; } +EXPORT_SYMBOL_NS_GPL(intel_vsec_add_aux, INTEL_VSEC); static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *header, struct intel_vsec_platform_info *info) @@ -235,7 +254,8 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he else intel_vsec_dev->ida = &intel_vsec_ida; - return intel_vsec_add_aux(pdev, intel_vsec_dev, intel_vsec_name(header->id)); + return intel_vsec_add_aux(pdev, NULL, intel_vsec_dev, + intel_vsec_name(header->id)); } static bool intel_vsec_walk_header(struct pci_dev *pdev, diff --git a/drivers/platform/x86/intel/vsec.h b/drivers/platform/x86/intel/vsec.h index 3deeb05cf394..330672588868 100644 --- a/drivers/platform/x86/intel/vsec.h +++ b/drivers/platform/x86/intel/vsec.h @@ -38,8 +38,15 @@ struct intel_vsec_device { struct ida *ida; struct intel_vsec_platform_info *info; int num_resources; + int id; /* xa */ + void *priv_data; + size_t priv_data_size; }; +int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent, + struct intel_vsec_device *intel_vsec_dev, + const char *name); + static inline struct intel_vsec_device *dev_to_ivdev(struct device *dev) { return container_of(dev, struct intel_vsec_device, auxdev.dev); diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index 1cf2471d54dd..17cc4b45e023 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -26,6 +26,21 @@ static const struct x86_cpu_id p2sb_cpu_ids[] = { {} }; +/* + * Cache BAR0 of P2SB device functions 0 to 7. + * TODO: The constant 8 is the number of functions that PCI specification + * defines. Same definitions exist tree-wide. Unify this definition and + * the other definitions then move to include/uapi/linux/pci.h. + */ +#define NR_P2SB_RES_CACHE 8 + +struct p2sb_res_cache { + u32 bus_dev_id; + struct resource res; +}; + +static struct p2sb_res_cache p2sb_resources[NR_P2SB_RES_CACHE]; + static int p2sb_get_devfn(unsigned int *devfn) { unsigned int fn = P2SB_DEVFN_DEFAULT; @@ -39,8 +54,16 @@ static int p2sb_get_devfn(unsigned int *devfn) return 0; } +static bool p2sb_valid_resource(struct resource *res) +{ + if (res->flags) + return true; + + return false; +} + /* Copy resource from the first BAR of the device in question */ -static int p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem) +static void p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem) { struct resource *bar0 = &pdev->resource[0]; @@ -56,49 +79,66 @@ static int p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem) mem->end = bar0->end; mem->flags = bar0->flags; mem->desc = bar0->desc; - - return 0; } -static int p2sb_scan_and_read(struct pci_bus *bus, unsigned int devfn, struct resource *mem) +static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn) { + struct p2sb_res_cache *cache = &p2sb_resources[PCI_FUNC(devfn)]; struct pci_dev *pdev; - int ret; pdev = pci_scan_single_device(bus, devfn); if (!pdev) - return -ENODEV; + return; - ret = p2sb_read_bar0(pdev, mem); + p2sb_read_bar0(pdev, &cache->res); + cache->bus_dev_id = bus->dev.id; pci_stop_and_remove_bus_device(pdev); - return ret; } -/** - * p2sb_bar - Get Primary to Sideband (P2SB) bridge device BAR - * @bus: PCI bus to communicate with - * @devfn: PCI slot and function to communicate with - * @mem: memory resource to be filled in - * - * The BIOS prevents the P2SB device from being enumerated by the PCI - * subsystem, so we need to unhide and hide it back to lookup the BAR. - * - * if @bus is NULL, the bus 0 in domain 0 will be used. - * If @devfn is 0, it will be replaced by devfn of the P2SB device. - * - * Caller must provide a valid pointer to @mem. - * - * Locking is handled by pci_rescan_remove_lock mutex. - * - * Return: - * 0 on success or appropriate errno value on error. - */ -int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) +static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) +{ + unsigned int slot, fn; + + if (PCI_FUNC(devfn) == 0) { + /* + * When function number of the P2SB device is zero, scan it and + * other function numbers, and if devices are available, cache + * their BAR0s. + */ + slot = PCI_SLOT(devfn); + for (fn = 0; fn < NR_P2SB_RES_CACHE; fn++) + p2sb_scan_and_cache_devfn(bus, PCI_DEVFN(slot, fn)); + } else { + /* Scan the P2SB device and cache its BAR0 */ + p2sb_scan_and_cache_devfn(bus, devfn); + } + + if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res)) + return -ENOENT; + + return 0; +} + +static struct pci_bus *p2sb_get_bus(struct pci_bus *bus) +{ + static struct pci_bus *p2sb_bus; + + bus = bus ?: p2sb_bus; + if (bus) + return bus; + + /* Assume P2SB is on the bus 0 in domain 0 */ + p2sb_bus = pci_find_bus(0, 0); + return p2sb_bus; +} + +static int p2sb_cache_resources(void) { - struct pci_dev *pdev_p2sb; unsigned int devfn_p2sb; u32 value = P2SBC_HIDE; + struct pci_bus *bus; + u16 class; int ret; /* Get devfn for P2SB device itself */ @@ -106,8 +146,17 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) if (ret) return ret; - /* if @bus is NULL, use bus 0 in domain 0 */ - bus = bus ?: pci_find_bus(0, 0); + bus = p2sb_get_bus(NULL); + if (!bus) + return -ENODEV; + + /* + * When a device with same devfn exists and its device class is not + * PCI_CLASS_MEMORY_OTHER for P2SB, do not touch it. + */ + pci_bus_read_config_word(bus, devfn_p2sb, PCI_CLASS_DEVICE, &class); + if (!PCI_POSSIBLE_ERROR(class) && class != PCI_CLASS_MEMORY_OTHER) + return -ENODEV; /* * Prevent concurrent PCI bus scan from seeing the P2SB device and @@ -115,17 +164,16 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) */ pci_lock_rescan_remove(); - /* Unhide the P2SB device, if needed */ + /* + * The BIOS prevents the P2SB device from being enumerated by the PCI + * subsystem, so we need to unhide and hide it back to lookup the BAR. + * Unhide the P2SB device here, if needed. + */ pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value); if (value & P2SBC_HIDE) pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, 0); - pdev_p2sb = pci_scan_single_device(bus, devfn_p2sb); - if (devfn) - ret = p2sb_scan_and_read(bus, devfn, mem); - else - ret = p2sb_read_bar0(pdev_p2sb, mem); - pci_stop_and_remove_bus_device(pdev_p2sb); + ret = p2sb_scan_and_cache(bus, devfn_p2sb); /* Hide the P2SB device, if it was hidden */ if (value & P2SBC_HIDE) @@ -133,12 +181,62 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) pci_unlock_rescan_remove(); - if (ret) - return ret; + return ret; +} + +/** + * p2sb_bar - Get Primary to Sideband (P2SB) bridge device BAR + * @bus: PCI bus to communicate with + * @devfn: PCI slot and function to communicate with + * @mem: memory resource to be filled in + * + * If @bus is NULL, the bus 0 in domain 0 will be used. + * If @devfn is 0, it will be replaced by devfn of the P2SB device. + * + * Caller must provide a valid pointer to @mem. + * + * Return: + * 0 on success or appropriate errno value on error. + */ +int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) +{ + struct p2sb_res_cache *cache; + int ret; + + bus = p2sb_get_bus(bus); + if (!bus) + return -ENODEV; + + if (!devfn) { + ret = p2sb_get_devfn(&devfn); + if (ret) + return ret; + } - if (mem->flags == 0) + cache = &p2sb_resources[PCI_FUNC(devfn)]; + if (cache->bus_dev_id != bus->dev.id) return -ENODEV; + if (!p2sb_valid_resource(&cache->res)) + return -ENOENT; + + memcpy(mem, &cache->res, sizeof(*mem)); return 0; } EXPORT_SYMBOL_GPL(p2sb_bar); + +static int __init p2sb_fs_init(void) +{ + p2sb_cache_resources(); + return 0; +} + +/* + * pci_rescan_remove_lock to avoid access to unhidden P2SB devices can + * not be locked in sysfs pci bus rescan path because of deadlock. To + * avoid the deadlock, access to P2SB devices with the lock at an early + * step in kernel initialization and cache required resources. This + * should happen after subsys_initcall which initializes PCI subsystem + * and before device_initcall which requires P2SB resources. + */ +fs_initcall(p2sb_fs_init); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 05a55bc31c79..c2fb19af1070 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8149,8 +8149,19 @@ static struct ibm_struct volume_driver_data = { * TPACPI_FAN_WR_TPEC is also available and should be used to * command the fan. The X31/X40/X41 seems to have 8 fan levels, * but the ACPI tables just mention level 7. + * + * TPACPI_FAN_RD_TPEC_NS: + * This mode is used for a few ThinkPads (L13 Yoga Gen2, X13 Yoga Gen2 etc.) + * that are using non-standard EC locations for reporting fan speeds. + * Currently these platforms only provide fan rpm reporting. + * */ +#define FAN_RPM_CAL_CONST 491520 /* FAN RPM calculation offset for some non-standard ECFW */ + +#define FAN_NS_CTRL_STATUS BIT(2) /* Bit which determines control is enabled or not */ +#define FAN_NS_CTRL BIT(4) /* Bit which determines control is by host or EC */ + enum { /* Fan control constants */ fan_status_offset = 0x2f, /* EC register 0x2f */ fan_rpm_offset = 0x84, /* EC register 0x84: LSB, 0x85 MSB (RPM) @@ -8158,6 +8169,11 @@ enum { /* Fan control constants */ fan_select_offset = 0x31, /* EC register 0x31 (Firmware 7M) bit 0 selects which fan is active */ + fan_status_offset_ns = 0x93, /* Special status/control offset for non-standard EC Fan1 */ + fan2_status_offset_ns = 0x96, /* Special status/control offset for non-standard EC Fan2 */ + fan_rpm_status_ns = 0x95, /* Special offset for Fan1 RPM status for non-standard EC */ + fan2_rpm_status_ns = 0x98, /* Special offset for Fan2 RPM status for non-standard EC */ + TP_EC_FAN_FULLSPEED = 0x40, /* EC fan mode: full speed */ TP_EC_FAN_AUTO = 0x80, /* EC fan mode: auto fan control */ @@ -8168,6 +8184,7 @@ enum fan_status_access_mode { TPACPI_FAN_NONE = 0, /* No fan status or control */ TPACPI_FAN_RD_ACPI_GFAN, /* Use ACPI GFAN */ TPACPI_FAN_RD_TPEC, /* Use ACPI EC regs 0x2f, 0x84-0x85 */ + TPACPI_FAN_RD_TPEC_NS, /* Use non-standard ACPI EC regs (eg: L13 Yoga gen2 etc.) */ }; enum fan_control_access_mode { @@ -8195,6 +8212,8 @@ static u8 fan_control_desired_level; static u8 fan_control_resume_level; static int fan_watchdog_maxinterval; +static bool fan_with_ns_addr; + static struct mutex fan_mutex; static void fan_watchdog_fire(struct work_struct *ignored); @@ -8325,6 +8344,15 @@ static int fan_get_status(u8 *status) } break; + case TPACPI_FAN_RD_TPEC_NS: + /* Default mode is AUTO which means controlled by EC */ + if (!acpi_ec_read(fan_status_offset_ns, &s)) + return -EIO; + + if (status) + *status = s; + + break; default: return -ENXIO; @@ -8341,7 +8369,8 @@ static int fan_get_status_safe(u8 *status) if (mutex_lock_killable(&fan_mutex)) return -ERESTARTSYS; rc = fan_get_status(&s); - if (!rc) + /* NS EC doesn't have register with level settings */ + if (!rc && !fan_with_ns_addr) fan_update_desired_level(s); mutex_unlock(&fan_mutex); @@ -8368,7 +8397,13 @@ static int fan_get_speed(unsigned int *speed) if (likely(speed)) *speed = (hi << 8) | lo; + break; + case TPACPI_FAN_RD_TPEC_NS: + if (!acpi_ec_read(fan_rpm_status_ns, &lo)) + return -EIO; + if (speed) + *speed = lo ? FAN_RPM_CAL_CONST / lo : 0; break; default: @@ -8380,7 +8415,7 @@ static int fan_get_speed(unsigned int *speed) static int fan2_get_speed(unsigned int *speed) { - u8 hi, lo; + u8 hi, lo, status; bool rc; switch (fan_status_access_mode) { @@ -8396,7 +8431,21 @@ static int fan2_get_speed(unsigned int *speed) if (likely(speed)) *speed = (hi << 8) | lo; + break; + case TPACPI_FAN_RD_TPEC_NS: + rc = !acpi_ec_read(fan2_status_offset_ns, &status); + if (rc) + return -EIO; + if (!(status & FAN_NS_CTRL_STATUS)) { + pr_info("secondary fan control not supported\n"); + return -EIO; + } + rc = !acpi_ec_read(fan2_rpm_status_ns, &lo); + if (rc) + return -EIO; + if (speed) + *speed = lo ? FAN_RPM_CAL_CONST / lo : 0; break; default: @@ -8899,6 +8948,7 @@ static const struct attribute_group fan_driver_attr_group = { #define TPACPI_FAN_2FAN 0x0002 /* EC 0x31 bit 0 selects fan2 */ #define TPACPI_FAN_2CTL 0x0004 /* selects fan2 control */ #define TPACPI_FAN_NOFAN 0x0008 /* no fan available */ +#define TPACPI_FAN_NS 0x0010 /* For EC with non-Standard register addresses */ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_QEC_IBM('1', 'Y', TPACPI_FAN_Q1), @@ -8917,6 +8967,8 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */ TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */ TPACPI_Q_LNV3('N', '3', '7', TPACPI_FAN_2CTL), /* T15g (2nd gen) */ + TPACPI_Q_LNV3('R', '1', 'F', TPACPI_FAN_NS), /* L13 Yoga Gen 2 */ + TPACPI_Q_LNV3('N', '2', 'U', TPACPI_FAN_NS), /* X13 Yoga Gen 2*/ TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN), /* X1 Tablet (2nd gen) */ }; @@ -8951,18 +9003,27 @@ static int __init fan_init(struct ibm_init_struct *iibm) return -ENODEV; } + if (quirks & TPACPI_FAN_NS) { + pr_info("ECFW with non-standard fan reg control found\n"); + fan_with_ns_addr = 1; + /* Fan ctrl support from host is undefined for now */ + tp_features.fan_ctrl_status_undef = 1; + } + if (gfan_handle) { /* 570, 600e/x, 770e, 770x */ fan_status_access_mode = TPACPI_FAN_RD_ACPI_GFAN; } else { /* all other ThinkPads: note that even old-style * ThinkPad ECs supports the fan control register */ - if (likely(acpi_ec_read(fan_status_offset, - &fan_control_initial_status))) { + if (fan_with_ns_addr || + likely(acpi_ec_read(fan_status_offset, &fan_control_initial_status))) { int res; unsigned int speed; - fan_status_access_mode = TPACPI_FAN_RD_TPEC; + fan_status_access_mode = fan_with_ns_addr ? + TPACPI_FAN_RD_TPEC_NS : TPACPI_FAN_RD_TPEC; + if (quirks & TPACPI_FAN_Q1) fan_quirk1_setup(); /* Try and probe the 2nd fan */ @@ -8971,7 +9032,8 @@ static int __init fan_init(struct ibm_init_struct *iibm) if (res >= 0 && speed != FAN_NOT_PRESENT) { /* It responded - so let's assume it's there */ tp_features.second_fan = 1; - tp_features.second_fan_ctl = 1; + /* fan control not currently available for ns ECFW */ + tp_features.second_fan_ctl = !fan_with_ns_addr; pr_info("secondary fan control detected & enabled\n"); } else { /* Fan not auto-detected */ @@ -9146,6 +9208,7 @@ static int fan_read(struct seq_file *m) str_enabled_disabled(status), status); break; + case TPACPI_FAN_RD_TPEC_NS: case TPACPI_FAN_RD_TPEC: /* all except 570, 600e/x, 770e, 770x */ rc = fan_get_status_safe(&status); @@ -9160,13 +9223,22 @@ static int fan_read(struct seq_file *m) seq_printf(m, "speed:\t\t%d\n", speed); - if (status & TP_EC_FAN_FULLSPEED) - /* Disengaged mode takes precedence */ - seq_printf(m, "level:\t\tdisengaged\n"); - else if (status & TP_EC_FAN_AUTO) - seq_printf(m, "level:\t\tauto\n"); - else - seq_printf(m, "level:\t\t%d\n", status); + if (fan_status_access_mode == TPACPI_FAN_RD_TPEC_NS) { + /* + * No full speed bit in NS EC + * EC Auto mode is set by default. + * No other levels settings available + */ + seq_printf(m, "level:\t\t%s\n", status & FAN_NS_CTRL ? "unknown" : "auto"); + } else { + if (status & TP_EC_FAN_FULLSPEED) + /* Disengaged mode takes precedence */ + seq_printf(m, "level:\t\tdisengaged\n"); + else if (status & TP_EC_FAN_AUTO) + seq_printf(m, "level:\t\tauto\n"); + else + seq_printf(m, "level:\t\t%d\n", status); + } break; case TPACPI_FAN_NONE: @@ -10439,6 +10511,7 @@ static int convert_dytc_to_profile(int funcmode, int dytcmode, return 0; default: /* Unknown function */ + pr_debug("unknown function 0x%x\n", funcmode); return -EOPNOTSUPP; } return 0; @@ -10624,8 +10697,8 @@ static void dytc_profile_refresh(void) return; perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF; - convert_dytc_to_profile(funcmode, perfmode, &profile); - if (profile != dytc_current_profile) { + err = convert_dytc_to_profile(funcmode, perfmode, &profile); + if (!err && profile != dytc_current_profile) { dytc_current_profile = profile; platform_profile_notify(); } diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 9a92d515abb9..11d72a353355 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -50,7 +50,7 @@ static const struct property_entry chuwi_hi8_air_props[] = { }; static const struct ts_dmi_data chuwi_hi8_air_data = { - .acpi_name = "MSSL1680:00", + .acpi_name = "MSSL1680", .properties = chuwi_hi8_air_props, }; @@ -913,6 +913,32 @@ static const struct ts_dmi_data teclast_tbook11_data = { .properties = teclast_tbook11_props, }; +static const struct property_entry teclast_x16_plus_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 8), + PROPERTY_ENTRY_U32("touchscreen-min-y", 14), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1916), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1264), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-teclast-x16-plus.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data teclast_x16_plus_data = { + .embedded_fw = { + .name = "silead/gsl3692-teclast-x16-plus.fw", + .prefix = { 0xf0, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00 }, + .length = 43560, + .sha256 = { 0x9d, 0xb0, 0x3d, 0xf1, 0x00, 0x3c, 0xb5, 0x25, + 0x62, 0x8a, 0xa0, 0x93, 0x4b, 0xe0, 0x4e, 0x75, + 0xd1, 0x27, 0xb1, 0x65, 0x3c, 0xba, 0xa5, 0x0f, + 0xcd, 0xb4, 0xbe, 0x00, 0xbb, 0xf6, 0x43, 0x29 }, + }, + .acpi_name = "MSSL1680:00", + .properties = teclast_x16_plus_props, +}; + static const struct property_entry teclast_x3_plus_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1980), PROPERTY_ENTRY_U32("touchscreen-size-y", 1500), @@ -1568,6 +1594,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Teclast X16 Plus */ + .driver_data = (void *)&teclast_x16_plus_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TECLAST"), + DMI_MATCH(DMI_PRODUCT_NAME, "Default string"), + DMI_MATCH(DMI_PRODUCT_SKU, "D3A5_A1"), + }, + }, + { /* Teclast X3 Plus */ .driver_data = (void *)&teclast_x3_plus_data, .matches = { @@ -1741,7 +1776,7 @@ static void ts_dmi_add_props(struct i2c_client *client) int error; if (has_acpi_companion(dev) && - !strncmp(ts_data->acpi_name, client->name, I2C_NAME_SIZE)) { + strstarts(client->name, ts_data->acpi_name)) { error = device_create_managed_software_node(dev, ts_data->properties, NULL); if (error) dev_err(dev, "failed to add properties: %d\n", error); diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c index 4f05f610391b..c02ce0834c2c 100644 --- a/drivers/pnp/pnpacpi/rsparser.c +++ b/drivers/pnp/pnpacpi/rsparser.c @@ -151,13 +151,13 @@ static int vendor_resource_matches(struct pnp_dev *dev, static void pnpacpi_parse_allocated_vendor(struct pnp_dev *dev, struct acpi_resource_vendor_typed *vendor) { - if (vendor_resource_matches(dev, vendor, &hp_ccsr_uuid, 16)) { - u64 start, length; + struct { u64 start, length; } range; - memcpy(&start, vendor->byte_data, sizeof(start)); - memcpy(&length, vendor->byte_data + 8, sizeof(length)); - - pnp_add_mem_resource(dev, start, start + length - 1, 0); + if (vendor_resource_matches(dev, vendor, &hp_ccsr_uuid, + sizeof(range))) { + memcpy(&range, vendor->byte_data, sizeof(range)); + pnp_add_mem_resource(dev, range.start, range.start + + range.length - 1, 0); } } diff --git a/drivers/power/supply/bq256xx_charger.c b/drivers/power/supply/bq256xx_charger.c index 01ad84fd147c..686eb8d86e22 100644 --- a/drivers/power/supply/bq256xx_charger.c +++ b/drivers/power/supply/bq256xx_charger.c @@ -1514,13 +1514,16 @@ static int bq256xx_hw_init(struct bq256xx_device *bq) wd_reg_val = i; break; } - if (bq->watchdog_timer > bq256xx_watchdog_time[i] && + if (i + 1 < BQ256XX_NUM_WD_VAL && + bq->watchdog_timer > bq256xx_watchdog_time[i] && bq->watchdog_timer < bq256xx_watchdog_time[i + 1]) wd_reg_val = i; } ret = regmap_update_bits(bq->regmap, BQ256XX_CHARGER_CONTROL_1, BQ256XX_WATCHDOG_MASK, wd_reg_val << BQ256XX_WDT_BIT_SHIFT); + if (ret) + return ret; ret = power_supply_get_battery_info(bq->charger, &bat_info); if (ret == -ENOMEM) diff --git a/drivers/power/supply/cw2015_battery.c b/drivers/power/supply/cw2015_battery.c index 473522b4326a..9d957cf8edf0 100644 --- a/drivers/power/supply/cw2015_battery.c +++ b/drivers/power/supply/cw2015_battery.c @@ -491,7 +491,7 @@ static int cw_battery_get_property(struct power_supply *psy, case POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW: if (cw_battery_valid_time_to_empty(cw_bat)) - val->intval = cw_bat->time_to_empty; + val->intval = cw_bat->time_to_empty * 60; else val->intval = 0; break; diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index d333e7422f4a..9726f96bf763 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -171,7 +171,7 @@ of_pwm_single_xlate(struct pwm_chip *pc, const struct of_phandle_args *args) pwm->args.period = args->args[0]; pwm->args.polarity = PWM_POLARITY_NORMAL; - if (args->args_count == 2 && args->args[2] & PWM_POLARITY_INVERTED) + if (args->args_count == 2 && args->args[1] & PWM_POLARITY_INVERTED) pwm->args.polarity = PWM_POLARITY_INVERSED; return pwm; diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c index a5fdf97c0d2e..246499128142 100644 --- a/drivers/pwm/pwm-jz4740.c +++ b/drivers/pwm/pwm-jz4740.c @@ -60,9 +60,10 @@ static int jz4740_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm) snprintf(name, sizeof(name), "timer%u", pwm->hwpwm); clk = clk_get(chip->dev, name); - if (IS_ERR(clk)) - return dev_err_probe(chip->dev, PTR_ERR(clk), - "Failed to get clock\n"); + if (IS_ERR(clk)) { + dev_err(chip->dev, "error %pe: Failed to get clock\n", clk); + return PTR_ERR(clk); + } err = clk_prepare_enable(clk); if (err < 0) { diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index 794ca5b02968..bdcdb7f38312 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -115,14 +115,14 @@ static int stm32_pwm_raw_capture(struct stm32_pwm *priv, struct pwm_device *pwm, int ret; /* Ensure registers have been updated, enable counter and capture */ - regmap_update_bits(priv->regmap, TIM_EGR, TIM_EGR_UG, TIM_EGR_UG); - regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, TIM_CR1_CEN); + regmap_set_bits(priv->regmap, TIM_EGR, TIM_EGR_UG); + regmap_set_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN); /* Use cc1 or cc3 DMA resp for PWM input channels 1 & 2 or 3 & 4 */ dma_id = pwm->hwpwm < 2 ? STM32_TIMERS_DMA_CH1 : STM32_TIMERS_DMA_CH3; ccen = pwm->hwpwm < 2 ? TIM_CCER_CC12E : TIM_CCER_CC34E; ccr = pwm->hwpwm < 2 ? TIM_CCR1 : TIM_CCR3; - regmap_update_bits(priv->regmap, TIM_CCER, ccen, ccen); + regmap_set_bits(priv->regmap, TIM_CCER, ccen); /* * Timer DMA burst mode. Request 2 registers, 2 bursts, to get both @@ -160,8 +160,8 @@ static int stm32_pwm_raw_capture(struct stm32_pwm *priv, struct pwm_device *pwm, } stop: - regmap_update_bits(priv->regmap, TIM_CCER, ccen, 0); - regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, 0); + regmap_clear_bits(priv->regmap, TIM_CCER, ccen); + regmap_clear_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN); return ret; } @@ -359,7 +359,7 @@ static int stm32_pwm_config(struct stm32_pwm *priv, int ch, regmap_write(priv->regmap, TIM_PSC, prescaler); regmap_write(priv->regmap, TIM_ARR, prd - 1); - regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, TIM_CR1_ARPE); + regmap_set_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE); /* Calculate the duty cycles */ dty = prd * duty_ns; @@ -377,7 +377,7 @@ static int stm32_pwm_config(struct stm32_pwm *priv, int ch, else regmap_update_bits(priv->regmap, TIM_CCMR2, mask, ccmr); - regmap_update_bits(priv->regmap, TIM_BDTR, TIM_BDTR_MOE, TIM_BDTR_MOE); + regmap_set_bits(priv->regmap, TIM_BDTR, TIM_BDTR_MOE); return 0; } @@ -411,13 +411,13 @@ static int stm32_pwm_enable(struct stm32_pwm *priv, int ch) if (priv->have_complementary_output) mask |= TIM_CCER_CC1NE << (ch * 4); - regmap_update_bits(priv->regmap, TIM_CCER, mask, mask); + regmap_set_bits(priv->regmap, TIM_CCER, mask); /* Make sure that registers are updated */ - regmap_update_bits(priv->regmap, TIM_EGR, TIM_EGR_UG, TIM_EGR_UG); + regmap_set_bits(priv->regmap, TIM_EGR, TIM_EGR_UG); /* Enable controller */ - regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, TIM_CR1_CEN); + regmap_set_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN); return 0; } @@ -431,11 +431,11 @@ static void stm32_pwm_disable(struct stm32_pwm *priv, int ch) if (priv->have_complementary_output) mask |= TIM_CCER_CC1NE << (ch * 4); - regmap_update_bits(priv->regmap, TIM_CCER, mask, 0); + regmap_clear_bits(priv->regmap, TIM_CCER, mask); /* When all channels are disabled, we can disable the controller */ if (!active_channels(priv)) - regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, 0); + regmap_clear_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN); clk_disable(priv->clk); } @@ -568,41 +568,30 @@ static void stm32_pwm_detect_complementary(struct stm32_pwm *priv) * If complementary bit doesn't exist writing 1 will have no * effect so we can detect it. */ - regmap_update_bits(priv->regmap, - TIM_CCER, TIM_CCER_CC1NE, TIM_CCER_CC1NE); + regmap_set_bits(priv->regmap, TIM_CCER, TIM_CCER_CC1NE); regmap_read(priv->regmap, TIM_CCER, &ccer); - regmap_update_bits(priv->regmap, TIM_CCER, TIM_CCER_CC1NE, 0); + regmap_clear_bits(priv->regmap, TIM_CCER, TIM_CCER_CC1NE); priv->have_complementary_output = (ccer != 0); } -static int stm32_pwm_detect_channels(struct stm32_pwm *priv) +static unsigned int stm32_pwm_detect_channels(struct stm32_pwm *priv, + unsigned int *num_enabled) { - u32 ccer; - int npwm = 0; + u32 ccer, ccer_backup; /* * If channels enable bits don't exist writing 1 will have no * effect so we can detect and count them. */ - regmap_update_bits(priv->regmap, - TIM_CCER, TIM_CCER_CCXE, TIM_CCER_CCXE); + regmap_read(priv->regmap, TIM_CCER, &ccer_backup); + regmap_set_bits(priv->regmap, TIM_CCER, TIM_CCER_CCXE); regmap_read(priv->regmap, TIM_CCER, &ccer); - regmap_update_bits(priv->regmap, TIM_CCER, TIM_CCER_CCXE, 0); - - if (ccer & TIM_CCER_CC1E) - npwm++; + regmap_write(priv->regmap, TIM_CCER, ccer_backup); - if (ccer & TIM_CCER_CC2E) - npwm++; + *num_enabled = hweight32(ccer_backup & TIM_CCER_CCXE); - if (ccer & TIM_CCER_CC3E) - npwm++; - - if (ccer & TIM_CCER_CC4E) - npwm++; - - return npwm; + return hweight32(ccer & TIM_CCER_CCXE); } static int stm32_pwm_probe(struct platform_device *pdev) @@ -611,6 +600,8 @@ static int stm32_pwm_probe(struct platform_device *pdev) struct device_node *np = dev->of_node; struct stm32_timers *ddata = dev_get_drvdata(pdev->dev.parent); struct stm32_pwm *priv; + unsigned int num_enabled; + unsigned int i; int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -633,7 +624,11 @@ static int stm32_pwm_probe(struct platform_device *pdev) priv->chip.dev = dev; priv->chip.ops = &stm32pwm_ops; - priv->chip.npwm = stm32_pwm_detect_channels(priv); + priv->chip.npwm = stm32_pwm_detect_channels(priv, &num_enabled); + + /* Initialize clock refcount to number of enabled PWM channels. */ + for (i = 0; i < num_enabled; i++) + clk_enable(priv->clk); ret = pwmchip_add(&priv->chip); if (ret < 0) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 34d3d8281906..c8702011b761 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -2925,7 +2925,8 @@ static int _regulator_enable(struct regulator *regulator) /* Fallthrough on positive return values - already enabled */ } - rdev->use_count++; + if (regulator->enable_count == 1) + rdev->use_count++; return 0; @@ -3000,37 +3001,40 @@ static int _regulator_disable(struct regulator *regulator) lockdep_assert_held_once(&rdev->mutex.base); - if (WARN(rdev->use_count <= 0, + if (WARN(regulator->enable_count == 0, "unbalanced disables for %s\n", rdev_get_name(rdev))) return -EIO; - /* are we the last user and permitted to disable ? */ - if (rdev->use_count == 1 && - (rdev->constraints && !rdev->constraints->always_on)) { - - /* we are last user */ - if (regulator_ops_is_valid(rdev, REGULATOR_CHANGE_STATUS)) { - ret = _notifier_call_chain(rdev, - REGULATOR_EVENT_PRE_DISABLE, - NULL); - if (ret & NOTIFY_STOP_MASK) - return -EINVAL; - - ret = _regulator_do_disable(rdev); - if (ret < 0) { - rdev_err(rdev, "failed to disable: %pe\n", ERR_PTR(ret)); - _notifier_call_chain(rdev, - REGULATOR_EVENT_ABORT_DISABLE, + if (regulator->enable_count == 1) { + /* disabling last enable_count from this regulator */ + /* are we the last user and permitted to disable ? */ + if (rdev->use_count == 1 && + (rdev->constraints && !rdev->constraints->always_on)) { + + /* we are last user */ + if (regulator_ops_is_valid(rdev, REGULATOR_CHANGE_STATUS)) { + ret = _notifier_call_chain(rdev, + REGULATOR_EVENT_PRE_DISABLE, + NULL); + if (ret & NOTIFY_STOP_MASK) + return -EINVAL; + + ret = _regulator_do_disable(rdev); + if (ret < 0) { + rdev_err(rdev, "failed to disable: %pe\n", ERR_PTR(ret)); + _notifier_call_chain(rdev, + REGULATOR_EVENT_ABORT_DISABLE, + NULL); + return ret; + } + _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, NULL); - return ret; } - _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, - NULL); - } - rdev->use_count = 0; - } else if (rdev->use_count > 1) { - rdev->use_count--; + rdev->use_count = 0; + } else if (rdev->use_count > 1) { + rdev->use_count--; + } } if (ret == 0) diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c index b9eeaff1c661..925e486f73a6 100644 --- a/drivers/regulator/pwm-regulator.c +++ b/drivers/regulator/pwm-regulator.c @@ -158,6 +158,9 @@ static int pwm_regulator_get_voltage(struct regulator_dev *rdev) pwm_get_state(drvdata->pwm, &pstate); voltage = pwm_get_relative_duty_cycle(&pstate, duty_unit); + if (voltage < min(max_uV_duty, min_uV_duty) || + voltage > max(max_uV_duty, min_uV_duty)) + return -ENOTRECOVERABLE; /* * The dutycycle for min_uV might be greater than the one for max_uV. diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c index 115345e9fded..82af27b0e469 100644 --- a/drivers/regulator/ti-abb-regulator.c +++ b/drivers/regulator/ti-abb-regulator.c @@ -734,9 +734,25 @@ static int ti_abb_probe(struct platform_device *pdev) return PTR_ERR(abb->setup_reg); } - abb->int_base = devm_platform_ioremap_resource_byname(pdev, "int-address"); - if (IS_ERR(abb->int_base)) - return PTR_ERR(abb->int_base); + pname = "int-address"; + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, pname); + if (!res) { + dev_err(dev, "Missing '%s' IO resource\n", pname); + return -ENODEV; + } + /* + * The MPU interrupt status register (PRM_IRQSTATUS_MPU) is + * shared between regulator-abb-{ivahd,dspeve,gpu} driver + * instances. Therefore use devm_ioremap() rather than + * devm_platform_ioremap_resource_byname() to avoid busy + * resource region conflicts. + */ + abb->int_base = devm_ioremap(dev, res->start, + resource_size(res)); + if (!abb->int_base) { + dev_err(dev, "Unable to map '%s'\n", pname); + return -ENOMEM; + } /* Map Optional resources */ pname = "efuse-address"; diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c index 210405c5f1d9..5791c29004c9 100644 --- a/drivers/remoteproc/pru_rproc.c +++ b/drivers/remoteproc/pru_rproc.c @@ -111,6 +111,7 @@ struct pru_private_data { * @dbg_single_step: debug state variable to set PRU into single step mode * @dbg_continuous: debug state variable to restore PRU execution mode * @evt_count: number of mapped events + * @gpmux_save: saved value for gpmux config */ struct pru_rproc { int id; @@ -130,6 +131,7 @@ struct pru_rproc { u32 dbg_single_step; u32 dbg_continuous; u8 evt_count; + u8 gpmux_save; }; static inline u32 pru_control_read_reg(struct pru_rproc *pru, unsigned int reg) @@ -231,6 +233,7 @@ struct rproc *pru_rproc_get(struct device_node *np, int index, struct device *dev; const char *fw_name; int ret; + u32 mux; rproc = __pru_rproc_get(np, index); if (IS_ERR(rproc)) @@ -255,6 +258,23 @@ struct rproc *pru_rproc_get(struct device_node *np, int index, if (pru_id) *pru_id = pru->id; + ret = pruss_cfg_get_gpmux(pru->pruss, pru->id, &pru->gpmux_save); + if (ret) { + dev_err(dev, "failed to get cfg gpmux: %d\n", ret); + goto err; + } + + /* An error here is acceptable for backward compatibility */ + ret = of_property_read_u32_index(np, "ti,pruss-gp-mux-sel", index, + &mux); + if (!ret) { + ret = pruss_cfg_set_gpmux(pru->pruss, pru->id, mux); + if (ret) { + dev_err(dev, "failed to set cfg gpmux: %d\n", ret); + goto err; + } + } + ret = of_property_read_string_index(np, "firmware-name", index, &fw_name); if (!ret) { @@ -293,6 +313,8 @@ void pru_rproc_put(struct rproc *rproc) pru = rproc->priv; + pruss_cfg_set_gpmux(pru->pruss, pru->id, pru->gpmux_save); + pru_rproc_set_firmware(rproc, NULL); mutex_lock(&pru->lock); diff --git a/drivers/reset/core.c b/drivers/reset/core.c index f0a076e94118..92cc13ef3e56 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -807,6 +807,9 @@ static void __reset_control_put_internal(struct reset_control *rstc) { lockdep_assert_held(&reset_list_mutex); + if (IS_ERR_OR_NULL(rstc)) + return; + kref_put(&rstc->refcnt, __reset_control_release); } @@ -1017,11 +1020,8 @@ EXPORT_SYMBOL_GPL(reset_control_put); void reset_control_bulk_put(int num_rstcs, struct reset_control_bulk_data *rstcs) { mutex_lock(&reset_list_mutex); - while (num_rstcs--) { - if (IS_ERR_OR_NULL(rstcs[num_rstcs].rstc)) - continue; + while (num_rstcs--) __reset_control_put_internal(rstcs[num_rstcs].rstc); - } mutex_unlock(&reset_list_mutex); } EXPORT_SYMBOL_GPL(reset_control_bulk_put); diff --git a/drivers/reset/hisilicon/hi6220_reset.c b/drivers/reset/hisilicon/hi6220_reset.c index 5ca145b64e63..30951914afac 100644 --- a/drivers/reset/hisilicon/hi6220_reset.c +++ b/drivers/reset/hisilicon/hi6220_reset.c @@ -164,7 +164,7 @@ static int hi6220_reset_probe(struct platform_device *pdev) if (!data) return -ENOMEM; - type = (enum hi6220_reset_ctrl_type)of_device_get_match_data(dev); + type = (uintptr_t)of_device_get_match_data(dev); regmap = syscon_node_to_regmap(np); if (IS_ERR(regmap)) { diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 905ac7910c98..f1af0f674615 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -378,6 +378,7 @@ static void virtio_rpmsg_release_device(struct device *dev) struct rpmsg_device *rpdev = to_rpmsg_device(dev); struct virtio_rpmsg_channel *vch = to_virtio_rpmsg_channel(rpdev); + kfree(rpdev->driver_override); kfree(vch); } diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 00e2ca7374ec..e0a798923ce0 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -231,7 +231,7 @@ static int cmos_read_time(struct device *dev, struct rtc_time *t) if (!pm_trace_rtc_valid()) return -EIO; - ret = mc146818_get_time(t); + ret = mc146818_get_time(t, 1000); if (ret < 0) { dev_err_ratelimited(dev, "unable to read current time\n"); return ret; @@ -292,7 +292,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t) /* This not only a rtc_op, but also called directly */ if (!is_valid_irq(cmos->irq)) - return -EIO; + return -ETIMEDOUT; /* Basic alarms only support hour, minute, and seconds fields. * Some also support day and month, for alarms up to a year in @@ -307,7 +307,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t) * * Use the mc146818_avoid_UIP() function to avoid this. */ - if (!mc146818_avoid_UIP(cmos_read_alarm_callback, &p)) + if (!mc146818_avoid_UIP(cmos_read_alarm_callback, 10, &p)) return -EIO; if (!(p.rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { @@ -556,8 +556,8 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t) * * Use mc146818_avoid_UIP() to avoid this. */ - if (!mc146818_avoid_UIP(cmos_set_alarm_callback, &p)) - return -EIO; + if (!mc146818_avoid_UIP(cmos_set_alarm_callback, 10, &p)) + return -ETIMEDOUT; cmos->alarm_expires = rtc_tm_to_time64(&t->time); @@ -818,18 +818,24 @@ static void rtc_wake_off(struct device *dev) } #ifdef CONFIG_X86 -/* Enable use_acpi_alarm mode for Intel platforms no earlier than 2015 */ static void use_acpi_alarm_quirks(void) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + if (dmi_get_bios_year() < 2015) + return; + break; + case X86_VENDOR_AMD: + case X86_VENDOR_HYGON: + if (dmi_get_bios_year() < 2021) + return; + break; + default: return; - + } if (!is_hpet_enabled()) return; - if (dmi_get_bios_year() < 2015) - return; - use_acpi_alarm = true; } #else diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c index f1c09f1db044..651bf3c279c7 100644 --- a/drivers/rtc/rtc-mc146818-lib.c +++ b/drivers/rtc/rtc-mc146818-lib.c @@ -8,26 +8,31 @@ #include <linux/acpi.h> #endif +#define UIP_RECHECK_DELAY 100 /* usec */ +#define UIP_RECHECK_DELAY_MS (USEC_PER_MSEC / UIP_RECHECK_DELAY) +#define UIP_RECHECK_LOOPS_MS(x) (x / UIP_RECHECK_DELAY_MS) + /* * Execute a function while the UIP (Update-in-progress) bit of the RTC is - * unset. + * unset. The timeout is configurable by the caller in ms. * * Warning: callback may be executed more then once. */ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), + int timeout, void *param) { int i; unsigned long flags; unsigned char seconds; - for (i = 0; i < 100; i++) { + for (i = 0; UIP_RECHECK_LOOPS_MS(i) < timeout; i++) { spin_lock_irqsave(&rtc_lock, flags); /* * Check whether there is an update in progress during which the * readout is unspecified. The maximum update time is ~2ms. Poll - * every 100 usec for completion. + * for completion. * * Store the second value before checking UIP so a long lasting * NMI which happens to hit after the UIP check cannot make @@ -37,7 +42,7 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) { spin_unlock_irqrestore(&rtc_lock, flags); - udelay(100); + udelay(UIP_RECHECK_DELAY); continue; } @@ -56,7 +61,7 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), */ if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) { spin_unlock_irqrestore(&rtc_lock, flags); - udelay(100); + udelay(UIP_RECHECK_DELAY); continue; } @@ -72,6 +77,10 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), } spin_unlock_irqrestore(&rtc_lock, flags); + if (UIP_RECHECK_LOOPS_MS(i) >= 100) + pr_warn("Reading current time from RTC took around %li ms\n", + UIP_RECHECK_LOOPS_MS(i)); + return true; } return false; @@ -84,7 +93,7 @@ EXPORT_SYMBOL_GPL(mc146818_avoid_UIP); */ bool mc146818_does_rtc_work(void) { - return mc146818_avoid_UIP(NULL, NULL); + return mc146818_avoid_UIP(NULL, 1000, NULL); } EXPORT_SYMBOL_GPL(mc146818_does_rtc_work); @@ -130,15 +139,27 @@ static void mc146818_get_time_callback(unsigned char seconds, void *param_in) p->ctrl = CMOS_READ(RTC_CONTROL); } -int mc146818_get_time(struct rtc_time *time) +/** + * mc146818_get_time - Get the current time from the RTC + * @time: pointer to struct rtc_time to store the current time + * @timeout: timeout value in ms + * + * This function reads the current time from the RTC and stores it in the + * provided struct rtc_time. The timeout parameter specifies the maximum + * time to wait for the RTC to become ready. + * + * Return: 0 on success, -ETIMEDOUT if the RTC did not become ready within + * the specified timeout, or another error code if an error occurred. + */ +int mc146818_get_time(struct rtc_time *time, int timeout) { struct mc146818_get_time_callback_param p = { .time = time }; - if (!mc146818_avoid_UIP(mc146818_get_time_callback, &p)) { + if (!mc146818_avoid_UIP(mc146818_get_time_callback, timeout, &p)) { memset(time, 0, sizeof(*time)); - return -EIO; + return -ETIMEDOUT; } if (!(p.ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index 0c1df1d5f1ac..a165b1a59fde 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -17,6 +17,7 @@ #include <linux/blk-mq.h> #include <linux/slab.h> #include <linux/list.h> +#include <linux/io.h> #include <asm/eadm.h> #include "scm_blk.h" @@ -130,7 +131,7 @@ static void scm_request_done(struct scm_request *scmrq) for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) { msb = &scmrq->aob->msb[i]; - aidaw = msb->data_addr; + aidaw = (u64)phys_to_virt(msb->data_addr); if ((msb->flags & MSB_FLAG_IDA) && aidaw && IS_ALIGNED(aidaw, PAGE_SIZE)) @@ -195,12 +196,12 @@ static int scm_request_prepare(struct scm_request *scmrq) msb->scm_addr = scmdev->address + ((u64) blk_rq_pos(req) << 9); msb->oc = (rq_data_dir(req) == READ) ? MSB_OC_READ : MSB_OC_WRITE; msb->flags |= MSB_FLAG_IDA; - msb->data_addr = (u64) aidaw; + msb->data_addr = (u64)virt_to_phys(aidaw); rq_for_each_segment(bv, req, iter) { WARN_ON(bv.bv_offset); msb->blk_count += bv.bv_len >> 12; - aidaw->data_addr = (u64) page_address(bv.bv_page); + aidaw->data_addr = virt_to_phys(page_address(bv.bv_page)); aidaw++; } diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index c533d1dadc6b..a5dba3829769 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -202,7 +202,8 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, return -EINVAL; if (cdev->private->state == DEV_STATE_NOT_OPER) return -ENODEV; - if (cdev->private->state == DEV_STATE_VERIFY) { + if (cdev->private->state == DEV_STATE_VERIFY || + cdev->private->flags.doverify) { /* Remember to fake irb when finished. */ if (!cdev->private->flags.fake_irb) { cdev->private->flags.fake_irb = FAKE_CMD_IRB; @@ -214,8 +215,7 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, } if (cdev->private->state != DEV_STATE_ONLINE || ((sch->schib.scsw.cmd.stctl & SCSW_STCTL_PRIM_STATUS) && - !(sch->schib.scsw.cmd.stctl & SCSW_STCTL_SEC_STATUS)) || - cdev->private->flags.doverify) + !(sch->schib.scsw.cmd.stctl & SCSW_STCTL_SEC_STATUS))) return -EBUSY; ret = cio_set_options (sch, flags); if (ret) diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 934515959ebf..86a8bd532489 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -425,6 +425,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q, VFIO_AP_DBF_WARN("%s: gisc registration failed: nisc=%d, isc=%d, apqn=%#04x\n", __func__, nisc, isc, q->apqn); + vfio_unpin_pages(&q->matrix_mdev->vdev, nib, 1); status.response_code = AP_RESPONSE_INVALID_GISA; return status; } @@ -638,8 +639,7 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev) * Return: a boolean value indicating whether the KVM guest's APCB was changed * by the filtering or not. */ -static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm, - struct ap_matrix_mdev *matrix_mdev) +static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev) { unsigned long apid, apqi, apqn; DECLARE_BITMAP(prev_shadow_apm, AP_DEVICES); @@ -660,8 +660,9 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm, bitmap_and(matrix_mdev->shadow_apcb.aqm, matrix_mdev->matrix.aqm, (unsigned long *)matrix_dev->info.aqm, AP_DOMAINS); - for_each_set_bit_inv(apid, apm, AP_DEVICES) { - for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) { + for_each_set_bit_inv(apid, matrix_mdev->shadow_apcb.apm, AP_DEVICES) { + for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm, + AP_DOMAINS) { /* * If the APQN is not bound to the vfio_ap device * driver, then we can't assign it to the guest's @@ -930,7 +931,6 @@ static ssize_t assign_adapter_store(struct device *dev, { int ret; unsigned long apid; - DECLARE_BITMAP(apm_delta, AP_DEVICES); struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev); mutex_lock(&ap_perms_mutex); @@ -959,11 +959,8 @@ static ssize_t assign_adapter_store(struct device *dev, } vfio_ap_mdev_link_adapter(matrix_mdev, apid); - memset(apm_delta, 0, sizeof(apm_delta)); - set_bit_inv(apid, apm_delta); - if (vfio_ap_mdev_filter_matrix(apm_delta, - matrix_mdev->matrix.aqm, matrix_mdev)) + if (vfio_ap_mdev_filter_matrix(matrix_mdev)) vfio_ap_mdev_update_guest_apcb(matrix_mdev); ret = count; @@ -1139,7 +1136,6 @@ static ssize_t assign_domain_store(struct device *dev, { int ret; unsigned long apqi; - DECLARE_BITMAP(aqm_delta, AP_DOMAINS); struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev); mutex_lock(&ap_perms_mutex); @@ -1168,11 +1164,8 @@ static ssize_t assign_domain_store(struct device *dev, } vfio_ap_mdev_link_domain(matrix_mdev, apqi); - memset(aqm_delta, 0, sizeof(aqm_delta)); - set_bit_inv(apqi, aqm_delta); - if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm, aqm_delta, - matrix_mdev)) + if (vfio_ap_mdev_filter_matrix(matrix_mdev)) vfio_ap_mdev_update_guest_apcb(matrix_mdev); ret = count; @@ -1749,6 +1742,7 @@ static ssize_t status_show(struct device *dev, { ssize_t nchars = 0; struct vfio_ap_queue *q; + unsigned long apid, apqi; struct ap_matrix_mdev *matrix_mdev; struct ap_device *apdev = to_ap_dev(dev); @@ -1756,8 +1750,21 @@ static ssize_t status_show(struct device *dev, q = dev_get_drvdata(&apdev->device); matrix_mdev = vfio_ap_mdev_for_queue(q); + /* If the queue is assigned to the matrix mediated device, then + * determine whether it is passed through to a guest; otherwise, + * indicate that it is unassigned. + */ if (matrix_mdev) { - if (matrix_mdev->kvm) + apid = AP_QID_CARD(q->apqn); + apqi = AP_QID_QUEUE(q->apqn); + /* + * If the queue is passed through to the guest, then indicate + * that it is in use; otherwise, indicate that it is + * merely assigned to a matrix mediated device. + */ + if (matrix_mdev->kvm && + test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) && + test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) nchars = scnprintf(buf, PAGE_SIZE, "%s\n", AP_QUEUE_IN_USE); else @@ -1858,11 +1865,22 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev) if (matrix_mdev) { vfio_ap_mdev_link_queue(matrix_mdev, q); - if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm, - matrix_mdev->matrix.aqm, - matrix_mdev)) + /* + * If we're in the process of handling the adding of adapters or + * domains to the host's AP configuration, then let the + * vfio_ap device driver's on_scan_complete callback filter the + * matrix and update the guest's AP configuration after all of + * the new queue devices are probed. + */ + if (!bitmap_empty(matrix_mdev->apm_add, AP_DEVICES) || + !bitmap_empty(matrix_mdev->aqm_add, AP_DOMAINS)) + goto done; + + if (vfio_ap_mdev_filter_matrix(matrix_mdev)) vfio_ap_mdev_update_guest_apcb(matrix_mdev); } + +done: dev_set_drvdata(&apdev->device, q); release_update_locks_for_mdev(matrix_mdev); @@ -2211,34 +2229,22 @@ void vfio_ap_on_cfg_changed(struct ap_config_info *cur_cfg_info, static void vfio_ap_mdev_hot_plug_cfg(struct ap_matrix_mdev *matrix_mdev) { - bool do_hotplug = false; - int filter_domains = 0; - int filter_adapters = 0; - DECLARE_BITMAP(apm, AP_DEVICES); - DECLARE_BITMAP(aqm, AP_DOMAINS); + bool filter_domains, filter_adapters, filter_cdoms, do_hotplug = false; mutex_lock(&matrix_mdev->kvm->lock); mutex_lock(&matrix_dev->mdevs_lock); - filter_adapters = bitmap_and(apm, matrix_mdev->matrix.apm, - matrix_mdev->apm_add, AP_DEVICES); - filter_domains = bitmap_and(aqm, matrix_mdev->matrix.aqm, - matrix_mdev->aqm_add, AP_DOMAINS); - - if (filter_adapters && filter_domains) - do_hotplug |= vfio_ap_mdev_filter_matrix(apm, aqm, matrix_mdev); - else if (filter_adapters) - do_hotplug |= - vfio_ap_mdev_filter_matrix(apm, - matrix_mdev->shadow_apcb.aqm, - matrix_mdev); - else - do_hotplug |= - vfio_ap_mdev_filter_matrix(matrix_mdev->shadow_apcb.apm, - aqm, matrix_mdev); + filter_adapters = bitmap_intersects(matrix_mdev->matrix.apm, + matrix_mdev->apm_add, AP_DEVICES); + filter_domains = bitmap_intersects(matrix_mdev->matrix.aqm, + matrix_mdev->aqm_add, AP_DOMAINS); + filter_cdoms = bitmap_intersects(matrix_mdev->matrix.adm, + matrix_mdev->adm_add, AP_DOMAINS); + + if (filter_adapters || filter_domains) + do_hotplug = vfio_ap_mdev_filter_matrix(matrix_mdev); - if (bitmap_intersects(matrix_mdev->matrix.adm, matrix_mdev->adm_add, - AP_DOMAINS)) + if (filter_cdoms) do_hotplug |= vfio_ap_mdev_filter_cdoms(matrix_mdev); if (do_hotplug) diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index c0f30cefec10..a41601139185 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -254,9 +254,10 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) if (!recover) { hash_del(&addr->hnode); kfree(addr); - continue; + } else { + /* prepare for recovery */ + addr->disp_flag = QETH_DISP_ADDR_ADD; } - addr->disp_flag = QETH_DISP_ADDR_ADD; } mutex_unlock(&card->ip_lock); @@ -277,9 +278,11 @@ static void qeth_l3_recover_ip(struct qeth_card *card) if (addr->disp_flag == QETH_DISP_ADDR_ADD) { rc = qeth_l3_register_addr_entry(card, addr); - if (!rc) { + if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) { + /* keep it in the records */ addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING; } else { + /* bad address */ hash_del(&addr->hnode); kfree(addr); } diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 03e71e3d5e5b..3b990cf2c195 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -1285,7 +1285,7 @@ source "drivers/scsi/arm/Kconfig" config JAZZ_ESP bool "MIPS JAZZ FAS216 SCSI support" - depends on MACH_JAZZ && SCSI + depends on MACH_JAZZ && SCSI=y select SCSI_SPI_ATTRS help This is the driver for the onboard SCSI host adapter of MIPS Magnum diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 7c6efde75da6..5e115e8b2ba4 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1678,7 +1678,6 @@ struct aac_dev u32 handle_pci_error; bool init_reset; u8 soft_reset_support; - u8 use_map_queue; }; #define aac_adapter_interrupt(dev) \ diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index 013a9a334972..25cee03d7f97 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -223,12 +223,8 @@ int aac_fib_setup(struct aac_dev * dev) struct fib *aac_fib_alloc_tag(struct aac_dev *dev, struct scsi_cmnd *scmd) { struct fib *fibptr; - u32 blk_tag; - int i; - blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd)); - i = blk_mq_unique_tag_to_tag(blk_tag); - fibptr = &dev->fibs[i]; + fibptr = &dev->fibs[scsi_cmd_to_rq(scmd)->tag]; /* * Null out fields that depend on being zero at the start of * each I/O diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index bff49b8ab057..5ba5c18b77b4 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -19,7 +19,6 @@ #include <linux/compat.h> #include <linux/blkdev.h> -#include <linux/blk-mq-pci.h> #include <linux/completion.h> #include <linux/init.h> #include <linux/interrupt.h> @@ -506,15 +505,6 @@ common_config: return 0; } -static void aac_map_queues(struct Scsi_Host *shost) -{ - struct aac_dev *aac = (struct aac_dev *)shost->hostdata; - - blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], - aac->pdev, 0); - aac->use_map_queue = true; -} - /** * aac_change_queue_depth - alter queue depths * @sdev: SCSI device we are considering @@ -1499,7 +1489,6 @@ static struct scsi_host_template aac_driver_template = { .bios_param = aac_biosparm, .shost_groups = aac_host_groups, .slave_configure = aac_slave_configure, - .map_queues = aac_map_queues, .change_queue_depth = aac_change_queue_depth, .sdev_groups = aac_dev_groups, .eh_abort_handler = aac_eh_abort, @@ -1787,8 +1776,6 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) shost->max_lun = AAC_MAX_LUN; pci_set_drvdata(pdev, shost); - shost->nr_hw_queues = aac->max_msix; - shost->host_tagset = 1; error = scsi_add_host(shost, &pdev->dev); if (error) @@ -1921,7 +1908,6 @@ static void aac_remove_one(struct pci_dev *pdev) struct aac_dev *aac = (struct aac_dev *)shost->hostdata; aac_cancel_rescan_worker(aac); - aac->use_map_queue = false; scsi_remove_host(shost); __aac_shutdown(aac); diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 61949f374188..11ef58204e96 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -493,10 +493,6 @@ static int aac_src_deliver_message(struct fib *fib) #endif u16 vector_no; - struct scsi_cmnd *scmd; - u32 blk_tag; - struct Scsi_Host *shost = dev->scsi_host_ptr; - struct blk_mq_queue_map *qmap; atomic_inc(&q->numpending); @@ -509,25 +505,8 @@ static int aac_src_deliver_message(struct fib *fib) if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) && dev->sa_firmware) vector_no = aac_get_vector(dev); - else { - if (!fib->vector_no || !fib->callback_data) { - if (shost && dev->use_map_queue) { - qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; - vector_no = qmap->mq_map[raw_smp_processor_id()]; - } - /* - * We hardcode the vector_no for - * reserved commands as a valid shost is - * absent during the init - */ - else - vector_no = 0; - } else { - scmd = (struct scsi_cmnd *)fib->callback_data; - blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd)); - vector_no = blk_mq_unique_tag_to_hwq(blk_tag); - } - } + else + vector_no = fib->vector_no; if (native_hba) { if (fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA_TMF) { diff --git a/drivers/scsi/arcmsr/arcmsr.h b/drivers/scsi/arcmsr/arcmsr.h index 07df255c4b1b..b513d4d9c35a 100644 --- a/drivers/scsi/arcmsr/arcmsr.h +++ b/drivers/scsi/arcmsr/arcmsr.h @@ -77,9 +77,13 @@ struct device_attribute; #ifndef PCI_DEVICE_ID_ARECA_1203 #define PCI_DEVICE_ID_ARECA_1203 0x1203 #endif +#ifndef PCI_DEVICE_ID_ARECA_1883 +#define PCI_DEVICE_ID_ARECA_1883 0x1883 +#endif #ifndef PCI_DEVICE_ID_ARECA_1884 #define PCI_DEVICE_ID_ARECA_1884 0x1884 #endif +#define PCI_DEVICE_ID_ARECA_1886_0 0x1886 #define PCI_DEVICE_ID_ARECA_1886 0x188A #define ARCMSR_HOURS (1000 * 60 * 60 * 4) #define ARCMSR_MINUTES (1000 * 60 * 60) diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index d3fb8a9c1c39..fc9d4005830b 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -214,8 +214,12 @@ static struct pci_device_id arcmsr_device_id_table[] = { .driver_data = ACB_ADAPTER_TYPE_A}, {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1880), .driver_data = ACB_ADAPTER_TYPE_C}, + {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1883), + .driver_data = ACB_ADAPTER_TYPE_C}, {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1884), .driver_data = ACB_ADAPTER_TYPE_E}, + {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1886_0), + .driver_data = ACB_ADAPTER_TYPE_F}, {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1886), .driver_data = ACB_ADAPTER_TYPE_F}, {0, 0}, /* Terminating entry */ @@ -4708,9 +4712,11 @@ static const char *arcmsr_info(struct Scsi_Host *host) case PCI_DEVICE_ID_ARECA_1680: case PCI_DEVICE_ID_ARECA_1681: case PCI_DEVICE_ID_ARECA_1880: + case PCI_DEVICE_ID_ARECA_1883: case PCI_DEVICE_ID_ARECA_1884: type = "SAS/SATA"; break; + case PCI_DEVICE_ID_ARECA_1886_0: case PCI_DEVICE_ID_ARECA_1886: type = "NVMe/SAS/SATA"; break; diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 05ddbb9bb7d8..451a58e0fd96 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -429,7 +429,6 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev, struct fcoe_ctlr *ctlr; struct fcoe_rcv_info *fr; struct fcoe_percpu_s *bg; - struct sk_buff *tmp_skb; interface = container_of(ptype, struct bnx2fc_interface, fcoe_packet_type); @@ -441,11 +440,9 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev, goto err; } - tmp_skb = skb_share_check(skb, GFP_ATOMIC); - if (!tmp_skb) - goto err; - - skb = tmp_skb; + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return -1; if (unlikely(eth_hdr(skb)->h_proto != htons(ETH_P_FCOE))) { printk(KERN_ERR PFX "bnx2fc_rcv: Wrong FC type frame\n"); diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 8a4124e7d204..ddc048069af2 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -319,17 +319,16 @@ static void fcoe_ctlr_announce(struct fcoe_ctlr *fip) { struct fcoe_fcf *sel; struct fcoe_fcf *fcf; - unsigned long flags; mutex_lock(&fip->ctlr_mutex); - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); kfree_skb(fip->flogi_req); fip->flogi_req = NULL; list_for_each_entry(fcf, &fip->fcfs, list) fcf->flogi_sent = 0; - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); sel = fip->sel_fcf; if (sel && ether_addr_equal(sel->fcf_mac, fip->dest_addr)) @@ -700,7 +699,6 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, { struct fc_frame *fp; struct fc_frame_header *fh; - unsigned long flags; u16 old_xid; u8 op; u8 mac[ETH_ALEN]; @@ -734,11 +732,11 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, op = FIP_DT_FLOGI; if (fip->mode == FIP_MODE_VN2VN) break; - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); kfree_skb(fip->flogi_req); fip->flogi_req = skb; fip->flogi_req_send = 1; - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); schedule_work(&fip->timer_work); return -EINPROGRESS; case ELS_FDISC: @@ -1707,11 +1705,10 @@ static int fcoe_ctlr_flogi_send_locked(struct fcoe_ctlr *fip) static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) { struct fcoe_fcf *fcf; - unsigned long flags; int error; mutex_lock(&fip->ctlr_mutex); - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); LIBFCOE_FIP_DBG(fip, "re-sending FLOGI - reselect\n"); fcf = fcoe_ctlr_select(fip); if (!fcf || fcf->flogi_sent) { @@ -1722,7 +1719,7 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) fcoe_ctlr_solicit(fip, NULL); error = fcoe_ctlr_flogi_send_locked(fip); } - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); mutex_unlock(&fip->ctlr_mutex); return error; } @@ -1739,9 +1736,8 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip) { struct fcoe_fcf *fcf; - unsigned long flags; - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); fcf = fip->sel_fcf; if (!fcf || !fip->flogi_req_send) goto unlock; @@ -1768,7 +1764,7 @@ static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip) } else /* XXX */ LIBFCOE_FIP_DBG(fip, "No FCF selected - defer send\n"); unlock: - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); } /** diff --git a/drivers/scsi/fnic/fnic_debugfs.c b/drivers/scsi/fnic/fnic_debugfs.c index 6fedc3b7d1ab..eb895a65ea8f 100644 --- a/drivers/scsi/fnic/fnic_debugfs.c +++ b/drivers/scsi/fnic/fnic_debugfs.c @@ -52,9 +52,10 @@ int fnic_debugfs_init(void) fc_trc_flag->fnic_trace = 2; fc_trc_flag->fc_trace = 3; fc_trc_flag->fc_clear = 4; + return 0; } - return 0; + return -ENOMEM; } /* diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index a8142e2b9643..450a8578157c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -1502,12 +1502,12 @@ EXPORT_SYMBOL_GPL(hisi_sas_controller_reset_done); static int hisi_sas_controller_prereset(struct hisi_hba *hisi_hba) { if (!hisi_hba->hw->soft_reset) - return -1; + return -ENOENT; down(&hisi_hba->sem); if (test_and_set_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags)) { up(&hisi_hba->sem); - return -1; + return -EPERM; } if (hisi_sas_debugfs_enable && hisi_hba->debugfs_itct[0].itct) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index c4305ec38ebf..7ae56a2fe232 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -1565,6 +1565,11 @@ static irqreturn_t phy_up_v3_hw(int phy_no, struct hisi_hba *hisi_hba) } phy->port_id = port_id; + spin_lock(&phy->lock); + /* Delete timer and set phy_attached atomically */ + del_timer(&phy->timer); + phy->phy_attached = 1; + spin_unlock(&phy->lock); /* * Call pm_runtime_get_noresume() which pairs with @@ -1578,11 +1583,6 @@ static irqreturn_t phy_up_v3_hw(int phy_no, struct hisi_hba *hisi_hba) res = IRQ_HANDLED; - spin_lock(&phy->lock); - /* Delete timer and set phy_attached atomically */ - del_timer(&phy->timer); - phy->phy_attached = 1; - spin_unlock(&phy->lock); end: if (phy->reset_completion) complete(phy->reset_completion); @@ -3330,7 +3330,7 @@ static void debugfs_snapshot_global_reg_v3_hw(struct hisi_hba *hisi_hba) u32 *databuf = hisi_hba->debugfs_regs[dump_index][DEBUGFS_GLOBAL].data; int i; - for (i = 0; i < debugfs_axi_reg.count; i++, databuf++) + for (i = 0; i < debugfs_global_reg.count; i++, databuf++) *databuf = hisi_sas_read32(hisi_hba, 4 * i); } @@ -4946,6 +4946,7 @@ static void hisi_sas_reset_done_v3_hw(struct pci_dev *pdev) { struct sas_ha_struct *sha = pci_get_drvdata(pdev); struct hisi_hba *hisi_hba = sha->lldd_ha; + struct Scsi_Host *shost = hisi_hba->shost; struct device *dev = hisi_hba->dev; int rc; @@ -4954,6 +4955,10 @@ static void hisi_sas_reset_done_v3_hw(struct pci_dev *pdev) rc = hw_init_v3_hw(hisi_hba); if (rc) { dev_err(dev, "FLR: hw init failed rc=%d\n", rc); + clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags); + scsi_unblock_requests(shost); + clear_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags); + up(&hisi_hba->sem); return; } @@ -4981,7 +4986,7 @@ static int _suspend_v3_hw(struct device *device) } if (test_and_set_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags)) - return -1; + return -EPERM; dev_warn(dev, "entering suspend state\n"); diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c index 6370cdbfba08..0f0732d56800 100644 --- a/drivers/scsi/isci/request.c +++ b/drivers/scsi/isci/request.c @@ -3390,7 +3390,7 @@ static enum sci_status isci_io_request_build(struct isci_host *ihost, return SCI_FAILURE; } - return SCI_SUCCESS; + return status; } static struct isci_request *isci_request_from_tag(struct isci_host *ihost, u16 tag) diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index 945adca5e72f..05be0810b5e3 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -265,6 +265,11 @@ static int fc_fcp_send_abort(struct fc_fcp_pkt *fsp) if (!fsp->seq_ptr) return -EINVAL; + if (fsp->state & FC_SRB_ABORT_PENDING) { + FC_FCP_DBG(fsp, "abort already pending\n"); + return -EBUSY; + } + this_cpu_inc(fsp->lp->stats->FcpPktAborts); fsp->state |= FC_SRB_ABORT_PENDING; @@ -1671,7 +1676,7 @@ static void fc_fcp_rec_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp) if (fsp->recov_retry++ < FC_MAX_RECOV_RETRY) fc_fcp_rec(fsp); else - fc_fcp_recovery(fsp, FC_ERROR); + fc_fcp_recovery(fsp, FC_TIMED_OUT); break; } fc_fcp_unlock_pkt(fsp); @@ -1690,11 +1695,12 @@ static void fc_fcp_recovery(struct fc_fcp_pkt *fsp, u8 code) fsp->status_code = code; fsp->cdb_status = 0; fsp->io_status = 0; - /* - * if this fails then we let the scsi command timer fire and - * scsi-ml escalate. - */ - fc_fcp_send_abort(fsp); + if (!fsp->cmd) + /* + * Only abort non-scsi commands; otherwise let the + * scsi command timer fire and scsi-ml escalate. + */ + fc_fcp_send_abort(fsp); } /** diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index 664ac3069c4b..dc5ac3cc70f6 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -33,6 +33,7 @@ struct lpfc_sli2_slim; #define ELX_MODEL_NAME_SIZE 80 +#define ELX_FW_NAME_SIZE 84 #define LPFC_PCI_DEV_LP 0x1 #define LPFC_PCI_DEV_OC 0x2 diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index f59de61803dc..1a0bafde34d8 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -14778,7 +14778,7 @@ out: int lpfc_sli4_request_firmware_update(struct lpfc_hba *phba, uint8_t fw_upgrade) { - uint8_t file_name[ELX_MODEL_NAME_SIZE]; + char file_name[ELX_FW_NAME_SIZE] = {0}; int ret; const struct firmware *fw; @@ -14787,7 +14787,7 @@ lpfc_sli4_request_firmware_update(struct lpfc_hba *phba, uint8_t fw_upgrade) LPFC_SLI_INTF_IF_TYPE_2) return -EPERM; - snprintf(file_name, ELX_MODEL_NAME_SIZE, "%s.grp", phba->ModelName); + scnprintf(file_name, sizeof(file_name), "%s.grp", phba->ModelName); if (fw_upgrade == INT_FW_UPGRADE) { ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_UEVENT, diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 7aac9fc71967..0bb7e164b525 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -1919,7 +1919,7 @@ out: * * Returns the number of SGEs added to the SGL. **/ -static int +static uint32_t lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct sli4_sge *sgl, int datasegcnt, struct lpfc_io_buf *lpfc_cmd) @@ -1927,8 +1927,8 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct scatterlist *sgde = NULL; /* s/g data entry */ struct sli4_sge_diseed *diseed = NULL; dma_addr_t physaddr; - int i = 0, num_sge = 0, status; - uint32_t reftag; + int i = 0, status; + uint32_t reftag, num_sge = 0; uint8_t txop, rxop; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS uint32_t rc; @@ -2100,7 +2100,7 @@ out: * * Returns the number of SGEs added to the SGL. **/ -static int +static uint32_t lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct sli4_sge *sgl, int datacnt, int protcnt, struct lpfc_io_buf *lpfc_cmd) @@ -2124,8 +2124,8 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, uint32_t rc; #endif uint32_t checking = 1; - uint32_t dma_offset = 0; - int num_sge = 0, j = 2; + uint32_t dma_offset = 0, num_sge = 0; + int j = 2; struct sli4_hybrid_sgl *sgl_xtra = NULL; sgpe = scsi_prot_sglist(sc); diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c index d10c6afb7f9c..8c662d08706f 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -223,6 +223,22 @@ static long mpi3mr_bsg_pel_enable(struct mpi3mr_ioc *mrioc, return rval; } + if (mrioc->unrecoverable) { + dprint_bsg_err(mrioc, "%s: unrecoverable controller\n", + __func__); + return -EFAULT; + } + + if (mrioc->reset_in_progress) { + dprint_bsg_err(mrioc, "%s: reset in progress\n", __func__); + return -EAGAIN; + } + + if (mrioc->stop_bsgs) { + dprint_bsg_err(mrioc, "%s: bsgs are blocked\n", __func__); + return -EAGAIN; + } + sg_copy_to_buffer(job->request_payload.sg_list, job->request_payload.sg_cnt, &pel_enable, sizeof(pel_enable)); diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index d2c7de804b99..41636c4c43af 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -1886,7 +1886,8 @@ static int mpi3mr_create_op_reply_q(struct mpi3mr_ioc *mrioc, u16 qidx) reply_qid = qidx + 1; op_reply_q->num_replies = MPI3MR_OP_REP_Q_QD; - if (!mrioc->pdev->revision) + if ((mrioc->pdev->device == MPI3_MFGPAGE_DEVID_SAS4116) && + !mrioc->pdev->revision) op_reply_q->num_replies = MPI3MR_OP_REP_Q_QD4K; op_reply_q->ci = 0; op_reply_q->ephase = 1; diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index 6d55698ea4d1..7a6b006e70c8 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -1044,8 +1044,14 @@ void mpi3mr_rfresh_tgtdevs(struct mpi3mr_ioc *mrioc) tgtdev = NULL; list_for_each_entry(tgtdev, &mrioc->tgtdev_list, list) { if ((tgtdev->dev_handle != MPI3MR_INVALID_DEV_HANDLE) && - !tgtdev->is_hidden && !tgtdev->host_exposed) - mpi3mr_report_tgtdev_to_host(mrioc, tgtdev->perst_id); + !tgtdev->is_hidden) { + if (!tgtdev->host_exposed) + mpi3mr_report_tgtdev_to_host(mrioc, + tgtdev->perst_id); + else if (tgtdev->starget) + starget_for_each_device(tgtdev->starget, + (void *)tgtdev, mpi3mr_update_sdev); + } } } @@ -4957,7 +4963,10 @@ mpi3mr_probe(struct pci_dev *pdev, const struct pci_device_id *id) mpi3mr_init_drv_cmd(&mrioc->evtack_cmds[i], MPI3MR_HOSTTAG_EVTACKCMD_MIN + i); - if (pdev->revision) + if ((pdev->device == MPI3_MFGPAGE_DEVID_SAS4116) && + !pdev->revision) + mrioc->enable_segqueue = false; + else mrioc->enable_segqueue = true; init_waitqueue_head(&mrioc->reset_waitq); diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 3cda5d26b66c..e70ab8db3014 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -328,21 +328,39 @@ static int scsi_vpd_inquiry(struct scsi_device *sdev, unsigned char *buffer, return result + 4; } +enum scsi_vpd_parameters { + SCSI_VPD_HEADER_SIZE = 4, + SCSI_VPD_LIST_SIZE = 36, +}; + static int scsi_get_vpd_size(struct scsi_device *sdev, u8 page) { - unsigned char vpd_header[SCSI_VPD_HEADER_SIZE] __aligned(4); + unsigned char vpd[SCSI_VPD_LIST_SIZE] __aligned(4); int result; if (sdev->no_vpd_size) return SCSI_DEFAULT_VPD_LEN; /* + * Fetch the supported pages VPD and validate that the requested page + * number is present. + */ + if (page != 0) { + result = scsi_vpd_inquiry(sdev, vpd, 0, sizeof(vpd)); + if (result < SCSI_VPD_HEADER_SIZE) + return 0; + + result -= SCSI_VPD_HEADER_SIZE; + if (!memchr(&vpd[SCSI_VPD_HEADER_SIZE], page, result)) + return 0; + } + /* * Fetch the VPD page header to find out how big the page * is. This is done to prevent problems on legacy devices * which can not handle allocation lengths as large as * potentially requested by the caller. */ - result = scsi_vpd_inquiry(sdev, vpd_header, page, sizeof(vpd_header)); + result = scsi_vpd_inquiry(sdev, vpd, page, SCSI_VPD_HEADER_SIZE); if (result < 0) return 0; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 02520f912306..cfa6f0edff17 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -61,11 +61,11 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd); static enum scsi_disposition scsi_try_to_abort_cmd(struct scsi_host_template *, struct scsi_cmnd *); -void scsi_eh_wakeup(struct Scsi_Host *shost) +void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy) { lockdep_assert_held(shost->host_lock); - if (scsi_host_busy(shost) == shost->host_failed) { + if (busy == shost->host_failed) { trace_scsi_eh_wakeup(shost); wake_up_process(shost->ehandler); SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost, @@ -88,7 +88,7 @@ void scsi_schedule_eh(struct Scsi_Host *shost) if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 || scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) { shost->host_eh_scheduled++; - scsi_eh_wakeup(shost); + scsi_eh_wakeup(shost, scsi_host_busy(shost)); } spin_unlock_irqrestore(shost->host_lock, flags); @@ -277,11 +277,12 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head) { struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); struct Scsi_Host *shost = scmd->device->host; + unsigned int busy = scsi_host_busy(shost); unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; - scsi_eh_wakeup(shost); + scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } @@ -1108,6 +1109,7 @@ retry: scsi_log_send(scmd); scmd->submitter = SUBMITTED_BY_SCSI_ERROR_HANDLER; + scmd->flags |= SCMD_LAST; /* * Lock sdev->state_mutex to avoid that scsi_device_quiesce() can @@ -2402,6 +2404,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg) scsi_init_command(dev, scmd); scmd->submitter = SUBMITTED_BY_SCSI_RESET_IOCTL; + scmd->flags |= SCMD_LAST; memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->cmd_len = 0; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index d25e1c247253..5c5954b78585 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -280,9 +280,11 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd) rcu_read_lock(); __clear_bit(SCMD_STATE_INFLIGHT, &cmd->state); if (unlikely(scsi_host_in_recovery(shost))) { + unsigned int busy = scsi_host_busy(shost); + spin_lock_irqsave(shost->host_lock, flags); if (shost->host_failed || shost->host_eh_scheduled) - scsi_eh_wakeup(shost); + scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } rcu_read_unlock(); diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index b14545acb40f..9b5fb30e684b 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -86,7 +86,7 @@ extern void scmd_eh_abort_handler(struct work_struct *work); extern enum blk_eh_timer_return scsi_timeout(struct request *req); extern int scsi_error_handler(void *host); extern enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *cmd); -extern void scsi_eh_wakeup(struct Scsi_Host *shost); +extern void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy); extern void scsi_eh_scmd_add(struct scsi_cmnd *); void scsi_eh_ready_devs(struct Scsi_Host *shost, struct list_head *work_q, diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 47d487729635..e44f6bb25a8e 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -6449,8 +6449,11 @@ static void pqi_map_queues(struct Scsi_Host *shost) { struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost); - blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], + if (!ctrl_info->disable_managed_interrupts) + return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], ctrl_info->pci_dev, 0); + else + return blk_mq_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT]); } static inline bool pqi_is_tape_changer_device(struct pqi_scsi_dev *device) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index c2d981d5a2dd..4fad9d85bd6f 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -326,6 +326,7 @@ enum storvsc_request_type { */ static int storvsc_ringbuffer_size = (128 * 1024); +static int aligned_ringbuffer_size; static u32 max_outstanding_req_per_channel; static int storvsc_change_queue_depth(struct scsi_device *sdev, int queue_depth); @@ -683,8 +684,8 @@ static void handle_sc_creation(struct vmbus_channel *new_sc) new_sc->next_request_id_callback = storvsc_next_request_id; ret = vmbus_open(new_sc, - storvsc_ringbuffer_size, - storvsc_ringbuffer_size, + aligned_ringbuffer_size, + aligned_ringbuffer_size, (void *)&props, sizeof(struct vmstorage_channel_properties), storvsc_on_channel_callback, new_sc); @@ -1964,7 +1965,7 @@ static int storvsc_probe(struct hv_device *device, dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1); stor_device->port_number = host->host_no; - ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc); + ret = storvsc_connect_to_vsp(device, aligned_ringbuffer_size, is_fc); if (ret) goto err_out1; @@ -2157,7 +2158,7 @@ static int storvsc_resume(struct hv_device *hv_dev) { int ret; - ret = storvsc_connect_to_vsp(hv_dev, storvsc_ringbuffer_size, + ret = storvsc_connect_to_vsp(hv_dev, aligned_ringbuffer_size, hv_dev_is_fc(hv_dev)); return ret; } @@ -2191,8 +2192,9 @@ static int __init storvsc_drv_init(void) * the ring buffer indices) by the max request size (which is * vmbus_channel_packet_multipage_buffer + struct vstor_packet + u64) */ + aligned_ringbuffer_size = VMBUS_RING_SIZE(storvsc_ringbuffer_size); max_outstanding_req_per_channel = - ((storvsc_ringbuffer_size - PAGE_SIZE) / + ((aligned_ringbuffer_size - PAGE_SIZE) / ALIGN(MAX_MULTIPAGE_BUFFER_PACKET + sizeof(struct vstor_packet) + sizeof(u64), sizeof(u64))); diff --git a/drivers/soc/mediatek/mtk-pm-domains.c b/drivers/soc/mediatek/mtk-pm-domains.c index 474b272f9b02..832adb570b50 100644 --- a/drivers/soc/mediatek/mtk-pm-domains.c +++ b/drivers/soc/mediatek/mtk-pm-domains.c @@ -499,6 +499,11 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren goto err_put_node; } + /* recursive call to add all subdomains */ + ret = scpsys_add_subdomain(scpsys, child); + if (ret) + goto err_put_node; + ret = pm_genpd_add_subdomain(parent_pd, child_pd); if (ret) { dev_err(scpsys->dev, "failed to add %s subdomain to parent %s\n", @@ -508,11 +513,6 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren dev_dbg(scpsys->dev, "%s add subdomain: %s\n", parent_pd->name, child_pd->name); } - - /* recursive call to add all subdomains */ - ret = scpsys_add_subdomain(scpsys, child); - if (ret) - goto err_put_node; } return 0; @@ -526,9 +526,6 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd) { int ret; - if (scpsys_domain_is_on(pd)) - scpsys_power_off(&pd->genpd); - /* * We're in the error cleanup already, so we only complain, * but won't emit another error on top of the original one. @@ -538,6 +535,8 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd) dev_err(pd->scpsys->dev, "failed to remove domain '%s' : %d - state may be inconsistent\n", pd->genpd.name, ret); + if (scpsys_domain_is_on(pd)) + scpsys_power_off(&pd->genpd); clk_bulk_put(pd->num_clks, pd->clks); clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks); diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index bc400669ee02..16a05143d0d6 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -680,14 +680,14 @@ static int _qcom_llcc_cfg_program(const struct llcc_slice_config *config, u32 disable_cap_alloc, retain_pc; disable_cap_alloc = config->dis_cap_alloc << config->slice_id; - ret = regmap_write(drv_data->bcast_regmap, - LLCC_TRP_SCID_DIS_CAP_ALLOC, disable_cap_alloc); + ret = regmap_update_bits(drv_data->bcast_regmap, LLCC_TRP_SCID_DIS_CAP_ALLOC, + BIT(config->slice_id), disable_cap_alloc); if (ret) return ret; retain_pc = config->retain_on_pc << config->slice_id; - ret = regmap_write(drv_data->bcast_regmap, - LLCC_TRP_PCB_ACT, retain_pc); + ret = regmap_update_bits(drv_data->bcast_regmap, LLCC_TRP_PCB_ACT, + BIT(config->slice_id), retain_pc); if (ret) return ret; } diff --git a/drivers/soc/renesas/r8a77980-sysc.c b/drivers/soc/renesas/r8a77980-sysc.c index 39ca84a67daa..621e411fc999 100644 --- a/drivers/soc/renesas/r8a77980-sysc.c +++ b/drivers/soc/renesas/r8a77980-sysc.c @@ -25,7 +25,8 @@ static const struct rcar_sysc_area r8a77980_areas[] __initconst = { PD_CPU_NOCR }, { "ca53-cpu3", 0x200, 3, R8A77980_PD_CA53_CPU3, R8A77980_PD_CA53_SCU, PD_CPU_NOCR }, - { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON }, + { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON, + PD_CPU_NOCR }, { "a3ir", 0x180, 0, R8A77980_PD_A3IR, R8A77980_PD_ALWAYS_ON }, { "a2ir0", 0x400, 0, R8A77980_PD_A2IR0, R8A77980_PD_A3IR }, { "a2ir1", 0x400, 1, R8A77980_PD_A2IR1, R8A77980_PD_A3IR }, diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c index f9d9b82b562d..8293cc40047f 100644 --- a/drivers/soc/xilinx/xlnx_event_manager.c +++ b/drivers/soc/xilinx/xlnx_event_manager.c @@ -477,7 +477,7 @@ static void xlnx_call_notify_cb_handler(const u32 *payload) } } if (!is_callback_found) - pr_warn("Didn't find any registered callback for 0x%x 0x%x\n", + pr_warn("Unhandled SGI node 0x%x event 0x%x. Expected with Xen hypervisor\n", payload[1], payload[2]); } @@ -555,7 +555,7 @@ static void xlnx_disable_percpu_irq(void *data) static int xlnx_event_init_sgi(struct platform_device *pdev) { int ret = 0; - int cpu = smp_processor_id(); + int cpu; /* * IRQ related structures are used for the following: * for each SGI interrupt ensure its mapped by GIC IRQ domain @@ -592,9 +592,12 @@ static int xlnx_event_init_sgi(struct platform_device *pdev) sgi_fwspec.param[0] = sgi_num; virq_sgi = irq_create_fwspec_mapping(&sgi_fwspec); + cpu = get_cpu(); per_cpu(cpu_number1, cpu) = cpu; ret = request_percpu_irq(virq_sgi, xlnx_event_handler, "xlnx_event_mgmt", &cpu_number1); + put_cpu(); + WARN_ON(ret); if (ret) { irq_dispose_mapping(virq_sgi); diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index 946e2186d244..15ea11ebcbe0 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -1101,9 +1101,10 @@ config SPI_ZYNQ_QSPI config SPI_ZYNQMP_GQSPI tristate "Xilinx ZynqMP GQSPI controller" - depends on (SPI_MASTER && HAS_DMA) || COMPILE_TEST + depends on (SPI_MEM && HAS_DMA) || COMPILE_TEST help Enables Xilinx GQSPI controller driver for Zynq UltraScale+ MPSoC. + This controller only supports SPI memory interface. config SPI_AMD tristate "AMD SPI controller" diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index c4f22d50dba5..78daf2b2143c 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -22,6 +22,7 @@ #include <linux/gpio/consumer.h> #include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> +#include <linux/iopoll.h> #include <trace/events/spi.h> /* SPI register offsets */ @@ -278,6 +279,7 @@ struct atmel_spi { bool keep_cs; u32 fifo_size; + bool last_polarity; u8 native_cs_free; u8 native_cs_for_gpio; }; @@ -291,6 +293,22 @@ struct atmel_spi_device { #define INVALID_DMA_ADDRESS 0xffffffff /* + * This frequency can be anything supported by the controller, but to avoid + * unnecessary delay, the highest possible frequency is chosen. + * + * This frequency is the highest possible which is not interfering with other + * chip select registers (see Note for Serial Clock Bit Rate configuration in + * Atmel-11121F-ATARM-SAMA5D3-Series-Datasheet_02-Feb-16, page 1283) + */ +#define DUMMY_MSG_FREQUENCY 0x02 +/* + * 8 bits is the minimum data the controller is capable of sending. + * + * This message can be anything as it should not be treated by any SPI device. + */ +#define DUMMY_MSG 0xAA + +/* * Version 2 of the SPI controller has * - CR.LASTXFER * - SPI_MR.DIV32 may become FDIV or must-be-zero (here: always zero) @@ -304,6 +322,43 @@ static bool atmel_spi_is_v2(struct atmel_spi *as) } /* + * Send a dummy message. + * + * This is sometimes needed when using a CS GPIO to force clock transition when + * switching between devices with different polarities. + */ +static void atmel_spi_send_dummy(struct atmel_spi *as, struct spi_device *spi, int chip_select) +{ + u32 status; + u32 csr; + + /* + * Set a clock frequency to allow sending message on SPI bus. + * The frequency here can be anything, but is needed for + * the controller to send the data. + */ + csr = spi_readl(as, CSR0 + 4 * chip_select); + csr = SPI_BFINS(SCBR, DUMMY_MSG_FREQUENCY, csr); + spi_writel(as, CSR0 + 4 * chip_select, csr); + + /* + * Read all data coming from SPI bus, needed to be able to send + * the message. + */ + spi_readl(as, RDR); + while (spi_readl(as, SR) & SPI_BIT(RDRF)) { + spi_readl(as, RDR); + cpu_relax(); + } + + spi_writel(as, TDR, DUMMY_MSG); + + readl_poll_timeout_atomic(as->regs + SPI_SR, status, + (status & SPI_BIT(TXEMPTY)), 1, 1000); +} + + +/* * Earlier SPI controllers (e.g. on at91rm9200) have a design bug whereby * they assume that spi slave device state will not change on deselect, so * that automagic deselection is OK. ("NPCSx rises if no data is to be @@ -319,11 +374,17 @@ static bool atmel_spi_is_v2(struct atmel_spi *as) * Master on Chip Select 0.") No workaround exists for that ... so for * nCS0 on that chip, we (a) don't use the GPIO, (b) can't support CS_HIGH, * and (c) will trigger that first erratum in some cases. + * + * When changing the clock polarity, the SPI controller waits for the next + * transmission to enforce the default clock state. This may be an issue when + * using a GPIO as Chip Select: the clock level is applied only when the first + * packet is sent, once the CS has already been asserted. The workaround is to + * avoid this by sending a first (dummy) message before toggling the CS state. */ - static void cs_activate(struct atmel_spi *as, struct spi_device *spi) { struct atmel_spi_device *asd = spi->controller_state; + bool new_polarity; int chip_select; u32 mr; @@ -352,6 +413,25 @@ static void cs_activate(struct atmel_spi *as, struct spi_device *spi) } mr = spi_readl(as, MR); + + /* + * Ensures the clock polarity is valid before we actually + * assert the CS to avoid spurious clock edges to be + * processed by the spi devices. + */ + if (spi_get_csgpiod(spi, 0)) { + new_polarity = (asd->csr & SPI_BIT(CPOL)) != 0; + if (new_polarity != as->last_polarity) { + /* + * Need to disable the GPIO before sending the dummy + * message because it is already set by the spi core. + */ + gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), 0); + atmel_spi_send_dummy(as, spi, chip_select); + as->last_polarity = new_polarity; + gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), 1); + } + } } else { u32 cpol = (spi->mode & SPI_CPOL) ? SPI_BIT(CPOL) : 0; int i; diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 137e7315a3cf..b24955910147 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -19,7 +19,7 @@ #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/spi/spi.h> -#include <linux/spi/spi-mem.h> +#include <linux/mtd/spi-nor.h> #include <linux/sysfs.h> #include <linux/types.h> #include "spi-bcm-qspi.h" @@ -1221,7 +1221,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, /* non-aligned and very short transfers are handled by MSPI */ if (!IS_ALIGNED((uintptr_t)addr, 4) || !IS_ALIGNED((uintptr_t)buf, 4) || - len < 4) + len < 4 || op->cmd.opcode == SPINOR_OP_RDSFDP) mspi_read = true; if (!has_bspi(qspi) || mspi_read) diff --git a/drivers/spi/spi-hisi-sfc-v3xx.c b/drivers/spi/spi-hisi-sfc-v3xx.c index d3a23b1c2a4c..61bf00dfe9c3 100644 --- a/drivers/spi/spi-hisi-sfc-v3xx.c +++ b/drivers/spi/spi-hisi-sfc-v3xx.c @@ -377,6 +377,11 @@ static const struct spi_controller_mem_ops hisi_sfc_v3xx_mem_ops = { static irqreturn_t hisi_sfc_v3xx_isr(int irq, void *data) { struct hisi_sfc_v3xx_host *host = data; + u32 reg; + + reg = readl(host->regbase + HISI_SFC_V3XX_INT_STAT); + if (!reg) + return IRQ_NONE; hisi_sfc_v3xx_disable_int(host); diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c index d65f047b6c82..1179a1115137 100644 --- a/drivers/spi/spi-ppc4xx.c +++ b/drivers/spi/spi-ppc4xx.c @@ -166,10 +166,8 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t) int scr; u8 cdm = 0; u32 speed; - u8 bits_per_word; /* Start with the generic configuration for this device. */ - bits_per_word = spi->bits_per_word; speed = spi->max_speed_hz; /* @@ -177,9 +175,6 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t) * the transfer to overwrite the generic configuration with zeros. */ if (t) { - if (t->bits_per_word) - bits_per_word = t->bits_per_word; - if (t->speed_hz) speed = min(t->speed_hz, spi->max_speed_hz); } diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index 9bca3d076f05..ec3a4939ee98 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -30,12 +30,15 @@ #include <asm/unaligned.h> +#define SH_MSIOF_FLAG_FIXED_DTDL_200 BIT(0) + struct sh_msiof_chipdata { u32 bits_per_word_mask; u16 tx_fifo_size; u16 rx_fifo_size; u16 ctlr_flags; u16 min_div_pow; + u32 flags; }; struct sh_msiof_spi_priv { @@ -134,14 +137,14 @@ struct sh_msiof_spi_priv { /* SIFCTR */ #define SIFCTR_TFWM_MASK GENMASK(31, 29) /* Transmit FIFO Watermark */ -#define SIFCTR_TFWM_64 (0 << 29) /* Transfer Request when 64 empty stages */ -#define SIFCTR_TFWM_32 (1 << 29) /* Transfer Request when 32 empty stages */ -#define SIFCTR_TFWM_24 (2 << 29) /* Transfer Request when 24 empty stages */ -#define SIFCTR_TFWM_16 (3 << 29) /* Transfer Request when 16 empty stages */ -#define SIFCTR_TFWM_12 (4 << 29) /* Transfer Request when 12 empty stages */ -#define SIFCTR_TFWM_8 (5 << 29) /* Transfer Request when 8 empty stages */ -#define SIFCTR_TFWM_4 (6 << 29) /* Transfer Request when 4 empty stages */ -#define SIFCTR_TFWM_1 (7 << 29) /* Transfer Request when 1 empty stage */ +#define SIFCTR_TFWM_64 (0UL << 29) /* Transfer Request when 64 empty stages */ +#define SIFCTR_TFWM_32 (1UL << 29) /* Transfer Request when 32 empty stages */ +#define SIFCTR_TFWM_24 (2UL << 29) /* Transfer Request when 24 empty stages */ +#define SIFCTR_TFWM_16 (3UL << 29) /* Transfer Request when 16 empty stages */ +#define SIFCTR_TFWM_12 (4UL << 29) /* Transfer Request when 12 empty stages */ +#define SIFCTR_TFWM_8 (5UL << 29) /* Transfer Request when 8 empty stages */ +#define SIFCTR_TFWM_4 (6UL << 29) /* Transfer Request when 4 empty stages */ +#define SIFCTR_TFWM_1 (7UL << 29) /* Transfer Request when 1 empty stage */ #define SIFCTR_TFUA_MASK GENMASK(26, 20) /* Transmit FIFO Usable Area */ #define SIFCTR_TFUA_SHIFT 20 #define SIFCTR_TFUA(i) ((i) << SIFCTR_TFUA_SHIFT) @@ -1073,6 +1076,16 @@ static const struct sh_msiof_chipdata rcar_gen3_data = { .min_div_pow = 1, }; +static const struct sh_msiof_chipdata rcar_r8a7795_data = { + .bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16) | + SPI_BPW_MASK(24) | SPI_BPW_MASK(32), + .tx_fifo_size = 64, + .rx_fifo_size = 64, + .ctlr_flags = SPI_CONTROLLER_MUST_TX, + .min_div_pow = 1, + .flags = SH_MSIOF_FLAG_FIXED_DTDL_200, +}; + static const struct of_device_id sh_msiof_match[] = { { .compatible = "renesas,sh-mobile-msiof", .data = &sh_data }, { .compatible = "renesas,msiof-r8a7743", .data = &rcar_gen2_data }, @@ -1083,6 +1096,7 @@ static const struct of_device_id sh_msiof_match[] = { { .compatible = "renesas,msiof-r8a7793", .data = &rcar_gen2_data }, { .compatible = "renesas,msiof-r8a7794", .data = &rcar_gen2_data }, { .compatible = "renesas,rcar-gen2-msiof", .data = &rcar_gen2_data }, + { .compatible = "renesas,msiof-r8a7795", .data = &rcar_r8a7795_data }, { .compatible = "renesas,msiof-r8a7796", .data = &rcar_gen3_data }, { .compatible = "renesas,rcar-gen3-msiof", .data = &rcar_gen3_data }, { .compatible = "renesas,rcar-gen4-msiof", .data = &rcar_gen3_data }, @@ -1280,6 +1294,9 @@ static int sh_msiof_spi_probe(struct platform_device *pdev) return -ENXIO; } + if (chipdata->flags & SH_MSIOF_FLAG_FIXED_DTDL_200) + info->dtdl = 200; + if (info->mode == MSIOF_SPI_SLAVE) ctlr = spi_alloc_slave(&pdev->dev, sizeof(struct sh_msiof_spi_priv)); diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 5d046be8b2dd..19688f333e0b 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -360,6 +360,18 @@ const struct spi_device_id *spi_get_device_id(const struct spi_device *sdev) } EXPORT_SYMBOL_GPL(spi_get_device_id); +const void *spi_get_device_match_data(const struct spi_device *sdev) +{ + const void *match; + + match = device_get_match_data(&sdev->dev); + if (match) + return match; + + return (const void *)spi_get_device_id(sdev)->driver_data; +} +EXPORT_SYMBOL_GPL(spi_get_device_match_data); + static int spi_match_device(struct device *dev, struct device_driver *drv) { const struct spi_device *spi = to_spi_device(dev); @@ -592,7 +604,7 @@ static void spi_dev_set_name(struct spi_device *spi) } dev_set_name(&spi->dev, "%s.%u", dev_name(&spi->controller->dev), - spi->chip_select); + spi_get_chipselect(spi, 0)); } static int spi_dev_check(struct device *dev, void *data) @@ -601,7 +613,7 @@ static int spi_dev_check(struct device *dev, void *data) struct spi_device *new_spi = data; if (spi->controller == new_spi->controller && - spi->chip_select == new_spi->chip_select) + spi_get_chipselect(spi, 0) == spi_get_chipselect(new_spi, 0)) return -EBUSY; return 0; } @@ -626,7 +638,7 @@ static int __spi_add_device(struct spi_device *spi) status = bus_for_each_dev(&spi_bus_type, NULL, spi, spi_dev_check); if (status) { dev_err(dev, "chipselect %d already in use\n", - spi->chip_select); + spi_get_chipselect(spi, 0)); return status; } @@ -637,7 +649,7 @@ static int __spi_add_device(struct spi_device *spi) } if (ctlr->cs_gpiods) - spi->cs_gpiod = ctlr->cs_gpiods[spi->chip_select]; + spi_set_csgpiod(spi, 0, ctlr->cs_gpiods[spi_get_chipselect(spi, 0)]); /* * Drivers may modify this initial i/o setup, but will @@ -680,8 +692,8 @@ int spi_add_device(struct spi_device *spi) int status; /* Chipselects are numbered 0..max; validate. */ - if (spi->chip_select >= ctlr->num_chipselect) { - dev_err(dev, "cs%d >= max %d\n", spi->chip_select, + if (spi_get_chipselect(spi, 0) >= ctlr->num_chipselect) { + dev_err(dev, "cs%d >= max %d\n", spi_get_chipselect(spi, 0), ctlr->num_chipselect); return -EINVAL; } @@ -702,8 +714,8 @@ static int spi_add_device_locked(struct spi_device *spi) struct device *dev = ctlr->dev.parent; /* Chipselects are numbered 0..max; validate. */ - if (spi->chip_select >= ctlr->num_chipselect) { - dev_err(dev, "cs%d >= max %d\n", spi->chip_select, + if (spi_get_chipselect(spi, 0) >= ctlr->num_chipselect) { + dev_err(dev, "cs%d >= max %d\n", spi_get_chipselect(spi, 0), ctlr->num_chipselect); return -EINVAL; } @@ -749,7 +761,7 @@ struct spi_device *spi_new_device(struct spi_controller *ctlr, WARN_ON(strlen(chip->modalias) >= sizeof(proxy->modalias)); - proxy->chip_select = chip->chip_select; + spi_set_chipselect(proxy, 0, chip->chip_select); proxy->max_speed_hz = chip->max_speed_hz; proxy->mode = chip->mode; proxy->irq = chip->irq; @@ -958,24 +970,23 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force) * Avoid calling into the driver (or doing delays) if the chip select * isn't actually changing from the last time this was called. */ - if (!force && ((enable && spi->controller->last_cs == spi->chip_select) || - (!enable && spi->controller->last_cs != spi->chip_select)) && + if (!force && ((enable && spi->controller->last_cs == spi_get_chipselect(spi, 0)) || + (!enable && spi->controller->last_cs != spi_get_chipselect(spi, 0))) && (spi->controller->last_cs_mode_high == (spi->mode & SPI_CS_HIGH))) return; trace_spi_set_cs(spi, activate); - spi->controller->last_cs = enable ? spi->chip_select : -1; + spi->controller->last_cs = enable ? spi_get_chipselect(spi, 0) : -1; spi->controller->last_cs_mode_high = spi->mode & SPI_CS_HIGH; - if ((spi->cs_gpiod || !spi->controller->set_cs_timing) && !activate) { + if ((spi_get_csgpiod(spi, 0) || !spi->controller->set_cs_timing) && !activate) spi_delay_exec(&spi->cs_hold, NULL); - } if (spi->mode & SPI_CS_HIGH) enable = !enable; - if (spi->cs_gpiod) { + if (spi_get_csgpiod(spi, 0)) { if (!(spi->mode & SPI_NO_CS)) { /* * Historically ACPI has no means of the GPIO polarity and @@ -988,10 +999,10 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force) * into account. */ if (has_acpi_companion(&spi->dev)) - gpiod_set_value_cansleep(spi->cs_gpiod, !enable); + gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), !enable); else /* Polarity handled by GPIO library */ - gpiod_set_value_cansleep(spi->cs_gpiod, activate); + gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), activate); } /* Some SPI masters need both GPIO CS & slave_select */ if ((spi->controller->flags & SPI_MASTER_GPIO_SS) && @@ -1001,7 +1012,7 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force) spi->controller->set_cs(spi, !enable); } - if (spi->cs_gpiod || !spi->controller->set_cs_timing) { + if (spi_get_csgpiod(spi, 0) || !spi->controller->set_cs_timing) { if (activate) spi_delay_exec(&spi->cs_setup, NULL); else @@ -1625,6 +1636,10 @@ static int __spi_pump_transfer_message(struct spi_controller *ctlr, pm_runtime_put_noidle(ctlr->dev.parent); dev_err(&ctlr->dev, "Failed to power device: %d\n", ret); + + msg->status = ret; + spi_finalize_current_message(ctlr); + return ret; } } @@ -2291,7 +2306,7 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, nc, rc); return rc; } - spi->chip_select = value; + spi_set_chipselect(spi, 0, value); /* Device speed */ if (!of_property_read_u32(nc, "spi-max-frequency", &value)) @@ -2405,7 +2420,7 @@ struct spi_device *spi_new_ancillary_device(struct spi_device *spi, strscpy(ancillary->modalias, "dummy", sizeof(ancillary->modalias)); /* Use provided chip-select for ancillary device */ - ancillary->chip_select = chip_select; + spi_set_chipselect(ancillary, 0, chip_select); /* Take over SPI mode/speed from SPI main device */ ancillary->max_speed_hz = spi->max_speed_hz; @@ -2652,7 +2667,7 @@ struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, spi->mode |= lookup.mode; spi->irq = lookup.irq; spi->bits_per_word = lookup.bits_per_word; - spi->chip_select = lookup.chip_select; + spi_set_chipselect(spi, 0, lookup.chip_select); return spi; } @@ -3612,6 +3627,37 @@ static int __spi_validate_bits_per_word(struct spi_controller *ctlr, } /** + * spi_set_cs_timing - configure CS setup, hold, and inactive delays + * @spi: the device that requires specific CS timing configuration + * + * Return: zero on success, else a negative error code. + */ +static int spi_set_cs_timing(struct spi_device *spi) +{ + struct device *parent = spi->controller->dev.parent; + int status = 0; + + if (spi->controller->set_cs_timing && !spi_get_csgpiod(spi, 0)) { + if (spi->controller->auto_runtime_pm) { + status = pm_runtime_get_sync(parent); + if (status < 0) { + pm_runtime_put_noidle(parent); + dev_err(&spi->controller->dev, "Failed to power device: %d\n", + status); + return status; + } + + status = spi->controller->set_cs_timing(spi); + pm_runtime_mark_last_busy(parent); + pm_runtime_put_autosuspend(parent); + } else { + status = spi->controller->set_cs_timing(spi); + } + } + return status; +} + +/** * spi_setup - setup SPI mode and clock rate * @spi: the device whose settings are being modified * Context: can sleep, and no requests are queued to the device @@ -3707,6 +3753,12 @@ int spi_setup(struct spi_device *spi) } } + status = spi_set_cs_timing(spi); + if (status) { + mutex_unlock(&spi->controller->io_mutex); + return status; + } + if (spi->controller->auto_runtime_pm && spi->controller->set_cs) { status = pm_runtime_resume_and_get(spi->controller->dev.parent); if (status < 0) { @@ -3790,7 +3842,7 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) * cs_change is set for each transfer. */ if ((spi->mode & SPI_CS_WORD) && (!(ctlr->mode_bits & SPI_CS_WORD) || - spi->cs_gpiod)) { + spi_get_csgpiod(spi, 0))) { size_t maxsize; int ret; diff --git a/drivers/spmi/spmi-mtk-pmif.c b/drivers/spmi/spmi-mtk-pmif.c index ad511f2c3324..bf8c0d4109b1 100644 --- a/drivers/spmi/spmi-mtk-pmif.c +++ b/drivers/spmi/spmi-mtk-pmif.c @@ -50,6 +50,7 @@ struct pmif { struct clk_bulk_data clks[PMIF_MAX_CLKS]; size_t nclks; const struct pmif_data *data; + raw_spinlock_t lock; }; static const char * const pmif_clock_names[] = { @@ -314,6 +315,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid, struct ch_reg *inf_reg; int ret; u32 data, cmd; + unsigned long flags; /* Check for argument validation. */ if (sid & ~0xf) { @@ -334,6 +336,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid, else return -EINVAL; + raw_spin_lock_irqsave(&arb->lock, flags); /* Wait for Software Interface FSM state to be IDLE. */ inf_reg = &arb->chan; ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta], @@ -343,6 +346,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid, /* set channel ready if the data has transferred */ if (pmif_is_fsm_vldclr(arb)) pmif_writel(arb, 1, inf_reg->ch_rdy); + raw_spin_unlock_irqrestore(&arb->lock, flags); dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n"); return ret; } @@ -350,6 +354,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid, /* Send the command. */ cmd = (opc << 30) | (sid << 24) | ((len - 1) << 16) | addr; pmif_writel(arb, cmd, inf_reg->ch_send); + raw_spin_unlock_irqrestore(&arb->lock, flags); /* * Wait for Software Interface FSM state to be WFVLDCLR, @@ -376,7 +381,8 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid, struct pmif *arb = spmi_controller_get_drvdata(ctrl); struct ch_reg *inf_reg; int ret; - u32 data, cmd; + u32 data, wdata, cmd; + unsigned long flags; if (len > 4) { dev_err(&ctrl->dev, "pmif supports 1..4 bytes per trans, but:%zu requested", len); @@ -394,6 +400,10 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid, else return -EINVAL; + /* Set the write data. */ + memcpy(&wdata, buf, len); + + raw_spin_lock_irqsave(&arb->lock, flags); /* Wait for Software Interface FSM state to be IDLE. */ inf_reg = &arb->chan; ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta], @@ -403,17 +413,17 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid, /* set channel ready if the data has transferred */ if (pmif_is_fsm_vldclr(arb)) pmif_writel(arb, 1, inf_reg->ch_rdy); + raw_spin_unlock_irqrestore(&arb->lock, flags); dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n"); return ret; } - /* Set the write data. */ - memcpy(&data, buf, len); - pmif_writel(arb, data, inf_reg->wdata); + pmif_writel(arb, wdata, inf_reg->wdata); /* Send the command. */ cmd = (opc << 30) | BIT(29) | (sid << 24) | ((len - 1) << 16) | addr; pmif_writel(arb, cmd, inf_reg->ch_send); + raw_spin_unlock_irqrestore(&arb->lock, flags); return 0; } @@ -465,7 +475,7 @@ static int mtk_spmi_probe(struct platform_device *pdev) for (i = 0; i < arb->nclks; i++) arb->clks[i].id = pmif_clock_names[i]; - err = devm_clk_bulk_get(&pdev->dev, arb->nclks, arb->clks); + err = clk_bulk_get(&pdev->dev, arb->nclks, arb->clks); if (err) { dev_err(&pdev->dev, "Failed to get clocks: %d\n", err); goto err_put_ctrl; @@ -474,7 +484,7 @@ static int mtk_spmi_probe(struct platform_device *pdev) err = clk_bulk_prepare_enable(arb->nclks, arb->clks); if (err) { dev_err(&pdev->dev, "Failed to enable clocks: %d\n", err); - goto err_put_ctrl; + goto err_put_clks; } ctrl->cmd = pmif_arb_cmd; @@ -488,6 +498,8 @@ static int mtk_spmi_probe(struct platform_device *pdev) arb->chan.ch_send = PMIF_SWINF_0_ACC + chan_offset; arb->chan.ch_rdy = PMIF_SWINF_0_VLD_CLR + chan_offset; + raw_spin_lock_init(&arb->lock); + platform_set_drvdata(pdev, ctrl); err = spmi_controller_add(ctrl); @@ -498,6 +510,8 @@ static int mtk_spmi_probe(struct platform_device *pdev) err_domain_remove: clk_bulk_disable_unprepare(arb->nclks, arb->clks); +err_put_clks: + clk_bulk_put(arb->nclks, arb->clks); err_put_ctrl: spmi_controller_put(ctrl); return err; @@ -509,6 +523,7 @@ static int mtk_spmi_remove(struct platform_device *pdev) struct pmif *arb = spmi_controller_get_drvdata(ctrl); clk_bulk_disable_unprepare(arb->nclks, arb->clks); + clk_bulk_put(arb->nclks, arb->clks); spmi_controller_remove(ctrl); spmi_controller_put(ctrl); return 0; diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index f177b20f0f2d..ceba63213894 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -608,7 +608,7 @@ static void ad5933_work(struct work_struct *work) struct ad5933_state, work.work); struct iio_dev *indio_dev = i2c_get_clientdata(st->client); __be16 buf[2]; - int val[2]; + u16 val[2]; unsigned char status; int ret; diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c index a9bd1e71ea48..d16cf4115d03 100644 --- a/drivers/staging/media/rkvdec/rkvdec.c +++ b/drivers/staging/media/rkvdec/rkvdec.c @@ -461,6 +461,9 @@ static const struct v4l2_ioctl_ops rkvdec_ioctl_ops = { .vidioc_streamon = v4l2_m2m_ioctl_streamon, .vidioc_streamoff = v4l2_m2m_ioctl_streamoff, + + .vidioc_decoder_cmd = v4l2_m2m_ioctl_stateless_decoder_cmd, + .vidioc_try_decoder_cmd = v4l2_m2m_ioctl_stateless_try_decoder_cmd, }; static int rkvdec_queue_setup(struct vb2_queue *vq, unsigned int *num_buffers, diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 301fe376a120..13558cbd9b82 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -147,7 +147,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd) struct se_session *se_sess = se_cmd->se_sess; struct se_node_acl *nacl = se_sess->se_node_acl; struct se_tmr_req *se_tmr = se_cmd->se_tmr_req; - unsigned long flags; rcu_read_lock(); deve = target_nacl_find_deve(nacl, se_cmd->orig_fe_lun); @@ -178,10 +177,6 @@ out_unlock: se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev); se_tmr->tmr_dev = rcu_dereference_raw(se_lun->lun_se_dev); - spin_lock_irqsave(&se_tmr->tmr_dev->se_tmr_lock, flags); - list_add_tail(&se_tmr->tmr_list, &se_tmr->tmr_dev->dev_tmr_list); - spin_unlock_irqrestore(&se_tmr->tmr_dev->se_tmr_lock, flags); - return 0; } EXPORT_SYMBOL(transport_lookup_tmr_lun); diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 7e81a53dbf3c..8d74e97c9874 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -338,11 +338,13 @@ static int fd_do_rw(struct se_cmd *cmd, struct file *fd, } iov_iter_bvec(&iter, is_write, bvec, sgl_nents, len); - if (is_write) + if (is_write) { + file_start_write(fd); ret = vfs_iter_write(fd, &iter, &pos, 0); - else + file_end_write(fd); + } else { ret = vfs_iter_read(fd, &iter, &pos, 0); - + } if (is_write) { if (ret < 0 || ret != data_length) { pr_err("%s() write returned %d\n", __func__, ret); @@ -474,7 +476,9 @@ fd_execute_write_same(struct se_cmd *cmd) } iov_iter_bvec(&iter, ITER_SOURCE, bvec, nolb, len); + file_start_write(fd_dev->fd_file); ret = vfs_iter_write(fd_dev->fd_file, &iter, &pos, 0); + file_end_write(fd_dev->fd_file); kfree(bvec); if (ret < 0 || ret != len) { diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 69a4c9581e80..7aec34c09066 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -910,12 +910,15 @@ new_bio: return 0; fail: - if (bio) - bio_put(bio); + if (bio) { + bio_uninit(bio); + kfree(bio); + } while (req->bio) { bio = req->bio; req->bio = bio->bi_next; - bio_put(bio); + bio_uninit(bio); + kfree(bio); } req->biotail = NULL; return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 0686882bcbda..fb93d74c5d0b 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -3627,6 +3627,10 @@ int transport_generic_handle_tmr( unsigned long flags; bool aborted = false; + spin_lock_irqsave(&cmd->se_dev->se_tmr_lock, flags); + list_add_tail(&cmd->se_tmr_req->tmr_list, &cmd->se_dev->dev_tmr_list); + spin_unlock_irqrestore(&cmd->se_dev->se_tmr_lock, flags); + spin_lock_irqsave(&cmd->t_state_lock, flags); if (cmd->transport_state & CMD_T_ABORTED) { aborted = true; diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c index a0640f762dc5..750dab3f259e 100644 --- a/drivers/thermal/intel/intel_hfi.c +++ b/drivers/thermal/intel/intel_hfi.c @@ -24,6 +24,7 @@ #include <linux/bitops.h> #include <linux/cpufeature.h> #include <linux/cpumask.h> +#include <linux/delay.h> #include <linux/gfp.h> #include <linux/io.h> #include <linux/kernel.h> @@ -34,7 +35,9 @@ #include <linux/processor.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/suspend.h> #include <linux/string.h> +#include <linux/syscore_ops.h> #include <linux/topology.h> #include <linux/workqueue.h> @@ -338,6 +341,52 @@ static void init_hfi_instance(struct hfi_instance *hfi_instance) hfi_instance->data = hfi_instance->hdr + hfi_features.hdr_size; } +/* Caller must hold hfi_instance_lock. */ +static void hfi_enable(void) +{ + u64 msr_val; + + rdmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val); + msr_val |= HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT; + wrmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val); +} + +static void hfi_set_hw_table(struct hfi_instance *hfi_instance) +{ + phys_addr_t hw_table_pa; + u64 msr_val; + + hw_table_pa = virt_to_phys(hfi_instance->hw_table); + msr_val = hw_table_pa | HW_FEEDBACK_PTR_VALID_BIT; + wrmsrl(MSR_IA32_HW_FEEDBACK_PTR, msr_val); +} + +/* Caller must hold hfi_instance_lock. */ +static void hfi_disable(void) +{ + u64 msr_val; + int i; + + rdmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val); + msr_val &= ~HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT; + wrmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val); + + /* + * Wait for hardware to acknowledge the disabling of HFI. Some + * processors may not do it. Wait for ~2ms. This is a reasonable + * time for hardware to complete any pending actions on the HFI + * memory. + */ + for (i = 0; i < 2000; i++) { + rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val); + if (msr_val & PACKAGE_THERM_STATUS_HFI_UPDATED) + break; + + udelay(1); + cpu_relax(); + } +} + /** * intel_hfi_online() - Enable HFI on @cpu * @cpu: CPU in which the HFI will be enabled @@ -355,8 +404,6 @@ void intel_hfi_online(unsigned int cpu) { struct hfi_instance *hfi_instance; struct hfi_cpu_info *info; - phys_addr_t hw_table_pa; - u64 msr_val; u16 die_id; /* Nothing to do if hfi_instances are missing. */ @@ -394,14 +441,16 @@ void intel_hfi_online(unsigned int cpu) /* * Hardware is programmed with the physical address of the first page * frame of the table. Hence, the allocated memory must be page-aligned. + * + * Some processors do not forget the initial address of the HFI table + * even after having been reprogrammed. Keep using the same pages. Do + * not free them. */ hfi_instance->hw_table = alloc_pages_exact(hfi_features.nr_table_pages, GFP_KERNEL | __GFP_ZERO); if (!hfi_instance->hw_table) goto unlock; - hw_table_pa = virt_to_phys(hfi_instance->hw_table); - /* * Allocate memory to keep a local copy of the table that * hardware generates. @@ -411,16 +460,6 @@ void intel_hfi_online(unsigned int cpu) if (!hfi_instance->local_table) goto free_hw_table; - /* - * Program the address of the feedback table of this die/package. On - * some processors, hardware remembers the old address of the HFI table - * even after having been reprogrammed and re-enabled. Thus, do not free - * the pages allocated for the table or reprogram the hardware with a - * new base address. Namely, program the hardware only once. - */ - msr_val = hw_table_pa | HW_FEEDBACK_PTR_VALID_BIT; - wrmsrl(MSR_IA32_HW_FEEDBACK_PTR, msr_val); - init_hfi_instance(hfi_instance); INIT_DELAYED_WORK(&hfi_instance->update_work, hfi_update_work_fn); @@ -429,13 +468,8 @@ void intel_hfi_online(unsigned int cpu) cpumask_set_cpu(cpu, hfi_instance->cpus); - /* - * Enable the hardware feedback interface and never disable it. See - * comment on programming the address of the table. - */ - rdmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val); - msr_val |= HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT; - wrmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val); + hfi_set_hw_table(hfi_instance); + hfi_enable(); unlock: mutex_unlock(&hfi_instance_lock); @@ -475,6 +509,10 @@ void intel_hfi_offline(unsigned int cpu) mutex_lock(&hfi_instance_lock); cpumask_clear_cpu(cpu, hfi_instance->cpus); + + if (!cpumask_weight(hfi_instance->cpus)) + hfi_disable(); + mutex_unlock(&hfi_instance_lock); } @@ -523,6 +561,30 @@ static __init int hfi_parse_features(void) return 0; } +static void hfi_do_enable(void) +{ + /* This code runs only on the boot CPU. */ + struct hfi_cpu_info *info = &per_cpu(hfi_cpu_info, 0); + struct hfi_instance *hfi_instance = info->hfi_instance; + + /* No locking needed. There is no concurrency with CPU online. */ + hfi_set_hw_table(hfi_instance); + hfi_enable(); +} + +static int hfi_do_disable(void) +{ + /* No locking needed. There is no concurrency with CPU offline. */ + hfi_disable(); + + return 0; +} + +static struct syscore_ops hfi_pm_ops = { + .resume = hfi_do_enable, + .suspend = hfi_do_disable, +}; + void __init intel_hfi_init(void) { struct hfi_instance *hfi_instance; @@ -554,6 +616,8 @@ void __init intel_hfi_init(void) if (!hfi_updates_wq) goto err_nomem; + register_syscore_ops(&hfi_pm_ops); + return; err_nomem: diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index d89f92032c1c..f691bce5c147 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -943,7 +943,7 @@ static void margining_port_remove(struct tb_port *port) snprintf(dir_name, sizeof(dir_name), "port%d", port->port); parent = debugfs_lookup(dir_name, port->sw->debugfs_dir); if (parent) - debugfs_remove_recursive(debugfs_lookup("margining", parent)); + debugfs_lookup_and_remove("margining", parent); kfree(port->usb4->margining); port->usb4->margining = NULL; diff --git a/drivers/tty/serial/8250/8250_bcm2835aux.c b/drivers/tty/serial/8250/8250_bcm2835aux.c index 15a2387a5b25..4f4502fb5454 100644 --- a/drivers/tty/serial/8250/8250_bcm2835aux.c +++ b/drivers/tty/serial/8250/8250_bcm2835aux.c @@ -119,6 +119,8 @@ static int bcm2835aux_serial_probe(struct platform_device *pdev) /* get the clock - this also enables the HW */ data->clk = devm_clk_get_optional(&pdev->dev, NULL); + if (IS_ERR(data->clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(data->clk), "could not get clk\n"); /* get the interrupt */ ret = platform_get_irq(pdev, 0); diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index b406cba10b0e..dca1abe36324 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -442,7 +442,7 @@ static int generic_rs485_config(struct uart_port *port, struct ktermios *termios } static const struct serial_rs485 generic_rs485_supported = { - .flags = SER_RS485_ENABLED, + .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND, }; static const struct exar8250_platform exar8250_default_platform = { @@ -486,7 +486,8 @@ static int iot2040_rs485_config(struct uart_port *port, struct ktermios *termios } static const struct serial_rs485 iot2040_rs485_supported = { - .flags = SER_RS485_ENABLED | SER_RS485_RX_DURING_TX | SER_RS485_TERMINATE_BUS, + .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | + SER_RS485_RX_DURING_TX | SER_RS485_TERMINATE_BUS, }; static const struct property_entry iot2040_gpio_properties[] = { diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 0b9c47172bc8..15e50fe40e4b 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -1521,7 +1521,7 @@ static int omap8250_remove(struct platform_device *pdev) err = pm_runtime_resume_and_get(&pdev->dev); if (err) - return err; + dev_err(&pdev->dev, "Failed to resume hardware\n"); serial8250_unregister_port(priv->line); priv->line = -ENODEV; diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index c74eaf2552c3..2f0f05259778 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1345,11 +1345,41 @@ static void pl011_start_tx_pio(struct uart_amba_port *uap) } } +static void pl011_rs485_tx_start(struct uart_amba_port *uap) +{ + struct uart_port *port = &uap->port; + u32 cr; + + /* Enable transmitter */ + cr = pl011_read(uap, REG_CR); + cr |= UART011_CR_TXE; + + /* Disable receiver if half-duplex */ + if (!(port->rs485.flags & SER_RS485_RX_DURING_TX)) + cr &= ~UART011_CR_RXE; + + if (port->rs485.flags & SER_RS485_RTS_ON_SEND) + cr &= ~UART011_CR_RTS; + else + cr |= UART011_CR_RTS; + + pl011_write(cr, uap, REG_CR); + + if (port->rs485.delay_rts_before_send) + mdelay(port->rs485.delay_rts_before_send); + + uap->rs485_tx_started = true; +} + static void pl011_start_tx(struct uart_port *port) { struct uart_amba_port *uap = container_of(port, struct uart_amba_port, port); + if ((uap->port.rs485.flags & SER_RS485_ENABLED) && + !uap->rs485_tx_started) + pl011_rs485_tx_start(uap); + if (!pl011_dma_tx_start(uap)) pl011_start_tx_pio(uap); } @@ -1431,42 +1461,12 @@ static bool pl011_tx_char(struct uart_amba_port *uap, unsigned char c, return true; } -static void pl011_rs485_tx_start(struct uart_amba_port *uap) -{ - struct uart_port *port = &uap->port; - u32 cr; - - /* Enable transmitter */ - cr = pl011_read(uap, REG_CR); - cr |= UART011_CR_TXE; - - /* Disable receiver if half-duplex */ - if (!(port->rs485.flags & SER_RS485_RX_DURING_TX)) - cr &= ~UART011_CR_RXE; - - if (port->rs485.flags & SER_RS485_RTS_ON_SEND) - cr &= ~UART011_CR_RTS; - else - cr |= UART011_CR_RTS; - - pl011_write(cr, uap, REG_CR); - - if (port->rs485.delay_rts_before_send) - mdelay(port->rs485.delay_rts_before_send); - - uap->rs485_tx_started = true; -} - /* Returns true if tx interrupts have to be (kept) enabled */ static bool pl011_tx_chars(struct uart_amba_port *uap, bool from_irq) { struct circ_buf *xmit = &uap->port.state->xmit; int count = uap->fifosize >> 1; - if ((uap->port.rs485.flags & SER_RS485_ENABLED) && - !uap->rs485_tx_started) - pl011_rs485_tx_start(uap); - if (uap->port.x_char) { if (!pl011_tx_char(uap, uap->port.x_char, from_irq)) return true; diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index d2137f6eff32..f8962a3d4421 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -450,13 +450,13 @@ static void imx_uart_stop_tx(struct uart_port *port) ucr1 = imx_uart_readl(sport, UCR1); imx_uart_writel(sport, ucr1 & ~UCR1_TRDYEN, UCR1); + ucr4 = imx_uart_readl(sport, UCR4); usr2 = imx_uart_readl(sport, USR2); - if (!(usr2 & USR2_TXDC)) { + if ((!(usr2 & USR2_TXDC)) && (ucr4 & UCR4_TCEN)) { /* The shifter is still busy, so retry once TC triggers */ return; } - ucr4 = imx_uart_readl(sport, UCR4); ucr4 &= ~UCR4_TCEN; imx_uart_writel(sport, ucr4, UCR4); @@ -2229,7 +2229,6 @@ static enum hrtimer_restart imx_trigger_stop_tx(struct hrtimer *t) return HRTIMER_NORESTART; } -static const struct serial_rs485 imx_no_rs485 = {}; /* No RS485 if no RTS */ static const struct serial_rs485 imx_rs485_supported = { .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND | SER_RS485_RX_DURING_TX, @@ -2319,8 +2318,6 @@ static int imx_uart_probe(struct platform_device *pdev) /* RTS is required to control the RS485 transmitter */ if (sport->have_rtscts || sport->have_rtsgpio) sport->port.rs485_supported = imx_rs485_supported; - else - sport->port.rs485_supported = imx_no_rs485; sport->port.flags = UPF_BOOT_AUTOCONF; timer_setup(&sport->timer, imx_uart_timeout, 0); @@ -2347,7 +2344,7 @@ static int imx_uart_probe(struct platform_device *pdev) /* For register access, we only need to enable the ipg clock. */ ret = clk_prepare_enable(sport->clk_ipg); if (ret) { - dev_err(&pdev->dev, "failed to enable per clk: %d\n", ret); + dev_err(&pdev->dev, "failed to enable ipg clk: %d\n", ret); return ret; } @@ -2359,14 +2356,8 @@ static int imx_uart_probe(struct platform_device *pdev) sport->ufcr = readl(sport->port.membase + UFCR); ret = uart_get_rs485_mode(&sport->port); - if (ret) { - clk_disable_unprepare(sport->clk_ipg); - return ret; - } - - if (sport->port.rs485.flags & SER_RS485_ENABLED && - (!sport->have_rtscts && !sport->have_rtsgpio)) - dev_err(&pdev->dev, "no RTS control, disabling rs485\n"); + if (ret) + goto err_clk; /* * If using the i.MX UART RTS/CTS control then the RTS (CTS_B) @@ -2446,8 +2437,6 @@ static int imx_uart_probe(struct platform_device *pdev) imx_uart_writel(sport, ucr3, UCR3); } - clk_disable_unprepare(sport->clk_ipg); - hrtimer_init(&sport->trigger_start_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer_init(&sport->trigger_stop_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sport->trigger_start_tx.function = imx_trigger_start_tx; @@ -2463,7 +2452,7 @@ static int imx_uart_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to request rx irq: %d\n", ret); - return ret; + goto err_clk; } ret = devm_request_irq(&pdev->dev, txirq, imx_uart_txint, 0, @@ -2471,7 +2460,7 @@ static int imx_uart_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to request tx irq: %d\n", ret); - return ret; + goto err_clk; } ret = devm_request_irq(&pdev->dev, rtsirq, imx_uart_rtsint, 0, @@ -2479,14 +2468,14 @@ static int imx_uart_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to request rts irq: %d\n", ret); - return ret; + goto err_clk; } } else { ret = devm_request_irq(&pdev->dev, rxirq, imx_uart_int, 0, dev_name(&pdev->dev), sport); if (ret) { dev_err(&pdev->dev, "failed to request irq: %d\n", ret); - return ret; + goto err_clk; } } @@ -2494,7 +2483,12 @@ static int imx_uart_probe(struct platform_device *pdev) platform_set_drvdata(pdev, sport); - return uart_add_one_port(&imx_uart_uart_driver, &sport->port); + ret = uart_add_one_port(&imx_uart_uart_driver, &sport->port); + +err_clk: + clk_disable_unprepare(sport->clk_ipg); + + return ret; } static int imx_uart_remove(struct platform_device *pdev) diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 338cb19dec23..163a89f84c9c 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -237,6 +237,14 @@ #define MAX310x_REV_MASK (0xf8) #define MAX310X_WRITE_BIT 0x80 +/* Port startup definitions */ +#define MAX310X_PORT_STARTUP_WAIT_RETRIES 20 /* Number of retries */ +#define MAX310X_PORT_STARTUP_WAIT_DELAY_MS 10 /* Delay between retries */ + +/* Crystal-related definitions */ +#define MAX310X_XTAL_WAIT_RETRIES 20 /* Number of retries */ +#define MAX310X_XTAL_WAIT_DELAY_MS 10 /* Delay between retries */ + /* MAX3107 specific */ #define MAX3107_REV_ID (0xa0) @@ -583,7 +591,7 @@ static int max310x_update_best_err(unsigned long f, long *besterr) return 1; } -static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s, +static s32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s, unsigned long freq, bool xtal) { unsigned int div, clksrc, pllcfg = 0; @@ -641,12 +649,20 @@ static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s, /* Wait for crystal */ if (xtal) { - unsigned int val; - msleep(10); - regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val); - if (!(val & MAX310X_STS_CLKREADY_BIT)) { - dev_warn(dev, "clock is not stable yet\n"); - } + bool stable = false; + unsigned int try = 0, val = 0; + + do { + msleep(MAX310X_XTAL_WAIT_DELAY_MS); + regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val); + + if (val & MAX310X_STS_CLKREADY_BIT) + stable = true; + } while (!stable && (++try < MAX310X_XTAL_WAIT_RETRIES)); + + if (!stable) + return dev_err_probe(dev, -EAGAIN, + "clock is not stable\n"); } return bestfreq; @@ -1274,7 +1290,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty { int i, ret, fmin, fmax, freq; struct max310x_port *s; - u32 uartclk = 0; + s32 uartclk = 0; bool xtal; for (i = 0; i < devtype->nr; i++) @@ -1337,6 +1353,9 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty goto out_clk; for (i = 0; i < devtype->nr; i++) { + bool started = false; + unsigned int try = 0, val = 0; + /* Reset port */ regmap_write(regmaps[i], MAX310X_MODE2_REG, MAX310X_MODE2_RST_BIT); @@ -1345,13 +1364,27 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty /* Wait for port startup */ do { - regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &ret); - } while (ret != 0x01); + msleep(MAX310X_PORT_STARTUP_WAIT_DELAY_MS); + regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &val); + + if (val == 0x01) + started = true; + } while (!started && (++try < MAX310X_PORT_STARTUP_WAIT_RETRIES)); + + if (!started) { + ret = dev_err_probe(dev, -EAGAIN, "port reset failed\n"); + goto out_uart; + } regmap_write(regmaps[i], MAX310X_MODE1_REG, devtype->mode1); } uartclk = max310x_set_ref_clk(dev, s, freq, xtal); + if (uartclk < 0) { + ret = uartclk; + goto out_uart; + } + dev_dbg(dev, "Reference clock set to %i Hz\n", uartclk); for (i = 0; i < devtype->nr; i++) { diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 7d0d2718ef59..beb7896ebf8a 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1512,6 +1512,13 @@ static struct omap_uart_port_info *of_get_uart_port_info(struct device *dev) return omap_up_info; } +static const struct serial_rs485 serial_omap_rs485_supported = { + .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND | + SER_RS485_RX_DURING_TX, + .delay_rts_before_send = 1, + .delay_rts_after_send = 1, +}; + static int serial_omap_probe_rs485(struct uart_omap_port *up, struct device *dev) { @@ -1526,6 +1533,9 @@ static int serial_omap_probe_rs485(struct uart_omap_port *up, if (!np) return 0; + up->port.rs485_config = serial_omap_config_rs485; + up->port.rs485_supported = serial_omap_rs485_supported; + ret = uart_get_rs485_mode(&up->port); if (ret) return ret; @@ -1560,13 +1570,6 @@ static int serial_omap_probe_rs485(struct uart_omap_port *up, return 0; } -static const struct serial_rs485 serial_omap_rs485_supported = { - .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND | - SER_RS485_RX_DURING_TX, - .delay_rts_before_send = 1, - .delay_rts_after_send = 1, -}; - static int serial_omap_probe(struct platform_device *pdev) { struct omap_uart_port_info *omap_up_info = dev_get_platdata(&pdev->dev); @@ -1634,17 +1637,11 @@ static int serial_omap_probe(struct platform_device *pdev) dev_info(up->port.dev, "no wakeirq for uart%d\n", up->port.line); - ret = serial_omap_probe_rs485(up, &pdev->dev); - if (ret < 0) - goto err_rs485; - sprintf(up->name, "OMAP UART%d", up->port.line); up->port.mapbase = mem->start; up->port.membase = base; up->port.flags = omap_up_info->flags; up->port.uartclk = omap_up_info->uartclk; - up->port.rs485_config = serial_omap_config_rs485; - up->port.rs485_supported = serial_omap_rs485_supported; if (!up->port.uartclk) { up->port.uartclk = DEFAULT_CLK_SPEED; dev_warn(&pdev->dev, @@ -1652,6 +1649,10 @@ static int serial_omap_probe(struct platform_device *pdev) DEFAULT_CLK_SPEED); } + ret = serial_omap_probe_rs485(up, &pdev->dev); + if (ret < 0) + goto err_rs485; + up->latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE; up->calc_latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE; cpu_latency_qos_add_request(&up->pm_qos_request, up->latency); diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index b4b849415c50..e331b57d6d7d 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -24,6 +24,7 @@ #include <linux/tty_flip.h> #include <linux/spi/spi.h> #include <linux/uaccess.h> +#include <linux/units.h> #include <uapi/linux/sched/types.h> #define SC16IS7XX_NAME "sc16is7xx" @@ -300,8 +301,8 @@ /* Misc definitions */ +#define SC16IS7XX_SPI_READ_BIT BIT(7) #define SC16IS7XX_FIFO_SIZE (64) -#define SC16IS7XX_REG_SHIFT 2 #define SC16IS7XX_GPIOS_PER_BANK 4 struct sc16is7xx_devtype { @@ -322,7 +323,8 @@ struct sc16is7xx_one_config { struct sc16is7xx_one { struct uart_port port; - u8 line; + struct regmap *regmap; + struct mutex efr_lock; /* EFR registers access */ struct kthread_work tx_work; struct kthread_work reg_work; struct kthread_delayed_work ms_work; @@ -333,7 +335,6 @@ struct sc16is7xx_one { struct sc16is7xx_port { const struct sc16is7xx_devtype *devtype; - struct regmap *regmap; struct clk *clk; #ifdef CONFIG_GPIOLIB struct gpio_chip gpio; @@ -343,7 +344,6 @@ struct sc16is7xx_port { unsigned char buf[SC16IS7XX_FIFO_SIZE]; struct kthread_worker kworker; struct task_struct *kworker_task; - struct mutex efr_lock; struct sc16is7xx_one p[]; }; @@ -361,48 +361,35 @@ static void sc16is7xx_stop_tx(struct uart_port *port); #define to_sc16is7xx_port(p,e) ((container_of((p), struct sc16is7xx_port, e))) #define to_sc16is7xx_one(p,e) ((container_of((p), struct sc16is7xx_one, e))) -static int sc16is7xx_line(struct uart_port *port) -{ - struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); - - return one->line; -} - static u8 sc16is7xx_port_read(struct uart_port *port, u8 reg) { - struct sc16is7xx_port *s = dev_get_drvdata(port->dev); + struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); unsigned int val = 0; - const u8 line = sc16is7xx_line(port); - regmap_read(s->regmap, (reg << SC16IS7XX_REG_SHIFT) | line, &val); + regmap_read(one->regmap, reg, &val); return val; } static void sc16is7xx_port_write(struct uart_port *port, u8 reg, u8 val) { - struct sc16is7xx_port *s = dev_get_drvdata(port->dev); - const u8 line = sc16is7xx_line(port); + struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); - regmap_write(s->regmap, (reg << SC16IS7XX_REG_SHIFT) | line, val); + regmap_write(one->regmap, reg, val); } static void sc16is7xx_fifo_read(struct uart_port *port, unsigned int rxlen) { struct sc16is7xx_port *s = dev_get_drvdata(port->dev); - const u8 line = sc16is7xx_line(port); - u8 addr = (SC16IS7XX_RHR_REG << SC16IS7XX_REG_SHIFT) | line; + struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); - regcache_cache_bypass(s->regmap, true); - regmap_raw_read(s->regmap, addr, s->buf, rxlen); - regcache_cache_bypass(s->regmap, false); + regmap_noinc_read(one->regmap, SC16IS7XX_RHR_REG, s->buf, rxlen); } static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send) { struct sc16is7xx_port *s = dev_get_drvdata(port->dev); - const u8 line = sc16is7xx_line(port); - u8 addr = (SC16IS7XX_THR_REG << SC16IS7XX_REG_SHIFT) | line; + struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); /* * Don't send zero-length data, at least on SPI it confuses the chip @@ -411,32 +398,15 @@ static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send) if (unlikely(!to_send)) return; - regcache_cache_bypass(s->regmap, true); - regmap_raw_write(s->regmap, addr, s->buf, to_send); - regcache_cache_bypass(s->regmap, false); + regmap_noinc_write(one->regmap, SC16IS7XX_THR_REG, s->buf, to_send); } static void sc16is7xx_port_update(struct uart_port *port, u8 reg, u8 mask, u8 val) { - struct sc16is7xx_port *s = dev_get_drvdata(port->dev); - const u8 line = sc16is7xx_line(port); - - regmap_update_bits(s->regmap, (reg << SC16IS7XX_REG_SHIFT) | line, - mask, val); -} - -static int sc16is7xx_alloc_line(void) -{ - int i; - - BUILD_BUG_ON(SC16IS7XX_MAX_DEVS > BITS_PER_LONG); - - for (i = 0; i < SC16IS7XX_MAX_DEVS; i++) - if (!test_and_set_bit(i, &sc16is7xx_lines)) - break; + struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); - return i; + regmap_update_bits(one->regmap, reg, mask, val); } static void sc16is7xx_power(struct uart_port *port, int on) @@ -478,7 +448,7 @@ static const struct sc16is7xx_devtype sc16is762_devtype = { static bool sc16is7xx_regmap_volatile(struct device *dev, unsigned int reg) { - switch (reg >> SC16IS7XX_REG_SHIFT) { + switch (reg) { case SC16IS7XX_RHR_REG: case SC16IS7XX_IIR_REG: case SC16IS7XX_LSR_REG: @@ -497,7 +467,7 @@ static bool sc16is7xx_regmap_volatile(struct device *dev, unsigned int reg) static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg) { - switch (reg >> SC16IS7XX_REG_SHIFT) { + switch (reg) { case SC16IS7XX_RHR_REG: return true; default: @@ -507,9 +477,14 @@ static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg) return false; } +static bool sc16is7xx_regmap_noinc(struct device *dev, unsigned int reg) +{ + return reg == SC16IS7XX_RHR_REG; +} + static int sc16is7xx_set_baud(struct uart_port *port, int baud) { - struct sc16is7xx_port *s = dev_get_drvdata(port->dev); + struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); u8 lcr; u8 prescaler = 0; unsigned long clk = port->uartclk, div = clk / 16 / baud; @@ -532,7 +507,7 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud) * because the bulk of the interrupt processing is run as a workqueue * job in thread context. */ - mutex_lock(&s->efr_lock); + mutex_lock(&one->efr_lock); lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG); @@ -541,17 +516,17 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud) SC16IS7XX_LCR_CONF_MODE_B); /* Enable enhanced features */ - regcache_cache_bypass(s->regmap, true); + regcache_cache_bypass(one->regmap, true); sc16is7xx_port_update(port, SC16IS7XX_EFR_REG, SC16IS7XX_EFR_ENABLE_BIT, SC16IS7XX_EFR_ENABLE_BIT); - regcache_cache_bypass(s->regmap, false); + regcache_cache_bypass(one->regmap, false); /* Put LCR back to the normal mode */ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr); - mutex_unlock(&s->efr_lock); + mutex_unlock(&one->efr_lock); sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_CLKSEL_BIT, @@ -562,10 +537,10 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud) SC16IS7XX_LCR_CONF_MODE_A); /* Write the new divisor */ - regcache_cache_bypass(s->regmap, true); + regcache_cache_bypass(one->regmap, true); sc16is7xx_port_write(port, SC16IS7XX_DLH_REG, div / 256); sc16is7xx_port_write(port, SC16IS7XX_DLL_REG, div % 256); - regcache_cache_bypass(s->regmap, false); + regcache_cache_bypass(one->regmap, false); /* Put LCR back to the normal mode */ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr); @@ -666,9 +641,9 @@ static void sc16is7xx_handle_tx(struct uart_port *port) } if (uart_circ_empty(xmit) || uart_tx_stopped(port)) { - spin_lock_irqsave(&port->lock, flags); + uart_port_lock_irqsave(port, &flags); sc16is7xx_stop_tx(port); - spin_unlock_irqrestore(&port->lock, flags); + uart_port_unlock_irqrestore(port, flags); return; } @@ -697,13 +672,15 @@ static void sc16is7xx_handle_tx(struct uart_port *port) sc16is7xx_fifo_write(port, to_send); } - spin_lock_irqsave(&port->lock, flags); + uart_port_lock_irqsave(port, &flags); if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) uart_write_wakeup(port); if (uart_circ_empty(xmit)) sc16is7xx_stop_tx(port); - spin_unlock_irqrestore(&port->lock, flags); + else + sc16is7xx_ier_set(port, SC16IS7XX_IER_THRI_BIT); + uart_port_unlock_irqrestore(port, flags); } static unsigned int sc16is7xx_get_hwmctrl(struct uart_port *port) @@ -721,11 +698,10 @@ static unsigned int sc16is7xx_get_hwmctrl(struct uart_port *port) static void sc16is7xx_update_mlines(struct sc16is7xx_one *one) { struct uart_port *port = &one->port; - struct sc16is7xx_port *s = dev_get_drvdata(port->dev); unsigned long flags; unsigned int status, changed; - lockdep_assert_held_once(&s->efr_lock); + lockdep_assert_held_once(&one->efr_lock); status = sc16is7xx_get_hwmctrl(port); changed = status ^ one->old_mctrl; @@ -735,7 +711,7 @@ static void sc16is7xx_update_mlines(struct sc16is7xx_one *one) one->old_mctrl = status; - spin_lock_irqsave(&port->lock, flags); + uart_port_lock_irqsave(port, &flags); if ((changed & TIOCM_RNG) && (status & TIOCM_RNG)) port->icount.rng++; if (changed & TIOCM_DSR) @@ -746,79 +722,82 @@ static void sc16is7xx_update_mlines(struct sc16is7xx_one *one) uart_handle_cts_change(port, status & TIOCM_CTS); wake_up_interruptible(&port->state->port.delta_msr_wait); - spin_unlock_irqrestore(&port->lock, flags); + uart_port_unlock_irqrestore(port, flags); } static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno) { + bool rc = true; + unsigned int iir, rxlen; struct uart_port *port = &s->p[portno].port; + struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); - do { - unsigned int iir, rxlen; - struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); - - iir = sc16is7xx_port_read(port, SC16IS7XX_IIR_REG); - if (iir & SC16IS7XX_IIR_NO_INT_BIT) - return false; - - iir &= SC16IS7XX_IIR_ID_MASK; - - switch (iir) { - case SC16IS7XX_IIR_RDI_SRC: - case SC16IS7XX_IIR_RLSE_SRC: - case SC16IS7XX_IIR_RTOI_SRC: - case SC16IS7XX_IIR_XOFFI_SRC: - rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG); - - /* - * There is a silicon bug that makes the chip report a - * time-out interrupt but no data in the FIFO. This is - * described in errata section 18.1.4. - * - * When this happens, read one byte from the FIFO to - * clear the interrupt. - */ - if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen) - rxlen = 1; - - if (rxlen) - sc16is7xx_handle_rx(port, rxlen, iir); - break; + mutex_lock(&one->efr_lock); + + iir = sc16is7xx_port_read(port, SC16IS7XX_IIR_REG); + if (iir & SC16IS7XX_IIR_NO_INT_BIT) { + rc = false; + goto out_port_irq; + } + + iir &= SC16IS7XX_IIR_ID_MASK; + + switch (iir) { + case SC16IS7XX_IIR_RDI_SRC: + case SC16IS7XX_IIR_RLSE_SRC: + case SC16IS7XX_IIR_RTOI_SRC: + case SC16IS7XX_IIR_XOFFI_SRC: + rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG); + + /* + * There is a silicon bug that makes the chip report a + * time-out interrupt but no data in the FIFO. This is + * described in errata section 18.1.4. + * + * When this happens, read one byte from the FIFO to + * clear the interrupt. + */ + if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen) + rxlen = 1; + + if (rxlen) + sc16is7xx_handle_rx(port, rxlen, iir); + break; /* CTSRTS interrupt comes only when CTS goes inactive */ - case SC16IS7XX_IIR_CTSRTS_SRC: - case SC16IS7XX_IIR_MSI_SRC: - sc16is7xx_update_mlines(one); - break; - case SC16IS7XX_IIR_THRI_SRC: - sc16is7xx_handle_tx(port); - break; - default: - dev_err_ratelimited(port->dev, - "ttySC%i: Unexpected interrupt: %x", - port->line, iir); - break; - } - } while (0); - return true; + case SC16IS7XX_IIR_CTSRTS_SRC: + case SC16IS7XX_IIR_MSI_SRC: + sc16is7xx_update_mlines(one); + break; + case SC16IS7XX_IIR_THRI_SRC: + sc16is7xx_handle_tx(port); + break; + default: + dev_err_ratelimited(port->dev, + "ttySC%i: Unexpected interrupt: %x", + port->line, iir); + break; + } + +out_port_irq: + mutex_unlock(&one->efr_lock); + + return rc; } static irqreturn_t sc16is7xx_irq(int irq, void *dev_id) { - struct sc16is7xx_port *s = (struct sc16is7xx_port *)dev_id; + bool keep_polling; - mutex_lock(&s->efr_lock); + struct sc16is7xx_port *s = (struct sc16is7xx_port *)dev_id; - while (1) { - bool keep_polling = false; + do { int i; + keep_polling = false; + for (i = 0; i < s->devtype->nr_uart; ++i) keep_polling |= sc16is7xx_port_irq(s, i); - if (!keep_polling) - break; - } - - mutex_unlock(&s->efr_lock); + } while (keep_polling); return IRQ_HANDLED; } @@ -826,20 +805,15 @@ static irqreturn_t sc16is7xx_irq(int irq, void *dev_id) static void sc16is7xx_tx_proc(struct kthread_work *ws) { struct uart_port *port = &(to_sc16is7xx_one(ws, tx_work)->port); - struct sc16is7xx_port *s = dev_get_drvdata(port->dev); - unsigned long flags; + struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); if ((port->rs485.flags & SER_RS485_ENABLED) && (port->rs485.delay_rts_before_send > 0)) msleep(port->rs485.delay_rts_before_send); - mutex_lock(&s->efr_lock); + mutex_lock(&one->efr_lock); sc16is7xx_handle_tx(port); - mutex_unlock(&s->efr_lock); - - spin_lock_irqsave(&port->lock, flags); - sc16is7xx_ier_set(port, SC16IS7XX_IER_THRI_BIT); - spin_unlock_irqrestore(&port->lock, flags); + mutex_unlock(&one->efr_lock); } static void sc16is7xx_reconf_rs485(struct uart_port *port) @@ -850,14 +824,14 @@ static void sc16is7xx_reconf_rs485(struct uart_port *port) struct serial_rs485 *rs485 = &port->rs485; unsigned long irqflags; - spin_lock_irqsave(&port->lock, irqflags); + uart_port_lock_irqsave(port, &irqflags); if (rs485->flags & SER_RS485_ENABLED) { efcr |= SC16IS7XX_EFCR_AUTO_RS485_BIT; if (rs485->flags & SER_RS485_RTS_AFTER_SEND) efcr |= SC16IS7XX_EFCR_RTS_INVERT_BIT; } - spin_unlock_irqrestore(&port->lock, irqflags); + uart_port_unlock_irqrestore(port, irqflags); sc16is7xx_port_update(port, SC16IS7XX_EFCR_REG, mask, efcr); } @@ -868,10 +842,10 @@ static void sc16is7xx_reg_proc(struct kthread_work *ws) struct sc16is7xx_one_config config; unsigned long irqflags; - spin_lock_irqsave(&one->port.lock, irqflags); + uart_port_lock_irqsave(&one->port, &irqflags); config = one->config; memset(&one->config, 0, sizeof(one->config)); - spin_unlock_irqrestore(&one->port.lock, irqflags); + uart_port_unlock_irqrestore(&one->port, irqflags); if (config.flags & SC16IS7XX_RECONF_MD) { u8 mcr = 0; @@ -942,9 +916,9 @@ static void sc16is7xx_ms_proc(struct kthread_work *ws) struct sc16is7xx_port *s = dev_get_drvdata(one->port.dev); if (one->port.state) { - mutex_lock(&s->efr_lock); + mutex_lock(&one->efr_lock); sc16is7xx_update_mlines(one); - mutex_unlock(&s->efr_lock); + mutex_unlock(&one->efr_lock); kthread_queue_delayed_work(&s->kworker, &one->ms_work, HZ); } @@ -977,18 +951,18 @@ static void sc16is7xx_throttle(struct uart_port *port) * value set in MCR register. Stop reading data from RX FIFO so the * AutoRTS feature will de-activate RTS output. */ - spin_lock_irqsave(&port->lock, flags); + uart_port_lock_irqsave(port, &flags); sc16is7xx_ier_clear(port, SC16IS7XX_IER_RDI_BIT); - spin_unlock_irqrestore(&port->lock, flags); + uart_port_unlock_irqrestore(port, flags); } static void sc16is7xx_unthrottle(struct uart_port *port) { unsigned long flags; - spin_lock_irqsave(&port->lock, flags); + uart_port_lock_irqsave(port, &flags); sc16is7xx_ier_set(port, SC16IS7XX_IER_RDI_BIT); - spin_unlock_irqrestore(&port->lock, flags); + uart_port_unlock_irqrestore(port, flags); } static unsigned int sc16is7xx_tx_empty(struct uart_port *port) @@ -1028,7 +1002,6 @@ static void sc16is7xx_set_termios(struct uart_port *port, struct ktermios *termios, const struct ktermios *old) { - struct sc16is7xx_port *s = dev_get_drvdata(port->dev); struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); unsigned int lcr, flow = 0; int baud; @@ -1087,13 +1060,13 @@ static void sc16is7xx_set_termios(struct uart_port *port, port->ignore_status_mask |= SC16IS7XX_LSR_BRK_ERROR_MASK; /* As above, claim the mutex while accessing the EFR. */ - mutex_lock(&s->efr_lock); + mutex_lock(&one->efr_lock); sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_CONF_MODE_B); /* Configure flow control */ - regcache_cache_bypass(s->regmap, true); + regcache_cache_bypass(one->regmap, true); sc16is7xx_port_write(port, SC16IS7XX_XON1_REG, termios->c_cc[VSTART]); sc16is7xx_port_write(port, SC16IS7XX_XOFF1_REG, termios->c_cc[VSTOP]); @@ -1112,12 +1085,12 @@ static void sc16is7xx_set_termios(struct uart_port *port, SC16IS7XX_EFR_REG, SC16IS7XX_EFR_FLOWCTRL_BITS, flow); - regcache_cache_bypass(s->regmap, false); + regcache_cache_bypass(one->regmap, false); /* Update LCR register */ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr); - mutex_unlock(&s->efr_lock); + mutex_unlock(&one->efr_lock); /* Get baud rate generator configuration */ baud = uart_get_baud_rate(port, termios, old, @@ -1127,7 +1100,7 @@ static void sc16is7xx_set_termios(struct uart_port *port, /* Setup baudrate generator */ baud = sc16is7xx_set_baud(port, baud); - spin_lock_irqsave(&port->lock, flags); + uart_port_lock_irqsave(port, &flags); /* Update timeout according to new baud rate */ uart_update_timeout(port, termios->c_cflag, baud); @@ -1135,7 +1108,7 @@ static void sc16is7xx_set_termios(struct uart_port *port, if (UART_ENABLE_MS(port, termios->c_cflag)) sc16is7xx_enable_ms(port); - spin_unlock_irqrestore(&port->lock, flags); + uart_port_unlock_irqrestore(port, flags); } static int sc16is7xx_config_rs485(struct uart_port *port, struct ktermios *termios, @@ -1163,7 +1136,6 @@ static int sc16is7xx_config_rs485(struct uart_port *port, struct ktermios *termi static int sc16is7xx_startup(struct uart_port *port) { struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); - struct sc16is7xx_port *s = dev_get_drvdata(port->dev); unsigned int val; unsigned long flags; @@ -1180,7 +1152,7 @@ static int sc16is7xx_startup(struct uart_port *port) sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_CONF_MODE_B); - regcache_cache_bypass(s->regmap, true); + regcache_cache_bypass(one->regmap, true); /* Enable write access to enhanced features and internal clock div */ sc16is7xx_port_update(port, SC16IS7XX_EFR_REG, @@ -1198,7 +1170,7 @@ static int sc16is7xx_startup(struct uart_port *port) SC16IS7XX_TCR_RX_RESUME(24) | SC16IS7XX_TCR_RX_HALT(48)); - regcache_cache_bypass(s->regmap, false); + regcache_cache_bypass(one->regmap, false); /* Now, initialize the UART */ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_WORD_LEN_8); @@ -1222,9 +1194,9 @@ static int sc16is7xx_startup(struct uart_port *port) sc16is7xx_port_write(port, SC16IS7XX_IER_REG, val); /* Enable modem status polling */ - spin_lock_irqsave(&port->lock, flags); + uart_port_lock_irqsave(port, &flags); sc16is7xx_enable_ms(port); - spin_unlock_irqrestore(&port->lock, flags); + uart_port_unlock_irqrestore(port, flags); return 0; } @@ -1426,7 +1398,8 @@ static int sc16is7xx_setup_gpio_chip(struct sc16is7xx_port *s) /* * Configure ports designated to operate as modem control lines. */ -static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s) +static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s, + struct regmap *regmap) { int i; int ret; @@ -1455,8 +1428,8 @@ static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s) if (s->mctrl_mask) regmap_update_bits( - s->regmap, - SC16IS7XX_IOCONTROL_REG << SC16IS7XX_REG_SHIFT, + regmap, + SC16IS7XX_IOCONTROL_REG, SC16IS7XX_IOCONTROL_MODEM_A_BIT | SC16IS7XX_IOCONTROL_MODEM_B_BIT, s->mctrl_mask); @@ -1471,7 +1444,7 @@ static const struct serial_rs485 sc16is7xx_rs485_supported = { static int sc16is7xx_probe(struct device *dev, const struct sc16is7xx_devtype *devtype, - struct regmap *regmap, int irq) + struct regmap *regmaps[], int irq) { unsigned long freq = 0, *pfreq = dev_get_platdata(dev); unsigned int val; @@ -1479,16 +1452,20 @@ static int sc16is7xx_probe(struct device *dev, int i, ret; struct sc16is7xx_port *s; - if (IS_ERR(regmap)) - return PTR_ERR(regmap); + for (i = 0; i < devtype->nr_uart; i++) + if (IS_ERR(regmaps[i])) + return PTR_ERR(regmaps[i]); /* * This device does not have an identification register that would * tell us if we are really connected to the correct device. * The best we can do is to check if communication is at all possible. + * + * Note: regmap[0] is used in the probe function to access registers + * common to all channels/ports, as it is guaranteed to be present on + * all variants. */ - ret = regmap_read(regmap, - SC16IS7XX_LSR_REG << SC16IS7XX_REG_SHIFT, &val); + ret = regmap_read(regmaps[0], SC16IS7XX_LSR_REG, &val); if (ret < 0) return -EPROBE_DEFER; @@ -1522,10 +1499,8 @@ static int sc16is7xx_probe(struct device *dev, return -EINVAL; } - s->regmap = regmap; s->devtype = devtype; dev_set_drvdata(dev, s); - mutex_init(&s->efr_lock); kthread_init_worker(&s->kworker); s->kworker_task = kthread_run(kthread_worker_fn, &s->kworker, @@ -1537,11 +1512,17 @@ static int sc16is7xx_probe(struct device *dev, sched_set_fifo(s->kworker_task); /* reset device, purging any pending irq / data */ - regmap_write(s->regmap, SC16IS7XX_IOCONTROL_REG << SC16IS7XX_REG_SHIFT, - SC16IS7XX_IOCONTROL_SRESET_BIT); + regmap_write(regmaps[0], SC16IS7XX_IOCONTROL_REG, + SC16IS7XX_IOCONTROL_SRESET_BIT); for (i = 0; i < devtype->nr_uart; ++i) { - s->p[i].line = i; + s->p[i].port.line = find_first_zero_bit(&sc16is7xx_lines, + SC16IS7XX_MAX_DEVS); + if (s->p[i].port.line >= SC16IS7XX_MAX_DEVS) { + ret = -ERANGE; + goto out_ports; + } + /* Initialize port data */ s->p[i].port.dev = dev; s->p[i].port.irq = irq; @@ -1561,12 +1542,9 @@ static int sc16is7xx_probe(struct device *dev, s->p[i].port.rs485_supported = sc16is7xx_rs485_supported; s->p[i].port.ops = &sc16is7xx_ops; s->p[i].old_mctrl = 0; - s->p[i].port.line = sc16is7xx_alloc_line(); + s->p[i].regmap = regmaps[i]; - if (s->p[i].port.line >= SC16IS7XX_MAX_DEVS) { - ret = -ENOMEM; - goto out_ports; - } + mutex_init(&s->p[i].efr_lock); ret = uart_get_rs485_mode(&s->p[i].port); if (ret) @@ -1583,20 +1561,25 @@ static int sc16is7xx_probe(struct device *dev, kthread_init_work(&s->p[i].tx_work, sc16is7xx_tx_proc); kthread_init_work(&s->p[i].reg_work, sc16is7xx_reg_proc); kthread_init_delayed_work(&s->p[i].ms_work, sc16is7xx_ms_proc); + /* Register port */ - uart_add_one_port(&sc16is7xx_uart, &s->p[i].port); + ret = uart_add_one_port(&sc16is7xx_uart, &s->p[i].port); + if (ret) + goto out_ports; + + set_bit(s->p[i].port.line, &sc16is7xx_lines); /* Enable EFR */ sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_CONF_MODE_B); - regcache_cache_bypass(s->regmap, true); + regcache_cache_bypass(regmaps[i], true); /* Enable write access to enhanced features */ sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_EFR_REG, SC16IS7XX_EFR_ENABLE_BIT); - regcache_cache_bypass(s->regmap, false); + regcache_cache_bypass(regmaps[i], false); /* Restore access to general registers */ sc16is7xx_port_write(&s->p[i].port, SC16IS7XX_LCR_REG, 0x00); @@ -1616,7 +1599,7 @@ static int sc16is7xx_probe(struct device *dev, s->p[u].irda_mode = true; } - ret = sc16is7xx_setup_mctrl_ports(s); + ret = sc16is7xx_setup_mctrl_ports(s, regmaps[0]); if (ret) goto out_ports; @@ -1651,10 +1634,9 @@ static int sc16is7xx_probe(struct device *dev, #endif out_ports: - for (i--; i >= 0; i--) { - uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port); - clear_bit(s->p[i].port.line, &sc16is7xx_lines); - } + for (i = 0; i < devtype->nr_uart; i++) + if (test_and_clear_bit(s->p[i].port.line, &sc16is7xx_lines)) + uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port); kthread_stop(s->kworker_task); @@ -1676,8 +1658,8 @@ static void sc16is7xx_remove(struct device *dev) for (i = 0; i < s->devtype->nr_uart; i++) { kthread_cancel_delayed_work_sync(&s->p[i].ms_work); - uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port); - clear_bit(s->p[i].port.line, &sc16is7xx_lines); + if (test_and_clear_bit(s->p[i].port.line, &sc16is7xx_lines)) + uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port); sc16is7xx_power(&s->p[i].port, 0); } @@ -1699,26 +1681,52 @@ static const struct of_device_id __maybe_unused sc16is7xx_dt_ids[] = { MODULE_DEVICE_TABLE(of, sc16is7xx_dt_ids); static struct regmap_config regcfg = { - .reg_bits = 7, - .pad_bits = 1, + .reg_bits = 5, + .pad_bits = 3, .val_bits = 8, .cache_type = REGCACHE_RBTREE, .volatile_reg = sc16is7xx_regmap_volatile, .precious_reg = sc16is7xx_regmap_precious, + .writeable_noinc_reg = sc16is7xx_regmap_noinc, + .readable_noinc_reg = sc16is7xx_regmap_noinc, + .max_raw_read = SC16IS7XX_FIFO_SIZE, + .max_raw_write = SC16IS7XX_FIFO_SIZE, + .max_register = SC16IS7XX_EFCR_REG, }; +static const char *sc16is7xx_regmap_name(u8 port_id) +{ + switch (port_id) { + case 0: return "port0"; + case 1: return "port1"; + default: + WARN_ON(true); + return NULL; + } +} + +static unsigned int sc16is7xx_regmap_port_mask(unsigned int port_id) +{ + /* CH1,CH0 are at bits 2:1. */ + return port_id << 1; +} + #ifdef CONFIG_SERIAL_SC16IS7XX_SPI static int sc16is7xx_spi_probe(struct spi_device *spi) { const struct sc16is7xx_devtype *devtype; - struct regmap *regmap; + struct regmap *regmaps[2]; + unsigned int i; int ret; /* Setup SPI bus */ spi->bits_per_word = 8; - /* only supports mode 0 on SC16IS762 */ + /* For all variants, only mode 0 is supported */ + if ((spi->mode & SPI_MODE_X_MASK) != SPI_MODE_0) + return dev_err_probe(&spi->dev, -EINVAL, "Unsupported SPI mode\n"); + spi->mode = spi->mode ? : SPI_MODE_0; - spi->max_speed_hz = spi->max_speed_hz ? : 15000000; + spi->max_speed_hz = spi->max_speed_hz ? : 4 * HZ_PER_MHZ; ret = spi_setup(spi); if (ret) return ret; @@ -1733,11 +1741,20 @@ static int sc16is7xx_spi_probe(struct spi_device *spi) devtype = (struct sc16is7xx_devtype *)id_entry->driver_data; } - regcfg.max_register = (0xf << SC16IS7XX_REG_SHIFT) | - (devtype->nr_uart - 1); - regmap = devm_regmap_init_spi(spi, ®cfg); + for (i = 0; i < devtype->nr_uart; i++) { + regcfg.name = sc16is7xx_regmap_name(i); + /* + * If read_flag_mask is 0, the regmap code sets it to a default + * of 0x80. Since we specify our own mask, we must add the READ + * bit ourselves: + */ + regcfg.read_flag_mask = sc16is7xx_regmap_port_mask(i) | + SC16IS7XX_SPI_READ_BIT; + regcfg.write_flag_mask = sc16is7xx_regmap_port_mask(i); + regmaps[i] = devm_regmap_init_spi(spi, ®cfg); + } - return sc16is7xx_probe(&spi->dev, devtype, regmap, spi->irq); + return sc16is7xx_probe(&spi->dev, devtype, regmaps, spi->irq); } static void sc16is7xx_spi_remove(struct spi_device *spi) @@ -1776,7 +1793,8 @@ static int sc16is7xx_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { const struct sc16is7xx_devtype *devtype; - struct regmap *regmap; + struct regmap *regmaps[2]; + unsigned int i; if (i2c->dev.of_node) { devtype = device_get_match_data(&i2c->dev); @@ -1786,11 +1804,14 @@ static int sc16is7xx_i2c_probe(struct i2c_client *i2c, devtype = (struct sc16is7xx_devtype *)id->driver_data; } - regcfg.max_register = (0xf << SC16IS7XX_REG_SHIFT) | - (devtype->nr_uart - 1); - regmap = devm_regmap_init_i2c(i2c, ®cfg); + for (i = 0; i < devtype->nr_uart; i++) { + regcfg.name = sc16is7xx_regmap_name(i); + regcfg.read_flag_mask = sc16is7xx_regmap_port_mask(i); + regcfg.write_flag_mask = sc16is7xx_regmap_port_mask(i); + regmaps[i] = devm_regmap_init_i2c(i2c, ®cfg); + } - return sc16is7xx_probe(&i2c->dev, devtype, regmap, i2c->irq); + return sc16is7xx_probe(&i2c->dev, devtype, regmaps, i2c->irq); } static void sc16is7xx_i2c_remove(struct i2c_client *client) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index d4e57f9017db..f0ed30d0a697 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1353,19 +1353,27 @@ static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs4 return; } + rs485->flags &= supported_flags; + /* Pick sane settings if the user hasn't */ - if ((supported_flags & (SER_RS485_RTS_ON_SEND|SER_RS485_RTS_AFTER_SEND)) && - !(rs485->flags & SER_RS485_RTS_ON_SEND) == + if (!(rs485->flags & SER_RS485_RTS_ON_SEND) == !(rs485->flags & SER_RS485_RTS_AFTER_SEND)) { - dev_warn_ratelimited(port->dev, - "%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n", - port->name, port->line); - rs485->flags |= SER_RS485_RTS_ON_SEND; - rs485->flags &= ~SER_RS485_RTS_AFTER_SEND; - supported_flags |= SER_RS485_RTS_ON_SEND|SER_RS485_RTS_AFTER_SEND; - } + if (supported_flags & SER_RS485_RTS_ON_SEND) { + rs485->flags |= SER_RS485_RTS_ON_SEND; + rs485->flags &= ~SER_RS485_RTS_AFTER_SEND; - rs485->flags &= supported_flags; + dev_warn_ratelimited(port->dev, + "%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n", + port->name, port->line); + } else { + rs485->flags |= SER_RS485_RTS_AFTER_SEND; + rs485->flags &= ~SER_RS485_RTS_ON_SEND; + + dev_warn_ratelimited(port->dev, + "%s (%d): invalid RTS setting, using RTS_AFTER_SEND instead\n", + port->name, port->line); + } + } uart_sanitize_serial_rs485_delays(port, rs485); @@ -1428,7 +1436,7 @@ static int uart_set_rs485_config(struct tty_struct *tty, struct uart_port *port, int ret; unsigned long flags; - if (!port->rs485_config) + if (!(port->rs485_supported.flags & SER_RS485_ENABLED)) return -ENOTTY; if (copy_from_user(&rs485, rs485_user, sizeof(*rs485_user))) @@ -3420,6 +3428,9 @@ int uart_get_rs485_mode(struct uart_port *port) u32 rs485_delay[2]; int ret; + if (!(port->rs485_supported.flags & SER_RS485_ENABLED)) + return 0; + ret = device_property_read_u32_array(dev, "rs485-rts-delay", rs485_delay, 2); if (!ret) { diff --git a/drivers/tty/tty.h b/drivers/tty/tty.h index c5ee21912755..91515e1ebc8d 100644 --- a/drivers/tty/tty.h +++ b/drivers/tty/tty.h @@ -63,7 +63,7 @@ int tty_check_change(struct tty_struct *tty); void __stop_tty(struct tty_struct *tty); void __start_tty(struct tty_struct *tty); void tty_write_unlock(struct tty_struct *tty); -int tty_write_lock(struct tty_struct *tty, int ndelay); +int tty_write_lock(struct tty_struct *tty, bool ndelay); void tty_vhangup_session(struct tty_struct *tty); void tty_open_proc_set_tty(struct file *filp, struct tty_struct *tty); int tty_signal_session_leader(struct tty_struct *tty, int exit_session); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 8fb6c6853556..aaf77a5616ff 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -939,7 +939,7 @@ void tty_write_unlock(struct tty_struct *tty) wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT); } -int tty_write_lock(struct tty_struct *tty, int ndelay) +int tty_write_lock(struct tty_struct *tty, bool ndelay) { if (!mutex_trylock(&tty->atomic_write_lock)) { if (ndelay) @@ -1153,7 +1153,7 @@ int tty_send_xchar(struct tty_struct *tty, char ch) return 0; } - if (tty_write_lock(tty, 0) < 0) + if (tty_write_lock(tty, false) < 0) return -ERESTARTSYS; down_read(&tty->termios_rwsem); @@ -2472,22 +2472,25 @@ static int send_break(struct tty_struct *tty, unsigned int duration) return 0; if (tty->driver->flags & TTY_DRIVER_HARDWARE_BREAK) - retval = tty->ops->break_ctl(tty, duration); - else { - /* Do the work ourselves */ - if (tty_write_lock(tty, 0) < 0) - return -EINTR; - retval = tty->ops->break_ctl(tty, -1); - if (retval) - goto out; - if (!signal_pending(current)) - msleep_interruptible(duration); + return tty->ops->break_ctl(tty, duration); + + /* Do the work ourselves */ + if (tty_write_lock(tty, false) < 0) + return -EINTR; + + retval = tty->ops->break_ctl(tty, -1); + if (!retval) { + msleep_interruptible(duration); retval = tty->ops->break_ctl(tty, 0); -out: - tty_write_unlock(tty); - if (signal_pending(current)) - retval = -EINTR; + } else if (retval == -EOPNOTSUPP) { + /* some drivers can tell only dynamically */ + retval = 0; } + tty_write_unlock(tty); + + if (signal_pending(current)) + retval = -EINTR; + return retval; } diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index ad1cf51ecd11..9d3b237304ea 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -506,7 +506,7 @@ retry_write_wait: if (retval < 0) return retval; - if (tty_write_lock(tty, 0) < 0) + if (tty_write_lock(tty, false) < 0) goto retry_write_wait; /* Racing writer? */ @@ -859,7 +859,7 @@ int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) ret = -EFAULT; return ret; case TIOCSLCKTRMIOS: - if (!capable(CAP_SYS_ADMIN)) + if (!checkpoint_restore_ns_capable(&init_user_ns)) return -EPERM; copy_termios_locked(real_tty, &kterm); if (user_termios_to_kernel_termios(&kterm, @@ -876,7 +876,7 @@ int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) ret = -EFAULT; return ret; case TIOCSLCKTRMIOS: - if (!capable(CAP_SYS_ADMIN)) + if (!checkpoint_restore_ns_capable(&init_user_ns)) return -EPERM; copy_termios_locked(real_tty, &kterm); if (user_termios_to_kernel_termios_1(&kterm, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index dc38d1fa7787..f3c25467e571 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -6159,7 +6159,6 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba) ufshcd_hold(hba, false); if (!ufshcd_is_clkgating_allowed(hba)) ufshcd_setup_clocks(hba, true); - ufshcd_release(hba); pm_op = hba->is_sys_suspended ? UFS_SYSTEM_PM : UFS_RUNTIME_PM; ufshcd_vops_resume(hba, pm_op); } else { @@ -8204,7 +8203,6 @@ static int ufshcd_add_lus(struct ufs_hba *hba) ufs_bsg_probe(hba); ufshpb_init(hba); scsi_scan_host(hba->host); - pm_runtime_put_sync(hba->dev); out: return ret; @@ -8331,15 +8329,12 @@ static void ufshcd_async_scan(void *data, async_cookie_t cookie) /* Probe and add UFS logical units */ ret = ufshcd_add_lus(hba); + out: - /* - * If we failed to initialize the device or the device is not - * present, turn off the power/clocks etc. - */ - if (ret) { - pm_runtime_put_sync(hba->dev); - ufshcd_hba_exit(hba); - } + pm_runtime_put_sync(hba->dev); + + if (ret) + dev_err(hba->dev, "%s failed: %d\n", __func__, ret); } static const struct attribute_group *ufshcd_driver_groups[] = { diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 43afbb7c5ab9..e55e8cef8def 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -466,13 +466,13 @@ static int uio_open(struct inode *inode, struct file *filep) mutex_lock(&minor_lock); idev = idr_find(&uio_idr, iminor(inode)); - mutex_unlock(&minor_lock); if (!idev) { ret = -ENODEV; + mutex_unlock(&minor_lock); goto out; } - get_device(&idev->dev); + mutex_unlock(&minor_lock); if (!try_module_get(idev->owner)) { ret = -ENODEV; @@ -1064,9 +1064,8 @@ void uio_unregister_device(struct uio_info *info) wake_up_interruptible(&idev->wait); kill_fasync(&idev->async_queue, SIGIO, POLL_HUP); - device_unregister(&idev->dev); - uio_free_minor(minor); + device_unregister(&idev->dev); return; } diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index 88c83d25a412..9a0c4cf8162d 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -828,7 +828,11 @@ void cdns3_gadget_giveback(struct cdns3_endpoint *priv_ep, return; } - if (request->complete) { + /* + * zlp request is appended by driver, needn't call usb_gadget_giveback_request() to notify + * gadget composite driver. + */ + if (request->complete && request->buf != priv_dev->zlp_buf) { spin_unlock(&priv_dev->lock); usb_gadget_giveback_request(&priv_ep->endpoint, request); @@ -1119,6 +1123,8 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, dma_addr_t trb_dma; u32 togle_pcs = 1; int sg_iter = 0; + int num_trb_req; + int trb_burst; int num_trb; int address; u32 control; @@ -1127,15 +1133,13 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, struct scatterlist *s = NULL; bool sg_supported = !!(request->num_mapped_sgs); + num_trb_req = sg_supported ? request->num_mapped_sgs : 1; + + /* ISO transfer require each SOF have a TD, each TD include some TRBs */ if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) - num_trb = priv_ep->interval; + num_trb = priv_ep->interval * num_trb_req; else - num_trb = sg_supported ? request->num_mapped_sgs : 1; - - if (num_trb > priv_ep->free_trbs) { - priv_ep->flags |= EP_RING_FULL; - return -ENOBUFS; - } + num_trb = num_trb_req; priv_req = to_cdns3_request(request); address = priv_ep->endpoint.desc->bEndpointAddress; @@ -1184,14 +1188,31 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, link_trb->control = cpu_to_le32(((priv_ep->pcs) ? TRB_CYCLE : 0) | TRB_TYPE(TRB_LINK) | TRB_TOGGLE | ch_bit); + + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) { + /* + * ISO require LINK TRB must be first one of TD. + * Fill LINK TRBs for left trb space to simply software process logic. + */ + while (priv_ep->enqueue) { + *trb = *link_trb; + trace_cdns3_prepare_trb(priv_ep, trb); + + cdns3_ep_inc_enq(priv_ep); + trb = priv_ep->trb_pool + priv_ep->enqueue; + priv_req->trb = trb; + } + } + } + + if (num_trb > priv_ep->free_trbs) { + priv_ep->flags |= EP_RING_FULL; + return -ENOBUFS; } if (priv_dev->dev_ver <= DEV_VER_V2) togle_pcs = cdns3_wa1_update_guard(priv_ep, trb); - if (sg_supported) - s = request->sg; - /* set incorrect Cycle Bit for first trb*/ control = priv_ep->pcs ? 0 : TRB_CYCLE; trb->length = 0; @@ -1209,6 +1230,9 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, do { u32 length; + if (!(sg_iter % num_trb_req) && sg_supported) + s = request->sg; + /* fill TRB */ control |= TRB_TYPE(TRB_NORMAL); if (sg_supported) { @@ -1223,7 +1247,36 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, total_tdl += DIV_ROUND_UP(length, priv_ep->endpoint.maxpacket); - trb->length |= cpu_to_le32(TRB_BURST_LEN(priv_ep->trb_burst_size) | + trb_burst = priv_ep->trb_burst_size; + + /* + * Supposed DMA cross 4k bounder problem should be fixed at DEV_VER_V2, but still + * met problem when do ISO transfer if sg enabled. + * + * Data pattern likes below when sg enabled, package size is 1k and mult is 2 + * [UVC Header(8B) ] [data(3k - 8)] ... + * + * The received data at offset 0xd000 will get 0xc000 data, len 0x70. Error happen + * as below pattern: + * 0xd000: wrong + * 0xe000: wrong + * 0xf000: correct + * 0x10000: wrong + * 0x11000: wrong + * 0x12000: correct + * ... + * + * But it is still unclear about why error have not happen below 0xd000, it should + * cross 4k bounder. But anyway, the below code can fix this problem. + * + * To avoid DMA cross 4k bounder at ISO transfer, reduce burst len according to 16. + */ + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && priv_dev->dev_ver <= DEV_VER_V2) + if (ALIGN_DOWN(trb->buffer, SZ_4K) != + ALIGN_DOWN(trb->buffer + length, SZ_4K)) + trb_burst = 16; + + trb->length |= cpu_to_le32(TRB_BURST_LEN(trb_burst) | TRB_LEN(length)); pcs = priv_ep->pcs ? TRB_CYCLE : 0; @@ -1250,7 +1303,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, if (sg_supported) { trb->control |= cpu_to_le32(TRB_ISP); /* Don't set chain bit for last TRB */ - if (sg_iter < num_trb - 1) + if ((sg_iter % num_trb_req) < num_trb_req - 1) trb->control |= cpu_to_le32(TRB_CHAIN); s = sg_next(s); @@ -1508,6 +1561,12 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev, /* The TRB was changed as link TRB, and the request was handled at ep_dequeue */ while (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) { + + /* ISO ep_traddr may stop at LINK TRB */ + if (priv_ep->dequeue == cdns3_get_dma_pos(priv_dev, priv_ep) && + priv_ep->type == USB_ENDPOINT_XFER_ISOC) + break; + trace_cdns3_complete_trb(priv_ep, trb); cdns3_ep_inc_deq(priv_ep); trb = priv_ep->trb_pool + priv_ep->dequeue; @@ -1540,6 +1599,10 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev, } if (request_handled) { + /* TRBs are duplicated by priv_ep->interval time for ISO IN */ + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && priv_ep->dir) + request->actual /= priv_ep->interval; + cdns3_gadget_giveback(priv_ep, priv_req, 0); request_handled = false; transfer_end = false; @@ -2035,11 +2098,10 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) bool is_iso_ep = (priv_ep->type == USB_ENDPOINT_XFER_ISOC); struct cdns3_device *priv_dev = priv_ep->cdns3_dev; u32 bEndpointAddress = priv_ep->num | priv_ep->dir; - u32 max_packet_size = 0; - u8 maxburst = 0; + u32 max_packet_size = priv_ep->wMaxPacketSize; + u8 maxburst = priv_ep->bMaxBurst; u32 ep_cfg = 0; u8 buffering; - u8 mult = 0; int ret; buffering = priv_dev->ep_buf_size - 1; @@ -2061,8 +2123,7 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) break; default: ep_cfg = EP_CFG_EPTYPE(USB_ENDPOINT_XFER_ISOC); - mult = priv_dev->ep_iso_burst - 1; - buffering = mult + 1; + buffering = (priv_ep->bMaxBurst + 1) * (priv_ep->mult + 1) - 1; } switch (priv_dev->gadget.speed) { @@ -2073,17 +2134,8 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) max_packet_size = is_iso_ep ? 1024 : 512; break; case USB_SPEED_SUPER: - /* It's limitation that driver assumes in driver. */ - mult = 0; - max_packet_size = 1024; - if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) { - maxburst = priv_dev->ep_iso_burst - 1; - buffering = (mult + 1) * - (maxburst + 1); - - if (priv_ep->interval > 1) - buffering++; - } else { + if (priv_ep->type != USB_ENDPOINT_XFER_ISOC) { + max_packet_size = 1024; maxburst = priv_dev->ep_buf_size - 1; } break; @@ -2112,7 +2164,6 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) if (priv_dev->dev_ver < DEV_VER_V2) priv_ep->trb_burst_size = 16; - mult = min_t(u8, mult, EP_CFG_MULT_MAX); buffering = min_t(u8, buffering, EP_CFG_BUFFERING_MAX); maxburst = min_t(u8, maxburst, EP_CFG_MAXBURST_MAX); @@ -2146,7 +2197,7 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) } ep_cfg |= EP_CFG_MAXPKTSIZE(max_packet_size) | - EP_CFG_MULT(mult) | + EP_CFG_MULT(priv_ep->mult) | /* must match EP setting */ EP_CFG_BUFFERING(buffering) | EP_CFG_MAXBURST(maxburst); @@ -2236,6 +2287,13 @@ usb_ep *cdns3_gadget_match_ep(struct usb_gadget *gadget, priv_ep->type = usb_endpoint_type(desc); priv_ep->flags |= EP_CLAIMED; priv_ep->interval = desc->bInterval ? BIT(desc->bInterval - 1) : 0; + priv_ep->wMaxPacketSize = usb_endpoint_maxp(desc); + priv_ep->mult = USB_EP_MAXP_MULT(priv_ep->wMaxPacketSize); + priv_ep->wMaxPacketSize &= USB_ENDPOINT_MAXP_MASK; + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && comp_desc) { + priv_ep->mult = USB_SS_MULT(comp_desc->bmAttributes) - 1; + priv_ep->bMaxBurst = comp_desc->bMaxBurst; + } spin_unlock_irqrestore(&priv_dev->lock, flags); return &priv_ep->endpoint; @@ -2485,11 +2543,11 @@ static int cdns3_gadget_ep_disable(struct usb_ep *ep) while (!list_empty(&priv_ep->wa2_descmiss_req_list)) { priv_req = cdns3_next_priv_request(&priv_ep->wa2_descmiss_req_list); + list_del_init(&priv_req->list); kfree(priv_req->request.buf); cdns3_gadget_ep_free_request(&priv_ep->endpoint, &priv_req->request); - list_del_init(&priv_req->list); --priv_ep->wa2_counter; } @@ -3019,22 +3077,40 @@ static int cdns3_gadget_check_config(struct usb_gadget *gadget) struct cdns3_endpoint *priv_ep; struct usb_ep *ep; int n_in = 0; + int iso = 0; + int out = 1; int total; + int n; list_for_each_entry(ep, &gadget->ep_list, ep_list) { priv_ep = ep_to_cdns3_ep(ep); - if ((priv_ep->flags & EP_CLAIMED) && (ep->address & USB_DIR_IN)) - n_in++; + if (!(priv_ep->flags & EP_CLAIMED)) + continue; + + n = (priv_ep->mult + 1) * (priv_ep->bMaxBurst + 1); + if (ep->address & USB_DIR_IN) { + /* + * ISO transfer: DMA start move data when get ISO, only transfer + * data as min(TD size, iso). No benefit for allocate bigger + * internal memory than 'iso'. + */ + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) + iso += n; + else + n_in++; + } else { + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) + out = max_t(int, out, n); + } } /* 2KB are reserved for EP0, 1KB for out*/ - total = 2 + n_in + 1; + total = 2 + n_in + out + iso; if (total > priv_dev->onchip_buffers) return -ENOMEM; - priv_dev->ep_buf_size = priv_dev->ep_iso_burst = - (priv_dev->onchip_buffers - 2) / (n_in + 1); + priv_dev->ep_buf_size = (priv_dev->onchip_buffers - 2 - iso) / (n_in + out); return 0; } diff --git a/drivers/usb/cdns3/cdns3-gadget.h b/drivers/usb/cdns3/cdns3-gadget.h index fbe4a8e3aa89..086a7bb83897 100644 --- a/drivers/usb/cdns3/cdns3-gadget.h +++ b/drivers/usb/cdns3/cdns3-gadget.h @@ -1168,6 +1168,9 @@ struct cdns3_endpoint { u8 dir; u8 num; u8 type; + u8 mult; + u8 bMaxBurst; + u16 wMaxPacketSize; int interval; int free_trbs; diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index 7b20d2d5c262..7242591b346b 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -394,7 +394,6 @@ pm_put: return ret; } - /** * cdns_wakeup_irq - interrupt handler for wakeup events * @irq: irq number for cdns3/cdnsp core device diff --git a/drivers/usb/cdns3/drd.c b/drivers/usb/cdns3/drd.c index e57a905e2092..c646890a7dc9 100644 --- a/drivers/usb/cdns3/drd.c +++ b/drivers/usb/cdns3/drd.c @@ -156,7 +156,8 @@ bool cdns_is_device(struct cdns *cdns) */ static void cdns_otg_disable_irq(struct cdns *cdns) { - writel(0, &cdns->otg_irq_regs->ien); + if (cdns->version) + writel(0, &cdns->otg_irq_regs->ien); } /** @@ -418,15 +419,20 @@ int cdns_drd_init(struct cdns *cdns) cdns->otg_regs = (void __iomem *)&cdns->otg_v1_regs->cmd; - if (readl(&cdns->otg_cdnsp_regs->did) == OTG_CDNSP_DID) { + state = readl(&cdns->otg_cdnsp_regs->did); + + if (OTG_CDNSP_CHECK_DID(state)) { cdns->otg_irq_regs = (struct cdns_otg_irq_regs __iomem *) &cdns->otg_cdnsp_regs->ien; cdns->version = CDNSP_CONTROLLER_V2; - } else { + } else if (OTG_CDNS3_CHECK_DID(state)) { cdns->otg_irq_regs = (struct cdns_otg_irq_regs __iomem *) &cdns->otg_v1_regs->ien; writel(1, &cdns->otg_v1_regs->simulate); cdns->version = CDNS3_CONTROLLER_V1; + } else { + dev_err(cdns->dev, "not supporte DID=0x%08x\n", state); + return -EINVAL; } if (cdns->pdata && @@ -486,7 +492,6 @@ int cdns_drd_exit(struct cdns *cdns) return 0; } - /* Indicate the cdns3 core was power lost before */ bool cdns_power_is_lost(struct cdns *cdns) { diff --git a/drivers/usb/cdns3/drd.h b/drivers/usb/cdns3/drd.h index 3a7995673af4..1e2aee14d629 100644 --- a/drivers/usb/cdns3/drd.h +++ b/drivers/usb/cdns3/drd.h @@ -79,7 +79,11 @@ struct cdnsp_otg_regs { __le32 susp_timing_ctrl; }; -#define OTG_CDNSP_DID 0x0004034E +/* CDNSP driver supports 0x000403xx Cadence USB controller family. */ +#define OTG_CDNSP_CHECK_DID(did) (((did) & GENMASK(31, 8)) == 0x00040300) + +/* CDNS3 driver supports 0x000402xx Cadence USB controller family. */ +#define OTG_CDNS3_CHECK_DID(did) (((did) & GENMASK(31, 8)) == 0x00040200) /* * Common registers interface for both CDNS3 and CDNSP version of DRD. diff --git a/drivers/usb/cdns3/host.c b/drivers/usb/cdns3/host.c index 6164fc4c96a4..ceca4d839dfd 100644 --- a/drivers/usb/cdns3/host.c +++ b/drivers/usb/cdns3/host.c @@ -18,6 +18,11 @@ #include "../host/xhci.h" #include "../host/xhci-plat.h" +/* + * The XECP_PORT_CAP_REG and XECP_AUX_CTRL_REG1 exist only + * in Cadence USB3 dual-role controller, so it can't be used + * with Cadence CDNSP dual-role controller. + */ #define XECP_PORT_CAP_REG 0x8000 #define XECP_AUX_CTRL_REG1 0x8120 @@ -57,6 +62,8 @@ static const struct xhci_plat_priv xhci_plat_cdns3_xhci = { .resume_quirk = xhci_cdns3_resume_quirk, }; +static const struct xhci_plat_priv xhci_plat_cdnsp_xhci; + static int __cdns_host_init(struct cdns *cdns) { struct platform_device *xhci; @@ -81,8 +88,13 @@ static int __cdns_host_init(struct cdns *cdns) goto err1; } - cdns->xhci_plat_data = kmemdup(&xhci_plat_cdns3_xhci, - sizeof(struct xhci_plat_priv), GFP_KERNEL); + if (cdns->version < CDNSP_CONTROLLER_V2) + cdns->xhci_plat_data = kmemdup(&xhci_plat_cdns3_xhci, + sizeof(struct xhci_plat_priv), GFP_KERNEL); + else + cdns->xhci_plat_data = kmemdup(&xhci_plat_cdnsp_xhci, + sizeof(struct xhci_plat_priv), GFP_KERNEL); + if (!cdns->xhci_plat_data) { ret = -ENOMEM; goto err1; diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index b9227f41cf1c..763d6858a8e6 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -523,6 +523,13 @@ static irqreturn_t ci_irq_handler(int irq, void *data) u32 otgsc = 0; if (ci->in_lpm) { + /* + * If we already have a wakeup irq pending there, + * let's just return to wait resume finished firstly. + */ + if (ci->wakeup_int) + return IRQ_HANDLED; + disable_irq_nosync(irq); ci->wakeup_int = true; pm_runtime_get(ci->dev); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 36bf051b345b..2a7eea4e251a 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -892,6 +892,9 @@ static int acm_tty_break_ctl(struct tty_struct *tty, int state) struct acm *acm = tty->driver_data; int retval; + if (!(acm->ctrl_caps & USB_CDC_CAP_BRK)) + return -EOPNOTSUPP; + retval = acm_send_break(acm, state ? 0xffff : 0); if (retval < 0) dev_dbg(&acm->control->dev, diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index 38703781ee2d..1283c427cdf8 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -301,7 +301,7 @@ static int ulpi_register(struct device *dev, struct ulpi *ulpi) return ret; } - root = debugfs_create_dir(dev_name(dev), ulpi_root); + root = debugfs_create_dir(dev_name(&ulpi->dev), ulpi_root); debugfs_create_file("regs", 0444, root, ulpi, &ulpi_regs_fops); dev_dbg(&ulpi->dev, "registered ULPI PHY: vendor %04x, product %04x\n", diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 81c8f564cf87..d960a56b760e 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -47,12 +47,18 @@ #define USB_VENDOR_TEXAS_INSTRUMENTS 0x0451 #define USB_PRODUCT_TUSB8041_USB3 0x8140 #define USB_PRODUCT_TUSB8041_USB2 0x8142 -#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01 -#define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02 +#define USB_VENDOR_MICROCHIP 0x0424 +#define USB_PRODUCT_USB4913 0x4913 +#define USB_PRODUCT_USB4914 0x4914 +#define USB_PRODUCT_USB4915 0x4915 +#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND BIT(0) +#define HUB_QUIRK_DISABLE_AUTOSUSPEND BIT(1) +#define HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL BIT(2) #define USB_TP_TRANSMISSION_DELAY 40 /* ns */ #define USB_TP_TRANSMISSION_DELAY_MAX 65535 /* ns */ #define USB_PING_RESPONSE_TIME 400 /* ns */ +#define USB_REDUCE_FRAME_INTR_BINTERVAL 9 /* Protect struct usb_device->state and ->children members * Note: Both are also protected by ->dev.sem, except that ->state can @@ -1904,6 +1910,14 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id) usb_autopm_get_interface_no_resume(intf); } + if ((id->driver_info & HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL) && + desc->endpoint[0].desc.bInterval > USB_REDUCE_FRAME_INTR_BINTERVAL) { + desc->endpoint[0].desc.bInterval = + USB_REDUCE_FRAME_INTR_BINTERVAL; + /* Tell the HCD about the interrupt ep's new bInterval */ + usb_set_interface(hdev, 0, 0); + } + if (hub_configure(hub, &desc->endpoint[0].desc) >= 0) { onboard_hub_create_pdevs(hdev, &hub->onboard_hub_devs); @@ -2375,17 +2389,25 @@ static int usb_enumerate_device_otg(struct usb_device *udev) } } else if (desc->bLength == sizeof (struct usb_otg_descriptor)) { - /* Set a_alt_hnp_support for legacy otg device */ - err = usb_control_msg(udev, - usb_sndctrlpipe(udev, 0), - USB_REQ_SET_FEATURE, 0, - USB_DEVICE_A_ALT_HNP_SUPPORT, - 0, NULL, 0, - USB_CTRL_SET_TIMEOUT); - if (err < 0) - dev_err(&udev->dev, - "set a_alt_hnp_support failed: %d\n", - err); + /* + * We are operating on a legacy OTP device + * These should be told that they are operating + * on the wrong port if we have another port that does + * support HNP + */ + if (bus->otg_port != 0) { + /* Set a_alt_hnp_support for legacy otg device */ + err = usb_control_msg(udev, + usb_sndctrlpipe(udev, 0), + USB_REQ_SET_FEATURE, 0, + USB_DEVICE_A_ALT_HNP_SUPPORT, + 0, NULL, 0, + USB_CTRL_SET_TIMEOUT); + if (err < 0) + dev_err(&udev->dev, + "set a_alt_hnp_support failed: %d\n", + err); + } } } #endif @@ -5885,6 +5907,21 @@ static const struct usb_device_id hub_id_table[] = { .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS, .idProduct = USB_PRODUCT_TUSB8041_USB3, .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT, + .idVendor = USB_VENDOR_MICROCHIP, + .idProduct = USB_PRODUCT_USB4913, + .driver_info = HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL}, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT, + .idVendor = USB_VENDOR_MICROCHIP, + .idProduct = USB_PRODUCT_USB4914, + .driver_info = HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL}, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT, + .idVendor = USB_VENDOR_MICROCHIP, + .idProduct = USB_PRODUCT_USB4915, + .driver_info = HUB_QUIRK_REDUCE_FRAME_INTR_BINTERVAL}, { .match_flags = USB_DEVICE_ID_MATCH_DEV_CLASS, .bDeviceClass = USB_CLASS_HUB}, { .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 586eda3408cb..3f08fe787627 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -277,48 +277,11 @@ int dwc3_core_soft_reset(struct dwc3 *dwc) /* * We're resetting only the device side because, if we're in host mode, * XHCI driver will reset the host block. If dwc3 was configured for - * host-only mode or current role is host, then we can return early. + * host-only mode, then we can return early. */ if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST) return 0; - /* - * If the dr_mode is host and the dwc->current_dr_role is not the - * corresponding DWC3_GCTL_PRTCAP_HOST, then the dwc3_core_init_mode - * isn't executed yet. Ensure the phy is ready before the controller - * updates the GCTL.PRTCAPDIR or other settings by soft-resetting - * the phy. - * - * Note: GUSB3PIPECTL[n] and GUSB2PHYCFG[n] are port settings where n - * is port index. If this is a multiport host, then we need to reset - * all active ports. - */ - if (dwc->dr_mode == USB_DR_MODE_HOST) { - u32 usb3_port; - u32 usb2_port; - - usb3_port = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); - usb3_port |= DWC3_GUSB3PIPECTL_PHYSOFTRST; - dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), usb3_port); - - usb2_port = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); - usb2_port |= DWC3_GUSB2PHYCFG_PHYSOFTRST; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), usb2_port); - - /* Small delay for phy reset assertion */ - usleep_range(1000, 2000); - - usb3_port &= ~DWC3_GUSB3PIPECTL_PHYSOFTRST; - dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), usb3_port); - - usb2_port &= ~DWC3_GUSB2PHYCFG_PHYSOFTRST; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), usb2_port); - - /* Wait for clock synchronization */ - msleep(50); - return 0; - } - reg = dwc3_readl(dwc->regs, DWC3_DCTL); reg |= DWC3_DCTL_CSFTRST; reg &= ~DWC3_DCTL_RUN_STOP; diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 61de693461da..ec3c33266547 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -236,7 +236,10 @@ void dwc3_ep0_stall_and_restart(struct dwc3 *dwc) struct dwc3_request *req; req = next_request(&dep->pending_list); - dwc3_gadget_giveback(dep, req, -ECONNRESET); + if (!dwc->connected) + dwc3_gadget_giveback(dep, req, -ESHUTDOWN); + else + dwc3_gadget_giveback(dep, req, -ECONNRESET); } dwc->eps[0]->trb_enqueue = 0; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 137602d9076f..b134110cc2ed 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -139,6 +139,24 @@ int dwc3_gadget_set_link_state(struct dwc3 *dwc, enum dwc3_link_state state) return -ETIMEDOUT; } +static void dwc3_ep0_reset_state(struct dwc3 *dwc) +{ + unsigned int dir; + + if (dwc->ep0state != EP0_SETUP_PHASE) { + dir = !!dwc->ep0_expect_in; + if (dwc->ep0state == EP0_DATA_PHASE) + dwc3_ep0_end_control_data(dwc, dwc->eps[dir]); + else + dwc3_ep0_end_control_data(dwc, dwc->eps[!dir]); + + dwc->eps[0]->trb_enqueue = 0; + dwc->eps[1]->trb_enqueue = 0; + + dwc3_ep0_stall_and_restart(dwc); + } +} + /** * dwc3_ep_inc_trb - increment a trb index. * @index: Pointer to the TRB index to increment. @@ -2075,7 +2093,17 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep, list_for_each_entry(r, &dep->pending_list, list) { if (r == req) { - dwc3_gadget_giveback(dep, req, -ECONNRESET); + /* + * Explicitly check for EP0/1 as dequeue for those + * EPs need to be handled differently. Control EP + * only deals with one USB req, and giveback will + * occur during dwc3_ep0_stall_and_restart(). EP0 + * requests are never added to started_list. + */ + if (dep->number > 1) + dwc3_gadget_giveback(dep, req, -ECONNRESET); + else + dwc3_ep0_reset_state(dwc); goto out; } } @@ -2520,6 +2548,11 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) int ret; spin_lock_irqsave(&dwc->lock, flags); + if (!dwc->pullups_connected) { + spin_unlock_irqrestore(&dwc->lock, flags); + return 0; + } + dwc->connected = false; /* @@ -2552,16 +2585,9 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) ret = wait_for_completion_timeout(&dwc->ep0_in_setup, msecs_to_jiffies(DWC3_PULL_UP_TIMEOUT)); if (ret == 0) { - unsigned int dir; - dev_warn(dwc->dev, "wait for SETUP phase timed out\n"); spin_lock_irqsave(&dwc->lock, flags); - dir = !!dwc->ep0_expect_in; - if (dwc->ep0state == EP0_DATA_PHASE) - dwc3_ep0_end_control_data(dwc, dwc->eps[dir]); - else - dwc3_ep0_end_control_data(dwc, dwc->eps[!dir]); - dwc3_ep0_stall_and_restart(dwc); + dwc3_ep0_reset_state(dwc); spin_unlock_irqrestore(&dwc->lock, flags); } } @@ -3848,16 +3874,14 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) dwc->setup_packet_pending = false; usb_gadget_set_state(dwc->gadget, USB_STATE_NOTATTACHED); - if (dwc->ep0state != EP0_SETUP_PHASE) { - unsigned int dir; + dwc3_ep0_reset_state(dwc); - dir = !!dwc->ep0_expect_in; - if (dwc->ep0state == EP0_DATA_PHASE) - dwc3_ep0_end_control_data(dwc, dwc->eps[dir]); - else - dwc3_ep0_end_control_data(dwc, dwc->eps[!dir]); - dwc3_ep0_stall_and_restart(dwc); - } + /* + * Request PM idle to address condition where usage count is + * already decremented to zero, but waiting for the disconnect + * interrupt to set dwc->connected to FALSE. + */ + pm_request_idle(dwc->dev); } static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) @@ -3913,20 +3937,7 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) * phase. So ensure that EP0 is in setup phase by issuing a stall * and restart if EP0 is not in setup phase. */ - if (dwc->ep0state != EP0_SETUP_PHASE) { - unsigned int dir; - - dir = !!dwc->ep0_expect_in; - if (dwc->ep0state == EP0_DATA_PHASE) - dwc3_ep0_end_control_data(dwc, dwc->eps[dir]); - else - dwc3_ep0_end_control_data(dwc, dwc->eps[!dir]); - - dwc->eps[0]->trb_enqueue = 0; - dwc->eps[1]->trb_enqueue = 0; - - dwc3_ep0_stall_and_restart(dwc); - } + dwc3_ep0_reset_state(dwc); /* * In the Synopsis DesignWare Cores USB3 Databook Rev. 3.30a @@ -4577,15 +4588,13 @@ int dwc3_gadget_suspend(struct dwc3 *dwc) unsigned long flags; int ret; - if (!dwc->gadget_driver) - return 0; - ret = dwc3_gadget_soft_disconnect(dwc); if (ret) goto err; spin_lock_irqsave(&dwc->lock, flags); - dwc3_disconnect_gadget(dwc); + if (dwc->gadget_driver) + dwc3_disconnect_gadget(dwc); spin_unlock_irqrestore(&dwc->lock, flags); return 0; diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c index f6f13e7f1ba1..f4d8e80c4c34 100644 --- a/drivers/usb/dwc3/host.c +++ b/drivers/usb/dwc3/host.c @@ -66,7 +66,7 @@ out: int dwc3_host_init(struct dwc3 *dwc) { - struct property_entry props[4]; + struct property_entry props[5]; struct platform_device *xhci; int ret, irq; int prop_idx = 0; @@ -94,6 +94,8 @@ int dwc3_host_init(struct dwc3 *dwc) memset(props, 0, sizeof(struct property_entry) * ARRAY_SIZE(props)); + props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-sg-trb-cache-size-quirk"); + if (dwc->usb3_lpm_capable) props[prop_idx++] = PROPERTY_ENTRY_BOOL("usb3-lpm-capable"); diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 7b9a4cf9b100..d35f30a9cae2 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -544,21 +544,37 @@ static int start_transfer(struct fsg_dev *fsg, struct usb_ep *ep, static bool start_in_transfer(struct fsg_common *common, struct fsg_buffhd *bh) { + int rc; + if (!fsg_is_set(common)) return false; bh->state = BUF_STATE_SENDING; - if (start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq)) + rc = start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq); + if (rc) { bh->state = BUF_STATE_EMPTY; + if (rc == -ESHUTDOWN) { + common->running = 0; + return false; + } + } return true; } static bool start_out_transfer(struct fsg_common *common, struct fsg_buffhd *bh) { + int rc; + if (!fsg_is_set(common)) return false; bh->state = BUF_STATE_RECEIVING; - if (start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq)) + rc = start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq); + if (rc) { bh->state = BUF_STATE_FULL; + if (rc == -ESHUTDOWN) { + common->running = 0; + return false; + } + } return true; } diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 6adf638bc51e..75e948ca5548 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1340,7 +1340,15 @@ parse_ntb: "Parsed NTB with %d frames\n", dgram_counter); to_process -= block_len; - if (to_process != 0) { + + /* + * Windows NCM driver avoids USB ZLPs by adding a 1-byte + * zero pad as needed. + */ + if (to_process == 1 && + (*(unsigned char *)(ntb_ptr + block_len) == 0x00)) { + to_process--; + } else if (to_process > 0) { ntb_ptr = (unsigned char *)(ntb_ptr + block_len); goto parse_ntb; } diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c index c4c1fbc12b4c..dc968960769e 100644 --- a/drivers/usb/host/fotg210-hcd.c +++ b/drivers/usb/host/fotg210-hcd.c @@ -429,8 +429,6 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh, temp = size; size -= temp; next += temp; - if (temp == size) - goto done; } temp = snprintf(next, size, "\n"); @@ -440,7 +438,6 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh, size -= temp; next += temp; -done: *sizep = size; *nextp = next; } diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c index a0921687444b..bb4f80627cdc 100644 --- a/drivers/usb/host/xhci-mtk.c +++ b/drivers/usb/host/xhci-mtk.c @@ -7,6 +7,7 @@ * Chunfeng Yun <chunfeng.yun@mediatek.com> */ +#include <linux/bitfield.h> #include <linux/dma-mapping.h> #include <linux/iopoll.h> #include <linux/kernel.h> @@ -73,6 +74,9 @@ #define FRMCNT_LEV1_RANG (0x12b << 8) #define FRMCNT_LEV1_RANG_MASK GENMASK(19, 8) +#define HSCH_CFG1 0x960 +#define SCH3_RXFIFO_DEPTH_MASK GENMASK(21, 20) + #define SS_GEN2_EOF_CFG 0x990 #define SSG2EOF_OFFSET 0x3c @@ -114,6 +118,8 @@ #define SSC_IP_SLEEP_EN BIT(4) #define SSC_SPM_INT_EN BIT(1) +#define SCH_FIFO_TO_KB(x) ((x) >> 10) + enum ssusb_uwk_vers { SSUSB_UWK_V1 = 1, SSUSB_UWK_V2, @@ -165,6 +171,35 @@ static void xhci_mtk_set_frame_interval(struct xhci_hcd_mtk *mtk) writel(value, hcd->regs + SS_GEN2_EOF_CFG); } +/* + * workaround: usb3.2 gen1 isoc rx hw issue + * host send out unexpected ACK afer device fininsh a burst transfer with + * a short packet. + */ +static void xhci_mtk_rxfifo_depth_set(struct xhci_hcd_mtk *mtk) +{ + struct usb_hcd *hcd = mtk->hcd; + u32 value; + + if (!mtk->rxfifo_depth) + return; + + value = readl(hcd->regs + HSCH_CFG1); + value &= ~SCH3_RXFIFO_DEPTH_MASK; + value |= FIELD_PREP(SCH3_RXFIFO_DEPTH_MASK, + SCH_FIFO_TO_KB(mtk->rxfifo_depth) - 1); + writel(value, hcd->regs + HSCH_CFG1); +} + +static void xhci_mtk_init_quirk(struct xhci_hcd_mtk *mtk) +{ + /* workaround only for mt8195 */ + xhci_mtk_set_frame_interval(mtk); + + /* workaround for SoCs using SSUSB about before IPM v1.6.0 */ + xhci_mtk_rxfifo_depth_set(mtk); +} + static int xhci_mtk_host_enable(struct xhci_hcd_mtk *mtk) { struct mu3c_ippc_regs __iomem *ippc = mtk->ippc_regs; @@ -453,8 +488,7 @@ static int xhci_mtk_setup(struct usb_hcd *hcd) if (ret) return ret; - /* workaround only for mt8195 */ - xhci_mtk_set_frame_interval(mtk); + xhci_mtk_init_quirk(mtk); } ret = xhci_gen_setup(hcd, xhci_mtk_quirks); @@ -531,6 +565,8 @@ static int xhci_mtk_probe(struct platform_device *pdev) of_property_read_u32(node, "mediatek,u2p-dis-msk", &mtk->u2p_dis_msk); + of_property_read_u32(node, "rx-fifo-depth", &mtk->rxfifo_depth); + ret = usb_wakeup_of_property_parse(mtk, node); if (ret) { dev_err(dev, "failed to parse uwk property\n"); diff --git a/drivers/usb/host/xhci-mtk.h b/drivers/usb/host/xhci-mtk.h index 1174a510dd38..2a6a47d0f09a 100644 --- a/drivers/usb/host/xhci-mtk.h +++ b/drivers/usb/host/xhci-mtk.h @@ -160,6 +160,8 @@ struct xhci_hcd_mtk { struct regmap *uwk; u32 uwk_reg_base; u32 uwk_vers; + /* quirk */ + u32 rxfifo_depth; }; static inline struct xhci_hcd_mtk *hcd_to_mtk(struct usb_hcd *hcd) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index c9438dc56f5f..b387d39bfb81 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -301,6 +301,9 @@ static int xhci_plat_probe(struct platform_device *pdev) if (device_property_read_bool(tmpdev, "quirk-broken-port-ped")) xhci->quirks |= XHCI_BROKEN_PORT_PED; + if (device_property_read_bool(tmpdev, "xhci-sg-trb-cache-size-quirk")) + xhci->quirks |= XHCI_SG_TRB_CACHE_SIZE_QUIRK; + device_property_read_u32(tmpdev, "imod-interval-ns", &xhci->imod_interval); } diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index 094e812e9e69..35483217b1f6 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1247,14 +1247,19 @@ static vm_fault_t mon_bin_vma_fault(struct vm_fault *vmf) struct mon_reader_bin *rp = vmf->vma->vm_private_data; unsigned long offset, chunk_idx; struct page *pageptr; + unsigned long flags; + spin_lock_irqsave(&rp->b_lock, flags); offset = vmf->pgoff << PAGE_SHIFT; - if (offset >= rp->b_size) + if (offset >= rp->b_size) { + spin_unlock_irqrestore(&rp->b_lock, flags); return VM_FAULT_SIGBUS; + } chunk_idx = offset / CHUNK_SIZE; pageptr = rp->b_vec[chunk_idx].pg; get_page(pageptr); vmf->page = pageptr; + spin_unlock_irqrestore(&rp->b_lock, flags); return 0; } diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c index 9299df53eb9d..160c9264339f 100644 --- a/drivers/usb/phy/phy-mxs-usb.c +++ b/drivers/usb/phy/phy-mxs-usb.c @@ -388,8 +388,7 @@ static void __mxs_phy_disconnect_line(struct mxs_phy *mxs_phy, bool disconnect) static bool mxs_phy_is_otg_host(struct mxs_phy *mxs_phy) { - return IS_ENABLED(CONFIG_USB_OTG) && - mxs_phy->phy.last_event == USB_EVENT_ID; + return mxs_phy->phy.last_event == USB_EVENT_ID; } static void mxs_phy_disconnect_line(struct mxs_phy *mxs_phy, bool on) diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index 32e6d19f7011..a327f8bc5704 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -19,7 +19,9 @@ static struct class *role_class; struct usb_role_switch { struct device dev; struct mutex lock; /* device lock*/ + struct module *module; /* the module this device depends on */ enum usb_role role; + bool registered; /* From descriptor */ struct device *usb2_port; @@ -46,6 +48,9 @@ int usb_role_switch_set_role(struct usb_role_switch *sw, enum usb_role role) if (IS_ERR_OR_NULL(sw)) return 0; + if (!sw->registered) + return -EOPNOTSUPP; + mutex_lock(&sw->lock); ret = sw->set(sw, role); @@ -71,7 +76,7 @@ enum usb_role usb_role_switch_get_role(struct usb_role_switch *sw) { enum usb_role role; - if (IS_ERR_OR_NULL(sw)) + if (IS_ERR_OR_NULL(sw) || !sw->registered) return USB_ROLE_NONE; mutex_lock(&sw->lock); @@ -133,7 +138,7 @@ struct usb_role_switch *usb_role_switch_get(struct device *dev) usb_role_switch_match); if (!IS_ERR_OR_NULL(sw)) - WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + WARN_ON(!try_module_get(sw->module)); return sw; } @@ -155,7 +160,7 @@ struct usb_role_switch *fwnode_usb_role_switch_get(struct fwnode_handle *fwnode) sw = fwnode_connection_find_match(fwnode, "usb-role-switch", NULL, usb_role_switch_match); if (!IS_ERR_OR_NULL(sw)) - WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + WARN_ON(!try_module_get(sw->module)); return sw; } @@ -170,7 +175,7 @@ EXPORT_SYMBOL_GPL(fwnode_usb_role_switch_get); void usb_role_switch_put(struct usb_role_switch *sw) { if (!IS_ERR_OR_NULL(sw)) { - module_put(sw->dev.parent->driver->owner); + module_put(sw->module); put_device(&sw->dev); } } @@ -187,15 +192,18 @@ struct usb_role_switch * usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) { struct device *dev; + struct usb_role_switch *sw = NULL; if (!fwnode) return NULL; dev = class_find_device_by_fwnode(role_class, fwnode); - if (dev) - WARN_ON(!try_module_get(dev->parent->driver->owner)); + if (dev) { + sw = to_role_switch(dev); + WARN_ON(!try_module_get(sw->module)); + } - return dev ? to_role_switch(dev) : NULL; + return sw; } EXPORT_SYMBOL_GPL(usb_role_switch_find_by_fwnode); @@ -337,6 +345,7 @@ usb_role_switch_register(struct device *parent, sw->set = desc->set; sw->get = desc->get; + sw->module = parent->driver->owner; sw->dev.parent = parent; sw->dev.fwnode = desc->fwnode; sw->dev.class = role_class; @@ -351,6 +360,8 @@ usb_role_switch_register(struct device *parent, return ERR_PTR(ret); } + sw->registered = true; + /* TODO: Symlinks for the host port and the device controller. */ return sw; @@ -365,8 +376,10 @@ EXPORT_SYMBOL_GPL(usb_role_switch_register); */ void usb_role_switch_unregister(struct usb_role_switch *sw) { - if (!IS_ERR_OR_NULL(sw)) + if (!IS_ERR_OR_NULL(sw)) { + sw->registered = false; device_unregister(&sw->dev); + } } EXPORT_SYMBOL_GPL(usb_role_switch_unregister); diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index f1d7a5a863aa..b3e60b384794 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -146,6 +146,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ { USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */ { USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */ + { USB_DEVICE(0x10C4, 0x87ED) }, /* IMST USB-Stick for Smart Meter */ { USB_DEVICE(0x10C4, 0x8856) }, /* CEL EM357 ZigBee USB Stick - LR */ { USB_DEVICE(0x10C4, 0x8857) }, /* CEL EM357 ZigBee USB Stick */ { USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 05e28a5ce42b..fe2173e37b06 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1033,9 +1033,9 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, ACTISENSE_USG_PID) }, { USB_DEVICE(FTDI_VID, ACTISENSE_NGT_PID) }, { USB_DEVICE(FTDI_VID, ACTISENSE_NGW_PID) }, - { USB_DEVICE(FTDI_VID, ACTISENSE_D9AC_PID) }, - { USB_DEVICE(FTDI_VID, ACTISENSE_D9AD_PID) }, - { USB_DEVICE(FTDI_VID, ACTISENSE_D9AE_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_UID_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_USA_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_NGX_PID) }, { USB_DEVICE(FTDI_VID, ACTISENSE_D9AF_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEAGAUGE_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEASWITCH_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index e2099445db70..21a2b5a25fc0 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1568,9 +1568,9 @@ #define ACTISENSE_USG_PID 0xD9A9 /* USG USB Serial Adapter */ #define ACTISENSE_NGT_PID 0xD9AA /* NGT NMEA2000 Interface */ #define ACTISENSE_NGW_PID 0xD9AB /* NGW NMEA2000 Gateway */ -#define ACTISENSE_D9AC_PID 0xD9AC /* Actisense Reserved */ -#define ACTISENSE_D9AD_PID 0xD9AD /* Actisense Reserved */ -#define ACTISENSE_D9AE_PID 0xD9AE /* Actisense Reserved */ +#define ACTISENSE_UID_PID 0xD9AC /* USB Isolating Device */ +#define ACTISENSE_USA_PID 0xD9AD /* USB to Serial Adapter */ +#define ACTISENSE_NGX_PID 0xD9AE /* NGX NMEA2000 Gateway */ #define ACTISENSE_D9AF_PID 0xD9AF /* Actisense Reserved */ #define CHETCO_SEAGAUGE_PID 0xA548 /* SeaGauge USB Adapter */ #define CHETCO_SEASWITCH_PID 0xA549 /* SeaSwitch USB Adapter */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 7f2aa72d52e6..c0a0cca65437 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -272,6 +272,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_RM500Q 0x0800 #define QUECTEL_PRODUCT_RM520N 0x0801 #define QUECTEL_PRODUCT_EC200U 0x0901 +#define QUECTEL_PRODUCT_EG912Y 0x6001 #define QUECTEL_PRODUCT_EC200S_CN 0x6002 #define QUECTEL_PRODUCT_EC200A 0x6005 #define QUECTEL_PRODUCT_EM061K_LWW 0x6008 @@ -1232,6 +1233,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, 0x0700, 0xff), /* BG95 */ .driver_info = RSVD(3) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10), .driver_info = ZLP }, @@ -1244,6 +1246,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG912Y, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, @@ -2242,6 +2245,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(0x0489, 0xe0b5), /* Foxconn T77W968 ESIM */ .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0da, 0xff), /* Foxconn T99W265 MBIM variant */ + .driver_info = RSVD(3) | RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0db, 0xff), /* Foxconn T99W265 MBIM */ .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0ee, 0xff), /* Foxconn T99W368 MBIM */ @@ -2264,6 +2269,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) }, /* Fibocom FM160 (MBIM mode) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a3, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff), /* Fibocom FM101-GL (laptop MBIM) */ .driver_info = RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */ diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index b1e844bf31f8..703a9c563557 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -184,6 +184,8 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */ {DEVICE_SWI(0x413c, 0x81d2)}, /* Dell Wireless 5818 */ + {DEVICE_SWI(0x413c, 0x8217)}, /* Dell Wireless DW5826e */ + {DEVICE_SWI(0x413c, 0x8218)}, /* Dell Wireless DW5826e QDL */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 20dcbccb290b..fd68204374f2 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1306,6 +1306,17 @@ UNUSUAL_DEV( 0x090c, 0x6000, 0x0100, 0x0100, US_FL_INITIAL_READ10 ), /* + * Patch by Tasos Sahanidis <tasos@tasossah.com> + * This flash drive always shows up with write protect enabled + * during the first mode sense. + */ +UNUSUAL_DEV(0x0951, 0x1697, 0x0100, 0x0100, + "Kingston", + "DT Ultimate G3", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_WP_DETECT), + +/* * This Pentax still camera is not conformant * to the USB storage specification: - * - It does not like the INQUIRY command. So we must handle this command diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 49d6b2388b87..3da404d5178d 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -263,11 +263,13 @@ static void typec_altmode_put_partner(struct altmode *altmode) { struct altmode *partner = altmode->partner; struct typec_altmode *adev; + struct typec_altmode *partner_adev; if (!partner) return; adev = &altmode->adev; + partner_adev = &partner->adev; if (is_typec_plug(adev->dev.parent)) { struct typec_plug *plug = to_typec_plug(adev->dev.parent); @@ -276,7 +278,7 @@ static void typec_altmode_put_partner(struct altmode *altmode) } else { partner->partner = NULL; } - put_device(&adev->dev); + put_device(&partner_adev->dev); } /** diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index dc2dea3768fb..0695ee54ff78 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -831,7 +831,9 @@ static void ucsi_handle_connector_change(struct work_struct *work) clear_bit(EVENT_PENDING, &con->ucsi->flags); + mutex_lock(&ucsi->ppm_lock); ret = ucsi_acknowledge_connector_change(ucsi); + mutex_unlock(&ucsi->ppm_lock); if (ret) dev_err(ucsi->dev, "%s: ACK failed (%d)", __func__, ret); diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c index 217355f1f9b9..48130d636a02 100644 --- a/drivers/usb/typec/ucsi/ucsi_acpi.c +++ b/drivers/usb/typec/ucsi/ucsi_acpi.c @@ -25,6 +25,8 @@ struct ucsi_acpi { unsigned long flags; guid_t guid; u64 cmd; + bool dell_quirk_probed; + bool dell_quirk_active; }; static int ucsi_acpi_dsm(struct ucsi_acpi *ua, int func) @@ -73,9 +75,13 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, const void *val, size_t val_len) { struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi); + bool ack = UCSI_COMMAND(*(u64 *)val) == UCSI_ACK_CC_CI; int ret; - set_bit(COMMAND_PENDING, &ua->flags); + if (ack) + set_bit(ACK_PENDING, &ua->flags); + else + set_bit(COMMAND_PENDING, &ua->flags); ret = ucsi_acpi_async_write(ucsi, offset, val, val_len); if (ret) @@ -85,7 +91,10 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, ret = -ETIMEDOUT; out_clear_bit: - clear_bit(COMMAND_PENDING, &ua->flags); + if (ack) + clear_bit(ACK_PENDING, &ua->flags); + else + clear_bit(COMMAND_PENDING, &ua->flags); return ret; } @@ -119,12 +128,73 @@ static const struct ucsi_operations ucsi_zenbook_ops = { .async_write = ucsi_acpi_async_write }; -static const struct dmi_system_id zenbook_dmi_id[] = { +/* + * Some Dell laptops expect that an ACK command with the + * UCSI_ACK_CONNECTOR_CHANGE bit set is followed by a (separate) + * ACK command that only has the UCSI_ACK_COMMAND_COMPLETE bit set. + * If this is not done events are not delivered to OSPM and + * subsequent commands will timeout. + */ +static int +ucsi_dell_sync_write(struct ucsi *ucsi, unsigned int offset, + const void *val, size_t val_len) +{ + struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi); + u64 cmd = *(u64 *)val, ack = 0; + int ret; + + if (UCSI_COMMAND(cmd) == UCSI_ACK_CC_CI && + cmd & UCSI_ACK_CONNECTOR_CHANGE) + ack = UCSI_ACK_CC_CI | UCSI_ACK_COMMAND_COMPLETE; + + ret = ucsi_acpi_sync_write(ucsi, offset, val, val_len); + if (ret != 0) + return ret; + if (ack == 0) + return ret; + + if (!ua->dell_quirk_probed) { + ua->dell_quirk_probed = true; + + cmd = UCSI_GET_CAPABILITY; + ret = ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &cmd, + sizeof(cmd)); + if (ret == 0) + return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, + &ack, sizeof(ack)); + if (ret != -ETIMEDOUT) + return ret; + + ua->dell_quirk_active = true; + dev_err(ua->dev, "Firmware bug: Additional ACK required after ACKing a connector change.\n"); + dev_err(ua->dev, "Firmware bug: Enabling workaround\n"); + } + + if (!ua->dell_quirk_active) + return ret; + + return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &ack, sizeof(ack)); +} + +static const struct ucsi_operations ucsi_dell_ops = { + .read = ucsi_acpi_read, + .sync_write = ucsi_dell_sync_write, + .async_write = ucsi_acpi_async_write +}; + +static const struct dmi_system_id ucsi_acpi_quirks[] = { { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"), }, + .driver_data = (void *)&ucsi_zenbook_ops, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + }, + .driver_data = (void *)&ucsi_dell_ops, }, { } }; @@ -142,8 +212,10 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data) if (UCSI_CCI_CONNECTOR(cci)) ucsi_connector_change(ua->ucsi, UCSI_CCI_CONNECTOR(cci)); - if (test_bit(COMMAND_PENDING, &ua->flags) && - cci & (UCSI_CCI_ACK_COMPLETE | UCSI_CCI_COMMAND_COMPLETE)) + if (cci & UCSI_CCI_ACK_COMPLETE && test_bit(ACK_PENDING, &ua->flags)) + complete(&ua->complete); + if (cci & UCSI_CCI_COMMAND_COMPLETE && + test_bit(COMMAND_PENDING, &ua->flags)) complete(&ua->complete); } @@ -151,6 +223,7 @@ static int ucsi_acpi_probe(struct platform_device *pdev) { struct acpi_device *adev = ACPI_COMPANION(&pdev->dev); const struct ucsi_operations *ops = &ucsi_acpi_ops; + const struct dmi_system_id *id; struct ucsi_acpi *ua; struct resource *res; acpi_status status; @@ -180,8 +253,9 @@ static int ucsi_acpi_probe(struct platform_device *pdev) init_completion(&ua->complete); ua->dev = &pdev->dev; - if (dmi_check_system(zenbook_dmi_id)) - ops = &ucsi_zenbook_ops; + id = dmi_first_match(ucsi_acpi_quirks); + if (id) + ops = id->driver_data; ua->ucsi = ucsi_create(&pdev->dev, ops); if (IS_ERR(ua->ucsi)) diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c index 5a09a09cca70..cce3d1837104 100644 --- a/drivers/vdpa/alibaba/eni_vdpa.c +++ b/drivers/vdpa/alibaba/eni_vdpa.c @@ -497,7 +497,7 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!eni_vdpa->vring) { ret = -ENOMEM; ENI_ERR(pdev, "failed to allocate virtqueues\n"); - goto err; + goto err_remove_vp_legacy; } for (i = 0; i < eni_vdpa->queues; i++) { @@ -509,11 +509,13 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = vdpa_register_device(&eni_vdpa->vdpa, eni_vdpa->queues); if (ret) { ENI_ERR(pdev, "failed to register to vdpa bus\n"); - goto err; + goto err_remove_vp_legacy; } return 0; +err_remove_vp_legacy: + vp_legacy_remove(&eni_vdpa->ldev); err: put_device(&eni_vdpa->vdpa.dev); return ret; diff --git a/drivers/vfio/iova_bitmap.c b/drivers/vfio/iova_bitmap.c index 0f19d502f351..dfab5b742191 100644 --- a/drivers/vfio/iova_bitmap.c +++ b/drivers/vfio/iova_bitmap.c @@ -99,7 +99,7 @@ struct iova_bitmap { struct iova_bitmap_map mapped; /* userspace address of the bitmap */ - u64 __user *bitmap; + u8 __user *bitmap; /* u64 index that @mapped points to */ unsigned long mapped_base_index; @@ -161,7 +161,7 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap) { struct iova_bitmap_map *mapped = &bitmap->mapped; unsigned long npages; - u64 __user *addr; + u8 __user *addr; long ret; /* @@ -175,17 +175,18 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap) sizeof(*bitmap->bitmap), PAGE_SIZE); /* - * We always cap at max number of 'struct page' a base page can fit. - * This is, for example, on x86 means 2M of bitmap data max. - */ - npages = min(npages, PAGE_SIZE / sizeof(struct page *)); - - /* * Bitmap address to be pinned is calculated via pointer arithmetic * with bitmap u64 word index. */ addr = bitmap->bitmap + bitmap->mapped_base_index; + /* + * We always cap at max number of 'struct page' a base page can fit. + * This is, for example, on x86 means 2M of bitmap data max. + */ + npages = min(npages + !!offset_in_page(addr), + PAGE_SIZE / sizeof(struct page *)); + ret = pin_user_pages_fast((unsigned long)addr, npages, FOLL_WRITE, mapped->pages); if (ret <= 0) @@ -246,7 +247,7 @@ struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length, mapped = &bitmap->mapped; mapped->pgshift = __ffs(page_size); - bitmap->bitmap = data; + bitmap->bitmap = (u8 __user *)data; bitmap->mapped_total_index = iova_bitmap_offset_to_index(bitmap, length - 1) + 1; bitmap->iova = iova; @@ -301,7 +302,7 @@ static unsigned long iova_bitmap_mapped_remaining(struct iova_bitmap *bitmap) remaining = bitmap->mapped_total_index - bitmap->mapped_base_index; remaining = min_t(unsigned long, remaining, - bytes / sizeof(*bitmap->bitmap)); + DIV_ROUND_UP(bytes, sizeof(*bitmap->bitmap))); return remaining; } @@ -405,6 +406,7 @@ void iova_bitmap_set(struct iova_bitmap *bitmap, mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE; unsigned long last_bit = (((iova + length - 1) - mapped->iova) >> mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE; + unsigned long last_page_idx = mapped->npages - 1; do { unsigned int page_idx = cur_bit / BITS_PER_PAGE; @@ -413,6 +415,9 @@ void iova_bitmap_set(struct iova_bitmap *bitmap, last_bit - cur_bit + 1); void *kaddr; + if (unlikely(page_idx > last_page_idx)) + break; + kaddr = kmap_local_page(mapped->pages[page_idx]); bitmap_set(kaddr, offset, nbits); kunmap_local(kaddr); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 2eea08029881..61c72e62abd4 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2588,12 +2588,11 @@ EXPORT_SYMBOL_GPL(vhost_disable_notify); /* Create a new message. */ struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type) { - struct vhost_msg_node *node = kmalloc(sizeof *node, GFP_KERNEL); + /* Make sure all padding within the structure is initialized. */ + struct vhost_msg_node *node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return NULL; - /* Make sure all padding within the structure is initialized. */ - memset(&node->msg, 0, sizeof node->msg); node->vq = vq; node->msg.type = type; return node; diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index a3cf1f764f29..49883c8012e6 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -132,11 +132,7 @@ int fb_deferred_io_fsync(struct file *file, loff_t start, loff_t end, int datasy return 0; inode_lock(inode); - /* Kill off the delayed work */ - cancel_delayed_work_sync(&info->deferred_work); - - /* Run it immediately */ - schedule_delayed_work(&info->deferred_work, 0); + flush_delayed_work(&info->deferred_work); inode_unlock(inode); return 0; @@ -321,7 +317,7 @@ static void fb_deferred_io_lastclose(struct fb_info *info) struct page *page; int i; - cancel_delayed_work_sync(&info->deferred_work); + flush_delayed_work(&info->deferred_work); /* clear out the mapping that we setup */ for (i = 0 ; i < info->fix.smem_len; i += PAGE_SIZE) { diff --git a/drivers/video/fbdev/imsttfb.c b/drivers/video/fbdev/imsttfb.c index b194e71f07bf..aa51cb72cbba 100644 --- a/drivers/video/fbdev/imsttfb.c +++ b/drivers/video/fbdev/imsttfb.c @@ -1419,7 +1419,6 @@ static int init_imstt(struct fb_info *info) if ((info->var.xres * info->var.yres) * (info->var.bits_per_pixel >> 3) > info->fix.smem_len || !(compute_imstt_regvals(par, info->var.xres, info->var.yres))) { printk("imsttfb: %ux%ux%u not supported\n", info->var.xres, info->var.yres, info->var.bits_per_pixel); - framebuffer_release(info); return -ENODEV; } @@ -1452,10 +1451,11 @@ static int init_imstt(struct fb_info *info) FBINFO_HWACCEL_FILLRECT | FBINFO_HWACCEL_YPAN; - fb_alloc_cmap(&info->cmap, 0, 0); + if (fb_alloc_cmap(&info->cmap, 0, 0)) + return -ENODEV; if (register_framebuffer(info) < 0) { - framebuffer_release(info); + fb_dealloc_cmap(&info->cmap); return -ENODEV; } diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index 36ada87b49a4..32b8374abeca 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -42,6 +42,7 @@ #include <video/videomode.h> #define PCR_TFT (1 << 31) +#define PCR_COLOR (1 << 30) #define PCR_BPIX_8 (3 << 25) #define PCR_BPIX_12 (4 << 25) #define PCR_BPIX_16 (5 << 25) @@ -150,6 +151,12 @@ enum imxfb_type { IMX21_FB, }; +enum imxfb_panel_type { + PANEL_TYPE_MONOCHROME, + PANEL_TYPE_CSTN, + PANEL_TYPE_TFT, +}; + struct imxfb_info { struct platform_device *pdev; void __iomem *regs; @@ -157,6 +164,7 @@ struct imxfb_info { struct clk *clk_ahb; struct clk *clk_per; enum imxfb_type devtype; + enum imxfb_panel_type panel_type; bool enabled; /* @@ -444,6 +452,13 @@ static int imxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) if (!is_imx1_fb(fbi) && imxfb_mode->aus_mode) fbi->lauscr = LAUSCR_AUS_MODE; + if (imxfb_mode->pcr & PCR_TFT) + fbi->panel_type = PANEL_TYPE_TFT; + else if (imxfb_mode->pcr & PCR_COLOR) + fbi->panel_type = PANEL_TYPE_CSTN; + else + fbi->panel_type = PANEL_TYPE_MONOCHROME; + /* * Copy the RGB parameters for this display * from the machine specific parameters. @@ -598,6 +613,7 @@ static int imxfb_activate_var(struct fb_var_screeninfo *var, struct fb_info *inf { struct imxfb_info *fbi = info->par; u32 ymax_mask = is_imx1_fb(fbi) ? YMAX_MASK_IMX1 : YMAX_MASK_IMX21; + u8 left_margin_low; pr_debug("var: xres=%d hslen=%d lm=%d rm=%d\n", var->xres, var->hsync_len, @@ -606,6 +622,13 @@ static int imxfb_activate_var(struct fb_var_screeninfo *var, struct fb_info *inf var->yres, var->vsync_len, var->upper_margin, var->lower_margin); + if (fbi->panel_type == PANEL_TYPE_TFT) + left_margin_low = 3; + else if (fbi->panel_type == PANEL_TYPE_CSTN) + left_margin_low = 2; + else + left_margin_low = 0; + #if DEBUG_VAR if (var->xres < 16 || var->xres > 1024) printk(KERN_ERR "%s: invalid xres %d\n", @@ -613,7 +636,7 @@ static int imxfb_activate_var(struct fb_var_screeninfo *var, struct fb_info *inf if (var->hsync_len < 1 || var->hsync_len > 64) printk(KERN_ERR "%s: invalid hsync_len %d\n", info->fix.id, var->hsync_len); - if (var->left_margin < 3 || var->left_margin > 255) + if (var->left_margin < left_margin_low || var->left_margin > 255) printk(KERN_ERR "%s: invalid left_margin %d\n", info->fix.id, var->left_margin); if (var->right_margin < 1 || var->right_margin > 255) @@ -639,7 +662,7 @@ static int imxfb_activate_var(struct fb_var_screeninfo *var, struct fb_info *inf writel(HCR_H_WIDTH(var->hsync_len - 1) | HCR_H_WAIT_1(var->right_margin - 1) | - HCR_H_WAIT_2(var->left_margin - 3), + HCR_H_WAIT_2(var->left_margin - left_margin_low), fbi->regs + LCDC_HCR); writel(VCR_V_WIDTH(var->vsync_len) | diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c index b7818b652698..a7b63c475f95 100644 --- a/drivers/video/fbdev/savage/savagefb_driver.c +++ b/drivers/video/fbdev/savage/savagefb_driver.c @@ -869,6 +869,9 @@ static int savagefb_check_var(struct fb_var_screeninfo *var, DBG("savagefb_check_var"); + if (!var->pixclock) + return -EINVAL; + var->transp.offset = 0; var->transp.length = 0; switch (var->bits_per_pixel) { diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index 1c197c3f9538..fe8996461b9e 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -1475,6 +1475,8 @@ sisfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) vtotal = var->upper_margin + var->lower_margin + var->vsync_len; + if (!var->pixclock) + return -EINVAL; pixclock = var->pixclock; if((var->vmode & FB_VMODE_MASK) == FB_VMODE_NONINTERLACED) { diff --git a/drivers/watchdog/bcm2835_wdt.c b/drivers/watchdog/bcm2835_wdt.c index 94907176a0e4..55c0f7b0e8fb 100644 --- a/drivers/watchdog/bcm2835_wdt.c +++ b/drivers/watchdog/bcm2835_wdt.c @@ -42,6 +42,7 @@ #define SECS_TO_WDOG_TICKS(x) ((x) << 16) #define WDOG_TICKS_TO_SECS(x) ((x) >> 16) +#define WDOG_TICKS_TO_MSECS(x) ((x) * 1000 >> 16) struct bcm2835_wdt { void __iomem *base; @@ -140,7 +141,7 @@ static struct watchdog_device bcm2835_wdt_wdd = { .info = &bcm2835_wdt_info, .ops = &bcm2835_wdt_ops, .min_timeout = 1, - .max_timeout = WDOG_TICKS_TO_SECS(PM_WDOG_TIME_SET), + .max_hw_heartbeat_ms = WDOG_TICKS_TO_MSECS(PM_WDOG_TIME_SET), .timeout = WDOG_TICKS_TO_SECS(PM_WDOG_TIME_SET), }; diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index f79f932bca14..79ed1626d8ea 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -178,7 +178,7 @@ static int hpwdt_pretimeout(unsigned int ulReason, struct pt_regs *regs) "3. OA Forward Progress Log\n" "4. iLO Event Log"; - if (ilo5 && ulReason == NMI_UNKNOWN && !mynmi) + if (ulReason == NMI_UNKNOWN && !mynmi) return NMI_DONE; if (ilo5 && !pretimeout && !mynmi) diff --git a/drivers/watchdog/it87_wdt.c b/drivers/watchdog/it87_wdt.c index bb1122909396..843f9f8e3917 100644 --- a/drivers/watchdog/it87_wdt.c +++ b/drivers/watchdog/it87_wdt.c @@ -255,6 +255,7 @@ static struct watchdog_device wdt_dev = { static int __init it87_wdt_init(void) { u8 chip_rev; + u8 ctrl; int rc; rc = superio_enter(); @@ -313,7 +314,18 @@ static int __init it87_wdt_init(void) superio_select(GPIO); superio_outb(WDT_TOV1, WDTCFG); - superio_outb(0x00, WDTCTRL); + + switch (chip_type) { + case IT8784_ID: + case IT8786_ID: + ctrl = superio_inb(WDTCTRL); + ctrl &= 0x08; + superio_outb(ctrl, WDTCTRL); + break; + default: + superio_outb(0x00, WDTCTRL); + } + superio_exit(); if (timeout < 1 || timeout > max_units * 60) { diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c index f91a260beaa7..3bdc7bfb7c75 100644 --- a/drivers/watchdog/rti_wdt.c +++ b/drivers/watchdog/rti_wdt.c @@ -70,9 +70,11 @@ static int rti_wdt_start(struct watchdog_device *wdd) { u32 timer_margin; struct rti_wdt_device *wdt = watchdog_get_drvdata(wdd); + int ret; - if (pm_runtime_suspended(wdd->parent)) - pm_runtime_get_sync(wdd->parent); + ret = pm_runtime_resume_and_get(wdd->parent); + if (ret) + return ret; /* set timeout period */ timer_margin = (u64)wdd->timeout * wdt->freq; @@ -227,8 +229,12 @@ static int rti_wdt_probe(struct platform_device *pdev) if (wdt->freq < 32768) wdt->freq = wdt->freq * 9 / 10; - devm_pm_runtime_enable(dev); - pm_runtime_get_noresume(dev); + pm_runtime_enable(dev); + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) { + pm_runtime_disable(&pdev->dev); + return dev_err_probe(dev, ret, "runtime pm failed\n"); + } platform_set_drvdata(pdev, wdt); @@ -247,7 +253,7 @@ static int rti_wdt_probe(struct platform_device *pdev) wdt->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(wdt->base)) { ret = PTR_ERR(wdt->base); - return ret; + goto err_iomap; } if (readl(wdt->base + RTIDWDCTRL) == WDENABLE_KEY) { @@ -273,7 +279,7 @@ static int rti_wdt_probe(struct platform_device *pdev) ret = rti_wdt_setup_hw_hb(wdd, wsize); if (ret) { dev_err(dev, "bad window size.\n"); - return ret; + goto err_iomap; } last_ping = heartbeat_ms - time_left_ms; @@ -288,7 +294,7 @@ static int rti_wdt_probe(struct platform_device *pdev) ret = watchdog_register_device(wdd); if (ret) { dev_err(dev, "cannot register watchdog device\n"); - return ret; + goto err_iomap; } if (last_ping) @@ -298,18 +304,24 @@ static int rti_wdt_probe(struct platform_device *pdev) pm_runtime_put_sync(&pdev->dev); return 0; + +err_iomap: + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + + return ret; } -static int rti_wdt_remove(struct platform_device *pdev) +static void rti_wdt_remove(struct platform_device *pdev) { struct rti_wdt_device *wdt = platform_get_drvdata(pdev); watchdog_unregister_device(&wdt->wdd); if (!pm_runtime_suspended(&pdev->dev)) - pm_runtime_put_sync(&pdev->dev); + pm_runtime_put(&pdev->dev); - return 0; + pm_runtime_disable(&pdev->dev); } static const struct of_device_id rti_wdt_of_match[] = { @@ -324,7 +336,7 @@ static struct platform_driver rti_wdt_driver = { .of_match_table = rti_wdt_of_match, }, .probe = rti_wdt_probe, - .remove = rti_wdt_remove, + .remove_new = rti_wdt_remove, }; module_platform_driver(rti_wdt_driver); diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index fdffa6859dde..81684d89dc98 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -1052,6 +1052,7 @@ static int watchdog_cdev_register(struct watchdog_device *wdd) /* Fill in the data structures */ cdev_init(&wd_data->cdev, &watchdog_fops); + wd_data->cdev.owner = wdd->ops->owner; /* Add the device */ err = cdev_device_add(&wd_data->cdev, &wd_data->dev); @@ -1066,8 +1067,6 @@ static int watchdog_cdev_register(struct watchdog_device *wdd) return err; } - wd_data->cdev.owner = wdd->ops->owner; - /* Record time of most recent heartbeat as 'just before now'. */ wd_data->last_hw_keepalive = ktime_sub(ktime_get(), 1); watchdog_set_open_deadline(wd_data); diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c index 940e5e9e8a54..335451309566 100644 --- a/drivers/xen/gntdev-dmabuf.c +++ b/drivers/xen/gntdev-dmabuf.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/dma-buf.h> +#include <linux/dma-direct.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/uaccess.h> @@ -50,7 +51,7 @@ struct gntdev_dmabuf { /* Number of pages this buffer has. */ int nr_pages; - /* Pages of this buffer. */ + /* Pages of this buffer (only for dma-buf export). */ struct page **pages; }; @@ -484,7 +485,7 @@ out: /* DMA buffer import support. */ static int -dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs, +dmabuf_imp_grant_foreign_access(unsigned long *gfns, u32 *refs, int count, int domid) { grant_ref_t priv_gref_head; @@ -507,7 +508,7 @@ dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs, } gnttab_grant_foreign_access_ref(cur_ref, domid, - xen_page_to_gfn(pages[i]), 0); + gfns[i], 0); refs[i] = cur_ref; } @@ -529,7 +530,6 @@ static void dmabuf_imp_end_foreign_access(u32 *refs, int count) static void dmabuf_imp_free_storage(struct gntdev_dmabuf *gntdev_dmabuf) { - kfree(gntdev_dmabuf->pages); kfree(gntdev_dmabuf->u.imp.refs); kfree(gntdev_dmabuf); } @@ -549,12 +549,6 @@ static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count) if (!gntdev_dmabuf->u.imp.refs) goto fail; - gntdev_dmabuf->pages = kcalloc(count, - sizeof(gntdev_dmabuf->pages[0]), - GFP_KERNEL); - if (!gntdev_dmabuf->pages) - goto fail; - gntdev_dmabuf->nr_pages = count; for (i = 0; i < count; i++) @@ -576,7 +570,8 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev, struct dma_buf *dma_buf; struct dma_buf_attachment *attach; struct sg_table *sgt; - struct sg_page_iter sg_iter; + struct sg_dma_page_iter sg_iter; + unsigned long *gfns; int i; dma_buf = dma_buf_get(fd); @@ -624,26 +619,31 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev, gntdev_dmabuf->u.imp.sgt = sgt; - /* Now convert sgt to array of pages and check for page validity. */ + gfns = kcalloc(count, sizeof(*gfns), GFP_KERNEL); + if (!gfns) { + ret = ERR_PTR(-ENOMEM); + goto fail_unmap; + } + + /* + * Now convert sgt to array of gfns without accessing underlying pages. + * It is not allowed to access the underlying struct page of an sg table + * exported by DMA-buf, but since we deal with special Xen dma device here + * (not a normal physical one) look at the dma addresses in the sg table + * and then calculate gfns directly from them. + */ i = 0; - for_each_sgtable_page(sgt, &sg_iter, 0) { - struct page *page = sg_page_iter_page(&sg_iter); - /* - * Check if page is valid: this can happen if we are given - * a page from VRAM or other resources which are not backed - * by a struct page. - */ - if (!pfn_valid(page_to_pfn(page))) { - ret = ERR_PTR(-EINVAL); - goto fail_unmap; - } + for_each_sgtable_dma_page(sgt, &sg_iter, 0) { + dma_addr_t addr = sg_page_iter_dma_address(&sg_iter); + unsigned long pfn = bfn_to_pfn(XEN_PFN_DOWN(dma_to_phys(dev, addr))); - gntdev_dmabuf->pages[i++] = page; + gfns[i++] = pfn_to_gfn(pfn); } - ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gntdev_dmabuf->pages, + ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gfns, gntdev_dmabuf->u.imp.refs, count, domid)); + kfree(gfns); if (IS_ERR(ret)) goto fail_end_access; diff --git a/fs/9p/cache.c b/fs/9p/cache.c index cebba4eaa0b5..12c0ae29f185 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -68,6 +68,8 @@ void v9fs_cache_inode_get_cookie(struct inode *inode) &path, sizeof(path), &version, sizeof(version), i_size_read(&v9inode->netfs.inode)); + if (v9inode->netfs.cache) + mapping_set_release_always(inode->i_mapping); p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n", inode, v9fs_inode_cookie(v9inode)); diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index bc417da7e9c1..633fe4f527b8 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -46,6 +46,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb); void v9fs_free_inode(struct inode *inode); struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev); +void v9fs_set_netfs_context(struct inode *inode); int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t rdev); void v9fs_evict_inode(struct inode *inode); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 4d1a4a8d9277..5e2657c1dbbe 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -250,7 +250,7 @@ void v9fs_free_inode(struct inode *inode) /* * Set parameters for the netfs library */ -static void v9fs_set_netfs_context(struct inode *inode) +void v9fs_set_netfs_context(struct inode *inode) { struct v9fs_inode *v9inode = V9FS_I(inode); netfs_inode_init(&v9inode->netfs, &v9fs_req_ops); @@ -344,8 +344,6 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, err = -EINVAL; goto error; } - - v9fs_set_netfs_context(inode); error: return err; @@ -377,6 +375,7 @@ struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev) iput(inode); return ERR_PTR(err); } + v9fs_set_netfs_context(inode); return inode; } @@ -479,6 +478,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb, goto error; v9fs_stat2inode(st, inode, sb, 0); + v9fs_set_netfs_context(inode); v9fs_cache_inode_get_cookie(inode); unlock_new_inode(inode); return inode; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 5cfa4b4f070f..e15ad46833e0 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -130,6 +130,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, goto error; v9fs_stat2inode_dotl(st, inode, 0); + v9fs_set_netfs_context(inode); v9fs_cache_inode_get_cookie(inode); retval = v9fs_get_acl(inode, fid); if (retval) diff --git a/fs/afs/callback.c b/fs/afs/callback.c index a484fa642808..90f9b2a46ff4 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -110,13 +110,14 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell, { struct afs_volume *volume = NULL; struct rb_node *p; - int seq = 0; + int seq = 1; do { /* Unfortunately, rbtree walking doesn't give reliable results * under just the RCU read lock, so we have to check for * changes. */ + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&cell->volume_lock, &seq); p = rcu_dereference_raw(cell->volumes.rb_node); diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 988c2ac7cece..926cb1188eba 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -409,10 +409,12 @@ static int afs_update_cell(struct afs_cell *cell) if (ret == -ENOMEM) goto out_wake; - ret = -ENOMEM; vllist = afs_alloc_vlserver_list(0); - if (!vllist) + if (!vllist) { + if (ret >= 0) + ret = -ENOMEM; goto out_wake; + } switch (ret) { case -ENODATA: diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 07dc4ec73520..cf811b77ee67 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -473,6 +473,14 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, continue; } + /* Don't expose silly rename entries to userspace. */ + if (nlen > 6 && + dire->u.name[0] == '.' && + ctx->actor != afs_lookup_filldir && + ctx->actor != afs_lookup_one_filldir && + memcmp(dire->u.name, ".__afs", 6) == 0) + continue; + /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, ntohl(dire->u.vnode), diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 91e804c70dd0..9937993cf29d 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -114,6 +114,7 @@ static int afs_probe_cell_name(struct dentry *dentry) struct afs_net *net = afs_d2net(dentry); const char *name = dentry->d_name.name; size_t len = dentry->d_name.len; + char *result = NULL; int ret; /* Names prefixed with a dot are R/W mounts. */ @@ -131,9 +132,22 @@ static int afs_probe_cell_name(struct dentry *dentry) } ret = dns_query(net->net, "afsdb", name, len, "srv=1", - NULL, NULL, false); - if (ret == -ENODATA || ret == -ENOKEY) + &result, NULL, false); + if (ret == -ENODATA || ret == -ENOKEY || ret == 0) ret = -ENOENT; + if (ret > 0 && ret >= sizeof(struct dns_server_list_v1_header)) { + struct dns_server_list_v1_header *v1 = (void *)result; + + if (v1->hdr.zero == 0 && + v1->hdr.content == DNS_PAYLOAD_IS_SERVER_LIST && + v1->hdr.version == 1 && + (v1->status != DNS_LOOKUP_GOOD && + v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) + return -ENOENT; + + } + + kfree(result); return ret; } @@ -252,20 +266,9 @@ static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags) return 1; } -/* - * Allow the VFS to enquire as to whether a dentry should be unhashed (mustn't - * sleep) - * - called from dput() when d_count is going to 0. - * - return 1 to request dentry be unhashed, 0 otherwise - */ -static int afs_dynroot_d_delete(const struct dentry *dentry) -{ - return d_really_is_positive(dentry); -} - const struct dentry_operations afs_dynroot_dentry_operations = { .d_revalidate = afs_dynroot_d_revalidate, - .d_delete = afs_dynroot_d_delete, + .d_delete = always_delete_dentry, .d_release = afs_d_release, .d_automount = afs_d_automount, }; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index c2d70fc1698c..a25fdc3e5231 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -585,6 +585,7 @@ struct afs_volume { #define AFS_VOLUME_OFFLINE 4 /* - T if volume offline notice given */ #define AFS_VOLUME_BUSY 5 /* - T if volume busy notice given */ #define AFS_VOLUME_MAYBE_NO_IBULK 6 /* - T if some servers don't have InlineBulkStatus */ +#define AFS_VOLUME_RM_TREE 7 /* - Set if volume removed from cell->volumes */ #ifdef CONFIG_AFS_FSCACHE struct fscache_volume *cache; /* Caching cookie */ #endif @@ -681,6 +682,8 @@ static inline void afs_vnode_set_cache(struct afs_vnode *vnode, { #ifdef CONFIG_AFS_FSCACHE vnode->netfs.cache = cookie; + if (cookie) + mapping_set_release_always(vnode->netfs.inode.i_mapping); #endif } @@ -1517,6 +1520,7 @@ extern struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *, extern struct afs_volume *afs_create_volume(struct afs_fs_context *); extern int afs_activate_volume(struct afs_volume *); extern void afs_deactivate_volume(struct afs_volume *); +bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason); extern struct afs_volume *afs_get_volume(struct afs_volume *, enum afs_volume_trace); extern void afs_put_volume(struct afs_net *, struct afs_volume *, enum afs_volume_trace); extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *); diff --git a/fs/afs/server.c b/fs/afs/server.c index b5237206eac3..0bd2f5ba6900 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -27,7 +27,7 @@ struct afs_server *afs_find_server(struct afs_net *net, const struct afs_addr_list *alist; struct afs_server *server = NULL; unsigned int i; - int seq = 0, diff; + int seq = 1, diff; rcu_read_lock(); @@ -35,6 +35,7 @@ struct afs_server *afs_find_server(struct afs_net *net, if (server) afs_unuse_server_notime(net, server, afs_server_trace_put_find_rsq); server = NULL; + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_addr_lock, &seq); if (srx->transport.family == AF_INET6) { @@ -90,7 +91,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu { struct afs_server *server = NULL; struct rb_node *p; - int diff, seq = 0; + int diff, seq = 1; _enter("%pU", uuid); @@ -102,7 +103,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu if (server) afs_unuse_server(net, server, afs_server_trace_put_uuid_rsq); server = NULL; - + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_lock, &seq); p = net->fs_servers.rb_node; diff --git a/fs/afs/volume.c b/fs/afs/volume.c index f4937029dcd7..a146d70efa65 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -32,8 +32,13 @@ static struct afs_volume *afs_insert_volume_into_cell(struct afs_cell *cell, } else if (p->vid > volume->vid) { pp = &(*pp)->rb_right; } else { - volume = afs_get_volume(p, afs_volume_trace_get_cell_insert); - goto found; + if (afs_try_get_volume(p, afs_volume_trace_get_cell_insert)) { + volume = p; + goto found; + } + + set_bit(AFS_VOLUME_RM_TREE, &volume->flags); + rb_replace_node_rcu(&p->cell_node, &volume->cell_node, &cell->volumes); } } @@ -56,7 +61,8 @@ static void afs_remove_volume_from_cell(struct afs_volume *volume) afs_volume_trace_remove); write_seqlock(&cell->volume_lock); hlist_del_rcu(&volume->proc_link); - rb_erase(&volume->cell_node, &cell->volumes); + if (!test_and_set_bit(AFS_VOLUME_RM_TREE, &volume->flags)) + rb_erase(&volume->cell_node, &cell->volumes); write_sequnlock(&cell->volume_lock); } } @@ -236,6 +242,20 @@ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume) } /* + * Try to get a reference on a volume record. + */ +bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason) +{ + int r; + + if (__refcount_inc_not_zero(&volume->ref, &r)) { + trace_afs_volume(volume->vid, r + 1, reason); + return true; + } + return false; +} + +/* * Get a reference on a volume record. */ struct afs_volume *afs_get_volume(struct afs_volume *volume, @@ -321,7 +341,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) { struct afs_server_list *new, *old, *discard; struct afs_vldb_entry *vldb; - char idbuf[16]; + char idbuf[24]; int ret, idsz; _enter(""); @@ -329,7 +349,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) /* We look up an ID by passing it as a decimal string in the * operation's name parameter. */ - idsz = sprintf(idbuf, "%llu", volume->vid); + idsz = snprintf(idbuf, sizeof(idbuf), "%llu", volume->vid); vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz); if (IS_ERR(vldb)) { @@ -595,6 +595,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) struct kioctx *ctx = req->ki_ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; @@ -1476,7 +1483,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 08017b180a10..9f77565bd7f5 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1318,6 +1318,7 @@ out: */ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) { + LIST_HEAD(retry_list); struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; struct btrfs_trans_handle *trans; @@ -1339,6 +1340,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->unused_bgs)) { + u64 used; int trimming; block_group = list_first_entry(&fs_info->unused_bgs, @@ -1374,9 +1376,9 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) goto next; } + spin_lock(&space_info->lock); spin_lock(&block_group->lock); - if (block_group->reserved || block_group->pinned || - block_group->used || block_group->ro || + if (btrfs_is_block_group_used(block_group) || block_group->ro || list_is_singular(&block_group->list)) { /* * We want to bail if we made new allocations or have @@ -1386,10 +1388,49 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) */ trace_btrfs_skip_unused_block_group(block_group); spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); + up_write(&space_info->groups_sem); + goto next; + } + + /* + * The block group may be unused but there may be space reserved + * accounting with the existence of that block group, that is, + * space_info->bytes_may_use was incremented by a task but no + * space was yet allocated from the block group by the task. + * That space may or may not be allocated, as we are generally + * pessimistic about space reservation for metadata as well as + * for data when using compression (as we reserve space based on + * the worst case, when data can't be compressed, and before + * actually attempting compression, before starting writeback). + * + * So check if the total space of the space_info minus the size + * of this block group is less than the used space of the + * space_info - if that's the case, then it means we have tasks + * that might be relying on the block group in order to allocate + * extents, and add back the block group to the unused list when + * we finish, so that we retry later in case no tasks ended up + * needing to allocate extents from the block group. + */ + used = btrfs_space_info_used(space_info, true); + if (space_info->total_bytes - block_group->length < used) { + /* + * Add a reference for the list, compensate for the ref + * drop under the "next" label for the + * fs_info->unused_bgs list. + */ + btrfs_get_block_group(block_group); + list_add_tail(&block_group->bg_list, &retry_list); + + trace_btrfs_skip_unused_block_group(block_group); + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); up_write(&space_info->groups_sem); goto next; } + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); /* We don't want to force the issue, only flip if it's ok. */ ret = inc_block_group_ro(block_group, 0); @@ -1513,12 +1554,16 @@ next: btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } + list_splice_tail(&retry_list, &fs_info->unused_bgs); spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); return; flip_async: btrfs_end_transaction(trans); + spin_lock(&fs_info->unused_bgs_lock); + list_splice_tail(&retry_list, &fs_info->unused_bgs); + spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); btrfs_put_block_group(block_group); btrfs_discard_punt_unused_bgs_list(fs_info); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 47a2dcbfee25..bace40a00637 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -241,6 +241,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) return (block_group->start + block_group->length); } +static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg) +{ + lockdep_assert_held(&bg->lock); + + return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0); +} + static inline bool btrfs_is_block_group_data_only( struct btrfs_block_group *block_group) { diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 27d06bb5e5c0..cca1acf2e037 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1552,6 +1552,7 @@ struct btrfs_drop_extents_args { struct btrfs_file_private { void *filldir_buf; + u64 last_index; }; diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 0b62ce77053f..63b7fa706743 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -197,7 +197,7 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode, start = round_down(start, fs_info->sectorsize); btrfs_free_reserved_data_space_noquota(fs_info, len); - btrfs_qgroup_free_data(inode, reserved, start, len); + btrfs_qgroup_free_data(inode, reserved, start, len, NULL); } /** @@ -243,7 +243,6 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv = &inode->block_rsv; u64 reserve_size = 0; u64 qgroup_rsv_size = 0; - u64 csum_leaves; unsigned outstanding_extents; lockdep_assert_held(&inode->lock); @@ -258,10 +257,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, outstanding_extents); reserve_size += btrfs_calc_metadata_size(fs_info, 1); } - csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, - inode->csum_bytes); - reserve_size += btrfs_calc_insert_metadata_size(fs_info, - csum_leaves); + if (!(inode->flags & BTRFS_INODE_NODATASUM)) { + u64 csum_leaves; + + csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes); + reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves); + } /* * For qgroup rsv, the calculation is very simple: * account one nodesize for each outstanding extent @@ -276,14 +277,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, spin_unlock(&block_rsv->lock); } -static void calc_inode_reservations(struct btrfs_fs_info *fs_info, +static void calc_inode_reservations(struct btrfs_inode *inode, u64 num_bytes, u64 disk_num_bytes, u64 *meta_reserve, u64 *qgroup_reserve) { + struct btrfs_fs_info *fs_info = inode->root->fs_info; u64 nr_extents = count_max_extents(fs_info, num_bytes); - u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); + u64 csum_leaves; u64 inode_update = btrfs_calc_metadata_size(fs_info, 1); + if (inode->flags & BTRFS_INODE_NODATASUM) + csum_leaves = 0; + else + csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); + *meta_reserve = btrfs_calc_insert_metadata_size(fs_info, nr_extents + csum_leaves); @@ -335,7 +342,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, * everything out and try again, which is bad. This way we just * over-reserve slightly, and clean up the mess when we are done. */ - calc_inode_reservations(fs_info, num_bytes, disk_num_bytes, + calc_inode_reservations(inode, num_bytes, disk_num_bytes, &meta_reserve, &qgroup_reserve); ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true, noflush); @@ -356,7 +363,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, spin_lock(&inode->lock); nr_extents = count_max_extents(fs_info, num_bytes); btrfs_mod_outstanding_extents(inode, nr_extents); - inode->csum_bytes += disk_num_bytes; + if (!(inode->flags & BTRFS_INODE_NODATASUM)) + inode->csum_bytes += disk_num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); @@ -390,7 +398,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, num_bytes = ALIGN(num_bytes, fs_info->sectorsize); spin_lock(&inode->lock); - inode->csum_bytes -= num_bytes; + if (!(inode->flags & BTRFS_INODE_NODATASUM)) + inode->csum_bytes -= num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 1331e56e8e84..c6426080cf0a 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1665,6 +1665,7 @@ int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode) } bool btrfs_readdir_get_delayed_items(struct inode *inode, + u64 last_index, struct list_head *ins_list, struct list_head *del_list) { @@ -1684,14 +1685,14 @@ bool btrfs_readdir_get_delayed_items(struct inode *inode, mutex_lock(&delayed_node->mutex); item = __btrfs_first_delayed_insertion_item(delayed_node); - while (item) { + while (item && item->index <= last_index) { refcount_inc(&item->refs); list_add_tail(&item->readdir_list, ins_list); item = __btrfs_next_delayed_item(item); } item = __btrfs_first_delayed_deletion_item(delayed_node); - while (item) { + while (item && item->index <= last_index) { refcount_inc(&item->refs); list_add_tail(&item->readdir_list, del_list); item = __btrfs_next_delayed_item(item); diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index 0163ca637a96..fc6fae9640f8 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -148,6 +148,7 @@ void btrfs_destroy_delayed_inodes(struct btrfs_fs_info *fs_info); /* Used for readdir() */ bool btrfs_readdir_get_delayed_items(struct inode *inode, + u64 last_index, struct list_head *ins_list, struct list_head *del_list); void btrfs_readdir_put_delayed_items(struct inode *inode, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 40152458e7b7..0d1b05ded1e3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1662,8 +1662,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { - /* Shouldn't get preallocated anon_dev for cached roots */ - ASSERT(!anon_dev); + /* + * Some other caller may have read out the newly inserted + * subvolume already (for things like backref walk etc). Not + * that common but still possible. In that case, we just need + * to free the anon_dev. + */ + if (unlikely(anon_dev)) { + free_anon_bdev(anon_dev); + anon_dev = 0; + } + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 2a7c9088fe1f..0d2cc186974d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1209,7 +1209,8 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, u64 bytes_left, end; u64 aligned_start = ALIGN(start, 1 << 9); - if (WARN_ON(start != aligned_start)) { + /* Adjust the range to be aligned to 512B sectors if necessary. */ + if (start != aligned_start) { len -= aligned_start - start; len = round_down(len, 1 << 9); start = aligned_start; @@ -4206,6 +4207,42 @@ static int prepare_allocation_clustered(struct btrfs_fs_info *fs_info, return 0; } +static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info, + struct find_free_extent_ctl *ffe_ctl) +{ + if (ffe_ctl->for_treelog) { + spin_lock(&fs_info->treelog_bg_lock); + if (fs_info->treelog_bg) + ffe_ctl->hint_byte = fs_info->treelog_bg; + spin_unlock(&fs_info->treelog_bg_lock); + } else if (ffe_ctl->for_data_reloc) { + spin_lock(&fs_info->relocation_bg_lock); + if (fs_info->data_reloc_bg) + ffe_ctl->hint_byte = fs_info->data_reloc_bg; + spin_unlock(&fs_info->relocation_bg_lock); + } else if (ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA) { + struct btrfs_block_group *block_group; + + spin_lock(&fs_info->zone_active_bgs_lock); + list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) { + /* + * No lock is OK here because avail is monotinically + * decreasing, and this is just a hint. + */ + u64 avail = block_group->zone_capacity - block_group->alloc_offset; + + if (block_group_bits(block_group, ffe_ctl->flags) && + avail >= ffe_ctl->num_bytes) { + ffe_ctl->hint_byte = block_group->start; + break; + } + } + spin_unlock(&fs_info->zone_active_bgs_lock); + } + + return 0; +} + static int prepare_allocation(struct btrfs_fs_info *fs_info, struct find_free_extent_ctl *ffe_ctl, struct btrfs_space_info *space_info, @@ -4216,19 +4253,7 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info, return prepare_allocation_clustered(fs_info, ffe_ctl, space_info, ins); case BTRFS_EXTENT_ALLOC_ZONED: - if (ffe_ctl->for_treelog) { - spin_lock(&fs_info->treelog_bg_lock); - if (fs_info->treelog_bg) - ffe_ctl->hint_byte = fs_info->treelog_bg; - spin_unlock(&fs_info->treelog_bg_lock); - } - if (ffe_ctl->for_data_reloc) { - spin_lock(&fs_info->relocation_bg_lock); - if (fs_info->data_reloc_bg) - ffe_ctl->hint_byte = fs_info->data_reloc_bg; - spin_unlock(&fs_info->relocation_bg_lock); - } - return 0; + return prepare_allocation_zoned(fs_info, ffe_ctl); default: BUG(); } diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index b14d2da9b26d..14478da87531 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -602,7 +602,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, } sums->bytenr = start; - sums->len = (int)size; + sums->len = size; offset = (start - key.offset) >> fs_info->sectorsize_bits; offset *= csum_size; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0a46fff3dd06..1783a0fbf166 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3191,7 +3191,7 @@ static long btrfs_fallocate(struct file *file, int mode, qgroup_reserved -= range->len; } else if (qgroup_reserved > 0) { btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved, - range->start, range->len); + range->start, range->len, NULL); qgroup_reserved -= range->len; } list_del(&range->list); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 4cd8e44cba4c..b27795e13ff3 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2685,13 +2685,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold); spin_lock(&ctl->tree_lock); - /* Count initial region as zone_unusable until it gets activated. */ if (!used) to_free = size; - else if (initial && - test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &block_group->fs_info->flags) && - (block_group->flags & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM))) - to_free = 0; else if (initial) to_free = block_group->zone_capacity; else if (offset >= block_group->alloc_offset) @@ -2719,8 +2714,7 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, reclaimable_unusable = block_group->zone_unusable - (block_group->length - block_group->zone_capacity); /* All the region is now unusable. Mark it as unused and reclaim */ - if (block_group->zone_unusable == block_group->length && - block_group->alloc_offset) { + if (block_group->zone_unusable == block_group->length) { btrfs_mark_bg_unused(block_group); } else if (bg_reclaim_threshold && reclaimable_unusable >= diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 81eac121c6b2..f7f4bcc09464 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -466,7 +466,7 @@ out: * And at reserve time, it's always aligned to page size, so * just free one page here. */ - btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE, NULL); btrfs_free_path(path); btrfs_end_transaction(trans); return ret; @@ -3364,8 +3364,23 @@ out: unwritten_start += logical_len; clear_extent_uptodate(io_tree, unwritten_start, end, NULL); - /* Drop extent maps for the part of the extent we didn't write. */ - btrfs_drop_extent_map_range(inode, unwritten_start, end, false); + /* + * Drop extent maps for the part of the extent we didn't write. + * + * We have an exception here for the free_space_inode, this is + * because when we do btrfs_get_extent() on the free space inode + * we will search the commit root. If this is a new block group + * we won't find anything, and we will trip over the assert in + * writepage where we do ASSERT(em->block_start != + * EXTENT_MAP_HOLE). + * + * Theoretically we could also skip this for any NOCOW extent as + * we don't mess with the extent map tree in the NOCOW case, but + * for now simply skip this if we are the free space inode. + */ + if (!btrfs_is_free_space_inode(inode)) + btrfs_drop_extent_map_range(inode, unwritten_start, + end, false); /* * If the ordered extent had an IOERR or something else went @@ -4689,6 +4704,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) u64 root_flags; int ret; + down_write(&fs_info->subvol_sem); + /* * Don't allow to delete a subvolume with send in progress. This is * inside the inode lock so the error handling that has to drop the bit @@ -4700,25 +4717,25 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) btrfs_warn(fs_info, "attempt to delete subvolume %llu during send", dest->root_key.objectid); - return -EPERM; + ret = -EPERM; + goto out_up_write; } if (atomic_read(&dest->nr_swapfiles)) { spin_unlock(&dest->root_item_lock); btrfs_warn(fs_info, "attempt to delete subvolume %llu with active swapfile", root->root_key.objectid); - return -EPERM; + ret = -EPERM; + goto out_up_write; } root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags | BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock); - down_write(&fs_info->subvol_sem); - ret = may_destroy_subvol(dest); if (ret) - goto out_up_write; + goto out_undead; btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); /* @@ -4728,7 +4745,7 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) */ ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); if (ret) - goto out_up_write; + goto out_undead; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { @@ -4794,15 +4811,17 @@ out_end_trans: inode->i_flags |= S_DEAD; out_release: btrfs_subvolume_release_metadata(root, &block_rsv); -out_up_write: - up_write(&fs_info->subvol_sem); +out_undead: if (ret) { spin_lock(&dest->root_item_lock); root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags & ~BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock); - } else { + } +out_up_write: + up_write(&fs_info->subvol_sem); + if (!ret) { d_invalidate(dentry); btrfs_prune_dentries(dest); ASSERT(dest->send_in_progress == 0); @@ -5372,7 +5391,7 @@ static void evict_inode_truncate_pages(struct inode *inode) */ if (state_flags & EXTENT_DELALLOC) btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start, - end - start + 1); + end - start + 1, NULL); clear_extent_bit(io_tree, start, end, EXTENT_CLEAR_ALL_BITS | EXTENT_DO_ACCOUNTING, @@ -5949,6 +5968,78 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, } /* + * Find the highest existing sequence number in a directory and then set the + * in-memory index_cnt variable to the first free sequence number. + */ +static int btrfs_set_inode_index_count(struct btrfs_inode *inode) +{ + struct btrfs_root *root = inode->root; + struct btrfs_key key, found_key; + struct btrfs_path *path; + struct extent_buffer *leaf; + int ret; + + key.objectid = btrfs_ino(inode); + key.type = BTRFS_DIR_INDEX_KEY; + key.offset = (u64)-1; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out; + /* FIXME: we should be able to handle this */ + if (ret == 0) + goto out; + ret = 0; + + if (path->slots[0] == 0) { + inode->index_cnt = BTRFS_DIR_START_INDEX; + goto out; + } + + path->slots[0]--; + + leaf = path->nodes[0]; + btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); + + if (found_key.objectid != btrfs_ino(inode) || + found_key.type != BTRFS_DIR_INDEX_KEY) { + inode->index_cnt = BTRFS_DIR_START_INDEX; + goto out; + } + + inode->index_cnt = found_key.offset + 1; +out: + btrfs_free_path(path); + return ret; +} + +static int btrfs_get_dir_last_index(struct btrfs_inode *dir, u64 *index) +{ + int ret = 0; + + btrfs_inode_lock(&dir->vfs_inode, 0); + if (dir->index_cnt == (u64)-1) { + ret = btrfs_inode_delayed_dir_index_count(dir); + if (ret) { + ret = btrfs_set_inode_index_count(dir); + if (ret) + goto out; + } + } + + /* index_cnt is the index number of next new entry, so decrement it. */ + *index = dir->index_cnt - 1; +out: + btrfs_inode_unlock(&dir->vfs_inode, 0); + + return ret; +} + +/* * All this infrastructure exists because dir_emit can fault, and we are holding * the tree lock when doing readdir. For now just allocate a buffer and copy * our information into that, and then dir_emit from the buffer. This is @@ -5960,10 +6051,17 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, static int btrfs_opendir(struct inode *inode, struct file *file) { struct btrfs_file_private *private; + u64 last_index; + int ret; + + ret = btrfs_get_dir_last_index(BTRFS_I(inode), &last_index); + if (ret) + return ret; private = kzalloc(sizeof(struct btrfs_file_private), GFP_KERNEL); if (!private) return -ENOMEM; + private->last_index = last_index; private->filldir_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!private->filldir_buf) { kfree(private); @@ -5973,6 +6071,19 @@ static int btrfs_opendir(struct inode *inode, struct file *file) return 0; } +static loff_t btrfs_dir_llseek(struct file *file, loff_t offset, int whence) +{ + struct btrfs_file_private *private = file->private_data; + int ret; + + ret = btrfs_get_dir_last_index(BTRFS_I(file_inode(file)), + &private->last_index); + if (ret) + return ret; + + return generic_file_llseek(file, offset, whence); +} + struct dir_entry { u64 ino; u64 offset; @@ -6030,7 +6141,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) INIT_LIST_HEAD(&ins_list); INIT_LIST_HEAD(&del_list); - put = btrfs_readdir_get_delayed_items(inode, &ins_list, &del_list); + put = btrfs_readdir_get_delayed_items(inode, private->last_index, + &ins_list, &del_list); again: key.type = BTRFS_DIR_INDEX_KEY; @@ -6047,6 +6159,8 @@ again: break; if (found_key.offset < ctx->pos) continue; + if (found_key.offset > private->last_index) + break; if (btrfs_should_delete_dir_index(&del_list, found_key.offset)) continue; di = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item); @@ -6183,57 +6297,6 @@ static int btrfs_update_time(struct inode *inode, struct timespec64 *now, } /* - * find the highest existing sequence number in a directory - * and then set the in-memory index_cnt variable to reflect - * free sequence numbers - */ -static int btrfs_set_inode_index_count(struct btrfs_inode *inode) -{ - struct btrfs_root *root = inode->root; - struct btrfs_key key, found_key; - struct btrfs_path *path; - struct extent_buffer *leaf; - int ret; - - key.objectid = btrfs_ino(inode); - key.type = BTRFS_DIR_INDEX_KEY; - key.offset = (u64)-1; - - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out; - /* FIXME: we should be able to handle this */ - if (ret == 0) - goto out; - ret = 0; - - if (path->slots[0] == 0) { - inode->index_cnt = BTRFS_DIR_START_INDEX; - goto out; - } - - path->slots[0]--; - - leaf = path->nodes[0]; - btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - - if (found_key.objectid != btrfs_ino(inode) || - found_key.type != BTRFS_DIR_INDEX_KEY) { - inode->index_cnt = BTRFS_DIR_START_INDEX; - goto out; - } - - inode->index_cnt = found_key.offset + 1; -out: - btrfs_free_path(path); - return ret; -} - -/* * helper to find a free sequence number in a given directory. This current * code is very simple, later versions will do smarter things in the btree */ @@ -8440,7 +8503,7 @@ next: * reserved data space. * Since the IO will never happen for this page. */ - btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur); + btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur, NULL); if (!inode_evicting) { clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_UPTODATE | @@ -9902,7 +9965,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( struct btrfs_path *path; u64 start = ins->objectid; u64 len = ins->offset; - int qgroup_released; + u64 qgroup_released = 0; int ret; memset(&stack_fi, 0, sizeof(stack_fi)); @@ -9915,9 +9978,9 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE); /* Encryption and other encoding is reserved and all 0 */ - qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len); - if (qgroup_released < 0) - return ERR_PTR(qgroup_released); + ret = btrfs_qgroup_release_data(inode, file_offset, len, &qgroup_released); + if (ret < 0) + return ERR_PTR(ret); if (trans) { ret = insert_reserved_file_extent(trans, inode, @@ -10726,6 +10789,13 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE) return -EINVAL; + /* + * Compressed extents should always have checksums, so error out if we + * have a NOCOW file or inode was created while mounted with NODATASUM. + */ + if (inode->flags & BTRFS_INODE_NODATASUM) + return -EINVAL; + orig_count = iov_iter_count(from); /* The extent size must be sane. */ @@ -10903,7 +10973,7 @@ out_delalloc_release: btrfs_delalloc_release_metadata(inode, disk_num_bytes, ret < 0); out_qgroup_free_data: if (ret < 0) - btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes); + btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes, NULL); out_free_data_space: /* * If btrfs_reserve_extent() succeeded, then we already decremented @@ -11401,7 +11471,7 @@ static const struct inode_operations btrfs_dir_inode_operations = { }; static const struct file_operations btrfs_dir_file_operations = { - .llseek = generic_file_llseek, + .llseek = btrfs_dir_llseek, .read = generic_read_dir, .iterate_shared = btrfs_real_readdir, .open = btrfs_opendir, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index e8e4781c48a5..196e222749cc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -780,6 +780,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, return -EOPNOTSUPP; } + if (btrfs_root_refs(&root->root_item) == 0) + return -ENOENT; + if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) return -EINVAL; @@ -3500,6 +3503,10 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) ret = -EFAULT; goto out; } + if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) { + ret = -EOPNOTSUPP; + goto out; + } /* compression requires us to start the IO */ if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { range.flags |= BTRFS_DEFRAG_RANGE_START_IO; @@ -4688,6 +4695,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) goto out; } + if (sa->create && is_fstree(sa->qgroupid)) { + ret = -EINVAL; + goto out; + } + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 0321753c16b9..1b2af4785c0e 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -172,11 +172,12 @@ int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, struct rb_node *node; struct btrfs_ordered_extent *entry; int ret; + u64 qgroup_rsv = 0; if (flags & ((1 << BTRFS_ORDERED_NOCOW) | (1 << BTRFS_ORDERED_PREALLOC))) { /* For nocow write, we can release the qgroup rsv right now */ - ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes); + ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes, &qgroup_rsv); if (ret < 0) return ret; ret = 0; @@ -185,7 +186,7 @@ int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, * The ordered extent has reserved qgroup space, release now * and pass the reserved number for qgroup_record to free. */ - ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes); + ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes, &qgroup_rsv); if (ret < 0) return ret; } @@ -203,7 +204,7 @@ int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, entry->inode = igrab(&inode->vfs_inode); entry->compress_type = compress_type; entry->truncated_len = (u64)-1; - entry->qgroup_rsv = ret; + entry->qgroup_rsv = qgroup_rsv; entry->physical = (u64)-1; ASSERT((flags & ~BTRFS_ORDERED_TYPE_FLAGS) == 0); diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index f59f2dbdb25e..cc3ca4bb9bd5 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -20,7 +20,7 @@ struct btrfs_ordered_sum { /* * this is the length in bytes covered by the sums array below. */ - int len; + u32 len; struct list_head list; /* last field is a variable length array of csums */ u8 sums[]; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 26cabffd5971..b3472bf6b288 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1635,6 +1635,15 @@ out: return ret; } +static bool qgroup_has_usage(struct btrfs_qgroup *qgroup) +{ + return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 || + qgroup->excl > 0 || qgroup->excl_cmpr > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0); +} + int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -1654,6 +1663,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) goto out; } + if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) { + ret = -EBUSY; + goto out; + } + /* Check if there are no children of this qgroup */ if (!list_empty(&qgroup->members)) { ret = -EBUSY; @@ -3833,13 +3847,14 @@ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, /* Free ranges specified by @reserved, normally in error path */ static int qgroup_free_reserved_data(struct btrfs_inode *inode, - struct extent_changeset *reserved, u64 start, u64 len) + struct extent_changeset *reserved, + u64 start, u64 len, u64 *freed_ret) { struct btrfs_root *root = inode->root; struct ulist_node *unode; struct ulist_iterator uiter; struct extent_changeset changeset; - int freed = 0; + u64 freed = 0; int ret; extent_changeset_init(&changeset); @@ -3880,7 +3895,9 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode, } btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed, BTRFS_QGROUP_RSV_DATA); - ret = freed; + if (freed_ret) + *freed_ret = freed; + ret = 0; out: extent_changeset_release(&changeset); return ret; @@ -3888,7 +3905,7 @@ out: static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, - int free) + u64 *released, int free) { struct extent_changeset changeset; int trace_op = QGROUP_RELEASE; @@ -3900,7 +3917,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, /* In release case, we shouldn't have @reserved */ WARN_ON(!free && reserved); if (free && reserved) - return qgroup_free_reserved_data(inode, reserved, start, len); + return qgroup_free_reserved_data(inode, reserved, start, len, released); extent_changeset_init(&changeset); ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1, EXTENT_QGROUP_RESERVED, &changeset); @@ -3915,7 +3932,8 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, btrfs_qgroup_free_refroot(inode->root->fs_info, inode->root->root_key.objectid, changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); - ret = changeset.bytes_changed; + if (released) + *released = changeset.bytes_changed; out: extent_changeset_release(&changeset); return ret; @@ -3934,9 +3952,10 @@ out: * NOTE: This function may sleep for memory allocation. */ int btrfs_qgroup_free_data(struct btrfs_inode *inode, - struct extent_changeset *reserved, u64 start, u64 len) + struct extent_changeset *reserved, + u64 start, u64 len, u64 *freed) { - return __btrfs_qgroup_release_data(inode, reserved, start, len, 1); + return __btrfs_qgroup_release_data(inode, reserved, start, len, freed, 1); } /* @@ -3954,9 +3973,9 @@ int btrfs_qgroup_free_data(struct btrfs_inode *inode, * * NOTE: This function may sleep for memory allocation. */ -int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len) +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released) { - return __btrfs_qgroup_release_data(inode, NULL, start, len, 0); + return __btrfs_qgroup_release_data(inode, NULL, start, len, released, 0); } static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes, diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 578c77e94200..c382923f7628 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -360,10 +360,10 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, /* New io_tree based accurate qgroup reserve API */ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len); -int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len); +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released); int btrfs_qgroup_free_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, - u64 len); + u64 len, u64 *freed); int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce); int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 4b052d4009d3..8083fe866d2b 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -883,8 +883,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, out_unlock: spin_unlock(&fs_info->ref_verify_lock); out: - if (ret) + if (ret) { + btrfs_free_ref_cache(fs_info); btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); + } return ret; } @@ -1015,8 +1017,8 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) } } if (ret) { - btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); btrfs_free_ref_cache(fs_info); + btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); } btrfs_free_path(path); return ret; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 4a4d65b5e24f..a75669972dc7 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -7852,7 +7852,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) } if (arg->flags & ~BTRFS_SEND_FLAG_MASK) { - ret = -EINVAL; + ret = -EOPNOTSUPP; goto out; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 74fef1f49c35..fc468d1079c2 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1704,6 +1704,10 @@ static ssize_t btrfs_devinfo_scrub_speed_max_store(struct kobject *kobj, unsigned long long limit; limit = memparse(buf, &endptr); + /* There could be trailing '\n', also catch any typos after the value. */ + endptr = skip_spaces(endptr); + if (*endptr != 0) + return -EINVAL; WRITE_ONCE(device->scrub_speed_max, limit); return len; } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 2b39c7f9226f..02e8398246ae 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1399,7 +1399,7 @@ static int check_extent_item(struct extent_buffer *leaf, if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) { extent_err(leaf, slot, "inline ref item overflows extent item, ptr %lu iref size %u end %lu", - ptr, inline_type, end); + ptr, btrfs_extent_inline_ref_size(inline_type), end); return -EUCLEAN; } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 675dbed075d8..99cb690da989 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1574,19 +1574,9 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) return; WARN_ON(cache->bytes_super != 0); - - /* Check for block groups never get activated */ - if (test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &cache->fs_info->flags) && - cache->flags & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM) && - !test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &cache->runtime_flags) && - cache->alloc_offset == 0) { - unusable = cache->length; - free = 0; - } else { - unusable = (cache->alloc_offset - cache->used) + - (cache->length - cache->zone_capacity); - free = cache->zone_capacity - cache->alloc_offset; - } + unusable = (cache->alloc_offset - cache->used) + + (cache->length - cache->zone_capacity); + free = cache->zone_capacity - cache->alloc_offset; /* We only need ->free_space in ALLOC_SEQ block groups */ cache->cached = BTRFS_CACHE_FINISHED; @@ -1882,7 +1872,6 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info, bool btrfs_zone_activate(struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; - struct btrfs_space_info *space_info = block_group->space_info; struct map_lookup *map; struct btrfs_device *device; u64 physical; @@ -1894,7 +1883,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) map = block_group->physical_map; - spin_lock(&space_info->lock); spin_lock(&block_group->lock); if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) { ret = true; @@ -1923,14 +1911,7 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) /* Successfully activated all the zones */ set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags); - WARN_ON(block_group->alloc_offset != 0); - if (block_group->zone_unusable == block_group->length) { - block_group->zone_unusable = block_group->length - block_group->zone_capacity; - space_info->bytes_zone_unusable -= block_group->zone_capacity; - } spin_unlock(&block_group->lock); - btrfs_try_granting_tickets(fs_info, space_info); - spin_unlock(&space_info->lock); /* For the active block group list */ btrfs_get_block_group(block_group); @@ -1943,7 +1924,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) out_unlock: spin_unlock(&block_group->lock); - spin_unlock(&space_info->lock); return ret; } diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c index 7077f72e6f47..f449f7340aad 100644 --- a/fs/cachefiles/cache.c +++ b/fs/cachefiles/cache.c @@ -168,6 +168,8 @@ error_unsupported: dput(root); error_open_root: cachefiles_end_secure(cache, saved_cred); + put_cred(cache->cache_cred); + cache->cache_cred = NULL; error_getsec: fscache_relinquish_cache(cache_cookie); cache->cache = NULL; diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index aa4efcabb5e3..5f4df9588620 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -805,6 +805,7 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) cachefiles_put_directory(cache->graveyard); cachefiles_put_directory(cache->store); mntput(cache->mnt); + put_cred(cache->cache_cred); kfree(cache->rootdirname); kfree(cache->secctx); diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 03ca8f2f657a..50b2ee163af6 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -584,6 +584,8 @@ static bool cachefiles_open_file(struct cachefiles_object *object, if (ret < 0) goto check_failed; + clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &object->cookie->flags); + object->file = file; /* Always update the atime on an object we've just looked up (this is diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 177d8e8d73fe..de1dee46d3df 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -36,6 +36,8 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) &ci->i_vino, sizeof(ci->i_vino), &ci->i_version, sizeof(ci->i_version), i_size_read(inode)); + if (ci->netfs.cache) + mapping_set_release_always(inode->i_mapping); } void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 36052a362683..57603782e7e2 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1391,7 +1391,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, if (flushing & CEPH_CAP_XATTR_EXCL) { arg->old_xattr_buf = __ceph_build_xattrs_blob(ci); arg->xattr_version = ci->i_xattrs.version; - arg->xattr_buf = ci->i_xattrs.blob; + arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob); } else { arg->xattr_buf = NULL; arg->old_xattr_buf = NULL; @@ -1457,6 +1457,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci) encode_cap_msg(msg, arg); ceph_con_send(&arg->session->s_con, msg); ceph_buffer_put(arg->old_xattr_buf); + ceph_buffer_put(arg->xattr_buf); if (arg->wake) wake_up_all(&ci->i_cap_wq); } @@ -4597,12 +4598,14 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, struct inode *dir, int mds, int drop, int unless) { - struct dentry *parent = NULL; struct ceph_mds_request_release *rel = *p; struct ceph_dentry_info *di = ceph_dentry(dentry); int force = 0; int ret; + /* This shouldn't happen */ + BUG_ON(!dir); + /* * force an record for the directory caps if we have a dentry lease. * this is racy (can't take i_ceph_lock and d_lock together), but it @@ -4612,14 +4615,9 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, spin_lock(&dentry->d_lock); if (di->lease_session && di->lease_session->s_mds == mds) force = 1; - if (!dir) { - parent = dget(dentry->d_parent); - dir = d_inode(parent); - } spin_unlock(&dentry->d_lock); ret = ceph_encode_inode_release(p, dir, mds, drop, unless, force); - dput(parent); spin_lock(&dentry->d_lock); if (ret && di->lease_session && di->lease_session->s_mds == mds) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 82874be94524..da9fcf48ab6c 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3650,11 +3650,11 @@ static void handle_session(struct ceph_mds_session *session, if (session->s_state == CEPH_MDS_SESSION_RECONNECTING) pr_info("mds%d reconnect success\n", session->s_mds); + session->s_features = features; if (session->s_state == CEPH_MDS_SESSION_OPEN) { pr_notice("mds%d is already opened\n", session->s_mds); } else { session->s_state = CEPH_MDS_SESSION_OPEN; - session->s_features = features; renewed_caps(mdsc, session, 0); if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features)) diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index f7fcf7f08ec6..ca4932e6f71b 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -194,10 +194,10 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc) } /* - * This function walks through the snaprealm for an inode and returns the - * ceph_snap_realm for the first snaprealm that has quotas set (max_files, + * This function walks through the snaprealm for an inode and set the + * realmp with the first snaprealm that has quotas set (max_files, * max_bytes, or any, depending on the 'which_quota' argument). If the root is - * reached, return the root ceph_snap_realm instead. + * reached, set the realmp with the root ceph_snap_realm instead. * * Note that the caller is responsible for calling ceph_put_snap_realm() on the * returned realm. @@ -208,18 +208,19 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc) * this function will return -EAGAIN; otherwise, the snaprealms walk-through * will be restarted. */ -static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc, - struct inode *inode, - enum quota_get_realm which_quota, - bool retry) +static int get_quota_realm(struct ceph_mds_client *mdsc, struct inode *inode, + enum quota_get_realm which_quota, + struct ceph_snap_realm **realmp, bool retry) { struct ceph_inode_info *ci = NULL; struct ceph_snap_realm *realm, *next; struct inode *in; bool has_quota; + if (realmp) + *realmp = NULL; if (ceph_snap(inode) != CEPH_NOSNAP) - return NULL; + return 0; restart: realm = ceph_inode(inode)->i_snap_realm; @@ -245,7 +246,7 @@ restart: break; ceph_put_snap_realm(mdsc, realm); if (!retry) - return ERR_PTR(-EAGAIN); + return -EAGAIN; goto restart; } @@ -254,8 +255,11 @@ restart: iput(in); next = realm->parent; - if (has_quota || !next) - return realm; + if (has_quota || !next) { + if (realmp) + *realmp = realm; + return 0; + } ceph_get_snap_realm(mdsc, next); ceph_put_snap_realm(mdsc, realm); @@ -264,7 +268,7 @@ restart: if (realm) ceph_put_snap_realm(mdsc, realm); - return NULL; + return 0; } bool ceph_quota_is_same_realm(struct inode *old, struct inode *new) @@ -272,6 +276,7 @@ bool ceph_quota_is_same_realm(struct inode *old, struct inode *new) struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(old->i_sb); struct ceph_snap_realm *old_realm, *new_realm; bool is_same; + int ret; restart: /* @@ -281,9 +286,9 @@ restart: * dropped and we can then restart the whole operation. */ down_read(&mdsc->snap_rwsem); - old_realm = get_quota_realm(mdsc, old, QUOTA_GET_ANY, true); - new_realm = get_quota_realm(mdsc, new, QUOTA_GET_ANY, false); - if (PTR_ERR(new_realm) == -EAGAIN) { + get_quota_realm(mdsc, old, QUOTA_GET_ANY, &old_realm, true); + ret = get_quota_realm(mdsc, new, QUOTA_GET_ANY, &new_realm, false); + if (ret == -EAGAIN) { up_read(&mdsc->snap_rwsem); if (old_realm) ceph_put_snap_realm(mdsc, old_realm); @@ -485,8 +490,8 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf) bool is_updated = false; down_read(&mdsc->snap_rwsem); - realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root), - QUOTA_GET_MAX_BYTES, true); + get_quota_realm(mdsc, d_inode(fsc->sb->s_root), QUOTA_GET_MAX_BYTES, + &realm, true); up_read(&mdsc->snap_rwsem); if (!realm) return false; diff --git a/fs/dcache.c b/fs/dcache.c index 52e6d5fdab6b..b09bc88dbbec 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -787,12 +787,12 @@ static inline bool fast_dput(struct dentry *dentry) */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); - if (dentry->d_lockref.count > 1) { - dentry->d_lockref.count--; + if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } - return false; + dentry->d_lockref.count--; + goto locked; } /* @@ -850,6 +850,7 @@ static inline bool fast_dput(struct dentry *dentry) * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ +locked: if (dentry->d_lockref.count) { spin_unlock(&dentry->d_lock); return true; diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index b54f470e0d03..b38304b44476 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -84,6 +84,14 @@ int debugfs_file_get(struct dentry *dentry) struct debugfs_fsdata *fsd; void *d_fsd; + /* + * This could only happen if some debugfs user erroneously calls + * debugfs_file_get() on a dentry that isn't even a file, let + * them know about it. + */ + if (WARN_ON(!d_is_reg(dentry))) + return -EINVAL; + d_fsd = READ_ONCE(dentry->d_fsdata); if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) { fsd = d_fsd; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 2e8e112b1993..08ef685167ec 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -237,17 +237,19 @@ static const struct super_operations debugfs_super_operations = { static void debugfs_release_dentry(struct dentry *dentry) { - void *fsd = dentry->d_fsdata; + struct debugfs_fsdata *fsd = dentry->d_fsdata; - if (!((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) - kfree(dentry->d_fsdata); + if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) + return; + + kfree(fsd); } static struct vfsmount *debugfs_automount(struct path *path) { - debugfs_automount_t f; - f = (debugfs_automount_t)path->dentry->d_fsdata; - return f(path->dentry, d_inode(path->dentry)->i_private); + struct debugfs_fsdata *fsd = path->dentry->d_fsdata; + + return fsd->automount(path->dentry, d_inode(path->dentry)->i_private); } static const struct dentry_operations debugfs_dops = { @@ -635,13 +637,23 @@ struct dentry *debugfs_create_automount(const char *name, void *data) { struct dentry *dentry = start_creating(name, parent); + struct debugfs_fsdata *fsd; struct inode *inode; if (IS_ERR(dentry)) return dentry; + fsd = kzalloc(sizeof(*fsd), GFP_KERNEL); + if (!fsd) { + failed_creating(dentry); + return ERR_PTR(-ENOMEM); + } + + fsd->automount = f; + if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); + kfree(fsd); return ERR_PTR(-EPERM); } @@ -649,13 +661,14 @@ struct dentry *debugfs_create_automount(const char *name, if (unlikely(!inode)) { pr_err("out of free dentries, can not create automount '%s'\n", name); + kfree(fsd); return failed_creating(dentry); } make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; inode->i_private = data; - dentry->d_fsdata = (void *)f; + dentry->d_fsdata = fsd; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h index 92af8ae31313..f7c489b5a368 100644 --- a/fs/debugfs/internal.h +++ b/fs/debugfs/internal.h @@ -17,8 +17,14 @@ extern const struct file_operations debugfs_full_proxy_file_operations; struct debugfs_fsdata { const struct file_operations *real_fops; - refcount_t active_users; - struct completion active_users_drained; + union { + /* automount_fn is used when real_fops is NULL */ + debugfs_automount_t automount; + struct { + refcount_t active_users; + struct completion active_users_drained; + }; + }; }; /* diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 6ed09edabea0..2c797eb519da 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -174,7 +174,7 @@ static LIST_HEAD(dlm_node_addrs); static DEFINE_SPINLOCK(dlm_node_addrs_spin); static struct listen_connection listen_con; -static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT]; +static struct sockaddr_storage dlm_local_addr[DLM_MAX_ADDR_COUNT]; static int dlm_local_count; int dlm_allow_conn; @@ -398,7 +398,7 @@ static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out, if (!sa_out) return 0; - if (dlm_local_addr[0]->ss_family == AF_INET) { + if (dlm_local_addr[0].ss_family == AF_INET) { struct sockaddr_in *in4 = (struct sockaddr_in *) &sas; struct sockaddr_in *ret4 = (struct sockaddr_in *) sa_out; ret4->sin_addr.s_addr = in4->sin_addr.s_addr; @@ -727,7 +727,7 @@ static void add_sock(struct socket *sock, struct connection *con) static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port, int *addr_len) { - saddr->ss_family = dlm_local_addr[0]->ss_family; + saddr->ss_family = dlm_local_addr[0].ss_family; if (saddr->ss_family == AF_INET) { struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr; in4_addr->sin_port = cpu_to_be16(port); @@ -1167,7 +1167,7 @@ static int sctp_bind_addrs(struct socket *sock, uint16_t port) int i, addr_len, result = 0; for (i = 0; i < dlm_local_count; i++) { - memcpy(&localaddr, dlm_local_addr[i], sizeof(localaddr)); + memcpy(&localaddr, &dlm_local_addr[i], sizeof(localaddr)); make_sockaddr(&localaddr, port, &addr_len); if (!i) @@ -1187,7 +1187,7 @@ static int sctp_bind_addrs(struct socket *sock, uint16_t port) /* Get local addresses */ static void init_local(void) { - struct sockaddr_storage sas, *addr; + struct sockaddr_storage sas; int i; dlm_local_count = 0; @@ -1195,21 +1195,10 @@ static void init_local(void) if (dlm_our_addr(&sas, i)) break; - addr = kmemdup(&sas, sizeof(*addr), GFP_NOFS); - if (!addr) - break; - dlm_local_addr[dlm_local_count++] = addr; + memcpy(&dlm_local_addr[dlm_local_count++], &sas, sizeof(sas)); } } -static void deinit_local(void) -{ - int i; - - for (i = 0; i < dlm_local_count; i++) - kfree(dlm_local_addr[i]); -} - static struct writequeue_entry *new_writequeue_entry(struct connection *con) { struct writequeue_entry *entry; @@ -1575,7 +1564,7 @@ static void dlm_connect(struct connection *con) } /* Create a socket to communicate with */ - result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, + result = sock_create_kern(&init_net, dlm_local_addr[0].ss_family, SOCK_STREAM, dlm_proto_ops->proto, &sock); if (result < 0) goto socket_err; @@ -1786,7 +1775,6 @@ void dlm_lowcomms_stop(void) foreach_conn(free_conn); srcu_read_unlock(&connections_srcu, idx); work_stop(); - deinit_local(); dlm_proto_ops = NULL; } @@ -1803,7 +1791,7 @@ static int dlm_listen_for_all(void) if (result < 0) return result; - result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, + result = sock_create_kern(&init_net, dlm_local_addr[0].ss_family, SOCK_STREAM, dlm_proto_ops->proto, &sock); if (result < 0) { log_print("Can't create comms socket: %d", result); @@ -1842,11 +1830,11 @@ static int dlm_tcp_bind(struct socket *sock) /* Bind to our cluster-known address connecting to avoid * routing problems. */ - memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr)); + memcpy(&src_addr, &dlm_local_addr[0], sizeof(src_addr)); make_sockaddr(&src_addr, 0, &addr_len); - result = sock->ops->bind(sock, (struct sockaddr *)&src_addr, - addr_len); + result = kernel_bind(sock, (struct sockaddr *)&src_addr, + addr_len); if (result < 0) { /* This *may* not indicate a critical error */ log_print("could not bind for connect: %d", result); @@ -1860,7 +1848,7 @@ static int dlm_tcp_connect(struct connection *con, struct socket *sock, { int ret; - ret = sock->ops->connect(sock, addr, addr_len, O_NONBLOCK); + ret = kernel_connect(sock, addr, addr_len, O_NONBLOCK); switch (ret) { case -EINPROGRESS: fallthrough; @@ -1899,9 +1887,9 @@ static int dlm_tcp_listen_bind(struct socket *sock) int addr_len; /* Bind to our port */ - make_sockaddr(dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len); - return sock->ops->bind(sock, (struct sockaddr *)dlm_local_addr[0], - addr_len); + make_sockaddr(&dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len); + return kernel_bind(sock, (struct sockaddr *)&dlm_local_addr[0], + addr_len); } static const struct dlm_proto_ops dlm_tcp_ops = { @@ -1928,12 +1916,12 @@ static int dlm_sctp_connect(struct connection *con, struct socket *sock, int ret; /* - * Make sock->ops->connect() function return in specified time, + * Make kernel_connect() function return in specified time, * since O_NONBLOCK argument in connect() function does not work here, * then, we should restore the default value of this attribute. */ sock_set_sndtimeo(sock->sk, 5); - ret = sock->ops->connect(sock, addr, addr_len, 0); + ret = kernel_connect(sock, addr, addr_len, 0); sock_set_sndtimeo(sock->sk, 0); if (ret < 0) return ret; @@ -1992,7 +1980,7 @@ int dlm_lowcomms_start(void) error = work_start(); if (error) - goto fail_local; + goto fail; dlm_allow_conn = 1; @@ -2022,8 +2010,6 @@ fail_listen: fail_proto_ops: dlm_allow_conn = 0; work_stop(); -fail_local: - deinit_local(); fail: return error; } diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index c214fe0981bd..55340ac61456 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -76,6 +76,14 @@ static struct inode *__ecryptfs_get_inode(struct inode *lower_inode, if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb)) return ERR_PTR(-EXDEV); + + /* Reject dealing with casefold directories. */ + if (IS_CASEFOLDED(lower_inode)) { + pr_err_ratelimited("%s: Can't handle casefolded directory.\n", + __func__); + return ERR_PTR(-EREMOTE); + } + if (!igrab(lower_inode)) return ERR_PTR(-ESTALE); inode = iget5_locked(sb, (unsigned long)lower_inode, diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 6780fc81cc11..77c7615bba5e 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -13,6 +13,7 @@ #include <linux/ucs2_string.h> #include <linux/slab.h> #include <linux/magic.h> +#include <linux/printk.h> #include "internal.h" @@ -226,8 +227,19 @@ static int efivarfs_get_tree(struct fs_context *fc) return get_tree_single(fc, efivarfs_fill_super); } +static int efivarfs_reconfigure(struct fs_context *fc) +{ + if (!efivar_supports_writes() && !(fc->sb_flags & SB_RDONLY)) { + pr_err("Firmware does not support SetVariableRT. Can not remount with rw\n"); + return -EINVAL; + } + + return 0; +} + static const struct fs_context_operations efivarfs_context_ops = { .get_tree = efivarfs_get_tree, + .reconfigure = efivarfs_reconfigure, }; static int efivarfs_init_fs_context(struct fs_context *fc) @@ -238,10 +250,13 @@ static int efivarfs_init_fs_context(struct fs_context *fc) static void efivarfs_kill_sb(struct super_block *sb) { + struct efivarfs_fs_info *sfi = sb->s_fs_info; + kill_litter_super(sb); /* Remove all entries and destroy */ efivar_entry_iter(efivarfs_destroy, &efivarfs_list, NULL); + kfree(sfi); } static struct file_system_type efivarfs_type = { diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h index 26fa170090b8..c4a3187bdb8f 100644 --- a/fs/erofs/compress.h +++ b/fs/erofs/compress.h @@ -21,6 +21,8 @@ struct z_erofs_decompress_req { }; struct z_erofs_decompressor { + int (*config)(struct super_block *sb, struct erofs_super_block *dsb, + void *data, int size); int (*decompress)(struct z_erofs_decompress_req *rq, struct page **pagepool); char *name; @@ -93,6 +95,8 @@ int z_erofs_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); /* prototypes for specific algorithms */ +int z_erofs_load_lzma_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size); int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); #endif diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 51b7ac7166d9..1eefa4411e06 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -24,11 +24,11 @@ struct z_erofs_lz4_decompress_ctx { unsigned int oend; }; -int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int size) +static int z_erofs_load_lz4_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size) { struct erofs_sb_info *sbi = EROFS_SB(sb); + struct z_erofs_lz4_cfgs *lz4 = data; u16 distance; if (lz4) { @@ -122,11 +122,11 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_lz4_decompress_ctx *ctx, } static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx, - void *inpage, unsigned int *inputmargin, int *maptype, - bool may_inplace) + void *inpage, void *out, unsigned int *inputmargin, + int *maptype, bool may_inplace) { struct z_erofs_decompress_req *rq = ctx->rq; - unsigned int omargin, total, i, j; + unsigned int omargin, total, i; struct page **in; void *src, *tmp; @@ -136,20 +136,20 @@ static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx, omargin < LZ4_DECOMPRESS_INPLACE_MARGIN(rq->inputsize)) goto docopy; - for (i = 0; i < ctx->inpages; ++i) { - DBG_BUGON(rq->in[i] == NULL); - for (j = 0; j < ctx->outpages - ctx->inpages + i; ++j) - if (rq->out[j] == rq->in[i]) - goto docopy; - } + for (i = 0; i < ctx->inpages; ++i) + if (rq->out[ctx->outpages - ctx->inpages + i] != + rq->in[i]) + goto docopy; + kunmap_local(inpage); + *maptype = 3; + return out + ((ctx->outpages - ctx->inpages) << PAGE_SHIFT); } if (ctx->inpages <= 1) { *maptype = 0; return inpage; } - kunmap_atomic(inpage); - might_sleep(); + kunmap_local(inpage); src = erofs_vm_map_ram(rq->in, ctx->inpages); if (!src) return ERR_PTR(-ENOMEM); @@ -162,7 +162,7 @@ docopy: src = erofs_get_pcpubuf(ctx->inpages); if (!src) { DBG_BUGON(1); - kunmap_atomic(inpage); + kunmap_local(inpage); return ERR_PTR(-EFAULT); } @@ -173,9 +173,9 @@ docopy: min_t(unsigned int, total, PAGE_SIZE - *inputmargin); if (!inpage) - inpage = kmap_atomic(*in); + inpage = kmap_local_page(*in); memcpy(tmp, inpage + *inputmargin, page_copycnt); - kunmap_atomic(inpage); + kunmap_local(inpage); inpage = NULL; tmp += page_copycnt; total -= page_copycnt; @@ -205,16 +205,16 @@ int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf, } static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx, - u8 *out) + u8 *dst) { struct z_erofs_decompress_req *rq = ctx->rq; bool support_0padding = false, may_inplace = false; unsigned int inputmargin; - u8 *headpage, *src; + u8 *out, *headpage, *src; int ret, maptype; DBG_BUGON(*rq->in == NULL); - headpage = kmap_atomic(*rq->in); + headpage = kmap_local_page(*rq->in); /* LZ4 decompression inplace is only safe if zero_padding is enabled */ if (erofs_sb_has_zero_padding(EROFS_SB(rq->sb))) { @@ -223,7 +223,7 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx, min_t(unsigned int, rq->inputsize, EROFS_BLKSIZ - rq->pageofs_in)); if (ret) { - kunmap_atomic(headpage); + kunmap_local(headpage); return ret; } may_inplace = !((rq->pageofs_in + rq->inputsize) & @@ -231,11 +231,12 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx, } inputmargin = rq->pageofs_in; - src = z_erofs_lz4_handle_overlap(ctx, headpage, &inputmargin, + src = z_erofs_lz4_handle_overlap(ctx, headpage, dst, &inputmargin, &maptype, may_inplace); if (IS_ERR(src)) return PTR_ERR(src); + out = dst + rq->pageofs_out; /* legacy format could compress extra data in a pcluster. */ if (rq->partial_decoding || !support_0padding) ret = LZ4_decompress_safe_partial(src + inputmargin, out, @@ -261,12 +262,12 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx, } if (maptype == 0) { - kunmap_atomic(headpage); + kunmap_local(headpage); } else if (maptype == 1) { vm_unmap_ram(src, ctx->inpages); } else if (maptype == 2) { erofs_put_pcpubuf(src); - } else { + } else if (maptype != 3) { DBG_BUGON(1); return -EFAULT; } @@ -289,7 +290,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, /* one optimized fast path only for non bigpcluster cases yet */ if (ctx.inpages == 1 && ctx.outpages == 1 && !rq->inplace_io) { DBG_BUGON(!*rq->out); - dst = kmap_atomic(*rq->out); + dst = kmap_local_page(*rq->out); dst_maptype = 0; goto dstmap_out; } @@ -309,9 +310,9 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, } dstmap_out: - ret = z_erofs_lz4_decompress_mem(&ctx, dst + rq->pageofs_out); + ret = z_erofs_lz4_decompress_mem(&ctx, dst); if (!dst_maptype) - kunmap_atomic(dst); + kunmap_local(dst); else if (dst_maptype == 2) vm_unmap_ram(dst, ctx.outpages); return ret; @@ -373,17 +374,71 @@ static struct z_erofs_decompressor decompressors[] = { .name = "interlaced" }, [Z_EROFS_COMPRESSION_LZ4] = { + .config = z_erofs_load_lz4_config, .decompress = z_erofs_lz4_decompress, .name = "lz4" }, #ifdef CONFIG_EROFS_FS_ZIP_LZMA [Z_EROFS_COMPRESSION_LZMA] = { + .config = z_erofs_load_lzma_config, .decompress = z_erofs_lzma_decompress, .name = "lzma" }, #endif }; +int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + unsigned int algs, alg; + erofs_off_t offset; + int size, ret = 0; + + if (!erofs_sb_has_compr_cfgs(sbi)) { + sbi->available_compr_algs = 1 << Z_EROFS_COMPRESSION_LZ4; + return z_erofs_load_lz4_config(sb, dsb, NULL, 0); + } + + sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); + if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { + erofs_err(sb, "unidentified algorithms %x, please upgrade kernel", + sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); + return -EOPNOTSUPP; + } + + offset = EROFS_SUPER_OFFSET + sbi->sb_size; + alg = 0; + for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { + void *data; + + if (!(algs & 1)) + continue; + + data = erofs_read_metadata(sb, &buf, &offset, &size); + if (IS_ERR(data)) { + ret = PTR_ERR(data); + break; + } + + if (alg >= ARRAY_SIZE(decompressors) || + !decompressors[alg].config) { + erofs_err(sb, "algorithm %d isn't enabled on this kernel", + alg); + ret = -EOPNOTSUPP; + } else { + ret = decompressors[alg].config(sb, + dsb, data, size); + } + + kfree(data); + if (ret) + break; + } + erofs_put_metabuf(&buf); + return ret; +} + int z_erofs_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool) { diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 49addc345aeb..970464c4b676 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -72,10 +72,10 @@ int z_erofs_lzma_init(void) } int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size) + struct erofs_super_block *dsb, void *data, int size) { static DEFINE_MUTEX(lzma_resize_mutex); + struct z_erofs_lzma_cfgs *lzma = data; unsigned int dict_size, i; struct z_erofs_lzma *strm, *head = NULL; int err; diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index d8d09fc3ed65..79a7a5815ea6 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -471,6 +471,8 @@ struct erofs_map_dev { /* data.c */ extern const struct file_operations erofs_file_fops; +void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp); void erofs_unmap_metabuf(struct erofs_buf *buf); void erofs_put_metabuf(struct erofs_buf *buf); void *erofs_bread(struct erofs_buf *buf, struct inode *inode, @@ -565,9 +567,7 @@ void z_erofs_exit_zip_subsystem(void); int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, struct erofs_workgroup *egrp); int erofs_try_to_free_cached_page(struct page *page); -int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int len); +int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb); #else static inline void erofs_shrinker_register(struct super_block *sb) {} static inline void erofs_shrinker_unregister(struct super_block *sb) {} @@ -575,36 +575,14 @@ static inline int erofs_init_shrinker(void) { return 0; } static inline void erofs_exit_shrinker(void) {} static inline int z_erofs_init_zip_subsystem(void) { return 0; } static inline void z_erofs_exit_zip_subsystem(void) {} -static inline int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int len) -{ - if (lz4 || dsb->u1.lz4_max_distance) { - erofs_err(sb, "lz4 algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} #endif /* !CONFIG_EROFS_FS_ZIP */ #ifdef CONFIG_EROFS_FS_ZIP_LZMA int z_erofs_lzma_init(void); void z_erofs_lzma_exit(void); -int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size); #else static inline int z_erofs_lzma_init(void) { return 0; } static inline int z_erofs_lzma_exit(void) { return 0; } -static inline int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size) { - if (lzma) { - erofs_err(sb, "lzma algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} #endif /* !CONFIG_EROFS_FS_ZIP */ /* flags for erofs_fscache_register_cookie() */ diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c index 0dc34721080c..e8ccaa761bd6 100644 --- a/fs/erofs/namei.c +++ b/fs/erofs/namei.c @@ -137,24 +137,24 @@ static void *find_target_block_classic(struct erofs_buf *target, /* string comparison without already matched prefix */ diff = erofs_dirnamecmp(name, &dname, &matched); - if (!diff) { - *_ndirents = 0; - goto out; - } else if (diff > 0) { - head = mid + 1; - startprfx = matched; - - if (!IS_ERR(candidate)) - erofs_put_metabuf(target); - *target = buf; - candidate = de; - *_ndirents = ndirents; - } else { + if (diff < 0) { erofs_put_metabuf(&buf); - back = mid - 1; endprfx = matched; + continue; + } + + if (!IS_ERR(candidate)) + erofs_put_metabuf(target); + *target = buf; + if (!diff) { + *_ndirents = 0; + return de; } + head = mid + 1; + startprfx = matched; + candidate = de; + *_ndirents = ndirents; continue; } out: /* free if the candidate is valid */ diff --git a/fs/erofs/super.c b/fs/erofs/super.c index bd8bf8fc2f5d..f2647126cb2f 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -126,8 +126,8 @@ static bool check_layout_compatibility(struct super_block *sb, #ifdef CONFIG_EROFS_FS_ZIP /* read variable-sized metadata, offset will be aligned by 4-byte */ -static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, - erofs_off_t *offset, int *lengthp) +void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp) { u8 *buffer, *ptr; int len, i, cnt; @@ -159,64 +159,15 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, } return buffer; } - -static int erofs_load_compr_cfgs(struct super_block *sb, - struct erofs_super_block *dsb) -{ - struct erofs_sb_info *sbi = EROFS_SB(sb); - struct erofs_buf buf = __EROFS_BUF_INITIALIZER; - unsigned int algs, alg; - erofs_off_t offset; - int size, ret = 0; - - sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); - if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { - erofs_err(sb, "try to load compressed fs with unsupported algorithms %x", - sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); - return -EINVAL; - } - - offset = EROFS_SUPER_OFFSET + sbi->sb_size; - alg = 0; - for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { - void *data; - - if (!(algs & 1)) - continue; - - data = erofs_read_metadata(sb, &buf, &offset, &size); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - - switch (alg) { - case Z_EROFS_COMPRESSION_LZ4: - ret = z_erofs_load_lz4_config(sb, dsb, data, size); - break; - case Z_EROFS_COMPRESSION_LZMA: - ret = z_erofs_load_lzma_config(sb, dsb, data, size); - break; - default: - DBG_BUGON(1); - ret = -EFAULT; - } - kfree(data); - if (ret) - break; - } - erofs_put_metabuf(&buf); - return ret; -} #else -static int erofs_load_compr_cfgs(struct super_block *sb, - struct erofs_super_block *dsb) +static int z_erofs_parse_cfgs(struct super_block *sb, + struct erofs_super_block *dsb) { - if (dsb->u1.available_compr_algs) { - erofs_err(sb, "try to load compressed fs when compression is disabled"); - return -EINVAL; - } - return 0; + if (!dsb->u1.available_compr_algs) + return 0; + + erofs_err(sb, "compression disabled, unable to mount compressed EROFS"); + return -EOPNOTSUPP; } #endif @@ -398,10 +349,7 @@ static int erofs_read_superblock(struct super_block *sb) } /* parse on-disk compression configurations */ - if (erofs_sb_has_compr_cfgs(sbi)) - ret = erofs_load_compr_cfgs(sb, dsb); - else - ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0); + ret = z_erofs_parse_cfgs(sb, dsb); if (ret < 0) goto out; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 1b91ac5be961..47e71964eeff 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -652,7 +652,6 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) if (ztailpacking) { pcl->obj.index = 0; /* which indicates ztailpacking */ - pcl->pageofs_in = erofs_blkoff(map->m_pa); pcl->tailpacking_size = map->m_plen; } else { pcl->obj.index = map->m_pa >> PAGE_SHIFT; @@ -852,6 +851,7 @@ repeat: get_page(fe->map.buf.page); WRITE_ONCE(fe->pcl->compressed_bvecs[0].page, fe->map.buf.page); + fe->pcl->pageofs_in = map->m_pa & ~PAGE_MASK; fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE; } else { /* bind cache first when cached decompression is preferred */ @@ -1192,12 +1192,11 @@ out: put_page(page); } else { for (i = 0; i < pclusterpages; ++i) { - page = pcl->compressed_bvecs[i].page; + /* consider shortlived pages added when decompressing */ + page = be->compressed_pages[i]; if (erofs_page_is_managed(sbi, page)) continue; - - /* recycle all individual short-lived pages */ (void)z_erofs_put_shortlivedpage(be->pagepool, page); WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL); } diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 0337b70b2dac..abcded1acd19 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -610,7 +610,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, .map = map, }; int err = 0; - unsigned int lclusterbits, endoff; + unsigned int lclusterbits, endoff, afmt; unsigned long initial_lcn; unsigned long long ofs, end; @@ -700,17 +700,20 @@ static int z_erofs_do_map_blocks(struct inode *inode, err = -EFSCORRUPTED; goto unmap_out; } - if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER) - map->m_algorithmformat = - Z_EROFS_COMPRESSION_INTERLACED; - else - map->m_algorithmformat = - Z_EROFS_COMPRESSION_SHIFTED; - } else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) { - map->m_algorithmformat = vi->z_algorithmtype[1]; + afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ? + Z_EROFS_COMPRESSION_INTERLACED : + Z_EROFS_COMPRESSION_SHIFTED; } else { - map->m_algorithmformat = vi->z_algorithmtype[0]; + afmt = m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2 ? + vi->z_algorithmtype[1] : vi->z_algorithmtype[0]; + if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) { + erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu", + afmt, vi->nid); + err = -EFSCORRUPTED; + goto unmap_out; + } } + map->m_algorithmformat = afmt; if ((flags & EROFS_GET_BLOCKS_FIEMAP) || ((flags & EROFS_GET_BLOCKS_READMORE) && diff --git a/fs/exec.c b/fs/exec.c index 283012eb1aeb..39f7751c90fc 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1410,6 +1410,9 @@ int begin_new_exec(struct linux_binprm * bprm) out_unlock: up_write(&me->signal->exec_update_lock); + if (!bprm->cred) + mutex_unlock(&me->signal->cred_guard_mutex); + out: return retval; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index aa5aadd70bbc..67af684e44e6 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2229,7 +2229,7 @@ static int ext4_fill_es_cache_info(struct inode *inode, /* - * ext4_ext_determine_hole - determine hole around given block + * ext4_ext_find_hole - find hole around given block according to the given path * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole @@ -2241,9 +2241,9 @@ static int ext4_fill_es_cache_info(struct inode *inode, * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ -static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, - struct ext4_ext_path *path, - ext4_lblk_t *lblk) +static ext4_lblk_t ext4_ext_find_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; @@ -2271,30 +2271,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, } /* - * ext4_ext_put_gap_in_cache: - * calculate boundaries of the gap that the requested block fits into - * and cache this gap - */ -static void -ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start, - ext4_lblk_t hole_len) -{ - struct extent_status es; - - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, - hole_start + hole_len - 1, &es); - if (es.es_len) { - /* There's delayed extent containing lblock? */ - if (es.es_lblk <= hole_start) - return; - hole_len = min(es.es_lblk - hole_start, hole_len); - } - ext_debug(inode, " -> %u:%u\n", hole_start, hole_len); - ext4_es_insert_extent(inode, hole_start, hole_len, ~0, - EXTENT_STATUS_HOLE); -} - -/* * ext4_ext_rm_idx: * removes index from the index block. */ @@ -4064,6 +4040,69 @@ static int get_implied_cluster_alloc(struct super_block *sb, return 0; } +/* + * Determine hole length around the given logical block, first try to + * locate and expand the hole from the given @path, and then adjust it + * if it's partially or completely converted to delayed extents, insert + * it into the extent cache tree if it's indeed a hole, finally return + * the length of the determined extent. + */ +static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t lblk) +{ + ext4_lblk_t hole_start, len; + struct extent_status es; + + hole_start = lblk; + len = ext4_ext_find_hole(inode, path, &hole_start); +again: + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, + hole_start + len - 1, &es); + if (!es.es_len) + goto insert_hole; + + /* + * There's a delalloc extent in the hole, handle it if the delalloc + * extent is in front of, behind and straddle the queried range. + */ + if (lblk >= es.es_lblk + es.es_len) { + /* + * The delalloc extent is in front of the queried range, + * find again from the queried start block. + */ + len -= lblk - hole_start; + hole_start = lblk; + goto again; + } else if (in_range(lblk, es.es_lblk, es.es_len)) { + /* + * The delalloc extent containing lblk, it must have been + * added after ext4_map_blocks() checked the extent status + * tree, adjust the length to the delalloc extent's after + * lblk. + */ + len = es.es_lblk + es.es_len - lblk; + return len; + } else { + /* + * The delalloc extent is partially or completely behind + * the queried range, update hole length until the + * beginning of the delalloc extent. + */ + len = min(es.es_lblk - hole_start, len); + } + +insert_hole: + /* Put just found gap into cache to speed up subsequent requests */ + ext_debug(inode, " -> %u:%u\n", hole_start, len); + ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE); + + /* Update hole_len to reflect hole size after lblk */ + if (hole_start != lblk) + len -= lblk - hole_start; + + return len; +} /* * Block allocation/map/preallocation routine for extents based files @@ -4181,22 +4220,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * we couldn't try to create block if create flag is zero */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { - ext4_lblk_t hole_start, hole_len; + ext4_lblk_t len; - hole_start = map->m_lblk; - hole_len = ext4_ext_determine_hole(inode, path, &hole_start); - /* - * put just found gap into cache to speed up - * subsequent requests - */ - ext4_ext_put_gap_in_cache(inode, hole_start, hole_len); + len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk); - /* Update hole_len to reflect hole size after map->m_lblk */ - if (hole_start != map->m_lblk) - hole_len -= map->m_lblk - hole_start; map->m_pblk = 0; - map->m_len = min_t(unsigned int, map->m_len, hole_len); - + map->m_len = min_t(unsigned int, map->m_len, len); goto out; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a6e41746890d..6a3e27771df7 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -831,7 +831,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) struct ext4_sb_info *sbi = EXT4_SB(sb); int new_order; - if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0) + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0) return; new_order = mb_avg_fragment_size_order(sb, @@ -1118,6 +1118,24 @@ void ext4_mb_generate_buddy(struct super_block *sb, atomic64_add(period, &sbi->s_mb_generation_time); } +static void mb_regenerate_buddy(struct ext4_buddy *e4b) +{ + int count; + int order = 1; + void *buddy; + + while ((buddy = mb_find_buddy(e4b, order++, &count))) + mb_set_bits(buddy, 0, count); + + e4b->bd_info->bb_fragments = 0; + memset(e4b->bd_info->bb_counters, 0, + sizeof(*e4b->bd_info->bb_counters) * + (e4b->bd_sb->s_blocksize_bits + 2)); + + ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, + e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); +} + /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -1767,11 +1785,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); - this_cpu_inc(discard_pa_seq); - e4b->bd_info->bb_free += count; - if (first < e4b->bd_info->bb_first_free) - e4b->bd_info->bb_first_free = first; - /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ @@ -1785,21 +1798,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; + /* + * Fastcommit replay can free already freed blocks which + * corrupts allocation info. Regenerate it. + */ + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + mb_regenerate_buddy(e4b); + goto check; + } + blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); - if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { - ext4_grp_locked_error(sb, e4b->bd_group, - inode ? inode->i_ino : 0, - blocknr, - "freeing already freed block (bit %u); block bitmap corrupt.", - block); - ext4_mark_group_bitmap_corrupted( - sb, e4b->bd_group, + ext4_grp_locked_error(sb, e4b->bd_group, + inode ? inode->i_ino : 0, blocknr, + "freeing already freed block (bit %u); block bitmap corrupt.", + block); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); - } - goto done; + return; } + this_cpu_inc(discard_pa_seq); + e4b->bd_info->bb_free += count; + if (first < e4b->bd_info->bb_first_free) + e4b->bd_info->bb_first_free = first; + /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; @@ -1824,9 +1847,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); -done: mb_set_largest_free_order(sb, e4b->bd_info); mb_update_avg_fragment_size(sb, e4b->bd_info); +check: mb_check_buddy(e4b); } @@ -2153,6 +2176,9 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, return err; ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { @@ -2160,6 +2186,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); @@ -2188,12 +2215,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, if (err) return err; - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) { - ext4_mb_unload_buddy(e4b); - return 0; - } - ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ @@ -2226,6 +2251,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); @@ -6421,11 +6447,16 @@ __acquires(bitlock) static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, ext4_group_t grp) { - if (grp < ext4_get_groups_count(sb)) - return EXT4_CLUSTERS_PER_GROUP(sb) - 1; - return (ext4_blocks_count(EXT4_SB(sb)->s_es) - - ext4_group_first_block_no(sb, grp) - 1) >> - EXT4_CLUSTER_BITS(sb); + unsigned long nr_clusters_in_group; + + if (grp < (ext4_get_groups_count(sb) - 1)) + nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb); + else + nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) - + ext4_group_first_block_no(sb, grp)) + >> EXT4_CLUSTER_BITS(sb); + + return nr_clusters_in_group - 1; } static bool ext4_trim_interrupted(void) @@ -6439,13 +6470,15 @@ static int ext4_try_to_trim_range(struct super_block *sb, __acquires(ext4_group_lock_ptr(sb, e4b->bd_group)) __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) { - ext4_grpblk_t next, count, free_count; + ext4_grpblk_t next, count, free_count, last, origin_start; bool set_trimmed = false; void *bitmap; + last = ext4_last_grp_cluster(sb, e4b->bd_group); bitmap = e4b->bd_bitmap; - if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group)) + if (start == 0 && max >= last) set_trimmed = true; + origin_start = start; start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; @@ -6454,7 +6487,10 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) start = mb_find_next_zero_bit(bitmap, max + 1, start); if (start > max) break; - next = mb_find_next_bit(bitmap, max + 1, start); + + next = mb_find_next_bit(bitmap, last + 1, start); + if (origin_start == 0 && next >= last) + set_trimmed = true; if ((next - start) >= minblocks) { int ret = ext4_trim_extent(sb, start, next - start, e4b); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 044e34cd835c..8e3ff150bc36 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -253,6 +253,7 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, { struct inode *orig_inode = file_inode(o_filp); struct page *pagep[2] = {NULL, NULL}; + struct folio *folio[2] = {NULL, NULL}; handle_t *handle; ext4_lblk_t orig_blk_offset, donor_blk_offset; unsigned long blocksize = orig_inode->i_sb->s_blocksize; @@ -313,6 +314,13 @@ again: * hold page's lock, if it is still the case data copy is not * necessary, just swap data blocks between orig and donor. */ + folio[0] = page_folio(pagep[0]); + folio[1] = page_folio(pagep[1]); + + VM_BUG_ON_FOLIO(folio_test_large(folio[0]), folio[0]); + VM_BUG_ON_FOLIO(folio_test_large(folio[1]), folio[1]); + VM_BUG_ON_FOLIO(folio_nr_pages(folio[0]) != folio_nr_pages(folio[1]), folio[1]); + if (unwritten) { ext4_double_down_write_data_sem(orig_inode, donor_inode); /* If any of extents in range became initialized we have to @@ -331,10 +339,8 @@ again: ext4_double_up_write_data_sem(orig_inode, donor_inode); goto data_copy; } - if ((page_has_private(pagep[0]) && - !try_to_release_page(pagep[0], 0)) || - (page_has_private(pagep[1]) && - !try_to_release_page(pagep[1], 0))) { + if (!filemap_release_folio(folio[0], 0) || + !filemap_release_folio(folio[1], 0)) { *err = -EBUSY; goto drop_data_sem; } @@ -344,19 +350,19 @@ again: block_len_in_page, 1, err); drop_data_sem: ext4_double_up_write_data_sem(orig_inode, donor_inode); - goto unlock_pages; + goto unlock_folios; } data_copy: - *err = mext_page_mkuptodate(pagep[0], from, from + replaced_size); + *err = mext_page_mkuptodate(&folio[0]->page, from, from + replaced_size); if (*err) - goto unlock_pages; + goto unlock_folios; /* At this point all buffers in range are uptodate, old mapping layout * is no longer required, try to drop it now. */ - if ((page_has_private(pagep[0]) && !try_to_release_page(pagep[0], 0)) || - (page_has_private(pagep[1]) && !try_to_release_page(pagep[1], 0))) { + if (!filemap_release_folio(folio[0], 0) || + !filemap_release_folio(folio[1], 0)) { *err = -EBUSY; - goto unlock_pages; + goto unlock_folios; } ext4_double_down_write_data_sem(orig_inode, donor_inode); replaced_count = ext4_swap_extents(handle, orig_inode, donor_inode, @@ -369,13 +375,13 @@ data_copy: replaced_size = block_len_in_page << orig_inode->i_blkbits; } else - goto unlock_pages; + goto unlock_folios; } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - if (!page_has_buffers(pagep[0])) - create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0); - bh = page_buffers(pagep[0]); + if (!folio_buffers(folio[0])) + create_empty_buffers(&folio[0]->page, 1 << orig_inode->i_blkbits, 0); + bh = folio_buffers(folio[0]); for (i = 0; i < data_offset_in_page; i++) bh = bh->b_this_page; for (i = 0; i < block_len_in_page; i++) { @@ -385,7 +391,7 @@ data_copy: bh = bh->b_this_page; } if (!*err) - *err = block_commit_write(pagep[0], from, from + replaced_size); + *err = block_commit_write(&folio[0]->page, from, from + replaced_size); if (unlikely(*err < 0)) goto repair_branches; @@ -395,11 +401,11 @@ data_copy: *err = ext4_jbd2_inode_add_write(handle, orig_inode, (loff_t)orig_page_offset << PAGE_SHIFT, replaced_size); -unlock_pages: - unlock_page(pagep[0]); - put_page(pagep[0]); - unlock_page(pagep[1]); - put_page(pagep[1]); +unlock_folios: + folio_unlock(folio[0]); + folio_put(folio[0]); + folio_unlock(folio[1]); + folio_put(folio[1]); stop_journal: ext4_journal_stop(handle); if (*err == -ENOSPC && @@ -430,7 +436,7 @@ repair_branches: *err = -EIO; } replaced_count = 0; - goto unlock_pages; + goto unlock_folios; } /** @@ -615,6 +621,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, goto out; o_end = o_start + len; + *moved_len = 0; while (o_start < o_end) { struct ext4_extent *ex; ext4_lblk_t cur_blk, next_blk; @@ -669,7 +676,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ - move_extent_per_page(o_filp, donor_inode, + *moved_len += move_extent_per_page(o_filp, donor_inode, orig_page_index, donor_page_index, offset_in_page, cur_len, unwritten, &ret); @@ -679,9 +686,6 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, o_start += cur_len; d_start += cur_len; } - *moved_len = o_start - orig_blk; - if (*moved_len > len) - *moved_len = len; out: if (*moved_len) { diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 9833ab6db117..f2ed15af703a 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -231,17 +231,24 @@ struct ext4_new_flex_group_data { in the flex group */ __u16 *bg_flags; /* block group flags of groups in @groups */ + ext4_group_t resize_bg; /* number of allocated + new_group_data */ ext4_group_t count; /* number of groups in @groups */ }; /* + * Avoiding memory allocation failures due to too many groups added each time. + */ +#define MAX_RESIZE_BG 16384 + +/* * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of * @flexbg_size. * * Returns NULL on failure otherwise address of the allocated structure. */ -static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) +static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size) { struct ext4_new_flex_group_data *flex_gd; @@ -249,17 +256,18 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) - goto out2; - flex_gd->count = flexbg_size; + if (unlikely(flexbg_size > MAX_RESIZE_BG)) + flex_gd->resize_bg = MAX_RESIZE_BG; + else + flex_gd->resize_bg = flexbg_size; - flex_gd->groups = kmalloc_array(flexbg_size, + flex_gd->groups = kmalloc_array(flex_gd->resize_bg, sizeof(struct ext4_new_group_data), GFP_NOFS); if (flex_gd->groups == NULL) goto out2; - flex_gd->bg_flags = kmalloc_array(flexbg_size, sizeof(__u16), + flex_gd->bg_flags = kmalloc_array(flex_gd->resize_bg, sizeof(__u16), GFP_NOFS); if (flex_gd->bg_flags == NULL) goto out1; @@ -296,7 +304,7 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd) */ static int ext4_alloc_group_tables(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, - int flexbg_size) + unsigned int flexbg_size) { struct ext4_new_group_data *group_data = flex_gd->groups; ext4_fsblk_t start_blk; @@ -397,12 +405,12 @@ next_group: group = group_data[0].group; printk(KERN_DEBUG "EXT4-fs: adding a flex group with " - "%d groups, flexbg size is %d:\n", flex_gd->count, + "%u groups, flexbg size is %u:\n", flex_gd->count, flexbg_size); for (i = 0; i < flex_gd->count; i++) { ext4_debug( - "adding %s group %u: %u blocks (%d free, %d mdata blocks)\n", + "adding %s group %u: %u blocks (%u free, %u mdata blocks)\n", ext4_bg_has_super(sb, group + i) ? "normal" : "no-super", group + i, group_data[i].blocks_count, @@ -1623,8 +1631,7 @@ exit: static int ext4_setup_next_flex_gd(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, - ext4_fsblk_t n_blocks_count, - unsigned long flexbg_size) + ext4_fsblk_t n_blocks_count) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; @@ -1648,7 +1655,7 @@ static int ext4_setup_next_flex_gd(struct super_block *sb, BUG_ON(last); ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last); - last_group = group | (flexbg_size - 1); + last_group = group | (flex_gd->resize_bg - 1); if (last_group > n_group) last_group = n_group; @@ -2010,8 +2017,9 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) ext4_fsblk_t o_blocks_count; ext4_fsblk_t n_blocks_count_retry = 0; unsigned long last_update_time = 0; - int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex; + int err = 0; int meta_bg; + unsigned int flexbg_size = ext4_flex_bg_size(sbi); /* See if the device is actually as big as what was requested */ bh = ext4_sb_bread(sb, n_blocks_count - 1, 0); @@ -2152,8 +2160,7 @@ retry: /* Add flex groups. Note that a regular group is a * flex group with 1 group. */ - while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count, - flexbg_size)) { + while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count)) { if (time_is_before_jiffies(last_update_time + HZ * 10)) { if (last_update_time) ext4_msg(sb, KERN_INFO, diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 5df04ed010ca..eb4d69f53337 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -984,7 +984,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) cp_blk_no = le32_to_cpu(fsb->cp_blkaddr); if (cur_page == cp2) - cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg); + cp_blk_no += BIT(le32_to_cpu(fsb->log_blocks_per_seg)); for (i = 1; i < cp_blks; i++) { void *sit_bitmap_ptr; diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 11d9dce994db..967262c37da5 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -55,6 +55,7 @@ struct f2fs_compress_ops { int (*init_decompress_ctx)(struct decompress_io_ctx *dic); void (*destroy_decompress_ctx)(struct decompress_io_ctx *dic); int (*decompress_pages)(struct decompress_io_ctx *dic); + bool (*is_level_valid)(int level); }; static unsigned int offset_in_cluster(struct compress_ctx *cc, pgoff_t index) @@ -241,7 +242,7 @@ static int lz4_init_compress_ctx(struct compress_ctx *cc) unsigned int size = LZ4_MEM_COMPRESS; #ifdef CONFIG_F2FS_FS_LZ4HC - if (F2FS_I(cc->inode)->i_compress_flag >> COMPRESS_LEVEL_OFFSET) + if (F2FS_I(cc->inode)->i_compress_level) size = LZ4HC_MEM_COMPRESS; #endif @@ -267,8 +268,7 @@ static void lz4_destroy_compress_ctx(struct compress_ctx *cc) #ifdef CONFIG_F2FS_FS_LZ4HC static int lz4hc_compress_pages(struct compress_ctx *cc) { - unsigned char level = F2FS_I(cc->inode)->i_compress_flag >> - COMPRESS_LEVEL_OFFSET; + unsigned char level = F2FS_I(cc->inode)->i_compress_level; int len; if (level) @@ -323,26 +323,34 @@ static int lz4_decompress_pages(struct decompress_io_ctx *dic) return 0; } +static bool lz4_is_level_valid(int lvl) +{ +#ifdef CONFIG_F2FS_FS_LZ4HC + return !lvl || (lvl >= LZ4HC_MIN_CLEVEL && lvl <= LZ4HC_MAX_CLEVEL); +#else + return lvl == 0; +#endif +} + static const struct f2fs_compress_ops f2fs_lz4_ops = { .init_compress_ctx = lz4_init_compress_ctx, .destroy_compress_ctx = lz4_destroy_compress_ctx, .compress_pages = lz4_compress_pages, .decompress_pages = lz4_decompress_pages, + .is_level_valid = lz4_is_level_valid, }; #endif #ifdef CONFIG_F2FS_FS_ZSTD -#define F2FS_ZSTD_DEFAULT_CLEVEL 1 - static int zstd_init_compress_ctx(struct compress_ctx *cc) { zstd_parameters params; zstd_cstream *stream; void *workspace; unsigned int workspace_size; - unsigned char level = F2FS_I(cc->inode)->i_compress_flag >> - COMPRESS_LEVEL_OFFSET; + unsigned char level = F2FS_I(cc->inode)->i_compress_level; + /* Need to remain this for backward compatibility */ if (!level) level = F2FS_ZSTD_DEFAULT_CLEVEL; @@ -493,6 +501,11 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic) return 0; } +static bool zstd_is_level_valid(int lvl) +{ + return lvl >= zstd_min_clevel() && lvl <= zstd_max_clevel(); +} + static const struct f2fs_compress_ops f2fs_zstd_ops = { .init_compress_ctx = zstd_init_compress_ctx, .destroy_compress_ctx = zstd_destroy_compress_ctx, @@ -500,6 +513,7 @@ static const struct f2fs_compress_ops f2fs_zstd_ops = { .init_decompress_ctx = zstd_init_decompress_ctx, .destroy_decompress_ctx = zstd_destroy_decompress_ctx, .decompress_pages = zstd_decompress_pages, + .is_level_valid = zstd_is_level_valid, }; #endif @@ -558,6 +572,16 @@ bool f2fs_is_compress_backend_ready(struct inode *inode) return f2fs_cops[F2FS_I(inode)->i_compress_algorithm]; } +bool f2fs_is_compress_level_valid(int alg, int lvl) +{ + const struct f2fs_compress_ops *cops = f2fs_cops[alg]; + + if (cops->is_level_valid) + return cops->is_level_valid(lvl); + + return lvl == 0; +} + static mempool_t *compress_page_pool; static int num_compress_pages = 512; module_param(num_compress_pages, uint, 0444); @@ -675,7 +699,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc) cc->cbuf->clen = cpu_to_le32(cc->clen); - if (fi->i_compress_flag & 1 << COMPRESS_CHKSUM) + if (fi->i_compress_flag & BIT(COMPRESS_CHKSUM)) chksum = f2fs_crc32(F2FS_I_SB(cc->inode), cc->cbuf->cdata, cc->clen); cc->cbuf->chksum = cpu_to_le32(chksum); @@ -773,7 +797,7 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task) ret = cops->decompress_pages(dic); - if (!ret && (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)) { + if (!ret && (fi->i_compress_flag & BIT(COMPRESS_CHKSUM))) { u32 provided = le32_to_cpu(dic->cbuf->chksum); u32 calculated = f2fs_crc32(sbi, dic->cbuf->cdata, dic->clen); @@ -1029,8 +1053,10 @@ static void set_cluster_dirty(struct compress_ctx *cc) int i; for (i = 0; i < cc->cluster_size; i++) - if (cc->rpages[i]) + if (cc->rpages[i]) { set_page_dirty(cc->rpages[i]); + set_page_private_gcing(cc->rpages[i]); + } } static int prepare_compress_overwrite(struct compress_ctx *cc, diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index ea05710ca9bd..8b561af37974 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -95,17 +95,17 @@ static enum count_type __read_io_type(struct page *page) /* postprocessing steps for read bios */ enum bio_post_read_step { #ifdef CONFIG_FS_ENCRYPTION - STEP_DECRYPT = 1 << 0, + STEP_DECRYPT = BIT(0), #else STEP_DECRYPT = 0, /* compile out the decryption-related code */ #endif #ifdef CONFIG_F2FS_FS_COMPRESSION - STEP_DECOMPRESS = 1 << 1, + STEP_DECOMPRESS = BIT(1), #else STEP_DECOMPRESS = 0, /* compile out the decompression-related code */ #endif #ifdef CONFIG_FS_VERITY - STEP_VERITY = 1 << 2, + STEP_VERITY = BIT(2), #else STEP_VERITY = 0, /* compile out the verity-related code */ #endif @@ -409,7 +409,7 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio) { - unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1; + unsigned int temp_mask = GENMASK(NR_TEMP_TYPE - 1, 0); unsigned int fua_flag, meta_flag, io_flag; blk_opf_t op_flags = 0; @@ -431,9 +431,9 @@ static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio) * 5 | 4 | 3 | 2 | 1 | 0 | * Cold | Warm | Hot | Cold | Warm | Hot | */ - if ((1 << fio->temp) & meta_flag) + if (BIT(fio->temp) & meta_flag) op_flags |= REQ_META; - if ((1 << fio->temp) & fua_flag) + if (BIT(fio->temp) & fua_flag) op_flags |= REQ_FUA; return op_flags; } @@ -2490,9 +2490,6 @@ int f2fs_encrypt_one_page(struct f2fs_io_info *fio) page = fio->compressed_page ? fio->compressed_page : fio->page; - /* wait for GCed page writeback via META_MAPPING */ - f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); - if (fscrypt_inode_uses_inline_crypto(inode)) return 0; @@ -2681,6 +2678,10 @@ got_it: goto out_writepage; } + /* wait for GCed page writeback via META_MAPPING */ + if (fio->post_read) + f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); + /* * If current allocation needs SSR, * it had better in-place writes for updated data. diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 8373eba3a133..510736d2ae11 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -29,7 +29,7 @@ static unsigned long dir_blocks(struct inode *inode) static unsigned int dir_buckets(unsigned int level, int dir_level) { if (level + dir_level < MAX_DIR_HASH_DEPTH / 2) - return 1 << (level + dir_level); + return BIT(level + dir_level); else return MAX_DIR_BUCKETS; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index f56abb39601a..e5a9498b89c0 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -64,7 +64,7 @@ enum { }; #ifdef CONFIG_F2FS_FAULT_INJECTION -#define F2FS_ALL_FAULT_TYPE ((1 << FAULT_MAX) - 1) +#define F2FS_ALL_FAULT_TYPE (GENMASK(FAULT_MAX - 1, 0)) struct f2fs_fault_info { atomic_t inject_ops; @@ -73,7 +73,7 @@ struct f2fs_fault_info { }; extern const char *f2fs_fault_name[FAULT_MAX]; -#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type))) +#define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type)) #endif /* @@ -840,7 +840,7 @@ struct f2fs_inode_info { unsigned char i_compress_algorithm; /* algorithm type */ unsigned char i_log_cluster_size; /* log of cluster size */ unsigned char i_compress_level; /* compress level (lz4hc,zstd) */ - unsigned short i_compress_flag; /* compress flag */ + unsigned char i_compress_flag; /* compress flag */ unsigned int i_cluster_size; /* cluster size */ unsigned int atomic_write_cnt; @@ -1412,7 +1412,7 @@ static inline void set_page_private_##name(struct page *page) \ static inline void clear_page_private_##name(struct page *page) \ { \ clear_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ - if (page_private(page) == 1 << PAGE_PRIVATE_NOT_POINTER) { \ + if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) { \ set_page_private(page, 0); \ if (PagePrivate(page)) { \ ClearPagePrivate(page); \ @@ -1462,8 +1462,8 @@ static inline void set_page_private_data(struct page *page, unsigned long data) static inline void clear_page_private_data(struct page *page) { - page_private(page) &= (1 << PAGE_PRIVATE_MAX) - 1; - if (page_private(page) == 1 << PAGE_PRIVATE_NOT_POINTER) { + page_private(page) &= GENMASK(PAGE_PRIVATE_MAX - 1, 0); + if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) { set_page_private(page, 0); if (PagePrivate(page)) { ClearPagePrivate(page); @@ -1501,6 +1501,8 @@ struct compress_data { #define F2FS_COMPRESSED_PAGE_MAGIC 0xF5F2C000 +#define F2FS_ZSTD_DEFAULT_CLEVEL 1 + #define COMPRESS_LEVEL_OFFSET 8 /* compress context */ @@ -2882,7 +2884,7 @@ static inline int f2fs_test_bit(unsigned int nr, char *addr) int mask; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); return mask & *addr; } @@ -2891,7 +2893,7 @@ static inline void f2fs_set_bit(unsigned int nr, char *addr) int mask; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); *addr |= mask; } @@ -2900,7 +2902,7 @@ static inline void f2fs_clear_bit(unsigned int nr, char *addr) int mask; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); *addr &= ~mask; } @@ -2910,7 +2912,7 @@ static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr) int ret; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); ret = mask & *addr; *addr |= mask; return ret; @@ -2922,7 +2924,7 @@ static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr) int ret; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); ret = mask & *addr; *addr &= ~mask; return ret; @@ -2933,7 +2935,7 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) int mask; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); *addr ^= mask; } @@ -4217,6 +4219,7 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata, int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock); void f2fs_compress_write_end_io(struct bio *bio, struct page *page); bool f2fs_is_compress_backend_ready(struct inode *inode); +bool f2fs_is_compress_level_valid(int alg, int lvl); int f2fs_init_compress_mempool(void); void f2fs_destroy_compress_mempool(void); void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task); @@ -4281,6 +4284,7 @@ static inline bool f2fs_is_compress_backend_ready(struct inode *inode) /* not support compression */ return false; } +static inline bool f2fs_is_compress_level_valid(int alg, int lvl) { return false; } static inline struct page *f2fs_compress_control_page(struct page *page) { WARN_ON_ONCE(1); @@ -4333,15 +4337,14 @@ static inline int set_compress_context(struct inode *inode) F2FS_OPTION(sbi).compress_log_size; F2FS_I(inode)->i_compress_flag = F2FS_OPTION(sbi).compress_chksum ? - 1 << COMPRESS_CHKSUM : 0; + BIT(COMPRESS_CHKSUM) : 0; F2FS_I(inode)->i_cluster_size = - 1 << F2FS_I(inode)->i_log_cluster_size; + BIT(F2FS_I(inode)->i_log_cluster_size); if ((F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 || F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) && F2FS_OPTION(sbi).compress_level) - F2FS_I(inode)->i_compress_flag |= - F2FS_OPTION(sbi).compress_level << - COMPRESS_LEVEL_OFFSET; + F2FS_I(inode)->i_compress_level = + F2FS_OPTION(sbi).compress_level; F2FS_I(inode)->i_flags |= F2FS_COMPR_FL; set_inode_flag(inode, FI_COMPRESSED_FILE); stat_inc_compr_inode(inode); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index d0c17366ebf4..46e4960a9dcf 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -42,7 +42,7 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf) vm_fault_t ret; ret = filemap_fault(vmf); - if (!ret) + if (ret & VM_FAULT_LOCKED) f2fs_update_iostat(F2FS_I_SB(inode), inode, APP_MAPPED_READ_IO, F2FS_BLKSIZE); @@ -1326,6 +1326,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, } memcpy_page(pdst, 0, psrc, 0, PAGE_SIZE); set_page_dirty(pdst); + set_page_private_gcing(pdst); f2fs_put_page(pdst, 1); f2fs_put_page(psrc, 1); @@ -2821,6 +2822,11 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, goto out; } + if (f2fs_compressed_file(src) || f2fs_compressed_file(dst)) { + ret = -EOPNOTSUPP; + goto out_unlock; + } + ret = -EINVAL; if (pos_in + len > src->i_size || pos_in + len < pos_in) goto out_unlock; @@ -3983,7 +3989,16 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) F2FS_I(inode)->i_compress_algorithm = option.algorithm; F2FS_I(inode)->i_log_cluster_size = option.log_cluster_size; - F2FS_I(inode)->i_cluster_size = 1 << option.log_cluster_size; + F2FS_I(inode)->i_cluster_size = BIT(option.log_cluster_size); + /* Set default level */ + if (F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) + F2FS_I(inode)->i_compress_level = F2FS_ZSTD_DEFAULT_CLEVEL; + else + F2FS_I(inode)->i_compress_level = 0; + /* Adjust mount option level */ + if (option.algorithm == F2FS_OPTION(sbi).compress_algorithm && + F2FS_OPTION(sbi).compress_level) + F2FS_I(inode)->i_compress_level = F2FS_OPTION(sbi).compress_level; f2fs_mark_inode_dirty_sync(inode, true); if (!f2fs_is_compress_backend_ready(inode)) @@ -4023,6 +4038,7 @@ static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len) f2fs_bug_on(F2FS_I_SB(inode), !page); set_page_dirty(page); + set_page_private_gcing(page); f2fs_put_page(page, 1); f2fs_put_page(page, 0); } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 1fc7760499f1..0010579f1736 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -450,12 +450,18 @@ static int do_read_inode(struct inode *inode) (fi->i_flags & F2FS_COMPR_FL)) { if (F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_log_cluster_size)) { + unsigned short compress_flag; + atomic_set(&fi->i_compr_blocks, le64_to_cpu(ri->i_compr_blocks)); fi->i_compress_algorithm = ri->i_compress_algorithm; fi->i_log_cluster_size = ri->i_log_cluster_size; - fi->i_compress_flag = le16_to_cpu(ri->i_compress_flag); - fi->i_cluster_size = 1 << fi->i_log_cluster_size; + compress_flag = le16_to_cpu(ri->i_compress_flag); + fi->i_compress_level = compress_flag >> + COMPRESS_LEVEL_OFFSET; + fi->i_compress_flag = compress_flag & + GENMASK(COMPRESS_LEVEL_OFFSET - 1, 0); + fi->i_cluster_size = BIT(fi->i_log_cluster_size); set_inode_flag(inode, FI_COMPRESSED_FILE); } } @@ -675,13 +681,17 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page) if (f2fs_sb_has_compression(F2FS_I_SB(inode)) && F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize, i_log_cluster_size)) { + unsigned short compress_flag; + ri->i_compr_blocks = cpu_to_le64(atomic_read( &F2FS_I(inode)->i_compr_blocks)); ri->i_compress_algorithm = F2FS_I(inode)->i_compress_algorithm; - ri->i_compress_flag = - cpu_to_le16(F2FS_I(inode)->i_compress_flag); + compress_flag = F2FS_I(inode)->i_compress_flag | + F2FS_I(inode)->i_compress_level << + COMPRESS_LEVEL_OFFSET; + ri->i_compress_flag = cpu_to_le16(compress_flag); ri->i_log_cluster_size = F2FS_I(inode)->i_log_cluster_size; } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index bd020a992c2e..328cd20b16a5 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -1099,7 +1099,7 @@ static int f2fs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, } if (old_dir_entry) { - if (old_dir != new_dir && !whiteout) + if (old_dir != new_dir) f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); else diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 6efccd7ccfe1..c6d0e0709632 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -2738,11 +2738,11 @@ recover_xnid: f2fs_update_inode_page(inode); /* 3: update and set xattr node page dirty */ - if (page) + if (page) { memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE); - - set_page_dirty(xpage); + set_page_dirty(xpage); + } f2fs_put_page(xpage, 1); return 0; diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 0aa48704c77a..7068f3ac036a 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -93,17 +93,15 @@ static inline void copy_node_info(struct node_info *dst, static inline void set_nat_flag(struct nat_entry *ne, unsigned int type, bool set) { - unsigned char mask = 0x01 << type; if (set) - ne->ni.flag |= mask; + ne->ni.flag |= BIT(type); else - ne->ni.flag &= ~mask; + ne->ni.flag &= ~BIT(type); } static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type) { - unsigned char mask = 0x01 << type; - return ne->ni.flag & mask; + return ne->ni.flag & BIT(type); } static inline void nat_reset_flag(struct nat_entry *ne) @@ -224,7 +222,7 @@ static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi, struct f2fs_nm_info *nm_i = NM_I(sbi); block_addr -= nm_i->nat_blkaddr; - block_addr ^= 1 << sbi->log_blocks_per_seg; + block_addr ^= BIT(sbi->log_blocks_per_seg); return block_addr + nm_i->nat_blkaddr; } @@ -394,7 +392,7 @@ static inline nid_t get_nid(struct page *p, int off, bool i) static inline int is_node(struct page *page, int type) { struct f2fs_node *rn = F2FS_NODE(page); - return le32_to_cpu(rn->footer.flag) & (1 << type); + return le32_to_cpu(rn->footer.flag) & BIT(type); } #define is_cold_node(page) is_node(page, COLD_BIT_SHIFT) @@ -407,9 +405,9 @@ static inline void set_cold_node(struct page *page, bool is_dir) unsigned int flag = le32_to_cpu(rn->footer.flag); if (is_dir) - flag &= ~(0x1 << COLD_BIT_SHIFT); + flag &= ~BIT(COLD_BIT_SHIFT); else - flag |= (0x1 << COLD_BIT_SHIFT); + flag |= BIT(COLD_BIT_SHIFT); rn->footer.flag = cpu_to_le32(flag); } @@ -418,9 +416,9 @@ static inline void set_mark(struct page *page, int mark, int type) struct f2fs_node *rn = F2FS_NODE(page); unsigned int flag = le32_to_cpu(rn->footer.flag); if (mark) - flag |= (0x1 << type); + flag |= BIT(type); else - flag &= ~(0x1 << type); + flag &= ~BIT(type); rn->footer.flag = cpu_to_le32(flag); #ifdef CONFIG_F2FS_CHECK_FS diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index dea95b48b647..53a6487f91e4 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -683,7 +683,16 @@ retry_dn: */ if (dest == NEW_ADDR) { f2fs_truncate_data_blocks_range(&dn, 1); - f2fs_reserve_new_block(&dn); + do { + err = f2fs_reserve_new_block(&dn); + if (err == -ENOSPC) { + f2fs_bug_on(sbi, 1); + break; + } + } while (err && + IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + if (err) + goto err; continue; } @@ -691,12 +700,14 @@ retry_dn: if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { if (src == NULL_ADDR) { - err = f2fs_reserve_new_block(&dn); - while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) + do { err = f2fs_reserve_new_block(&dn); - /* We should not get -ENOSPC */ - f2fs_bug_on(sbi, err); + if (err == -ENOSPC) { + f2fs_bug_on(sbi, 1); + break; + } + } while (err && + IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); if (err) goto err; } @@ -887,6 +898,8 @@ skip: if (!err && fix_curseg_write_pointer && !f2fs_readonly(sbi->sb) && f2fs_sb_has_blkzoned(sbi)) { err = f2fs_fix_curseg_write_pointer(sbi); + if (!err) + err = f2fs_check_write_pointer(sbi); ret = err; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 1ba85ef97cbd..0c0d0671febe 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -613,14 +613,12 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) { #ifdef CONFIG_F2FS_FS_LZ4HC unsigned int level; -#endif if (strlen(str) == 3) { F2FS_OPTION(sbi).compress_level = 0; return 0; } -#ifdef CONFIG_F2FS_FS_LZ4HC str += 3; if (str[0] != ':') { @@ -630,7 +628,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) if (kstrtouint(str + 1, 10, &level)) return -EINVAL; - if (level < LZ4HC_MIN_CLEVEL || level > LZ4HC_MAX_CLEVEL) { + if (!f2fs_is_compress_level_valid(COMPRESS_LZ4, level)) { f2fs_info(sbi, "invalid lz4hc compress level: %d", level); return -EINVAL; } @@ -638,6 +636,10 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) F2FS_OPTION(sbi).compress_level = level; return 0; #else + if (strlen(str) == 3) { + F2FS_OPTION(sbi).compress_level = 0; + return 0; + } f2fs_info(sbi, "kernel doesn't support lz4hc compression"); return -EINVAL; #endif @@ -651,7 +653,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) int len = 4; if (strlen(str) == len) { - F2FS_OPTION(sbi).compress_level = 0; + F2FS_OPTION(sbi).compress_level = F2FS_ZSTD_DEFAULT_CLEVEL; return 0; } @@ -664,7 +666,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) if (kstrtouint(str + 1, 10, &level)) return -EINVAL; - if (!level || level > zstd_max_clevel()) { + if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) { f2fs_info(sbi, "invalid zstd compress level: %d", level); return -EINVAL; } @@ -898,8 +900,8 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) if (args->from && match_int(args, &arg)) return -EINVAL; if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_VECS)) { - f2fs_warn(sbi, "Not support %d, larger than %d", - 1 << arg, BIO_MAX_VECS); + f2fs_warn(sbi, "Not support %ld, larger than %d", + BIT(arg), BIO_MAX_VECS); return -EINVAL; } F2FS_OPTION(sbi).write_io_size_bits = arg; @@ -1340,7 +1342,7 @@ default_check: #endif if (F2FS_IO_SIZE_BITS(sbi) && !f2fs_lfs_mode(sbi)) { - f2fs_err(sbi, "Should set mode=lfs with %uKB-sized IO", + f2fs_err(sbi, "Should set mode=lfs with %luKB-sized IO", F2FS_IO_SIZE_KB(sbi)); return -EINVAL; } @@ -3356,7 +3358,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, total_sections = le32_to_cpu(raw_super->section_count); /* blocks_per_seg should be 512, given the above check */ - blocks_per_seg = 1 << le32_to_cpu(raw_super->log_blocks_per_seg); + blocks_per_seg = BIT(le32_to_cpu(raw_super->log_blocks_per_seg)); if (segment_count > F2FS_MAX_SEGMENT || segment_count < F2FS_MIN_SEGMENTS) { @@ -3625,9 +3627,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->log_sectors_per_block = le32_to_cpu(raw_super->log_sectors_per_block); sbi->log_blocksize = le32_to_cpu(raw_super->log_blocksize); - sbi->blocksize = 1 << sbi->log_blocksize; + sbi->blocksize = BIT(sbi->log_blocksize); sbi->log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); - sbi->blocks_per_seg = 1 << sbi->log_blocks_per_seg; + sbi->blocks_per_seg = BIT(sbi->log_blocks_per_seg); sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec); sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone); sbi->total_sections = le32_to_cpu(raw_super->section_count); @@ -3883,7 +3885,7 @@ void f2fs_handle_stop(struct f2fs_sb_info *sbi, unsigned char reason) f2fs_down_write(&sbi->sb_lock); - if (raw_super->s_stop_reason[reason] < ((1 << BITS_PER_BYTE) - 1)) + if (raw_super->s_stop_reason[reason] < GENMASK(BITS_PER_BYTE - 1, 0)) raw_super->s_stop_reason[reason]++; err = f2fs_commit_super(sbi, false); @@ -4033,7 +4035,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) FDEV(i).start_blk, FDEV(i).end_blk); } f2fs_info(sbi, - "IO Block Size: %8d KB", F2FS_IO_SIZE_KB(sbi)); + "IO Block Size: %8ld KB", F2FS_IO_SIZE_KB(sbi)); return 0; } diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 3d68bfa75cf2..751a108e612f 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -451,7 +451,7 @@ out: if (ret < 0) return ret; #ifdef CONFIG_F2FS_FAULT_INJECTION - if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX)) + if (a->struct_type == FAULT_INFO_TYPE && t >= BIT(FAULT_MAX)) return -EINVAL; if (a->struct_type == FAULT_INFO_RATE && t >= UINT_MAX) return -EINVAL; diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index adaad16468d8..0631b383e21f 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -660,11 +660,14 @@ retry: here = __find_xattr(base_addr, last_base_addr, NULL, index, len, name); if (!here) { if (!F2FS_I(inode)->i_xattr_nid) { + error = f2fs_recover_xattr_data(inode, NULL); f2fs_notice(F2FS_I_SB(inode), - "recover xattr in inode (%lu)", inode->i_ino); - f2fs_recover_xattr_data(inode, NULL); - kfree(base_addr); - goto retry; + "recover xattr in inode (%lu), error(%d)", + inode->i_ino, error); + if (!error) { + kfree(base_addr); + goto retry; + } } f2fs_err(F2FS_I_SB(inode), "set inode (%lu) has corrupted xattr", inode->i_ino); @@ -754,6 +757,12 @@ retry: memcpy(pval, value, size); last->e_value_size = cpu_to_le16(size); new_hsize += newsize; + /* + * Explicitly add the null terminator. The unused xattr space + * is supposed to always be zeroed, which would make this + * unnecessary, but don't depend on that. + */ + *(u32 *)((u8 *)last + newsize) = 0; } error = write_all_xattrs(inode, new_hsize, base_addr, ipage); diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index d645f8b302a2..9397ed39b0b4 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -179,13 +179,14 @@ EXPORT_SYMBOL(fscache_acquire_cache); void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where) { - unsigned int debug_id = cache->debug_id; + unsigned int debug_id; bool zero; int ref; if (IS_ERR_OR_NULL(cache)) return; + debug_id = cache->debug_id; zero = __refcount_dec_and_test(&cache->ref, &ref); trace_fscache_cache(debug_id, ref - 1, where); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 98a9cf531873..a9681fecbd91 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -63,6 +63,19 @@ struct fuse_forget_link { struct fuse_forget_link *next; }; +/* Submount lookup tracking */ +struct fuse_submount_lookup { + /** Refcount */ + refcount_t count; + + /** Unique ID, which identifies the inode between userspace + * and kernel */ + u64 nodeid; + + /** The request used for sending the FORGET message */ + struct fuse_forget_link *forget; +}; + /** FUSE inode */ struct fuse_inode { /** Inode data */ @@ -155,6 +168,8 @@ struct fuse_inode { */ struct fuse_inode_dax *dax; #endif + /** Submount specific lookup tracking */ + struct fuse_submount_lookup *submount_lookup; }; /** FUSE inode state bits */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index bc3c3e76c646..f81000d96887 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -68,6 +68,24 @@ struct fuse_forget_link *fuse_alloc_forget(void) return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT); } +static struct fuse_submount_lookup *fuse_alloc_submount_lookup(void) +{ + struct fuse_submount_lookup *sl; + + sl = kzalloc(sizeof(struct fuse_submount_lookup), GFP_KERNEL_ACCOUNT); + if (!sl) + return NULL; + sl->forget = fuse_alloc_forget(); + if (!sl->forget) + goto out_free; + + return sl; + +out_free: + kfree(sl); + return NULL; +} + static struct inode *fuse_alloc_inode(struct super_block *sb) { struct fuse_inode *fi; @@ -83,6 +101,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) fi->attr_version = 0; fi->orig_ino = 0; fi->state = 0; + fi->submount_lookup = NULL; mutex_init(&fi->mutex); spin_lock_init(&fi->lock); fi->forget = fuse_alloc_forget(); @@ -113,6 +132,17 @@ static void fuse_free_inode(struct inode *inode) kmem_cache_free(fuse_inode_cachep, fi); } +static void fuse_cleanup_submount_lookup(struct fuse_conn *fc, + struct fuse_submount_lookup *sl) +{ + if (!refcount_dec_and_test(&sl->count)) + return; + + fuse_queue_forget(fc, sl->forget, sl->nodeid, 1); + sl->forget = NULL; + kfree(sl); +} + static void fuse_evict_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -132,6 +162,11 @@ static void fuse_evict_inode(struct inode *inode) fi->nlookup); fi->forget = NULL; } + + if (fi->submount_lookup) { + fuse_cleanup_submount_lookup(fc, fi->submount_lookup); + fi->submount_lookup = NULL; + } } if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) { WARN_ON(!list_empty(&fi->write_files)); @@ -311,6 +346,13 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, fuse_dax_dontcache(inode, attr->flags); } +static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl, + u64 nodeid) +{ + sl->nodeid = nodeid; + refcount_set(&sl->count, 1); +} + static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr) { inode->i_mode = attr->mode & S_IFMT; @@ -368,12 +410,22 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, */ if (fc->auto_submounts && (attr->flags & FUSE_ATTR_SUBMOUNT) && S_ISDIR(attr->mode)) { + struct fuse_inode *fi; + inode = new_inode(sb); if (!inode) return NULL; fuse_init_inode(inode, attr); - get_fuse_inode(inode)->nodeid = nodeid; + fi = get_fuse_inode(inode); + fi->nodeid = nodeid; + fi->submount_lookup = fuse_alloc_submount_lookup(); + if (!fi->submount_lookup) { + iput(inode); + return NULL; + } + /* Sets nlookup = 1 on fi->submount_lookup->nlookup */ + fuse_init_submount_lookup(fi->submount_lookup, nodeid); inode->i_flags |= S_AUTOMOUNT; goto done; } @@ -396,11 +448,11 @@ retry: iput(inode); goto retry; } -done: fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->nlookup++; spin_unlock(&fi->lock); +done: fuse_change_attributes(inode, attr, attr_valid, attr_version); return inode; @@ -1439,6 +1491,8 @@ static int fuse_fill_super_submount(struct super_block *sb, struct super_block *parent_sb = parent_fi->inode.i_sb; struct fuse_attr root_attr; struct inode *root; + struct fuse_submount_lookup *sl; + struct fuse_inode *fi; fuse_sb_defaults(sb); fm->sb = sb; @@ -1461,12 +1515,27 @@ static int fuse_fill_super_submount(struct super_block *sb, * its nlookup should not be incremented. fuse_iget() does * that, though, so undo it here. */ - get_fuse_inode(root)->nlookup--; + fi = get_fuse_inode(root); + fi->nlookup--; + sb->s_d_op = &fuse_dentry_operations; sb->s_root = d_make_root(root); if (!sb->s_root) return -ENOMEM; + /* + * Grab the parent's submount_lookup pointer and take a + * reference on the shared nlookup from the parent. This is to + * prevent the last forget for this nodeid from getting + * triggered until all users have finished with it. + */ + sl = parent_fi->submount_lookup; + WARN_ON(!sl); + if (sl) { + refcount_inc(&sl->count); + fi->submount_lookup = sl; + } + return 0; } diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index f602fb844951..dcaaa32efc4a 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -2306,7 +2306,7 @@ void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_rgrpd *rgd, (unsigned long long)rgd->rd_addr, rgd->rd_flags, rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes, rgd->rd_requested, rgd->rd_reserved, rgd->rd_extfail_pt); - if (rgd->rd_sbd->sd_args.ar_rgrplvb) { + if (rgd->rd_sbd->sd_args.ar_rgrplvb && rgd->rd_rgl) { struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl; gfs2_print_dbg(seq, "%s L: f:%02x b:%u i:%u\n", fs_id_buf, diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 8eea709e3659..4fe4b3393e71 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -123,6 +123,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); + vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has @@ -164,10 +165,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); ret = -ENOMEM; + + vm_flags = vma->vm_flags; + /* + * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip + * reserving here. Note: only for SHM hugetlbfs file, the inode + * flag S_PRIVATE is set. + */ + if (inode->i_flags & S_PRIVATE) + vm_flags |= VM_NORESERVE; + if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, - vma->vm_flags)) + vm_flags)) goto out; ret = 0; @@ -1350,6 +1361,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct fs_parse_result result; + struct hstate *h; char *rest; unsigned long ps; int opt; @@ -1394,11 +1406,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par case Opt_pagesize: ps = memparse(param->string, &rest); - ctx->hstate = size_to_hstate(ps); - if (!ctx->hstate) { + h = size_to_hstate(ps); + if (!h) { pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } + ctx->hstate = h; return 0; case Opt_min_size: diff --git a/fs/inode.c b/fs/inode.c index 73ad1b0d4775..8cfda7a6d590 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -215,6 +215,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) lockdep_set_class_and_name(&mapping->invalidate_lock, &sb->s_type->invalidate_lock_key, "mapping.invalidate_lock"); + if (sb->s_iflags & SB_I_STABLE_WRITES) + mapping_set_stable_writes(mapping); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ diff --git a/fs/ioctl.c b/fs/ioctl.c index 80ac36aea913..2bd05509295a 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -916,8 +916,7 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, if (!f.file) return -EBADF; - /* RED-PEN how should LSM module know it's handling 32bit? */ - error = security_file_ioctl(f.file, cmd, arg); + error = security_file_ioctl_compat(f.file, cmd, arg); if (error) goto out; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index f1d9db6686e3..556b259a00ba 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -123,7 +123,7 @@ static int journal_submit_commit_record(journal_t *journal, struct commit_header *tmp; struct buffer_head *bh; struct timespec64 now; - blk_opf_t write_flags = REQ_OP_WRITE | REQ_SYNC; + blk_opf_t write_flags = REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS; *cbh = NULL; @@ -300,6 +300,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal, if (!ret) ret = err; } + cond_resched(); spin_lock(&journal->j_list_lock); jinode->i_flags &= ~JI_COMMIT_RUNNING; smp_mb(); @@ -429,8 +430,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) */ jbd2_journal_update_sb_log_tail(journal, journal->j_tail_sequence, - journal->j_tail, - REQ_SYNC); + journal->j_tail, 0); mutex_unlock(&journal->j_checkpoint_mutex); } else { jbd2_debug(3, "superblock not updated\n"); @@ -749,6 +749,7 @@ start_journal_io: for (i = 0; i < bufs; i++) { struct buffer_head *bh = wbuf[i]; + /* * Compute checksum. */ @@ -761,7 +762,8 @@ start_journal_io: clear_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = journal_end_buffer_io_sync; - submit_bh(REQ_OP_WRITE | REQ_SYNC, bh); + submit_bh(REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS, + bh); } cond_resched(); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 2696f43e7239..3df45e4699f1 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1109,8 +1109,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) * space and if we lose sb update during power failure we'd replay * old transaction with possibly newly overwritten data. */ - ret = jbd2_journal_update_sb_log_tail(journal, tid, block, - REQ_SYNC | REQ_FUA); + ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA); if (ret) goto out; @@ -1597,8 +1596,7 @@ static int journal_reset(journal_t *journal) */ jbd2_journal_update_sb_log_tail(journal, journal->j_tail_sequence, - journal->j_tail, - REQ_SYNC | REQ_FUA); + journal->j_tail, REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } return jbd2_journal_start_thread(journal); @@ -1620,9 +1618,16 @@ static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags) return -EIO; } - trace_jbd2_write_superblock(journal, write_flags); + /* + * Always set high priority flags to exempt from block layer's + * QOS policies, e.g. writeback throttle. + */ + write_flags |= JBD2_JOURNAL_REQ_FLAGS; if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); + + trace_jbd2_write_superblock(journal, write_flags); + if (buffer_write_io_error(bh)) { /* * Oh, dear. A previous attempt to write the journal @@ -1871,7 +1876,7 @@ void jbd2_journal_update_sb_errno(journal_t *journal) jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); sb->s_errno = cpu_to_be32(errcode); - jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA); + jbd2_write_superblock(journal, REQ_FUA); } EXPORT_SYMBOL(jbd2_journal_update_sb_errno); @@ -2176,8 +2181,7 @@ int jbd2_journal_destroy(journal_t *journal) ++journal->j_transaction_sequence; write_unlock(&journal->j_state_lock); - jbd2_mark_journal_empty(journal, - REQ_SYNC | REQ_PREFLUSH | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_PREFLUSH | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } else err = -EIO; @@ -2486,7 +2490,7 @@ int jbd2_journal_flush(journal_t *journal, unsigned int flags) * the magic code for a fully-recovered superblock. Any future * commits of data to the journal will restore the current * s_start value. */ - jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_FUA); if (flags) err = __jbd2_journal_erase(journal, flags); @@ -2536,7 +2540,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) if (write) { /* Lock to make assertions happy... */ mutex_lock_io(&journal->j_checkpoint_mutex); - jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 4d56f6081a5d..4462274e325a 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -63,10 +63,10 @@ */ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); -static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval); -static int dbBackSplit(dmtree_t * tp, int leafno); -static int dbJoin(dmtree_t * tp, int leafno, int newval); -static void dbAdjTree(dmtree_t * tp, int leafno, int newval); +static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl); +static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl); +static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl); +static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl); static int dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level); static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results); @@ -2103,7 +2103,7 @@ static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, * system. */ if (dp->tree.stree[word] == NOFREE) - dbBackSplit((dmtree_t *) & dp->tree, word); + dbBackSplit((dmtree_t *)&dp->tree, word, false); dbAllocBits(bmp, dp, blkno, nblocks); } @@ -2189,7 +2189,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * the binary system of the leaves if need be. */ dbSplit(tp, word, BUDMIN, - dbMaxBud((u8 *) & dp->wmap[word])); + dbMaxBud((u8 *)&dp->wmap[word]), false); word += 1; } else { @@ -2229,7 +2229,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * system of the leaves to reflect the current * allocation (size). */ - dbSplit(tp, word, size, NOFREE); + dbSplit(tp, word, size, NOFREE, false); /* get the number of dmap words handled */ nw = BUDSIZE(size, BUDMIN); @@ -2336,7 +2336,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, /* update the leaf for this dmap word. */ rc = dbJoin(tp, word, - dbMaxBud((u8 *) & dp->wmap[word])); + dbMaxBud((u8 *)&dp->wmap[word]), false); if (rc) return rc; @@ -2369,7 +2369,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, /* update the leaf. */ - rc = dbJoin(tp, word, size); + rc = dbJoin(tp, word, size, false); if (rc) return rc; @@ -2521,16 +2521,16 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) * that it is at the front of a binary buddy system. */ if (oldval == NOFREE) { - rc = dbBackSplit((dmtree_t *) dcp, leafno); + rc = dbBackSplit((dmtree_t *)dcp, leafno, true); if (rc) { release_metapage(mp); return rc; } oldval = dcp->stree[ti]; } - dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval); + dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval, true); } else { - rc = dbJoin((dmtree_t *) dcp, leafno, newval); + rc = dbJoin((dmtree_t *) dcp, leafno, newval, true); if (rc) { release_metapage(mp); return rc; @@ -2561,7 +2561,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) */ if (alloc) { dbJoin((dmtree_t *) dcp, leafno, - oldval); + oldval, true); } else { /* the dbJoin() above might have * caused a larger binary buddy system @@ -2571,9 +2571,9 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) */ if (dcp->stree[ti] == NOFREE) dbBackSplit((dmtree_t *) - dcp, leafno); + dcp, leafno, true); dbSplit((dmtree_t *) dcp, leafno, - dcp->budmin, oldval); + dcp->budmin, oldval, true); } /* release the buffer and return the error. @@ -2621,7 +2621,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ -static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) +static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl) { int budsz; int cursz; @@ -2643,7 +2643,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) while (cursz >= splitsz) { /* update the buddy's leaf with its new value. */ - dbAdjTree(tp, leafno ^ budsz, cursz); + dbAdjTree(tp, leafno ^ budsz, cursz, is_ctl); /* on to the next size and buddy. */ @@ -2655,7 +2655,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) /* adjust the dmap tree to reflect the specified leaf's new * value. */ - dbAdjTree(tp, leafno, newval); + dbAdjTree(tp, leafno, newval, is_ctl); } @@ -2686,7 +2686,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ -static int dbBackSplit(dmtree_t * tp, int leafno) +static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl) { int budsz, bud, w, bsz, size; int cursz; @@ -2737,7 +2737,7 @@ static int dbBackSplit(dmtree_t * tp, int leafno) * system in two. */ cursz = leaf[bud] - 1; - dbSplit(tp, bud, cursz, cursz); + dbSplit(tp, bud, cursz, cursz, is_ctl); break; } } @@ -2765,7 +2765,7 @@ static int dbBackSplit(dmtree_t * tp, int leafno) * * RETURN VALUES: none */ -static int dbJoin(dmtree_t * tp, int leafno, int newval) +static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int budsz, buddy; s8 *leaf; @@ -2820,12 +2820,12 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) if (leafno < buddy) { /* leafno is the left buddy. */ - dbAdjTree(tp, buddy, NOFREE); + dbAdjTree(tp, buddy, NOFREE, is_ctl); } else { /* buddy is the left buddy and becomes * leafno. */ - dbAdjTree(tp, leafno, NOFREE); + dbAdjTree(tp, leafno, NOFREE, is_ctl); leafno = buddy; } @@ -2838,7 +2838,7 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) /* update the leaf value. */ - dbAdjTree(tp, leafno, newval); + dbAdjTree(tp, leafno, newval, is_ctl); return 0; } @@ -2859,15 +2859,20 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) * * RETURN VALUES: none */ -static void dbAdjTree(dmtree_t * tp, int leafno, int newval) +static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int lp, pp, k; - int max; + int max, size; + + size = is_ctl ? CTLTREESIZE : TREESIZE; /* pick up the index of the leaf for this leafno. */ lp = leafno + le32_to_cpu(tp->dmt_leafidx); + if (WARN_ON_ONCE(lp >= size || lp < 0)) + return; + /* is the current value the same as the old value ? if so, * there is nothing to do. */ diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 92b7c533407c..031d8f570f58 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -633,6 +633,11 @@ int dtSearch(struct inode *ip, struct component_name * key, ino_t * data, for (base = 0, lim = p->header.nextindex; lim; lim >>= 1) { index = base + (lim >> 1); + if (stbl[index] < 0) { + rc = -EIO; + goto out; + } + if (p->header.flag & BT_LEAF) { /* uppercase leaf name to compare */ cmp = @@ -1970,7 +1975,7 @@ static int dtSplitRoot(tid_t tid, do { f = &rp->slot[fsi]; fsi = f->next; - } while (fsi != -1); + } while (fsi >= 0); f->next = n; } diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 6ed2e1d4c894..ac42f8ee553f 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -2179,6 +2179,9 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) /* get the ag and iag numbers for this iag. */ agno = BLKTOAG(le64_to_cpu(iagp->agstart), sbi); + if (agno >= MAXAG || agno < 0) + return -EIO; + iagno = le32_to_cpu(iagp->iagnum); /* check if this is the last free extent within the diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index 48d1f70f786c..21d8d4a5c67a 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -172,15 +172,15 @@ int jfs_mount(struct super_block *sb) } jfs_info("jfs_mount: ipimap:0x%p", ipimap); - /* map further access of per fileset inodes by the fileset inode */ - sbi->ipimap = ipimap; - /* initialize fileset inode allocation map */ if ((rc = diMount(ipimap))) { jfs_err("jfs_mount: diMount failed w/rc = %d", rc); goto err_ipimap; } + /* map further access of per fileset inodes by the fileset inode */ + sbi->ipimap = ipimap; + return rc; /* diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 44842e6cf0a9..a00e11ebfa77 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -669,6 +669,18 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, { struct kernfs_node *kn; + if (parent->mode & S_ISGID) { + /* this code block imitates inode_init_owner() for + * kernfs + */ + + if (parent->iattr) + gid = parent->iattr->ia_gid; + + if (flags & KERNFS_DIR) + mode |= S_ISGID; + } + kn = __kernfs_new_node(kernfs_root(parent), parent, name, mode, uid, gid, flags); if (kn) { diff --git a/fs/namei.c b/fs/namei.c index 5e1c2ab2ae70..9e336b408ed1 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -253,6 +253,7 @@ getname_kernel(const char * filename) return result; } +EXPORT_SYMBOL(getname_kernel); void putname(struct filename *name) { @@ -271,6 +272,7 @@ void putname(struct filename *name) } else __putname(name); } +EXPORT_SYMBOL(putname); /** * check_acl - perform ACL permission checking @@ -1581,8 +1583,9 @@ static struct dentry *lookup_dcache(const struct qstr *name, * when directory is guaranteed to have no in-lookup children * at all. */ -static struct dentry *__lookup_hash(const struct qstr *name, - struct dentry *base, unsigned int flags) +struct dentry *lookup_one_qstr_excl(const struct qstr *name, + struct dentry *base, + unsigned int flags) { struct dentry *dentry = lookup_dcache(name, base, flags); struct dentry *old; @@ -1606,6 +1609,7 @@ static struct dentry *__lookup_hash(const struct qstr *name, } return dentry; } +EXPORT_SYMBOL(lookup_one_qstr_excl); static struct dentry *lookup_fast(struct nameidata *nd) { @@ -2532,16 +2536,17 @@ static int path_parentat(struct nameidata *nd, unsigned flags, } /* Note: this does not consume "name" */ -static int filename_parentat(int dfd, struct filename *name, - unsigned int flags, struct path *parent, - struct qstr *last, int *type) +static int __filename_parentat(int dfd, struct filename *name, + unsigned int flags, struct path *parent, + struct qstr *last, int *type, + const struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); - set_nameidata(&nd, dfd, name, NULL); + set_nameidata(&nd, dfd, name, root); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); @@ -2556,6 +2561,13 @@ static int filename_parentat(int dfd, struct filename *name, return retval; } +static int filename_parentat(int dfd, struct filename *name, + unsigned int flags, struct path *parent, + struct qstr *last, int *type) +{ + return __filename_parentat(dfd, name, flags, parent, last, type, NULL); +} + /* does lookup, returns the object with parent locked */ static struct dentry *__kern_path_locked(struct filename *name, struct path *path) { @@ -2571,7 +2583,7 @@ static struct dentry *__kern_path_locked(struct filename *name, struct path *pat return ERR_PTR(-EINVAL); } inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - d = __lookup_hash(&last, path->dentry, 0); + d = lookup_one_qstr_excl(&last, path->dentry, 0); if (IS_ERR(d)) { inode_unlock(path->dentry->d_inode); path_put(path); @@ -2600,6 +2612,24 @@ int kern_path(const char *name, unsigned int flags, struct path *path) EXPORT_SYMBOL(kern_path); /** + * vfs_path_parent_lookup - lookup a parent path relative to a dentry-vfsmount pair + * @filename: filename structure + * @flags: lookup flags + * @parent: pointer to struct path to fill + * @last: last component + * @type: type of the last component + * @root: pointer to struct path of the base directory + */ +int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, + struct path *parent, struct qstr *last, int *type, + const struct path *root) +{ + return __filename_parentat(AT_FDCWD, filename, flags, parent, last, + type, root); +} +EXPORT_SYMBOL(vfs_path_parent_lookup); + +/** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory * @mnt: pointer to vfs mount of the base directory @@ -2980,39 +3010,79 @@ static inline int may_create(struct user_namespace *mnt_userns, return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); } +static struct dentry *lock_two_directories(struct dentry *p1, struct dentry *p2) +{ + struct dentry *p; + + p = d_ancestor(p2, p1); + if (p) { + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); + return p; + } + + p = d_ancestor(p1, p2); + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); + return p; +} + /* * p1 and p2 should be directories on the same fs. */ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { - struct dentry *p; - if (p1 == p2) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); return NULL; } mutex_lock(&p1->d_sb->s_vfs_rename_mutex); + return lock_two_directories(p1, p2); +} +EXPORT_SYMBOL(lock_rename); - p = d_ancestor(p2, p1); - if (p) { +/* + * c1 and p2 should be on the same fs. + */ +struct dentry *lock_rename_child(struct dentry *c1, struct dentry *p2) +{ + if (READ_ONCE(c1->d_parent) == p2) { + /* + * hopefully won't need to touch ->s_vfs_rename_mutex at all. + */ inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p1->d_inode, I_MUTEX_CHILD); - return p; - } + /* + * now that p2 is locked, nobody can move in or out of it, + * so the test below is safe. + */ + if (likely(c1->d_parent == p2)) + return NULL; - p = d_ancestor(p1, p2); - if (p) { - inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p2->d_inode, I_MUTEX_CHILD); - return p; + /* + * c1 got moved out of p2 while we'd been taking locks; + * unlock and fall back to slow case. + */ + inode_unlock(p2->d_inode); } - lock_two_inodes(p1->d_inode, p2->d_inode, - I_MUTEX_PARENT, I_MUTEX_PARENT2); + mutex_lock(&c1->d_sb->s_vfs_rename_mutex); + /* + * nobody can move out of any directories on this fs. + */ + if (likely(c1->d_parent != p2)) + return lock_two_directories(c1->d_parent, p2); + + /* + * c1 got moved into p2 while we were taking locks; + * we need p2 locked and ->s_vfs_rename_mutex unlocked, + * for consistency with lock_rename(). + */ + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); + mutex_unlock(&c1->d_sb->s_vfs_rename_mutex); return NULL; } -EXPORT_SYMBOL(lock_rename); +EXPORT_SYMBOL(lock_rename_child); void unlock_rename(struct dentry *p1, struct dentry *p2) { @@ -3806,7 +3876,8 @@ static struct dentry *filename_create(int dfd, struct filename *name, if (last.name[last.len] && !want_dir) create_flags = 0; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path->dentry, reval_flag | create_flags); + dentry = lookup_one_qstr_excl(&last, path->dentry, + reval_flag | create_flags); if (IS_ERR(dentry)) goto unlock; @@ -4168,7 +4239,7 @@ retry: goto exit2; inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path.dentry, lookup_flags); + dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit3; @@ -4302,7 +4373,7 @@ retry: goto exit2; retry_deleg: inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path.dentry, lookup_flags); + dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { struct user_namespace *mnt_userns; @@ -4658,11 +4729,12 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. - * That's where 4.4 screws up. Current fix: serialization on + * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. - * c) we have to lock _four_ objects - parents and victim (if it exists), - * and source. + * c) we may have to lock up to _four_ objects - parents and victim (if it exists), + * and source (if it's a non-directory or a subdirectory that moves to + * different parent). * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change @@ -4694,6 +4766,7 @@ int vfs_rename(struct renamedata *rd) bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; + bool lock_old_subdir, lock_new_subdir; if (source == target) return 0; @@ -4747,15 +4820,32 @@ int vfs_rename(struct renamedata *rd) take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* - * Lock all moved children. Moved directories may need to change parent - * pointer so they need the lock to prevent against concurrent - * directory changes moving parent pointer. For regular files we've - * historically always done this. The lockdep locking subclasses are - * somewhat arbitrary but RENAME_EXCHANGE in particular can swap - * regular files and directories so it's difficult to tell which - * subclasses to use. + * Lock children. + * The source subdirectory needs to be locked on cross-directory + * rename or cross-directory exchange since its parent changes. + * The target subdirectory needs to be locked on cross-directory + * exchange due to parent change and on any rename due to becoming + * a victim. + * Non-directories need locking in all cases (for NFS reasons); + * they get locked after any subdirectories (in inode address order). + * + * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. + * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ - lock_two_inodes(source, target, I_MUTEX_NORMAL, I_MUTEX_NONDIR2); + lock_old_subdir = new_dir != old_dir; + lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); + if (is_dir) { + if (lock_old_subdir) + inode_lock_nested(source, I_MUTEX_CHILD); + if (target && (!new_is_dir || lock_new_subdir)) + inode_lock(target); + } else if (new_is_dir) { + if (lock_new_subdir) + inode_lock_nested(target, I_MUTEX_CHILD); + inode_lock(source); + } else { + lock_two_nondirectories(source, target); + } error = -EPERM; if (IS_SWAPFILE(source) || (target && IS_SWAPFILE(target))) @@ -4803,8 +4893,9 @@ int vfs_rename(struct renamedata *rd) d_exchange(old_dentry, new_dentry); } out: - inode_unlock(source); - if (target) + if (!is_dir || lock_old_subdir) + inode_unlock(source); + if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) { @@ -4876,7 +4967,8 @@ retry: retry_deleg: trap = lock_rename(new_path.dentry, old_path.dentry); - old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags); + old_dentry = lookup_one_qstr_excl(&old_last, old_path.dentry, + lookup_flags); error = PTR_ERR(old_dentry); if (IS_ERR(old_dentry)) goto exit3; @@ -4884,7 +4976,8 @@ retry_deleg: error = -ENOENT; if (d_is_negative(old_dentry)) goto exit4; - new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags); + new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry, + lookup_flags | target_flags); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto exit4; diff --git a/fs/namespace.c b/fs/namespace.c index e04a9e9e3f14..1533550f7356 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2693,7 +2693,12 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags, if (IS_ERR(fc)) return PTR_ERR(fc); + /* + * Indicate to the filesystem that the remount request is coming + * from the legacy mount system call. + */ fc->oldapi = true; + err = parse_monolithic_mount_data(fc, data); if (!err) { down_write(&sb->s_umount); @@ -3027,6 +3032,12 @@ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, if (IS_ERR(fc)) return PTR_ERR(fc); + /* + * Indicate to the filesystem that the mount request is coming + * from the legacy mount system call. + */ + fc->oldapi = true; + if (subtype) err = vfs_parse_fs_string(fc, "subtype", subtype, strlen(subtype)); @@ -4161,10 +4172,15 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) /* * If this is an attached mount make sure it's located in the callers * mount namespace. If it's not don't let the caller interact with it. - * If this is a detached mount make sure it has an anonymous mount - * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE. + * + * If this mount doesn't have a parent it's most often simply a + * detached mount with an anonymous mount namespace. IOW, something + * that's simply not attached yet. But there are apparently also users + * that do change mount properties on the rootfs itself. That obviously + * neither has a parent nor is it a detached mount so we cannot + * unconditionally check for detached mounts. */ - if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns))) + if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt)) goto out; /* diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 943aeea1eb16..6be13e0ec170 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -580,6 +580,8 @@ retry: nfs4_delete_deviceid(node->ld, node->nfs_client, id); goto retry; } + + nfs4_put_deviceid_node(node); return ERR_PTR(-ENODEV); } @@ -893,10 +895,9 @@ bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) } if (pgio->pg_dreq == NULL) - wb_size = pnfs_num_cont_bytes(pgio->pg_inode, - req->wb_index); + wb_size = pnfs_num_cont_bytes(pgio->pg_inode, req->wb_index); else - wb_size = nfs_dreq_bytes_left(pgio->pg_dreq); + wb_size = nfs_dreq_bytes_left(pgio->pg_dreq, req_offset(req)); pnfs_generic_pg_init_write(pgio, req, wb_size); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 3bb530d4bb5c..8fdb65e1b14a 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -195,9 +195,10 @@ static void nfs_direct_req_release(struct nfs_direct_req *dreq) kref_put(&dreq->kref, nfs_direct_req_free); } -ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq) +ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset) { - return dreq->bytes_left; + loff_t start = offset - dreq->io_start; + return dreq->max_count - start; } EXPORT_SYMBOL_GPL(nfs_dreq_bytes_left); diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index e731c00a9fcb..d3c938dd2b12 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -176,6 +176,9 @@ void nfs_fscache_init_inode(struct inode *inode) &auxdata, /* aux_data */ sizeof(auxdata), i_size_read(inode)); + + if (netfs_inode(inode)->cache) + mapping_set_release_always(inode->i_mapping); } /* diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 4b07a0508f9d..35a8ae46b6c3 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -640,7 +640,7 @@ extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry); /* direct.c */ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, struct nfs_direct_req *dreq); -extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq); +extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset); /* nfs4proc.c */ extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 85a952143e9f..ec3f0103e1a7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -170,6 +170,7 @@ static int nfs4_map_errors(int err) case -NFS4ERR_RESOURCE: case -NFS4ERR_LAYOUTTRYLATER: case -NFS4ERR_RECALLCONFLICT: + case -NFS4ERR_RETURNCONFLICT: return -EREMOTEIO; case -NFS4ERR_WRONGSEC: case -NFS4ERR_WRONG_CRED: @@ -558,6 +559,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server, case -NFS4ERR_GRACE: case -NFS4ERR_LAYOUTTRYLATER: case -NFS4ERR_RECALLCONFLICT: + case -NFS4ERR_RETURNCONFLICT: exception->delay = 1; return 0; @@ -9667,6 +9669,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, status = -EBUSY; break; case -NFS4ERR_RECALLCONFLICT: + case -NFS4ERR_RETURNCONFLICT: status = -ERECALLCONFLICT; break; case -NFS4ERR_DELEG_REVOKED: diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 1ffb1068216b..4448ff829cbb 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2729,7 +2729,8 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r if (pgio->pg_dreq == NULL) rd_size = i_size_read(pgio->pg_inode) - req_offset(req); else - rd_size = nfs_dreq_bytes_left(pgio->pg_dreq); + rd_size = nfs_dreq_bytes_left(pgio->pg_dreq, + req_offset(req)); pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index faecdbfa01a2..b3f6dda930d8 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4908,10 +4908,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&fp->fi_lock); fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); - spin_unlock(&fp->fi_lock); return false; } @@ -5499,12 +5497,13 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (status) goto out_unlock; + status = -EAGAIN; + if (fp->fi_had_conflict) + goto out_unlock; + spin_lock(&state_lock); spin_lock(&fp->fi_lock); - if (fp->fi_had_conflict) - status = -EAGAIN; - else - status = hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); @@ -7736,14 +7735,16 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { struct file_lock *fl; int status = false; - struct nfsd_file *nf = find_any_file(fp); + struct nfsd_file *nf; struct inode *inode; struct file_lock_context *flctx; + spin_lock(&fp->fi_lock); + nf = find_any_file_locked(fp); if (!nf) { /* Any valid lock stateid should have some sort of access */ WARN_ON_ONCE(1); - return status; + goto out; } inode = locks_inode(nf->nf_file); @@ -7759,7 +7760,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) } spin_unlock(&flctx->flc_lock); } - nfsd_file_put(nf); +out: + spin_unlock(&fp->fi_lock); return status; } @@ -7769,10 +7771,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) * @cstate: NFSv4 COMPOUND state * @u: RELEASE_LOCKOWNER arguments * - * The lockowner's so_count is bumped when a lock record is added - * or when copying a conflicting lock. The latter case is brief, - * but can lead to fleeting false positives when looking for - * locks-in-use. + * Check if theree are any locks still held and if not - free the lockowner + * and any lock state that is owned. * * Return values: * %nfs_ok: lockowner released or not found @@ -7808,10 +7808,13 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, spin_unlock(&clp->cl_lock); return nfs_ok; } - if (atomic_read(&lo->lo_owner.so_count) != 2) { - spin_unlock(&clp->cl_lock); - nfs4_put_stateowner(&lo->lo_owner); - return nfserr_locks_held; + + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + if (check_for_locks(stp->st_stid.sc_file, lo)) { + spin_unlock(&clp->cl_lock); + nfs4_put_stateowner(&lo->lo_owner); + return nfserr_locks_held; + } } unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index f6cc99af8192..c7695ebd28dc 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -1138,11 +1138,12 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file) int nfsd_pool_stats_release(struct inode *inode, struct file *file) { + struct seq_file *seq = file->private_data; + struct svc_serv *serv = seq->private; int ret = seq_release(inode, file); - struct net *net = inode->i_sb->s_fs_info; mutex_lock(&nfsd_mutex); - nfsd_put(net); + svc_put(serv); mutex_unlock(&nfsd_mutex); return ret; } diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 9930fa901039..1e7f653c1df7 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -40,8 +40,21 @@ static inline struct nilfs_dat_info *NILFS_DAT_I(struct inode *dat) static int nilfs_dat_prepare_entry(struct inode *dat, struct nilfs_palloc_req *req, int create) { - return nilfs_palloc_get_entry_block(dat, req->pr_entry_nr, - create, &req->pr_entry_bh); + int ret; + + ret = nilfs_palloc_get_entry_block(dat, req->pr_entry_nr, + create, &req->pr_entry_bh); + if (unlikely(ret == -ENOENT)) { + nilfs_err(dat->i_sb, + "DAT doesn't have a block to manage vblocknr = %llu", + (unsigned long long)req->pr_entry_nr); + /* + * Return internal code -EINVAL to notify bmap layer of + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } static void nilfs_dat_commit_entry(struct inode *dat, @@ -123,11 +136,7 @@ static void nilfs_dat_commit_free(struct inode *dat, int nilfs_dat_prepare_start(struct inode *dat, struct nilfs_palloc_req *req) { - int ret; - - ret = nilfs_dat_prepare_entry(dat, req, 0); - WARN_ON(ret == -ENOENT); - return ret; + return nilfs_dat_prepare_entry(dat, req, 0); } void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req, @@ -154,10 +163,8 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) int ret; ret = nilfs_dat_prepare_entry(dat, req, 0); - if (ret < 0) { - WARN_ON(ret == -ENOENT); + if (ret < 0) return ret; - } kaddr = kmap_atomic(req->pr_entry_bh->b_page); entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr, diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index a265d391ffe9..822e8d95d31e 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -105,7 +105,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf) nilfs_transaction_commit(inode->i_sb); mapped: - wait_for_stable_page(page); + /* + * Since checksumming including data blocks is performed to determine + * the validity of the log to be written and used for recovery, it is + * necessary to wait for writeback to finish here, regardless of the + * stable write requirement of the backing device. + */ + wait_on_page_writeback(page); out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 0955b657938f..a9b8d77c8c1d 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs, static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, struct nilfs_recovery_block *rb, - struct page *page) + loff_t pos, struct page *page) { struct buffer_head *bh_org; + size_t from = pos & ~PAGE_MASK; void *kaddr; bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize); @@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, return -EIO; kaddr = kmap_atomic(page); - memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size); + memcpy(kaddr + from, bh_org->b_data, bh_org->b_size); kunmap_atomic(kaddr); brelse(bh_org); return 0; @@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_inode; } - err = nilfs_recovery_copy_block(nilfs, rb, page); + err = nilfs_recovery_copy_block(nilfs, rb, pos, page); if (unlikely(err)) goto failed_page; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index a4a147a983e0..0a84613960db 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1702,7 +1702,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - set_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { lock_page(bd_page); @@ -1713,6 +1712,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) } break; } + set_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_begin_page_io(fs_page); fs_page = bh->b_page; @@ -1798,7 +1798,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { @@ -1807,6 +1806,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) } break; } + clear_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, err); fs_page = bh->b_page; @@ -1894,8 +1894,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) BIT(BH_Delay) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Redirected)); - set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh == segbuf->sb_super_root) { + set_buffer_uptodate(bh); + clear_buffer_dirty(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; @@ -1903,6 +1904,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) update_sr = true; break; } + set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, 0); fs_page = bh->b_page; diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 2215179c925b..2618bf5a3789 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -1658,8 +1658,10 @@ repack: le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); - if (!attr_b) - return -ENOENT; + if (!attr_b) { + err = -ENOENT; + goto out; + } attr = attr_b; le = le_b; @@ -1740,13 +1742,15 @@ ins_ext: ok: run_truncate_around(run, vcn); out: - if (new_valid > data_size) - new_valid = data_size; + if (attr_b) { + if (new_valid > data_size) + new_valid = data_size; - valid_size = le64_to_cpu(attr_b->nres.valid_size); - if (new_valid != valid_size) { - attr_b->nres.valid_size = cpu_to_le64(valid_size); - mi_b->dirty = true; + valid_size = le64_to_cpu(attr_b->nres.valid_size); + if (new_valid != valid_size) { + attr_b->nres.valid_size = cpu_to_le64(valid_size); + mi_b->dirty = true; + } } return err; diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index 0c6a68e71e7d..723e49ec83ce 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -127,12 +127,13 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, { size_t off; u16 sz; + const unsigned le_min_size = le_size(0); if (!le) { le = ni->attr_list.le; } else { sz = le16_to_cpu(le->size); - if (sz < sizeof(struct ATTR_LIST_ENTRY)) { + if (sz < le_min_size) { /* Impossible 'cause we should not return such le. */ return NULL; } @@ -141,7 +142,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, /* Check boundary. */ off = PtrOffset(ni->attr_list.le, le); - if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) { + if (off + le_min_size > ni->attr_list.size) { /* The regular end of list. */ return NULL; } @@ -149,8 +150,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, sz = le16_to_cpu(le->size); /* Check le for errors. */ - if (sz < sizeof(struct ATTR_LIST_ENTRY) || - off + sz > ni->attr_list.size || + if (sz < le_min_size || off + sz > ni->attr_list.size || sz < le->name_off + le->name_len * sizeof(short)) { return NULL; } diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index d4d9f4ffb6d9..72cdfa8727d3 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -309,11 +309,31 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, return 0; } - /* NTFS: symlinks are "dir + reparse" or "file + reparse" */ - if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) - dt_type = DT_LNK; - else - dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + /* + * NTFS: symlinks are "dir + reparse" or "file + reparse" + * Unfortunately reparse attribute is used for many purposes (several dozens). + * It is not possible here to know is this name symlink or not. + * To get exactly the type of name we should to open inode (read mft). + * getattr for opened file (fstat) correctly returns symlink. + */ + dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + + /* + * It is not reliable to detect the type of name using duplicated information + * stored in parent directory. + * The only correct way to get the type of name - read MFT record and find ATTR_STD. + * The code below is not good idea. + * It does additional locks/reads just to get the type of name. + * Should we use additional mount option to enable branch below? + */ + if ((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) && + ino != ni->mi.rno) { + struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL); + if (!IS_ERR_OR_NULL(inode)) { + dt_type = fs_umode_to_dtype(inode->i_mode); + iput(inode); + } + } return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); } @@ -495,11 +515,9 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, struct INDEX_HDR *hdr; const struct ATTR_FILE_NAME *fname; u32 e_size, off, end; - u64 vbo = 0; size_t drs = 0, fles = 0, bit = 0; - loff_t i_size = ni->vfs_inode.i_size; struct indx_node *node = NULL; - u8 index_bits = ni->dir.index_bits; + size_t max_indx = ni->vfs_inode.i_size >> ni->dir.index_bits; if (is_empty) *is_empty = true; @@ -543,7 +561,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, fles += 1; } - if (vbo >= i_size) + if (bit >= max_indx) goto out; err = indx_used_bit(&ni->dir, ni, &bit); @@ -553,8 +571,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, if (bit == MINUS_ONE_T) goto out; - vbo = (u64)bit << index_bits; - if (vbo >= i_size) + if (bit >= max_indx) goto out; err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits, @@ -564,7 +581,6 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, hdr = &node->index->ihdr; bit += 1; - vbo = (u64)bit << ni->dir.idx2vbn_bits; } out: diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index f31c0389a2e7..14efe46df91e 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -1110,6 +1110,8 @@ out: iocb->ki_pos += written; if (iocb->ki_pos > ni->i_valid) ni->i_valid = iocb->ki_pos; + if (iocb->ki_pos > i_size) + i_size_write(inode, iocb->ki_pos); return written; } diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 710cb5aa5a65..d53ef128fa73 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -465,7 +465,7 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr) { const struct RESTART_AREA *ra; u16 cl, fl, ul; - u32 off, l_size, file_dat_bits, file_size_round; + u32 off, l_size, seq_bits; u16 ro = le16_to_cpu(rhdr->ra_off); u32 sys_page = le32_to_cpu(rhdr->sys_page_size); @@ -511,13 +511,15 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr) /* Make sure the sequence number bits match the log file size. */ l_size = le64_to_cpu(ra->l_size); - file_dat_bits = sizeof(u64) * 8 - le32_to_cpu(ra->seq_num_bits); - file_size_round = 1u << (file_dat_bits + 3); - if (file_size_round != l_size && - (file_size_round < l_size || (file_size_round / 2) > l_size)) { - return false; + seq_bits = sizeof(u64) * 8 + 3; + while (l_size) { + l_size >>= 1; + seq_bits -= 1; } + if (seq_bits != ra->seq_num_bits) + return false; + /* The log page data offset and record header length must be quad-aligned. */ if (!IS_ALIGNED(le16_to_cpu(ra->data_off), 8) || !IS_ALIGNED(le16_to_cpu(ra->rec_hdr_len), 8)) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 873b1434a998..1eac80d55b55 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -976,6 +976,30 @@ static inline __le32 security_hash(const void *sd, size_t bytes) return cpu_to_le32(hash); } +/* + * simple wrapper for sb_bread_unmovable. + */ +struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block) +{ + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct buffer_head *bh; + + if (unlikely(block >= sbi->volume.blocks)) { + /* prevent generic message "attempt to access beyond end of device" */ + ntfs_err(sb, "try to read out of volume at offset 0x%llx", + (u64)block << sb->s_blocksize_bits); + return NULL; + } + + bh = sb_bread_unmovable(sb, block); + if (bh) + return bh; + + ntfs_err(sb, "failed to read volume at offset 0x%llx", + (u64)block << sb->s_blocksize_bits); + return NULL; +} + int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer) { struct block_device *bdev = sb->s_bdev; @@ -1842,10 +1866,12 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) goto out; } - root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT)); - if (root_sdh->type != ATTR_ZERO || + if(!(root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || + root_sdh->type != ATTR_ZERO || root_sdh->rule != NTFS_COLLATION_TYPE_SECURITY_HASH || - offsetof(struct INDEX_ROOT, ihdr) + root_sdh->ihdr.used > attr->res.data_size) { + offsetof(struct INDEX_ROOT, ihdr) + + le32_to_cpu(root_sdh->ihdr.used) > + le32_to_cpu(attr->res.data_size)) { err = -EINVAL; goto out; } @@ -1861,10 +1887,12 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) goto out; } - root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT)); - if (root_sii->type != ATTR_ZERO || + if(!(root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || + root_sii->type != ATTR_ZERO || root_sii->rule != NTFS_COLLATION_TYPE_UINT || - offsetof(struct INDEX_ROOT, ihdr) + root_sii->ihdr.used > attr->res.data_size) { + offsetof(struct INDEX_ROOT, ihdr) + + le32_to_cpu(root_sii->ihdr.used) > + le32_to_cpu(attr->res.data_size)) { err = -EINVAL; goto out; } diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index b89a33f5761e..7371f7855e4c 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1097,7 +1097,8 @@ ok: } /* check for index header length */ - if (offsetof(struct INDEX_BUFFER, ihdr) + ib->ihdr.used > bytes) { + if (offsetof(struct INDEX_BUFFER, ihdr) + le32_to_cpu(ib->ihdr.used) > + bytes) { err = -EINVAL; goto out; } diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index dc937089a464..42dd9fdaf415 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -402,7 +402,6 @@ end_enum: goto out; if (!is_match && name) { - /* Reuse rec as buffer for ascii name. */ err = -ENOENT; goto out; } @@ -417,6 +416,7 @@ end_enum: if (names != le16_to_cpu(rec->hard_links)) { /* Correct minor error on the fly. Do not mark inode as dirty. */ + ntfs_inode_warn(inode, "Correct links count -> %u.", names); rec->hard_links = cpu_to_le16(names); ni->mi.dirty = true; } diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 0f38d558169a..ba26a465b309 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -517,12 +517,10 @@ struct ATTR_LIST_ENTRY { __le64 vcn; // 0x08: Starting VCN of this attribute. struct MFT_REF ref; // 0x10: MFT record number with attribute. __le16 id; // 0x18: struct ATTRIB ID. - __le16 name[3]; // 0x1A: Just to align. To get real name can use bNameOffset. + __le16 name[]; // 0x1A: Just to align. To get real name can use name_off. }; // sizeof(0x20) -static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20); - static inline u32 le_size(u8 name_len) { return ALIGN(offsetof(struct ATTR_LIST_ENTRY, name) + diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 8c9abaf139e6..0f9bec29f2b7 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -467,7 +467,7 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn, int al_update(struct ntfs_inode *ni, int sync); static inline size_t al_aligned(size_t size) { - return (size + 1023) & ~(size_t)1023; + return size_add(size, 1023) & ~(size_t)1023; } /* Globals from bitfunc.c */ @@ -580,6 +580,7 @@ bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes); int log_replay(struct ntfs_inode *ni, bool *initialized); /* Globals from fsntfs.c */ +struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block); bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes); int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, bool simple); @@ -1012,19 +1013,6 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size) return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; } -static inline struct buffer_head *ntfs_bread(struct super_block *sb, - sector_t block) -{ - struct buffer_head *bh = sb_bread(sb, block); - - if (bh) - return bh; - - ntfs_err(sb, "failed to read volume at offset 0x%llx", - (u64)block << sb->s_blocksize_bits); - return NULL; -} - static inline struct ntfs_inode *ntfs_i(struct inode *inode) { return container_of(inode, struct ntfs_inode, vfs_inode); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index ba336c7280b8..a8d4ed7bca02 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -226,11 +226,6 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return NULL; } - if (off + asize < off) { - /* overflow check */ - return NULL; - } - attr = Add2Ptr(attr, asize); off += asize; } @@ -253,8 +248,8 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) if ((t32 & 0xf) || (t32 > 0x100)) return NULL; - /* Check boundary. */ - if (off + asize > used) + /* Check overflow and boundary. */ + if (off + asize < off || off + asize > used) return NULL; /* Check size of attribute. */ @@ -491,8 +486,20 @@ bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi, return false; if (ni && is_attr_indexed(attr)) { - le16_add_cpu(&ni->mi.mrec->hard_links, -1); - ni->mi.dirty = true; + u16 links = le16_to_cpu(ni->mi.mrec->hard_links); + struct ATTR_FILE_NAME *fname = + attr->type != ATTR_NAME ? + NULL : + resident_data_ex(attr, + SIZEOF_ATTRIBUTE_FILENAME); + if (fname && fname->type == FILE_NAME_DOS) { + /* Do not decrease links count deleting DOS name. */ + } else if (!links) { + /* minor error. Not critical. */ + } else { + ni->mi.mrec->hard_links = cpu_to_le16(links - 1); + ni->mi.dirty = true; + } } used -= asize; diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index df15e00c2a3a..d98cf7b382bc 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -217,6 +217,9 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, if (!ea->name_len) break; + if (ea->name_len > ea_size) + break; + if (buffer) { /* Check if we can use field ea->name */ if (off + ea_size > size) diff --git a/fs/pipe.c b/fs/pipe.c index 42c7ff41c2db..9873a6030df5 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -436,12 +436,10 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) { + if (pipe_has_watch_queue(pipe)) { ret = -EXDEV; goto out; } -#endif /* * If it wasn't empty we try to merge new data into @@ -1303,6 +1301,11 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) pipe->tail = tail; pipe->head = head; + if (!pipe_has_watch_queue(pipe)) { + pipe->max_usage = nr_slots; + pipe->nr_accounted = nr_slots; + } + spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ @@ -1320,10 +1323,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) unsigned int nr_slots, size; long ret = 0; -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) + if (pipe_has_watch_queue(pipe)) return -EBUSY; -#endif size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; @@ -1356,8 +1357,6 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) if (ret < 0) goto out_revert_acct; - pipe->max_usage = nr_slots; - pipe->nr_accounted = nr_slots; return pipe->max_usage * PAGE_SIZE; out_revert_acct: @@ -1375,10 +1374,8 @@ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) if (file->f_op != &pipefifo_fops || !pipe) return NULL; -#ifdef CONFIG_WATCH_QUEUE - if (for_splice && pipe->watch_queue) + if (for_splice && pipe_has_watch_queue(pipe)) return NULL; -#endif return pipe; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 49283b8103c7..1b0d78dfd20f 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -501,7 +501,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = utime = stime = 0; + cutime = cstime = 0; cgtime = gtime = 0; if (lock_task_sighand(task, &flags)) { @@ -535,7 +535,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, min_flt += sig->min_flt; maj_flt += sig->maj_flt; - thread_group_cputime_adjusted(task, &utime, &stime); gtime += sig->gtime; if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) @@ -551,10 +550,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, if (permitted && (!whole || num_threads < 2)) wchan = !task_is_running(task); - if (!whole) { + + if (whole) { + thread_group_cputime_adjusted(task, &utime, &stime); + } else { + task_cputime_adjusted(task, &utime, &stime); min_flt = task->min_flt; maj_flt = task->maj_flt; - task_cputime_adjusted(task, &utime, &stime); gtime = task_gtime(task); } diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index f3fa3625d772..e15b4631364a 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -519,6 +519,7 @@ static int ramoops_init_przs(const char *name, } zone_sz = mem_sz / *cnt; + zone_sz = ALIGN_DOWN(zone_sz, 2); if (!zone_sz) { dev_err(dev, "%s zone size == 0\n", name); goto fail; diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 1e755d093d92..f479e0755a24 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -190,7 +190,7 @@ static int persistent_ram_init_ecc(struct persistent_ram_zone *prz, { int numerr; struct persistent_ram_buffer *buffer = prz->buffer; - int ecc_blocks; + size_t ecc_blocks; size_t ecc_total; if (!ecc_info || !ecc_info->ecc_size) diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 5a132c1e6f6c..fd082151c5f9 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -149,7 +149,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, return -EOPNOTSUPP; ses = tcon->ses; - server = ses->server; + server = cifs_pick_channel(ses); cfids = tcon->cfids; if (!server->ops->new_lease_key) @@ -268,10 +268,12 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) goto oshr_free; - smb2_parse_contexts(server, o_rsp, + rc = smb2_parse_contexts(server, rsp_iov, &oparms.fid->epoch, - oparms.fid->lease_key, &oplock, - NULL, NULL); + oparms.fid->lease_key, + &oplock, NULL, NULL); + if (rc) + goto oshr_free; if (!(oplock & SMB2_LEASE_READ_CACHING_HE)) goto oshr_free; qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index 0acb455368f2..5df8d9323337 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -38,11 +38,13 @@ void cifs_dump_detail(void *buf, struct TCP_Server_Info *server) #ifdef CONFIG_CIFS_DEBUG2 struct smb_hdr *smb = buf; - cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d\n", - smb->Command, smb->Status.CifsError, - smb->Flags, smb->Flags2, smb->Mid, smb->Pid); - cifs_dbg(VFS, "smb buf %p len %u\n", smb, - server->ops->calc_smb_size(smb)); + cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d Wct: %d\n", + smb->Command, smb->Status.CifsError, smb->Flags, + smb->Flags2, smb->Mid, smb->Pid, smb->WordCount); + if (!server->ops->check_message(buf, server->total_read, server)) { + cifs_dbg(VFS, "smb buf %p len %u\n", smb, + server->ops->calc_smb_size(smb)); + } #endif /* CONFIG_CIFS_DEBUG2 */ } diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index d0ac2648c0d6..d3d4cf6321fd 100644 --- a/fs/smb/client/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -444,7 +444,7 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, len = cifs_strtoUTF16(user, ses->user_name, len, nls_cp); UniStrupr(user); } else { - memset(user, '\0', 2); + *(u16 *)user = 0; } rc = crypto_shash_update(ses->server->secmech.hmacmd5, diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 2e15b182e59f..7286a56aebfa 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -1240,7 +1240,7 @@ static int cifs_flush_folio(struct inode *inode, loff_t pos, loff_t *_fstart, lo int rc = 0; folio = filemap_get_folio(inode->i_mapping, index); - if (IS_ERR(folio)) + if (!folio) return 0; size = folio_size(folio); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 2e814eadd6ae..58bb54994e22 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -86,7 +86,7 @@ #define SMB_INTERFACE_POLL_INTERVAL 600 /* maximum number of PDUs in one compound */ -#define MAX_COMPOUND 5 +#define MAX_COMPOUND 7 /* * Default number of credits to keep available for SMB3. @@ -513,7 +513,8 @@ struct smb_version_operations { struct mid_q_entry **, char **, int *); enum securityEnum (*select_sectype)(struct TCP_Server_Info *, enum securityEnum); - int (*next_header)(char *); + int (*next_header)(struct TCP_Server_Info *server, char *buf, + unsigned int *noff); /* ioctl passthrough for query_info */ int (*ioctl_query_info)(const unsigned int xid, struct cifs_tcon *tcon, @@ -971,7 +972,6 @@ release_iface(struct kref *ref) struct cifs_server_iface *iface = container_of(ref, struct cifs_server_iface, refcount); - list_del_init(&iface->iface_head); kfree(iface); } diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index c403816d0b6c..97bb1838555b 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -882,11 +882,13 @@ typedef struct smb_com_open_rsp { __u8 OplockLevel; __u16 Fid; __le32 CreateAction; - __le64 CreationTime; - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le32 FileAttributes; + struct_group(common_attributes, + __le64 CreationTime; + __le64 LastAccessTime; + __le64 LastWriteTime; + __le64 ChangeTime; + __le32 FileAttributes; + ); __le64 AllocationSize; __le64 EndOfFile; __le16 FileType; @@ -2268,11 +2270,13 @@ typedef struct { /* QueryFileInfo/QueryPathinfo (also for SetPath/SetFile) data buffer formats */ /******************************************************************************/ typedef struct { /* data block encoding of response to level 263 QPathInfo */ - __le64 CreationTime; - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le32 Attributes; + struct_group(common_attributes, + __le64 CreationTime; + __le64 LastAccessTime; + __le64 LastWriteTime; + __le64 ChangeTime; + __le32 Attributes; + ); __u32 Pad1; __le64 AllocationSize; __le64 EndOfFile; /* size ie offset to first free byte in file */ diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index c90d4ec9292c..67c5fc2b2db9 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1234,8 +1234,10 @@ openRetry: *oplock |= CIFS_CREATE_ACTION; if (buf) { - /* copy from CreationTime to Attributes */ - memcpy((char *)buf, (char *)&rsp->CreationTime, 36); + /* copy commonly used attributes */ + memcpy(&buf->common_attributes, + &rsp->common_attributes, + sizeof(buf->common_attributes)); /* the file_info buf is endian converted by caller */ buf->AllocationSize = rsp->AllocationSize; buf->EndOfFile = rsp->EndOfFile; diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 5b1991893834..49fdc6dfdcf8 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -258,10 +258,13 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) { /* check if iface is still active */ - if (!cifs_chan_is_iface_active(ses, server)) + spin_lock(&ses->chan_lock); + if (!cifs_chan_is_iface_active(ses, server)) { + spin_unlock(&ses->chan_lock); cifs_chan_update_iface(ses, server); + spin_lock(&ses->chan_lock); + } - spin_lock(&ses->chan_lock); if (!mark_smb_session && cifs_chan_needs_reconnect(ses, server)) { spin_unlock(&ses->chan_lock); continue; @@ -1225,7 +1228,12 @@ next_pdu: server->total_read += length; if (server->ops->next_header) { - next_offset = server->ops->next_header(buf); + if (server->ops->next_header(server, buf, &next_offset)) { + cifs_dbg(VFS, "%s: malformed response (next_offset=%u)\n", + __func__, next_offset); + cifs_reconnect(server, true); + continue; + } if (next_offset) server->pdu_size = next_offset; } diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index f4818599c00a..4d5302b58b53 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -209,7 +209,7 @@ cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_c switch (match_token(value, cifs_secflavor_tokens, args)) { case Opt_sec_krb5p: - cifs_errorf(fc, "sec=krb5p is not supported!\n"); + cifs_errorf(fc, "sec=krb5p is not supported. Use sec=krb5,seal instead\n"); return 1; case Opt_sec_krb5i: ctx->sign = true; diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index e73625b5d0cc..f64bad513ba6 100644 --- a/fs/smb/client/fscache.c +++ b/fs/smb/client/fscache.c @@ -108,6 +108,8 @@ void cifs_fscache_get_inode_cookie(struct inode *inode) &cifsi->uniqueid, sizeof(cifsi->uniqueid), &cd, sizeof(cd), i_size_read(&cifsi->netfs.inode)); + if (cifsi->netfs.cache) + mapping_set_release_always(inode->i_mapping); } void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 7be51f9d2fa1..5343898bac8a 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -264,7 +264,7 @@ cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info, fattr->cf_dtype = DT_REG; break; case UNIX_SYMLINK: - fattr->cf_mode |= S_IFLNK; + fattr->cf_mode |= S_IFLNK | cifs_sb->ctx->file_mode; fattr->cf_dtype = DT_LNK; break; case UNIX_DIR: diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 31e06133acc3..41290c12d0bc 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -350,6 +350,10 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server) cifs_dbg(VFS, "Length less than smb header size\n"); } return -EIO; + } else if (total_read < sizeof(*smb) + 2 * smb->WordCount) { + cifs_dbg(VFS, "%s: can't read BCC due to invalid WordCount(%u)\n", + __func__, smb->WordCount); + return -EIO; } /* otherwise, there is enough to get to the BCC */ diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 2d75ba5aaa8a..5990bdbae598 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -304,14 +304,16 @@ cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info, } static void cifs_fulldir_info_to_fattr(struct cifs_fattr *fattr, - SEARCH_ID_FULL_DIR_INFO *info, + const void *info, struct cifs_sb_info *cifs_sb) { + const FILE_FULL_DIRECTORY_INFO *di = info; + __dir_info_to_fattr(fattr, info); - /* See MS-FSCC 2.4.19 FileIdFullDirectoryInformation */ + /* See MS-FSCC 2.4.14, 2.4.19 */ if (fattr->cf_cifsattrs & ATTR_REPARSE) - fattr->cf_cifstag = le32_to_cpu(info->EaSize); + fattr->cf_cifstag = le32_to_cpu(di->EaSize); cifs_fill_common_info(fattr, cifs_sb); } @@ -425,7 +427,7 @@ ffirst_retry: } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) { cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO; } else /* not srvinos - BB fixme add check for backlevel? */ { - cifsFile->srch_inf.info_level = SMB_FIND_FILE_DIRECTORY_INFO; + cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO; } search_flags = CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME; @@ -1019,10 +1021,9 @@ static int cifs_filldir(char *find_entry, struct file *file, (FIND_FILE_STANDARD_INFO *)find_entry, cifs_sb); break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: case SMB_FIND_FILE_ID_FULL_DIR_INFO: - cifs_fulldir_info_to_fattr(&fattr, - (SEARCH_ID_FULL_DIR_INFO *)find_entry, - cifs_sb); + cifs_fulldir_info_to_fattr(&fattr, find_entry, cifs_sb); break; default: cifs_dir_info_to_fattr(&fattr, diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 634035bcb934..b8e14bcd2c68 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -248,6 +248,8 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) &iface->sockaddr, rc); kref_put(&iface->refcount, release_iface); + /* failure to add chan should increase weight */ + iface->weight_fulfilled++; continue; } diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index ba6cc50af390..a7475bc05cac 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -34,7 +34,7 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) len = (u32)err->ErrorContextCount * (offsetof(struct smb2_error_context_rsp, ErrorContextData) + sizeof(struct smb2_symlink_err_rsp)); - if (le32_to_cpu(err->ByteCount) < len || iov->iov_len < len + sizeof(*err)) + if (le32_to_cpu(err->ByteCount) < len || iov->iov_len < len + sizeof(*err) + 1) return ERR_PTR(-EINVAL); p = (struct smb2_error_context_rsp *)err->ErrorData; diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 88942b1fb431..15fa022e7999 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -113,7 +113,7 @@ static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, } else if (nc_offset + 1 == non_ctxlen) { cifs_dbg(FYI, "no SPNEGO security blob in negprot rsp\n"); size_of_pad_before_neg_ctxts = 0; - } else if (non_ctxlen == SMB311_NEGPROT_BASE_SIZE) + } else if (non_ctxlen == SMB311_NEGPROT_BASE_SIZE + 1) /* has padding, but no SPNEGO blob */ size_of_pad_before_neg_ctxts = nc_offset - non_ctxlen + 1; else @@ -173,6 +173,21 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) } mid = le64_to_cpu(shdr->MessageId); + if (check_smb2_hdr(shdr, mid)) + return 1; + + if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) { + cifs_dbg(VFS, "Invalid structure size %u\n", + le16_to_cpu(shdr->StructureSize)); + return 1; + } + + command = le16_to_cpu(shdr->Command); + if (command >= NUMBER_OF_SMB2_COMMANDS) { + cifs_dbg(VFS, "Invalid SMB2 command %d\n", command); + return 1; + } + if (len < pdu_size) { if ((len >= hdr_size) && (shdr->Status != 0)) { @@ -193,21 +208,6 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) return 1; } - if (check_smb2_hdr(shdr, mid)) - return 1; - - if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) { - cifs_dbg(VFS, "Invalid structure size %u\n", - le16_to_cpu(shdr->StructureSize)); - return 1; - } - - command = le16_to_cpu(shdr->Command); - if (command >= NUMBER_OF_SMB2_COMMANDS) { - cifs_dbg(VFS, "Invalid SMB2 command %d\n", command); - return 1; - } - if (smb2_rsp_struct_sizes[command] != pdu->StructureSize2) { if (command != SMB2_OPLOCK_BREAK_HE && (shdr->Status == 0 || pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2_LE)) { diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 1b3489a2f0db..34d1262004df 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -398,8 +398,10 @@ smb2_dump_detail(void *buf, struct TCP_Server_Info *server) cifs_server_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Mid: %llu Pid: %d\n", shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId, shdr->Id.SyncId.ProcessId); - cifs_server_dbg(VFS, "smb buf %p len %u\n", buf, - server->ops->calc_smb_size(buf)); + if (!server->ops->check_message(buf, server->total_read, server)) { + cifs_server_dbg(VFS, "smb buf %p len %u\n", buf, + server->ops->calc_smb_size(buf)); + } #endif } @@ -588,16 +590,12 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, } /* - * Go through iface_list and do kref_put to remove - * any unused ifaces. ifaces in use will be removed - * when the last user calls a kref_put on it + * Go through iface_list and mark them as inactive */ list_for_each_entry_safe(iface, niface, &ses->iface_list, - iface_head) { + iface_head) iface->is_active = 0; - kref_put(&iface->refcount, release_iface); - ses->iface_count--; - } + spin_unlock(&ses->iface_lock); /* @@ -615,7 +613,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, goto out; } - while (bytes_left >= sizeof(*p)) { + while (bytes_left >= (ssize_t)sizeof(*p)) { memset(&tmp_iface, 0, sizeof(tmp_iface)); tmp_iface.speed = le64_to_cpu(p->LinkSpeed); tmp_iface.rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0; @@ -672,10 +670,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, iface_head) { ret = iface_cmp(iface, &tmp_iface); if (!ret) { - /* just get a ref so that it doesn't get picked/freed */ iface->is_active = 1; - kref_get(&iface->refcount); - ses->iface_count++; spin_unlock(&ses->iface_lock); goto next_iface; } else if (ret < 0) { @@ -742,6 +737,20 @@ next_iface: } out: + /* + * Go through the list again and put the inactive entries + */ + spin_lock(&ses->iface_lock); + list_for_each_entry_safe(iface, niface, &ses->iface_list, + iface_head) { + if (!iface->is_active) { + list_del(&iface->iface_head); + kref_put(&iface->refcount, release_iface); + ses->iface_count--; + } + } + spin_unlock(&ses->iface_lock); + return rc; } @@ -778,9 +787,14 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_ goto out; /* check if iface is still active */ + spin_lock(&ses->chan_lock); pserver = ses->chans[0].server; - if (pserver && !cifs_chan_is_iface_active(ses, pserver)) + if (pserver && !cifs_chan_is_iface_active(ses, pserver)) { + spin_unlock(&ses->chan_lock); cifs_chan_update_iface(ses, pserver); + spin_lock(&ses->chan_lock); + } + spin_unlock(&ses->chan_lock); out: kfree(out_buf); @@ -5196,17 +5210,22 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid) NULL, 0, 0, false); } -static int -smb2_next_header(char *buf) +static int smb2_next_header(struct TCP_Server_Info *server, char *buf, + unsigned int *noff) { struct smb2_hdr *hdr = (struct smb2_hdr *)buf; struct smb2_transform_hdr *t_hdr = (struct smb2_transform_hdr *)buf; - if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) - return sizeof(struct smb2_transform_hdr) + - le32_to_cpu(t_hdr->OriginalMessageSize); - - return le32_to_cpu(hdr->NextCommand); + if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) { + *noff = le32_to_cpu(t_hdr->OriginalMessageSize); + if (unlikely(check_add_overflow(*noff, sizeof(*t_hdr), noff))) + return -EINVAL; + } else { + *noff = le32_to_cpu(hdr->NextCommand); + } + if (unlikely(*noff && *noff < MID_HEADER_SIZE(server))) + return -EINVAL; + return 0; } static int @@ -5747,7 +5766,7 @@ struct smb_version_values smb20_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5769,7 +5788,7 @@ struct smb_version_values smb21_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5790,7 +5809,7 @@ struct smb_version_values smb3any_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5811,7 +5830,7 @@ struct smb_version_values smbdefault_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5832,7 +5851,7 @@ struct smb_version_values smb30_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5853,7 +5872,7 @@ struct smb_version_values smb302_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5874,7 +5893,7 @@ struct smb_version_values smb311_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 847d69d327c2..4c1231496a72 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -372,10 +372,15 @@ static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, void **request_buf, unsigned int *total_len) { /* BB eventually switch this to SMB2 specific small buf size */ - if (smb2_command == SMB2_SET_INFO) + switch (smb2_command) { + case SMB2_SET_INFO: + case SMB2_QUERY_INFO: *request_buf = cifs_buf_get(); - else + break; + default: *request_buf = cifs_small_buf_get(); + break; + } if (*request_buf == NULL) { /* BB should we add a retry in here if not a writepage? */ return -ENOMEM; @@ -1381,7 +1386,7 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) /* Testing shows that buffer offset must be at location of Buffer[0] */ req->SecurityBufferOffset = - cpu_to_le16(sizeof(struct smb2_sess_setup_req) - 1 /* pad */); + cpu_to_le16(sizeof(struct smb2_sess_setup_req)); req->SecurityBufferLength = cpu_to_le16(sess_data->iov[1].iov_len); memset(&rqst, 0, sizeof(struct smb_rqst)); @@ -1900,8 +1905,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, iov[0].iov_len = total_len - 1; /* Testing shows that buffer offset must be at location of Buffer[0] */ - req->PathOffset = cpu_to_le16(sizeof(struct smb2_tree_connect_req) - - 1 /* pad */); + req->PathOffset = cpu_to_le16(sizeof(struct smb2_tree_connect_req)); req->PathLength = cpu_to_le16(unc_path_len - 2); iov[1].iov_base = unc_path; iov[1].iov_len = unc_path_len; @@ -2141,17 +2145,18 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info, posix->nlink, posix->mode, posix->reparse_tag); } -void -smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, __u8 *oplock, - struct smb2_file_all_info *buf, - struct create_posix_rsp *posix) +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix) { - char *data_offset; + struct smb2_create_rsp *rsp = rsp_iov->iov_base; struct create_context *cc; - unsigned int next; - unsigned int remaining; + size_t rem, off, len; + size_t doff, dlen; + size_t noff, nlen; char *name; static const char smb3_create_tag_posix[] = { 0x93, 0xAD, 0x25, 0x50, 0x9C, @@ -2160,45 +2165,63 @@ smb2_parse_contexts(struct TCP_Server_Info *server, }; *oplock = 0; - data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); - remaining = le32_to_cpu(rsp->CreateContextsLength); - cc = (struct create_context *)data_offset; + + off = le32_to_cpu(rsp->CreateContextsOffset); + rem = le32_to_cpu(rsp->CreateContextsLength); + if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len) + return -EINVAL; + cc = (struct create_context *)((u8 *)rsp + off); /* Initialize inode number to 0 in case no valid data in qfid context */ if (buf) buf->IndexNumber = 0; - while (remaining >= sizeof(struct create_context)) { - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) - *oplock = server->ops->parse_lease_buf(cc, epoch, - lease_key); - else if (buf && (le16_to_cpu(cc->NameLength) == 4) && - strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) - parse_query_id_ctxt(cc, buf); - else if ((le16_to_cpu(cc->NameLength) == 16)) { - if (posix && - memcmp(name, smb3_create_tag_posix, 16) == 0) + while (rem >= sizeof(*cc)) { + doff = le16_to_cpu(cc->DataOffset); + dlen = le32_to_cpu(cc->DataLength); + if (check_add_overflow(doff, dlen, &len) || len > rem) + return -EINVAL; + + noff = le16_to_cpu(cc->NameOffset); + nlen = le16_to_cpu(cc->NameLength); + if (noff + nlen > doff) + return -EINVAL; + + name = (char *)cc + noff; + switch (nlen) { + case 4: + if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) { + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + } else if (buf && + !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) { + parse_query_id_ctxt(cc, buf); + } + break; + case 16: + if (posix && !memcmp(name, smb3_create_tag_posix, 16)) parse_posix_ctxt(cc, buf, posix); + break; + default: + cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n", + __func__, nlen, dlen); + if (IS_ENABLED(CONFIG_CIFS_DEBUG2)) + cifs_dump_mem("context data: ", cc, dlen); + break; } - /* else { - cifs_dbg(FYI, "Context not matched with len %d\n", - le16_to_cpu(cc->NameLength)); - cifs_dump_mem("Cctxt name: ", name, 4); - } */ - - next = le32_to_cpu(cc->Next); - if (!next) + + off = le32_to_cpu(cc->Next); + if (!off) break; - remaining -= next; - cc = (struct create_context *)((char *)cc + next); + if (check_sub_overflow(rem, off, &rem)) + return -EINVAL; + cc = (struct create_context *)((u8 *)cc + off); } if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) *oplock = rsp->OplockLevel; - return; + return 0; } static int @@ -3078,8 +3101,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } - smb2_parse_contexts(server, rsp, &oparms->fid->epoch, - oparms->fid->lease_key, oplock, buf, posix); + rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf, posix); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); @@ -3425,12 +3448,10 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, } else { trace_smb3_close_done(xid, persistent_fid, tcon->tid, ses->Suid); - /* - * Note that have to subtract 4 since struct network_open_info - * has a final 4 byte pad that close response does not have - */ if (pbuf) - memcpy(pbuf, (char *)&rsp->CreationTime, sizeof(*pbuf) - 4); + memcpy(&pbuf->network_open_info, + &rsp->network_open_info, + sizeof(pbuf->network_open_info)); } atomic_dec(&tcon->num_remote_opens); @@ -3523,8 +3544,13 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, struct smb2_query_info_req *req; struct kvec *iov = rqst->rq_iov; unsigned int total_len; + size_t len; int rc; + if (unlikely(check_add_overflow(input_len, sizeof(*req), &len) || + len > CIFSMaxBufSize)) + return -EINVAL; + rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, server, (void **) &req, &total_len); if (rc) @@ -3546,7 +3572,7 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, iov[0].iov_base = (char *)req; /* 1 for Buffer */ - iov[0].iov_len = total_len - 1 + input_len; + iov[0].iov_len = len; return 0; } @@ -3554,7 +3580,7 @@ void SMB2_query_info_free(struct smb_rqst *rqst) { if (rqst && rqst->rq_iov) - cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */ + cifs_buf_release(rqst->rq_iov[0].iov_base); /* request */ } static int @@ -3786,7 +3812,7 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, ses->Suid, (u8)watch_tree, completion_filter); /* validate that notify information is plausible */ if ((rsp_iov.iov_base == NULL) || - (rsp_iov.iov_len < sizeof(struct smb2_change_notify_rsp))) + (rsp_iov.iov_len < sizeof(struct smb2_change_notify_rsp) + 1)) goto cnotify_exit; smb_rsp = (struct smb2_change_notify_rsp *)rsp_iov.iov_base; @@ -4984,6 +5010,9 @@ int SMB2_query_directory_init(const unsigned int xid, case SMB_FIND_FILE_POSIX_INFO: req->FileInformationClass = SMB_FIND_FILE_POSIX_INFO; break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: + req->FileInformationClass = FILE_FULL_DIRECTORY_INFORMATION; + break; default: cifs_tcon_dbg(VFS, "info level %u isn't supported\n", info_level); @@ -4999,7 +5028,7 @@ int SMB2_query_directory_init(const unsigned int xid, memcpy(bufptr, &asteriks, len); req->FileNameOffset = - cpu_to_le16(sizeof(struct smb2_query_directory_req) - 1); + cpu_to_le16(sizeof(struct smb2_query_directory_req)); req->FileNameLength = cpu_to_le16(len); /* * BB could be 30 bytes or so longer if we used SMB2 specific @@ -5053,6 +5082,9 @@ smb2_parse_query_directory(struct cifs_tcon *tcon, /* note that posix payload are variable size */ info_buf_size = sizeof(struct smb2_posix_info); break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: + info_buf_size = sizeof(FILE_FULL_DIRECTORY_INFO); + break; default: cifs_tcon_dbg(VFS, "info level %u isn't supported\n", srch_inf->info_level); @@ -5195,8 +5227,7 @@ SMB2_set_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, req->VolatileFileId = volatile_fid; req->AdditionalInformation = cpu_to_le32(additional_info); - req->BufferOffset = - cpu_to_le16(sizeof(struct smb2_set_info_req) - 1); + req->BufferOffset = cpu_to_le16(sizeof(struct smb2_set_info_req)); req->BufferLength = cpu_to_le32(*size); memcpy(req->Buffer, *data, *size); @@ -5430,15 +5461,20 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, req->VolatileFileId = volatile_fid; /* 1 for pad */ req->InputBufferOffset = - cpu_to_le16(sizeof(struct smb2_query_info_req) - 1); + cpu_to_le16(sizeof(struct smb2_query_info_req)); req->OutputBufferLength = cpu_to_le32( - outbuf_len + sizeof(struct smb2_query_info_rsp) - 1); + outbuf_len + sizeof(struct smb2_query_info_rsp)); iov->iov_base = (char *)req; iov->iov_len = total_len; return 0; } +static inline void free_qfs_info_req(struct kvec *iov) +{ + cifs_buf_release(iov->iov_base); +} + int SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata) @@ -5470,7 +5506,7 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(iov.iov_base); + free_qfs_info_req(&iov); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); goto posix_qfsinf_exit; @@ -5521,7 +5557,7 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(iov.iov_base); + free_qfs_info_req(&iov); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); goto qfsinf_exit; @@ -5588,7 +5624,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(iov.iov_base); + free_qfs_info_req(&iov); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); goto qfsattr_exit; diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index 1237bb86e93a..8d011fedecd0 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -57,7 +57,7 @@ struct smb2_rdma_crypto_transform { #define COMPOUND_FID 0xFFFFFFFFFFFFFFFFULL #define SMB2_SYMLINK_STRUCT_SIZE \ - (sizeof(struct smb2_err_rsp) - 1 + sizeof(struct smb2_symlink_err_rsp)) + (sizeof(struct smb2_err_rsp) + sizeof(struct smb2_symlink_err_rsp)) #define SYMLINK_ERROR_TAG 0x4c4d5953 @@ -339,13 +339,15 @@ struct smb2_file_reparse_point_info { } __packed; struct smb2_file_network_open_info { - __le64 CreationTime; - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le64 AllocationSize; - __le64 EndOfFile; - __le32 Attributes; + struct_group(network_open_info, + __le64 CreationTime; + __le64 LastAccessTime; + __le64 LastWriteTime; + __le64 ChangeTime; + __le64 AllocationSize; + __le64 EndOfFile; + __le32 Attributes; + ); __le32 Reserved; } __packed; /* level 34 Query also similar returned in close rsp and open rsp */ diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index be21b5d26f67..b325fde010ad 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -249,11 +249,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern void smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, - __u8 *oplock, struct smb2_file_all_info *buf, - struct create_posix_rsp *posix); +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix); + extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 8a1dd8407a3a..df44acaec9ae 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -427,10 +427,17 @@ unmask: server->conn_id, server->hostname); } smbd_done: - if (rc < 0 && rc != -EINTR) + /* + * there's hardly any use for the layers above to know the + * actual error code here. All they should do at this point is + * to retry the connection and hope it goes away. + */ + if (rc < 0 && rc != -EINTR && rc != -EAGAIN) { cifs_server_dbg(VFS, "Error %d sending data on socket to server\n", rc); - else if (rc > 0) + rc = -ECONNABORTED; + cifs_signal_cifsd_for_reconnect(server, false); + } else if (rc > 0) rc = 0; out: cifs_in_send_dec(server); @@ -449,8 +456,8 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, if (!(flags & CIFS_TRANSFORM_REQ)) return __smb_send_rqst(server, num_rqst, rqst); - if (num_rqst > MAX_COMPOUND - 1) - return -ENOMEM; + if (WARN_ON_ONCE(num_rqst > MAX_COMPOUND - 1)) + return -EIO; if (!server->ops->init_transform_rq) { cifs_server_dbg(VFS, "Encryption requested but transform callback is missing\n"); diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index c8a4014f9d39..a3936ff53d9d 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -189,7 +189,7 @@ struct smb2_err_rsp { __u8 ErrorContextCount; __u8 Reserved; __le32 ByteCount; /* even if zero, at least one byte follows */ - __u8 ErrorData[1]; /* variable length */ + __u8 ErrorData[]; /* variable length */ } __packed; #define SMB3_AES_CCM_NONCE 11 @@ -330,7 +330,7 @@ struct smb2_tree_connect_req { __le16 Flags; /* Flags in SMB3.1.1 */ __le16 PathOffset; __le16 PathLength; - __u8 Buffer[1]; /* variable length */ + __u8 Buffer[]; /* variable length */ } __packed; /* Possible ShareType values */ @@ -617,7 +617,7 @@ struct smb2_negotiate_rsp { __le16 SecurityBufferOffset; __le16 SecurityBufferLength; __le32 NegotiateContextOffset; /* Pre:SMB3.1.1 was reserved/ignored */ - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; @@ -638,7 +638,7 @@ struct smb2_sess_setup_req { __le16 SecurityBufferOffset; __le16 SecurityBufferLength; __le64 PreviousSessionId; - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; /* Currently defined SessionFlags */ @@ -655,7 +655,7 @@ struct smb2_sess_setup_rsp { __le16 SessionFlags; __le16 SecurityBufferOffset; __le16 SecurityBufferLength; - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; @@ -699,13 +699,16 @@ struct smb2_close_rsp { __le16 StructureSize; /* 60 */ __le16 Flags; __le32 Reserved; - __le64 CreationTime; - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le64 AllocationSize; /* Beginning of FILE_STANDARD_INFO equivalent */ - __le64 EndOfFile; - __le32 Attributes; + struct_group(network_open_info, + __le64 CreationTime; + __le64 LastAccessTime; + __le64 LastWriteTime; + __le64 ChangeTime; + /* Beginning of FILE_STANDARD_INFO equivalent */ + __le64 AllocationSize; + __le64 EndOfFile; + __le32 Attributes; + ); } __packed; @@ -737,7 +740,7 @@ struct smb2_read_req { __le32 RemainingBytes; __le16 ReadChannelInfoOffset; __le16 ReadChannelInfoLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* Read flags */ @@ -752,7 +755,7 @@ struct smb2_read_rsp { __le32 DataLength; __le32 DataRemaining; __le32 Flags; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; @@ -776,7 +779,7 @@ struct smb2_write_req { __le16 WriteChannelInfoOffset; __le16 WriteChannelInfoLength; __le32 Flags; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_write_rsp { @@ -787,7 +790,7 @@ struct smb2_write_rsp { __le32 DataLength; __le32 DataRemaining; __u32 Reserved2; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; @@ -834,7 +837,10 @@ struct smb2_lock_req { __u64 PersistentFileId; __u64 VolatileFileId; /* Followed by at least one */ - struct smb2_lock_element locks[1]; + union { + struct smb2_lock_element lock; + DECLARE_FLEX_ARRAY(struct smb2_lock_element, locks); + }; } __packed; struct smb2_lock_rsp { @@ -888,7 +894,7 @@ struct smb2_query_directory_req { __le16 FileNameOffset; __le16 FileNameLength; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_query_directory_rsp { @@ -896,7 +902,7 @@ struct smb2_query_directory_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* @@ -919,7 +925,7 @@ struct smb2_set_info_req { __le32 AdditionalInformation; __u64 PersistentFileId; __u64 VolatileFileId; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_set_info_rsp { @@ -974,7 +980,7 @@ struct smb2_change_notify_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; /* array of file notify structs */ + __u8 Buffer[]; /* array of file notify structs */ } __packed; @@ -1180,7 +1186,7 @@ struct smb2_create_rsp { __u64 VolatileFileId; __le32 CreateContextsOffset; __le32 CreateContextsLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct create_posix { @@ -1196,6 +1202,7 @@ struct create_posix { #define SMB2_LEASE_WRITE_CACHING_LE cpu_to_le32(0x04) #define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE cpu_to_le32(0x02) +#define SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE cpu_to_le32(0x04) #define SMB2_LEASE_KEY_SIZE 16 @@ -1523,7 +1530,7 @@ struct smb2_query_info_req { __le32 Flags; __u64 PersistentFileId; __u64 VolatileFileId; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_query_info_rsp { @@ -1531,7 +1538,7 @@ struct smb2_query_info_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* @@ -1592,7 +1599,10 @@ struct smb2_file_all_info { /* data block encoding of response to level 18 */ __le32 Mode; __le32 AlignmentRequirement; __le32 FileNameLength; - char FileName[1]; + union { + char __pad; /* Legacy structure padding */ + DECLARE_FLEX_ARRAY(char, FileName); + }; } __packed; /* level 18 Query */ struct smb2_file_eof_info { /* encoding of request for level 10 */ diff --git a/fs/smb/server/Kconfig b/fs/smb/server/Kconfig index e1fe17747ed6..d036ab80fec3 100644 --- a/fs/smb/server/Kconfig +++ b/fs/smb/server/Kconfig @@ -1,5 +1,5 @@ config SMB_SERVER - tristate "SMB3 server support (EXPERIMENTAL)" + tristate "SMB3 server support" depends on INET depends on MULTIUSER depends on FILE_LOCKING @@ -33,14 +33,16 @@ config SMB_SERVER in ksmbd-tools, available from https://github.com/cifsd-team/ksmbd-tools. More detail about how to run the ksmbd kernel server is - available via README file + available via the README file (https://github.com/cifsd-team/ksmbd-tools/blob/master/README). ksmbd kernel server includes support for auto-negotiation, Secure negotiate, Pre-authentication integrity, oplock/lease, compound requests, multi-credit, packet signing, RDMA(smbdirect), smb3 encryption, copy-offload, secure per-user session - establishment via NTLM or NTLMv2. + establishment via Kerberos or NTLMv2. + +if SMB_SERVER config SMB_SERVER_SMBDIRECT bool "Support for SMB Direct protocol" @@ -54,6 +56,8 @@ config SMB_SERVER_SMBDIRECT SMB Direct allows transferring SMB packets over RDMA. If unsure, say N. +endif + config SMB_SERVER_CHECK_CAP_NET_ADMIN bool "Enable check network administration capability" depends on SMB_SERVER diff --git a/fs/smb/server/asn1.c b/fs/smb/server/asn1.c index c03eba090368..b931a99ab9c8 100644 --- a/fs/smb/server/asn1.c +++ b/fs/smb/server/asn1.c @@ -208,32 +208,34 @@ int ksmbd_neg_token_init_mech_type(void *context, size_t hdrlen, return 0; } -int ksmbd_neg_token_init_mech_token(void *context, size_t hdrlen, - unsigned char tag, const void *value, - size_t vlen) +static int ksmbd_neg_token_alloc(void *context, size_t hdrlen, + unsigned char tag, const void *value, + size_t vlen) { struct ksmbd_conn *conn = context; - conn->mechToken = kmalloc(vlen + 1, GFP_KERNEL); + if (!vlen) + return -EINVAL; + + conn->mechToken = kmemdup_nul(value, vlen, GFP_KERNEL); if (!conn->mechToken) return -ENOMEM; - memcpy(conn->mechToken, value, vlen); - conn->mechToken[vlen] = '\0'; + conn->mechTokenLen = (unsigned int)vlen; + return 0; } -int ksmbd_neg_token_targ_resp_token(void *context, size_t hdrlen, +int ksmbd_neg_token_init_mech_token(void *context, size_t hdrlen, unsigned char tag, const void *value, size_t vlen) { - struct ksmbd_conn *conn = context; - - conn->mechToken = kmalloc(vlen + 1, GFP_KERNEL); - if (!conn->mechToken) - return -ENOMEM; + return ksmbd_neg_token_alloc(context, hdrlen, tag, value, vlen); +} - memcpy(conn->mechToken, value, vlen); - conn->mechToken[vlen] = '\0'; - return 0; +int ksmbd_neg_token_targ_resp_token(void *context, size_t hdrlen, + unsigned char tag, const void *value, + size_t vlen) +{ + return ksmbd_neg_token_alloc(context, hdrlen, tag, value, vlen); } diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 15e5684e328c..229a6527870d 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -1032,11 +1032,15 @@ static struct scatterlist *ksmbd_init_sg(struct kvec *iov, unsigned int nvec, { struct scatterlist *sg; unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20; - int i, nr_entries[3] = {0}, total_entries = 0, sg_idx = 0; + int i, *nr_entries, total_entries = 0, sg_idx = 0; if (!nvec) return NULL; + nr_entries = kcalloc(nvec, sizeof(int), GFP_KERNEL); + if (!nr_entries) + return NULL; + for (i = 0; i < nvec - 1; i++) { unsigned long kaddr = (unsigned long)iov[i + 1].iov_base; @@ -1054,8 +1058,10 @@ static struct scatterlist *ksmbd_init_sg(struct kvec *iov, unsigned int nvec, total_entries += 2; sg = kmalloc_array(total_entries, sizeof(struct scatterlist), GFP_KERNEL); - if (!sg) + if (!sg) { + kfree(nr_entries); return NULL; + } sg_init_table(sg, total_entries); smb2_sg_set_buf(&sg[sg_idx++], iov[0].iov_base + 24, assoc_data_len); @@ -1089,6 +1095,7 @@ static struct scatterlist *ksmbd_init_sg(struct kvec *iov, unsigned int nvec, } } smb2_sg_set_buf(&sg[sg_idx], sign, SMB2_SIGNATURE_SIZE); + kfree(nr_entries); return sg; } diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index ff97cad8d5b4..09e1e7771592 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -114,10 +114,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) struct ksmbd_conn *conn = work->conn; struct list_head *requests_queue = NULL; - if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) { + if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; - work->syncronous = true; - } if (requests_queue) { atomic_inc(&conn->req_running); @@ -127,28 +125,22 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) } } -int ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) +void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - int ret = 1; if (list_empty(&work->request_entry) && list_empty(&work->async_request_entry)) - return 0; + return; - if (!work->multiRsp) - atomic_dec(&conn->req_running); + atomic_dec(&conn->req_running); spin_lock(&conn->request_lock); - if (!work->multiRsp) { - list_del_init(&work->request_entry); - if (work->syncronous == false) - list_del_init(&work->async_request_entry); - ret = 0; - } + list_del_init(&work->request_entry); spin_unlock(&conn->request_lock); + if (work->asynchronous) + release_async_work(work); wake_up_all(&conn->req_running_q); - return ret; } void ksmbd_conn_lock(struct ksmbd_conn *conn) @@ -175,63 +167,31 @@ void ksmbd_all_conn_set_status(u64 sess_id, u32 status) void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id) { - struct ksmbd_conn *bind_conn; - wait_event(conn->req_running_q, atomic_read(&conn->req_running) < 2); - - down_read(&conn_list_lock); - list_for_each_entry(bind_conn, &conn_list, conns_list) { - if (bind_conn == conn) - continue; - - if ((bind_conn->binding || xa_load(&bind_conn->sessions, sess_id)) && - !ksmbd_conn_releasing(bind_conn) && - atomic_read(&bind_conn->req_running)) { - wait_event(bind_conn->req_running_q, - atomic_read(&bind_conn->req_running) == 0); - } - } - up_read(&conn_list_lock); } int ksmbd_conn_write(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - size_t len = 0; int sent; - struct kvec iov[3]; - int iov_idx = 0; if (!work->response_buf) { pr_err("NULL response header\n"); return -EINVAL; } - if (work->tr_buf) { - iov[iov_idx] = (struct kvec) { work->tr_buf, - sizeof(struct smb2_transform_hdr) + 4 }; - len += iov[iov_idx++].iov_len; - } + if (work->send_no_response) + return 0; - if (work->aux_payload_sz) { - iov[iov_idx] = (struct kvec) { work->response_buf, work->resp_hdr_sz }; - len += iov[iov_idx++].iov_len; - iov[iov_idx] = (struct kvec) { work->aux_payload_buf, work->aux_payload_sz }; - len += iov[iov_idx++].iov_len; - } else { - if (work->tr_buf) - iov[iov_idx].iov_len = work->resp_hdr_sz; - else - iov[iov_idx].iov_len = get_rfc1002_len(work->response_buf) + 4; - iov[iov_idx].iov_base = work->response_buf; - len += iov[iov_idx++].iov_len; - } + if (!work->iov_idx) + return -EINVAL; ksmbd_conn_lock(conn); - sent = conn->transport->ops->writev(conn->transport, &iov[0], - iov_idx, len, - work->need_invalidate_rkey, - work->remote_key); + sent = conn->transport->ops->writev(conn->transport, work->iov, + work->iov_cnt, + get_rfc1002_len(work->iov[0].iov_base) + 4, + work->need_invalidate_rkey, + work->remote_key); ksmbd_conn_unlock(conn); if (sent < 0) { @@ -324,6 +284,7 @@ int ksmbd_conn_handler_loop(void *p) goto out; conn->last_active = jiffies; + set_freezable(); while (ksmbd_conn_alive(conn)) { if (try_to_freeze()) continue; @@ -345,7 +306,7 @@ int ksmbd_conn_handler_loop(void *p) max_allowed_pdu_size = SMB3_MAX_MSGSIZE; if (pdu_size > max_allowed_pdu_size) { - pr_err_ratelimited("PDU length(%u) excceed maximum allowed pdu size(%u) on connection(%d)\n", + pr_err_ratelimited("PDU length(%u) exceeded maximum allowed pdu size(%u) on connection(%d)\n", pdu_size, max_allowed_pdu_size, READ_ONCE(conn->status)); break; @@ -455,13 +416,7 @@ static void stop_sessions(void) again: down_read(&conn_list_lock); list_for_each_entry(conn, &conn_list, conns_list) { - struct task_struct *task; - t = conn->transport; - task = t->handler; - if (task) - ksmbd_debug(CONN, "Stop session handler %s/%d\n", - task->comm, task_pid_nr(task)); ksmbd_conn_set_exiting(conn); if (t->ops->shutdown) { up_read(&conn_list_lock); diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 335fdd714d59..0e04cf8b1d89 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -88,6 +88,7 @@ struct ksmbd_conn { __u16 dialect; char *mechToken; + unsigned int mechTokenLen; struct ksmbd_conn_ops *conn_ops; @@ -134,7 +135,6 @@ struct ksmbd_transport_ops { struct ksmbd_transport { struct ksmbd_conn *conn; struct ksmbd_transport_ops *ops; - struct task_struct *handler; }; #define KSMBD_TCP_RECV_TIMEOUT (7 * HZ) @@ -159,7 +159,7 @@ int ksmbd_conn_rdma_write(struct ksmbd_conn *conn, struct smb2_buffer_desc_v1 *desc, unsigned int desc_len); void ksmbd_conn_enqueue_request(struct ksmbd_work *work); -int ksmbd_conn_try_dequeue_request(struct ksmbd_work *work); +void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work); void ksmbd_conn_init_server_callbacks(struct ksmbd_conn_ops *ops); int ksmbd_conn_handler_loop(void *p); int ksmbd_conn_transport_init(void); diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index ce866ff159bf..0ebf91ffa236 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -74,6 +74,7 @@ struct ksmbd_heartbeat { #define KSMBD_GLOBAL_FLAG_SMB2_LEASES BIT(0) #define KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION BIT(1) #define KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL BIT(2) +#define KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF BIT(3) /* * IPC request for ksmbd server startup @@ -303,7 +304,8 @@ enum ksmbd_event { KSMBD_EVENT_SPNEGO_AUTHEN_REQUEST, KSMBD_EVENT_SPNEGO_AUTHEN_RESPONSE = 15, - KSMBD_EVENT_MAX + __KSMBD_EVENT_MAX, + KSMBD_EVENT_MAX = __KSMBD_EVENT_MAX - 1 }; /* @@ -351,7 +353,8 @@ enum KSMBD_TREE_CONN_STATUS { #define KSMBD_SHARE_FLAG_STREAMS BIT(11) #define KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS BIT(12) #define KSMBD_SHARE_FLAG_ACL_XATTR BIT(13) -#define KSMBD_SHARE_FLAG_UPDATE BIT(14) +#define KSMBD_SHARE_FLAG_UPDATE BIT(14) +#define KSMBD_SHARE_FLAG_CROSSMNT BIT(15) /* * Tree connect request flags. diff --git a/fs/smb/server/ksmbd_work.c b/fs/smb/server/ksmbd_work.c index 14b9caebf7a4..d7c676c151e2 100644 --- a/fs/smb/server/ksmbd_work.c +++ b/fs/smb/server/ksmbd_work.c @@ -27,18 +27,38 @@ struct ksmbd_work *ksmbd_alloc_work_struct(void) INIT_LIST_HEAD(&work->async_request_entry); INIT_LIST_HEAD(&work->fp_entry); INIT_LIST_HEAD(&work->interim_entry); + INIT_LIST_HEAD(&work->aux_read_list); + work->iov_alloc_cnt = 4; + work->iov = kcalloc(work->iov_alloc_cnt, sizeof(struct kvec), + GFP_KERNEL); + if (!work->iov) { + kmem_cache_free(work_cache, work); + work = NULL; + } } return work; } void ksmbd_free_work_struct(struct ksmbd_work *work) { + struct aux_read *ar, *tmp; + WARN_ON(work->saved_cred != NULL); kvfree(work->response_buf); - kvfree(work->aux_payload_buf); + + list_for_each_entry_safe(ar, tmp, &work->aux_read_list, entry) { + kvfree(ar->buf); + list_del(&ar->entry); + kfree(ar); + } + kfree(work->tr_buf); kvfree(work->request_buf); + kfree(work->iov); + if (!list_empty(&work->interim_entry)) + list_del(&work->interim_entry); + if (work->async_id) ksmbd_release_id(&work->conn->async_ida, work->async_id); kmem_cache_free(work_cache, work); @@ -77,3 +97,81 @@ bool ksmbd_queue_work(struct ksmbd_work *work) { return queue_work(ksmbd_wq, &work->work); } + +static inline void __ksmbd_iov_pin(struct ksmbd_work *work, void *ib, + unsigned int ib_len) +{ + work->iov[++work->iov_idx].iov_base = ib; + work->iov[work->iov_idx].iov_len = ib_len; + work->iov_cnt++; +} + +static int __ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len, + void *aux_buf, unsigned int aux_size) +{ + struct aux_read *ar = NULL; + int need_iov_cnt = 1; + + if (aux_size) { + need_iov_cnt++; + ar = kmalloc(sizeof(struct aux_read), GFP_KERNEL); + if (!ar) + return -ENOMEM; + } + + if (work->iov_alloc_cnt < work->iov_cnt + need_iov_cnt) { + struct kvec *new; + + work->iov_alloc_cnt += 4; + new = krealloc(work->iov, + sizeof(struct kvec) * work->iov_alloc_cnt, + GFP_KERNEL | __GFP_ZERO); + if (!new) { + kfree(ar); + work->iov_alloc_cnt -= 4; + return -ENOMEM; + } + work->iov = new; + } + + /* Plus rfc_length size on first iov */ + if (!work->iov_idx) { + work->iov[work->iov_idx].iov_base = work->response_buf; + *(__be32 *)work->iov[0].iov_base = 0; + work->iov[work->iov_idx].iov_len = 4; + work->iov_cnt++; + } + + __ksmbd_iov_pin(work, ib, len); + inc_rfc1001_len(work->iov[0].iov_base, len); + + if (aux_size) { + __ksmbd_iov_pin(work, aux_buf, aux_size); + inc_rfc1001_len(work->iov[0].iov_base, aux_size); + + ar->buf = aux_buf; + list_add(&ar->entry, &work->aux_read_list); + } + + return 0; +} + +int ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len) +{ + return __ksmbd_iov_pin_rsp(work, ib, len, NULL, 0); +} + +int ksmbd_iov_pin_rsp_read(struct ksmbd_work *work, void *ib, int len, + void *aux_buf, unsigned int aux_size) +{ + return __ksmbd_iov_pin_rsp(work, ib, len, aux_buf, aux_size); +} + +int allocate_interim_rsp_buf(struct ksmbd_work *work) +{ + work->response_buf = kzalloc(MAX_CIFS_SMALL_BUFFER_SIZE, GFP_KERNEL); + if (!work->response_buf) + return -ENOMEM; + work->response_sz = MAX_CIFS_SMALL_BUFFER_SIZE; + return 0; +} diff --git a/fs/smb/server/ksmbd_work.h b/fs/smb/server/ksmbd_work.h index 5ece58e40c97..8ca2c813246e 100644 --- a/fs/smb/server/ksmbd_work.h +++ b/fs/smb/server/ksmbd_work.h @@ -19,6 +19,11 @@ enum { KSMBD_WORK_CLOSED, }; +struct aux_read { + void *buf; + struct list_head entry; +}; + /* one of these for every pending CIFS request at the connection */ struct ksmbd_work { /* Server corresponding to this mid */ @@ -31,13 +36,19 @@ struct ksmbd_work { /* Response buffer */ void *response_buf; - /* Read data buffer */ - void *aux_payload_buf; + struct list_head aux_read_list; + + struct kvec *iov; + int iov_alloc_cnt; + int iov_cnt; + int iov_idx; /* Next cmd hdr in compound req buf*/ int next_smb2_rcv_hdr_off; /* Next cmd hdr in compound rsp buf*/ int next_smb2_rsp_hdr_off; + /* Current cmd hdr in compound rsp buf*/ + int curr_smb2_rsp_hdr_off; /* * Current Local FID assigned compound response if SMB2 CREATE @@ -53,22 +64,17 @@ struct ksmbd_work { unsigned int credits_granted; /* response smb header size */ - unsigned int resp_hdr_sz; unsigned int response_sz; - /* Read data count */ - unsigned int aux_payload_sz; void *tr_buf; unsigned char state; - /* Multiple responses for one request e.g. SMB ECHO */ - bool multiRsp:1; /* No response for cancelled request */ bool send_no_response:1; /* Request is encrypted */ bool encrypted:1; /* Is this SYNC or ASYNC ksmbd_work */ - bool syncronous:1; + bool asynchronous:1; bool need_invalidate_rkey:1; unsigned int remote_key; @@ -96,6 +102,15 @@ static inline void *ksmbd_resp_buf_next(struct ksmbd_work *work) } /** + * ksmbd_resp_buf_curr - Get current buffer on compound response. + * @work: smb work containing response buffer + */ +static inline void *ksmbd_resp_buf_curr(struct ksmbd_work *work) +{ + return work->response_buf + work->curr_smb2_rsp_hdr_off + 4; +} + +/** * ksmbd_req_buf_next - Get next buffer on compound request. * @work: smb work containing response buffer */ @@ -113,5 +128,8 @@ int ksmbd_work_pool_init(void); int ksmbd_workqueue_init(void); void ksmbd_workqueue_destroy(void); bool ksmbd_queue_work(struct ksmbd_work *work); - +int ksmbd_iov_pin_rsp_read(struct ksmbd_work *work, void *ib, int len, + void *aux_buf, unsigned int aux_size); +int ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len); +int allocate_interim_rsp_buf(struct ksmbd_work *work); #endif /* __KSMBD_WORK_H__ */ diff --git a/fs/smb/server/mgmt/share_config.h b/fs/smb/server/mgmt/share_config.h index 3fd338293942..5f591751b923 100644 --- a/fs/smb/server/mgmt/share_config.h +++ b/fs/smb/server/mgmt/share_config.h @@ -34,29 +34,22 @@ struct ksmbd_share_config { #define KSMBD_SHARE_INVALID_UID ((__u16)-1) #define KSMBD_SHARE_INVALID_GID ((__u16)-1) -static inline int share_config_create_mode(struct ksmbd_share_config *share, - umode_t posix_mode) +static inline umode_t +share_config_create_mode(struct ksmbd_share_config *share, + umode_t posix_mode) { - if (!share->force_create_mode) { - if (!posix_mode) - return share->create_mask; - else - return posix_mode & share->create_mask; - } - return share->force_create_mode & share->create_mask; + umode_t mode = (posix_mode ?: (umode_t)-1) & share->create_mask; + + return mode | share->force_create_mode; } -static inline int share_config_directory_mode(struct ksmbd_share_config *share, - umode_t posix_mode) +static inline umode_t +share_config_directory_mode(struct ksmbd_share_config *share, + umode_t posix_mode) { - if (!share->force_directory_mode) { - if (!posix_mode) - return share->directory_mask; - else - return posix_mode & share->directory_mask; - } + umode_t mode = (posix_mode ?: (umode_t)-1) & share->directory_mask; - return share->force_directory_mode & share->directory_mask; + return mode | share->force_directory_mode; } static inline int test_share_config_flag(struct ksmbd_share_config *share, diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index f07a05f37651..d2c81a8a11dd 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -73,7 +73,10 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, tree_conn->user = sess->user; tree_conn->share_conf = sc; + tree_conn->t_state = TREE_NEW; status.tree_conn = tree_conn; + atomic_set(&tree_conn->refcount, 1); + init_waitqueue_head(&tree_conn->refcount_q); ret = xa_err(xa_store(&sess->tree_conns, tree_conn->id, tree_conn, GFP_KERNEL)); @@ -93,14 +96,33 @@ out_error: return status; } +void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon) +{ + /* + * Checking waitqueue to releasing tree connect on + * tree disconnect. waitqueue_active is safe because it + * uses atomic operation for condition. + */ + if (!atomic_dec_return(&tcon->refcount) && + waitqueue_active(&tcon->refcount_q)) + wake_up(&tcon->refcount_q); +} + int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *tree_conn) { int ret; + write_lock(&sess->tree_conns_lock); + xa_erase(&sess->tree_conns, tree_conn->id); + write_unlock(&sess->tree_conns_lock); + + if (!atomic_dec_and_test(&tree_conn->refcount)) + wait_event(tree_conn->refcount_q, + atomic_read(&tree_conn->refcount) == 0); + ret = ksmbd_ipc_tree_disconnect_request(sess->id, tree_conn->id); ksmbd_release_tree_conn_id(sess, tree_conn->id); - xa_erase(&sess->tree_conns, tree_conn->id); ksmbd_share_config_put(tree_conn->share_conf); kfree(tree_conn); return ret; @@ -111,26 +133,19 @@ struct ksmbd_tree_connect *ksmbd_tree_conn_lookup(struct ksmbd_session *sess, { struct ksmbd_tree_connect *tcon; + read_lock(&sess->tree_conns_lock); tcon = xa_load(&sess->tree_conns, id); if (tcon) { - if (test_bit(TREE_CONN_EXPIRE, &tcon->status)) + if (tcon->t_state != TREE_CONNECTED) + tcon = NULL; + else if (!atomic_inc_not_zero(&tcon->refcount)) tcon = NULL; } + read_unlock(&sess->tree_conns_lock); return tcon; } -struct ksmbd_share_config *ksmbd_tree_conn_share(struct ksmbd_session *sess, - unsigned int id) -{ - struct ksmbd_tree_connect *tc; - - tc = ksmbd_tree_conn_lookup(sess, id); - if (tc) - return tc->share_conf; - return NULL; -} - int ksmbd_tree_conn_session_logoff(struct ksmbd_session *sess) { int ret = 0; @@ -140,8 +155,18 @@ int ksmbd_tree_conn_session_logoff(struct ksmbd_session *sess) if (!sess) return -EINVAL; - xa_for_each(&sess->tree_conns, id, tc) + xa_for_each(&sess->tree_conns, id, tc) { + write_lock(&sess->tree_conns_lock); + if (tc->t_state == TREE_DISCONNECTED) { + write_unlock(&sess->tree_conns_lock); + ret = -ENOENT; + continue; + } + tc->t_state = TREE_DISCONNECTED; + write_unlock(&sess->tree_conns_lock); + ret |= ksmbd_tree_conn_disconnect(sess, tc); + } xa_destroy(&sess->tree_conns); return ret; } diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h index 700df36cf3e3..6377a70b811c 100644 --- a/fs/smb/server/mgmt/tree_connect.h +++ b/fs/smb/server/mgmt/tree_connect.h @@ -14,7 +14,11 @@ struct ksmbd_share_config; struct ksmbd_user; struct ksmbd_conn; -#define TREE_CONN_EXPIRE 1 +enum { + TREE_NEW = 0, + TREE_CONNECTED, + TREE_DISCONNECTED +}; struct ksmbd_tree_connect { int id; @@ -27,7 +31,9 @@ struct ksmbd_tree_connect { int maximal_access; bool posix_extensions; - unsigned long status; + atomic_t refcount; + wait_queue_head_t refcount_q; + unsigned int t_state; }; struct ksmbd_tree_conn_status { @@ -46,6 +52,7 @@ struct ksmbd_session; struct ksmbd_tree_conn_status ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, const char *share_name); +void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon); int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *tree_conn); @@ -53,9 +60,6 @@ int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *ksmbd_tree_conn_lookup(struct ksmbd_session *sess, unsigned int id); -struct ksmbd_share_config *ksmbd_tree_conn_share(struct ksmbd_session *sess, - unsigned int id); - int ksmbd_tree_conn_session_logoff(struct ksmbd_session *sess); #endif /* __TREE_CONNECT_MANAGEMENT_H__ */ diff --git a/fs/smb/server/mgmt/user_config.h b/fs/smb/server/mgmt/user_config.h index 6a44109617f1..e068a19fd904 100644 --- a/fs/smb/server/mgmt/user_config.h +++ b/fs/smb/server/mgmt/user_config.h @@ -18,7 +18,6 @@ struct ksmbd_user { size_t passkey_sz; char *passkey; - unsigned int failed_login_count; }; static inline bool user_guest(struct ksmbd_user *user) diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index cf6621e21ba3..15f68ee05089 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -25,7 +25,6 @@ static DECLARE_RWSEM(sessions_table_lock); struct ksmbd_session_rpc { int id; unsigned int method; - struct list_head list; }; static void free_channel_list(struct ksmbd_session *sess) @@ -58,15 +57,14 @@ static void __session_rpc_close(struct ksmbd_session *sess, static void ksmbd_session_rpc_clear_list(struct ksmbd_session *sess) { struct ksmbd_session_rpc *entry; + long index; - while (!list_empty(&sess->rpc_handle_list)) { - entry = list_entry(sess->rpc_handle_list.next, - struct ksmbd_session_rpc, - list); - - list_del(&entry->list); + xa_for_each(&sess->rpc_handle_list, index, entry) { + xa_erase(&sess->rpc_handle_list, index); __session_rpc_close(sess, entry); } + + xa_destroy(&sess->rpc_handle_list); } static int __rpc_method(char *rpc_name) @@ -102,13 +100,13 @@ int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name) entry = kzalloc(sizeof(struct ksmbd_session_rpc), GFP_KERNEL); if (!entry) - return -EINVAL; + return -ENOMEM; - list_add(&entry->list, &sess->rpc_handle_list); entry->method = method; entry->id = ksmbd_ipc_id_alloc(); if (entry->id < 0) goto free_entry; + xa_store(&sess->rpc_handle_list, entry->id, entry, GFP_KERNEL); resp = ksmbd_rpc_open(sess, entry->id); if (!resp) @@ -117,9 +115,9 @@ int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name) kvfree(resp); return entry->id; free_id: + xa_erase(&sess->rpc_handle_list, entry->id); ksmbd_rpc_id_free(entry->id); free_entry: - list_del(&entry->list); kfree(entry); return -EINVAL; } @@ -128,24 +126,17 @@ void ksmbd_session_rpc_close(struct ksmbd_session *sess, int id) { struct ksmbd_session_rpc *entry; - list_for_each_entry(entry, &sess->rpc_handle_list, list) { - if (entry->id == id) { - list_del(&entry->list); - __session_rpc_close(sess, entry); - break; - } - } + entry = xa_erase(&sess->rpc_handle_list, id); + if (entry) + __session_rpc_close(sess, entry); } int ksmbd_session_rpc_method(struct ksmbd_session *sess, int id) { struct ksmbd_session_rpc *entry; - list_for_each_entry(entry, &sess->rpc_handle_list, list) { - if (entry->id == id) - return entry->method; - } - return 0; + entry = xa_load(&sess->rpc_handle_list, id); + return entry ? entry->method : 0; } void ksmbd_session_destroy(struct ksmbd_session *sess) @@ -362,8 +353,9 @@ static struct ksmbd_session *__session_create(int protocol) set_session_flag(sess, protocol); xa_init(&sess->tree_conns); xa_init(&sess->ksmbd_chann_list); - INIT_LIST_HEAD(&sess->rpc_handle_list); + xa_init(&sess->rpc_handle_list); sess->sequence_number = 1; + rwlock_init(&sess->tree_conns_lock); ret = __init_smb2_session(sess); if (ret) diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index 51f38e5b61ab..63cb08fffde8 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -52,7 +52,7 @@ struct ksmbd_session { struct xarray ksmbd_chann_list; struct xarray tree_conns; struct ida tree_conn_ida; - struct list_head rpc_handle_list; + struct xarray rpc_handle_list; __u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE]; __u8 smb3decryptionkey[SMB3_ENC_DEC_KEY_SIZE]; @@ -60,6 +60,7 @@ struct ksmbd_session { struct ksmbd_file_table file_table; unsigned long last_active; + rwlock_t tree_conns_lock; }; static inline int test_session_flag(struct ksmbd_session *sess, int bit) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index c81aee9ce7ec..1253e9bde34c 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -102,9 +102,10 @@ static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx) lease->new_state = 0; lease->flags = lctx->flags; lease->duration = lctx->duration; + lease->is_dir = lctx->is_dir; memcpy(lease->parent_lease_key, lctx->parent_lease_key, SMB2_LEASE_KEY_SIZE); lease->version = lctx->version; - lease->epoch = 0; + lease->epoch = le16_to_cpu(lctx->epoch) + 1; INIT_LIST_HEAD(&opinfo->lease_entry); opinfo->o_lease = lease; @@ -395,8 +396,8 @@ void close_id_del_oplock(struct ksmbd_file *fp) { struct oplock_info *opinfo; - if (S_ISDIR(file_inode(fp->filp)->i_mode)) - return; + if (fp->reserve_lease_break) + smb_lazy_parent_lease_break_close(fp); opinfo = opinfo_get(fp); if (!opinfo) @@ -543,24 +544,30 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, /* upgrading lease */ if ((atomic_read(&ci->op_count) + atomic_read(&ci->sop_count)) == 1) { - if (lease->state == - (lctx->req_state & lease->state)) { + if (lease->state != SMB2_LEASE_NONE_LE && + lease->state == (lctx->req_state & lease->state)) { + lease->epoch++; lease->state |= lctx->req_state; if (lctx->req_state & SMB2_LEASE_WRITE_CACHING_LE) lease_read_to_write(opinfo); + } } else if ((atomic_read(&ci->op_count) + atomic_read(&ci->sop_count)) > 1) { if (lctx->req_state == (SMB2_LEASE_READ_CACHING_LE | - SMB2_LEASE_HANDLE_CACHING_LE)) + SMB2_LEASE_HANDLE_CACHING_LE)) { + lease->epoch++; lease->state = lctx->req_state; + } } if (lctx->req_state && lease->state == - SMB2_LEASE_NONE_LE) + SMB2_LEASE_NONE_LE) { + lease->epoch++; lease_none_upgrade(opinfo, lctx->req_state); + } } read_lock(&ci->m_lock); } @@ -616,15 +623,6 @@ static int oplock_break_pending(struct oplock_info *opinfo, int req_op_level) return 0; } -static inline int allocate_oplock_break_buf(struct ksmbd_work *work) -{ - work->response_buf = kzalloc(MAX_CIFS_SMALL_BUFFER_SIZE, GFP_KERNEL); - if (!work->response_buf) - return -ENOMEM; - work->response_sz = MAX_CIFS_SMALL_BUFFER_SIZE; - return 0; -} - /** * __smb2_oplock_break_noti() - send smb2 oplock break cmd from conn * to client @@ -639,7 +637,6 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) { struct smb2_oplock_break *rsp = NULL; struct ksmbd_work *work = container_of(wk, struct ksmbd_work, work); - struct ksmbd_conn *conn = work->conn; struct oplock_break_info *br_info = work->request_buf; struct smb2_hdr *rsp_hdr; struct ksmbd_file *fp; @@ -648,7 +645,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) if (!fp) goto out; - if (allocate_oplock_break_buf(work)) { + if (allocate_interim_rsp_buf(work)) { pr_err("smb2_allocate_rsp_buf failed! "); ksmbd_fd_put(work, fp); goto out; @@ -656,8 +653,6 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) rsp_hdr = smb2_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - *(__be32 *)work->response_buf = - cpu_to_be32(conn->vals->header_size); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->CreditRequest = cpu_to_le16(0); @@ -684,13 +679,15 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) rsp->PersistentFid = fp->persistent_id; rsp->VolatileFid = fp->volatile_id; - inc_rfc1001_len(work->response_buf, 24); + ksmbd_fd_put(work, fp); + if (ksmbd_iov_pin_rsp(work, (void *)rsp, + sizeof(struct smb2_oplock_break))) + goto out; ksmbd_debug(OPLOCK, "sending oplock break v_id %llu p_id = %llu lock level = %d\n", rsp->VolatileFid, rsp->PersistentFid, rsp->OplockLevel); - ksmbd_fd_put(work, fp); ksmbd_conn_write(work); out: @@ -751,18 +748,15 @@ static void __smb2_lease_break_noti(struct work_struct *wk) struct smb2_lease_break *rsp = NULL; struct ksmbd_work *work = container_of(wk, struct ksmbd_work, work); struct lease_break_info *br_info = work->request_buf; - struct ksmbd_conn *conn = work->conn; struct smb2_hdr *rsp_hdr; - if (allocate_oplock_break_buf(work)) { + if (allocate_interim_rsp_buf(work)) { ksmbd_debug(OPLOCK, "smb2_allocate_rsp_buf failed! "); goto out; } rsp_hdr = smb2_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - *(__be32 *)work->response_buf = - cpu_to_be32(conn->vals->header_size); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->CreditRequest = cpu_to_le16(0); @@ -791,7 +785,9 @@ static void __smb2_lease_break_noti(struct work_struct *wk) rsp->AccessMaskHint = 0; rsp->ShareMaskHint = 0; - inc_rfc1001_len(work->response_buf, 44); + if (ksmbd_iov_pin_rsp(work, (void *)rsp, + sizeof(struct smb2_lease_break))) + goto out; ksmbd_conn_write(work); @@ -844,7 +840,8 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo) interim_entry); setup_async_work(in_work, NULL, NULL); smb2_send_interim_resp(in_work, STATUS_PENDING); - list_del(&in_work->interim_entry); + list_del_init(&in_work->interim_entry); + release_async_work(in_work); } INIT_WORK(&work->work, __smb2_lease_break_noti); ksmbd_queue_work(work); @@ -910,7 +907,8 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level) lease->new_state = SMB2_LEASE_READ_CACHING_LE; } else { - if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE) + if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE && + !lease->is_dir) lease->new_state = SMB2_LEASE_READ_CACHING_LE; else @@ -1042,6 +1040,8 @@ static void copy_lease(struct oplock_info *op1, struct oplock_info *op2) SMB2_LEASE_KEY_SIZE); lease2->duration = lease1->duration; lease2->flags = lease1->flags; + lease2->epoch = lease1->epoch; + lease2->version = lease1->version; } static int add_lease_global_list(struct oplock_info *opinfo) @@ -1091,6 +1091,89 @@ static void set_oplock_level(struct oplock_info *opinfo, int level, } } +void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, + struct lease_ctx_info *lctx) +{ + struct oplock_info *opinfo; + struct ksmbd_inode *p_ci = NULL; + + if (lctx->version != 2) + return; + + p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent); + if (!p_ci) + return; + + read_lock(&p_ci->m_lock); + list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { + if (!opinfo->is_lease) + continue; + + if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE && + (!(lctx->flags & SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) || + !compare_guid_key(opinfo, fp->conn->ClientGUID, + lctx->parent_lease_key))) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + continue; + + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + continue; + } + + read_unlock(&p_ci->m_lock); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + opinfo_conn_put(opinfo); + read_lock(&p_ci->m_lock); + } + } + read_unlock(&p_ci->m_lock); + + ksmbd_inode_put(p_ci); +} + +void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) +{ + struct oplock_info *opinfo; + struct ksmbd_inode *p_ci = NULL; + + rcu_read_lock(); + opinfo = rcu_dereference(fp->f_opinfo); + rcu_read_unlock(); + + if (!opinfo->is_lease || opinfo->o_lease->version != 2) + return; + + p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent); + if (!p_ci) + return; + + read_lock(&p_ci->m_lock); + list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { + if (!opinfo->is_lease) + continue; + + if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + continue; + + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + continue; + } + read_unlock(&p_ci->m_lock); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + opinfo_conn_put(opinfo); + read_lock(&p_ci->m_lock); + } + } + read_unlock(&p_ci->m_lock); + + ksmbd_inode_put(p_ci); +} + /** * smb_grant_oplock() - handle oplock/lease request on file open * @work: smb work @@ -1114,9 +1197,11 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, bool prev_op_has_lease; __le32 prev_op_state = 0; - /* not support directory lease */ - if (S_ISDIR(file_inode(fp->filp)->i_mode)) - return 0; + /* Only v2 leases handle the directory */ + if (S_ISDIR(file_inode(fp->filp)->i_mode)) { + if (!lctx || lctx->version != 2) + return 0; + } opinfo = alloc_opinfo(work, pid, tid); if (!opinfo) @@ -1374,6 +1459,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE); buf->lcontext.LeaseFlags = lease->flags; + buf->lcontext.Epoch = cpu_to_le16(lease->epoch); buf->lcontext.LeaseState = lease->state; memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, SMB2_LEASE_KEY_SIZE); @@ -1410,10 +1496,11 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) /** * parse_lease_state() - parse lease context containted in file open request * @open_req: buffer containing smb2 file open(create) request + * @is_dir: whether leasing file is directory * * Return: oplock state, -ENOENT if create lease context not found */ -struct lease_ctx_info *parse_lease_state(void *open_req) +struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) { struct create_context *cc; struct smb2_create_req *req = (struct smb2_create_req *)open_req; @@ -1431,8 +1518,14 @@ struct lease_ctx_info *parse_lease_state(void *open_req) struct create_lease_v2 *lc = (struct create_lease_v2 *)cc; memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); - lreq->req_state = lc->lcontext.LeaseState; + if (is_dir) { + lreq->req_state = lc->lcontext.LeaseState & + ~SMB2_LEASE_WRITE_CACHING_LE; + lreq->is_dir = true; + } else + lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; + lreq->epoch = lc->lcontext.Epoch; lreq->duration = lc->lcontext.LeaseDuration; memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, SMB2_LEASE_KEY_SIZE); diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 4b0fe6da7694..5b93ea9196c0 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -34,7 +34,9 @@ struct lease_ctx_info { __le32 flags; __le64 duration; __u8 parent_lease_key[SMB2_LEASE_KEY_SIZE]; + __le16 epoch; int version; + bool is_dir; }; struct lease_table { @@ -53,6 +55,7 @@ struct lease { __u8 parent_lease_key[SMB2_LEASE_KEY_SIZE]; int version; unsigned short epoch; + bool is_dir; struct lease_table *l_lb; }; @@ -108,7 +111,7 @@ void opinfo_put(struct oplock_info *opinfo); /* Lease related functions */ void create_lease_buf(u8 *rbuf, struct lease *lease); -struct lease_ctx_info *parse_lease_state(void *open_req); +struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir); __u8 smb2_map_lease_to_oplock(__le32 lease_state); int lease_read_to_write(struct oplock_info *opinfo); @@ -124,4 +127,7 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, struct lease_ctx_info *lctx); void destroy_lease_table(struct ksmbd_conn *conn); +void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, + struct lease_ctx_info *lctx); +void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp); #endif /* __KSMBD_OPLOCK_H */ diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 9804cabe72a8..11b201e6ee44 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -115,8 +115,10 @@ static int __process_request(struct ksmbd_work *work, struct ksmbd_conn *conn, if (check_conn_state(work)) return SERVER_HANDLER_CONTINUE; - if (ksmbd_verify_smb_message(work)) + if (ksmbd_verify_smb_message(work)) { + conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER); return SERVER_HANDLER_ABORT; + } command = conn->ops->get_cmd_val(work); *cmd = command; @@ -163,6 +165,7 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, { u16 command = 0; int rc; + bool is_chained = false; if (conn->ops->allocate_rsp_buf(work)) return; @@ -229,16 +232,17 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, } } + is_chained = is_chained_smb2_message(work); + if (work->sess && (work->sess->sign || smb3_11_final_sess_setup_resp(work) || conn->ops->is_sign_req(work, command))) conn->ops->set_sign_rsp(work); - } while (is_chained_smb2_message(work)); - - if (work->send_no_response) - return; + } while (is_chained == true); send: + if (work->tcon) + ksmbd_tree_connect_put(work->tcon); smb3_preauth_hash_rsp(work); if (work->sess && work->sess->enc && work->encrypted && conn->ops->encrypt_resp) { @@ -442,11 +446,9 @@ static ssize_t stats_show(struct class *class, struct class_attribute *attr, "reset", "shutdown" }; - - ssize_t sz = scnprintf(buf, PAGE_SIZE, "%d %s %d %lu\n", stats_version, - state[server_conf.state], server_conf.tcp_port, - server_conf.ipc_last_active / HZ); - return sz; + return sysfs_emit(buf, "%d %s %d %lu\n", stats_version, + state[server_conf.state], server_conf.tcp_port, + server_conf.ipc_last_active / HZ); } static ssize_t kill_server_store(struct class *class, @@ -478,19 +480,13 @@ static ssize_t debug_show(struct class *class, struct class_attribute *attr, for (i = 0; i < ARRAY_SIZE(debug_type_strings); i++) { if ((ksmbd_debug_types >> i) & 1) { - pos = scnprintf(buf + sz, - PAGE_SIZE - sz, - "[%s] ", - debug_type_strings[i]); + pos = sysfs_emit_at(buf, sz, "[%s] ", debug_type_strings[i]); } else { - pos = scnprintf(buf + sz, - PAGE_SIZE - sz, - "%s ", - debug_type_strings[i]); + pos = sysfs_emit_at(buf, sz, "%s ", debug_type_strings[i]); } sz += pos; } - sz += scnprintf(buf + sz, PAGE_SIZE - sz, "\n"); + sz += sysfs_emit_at(buf, sz, "\n"); return sz; } @@ -599,8 +595,6 @@ static int __init ksmbd_server_init(void) if (ret) goto err_crypto_destroy; - pr_warn_once("The ksmbd server is experimental\n"); - return 0; err_crypto_destroy: diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index e881df1d10cb..03dded29a980 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -106,16 +106,25 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, break; case SMB2_CREATE: { + unsigned short int name_off = + le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); + unsigned short int name_len = + le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); + if (((struct smb2_create_req *)hdr)->CreateContextsLength) { *off = le32_to_cpu(((struct smb2_create_req *) hdr)->CreateContextsOffset); *len = le32_to_cpu(((struct smb2_create_req *) hdr)->CreateContextsLength); - break; + if (!name_len) + break; + + if (name_off + name_len < (u64)*off + *len) + break; } - *off = le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); - *len = le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); + *off = name_off; + *len = name_len; break; } case SMB2_QUERY_INFO: @@ -440,10 +449,8 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) validate_credit: if ((work->conn->vals->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU) && - smb2_validate_credit_charge(work->conn, hdr)) { - work->conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER); + smb2_validate_credit_charge(work->conn, hdr)) return 1; - } return 0; } diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index ab23da2120b9..27a9dce3e03a 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -26,7 +26,7 @@ static struct smb_version_values smb21_server_values = { .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -52,7 +52,7 @@ static struct smb_version_values smb30_server_values = { .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -79,7 +79,7 @@ static struct smb_version_values smb302_server_values = { .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -106,7 +106,7 @@ static struct smb_version_values smb311_server_values = { .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -221,7 +221,8 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION && conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) @@ -245,10 +246,12 @@ void init_smb3_02_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION && - conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || + (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && + conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) @@ -269,7 +272,13 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; + + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || + (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && + conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) + conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 1598ad6155fe..66d25d0e34d8 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -144,12 +144,18 @@ void smb2_set_err_rsp(struct ksmbd_work *work) err_rsp = smb2_get_msg(work->response_buf); if (err_rsp->hdr.Status != STATUS_STOPPED_ON_SYMLINK) { + int err; + err_rsp->StructureSize = SMB2_ERROR_STRUCTURE_SIZE2_LE; err_rsp->ErrorContextCount = 0; err_rsp->Reserved = 0; err_rsp->ByteCount = 0; err_rsp->ErrorData[0] = 0; - inc_rfc1001_len(work->response_buf, SMB2_ERROR_STRUCTURE_SIZE2); + err = ksmbd_iov_pin_rsp(work, (void *)err_rsp, + __SMB2_HEADER_STRUCTURE_SIZE + + SMB2_ERROR_STRUCTURE_SIZE2); + if (err) + work->send_no_response = 1; } } @@ -224,11 +230,12 @@ void set_smb2_rsp_status(struct ksmbd_work *work, __le32 err) { struct smb2_hdr *rsp_hdr; - if (work->next_smb2_rcv_hdr_off) - rsp_hdr = ksmbd_resp_buf_next(work); - else - rsp_hdr = smb2_get_msg(work->response_buf); + rsp_hdr = smb2_get_msg(work->response_buf); rsp_hdr->Status = err; + + work->iov_idx = 0; + work->iov_cnt = 0; + work->next_smb2_rcv_hdr_off = 0; smb2_set_err_rsp(work); } @@ -244,9 +251,7 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) struct smb2_hdr *rsp_hdr; struct smb2_negotiate_rsp *rsp; struct ksmbd_conn *conn = work->conn; - - *(__be32 *)work->response_buf = - cpu_to_be32(conn->vals->header_size); + int err; rsp_hdr = smb2_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); @@ -285,13 +290,13 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) rsp->SecurityBufferLength = cpu_to_le16(AUTH_GSS_LENGTH); ksmbd_copy_gss_neg_header((char *)(&rsp->hdr) + le16_to_cpu(rsp->SecurityBufferOffset)); - inc_rfc1001_len(work->response_buf, - sizeof(struct smb2_negotiate_rsp) - - sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) + - AUTH_GSS_LENGTH); rsp->SecurityMode = SMB2_NEGOTIATE_SIGNING_ENABLED_LE; if (server_conf.signing == KSMBD_CONFIG_OPT_MANDATORY) rsp->SecurityMode |= SMB2_NEGOTIATE_SIGNING_REQUIRED_LE; + err = ksmbd_iov_pin_rsp(work, rsp, + sizeof(struct smb2_negotiate_rsp) + AUTH_GSS_LENGTH); + if (err) + return err; conn->use_spnego = true; ksmbd_conn_set_need_negotiate(conn); @@ -390,11 +395,12 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) next_hdr_offset = le32_to_cpu(req->NextCommand); new_len = ALIGN(len, 8); - inc_rfc1001_len(work->response_buf, - sizeof(struct smb2_hdr) + new_len - len); + work->iov[work->iov_idx].iov_len += (new_len - len); + inc_rfc1001_len(work->response_buf, new_len - len); rsp->NextCommand = cpu_to_le32(new_len); work->next_smb2_rcv_hdr_off += next_hdr_offset; + work->curr_smb2_rsp_hdr_off = work->next_smb2_rsp_hdr_off; work->next_smb2_rsp_hdr_off += new_len; ksmbd_debug(SMB, "Compound req new_len = %d rcv off = %d rsp off = %d\n", @@ -470,10 +476,10 @@ bool is_chained_smb2_message(struct ksmbd_work *work) len = len - get_rfc1002_len(work->response_buf); if (len) { ksmbd_debug(SMB, "padding len %u\n", len); + work->iov[work->iov_idx].iov_len += len; inc_rfc1001_len(work->response_buf, len); - if (work->aux_payload_sz) - work->aux_payload_sz += len; } + work->curr_smb2_rsp_hdr_off = work->next_smb2_rsp_hdr_off; } return false; } @@ -488,11 +494,8 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work) { struct smb2_hdr *rsp_hdr = smb2_get_msg(work->response_buf); struct smb2_hdr *rcv_hdr = smb2_get_msg(work->request_buf); - struct ksmbd_conn *conn = work->conn; memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - *(__be32 *)work->response_buf = - cpu_to_be32(conn->vals->header_size); rsp_hdr->ProtocolId = rcv_hdr->ProtocolId; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->Command = rcv_hdr->Command; @@ -508,12 +511,6 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work) rsp_hdr->SessionId = rcv_hdr->SessionId; memcpy(rsp_hdr->Signature, rcv_hdr->Signature, 16); - work->syncronous = true; - if (work->async_id) { - ksmbd_release_id(&conn->async_ida, work->async_id); - work->async_id = 0; - } - return 0; } @@ -549,7 +546,7 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) if (le32_to_cpu(hdr->NextCommand) > 0) sz = large_sz; - work->response_buf = kvmalloc(sz, GFP_KERNEL | __GFP_ZERO); + work->response_buf = kvzalloc(sz, GFP_KERNEL); if (!work->response_buf) return -ENOMEM; @@ -659,21 +656,16 @@ smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls) int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) { - struct smb2_hdr *rsp_hdr; struct ksmbd_conn *conn = work->conn; int id; - rsp_hdr = smb2_get_msg(work->response_buf); - rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND; - id = ksmbd_acquire_async_msg_id(&conn->async_ida); if (id < 0) { pr_err("Failed to alloc async message id\n"); return id; } - work->syncronous = false; + work->asynchronous = true; work->async_id = id; - rsp_hdr->Id.AsyncId = cpu_to_le64(id); ksmbd_debug(SMB, "Send interim Response to inform async request id : %d\n", @@ -691,18 +683,47 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) return 0; } +void release_async_work(struct ksmbd_work *work) +{ + struct ksmbd_conn *conn = work->conn; + + spin_lock(&conn->request_lock); + list_del_init(&work->async_request_entry); + spin_unlock(&conn->request_lock); + + work->asynchronous = 0; + work->cancel_fn = NULL; + kfree(work->cancel_argv); + work->cancel_argv = NULL; + if (work->async_id) { + ksmbd_release_id(&conn->async_ida, work->async_id); + work->async_id = 0; + } +} + void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) { struct smb2_hdr *rsp_hdr; + struct ksmbd_work *in_work = ksmbd_alloc_work_struct(); - rsp_hdr = smb2_get_msg(work->response_buf); - smb2_set_err_rsp(work); + if (allocate_interim_rsp_buf(in_work)) { + pr_err("smb_allocate_rsp_buf failed!\n"); + ksmbd_free_work_struct(in_work); + return; + } + + in_work->conn = work->conn; + memcpy(smb2_get_msg(in_work->response_buf), ksmbd_resp_buf_next(work), + __SMB2_HEADER_STRUCTURE_SIZE); + + rsp_hdr = smb2_get_msg(in_work->response_buf); + rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND; + rsp_hdr->Id.AsyncId = cpu_to_le64(work->async_id); + smb2_set_err_rsp(in_work); rsp_hdr->Status = status; - work->multiRsp = 1; - ksmbd_conn_write(work); - rsp_hdr->Status = 0; - work->multiRsp = 0; + ksmbd_conn_write(in_work); + ksmbd_free_work_struct(in_work); } static __le32 smb2_get_reparse_tag_special_file(umode_t mode) @@ -774,19 +795,6 @@ static void build_encrypt_ctxt(struct smb2_encryption_neg_context *pneg_ctxt, pneg_ctxt->Ciphers[0] = cipher_type; } -static void build_compression_ctxt(struct smb2_compression_capabilities_context *pneg_ctxt, - __le16 comp_algo) -{ - pneg_ctxt->ContextType = SMB2_COMPRESSION_CAPABILITIES; - pneg_ctxt->DataLength = - cpu_to_le16(sizeof(struct smb2_compression_capabilities_context) - - sizeof(struct smb2_neg_context)); - pneg_ctxt->Reserved = cpu_to_le32(0); - pneg_ctxt->CompressionAlgorithmCount = cpu_to_le16(1); - pneg_ctxt->Flags = cpu_to_le32(0); - pneg_ctxt->CompressionAlgorithms[0] = comp_algo; -} - static void build_sign_cap_ctxt(struct smb2_signing_capabilities *pneg_ctxt, __le16 sign_algo) { @@ -822,11 +830,10 @@ static void build_posix_ctxt(struct smb2_posix_neg_context *pneg_ctxt) pneg_ctxt->Name[15] = 0x7C; } -static void assemble_neg_contexts(struct ksmbd_conn *conn, - struct smb2_negotiate_rsp *rsp, - void *smb2_buf_len) +static unsigned int assemble_neg_contexts(struct ksmbd_conn *conn, + struct smb2_negotiate_rsp *rsp) { - char *pneg_ctxt = (char *)rsp + + char * const pneg_ctxt = (char *)rsp + le32_to_cpu(rsp->NegotiateContextOffset); int neg_ctxt_cnt = 1; int ctxt_size; @@ -835,62 +842,46 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, "assemble SMB2_PREAUTH_INTEGRITY_CAPABILITIES context\n"); build_preauth_ctxt((struct smb2_preauth_neg_context *)pneg_ctxt, conn->preauth_info->Preauth_HashId); - rsp->NegotiateContextCount = cpu_to_le16(neg_ctxt_cnt); - inc_rfc1001_len(smb2_buf_len, AUTH_GSS_PADDING); ctxt_size = sizeof(struct smb2_preauth_neg_context); - /* Round to 8 byte boundary */ - pneg_ctxt += round_up(sizeof(struct smb2_preauth_neg_context), 8); if (conn->cipher_type) { + /* Round to 8 byte boundary */ ctxt_size = round_up(ctxt_size, 8); ksmbd_debug(SMB, "assemble SMB2_ENCRYPTION_CAPABILITIES context\n"); - build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt, + build_encrypt_ctxt((struct smb2_encryption_neg_context *) + (pneg_ctxt + ctxt_size), conn->cipher_type); - rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt); + neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_encryption_neg_context) + 2; - /* Round to 8 byte boundary */ - pneg_ctxt += - round_up(sizeof(struct smb2_encryption_neg_context) + 2, - 8); } - if (conn->compress_algorithm) { - ctxt_size = round_up(ctxt_size, 8); - ksmbd_debug(SMB, - "assemble SMB2_COMPRESSION_CAPABILITIES context\n"); - /* Temporarily set to SMB3_COMPRESS_NONE */ - build_compression_ctxt((struct smb2_compression_capabilities_context *)pneg_ctxt, - conn->compress_algorithm); - rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt); - ctxt_size += sizeof(struct smb2_compression_capabilities_context) + 2; - /* Round to 8 byte boundary */ - pneg_ctxt += round_up(sizeof(struct smb2_compression_capabilities_context) + 2, - 8); - } + /* compression context not yet supported */ + WARN_ON(conn->compress_algorithm != SMB3_COMPRESS_NONE); if (conn->posix_ext_supported) { ctxt_size = round_up(ctxt_size, 8); ksmbd_debug(SMB, "assemble SMB2_POSIX_EXTENSIONS_AVAILABLE context\n"); - build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt); - rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt); + build_posix_ctxt((struct smb2_posix_neg_context *) + (pneg_ctxt + ctxt_size)); + neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_posix_neg_context); - /* Round to 8 byte boundary */ - pneg_ctxt += round_up(sizeof(struct smb2_posix_neg_context), 8); } if (conn->signing_negotiated) { ctxt_size = round_up(ctxt_size, 8); ksmbd_debug(SMB, "assemble SMB2_SIGNING_CAPABILITIES context\n"); - build_sign_cap_ctxt((struct smb2_signing_capabilities *)pneg_ctxt, + build_sign_cap_ctxt((struct smb2_signing_capabilities *) + (pneg_ctxt + ctxt_size), conn->signing_algorithm); - rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt); + neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_signing_capabilities) + 2; } - inc_rfc1001_len(smb2_buf_len, ctxt_size); + rsp->NegotiateContextCount = cpu_to_le16(neg_ctxt_cnt); + return ctxt_size + AUTH_GSS_PADDING; } static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, @@ -935,7 +926,7 @@ static void decode_encrypt_ctxt(struct ksmbd_conn *conn, return; } - if (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION)) + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) return; for (i = 0; i < cph_cnt; i++) { @@ -1106,7 +1097,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) struct smb2_negotiate_req *req = smb2_get_msg(work->request_buf); struct smb2_negotiate_rsp *rsp = smb2_get_msg(work->response_buf); int rc = 0; - unsigned int smb2_buf_len, smb2_neg_size; + unsigned int smb2_buf_len, smb2_neg_size, neg_ctxt_len = 0; __le32 status; ksmbd_debug(SMB, "Received negotiate request\n"); @@ -1199,7 +1190,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) conn->preauth_info->Preauth_HashValue); rsp->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT); - assemble_neg_contexts(conn, rsp, work->response_buf); + neg_ctxt_len = assemble_neg_contexts(conn, rsp); break; case SMB302_PROT_ID: init_smb3_02_server(conn); @@ -1249,9 +1240,6 @@ int smb2_handle_negotiate(struct ksmbd_work *work) rsp->SecurityBufferLength = cpu_to_le16(AUTH_GSS_LENGTH); ksmbd_copy_gss_neg_header((char *)(&rsp->hdr) + le16_to_cpu(rsp->SecurityBufferOffset)); - inc_rfc1001_len(work->response_buf, sizeof(struct smb2_negotiate_rsp) - - sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) + - AUTH_GSS_LENGTH); rsp->SecurityMode = SMB2_NEGOTIATE_SIGNING_ENABLED_LE; conn->use_spnego = true; @@ -1269,9 +1257,15 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_conn_set_need_negotiate(conn); err_out: + if (rc) + rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; + + if (!rc) + rc = ksmbd_iov_pin_rsp(work, rsp, + sizeof(struct smb2_negotiate_rsp) + + AUTH_GSS_LENGTH + neg_ctxt_len); if (rc < 0) smb2_set_err_rsp(work); - return rc; } @@ -1418,7 +1412,10 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, char *name; unsigned int name_off, name_len, secbuf_len; - secbuf_len = le16_to_cpu(req->SecurityBufferLength); + if (conn->use_spnego && conn->mechToken) + secbuf_len = conn->mechTokenLen; + else + secbuf_len = le16_to_cpu(req->SecurityBufferLength); if (secbuf_len < sizeof(struct authenticate_message)) { ksmbd_debug(SMB, "blob len %d too small\n", secbuf_len); return NULL; @@ -1471,7 +1468,6 @@ static int ntlm_authenticate(struct ksmbd_work *work, memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); kfree(spnego_blob); - inc_rfc1001_len(work->response_buf, spnego_blob_len - 1); } user = session_user(conn, req); @@ -1510,7 +1506,10 @@ static int ntlm_authenticate(struct ksmbd_work *work, struct authenticate_message *authblob; authblob = user_authblob(conn, req); - sz = le16_to_cpu(req->SecurityBufferLength); + if (conn->use_spnego && conn->mechToken) + sz = conn->mechTokenLen; + else + sz = le16_to_cpu(req->SecurityBufferLength); rc = ksmbd_decode_ntlmssp_auth_blob(authblob, sz, conn, sess); if (rc) { set_user_flag(sess->user, KSMBD_USER_FLAG_BAD_PASSWORD); @@ -1544,7 +1543,8 @@ static int ntlm_authenticate(struct ksmbd_work *work, return -EINVAL; } sess->enc = true; - rsp->SessionFlags = SMB2_SESSION_FLAG_ENCRYPT_DATA_LE; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION) + rsp->SessionFlags = SMB2_SESSION_FLAG_ENCRYPT_DATA_LE; /* * signing is disable if encryption is enable * on this session @@ -1616,7 +1616,6 @@ static int krb5_authenticate(struct ksmbd_work *work, return -EINVAL; } rsp->SecurityBufferLength = cpu_to_le16(out_len); - inc_rfc1001_len(work->response_buf, out_len - 1); if ((conn->sign || server_conf.enforced_signing) || (req->SecurityMode & SMB2_NEGOTIATE_SIGNING_REQUIRED)) @@ -1630,7 +1629,8 @@ static int krb5_authenticate(struct ksmbd_work *work, return -EINVAL; } sess->enc = true; - rsp->SessionFlags = SMB2_SESSION_FLAG_ENCRYPT_DATA_LE; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION) + rsp->SessionFlags = SMB2_SESSION_FLAG_ENCRYPT_DATA_LE; sess->sign = false; } @@ -1687,7 +1687,6 @@ int smb2_sess_setup(struct ksmbd_work *work) rsp->SessionFlags = 0; rsp->SecurityBufferOffset = cpu_to_le16(72); rsp->SecurityBufferLength = 0; - inc_rfc1001_len(work->response_buf, 9); ksmbd_conn_lock(conn); if (!req->hdr.SessionId) { @@ -1783,8 +1782,7 @@ int smb2_sess_setup(struct ksmbd_work *work) negblob_off = le16_to_cpu(req->SecurityBufferOffset); negblob_len = le16_to_cpu(req->SecurityBufferLength); - if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer) || - negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) { + if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer)) { rc = -EINVAL; goto out_err; } @@ -1793,8 +1791,15 @@ int smb2_sess_setup(struct ksmbd_work *work) negblob_off); if (decode_negotiation_token(conn, negblob, negblob_len) == 0) { - if (conn->mechToken) + if (conn->mechToken) { negblob = (struct negotiate_message *)conn->mechToken; + negblob_len = conn->mechTokenLen; + } + } + + if (negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) { + rc = -EINVAL; + goto out_err; } if (server_conf.auth_mechs & conn->auth_mechs) { @@ -1823,13 +1828,6 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; rsp->hdr.Status = STATUS_MORE_PROCESSING_REQUIRED; - /* - * Note: here total size -1 is done as an - * adjustment for 0 size blob - */ - inc_rfc1001_len(work->response_buf, - le16_to_cpu(rsp->SecurityBufferLength) - 1); - } else if (negblob->MessageType == NtLmAuthenticate) { rc = ntlm_authenticate(work, req, rsp); if (rc) @@ -1914,6 +1912,18 @@ out_err: ksmbd_conn_set_need_negotiate(conn); } } + smb2_set_err_rsp(work); + } else { + unsigned int iov_len; + + if (rsp->SecurityBufferLength) + iov_len = offsetof(struct smb2_sess_setup_rsp, Buffer) + + le16_to_cpu(rsp->SecurityBufferLength); + else + iov_len = sizeof(struct smb2_sess_setup_rsp); + rc = ksmbd_iov_pin_rsp(work, rsp, iov_len); + if (rc) + rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; } ksmbd_conn_unlock(conn); @@ -1991,14 +2001,20 @@ int smb2_tree_connect(struct ksmbd_work *work) if (conn->posix_ext_supported) status.tree_conn->posix_extensions = true; + write_lock(&sess->tree_conns_lock); + status.tree_conn->t_state = TREE_CONNECTED; + write_unlock(&sess->tree_conns_lock); rsp->StructureSize = cpu_to_le16(16); - inc_rfc1001_len(work->response_buf, 16); out_err1: rsp->Capabilities = 0; rsp->Reserved = 0; /* default manual caching */ rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING; + rc = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_tree_connect_rsp)); + if (rc) + status.ret = KSMBD_TREE_CONN_STATUS_NOMEM; + if (!IS_ERR(treename)) kfree(treename); if (!IS_ERR(name)) @@ -2111,26 +2127,56 @@ int smb2_tree_disconnect(struct ksmbd_work *work) struct smb2_tree_disconnect_req *req; struct ksmbd_session *sess = work->sess; struct ksmbd_tree_connect *tcon = work->tcon; + int err; WORK_BUFFERS(work, req, rsp); - rsp->StructureSize = cpu_to_le16(4); - inc_rfc1001_len(work->response_buf, 4); - ksmbd_debug(SMB, "request\n"); - if (!tcon || test_and_set_bit(TREE_CONN_EXPIRE, &tcon->status)) { + if (!tcon) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; - smb2_set_err_rsp(work); - return 0; + err = -ENOENT; + goto err_out; } ksmbd_close_tree_conn_fds(work); - ksmbd_tree_conn_disconnect(sess, tcon); + + write_lock(&sess->tree_conns_lock); + if (tcon->t_state == TREE_DISCONNECTED) { + write_unlock(&sess->tree_conns_lock); + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; + err = -ENOENT; + goto err_out; + } + + WARN_ON_ONCE(atomic_dec_and_test(&tcon->refcount)); + tcon->t_state = TREE_DISCONNECTED; + write_unlock(&sess->tree_conns_lock); + + err = ksmbd_tree_conn_disconnect(sess, tcon); + if (err) { + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; + goto err_out; + } + work->tcon = NULL; + + rsp->StructureSize = cpu_to_le16(4); + err = ksmbd_iov_pin_rsp(work, rsp, + sizeof(struct smb2_tree_disconnect_rsp)); + if (err) { + rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; + goto err_out; + } + return 0; + +err_out: + smb2_set_err_rsp(work); + return err; + } /** @@ -2146,17 +2192,23 @@ int smb2_session_logoff(struct ksmbd_work *work) struct smb2_logoff_rsp *rsp; struct ksmbd_session *sess; u64 sess_id; + int err; WORK_BUFFERS(work, req, rsp); - sess_id = le64_to_cpu(req->hdr.SessionId); - - rsp->StructureSize = cpu_to_le16(4); - inc_rfc1001_len(work->response_buf, 4); - ksmbd_debug(SMB, "request\n"); + ksmbd_conn_lock(conn); + if (!ksmbd_conn_good(conn)) { + ksmbd_conn_unlock(conn); + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; + smb2_set_err_rsp(work); + return -ENOENT; + } + sess_id = le64_to_cpu(req->hdr.SessionId); ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_RECONNECT); + ksmbd_conn_unlock(conn); + ksmbd_close_session_fds(work); ksmbd_conn_wait_idle(conn, sess_id); @@ -2169,7 +2221,7 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; smb2_set_err_rsp(work); - return 0; + return -ENOENT; } ksmbd_destroy_file_table(&sess->file_table); @@ -2178,6 +2230,14 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_free_user(sess->user); sess->user = NULL; ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_NEGOTIATE); + + rsp->StructureSize = cpu_to_le16(4); + err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); + if (err) { + rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; + smb2_set_err_rsp(work); + return err; + } return 0; } @@ -2230,7 +2290,10 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) rsp->CreateContextsOffset = 0; rsp->CreateContextsLength = 0; - inc_rfc1001_len(work->response_buf, 88); /* StructureSize - 1*/ + err = ksmbd_iov_pin_rsp(work, rsp, offsetof(struct smb2_create_rsp, Buffer)); + if (err) + goto out; + kfree(name); return 0; @@ -2258,11 +2321,12 @@ out: * @eabuf: set info command buffer * @buf_len: set info command buffer length * @path: dentry path for get ea + * @get_write: get write access to a mount * * Return: 0 on success, otherwise error */ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, - const struct path *path) + const struct path *path, bool get_write) { struct user_namespace *user_ns = mnt_user_ns(path->mnt); char *attr_name = NULL, *value; @@ -2309,7 +2373,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, /* delete the EA only when it exits */ if (rc > 0) { rc = ksmbd_vfs_remove_xattr(user_ns, - path->dentry, + path, attr_name); if (rc < 0) { @@ -2323,9 +2387,9 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, /* if the EA doesn't exist, just do nothing. */ rc = 0; } else { - rc = ksmbd_vfs_setxattr(user_ns, - path->dentry, attr_name, value, - le16_to_cpu(eabuf->EaValueLength), 0); + rc = ksmbd_vfs_setxattr(user_ns, path, attr_name, value, + le16_to_cpu(eabuf->EaValueLength), + 0, true); if (rc < 0) { ksmbd_debug(SMB, "ksmbd_vfs_setxattr is failed(%d)\n", @@ -2388,8 +2452,7 @@ static noinline int smb2_set_stream_name_xattr(const struct path *path, return -EBADF; } - rc = ksmbd_vfs_setxattr(user_ns, path->dentry, - xattr_stream_name, NULL, 0, 0); + rc = ksmbd_vfs_setxattr(user_ns, path, xattr_stream_name, NULL, 0, 0, false); if (rc < 0) pr_err("Failed to store XATTR stream name :%d\n", rc); return 0; @@ -2417,7 +2480,7 @@ static int smb2_remove_smb_xattrs(const struct path *path) if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN)) { - err = ksmbd_vfs_remove_xattr(user_ns, path->dentry, + err = ksmbd_vfs_remove_xattr(user_ns, path, name); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", @@ -2464,8 +2527,7 @@ static void smb2_new_xattrs(struct ksmbd_tree_connect *tcon, const struct path * da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_user_ns(path->mnt), - path->dentry, &da); + rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_user_ns(path->mnt), path, &da, true); if (rc) ksmbd_debug(SMB, "failed to store file attribute into xattr\n"); } @@ -2492,8 +2554,9 @@ static void smb2_update_xattrs(struct ksmbd_tree_connect *tcon, } } -static int smb2_creat(struct ksmbd_work *work, struct path *path, char *name, - int open_flags, umode_t posix_mode, bool is_dir) +static int smb2_creat(struct ksmbd_work *work, struct path *parent_path, + struct path *path, char *name, int open_flags, + umode_t posix_mode, bool is_dir) { struct ksmbd_tree_connect *tcon = work->tcon; struct ksmbd_share_config *share = tcon->share_conf; @@ -2520,7 +2583,7 @@ static int smb2_creat(struct ksmbd_work *work, struct path *path, char *name, return rc; } - rc = ksmbd_vfs_kern_path(work, name, 0, path, 0); + rc = ksmbd_vfs_kern_path_locked(work, name, 0, parent_path, path, 0); if (rc) { pr_err("cannot get linux path (%s), err = %d\n", name, rc); @@ -2554,7 +2617,7 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, sizeof(struct create_sd_buf_req)) return -EINVAL; return set_info_sec(work->conn, work->tcon, path, &sd_buf->ntsd, - le32_to_cpu(sd_buf->ccontext.DataLength), true); + le32_to_cpu(sd_buf->ccontext.DataLength), true, false); } static void ksmbd_acls_fattr(struct smb_fattr *fattr, @@ -2590,7 +2653,7 @@ int smb2_open(struct ksmbd_work *work) struct ksmbd_tree_connect *tcon = work->tcon; struct smb2_create_req *req; struct smb2_create_rsp *rsp; - struct path path; + struct path path, parent_path; struct ksmbd_share_config *share = tcon->share_conf; struct ksmbd_file *fp = NULL; struct file *filp = NULL; @@ -2614,6 +2677,7 @@ int smb2_open(struct ksmbd_work *work) u64 time; umode_t posix_mode = 0; __le32 daccess, maximal_access = 0; + int iov_len = 0; WORK_BUFFERS(work, req, rsp); @@ -2635,7 +2699,7 @@ int smb2_open(struct ksmbd_work *work) *(char *)req->Buffer == '\\') { pr_err("not allow directory name included leading slash\n"); rc = -EINVAL; - goto err_out1; + goto err_out2; } name = smb2_get_name(req->Buffer, @@ -2646,7 +2710,7 @@ int smb2_open(struct ksmbd_work *work) if (rc != -ENOMEM) rc = -ENOENT; name = NULL; - goto err_out1; + goto err_out2; } ksmbd_debug(SMB, "converted name = %s\n", name); @@ -2654,48 +2718,44 @@ int smb2_open(struct ksmbd_work *work) if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_STREAMS)) { rc = -EBADF; - goto err_out1; + goto err_out2; } rc = parse_stream_name(name, &stream_name, &s_type); if (rc < 0) - goto err_out1; + goto err_out2; } rc = ksmbd_validate_filename(name); if (rc < 0) - goto err_out1; + goto err_out2; if (ksmbd_share_veto_filename(share, name)) { rc = -ENOENT; ksmbd_debug(SMB, "Reject open(), vetoed file: %s\n", name); - goto err_out1; + goto err_out2; } } else { name = kstrdup("", GFP_KERNEL); if (!name) { rc = -ENOMEM; - goto err_out1; + goto err_out2; } } - req_op_level = req->RequestedOplockLevel; - if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) - lc = parse_lease_state(req); - if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) { pr_err("Invalid impersonationlevel : 0x%x\n", le32_to_cpu(req->ImpersonationLevel)); rc = -EIO; rsp->hdr.Status = STATUS_BAD_IMPERSONATION_LEVEL; - goto err_out1; + goto err_out2; } if (req->CreateOptions && !(req->CreateOptions & CREATE_OPTIONS_MASK_LE)) { pr_err("Invalid create options : 0x%x\n", le32_to_cpu(req->CreateOptions)); rc = -EINVAL; - goto err_out1; + goto err_out2; } else { if (req->CreateOptions & FILE_SEQUENTIAL_ONLY_LE && req->CreateOptions & FILE_RANDOM_ACCESS_LE) @@ -2705,13 +2765,13 @@ int smb2_open(struct ksmbd_work *work) (FILE_OPEN_BY_FILE_ID_LE | CREATE_TREE_CONNECTION | FILE_RESERVE_OPFILTER_LE)) { rc = -EOPNOTSUPP; - goto err_out1; + goto err_out2; } if (req->CreateOptions & FILE_DIRECTORY_FILE_LE) { if (req->CreateOptions & FILE_NON_DIRECTORY_FILE_LE) { rc = -EINVAL; - goto err_out1; + goto err_out2; } else if (req->CreateOptions & FILE_NO_COMPRESSION_LE) { req->CreateOptions = ~(FILE_NO_COMPRESSION_LE); } @@ -2723,21 +2783,21 @@ int smb2_open(struct ksmbd_work *work) pr_err("Invalid create disposition : 0x%x\n", le32_to_cpu(req->CreateDisposition)); rc = -EINVAL; - goto err_out1; + goto err_out2; } if (!(req->DesiredAccess & DESIRED_ACCESS_MASK)) { pr_err("Invalid desired access : 0x%x\n", le32_to_cpu(req->DesiredAccess)); rc = -EACCES; - goto err_out1; + goto err_out2; } if (req->FileAttributes && !(req->FileAttributes & FILE_ATTRIBUTE_MASK_LE)) { pr_err("Invalid file attribute : 0x%x\n", le32_to_cpu(req->FileAttributes)); rc = -EINVAL; - goto err_out1; + goto err_out2; } if (req->CreateContextsOffset) { @@ -2745,19 +2805,19 @@ int smb2_open(struct ksmbd_work *work) context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); - goto err_out1; + goto err_out2; } else if (context) { ea_buf = (struct create_ea_buf_req *)context; if (le16_to_cpu(context->DataOffset) + le32_to_cpu(context->DataLength) < sizeof(struct create_ea_buf_req)) { rc = -EINVAL; - goto err_out1; + goto err_out2; } if (req->CreateOptions & FILE_NO_EA_KNOWLEDGE_LE) { rsp->hdr.Status = STATUS_ACCESS_DENIED; rc = -EACCES; - goto err_out1; + goto err_out2; } } @@ -2765,7 +2825,7 @@ int smb2_open(struct ksmbd_work *work) SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); - goto err_out1; + goto err_out2; } else if (context) { ksmbd_debug(SMB, "get query maximal access context\n"); @@ -2776,11 +2836,11 @@ int smb2_open(struct ksmbd_work *work) SMB2_CREATE_TIMEWARP_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); - goto err_out1; + goto err_out2; } else if (context) { ksmbd_debug(SMB, "get timewarp context\n"); rc = -EBADF; - goto err_out1; + goto err_out2; } if (tcon->posix_extensions) { @@ -2788,7 +2848,7 @@ int smb2_open(struct ksmbd_work *work) SMB2_CREATE_TAG_POSIX, 16); if (IS_ERR(context)) { rc = PTR_ERR(context); - goto err_out1; + goto err_out2; } else if (context) { struct create_posix *posix = (struct create_posix *)context; @@ -2796,7 +2856,7 @@ int smb2_open(struct ksmbd_work *work) le32_to_cpu(context->DataLength) < sizeof(struct create_posix) - 4) { rc = -EINVAL; - goto err_out1; + goto err_out2; } ksmbd_debug(SMB, "get posix context\n"); @@ -2808,11 +2868,14 @@ int smb2_open(struct ksmbd_work *work) if (ksmbd_override_fsids(work)) { rc = -ENOMEM; - goto err_out1; + goto err_out2; } - rc = ksmbd_vfs_kern_path(work, name, LOOKUP_NO_SYMLINKS, &path, 1); + rc = ksmbd_vfs_kern_path_locked(work, name, LOOKUP_NO_SYMLINKS, + &parent_path, &path, 1); if (!rc) { + file_present = true; + if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) { /* * If file exists with under flags, return access @@ -2821,7 +2884,6 @@ int smb2_open(struct ksmbd_work *work) if (req->CreateDisposition == FILE_OVERWRITE_IF_LE || req->CreateDisposition == FILE_OPEN_IF_LE) { rc = -EACCES; - path_put(&path); goto err_out; } @@ -2829,26 +2891,23 @@ int smb2_open(struct ksmbd_work *work) ksmbd_debug(SMB, "User does not have write permission\n"); rc = -EACCES; - path_put(&path); goto err_out; } } else if (d_is_symlink(path.dentry)) { rc = -EACCES; - path_put(&path); goto err_out; } - } - if (rc) { + file_present = true; + user_ns = mnt_user_ns(path.mnt); + } else { if (rc != -ENOENT) goto err_out; ksmbd_debug(SMB, "can not get linux path for %s, rc = %d\n", name, rc); rc = 0; - } else { - file_present = true; - user_ns = mnt_user_ns(path.mnt); } + if (stream_name) { if (req->CreateOptions & FILE_DIRECTORY_FILE_LE) { if (s_type == DATA_STREAM) { @@ -2910,11 +2969,9 @@ int smb2_open(struct ksmbd_work *work) if (!file_present) { daccess = cpu_to_le32(GENERIC_ALL_FLAGS); } else { - rc = ksmbd_vfs_query_maximal_access(user_ns, + ksmbd_vfs_query_maximal_access(user_ns, path.dentry, &daccess); - if (rc) - goto err_out; already_permitted = true; } maximal_access = daccess; @@ -2925,7 +2982,7 @@ int smb2_open(struct ksmbd_work *work) &may_flags); if (!test_tree_conn_flag(tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { - if (open_flags & O_CREAT) { + if (open_flags & (O_CREAT | O_TRUNC)) { ksmbd_debug(SMB, "User does not have write permission\n"); rc = -EACCES; @@ -2935,7 +2992,8 @@ int smb2_open(struct ksmbd_work *work) /*create file if not present */ if (!file_present) { - rc = smb2_creat(work, &path, name, open_flags, posix_mode, + rc = smb2_creat(work, &parent_path, &path, name, open_flags, + posix_mode, req->CreateOptions & FILE_DIRECTORY_FILE_LE); if (rc) { if (rc == -ENOENT) { @@ -2956,7 +3014,7 @@ int smb2_open(struct ksmbd_work *work) rc = smb2_set_ea(&ea_buf->ea, le32_to_cpu(ea_buf->ccontext.DataLength), - &path); + &path, false); if (rc == -EOPNOTSUPP) rc = 0; else if (rc) @@ -2976,15 +3034,16 @@ int smb2_open(struct ksmbd_work *work) if ((daccess & FILE_DELETE_LE) || (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE)) { - rc = ksmbd_vfs_may_delete(user_ns, - path.dentry); + rc = inode_permission(user_ns, + d_inode(path.dentry->d_parent), + MAY_EXEC | MAY_WRITE); if (rc) goto err_out; } } } - rc = ksmbd_query_inode_status(d_inode(path.dentry->d_parent)); + rc = ksmbd_query_inode_status(path.dentry->d_parent); if (rc == KSMBD_INODE_STATUS_PENDING_DELETE) { rc = -EBUSY; goto err_out; @@ -3040,7 +3099,7 @@ int smb2_open(struct ksmbd_work *work) struct inode *inode = d_inode(path.dentry); posix_acl_rc = ksmbd_vfs_inherit_posix_acl(user_ns, - inode, + &path, d_inode(path.dentry->d_parent)); if (posix_acl_rc) ksmbd_debug(SMB, "inherit posix acl failed : %d\n", posix_acl_rc); @@ -3056,7 +3115,7 @@ int smb2_open(struct ksmbd_work *work) if (rc) { if (posix_acl_rc) ksmbd_vfs_set_init_posix_acl(user_ns, - inode); + &path); if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) { @@ -3096,9 +3155,10 @@ int smb2_open(struct ksmbd_work *work) rc = ksmbd_vfs_set_sd_xattr(conn, user_ns, - path.dentry, + &path, pntsd, - pntsd_size); + pntsd_size, + false); kfree(pntsd); if (rc) pr_err("failed to store ntacl in xattr : %d\n", @@ -3121,11 +3181,6 @@ int smb2_open(struct ksmbd_work *work) fp->attrib_only = !(req->DesiredAccess & ~(FILE_READ_ATTRIBUTES_LE | FILE_WRITE_ATTRIBUTES_LE | FILE_SYNCHRONIZE_LE)); - if (!S_ISDIR(file_inode(filp)->i_mode) && open_flags & O_TRUNC && - !fp->attrib_only && !stream_name) { - smb_break_all_oplock(work, fp); - need_truncate = 1; - } /* fp should be searchable through ksmbd_inode.m_fp_list * after daccess, saccess, attrib_only, and stream are @@ -3141,23 +3196,43 @@ int smb2_open(struct ksmbd_work *work) goto err_out; } + if (file_present || created) + ksmbd_vfs_kern_path_unlock(&parent_path, &path); + + if (!S_ISDIR(file_inode(filp)->i_mode) && open_flags & O_TRUNC && + !fp->attrib_only && !stream_name) { + smb_break_all_oplock(work, fp); + need_truncate = 1; + } + + req_op_level = req->RequestedOplockLevel; + if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) + lc = parse_lease_state(req, S_ISDIR(file_inode(filp)->i_mode)); + share_ret = ksmbd_smb_check_shared_mode(fp->filp, fp); if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS) || (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && !(conn->vals->capabilities & SMB2_GLOBAL_CAP_LEASING))) { if (share_ret < 0 && !S_ISDIR(file_inode(fp->filp)->i_mode)) { rc = share_ret; - goto err_out; + goto err_out1; } } else { if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) { + /* + * Compare parent lease using parent key. If there is no + * a lease that has same parent key, Send lease break + * notification. + */ + smb_send_parent_lease_break_noti(fp, lc); + req_op_level = smb2_map_lease_to_oplock(lc->req_state); ksmbd_debug(SMB, "lease req for(%s) req oplock state 0x%x, lease state 0x%x\n", name, req_op_level, lc->req_state); rc = find_same_lease_key(sess, fp->f_ci, lc); if (rc) - goto err_out; + goto err_out1; } else if (open_flags == O_RDONLY && (req_op_level == SMB2_OPLOCK_LEVEL_BATCH || req_op_level == SMB2_OPLOCK_LEVEL_EXCLUSIVE)) @@ -3168,16 +3243,16 @@ int smb2_open(struct ksmbd_work *work) le32_to_cpu(req->hdr.Id.SyncId.TreeId), lc, share_ret); if (rc < 0) - goto err_out; + goto err_out1; } if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) ksmbd_fd_set_delete_on_close(fp, file_info); if (need_truncate) { - rc = smb2_create_truncate(&path); + rc = smb2_create_truncate(&fp->filp->f_path); if (rc) - goto err_out; + goto err_out1; } if (req->CreateContextsOffset) { @@ -3187,7 +3262,7 @@ int smb2_open(struct ksmbd_work *work) SMB2_CREATE_ALLOCATION_SIZE, 4); if (IS_ERR(az_req)) { rc = PTR_ERR(az_req); - goto err_out; + goto err_out1; } else if (az_req) { loff_t alloc_size; int err; @@ -3196,7 +3271,7 @@ int smb2_open(struct ksmbd_work *work) le32_to_cpu(az_req->ccontext.DataLength) < sizeof(struct create_alloc_size_req)) { rc = -EINVAL; - goto err_out; + goto err_out1; } alloc_size = le64_to_cpu(az_req->AllocationSize); ksmbd_debug(SMB, @@ -3214,7 +3289,7 @@ int smb2_open(struct ksmbd_work *work) context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); - goto err_out; + goto err_out1; } else if (context) { ksmbd_debug(SMB, "get query on disk id context\n"); query_disk_id = 1; @@ -3223,7 +3298,7 @@ int smb2_open(struct ksmbd_work *work) rc = ksmbd_vfs_getattr(&path, &stat); if (rc) - goto err_out; + goto err_out1; if (stat.result_mask & STATX_BTIME) fp->create_time = ksmbd_UnixTimeToNT(stat.btime); @@ -3266,7 +3341,7 @@ int smb2_open(struct ksmbd_work *work) rsp->CreateContextsOffset = 0; rsp->CreateContextsLength = 0; - inc_rfc1001_len(work->response_buf, 88); /* StructureSize - 1*/ + iov_len = offsetof(struct smb2_create_rsp, Buffer); /* If lease is request send lease context response */ if (opinfo && opinfo->is_lease) { @@ -3281,8 +3356,7 @@ int smb2_open(struct ksmbd_work *work) create_lease_buf(rsp->Buffer, opinfo->o_lease); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_lease_size); - inc_rfc1001_len(work->response_buf, - conn->vals->create_lease_size); + iov_len += conn->vals->create_lease_size; next_ptr = &lease_ccontext->Next; next_off = conn->vals->create_lease_size; } @@ -3302,8 +3376,7 @@ int smb2_open(struct ksmbd_work *work) le32_to_cpu(maximal_access)); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_mxac_size); - inc_rfc1001_len(work->response_buf, - conn->vals->create_mxac_size); + iov_len += conn->vals->create_mxac_size; if (next_ptr) *next_ptr = cpu_to_le32(next_off); next_ptr = &mxac_ccontext->Next; @@ -3321,8 +3394,7 @@ int smb2_open(struct ksmbd_work *work) stat.ino, tcon->id); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_disk_id_size); - inc_rfc1001_len(work->response_buf, - conn->vals->create_disk_id_size); + iov_len += conn->vals->create_disk_id_size; if (next_ptr) *next_ptr = cpu_to_le32(next_off); next_ptr = &disk_id_ccontext->Next; @@ -3336,8 +3408,7 @@ int smb2_open(struct ksmbd_work *work) fp); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_posix_size); - inc_rfc1001_len(work->response_buf, - conn->vals->create_posix_size); + iov_len += conn->vals->create_posix_size; if (next_ptr) *next_ptr = cpu_to_le32(next_off); } @@ -3348,10 +3419,17 @@ int smb2_open(struct ksmbd_work *work) } err_out: - if (file_present || created) - path_put(&path); - ksmbd_revert_fsids(work); + if (rc && (file_present || created)) + ksmbd_vfs_kern_path_unlock(&parent_path, &path); + err_out1: + ksmbd_revert_fsids(work); + +err_out2: + if (!rc) { + ksmbd_update_fstate(&work->sess->file_table, fp, FP_INITED); + rc = ksmbd_iov_pin_rsp(work, (void *)rsp, iov_len); + } if (rc) { if (rc == -EINVAL) rsp->hdr.Status = STATUS_INVALID_PARAMETER; @@ -3525,7 +3603,7 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, goto free_conv_name; } - struct_sz = readdir_info_level_struct_sz(info_level) - 1 + conv_len; + struct_sz = readdir_info_level_struct_sz(info_level) + conv_len; next_entry_offset = ALIGN(struct_sz, KSMBD_DIR_INFO_ALIGNMENT); d_info->last_entry_off_align = next_entry_offset - struct_sz; @@ -3777,7 +3855,7 @@ static int reserve_populate_dentry(struct ksmbd_dir_info *d_info, return -EOPNOTSUPP; conv_len = (d_info->name_len + 1) * 2; - next_entry_offset = ALIGN(struct_sz - 1 + conv_len, + next_entry_offset = ALIGN(struct_sz + conv_len, KSMBD_DIR_INFO_ALIGNMENT); if (next_entry_offset > d_info->out_buf_len) { @@ -4077,7 +4155,10 @@ int smb2_query_dir(struct ksmbd_work *work) rsp->OutputBufferOffset = cpu_to_le16(0); rsp->OutputBufferLength = cpu_to_le32(0); rsp->Buffer[0] = 0; - inc_rfc1001_len(work->response_buf, 9); + rc = ksmbd_iov_pin_rsp(work, (void *)rsp, + sizeof(struct smb2_query_directory_rsp)); + if (rc) + goto err_out; } else { no_buf_len: ((struct file_directory_info *) @@ -4089,7 +4170,11 @@ no_buf_len: rsp->StructureSize = cpu_to_le16(9); rsp->OutputBufferOffset = cpu_to_le16(72); rsp->OutputBufferLength = cpu_to_le32(d_info.data_count); - inc_rfc1001_len(work->response_buf, 8 + d_info.data_count); + rc = ksmbd_iov_pin_rsp(work, (void *)rsp, + offsetof(struct smb2_query_directory_rsp, Buffer) + + d_info.data_count); + if (rc) + goto err_out; } kfree(srch_ptr); @@ -4130,27 +4215,18 @@ err_out2: * @reqOutputBufferLength: max buffer length expected in command response * @rsp: query info response buffer contains output buffer length * @rsp_org: base response buffer pointer in case of chained response - * @infoclass_size: query info class response buffer size * * Return: 0 on success, otherwise error */ static int buffer_check_err(int reqOutputBufferLength, struct smb2_query_info_rsp *rsp, - void *rsp_org, int infoclass_size) + void *rsp_org) { if (reqOutputBufferLength < le32_to_cpu(rsp->OutputBufferLength)) { - if (reqOutputBufferLength < infoclass_size) { - pr_err("Invalid Buffer Size Requested\n"); - rsp->hdr.Status = STATUS_INFO_LENGTH_MISMATCH; - *(__be32 *)rsp_org = cpu_to_be32(sizeof(struct smb2_hdr)); - return -EINVAL; - } - - ksmbd_debug(SMB, "Buffer Overflow\n"); - rsp->hdr.Status = STATUS_BUFFER_OVERFLOW; - *(__be32 *)rsp_org = cpu_to_be32(sizeof(struct smb2_hdr) + - reqOutputBufferLength); - rsp->OutputBufferLength = cpu_to_le32(reqOutputBufferLength); + pr_err("Invalid Buffer Size Requested\n"); + rsp->hdr.Status = STATUS_INFO_LENGTH_MISMATCH; + *(__be32 *)rsp_org = cpu_to_be32(sizeof(struct smb2_hdr)); + return -EINVAL; } return 0; } @@ -4169,7 +4245,6 @@ static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp, sinfo->Directory = 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_standard_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_standard_info)); } static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num, @@ -4183,7 +4258,6 @@ static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num, file_info->IndexNumber = cpu_to_le64(num | (1ULL << 63)); rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_internal_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_internal_info)); } static int smb2_get_info_file_pipe(struct ksmbd_session *sess, @@ -4209,14 +4283,12 @@ static int smb2_get_info_file_pipe(struct ksmbd_session *sess, case FILE_STANDARD_INFORMATION: get_standard_info_pipe(rsp, rsp_org); rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, rsp_org, - FILE_STANDARD_INFORMATION_SIZE); + rsp, rsp_org); break; case FILE_INTERNAL_INFORMATION: get_internal_info_pipe(rsp, id, rsp_org); rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, rsp_org, - FILE_INTERNAL_INFORMATION_SIZE); + rsp, rsp_org); break; default: ksmbd_debug(SMB, "smb2_info_file_pipe for %u not supported\n", @@ -4384,7 +4456,6 @@ done: if (rsp_data_cnt == 0) rsp->hdr.Status = STATUS_NO_EAS_ON_FILE; rsp->OutputBufferLength = cpu_to_le32(rsp_data_cnt); - inc_rfc1001_len(rsp_org, rsp_data_cnt); out: kvfree(xattr_list); return rc; @@ -4399,7 +4470,6 @@ static void get_file_access_info(struct smb2_query_info_rsp *rsp, file_info->AccessFlags = fp->daccess; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_access_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_access_info)); } static int get_file_basic_info(struct smb2_query_info_rsp *rsp, @@ -4429,7 +4499,6 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, basic_info->Pad1 = 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_basic_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_basic_info)); return 0; } @@ -4454,8 +4523,6 @@ static void get_file_standard_info(struct smb2_query_info_rsp *rsp, sinfo->Directory = S_ISDIR(stat.mode) ? 1 : 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_standard_info)); - inc_rfc1001_len(rsp_org, - sizeof(struct smb2_file_standard_info)); } static void get_file_alignment_info(struct smb2_query_info_rsp *rsp, @@ -4467,8 +4534,6 @@ static void get_file_alignment_info(struct smb2_query_info_rsp *rsp, file_info->AlignmentRequirement = 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_alignment_info)); - inc_rfc1001_len(rsp_org, - sizeof(struct smb2_file_alignment_info)); } static int get_file_all_info(struct ksmbd_work *work, @@ -4532,7 +4597,6 @@ static int get_file_all_info(struct ksmbd_work *work, rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_all_info) + conv_len - 1); kfree(filename); - inc_rfc1001_len(rsp_org, le32_to_cpu(rsp->OutputBufferLength)); return 0; } @@ -4555,7 +4619,6 @@ static void get_file_alternate_info(struct ksmbd_work *work, file_info->FileNameLength = cpu_to_le32(conv_len); rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_alt_name_info) + conv_len); - inc_rfc1001_len(rsp_org, le32_to_cpu(rsp->OutputBufferLength)); } static void get_file_stream_info(struct ksmbd_work *work, @@ -4655,7 +4718,6 @@ out: kvfree(xattr_list); rsp->OutputBufferLength = cpu_to_le32(nbytes); - inc_rfc1001_len(rsp_org, nbytes); } static void get_file_internal_info(struct smb2_query_info_rsp *rsp, @@ -4670,7 +4732,6 @@ static void get_file_internal_info(struct smb2_query_info_rsp *rsp, file_info->IndexNumber = cpu_to_le64(stat.ino); rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_internal_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_internal_info)); } static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, @@ -4706,7 +4767,6 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, file_info->Reserved = cpu_to_le32(0); rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_ntwrk_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_ntwrk_info)); return 0; } @@ -4718,7 +4778,6 @@ static void get_file_ea_info(struct smb2_query_info_rsp *rsp, void *rsp_org) file_info->EASize = 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_ea_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_ea_info)); } static void get_file_position_info(struct smb2_query_info_rsp *rsp, @@ -4730,7 +4789,6 @@ static void get_file_position_info(struct smb2_query_info_rsp *rsp, file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos); rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_pos_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_pos_info)); } static void get_file_mode_info(struct smb2_query_info_rsp *rsp, @@ -4742,7 +4800,6 @@ static void get_file_mode_info(struct smb2_query_info_rsp *rsp, file_info->Mode = fp->coption & FILE_MODE_INFO_MASK; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_mode_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_mode_info)); } static void get_file_compression_info(struct smb2_query_info_rsp *rsp, @@ -4764,7 +4821,6 @@ static void get_file_compression_info(struct smb2_query_info_rsp *rsp, rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_comp_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_comp_info)); } static int get_file_attribute_tag_info(struct smb2_query_info_rsp *rsp, @@ -4783,11 +4839,10 @@ static int get_file_attribute_tag_info(struct smb2_query_info_rsp *rsp, file_info->ReparseTag = 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_attr_tag_info)); - inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_attr_tag_info)); return 0; } -static int find_file_posix_info(struct smb2_query_info_rsp *rsp, +static void find_file_posix_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { struct smb311_posix_qinfo *file_info; @@ -4825,8 +4880,6 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, SIDUNIX_GROUP, (struct smb_sid *)&file_info->Sids[16]); rsp->OutputBufferLength = cpu_to_le32(out_buf_len); - inc_rfc1001_len(rsp_org, out_buf_len); - return out_buf_len; } static int smb2_get_info_file(struct ksmbd_work *work, @@ -4836,7 +4889,6 @@ static int smb2_get_info_file(struct ksmbd_work *work, struct ksmbd_file *fp; int fileinfoclass = 0; int rc = 0; - int file_infoclass_size; unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; if (test_share_config_flag(work->tcon->share_conf, @@ -4869,85 +4921,69 @@ static int smb2_get_info_file(struct ksmbd_work *work, switch (fileinfoclass) { case FILE_ACCESS_INFORMATION: get_file_access_info(rsp, fp, work->response_buf); - file_infoclass_size = FILE_ACCESS_INFORMATION_SIZE; break; case FILE_BASIC_INFORMATION: rc = get_file_basic_info(rsp, fp, work->response_buf); - file_infoclass_size = FILE_BASIC_INFORMATION_SIZE; break; case FILE_STANDARD_INFORMATION: get_file_standard_info(rsp, fp, work->response_buf); - file_infoclass_size = FILE_STANDARD_INFORMATION_SIZE; break; case FILE_ALIGNMENT_INFORMATION: get_file_alignment_info(rsp, work->response_buf); - file_infoclass_size = FILE_ALIGNMENT_INFORMATION_SIZE; break; case FILE_ALL_INFORMATION: rc = get_file_all_info(work, rsp, fp, work->response_buf); - file_infoclass_size = FILE_ALL_INFORMATION_SIZE; break; case FILE_ALTERNATE_NAME_INFORMATION: get_file_alternate_info(work, rsp, fp, work->response_buf); - file_infoclass_size = FILE_ALTERNATE_NAME_INFORMATION_SIZE; break; case FILE_STREAM_INFORMATION: get_file_stream_info(work, rsp, fp, work->response_buf); - file_infoclass_size = FILE_STREAM_INFORMATION_SIZE; break; case FILE_INTERNAL_INFORMATION: get_file_internal_info(rsp, fp, work->response_buf); - file_infoclass_size = FILE_INTERNAL_INFORMATION_SIZE; break; case FILE_NETWORK_OPEN_INFORMATION: rc = get_file_network_open_info(rsp, fp, work->response_buf); - file_infoclass_size = FILE_NETWORK_OPEN_INFORMATION_SIZE; break; case FILE_EA_INFORMATION: get_file_ea_info(rsp, work->response_buf); - file_infoclass_size = FILE_EA_INFORMATION_SIZE; break; case FILE_FULL_EA_INFORMATION: rc = smb2_get_ea(work, fp, req, rsp, work->response_buf); - file_infoclass_size = FILE_FULL_EA_INFORMATION_SIZE; break; case FILE_POSITION_INFORMATION: get_file_position_info(rsp, fp, work->response_buf); - file_infoclass_size = FILE_POSITION_INFORMATION_SIZE; break; case FILE_MODE_INFORMATION: get_file_mode_info(rsp, fp, work->response_buf); - file_infoclass_size = FILE_MODE_INFORMATION_SIZE; break; case FILE_COMPRESSION_INFORMATION: get_file_compression_info(rsp, fp, work->response_buf); - file_infoclass_size = FILE_COMPRESSION_INFORMATION_SIZE; break; case FILE_ATTRIBUTE_TAG_INFORMATION: rc = get_file_attribute_tag_info(rsp, fp, work->response_buf); - file_infoclass_size = FILE_ATTRIBUTE_TAG_INFORMATION_SIZE; break; case SMB_FIND_FILE_POSIX_INFO: if (!work->tcon->posix_extensions) { pr_err("client doesn't negotiate with SMB3.1.1 POSIX Extensions\n"); rc = -EOPNOTSUPP; } else { - file_infoclass_size = find_file_posix_info(rsp, fp, - work->response_buf); + find_file_posix_info(rsp, fp, work->response_buf); } break; default: @@ -4957,8 +4993,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, } if (!rc) rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, work->response_buf, - file_infoclass_size); + rsp, work->response_buf); ksmbd_fd_put(work, fp); return rc; } @@ -4974,7 +5009,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, struct kstatfs stfs; struct path path; int rc = 0, len; - int fs_infoclass_size = 0; if (!share->path) return -EIO; @@ -5004,8 +5038,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->DeviceType = cpu_to_le32(stfs.f_type); info->DeviceCharacteristics = cpu_to_le32(0x00000020); rsp->OutputBufferLength = cpu_to_le32(8); - inc_rfc1001_len(work->response_buf, 8); - fs_infoclass_size = FS_DEVICE_INFORMATION_SIZE; break; } case FS_ATTRIBUTE_INFORMATION: @@ -5034,8 +5066,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->FileSystemNameLen = cpu_to_le32(len); sz = sizeof(struct filesystem_attribute_info) - 2 + len; rsp->OutputBufferLength = cpu_to_le32(sz); - inc_rfc1001_len(work->response_buf, sz); - fs_infoclass_size = FS_ATTRIBUTE_INFORMATION_SIZE; break; } case FS_VOLUME_INFORMATION: @@ -5062,8 +5092,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->Reserved = 0; sz = sizeof(struct filesystem_vol_info) - 2 + len; rsp->OutputBufferLength = cpu_to_le32(sz); - inc_rfc1001_len(work->response_buf, sz); - fs_infoclass_size = FS_VOLUME_INFORMATION_SIZE; break; } case FS_SIZE_INFORMATION: @@ -5076,8 +5104,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->SectorsPerAllocationUnit = cpu_to_le32(1); info->BytesPerSector = cpu_to_le32(stfs.f_bsize); rsp->OutputBufferLength = cpu_to_le32(24); - inc_rfc1001_len(work->response_buf, 24); - fs_infoclass_size = FS_SIZE_INFORMATION_SIZE; break; } case FS_FULL_SIZE_INFORMATION: @@ -5093,8 +5119,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->SectorsPerAllocationUnit = cpu_to_le32(1); info->BytesPerSector = cpu_to_le32(stfs.f_bsize); rsp->OutputBufferLength = cpu_to_le32(32); - inc_rfc1001_len(work->response_buf, 32); - fs_infoclass_size = FS_FULL_SIZE_INFORMATION_SIZE; break; } case FS_OBJECT_ID_INFORMATION: @@ -5114,8 +5138,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->extended_info.rel_date = 0; memcpy(info->extended_info.version_string, "1.1.0", strlen("1.1.0")); rsp->OutputBufferLength = cpu_to_le32(64); - inc_rfc1001_len(work->response_buf, 64); - fs_infoclass_size = FS_OBJECT_ID_INFORMATION_SIZE; break; } case FS_SECTOR_SIZE_INFORMATION: @@ -5137,8 +5159,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->ByteOffsetForSectorAlignment = 0; info->ByteOffsetForPartitionAlignment = 0; rsp->OutputBufferLength = cpu_to_le32(28); - inc_rfc1001_len(work->response_buf, 28); - fs_infoclass_size = FS_SECTOR_SIZE_INFORMATION_SIZE; break; } case FS_CONTROL_INFORMATION: @@ -5159,8 +5179,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->DefaultQuotaLimit = cpu_to_le64(SMB2_NO_FID); info->Padding = 0; rsp->OutputBufferLength = cpu_to_le32(48); - inc_rfc1001_len(work->response_buf, 48); - fs_infoclass_size = FS_CONTROL_INFORMATION_SIZE; break; } case FS_POSIX_INFORMATION: @@ -5180,8 +5198,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->TotalFileNodes = cpu_to_le64(stfs.f_files); info->FreeFileNodes = cpu_to_le64(stfs.f_ffree); rsp->OutputBufferLength = cpu_to_le32(56); - inc_rfc1001_len(work->response_buf, 56); - fs_infoclass_size = FS_POSIX_INFORMATION_SIZE; } break; } @@ -5190,8 +5206,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, return -EOPNOTSUPP; } rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, work->response_buf, - fs_infoclass_size); + rsp, work->response_buf); path_put(&path); return rc; } @@ -5225,7 +5240,6 @@ static int smb2_get_info_sec(struct ksmbd_work *work, secdesclen = sizeof(struct smb_ntsd); rsp->OutputBufferLength = cpu_to_le32(secdesclen); - inc_rfc1001_len(work->response_buf, secdesclen); return 0; } @@ -5270,7 +5284,6 @@ static int smb2_get_info_sec(struct ksmbd_work *work, return rc; rsp->OutputBufferLength = cpu_to_le32(secdesclen); - inc_rfc1001_len(work->response_buf, secdesclen); return 0; } @@ -5309,6 +5322,14 @@ int smb2_query_info(struct ksmbd_work *work) rc = -EOPNOTSUPP; } + if (!rc) { + rsp->StructureSize = cpu_to_le16(9); + rsp->OutputBufferOffset = cpu_to_le16(72); + rc = ksmbd_iov_pin_rsp(work, (void *)rsp, + offsetof(struct smb2_query_info_rsp, Buffer) + + le32_to_cpu(rsp->OutputBufferLength)); + } + if (rc < 0) { if (rc == -EACCES) rsp->hdr.Status = STATUS_ACCESS_DENIED; @@ -5316,6 +5337,8 @@ int smb2_query_info(struct ksmbd_work *work) rsp->hdr.Status = STATUS_FILE_CLOSED; else if (rc == -EIO) rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; + else if (rc == -ENOMEM) + rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; else if (rc == -EOPNOTSUPP || rsp->hdr.Status == 0) rsp->hdr.Status = STATUS_INVALID_INFO_CLASS; smb2_set_err_rsp(work); @@ -5324,9 +5347,6 @@ int smb2_query_info(struct ksmbd_work *work) rc); return rc; } - rsp->StructureSize = cpu_to_le16(9); - rsp->OutputBufferOffset = cpu_to_le16(72); - inc_rfc1001_len(work->response_buf, 8); return 0; } @@ -5357,8 +5377,9 @@ static noinline int smb2_close_pipe(struct ksmbd_work *work) rsp->AllocationSize = 0; rsp->EndOfFile = 0; rsp->Attributes = 0; - inc_rfc1001_len(work->response_buf, 60); - return 0; + + return ksmbd_iov_pin_rsp(work, (void *)rsp, + sizeof(struct smb2_close_rsp)); } /** @@ -5463,15 +5484,17 @@ int smb2_close(struct ksmbd_work *work) err = ksmbd_close_fd(work, volatile_id); out: + if (!err) + err = ksmbd_iov_pin_rsp(work, (void *)rsp, + sizeof(struct smb2_close_rsp)); + if (err) { if (rsp->hdr.Status == 0) rsp->hdr.Status = STATUS_FILE_CLOSED; smb2_set_err_rsp(work); - } else { - inc_rfc1001_len(work->response_buf, 60); } - return 0; + return err; } /** @@ -5489,50 +5512,24 @@ int smb2_echo(struct ksmbd_work *work) rsp->StructureSize = cpu_to_le16(4); rsp->Reserved = 0; - inc_rfc1001_len(work->response_buf, 4); - return 0; + return ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_echo_rsp)); } static int smb2_rename(struct ksmbd_work *work, struct ksmbd_file *fp, - struct user_namespace *user_ns, struct smb2_file_rename_info *file_info, struct nls_table *local_nls) { struct ksmbd_share_config *share = fp->tcon->share_conf; - char *new_name = NULL, *abs_oldname = NULL, *old_name = NULL; - char *pathname = NULL; - struct path path; - bool file_present = true; - int rc; + char *new_name = NULL; + int rc, flags = 0; ksmbd_debug(SMB, "setting FILE_RENAME_INFO\n"); - pathname = kmalloc(PATH_MAX, GFP_KERNEL); - if (!pathname) - return -ENOMEM; - - abs_oldname = file_path(fp->filp, pathname, PATH_MAX); - if (IS_ERR(abs_oldname)) { - rc = -EINVAL; - goto out; - } - old_name = strrchr(abs_oldname, '/'); - if (old_name && old_name[1] != '\0') { - old_name++; - } else { - ksmbd_debug(SMB, "can't get last component in path %s\n", - abs_oldname); - rc = -ENOENT; - goto out; - } - new_name = smb2_get_name(file_info->FileName, le32_to_cpu(file_info->FileNameLength), local_nls); - if (IS_ERR(new_name)) { - rc = PTR_ERR(new_name); - goto out; - } + if (IS_ERR(new_name)) + return PTR_ERR(new_name); if (strchr(new_name, ':')) { int s_type; @@ -5558,10 +5555,10 @@ static int smb2_rename(struct ksmbd_work *work, if (rc) goto out; - rc = ksmbd_vfs_setxattr(user_ns, - fp->filp->f_path.dentry, + rc = ksmbd_vfs_setxattr(file_mnt_user_ns(fp->filp), + &fp->filp->f_path, xattr_stream_name, - NULL, 0, 0); + NULL, 0, 0, true); if (rc < 0) { pr_err("failed to store stream name in xattr: %d\n", rc); @@ -5573,47 +5570,19 @@ static int smb2_rename(struct ksmbd_work *work, } ksmbd_debug(SMB, "new name %s\n", new_name); - rc = ksmbd_vfs_kern_path(work, new_name, LOOKUP_NO_SYMLINKS, &path, 1); - if (rc) { - if (rc != -ENOENT) - goto out; - file_present = false; - } else { - path_put(&path); - } - if (ksmbd_share_veto_filename(share, new_name)) { rc = -ENOENT; ksmbd_debug(SMB, "Can't rename vetoed file: %s\n", new_name); goto out; } - if (file_info->ReplaceIfExists) { - if (file_present) { - rc = ksmbd_vfs_remove_file(work, new_name); - if (rc) { - if (rc != -ENOTEMPTY) - rc = -EINVAL; - ksmbd_debug(SMB, "cannot delete %s, rc %d\n", - new_name, rc); - goto out; - } - } - } else { - if (file_present && - strncmp(old_name, path.dentry->d_name.name, strlen(old_name))) { - rc = -EEXIST; - ksmbd_debug(SMB, - "cannot rename already existing file\n"); - goto out; - } - } + if (!file_info->ReplaceIfExists) + flags = RENAME_NOREPLACE; - rc = ksmbd_vfs_fp_rename(work, fp, new_name); + smb_break_all_levII_oplock(work, fp, 0); + rc = ksmbd_vfs_rename(work, &fp->filp->f_path, new_name, flags); out: - kfree(pathname); - if (!IS_ERR(new_name)) - kfree(new_name); + kfree(new_name); return rc; } @@ -5624,8 +5593,8 @@ static int smb2_create_link(struct ksmbd_work *work, struct nls_table *local_nls) { char *link_name = NULL, *target_name = NULL, *pathname = NULL; - struct path path; - bool file_present = true; + struct path path, parent_path; + bool file_present = false; int rc; if (buf_len < (u64)sizeof(struct smb2_file_link_info) + @@ -5653,18 +5622,17 @@ static int smb2_create_link(struct ksmbd_work *work, } ksmbd_debug(SMB, "target name is %s\n", target_name); - rc = ksmbd_vfs_kern_path(work, link_name, LOOKUP_NO_SYMLINKS, &path, 0); + rc = ksmbd_vfs_kern_path_locked(work, link_name, LOOKUP_NO_SYMLINKS, + &parent_path, &path, 0); if (rc) { if (rc != -ENOENT) goto out; - file_present = false; - } else { - path_put(&path); - } + } else + file_present = true; if (file_info->ReplaceIfExists) { if (file_present) { - rc = ksmbd_vfs_remove_file(work, link_name); + rc = ksmbd_vfs_remove_file(work, &path); if (rc) { rc = -EINVAL; ksmbd_debug(SMB, "cannot delete %s\n", @@ -5684,6 +5652,9 @@ static int smb2_create_link(struct ksmbd_work *work, if (rc) rc = -EINVAL; out: + if (file_present) + ksmbd_vfs_kern_path_unlock(&parent_path, &path); + if (!IS_ERR(link_name)) kfree(link_name); kfree(pathname); @@ -5750,8 +5721,8 @@ static int set_file_basic_info(struct ksmbd_file *fp, da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(user_ns, - filp->f_path.dentry, &da); + rc = ksmbd_vfs_set_dos_attrib_xattr(user_ns, &filp->f_path, &da, + true); if (rc) ksmbd_debug(SMB, "failed to restore file attribute in EA\n"); @@ -5861,12 +5832,6 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, struct smb2_file_rename_info *rename_info, unsigned int buf_len) { - struct user_namespace *user_ns; - struct ksmbd_file *parent_fp; - struct dentry *parent; - struct dentry *dentry = fp->filp->f_path.dentry; - int ret; - if (!(fp->daccess & FILE_DELETE_LE)) { pr_err("no right to delete : 0x%x\n", fp->daccess); return -EACCES; @@ -5876,32 +5841,10 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, le32_to_cpu(rename_info->FileNameLength)) return -EINVAL; - user_ns = file_mnt_user_ns(fp->filp); - if (ksmbd_stream_fd(fp)) - goto next; - - parent = dget_parent(dentry); - ret = ksmbd_vfs_lock_parent(user_ns, parent, dentry); - if (ret) { - dput(parent); - return ret; - } - - parent_fp = ksmbd_lookup_fd_inode(d_inode(parent)); - inode_unlock(d_inode(parent)); - dput(parent); + if (!le32_to_cpu(rename_info->FileNameLength)) + return -EINVAL; - if (parent_fp) { - if (parent_fp->daccess & FILE_DELETE_LE) { - pr_err("parent dir is opened with delete access\n"); - ksmbd_fd_put(work, parent_fp); - return -ESHARE; - } - ksmbd_fd_put(work, parent_fp); - } -next: - return smb2_rename(work, fp, user_ns, rename_info, - work->conn->local_nls); + return smb2_rename(work, fp, rename_info, work->conn->local_nls); } static int set_file_disposition_info(struct ksmbd_file *fp, @@ -6012,12 +5955,6 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, } case FILE_RENAME_INFORMATION: { - if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { - ksmbd_debug(SMB, - "User does not have write permission\n"); - return -EACCES; - } - if (buf_len < sizeof(struct smb2_file_rename_info)) return -EINVAL; @@ -6037,12 +5974,6 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, } case FILE_DISPOSITION_INFORMATION: { - if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { - ksmbd_debug(SMB, - "User does not have write permission\n"); - return -EACCES; - } - if (buf_len < sizeof(struct smb2_file_disposition_info)) return -EINVAL; @@ -6061,7 +5992,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return smb2_set_ea((struct smb2_ea_info *)req->Buffer, - buf_len, &fp->filp->f_path); + buf_len, &fp->filp->f_path, true); } case FILE_POSITION_INFORMATION: { @@ -6091,7 +6022,7 @@ static int smb2_set_info_sec(struct ksmbd_file *fp, int addition_info, fp->saccess |= FILE_SHARE_DELETE_LE; return set_info_sec(fp->conn, fp->tcon, &fp->filp->f_path, pntsd, - buf_len, false); + buf_len, false, true); } /** @@ -6104,7 +6035,7 @@ int smb2_set_info(struct ksmbd_work *work) { struct smb2_set_info_req *req; struct smb2_set_info_rsp *rsp; - struct ksmbd_file *fp; + struct ksmbd_file *fp = NULL; int rc = 0; unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; @@ -6124,6 +6055,13 @@ int smb2_set_info(struct ksmbd_work *work) rsp = smb2_get_msg(work->response_buf); } + if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { + ksmbd_debug(SMB, "User does not have write permission\n"); + pr_err("User does not have write permission\n"); + rc = -EACCES; + goto err_out; + } + if (!has_file_id(id)) { id = req->VolatileFileId; pid = req->PersistentFileId; @@ -6161,7 +6099,10 @@ int smb2_set_info(struct ksmbd_work *work) goto err_out; rsp->StructureSize = cpu_to_le16(2); - inc_rfc1001_len(work->response_buf, 2); + rc = ksmbd_iov_pin_rsp(work, (void *)rsp, + sizeof(struct smb2_set_info_rsp)); + if (rc) + goto err_out; ksmbd_fd_put(work, fp); return 0; @@ -6208,28 +6149,38 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) id = req->VolatileFileId; - inc_rfc1001_len(work->response_buf, 16); rpc_resp = ksmbd_rpc_read(work->sess, id); if (rpc_resp) { + void *aux_payload_buf; + if (rpc_resp->flags != KSMBD_RPC_OK) { err = -EINVAL; goto out; } - work->aux_payload_buf = - kvmalloc(rpc_resp->payload_sz, GFP_KERNEL | __GFP_ZERO); - if (!work->aux_payload_buf) { + aux_payload_buf = + kvmalloc(rpc_resp->payload_sz, GFP_KERNEL); + if (!aux_payload_buf) { err = -ENOMEM; goto out; } - memcpy(work->aux_payload_buf, rpc_resp->payload, - rpc_resp->payload_sz); + memcpy(aux_payload_buf, rpc_resp->payload, rpc_resp->payload_sz); nbytes = rpc_resp->payload_sz; - work->resp_hdr_sz = get_rfc1002_len(work->response_buf) + 4; - work->aux_payload_sz = nbytes; + err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, + offsetof(struct smb2_read_rsp, Buffer), + aux_payload_buf, nbytes); + if (err) { + kvfree(aux_payload_buf); + goto out; + } kvfree(rpc_resp); + } else { + err = ksmbd_iov_pin_rsp(work, (void *)rsp, + offsetof(struct smb2_read_rsp, Buffer)); + if (err) + goto out; } rsp->StructureSize = cpu_to_le16(17); @@ -6238,7 +6189,6 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) rsp->DataLength = cpu_to_le32(nbytes); rsp->DataRemaining = 0; rsp->Flags = 0; - inc_rfc1001_len(work->response_buf, nbytes); return 0; out: @@ -6312,13 +6262,8 @@ int smb2_read(struct ksmbd_work *work) int err = 0; bool is_rdma_channel = false; unsigned int max_read_size = conn->vals->max_read_size; - - WORK_BUFFERS(work, req, rsp); - if (work->next_smb2_rcv_hdr_off) { - work->send_no_response = 1; - err = -EOPNOTSUPP; - goto out; - } + unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; + void *aux_payload_buf; if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) { @@ -6326,6 +6271,25 @@ int smb2_read(struct ksmbd_work *work) return smb2_read_pipe(work); } + if (work->next_smb2_rcv_hdr_off) { + req = ksmbd_req_buf_next(work); + rsp = ksmbd_resp_buf_next(work); + if (!has_file_id(req->VolatileFileId)) { + ksmbd_debug(SMB, "Compound request set FID = %llu\n", + work->compound_fid); + id = work->compound_fid; + pid = work->compound_pfid; + } + } else { + req = smb2_get_msg(work->request_buf); + rsp = smb2_get_msg(work->response_buf); + } + + if (!has_file_id(id)) { + id = req->VolatileFileId; + pid = req->PersistentFileId; + } + if (req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE || req->Channel == SMB2_CHANNEL_RDMA_V1) { is_rdma_channel = true; @@ -6348,7 +6312,7 @@ int smb2_read(struct ksmbd_work *work) goto out; } - fp = ksmbd_lookup_fd_slow(work, req->VolatileFileId, req->PersistentFileId); + fp = ksmbd_lookup_fd_slow(work, id, pid); if (!fp) { err = -ENOENT; goto out; @@ -6374,21 +6338,20 @@ int smb2_read(struct ksmbd_work *work) ksmbd_debug(SMB, "filename %pD, offset %lld, len %zu\n", fp->filp, offset, length); - work->aux_payload_buf = kvmalloc(length, GFP_KERNEL | __GFP_ZERO); - if (!work->aux_payload_buf) { + aux_payload_buf = kvzalloc(length, GFP_KERNEL); + if (!aux_payload_buf) { err = -ENOMEM; goto out; } - nbytes = ksmbd_vfs_read(work, fp, length, &offset); + nbytes = ksmbd_vfs_read(work, fp, length, &offset, aux_payload_buf); if (nbytes < 0) { err = nbytes; goto out; } if ((nbytes == 0 && length != 0) || nbytes < mincount) { - kvfree(work->aux_payload_buf); - work->aux_payload_buf = NULL; + kvfree(aux_payload_buf); rsp->hdr.Status = STATUS_END_OF_FILE; smb2_set_err_rsp(work); ksmbd_fd_put(work, fp); @@ -6401,11 +6364,10 @@ int smb2_read(struct ksmbd_work *work) if (is_rdma_channel == true) { /* write data to the client using rdma channel */ remain_bytes = smb2_read_rdma_channel(work, req, - work->aux_payload_buf, + aux_payload_buf, nbytes); - kvfree(work->aux_payload_buf); - work->aux_payload_buf = NULL; - + kvfree(aux_payload_buf); + aux_payload_buf = NULL; nbytes = 0; if (remain_bytes < 0) { err = (int)remain_bytes; @@ -6419,10 +6381,13 @@ int smb2_read(struct ksmbd_work *work) rsp->DataLength = cpu_to_le32(nbytes); rsp->DataRemaining = cpu_to_le32(remain_bytes); rsp->Flags = 0; - inc_rfc1001_len(work->response_buf, 16); - work->resp_hdr_sz = get_rfc1002_len(work->response_buf) + 4; - work->aux_payload_sz = nbytes; - inc_rfc1001_len(work->response_buf, nbytes); + err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, + offsetof(struct smb2_read_rsp, Buffer), + aux_payload_buf, nbytes); + if (err) { + kvfree(aux_payload_buf); + goto out; + } ksmbd_fd_put(work, fp); return 0; @@ -6505,8 +6470,8 @@ static noinline int smb2_write_pipe(struct ksmbd_work *work) rsp->DataLength = cpu_to_le32(length); rsp->DataRemaining = 0; rsp->Reserved2 = 0; - inc_rfc1001_len(work->response_buf, 16); - return 0; + err = ksmbd_iov_pin_rsp(work, (void *)rsp, + offsetof(struct smb2_write_rsp, Buffer)); out: if (err) { rsp->hdr.Status = STATUS_INVALID_HANDLE; @@ -6525,7 +6490,7 @@ static ssize_t smb2_write_rdma_channel(struct ksmbd_work *work, int ret; ssize_t nbytes; - data_buf = kvmalloc(length, GFP_KERNEL | __GFP_ZERO); + data_buf = kvzalloc(length, GFP_KERNEL); if (!data_buf) return -ENOMEM; @@ -6662,7 +6627,9 @@ int smb2_write(struct ksmbd_work *work) rsp->DataLength = cpu_to_le32(nbytes); rsp->DataRemaining = 0; rsp->Reserved2 = 0; - inc_rfc1001_len(work->response_buf, 16); + err = ksmbd_iov_pin_rsp(work, rsp, offsetof(struct smb2_write_rsp, Buffer)); + if (err) + goto out; ksmbd_fd_put(work, fp); return 0; @@ -6709,15 +6676,11 @@ int smb2_flush(struct ksmbd_work *work) rsp->StructureSize = cpu_to_le16(4); rsp->Reserved = 0; - inc_rfc1001_len(work->response_buf, 4); - return 0; + return ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_flush_rsp)); out: - if (err) { - rsp->hdr.Status = STATUS_INVALID_HANDLE; - smb2_set_err_rsp(work); - } - + rsp->hdr.Status = STATUS_INVALID_HANDLE; + smb2_set_err_rsp(work); return err; } @@ -6843,7 +6806,7 @@ static int smb2_set_flock_flags(struct file_lock *flock, int flags) case SMB2_LOCKFLAG_UNLOCK: ksmbd_debug(SMB, "received unlock request\n"); flock->fl_type = F_UNLCK; - cmd = 0; + cmd = F_SETLK; break; } @@ -6949,6 +6912,7 @@ int smb2_lock(struct ksmbd_work *work) if (lock_start > U64_MAX - lock_length) { pr_err("Invalid lock range requested\n"); rsp->hdr.Status = STATUS_INVALID_LOCK_RANGE; + locks_free_lock(flock); goto out; } @@ -6968,6 +6932,7 @@ int smb2_lock(struct ksmbd_work *work) "the end offset(%llx) is smaller than the start offset(%llx)\n", flock->fl_end, flock->fl_start); rsp->hdr.Status = STATUS_INVALID_LOCK_RANGE; + locks_free_lock(flock); goto out; } @@ -6979,6 +6944,7 @@ int smb2_lock(struct ksmbd_work *work) flock->fl_type != F_UNLCK) { pr_err("conflict two locks in one request\n"); err = -EINVAL; + locks_free_lock(flock); goto out; } } @@ -6987,6 +6953,7 @@ int smb2_lock(struct ksmbd_work *work) smb_lock = smb2_lock_init(flock, cmd, flags, &lock_list); if (!smb_lock) { err = -EINVAL; + locks_free_lock(flock); goto out; } } @@ -7118,10 +7085,6 @@ skip: ksmbd_debug(SMB, "would have to wait for getting lock\n"); - spin_lock(&work->conn->llist_lock); - list_add_tail(&smb_lock->clist, - &work->conn->lock_list); - spin_unlock(&work->conn->llist_lock); list_add(&smb_lock->llist, &rollback_list); argv = kmalloc(sizeof(void *), GFP_KERNEL); @@ -7147,19 +7110,12 @@ skip: ksmbd_vfs_posix_lock_wait(flock); - spin_lock(&work->conn->request_lock); spin_lock(&fp->f_lock); list_del(&work->fp_entry); - work->cancel_fn = NULL; - kfree(argv); spin_unlock(&fp->f_lock); - spin_unlock(&work->conn->request_lock); if (work->state != KSMBD_WORK_ACTIVE) { list_del(&smb_lock->llist); - spin_lock(&work->conn->llist_lock); - list_del(&smb_lock->clist); - spin_unlock(&work->conn->llist_lock); locks_free_lock(flock); if (work->state == KSMBD_WORK_CANCELLED) { @@ -7171,8 +7127,7 @@ skip: work->send_no_response = 1; goto out; } - init_smb2_rsp_hdr(work); - smb2_set_err_rsp(work); + rsp->hdr.Status = STATUS_RANGE_NOT_LOCKED; kfree(smb_lock); @@ -7180,19 +7135,16 @@ skip: } list_del(&smb_lock->llist); - spin_lock(&work->conn->llist_lock); - list_del(&smb_lock->clist); - spin_unlock(&work->conn->llist_lock); - + release_async_work(work); goto retry; } else if (!rc) { + list_add(&smb_lock->llist, &rollback_list); spin_lock(&work->conn->llist_lock); list_add_tail(&smb_lock->clist, &work->conn->lock_list); list_add_tail(&smb_lock->flist, &fp->lock_list); spin_unlock(&work->conn->llist_lock); - list_add(&smb_lock->llist, &rollback_list); ksmbd_debug(SMB, "successful in taking lock\n"); } else { goto out; @@ -7207,7 +7159,10 @@ skip: ksmbd_debug(SMB, "successful in taking lock\n"); rsp->hdr.Status = STATUS_SUCCESS; rsp->Reserved = 0; - inc_rfc1001_len(work->response_buf, 4); + err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_lock_rsp)); + if (err) + goto out; + ksmbd_fd_put(work, fp); return 0; @@ -7226,7 +7181,7 @@ out: rlock->fl_start = smb_lock->start; rlock->fl_end = smb_lock->end; - rc = vfs_lock_file(filp, 0, rlock, NULL); + rc = vfs_lock_file(filp, F_SETLK, rlock, NULL); if (rc) pr_err("rollback unlock fail : %d\n", rc); @@ -7648,7 +7603,8 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id, da.attr = le32_to_cpu(fp->f_ci->m_fattr); ret = ksmbd_vfs_set_dos_attrib_xattr(user_ns, - fp->filp->f_path.dentry, &da); + &fp->filp->f_path, + &da, true); if (ret) fp->f_ci->m_fattr = old_fattr; } @@ -8003,9 +7959,9 @@ dup_ext_out: rsp->Reserved = cpu_to_le16(0); rsp->Flags = cpu_to_le32(0); rsp->Reserved2 = cpu_to_le32(0); - inc_rfc1001_len(work->response_buf, 48 + nbytes); - - return 0; + ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_ioctl_rsp) + nbytes); + if (!ret) + return ret; out: if (ret == -EACCES) @@ -8140,8 +8096,9 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) rsp->Reserved2 = 0; rsp->VolatileFid = volatile_id; rsp->PersistentFid = persistent_id; - inc_rfc1001_len(work->response_buf, 24); - return; + ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_oplock_break)); + if (!ret) + return; err_out: opinfo->op_state = OPLOCK_STATE_NONE; @@ -8273,6 +8230,11 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) le32_to_cpu(req->LeaseState)); } + if (ret < 0) { + rsp->hdr.Status = err; + goto err_out; + } + lease_state = lease->state; opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); @@ -8280,22 +8242,17 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) wake_up_interruptible_all(&opinfo->oplock_brk); opinfo_put(opinfo); - if (ret < 0) { - rsp->hdr.Status = err; - goto err_out; - } - rsp->StructureSize = cpu_to_le16(36); rsp->Reserved = 0; rsp->Flags = 0; memcpy(rsp->LeaseKey, req->LeaseKey, 16); rsp->LeaseState = lease_state; rsp->LeaseDuration = 0; - inc_rfc1001_len(work->response_buf, 36); - return; + ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_lease_ack)); + if (!ret) + return; err_out: - opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); atomic_dec(&opinfo->breaking_cnt); wake_up_interruptible_all(&opinfo->oplock_brk); @@ -8430,43 +8387,19 @@ int smb2_check_sign_req(struct ksmbd_work *work) void smb2_set_sign_rsp(struct ksmbd_work *work) { struct smb2_hdr *hdr; - struct smb2_hdr *req_hdr; char signature[SMB2_HMACSHA256_SIZE]; - struct kvec iov[2]; - size_t len; + struct kvec *iov; int n_vec = 1; - hdr = smb2_get_msg(work->response_buf); - if (work->next_smb2_rsp_hdr_off) - hdr = ksmbd_resp_buf_next(work); - - req_hdr = ksmbd_req_buf_next(work); - - if (!work->next_smb2_rsp_hdr_off) { - len = get_rfc1002_len(work->response_buf); - if (req_hdr->NextCommand) - len = ALIGN(len, 8); - } else { - len = get_rfc1002_len(work->response_buf) - - work->next_smb2_rsp_hdr_off; - len = ALIGN(len, 8); - } - - if (req_hdr->NextCommand) - hdr->NextCommand = cpu_to_le32(len); - + hdr = ksmbd_resp_buf_curr(work); hdr->Flags |= SMB2_FLAGS_SIGNED; memset(hdr->Signature, 0, SMB2_SIGNATURE_SIZE); - iov[0].iov_base = (char *)&hdr->ProtocolId; - iov[0].iov_len = len; - - if (work->aux_payload_sz) { - iov[0].iov_len -= work->aux_payload_sz; - - iov[1].iov_base = work->aux_payload_buf; - iov[1].iov_len = work->aux_payload_sz; + if (hdr->Command == SMB2_READ) { + iov = &work->iov[work->iov_idx - 1]; n_vec++; + } else { + iov = &work->iov[work->iov_idx]; } if (!ksmbd_sign_smb2_pdu(work->conn, work->sess->sess_key, iov, n_vec, @@ -8542,29 +8475,14 @@ int smb3_check_sign_req(struct ksmbd_work *work) void smb3_set_sign_rsp(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_hdr *req_hdr, *hdr; + struct smb2_hdr *hdr; struct channel *chann; char signature[SMB2_CMACAES_SIZE]; - struct kvec iov[2]; + struct kvec *iov; int n_vec = 1; - size_t len; char *signing_key; - hdr = smb2_get_msg(work->response_buf); - if (work->next_smb2_rsp_hdr_off) - hdr = ksmbd_resp_buf_next(work); - - req_hdr = ksmbd_req_buf_next(work); - - if (!work->next_smb2_rsp_hdr_off) { - len = get_rfc1002_len(work->response_buf); - if (req_hdr->NextCommand) - len = ALIGN(len, 8); - } else { - len = get_rfc1002_len(work->response_buf) - - work->next_smb2_rsp_hdr_off; - len = ALIGN(len, 8); - } + hdr = ksmbd_resp_buf_curr(work); if (conn->binding == false && le16_to_cpu(hdr->Command) == SMB2_SESSION_SETUP_HE) { @@ -8580,21 +8498,18 @@ void smb3_set_sign_rsp(struct ksmbd_work *work) if (!signing_key) return; - if (req_hdr->NextCommand) - hdr->NextCommand = cpu_to_le32(len); - hdr->Flags |= SMB2_FLAGS_SIGNED; memset(hdr->Signature, 0, SMB2_SIGNATURE_SIZE); - iov[0].iov_base = (char *)&hdr->ProtocolId; - iov[0].iov_len = len; - if (work->aux_payload_sz) { - iov[0].iov_len -= work->aux_payload_sz; - iov[1].iov_base = work->aux_payload_buf; - iov[1].iov_len = work->aux_payload_sz; + + if (hdr->Command == SMB2_READ) { + iov = &work->iov[work->iov_idx - 1]; n_vec++; + } else { + iov = &work->iov[work->iov_idx]; } - if (!ksmbd_sign_smb3_pdu(conn, signing_key, iov, n_vec, signature)) + if (!ksmbd_sign_smb3_pdu(conn, signing_key, iov, n_vec, + signature)) memcpy(hdr->Signature, signature, SMB2_SIGNATURE_SIZE); } @@ -8661,45 +8576,22 @@ static void fill_transform_hdr(void *tr_buf, char *old_buf, __le16 cipher_type) int smb3_encrypt_resp(struct ksmbd_work *work) { - char *buf = work->response_buf; - struct kvec iov[3]; + struct kvec *iov = work->iov; int rc = -ENOMEM; - int buf_size = 0, rq_nvec = 2 + (work->aux_payload_sz ? 1 : 0); + void *tr_buf; - if (ARRAY_SIZE(iov) < rq_nvec) - return -ENOMEM; - - work->tr_buf = kzalloc(sizeof(struct smb2_transform_hdr) + 4, GFP_KERNEL); - if (!work->tr_buf) + tr_buf = kzalloc(sizeof(struct smb2_transform_hdr) + 4, GFP_KERNEL); + if (!tr_buf) return rc; /* fill transform header */ - fill_transform_hdr(work->tr_buf, buf, work->conn->cipher_type); + fill_transform_hdr(tr_buf, work->response_buf, work->conn->cipher_type); - iov[0].iov_base = work->tr_buf; + iov[0].iov_base = tr_buf; iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4; - buf_size += iov[0].iov_len - 4; - - iov[1].iov_base = buf + 4; - iov[1].iov_len = get_rfc1002_len(buf); - if (work->aux_payload_sz) { - iov[1].iov_len = work->resp_hdr_sz - 4; + work->tr_buf = tr_buf; - iov[2].iov_base = work->aux_payload_buf; - iov[2].iov_len = work->aux_payload_sz; - buf_size += iov[2].iov_len; - } - buf_size += iov[1].iov_len; - work->resp_hdr_sz = iov[1].iov_len; - - rc = ksmbd_crypt_message(work, iov, rq_nvec, 1); - if (rc) - return rc; - - memmove(buf, iov[1].iov_base, iov[1].iov_len); - *(__be32 *)work->tr_buf = cpu_to_be32(buf_size); - - return rc; + return ksmbd_crypt_message(work, iov, work->iov_idx + 1, 1); } bool smb3_is_transform_hdr(void *buf) diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 665a83737854..59e3de95961c 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -446,7 +446,7 @@ struct smb2_posix_info { /* SidBuffer contain two sids (UNIX user sid(16), UNIX group sid(16)) */ u8 SidBuffer[32]; __le32 name_len; - u8 name[1]; + u8 name[]; /* * var sized owner SID * var sized group SID @@ -488,6 +488,7 @@ int find_matching_smb2_dialect(int start_index, __le16 *cli_dialects, struct file_lock *smb_flock_init(struct file *f); int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg); +void release_async_work(struct ksmbd_work *work); void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status); struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn *conn); diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index adc41b57b84c..e90a1e8c1951 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -158,8 +158,12 @@ int ksmbd_verify_smb_message(struct ksmbd_work *work) */ bool ksmbd_smb_request(struct ksmbd_conn *conn) { - __le32 *proto = (__le32 *)smb2_get_msg(conn->request_buf); + __le32 *proto; + if (conn->request_buf[0] != 0) + return false; + + proto = (__le32 *)smb2_get_msg(conn->request_buf); if (*proto == SMB2_COMPRESSION_TRANSFORM_ID) { pr_err_ratelimited("smb2 compression not support yet"); return false; @@ -266,7 +270,7 @@ static int ksmbd_negotiate_smb_dialect(void *buf) if (smb2_neg_size > smb_buf_length) goto err_out; - if (smb2_neg_size + le16_to_cpu(req->DialectCount) * sizeof(__le16) > + if (struct_size(req, Dialects, le16_to_cpu(req->DialectCount)) > smb_buf_length) goto err_out; @@ -319,12 +323,6 @@ static int init_smb1_rsp_hdr(struct ksmbd_work *work) struct smb_hdr *rsp_hdr = (struct smb_hdr *)work->response_buf; struct smb_hdr *rcv_hdr = (struct smb_hdr *)work->request_buf; - /* - * Remove 4 byte direct TCP header. - */ - *(__be32 *)work->response_buf = - cpu_to_be32(sizeof(struct smb_hdr) - 4); - rsp_hdr->Command = SMB_COM_NEGOTIATE; *(__le32 *)rsp_hdr->Protocol = SMB1_PROTO_NUMBER; rsp_hdr->Flags = SMBFLG_RESPONSE; @@ -359,8 +357,8 @@ static int smb1_check_user_session(struct ksmbd_work *work) */ static int smb1_allocate_rsp_buf(struct ksmbd_work *work) { - work->response_buf = kmalloc(MAX_CIFS_SMALL_BUFFER_SIZE, - GFP_KERNEL | __GFP_ZERO); + work->response_buf = kzalloc(MAX_CIFS_SMALL_BUFFER_SIZE, + GFP_KERNEL); work->response_sz = MAX_CIFS_SMALL_BUFFER_SIZE; if (!work->response_buf) { @@ -571,10 +569,11 @@ static int smb_handle_negotiate(struct ksmbd_work *work) ksmbd_debug(SMB, "Unsupported SMB1 protocol\n"); - /* Add 2 byte bcc and 2 byte DialectIndex. */ - inc_rfc1001_len(work->response_buf, 4); - neg_rsp->hdr.Status.CifsError = STATUS_SUCCESS; + if (ksmbd_iov_pin_rsp(work, (void *)neg_rsp, + sizeof(struct smb_negotiate_rsp) - 4)) + return -ENOMEM; + neg_rsp->hdr.Status.CifsError = STATUS_SUCCESS; neg_rsp->hdr.WordCount = 1; neg_rsp->DialectIndex = cpu_to_le16(work->conn->dialect); neg_rsp->ByteCount = 0; diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h index 1cbb492cdefe..f1092519c0c2 100644 --- a/fs/smb/server/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -200,7 +200,7 @@ struct smb_hdr { struct smb_negotiate_req { struct smb_hdr hdr; /* wct = 0 */ __le16 ByteCount; - unsigned char DialectsArray[1]; + unsigned char DialectsArray[]; } __packed; struct smb_negotiate_rsp { @@ -263,14 +263,14 @@ struct file_directory_info { __le64 AllocationSize; __le32 ExtFileAttributes; __le32 FileNameLength; - char FileName[1]; + char FileName[]; } __packed; /* level 0x101 FF resp data */ struct file_names_info { __le32 NextEntryOffset; __u32 FileIndex; __le32 FileNameLength; - char FileName[1]; + char FileName[]; } __packed; /* level 0xc FF resp data */ struct file_full_directory_info { @@ -285,7 +285,7 @@ struct file_full_directory_info { __le32 ExtFileAttributes; __le32 FileNameLength; __le32 EaSize; - char FileName[1]; + char FileName[]; } __packed; /* level 0x102 FF resp */ struct file_both_directory_info { @@ -303,7 +303,7 @@ struct file_both_directory_info { __u8 ShortNameLength; __u8 Reserved; __u8 ShortName[24]; - char FileName[1]; + char FileName[]; } __packed; /* level 0x104 FFrsp data */ struct file_id_both_directory_info { @@ -323,7 +323,7 @@ struct file_id_both_directory_info { __u8 ShortName[24]; __le16 Reserved2; __le64 UniqueId; - char FileName[1]; + char FileName[]; } __packed; struct file_id_full_dir_info { @@ -340,7 +340,7 @@ struct file_id_full_dir_info { __le32 EaSize; /* EA size */ __le32 Reserved; __le64 UniqueId; /* inode num - le since Samba puts ino in low 32 bit*/ - char FileName[1]; + char FileName[]; } __packed; /* level 0x105 FF rsp data */ struct smb_version_values { diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index c24df86eb112..6fd3560028d3 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -97,7 +97,7 @@ int compare_sids(const struct smb_sid *ctsid, const struct smb_sid *cwsid) /* compare all of the subauth values if any */ num_sat = ctsid->num_subauth; num_saw = cwsid->num_subauth; - num_subauth = num_sat < num_saw ? num_sat : num_saw; + num_subauth = min(num_sat, num_saw); if (num_subauth) { for (i = 0; i < num_subauth; ++i) { if (ctsid->sub_auth[i] != cwsid->sub_auth[i]) { @@ -401,10 +401,6 @@ static void parse_dacl(struct user_namespace *user_ns, if (num_aces > ULONG_MAX / sizeof(struct smb_ace *)) return; - ppace = kmalloc_array(num_aces, sizeof(struct smb_ace *), GFP_KERNEL); - if (!ppace) - return; - ret = init_acl_state(&acl_state, num_aces); if (ret) return; @@ -414,6 +410,13 @@ static void parse_dacl(struct user_namespace *user_ns, return; } + ppace = kmalloc_array(num_aces, sizeof(struct smb_ace *), GFP_KERNEL); + if (!ppace) { + free_acl_state(&default_acl_state); + free_acl_state(&acl_state); + return; + } + /* * reset rwx permissions for user/group/other. * Also, if num_aces is 0 i.e. DACL has no ACEs, @@ -1185,8 +1188,7 @@ pass: pntsd_size += sizeof(struct smb_acl) + nt_size; } - ksmbd_vfs_set_sd_xattr(conn, user_ns, - path->dentry, pntsd, pntsd_size); + ksmbd_vfs_set_sd_xattr(conn, user_ns, path, pntsd, pntsd_size, false); kfree(pntsd); } @@ -1313,7 +1315,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, if (IS_ENABLED(CONFIG_FS_POSIX_ACL)) { posix_acls = get_acl(d_inode(path->dentry), ACL_TYPE_ACCESS); - if (posix_acls && !found) { + if (!IS_ERR_OR_NULL(posix_acls) && !found) { unsigned int id = -1; pa_entry = posix_acls->a_entries; @@ -1337,7 +1339,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, } } } - if (posix_acls) + if (!IS_ERR_OR_NULL(posix_acls)) posix_acl_release(posix_acls); } @@ -1378,7 +1380,7 @@ err_out: int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, const struct path *path, struct smb_ntsd *pntsd, int ntsd_len, - bool type_check) + bool type_check, bool get_write) { int rc; struct smb_fattr fattr = {{0}}; @@ -1406,7 +1408,7 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, newattrs.ia_valid |= ATTR_MODE; newattrs.ia_mode = (inode->i_mode & ~0777) | (fattr.cf_mode & 0777); - ksmbd_vfs_remove_acl_xattrs(user_ns, path->dentry); + ksmbd_vfs_remove_acl_xattrs(user_ns, path); /* Update posix acls */ if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && fattr.cf_dacls) { rc = set_posix_acl(user_ns, inode, @@ -1437,15 +1439,14 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, if (test_share_config_flag(tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) { /* Update WinACL in xattr */ - ksmbd_vfs_remove_sd_xattrs(user_ns, path->dentry); - ksmbd_vfs_set_sd_xattr(conn, user_ns, - path->dentry, pntsd, ntsd_len); + ksmbd_vfs_remove_sd_xattrs(user_ns, path); + ksmbd_vfs_set_sd_xattr(conn, user_ns, path, pntsd, ntsd_len, + get_write); } out: posix_acl_release(fattr.cf_acls); posix_acl_release(fattr.cf_dacls); - mark_inode_dirty(inode); return rc; } diff --git a/fs/smb/server/smbacl.h b/fs/smb/server/smbacl.h index 618f2e0236b3..9651a2551888 100644 --- a/fs/smb/server/smbacl.h +++ b/fs/smb/server/smbacl.h @@ -207,7 +207,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, __le32 *pdaccess, int uid); int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, const struct path *path, struct smb_ntsd *pntsd, int ntsd_len, - bool type_check); + bool type_check, bool get_write); void id_to_sid(unsigned int cid, uint sidtype, struct smb_sid *ssid); void ksmbd_init_domain(u32 *sub_auth); diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 40c721f9227e..f29bb03f0dc4 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -74,7 +74,7 @@ static int handle_unsupported_event(struct sk_buff *skb, struct genl_info *info) static int handle_generic_event(struct sk_buff *skb, struct genl_info *info); static int ksmbd_ipc_heartbeat_request(void); -static const struct nla_policy ksmbd_nl_policy[KSMBD_EVENT_MAX] = { +static const struct nla_policy ksmbd_nl_policy[KSMBD_EVENT_MAX + 1] = { [KSMBD_EVENT_UNSPEC] = { .len = 0, }, @@ -229,7 +229,7 @@ static struct ksmbd_ipc_msg *ipc_msg_alloc(size_t sz) struct ksmbd_ipc_msg *msg; size_t msg_sz = sz + sizeof(struct ksmbd_ipc_msg); - msg = kvmalloc(msg_sz, GFP_KERNEL | __GFP_ZERO); + msg = kvzalloc(msg_sz, GFP_KERNEL); if (msg) msg->sz = sz; return msg; @@ -268,7 +268,7 @@ static int handle_response(int type, void *payload, size_t sz) entry->type + 1, type); } - entry->response = kvmalloc(sz, GFP_KERNEL | __GFP_ZERO); + entry->response = kvzalloc(sz, GFP_KERNEL); if (!entry->response) { ret = -ENOMEM; break; @@ -403,7 +403,7 @@ static int handle_generic_event(struct sk_buff *skb, struct genl_info *info) return -EPERM; #endif - if (type >= KSMBD_EVENT_MAX) { + if (type > KSMBD_EVENT_MAX) { WARN_ON(1); return -EINVAL; } diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 7578200f63b1..8faa25c6e129 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -1241,14 +1241,12 @@ static int smb_direct_writev(struct ksmbd_transport *t, //FIXME: skip RFC1002 header.. buflen -= 4; - iov[0].iov_base += 4; - iov[0].iov_len -= 4; remaining_data_length = buflen; ksmbd_debug(RDMA, "Sending smb (RDMA): smb_len=%u\n", buflen); smb_direct_send_ctx_init(st, &send_ctx, need_invalidate, remote_key); - start = i = 0; + start = i = 1; buflen = 0; while (true) { buflen += iov[i].iov_len; @@ -2041,6 +2039,7 @@ static bool rdma_frwr_is_supported(struct ib_device_attr *attrs) static int smb_direct_handle_connect_request(struct rdma_cm_id *new_cm_id) { struct smb_direct_transport *t; + struct task_struct *handler; int ret; if (!rdma_frwr_is_supported(&new_cm_id->device->attrs)) { @@ -2058,11 +2057,11 @@ static int smb_direct_handle_connect_request(struct rdma_cm_id *new_cm_id) if (ret) goto out_err; - KSMBD_TRANS(t)->handler = kthread_run(ksmbd_conn_handler_loop, - KSMBD_TRANS(t)->conn, "ksmbd:r%u", - smb_direct_port); - if (IS_ERR(KSMBD_TRANS(t)->handler)) { - ret = PTR_ERR(KSMBD_TRANS(t)->handler); + handler = kthread_run(ksmbd_conn_handler_loop, + KSMBD_TRANS(t)->conn, "ksmbd:r%u", + smb_direct_port); + if (IS_ERR(handler)) { + ret = PTR_ERR(handler); pr_err("Can't start thread\n"); goto out_err; } @@ -2142,8 +2141,7 @@ static int smb_direct_ib_client_add(struct ib_device *ib_dev) if (ib_dev->node_type != RDMA_NODE_IB_CA) smb_direct_port = SMB_DIRECT_PORT_IWARP; - if (!ib_dev->ops.get_netdev || - !rdma_frwr_is_supported(&ib_dev->attrs)) + if (!rdma_frwr_is_supported(&ib_dev->attrs)) return 0; smb_dev = kzalloc(sizeof(*smb_dev), GFP_KERNEL); @@ -2243,17 +2241,38 @@ bool ksmbd_rdma_capable_netdev(struct net_device *netdev) for (i = 0; i < smb_dev->ib_dev->phys_port_cnt; i++) { struct net_device *ndev; - ndev = smb_dev->ib_dev->ops.get_netdev(smb_dev->ib_dev, - i + 1); - if (!ndev) - continue; + if (smb_dev->ib_dev->ops.get_netdev) { + ndev = smb_dev->ib_dev->ops.get_netdev( + smb_dev->ib_dev, i + 1); + if (!ndev) + continue; - if (ndev == netdev) { + if (ndev == netdev) { + dev_put(ndev); + rdma_capable = true; + goto out; + } dev_put(ndev); - rdma_capable = true; - goto out; + /* if ib_dev does not implement ops.get_netdev + * check for matching infiniband GUID in hw_addr + */ + } else if (netdev->type == ARPHRD_INFINIBAND) { + struct netdev_hw_addr *ha; + union ib_gid gid; + u32 port_num; + int ret; + + netdev_hw_addr_list_for_each( + ha, &netdev->dev_addrs) { + memcpy(&gid, ha->addr + 4, sizeof(gid)); + ret = ib_find_gid(smb_dev->ib_dev, &gid, + &port_num, NULL); + if (!ret) { + rdma_capable = true; + goto out; + } + } } - dev_put(ndev); } } out: diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index eff7a1d793f0..9d4222154dcc 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -185,6 +185,7 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk) struct sockaddr *csin; int rc = 0; struct tcp_transport *t; + struct task_struct *handler; t = alloc_transport(client_sk); if (!t) { @@ -199,13 +200,13 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk) goto out_error; } - KSMBD_TRANS(t)->handler = kthread_run(ksmbd_conn_handler_loop, - KSMBD_TRANS(t)->conn, - "ksmbd:%u", - ksmbd_tcp_get_port(csin)); - if (IS_ERR(KSMBD_TRANS(t)->handler)) { + handler = kthread_run(ksmbd_conn_handler_loop, + KSMBD_TRANS(t)->conn, + "ksmbd:%u", + ksmbd_tcp_get_port(csin)); + if (IS_ERR(handler)) { pr_err("cannot start conn thread\n"); - rc = PTR_ERR(KSMBD_TRANS(t)->handler); + rc = PTR_ERR(handler); free_transport(t); } return rc; diff --git a/fs/smb/server/unicode.c b/fs/smb/server/unicode.c index a0db699ddafd..33fc6d45c0f3 100644 --- a/fs/smb/server/unicode.c +++ b/fs/smb/server/unicode.c @@ -15,45 +15,9 @@ #include "smb_common.h" /* - * smb_utf16_bytes() - how long will a string be after conversion? - * @from: pointer to input string - * @maxbytes: don't go past this many bytes of input string - * @codepage: destination codepage - * - * Walk a utf16le string and return the number of bytes that the string will - * be after being converted to the given charset, not including any null - * termination required. Don't walk past maxbytes in the source buffer. - * - * Return: string length after conversion - */ -static int smb_utf16_bytes(const __le16 *from, int maxbytes, - const struct nls_table *codepage) -{ - int i; - int charlen, outlen = 0; - int maxwords = maxbytes / 2; - char tmp[NLS_MAX_CHARSET_SIZE]; - __u16 ftmp; - - for (i = 0; i < maxwords; i++) { - ftmp = get_unaligned_le16(&from[i]); - if (ftmp == 0) - break; - - charlen = codepage->uni2char(ftmp, tmp, NLS_MAX_CHARSET_SIZE); - if (charlen > 0) - outlen += charlen; - else - outlen++; - } - - return outlen; -} - -/* * cifs_mapchar() - convert a host-endian char to proper char in codepage * @target: where converted character should be copied - * @src_char: 2 byte host-endian source character + * @from: host-endian source string * @cp: codepage to which character should be converted * @mapchar: should character be mapped according to mapchars mount option? * @@ -64,10 +28,13 @@ static int smb_utf16_bytes(const __le16 *from, int maxbytes, * Return: string length after conversion */ static int -cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp, +cifs_mapchar(char *target, const __u16 *from, const struct nls_table *cp, bool mapchar) { int len = 1; + __u16 src_char; + + src_char = *from; if (!mapchar) goto cp_convert; @@ -105,30 +72,66 @@ out: cp_convert: len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE); - if (len <= 0) { - *target = '?'; - len = 1; - } + if (len <= 0) + goto surrogate_pair; + + goto out; + +surrogate_pair: + /* convert SURROGATE_PAIR and IVS */ + if (strcmp(cp->charset, "utf8")) + goto unknown; + len = utf16s_to_utf8s(from, 3, UTF16_LITTLE_ENDIAN, target, 6); + if (len <= 0) + goto unknown; + return len; +unknown: + *target = '?'; + len = 1; goto out; } /* - * is_char_allowed() - check for valid character - * @ch: input character to be checked + * smb_utf16_bytes() - compute converted string length + * @from: pointer to input string + * @maxbytes: input string length + * @codepage: destination codepage + * + * Walk a utf16le string and return the number of bytes that the string will + * be after being converted to the given charset, not including any null + * termination required. Don't walk past maxbytes in the source buffer. * - * Return: 1 if char is allowed, otherwise 0 + * Return: string length after conversion */ -static inline int is_char_allowed(char *ch) +static int smb_utf16_bytes(const __le16 *from, int maxbytes, + const struct nls_table *codepage) { - /* check for control chars, wildcards etc. */ - if (!(*ch & 0x80) && - (*ch <= 0x1f || - *ch == '?' || *ch == '"' || *ch == '<' || - *ch == '>' || *ch == '|')) - return 0; - - return 1; + int i, j; + int charlen, outlen = 0; + int maxwords = maxbytes / 2; + char tmp[NLS_MAX_CHARSET_SIZE]; + __u16 ftmp[3]; + + for (i = 0; i < maxwords; i++) { + ftmp[0] = get_unaligned_le16(&from[i]); + if (ftmp[0] == 0) + break; + for (j = 1; j <= 2; j++) { + if (i + j < maxwords) + ftmp[j] = get_unaligned_le16(&from[i + j]); + else + ftmp[j] = 0; + } + + charlen = cifs_mapchar(tmp, ftmp, codepage, 0); + if (charlen > 0) + outlen += charlen; + else + outlen++; + } + + return outlen; } /* @@ -158,12 +161,12 @@ static inline int is_char_allowed(char *ch) static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen, const struct nls_table *codepage, bool mapchar) { - int i, charlen, safelen; + int i, j, charlen, safelen; int outlen = 0; int nullsize = nls_nullsize(codepage); int fromwords = fromlen / 2; char tmp[NLS_MAX_CHARSET_SIZE]; - __u16 ftmp; + __u16 ftmp[3]; /* ftmp[3] = 3array x 2bytes = 6bytes UTF-16 */ /* * because the chars can be of varying widths, we need to take care @@ -174,9 +177,15 @@ static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen, safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize); for (i = 0; i < fromwords; i++) { - ftmp = get_unaligned_le16(&from[i]); - if (ftmp == 0) + ftmp[0] = get_unaligned_le16(&from[i]); + if (ftmp[0] == 0) break; + for (j = 1; j <= 2; j++) { + if (i + j < fromwords) + ftmp[j] = get_unaligned_le16(&from[i + j]); + else + ftmp[j] = 0; + } /* * check to see if converting this character might make the @@ -191,6 +200,19 @@ static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen, /* put converted char into 'to' buffer */ charlen = cifs_mapchar(&to[outlen], ftmp, codepage, mapchar); outlen += charlen; + + /* + * charlen (=bytes of UTF-8 for 1 character) + * 4bytes UTF-8(surrogate pair) is charlen=4 + * (4bytes UTF-16 code) + * 7-8bytes UTF-8(IVS) is charlen=3+4 or 4+4 + * (2 UTF-8 pairs divided to 2 UTF-16 pairs) + */ + if (charlen == 4) + i++; + else if (charlen >= 5) + /* 5-6bytes UTF-8 */ + i += 2; } /* properly null-terminate string */ @@ -325,6 +347,9 @@ int smbConvertToUTF16(__le16 *target, const char *source, int srclen, char src_char; __le16 dst_char; wchar_t tmp; + wchar_t wchar_to[6]; /* UTF-16 */ + int ret; + unicode_t u; if (!mapchars) return smb_strtoUTF16(target, source, srclen, cp); @@ -367,11 +392,57 @@ int smbConvertToUTF16(__le16 *target, const char *source, int srclen, * if no match, use question mark, which at least in * some cases serves as wild card */ - if (charlen < 1) { - dst_char = cpu_to_le16(0x003f); - charlen = 1; + if (charlen > 0) + goto ctoUTF16; + + /* convert SURROGATE_PAIR */ + if (strcmp(cp->charset, "utf8")) + goto unknown; + if (*(source + i) & 0x80) { + charlen = utf8_to_utf32(source + i, 6, &u); + if (charlen < 0) + goto unknown; + } else + goto unknown; + ret = utf8s_to_utf16s(source + i, charlen, + UTF16_LITTLE_ENDIAN, + wchar_to, 6); + if (ret < 0) + goto unknown; + + i += charlen; + dst_char = cpu_to_le16(*wchar_to); + if (charlen <= 3) + /* 1-3bytes UTF-8 to 2bytes UTF-16 */ + put_unaligned(dst_char, &target[j]); + else if (charlen == 4) { + /* + * 4bytes UTF-8(surrogate pair) to 4bytes UTF-16 + * 7-8bytes UTF-8(IVS) divided to 2 UTF-16 + * (charlen=3+4 or 4+4) + */ + put_unaligned(dst_char, &target[j]); + dst_char = cpu_to_le16(*(wchar_to + 1)); + j++; + put_unaligned(dst_char, &target[j]); + } else if (charlen >= 5) { + /* 5-6bytes UTF-8 to 6bytes UTF-16 */ + put_unaligned(dst_char, &target[j]); + dst_char = cpu_to_le16(*(wchar_to + 1)); + j++; + put_unaligned(dst_char, &target[j]); + dst_char = cpu_to_le16(*(wchar_to + 2)); + j++; + put_unaligned(dst_char, &target[j]); } + continue; + +unknown: + dst_char = cpu_to_le16(0x003f); + charlen = 1; } + +ctoUTF16: /* * character may take more than one byte in the source string, * but will take exactly two bytes in the target string diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 36914db8b661..fe2c80ea2e47 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -17,6 +17,7 @@ #include <linux/vmalloc.h> #include <linux/sched/xacct.h> #include <linux/crc32c.h> +#include <linux/namei.h> #include "../../internal.h" /* for vfs_path_lookup */ @@ -36,19 +37,6 @@ #include "mgmt/user_session.h" #include "mgmt/user_config.h" -static char *extract_last_component(char *path) -{ - char *p = strrchr(path, '/'); - - if (p && p[1] != '\0') { - *p = '\0'; - p++; - } else { - p = NULL; - } - return p; -} - static void ksmbd_vfs_inherit_owner(struct ksmbd_work *work, struct inode *parent_inode, struct inode *inode) @@ -62,67 +50,96 @@ static void ksmbd_vfs_inherit_owner(struct ksmbd_work *work, /** * ksmbd_vfs_lock_parent() - lock parent dentry if it is stable - * - * the parent dentry got by dget_parent or @parent could be - * unstable, we try to lock a parent inode and lookup the - * child dentry again. - * - * the reference count of @parent isn't incremented. */ -int ksmbd_vfs_lock_parent(struct user_namespace *user_ns, struct dentry *parent, - struct dentry *child) +int ksmbd_vfs_lock_parent(struct dentry *parent, struct dentry *child) { - struct dentry *dentry; - int ret = 0; - inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); - dentry = lookup_one(user_ns, child->d_name.name, parent, - child->d_name.len); - if (IS_ERR(dentry)) { - ret = PTR_ERR(dentry); - goto out_err; - } - - if (dentry != child) { - ret = -ESTALE; - dput(dentry); - goto out_err; + if (child->d_parent != parent) { + inode_unlock(d_inode(parent)); + return -ENOENT; } - dput(dentry); return 0; -out_err: - inode_unlock(d_inode(parent)); - return ret; } -int ksmbd_vfs_may_delete(struct user_namespace *user_ns, - struct dentry *dentry) +static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf, + char *pathname, unsigned int flags, + struct path *parent_path, + struct path *path) { - struct dentry *parent; - int ret; + struct qstr last; + struct filename *filename; + struct path *root_share_path = &share_conf->vfs_path; + int err, type; + struct dentry *d; + + if (pathname[0] == '\0') { + pathname = share_conf->path; + root_share_path = NULL; + } else { + flags |= LOOKUP_BENEATH; + } + + filename = getname_kernel(pathname); + if (IS_ERR(filename)) + return PTR_ERR(filename); - parent = dget_parent(dentry); - ret = ksmbd_vfs_lock_parent(user_ns, parent, dentry); - if (ret) { - dput(parent); - return ret; + err = vfs_path_parent_lookup(filename, flags, + parent_path, &last, &type, + root_share_path); + if (err) { + putname(filename); + return err; } - ret = inode_permission(user_ns, d_inode(parent), - MAY_EXEC | MAY_WRITE); + if (unlikely(type != LAST_NORM)) { + path_put(parent_path); + putname(filename); + return -ENOENT; + } - inode_unlock(d_inode(parent)); - dput(parent); - return ret; + err = mnt_want_write(parent_path->mnt); + if (err) { + path_put(parent_path); + putname(filename); + return -ENOENT; + } + + inode_lock_nested(parent_path->dentry->d_inode, I_MUTEX_PARENT); + d = lookup_one_qstr_excl(&last, parent_path->dentry, 0); + if (IS_ERR(d)) + goto err_out; + + if (d_is_negative(d)) { + dput(d); + goto err_out; + } + + path->dentry = d; + path->mnt = mntget(parent_path->mnt); + + if (test_share_config_flag(share_conf, KSMBD_SHARE_FLAG_CROSSMNT)) { + err = follow_down(path); + if (err < 0) { + path_put(path); + goto err_out; + } + } + + putname(filename); + return 0; + +err_out: + inode_unlock(d_inode(parent_path->dentry)); + mnt_drop_write(parent_path->mnt); + path_put(parent_path); + putname(filename); + return -ENOENT; } -int ksmbd_vfs_query_maximal_access(struct user_namespace *user_ns, +void ksmbd_vfs_query_maximal_access(struct user_namespace *user_ns, struct dentry *dentry, __le32 *daccess) { - struct dentry *parent; - int ret = 0; - *daccess = cpu_to_le32(FILE_READ_ATTRIBUTES | READ_CONTROL); if (!inode_permission(user_ns, d_inode(dentry), MAY_OPEN | MAY_WRITE)) @@ -137,19 +154,8 @@ int ksmbd_vfs_query_maximal_access(struct user_namespace *user_ns, if (!inode_permission(user_ns, d_inode(dentry), MAY_OPEN | MAY_EXEC)) *daccess |= FILE_EXECUTE_LE; - parent = dget_parent(dentry); - ret = ksmbd_vfs_lock_parent(user_ns, parent, dentry); - if (ret) { - dput(parent); - return ret; - } - - if (!inode_permission(user_ns, d_inode(parent), MAY_EXEC | MAY_WRITE)) + if (!inode_permission(user_ns, d_inode(dentry->d_parent), MAY_EXEC | MAY_WRITE)) *daccess |= FILE_DELETE_LE; - - inode_unlock(d_inode(parent)); - dput(parent); - return ret; } /** @@ -185,6 +191,7 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) } else { pr_err("File(%s): creation failed (err:%d)\n", name, err); } + done_path_create(&path, dentry); return err; } @@ -218,27 +225,26 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) user_ns = mnt_user_ns(path.mnt); mode |= S_IFDIR; err = vfs_mkdir(user_ns, d_inode(path.dentry), dentry, mode); - if (err) { - goto out; - } else if (d_unhashed(dentry)) { + if (!err && d_unhashed(dentry)) { struct dentry *d; d = lookup_one(user_ns, dentry->d_name.name, dentry->d_parent, dentry->d_name.len); if (IS_ERR(d)) { err = PTR_ERR(d); - goto out; + goto out_err; } if (unlikely(d_is_negative(d))) { dput(d); err = -ENOENT; - goto out; + goto out_err; } ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), d_inode(d)); dput(d); } -out: + +out_err: done_path_create(&path, dentry); if (err) pr_err("mkdir(%s): creation failed (err:%d)\n", name, err); @@ -358,15 +364,15 @@ out: * @fid: file id of open file * @count: read byte count * @pos: file pos + * @rbuf: read data buffer * * Return: number of read bytes on success, otherwise error */ int ksmbd_vfs_read(struct ksmbd_work *work, struct ksmbd_file *fp, size_t count, - loff_t *pos) + loff_t *pos, char *rbuf) { struct file *filp = fp->filp; ssize_t nbytes = 0; - char *rbuf = work->aux_payload_buf; struct inode *inode = file_inode(filp); if (S_ISDIR(inode->i_mode)) @@ -410,7 +416,8 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, { char *stream_buf = NULL, *wbuf; struct user_namespace *user_ns = file_mnt_user_ns(fp->filp); - size_t size, v_len; + size_t size; + ssize_t v_len; int err = 0; ksmbd_debug(VFS, "write stream data pos : %llu, count : %zd\n", @@ -427,14 +434,14 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, fp->stream.name, fp->stream.size, &stream_buf); - if ((int)v_len < 0) { + if (v_len < 0) { pr_err("not found stream in xattr : %zd\n", v_len); - err = (int)v_len; + err = v_len; goto out; } if (v_len < size) { - wbuf = kvmalloc(size, GFP_KERNEL | __GFP_ZERO); + wbuf = kvzalloc(size, GFP_KERNEL); if (!wbuf) { err = -ENOMEM; goto out; @@ -449,11 +456,12 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, memcpy(&stream_buf[*pos], buf, count); err = ksmbd_vfs_setxattr(user_ns, - fp->filp->f_path.dentry, + &fp->filp->f_path, fp->stream.name, (void *)stream_buf, size, - 0); + 0, + true); if (err < 0) goto out; @@ -510,6 +518,9 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp, } } + /* Reserve lease break for parent dir at closing time */ + fp->reserve_lease_break = true; + /* Do we need to break any of a levelII oplock? */ smb_break_all_levII_oplock(work, fp, 1); @@ -581,54 +592,32 @@ int ksmbd_vfs_fsync(struct ksmbd_work *work, u64 fid, u64 p_id) * * Return: 0 on success, otherwise error */ -int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name) +int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path) { struct user_namespace *user_ns; - struct path path; - struct dentry *parent; + struct dentry *parent = path->dentry->d_parent; int err; if (ksmbd_override_fsids(work)) return -ENOMEM; - err = ksmbd_vfs_kern_path(work, name, LOOKUP_NO_SYMLINKS, &path, false); - if (err) { - ksmbd_debug(VFS, "can't get %s, err %d\n", name, err); - ksmbd_revert_fsids(work); - return err; - } - - user_ns = mnt_user_ns(path.mnt); - parent = dget_parent(path.dentry); - err = ksmbd_vfs_lock_parent(user_ns, parent, path.dentry); - if (err) { - dput(parent); - path_put(&path); - ksmbd_revert_fsids(work); - return err; - } - - if (!d_inode(path.dentry)->i_nlink) { + if (!d_inode(path->dentry)->i_nlink) { err = -ENOENT; goto out_err; } - if (S_ISDIR(d_inode(path.dentry)->i_mode)) { - err = vfs_rmdir(user_ns, d_inode(parent), path.dentry); + user_ns = mnt_user_ns(path->mnt); + if (S_ISDIR(d_inode(path->dentry)->i_mode)) { + err = vfs_rmdir(user_ns, d_inode(parent), path->dentry); if (err && err != -ENOTEMPTY) - ksmbd_debug(VFS, "%s: rmdir failed, err %d\n", name, - err); + ksmbd_debug(VFS, "rmdir failed, err %d\n", err); } else { - err = vfs_unlink(user_ns, d_inode(parent), path.dentry, NULL); + err = vfs_unlink(user_ns, d_inode(parent), path->dentry, NULL); if (err) - ksmbd_debug(VFS, "%s: unlink failed, err %d\n", name, - err); + ksmbd_debug(VFS, "unlink failed, err %d\n", err); } out_err: - inode_unlock(d_inode(parent)); - dput(parent); - path_put(&path); ksmbd_revert_fsids(work); return err; } @@ -687,149 +676,120 @@ out1: return err; } -static int ksmbd_validate_entry_in_use(struct dentry *src_dent) +int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, + char *newname, int flags) { - struct dentry *dst_dent; + struct dentry *old_parent, *new_dentry, *trap; + struct dentry *old_child = old_path->dentry; + struct path new_path; + struct qstr new_last; + struct renamedata rd; + struct filename *to; + struct ksmbd_share_config *share_conf = work->tcon->share_conf; + struct ksmbd_file *parent_fp; + int new_type; + int err, lookup_flags = LOOKUP_NO_SYMLINKS; + + if (ksmbd_override_fsids(work)) + return -ENOMEM; - spin_lock(&src_dent->d_lock); - list_for_each_entry(dst_dent, &src_dent->d_subdirs, d_child) { - struct ksmbd_file *child_fp; + to = getname_kernel(newname); + if (IS_ERR(to)) { + err = PTR_ERR(to); + goto revert_fsids; + } - if (d_really_is_negative(dst_dent)) - continue; +retry: + err = vfs_path_parent_lookup(to, lookup_flags | LOOKUP_BENEATH, + &new_path, &new_last, &new_type, + &share_conf->vfs_path); + if (err) + goto out1; - child_fp = ksmbd_lookup_fd_inode(d_inode(dst_dent)); - if (child_fp) { - spin_unlock(&src_dent->d_lock); - ksmbd_debug(VFS, "Forbid rename, sub file/dir is in use\n"); - return -EACCES; - } + if (old_path->mnt != new_path.mnt) { + err = -EXDEV; + goto out2; } - spin_unlock(&src_dent->d_lock); - return 0; -} + err = mnt_want_write(old_path->mnt); + if (err) + goto out2; -static int __ksmbd_vfs_rename(struct ksmbd_work *work, - struct user_namespace *src_user_ns, - struct dentry *src_dent_parent, - struct dentry *src_dent, - struct user_namespace *dst_user_ns, - struct dentry *dst_dent_parent, - struct dentry *trap_dent, - char *dst_name) -{ - struct dentry *dst_dent; - int err; + trap = lock_rename_child(old_child, new_path.dentry); - if (!work->tcon->posix_extensions) { - err = ksmbd_validate_entry_in_use(src_dent); - if (err) - return err; + old_parent = dget(old_child->d_parent); + if (d_unhashed(old_child)) { + err = -EINVAL; + goto out3; } - if (d_really_is_negative(src_dent_parent)) - return -ENOENT; - if (d_really_is_negative(dst_dent_parent)) - return -ENOENT; - if (d_really_is_negative(src_dent)) - return -ENOENT; - if (src_dent == trap_dent) - return -EINVAL; - - if (ksmbd_override_fsids(work)) - return -ENOMEM; + parent_fp = ksmbd_lookup_fd_inode(old_child->d_parent); + if (parent_fp) { + if (parent_fp->daccess & FILE_DELETE_LE) { + pr_err("parent dir is opened with delete access\n"); + err = -ESHARE; + ksmbd_fd_put(work, parent_fp); + goto out3; + } + ksmbd_fd_put(work, parent_fp); + } - dst_dent = lookup_one(dst_user_ns, dst_name, dst_dent_parent, - strlen(dst_name)); - err = PTR_ERR(dst_dent); - if (IS_ERR(dst_dent)) { - pr_err("lookup failed %s [%d]\n", dst_name, err); - goto out; + new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry, + lookup_flags | LOOKUP_RENAME_TARGET); + if (IS_ERR(new_dentry)) { + err = PTR_ERR(new_dentry); + goto out3; } - err = -ENOTEMPTY; - if (dst_dent != trap_dent && !d_really_is_positive(dst_dent)) { - struct renamedata rd = { - .old_mnt_userns = src_user_ns, - .old_dir = d_inode(src_dent_parent), - .old_dentry = src_dent, - .new_mnt_userns = dst_user_ns, - .new_dir = d_inode(dst_dent_parent), - .new_dentry = dst_dent, - }; - err = vfs_rename(&rd); + if (d_is_symlink(new_dentry)) { + err = -EACCES; + goto out4; } - if (err) - pr_err("vfs_rename failed err %d\n", err); - if (dst_dent) - dput(dst_dent); -out: - ksmbd_revert_fsids(work); - return err; -} -int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, - char *newname) -{ - struct user_namespace *user_ns; - struct path dst_path; - struct dentry *src_dent_parent, *dst_dent_parent; - struct dentry *src_dent, *trap_dent, *src_child; - char *dst_name; - int err; + if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) { + err = -EEXIST; + goto out4; + } - dst_name = extract_last_component(newname); - if (!dst_name) { - dst_name = newname; - newname = ""; + if (old_child == trap) { + err = -EINVAL; + goto out4; } - src_dent_parent = dget_parent(fp->filp->f_path.dentry); - src_dent = fp->filp->f_path.dentry; + if (new_dentry == trap) { + err = -ENOTEMPTY; + goto out4; + } + + rd.old_mnt_userns = mnt_user_ns(old_path->mnt), + rd.old_dir = d_inode(old_parent), + rd.old_dentry = old_child, + rd.new_mnt_userns = mnt_user_ns(new_path.mnt), + rd.new_dir = new_path.dentry->d_inode, + rd.new_dentry = new_dentry, + rd.flags = flags, + rd.delegated_inode = NULL, + err = vfs_rename(&rd); + if (err) + ksmbd_debug(VFS, "vfs_rename failed err %d\n", err); - err = ksmbd_vfs_kern_path(work, newname, - LOOKUP_NO_SYMLINKS | LOOKUP_DIRECTORY, - &dst_path, false); - if (err) { - ksmbd_debug(VFS, "Cannot get path for %s [%d]\n", newname, err); - goto out; +out4: + dput(new_dentry); +out3: + dput(old_parent); + unlock_rename(old_parent, new_path.dentry); + mnt_drop_write(old_path->mnt); +out2: + path_put(&new_path); + + if (retry_estale(err, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; } - dst_dent_parent = dst_path.dentry; - - trap_dent = lock_rename(src_dent_parent, dst_dent_parent); - dget(src_dent); - dget(dst_dent_parent); - user_ns = file_mnt_user_ns(fp->filp); - src_child = lookup_one(user_ns, src_dent->d_name.name, src_dent_parent, - src_dent->d_name.len); - if (IS_ERR(src_child)) { - err = PTR_ERR(src_child); - goto out_lock; - } - - if (src_child != src_dent) { - err = -ESTALE; - dput(src_child); - goto out_lock; - } - dput(src_child); - - err = __ksmbd_vfs_rename(work, - user_ns, - src_dent_parent, - src_dent, - mnt_user_ns(dst_path.mnt), - dst_dent_parent, - trap_dent, - dst_name); -out_lock: - dput(src_dent); - dput(dst_dent_parent); - unlock_rename(src_dent_parent, dst_dent_parent); - path_put(&dst_path); -out: - dput(src_dent_parent); +out1: + putname(to); +revert_fsids: + ksmbd_revert_fsids(work); return err; } @@ -892,7 +852,7 @@ ssize_t ksmbd_vfs_listxattr(struct dentry *dentry, char **list) if (size <= 0) return size; - vlist = kvmalloc(size, GFP_KERNEL | __GFP_ZERO); + vlist = kvzalloc(size, GFP_KERNEL); if (!vlist) return -ENOMEM; @@ -950,28 +910,38 @@ ssize_t ksmbd_vfs_getxattr(struct user_namespace *user_ns, /** * ksmbd_vfs_setxattr() - vfs helper for smb set extended attributes value * @user_ns: user namespace - * @dentry: dentry to set XATTR at - * @name: xattr name for setxattr - * @value: xattr value to set - * @size: size of xattr value + * @path: path of dentry to set XATTR at + * @attr_name: xattr name for setxattr + * @attr_value: xattr value to set + * @attr_size: size of xattr value * @flags: destination buffer length + * @get_write: get write access to a mount * * Return: 0 on success, otherwise error */ int ksmbd_vfs_setxattr(struct user_namespace *user_ns, - struct dentry *dentry, const char *attr_name, - void *attr_value, size_t attr_size, int flags) + const struct path *path, const char *attr_name, + void *attr_value, size_t attr_size, int flags, + bool get_write) { int err; + if (get_write == true) { + err = mnt_want_write(path->mnt); + if (err) + return err; + } + err = vfs_setxattr(user_ns, - dentry, + path->dentry, attr_name, attr_value, attr_size, flags); if (err) ksmbd_debug(VFS, "setxattr failed, err %d\n", err); + if (get_write == true) + mnt_drop_write(path->mnt); return err; } @@ -1075,19 +1045,34 @@ int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, } int ksmbd_vfs_remove_xattr(struct user_namespace *user_ns, - struct dentry *dentry, char *attr_name) + const struct path *path, char *attr_name) { - return vfs_removexattr(user_ns, dentry, attr_name); + int err; + + err = mnt_want_write(path->mnt); + if (err) + return err; + + err = vfs_removexattr(user_ns, path->dentry, attr_name); + mnt_drop_write(path->mnt); + + return err; } -int ksmbd_vfs_unlink(struct user_namespace *user_ns, - struct dentry *dir, struct dentry *dentry) +int ksmbd_vfs_unlink(struct file *filp) { int err = 0; + struct dentry *dir, *dentry = filp->f_path.dentry; + struct user_namespace *user_ns = file_mnt_user_ns(filp); - err = ksmbd_vfs_lock_parent(user_ns, dir, dentry); + err = mnt_want_write(filp->f_path.mnt); if (err) return err; + + dir = dget_parent(dentry); + err = ksmbd_vfs_lock_parent(dir, dentry); + if (err) + goto out; dget(dentry); if (S_ISDIR(d_inode(dentry)->i_mode)) @@ -1099,6 +1084,9 @@ int ksmbd_vfs_unlink(struct user_namespace *user_ns, inode_unlock(d_inode(dir)); if (err) ksmbd_debug(VFS, "failed to delete, err %d\n", err); +out: + dput(dir); + mnt_drop_write(filp->f_path.mnt); return err; } @@ -1201,32 +1189,29 @@ static int ksmbd_vfs_lookup_in_dir(const struct path *dir, char *name, } /** - * ksmbd_vfs_kern_path() - lookup a file and get path info - * @name: file path that is relative to share - * @flags: lookup flags - * @path: if lookup succeed, return path info + * ksmbd_vfs_kern_path_locked() - lookup a file and get path info + * @name: file path that is relative to share + * @flags: lookup flags + * @parent_path: if lookup succeed, return parent_path info + * @path: if lookup succeed, return path info * @caseless: caseless filename lookup * * Return: 0 on success, otherwise error */ -int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, - unsigned int flags, struct path *path, bool caseless) +int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, + unsigned int flags, struct path *parent_path, + struct path *path, bool caseless) { struct ksmbd_share_config *share_conf = work->tcon->share_conf; int err; - flags |= LOOKUP_BENEATH; - err = vfs_path_lookup(share_conf->vfs_path.dentry, - share_conf->vfs_path.mnt, - name, - flags, - path); + err = ksmbd_vfs_path_lookup_locked(share_conf, name, flags, parent_path, + path); if (!err) return 0; if (caseless) { char *filepath; - struct path parent; size_t path_len, remain_len; filepath = kstrdup(name, GFP_KERNEL); @@ -1236,10 +1221,10 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, path_len = strlen(filepath); remain_len = path_len; - parent = share_conf->vfs_path; - path_get(&parent); + *parent_path = share_conf->vfs_path; + path_get(parent_path); - while (d_can_lookup(parent.dentry)) { + while (d_can_lookup(parent_path->dentry)) { char *filename = filepath + path_len - remain_len; char *next = strchrnul(filename, '/'); size_t filename_len = next - filename; @@ -1248,12 +1233,11 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, if (filename_len == 0) break; - err = ksmbd_vfs_lookup_in_dir(&parent, filename, + err = ksmbd_vfs_lookup_in_dir(parent_path, filename, filename_len, work->conn->um); - path_put(&parent); if (err) - goto out; + goto out2; next[0] = '\0'; @@ -1261,26 +1245,50 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, share_conf->vfs_path.mnt, filepath, flags, - &parent); + path); if (err) - goto out; - else if (is_last) { - *path = parent; - goto out; - } + goto out2; + else if (is_last) + goto out1; + path_put(parent_path); + *parent_path = *path; next[0] = '/'; remain_len -= filename_len + 1; } - path_put(&parent); err = -EINVAL; -out: +out2: + path_put(parent_path); +out1: kfree(filepath); } + + if (!err) { + err = mnt_want_write(parent_path->mnt); + if (err) { + path_put(path); + path_put(parent_path); + return err; + } + + err = ksmbd_vfs_lock_parent(parent_path->dentry, path->dentry); + if (err) { + path_put(path); + path_put(parent_path); + } + } return err; } +void ksmbd_vfs_kern_path_unlock(struct path *parent_path, struct path *path) +{ + inode_unlock(d_inode(parent_path->dentry)); + mnt_drop_write(parent_path->mnt); + path_put(path); + path_put(parent_path); +} + struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, const char *name, unsigned int flags, @@ -1299,13 +1307,13 @@ struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, } int ksmbd_vfs_remove_acl_xattrs(struct user_namespace *user_ns, - struct dentry *dentry) + const struct path *path) { char *name, *xattr_list = NULL; ssize_t xattr_list_len; int err = 0; - xattr_list_len = ksmbd_vfs_listxattr(dentry, &xattr_list); + xattr_list_len = ksmbd_vfs_listxattr(path->dentry, &xattr_list); if (xattr_list_len < 0) { goto out; } else if (!xattr_list_len) { @@ -1321,25 +1329,25 @@ int ksmbd_vfs_remove_acl_xattrs(struct user_namespace *user_ns, sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1) || !strncmp(name, XATTR_NAME_POSIX_ACL_DEFAULT, sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1)) { - err = ksmbd_vfs_remove_xattr(user_ns, dentry, name); + err = ksmbd_vfs_remove_xattr(user_ns, path, name); if (err) ksmbd_debug(SMB, "remove acl xattr failed : %s\n", name); } } + out: kvfree(xattr_list); return err; } -int ksmbd_vfs_remove_sd_xattrs(struct user_namespace *user_ns, - struct dentry *dentry) +int ksmbd_vfs_remove_sd_xattrs(struct user_namespace *user_ns, const struct path *path) { char *name, *xattr_list = NULL; ssize_t xattr_list_len; int err = 0; - xattr_list_len = ksmbd_vfs_listxattr(dentry, &xattr_list); + xattr_list_len = ksmbd_vfs_listxattr(path->dentry, &xattr_list); if (xattr_list_len < 0) { goto out; } else if (!xattr_list_len) { @@ -1352,7 +1360,7 @@ int ksmbd_vfs_remove_sd_xattrs(struct user_namespace *user_ns, ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); if (!strncmp(name, XATTR_NAME_SD, XATTR_NAME_SD_LEN)) { - err = ksmbd_vfs_remove_xattr(user_ns, dentry, name); + err = ksmbd_vfs_remove_xattr(user_ns, path, name); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", name); } @@ -1376,7 +1384,7 @@ static struct xattr_smb_acl *ksmbd_vfs_make_xattr_posix_acl(struct user_namespac return NULL; posix_acls = get_acl(inode, acl_type); - if (!posix_acls) + if (IS_ERR_OR_NULL(posix_acls)) return NULL; smb_acl = kzalloc(sizeof(struct xattr_smb_acl) + @@ -1429,13 +1437,15 @@ out: int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, struct user_namespace *user_ns, - struct dentry *dentry, - struct smb_ntsd *pntsd, int len) + const struct path *path, + struct smb_ntsd *pntsd, int len, + bool get_write) { int rc; struct ndr sd_ndr = {0}, acl_ndr = {0}; struct xattr_ntacl acl = {0}; struct xattr_smb_acl *smb_acl, *def_smb_acl = NULL; + struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); acl.version = 4; @@ -1487,9 +1497,9 @@ int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, goto out; } - rc = ksmbd_vfs_setxattr(user_ns, dentry, + rc = ksmbd_vfs_setxattr(user_ns, path, XATTR_NAME_SD, sd_ndr.data, - sd_ndr.offset, 0); + sd_ndr.offset, 0, get_write); if (rc < 0) pr_err("Failed to store XATTR ntacl :%d\n", rc); @@ -1577,8 +1587,9 @@ free_n_data: } int ksmbd_vfs_set_dos_attrib_xattr(struct user_namespace *user_ns, - struct dentry *dentry, - struct xattr_dos_attrib *da) + const struct path *path, + struct xattr_dos_attrib *da, + bool get_write) { struct ndr n; int err; @@ -1587,8 +1598,8 @@ int ksmbd_vfs_set_dos_attrib_xattr(struct user_namespace *user_ns, if (err) return err; - err = ksmbd_vfs_setxattr(user_ns, dentry, XATTR_NAME_DOS_ATTRIBUTE, - (void *)n.data, n.offset, 0); + err = ksmbd_vfs_setxattr(user_ns, path, XATTR_NAME_DOS_ATTRIBUTE, + (void *)n.data, n.offset, 0, get_write); if (err) ksmbd_debug(SMB, "failed to store dos attribute in xattr\n"); kfree(n.data); @@ -1824,10 +1835,11 @@ void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock) } int ksmbd_vfs_set_init_posix_acl(struct user_namespace *user_ns, - struct inode *inode) + struct path *path) { struct posix_acl_state acl_state; struct posix_acl *acls; + struct inode *inode = d_inode(path->dentry); int rc; if (!IS_ENABLED(CONFIG_FS_POSIX_ACL)) @@ -1856,6 +1868,7 @@ int ksmbd_vfs_set_init_posix_acl(struct user_namespace *user_ns, return -ENOMEM; } posix_state_to_acl(&acl_state, acls->a_entries); + rc = set_posix_acl(user_ns, inode, ACL_TYPE_ACCESS, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n", @@ -1868,23 +1881,25 @@ int ksmbd_vfs_set_init_posix_acl(struct user_namespace *user_ns, ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n", rc); } + free_acl_state(&acl_state); posix_acl_release(acls); return rc; } int ksmbd_vfs_inherit_posix_acl(struct user_namespace *user_ns, - struct inode *inode, struct inode *parent_inode) + struct path *path, struct inode *parent_inode) { struct posix_acl *acls; struct posix_acl_entry *pace; + struct inode *inode = d_inode(path->dentry); int rc, i; if (!IS_ENABLED(CONFIG_FS_POSIX_ACL)) return -EOPNOTSUPP; acls = get_acl(parent_inode, ACL_TYPE_DEFAULT); - if (!acls) + if (IS_ERR_OR_NULL(acls)) return -ENOENT; pace = acls->a_entries; @@ -1906,6 +1921,7 @@ int ksmbd_vfs_inherit_posix_acl(struct user_namespace *user_ns, ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n", rc); } + posix_acl_release(acls); return rc; } diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index 593059ca8511..e761dde2443e 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -71,25 +71,23 @@ struct ksmbd_kstat { __le32 file_attributes; }; -int ksmbd_vfs_lock_parent(struct user_namespace *user_ns, struct dentry *parent, - struct dentry *child); -int ksmbd_vfs_may_delete(struct user_namespace *user_ns, struct dentry *dentry); -int ksmbd_vfs_query_maximal_access(struct user_namespace *user_ns, +int ksmbd_vfs_lock_parent(struct dentry *parent, struct dentry *child); +void ksmbd_vfs_query_maximal_access(struct user_namespace *user_ns, struct dentry *dentry, __le32 *daccess); int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode); int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode); -int ksmbd_vfs_read(struct ksmbd_work *work, struct ksmbd_file *fp, - size_t count, loff_t *pos); +int ksmbd_vfs_read(struct ksmbd_work *work, struct ksmbd_file *fp, size_t count, + loff_t *pos, char *rbuf); int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp, char *buf, size_t count, loff_t *pos, bool sync, ssize_t *written); int ksmbd_vfs_fsync(struct ksmbd_work *work, u64 fid, u64 p_id); -int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name); +int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path); int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname, const char *newname); int ksmbd_vfs_getattr(const struct path *path, struct kstat *stat); -int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, - char *newname); +int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, + char *newname, int flags); int ksmbd_vfs_truncate(struct ksmbd_work *work, struct ksmbd_file *fp, loff_t size); struct srv_copychunk; @@ -110,15 +108,17 @@ ssize_t ksmbd_vfs_casexattr_len(struct user_namespace *user_ns, struct dentry *dentry, char *attr_name, int attr_name_len); int ksmbd_vfs_setxattr(struct user_namespace *user_ns, - struct dentry *dentry, const char *attr_name, - void *attr_value, size_t attr_size, int flags); + const struct path *path, const char *attr_name, + void *attr_value, size_t attr_size, int flags, + bool get_write); int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name, size_t *xattr_stream_name_size, int s_type); int ksmbd_vfs_remove_xattr(struct user_namespace *user_ns, - struct dentry *dentry, char *attr_name); -int ksmbd_vfs_kern_path(struct ksmbd_work *work, - char *name, unsigned int flags, struct path *path, - bool caseless); + const struct path *path, char *attr_name); +int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, + unsigned int flags, struct path *parent_path, + struct path *path, bool caseless); +void ksmbd_vfs_kern_path_unlock(struct path *parent_path, struct path *path); struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, const char *name, unsigned int flags, @@ -131,8 +131,7 @@ struct file_allocated_range_buffer; int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, struct file_allocated_range_buffer *ranges, unsigned int in_count, unsigned int *out_count); -int ksmbd_vfs_unlink(struct user_namespace *user_ns, - struct dentry *dir, struct dentry *dentry); +int ksmbd_vfs_unlink(struct file *filp); void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat); int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, struct user_namespace *user_ns, @@ -142,26 +141,27 @@ void ksmbd_vfs_posix_lock_wait(struct file_lock *flock); int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout); void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock); int ksmbd_vfs_remove_acl_xattrs(struct user_namespace *user_ns, - struct dentry *dentry); -int ksmbd_vfs_remove_sd_xattrs(struct user_namespace *user_ns, - struct dentry *dentry); + const struct path *path); +int ksmbd_vfs_remove_sd_xattrs(struct user_namespace *user_ns, const struct path *path); int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, struct user_namespace *user_ns, - struct dentry *dentry, - struct smb_ntsd *pntsd, int len); + const struct path *path, + struct smb_ntsd *pntsd, int len, + bool get_write); int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn, struct user_namespace *user_ns, struct dentry *dentry, struct smb_ntsd **pntsd); int ksmbd_vfs_set_dos_attrib_xattr(struct user_namespace *user_ns, - struct dentry *dentry, - struct xattr_dos_attrib *da); + const struct path *path, + struct xattr_dos_attrib *da, + bool get_write); int ksmbd_vfs_get_dos_attrib_xattr(struct user_namespace *user_ns, struct dentry *dentry, struct xattr_dos_attrib *da); int ksmbd_vfs_set_init_posix_acl(struct user_namespace *user_ns, - struct inode *inode); + struct path *path); int ksmbd_vfs_inherit_posix_acl(struct user_namespace *user_ns, - struct inode *inode, + struct path *path, struct inode *parent_inode); #endif /* __KSMBD_VFS_H__ */ diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 6ec6c129465d..2528ce8aeebb 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -65,14 +65,14 @@ static unsigned long inode_hash(struct super_block *sb, unsigned long hashval) return tmp & inode_hash_mask; } -static struct ksmbd_inode *__ksmbd_inode_lookup(struct inode *inode) +static struct ksmbd_inode *__ksmbd_inode_lookup(struct dentry *de) { struct hlist_head *head = inode_hashtable + - inode_hash(inode->i_sb, inode->i_ino); + inode_hash(d_inode(de)->i_sb, (unsigned long)de); struct ksmbd_inode *ci = NULL, *ret_ci = NULL; hlist_for_each_entry(ci, head, m_hash) { - if (ci->m_inode == inode) { + if (ci->m_de == de) { if (atomic_inc_not_zero(&ci->m_count)) ret_ci = ci; break; @@ -83,26 +83,27 @@ static struct ksmbd_inode *__ksmbd_inode_lookup(struct inode *inode) static struct ksmbd_inode *ksmbd_inode_lookup(struct ksmbd_file *fp) { - return __ksmbd_inode_lookup(file_inode(fp->filp)); + return __ksmbd_inode_lookup(fp->filp->f_path.dentry); } -static struct ksmbd_inode *ksmbd_inode_lookup_by_vfsinode(struct inode *inode) +struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d) { struct ksmbd_inode *ci; read_lock(&inode_hash_lock); - ci = __ksmbd_inode_lookup(inode); + ci = __ksmbd_inode_lookup(d); read_unlock(&inode_hash_lock); + return ci; } -int ksmbd_query_inode_status(struct inode *inode) +int ksmbd_query_inode_status(struct dentry *dentry) { struct ksmbd_inode *ci; int ret = KSMBD_INODE_STATUS_UNKNOWN; read_lock(&inode_hash_lock); - ci = __ksmbd_inode_lookup(inode); + ci = __ksmbd_inode_lookup(dentry); if (ci) { ret = KSMBD_INODE_STATUS_OK; if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)) @@ -142,7 +143,7 @@ void ksmbd_fd_set_delete_on_close(struct ksmbd_file *fp, static void ksmbd_inode_hash(struct ksmbd_inode *ci) { struct hlist_head *b = inode_hashtable + - inode_hash(ci->m_inode->i_sb, ci->m_inode->i_ino); + inode_hash(d_inode(ci->m_de)->i_sb, (unsigned long)ci->m_de); hlist_add_head(&ci->m_hash, b); } @@ -156,7 +157,6 @@ static void ksmbd_inode_unhash(struct ksmbd_inode *ci) static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp) { - ci->m_inode = file_inode(fp->filp); atomic_set(&ci->m_count, 1); atomic_set(&ci->op_count, 0); atomic_set(&ci->sop_count, 0); @@ -165,6 +165,7 @@ static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp) INIT_LIST_HEAD(&ci->m_fp_list); INIT_LIST_HEAD(&ci->m_op_list); rwlock_init(&ci->m_lock); + ci->m_de = fp->filp->f_path.dentry; return 0; } @@ -208,7 +209,7 @@ static void ksmbd_inode_free(struct ksmbd_inode *ci) kfree(ci); } -static void ksmbd_inode_put(struct ksmbd_inode *ci) +void ksmbd_inode_put(struct ksmbd_inode *ci) { if (atomic_dec_and_test(&ci->m_count)) ksmbd_inode_free(ci); @@ -243,7 +244,6 @@ void ksmbd_release_inode_hash(void) static void __ksmbd_inode_close(struct ksmbd_file *fp) { - struct dentry *dir, *dentry; struct ksmbd_inode *ci = fp->f_ci; int err; struct file *filp; @@ -252,7 +252,7 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) if (ksmbd_stream_fd(fp) && (ci->m_flags & S_DEL_ON_CLS_STREAM)) { ci->m_flags &= ~S_DEL_ON_CLS_STREAM; err = ksmbd_vfs_remove_xattr(file_mnt_user_ns(filp), - filp->f_path.dentry, + &filp->f_path, fp->stream.name); if (err) pr_err("remove xattr failed : %s\n", @@ -262,11 +262,9 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) if (atomic_dec_and_test(&ci->m_count)) { write_lock(&ci->m_lock); if (ci->m_flags & (S_DEL_ON_CLS | S_DEL_PENDING)) { - dentry = filp->f_path.dentry; - dir = dentry->d_parent; ci->m_flags &= ~(S_DEL_ON_CLS | S_DEL_PENDING); write_unlock(&ci->m_lock); - ksmbd_vfs_unlink(file_mnt_user_ns(filp), dir, dentry); + ksmbd_vfs_unlink(filp); write_lock(&ci->m_lock); } write_unlock(&ci->m_lock); @@ -335,6 +333,9 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) static struct ksmbd_file *ksmbd_fp_get(struct ksmbd_file *fp) { + if (fp->f_state != FP_INITED) + return NULL; + if (!atomic_inc_not_zero(&fp->refcount)) return NULL; return fp; @@ -384,15 +385,20 @@ int ksmbd_close_fd(struct ksmbd_work *work, u64 id) return 0; ft = &work->sess->file_table; - read_lock(&ft->lock); + write_lock(&ft->lock); fp = idr_find(ft->idr, id); if (fp) { set_close_state_blocked_works(fp); - if (!atomic_dec_and_test(&fp->refcount)) + if (fp->f_state != FP_INITED) fp = NULL; + else { + fp->f_state = FP_CLOSED; + if (!atomic_dec_and_test(&fp->refcount)) + fp = NULL; + } } - read_unlock(&ft->lock); + write_unlock(&ft->lock); if (!fp) return -EINVAL; @@ -482,12 +488,15 @@ struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid) return fp; } -struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode) +struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry) { struct ksmbd_file *lfp; struct ksmbd_inode *ci; + struct inode *inode = d_inode(dentry); - ci = ksmbd_inode_lookup_by_vfsinode(inode); + read_lock(&inode_hash_lock); + ci = __ksmbd_inode_lookup(dentry); + read_unlock(&inode_hash_lock); if (!ci) return NULL; @@ -572,6 +581,7 @@ struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp) fp->tcon = work->tcon; fp->volatile_id = KSMBD_NO_FID; fp->persistent_id = KSMBD_NO_FID; + fp->f_state = FP_NEW; fp->f_ci = ksmbd_inode_get(fp); if (!fp->f_ci) { @@ -593,6 +603,17 @@ err_out: return ERR_PTR(ret); } +void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, + unsigned int state) +{ + if (!fp) + return; + + write_lock(&ft->lock); + fp->f_state = state; + write_unlock(&ft->lock); +} + static int __close_file_table_ids(struct ksmbd_file_table *ft, struct ksmbd_tree_connect *tcon, diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index fcb13413fa8d..a528f0cc775a 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -51,7 +51,7 @@ struct ksmbd_inode { atomic_t op_count; /* opinfo count for streams */ atomic_t sop_count; - struct inode *m_inode; + struct dentry *m_de; unsigned int m_flags; struct hlist_node m_hash; struct list_head m_fp_list; @@ -60,6 +60,12 @@ struct ksmbd_inode { __le32 m_fattr; }; +enum { + FP_NEW = 0, + FP_INITED, + FP_CLOSED +}; + struct ksmbd_file { struct file *filp; u64 persistent_id; @@ -98,6 +104,8 @@ struct ksmbd_file { /* if ls is happening on directory, below is valid*/ struct ksmbd_readdir_data readdir_data; int dot_dotdot[2]; + unsigned int f_state; + bool reserve_lease_break; }; static inline void set_ctx_actor(struct dir_context *ctx, @@ -131,9 +139,11 @@ struct ksmbd_file *ksmbd_lookup_foreign_fd(struct ksmbd_work *work, u64 id); struct ksmbd_file *ksmbd_lookup_fd_slow(struct ksmbd_work *work, u64 id, u64 pid); void ksmbd_fd_put(struct ksmbd_work *work, struct ksmbd_file *fp); +struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d); +void ksmbd_inode_put(struct ksmbd_inode *ci); struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id); struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid); -struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode); +struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry); unsigned int ksmbd_open_durable_fd(struct ksmbd_file *fp); struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp); void ksmbd_close_tree_conn_fds(struct ksmbd_work *work); @@ -142,6 +152,8 @@ int ksmbd_close_inode_fds(struct ksmbd_work *work, struct inode *inode); int ksmbd_init_global_file_table(void); void ksmbd_free_global_file_table(void); void ksmbd_set_fd_limit(unsigned long limit); +void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, + unsigned int state); /* * INODE hash @@ -155,7 +167,7 @@ enum KSMBD_INODE_STATUS { KSMBD_INODE_STATUS_PENDING_DELETE, }; -int ksmbd_query_inode_status(struct inode *inode); +int ksmbd_query_inode_status(struct dentry *dentry); bool ksmbd_inode_pending_delete(struct ksmbd_file *fp); void ksmbd_set_inode_pending_delete(struct ksmbd_file *fp); void ksmbd_clear_inode_pending_delete(struct ksmbd_file *fp); diff --git a/fs/splice.c b/fs/splice.c index 5969b7a1d353..d0230cf8ec57 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -65,8 +65,7 @@ static bool page_cache_pipe_buf_try_steal(struct pipe_inode_info *pipe, */ folio_wait_writeback(folio); - if (folio_has_private(folio) && - !filemap_release_folio(folio, GFP_KERNEL)) + if (!filemap_release_folio(folio, GFP_KERNEL)) goto out_unlock; /* @@ -765,6 +764,17 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, } /* + * Indicate to the caller that there was a premature EOF when reading from the + * source and the caller didn't indicate they would be sending more data after + * this. + */ +static void do_splice_eof(struct splice_desc *sd) +{ + if (sd->splice_eof) + sd->splice_eof(sd); +} + +/* * Attempt to initiate a splice from a file to a pipe. */ static long do_splice_to(struct file *in, loff_t *ppos, @@ -864,7 +874,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, ret = do_splice_to(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) - goto out_release; + goto read_failure; read_len = ret; sd->total_len = read_len; @@ -904,6 +914,15 @@ done: file_accessed(in); return bytes; +read_failure: + /* + * If the user did *not* set SPLICE_F_MORE *and* we didn't hit that + * "use all of len" case that cleared SPLICE_F_MORE, *and* we did a + * "->splice_in()" that returned EOF (ie zero) *and* we have sent at + * least 1 byte *then* we will also do the ->splice_eof() call. + */ + if (ret == 0 && !more && len > 0 && bytes) + do_splice_eof(sd); out_release: /* * If we did an incomplete transfer we must release @@ -932,6 +951,14 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, sd->flags); } +static void direct_file_splice_eof(struct splice_desc *sd) +{ + struct file *file = sd->u.file; + + if (file->f_op->splice_eof) + file->f_op->splice_eof(file); +} + /** * do_splice_direct - splices data directly between two files * @in: file to splice from @@ -957,6 +984,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, .flags = flags, .pos = *ppos, .u.file = out, + .splice_eof = direct_file_splice_eof, .opos = opos, }; long ret; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 66ba57a139d2..4d9782e2fab1 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1226,6 +1226,8 @@ out_cancel: dir_ui->ui_size = dir->i_size; mutex_unlock(&dir_ui->ui_mutex); out_inode: + /* Free inode->i_link before inode is marked as bad. */ + fscrypt_free_inode(inode); make_bad_inode(inode); iput(inode); out_fname: diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 6b7d95b65f4b..f4728e65d1bd 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -65,6 +65,7 @@ static void do_insert_old_idx(struct ubifs_info *c, else { ubifs_err(c, "old idx added twice!"); kfree(old_idx); + return; } } rb_link_node(&old_idx->rb, parent, p); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4b179526913f..12662b169b71 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1458,6 +1458,18 @@ xfs_fs_fill_super( mp->m_super = sb; + /* + * Copy VFS mount flags from the context now that all parameter parsing + * is guaranteed to have been completed by either the old mount API or + * the newer fsopen/fsconfig API. + */ + if (fc->sb_flags & SB_RDONLY) + set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); + if (fc->sb_flags & SB_DIRSYNC) + mp->m_features |= XFS_FEAT_DIRSYNC; + if (fc->sb_flags & SB_SYNCHRONOUS) + mp->m_features |= XFS_FEAT_WSYNC; + error = xfs_fs_validate_params(mp); if (error) goto out_free_names; @@ -1915,6 +1927,11 @@ static const struct fs_context_operations xfs_context_ops = { .free = xfs_fs_free, }; +/* + * WARNING: do not initialise any parameters in this function that depend on + * mount option parsing having already been performed as this can be called from + * fsopen() before any parameters have been set. + */ static int xfs_init_fs_context( struct fs_context *fc) { @@ -1947,16 +1964,6 @@ static int xfs_init_fs_context( mp->m_logbsize = -1; mp->m_allocsize_log = 16; /* 64k */ - /* - * Copy binary VFS mount flags we are interested in. - */ - if (fc->sb_flags & SB_RDONLY) - set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); - if (fc->sb_flags & SB_DIRSYNC) - mp->m_features |= XFS_FEAT_DIRSYNC; - if (fc->sb_flags & SB_SYNCHRONOUS) - mp->m_features |= XFS_FEAT_WSYNC; - fc->s_fs_info = mp; fc->ops = &xfs_context_ops; diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 63cd50840419..8d5f4a5a74e6 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -349,7 +349,12 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, struct zonefs_inode_info *zi = ZONEFS_I(inode); if (error) { - zonefs_io_error(inode, true); + /* + * For Sync IOs, error recovery is called from + * zonefs_file_dio_write(). + */ + if (!is_sync_kiocb(iocb)) + zonefs_io_error(inode, true); return error; } @@ -577,6 +582,14 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ret = -EINVAL; goto inode_unlock; } + /* + * Advance the zone write pointer offset. This assumes that the + * IO will succeed, which is OK to do because we do not allow + * partial writes (IOMAP_DIO_PARTIAL is not set) and if the IO + * fails, the error path will correct the write pointer offset. + */ + z->z_wpoffset += count; + zonefs_inode_account_active(inode); mutex_unlock(&zi->i_truncate_mutex); append = sync; } @@ -596,20 +609,19 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ret = -EBUSY; } - if (zonefs_zone_is_seq(z) && - (ret > 0 || ret == -EIOCBQUEUED)) { - if (ret > 0) - count = ret; - - /* - * Update the zone write pointer offset assuming the write - * operation succeeded. If it did not, the error recovery path - * will correct it. Also do active seq file accounting. - */ - mutex_lock(&zi->i_truncate_mutex); - z->z_wpoffset += count; - zonefs_inode_account_active(inode); - mutex_unlock(&zi->i_truncate_mutex); + /* + * For a failed IO or partial completion, trigger error recovery + * to update the zone write pointer offset to a correct value. + * For asynchronous IOs, zonefs_file_write_dio_end_io() may already + * have executed error recovery if the IO already completed when we + * reach here. However, we cannot know that and execute error recovery + * again (that will not change anything). + */ + if (zonefs_zone_is_seq(z)) { + if (ret > 0 && ret != count) + ret = -EIO; + if (ret < 0 && ret != -EIOCBQUEUED) + zonefs_io_error(inode, true); } inode_unlock: diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 270ded209dde..f6b701261078 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -245,16 +245,18 @@ static void zonefs_inode_update_mode(struct inode *inode) z->z_flags &= ~ZONEFS_ZONE_INIT_MODE; } -struct zonefs_ioerr_data { - struct inode *inode; - bool write; -}; - static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, void *data) { - struct zonefs_ioerr_data *err = data; - struct inode *inode = err->inode; + struct blk_zone *z = data; + + *z = *zone; + return 0; +} + +static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone, + bool write) +{ struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); @@ -269,8 +271,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, data_size = zonefs_check_zone_condition(sb, z, zone); isize = i_size_read(inode); if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) && - !err->write && isize == data_size) - return 0; + !write && isize == data_size) + return; /* * At this point, we detected either a bad zone or an inconsistency @@ -291,7 +293,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, * In all cases, warn about inode size inconsistency and handle the * IO error according to the zone condition and to the mount options. */ - if (zonefs_zone_is_seq(z) && isize != data_size) + if (isize != data_size) zonefs_warn(sb, "inode %lu: invalid size %lld (should be %lld)\n", inode->i_ino, isize, data_size); @@ -351,8 +353,6 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, zonefs_i_size_write(inode, data_size); z->z_wpoffset = data_size; zonefs_inode_account_active(inode); - - return 0; } /* @@ -366,23 +366,25 @@ void __zonefs_io_error(struct inode *inode, bool write) { struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; - struct zonefs_sb_info *sbi = ZONEFS_SB(sb); unsigned int noio_flag; - unsigned int nr_zones = 1; - struct zonefs_ioerr_data err = { - .inode = inode, - .write = write, - }; + struct blk_zone zone; int ret; /* - * The only files that have more than one zone are conventional zone - * files with aggregated conventional zones, for which the inode zone - * size is always larger than the device zone size. + * Conventional zone have no write pointer and cannot become read-only + * or offline. So simply fake a report for a single or aggregated zone + * and let zonefs_handle_io_error() correct the zone inode information + * according to the mount options. */ - if (z->z_size > bdev_zone_sectors(sb->s_bdev)) - nr_zones = z->z_size >> - (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + if (!zonefs_zone_is_seq(z)) { + zone.start = z->z_sector; + zone.len = z->z_size >> SECTOR_SHIFT; + zone.wp = zone.start + zone.len; + zone.type = BLK_ZONE_TYPE_CONVENTIONAL; + zone.cond = BLK_ZONE_COND_NOT_WP; + zone.capacity = zone.len; + goto handle_io_error; + } /* * Memory allocations in blkdev_report_zones() can trigger a memory @@ -393,12 +395,20 @@ void __zonefs_io_error(struct inode *inode, bool write) * the GFP_NOIO context avoids both problems. */ noio_flag = memalloc_noio_save(); - ret = blkdev_report_zones(sb->s_bdev, z->z_sector, nr_zones, - zonefs_io_error_cb, &err); - if (ret != nr_zones) + ret = blkdev_report_zones(sb->s_bdev, z->z_sector, 1, + zonefs_io_error_cb, &zone); + memalloc_noio_restore(noio_flag); + + if (ret != 1) { zonefs_err(sb, "Get inode %lu zone information failed %d\n", inode->i_ino, ret); - memalloc_noio_restore(noio_flag); + zonefs_warn(sb, "remounting filesystem read-only\n"); + sb->s_flags |= SB_RDONLY; + return; + } + +handle_io_error: + zonefs_handle_io_error(inode, &zone, write); } static struct kmem_cache *zonefs_inode_cachep; diff --git a/include/asm-generic/numa.h b/include/asm-generic/numa.h index 1a3ad6d29833..c32e0cf23c90 100644 --- a/include/asm-generic/numa.h +++ b/include/asm-generic/numa.h @@ -35,6 +35,7 @@ int __init numa_add_memblk(int nodeid, u64 start, u64 end); void __init numa_set_distance(int from, int to, int distance); void __init numa_free_distance(void); void __init early_map_cpu_to_node(unsigned int cpu, int nid); +int __init early_cpu_to_node(int cpu); void numa_store_cpu_info(unsigned int cpu); void numa_add_cpu(unsigned int cpu); void numa_remove_cpu(unsigned int cpu); @@ -46,6 +47,7 @@ static inline void numa_add_cpu(unsigned int cpu) { } static inline void numa_remove_cpu(unsigned int cpu) { } static inline void arch_numa_init(void) { } static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { } +static inline int early_cpu_to_node(int cpu) { return 0; } #endif /* CONFIG_NUMA */ diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 699650f81970..a84c64e5f11e 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -104,9 +104,9 @@ static inline u32 get_unaligned_le24(const void *p) static inline void __put_unaligned_be24(const u32 val, u8 *p) { - *p++ = val >> 16; - *p++ = val >> 8; - *p++ = val; + *p++ = (val >> 16) & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = val & 0xff; } static inline void put_unaligned_be24(const u32 val, void *p) @@ -116,9 +116,9 @@ static inline void put_unaligned_be24(const u32 val, void *p) static inline void __put_unaligned_le24(const u32 val, u8 *p) { - *p++ = val; - *p++ = val >> 8; - *p++ = val >> 16; + *p++ = val & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = (val >> 16) & 0xff; } static inline void put_unaligned_le24(const u32 val, void *p) @@ -128,12 +128,12 @@ static inline void put_unaligned_le24(const u32 val, void *p) static inline void __put_unaligned_be48(const u64 val, u8 *p) { - *p++ = val >> 40; - *p++ = val >> 32; - *p++ = val >> 24; - *p++ = val >> 16; - *p++ = val >> 8; - *p++ = val; + *p++ = (val >> 40) & 0xff; + *p++ = (val >> 32) & 0xff; + *p++ = (val >> 24) & 0xff; + *p++ = (val >> 16) & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = val & 0xff; } static inline void put_unaligned_be48(const u64 val, void *p) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 7ad6f51b3d91..1d1f480a5e9e 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -351,7 +351,6 @@ *(.ref.data) \ *(.data..shared_aligned) /* percpu related */ \ MEM_KEEP(init.data*) \ - MEM_KEEP(exit.data*) \ *(.data.unlikely) \ __start_once = .; \ *(.data.once) \ @@ -546,7 +545,6 @@ __init_rodata : AT(ADDR(__init_rodata) - LOAD_OFFSET) { \ *(.ref.rodata) \ MEM_KEEP(init.rodata) \ - MEM_KEEP(exit.rodata) \ } \ \ /* Built-in module parameters. */ \ @@ -601,7 +599,6 @@ *(.ref.text) \ *(.text.asan.* .text.tsan.*) \ MEM_KEEP(init.text*) \ - MEM_KEEP(exit.text*) \ /* sched.text is aling to function alignment to secure we have same @@ -751,13 +748,10 @@ *(.exit.data .exit.data.*) \ *(.fini_array .fini_array.*) \ *(.dtors .dtors.*) \ - MEM_DISCARD(exit.data*) \ - MEM_DISCARD(exit.rodata*) #define EXIT_TEXT \ *(.exit.text) \ *(.text.exit) \ - MEM_DISCARD(exit.text) #define EXIT_CALL \ *(.exitcall.exit) diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index a5db86670bdf..a406e281ae57 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -138,6 +138,7 @@ struct af_alg_async_req { * recvmsg is invoked. * @init: True if metadata has been sent. * @len: Length of memory allocated for this data structure. + * @inflight: Non-zero when AIO requests are in flight. */ struct af_alg_ctx { struct list_head tsgl_list; @@ -156,6 +157,8 @@ struct af_alg_ctx { bool init; unsigned int len; + + unsigned int inflight; }; int af_alg_register_type(const struct af_alg_type *type); diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 6b656ea23b96..ad6c06b960fd 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -191,7 +191,7 @@ struct drm_bridge_funcs { * or &drm_encoder_helper_funcs.dpms hook. * * The bridge must assume that the display pipe (i.e. clocks and timing - * singals) feeding it is no longer running when this callback is + * signals) feeding it is no longer running when this callback is * called. * * The @post_disable callback is optional. @@ -204,6 +204,20 @@ struct drm_bridge_funcs { void (*post_disable)(struct drm_bridge *bridge); /** + * @late_disable: + * + * This callback should disable the bridge. It is called right after the + * preceding element in the display pipe is disabled. If the preceding + * element is a bridge this means it's called after that bridge's + * @atomic_post_disable. If the preceding element is a &drm_crtc it's + * called right after the crtc's &drm_crtc_helper_funcs.atomic_disable + * hook. + * + * The @elate_disable callback is optional. + */ + void (*late_disable)(struct drm_bridge *bridge); + + /** * @mode_set: * * This callback should set the given mode on the bridge. It is called @@ -232,6 +246,26 @@ struct drm_bridge_funcs { void (*mode_set)(struct drm_bridge *bridge, const struct drm_display_mode *mode, const struct drm_display_mode *adjusted_mode); + + /** + * @early_enable: + * + * This callback should enable the bridge. It is called right before + * the preceding element in the display pipe is enabled. If the + * preceding element is a bridge this means it's called before that + * bridge's @atomic_early_enable. If the preceding element is a + * &drm_crtc it's called right before the crtc's + * &drm_crtc_helper_funcs.atomic_enable hook. + * + * The display pipe (i.e. clocks and timing signals) feeding this bridge + * will not yet be running when this callback is called. The bridge can + * enable the display link feeding the next bridge in the chain (if + * there is one) when this callback is called. + * + * The @early_enable callback is optional. + */ + void (*early_enable)(struct drm_bridge *bridge); + /** * @pre_enable: * @@ -283,6 +317,26 @@ struct drm_bridge_funcs { void (*enable)(struct drm_bridge *bridge); /** + * @early_enable: + * + * This callback should enable the bridge. It is called right before + * the preceding element in the display pipe is enabled. If the + * preceding element is a bridge this means it's called before that + * bridge's @atomic_early_enable. If the preceding element is a + * &drm_crtc it's called right before the crtc's + * &drm_crtc_helper_funcs.atomic_enable hook. + * + * The display pipe (i.e. clocks and timing signals) feeding this bridge + * will not yet be running when this callback is called. The bridge can + * enable the display link feeding the next bridge in the chain (if + * there is one) when this callback is called. + * + * The @early_enable callback is optional. + */ + void (*atomic_early_enable)(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state); + + /** * @atomic_pre_enable: * * This callback should enable the bridge. It is called right before @@ -383,6 +437,21 @@ struct drm_bridge_funcs { struct drm_bridge_state *old_bridge_state); /** + * @late_disable: + * + * This callback should disable the bridge. It is called right after the + * preceding element in the display pipe is disabled. If the preceding + * element is a bridge this means it's called after that bridge's + * @atomic_post_disable. If the preceding element is a &drm_crtc it's + * called right after the crtc's &drm_crtc_helper_funcs.atomic_disable + * hook. + * + * The @elate_disable callback is optional. + */ + void (*atomic_late_disable)(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state); + + /** * @atomic_duplicate_state: * * Duplicate the current bridge state object (which is guaranteed to be @@ -899,6 +968,10 @@ void drm_atomic_bridge_chain_disable(struct drm_bridge *bridge, struct drm_atomic_state *state); void drm_atomic_bridge_chain_post_disable(struct drm_bridge *bridge, struct drm_atomic_state *state); +void drm_atomic_bridge_chain_late_disable(struct drm_bridge *bridge, + struct drm_atomic_state *state); +void drm_atomic_bridge_chain_early_enable(struct drm_bridge *bridge, + struct drm_atomic_state *state); void drm_atomic_bridge_chain_pre_enable(struct drm_bridge *bridge, struct drm_atomic_state *state); void drm_atomic_bridge_chain_enable(struct drm_bridge *bridge, diff --git a/include/drm/drm_color_mgmt.h b/include/drm/drm_color_mgmt.h index 81c298488b0c..6b5eec10c3db 100644 --- a/include/drm/drm_color_mgmt.h +++ b/include/drm/drm_color_mgmt.h @@ -24,6 +24,7 @@ #define __DRM_COLOR_MGMT_H__ #include <linux/ctype.h> +#include <linux/math64.h> #include <drm/drm_property.h> struct drm_crtc; diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index 9054a5185e1a..31171914990a 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -168,6 +168,7 @@ struct mipi_dsi_device_info { * struct mipi_dsi_device - DSI peripheral device * @host: DSI host for this peripheral * @dev: driver model device node for this peripheral + * @attached: the DSI device has been successfully attached * @name: DSI peripheral chip type * @channel: virtual channel assigned to the peripheral * @format: pixel format for video mode @@ -184,6 +185,7 @@ struct mipi_dsi_device_info { struct mipi_dsi_device { struct mipi_dsi_host *host; struct device dev; + bool attached; char name[DSI_DEV_NAME_SIZE]; unsigned int channel; diff --git a/include/dt-bindings/clock/qcom,videocc-sm8150.h b/include/dt-bindings/clock/qcom,videocc-sm8150.h index e24ee840cfdb..c557b78dc572 100644 --- a/include/dt-bindings/clock/qcom,videocc-sm8150.h +++ b/include/dt-bindings/clock/qcom,videocc-sm8150.h @@ -16,6 +16,10 @@ /* VIDEO_CC Resets */ #define VIDEO_CC_MVSC_CORE_CLK_BCR 0 +#define VIDEO_CC_INTERFACE_BCR 1 +#define VIDEO_CC_MVS0_BCR 2 +#define VIDEO_CC_MVS1_BCR 3 +#define VIDEO_CC_MVSC_BCR 4 /* VIDEO_CC GDSCRs */ #define VENUS_GDSC 0 diff --git a/include/linux/async.h b/include/linux/async.h index cce4ad31e8fc..33c9ff4afb49 100644 --- a/include/linux/async.h +++ b/include/linux/async.h @@ -90,6 +90,8 @@ async_schedule_dev(async_func_t func, struct device *dev) return async_schedule_node(func, dev, dev_to_node(dev)); } +bool async_schedule_dev_nocall(async_func_t func, struct device *dev); + /** * async_schedule_dev_domain - A device specific version of async_schedule_domain * @func: function to execute asynchronously diff --git a/include/linux/bio.h b/include/linux/bio.h index 2c5806997bbf..2b9fc5edf49d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -279,6 +279,11 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, { struct bio_vec *bvec = bio_first_bvec_all(bio) + i; + if (unlikely(i >= bio->bi_vcnt)) { + fi->folio = NULL; + return; + } + fi->folio = page_folio(bvec->bv_page); fi->offset = bvec->bv_offset + PAGE_SIZE * (bvec->bv_page - &fi->folio->page); @@ -296,10 +301,8 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) fi->offset = 0; fi->length = min(folio_size(fi->folio), fi->_seg_count); fi->_next = folio_next(fi->folio); - } else if (fi->_i + 1 < bio->bi_vcnt) { - bio_first_folio(fi, bio, fi->_i + 1); } else { - fi->folio = NULL; + bio_first_folio(fi, bio, fi->_i + 1); } } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 57674b3c5877..e255674a9ee7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -565,7 +565,7 @@ struct request_queue { #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ -#define QUEUE_FLAG_HW_WC 18 /* Write back caching supported */ +#define QUEUE_FLAG_HW_WC 13 /* Write back caching supported */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ @@ -1109,11 +1109,12 @@ static inline bool bdev_is_partition(struct block_device *bdev) enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, - BLK_DEF_MAX_SECTORS = 2560, BLK_MAX_SEGMENT_SIZE = 65536, BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; +#define BLK_DEF_MAX_SECTORS 2560u + static inline unsigned long queue_segment_boundary(const struct request_queue *q) { return q->limits.seg_boundary_mask; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1fba826f0ace..1ca1902af23e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -102,7 +102,11 @@ struct bpf_map_ops { /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); - void (*map_fd_put_ptr)(void *ptr); + /* If need_defer is true, the implementation should guarantee that + * the to-be-put element is still alive before the bpf program, which + * may manipulate it, exists. + */ + void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, @@ -233,7 +237,11 @@ struct bpf_map { */ atomic64_t refcnt ____cacheline_aligned; atomic64_t usercnt; - struct work_struct work; + /* rcu is used before freeing and work is only used during freeing */ + union { + struct work_struct work; + struct rcu_head rcu; + }; struct mutex freeze_mutex; atomic64_t writecnt; /* 'Ownership' of program-containing map is claimed by the first program @@ -249,6 +257,8 @@ struct bpf_map { } owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ + bool free_after_mult_rcu_gp; + s64 __percpu *elem_count; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -702,10 +712,14 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +static bool bpf_is_ldimm64(const struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + static inline bool bpf_pseudo_func(const struct bpf_insn *insn) { - return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && - insn->src_reg == BPF_PSEUDO_FUNC; + return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } struct bpf_prog_ops { @@ -825,6 +839,11 @@ struct btf_func_model { */ #define BPF_TRAMP_F_SHARE_IPMODIFY BIT(6) +/* Indicate that current trampoline is in a tail call context. Then, it has to + * cache and restore tail_call_cnt to avoid infinite tail call loop. + */ +#define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ @@ -1782,6 +1801,35 @@ bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, } #endif +static inline int +bpf_map_init_elem_count(struct bpf_map *map) +{ + size_t size = sizeof(*map->elem_count), align = size; + gfp_t flags = GFP_USER | __GFP_NOWARN; + + map->elem_count = bpf_map_alloc_percpu(map, size, align, flags); + if (!map->elem_count) + return -ENOMEM; + + return 0; +} + +static inline void +bpf_map_free_elem_count(struct bpf_map *map) +{ + free_percpu(map->elem_count); +} + +static inline void bpf_map_inc_elem_count(struct bpf_map *map) +{ + this_cpu_inc(*map->elem_count); +} + +static inline void bpf_map_dec_elem_count(struct bpf_map *map) +{ + this_cpu_dec(*map->elem_count); +} + extern int sysctl_unprivileged_bpf_disabled; static inline bool bpf_allow_ptr_leaks(void) @@ -2681,6 +2729,9 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old); + void *bpf_arch_text_copy(void *dst, void *src, size_t len); int bpf_arch_text_invalidate(void *dst, size_t len); @@ -2688,10 +2739,18 @@ struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); #define MAX_BPRINTF_VARARGS 12 +#define MAX_BPRINTF_BUF 1024 + +struct bpf_bprintf_data { + u32 *bin_args; + char *buf; + bool get_bin_args; + bool get_buf; +}; int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, - u32 **bin_buf, u32 num_args); -void bpf_bprintf_cleanup(void); + u32 num_args, struct bpf_bprintf_data *data); +void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); /* the implementation of the opaque uapi struct bpf_dynptr */ struct bpf_dynptr_kern { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1a32baa78ce2..f080ccf27d25 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -429,6 +429,7 @@ struct bpf_insn_aux_data { /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ bool prune_point; + bool jmp_point; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h new file mode 100644 index 000000000000..53f1a7a932b0 --- /dev/null +++ b/include/linux/cleanup.h @@ -0,0 +1,171 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_GUARDS_H +#define __LINUX_GUARDS_H + +#include <linux/compiler.h> + +/* + * DEFINE_FREE(name, type, free): + * simple helper macro that defines the required wrapper for a __free() + * based cleanup function. @free is an expression using '_T' to access + * the variable. + * + * __free(name): + * variable attribute to add a scoped based cleanup to the variable. + * + * no_free_ptr(var): + * like a non-atomic xchg(var, NULL), such that the cleanup function will + * be inhibited -- provided it sanely deals with a NULL value. + * + * return_ptr(p): + * returns p while inhibiting the __free(). + * + * Ex. + * + * DEFINE_FREE(kfree, void *, if (_T) kfree(_T)) + * + * struct obj *p __free(kfree) = kmalloc(...); + * if (!p) + * return NULL; + * + * if (!init_obj(p)) + * return NULL; + * + * return_ptr(p); + */ + +#define DEFINE_FREE(_name, _type, _free) \ + static inline void __free_##_name(void *p) { _type _T = *(_type *)p; _free; } + +#define __free(_name) __cleanup(__free_##_name) + +#define no_free_ptr(p) \ + ({ __auto_type __ptr = (p); (p) = NULL; __ptr; }) + +#define return_ptr(p) return no_free_ptr(p) + + +/* + * DEFINE_CLASS(name, type, exit, init, init_args...): + * helper to define the destructor and constructor for a type. + * @exit is an expression using '_T' -- similar to FREE above. + * @init is an expression in @init_args resulting in @type + * + * EXTEND_CLASS(name, ext, init, init_args...): + * extends class @name to @name@ext with the new constructor + * + * CLASS(name, var)(args...): + * declare the variable @var as an instance of the named class + * + * Ex. + * + * DEFINE_CLASS(fdget, struct fd, fdput(_T), fdget(fd), int fd) + * + * CLASS(fdget, f)(fd); + * if (!f.file) + * return -EBADF; + * + * // use 'f' without concern + */ + +#define DEFINE_CLASS(_name, _type, _exit, _init, _init_args...) \ +typedef _type class_##_name##_t; \ +static inline void class_##_name##_destructor(_type *p) \ +{ _type _T = *p; _exit; } \ +static inline _type class_##_name##_constructor(_init_args) \ +{ _type t = _init; return t; } + +#define EXTEND_CLASS(_name, ext, _init, _init_args...) \ +typedef class_##_name##_t class_##_name##ext##_t; \ +static inline void class_##_name##ext##_destructor(class_##_name##_t *p)\ +{ class_##_name##_destructor(p); } \ +static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ +{ class_##_name##_t t = _init; return t; } + +#define CLASS(_name, var) \ + class_##_name##_t var __cleanup(class_##_name##_destructor) = \ + class_##_name##_constructor + + +/* + * DEFINE_GUARD(name, type, lock, unlock): + * trivial wrapper around DEFINE_CLASS() above specifically + * for locks. + * + * guard(name): + * an anonymous instance of the (guard) class + * + * scoped_guard (name, args...) { }: + * similar to CLASS(name, scope)(args), except the variable (with the + * explicit name 'scope') is declard in a for-loop such that its scope is + * bound to the next (compound) statement. + * + */ + +#define DEFINE_GUARD(_name, _type, _lock, _unlock) \ + DEFINE_CLASS(_name, _type, _unlock, ({ _lock; _T; }), _type _T) + +#define guard(_name) \ + CLASS(_name, __UNIQUE_ID(guard)) + +#define scoped_guard(_name, args...) \ + for (CLASS(_name, scope)(args), \ + *done = NULL; !done; done = (void *)1) + +/* + * Additional helper macros for generating lock guards with types, either for + * locks that don't have a native type (eg. RCU, preempt) or those that need a + * 'fat' pointer (eg. spin_lock_irqsave). + * + * DEFINE_LOCK_GUARD_0(name, lock, unlock, ...) + * DEFINE_LOCK_GUARD_1(name, type, lock, unlock, ...) + * + * will result in the following type: + * + * typedef struct { + * type *lock; // 'type := void' for the _0 variant + * __VA_ARGS__; + * } class_##name##_t; + * + * As above, both _lock and _unlock are statements, except this time '_T' will + * be a pointer to the above struct. + */ + +#define __DEFINE_UNLOCK_GUARD(_name, _type, _unlock, ...) \ +typedef struct { \ + _type *lock; \ + __VA_ARGS__; \ +} class_##_name##_t; \ + \ +static inline void class_##_name##_destructor(class_##_name##_t *_T) \ +{ \ + if (_T->lock) { _unlock; } \ +} + + +#define __DEFINE_LOCK_GUARD_1(_name, _type, _lock) \ +static inline class_##_name##_t class_##_name##_constructor(_type *l) \ +{ \ + class_##_name##_t _t = { .lock = l }, *_T = &_t; \ + _lock; \ + return _t; \ +} + +#define __DEFINE_LOCK_GUARD_0(_name, _lock) \ +static inline class_##_name##_t class_##_name##_constructor(void) \ +{ \ + class_##_name##_t _t = { .lock = (void*)1 }, \ + *_T __maybe_unused = &_t; \ + _lock; \ + return _t; \ +} + +#define DEFINE_LOCK_GUARD_1(_name, _type, _lock, _unlock, ...) \ +__DEFINE_UNLOCK_GUARD(_name, _type, _unlock, __VA_ARGS__) \ +__DEFINE_LOCK_GUARD_1(_name, _type, _lock) + +#define DEFINE_LOCK_GUARD_0(_name, _lock, _unlock, ...) \ +__DEFINE_UNLOCK_GUARD(_name, void, _unlock, __VA_ARGS__) \ +__DEFINE_LOCK_GUARD_0(_name, _lock) + +#endif /* __LINUX_GUARDS_H */ diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 15e336281d1f..94fcfefb52f3 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -446,8 +446,8 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, */ #define clk_hw_register_fixed_rate_with_accuracy_parent_hw(dev, name, \ parent_hw, flags, fixed_rate, fixed_accuracy) \ - __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw) \ - NULL, NULL, (flags), (fixed_rate), \ + __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw), \ + NULL, (flags), (fixed_rate), \ (fixed_accuracy), 0, false) /** * clk_hw_register_fixed_rate_with_accuracy_parent_data - register fixed-rate diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 6cfd6902bd5b..9b673fefcef8 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -5,6 +5,15 @@ /* Compiler specific definitions for Clang compiler */ +/* + * Clang prior to 17 is being silly and considers many __cleanup() variables + * as unused (because they are, their sole purpose is to go out of scope). + * + * https://reviews.llvm.org/D152180 + */ +#undef __cleanup +#define __cleanup(func) __maybe_unused __attribute__((__cleanup__(func))) + /* same as gcc, this was present in clang-2.6 so we can assume it works * with any version that can compile the kernel */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index f55a37efdb97..149a520515e1 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,6 +66,26 @@ __builtin_unreachable(); \ } while (0) +/* + * GCC 'asm goto' with outputs miscompiles certain code sequences: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 + * + * Work around it via the same compiler barrier quirk that we used + * to use for the old 'asm goto' workaround. + * + * Also, always mark such 'asm goto' statements as volatile: all + * asm goto statements are supposed to be volatile as per the + * documentation, but some versions of gcc didn't actually do + * that for asms with outputs: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 + */ +#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND +#define asm_goto_output(x...) \ + do { asm volatile goto(x); asm (""); } while (0) +#endif + #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 898b3458b24a..ae4c9579ca5f 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -76,6 +76,12 @@ #endif /* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-cleanup-variable-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#cleanup + */ +#define __cleanup(func) __attribute__((__cleanup__(func))) + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index eb0466236661..574b4121ebe3 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -284,8 +284,15 @@ struct ftrace_likely_data { # define __realloc_size(x, ...) #endif -#ifndef asm_volatile_goto -#define asm_volatile_goto(x...) asm goto(x) +/* + * Some versions of gcc do not mark 'asm goto' volatile: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979 + * + * We do it here by hand, because it doesn't hurt. + */ +#ifndef asm_goto_output +#define asm_goto_output(x...) asm volatile goto(x) #endif #ifdef CONFIG_CC_HAS_ASM_INLINE diff --git a/include/linux/damon.h b/include/linux/damon.h index b13be7ae2275..e6941b239f44 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -8,6 +8,7 @@ #ifndef _DAMON_H_ #define _DAMON_H_ +#include <linux/completion.h> #include <linux/mutex.h> #include <linux/time64.h> #include <linux/types.h> @@ -452,6 +453,8 @@ struct damon_ctx { /* private: internal use only */ struct timespec64 last_aggregation; struct timespec64 last_ops_update; + /* for waiting until the execution of the kdamond_fn is started */ + struct completion kdamond_started; /* public: */ struct task_struct *kdamond; diff --git a/include/linux/device.h b/include/linux/device.h index 7cf24330d681..5520bb546a4a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -30,6 +30,7 @@ #include <linux/device/bus.h> #include <linux/device/class.h> #include <linux/device/driver.h> +#include <linux/cleanup.h> #include <asm/device.h> struct device; @@ -898,6 +899,9 @@ void device_unregister(struct device *dev); void device_initialize(struct device *dev); int __must_check device_add(struct device *dev); void device_del(struct device *dev); + +DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T)) + int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse(struct device *dev, void *data, @@ -1071,6 +1075,9 @@ extern int (*platform_notify_remove)(struct device *dev); */ struct device *get_device(struct device *dev); void put_device(struct device *dev); + +DEFINE_FREE(put_device, struct device *, if (_T) put_device(_T)) + bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 1262d92ab88f..2e71ca35942e 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -37,6 +37,8 @@ dm_bufio_client_create(struct block_device *bdev, unsigned int block_size, */ void dm_bufio_client_destroy(struct dm_bufio_client *c); +void dm_bufio_client_reset(struct dm_bufio_client *c); + /* * Set the sector range. * When this function is called, there must be no I/O in progress on the bufio diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c923f4e60f24..3576c6e89fea 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -954,7 +954,8 @@ static inline int dmaengine_slave_config(struct dma_chan *chan, static inline bool is_slave_direction(enum dma_transfer_direction direction) { - return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM); + return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM) || + (direction == DMA_DEV_TO_DEV); } static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single( diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h index fe7e6ba918f1..29de29af9546 100644 --- a/include/linux/export-internal.h +++ b/include/linux/export-internal.h @@ -12,6 +12,7 @@ #define SYMBOL_CRC(sym, crc, sec) \ asm(".section \"___kcrctab" sec "+" #sym "\",\"a\"" "\n" \ + ".balign 4" "\n" \ "__crc_" #sym ":" "\n" \ ".long " #crc "\n" \ ".previous" "\n") diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index ee0d75d9a302..1e0df607e40c 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -40,9 +40,8 @@ #define F2FS_ENC_UTF8_12_1 1 -#define F2FS_IO_SIZE(sbi) (1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ -#define F2FS_IO_SIZE_KB(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */ -#define F2FS_IO_SIZE_BYTES(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 12)) /* B */ +#define F2FS_IO_SIZE(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ +#define F2FS_IO_SIZE_KB(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits + 2) /* KB */ #define F2FS_IO_SIZE_BITS(sbi) (F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */ #define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1) #define F2FS_IO_ALIGNED(sbi) (F2FS_IO_SIZE(sbi) > 1) @@ -340,7 +339,7 @@ enum { OFFSET_BIT_SHIFT }; -#define OFFSET_BIT_MASK (0x07) /* (0x01 << OFFSET_BIT_SHIFT) - 1 */ +#define OFFSET_BIT_MASK GENMASK(OFFSET_BIT_SHIFT - 1, 0) struct node_footer { __le32 nid; /* node id */ @@ -545,7 +544,7 @@ typedef __le32 f2fs_hash_t; #define MAX_DIR_HASH_DEPTH 63 /* MAX buckets in one level of dir */ -#define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1)) +#define MAX_DIR_BUCKETS BIT((MAX_DIR_HASH_DEPTH / 2) - 1) /* * space utilization of regular dentry and inline dentry (w/o extra reservation) diff --git a/include/linux/file.h b/include/linux/file.h index 39704eae83e2..6e9099d29343 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/posix_types.h> #include <linux/errno.h> +#include <linux/cleanup.h> struct file; @@ -80,6 +81,8 @@ static inline void fdput_pos(struct fd f) fdput(f); } +DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) + extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); @@ -88,6 +91,9 @@ extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); +DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), + get_unused_fd_flags(flags), unsigned flags) + extern void fd_install(unsigned int fd, struct file *file); extern int __receive_fd(struct file *file, int __user *ufd, diff --git a/include/linux/fs.h b/include/linux/fs.h index b6af6abc7a77..67313881f8ac 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -337,6 +337,8 @@ enum rw_hint { #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) struct kiocb { struct file *ki_filp; @@ -2177,6 +2179,7 @@ struct file_operations { int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); + void (*splice_eof)(struct file *file); int (*setlease)(struct file *, long, struct file_lock **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); diff --git a/include/linux/group_cpus.h b/include/linux/group_cpus.h new file mode 100644 index 000000000000..e42807ec61f6 --- /dev/null +++ b/include/linux/group_cpus.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2016 Thomas Gleixner. + * Copyright (C) 2016-2017 Christoph Hellwig. + */ + +#ifndef __LINUX_GROUP_CPUS_H +#define __LINUX_GROUP_CPUS_H +#include <linux/kernel.h> +#include <linux/cpu.h> + +struct cpumask *group_cpus_evenly(unsigned int numgrps); + +#endif diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 41203ce27d64..b566ae420449 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -161,6 +161,11 @@ enum qm_cap_bits { QM_SUPPORT_RPM, }; +struct qm_dev_alg { + u64 alg_msk; + const char *alg; +}; + struct dfx_diff_registers { u32 *regs; u32 reg_offset; @@ -266,6 +271,16 @@ struct hisi_qm_cap_info { u32 v3_val; }; +struct hisi_qm_cap_record { + u32 type; + u32 cap_val; +}; + +struct hisi_qm_cap_tables { + struct hisi_qm_cap_record *qm_cap_table; + struct hisi_qm_cap_record *dev_cap_table; +}; + struct hisi_qm_list { struct mutex lock; struct list_head list; @@ -337,7 +352,6 @@ struct hisi_qm { struct work_struct rst_work; struct work_struct cmd_process; - const char *algs; bool use_sva; bool is_frozen; @@ -348,6 +362,8 @@ struct hisi_qm { struct qm_shaper_factor *factor; u32 mb_qos; u32 type_rate; + + struct hisi_qm_cap_tables cap_tables; }; struct hisi_qp_status { @@ -521,6 +537,8 @@ void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); u32 hisi_qm_get_hw_info(struct hisi_qm *qm, const struct hisi_qm_cap_info *info_table, u32 index, bool is_read); +int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs, + u32 dev_algs_size); /* Used by VFIO ACC live migration driver */ struct pci_driver *hisi_sec_get_pf_driver(void); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index f2044d5a652b..254d4a898179 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -197,6 +197,7 @@ enum hrtimer_base_type { * @max_hang_time: Maximum time spent in hrtimer_interrupt * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are * expired + * @online: CPU is online from an hrtimers point of view * @timer_waiters: A hrtimer_cancel() invocation waits for the timer * callback to finish. * @expires_next: absolute time of the next event, is required for remote @@ -219,7 +220,8 @@ struct hrtimer_cpu_base { unsigned int hres_active : 1, in_hrtirq : 1, hang_detected : 1, - softirq_activated : 1; + softirq_activated : 1, + online : 1; #ifdef CONFIG_HIGH_RES_TIMERS unsigned int nr_events; unsigned short nr_retries; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 870ae4cd8202..dce105f67b4d 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2658,12 +2658,14 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) static inline const struct ieee80211_he_6ghz_oper * ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) { - const u8 *ret = (const void *)&he_oper->optional; + const u8 *ret; u32 he_oper_params; if (!he_oper) return NULL; + ret = (const void *)&he_oper->optional; + he_oper_params = le32_to_cpu(he_oper->he_oper_params); if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)) diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 7852f6c9a714..719cf9cc6e1a 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -8,6 +8,8 @@ #ifndef __AD_SIGMA_DELTA_H__ #define __AD_SIGMA_DELTA_H__ +#include <linux/iio/iio.h> + enum ad_sigma_delta_mode { AD_SD_MODE_CONTINUOUS = 0, AD_SD_MODE_SINGLE = 1, @@ -99,7 +101,7 @@ struct ad_sigma_delta { * 'rx_buf' is up to 32 bits per sample + 64 bit timestamp, * rounded to 16 bytes to take into account padding. */ - uint8_t tx_buf[4] ____cacheline_aligned; + uint8_t tx_buf[4] __aligned(IIO_DMA_MINALIGN); uint8_t rx_buf[16] __aligned(8); }; diff --git a/include/linux/iio/adc/adi-axi-adc.h b/include/linux/iio/adc/adi-axi-adc.h index 52620e5b8052..b7904992d561 100644 --- a/include/linux/iio/adc/adi-axi-adc.h +++ b/include/linux/iio/adc/adi-axi-adc.h @@ -41,6 +41,7 @@ struct adi_axi_adc_chip_info { * @reg_access IIO debugfs_reg_access hook for the client ADC * @read_raw IIO read_raw hook for the client ADC * @write_raw IIO write_raw hook for the client ADC + * @read_avail IIO read_avail hook for the client ADC */ struct adi_axi_adc_conv { const struct adi_axi_adc_chip_info *chip_info; @@ -54,6 +55,9 @@ struct adi_axi_adc_conv { int (*write_raw)(struct adi_axi_adc_conv *conv, struct iio_chan_spec const *chan, int val, int val2, long mask); + int (*read_avail)(struct adi_axi_adc_conv *conv, + struct iio_chan_spec const *chan, + const int **val, int *type, int *length, long mask); }; struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev, diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index db4a1b260348..c34e648f07e2 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -261,9 +261,9 @@ struct st_sensor_data { bool hw_irq_trigger; s64 hw_timestamp; - char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned; - struct mutex odr_lock; + + char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] __aligned(IIO_DMA_MINALIGN); }; #ifdef CONFIG_IIO_BUFFER diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index bcbefb757475..af083aa0c431 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -11,6 +11,7 @@ #include <linux/spi/spi.h> #include <linux/interrupt.h> +#include <linux/iio/iio.h> #include <linux/iio/types.h> #define ADIS_WRITE_REG(reg) ((0x80 | (reg))) @@ -131,7 +132,7 @@ struct adis { unsigned long irq_flag; void *buffer; - u8 tx[10] ____cacheline_aligned; + u8 tx[10] __aligned(IIO_DMA_MINALIGN); u8 rx[4]; }; diff --git a/include/linux/init.h b/include/linux/init.h index 077d7f93b402..c96aea3229ca 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -87,9 +87,6 @@ __latent_entropy #define __meminitdata __section(".meminit.data") #define __meminitconst __section(".meminit.rodata") -#define __memexit __section(".memexit.text") __exitused __cold notrace -#define __memexitdata __section(".memexit.data") -#define __memexitconst __section(".memexit.rodata") /* For assembly routines */ #define __HEAD .section ".head.text","ax" diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 8cd11a223260..136f2980cba3 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -66,6 +66,9 @@ void irq_work_sync(struct irq_work *work); void irq_work_run(void); bool irq_work_needs_cpu(void); void irq_work_single(void *arg); + +void arch_irq_work_raise(void); + #else static inline bool irq_work_needs_cpu(void) { return false; } static inline void irq_work_run(void) { } diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 5ec0fa71399e..2b665c32f5fe 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -13,6 +13,7 @@ #define _LINUX_TRACE_IRQFLAGS_H #include <linux/typecheck.h> +#include <linux/cleanup.h> #include <asm/irqflags.h> #include <asm/percpu.h> @@ -267,4 +268,10 @@ extern void warn_bogus_irq_restore(void); #define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags) +DEFINE_LOCK_GUARD_0(irq, local_irq_disable(), local_irq_enable()) +DEFINE_LOCK_GUARD_0(irqsave, + local_irq_save(_T->flags), + local_irq_restore(_T->flags), + unsigned long flags) + #endif diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index ebb1608d9dcd..6611af5f1d0c 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1374,6 +1374,9 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) +/* Journal high priority write IO operation flags */ +#define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE) + /* * Journal flag definitions */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 6e6f0238d63c..4603e6e30c0e 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -471,10 +471,10 @@ static inline void kasan_free_module_shadow(const struct vm_struct *vm) {} #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) void kasan_non_canonical_hook(unsigned long addr); -#else /* CONFIG_KASAN */ +#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ static inline void kasan_non_canonical_hook(unsigned long addr) { } -#endif /* CONFIG_KASAN */ +#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ #endif /* LINUX_KASAN_H */ diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 7d985a1dfe4a..5caf3ce82373 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -73,6 +73,7 @@ struct key_type { unsigned int flags; #define KEY_TYPE_NET_DOMAIN 0x00000001 /* Keys of this type have a net namespace domain */ +#define KEY_TYPE_INSTANT_REAP 0x00000002 /* Keys of this type don't have a delay after expiring */ /* vet a description */ int (*vet_description)(const char *description); diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 02b19c508b78..6239a378c0ea 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -165,6 +165,8 @@ LSM_HOOK(int, 0, file_alloc_security, struct file *file) LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file) LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd, unsigned long arg) +LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd, + unsigned long arg) LSM_HOOK(int, 0, mmap_addr, unsigned long addr) LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index b0da04fe087b..34dfcc77f505 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -126,10 +126,11 @@ struct cmos_rtc_board_info { #endif /* ARCH_RTC_LOCATION */ bool mc146818_does_rtc_work(void); -int mc146818_get_time(struct rtc_time *time); +int mc146818_get_time(struct rtc_time *time, int timeout); int mc146818_set_time(struct rtc_time *time); bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), + int timeout, void *param); #endif /* _MC146818RTC_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 50ad19662a32..6790f08066b7 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,6 +118,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); int memblock_physmem_add(phys_addr_t base, phys_addr_t size); #endif void memblock_trim_memory(phys_addr_t align); +unsigned long memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, + phys_addr_t base2, phys_addr_t size2); bool memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size); int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3660ce6a9349..93ec34a94b72 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -282,18 +282,23 @@ struct mlx5_cmd_stats { struct mlx5_cmd { struct mlx5_nb nb; + /* members which needs to be queried or reinitialized each reload */ + struct { + u16 cmdif_rev; + u8 log_sz; + u8 log_stride; + int max_reg_cmds; + unsigned long bitmask; + struct semaphore sem; + struct semaphore pages_sem; + struct semaphore throttle_sem; + } vars; enum mlx5_cmdif_state state; void *cmd_alloc_buf; dma_addr_t alloc_dma; int alloc_size; void *cmd_buf; dma_addr_t dma; - u16 cmdif_rev; - u8 log_sz; - u8 log_stride; - int max_reg_cmds; - int events; - u32 __iomem *vector; /* protect command queue allocations */ @@ -303,11 +308,8 @@ struct mlx5_cmd { */ spinlock_t token_lock; u8 token; - unsigned long bitmask; char wq_name[MLX5_CMD_WQ_MAX_NAME]; struct workqueue_struct *wq; - struct semaphore sem; - struct semaphore pages_sem; int mode; u16 allowed_opcode; struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS]; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 323ee36df683..3b9f4d7c40c3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1622,6 +1622,7 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { + struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif @@ -1815,7 +1816,7 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); - return test_bit(idx, ms->usage->subsection_map); + return test_bit(idx, READ_ONCE(ms->usage)->subsection_map); } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) @@ -1839,6 +1840,7 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; + int ret; /* * Ensure the upper PAGE_SHIFT bits are clear in the @@ -1852,13 +1854,19 @@ static inline int pfn_valid(unsigned long pfn) if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); - if (!valid_section(ms)) + rcu_read_lock_sched(); + if (!valid_section(ms)) { + rcu_read_unlock_sched(); return 0; + } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ - return early_section(ms) || pfn_section_valid(ms, pfn); + ret = early_section(ms) || pfn_section_valid(ms, pfn); + rcu_read_unlock_sched(); + + return ret; } #endif diff --git a/include/linux/module.h b/include/linux/module.h index ec61fb53979a..35876e89eb93 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -879,8 +879,17 @@ static inline bool module_sig_ok(struct module *module) } #endif /* CONFIG_MODULE_SIG */ +#if defined(CONFIG_MODULES) && defined(CONFIG_KALLSYMS) int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); +#else +static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_MODULES && CONFIG_KALLSYMS */ #endif /* _LINUX_MODULE_H */ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 8f226d460f51..a33aa9eb9fc3 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -19,6 +19,7 @@ #include <asm/processor.h> #include <linux/osq_lock.h> #include <linux/debug_locks.h> +#include <linux/cleanup.h> #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ @@ -219,4 +220,7 @@ extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); +DEFINE_GUARD(mutex, struct mutex *, mutex_lock(_T), mutex_unlock(_T)) +DEFINE_FREE(mutex, struct mutex *, if (_T) mutex_unlock(_T)) + #endif /* __LINUX_MUTEX_H */ diff --git a/include/linux/namei.h b/include/linux/namei.h index 00fee52df842..5c0149603dc3 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -57,12 +57,18 @@ static inline int user_path_at(int dfd, const char __user *name, unsigned flags, return user_path_at_empty(dfd, name, flags, path, NULL); } +struct dentry *lookup_one_qstr_excl(const struct qstr *name, + struct dentry *base, + unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); +int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, + struct path *parent, struct qstr *last, int *type, + const struct path *root); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); @@ -81,6 +87,7 @@ extern int follow_down(struct path *); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); +extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); extern int __must_check nd_jump_link(const struct path *path); diff --git a/include/linux/net.h b/include/linux/net.h index 18d942bbdf6e..25baca60f6cb 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -209,6 +209,7 @@ struct proto_ops { int offset, size_t size, int flags); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); + void (*splice_eof)(struct socket *sock); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 72f5ebc5c97a..0b217d4ae2a4 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -186,6 +186,8 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Cancel ongoing garbage collectors before destroying the set*/ + void (*cancel_gc)(struct ip_set *set); /* Region-locking is used */ bool region_lock; }; @@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { + /* For call_cru in destroy */ + struct rcu_head rcu; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index f980edfdd278..743475ca7e9d 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -42,7 +42,7 @@ static inline int nf_bridge_get_physinif(const struct sk_buff *skb) if (!nf_bridge) return 0; - return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0; + return nf_bridge->physinif; } static inline int nf_bridge_get_physoutif(const struct sk_buff *skb) @@ -56,11 +56,11 @@ static inline int nf_bridge_get_physoutif(const struct sk_buff *skb) } static inline struct net_device * -nf_bridge_get_physindev(const struct sk_buff *skb) +nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); - return nf_bridge ? nf_bridge->physindev : NULL; + return nf_bridge ? dev_get_by_index_rcu(net, nf_bridge->physinif) : NULL; } static inline struct net_device * diff --git a/include/linux/of.h b/include/linux/of.h index 6b79ef9a6541..1c5301e10442 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1155,7 +1155,8 @@ static inline int of_property_read_string_index(const struct device_node *np, * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. * - * Search for a property in a device node. + * Search for a boolean property in a device node. Usage on non-boolean + * property types is deprecated. * * Return: true if the property exists false otherwise. */ @@ -1168,6 +1169,20 @@ static inline bool of_property_read_bool(const struct device_node *np, } /** + * of_property_present - Test if a property is present in a node + * @np: device node to search for the property. + * @propname: name of the property to be searched. + * + * Test for a property present in a device node. + * + * Return: true if the property exists false otherwise. + */ +static inline bool of_property_present(const struct device_node *np, const char *propname) +{ + return of_property_read_bool(np, propname); +} + +/** * of_property_read_u8_array - Find and read an array of u8 from a property. * * @np: device node from which the property value is to be read. diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 03307b72de6c..1be5a1fa6a3a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -199,6 +199,9 @@ enum mapping_flags { /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, AS_LARGE_FOLIO_SUPPORT = 6, + AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ + AS_STABLE_WRITES, /* must wait for writeback before modifying + folio contents */ }; /** @@ -269,6 +272,36 @@ static inline int mapping_use_writeback_tags(struct address_space *mapping) return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } +static inline bool mapping_release_always(const struct address_space *mapping) +{ + return test_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline void mapping_set_release_always(struct address_space *mapping) +{ + set_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline void mapping_clear_release_always(struct address_space *mapping) +{ + clear_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline bool mapping_stable_writes(const struct address_space *mapping) +{ + return test_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_set_stable_writes(struct address_space *mapping) +{ + set_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_clear_stable_writes(struct address_space *mapping) +{ + clear_bit(AS_STABLE_WRITES, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index b76ff0850618..73cc1e7dd15a 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3000,6 +3000,7 @@ #define PCI_DEVICE_ID_INTEL_82443GX_0 0x71a0 #define PCI_DEVICE_ID_INTEL_82443GX_2 0x71a2 #define PCI_DEVICE_ID_INTEL_82372FB_1 0x7601 +#define PCI_DEVICE_ID_INTEL_HDA_ARL 0x7728 #define PCI_DEVICE_ID_INTEL_SCH_LPC 0x8119 #define PCI_DEVICE_ID_INTEL_SCH_IDE 0x811a #define PCI_DEVICE_ID_INTEL_E6XX_CU 0x8183 diff --git a/include/linux/percpu.h b/include/linux/percpu.h index f1ec5ad1351c..ba00a49369ca 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -8,6 +8,7 @@ #include <linux/cpumask.h> #include <linux/pfn.h> #include <linux/init.h> +#include <linux/cleanup.h> #include <asm/percpu.h> @@ -128,6 +129,9 @@ extern void __init setup_per_cpu_areas(void); extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); extern void free_percpu(void __percpu *__pdata); + +DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) + extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #define alloc_percpu_gfp(type, gfp) \ diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 28b3c6a67397..1f1e7ae95320 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -125,6 +125,22 @@ struct pipe_buf_operations { }; /** + * pipe_has_watch_queue - Check whether the pipe is a watch_queue, + * i.e. it was created with O_NOTIFICATION_PIPE + * @pipe: The pipe to check + * + * Return: true if pipe is a watch queue, false otherwise. + */ +static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) +{ +#ifdef CONFIG_WATCH_QUEUE + return pipe->watch_queue != NULL; +#else + return false; +#endif +} + +/** * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 8cfcc5d45451..9aa6358a1a16 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -8,6 +8,7 @@ */ #include <linux/linkage.h> +#include <linux/cleanup.h> #include <linux/list.h> /* @@ -474,4 +475,8 @@ static __always_inline void preempt_enable_nested(void) preempt_enable(); } +DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable()) +DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace()) +DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) + #endif /* __LINUX_PREEMPT_H */ diff --git a/include/linux/property.h b/include/linux/property.h index 117cc200c656..587b5b666b5b 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -32,7 +32,12 @@ enum dev_dma_attr { DEV_DMA_COHERENT, }; -struct fwnode_handle *dev_fwnode(const struct device *dev); +const struct fwnode_handle *__dev_fwnode_const(const struct device *dev); +struct fwnode_handle *__dev_fwnode(struct device *dev); +#define dev_fwnode(dev) \ + _Generic((dev), \ + const struct device *: __dev_fwnode_const, \ + struct device *: __dev_fwnode)(dev) bool device_property_present(struct device *dev, const char *propname); int device_property_read_u8_array(struct device *dev, const char *propname, diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e9e61cd27ef6..d2507168b9c7 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -27,6 +27,7 @@ #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> +#include <linux/cleanup.h> #include <asm/processor.h> #include <linux/cpumask.h> #include <linux/context_tracking_irq.h> @@ -243,6 +244,18 @@ static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** + * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? + * + * As an accident of implementation, an RCU Tasks Trace grace period also + * acts as an RCU grace period. However, this could change at any time. + * Code relying on this accident must call this function to verify that + * this accident is still happening. + * + * You have been warned! + */ +static inline bool rcu_trace_implies_rcu_gp(void) { return true; } + +/** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to @@ -1065,4 +1078,6 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) extern int rcu_expedited; extern int rcu_normal; +DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock()) + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 2bdba700bc3e..7d1ecd9b4373 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -250,8 +250,8 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound, * guarantee the pinned page won't be randomly replaced in the * future on write faults. */ - if (likely(!is_device_private_page(page) && - unlikely(page_needs_cow_for_dma(vma, page)))) + if (likely(!is_device_private_page(page)) && + unlikely(page_needs_cow_for_dma(vma, page))) return -EBUSY; ClearPageAnonExclusive(page); diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index efa5c324369a..1dd530ce8b45 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -15,6 +15,7 @@ #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/err.h> +#include <linux/cleanup.h> #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __RWSEM_DEP_MAP_INIT(lockname) \ @@ -201,6 +202,13 @@ extern void up_read(struct rw_semaphore *sem); */ extern void up_write(struct rw_semaphore *sem); +DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T)) +DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T)) + +DEFINE_FREE(up_read, struct rw_semaphore *, if (_T) up_read(_T)) +DEFINE_FREE(up_write, struct rw_semaphore *, if (_T) up_write(_T)) + + /* * downgrade write lock to read lock */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 7291fb6399d2..aaa25ed1a8fe 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -145,6 +145,8 @@ static inline void put_task_struct(struct task_struct *t) __put_task_struct(t); } +DEFINE_FREE(put_task, struct task_struct *, if (_T) put_task_struct(_T)) + static inline void put_task_struct_many(struct task_struct *t, int nr) { if (refcount_sub_and_test(nr, &t->usage)) diff --git a/include/linux/security.h b/include/linux/security.h index a6c97cc57caa..2772f6375f14 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -385,6 +385,8 @@ int security_file_permission(struct file *file, int mask); int security_file_alloc(struct file *file); void security_file_free(struct file *file); int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +int security_file_ioctl_compat(struct file *file, unsigned int cmd, + unsigned long arg); int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags); int security_mmap_addr(unsigned long addr); @@ -969,6 +971,13 @@ static inline int security_file_ioctl(struct file *file, unsigned int cmd, return 0; } +static inline int security_file_ioctl_compat(struct file *file, + unsigned int cmd, + unsigned long arg) +{ + return 0; +} + static inline int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index d657f2a42a7b..13bf20242b61 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -583,6 +583,85 @@ struct uart_port { void *private_data; /* generic platform data pointer */ }; +/** + * uart_port_lock - Lock the UART port + * @up: Pointer to UART port structure + */ +static inline void uart_port_lock(struct uart_port *up) +{ + spin_lock(&up->lock); +} + +/** + * uart_port_lock_irq - Lock the UART port and disable interrupts + * @up: Pointer to UART port structure + */ +static inline void uart_port_lock_irq(struct uart_port *up) +{ + spin_lock_irq(&up->lock); +} + +/** + * uart_port_lock_irqsave - Lock the UART port, save and disable interrupts + * @up: Pointer to UART port structure + * @flags: Pointer to interrupt flags storage + */ +static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) +{ + spin_lock_irqsave(&up->lock, *flags); +} + +/** + * uart_port_trylock - Try to lock the UART port + * @up: Pointer to UART port structure + * + * Returns: True if lock was acquired, false otherwise + */ +static inline bool uart_port_trylock(struct uart_port *up) +{ + return spin_trylock(&up->lock); +} + +/** + * uart_port_trylock_irqsave - Try to lock the UART port, save and disable interrupts + * @up: Pointer to UART port structure + * @flags: Pointer to interrupt flags storage + * + * Returns: True if lock was acquired, false otherwise + */ +static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long *flags) +{ + return spin_trylock_irqsave(&up->lock, *flags); +} + +/** + * uart_port_unlock - Unlock the UART port + * @up: Pointer to UART port structure + */ +static inline void uart_port_unlock(struct uart_port *up) +{ + spin_unlock(&up->lock); +} + +/** + * uart_port_unlock_irq - Unlock the UART port and re-enable interrupts + * @up: Pointer to UART port structure + */ +static inline void uart_port_unlock_irq(struct uart_port *up) +{ + spin_unlock_irq(&up->lock); +} + +/** + * uart_port_unlock_irqrestore - Unlock the UART port, restore interrupts + * @up: Pointer to UART port structure + * @flags: The saved interrupt flags for restore + */ +static inline void uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) +{ + spin_unlock_irqrestore(&up->lock, flags); +} + static inline int serial_port_in(struct uart_port *up, int offset) { return up->serial_in(up, offset); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2feee144fc0e..c30d419ebf54 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -301,7 +301,7 @@ struct nf_bridge_info { u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; - struct net_device *physindev; + int physinif; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c1637515a8a4..bd4418377bac 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -106,6 +106,7 @@ struct sk_psock { struct mutex work_mutex; struct sk_psock_work_state work_state; struct delayed_work work; + struct sock *sk_pair; struct rcu_work rwork; }; @@ -499,12 +500,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return !!psock->saved_data_ready; } -static inline bool sk_is_udp(const struct sock *sk) -{ - return sk->sk_type == SOCK_DGRAM && - sk->sk_protocol == IPPROTO_UDP; -} - #if IS_ENABLED(CONFIG_NET_SOCK_MSG) #define BPF_F_STRPARSER (1UL << 1) diff --git a/include/linux/slab.h b/include/linux/slab.h index 45efc6c553b8..cb4b5deca9a9 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> +#include <linux/cleanup.h> /* @@ -197,6 +198,8 @@ void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); +DEFINE_FREE(kfree, void *, if (_T) kfree(_T)) + /** * ksize - Report actual allocation size of associated object * diff --git a/include/linux/socket.h b/include/linux/socket.h index 1db29aab8f9c..d79efd026880 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -33,7 +33,10 @@ typedef __kernel_sa_family_t sa_family_t; struct sockaddr { sa_family_t sa_family; /* address family, AF_xxx */ - char sa_data[14]; /* 14 bytes of protocol address */ + union { + char sa_data_min[14]; /* Minimum 14 bytes of protocol address */ + DECLARE_FLEX_ARRAY(char, sa_data); + }; }; struct linger { @@ -324,6 +327,7 @@ struct ucred { */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ +#define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file descriptor received through @@ -334,6 +338,8 @@ struct ucred { #define MSG_CMSG_COMPAT 0 /* We never have 32 bit fixups */ #endif +/* Flags to be cleared on entry by sendmsg and sendmmsg syscalls */ +#define MSG_INTERNAL_SENDMSG_FLAGS (MSG_SPLICE_PAGES) /* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */ #define SOL_IP 0 diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 877395e075af..8e9054d9f6df 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -263,6 +263,26 @@ static inline void *spi_get_drvdata(struct spi_device *spi) return dev_get_drvdata(&spi->dev); } +static inline u8 spi_get_chipselect(const struct spi_device *spi, u8 idx) +{ + return spi->chip_select; +} + +static inline void spi_set_chipselect(struct spi_device *spi, u8 idx, u8 chipselect) +{ + spi->chip_select = chipselect; +} + +static inline struct gpio_desc *spi_get_csgpiod(const struct spi_device *spi, u8 idx) +{ + return spi->cs_gpiod; +} + +static inline void spi_set_csgpiod(struct spi_device *spi, u8 idx, struct gpio_desc *csgpiod) +{ + spi->cs_gpiod = csgpiod; +} + struct spi_message; /** @@ -1515,6 +1535,9 @@ extern void spi_unregister_device(struct spi_device *spi); extern const struct spi_device_id * spi_get_device_id(const struct spi_device *sdev); +extern const void * +spi_get_device_match_data(const struct spi_device *sdev); + static inline bool spi_transfer_is_last(struct spi_controller *ctlr, struct spi_transfer *xfer) { diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 1341f7d62da4..83377540c369 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -61,6 +61,7 @@ #include <linux/stringify.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> +#include <linux/cleanup.h> #include <asm/barrier.h> #include <asm/mmiowb.h> @@ -493,5 +494,35 @@ int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, void free_bucket_spinlocks(spinlock_t *locks); +DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t, + raw_spin_lock(_T->lock), + raw_spin_unlock(_T->lock)) + +DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t, + raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING), + raw_spin_unlock(_T->lock)) + +DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t, + raw_spin_lock_irq(_T->lock), + raw_spin_unlock_irq(_T->lock)) + +DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t, + raw_spin_lock_irqsave(_T->lock, _T->flags), + raw_spin_unlock_irqrestore(_T->lock, _T->flags), + unsigned long flags) + +DEFINE_LOCK_GUARD_1(spinlock, spinlock_t, + spin_lock(_T->lock), + spin_unlock(_T->lock)) + +DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t, + spin_lock_irq(_T->lock), + spin_unlock_irq(_T->lock)) + +DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t, + spin_lock_irqsave(_T->lock, _T->flags), + spin_unlock_irqrestore(_T->lock, _T->flags), + unsigned long flags) + #undef __LINUX_INSIDE_SPINLOCK_H #endif /* __LINUX_SPINLOCK_H */ diff --git a/include/linux/splice.h b/include/linux/splice.h index a55179fd60fc..41a70687be85 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -38,6 +38,7 @@ struct splice_desc { struct file *file; /* file to read/write */ void *data; /* cookie */ } u; + void (*splice_eof)(struct splice_desc *sd); /* Unexpected EOF handler */ loff_t pos; /* file position */ loff_t *opos; /* sendfile: output position */ size_t num_spliced; /* number of bytes already spliced */ diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 01226e4d960a..f9e1fa7ff86f 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -212,4 +212,9 @@ static inline void smp_mb__after_srcu_read_unlock(void) /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } +DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, + _T->idx = srcu_read_lock(_T->lock), + srcu_read_unlock(_T->lock, _T->idx), + int idx) + #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index a18cf4b7c724..add47f43e568 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -571,6 +571,11 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } +static inline int swapcache_prepare(swp_entry_t swp) +{ + return 0; +} + static inline void swap_free(swp_entry_t swp) { } diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a34b0f9a9972..27a6ba1c0ec4 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -123,6 +123,7 @@ enum landlock_rule_type; #define __TYPE_IS_LL(t) (__TYPE_AS(t, 0LL) || __TYPE_AS(t, 0ULL)) #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a #define __SC_CAST(t, a) (__force t) a +#define __SC_TYPE(t, a) t #define __SC_ARGS(t, a) a #define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long)) diff --git a/include/linux/udp.h b/include/linux/udp.h index e96da4157d04..efd9ab6df379 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -30,25 +30,33 @@ static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) return (num + net_hash_mix(net)) & mask; } +enum { + UDP_FLAGS_CORK, /* Cork is required */ + UDP_FLAGS_NO_CHECK6_TX, /* Send zero UDP6 checksums on TX? */ + UDP_FLAGS_NO_CHECK6_RX, /* Allow zero UDP6 checksums on RX? */ + UDP_FLAGS_GRO_ENABLED, /* Request GRO aggregation */ + UDP_FLAGS_ACCEPT_FRAGLIST, + UDP_FLAGS_ACCEPT_L4, + UDP_FLAGS_ENCAP_ENABLED, /* This socket enabled encap */ +}; + struct udp_sock { /* inet_sock has to be the first member */ struct inet_sock inet; #define udp_port_hash inet.sk.__sk_common.skc_u16hashes[0] #define udp_portaddr_hash inet.sk.__sk_common.skc_u16hashes[1] #define udp_portaddr_node inet.sk.__sk_common.skc_portaddr_node + + unsigned long udp_flags; + int pending; /* Any pending frames ? */ - unsigned int corkflag; /* Cork is required */ __u8 encap_type; /* Is this an Encapsulation socket? */ - unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ - no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ - encap_enabled:1, /* This socket enabled encap - * processing; UDP tunnels and - * different encapsulation layer set - * this - */ - gro_enabled:1, /* Request GRO aggregation */ - accept_udp_l4:1, - accept_udp_fraglist:1; + +/* indicator bits used by pcflag: */ +#define UDPLITE_BIT 0x1 /* set by udplite proto init function */ +#define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ +#define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ + __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. @@ -60,12 +68,6 @@ struct udp_sock { */ __u16 pcslen; __u16 pcrlen; -/* indicator bits used by pcflag: */ -#define UDPLITE_BIT 0x1 /* set by udplite proto init function */ -#define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ -#define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ - __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ - __u8 unused[3]; /* * For encapsulation sockets. */ @@ -89,6 +91,17 @@ struct udp_sock { int forward_deficit; }; +#define udp_test_bit(nr, sk) \ + test_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_set_bit(nr, sk) \ + set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_test_and_set_bit(nr, sk) \ + test_and_set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_clear_bit(nr, sk) \ + clear_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_assign_bit(nr, sk, val) \ + assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) + #define UDP_MAX_SEGMENTS (1 << 6UL) static inline struct udp_sock *udp_sk(const struct sock *sk) @@ -98,22 +111,22 @@ static inline struct udp_sock *udp_sk(const struct sock *sk) static inline void udp_set_no_check6_tx(struct sock *sk, bool val) { - udp_sk(sk)->no_check6_tx = val; + udp_assign_bit(NO_CHECK6_TX, sk, val); } static inline void udp_set_no_check6_rx(struct sock *sk, bool val) { - udp_sk(sk)->no_check6_rx = val; + udp_assign_bit(NO_CHECK6_RX, sk, val); } -static inline bool udp_get_no_check6_tx(struct sock *sk) +static inline bool udp_get_no_check6_tx(const struct sock *sk) { - return udp_sk(sk)->no_check6_tx; + return udp_test_bit(NO_CHECK6_TX, sk); } -static inline bool udp_get_no_check6_rx(struct sock *sk) +static inline bool udp_get_no_check6_rx(const struct sock *sk) { - return udp_sk(sk)->no_check6_rx; + return udp_test_bit(NO_CHECK6_RX, sk); } static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, @@ -132,10 +145,12 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) if (!skb_is_gso(skb)) return false; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && !udp_sk(sk)->accept_udp_l4) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + !udp_test_bit(ACCEPT_L4, sk)) return true; - if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist) + if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && + !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; return false; @@ -143,8 +158,8 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) static inline void udp_allow_gso(struct sock *sk) { - udp_sk(sk)->accept_udp_l4 = 1; - udp_sk(sk)->accept_udp_fraglist = 1; + udp_set_bit(ACCEPT_L4, sk); + udp_set_bit(ACCEPT_FRAGLIST, sk); } #define udp_portaddr_for_each_entry(__sk, list) \ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 480fa579787e..0920b669b9b3 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -45,12 +45,6 @@ struct scm_stat { #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) -#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) -#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) -#define unix_state_lock_nested(s) \ - spin_lock_nested(&unix_sk(s)->lock, \ - SINGLE_DEPTH_NESTING) - /* The AF_UNIX socket */ struct unix_sock { /* WARNING: sk has to be the first member */ @@ -77,6 +71,21 @@ static inline struct unix_sock *unix_sk(const struct sock *sk) { return (struct unix_sock *)sk; } +#define unix_peer(sk) (unix_sk(sk)->peer) + +#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) +#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) +enum unix_socket_lock_class { + U_LOCK_NORMAL, + U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ + U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ +}; + +static inline void unix_state_lock_nested(struct sock *sk, + enum unix_socket_lock_class subclass) +{ + spin_lock_nested(&unix_sk(sk)->lock, subclass); +} #define peer_wait peer_wq.wait diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 583aebd8c1e0..09c978f3d95d 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -187,6 +187,7 @@ struct blocked_key { struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; + u8 link_type; u8 type; u8 val[16]; }; @@ -196,6 +197,7 @@ struct smp_ltk { struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; + u8 link_type; u8 authenticated; u8 type; u8 enc_size; @@ -210,6 +212,7 @@ struct smp_irk { bdaddr_t rpa; bdaddr_t bdaddr; u8 addr_type; + u8 link_type; u8 val[16]; }; @@ -217,6 +220,8 @@ struct link_key { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; + u8 bdaddr_type; + u8 link_type; u8 type; u8 val[HCI_LINK_KEY_SIZE]; u8 pin_len; @@ -937,7 +942,6 @@ void hci_inquiry_cache_flush(struct hci_dev *hdev); /* ----- HCI Connections ----- */ enum { HCI_CONN_AUTH_PEND, - HCI_CONN_REAUTH_PEND, HCI_CONN_ENCRYPT_PEND, HCI_CONN_RSWITCH_PEND, HCI_CONN_MODE_CHANGE_PEND, diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 88ff7bb2bb9b..632086b2f644 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -16,7 +16,7 @@ struct dst_ops { unsigned short family; unsigned int gc_thresh; - int (*gc)(struct dst_ops *ops); + void (*gc)(struct dst_ops *ops); struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); unsigned int (*mtu)(const struct dst_entry *); diff --git a/include/net/inet_common.h b/include/net/inet_common.h index cec453c18f1d..4673bbfd2811 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -33,6 +33,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags, bool kern); int inet_send_prepare(struct sock *sk); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); +void inet_splice_eof(struct socket *sock); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c2b15f7e5516..080968d6e6c5 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -346,4 +346,12 @@ static inline bool inet_csk_has_ulp(struct sock *sk) return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops; } +static inline void inet_init_csk_locks(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + spin_lock_init(&icsk->icsk_accept_queue.rskq_lock); + spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock); +} + #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c2432c2addc8..c98890e21401 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -270,11 +270,6 @@ struct inet_sock { #define IP_CMSG_CHECKSUM BIT(7) #define IP_CMSG_RECVFRAGSIZE BIT(8) -static inline bool sk_is_inet(struct sock *sk) -{ - return sk->sk_family == AF_INET || sk->sk_family == AF_INET6; -} - /** * sk_to_full_sk - Access to a full socket * @sk: pointer to a socket diff --git a/include/net/ip.h b/include/net/ip.h index c286344628db..4f11f7df7dd6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -95,7 +95,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm_init(ipcm); ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark); - ipcm->sockc.tsflags = inet->sk.sk_tsflags; + ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags); ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; ipcm->protocol = inet->inet_num; @@ -752,7 +752,7 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev); * Functions provided by ip_sockglue.c */ -void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb); +void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst); void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, int tlen, int offset); int ip_cmsg_send(struct sock *sk, struct msghdr *msg, diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 49aa79c7b278..581cd37aa98b 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -262,8 +262,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, */ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) { - if (skb->protocol == htons(ETH_P_802_2)) - memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN); + memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN); } /** @@ -275,8 +274,7 @@ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) */ static inline void llc_pdu_decode_da(struct sk_buff *skb, u8 *da) { - if (skb->protocol == htons(ETH_P_802_2)) - memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN); + memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN); } /** diff --git a/include/net/netfilter/nf_conntrack_act_ct.h b/include/net/netfilter/nf_conntrack_act_ct.h index 078d3c52c03f..e5f2f0b73a9a 100644 --- a/include/net/netfilter/nf_conntrack_act_ct.h +++ b/include/net/netfilter/nf_conntrack_act_ct.h @@ -20,7 +20,22 @@ static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_find(const struct nf #endif } -static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct nf_conn *ct) +static inline void nf_conn_act_ct_ext_fill(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ +#if IS_ENABLED(CONFIG_NET_ACT_CT) + struct nf_conn_act_ct_ext *act_ct_ext; + + act_ct_ext = nf_conn_act_ct_ext_find(ct); + if (dev_net(skb->dev) == &init_net && act_ct_ext) + act_ct_ext->ifindex[CTINFO2DIR(ctinfo)] = skb->dev->ifindex; +#endif +} + +static inline struct +nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) { #if IS_ENABLED(CONFIG_NET_ACT_CT) struct nf_conn_act_ct_ext *act_ct = nf_ct_ext_find(ct, NF_CT_EXT_ACT_CT); @@ -29,22 +44,11 @@ static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct nf_conn * return act_ct; act_ct = nf_ct_ext_add(ct, NF_CT_EXT_ACT_CT, GFP_ATOMIC); + nf_conn_act_ct_ext_fill(skb, ct, ctinfo); return act_ct; #else return NULL; #endif } -static inline void nf_conn_act_ct_ext_fill(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ -#if IS_ENABLED(CONFIG_NET_ACT_CT) - struct nf_conn_act_ct_ext *act_ct_ext; - - act_ct_ext = nf_conn_act_ct_ext_find(ct); - if (dev_net(skb->dev) == &init_net && act_ct_ext) - act_ct_ext->ifindex[CTINFO2DIR(ctinfo)] = skb->dev->ifindex; -#endif -} - #endif /* _NF_CONNTRACK_ACT_CT_H */ diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index cd982f4a0f50..4a767b3d20b9 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -53,14 +53,17 @@ struct nf_flowtable_type { struct list_head list; int family; int (*init)(struct nf_flowtable *ft); + bool (*gc)(const struct flow_offload *flow); int (*setup)(struct nf_flowtable *ft, struct net_device *dev, enum flow_block_command cmd); int (*action)(struct net *net, - const struct flow_offload *flow, + struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); void (*free)(struct nf_flowtable *ft); + void (*get)(struct nf_flowtable *ft); + void (*put)(struct nf_flowtable *ft); nf_hookfn *hook; struct module *owner; }; @@ -164,6 +167,8 @@ enum nf_flow_flags { NF_FLOW_HW_DYING, NF_FLOW_HW_DEAD, NF_FLOW_HW_PENDING, + NF_FLOW_HW_BIDIRECTIONAL, + NF_FLOW_HW_ESTABLISHED, }; enum flow_offload_type { @@ -237,6 +242,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, } list_add_tail(&block_cb->list, &block->cb_list); + up_write(&flow_table->flow_block_lock); + + if (flow_table->type->get) + flow_table->type->get(flow_table); + return 0; unlock: up_write(&flow_table->flow_block_lock); @@ -259,14 +269,17 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, WARN_ON(true); } up_write(&flow_table->flow_block_lock); + + if (flow_table->type->put) + flow_table->type->put(flow_table); } -int flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route); +void flow_offload_route_init(struct flow_offload *flow, + struct nf_flow_route *route); int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, - struct flow_offload *flow); + struct flow_offload *flow, bool force); struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); @@ -312,10 +325,10 @@ void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable); int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, struct net_device *dev, enum flow_block_command cmd); -int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); -int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c726da3b7d68..2fa344cb66f6 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1286,6 +1286,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, * @type: stateful object numeric type * @owner: module owner * @maxattr: maximum netlink attribute + * @family: address family for AF-specific object types * @policy: netlink attribute policy */ struct nft_object_type { @@ -1295,6 +1296,7 @@ struct nft_object_type { struct list_head list; u32 type; unsigned int maxattr; + u8 family; struct module *owner; const struct nla_policy *policy; }; diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index c4a6147b0ef8..5225d2bd1a6e 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -29,8 +29,8 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) if (iph->ihl < 5 || iph->version != 4) return -1; - len = ntohs(iph->tot_len); - thoff = iph->ihl * 4; + len = iph_totlen(pkt->skb, iph); + thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4); if (pkt->skb->len < len) return -1; else if (len < thoff) @@ -62,7 +62,7 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt) if (iph->ihl < 5 || iph->version != 4) goto inhdr_error; - len = ntohs(iph->tot_len); + len = iph_totlen(pkt->skb, iph); thoff = iph->ihl * 4; if (pkt->skb->len < len) { __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS); diff --git a/include/net/sock.h b/include/net/sock.h index b6027b01c245..579732d47dfc 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1279,6 +1279,7 @@ struct proto { size_t len, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); + void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*bind_add)(struct sock *sk, @@ -1928,7 +1929,9 @@ struct sockcm_cookie { static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { - *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags }; + *sockc = (struct sockcm_cookie) { + .tsflags = READ_ONCE(sk->sk_tsflags) + }; } int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, @@ -2741,9 +2744,9 @@ void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { - ktime_t kt = skb->tstamp; struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); - + u32 tsflags = READ_ONCE(sk->sk_tsflags); + ktime_t kt = skb->tstamp; /* * generate control messages if * - receive time stamping in software requested @@ -2751,10 +2754,10 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) * - hardware time stamps available and wanted */ if (sock_flag(sk, SOCK_RCVTSTAMP) || - (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || - (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) || + (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || + (kt && tsflags & SOF_TIMESTAMPING_SOFTWARE) || (hwtstamps->hwtstamp && - (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) + (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else sock_write_timestamp(sk, kt); @@ -2776,7 +2779,8 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) - if (sk->sk_flags & FLAGS_RECV_CMSGS || sk->sk_tsflags & TSFLAGS_ANY) + if (sk->sk_flags & FLAGS_RECV_CMSGS || + READ_ONCE(sk->sk_tsflags) & TSFLAGS_ANY) __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); @@ -2820,9 +2824,30 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } +static inline bool sk_is_inet(const struct sock *sk) +{ + int family = READ_ONCE(sk->sk_family); + + return family == AF_INET || family == AF_INET6; +} + static inline bool sk_is_tcp(const struct sock *sk) { - return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; + return sk_is_inet(sk) && + sk->sk_type == SOCK_STREAM && + sk->sk_protocol == IPPROTO_TCP; +} + +static inline bool sk_is_udp(const struct sock *sk) +{ + return sk_is_inet(sk) && + sk->sk_type == SOCK_DGRAM && + sk->sk_protocol == IPPROTO_UDP; +} + +static inline bool sk_is_stream_unix(const struct sock *sk) +{ + return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM; } /** diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 7dcdc97c0bc3..a3d8f013adcd 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -303,6 +303,9 @@ void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct netlink_ext_ack *extack); +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj); int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack); diff --git a/include/net/tcp.h b/include/net/tcp.h index c3d56b337f35..8ea1fba84eff 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -332,6 +332,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg); +void tcp_splice_eof(struct socket *sock); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, @@ -2289,7 +2290,7 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ - int (*get_info)(const struct sock *sk, struct sk_buff *skb); + int (*get_info)(struct sock *sk, struct sk_buff *skb); size_t (*get_info_size)(const struct sock *sk); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, diff --git a/include/net/tls.h b/include/net/tls.h index c36bf4c50027..899c863aba02 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -108,9 +108,6 @@ struct tls_sw_context_tx { struct tls_rec *open_rec; struct list_head tx_list; atomic_t encrypt_pending; - /* protect crypto_wait with encrypt_pending */ - spinlock_t encrypt_compl_lock; - int async_notify; u8 async_capable:1; #define BIT_TX_SCHEDULED 0 @@ -147,8 +144,6 @@ struct tls_sw_context_rx { struct tls_strparser strp; atomic_t decrypt_pending; - /* protect crypto_wait with decrypt_pending*/ - spinlock_t decrypt_compl_lock; struct sk_buff_head async_hold; struct wait_queue_head wq; }; diff --git a/include/net/udp.h b/include/net/udp.h index fee053bcd17c..fa4cdbe55552 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -269,6 +269,7 @@ int udp_get_port(struct sock *sk, unsigned short snum, int udp_err(struct sk_buff *, u32); int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); +void udp_splice_eof(struct socket *sock); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 72394f441dad..e5f81710b18f 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -174,16 +174,13 @@ static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) } #endif -static inline void udp_tunnel_encap_enable(struct socket *sock) +static inline void udp_tunnel_encap_enable(struct sock *sk) { - struct udp_sock *up = udp_sk(sock->sk); - - if (up->encap_enabled) + if (udp_test_and_set_bit(ENCAP_ENABLED, sk)) return; - up->encap_enabled = 1; #if IS_ENABLED(CONFIG_IPV6) - if (sock->sk->sk_family == PF_INET6) + if (READ_ONCE(sk->sk_family) == PF_INET6) ipv6_stub->udpv6_encap_enable(); #endif udp_encap_enable(); diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index fdc31fdb612d..d2751ed536df 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -100,10 +100,6 @@ struct scsi_vpd { unsigned char data[]; }; -enum scsi_vpd_parameters { - SCSI_VPD_HEADER_SIZE = 4, -}; - struct scsi_device { struct Scsi_Host *host; struct request_queue *request_queue; diff --git a/include/trace/events/9p.h b/include/trace/events/9p.h index 4dfa6d7f83ba..cd104a1343e2 100644 --- a/include/trace/events/9p.h +++ b/include/trace/events/9p.h @@ -178,18 +178,21 @@ TRACE_EVENT(9p_protocol_dump, __field( void *, clnt ) __field( __u8, type ) __field( __u16, tag ) - __array( unsigned char, line, P9_PROTO_DUMP_SZ ) + __dynamic_array(unsigned char, line, + min_t(size_t, pdu->capacity, P9_PROTO_DUMP_SZ)) ), TP_fast_assign( __entry->clnt = clnt; __entry->type = pdu->id; __entry->tag = pdu->tag; - memcpy(__entry->line, pdu->sdata, P9_PROTO_DUMP_SZ); + memcpy(__get_dynamic_array(line), pdu->sdata, + __get_dynamic_array_len(line)); ), - TP_printk("clnt %lu %s(tag = %d)\n%.3x: %16ph\n%.3x: %16ph\n", + TP_printk("clnt %lu %s(tag = %d)\n%*ph\n", (unsigned long)__entry->clnt, show_9p_op(__entry->type), - __entry->tag, 0, __entry->line, 16, __entry->line + 16) + __entry->tag, __get_dynamic_array_len(line), + __get_dynamic_array(line)) ); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 92dbe89dafbf..201dc77ebbd7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4353,6 +4353,8 @@ union bpf_attr { * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags) * Description * Return a user or a kernel stack in bpf program provided buffer. + * Note: the user stack will only be populated if the *task* is + * the current task; all other tasks will return -EOPNOTSUPP. * To achieve this, the helper needs *task*, which is a valid * pointer to **struct task_struct**. To store the stacktrace, the * bpf program provides *buf* with a nonnegative *size*. @@ -4364,6 +4366,7 @@ union bpf_attr { * * **BPF_F_USER_STACK** * Collect a user space stack instead of a kernel stack. + * The *task* must be the current task. * **BPF_F_USER_BUILD_ID** * Collect buildid+offset instead of ips for user stack, * only valid if **BPF_F_USER_STACK** is also specified. diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index d4d4fa0bb362..24b54635bae9 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -585,6 +585,9 @@ struct btrfs_ioctl_clone_range_args { */ #define BTRFS_DEFRAG_RANGE_COMPRESS 1 #define BTRFS_DEFRAG_RANGE_START_IO 2 +#define BTRFS_DEFRAG_RANGE_FLAGS_SUPP (BTRFS_DEFRAG_RANGE_COMPRESS | \ + BTRFS_DEFRAG_RANGE_START_IO) + struct btrfs_ioctl_defrag_range_args { /* start of the defrag operation */ __u64 start; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index af8f4c304d27..707af820f1a9 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -266,9 +266,11 @@ enum nft_rule_attributes { /** * enum nft_rule_compat_flags - nf_tables rule compat flags * + * @NFT_RULE_COMPAT_F_UNUSED: unused * @NFT_RULE_COMPAT_F_INV: invert the check result */ enum nft_rule_compat_flags { + NFT_RULE_COMPAT_F_UNUSED = (1 << 0), NFT_RULE_COMPAT_F_INV = (1 << 1), NFT_RULE_COMPAT_F_MASK = NFT_RULE_COMPAT_F_INV, }; diff --git a/init/Kconfig b/init/Kconfig index de255842f5d0..ffb927bf6034 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -89,6 +89,15 @@ config CC_HAS_ASM_GOTO_TIED_OUTPUT # Detect buggy gcc and clang, fixed in gcc-11 clang-14. def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) +config GCC_ASM_GOTO_OUTPUT_WORKAROUND + bool + depends on CC_IS_GCC && CC_HAS_ASM_GOTO_OUTPUT + # Fixed in GCC 14, 13.3, 12.4 and 11.5 + # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 + default y if GCC_VERSION < 110500 + default y if GCC_VERSION >= 120000 && GCC_VERSION < 120400 + default y if GCC_VERSION >= 130000 && GCC_VERSION < 130300 + config TOOLS_SUPPORT_RELR def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh) @@ -1914,7 +1923,7 @@ config RUST depends on !MODVERSIONS depends on !GCC_PLUGINS depends on !RANDSTRUCT - depends on !DEBUG_INFO_BTF + depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE select CONSTRUCTORS help Enables Rust support in the kernel. diff --git a/init/do_mounts.c b/init/do_mounts.c index 811e94daf0a8..2d705b9c8400 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -665,7 +665,10 @@ struct file_system_type rootfs_fs_type = { void __init init_rootfs(void) { - if (IS_ENABLED(CONFIG_TMPFS) && !saved_root_name[0] && - (!root_fs_names || strstr(root_fs_names, "tmpfs"))) - is_tmpfs = true; + if (IS_ENABLED(CONFIG_TMPFS)) { + if (!saved_root_name[0] && !root_fs_names) + is_tmpfs = true; + else if (root_fs_names && !!strstr(root_fs_names, "tmpfs")) + is_tmpfs = true; + } } diff --git a/io_uring/net.c b/io_uring/net.c index 57c626cb4d1a..c062ce66af12 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -389,6 +389,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) if (flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg.msg_flags = flags; ret = sock_sendmsg(sock, &msg); if (ret < min_ret) { @@ -874,6 +875,7 @@ retry_multishot: if (!buf) return -ENOBUFS; sr->buf = buf; + sr->len = len; } ret = import_single_range(ITER_DEST, sr->buf, len, &iov, &msg.msg_iter); @@ -1137,6 +1139,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags) msg_flags |= MSG_DONTWAIT; if (msg_flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); + msg_flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg.msg_flags = msg_flags; msg.msg_ubuf = &io_notif_to_data(zc->notif)->uarg; @@ -1323,7 +1326,7 @@ retry: * has already been done */ if (issue_flags & IO_URING_F_MULTISHOT) - ret = IOU_ISSUE_SKIP_COMPLETE; + return IOU_ISSUE_SKIP_COMPLETE; return ret; } if (ret == -ERESTARTSYS) @@ -1347,7 +1350,8 @@ retry: if (io_post_aux_cqe(ctx, req->cqe.user_data, ret, IORING_CQE_F_MORE, false)) goto retry; - return -ECANCELED; + io_req_set_res(req, ret, 0); + return IOU_STOP_MULTISHOT; } int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) diff --git a/io_uring/rw.c b/io_uring/rw.c index 0133db648d8e..038e6b13a749 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -534,15 +534,19 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) struct iovec *iov; int ret; + iorw->bytes_done = 0; + iorw->free_iovec = NULL; + /* submission path, ->uring_lock should already be taken */ ret = io_import_iovec(rw, req, &iov, &iorw->s, 0); if (unlikely(ret < 0)) return ret; - iorw->bytes_done = 0; - iorw->free_iovec = iov; - if (iov) + if (iov) { + iorw->free_iovec = iov; req->flags |= REQ_F_NEED_CLEANUP; + } + return 0; } diff --git a/kernel/async.c b/kernel/async.c index b2c4ba5686ee..673bba6bdf3a 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -145,6 +145,39 @@ static void async_run_entry_fn(struct work_struct *work) wake_up(&async_done); } +static async_cookie_t __async_schedule_node_domain(async_func_t func, + void *data, int node, + struct async_domain *domain, + struct async_entry *entry) +{ + async_cookie_t newcookie; + unsigned long flags; + + INIT_LIST_HEAD(&entry->domain_list); + INIT_LIST_HEAD(&entry->global_list); + INIT_WORK(&entry->work, async_run_entry_fn); + entry->func = func; + entry->data = data; + entry->domain = domain; + + spin_lock_irqsave(&async_lock, flags); + + /* allocate cookie and queue */ + newcookie = entry->cookie = next_cookie++; + + list_add_tail(&entry->domain_list, &domain->pending); + if (domain->registered) + list_add_tail(&entry->global_list, &async_global_pending); + + atomic_inc(&entry_count); + spin_unlock_irqrestore(&async_lock, flags); + + /* schedule for execution */ + queue_work_node(node, system_unbound_wq, &entry->work); + + return newcookie; +} + /** * async_schedule_node_domain - NUMA specific version of async_schedule_domain * @func: function to execute asynchronously @@ -186,29 +219,8 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data, func(data, newcookie); return newcookie; } - INIT_LIST_HEAD(&entry->domain_list); - INIT_LIST_HEAD(&entry->global_list); - INIT_WORK(&entry->work, async_run_entry_fn); - entry->func = func; - entry->data = data; - entry->domain = domain; - - spin_lock_irqsave(&async_lock, flags); - - /* allocate cookie and queue */ - newcookie = entry->cookie = next_cookie++; - - list_add_tail(&entry->domain_list, &domain->pending); - if (domain->registered) - list_add_tail(&entry->global_list, &async_global_pending); - - atomic_inc(&entry_count); - spin_unlock_irqrestore(&async_lock, flags); - - /* schedule for execution */ - queue_work_node(node, system_unbound_wq, &entry->work); - return newcookie; + return __async_schedule_node_domain(func, data, node, domain, entry); } EXPORT_SYMBOL_GPL(async_schedule_node_domain); @@ -232,6 +244,35 @@ async_cookie_t async_schedule_node(async_func_t func, void *data, int node) EXPORT_SYMBOL_GPL(async_schedule_node); /** + * async_schedule_dev_nocall - A simplified variant of async_schedule_dev() + * @func: function to execute asynchronously + * @dev: device argument to be passed to function + * + * @dev is used as both the argument for the function and to provide NUMA + * context for where to run the function. + * + * If the asynchronous execution of @func is scheduled successfully, return + * true. Otherwise, do nothing and return false, unlike async_schedule_dev() + * that will run the function synchronously then. + */ +bool async_schedule_dev_nocall(async_func_t func, struct device *dev) +{ + struct async_entry *entry; + + entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL); + + /* Give up if there is no memory or too much work. */ + if (!entry || atomic_read(&entry_count) > MAX_WORK) { + kfree(entry); + return false; + } + + __async_schedule_node_domain(func, dev, dev_to_node(dev), + &async_dfl_domain, entry); + return true; +} + +/** * async_synchronize_full - synchronize all asynchronous function calls * * This function waits until all asynchronous function calls have been done. diff --git a/kernel/audit.c b/kernel/audit.c index 9bc0b0301198..99127521cda8 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -488,15 +488,19 @@ static void auditd_conn_free(struct rcu_head *rcu) * @pid: auditd PID * @portid: auditd netlink portid * @net: auditd network namespace pointer + * @skb: the netlink command from the audit daemon + * @ack: netlink ack flag, cleared if ack'd here * * Description: * This function will obtain and drop network namespace references as * necessary. Returns zero on success, negative values on failure. */ -static int auditd_set(struct pid *pid, u32 portid, struct net *net) +static int auditd_set(struct pid *pid, u32 portid, struct net *net, + struct sk_buff *skb, bool *ack) { unsigned long flags; struct auditd_connection *ac_old, *ac_new; + struct nlmsghdr *nlh; if (!pid || !net) return -EINVAL; @@ -508,6 +512,13 @@ static int auditd_set(struct pid *pid, u32 portid, struct net *net) ac_new->portid = portid; ac_new->net = get_net(net); + /* send the ack now to avoid a race with the queue backlog */ + if (*ack) { + nlh = nlmsg_hdr(skb); + netlink_ack(skb, nlh, 0, NULL); + *ack = false; + } + spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); @@ -1201,7 +1212,8 @@ static int audit_replace(struct pid *pid) return auditd_send_unicast_skb(skb); } -static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, + bool *ack) { u32 seq; void *data; @@ -1294,7 +1306,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) /* register a new auditd connection */ err = auditd_set(req_pid, NETLINK_CB(skb).portid, - sock_net(NETLINK_CB(skb).sk)); + sock_net(NETLINK_CB(skb).sk), + skb, ack); if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, @@ -1539,9 +1552,10 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) * Parse the provided skb and deal with any messages that may be present, * malformed skbs are discarded. */ -static void audit_receive(struct sk_buff *skb) +static void audit_receive(struct sk_buff *skb) { struct nlmsghdr *nlh; + bool ack; /* * len MUST be signed for nlmsg_next to be able to dec it below 0 * if the nlmsg_len was not aligned @@ -1554,9 +1568,12 @@ static void audit_receive(struct sk_buff *skb) audit_ctl_lock(); while (nlmsg_ok(nlh, len)) { - err = audit_receive_msg(skb, nlh); - /* if err or if this message says it wants a response */ - if (err || (nlh->nlmsg_flags & NLM_F_ACK)) + ack = nlh->nlmsg_flags & NLM_F_ACK; + err = audit_receive_msg(skb, nlh, &ack); + + /* send an ack if the user asked for one and audit_receive_msg + * didn't already do it, or if there was an error. */ + if (ack || err) netlink_ack(skb, nlh, err, NULL); nlh = nlmsg_next(nlh, &len); diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 832b2659e96e..c04e69f34e4d 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -852,7 +852,7 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, } if (old_ptr) - map->ops->map_fd_put_ptr(old_ptr); + map->ops->map_fd_put_ptr(map, old_ptr, true); return 0; } @@ -875,7 +875,7 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key) } if (old_ptr) { - map->ops->map_fd_put_ptr(old_ptr); + map->ops->map_fd_put_ptr(map, old_ptr, true); return 0; } else { return -ENOENT; @@ -898,8 +898,9 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, return prog; } -static void prog_fd_array_put_ptr(void *ptr) +static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { + /* bpf_prog is freed after one RCU or tasks trace grace period */ bpf_prog_put(ptr); } @@ -997,11 +998,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map, mutex_unlock(&aux->poke_mutex); } +void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old) +{ + WARN_ON_ONCE(1); +} + static void prog_array_map_poke_run(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new) { - u8 *old_addr, *new_addr, *old_bypass_addr; struct prog_poke_elem *elem; struct bpf_array_aux *aux; @@ -1010,7 +1016,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, list_for_each_entry(elem, &aux->poke_progs, list) { struct bpf_jit_poke_descriptor *poke; - int i, ret; + int i; for (i = 0; i < elem->aux->size_poke_tab; i++) { poke = &elem->aux->poke_tab[i]; @@ -1029,21 +1035,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, * activated, so tail call updates can arrive from here * while JIT is still finishing its final fixup for * non-activated poke entries. - * 3) On program teardown, the program's kallsym entry gets - * removed out of RCU callback, but we can only untrack - * from sleepable context, therefore bpf_arch_text_poke() - * might not see that this is in BPF text section and - * bails out with -EINVAL. As these are unreachable since - * RCU grace period already passed, we simply skip them. - * 4) Also programs reaching refcount of zero while patching + * 3) Also programs reaching refcount of zero while patching * is in progress is okay since we're protected under * poke_mutex and untrack the programs before the JIT - * buffer is freed. When we're still in the middle of - * patching and suddenly kallsyms entry of the program - * gets evicted, we just skip the rest which is fine due - * to point 3). - * 5) Any other error happening below from bpf_arch_text_poke() - * is a unexpected bug. + * buffer is freed. */ if (!READ_ONCE(poke->tailcall_target_stable)) continue; @@ -1053,39 +1048,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, poke->tail_call.key != key) continue; - old_bypass_addr = old ? NULL : poke->bypass_addr; - old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; - new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; - - if (new) { - ret = bpf_arch_text_poke(poke->tailcall_target, - BPF_MOD_JUMP, - old_addr, new_addr); - BUG_ON(ret < 0 && ret != -EINVAL); - if (!old) { - ret = bpf_arch_text_poke(poke->tailcall_bypass, - BPF_MOD_JUMP, - poke->bypass_addr, - NULL); - BUG_ON(ret < 0 && ret != -EINVAL); - } - } else { - ret = bpf_arch_text_poke(poke->tailcall_bypass, - BPF_MOD_JUMP, - old_bypass_addr, - poke->bypass_addr); - BUG_ON(ret < 0 && ret != -EINVAL); - /* let other CPUs finish the execution of program - * so that it will not possible to expose them - * to invalid nop, stack unwind, nop state - */ - if (!ret) - synchronize_rcu(); - ret = bpf_arch_text_poke(poke->tailcall_target, - BPF_MOD_JUMP, - old_addr, NULL); - BUG_ON(ret < 0 && ret != -EINVAL); - } + bpf_arch_poke_desc_update(poke, new, old); } } } @@ -1223,8 +1186,9 @@ err_out: return ee; } -static void perf_event_fd_array_put_ptr(void *ptr) +static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { + /* bpf_perf_event is freed after one RCU grace period */ bpf_event_entry_free_rcu(ptr); } @@ -1277,7 +1241,7 @@ static void *cgroup_fd_array_get_ptr(struct bpf_map *map, return cgroup_get_from_fd(fd); } -static void cgroup_fd_array_put_ptr(void *ptr) +static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { /* cgroup_put free cgrp after a rcu grace period */ cgroup_put(ptr); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 7225cb67c0d3..76bf1de26115 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -365,9 +365,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old, static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { - const s32 off_min = S16_MIN, off_max = S16_MAX; + s64 off_min, off_max, off; s32 delta = end_new - end_old; - s32 off = insn->off; + + if (insn->code == (BPF_JMP32 | BPF_JA)) { + off = insn->imm; + off_min = S32_MIN; + off_max = S32_MAX; + } else { + off = insn->off; + off_min = S16_MIN; + off_max = S16_MAX; + } if (curr < pos && curr + off + 1 >= end_old) off += delta; @@ -375,8 +384,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, off -= delta; if (off < off_min || off > off_max) return -ERANGE; - if (!probe_pass) - insn->off = off; + if (!probe_pass) { + if (insn->code == (BPF_JMP32 | BPF_JA)) + insn->imm = off; + else + insn->off = off; + } return 0; } @@ -1586,6 +1599,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(JMP, JSLE, K), \ INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ + INSN_2(JMP32, JA), \ /* Store instructions. */ \ /* Register based. */ \ INSN_3(STX, MEM, B), \ @@ -1862,6 +1876,9 @@ out: JMP_JA: insn += insn->off; CONT; + JMP32_JA: + insn += insn->imm; + CONT; JMP_EXIT: return BPF_R0; /* JMP */ diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index ce0051eee746..88c71de0a0a9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -880,7 +880,7 @@ static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) if (map->ops->map_fd_put_ptr) { ptr = fd_htab_map_get_ptr(map, l); - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, true); } } @@ -2424,7 +2424,7 @@ static void fd_htab_map_free(struct bpf_map *map) hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { void *ptr = fd_htab_map_get_ptr(map, l); - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, false); } } @@ -2465,7 +2465,7 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, ret = htab_map_update_elem(map, key, &ptr, map_flags); if (ret) - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, false); return ret; } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6212e4ae084b..83f8f67e933d 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -28,12 +28,13 @@ * * Different map implementations will rely on rcu in map methods * lookup/update/delete, therefore eBPF programs must run under rcu lock - * if program is allowed to access maps, so check rcu_read_lock_held in - * all three functions. + * if program is allowed to access maps, so check rcu_read_lock_held() or + * rcu_read_lock_trace_held() in all three functions. */ BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key) { - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); return (unsigned long) map->ops->map_lookup_elem(map, key); } @@ -49,7 +50,8 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = { BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key, void *, value, u64, flags) { - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); return map->ops->map_update_elem(map, key, value, flags); } @@ -66,7 +68,8 @@ const struct bpf_func_proto bpf_map_update_elem_proto = { BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key) { - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); return map->ops->map_delete_elem(map, key); } @@ -750,19 +753,20 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, /* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary * arguments representation. */ -#define MAX_BPRINTF_BUF_LEN 512 +#define MAX_BPRINTF_BIN_ARGS 512 /* Support executing three nested bprintf helper calls on a given CPU */ #define MAX_BPRINTF_NEST_LEVEL 3 struct bpf_bprintf_buffers { - char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN]; + char bin_args[MAX_BPRINTF_BIN_ARGS]; + char buf[MAX_BPRINTF_BUF]; }; -static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); + +static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs); static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); -static int try_get_fmt_tmp_buf(char **tmp_buf) +static int try_get_buffers(struct bpf_bprintf_buffers **bufs) { - struct bpf_bprintf_buffers *bufs; int nest_level; preempt_disable(); @@ -772,18 +776,19 @@ static int try_get_fmt_tmp_buf(char **tmp_buf) preempt_enable(); return -EBUSY; } - bufs = this_cpu_ptr(&bpf_bprintf_bufs); - *tmp_buf = bufs->tmp_bufs[nest_level - 1]; + *bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]); return 0; } -void bpf_bprintf_cleanup(void) +void bpf_bprintf_cleanup(struct bpf_bprintf_data *data) { - if (this_cpu_read(bpf_bprintf_nest_level)) { - this_cpu_dec(bpf_bprintf_nest_level); - preempt_enable(); - } + if (!data->bin_args && !data->buf) + return; + if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0)) + return; + this_cpu_dec(bpf_bprintf_nest_level); + preempt_enable(); } /* @@ -792,18 +797,20 @@ void bpf_bprintf_cleanup(void) * Returns a negative value if fmt is an invalid format string or 0 otherwise. * * This can be used in two ways: - * - Format string verification only: when bin_args is NULL + * - Format string verification only: when data->get_bin_args is false * - Arguments preparation: in addition to the above verification, it writes in - * bin_args a binary representation of arguments usable by bstr_printf where - * pointers from BPF have been sanitized. + * data->bin_args a binary representation of arguments usable by bstr_printf + * where pointers from BPF have been sanitized. * * In argument preparation mode, if 0 is returned, safe temporary buffers are * allocated and bpf_bprintf_cleanup should be called to free them after use. */ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, - u32 **bin_args, u32 num_args) + u32 num_args, struct bpf_bprintf_data *data) { + bool get_buffers = (data->get_bin_args && num_args) || data->get_buf; char *unsafe_ptr = NULL, *tmp_buf = NULL, *tmp_buf_end, *fmt_end; + struct bpf_bprintf_buffers *buffers = NULL; size_t sizeof_cur_arg, sizeof_cur_ip; int err, i, num_spec = 0; u64 cur_arg; @@ -814,14 +821,19 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, return -EINVAL; fmt_size = fmt_end - fmt; - if (bin_args) { - if (num_args && try_get_fmt_tmp_buf(&tmp_buf)) - return -EBUSY; + if (get_buffers && try_get_buffers(&buffers)) + return -EBUSY; - tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN; - *bin_args = (u32 *)tmp_buf; + if (data->get_bin_args) { + if (num_args) + tmp_buf = buffers->bin_args; + tmp_buf_end = tmp_buf + MAX_BPRINTF_BIN_ARGS; + data->bin_args = (u32 *)tmp_buf; } + if (data->get_buf) + data->buf = buffers->buf; + for (i = 0; i < fmt_size; i++) { if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) { err = -EINVAL; @@ -1015,31 +1027,33 @@ nocopy_fmt: err = 0; out: if (err) - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(data); return err; } BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt, - const void *, data, u32, data_len) + const void *, args, u32, data_len) { + struct bpf_bprintf_data data = { + .get_bin_args = true, + }; int err, num_args; - u32 *bin_args; if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 || - (data_len && !data)) + (data_len && !args)) return -EINVAL; num_args = data_len / 8; /* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we * can safely give an unbounded size. */ - err = bpf_bprintf_prepare(fmt, UINT_MAX, data, &bin_args, num_args); + err = bpf_bprintf_prepare(fmt, UINT_MAX, args, num_args, &data); if (err < 0) return err; - err = bstr_printf(str, str_size, fmt, bin_args); + err = bstr_printf(str, str_size, fmt, data.bin_args); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return err + 1; } @@ -1077,6 +1091,7 @@ struct bpf_hrtimer { struct bpf_prog *prog; void __rcu *callback_fn; void *value; + struct rcu_head rcu; }; /* the actual struct hidden inside uapi struct bpf_timer */ @@ -1298,6 +1313,7 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer) if (in_nmi()) return -EOPNOTSUPP; + rcu_read_lock(); __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; if (!t) { @@ -1319,6 +1335,7 @@ out: * if it was running. */ ret = ret ?: hrtimer_cancel(&t->timer); + rcu_read_unlock(); return ret; } @@ -1373,7 +1390,7 @@ out: */ if (this_cpu_read(hrtimer_running) != t) hrtimer_cancel(&t->timer); - kfree(t); + kfree_rcu(t, rcu); } BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index d833496e9e42..ce3a091d52e8 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -231,6 +231,9 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) struct lpm_trie_node *node, *found = NULL; struct bpf_lpm_trie_key *key = _key; + if (key->prefixlen > trie->max_prefixlen) + return NULL; + /* Start walking the trie from the root node ... */ for (node = rcu_dereference_check(trie->root, rcu_read_lock_bh_held()); diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 8e87f69aae60..141f3332038c 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -115,12 +115,17 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, return inner_map; } -void bpf_map_fd_put_ptr(void *ptr) +void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { - /* ptr->ops->map_free() has to go through one - * rcu grace period by itself. + struct bpf_map *inner_map = ptr; + + /* The inner map may still be used by both non-sleepable and sleepable + * bpf program, so free it after one RCU grace period and one tasks + * trace RCU grace period. */ - bpf_map_put(ptr); + if (need_defer) + WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true); + bpf_map_put(inner_map); } u32 bpf_map_fd_sys_lookup_elem(void *ptr) diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h index bcb7534afb3c..7d61602354de 100644 --- a/kernel/bpf/map_in_map.h +++ b/kernel/bpf/map_in_map.h @@ -13,7 +13,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd); void bpf_map_meta_free(struct bpf_map *map_meta); void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file, int ufd); -void bpf_map_fd_put_ptr(void *ptr); +void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer); u32 bpf_map_fd_sys_lookup_elem(void *ptr); #endif diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index aecea7451b61..f86db3cf7212 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -391,6 +391,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, { u32 trace_nr, copy_len, elem_size, num_elem, max_depth; bool user_build_id = flags & BPF_F_USER_BUILD_ID; + bool crosstask = task && task != current; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; @@ -413,6 +414,14 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, if (task && user && !user_mode(regs)) goto err_fault; + /* get_perf_callchain does not support crosstask user stack walking + * but returns an empty stack instead of NULL. + */ + if (crosstask && user) { + err = -EOPNOTSUPP; + goto clear; + } + num_elem = size / elem_size; max_depth = num_elem + skip; if (sysctl_perf_event_max_stack < max_depth) @@ -424,7 +433,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, trace = get_callchain_entry_for_task(task, max_depth); else trace = get_perf_callchain(regs, 0, kernel, user, max_depth, - false, false); + crosstask, false); if (unlikely(!trace)) goto err_fault; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0c8b7733573e..1e46a84694b8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -628,6 +628,28 @@ static void bpf_map_put_uref(struct bpf_map *map) } } +static void bpf_map_free_in_work(struct bpf_map *map) +{ + INIT_WORK(&map->work, bpf_map_free_deferred); + /* Avoid spawning kworkers, since they all might contend + * for the same mutex like slab_mutex. + */ + queue_work(system_unbound_wq, &map->work); +} + +static void bpf_map_free_rcu_gp(struct rcu_head *rcu) +{ + bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu)); +} + +static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_map_free_rcu_gp(rcu); + else + call_rcu(rcu, bpf_map_free_rcu_gp); +} + /* decrement map refcnt and schedule it for freeing via workqueue * (unrelying map implementation ops->map_free() might sleep) */ @@ -637,11 +659,11 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) /* bpf_map_free_id() must be called first */ bpf_map_free_id(map, do_idr_lock); btf_put(map->btf); - INIT_WORK(&map->work, bpf_map_free_deferred); - /* Avoid spawning kworkers, since they all might contend - * for the same mutex like slab_mutex. - */ - queue_work(system_unbound_wq, &map->work); + + if (READ_ONCE(map->free_after_mult_rcu_gp)) + call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); + else + bpf_map_free_in_work(map); } } @@ -1576,6 +1598,9 @@ int generic_map_delete_batch(struct bpf_map *map, if (!max_count) return 0; + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; @@ -1635,6 +1660,9 @@ int generic_map_update_batch(struct bpf_map *map, if (!max_count) return 0; + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; @@ -3036,6 +3064,10 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, * * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program * was detached and is going for re-attachment. + * + * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf + * are NULL, then program was already attached and user did not provide + * tgt_prog_fd so we have no way to find out or create trampoline */ if (!prog->aux->dst_trampoline && !tgt_prog) { /* @@ -3049,6 +3081,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, err = -EINVAL; goto out_unlock; } + /* We can allow re-attach only if we have valid attach_btf. */ + if (!prog->aux->attach_btf) { + err = -EINVAL; + goto out_unlock; + } btf_id = prog->aux->attach_btf_id; key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id); } diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index c4381dfcd6b0..748ac8616994 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -443,8 +443,8 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut goto out; } - /* clear all bits except SHARE_IPMODIFY */ - tr->flags &= BPF_TRAMP_F_SHARE_IPMODIFY; + /* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */ + tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX); if (tlinks[BPF_TRAMP_FEXIT].nr_links || tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 12d360d80c14..1a29ac4db6ea 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2254,7 +2254,10 @@ static int check_subprogs(struct bpf_verifier_env *env) goto next; if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) goto next; - off = i + insn[i].off + 1; + if (code == (BPF_JMP32 | BPF_JA)) + off = i + insn[i].imm + 1; + else + off = i + insn[i].off + 1; if (off < subprog_start || off >= subprog_end) { verbose(env, "jump out of range from insn %d to %d\n", i, off); return -EINVAL; @@ -2266,6 +2269,7 @@ next: * or unconditional jump back */ if (code != (BPF_JMP | BPF_EXIT) && + code != (BPF_JMP32 | BPF_JA) && code != (BPF_JMP | BPF_JA)) { verbose(env, "last insn is not an exit or jmp\n"); return -EINVAL; @@ -2512,6 +2516,16 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return 0; } +static void mark_jmp_point(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].jmp_point = true; +} + +static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].jmp_point; +} + /* for any branch, call, exit record the history of jmps in the given state */ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur) @@ -2520,6 +2534,9 @@ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_idx_pair *p; size_t alloc_size; + if (!is_jmp_point(env, env->insn_idx)) + return 0; + cnt++; alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p))); p = krealloc(cur->jmp_history, alloc_size, GFP_USER); @@ -2534,12 +2551,29 @@ static int push_jmp_history(struct bpf_verifier_env *env, /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. + * Return -ENOENT if we exhausted all instructions within given state. + * + * It's legal to have a bit of a looping with the same starting and ending + * insn index within the same state, e.g.: 3->4->5->3, so just because current + * instruction index is the same as state's first_idx doesn't mean we are + * done. If there is still some jump history left, we should keep going. We + * need to take into account that we might have a jump history between given + * state's parent and itself, due to checkpointing. In this case, we'll have + * history entry recording a jump from last instruction of parent state and + * first instruction of given state. */ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, u32 *history) { u32 cnt = *history; + if (i == st->first_insn_idx) { + if (cnt == 0) + return -ENOENT; + if (cnt == 1 && st->jmp_history[0].idx == i) + return -ENOENT; + } + if (cnt && st->jmp_history[cnt - 1].idx == i) { i = st->jmp_history[cnt - 1].prev_idx; (*history)--; @@ -3035,9 +3069,9 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r * Nothing to be tracked further in the parent state. */ return 0; - if (i == first_idx) - break; i = get_prev_insn_idx(st, i, &history); + if (i == -ENOENT) + break; if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask @@ -3250,7 +3284,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, * so it's aligned access and [off, off + size) are within stack limits */ if (!env->allow_ptr_leaks && - state->stack[spi].slot_type[0] == STACK_SPILL && + is_spilled_reg(&state->stack[spi]) && size != BPF_REG_SIZE) { verbose(env, "attempt to corrupt spilled pointer on stack\n"); return -EACCES; @@ -4916,10 +4950,7 @@ static int check_stack_access_within_bounds( if (tnum_is_const(reg->var_off)) { min_off = reg->var_off.value + off; - if (access_size > 0) - max_off = min_off + access_size - 1; - else - max_off = min_off; + max_off = min_off + access_size; } else { if (reg->smax_value >= BPF_MAX_VAR_OFF || reg->smin_value <= -BPF_MAX_VAR_OFF) { @@ -4928,15 +4959,12 @@ static int check_stack_access_within_bounds( return -EACCES; } min_off = reg->smin_value + off; - if (access_size > 0) - max_off = reg->smax_value + off + access_size - 1; - else - max_off = min_off; + max_off = reg->smax_value + off + access_size; } err = check_stack_slot_within_bounds(min_off, state, type); - if (!err) - err = check_stack_slot_within_bounds(max_off, state, type); + if (!err && max_off > 0) + err = -EINVAL; /* out of stack access into non-negative offsets */ if (err) { if (tnum_is_const(reg->var_off)) { @@ -7250,6 +7278,13 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) verbose(env, "R0 not a scalar value\n"); return -EACCES; } + + /* we are going to rely on register's precise value */ + err = mark_reg_read(env, r0, r0->parent, REG_LIVE_READ64); + err = err ?: mark_chain_precision(env, BPF_REG_0); + if (err) + return err; + if (!tnum_in(range, r0->var_off)) { verbose_invalid_scalar(env, r0, &range, "callback return", "R0"); return -EINVAL; @@ -7413,6 +7448,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, struct bpf_reg_state *fmt_reg = ®s[BPF_REG_3]; struct bpf_reg_state *data_len_reg = ®s[BPF_REG_5]; struct bpf_map *fmt_map = fmt_reg->map_ptr; + struct bpf_bprintf_data data = {}; int err, fmt_map_off, num_args; u64 fmt_addr; char *fmt; @@ -7437,7 +7473,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, /* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we * can focus on validating the format specifiers. */ - err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, NULL, num_args); + err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, num_args, &data); if (err < 0) verbose(env, "Invalid format string\n"); @@ -8506,6 +8542,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } switch (base_type(ptr_reg->type)) { + case PTR_TO_FLOW_KEYS: + if (known) + break; + fallthrough; case CONST_PTR_TO_MAP: /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) @@ -11000,11 +11040,16 @@ static struct bpf_verifier_state_list **explored_state( return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; } -static void init_explored_state(struct bpf_verifier_env *env, int idx) +static void mark_prune_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].prune_point = true; } +static bool is_prune_point(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].prune_point; +} + enum { DONE_EXPLORING = 0, KEEP_EXPLORING = 1, @@ -11033,9 +11078,11 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, return -EINVAL; } - if (e == BRANCH) + if (e == BRANCH) { /* mark branch target for state pruning */ - init_explored_state(env, w); + mark_prune_point(env, w); + mark_jmp_point(env, w); + } if (insn_state[w] == 0) { /* tree-edge */ @@ -11062,21 +11109,23 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, return DONE_EXPLORING; } -static int visit_func_call_insn(int t, int insn_cnt, - struct bpf_insn *insns, +static int visit_func_call_insn(int t, struct bpf_insn *insns, struct bpf_verifier_env *env, bool visit_callee) { - int ret; + int ret, insn_sz; - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); + insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1; + ret = push_insn(t, t + insn_sz, FALLTHROUGH, env, false); if (ret) return ret; - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); + mark_prune_point(env, t + insn_sz); + /* when we exit from subprog, we need to record non-linear history */ + mark_jmp_point(env, t + insn_sz); + if (visit_callee) { - init_explored_state(env, t); + mark_prune_point(env, t); ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env, /* It's ok to allow recursion from CFG point of * view. __check_func_call() will do the actual @@ -11092,65 +11141,64 @@ static int visit_func_call_insn(int t, int insn_cnt, * DONE_EXPLORING - the instruction was fully explored * KEEP_EXPLORING - there is still work to be done before it is fully explored */ -static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env) +static int visit_insn(int t, struct bpf_verifier_env *env) { - struct bpf_insn *insns = env->prog->insnsi; - int ret; + struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t]; + int ret, off, insn_sz; - if (bpf_pseudo_func(insns + t)) - return visit_func_call_insn(t, insn_cnt, insns, env, true); + if (bpf_pseudo_func(insn)) + return visit_func_call_insn(t, insns, env, true); /* All non-branch instructions have a single fall-through edge. */ - if (BPF_CLASS(insns[t].code) != BPF_JMP && - BPF_CLASS(insns[t].code) != BPF_JMP32) - return push_insn(t, t + 1, FALLTHROUGH, env, false); + if (BPF_CLASS(insn->code) != BPF_JMP && + BPF_CLASS(insn->code) != BPF_JMP32) { + insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; + return push_insn(t, t + insn_sz, FALLTHROUGH, env, false); + } - switch (BPF_OP(insns[t].code)) { + switch (BPF_OP(insn->code)) { case BPF_EXIT: return DONE_EXPLORING; case BPF_CALL: - if (insns[t].imm == BPF_FUNC_timer_set_callback) - /* Mark this call insn to trigger is_state_visited() check - * before call itself is processed by __check_func_call(). - * Otherwise new async state will be pushed for further - * exploration. + if (insn->imm == BPF_FUNC_timer_set_callback) + /* Mark this call insn as a prune point to trigger + * is_state_visited() check before call itself is + * processed by __check_func_call(). Otherwise new + * async state will be pushed for further exploration. */ - init_explored_state(env, t); - return visit_func_call_insn(t, insn_cnt, insns, env, - insns[t].src_reg == BPF_PSEUDO_CALL); + mark_prune_point(env, t); + return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL); case BPF_JA: - if (BPF_SRC(insns[t].code) != BPF_K) + if (BPF_SRC(insn->code) != BPF_K) return -EINVAL; + if (BPF_CLASS(insn->code) == BPF_JMP) + off = insn->off; + else + off = insn->imm; + /* unconditional jump with single edge */ - ret = push_insn(t, t + insns[t].off + 1, FALLTHROUGH, env, + ret = push_insn(t, t + off + 1, FALLTHROUGH, env, true); if (ret) return ret; - /* unconditional jmp is not a good pruning point, - * but it's marked, since backtracking needs - * to record jmp history in is_state_visited(). - */ - init_explored_state(env, t + insns[t].off + 1); - /* tell verifier to check for equivalent states - * after every call and jump - */ - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); + mark_prune_point(env, t + off + 1); + mark_jmp_point(env, t + off + 1); return ret; default: /* conditional jump with two edges */ - init_explored_state(env, t); + mark_prune_point(env, t); + ret = push_insn(t, t + 1, FALLTHROUGH, env, true); if (ret) return ret; - return push_insn(t, t + insns[t].off + 1, BRANCH, env, true); + return push_insn(t, t + insn->off + 1, BRANCH, env, true); } } @@ -11181,7 +11229,7 @@ static int check_cfg(struct bpf_verifier_env *env) while (env->cfg.cur_stack > 0) { int t = insn_stack[env->cfg.cur_stack - 1]; - ret = visit_insn(t, insn_cnt, env); + ret = visit_insn(t, env); switch (ret) { case DONE_EXPLORING: insn_state[t] = EXPLORED; @@ -11205,11 +11253,21 @@ static int check_cfg(struct bpf_verifier_env *env) } for (i = 0; i < insn_cnt; i++) { + struct bpf_insn *insn = &env->prog->insnsi[i]; + if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } + if (bpf_is_ldimm64(insn)) { + if (insn_state[i + 1] != 0) { + verbose(env, "jump into the middle of ldimm64 insn %d\n", i); + ret = -EINVAL; + goto err_free; + } + i++; /* skip second half of ldimm64 */ + } } ret = 0; /* cfg looks good */ @@ -12178,11 +12236,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) bool add_new_state = env->test_state_freq ? true : false; cur->last_insn_idx = env->prev_insn_idx; - if (!env->insn_aux_data[insn_idx].prune_point) + if (!is_prune_point(env, insn_idx)) /* this 'insn_idx' instruction wasn't marked, so we will not * be doing state search here */ - return 0; + return push_jmp_history(env, cur); /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 @@ -12674,15 +12732,18 @@ static int do_check(struct bpf_verifier_env *env) return err; } else if (opcode == BPF_JA) { if (BPF_SRC(insn->code) != BPF_K || - insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || - class == BPF_JMP32) { + (class == BPF_JMP && insn->imm != 0) || + (class == BPF_JMP32 && insn->off != 0)) { verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } - env->insn_idx += insn->off + 1; + if (class == BPF_JMP) + env->insn_idx += insn->off + 1; + else + env->insn_idx += insn->imm + 1; continue; } else if (opcode == BPF_EXIT) { @@ -13508,13 +13569,13 @@ static bool insn_is_cond_jump(u8 code) { u8 op; + op = BPF_OP(code); if (BPF_CLASS(code) == BPF_JMP32) - return true; + return op != BPF_JA; if (BPF_CLASS(code) != BPF_JMP) return false; - op = BPF_OP(code); return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL; } @@ -15442,6 +15503,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) if (!tr) return -ENOMEM; + if (tgt_prog && tgt_prog->aux->tail_call_reachable) + tr->flags = BPF_TRAMP_F_TAIL_CALL_CTX; + prog->aux->dst_trampoline = tr; return 0; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 551468d9c5a8..e6f0101941ed 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -446,9 +446,31 @@ static int __init smt_cmdline_disable(char *str) } early_param("nosmt", smt_cmdline_disable); -static inline bool cpu_smt_allowed(unsigned int cpu) +/* + * For Archicture supporting partial SMT states check if the thread is allowed. + * Otherwise this has already been checked through cpu_smt_max_threads when + * setting the SMT level. + */ +static inline bool cpu_smt_thread_allowed(unsigned int cpu) { - if (cpu_smt_control == CPU_SMT_ENABLED) +#ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC + return topology_smt_thread_allowed(cpu); +#else + return true; +#endif +} + +static inline bool cpu_bootable(unsigned int cpu) +{ + if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) + return true; + + /* All CPUs are bootable if controls are not configured */ + if (cpu_smt_control == CPU_SMT_NOT_IMPLEMENTED) + return true; + + /* All CPUs are bootable if CPU is not SMT capable */ + if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return true; if (topology_is_primary_thread(cpu)) @@ -471,7 +493,7 @@ bool cpu_smt_possible(void) } EXPORT_SYMBOL_GPL(cpu_smt_possible); #else -static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } +static inline bool cpu_bootable(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state @@ -574,10 +596,10 @@ static int bringup_wait_for_ap(unsigned int cpu) * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the - * cpu_smt_allowed() check will now return false if this is not the + * cpu_bootable() check will now return false if this is not the * primary sibling. */ - if (!cpu_smt_allowed(cpu)) + if (!cpu_bootable(cpu)) return -ECANCELED; if (st->target <= CPUHP_AP_ONLINE_IDLE) @@ -1464,7 +1486,7 @@ static int cpu_up(unsigned int cpu, enum cpuhp_state target) err = -EBUSY; goto out; } - if (!cpu_smt_allowed(cpu)) { + if (!cpu_bootable(cpu)) { err = -EPERM; goto out; } @@ -2294,6 +2316,12 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; + /* + * Disable can be called with CPU_SMT_ENABLED when changing + * from a higher to lower number of SMT threads per core. + */ + if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) + continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; @@ -2328,6 +2356,8 @@ int cpuhp_smt_enable(void) /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; + if (!cpu_smt_thread_allowed(cpu)) + continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 438b868cbfa9..35aa2e98a92a 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1349,8 +1349,6 @@ do_full_getstr: /* PROMPT can only be set if we have MEM_READ permission. */ snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"), raw_smp_processor_id()); - if (defcmd_in_progress) - strncat(kdb_prompt_str, "[defcmd]", CMD_BUFLEN); /* * Fetch command from keyboard diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index c21abc77c53e..ff5683a57f77 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -132,8 +132,10 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, void dma_release_coherent_memory(struct device *dev) { - if (dev) + if (dev) { _dma_release_coherent_memory(dev->dma_mem); + dev->dma_mem = NULL; + } } static void *__dma_alloc_from_coherent(struct device *dev, diff --git a/kernel/events/core.c b/kernel/events/core.c index 8c7d2f4f5fba..872d149b1959 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11223,9 +11223,30 @@ static DEVICE_ATTR_RW(perf_event_mux_interval_ms); static struct attribute *pmu_dev_attrs[] = { &dev_attr_type.attr, &dev_attr_perf_event_mux_interval_ms.attr, + &dev_attr_nr_addr_filters.attr, + NULL, +}; + +static umode_t pmu_dev_is_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct pmu *pmu = dev_get_drvdata(dev); + + if (n == 2 && !pmu->nr_addr_filters) + return 0; + + return a->mode; +} + +static struct attribute_group pmu_dev_attr_group = { + .is_visible = pmu_dev_is_visible, + .attrs = pmu_dev_attrs, +}; + +static const struct attribute_group *pmu_dev_groups[] = { + &pmu_dev_attr_group, NULL, }; -ATTRIBUTE_GROUPS(pmu_dev); static int pmu_bus_running; static struct bus_type pmu_bus = { @@ -11261,18 +11282,11 @@ static int pmu_dev_alloc(struct pmu *pmu) if (ret) goto free_dev; - /* For PMUs with address filters, throw in an extra attribute: */ - if (pmu->nr_addr_filters) - ret = device_create_file(pmu->dev, &dev_attr_nr_addr_filters); - - if (ret) - goto del_dev; - - if (pmu->attr_update) + if (pmu->attr_update) { ret = sysfs_update_groups(&pmu->dev->kobj, pmu->attr_update); - - if (ret) - goto del_dev; + if (ret) + goto del_dev; + } out: return ret; diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index d9a5c1d65a79..44a4eba80315 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -7,398 +7,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/cpu.h> -#include <linux/sort.h> - -static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk, - unsigned int cpus_per_vec) -{ - const struct cpumask *siblmsk; - int cpu, sibl; - - for ( ; cpus_per_vec > 0; ) { - cpu = cpumask_first(nmsk); - - /* Should not happen, but I'm too lazy to think about it */ - if (cpu >= nr_cpu_ids) - return; - - cpumask_clear_cpu(cpu, nmsk); - cpumask_set_cpu(cpu, irqmsk); - cpus_per_vec--; - - /* If the cpu has siblings, use them first */ - siblmsk = topology_sibling_cpumask(cpu); - for (sibl = -1; cpus_per_vec > 0; ) { - sibl = cpumask_next(sibl, siblmsk); - if (sibl >= nr_cpu_ids) - break; - if (!cpumask_test_and_clear_cpu(sibl, nmsk)) - continue; - cpumask_set_cpu(sibl, irqmsk); - cpus_per_vec--; - } - } -} - -static cpumask_var_t *alloc_node_to_cpumask(void) -{ - cpumask_var_t *masks; - int node; - - masks = kcalloc(nr_node_ids, sizeof(cpumask_var_t), GFP_KERNEL); - if (!masks) - return NULL; - - for (node = 0; node < nr_node_ids; node++) { - if (!zalloc_cpumask_var(&masks[node], GFP_KERNEL)) - goto out_unwind; - } - - return masks; - -out_unwind: - while (--node >= 0) - free_cpumask_var(masks[node]); - kfree(masks); - return NULL; -} - -static void free_node_to_cpumask(cpumask_var_t *masks) -{ - int node; - - for (node = 0; node < nr_node_ids; node++) - free_cpumask_var(masks[node]); - kfree(masks); -} - -static void build_node_to_cpumask(cpumask_var_t *masks) -{ - int cpu; - - for_each_possible_cpu(cpu) - cpumask_set_cpu(cpu, masks[cpu_to_node(cpu)]); -} - -static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask, - const struct cpumask *mask, nodemask_t *nodemsk) -{ - int n, nodes = 0; - - /* Calculate the number of nodes in the supplied affinity mask */ - for_each_node(n) { - if (cpumask_intersects(mask, node_to_cpumask[n])) { - node_set(n, *nodemsk); - nodes++; - } - } - return nodes; -} - -struct node_vectors { - unsigned id; - - union { - unsigned nvectors; - unsigned ncpus; - }; -}; - -static int ncpus_cmp_func(const void *l, const void *r) -{ - const struct node_vectors *ln = l; - const struct node_vectors *rn = r; - - return ln->ncpus - rn->ncpus; -} - -/* - * Allocate vector number for each node, so that for each node: - * - * 1) the allocated number is >= 1 - * - * 2) the allocated numbver is <= active CPU number of this node - * - * The actual allocated total vectors may be less than @numvecs when - * active total CPU number is less than @numvecs. - * - * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]' - * for each node. - */ -static void alloc_nodes_vectors(unsigned int numvecs, - cpumask_var_t *node_to_cpumask, - const struct cpumask *cpu_mask, - const nodemask_t nodemsk, - struct cpumask *nmsk, - struct node_vectors *node_vectors) -{ - unsigned n, remaining_ncpus = 0; - - for (n = 0; n < nr_node_ids; n++) { - node_vectors[n].id = n; - node_vectors[n].ncpus = UINT_MAX; - } - - for_each_node_mask(n, nodemsk) { - unsigned ncpus; - - cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); - ncpus = cpumask_weight(nmsk); - - if (!ncpus) - continue; - remaining_ncpus += ncpus; - node_vectors[n].ncpus = ncpus; - } - - numvecs = min_t(unsigned, remaining_ncpus, numvecs); - - sort(node_vectors, nr_node_ids, sizeof(node_vectors[0]), - ncpus_cmp_func, NULL); - - /* - * Allocate vectors for each node according to the ratio of this - * node's nr_cpus to remaining un-assigned ncpus. 'numvecs' is - * bigger than number of active numa nodes. Always start the - * allocation from the node with minimized nr_cpus. - * - * This way guarantees that each active node gets allocated at - * least one vector, and the theory is simple: over-allocation - * is only done when this node is assigned by one vector, so - * other nodes will be allocated >= 1 vector, since 'numvecs' is - * bigger than number of numa nodes. - * - * One perfect invariant is that number of allocated vectors for - * each node is <= CPU count of this node: - * - * 1) suppose there are two nodes: A and B - * ncpu(X) is CPU count of node X - * vecs(X) is the vector count allocated to node X via this - * algorithm - * - * ncpu(A) <= ncpu(B) - * ncpu(A) + ncpu(B) = N - * vecs(A) + vecs(B) = V - * - * vecs(A) = max(1, round_down(V * ncpu(A) / N)) - * vecs(B) = V - vecs(A) - * - * both N and V are integer, and 2 <= V <= N, suppose - * V = N - delta, and 0 <= delta <= N - 2 - * - * 2) obviously vecs(A) <= ncpu(A) because: - * - * if vecs(A) is 1, then vecs(A) <= ncpu(A) given - * ncpu(A) >= 1 - * - * otherwise, - * vecs(A) <= V * ncpu(A) / N <= ncpu(A), given V <= N - * - * 3) prove how vecs(B) <= ncpu(B): - * - * if round_down(V * ncpu(A) / N) == 0, vecs(B) won't be - * over-allocated, so vecs(B) <= ncpu(B), - * - * otherwise: - * - * vecs(A) = - * round_down(V * ncpu(A) / N) = - * round_down((N - delta) * ncpu(A) / N) = - * round_down((N * ncpu(A) - delta * ncpu(A)) / N) >= - * round_down((N * ncpu(A) - delta * N) / N) = - * cpu(A) - delta - * - * then: - * - * vecs(A) - V >= ncpu(A) - delta - V - * => - * V - vecs(A) <= V + delta - ncpu(A) - * => - * vecs(B) <= N - ncpu(A) - * => - * vecs(B) <= cpu(B) - * - * For nodes >= 3, it can be thought as one node and another big - * node given that is exactly what this algorithm is implemented, - * and we always re-calculate 'remaining_ncpus' & 'numvecs', and - * finally for each node X: vecs(X) <= ncpu(X). - * - */ - for (n = 0; n < nr_node_ids; n++) { - unsigned nvectors, ncpus; - - if (node_vectors[n].ncpus == UINT_MAX) - continue; - - WARN_ON_ONCE(numvecs == 0); - - ncpus = node_vectors[n].ncpus; - nvectors = max_t(unsigned, 1, - numvecs * ncpus / remaining_ncpus); - WARN_ON_ONCE(nvectors > ncpus); - - node_vectors[n].nvectors = nvectors; - - remaining_ncpus -= ncpus; - numvecs -= nvectors; - } -} - -static int __irq_build_affinity_masks(unsigned int startvec, - unsigned int numvecs, - unsigned int firstvec, - cpumask_var_t *node_to_cpumask, - const struct cpumask *cpu_mask, - struct cpumask *nmsk, - struct irq_affinity_desc *masks) -{ - unsigned int i, n, nodes, cpus_per_vec, extra_vecs, done = 0; - unsigned int last_affv = firstvec + numvecs; - unsigned int curvec = startvec; - nodemask_t nodemsk = NODE_MASK_NONE; - struct node_vectors *node_vectors; - - if (cpumask_empty(cpu_mask)) - return 0; - - nodes = get_nodes_in_cpumask(node_to_cpumask, cpu_mask, &nodemsk); - - /* - * If the number of nodes in the mask is greater than or equal the - * number of vectors we just spread the vectors across the nodes. - */ - if (numvecs <= nodes) { - for_each_node_mask(n, nodemsk) { - /* Ensure that only CPUs which are in both masks are set */ - cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); - cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk); - if (++curvec == last_affv) - curvec = firstvec; - } - return numvecs; - } - - node_vectors = kcalloc(nr_node_ids, - sizeof(struct node_vectors), - GFP_KERNEL); - if (!node_vectors) - return -ENOMEM; - - /* allocate vector number for each node */ - alloc_nodes_vectors(numvecs, node_to_cpumask, cpu_mask, - nodemsk, nmsk, node_vectors); - - for (i = 0; i < nr_node_ids; i++) { - unsigned int ncpus, v; - struct node_vectors *nv = &node_vectors[i]; - - if (nv->nvectors == UINT_MAX) - continue; - - /* Get the cpus on this node which are in the mask */ - cpumask_and(nmsk, cpu_mask, node_to_cpumask[nv->id]); - ncpus = cpumask_weight(nmsk); - if (!ncpus) - continue; - - WARN_ON_ONCE(nv->nvectors > ncpus); - - /* Account for rounding errors */ - extra_vecs = ncpus - nv->nvectors * (ncpus / nv->nvectors); - - /* Spread allocated vectors on CPUs of the current node */ - for (v = 0; v < nv->nvectors; v++, curvec++) { - cpus_per_vec = ncpus / nv->nvectors; - - /* Account for extra vectors to compensate rounding errors */ - if (extra_vecs) { - cpus_per_vec++; - --extra_vecs; - } - - /* - * wrapping has to be considered given 'startvec' - * may start anywhere - */ - if (curvec >= last_affv) - curvec = firstvec; - irq_spread_init_one(&masks[curvec].mask, nmsk, - cpus_per_vec); - } - done += nv->nvectors; - } - kfree(node_vectors); - return done; -} - -/* - * build affinity in two stages: - * 1) spread present CPU on these vectors - * 2) spread other possible CPUs on these vectors - */ -static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs, - unsigned int firstvec, - struct irq_affinity_desc *masks) -{ - unsigned int curvec = startvec, nr_present = 0, nr_others = 0; - cpumask_var_t *node_to_cpumask; - cpumask_var_t nmsk, npresmsk; - int ret = -ENOMEM; - - if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL)) - return ret; - - if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL)) - goto fail_nmsk; - - node_to_cpumask = alloc_node_to_cpumask(); - if (!node_to_cpumask) - goto fail_npresmsk; - - /* Stabilize the cpumasks */ - cpus_read_lock(); - build_node_to_cpumask(node_to_cpumask); - - /* Spread on present CPUs starting from affd->pre_vectors */ - ret = __irq_build_affinity_masks(curvec, numvecs, firstvec, - node_to_cpumask, cpu_present_mask, - nmsk, masks); - if (ret < 0) - goto fail_build_affinity; - nr_present = ret; - - /* - * Spread on non present CPUs starting from the next vector to be - * handled. If the spreading of present CPUs already exhausted the - * vector space, assign the non present CPUs to the already spread - * out vectors. - */ - if (nr_present >= numvecs) - curvec = firstvec; - else - curvec = firstvec + nr_present; - cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask); - ret = __irq_build_affinity_masks(curvec, numvecs, firstvec, - node_to_cpumask, npresmsk, nmsk, - masks); - if (ret >= 0) - nr_others = ret; - - fail_build_affinity: - cpus_read_unlock(); - - if (ret >= 0) - WARN_ON(nr_present + nr_others < numvecs); - - free_node_to_cpumask(node_to_cpumask); - - fail_npresmsk: - free_cpumask_var(npresmsk); - - fail_nmsk: - free_cpumask_var(nmsk); - return ret < 0 ? ret : 0; -} +#include <linux/group_cpus.h> static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs) { @@ -461,14 +70,18 @@ irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd) */ for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) { unsigned int this_vecs = affd->set_size[i]; - int ret; + int j; + struct cpumask *result = group_cpus_evenly(this_vecs); - ret = irq_build_affinity_masks(curvec, this_vecs, - curvec, masks); - if (ret) { + if (!result) { kfree(masks); return NULL; } + + for (j = 0; j < this_vecs; j++) + cpumask_copy(&masks[curvec + j].mask, &result[j]); + kfree(result); + curvec += this_vecs; usedvecs += this_vecs; } diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index f5c5c9175333..4523f99b0358 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -494,7 +494,6 @@ unsigned long module_kallsyms_lookup_name(const char *name) return ret; } -#ifdef CONFIG_LIVEPATCH int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data) @@ -531,4 +530,3 @@ out: mutex_unlock(&module_mutex); return ret; } -#endif /* CONFIG_LIVEPATCH */ diff --git a/kernel/power/swap.c b/kernel/power/swap.c index cc44c37699de..5ab54ab5ace7 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -605,11 +605,11 @@ static int crc32_threadfn(void *data) unsigned i; while (1) { - wait_event(d->go, atomic_read(&d->ready) || + wait_event(d->go, atomic_read_acquire(&d->ready) || kthread_should_stop()); if (kthread_should_stop()) { d->thr = NULL; - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); break; } @@ -618,7 +618,7 @@ static int crc32_threadfn(void *data) for (i = 0; i < d->run_threads; i++) *d->crc32 = crc32_le(*d->crc32, d->unc[i], *d->unc_len[i]); - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); } return 0; @@ -648,12 +648,12 @@ static int lzo_compress_threadfn(void *data) struct cmp_data *d = data; while (1) { - wait_event(d->go, atomic_read(&d->ready) || + wait_event(d->go, atomic_read_acquire(&d->ready) || kthread_should_stop()); if (kthread_should_stop()) { d->thr = NULL; d->ret = -1; - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); break; } @@ -662,7 +662,7 @@ static int lzo_compress_threadfn(void *data) d->ret = lzo1x_1_compress(d->unc, d->unc_len, d->cmp + LZO_HEADER, &d->cmp_len, d->wrk); - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); } return 0; @@ -797,7 +797,7 @@ static int save_image_lzo(struct swap_map_handle *handle, data[thr].unc_len = off; - atomic_set(&data[thr].ready, 1); + atomic_set_release(&data[thr].ready, 1); wake_up(&data[thr].go); } @@ -805,12 +805,12 @@ static int save_image_lzo(struct swap_map_handle *handle, break; crc->run_threads = thr; - atomic_set(&crc->ready, 1); + atomic_set_release(&crc->ready, 1); wake_up(&crc->go); for (run_threads = thr, thr = 0; thr < run_threads; thr++) { wait_event(data[thr].done, - atomic_read(&data[thr].stop)); + atomic_read_acquire(&data[thr].stop)); atomic_set(&data[thr].stop, 0); ret = data[thr].ret; @@ -849,7 +849,7 @@ static int save_image_lzo(struct swap_map_handle *handle, } } - wait_event(crc->done, atomic_read(&crc->stop)); + wait_event(crc->done, atomic_read_acquire(&crc->stop)); atomic_set(&crc->stop, 0); } @@ -1131,12 +1131,12 @@ static int lzo_decompress_threadfn(void *data) struct dec_data *d = data; while (1) { - wait_event(d->go, atomic_read(&d->ready) || + wait_event(d->go, atomic_read_acquire(&d->ready) || kthread_should_stop()); if (kthread_should_stop()) { d->thr = NULL; d->ret = -1; - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); break; } @@ -1149,7 +1149,7 @@ static int lzo_decompress_threadfn(void *data) flush_icache_range((unsigned long)d->unc, (unsigned long)d->unc + d->unc_len); - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); } return 0; @@ -1334,7 +1334,7 @@ static int load_image_lzo(struct swap_map_handle *handle, } if (crc->run_threads) { - wait_event(crc->done, atomic_read(&crc->stop)); + wait_event(crc->done, atomic_read_acquire(&crc->stop)); atomic_set(&crc->stop, 0); crc->run_threads = 0; } @@ -1370,7 +1370,7 @@ static int load_image_lzo(struct swap_map_handle *handle, pg = 0; } - atomic_set(&data[thr].ready, 1); + atomic_set_release(&data[thr].ready, 1); wake_up(&data[thr].go); } @@ -1389,7 +1389,7 @@ static int load_image_lzo(struct swap_map_handle *handle, for (run_threads = thr, thr = 0; thr < run_threads; thr++) { wait_event(data[thr].done, - atomic_read(&data[thr].stop)); + atomic_read_acquire(&data[thr].stop)); atomic_set(&data[thr].stop, 0); ret = data[thr].ret; @@ -1420,7 +1420,7 @@ static int load_image_lzo(struct swap_map_handle *handle, ret = snapshot_write_next(snapshot); if (ret <= 0) { crc->run_threads = thr + 1; - atomic_set(&crc->ready, 1); + atomic_set_release(&crc->ready, 1); wake_up(&crc->go); goto out_finish; } @@ -1428,13 +1428,13 @@ static int load_image_lzo(struct swap_map_handle *handle, } crc->run_threads = thr; - atomic_set(&crc->ready, 1); + atomic_set_release(&crc->ready, 1); wake_up(&crc->go); } out_finish: if (crc->run_threads) { - wait_event(crc->done, atomic_read(&crc->stop)); + wait_event(crc->done, atomic_read_acquire(&crc->stop)); atomic_set(&crc->stop, 0); } stop = ktime_get(); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 8fdf07672038..929dcbc04d29 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -1100,10 +1100,37 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, spin_lock_irqsave_sdp_contention(sdp, &flags); if (rhp) rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); + /* + * The snapshot for acceleration must be taken _before_ the read of the + * current gp sequence used for advancing, otherwise advancing may fail + * and acceleration may then fail too. + * + * This could happen if: + * + * 1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the + * RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8). + * + * 2) The grace period for RCU_WAIT_TAIL is seen as started but not + * completed so rcu_seq_current() returns X + SRCU_STATE_SCAN1. + * + * 3) This value is passed to rcu_segcblist_advance() which can't move + * any segment forward and fails. + * + * 4) srcu_gp_start_if_needed() still proceeds with callback acceleration. + * But then the call to rcu_seq_snap() observes the grace period for the + * RCU_WAIT_TAIL segment as completed and the subsequent one for the + * RCU_NEXT_READY_TAIL segment as started (ie: X + 4 + SRCU_STATE_SCAN1) + * so it returns a snapshot of the next grace period, which is X + 12. + * + * 5) The value of X + 12 is passed to rcu_segcblist_accelerate() but the + * freshly enqueued callback in RCU_NEXT_TAIL can't move to + * RCU_NEXT_READY_TAIL which already has callbacks for a previous grace + * period (gp_num = X + 8). So acceleration fails. + */ + s = rcu_seq_snap(&ssp->srcu_gp_seq); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_gp_seq)); - s = rcu_seq_snap(&ssp->srcu_gp_seq); - (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s); + WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp); if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) { sdp->srcu_gp_seq_needed = s; needgp = true; diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index c1f18c63b9b1..b5d5b6cf093a 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -1570,6 +1570,8 @@ static void rcu_tasks_trace_postscan(struct list_head *hop) { // Wait for late-stage exiting tasks to finish exiting. // These might have passed the call to exit_tasks_rcu_finish(). + + // If you remove the following line, update rcu_trace_implies_rcu_gp()!!! synchronize_rcu(); // Any tasks that exit after this point will set // TRC_NEED_QS_CHECKED in ->trc_reader_special.b.need_qs. diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 15df37bc052a..9d7464a90f85 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1051,6 +1051,38 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp) return needmore; } +static void swake_up_one_online_ipi(void *arg) +{ + struct swait_queue_head *wqh = arg; + + swake_up_one(wqh); +} + +static void swake_up_one_online(struct swait_queue_head *wqh) +{ + int cpu = get_cpu(); + + /* + * If called from rcutree_report_cpu_starting(), wake up + * is dangerous that late in the CPU-down hotplug process. The + * scheduler might queue an ignored hrtimer. Defer the wake up + * to an online CPU instead. + */ + if (unlikely(cpu_is_offline(cpu))) { + int target; + + target = cpumask_any_and(housekeeping_cpumask(HK_TYPE_RCU), + cpu_online_mask); + + smp_call_function_single(target, swake_up_one_online_ipi, + wqh, 0); + put_cpu(); + } else { + put_cpu(); + swake_up_one(wqh); + } +} + /* * Awaken the grace-period kthread. Don't do a self-awaken (unless in an * interrupt or softirq handler, in which case we just might immediately @@ -1075,7 +1107,7 @@ static void rcu_gp_kthread_wake(void) return; WRITE_ONCE(rcu_state.gp_wake_time, jiffies); WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq)); - swake_up_one(&rcu_state.gp_wq); + swake_up_one_online(&rcu_state.gp_wq); } /* diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index aa3ec3c3b9f7..6d2cbed96b46 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -172,7 +172,6 @@ static bool sync_rcu_exp_done_unlocked(struct rcu_node *rnp) return ret; } - /* * Report the exit from RCU read-side critical section for the last task * that queued itself during or before the current expedited preemptible-RCU @@ -200,7 +199,7 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - swake_up_one(&rcu_state.expedited_wq); + swake_up_one_online(&rcu_state.expedited_wq); } break; } diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 0c5be7ebb1dc..08b16d20c85b 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -161,6 +161,9 @@ | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK) +static DEFINE_MUTEX(membarrier_ipi_mutex); +#define SERIALIZE_IPI() guard(mutex)(&membarrier_ipi_mutex) + static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ @@ -258,6 +261,7 @@ static int membarrier_global_expedited(void) if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + SERIALIZE_IPI(); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { @@ -346,6 +350,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + SERIALIZE_IPI(); cpus_read_lock(); if (cpu_id >= 0) { @@ -459,6 +464,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm) * between threads which are users of @mm has its membarrier state * updated. */ + SERIALIZE_IPI(); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 76bafa8d331a..3a2335bc1d58 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -37,6 +37,8 @@ static struct ctl_table sched_rt_sysctls[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = sched_rt_handler, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, }, { .procname = "sched_rt_runtime_us", @@ -44,6 +46,8 @@ static struct ctl_table sched_rt_sysctls[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = sched_rt_handler, + .extra1 = SYSCTL_NEG_ONE, + .extra2 = SYSCTL_INT_MAX, }, { .procname = "sched_rr_timeslice_ms", @@ -2970,9 +2974,6 @@ static int sched_rt_global_constraints(void) #ifdef CONFIG_SYSCTL static int sched_rt_global_validate(void) { - if (sysctl_sched_rt_period <= 0) - return -EINVAL; - if ((sysctl_sched_rt_runtime != RUNTIME_INF) && ((sysctl_sched_rt_runtime > sysctl_sched_rt_period) || ((u64)sysctl_sched_rt_runtime * @@ -3003,7 +3004,7 @@ static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, old_period = sysctl_sched_rt_period; old_runtime = sysctl_sched_rt_runtime; - ret = proc_dointvec(table, write, buffer, lenp, ppos); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) { ret = sched_rt_global_validate(); @@ -3047,6 +3048,9 @@ static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, sched_rr_timeslice = sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE : msecs_to_jiffies(sysctl_sched_rr_timeslice); + + if (sysctl_sched_rr_timeslice <= 0) + sysctl_sched_rr_timeslice = jiffies_to_msecs(RR_TIMESLICE); } mutex_unlock(&mutex); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 1c90e710d537..cc6db3bce1b2 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -126,6 +126,7 @@ static DECLARE_WORK(watchdog_work, clocksource_watchdog_work); static DEFINE_SPINLOCK(watchdog_lock); static int watchdog_running; static atomic_t watchdog_reset_pending; +static int64_t watchdog_max_interval; static inline void clocksource_watchdog_lock(unsigned long *flags) { @@ -144,6 +145,7 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating); * Interval: 0.5sec. */ #define WATCHDOG_INTERVAL (HZ >> 1) +#define WATCHDOG_INTERVAL_MAX_NS ((2 * WATCHDOG_INTERVAL) * (NSEC_PER_SEC / HZ)) static void clocksource_watchdog_work(struct work_struct *work) { @@ -396,8 +398,8 @@ static inline void clocksource_reset_watchdog(void) static void clocksource_watchdog(struct timer_list *unused) { u64 csnow, wdnow, cslast, wdlast, delta; + int64_t wd_nsec, cs_nsec, interval; int next_cpu, reset_pending; - int64_t wd_nsec, cs_nsec; struct clocksource *cs; enum wd_read_status read_ret; unsigned long extra_wait = 0; @@ -467,6 +469,27 @@ static void clocksource_watchdog(struct timer_list *unused) if (atomic_read(&watchdog_reset_pending)) continue; + /* + * The processing of timer softirqs can get delayed (usually + * on account of ksoftirqd not getting to run in a timely + * manner), which causes the watchdog interval to stretch. + * Skew detection may fail for longer watchdog intervals + * on account of fixed margins being used. + * Some clocksources, e.g. acpi_pm, cannot tolerate + * watchdog intervals longer than a few seconds. + */ + interval = max(cs_nsec, wd_nsec); + if (unlikely(interval > WATCHDOG_INTERVAL_MAX_NS)) { + if (system_state > SYSTEM_SCHEDULING && + interval > 2 * watchdog_max_interval) { + watchdog_max_interval = interval; + pr_warn("Long readout interval, skipping watchdog check: cs_nsec: %lld wd_nsec: %lld\n", + cs_nsec, wd_nsec); + } + watchdog_timer.expires = jiffies; + continue; + } + /* Check the deviation from the watchdog clocksource. */ md = cs->uncertainty_margin + watchdog->uncertainty_margin; if (abs(cs_nsec - wd_nsec) > md) { diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 5561dabc9b22..9bb88836c42e 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1082,6 +1082,7 @@ static int enqueue_hrtimer(struct hrtimer *timer, enum hrtimer_mode mode) { debug_activate(timer, mode); + WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; @@ -2180,6 +2181,7 @@ int hrtimers_prepare_cpu(unsigned int cpu) cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; + cpu_base->online = 1; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } @@ -2247,6 +2249,7 @@ int hrtimers_cpu_dying(unsigned int dying_cpu) smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); + old_base->online = 0; raw_spin_unlock(&old_base->lock); return 0; @@ -2263,7 +2266,7 @@ void __init hrtimers_init(void) /** * schedule_hrtimeout_range_clock - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) + * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks * @mode: timer mode * @clock_id: timer clock to be used */ @@ -2290,6 +2293,13 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, return -EINTR; } + /* + * Override any slack passed by the user if under + * rt contraints. + */ + if (rt_task(current)) + delta = 0; + hrtimer_init_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); hrtimer_sleeper_start_expires(&t, mode); @@ -2309,7 +2319,7 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); /** * schedule_hrtimeout_range - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) + * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks * @mode: timer mode * * Make the current task sleep until the given expiry time has @@ -2317,7 +2327,8 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); * the current task state has been set (see set_current_state()). * * The @delta argument gives the kernel the freedom to schedule the - * actual wakeup to a time that is both power and performance friendly. + * actual wakeup to a time that is both power and performance friendly + * for regular (non RT/DL) tasks. * The kernel give the normal best effort behavior for "@expires+@delta", * but may decide to fire the timer earlier, but no earlier than @expires. * diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 798e1841d286..8cfdc6b978d7 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1556,13 +1556,23 @@ void tick_setup_sched_timer(void) void tick_cancel_sched_timer(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + ktime_t idle_sleeptime, iowait_sleeptime; + unsigned long idle_calls, idle_sleeps; # ifdef CONFIG_HIGH_RES_TIMERS if (ts->sched_timer.base) hrtimer_cancel(&ts->sched_timer); # endif + idle_sleeptime = ts->idle_sleeptime; + iowait_sleeptime = ts->iowait_sleeptime; + idle_calls = ts->idle_calls; + idle_sleeps = ts->idle_sleeps; memset(ts, 0, sizeof(*ts)); + ts->idle_sleeptime = idle_sleeptime; + ts->iowait_sleeptime = iowait_sleeptime; + ts->idle_calls = idle_calls; + ts->idle_sleeps = idle_sleeps; } #endif diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f4a494a457c5..3fdde232eaa9 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -368,8 +368,6 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void) return &bpf_probe_write_user_proto; } -static DEFINE_RAW_SPINLOCK(trace_printk_lock); - #define MAX_TRACE_PRINTK_VARARGS 3 #define BPF_TRACE_PRINTK_SIZE 1024 @@ -377,23 +375,22 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 }; - u32 *bin_args; - static char buf[BPF_TRACE_PRINTK_SIZE]; - unsigned long flags; + struct bpf_bprintf_data data = { + .get_bin_args = true, + .get_buf = true, + }; int ret; - ret = bpf_bprintf_prepare(fmt, fmt_size, args, &bin_args, - MAX_TRACE_PRINTK_VARARGS); + ret = bpf_bprintf_prepare(fmt, fmt_size, args, + MAX_TRACE_PRINTK_VARARGS, &data); if (ret < 0) return ret; - raw_spin_lock_irqsave(&trace_printk_lock, flags); - ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); - trace_bpf_trace_printk(buf); - raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + trace_bpf_trace_printk(data.buf); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return ret; } @@ -426,30 +423,29 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data, +BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, args, u32, data_len) { - static char buf[BPF_TRACE_PRINTK_SIZE]; - unsigned long flags; + struct bpf_bprintf_data data = { + .get_bin_args = true, + .get_buf = true, + }; int ret, num_args; - u32 *bin_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || - (data_len && !data)) + (data_len && !args)) return -EINVAL; num_args = data_len / 8; - ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + ret = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (ret < 0) return ret; - raw_spin_lock_irqsave(&trace_printk_lock, flags); - ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); - trace_bpf_trace_printk(buf); - raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + trace_bpf_trace_printk(data.buf); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return ret; } @@ -471,23 +467,25 @@ const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) } BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, - const void *, data, u32, data_len) + const void *, args, u32, data_len) { + struct bpf_bprintf_data data = { + .get_bin_args = true, + }; int err, num_args; - u32 *bin_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || - (data_len && !data)) + (data_len && !args)) return -EINVAL; num_args = data_len / 8; - err = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + err = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (err < 0) return err; - seq_bprintf(m, fmt, bin_args); + seq_bprintf(m, fmt, data.bin_args); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return seq_has_overflowed(m) ? -EOVERFLOW : 0; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 61803208706a..e019a9278794 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -646,8 +646,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) *cnt = rb_time_cnt(top); - /* If top and msb counts don't match, this interrupted a write */ - if (*cnt != rb_time_cnt(msb)) + /* If top, msb or bottom counts don't match, this interrupted a write */ + if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom)) return false; /* The shift to msb will lose its cnt bits */ @@ -705,48 +705,6 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set) return ret == expect; } -static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) -{ - unsigned long cnt, top, bottom, msb; - unsigned long cnt2, top2, bottom2, msb2; - u64 val; - - /* Any interruptions in this function should cause a failure */ - cnt = local_read(&t->cnt); - - /* The cmpxchg always fails if it interrupted an update */ - if (!__rb_time_read(t, &val, &cnt2)) - return false; - - if (val != expect) - return false; - - if ((cnt & 3) != cnt2) - return false; - - cnt2 = cnt + 1; - - rb_time_split(val, &top, &bottom, &msb); - msb = rb_time_val_cnt(msb, cnt); - top = rb_time_val_cnt(top, cnt); - bottom = rb_time_val_cnt(bottom, cnt); - - rb_time_split(set, &top2, &bottom2, &msb2); - msb2 = rb_time_val_cnt(msb2, cnt); - top2 = rb_time_val_cnt(top2, cnt2); - bottom2 = rb_time_val_cnt(bottom2, cnt2); - - if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2)) - return false; - if (!rb_time_read_cmpxchg(&t->msb, msb, msb2)) - return false; - if (!rb_time_read_cmpxchg(&t->top, top, top2)) - return false; - if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2)) - return false; - return true; -} - #else /* 64 bits */ /* local64_t always succeeds */ @@ -760,13 +718,6 @@ static void rb_time_set(rb_time_t *t, u64 val) { local64_set(&t->time, val); } - -static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) -{ - u64 val; - val = local64_cmpxchg(&t->time, expect, set); - return val == expect; -} #endif /* @@ -935,9 +886,14 @@ static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int f if (!nr_pages || !full) return true; - dirty = ring_buffer_nr_dirty_pages(buffer, cpu); + /* + * Add one as dirty will never equal nr_pages, as the sub-buffer + * that the writer is on is not counted as dirty. + * This is needed if "buffer_percent" is set to 100. + */ + dirty = ring_buffer_nr_dirty_pages(buffer, cpu) + 1; - return (dirty * 100) > (full * nr_pages); + return (dirty * 100) >= (full * nr_pages); } /* @@ -997,7 +953,8 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) /* make sure the waiters see the new index */ smp_wmb(); - rb_wake_up_waiters(&rbwork->work); + /* This can be called in any context */ + irq_work_queue(&rbwork->work); } /** @@ -1138,7 +1095,7 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return -EINVAL; + return EPOLLERR; cpu_buffer = buffer->buffers[cpu]; work = &cpu_buffer->irq_work; @@ -2981,25 +2938,6 @@ static unsigned rb_calculate_event_length(unsigned length) return length; } -static u64 rb_time_delta(struct ring_buffer_event *event) -{ - switch (event->type_len) { - case RINGBUF_TYPE_PADDING: - return 0; - - case RINGBUF_TYPE_TIME_EXTEND: - return rb_event_time_stamp(event); - - case RINGBUF_TYPE_TIME_STAMP: - return 0; - - case RINGBUF_TYPE_DATA: - return event->time_delta; - default: - return 0; - } -} - static inline int rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) @@ -3008,8 +2946,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *bpage; unsigned long index; unsigned long addr; - u64 write_stamp; - u64 delta; new_index = rb_event_index(event); old_index = new_index + rb_event_ts_length(event); @@ -3018,14 +2954,10 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, bpage = READ_ONCE(cpu_buffer->tail_page); - delta = rb_time_delta(event); - - if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp)) - return 0; - - /* Make sure the write stamp is read before testing the location */ - barrier(); - + /* + * Make sure the tail_page is still the same and + * the next write location is the end of this event + */ if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) { unsigned long write_mask = local_read(&bpage->write) & ~RB_WRITE_MASK; @@ -3036,20 +2968,20 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, * to make sure that the next event adds an absolute * value and does not rely on the saved write stamp, which * is now going to be bogus. + * + * By setting the before_stamp to zero, the next event + * is not going to use the write_stamp and will instead + * create an absolute timestamp. This means there's no + * reason to update the wirte_stamp! */ rb_time_set(&cpu_buffer->before_stamp, 0); - /* Something came in, can't discard */ - if (!rb_time_cmpxchg(&cpu_buffer->write_stamp, - write_stamp, write_stamp - delta)) - return 0; - /* * If an event were to come in now, it would see that the * write_stamp and the before_stamp are different, and assume * that this event just added itself before updating * the write stamp. The interrupting event will fix the - * write stamp for us, and use the before stamp as its delta. + * write stamp for us, and use an absolute timestamp. */ /* @@ -3488,7 +3420,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, return; /* - * If this interrupted another event, + * If this interrupted another event, */ if (atomic_inc_return(this_cpu_ptr(&checking)) != 1) goto out; @@ -3632,20 +3564,36 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, } else { u64 ts; /* SLOW PATH - Interrupted between A and C */ - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - /* Was interrupted before here, write_stamp must be valid */ + + /* Save the old before_stamp */ + a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); RB_WARN_ON(cpu_buffer, !a_ok); + + /* + * Read a new timestamp and update the before_stamp to make + * the next event after this one force using an absolute + * timestamp. This is in case an interrupt were to come in + * between E and F. + */ ts = rb_time_stamp(cpu_buffer->buffer); + rb_time_set(&cpu_buffer->before_stamp, ts); + barrier(); - /*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && - info->after < ts && - rb_time_cmpxchg(&cpu_buffer->write_stamp, - info->after, ts)) { - /* Nothing came after this event between C and E */ + /*E*/ a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); + /* Was interrupted before here, write_stamp must be valid */ + RB_WARN_ON(cpu_buffer, !a_ok); + barrier(); + /*F*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && + info->after == info->before && info->after < ts) { + /* + * Nothing came after this event between C and F, it is + * safe to use info->after for the delta as it + * matched info->before and is still valid. + */ info->delta = ts - info->after; } else { /* - * Interrupted between C and E: + * Interrupted between C and F: * Lost the previous events time stamp. Just set the * delta to zero, and this will be the same time as * the event this event interrupted. And the events that @@ -3696,6 +3644,12 @@ rb_reserve_next_event(struct trace_buffer *buffer, int nr_loops = 0; int add_ts_default; + /* ring buffer does cmpxchg, make sure it is safe in NMI context */ + if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && + (unlikely(in_nmi()))) { + return NULL; + } + rb_start_commit(cpu_buffer); /* The commit page can not change after this */ diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index 8d77526892f4..d944924cd1e1 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -477,6 +477,17 @@ static int __init synth_event_gen_test_init(void) ret = test_trace_synth_event(); WARN_ON(ret); + + /* Disable when done */ + trace_array_set_clr_event(gen_synth_test->tr, + "synthetic", + "gen_synth_test", false); + trace_array_set_clr_event(empty_synth_test->tr, + "synthetic", + "empty_synth_test", false); + trace_array_set_clr_event(create_synth_test->tr, + "synthetic", + "create_synth_test", false); out: return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 87eca95b57fb..f667d6bdddda 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -40,6 +40,7 @@ #include <linux/ctype.h> #include <linux/init.h> #include <linux/panic_notifier.h> +#include <linux/kmemleak.h> #include <linux/poll.h> #include <linux/nmi.h> #include <linux/fs.h> @@ -1850,6 +1851,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); + + /* Any waiters on the old snapshot buffer need to wake up */ + ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS); } /** @@ -1901,12 +1905,23 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) static int wait_on_pipe(struct trace_iterator *iter, int full) { + int ret; + /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, - full); + ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full); + +#ifdef CONFIG_TRACER_MAX_TRACE + /* + * Make sure this is still the snapshot buffer, as if a snapshot were + * to happen, this would now be the main buffer. + */ + if (iter->snapshot) + iter->array_buffer = &iter->tr->max_buffer; +#endif + return ret; } #ifdef CONFIG_FTRACE_STARTUP_TEST @@ -2235,7 +2250,7 @@ struct saved_cmdlines_buffer { unsigned *map_cmdline_to_pid; unsigned cmdline_num; int cmdline_idx; - char *saved_cmdlines; + char saved_cmdlines[]; }; static struct saved_cmdlines_buffer *savedcmd; @@ -2249,47 +2264,60 @@ static inline void set_cmdline(int idx, const char *cmdline) strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN); } -static int allocate_cmdlines_buffer(unsigned int val, - struct saved_cmdlines_buffer *s) +static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) +{ + int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN); + + kfree(s->map_cmdline_to_pid); + kmemleak_free(s); + free_pages((unsigned long)s, order); +} + +static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) { + struct saved_cmdlines_buffer *s; + struct page *page; + int orig_size, size; + int order; + + /* Figure out how much is needed to hold the given number of cmdlines */ + orig_size = sizeof(*s) + val * TASK_COMM_LEN; + order = get_order(orig_size); + size = 1 << (order + PAGE_SHIFT); + page = alloc_pages(GFP_KERNEL, order); + if (!page) + return NULL; + + s = page_address(page); + kmemleak_alloc(s, size, 1, GFP_KERNEL); + memset(s, 0, sizeof(*s)); + + /* Round up to actual allocation */ + val = (size - sizeof(*s)) / TASK_COMM_LEN; + s->cmdline_num = val; + s->map_cmdline_to_pid = kmalloc_array(val, sizeof(*s->map_cmdline_to_pid), GFP_KERNEL); - if (!s->map_cmdline_to_pid) - return -ENOMEM; - - s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL); - if (!s->saved_cmdlines) { - kfree(s->map_cmdline_to_pid); - return -ENOMEM; + if (!s->map_cmdline_to_pid) { + free_saved_cmdlines_buffer(s); + return NULL; } s->cmdline_idx = 0; - s->cmdline_num = val; memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(s->map_pid_to_cmdline)); memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP, val * sizeof(*s->map_cmdline_to_pid)); - return 0; + return s; } static int trace_create_savedcmd(void) { - int ret; - - savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL); - if (!savedcmd) - return -ENOMEM; + savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT); - ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd); - if (ret < 0) { - kfree(savedcmd); - savedcmd = NULL; - return -ENOMEM; - } - - return 0; + return savedcmd ? 0 : -ENOMEM; } int is_tracing_stopped(void) @@ -4665,7 +4693,11 @@ static int s_show(struct seq_file *m, void *v) iter->leftover = ret; } else { - print_trace_line(iter); + ret = print_trace_line(iter); + if (ret == TRACE_TYPE_PARTIAL_LINE) { + iter->seq.full = 0; + trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); + } ret = trace_print_seq(m, &iter->seq); /* * If we overflow the seq_file buffer, then it will @@ -4898,6 +4930,12 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp) return 0; } +int tracing_single_release_file_tr(struct inode *inode, struct file *filp) +{ + tracing_release_file_tr(inode, filp); + return single_release(inode, filp); +} + static int tracing_mark_open(struct inode *inode, struct file *filp) { stream_open(inode, filp); @@ -5948,26 +5986,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } -static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) -{ - kfree(s->saved_cmdlines); - kfree(s->map_cmdline_to_pid); - kfree(s); -} - static int tracing_resize_saved_cmdlines(unsigned int val) { struct saved_cmdlines_buffer *s, *savedcmd_temp; - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = allocate_cmdlines_buffer(val); if (!s) return -ENOMEM; - if (allocate_cmdlines_buffer(val, s) < 0) { - kfree(s); - return -ENOMEM; - } - preempt_disable(); arch_spin_lock(&trace_cmdline_lock); savedcmd_temp = savedcmd; @@ -8433,7 +8459,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, wait_index = READ_ONCE(iter->wait_index); - ret = wait_on_pipe(iter, iter->tr->buffer_percent); + ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 10aaafa2936d..aad7fcd84617 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -592,6 +592,7 @@ int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); int tracing_open_file_tr(struct inode *inode, struct file *filp); int tracing_release_file_tr(struct inode *inode, struct file *filp); +int tracing_single_release_file_tr(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); bool tracer_tracing_is_on(struct trace_array *tr); void tracer_tracing_on(struct trace_array *tr); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 1470af219073..3b0da1bddf63 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5532,10 +5532,12 @@ static int event_hist_open(struct inode *inode, struct file *file) { int ret; - ret = security_locked_down(LOCKDOWN_TRACEFS); + ret = tracing_open_file_tr(inode, file); if (ret) return ret; + /* Clear private_data to avoid warning in single_open() */ + file->private_data = NULL; return single_open(file, hist_show, file); } @@ -5543,7 +5545,7 @@ const struct file_operations event_hist_fops = { .open = event_hist_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = tracing_single_release_file_tr, }; #ifdef CONFIG_HIST_TRIGGERS_DEBUG @@ -5809,10 +5811,12 @@ static int event_hist_debug_open(struct inode *inode, struct file *file) { int ret; - ret = security_locked_down(LOCKDOWN_TRACEFS); + ret = tracing_open_file_tr(inode, file); if (ret) return ret; + /* Clear private_data to avoid warning in single_open() */ + file->private_data = NULL; return single_open(file, hist_debug_show, file); } @@ -5820,7 +5824,7 @@ const struct file_operations event_hist_debug_fops = { .open = event_hist_debug_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = tracing_single_release_file_tr, }; #endif diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 918730d74932..f941ce01ee35 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1455,8 +1455,10 @@ register_snapshot_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) { - if (tracing_alloc_snapshot_instance(file->tr) != 0) - return 0; + int ret = tracing_alloc_snapshot_instance(file->tr); + + if (ret < 0) + return ret; return register_trigger(glob, data, file); } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index a34a4fcdab7b..e3993d19687d 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -714,14 +714,31 @@ static int count_symbols(void *data, unsigned long unused) return 0; } +struct sym_count_ctx { + unsigned int count; + const char *name; +}; + +static int count_mod_symbols(void *data, const char *name, + struct module *module, unsigned long unused) +{ + struct sym_count_ctx *ctx = data; + + if (strcmp(name, ctx->name) == 0) + ctx->count++; + + return 0; +} + static unsigned int number_of_same_symbols(char *func_name) { - unsigned int count; + struct sym_count_ctx ctx = { .count = 0, .name = func_name }; + + kallsyms_on_each_match_symbol(count_symbols, func_name, &ctx.count); - count = 0; - kallsyms_on_each_match_symbol(count_symbols, func_name, &count); + module_kallsyms_on_each_symbol(count_mod_symbols, &ctx); - return count; + return ctx.count; } static int __trace_kprobe_create(int argc, const char *argv[]) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 5cd4fb656306..bf1965b18099 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1445,11 +1445,12 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter, { struct print_entry *field; struct trace_seq *s = &iter->seq; + int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); seq_print_ip_sym(s, field->ip, flags); - trace_seq_printf(s, ": %s", field->buf); + trace_seq_printf(s, ": %.*s", max, field->buf); return trace_handle_return(s); } @@ -1458,10 +1459,11 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags, struct trace_event *event) { struct print_entry *field; + int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); - trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf); + trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf); return trace_handle_return(&iter->seq); } diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index c774e560f2f9..a4dcf0f24352 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -574,7 +574,12 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only) } memcpy(elt->key, key, map->key_size); - entry->val = elt; + /* + * Ensure the initialization is visible and + * publish the elt. + */ + smp_wmb(); + WRITE_ONCE(entry->val, elt); atomic64_inc(&map->hits); return entry->val; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 4db0199651f5..95541b99aa8e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -364,6 +364,15 @@ config PAHOLE_HAS_BTF_TAG btf_decl_tag) or not. Currently only clang compiler implements these attributes, so make the config depend on CC_IS_CLANG. +config PAHOLE_HAS_LANG_EXCLUDE + def_bool PAHOLE_VERSION >= 124 + help + Support for the --lang_exclude flag which makes pahole exclude + compilation units from the supplied language. Used in Kbuild to + omit Rust CUs which are not supported in version 1.24 of pahole, + otherwise it would emit malformed kernel and module binaries when + using DEBUG_INFO_BTF_MODULES. + config DEBUG_INFO_BTF_MODULES def_bool y depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF diff --git a/lib/Makefile b/lib/Makefile index 5ffe72ec9979..6f1611d053e6 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -361,6 +361,8 @@ obj-$(CONFIG_SBITMAP) += sbitmap.o obj-$(CONFIG_PARMAN) += parman.o +obj-y += group_cpus.o + # GCC library routines obj-$(CONFIG_GENERIC_LIB_ASHLDI3) += ashldi3.o obj-$(CONFIG_GENERIC_LIB_ASHRDI3) += ashrdi3.o diff --git a/lib/debugobjects.c b/lib/debugobjects.c index dacb80c22c4f..5dfa582dbadd 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -609,9 +609,8 @@ static void debug_objects_fill_pool(void) static void __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags; debug_objects_fill_pool(); @@ -632,24 +631,18 @@ __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: obj->state = ODEBUG_STATE_INIT; - break; - - case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "init"); - debug_object_fixup(descr->fixup_init, addr, state); - return; - - case ODEBUG_STATE_DESTROYED: raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "init"); return; default: break; } + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "init"); + + if (o.state == ODEBUG_STATE_ACTIVE) + debug_object_fixup(descr->fixup_init, addr, o.state); } /** @@ -690,11 +683,9 @@ EXPORT_SYMBOL_GPL(debug_object_init_on_stack); int debug_object_activate(void *addr, const struct debug_obj_descr *descr) { struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; - enum debug_obj_state state; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - int ret; if (!debug_objects_enabled) return 0; @@ -706,49 +697,38 @@ int debug_object_activate(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags); obj = lookup_object_or_alloc(addr, db, descr, false, true); - if (likely(!IS_ERR_OR_NULL(obj))) { - bool print_object = false; - + if (unlikely(!obj)) { + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_objects_oom(); + return 0; + } else if (likely(!IS_ERR(obj))) { switch (obj->state) { - case ODEBUG_STATE_INIT: - case ODEBUG_STATE_INACTIVE: - obj->state = ODEBUG_STATE_ACTIVE; - ret = 0; - break; - case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "activate"); - ret = debug_object_fixup(descr->fixup_activate, addr, state); - return ret ? 0 : -EINVAL; - case ODEBUG_STATE_DESTROYED: - print_object = true; - ret = -EINVAL; + o = *obj; break; + case ODEBUG_STATE_INIT: + case ODEBUG_STATE_INACTIVE: + obj->state = ODEBUG_STATE_ACTIVE; + fallthrough; default: - ret = 0; - break; + raw_spin_unlock_irqrestore(&db->lock, flags); + return 0; } - raw_spin_unlock_irqrestore(&db->lock, flags); - if (print_object) - debug_print_object(obj, "activate"); - return ret; } raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "activate"); - /* If NULL the allocation has hit OOM */ - if (!obj) { - debug_objects_oom(); - return 0; + switch (o.state) { + case ODEBUG_STATE_ACTIVE: + case ODEBUG_STATE_NOTAVAILABLE: + if (debug_object_fixup(descr->fixup_activate, addr, o.state)) + return 0; + fallthrough; + default: + return -EINVAL; } - - /* Object is neither static nor tracked. It's not initialized */ - debug_print_object(&o, "activate"); - ret = debug_object_fixup(descr->fixup_activate, addr, ODEBUG_STATE_NOTAVAILABLE); - return ret ? 0 : -EINVAL; } EXPORT_SYMBOL_GPL(debug_object_activate); @@ -759,10 +739,10 @@ EXPORT_SYMBOL_GPL(debug_object_activate); */ void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) { + struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - bool print_object = false; if (!debug_objects_enabled) return; @@ -774,33 +754,24 @@ void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) obj = lookup_object(addr, db); if (obj) { switch (obj->state) { + case ODEBUG_STATE_DESTROYED: + break; case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: case ODEBUG_STATE_ACTIVE: - if (!obj->astate) - obj->state = ODEBUG_STATE_INACTIVE; - else - print_object = true; - break; - - case ODEBUG_STATE_DESTROYED: - print_object = true; - break; + if (obj->astate) + break; + obj->state = ODEBUG_STATE_INACTIVE; + fallthrough; default: - break; + raw_spin_unlock_irqrestore(&db->lock, flags); + return; } + o = *obj; } raw_spin_unlock_irqrestore(&db->lock, flags); - if (!obj) { - struct debug_obj o = { .object = addr, - .state = ODEBUG_STATE_NOTAVAILABLE, - .descr = descr }; - - debug_print_object(&o, "deactivate"); - } else if (print_object) { - debug_print_object(obj, "deactivate"); - } + debug_print_object(&o, "deactivate"); } EXPORT_SYMBOL_GPL(debug_object_deactivate); @@ -811,11 +782,9 @@ EXPORT_SYMBOL_GPL(debug_object_deactivate); */ void debug_object_destroy(void *addr, const struct debug_obj_descr *descr) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags; - bool print_object = false; if (!debug_objects_enabled) return; @@ -825,32 +794,31 @@ void debug_object_destroy(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags); obj = lookup_object(addr, db); - if (!obj) - goto out_unlock; + if (!obj) { + raw_spin_unlock_irqrestore(&db->lock, flags); + return; + } switch (obj->state) { + case ODEBUG_STATE_ACTIVE: + case ODEBUG_STATE_DESTROYED: + break; case ODEBUG_STATE_NONE: case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: obj->state = ODEBUG_STATE_DESTROYED; - break; - case ODEBUG_STATE_ACTIVE: - state = obj->state; + fallthrough; + default: raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "destroy"); - debug_object_fixup(descr->fixup_destroy, addr, state); return; - - case ODEBUG_STATE_DESTROYED: - print_object = true; - break; - default: - break; } -out_unlock: + + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); - if (print_object) - debug_print_object(obj, "destroy"); + debug_print_object(&o, "destroy"); + + if (o.state == ODEBUG_STATE_ACTIVE) + debug_object_fixup(descr->fixup_destroy, addr, o.state); } EXPORT_SYMBOL_GPL(debug_object_destroy); @@ -861,9 +829,8 @@ EXPORT_SYMBOL_GPL(debug_object_destroy); */ void debug_object_free(void *addr, const struct debug_obj_descr *descr) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags; if (!debug_objects_enabled) @@ -874,24 +841,26 @@ void debug_object_free(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags); obj = lookup_object(addr, db); - if (!obj) - goto out_unlock; + if (!obj) { + raw_spin_unlock_irqrestore(&db->lock, flags); + return; + } switch (obj->state) { case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "free"); - debug_object_fixup(descr->fixup_free, addr, state); - return; + break; default: hlist_del(&obj->node); raw_spin_unlock_irqrestore(&db->lock, flags); free_object(obj); return; } -out_unlock: + + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "free"); + + debug_object_fixup(descr->fixup_free, addr, o.state); } EXPORT_SYMBOL_GPL(debug_object_free); @@ -943,10 +912,10 @@ void debug_object_active_state(void *addr, const struct debug_obj_descr *descr, unsigned int expect, unsigned int next) { + struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - bool print_object = false; if (!debug_objects_enabled) return; @@ -959,28 +928,19 @@ debug_object_active_state(void *addr, const struct debug_obj_descr *descr, if (obj) { switch (obj->state) { case ODEBUG_STATE_ACTIVE: - if (obj->astate == expect) - obj->astate = next; - else - print_object = true; - break; - + if (obj->astate != expect) + break; + obj->astate = next; + raw_spin_unlock_irqrestore(&db->lock, flags); + return; default: - print_object = true; break; } + o = *obj; } raw_spin_unlock_irqrestore(&db->lock, flags); - if (!obj) { - struct debug_obj o = { .object = addr, - .state = ODEBUG_STATE_NOTAVAILABLE, - .descr = descr }; - - debug_print_object(&o, "active_state"); - } else if (print_object) { - debug_print_object(obj, "active_state"); - } + debug_print_object(&o, "active_state"); } EXPORT_SYMBOL_GPL(debug_object_active_state); @@ -988,12 +948,10 @@ EXPORT_SYMBOL_GPL(debug_object_active_state); static void __debug_check_no_obj_freed(const void *address, unsigned long size) { unsigned long flags, oaddr, saddr, eaddr, paddr, chunks; - const struct debug_obj_descr *descr; - enum debug_obj_state state; + int cnt, objs_checked = 0; + struct debug_obj *obj, o; struct debug_bucket *db; struct hlist_node *tmp; - struct debug_obj *obj; - int cnt, objs_checked = 0; saddr = (unsigned long) address; eaddr = saddr + size; @@ -1015,12 +973,10 @@ repeat: switch (obj->state) { case ODEBUG_STATE_ACTIVE: - descr = obj->descr; - state = obj->state; + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "free"); - debug_object_fixup(descr->fixup_free, - (void *) oaddr, state); + debug_print_object(&o, "free"); + debug_object_fixup(o.descr->fixup_free, (void *)oaddr, o.state); goto repeat; default: hlist_del(&obj->node); diff --git a/lib/group_cpus.c b/lib/group_cpus.c new file mode 100644 index 000000000000..0292611901b8 --- /dev/null +++ b/lib/group_cpus.c @@ -0,0 +1,438 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2016 Thomas Gleixner. + * Copyright (C) 2016-2017 Christoph Hellwig. + */ +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/cpu.h> +#include <linux/sort.h> +#include <linux/group_cpus.h> + +#ifdef CONFIG_SMP + +static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk, + unsigned int cpus_per_grp) +{ + const struct cpumask *siblmsk; + int cpu, sibl; + + for ( ; cpus_per_grp > 0; ) { + cpu = cpumask_first(nmsk); + + /* Should not happen, but I'm too lazy to think about it */ + if (cpu >= nr_cpu_ids) + return; + + cpumask_clear_cpu(cpu, nmsk); + cpumask_set_cpu(cpu, irqmsk); + cpus_per_grp--; + + /* If the cpu has siblings, use them first */ + siblmsk = topology_sibling_cpumask(cpu); + for (sibl = -1; cpus_per_grp > 0; ) { + sibl = cpumask_next(sibl, siblmsk); + if (sibl >= nr_cpu_ids) + break; + if (!cpumask_test_and_clear_cpu(sibl, nmsk)) + continue; + cpumask_set_cpu(sibl, irqmsk); + cpus_per_grp--; + } + } +} + +static cpumask_var_t *alloc_node_to_cpumask(void) +{ + cpumask_var_t *masks; + int node; + + masks = kcalloc(nr_node_ids, sizeof(cpumask_var_t), GFP_KERNEL); + if (!masks) + return NULL; + + for (node = 0; node < nr_node_ids; node++) { + if (!zalloc_cpumask_var(&masks[node], GFP_KERNEL)) + goto out_unwind; + } + + return masks; + +out_unwind: + while (--node >= 0) + free_cpumask_var(masks[node]); + kfree(masks); + return NULL; +} + +static void free_node_to_cpumask(cpumask_var_t *masks) +{ + int node; + + for (node = 0; node < nr_node_ids; node++) + free_cpumask_var(masks[node]); + kfree(masks); +} + +static void build_node_to_cpumask(cpumask_var_t *masks) +{ + int cpu; + + for_each_possible_cpu(cpu) + cpumask_set_cpu(cpu, masks[cpu_to_node(cpu)]); +} + +static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask, + const struct cpumask *mask, nodemask_t *nodemsk) +{ + int n, nodes = 0; + + /* Calculate the number of nodes in the supplied affinity mask */ + for_each_node(n) { + if (cpumask_intersects(mask, node_to_cpumask[n])) { + node_set(n, *nodemsk); + nodes++; + } + } + return nodes; +} + +struct node_groups { + unsigned id; + + union { + unsigned ngroups; + unsigned ncpus; + }; +}; + +static int ncpus_cmp_func(const void *l, const void *r) +{ + const struct node_groups *ln = l; + const struct node_groups *rn = r; + + return ln->ncpus - rn->ncpus; +} + +/* + * Allocate group number for each node, so that for each node: + * + * 1) the allocated number is >= 1 + * + * 2) the allocated number is <= active CPU number of this node + * + * The actual allocated total groups may be less than @numgrps when + * active total CPU number is less than @numgrps. + * + * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]' + * for each node. + */ +static void alloc_nodes_groups(unsigned int numgrps, + cpumask_var_t *node_to_cpumask, + const struct cpumask *cpu_mask, + const nodemask_t nodemsk, + struct cpumask *nmsk, + struct node_groups *node_groups) +{ + unsigned n, remaining_ncpus = 0; + + for (n = 0; n < nr_node_ids; n++) { + node_groups[n].id = n; + node_groups[n].ncpus = UINT_MAX; + } + + for_each_node_mask(n, nodemsk) { + unsigned ncpus; + + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + ncpus = cpumask_weight(nmsk); + + if (!ncpus) + continue; + remaining_ncpus += ncpus; + node_groups[n].ncpus = ncpus; + } + + numgrps = min_t(unsigned, remaining_ncpus, numgrps); + + sort(node_groups, nr_node_ids, sizeof(node_groups[0]), + ncpus_cmp_func, NULL); + + /* + * Allocate groups for each node according to the ratio of this + * node's nr_cpus to remaining un-assigned ncpus. 'numgrps' is + * bigger than number of active numa nodes. Always start the + * allocation from the node with minimized nr_cpus. + * + * This way guarantees that each active node gets allocated at + * least one group, and the theory is simple: over-allocation + * is only done when this node is assigned by one group, so + * other nodes will be allocated >= 1 groups, since 'numgrps' is + * bigger than number of numa nodes. + * + * One perfect invariant is that number of allocated groups for + * each node is <= CPU count of this node: + * + * 1) suppose there are two nodes: A and B + * ncpu(X) is CPU count of node X + * grps(X) is the group count allocated to node X via this + * algorithm + * + * ncpu(A) <= ncpu(B) + * ncpu(A) + ncpu(B) = N + * grps(A) + grps(B) = G + * + * grps(A) = max(1, round_down(G * ncpu(A) / N)) + * grps(B) = G - grps(A) + * + * both N and G are integer, and 2 <= G <= N, suppose + * G = N - delta, and 0 <= delta <= N - 2 + * + * 2) obviously grps(A) <= ncpu(A) because: + * + * if grps(A) is 1, then grps(A) <= ncpu(A) given + * ncpu(A) >= 1 + * + * otherwise, + * grps(A) <= G * ncpu(A) / N <= ncpu(A), given G <= N + * + * 3) prove how grps(B) <= ncpu(B): + * + * if round_down(G * ncpu(A) / N) == 0, vecs(B) won't be + * over-allocated, so grps(B) <= ncpu(B), + * + * otherwise: + * + * grps(A) = + * round_down(G * ncpu(A) / N) = + * round_down((N - delta) * ncpu(A) / N) = + * round_down((N * ncpu(A) - delta * ncpu(A)) / N) >= + * round_down((N * ncpu(A) - delta * N) / N) = + * cpu(A) - delta + * + * then: + * + * grps(A) - G >= ncpu(A) - delta - G + * => + * G - grps(A) <= G + delta - ncpu(A) + * => + * grps(B) <= N - ncpu(A) + * => + * grps(B) <= cpu(B) + * + * For nodes >= 3, it can be thought as one node and another big + * node given that is exactly what this algorithm is implemented, + * and we always re-calculate 'remaining_ncpus' & 'numgrps', and + * finally for each node X: grps(X) <= ncpu(X). + * + */ + for (n = 0; n < nr_node_ids; n++) { + unsigned ngroups, ncpus; + + if (node_groups[n].ncpus == UINT_MAX) + continue; + + WARN_ON_ONCE(numgrps == 0); + + ncpus = node_groups[n].ncpus; + ngroups = max_t(unsigned, 1, + numgrps * ncpus / remaining_ncpus); + WARN_ON_ONCE(ngroups > ncpus); + + node_groups[n].ngroups = ngroups; + + remaining_ncpus -= ncpus; + numgrps -= ngroups; + } +} + +static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps, + cpumask_var_t *node_to_cpumask, + const struct cpumask *cpu_mask, + struct cpumask *nmsk, struct cpumask *masks) +{ + unsigned int i, n, nodes, cpus_per_grp, extra_grps, done = 0; + unsigned int last_grp = numgrps; + unsigned int curgrp = startgrp; + nodemask_t nodemsk = NODE_MASK_NONE; + struct node_groups *node_groups; + + if (cpumask_empty(cpu_mask)) + return 0; + + nodes = get_nodes_in_cpumask(node_to_cpumask, cpu_mask, &nodemsk); + + /* + * If the number of nodes in the mask is greater than or equal the + * number of groups we just spread the groups across the nodes. + */ + if (numgrps <= nodes) { + for_each_node_mask(n, nodemsk) { + /* Ensure that only CPUs which are in both masks are set */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + cpumask_or(&masks[curgrp], &masks[curgrp], nmsk); + if (++curgrp == last_grp) + curgrp = 0; + } + return numgrps; + } + + node_groups = kcalloc(nr_node_ids, + sizeof(struct node_groups), + GFP_KERNEL); + if (!node_groups) + return -ENOMEM; + + /* allocate group number for each node */ + alloc_nodes_groups(numgrps, node_to_cpumask, cpu_mask, + nodemsk, nmsk, node_groups); + for (i = 0; i < nr_node_ids; i++) { + unsigned int ncpus, v; + struct node_groups *nv = &node_groups[i]; + + if (nv->ngroups == UINT_MAX) + continue; + + /* Get the cpus on this node which are in the mask */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[nv->id]); + ncpus = cpumask_weight(nmsk); + if (!ncpus) + continue; + + WARN_ON_ONCE(nv->ngroups > ncpus); + + /* Account for rounding errors */ + extra_grps = ncpus - nv->ngroups * (ncpus / nv->ngroups); + + /* Spread allocated groups on CPUs of the current node */ + for (v = 0; v < nv->ngroups; v++, curgrp++) { + cpus_per_grp = ncpus / nv->ngroups; + + /* Account for extra groups to compensate rounding errors */ + if (extra_grps) { + cpus_per_grp++; + --extra_grps; + } + + /* + * wrapping has to be considered given 'startgrp' + * may start anywhere + */ + if (curgrp >= last_grp) + curgrp = 0; + grp_spread_init_one(&masks[curgrp], nmsk, + cpus_per_grp); + } + done += nv->ngroups; + } + kfree(node_groups); + return done; +} + +/** + * group_cpus_evenly - Group all CPUs evenly per NUMA/CPU locality + * @numgrps: number of groups + * + * Return: cpumask array if successful, NULL otherwise. And each element + * includes CPUs assigned to this group + * + * Try to put close CPUs from viewpoint of CPU and NUMA locality into + * same group, and run two-stage grouping: + * 1) allocate present CPUs on these groups evenly first + * 2) allocate other possible CPUs on these groups evenly + * + * We guarantee in the resulted grouping that all CPUs are covered, and + * no same CPU is assigned to multiple groups + */ +struct cpumask *group_cpus_evenly(unsigned int numgrps) +{ + unsigned int curgrp = 0, nr_present = 0, nr_others = 0; + cpumask_var_t *node_to_cpumask; + cpumask_var_t nmsk, npresmsk; + int ret = -ENOMEM; + struct cpumask *masks = NULL; + + if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL)) + return NULL; + + if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL)) + goto fail_nmsk; + + node_to_cpumask = alloc_node_to_cpumask(); + if (!node_to_cpumask) + goto fail_npresmsk; + + masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL); + if (!masks) + goto fail_node_to_cpumask; + + build_node_to_cpumask(node_to_cpumask); + + /* + * Make a local cache of 'cpu_present_mask', so the two stages + * spread can observe consistent 'cpu_present_mask' without holding + * cpu hotplug lock, then we can reduce deadlock risk with cpu + * hotplug code. + * + * Here CPU hotplug may happen when reading `cpu_present_mask`, and + * we can live with the case because it only affects that hotplug + * CPU is handled in the 1st or 2nd stage, and either way is correct + * from API user viewpoint since 2-stage spread is sort of + * optimization. + */ + cpumask_copy(npresmsk, data_race(cpu_present_mask)); + + /* grouping present CPUs first */ + ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask, + npresmsk, nmsk, masks); + if (ret < 0) + goto fail_build_affinity; + nr_present = ret; + + /* + * Allocate non present CPUs starting from the next group to be + * handled. If the grouping of present CPUs already exhausted the + * group space, assign the non present CPUs to the already + * allocated out groups. + */ + if (nr_present >= numgrps) + curgrp = 0; + else + curgrp = nr_present; + cpumask_andnot(npresmsk, cpu_possible_mask, npresmsk); + ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask, + npresmsk, nmsk, masks); + if (ret >= 0) + nr_others = ret; + + fail_build_affinity: + if (ret >= 0) + WARN_ON(nr_present + nr_others < numgrps); + + fail_node_to_cpumask: + free_node_to_cpumask(node_to_cpumask); + + fail_npresmsk: + free_cpumask_var(npresmsk); + + fail_nmsk: + free_cpumask_var(nmsk); + if (ret < 0) { + kfree(masks); + return NULL; + } + return masks; +} +#else /* CONFIG_SMP */ +struct cpumask *group_cpus_evenly(unsigned int numgrps) +{ + struct cpumask *masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL); + + if (!masks) + return NULL; + + /* assign all CPUs(cpu 0) to the 1st group only */ + cpumask_copy(&masks[0], cpu_possible_mask); + return masks; +} +#endif /* CONFIG_SMP */ diff --git a/lib/idr.c b/lib/idr.c index 13f2758c2377..da36054c3ca0 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -508,7 +508,7 @@ void ida_free(struct ida *ida, unsigned int id) goto delete; xas_store(&xas, xa_mk_value(v)); } else { - if (!test_bit(bit, bitmap->bitmap)) + if (!bitmap || !test_bit(bit, bitmap->bitmap)) goto err; __clear_bit(bit, bitmap->bitmap); xas_set_mark(&xas, XA_FREE_MARK); diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index b08bb1fba106..de5e71458358 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -52,12 +52,14 @@ static void debugfs_print_result(struct seq_file *seq, static int debugfs_print_results(struct seq_file *seq, void *v) { struct kunit_suite *suite = (struct kunit_suite *)seq->private; - enum kunit_status success = kunit_suite_has_succeeded(suite); + enum kunit_status success; struct kunit_case *test_case; if (!suite) return 0; + success = kunit_suite_has_succeeded(suite); + /* Print KTAP header so the debugfs log can be parsed as valid KTAP. */ seq_puts(seq, "KTAP version 1\n"); seq_puts(seq, "1..1\n"); diff --git a/lib/mpi/ec.c b/lib/mpi/ec.c index 40f5908e57a4..e16dca1e23d5 100644 --- a/lib/mpi/ec.c +++ b/lib/mpi/ec.c @@ -584,6 +584,9 @@ void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model, ctx->a = mpi_copy(a); ctx->b = mpi_copy(b); + ctx->d = NULL; + ctx->t.two_inv_p = NULL; + ctx->t.p_barrett = use_barrett > 0 ? mpi_barrett_init(ctx->p, 0) : NULL; mpi_ec_get_reset(ctx); diff --git a/lib/test_ida.c b/lib/test_ida.c index b06880625961..55105baa19da 100644 --- a/lib/test_ida.c +++ b/lib/test_ida.c @@ -150,6 +150,45 @@ static void ida_check_conv(struct ida *ida) IDA_BUG_ON(ida, !ida_is_empty(ida)); } +/* + * Check various situations where we attempt to free an ID we don't own. + */ +static void ida_check_bad_free(struct ida *ida) +{ + unsigned long i; + + printk("vvv Ignore \"not allocated\" warnings\n"); + /* IDA is empty; all of these will fail */ + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a single value entry */ + IDA_BUG_ON(ida, ida_alloc_min(ida, 3, GFP_KERNEL) != 3); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a single bitmap */ + IDA_BUG_ON(ida, ida_alloc_min(ida, 1023, GFP_KERNEL) != 1023); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + + /* IDA contains a tree */ + IDA_BUG_ON(ida, ida_alloc_min(ida, (1 << 20) - 1, GFP_KERNEL) != (1 << 20) - 1); + ida_free(ida, 0); + for (i = 0; i < 31; i++) + ida_free(ida, 1 << i); + printk("^^^ \"not allocated\" warnings over\n"); + + ida_free(ida, 3); + ida_free(ida, 1023); + ida_free(ida, (1 << 20) - 1); + + IDA_BUG_ON(ida, !ida_is_empty(ida)); +} + static DEFINE_IDA(ida); static int ida_checks(void) @@ -162,6 +201,7 @@ static int ida_checks(void) ida_check_leaf(&ida, 1024 * 64); ida_check_max(&ida); ida_check_conv(&ida); + ida_check_bad_free(&ida); printk("IDA: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run != tests_passed) ? 0 : -EINVAL; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 24f37bab8bc1..fa1c19701855 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2092,15 +2092,20 @@ char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { - struct fwnode_handle *__fwnode = - fwnode_get_nth_parent(fwnode, depth); + /* + * Only get a reference for other nodes (i.e. parent nodes). + * fwnode refcount may be 0 here. + */ + struct fwnode_handle *__fwnode = depth ? + fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); - fwnode_handle_put(__fwnode); + if (depth) + fwnode_handle_put(__fwnode); } return buf; diff --git a/mm/damon/core.c b/mm/damon/core.c index 36d098d06c55..5db9bec8ae67 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -383,6 +383,8 @@ struct damon_ctx *damon_new_ctx(void) if (!ctx) return NULL; + init_completion(&ctx->kdamond_started); + ctx->attrs.sample_interval = 5 * 1000; ctx->attrs.aggr_interval = 100 * 1000; ctx->attrs.ops_update_interval = 60 * 1000 * 1000; @@ -519,11 +521,14 @@ static int __damon_start(struct damon_ctx *ctx) mutex_lock(&ctx->kdamond_lock); if (!ctx->kdamond) { err = 0; + reinit_completion(&ctx->kdamond_started); ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", nr_running_ctxs); if (IS_ERR(ctx->kdamond)) { err = PTR_ERR(ctx->kdamond); ctx->kdamond = NULL; + } else { + wait_for_completion(&ctx->kdamond_started); } } mutex_unlock(&ctx->kdamond_lock); @@ -1147,6 +1152,8 @@ static int kdamond_fn(void *data) pr_debug("kdamond (%d) starts\n", current->pid); + complete(&ctx->kdamond_started); + if (ctx->ops.init) ctx->ops.init(ctx); if (ctx->callback.before_start && ctx->callback.before_start(ctx)) diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 63bdad20dbaf..98a678129b06 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -185,9 +185,21 @@ static struct damos *damon_lru_sort_new_cold_scheme(unsigned int cold_thres) return damon_lru_sort_new_scheme(&pattern, DAMOS_LRU_DEPRIO); } +static void damon_lru_sort_copy_quota_status(struct damos_quota *dst, + struct damos_quota *src) +{ + dst->total_charged_sz = src->total_charged_sz; + dst->total_charged_ns = src->total_charged_ns; + dst->charged_sz = src->charged_sz; + dst->charged_from = src->charged_from; + dst->charge_target_from = src->charge_target_from; + dst->charge_addr_from = src->charge_addr_from; +} + static int damon_lru_sort_apply_parameters(void) { - struct damos *scheme; + struct damos *scheme, *hot_scheme, *cold_scheme; + struct damos *old_hot_scheme = NULL, *old_cold_scheme = NULL; unsigned int hot_thres, cold_thres; int err = 0; @@ -195,18 +207,35 @@ static int damon_lru_sort_apply_parameters(void) if (err) return err; + damon_for_each_scheme(scheme, ctx) { + if (!old_hot_scheme) { + old_hot_scheme = scheme; + continue; + } + old_cold_scheme = scheme; + } + hot_thres = damon_max_nr_accesses(&damon_lru_sort_mon_attrs) * hot_thres_access_freq / 1000; - scheme = damon_lru_sort_new_hot_scheme(hot_thres); - if (!scheme) + hot_scheme = damon_lru_sort_new_hot_scheme(hot_thres); + if (!hot_scheme) return -ENOMEM; - damon_set_schemes(ctx, &scheme, 1); + if (old_hot_scheme) + damon_lru_sort_copy_quota_status(&hot_scheme->quota, + &old_hot_scheme->quota); cold_thres = cold_min_age / damon_lru_sort_mon_attrs.aggr_interval; - scheme = damon_lru_sort_new_cold_scheme(cold_thres); - if (!scheme) + cold_scheme = damon_lru_sort_new_cold_scheme(cold_thres); + if (!cold_scheme) { + damon_destroy_scheme(hot_scheme); return -ENOMEM; - damon_add_scheme(ctx, scheme); + } + if (old_cold_scheme) + damon_lru_sort_copy_quota_status(&cold_scheme->quota, + &old_cold_scheme->quota); + + damon_set_schemes(ctx, &hot_scheme, 1); + damon_add_scheme(ctx, cold_scheme); return damon_set_region_biggest_system_ram_default(target, &monitor_region_start, diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 162c9b1ca00f..cc337e94acfd 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -141,9 +141,20 @@ static struct damos *damon_reclaim_new_scheme(void) &damon_reclaim_wmarks); } +static void damon_reclaim_copy_quota_status(struct damos_quota *dst, + struct damos_quota *src) +{ + dst->total_charged_sz = src->total_charged_sz; + dst->total_charged_ns = src->total_charged_ns; + dst->charged_sz = src->charged_sz; + dst->charged_from = src->charged_from; + dst->charge_target_from = src->charge_target_from; + dst->charge_addr_from = src->charge_addr_from; +} + static int damon_reclaim_apply_parameters(void) { - struct damos *scheme; + struct damos *scheme, *old_scheme; int err = 0; err = damon_set_attrs(ctx, &damon_reclaim_mon_attrs); @@ -154,6 +165,11 @@ static int damon_reclaim_apply_parameters(void) scheme = damon_reclaim_new_scheme(); if (!scheme) return -ENOMEM; + if (!list_empty(&ctx->schemes)) { + damon_for_each_scheme(old_scheme, ctx) + damon_reclaim_copy_quota_status(&scheme->quota, + &old_scheme->quota); + } damon_set_schemes(ctx, &scheme, 1); return damon_set_region_biggest_system_ram_default(target, diff --git a/mm/filemap.c b/mm/filemap.c index d633ab8cd56f..2809b1174f04 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2745,6 +2745,15 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* + * Pairs with a barrier in + * block_write_end()->mark_buffer_dirty() or other page + * dirtying routines like iomap_write_end() to ensure + * changes to page contents are visible before we see + * increased inode size. + */ + smp_rmb(); + + /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ @@ -3996,6 +4005,8 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp) struct address_space * const mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); + if (!folio_needs_release(folio)) + return true; if (folio_test_writeback(folio)) return false; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2753fb54cdf3..59577946735b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2694,8 +2694,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) gfp = current_gfp_context(mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK); - if (folio_test_private(folio) && - !filemap_release_folio(folio, gfp)) { + if (!filemap_release_folio(folio, gfp)) { ret = -EBUSY; goto out; } diff --git a/mm/internal.h b/mm/internal.h index 6b7ef495b56d..d01130efce5f 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -163,6 +163,17 @@ static inline void set_page_refcounted(struct page *page) set_page_count(page, 1); } +/* + * Return true if a folio needs ->release_folio() calling upon it. + */ +static inline bool folio_needs_release(struct folio *folio) +{ + struct address_space *mapping = folio_mapping(folio); + + return folio_has_private(folio) || + (mapping && mapping_release_always(mapping)); +} + extern unsigned long highest_memmap_pfn; /* diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 66a37f177d23..5d9ae80df495 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -523,8 +523,9 @@ void kasan_report_async(void) } #endif /* CONFIG_KASAN_HW_TAGS */ +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) /* - * With CONFIG_KASAN, accesses to bogus pointers (outside the high + * With CONFIG_KASAN_INLINE, accesses to bogus pointers (outside the high * canonical half of the address space) cause out-of-bounds shadow memory reads * before the actual access. For addresses in the low canonical half of the * address space, as well as most non-canonical addresses, that out-of-bounds @@ -560,3 +561,4 @@ void kasan_non_canonical_hook(unsigned long addr) pr_alert("KASAN: %s in range [0x%016lx-0x%016lx]\n", bug_type, orig_addr, orig_addr + KASAN_GRANULE_SIZE - 1); } +#endif diff --git a/mm/khugepaged.c b/mm/khugepaged.c index ef72d3df4b65..65bd0b105266 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1818,6 +1818,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, xas_set(&xas, start); for (index = start; index < end; index++) { struct page *page = xas_next(&xas); + struct folio *folio; VM_BUG_ON(index != xas.xa_index); if (is_shmem) { @@ -1844,8 +1845,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, } if (xa_is_value(page) || !PageUptodate(page)) { - struct folio *folio; - xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_get_folio(mapping->host, index, @@ -1933,13 +1932,15 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, goto out_unlock; } - if (page_mapping(page) != mapping) { + folio = page_folio(page); + + if (folio_mapping(folio) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } - if (!is_shmem && (PageDirty(page) || - PageWriteback(page))) { + if (!is_shmem && (folio_test_dirty(folio) || + folio_test_writeback(folio))) { /* * khugepaged only works on read-only fd, so this * page is dirty because it hasn't been flushed @@ -1949,20 +1950,19 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, goto out_unlock; } - if (isolate_lru_page(page)) { + if (folio_isolate_lru(folio)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } - if (page_has_private(page) && - !try_to_release_page(page, GFP_KERNEL)) { + if (!filemap_release_folio(folio, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; - putback_lru_page(page); + folio_putback_lru(folio); goto out_unlock; } - if (page_mapped(page)) - try_to_unmap(page_folio(page), + if (folio_mapped(folio)) + try_to_unmap(folio, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); diff --git a/mm/memblock.c b/mm/memblock.c index 511d4783dcf1..516efec80851 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -175,8 +175,9 @@ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) /* * Address comparison utilities */ -static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, - phys_addr_t base2, phys_addr_t size2) +unsigned long __init_memblock +memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2, + phys_addr_t size2) { return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9da98e3e71cf..4570d3e315cf 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -7517,9 +7517,13 @@ bool mem_cgroup_swap_full(struct folio *folio) static int __init setup_swap_account(char *s) { - pr_warn_once("The swapaccount= commandline option is deprecated. " - "Please report your usecase to linux-mm@kvack.org if you " - "depend on this functionality.\n"); + bool res; + + if (!kstrtobool(s, &res) && !res) + pr_warn_once("The swapaccount=0 commandline option is deprecated " + "in favor of configuring swap control via cgroupfs. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); return 1; } __setup("swapaccount=", setup_swap_account); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 99de0328d1be..5b846ed5dcbe 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -827,16 +827,15 @@ static int truncate_error_page(struct page *p, unsigned long pfn, int ret = MF_FAILED; if (mapping->a_ops->error_remove_page) { + struct folio *folio = page_folio(p); int err = mapping->a_ops->error_remove_page(mapping, p); - if (err != 0) { + if (err != 0) pr_info("%#lx: Failed to punch page: %d\n", pfn, err); - } else if (page_has_private(p) && - !try_to_release_page(p, GFP_NOIO)) { + else if (!filemap_release_folio(folio, GFP_NOIO)) pr_info("%#lx: failed to release buffers\n", pfn); - } else { + else ret = MF_RECOVERED; - } } else { /* * If the file system doesn't support it just invalidate @@ -1421,7 +1420,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * This check implies we don't kill processes if their pages * are in the swap cache early. Those are always late kills. */ - if (!page_mapped(hpage)) + if (!page_mapped(p)) return true; if (PageKsm(p)) { @@ -1477,10 +1476,10 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, try_to_unmap(folio, ttu); } - unmap_success = !page_mapped(hpage); + unmap_success = !page_mapped(p); if (!unmap_success) pr_err("%#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(hpage)); + pfn, page_mapcount(p)); /* * try_to_unmap() might put mlocked page in lru cache, so call @@ -1560,7 +1559,7 @@ static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn, * mapping being torn down is communicated in siginfo, see * kill_proc() */ - loff_t start = (index << PAGE_SHIFT) & ~(size - 1); + loff_t start = ((loff_t)index << PAGE_SHIFT) & ~(size - 1); unmap_mapping_range(mapping, start, size, 0); } diff --git a/mm/memory.c b/mm/memory.c index 0d1b3ee8fcd7..fb83cf56377a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3617,8 +3617,8 @@ EXPORT_SYMBOL_GPL(unmap_mapping_pages); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { - pgoff_t hba = holebegin >> PAGE_SHIFT; - pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; + pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { @@ -3761,6 +3761,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; + bool need_clear_cache = false; bool exclusive = false; swp_entry_t entry; pte_t pte; @@ -3822,6 +3823,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { + /* + * Prevent parallel swapin from proceeding with + * the cache flag. Otherwise, another thread may + * finish swapin first, free the entry, and swapout + * reusing the same entry. It's undetectable as + * pte_same() returns true due to entry reuse. + */ + if (swapcache_prepare(entry)) { + /* Relax a bit to prevent rapid repeated page faults */ + schedule_timeout_uninterruptible(1); + goto out; + } + need_clear_cache = true; + /* skip swapcache */ folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false); @@ -4073,6 +4088,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: + /* Clear the swap cache pin for direct swapin after PTL unlock */ + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; @@ -4086,6 +4104,8 @@ out_release: folio_unlock(swapcache); folio_put(swapcache); } + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index bd2570b4f9b7..3b9d3a4b4386 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1069,6 +1069,9 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1089,7 +1092,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); /* associate pfn range with the zone */ move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE); @@ -1148,7 +1150,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, writeback_set_ratelimit(); memory_notify(MEM_ONLINE, &arg); - mem_hotplug_done(); return 0; failed_addition: @@ -1157,7 +1158,6 @@ failed_addition: (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); remove_pfn_range_from_zone(zone, pfn, nr_pages); - mem_hotplug_done(); return ret; } @@ -1382,7 +1382,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) ret = create_memory_block_devices(start, size, mhp_altmap.alloc, group); if (ret) { - arch_remove_memory(start, size, NULL); + arch_remove_memory(start, size, params.altmap); goto error; } @@ -1787,6 +1787,9 @@ static int count_system_ram_pages_cb(unsigned long start_pfn, return 0; } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1809,8 +1812,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); - /* * Don't allow to offline memory blocks that contain holes. * Consequently, memory blocks with holes can never get onlined @@ -1946,7 +1947,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, memory_notify(MEM_OFFLINE, &arg); remove_pfn_range_from_zone(zone, start_pfn, nr_pages); - mem_hotplug_done(); return 0; failed_removal_isolated: @@ -1961,7 +1961,6 @@ failed_removal: (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1, reason); - mem_hotplug_done(); return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index 9372a826e6d0..c93dd6a31c31 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -388,6 +388,7 @@ int folio_migrate_mapping(struct address_space *mapping, int dirty; int expected_count = folio_expected_refs(mapping, folio) + extra_count; long nr = folio_nr_pages(folio); + long entries, i; if (!mapping) { /* Anonymous page without mapping */ @@ -425,8 +426,10 @@ int folio_migrate_mapping(struct address_space *mapping, folio_set_swapcache(newfolio); newfolio->private = folio_get_private(folio); } + entries = nr; } else { VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); + entries = 1; } /* Move dirty while page refs frozen and newpage not yet exposed */ @@ -436,7 +439,11 @@ int folio_migrate_mapping(struct address_space *mapping, folio_set_dirty(newfolio); } - xas_store(&xas, newfolio); + /* Swap cache still stores N entries instead of a high-order entry */ + for (i = 0; i < entries; i++) { + xas_store(&xas, newfolio); + xas_next(&xas); + } /* * Drop cache reference from old page by unfreezing @@ -907,8 +914,7 @@ static int fallback_migrate_folio(struct address_space *mapping, * Buffers may be managed in a filesystem specific way. * We must have no buffers or drop them. */ - if (folio_test_private(src) && - !filemap_release_folio(src, GFP_KERNEL)) + if (!filemap_release_folio(src, GFP_KERNEL)) return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY; return migrate_folio(mapping, dst, src, mode); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7e9d8d857ecc..d3e9d12860b9 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1526,7 +1526,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? - div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; + div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need @@ -3078,7 +3078,7 @@ EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); */ void folio_wait_stable(struct folio *folio) { - if (folio_inode(folio)->i_sb->s_iflags & SB_I_STABLE_WRITES) + if (mapping_stable_writes(folio_mapping(folio))) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4583f8a42d91..c783806eefc9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4921,14 +4921,9 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, else (*no_progress_loops)++; - /* - * Make sure we converge to OOM if we cannot make any progress - * several times in the row. - */ - if (*no_progress_loops > MAX_RECLAIM_RETRIES) { - /* Before OOM, exhaust highatomic_reserve */ - return unreserve_highatomic_pageblock(ac, true); - } + if (*no_progress_loops > MAX_RECLAIM_RETRIES) + goto out; + /* * Keep reclaiming pages while there is a chance this will lead @@ -4971,6 +4966,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, schedule_timeout_uninterruptible(1); else cond_resched(); +out: + /* Before OOM, exhaust highatomic_reserve */ + if (!ret) + return unreserve_highatomic_pageblock(ac, true); + return ret; } diff --git a/mm/sparse.c b/mm/sparse.c index e5a8a3a0edd7..05d1e7b6c6db 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -793,6 +793,13 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages, unsigned long section_nr = pfn_to_section_nr(pfn); /* + * Mark the section invalid so that valid_section() + * return false. This prevents code from dereferencing + * ms->usage array. + */ + ms->section_mem_map &= ~SECTION_HAS_MEM_MAP; + + /* * When removing an early section, the usage map is kept (as the * usage maps of other sections fall into the same page). It * will be re-used when re-adding the section - which is then no @@ -800,16 +807,10 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages, * was allocated during boot. */ if (!PageReserved(virt_to_page(ms->usage))) { - kfree(ms->usage); - ms->usage = NULL; + kfree_rcu(ms->usage, rcu); + WRITE_ONCE(ms->usage, NULL); } memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); - /* - * Mark the section invalid so that valid_section() - * return false. This prevents code from dereferencing - * ms->usage array. - */ - ms->section_mem_map &= ~SECTION_HAS_MEM_MAP; } /* diff --git a/mm/swap.h b/mm/swap.h index cc08c459c619..5eff40ef7693 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -39,6 +39,7 @@ void __delete_from_swap_cache(struct folio *folio, void delete_from_swap_cache(struct folio *folio); void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry); struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index); @@ -98,6 +99,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc) return 0; } +static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ +} + static inline struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 71db6d8a1ea3..cca9fda9d036 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3373,6 +3373,19 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char usage; + + ci = lock_cluster_or_swap_info(si, offset); + usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); + unlock_cluster_or_swap_info(si, ci); + if (!usage) + free_swap_slot(entry); +} + struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); diff --git a/mm/truncate.c b/mm/truncate.c index c0be77e5c008..0d4dd233f518 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -19,7 +19,6 @@ #include <linux/highmem.h> #include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> -#include <linux/buffer_head.h> /* grr. try_to_release_page */ #include <linux/shmem_fs.h> #include <linux/rmap.h> #include "internal.h" @@ -276,7 +275,7 @@ static long mapping_evict_folio(struct address_space *mapping, if (folio_ref_count(folio) > folio_nr_pages(folio) + folio_has_private(folio) + 1) return 0; - if (folio_has_private(folio) && !filemap_release_folio(folio, 0)) + if (!filemap_release_folio(folio, 0)) return 0; return remove_mapping(mapping, folio); @@ -581,8 +580,7 @@ static int invalidate_complete_folio2(struct address_space *mapping, if (folio->mapping != mapping) return 0; - if (folio_has_private(folio) && - !filemap_release_folio(folio, GFP_KERNEL)) + if (!filemap_release_folio(folio, GFP_KERNEL)) return 0; spin_lock(&mapping->host->i_lock); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 650ab6cfd5f4..992a0a16846f 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -327,6 +327,7 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, enum mcopy_atomic_mode mode, bool wp_copy) { @@ -445,6 +446,15 @@ retry: goto out; } mmap_read_lock(dst_mm); + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + if (mmap_changing && atomic_read(mmap_changing)) { + err = -EAGAIN; + break; + } dst_vma = NULL; goto retry; @@ -480,6 +490,7 @@ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, enum mcopy_atomic_mode mode, bool wp_copy); #endif /* CONFIG_HUGETLB_PAGE */ @@ -601,8 +612,8 @@ retry: */ if (is_vm_hugetlb_page(dst_vma)) return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start, - src_start, len, mcopy_mode, - wp_copy); + src_start, len, mmap_changing, + mcopy_mode, wp_copy); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; diff --git a/mm/vmscan.c b/mm/vmscan.c index 3f090faa6377..9f3cfb7caa48 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1992,7 +1992,7 @@ retry: * (refcount == 1) it can be freed. Otherwise, leave * the folio on the LRU so it is swappable. */ - if (folio_has_private(folio)) { + if (folio_needs_release(folio)) { if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; if (!mapping && folio_ref_count(folio) == 1) { @@ -2618,9 +2618,9 @@ static void shrink_active_list(unsigned long nr_to_scan, } if (unlikely(buffer_heads_over_limit)) { - if (folio_test_private(folio) && folio_trylock(folio)) { - if (folio_test_private(folio)) - filemap_release_folio(folio, 0); + if (folio_needs_release(folio) && + folio_trylock(folio)) { + filemap_release_folio(folio, 0); folio_unlock(folio); } } diff --git a/mm/zswap.c b/mm/zswap.c index b3829ada4a41..b7cb126797f9 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1013,6 +1013,8 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) if (zswap_rb_search(&tree->rbroot, entry->offset) != entry) { spin_unlock(&tree->lock); delete_from_swap_cache(page_folio(page)); + unlock_page(page); + put_page(page); ret = -ENOMEM; goto fail; } diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 0beb44f2fe1f..f00158234505 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -407,6 +407,8 @@ int vlan_vids_add_by_dev(struct net_device *dev, return 0; list_for_each_entry(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; err = vlan_vid_add(dev, vid_info->proto, vid_info->vid); if (err) goto unwind; @@ -417,6 +419,8 @@ unwind: list_for_each_entry_continue_reverse(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; vlan_vid_del(dev, vid_info->proto, vid_info->vid); } @@ -436,8 +440,11 @@ void vlan_vids_del_by_dev(struct net_device *dev, if (!vlan_info) return; - list_for_each_entry(vid_info, &vlan_info->vid_list, list) + list_for_each_entry(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; vlan_vid_del(dev, vid_info->proto, vid_info->vid); + } } EXPORT_SYMBOL(vlan_vids_del_by_dev); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 214532173536..a3b68243fd4b 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -118,12 +118,16 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_VLAN_INGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) { + if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) + continue; m = nla_data(attr); vlan_dev_set_ingress_priority(dev, m->to, m->from); } } if (data[IFLA_VLAN_EGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) { + if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) + continue; m = nla_data(attr); err = vlan_dev_set_egress_priority(dev, m->from, m->to); if (err) diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 4e3a2a1ffcb3..0e6603b1ec90 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -394,6 +394,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, uint16_t *nwname = va_arg(ap, uint16_t *); char ***wnames = va_arg(ap, char ***); + *wnames = NULL; + errcode = p9pdu_readf(pdu, proto_version, "w", nwname); if (!errcode) { @@ -403,6 +405,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, GFP_NOFS); if (!*wnames) errcode = -ENOMEM; + else + (*wnames)[0] = NULL; } if (!errcode) { @@ -414,8 +418,10 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, proto_version, "s", &(*wnames)[i]); - if (errcode) + if (errcode) { + (*wnames)[i] = NULL; break; + } } } @@ -423,11 +429,14 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, if (*wnames) { int i; - for (i = 0; i < *nwname; i++) + for (i = 0; i < *nwname; i++) { + if (!(*wnames)[i]) + break; kfree((*wnames)[i]); + } + kfree(*wnames); + *wnames = NULL; } - kfree(*wnames); - *wnames = NULL; } } break; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 1c3c7ff5c3c6..f1b7510359e4 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -264,11 +264,14 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (flags & MSG_OOB) return -EOPNOTSUPP; + lock_sock(sk); + skb = skb_recv_datagram(sk, flags, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) - return 0; + err = 0; + release_sock(sk); return err; } @@ -294,6 +297,8 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); + release_sock(sk); + if (flags & MSG_TRUNC) copied = skblen; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 55e0ecd88543..12d36875358b 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -2314,12 +2314,10 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); - /* If we're already encrypted set the REAUTH_PEND flag, - * otherwise set the ENCRYPT_PEND. + /* Set the ENCRYPT_PEND to trigger encryption after + * authentication. */ - if (test_bit(HCI_CONN_ENCRYPT, &conn->flags)) - set_bit(HCI_CONN_REAUTH_PEND, &conn->flags); - else + if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); } diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 3f401ec5bb0c..6124b3425f35 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -1045,10 +1045,12 @@ static int min_key_size_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val > hdev->le_max_key_size || val < SMP_MIN_ENC_KEY_SIZE) + hci_dev_lock(hdev); + if (val > hdev->le_max_key_size || val < SMP_MIN_ENC_KEY_SIZE) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_min_key_size = val; hci_dev_unlock(hdev); @@ -1073,10 +1075,12 @@ static int max_key_size_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val > SMP_MAX_ENC_KEY_SIZE || val < hdev->le_min_key_size) + hci_dev_lock(hdev); + if (val > SMP_MAX_ENC_KEY_SIZE || val < hdev->le_min_key_size) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_max_key_size = val; hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index c86a45344fe2..56ecc5f97b91 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -515,6 +515,9 @@ static u8 hci_cc_read_class_of_dev(struct hci_dev *hdev, void *data, { struct hci_rp_read_class_of_dev *rp = data; + if (WARN_ON(!hdev)) + return HCI_ERROR_UNSPECIFIED; + bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) @@ -746,9 +749,23 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data, } else { conn->enc_key_size = rp->key_size; status = 0; + + if (conn->enc_key_size < hdev->min_enc_key_size) { + /* As slave role, the conn->state has been set to + * BT_CONNECTED and l2cap conn req might not be received + * yet, at this moment the l2cap layer almost does + * nothing with the non-zero status. + * So we also clear encrypt related bits, and then the + * handler of l2cap conn req will get the right secure + * state at a later time. + */ + status = HCI_ERROR_AUTH_FAILURE; + clear_bit(HCI_CONN_ENCRYPT, &conn->flags); + clear_bit(HCI_CONN_AES_CCM, &conn->flags); + } } - hci_encrypt_cfm(conn, 0); + hci_encrypt_cfm(conn, status); done: hci_dev_unlock(hdev); @@ -2298,7 +2315,8 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) return; } - set_bit(HCI_INQUIRY, &hdev->flags); + if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY)) + set_bit(HCI_INQUIRY, &hdev->flags); } static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) @@ -3493,14 +3511,8 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, void *data, if (!ev->status) { clear_bit(HCI_CONN_AUTH_FAILURE, &conn->flags); - - if (!hci_conn_ssp_enabled(conn) && - test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) { - bt_dev_info(hdev, "re-auth of legacy device is not possible."); - } else { - set_bit(HCI_CONN_AUTH, &conn->flags); - conn->sec_level = conn->pending_sec_level; - } + set_bit(HCI_CONN_AUTH, &conn->flags); + conn->sec_level = conn->pending_sec_level; } else { if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING) set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags); @@ -3509,7 +3521,6 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, void *data, } clear_bit(HCI_CONN_AUTH_PEND, &conn->flags); - clear_bit(HCI_CONN_REAUTH_PEND, &conn->flags); if (conn->state == BT_CONFIG) { if (!ev->status && hci_conn_ssp_enabled(conn)) { diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index d74fe13f3dce..45d19294aa77 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -3780,12 +3780,14 @@ static int hci_set_event_mask_sync(struct hci_dev *hdev) if (lmp_bredr_capable(hdev)) { events[4] |= 0x01; /* Flow Specification Complete */ - /* Don't set Disconnect Complete when suspended as that - * would wakeup the host when disconnecting due to - * suspend. + /* Don't set Disconnect Complete and mode change when + * suspended as that would wakeup the host when disconnecting + * due to suspend. */ - if (hdev->suspended) + if (hdev->suspended) { events[0] &= 0xef; + events[2] &= 0xf7; + } } else { /* Use a different default for LE-only devices */ memset(events, 0, sizeof(events)); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a7899857aee5..81f5974e5eb5 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6493,6 +6493,14 @@ drop: kfree_skb(skb); } +static inline void l2cap_sig_send_rej(struct l2cap_conn *conn, u16 ident) +{ + struct l2cap_cmd_rej_unk rej; + + rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); + l2cap_send_cmd(conn, ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); +} + static inline void l2cap_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) { @@ -6518,23 +6526,25 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, if (len > skb->len || !cmd->ident) { BT_DBG("corrupted command"); - break; + l2cap_sig_send_rej(conn, cmd->ident); + skb_pull(skb, len > skb->len ? skb->len : len); + continue; } err = l2cap_bredr_sig_cmd(conn, cmd, len, skb->data); if (err) { - struct l2cap_cmd_rej_unk rej; - BT_ERR("Wrong link type (%d)", err); - - rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); - l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ, - sizeof(rej), &rej); + l2cap_sig_send_rej(conn, cmd->ident); } skb_pull(skb, len); } + if (skb->len > 0) { + BT_DBG("corrupted command"); + l2cap_sig_send_rej(conn, 0); + } + drop: kfree_skb(skb); } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d2e8565d0b33..6d631a2e6016 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2883,7 +2883,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, for (i = 0; i < key_count; i++) { struct mgmt_link_key_info *key = &cp->keys[i]; - if (key->addr.type != BDADDR_BREDR || key->type > 0x08) + /* Considering SMP over BREDR/LE, there is no need to check addr_type */ + if (key->type > 0x08) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, MGMT_STATUS_INVALID_PARAMS); @@ -7129,6 +7130,7 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, for (i = 0; i < irk_count; i++) { struct mgmt_irk_info *irk = &cp->irks[i]; + u8 addr_type = le_addr_type(irk->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, @@ -7138,8 +7140,12 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, continue; } + /* When using SMP over BR/EDR, the addr type should be set to BREDR */ + if (irk->addr.type == BDADDR_BREDR) + addr_type = BDADDR_BREDR; + hci_add_irk(hdev, &irk->addr.bdaddr, - le_addr_type(irk->addr.type), irk->val, + addr_type, irk->val, BDADDR_ANY); } @@ -7220,6 +7226,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, for (i = 0; i < key_count; i++) { struct mgmt_ltk_info *key = &cp->keys[i]; u8 type, authenticated; + u8 addr_type = le_addr_type(key->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LTK, @@ -7254,8 +7261,12 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, continue; } + /* When using SMP over BR/EDR, the addr type should be set to BREDR */ + if (key->addr.type == BDADDR_BREDR) + addr_type = BDADDR_BREDR; + hci_add_ltk(hdev, &key->addr.bdaddr, - le_addr_type(key->addr.type), type, authenticated, + addr_type, type, authenticated, key->val, key->enc_size, key->ediv, key->rand); } @@ -9523,7 +9534,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = BDADDR_BREDR; + ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); ev.key.type = key->type; memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE); ev.key.pin_len = key->pin_len; @@ -9574,7 +9585,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); ev.key.type = mgmt_ltk_type(key); ev.key.enc_size = key->enc_size; ev.key.ediv = key->ediv; @@ -9603,7 +9614,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent) bacpy(&ev.rpa, &irk->rpa); bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr); - ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type); + ev.irk.addr.type = link_to_bdaddr(irk->link_type, irk->addr_type); memcpy(ev.irk.val, irk->val, sizeof(irk->val)); mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL); @@ -9632,7 +9643,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr); - ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(csrk->link_type, csrk->bdaddr_type); ev.key.type = csrk->type; memcpy(ev.key.val, csrk->val, sizeof(csrk->val)); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 70663229b3cc..ecb005bce65a 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1058,6 +1058,7 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->remote_irk) { + smp->remote_irk->link_type = hcon->type; mgmt_new_irk(hdev, smp->remote_irk, persistent); /* Now that user space can be considered to know the @@ -1072,24 +1073,28 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->csrk) { + smp->csrk->link_type = hcon->type; smp->csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->csrk, persistent); } if (smp->responder_csrk) { + smp->responder_csrk->link_type = hcon->type; smp->responder_csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->responder_csrk, persistent); } if (smp->ltk) { + smp->ltk->link_type = hcon->type; smp->ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->ltk, persistent); } if (smp->responder_ltk) { + smp->responder_ltk->link_type = hcon->type; smp->responder_ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->responder_ltk, persistent); @@ -1109,6 +1114,8 @@ static void smp_notify_keys(struct l2cap_conn *conn) key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst, smp->link_key, type, 0, &persistent); if (key) { + key->link_type = hcon->type; + key->bdaddr_type = hcon->dst_type; mgmt_new_link_key(hdev, key, persistent); /* Don't keep debug keys around if the relevant diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c index 5c4c369f8536..2faab44652e7 100644 --- a/net/bridge/br_cfm_netlink.c +++ b/net/bridge/br_cfm_netlink.c @@ -362,7 +362,7 @@ static int br_cc_ccm_tx_parse(struct net_bridge *br, struct nlattr *attr, memset(&tx_info, 0, sizeof(tx_info)); - instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]); + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE]); nla_memcpy(&tx_info.dmac.addr, tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC], sizeof(tx_info.dmac.addr)); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index db4f2641d1cd..9765f9f9bf7f 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1607,6 +1607,10 @@ static void br_ip6_multicast_querier_expired(struct timer_list *t) } #endif +static void br_multicast_query_delay_expired(struct timer_list *t) +{ +} + static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx, struct br_ip *ip, struct sk_buff *skb) @@ -3024,7 +3028,7 @@ br_multicast_update_query_timer(struct net_bridge_mcast *brmctx, unsigned long max_delay) { if (!timer_pending(&query->timer)) - query->delay_time = jiffies + max_delay; + mod_timer(&query->delay_timer, jiffies + max_delay); mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval); } @@ -3867,13 +3871,11 @@ void br_multicast_ctx_init(struct net_bridge *br, brmctx->multicast_querier_interval = 255 * HZ; brmctx->multicast_membership_interval = 260 * HZ; - brmctx->ip4_other_query.delay_time = 0; brmctx->ip4_querier.port_ifidx = 0; seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock); brmctx->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) brmctx->multicast_mld_version = 1; - brmctx->ip6_other_query.delay_time = 0; brmctx->ip6_querier.port_ifidx = 0; seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock); #endif @@ -3882,6 +3884,8 @@ void br_multicast_ctx_init(struct net_bridge *br, br_ip4_multicast_local_router_expired, 0); timer_setup(&brmctx->ip4_other_query.timer, br_ip4_multicast_querier_expired, 0); + timer_setup(&brmctx->ip4_other_query.delay_timer, + br_multicast_query_delay_expired, 0); timer_setup(&brmctx->ip4_own_query.timer, br_ip4_multicast_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) @@ -3889,6 +3893,8 @@ void br_multicast_ctx_init(struct net_bridge *br, br_ip6_multicast_local_router_expired, 0); timer_setup(&brmctx->ip6_other_query.timer, br_ip6_multicast_querier_expired, 0); + timer_setup(&brmctx->ip6_other_query.delay_timer, + br_multicast_query_delay_expired, 0); timer_setup(&brmctx->ip6_own_query.timer, br_ip6_multicast_query_expired, 0); #endif @@ -4023,10 +4029,12 @@ static void __br_multicast_stop(struct net_bridge_mcast *brmctx) { del_timer_sync(&brmctx->ip4_mc_router_timer); del_timer_sync(&brmctx->ip4_other_query.timer); + del_timer_sync(&brmctx->ip4_other_query.delay_timer); del_timer_sync(&brmctx->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) del_timer_sync(&brmctx->ip6_mc_router_timer); del_timer_sync(&brmctx->ip6_other_query.timer); + del_timer_sync(&brmctx->ip6_other_query.delay_timer); del_timer_sync(&brmctx->ip6_own_query.timer); #endif } @@ -4469,13 +4477,15 @@ int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val) max_delay = brmctx->multicast_query_response_interval; if (!timer_pending(&brmctx->ip4_other_query.timer)) - brmctx->ip4_other_query.delay_time = jiffies + max_delay; + mod_timer(&brmctx->ip4_other_query.delay_timer, + jiffies + max_delay); br_multicast_start_querier(brmctx, &brmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) if (!timer_pending(&brmctx->ip6_other_query.timer)) - brmctx->ip6_other_query.delay_time = jiffies + max_delay; + mod_timer(&brmctx->ip6_other_query.delay_timer, + jiffies + max_delay); br_multicast_start_querier(brmctx, &brmctx->ip6_own_query); #endif diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 01d690d9fe5f..202ad43e35d6 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -279,8 +279,17 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ if ((READ_ONCE(neigh->nud_state) & NUD_CONNECTED) && READ_ONCE(neigh->hh.hh_len)) { + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + neigh_release(neigh); + goto free_skb; + } + neigh_hh_bridge(&neigh->hh, skb); - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; + ret = br_handle_frame_finish(net, sk, skb); } else { /* the neighbour function below overwrites the complete @@ -352,12 +361,18 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb, */ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb->dev; + struct net_device *dev = skb->dev, *br_indev; struct iphdr *iph = ip_hdr(skb); struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; int err; + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + kfree_skb(skb); + return 0; + } + nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { @@ -397,7 +412,7 @@ free_skb: } else { if (skb_dst(skb)->dev == dev) { bridged_dnat: - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, @@ -410,7 +425,7 @@ bridged_dnat: skb->pkt_type = PACKET_HOST; } } else { - rt = bridge_parent_rtable(nf_bridge->physindev); + rt = bridge_parent_rtable(br_indev); if (!rt) { kfree_skb(skb); return 0; @@ -419,7 +434,7 @@ bridged_dnat: skb_dst_set_noref(skb, &rt->dst); } - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, @@ -456,7 +471,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net) } nf_bridge->in_prerouting = 1; - nf_bridge->physindev = skb->dev; + nf_bridge->physinif = skb->dev->ifindex; skb->dev = brnf_get_logical_dev(skb, skb->dev, net); if (skb->protocol == htons(ETH_P_8021Q)) @@ -553,7 +568,11 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff if (skb->protocol == htons(ETH_P_IPV6)) nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; - in = nf_bridge->physindev; + in = nf_bridge_get_physindev(skb, net); + if (!in) { + kfree_skb(skb); + return 0; + } if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; @@ -897,6 +916,13 @@ static unsigned int ip_sabotage_in(void *priv, static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(skb, dev_net(skb->dev)); + if (!br_indev) { + kfree_skb(skb); + return; + } skb_pull(skb, ETH_HLEN); nf_bridge->bridged_dnat = 0; @@ -906,7 +932,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN), nf_bridge->neigh_header, ETH_HLEN - ETH_ALEN); - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge->physoutdev = NULL; br_handle_frame_finish(dev_net(skb->dev), NULL, skb); diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 6b07f30675bb..cd24ab9bb136 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -161,9 +161,15 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; - struct net_device *dev = skb->dev; + struct net_device *dev = skb->dev, *br_indev; const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + kfree_skb(skb); + return 0; + } + nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { @@ -181,7 +187,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc } if (skb_dst(skb)->dev == dev) { - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, @@ -192,7 +198,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); skb->pkt_type = PACKET_HOST; } else { - rt = bridge_parent_rtable(nf_bridge->physindev); + rt = bridge_parent_rtable(br_indev); if (!rt) { kfree_skb(skb); return 0; @@ -201,7 +207,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc skb_dst_set_noref(skb, &rt->dst); } - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 06e5f6faa431..51d010f64e06 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -77,7 +77,7 @@ struct bridge_mcast_own_query { /* other querier */ struct bridge_mcast_other_query { struct timer_list timer; - unsigned long delay_time; + struct timer_list delay_timer; }; /* selected querier */ @@ -1083,7 +1083,7 @@ __br_multicast_querier_exists(struct net_bridge_mcast *brmctx, own_querier_enabled = false; } - return time_is_before_jiffies(querier->delay_time) && + return !timer_pending(&querier->delay_timer) && (own_querier_enabled || timer_pending(&querier->timer)); } diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 4b3982c368b3..b61ef2dff7a4 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -593,21 +593,40 @@ br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, } static int br_switchdev_mdb_queue_one(struct list_head *mdb_list, + struct net_device *dev, + unsigned long action, enum switchdev_obj_id id, const struct net_bridge_mdb_entry *mp, struct net_device *orig_dev) { - struct switchdev_obj_port_mdb *mdb; + struct switchdev_obj_port_mdb mdb = { + .obj = { + .id = id, + .orig_dev = orig_dev, + }, + }; + struct switchdev_obj_port_mdb *pmdb; - mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC); - if (!mdb) - return -ENOMEM; + br_switchdev_mdb_populate(&mdb, mp); + + if (action == SWITCHDEV_PORT_OBJ_ADD && + switchdev_port_obj_act_is_deferred(dev, action, &mdb.obj)) { + /* This event is already in the deferred queue of + * events, so this replay must be elided, lest the + * driver receives duplicate events for it. This can + * only happen when replaying additions, since + * modifications are always immediately visible in + * br->mdb_list, whereas actual event delivery may be + * delayed. + */ + return 0; + } - mdb->obj.id = id; - mdb->obj.orig_dev = orig_dev; - br_switchdev_mdb_populate(mdb, mp); - list_add_tail(&mdb->obj.list, mdb_list); + pmdb = kmemdup(&mdb, sizeof(mdb), GFP_ATOMIC); + if (!pmdb) + return -ENOMEM; + list_add_tail(&pmdb->obj.list, mdb_list); return 0; } @@ -675,51 +694,50 @@ br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev, if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) return 0; - /* We cannot walk over br->mdb_list protected just by the rtnl_mutex, - * because the write-side protection is br->multicast_lock. But we - * need to emulate the [ blocking ] calling context of a regular - * switchdev event, so since both br->multicast_lock and RCU read side - * critical sections are atomic, we have no choice but to pick the RCU - * read side lock, queue up all our events, leave the critical section - * and notify switchdev from blocking context. + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + + /* br_switchdev_mdb_queue_one() will take care to not queue a + * replay of an event that is already pending in the switchdev + * deferred queue. In order to safely determine that, there + * must be no new deferred MDB notifications enqueued for the + * duration of the MDB scan. Therefore, grab the write-side + * lock to avoid racing with any concurrent IGMP/MLD snooping. */ - rcu_read_lock(); + spin_lock_bh(&br->multicast_lock); - hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { + hlist_for_each_entry(mp, &br->mdb_list, mdb_node) { struct net_bridge_port_group __rcu * const *pp; const struct net_bridge_port_group *p; if (mp->host_joined) { - err = br_switchdev_mdb_queue_one(&mdb_list, + err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_HOST_MDB, mp, br_dev); if (err) { - rcu_read_unlock(); + spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } - for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->key.port->dev != dev) continue; - err = br_switchdev_mdb_queue_one(&mdb_list, + err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_PORT_MDB, mp, dev); if (err) { - rcu_read_unlock(); + spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } } - rcu_read_unlock(); - - if (adding) - action = SWITCHDEV_PORT_OBJ_ADD; - else - action = SWITCHDEV_PORT_OBJ_DEL; + spin_unlock_bh(&br->multicast_lock); list_for_each_entry(obj, &mdb_list, list) { err = br_switchdev_mdb_replay_one(nb, dev, @@ -780,6 +798,16 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL); + + /* Make sure that the device leaving this bridge has seen all + * relevant events before it is disassociated. In the normal + * case, when the device is directly attached to the bridge, + * this is covered by del_nbp(). If the association was indirect + * however, e.g. via a team or bond, and the device is leaving + * that intermediate device, then the bridge port remains in + * place. + */ + switchdev_deferred_process(); } /* Let the bridge know that this port is offloaded, so that it can assign a diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 16af1a7f80f6..31a93cae5111 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -86,7 +86,7 @@ struct j1939_priv { unsigned int tp_max_packet_size; /* lock for j1939_socks list */ - spinlock_t j1939_socks_lock; + rwlock_t j1939_socks_lock; struct list_head j1939_socks; struct kref rx_kref; @@ -301,6 +301,7 @@ struct j1939_sock { int ifindex; struct j1939_addr addr; + spinlock_t filters_lock; struct j1939_filter *filters; int nfilters; pgn_t pgn_rx_filter; diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index ecff1c947d68..a6fb89fa6278 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) return ERR_PTR(-ENOMEM); j1939_tp_init(priv); - spin_lock_init(&priv->j1939_socks_lock); + rwlock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); mutex_lock(&j1939_netdev_lock); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 9c828067b448..58909b36561a 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk) jsk->state |= J1939_SOCK_BOUND; j1939_priv_get(priv); - spin_lock_bh(&priv->j1939_socks_lock); + write_lock_bh(&priv->j1939_socks_lock); list_add_tail(&jsk->list, &priv->j1939_socks); - spin_unlock_bh(&priv->j1939_socks_lock); + write_unlock_bh(&priv->j1939_socks_lock); } static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) { - spin_lock_bh(&priv->j1939_socks_lock); + write_lock_bh(&priv->j1939_socks_lock); list_del_init(&jsk->list); - spin_unlock_bh(&priv->j1939_socks_lock); + write_unlock_bh(&priv->j1939_socks_lock); j1939_priv_put(priv); jsk->state &= ~J1939_SOCK_BOUND; @@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk, static bool j1939_sk_match_filter(struct j1939_sock *jsk, const struct j1939_sk_buff_cb *skcb) { - const struct j1939_filter *f = jsk->filters; - int nfilter = jsk->nfilters; + const struct j1939_filter *f; + int nfilter; + + spin_lock_bh(&jsk->filters_lock); + + f = jsk->filters; + nfilter = jsk->nfilters; if (!nfilter) /* receive all when no filters are assigned */ - return true; + goto filter_match_found; for (; nfilter; ++f, --nfilter) { if ((skcb->addr.pgn & f->pgn_mask) != f->pgn) @@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk, continue; if ((skcb->addr.src_name & f->name_mask) != f->name) continue; - return true; + goto filter_match_found; } + + spin_unlock_bh(&jsk->filters_lock); return false; + +filter_match_found: + spin_unlock_bh(&jsk->filters_lock); + return true; } static bool j1939_sk_recv_match_one(struct j1939_sock *jsk, @@ -329,13 +340,13 @@ bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb) struct j1939_sock *jsk; bool match = false; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { match = j1939_sk_recv_match_one(jsk, skcb); if (match) break; } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); return match; } @@ -344,11 +355,11 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sock *jsk; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { j1939_sk_recv_one(jsk, skb); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); } static void j1939_sk_sock_destruct(struct sock *sk) @@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + spin_lock_init(&jsk->filters_lock); /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ sock_set_flag(sk, SOCK_RCU_FREE); @@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, } lock_sock(&jsk->sk); + spin_lock_bh(&jsk->filters_lock); ofilters = jsk->filters; jsk->filters = filters; jsk->nfilters = count; + spin_unlock_bh(&jsk->filters_lock); release_sock(&jsk->sk); kfree(ofilters); return 0; @@ -974,6 +988,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk, struct sock_exterr_skb *serr; struct sk_buff *skb; char *state = "UNK"; + u32 tsflags; int err; jsk = j1939_sk(sk); @@ -981,13 +996,14 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk, if (!(jsk->state & J1939_SOCK_ERRQUEUE)) return; + tsflags = READ_ONCE(sk->sk_tsflags); switch (type) { case J1939_ERRQUEUE_TX_ACK: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) + if (!(tsflags & SOF_TIMESTAMPING_TX_ACK)) return; break; case J1939_ERRQUEUE_TX_SCHED: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) + if (!(tsflags & SOF_TIMESTAMPING_TX_SCHED)) return; break; case J1939_ERRQUEUE_TX_ABORT: @@ -997,7 +1013,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk, case J1939_ERRQUEUE_RX_DPO: fallthrough; case J1939_ERRQUEUE_RX_ABORT: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE)) + if (!(tsflags & SOF_TIMESTAMPING_RX_SOFTWARE)) return; break; default: @@ -1054,7 +1070,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk, } serr->opt_stats = true; - if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + if (tsflags & SOF_TIMESTAMPING_OPT_ID) serr->ee.ee_data = session->tskey; netdev_dbg(session->priv->ndev, "%s: 0x%p tskey: %i, state: %s\n", @@ -1078,12 +1094,12 @@ void j1939_sk_errqueue(struct j1939_session *session, } /* spread RX notifications to all sockets subscribed to this session */ - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { if (j1939_sk_recv_match_one(jsk, &session->skcb)) __j1939_sk_errqueue(session, &jsk->sk, type); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); }; void j1939_sk_send_loop_abort(struct sock *sk, int err) @@ -1271,7 +1287,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) struct j1939_sock *jsk; int error_code = ENETDOWN; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { jsk->sk.sk_err = error_code; if (!sock_flag(&jsk->sk, SOCK_DEAD)) @@ -1279,7 +1295,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) j1939_sk_queue_drop_all(priv, jsk, error_code); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); } static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, diff --git a/net/can/raw.c b/net/can/raw.c index 8c104339d538..488320738e31 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -881,6 +881,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) skb->dev = dev; skb->priority = sk->sk_priority; + skb->mark = sk->sk_mark; skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); diff --git a/net/core/dev.c b/net/core/dev.c index 0d5aa820fd83..60619fe8af5f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3551,6 +3551,9 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; + if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size))) + return features & ~NETIF_F_GSO_MASK; + if (!skb_shinfo(skb)->gso_type) { skb_warn_bad_offload(skb); return features & ~NETIF_F_GSO_MASK; @@ -8858,7 +8861,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { - size_t size = sizeof(sa->sa_data); + size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; @@ -11320,6 +11323,7 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit_net(struct net *net) { + struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the @@ -11342,6 +11346,14 @@ static void __net_exit default_device_exit_net(struct net *net) snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); + + netdev_for_each_altname_safe(dev, name_node, tmp) + if (netdev_name_in_use(&init_net, name_node->name)) { + netdev_name_node_del(name_node); + synchronize_rcu(); + __netdev_name_node_alt_destroy(name_node); + } + err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", diff --git a/net/core/dev.h b/net/core/dev.h index 9ca91457c197..db9ff8cd8d46 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -63,6 +63,9 @@ int dev_change_name(struct net_device *dev, const char *newname); #define netdev_for_each_altname(dev, namenode) \ list_for_each_entry((namenode), &(dev)->name_node->list, list) +#define netdev_for_each_altname_safe(dev, namenode, next) \ + list_for_each_entry_safe((namenode), (next), &(dev)->name_node->list, \ + list) int netdev_name_node_alt_create(struct net_device *dev, const char *name); int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 7674bb9f3076..5cdbfbf9a7dc 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -342,7 +342,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, if (ifr->ifr_hwaddr.sa_family != dev->type) return -EINVAL; memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof(ifr->ifr_hwaddr.sa_data), + min(sizeof(ifr->ifr_hwaddr.sa_data_min), (size_t)dev->addr_len)); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return 0; diff --git a/net/core/dst.c b/net/core/dst.c index bc9c9be4e080..d178c564138e 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -82,12 +82,8 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, if (ops->gc && !(flags & DST_NOCOUNT) && - dst_entries_get_fast(ops) > ops->gc_thresh) { - if (ops->gc(ops)) { - pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n"); - return NULL; - } - } + dst_entries_get_fast(ops) > ops->gc_thresh) + ops->gc(ops); dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 41daa47d0393..c842f150c304 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -253,9 +253,11 @@ static int neigh_forced_gc(struct neigh_table *tbl) { int max_clean = atomic_read(&tbl->gc_entries) - READ_ONCE(tbl->gc_thresh2); + u64 tmax = ktime_get_ns() + NSEC_PER_MSEC; unsigned long tref = jiffies - 5 * HZ; struct neighbour *n, *tmp; int shrunk = 0; + int loop = 0; NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs); @@ -278,11 +280,16 @@ static int neigh_forced_gc(struct neigh_table *tbl) shrunk++; if (shrunk >= max_clean) break; + if (++loop == 16) { + if (ktime_get_ns() > tmax) + goto unlock; + loop = 0; + } } } WRITE_ONCE(tbl->last_flush, jiffies); - +unlock: write_unlock_bh(&tbl->lock); return shrunk; diff --git a/net/core/request_sock.c b/net/core/request_sock.c index f35c2e998406..63de5c635842 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -33,9 +33,6 @@ void reqsk_queue_alloc(struct request_sock_queue *queue) { - spin_lock_init(&queue->rskq_lock); - - spin_lock_init(&queue->fastopenq.lock); queue->fastopenq.rskq_rst_head = NULL; queue->fastopenq.rskq_rst_tail = NULL; queue->fastopenq.qlen = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 854b3fd66b1b..7cf1e42d7f93 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2797,13 +2797,6 @@ static int do_setlink(const struct sk_buff *skb, call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); } - if (tb[IFLA_MASTER]) { - err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack); - if (err) - goto errout; - status |= DO_SETLINK_MODIFIED; - } - if (ifm->ifi_flags || ifm->ifi_change) { err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm), extack); @@ -2811,6 +2804,13 @@ static int do_setlink(const struct sk_buff *skb, goto errout; } + if (tb[IFLA_MASTER]) { + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack); + if (err) + goto errout; + status |= DO_SETLINK_MODIFIED; + } + if (tb[IFLA_CARRIER]) { err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER])); if (err) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 73b1e0e53534..d4bd10f8723d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4213,8 +4213,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. + * Cap len to not accidentally hit GSO_BY_FRAGS. */ - partial_segs = len / mss; + partial_segs = min(len, GSO_BY_FRAGS - 1U) / mss; if (partial_segs > 1) mss *= partial_segs; else @@ -4913,7 +4914,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, serr->ee.ee_info = tstype; serr->opt_stats = opt_stats; serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0; - if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { + if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk_is_tcp(sk)) serr->ee.ee_data -= atomic_read(&sk->sk_tskey); @@ -4969,21 +4970,23 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, { struct sk_buff *skb; bool tsonly, opt_stats = false; + u32 tsflags; if (!sk) return; - if (!hwtstamps && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && + tsflags = READ_ONCE(sk->sk_tsflags); + if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS) return; - tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY; + tsonly = tsflags & SOF_TIMESTAMPING_OPT_TSONLY; if (!skb_may_tx_timestamp(sk, tsonly)) return; if (tsonly) { #ifdef CONFIG_INET - if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && + if ((tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk_is_tcp(sk)) { skb = tcp_get_timestamping_opt_stats(sk, orig_skb, ack_skb); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a5c1f67dc96e..39643f78cf78 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -825,6 +825,8 @@ static void sk_psock_destroy(struct work_struct *work) if (psock->sk_redir) sock_put(psock->sk_redir); + if (psock->sk_pair) + sock_put(psock->sk_pair); sock_put(psock->sk); kfree(psock); } @@ -1215,8 +1217,11 @@ static void sk_psock_verdict_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); - if (psock) - psock->saved_data_ready(sk); + if (psock) { + read_lock_bh(&sk->sk_callback_lock); + sk_psock_data_ready(sk, psock); + read_unlock_bh(&sk->sk_callback_lock); + } rcu_read_unlock(); } } diff --git a/net/core/sock.c b/net/core/sock.c index 4305e55dbfba..c8803b95ea0d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -107,6 +107,7 @@ #include <linux/interrupt.h> #include <linux/poll.h> #include <linux/tcp.h> +#include <linux/udp.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/user_namespace.h> @@ -890,7 +891,7 @@ static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) if (!match) return -EINVAL; - sk->sk_bind_phc = phc_index; + WRITE_ONCE(sk->sk_bind_phc, phc_index); return 0; } @@ -926,7 +927,7 @@ int sock_set_timestamping(struct sock *sk, int optname, return ret; } - sk->sk_tsflags = val; + WRITE_ONCE(sk->sk_tsflags, val); sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); if (val & SOF_TIMESTAMPING_RX_SOFTWARE) @@ -1704,9 +1705,16 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: lv = sizeof(v.timestamping); - v.timestamping.flags = sk->sk_tsflags; - v.timestamping.bind_phc = sk->sk_bind_phc; + /* For the later-added case SO_TIMESTAMPING_NEW: Be strict about only + * returning the flags when they were set through the same option. + * Don't change the beviour for the old case SO_TIMESTAMPING_OLD. + */ + if (optname == SO_TIMESTAMPING_OLD || sock_flag(sk, SOCK_TSTAMP_NEW)) { + v.timestamping.flags = READ_ONCE(sk->sk_tsflags); + v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc); + } break; case SO_RCVTIMEO_OLD: @@ -2764,6 +2772,7 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; @@ -4101,8 +4110,14 @@ bool sk_busy_loop_end(void *p, unsigned long start_time) { struct sock *sk = p; - return !skb_queue_empty_lockless(&sk->sk_receive_queue) || - sk_busy_loop_timeout(sk, start_time); + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) + return true; + + if (sk_is_udp(sk) && + !skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) + return true; + + return sk_busy_loop_timeout(sk, start_time); } EXPORT_SYMBOL(sk_busy_loop_end); #endif /* CONFIG_NET_RX_BUSY_POLL */ diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 38e01f82f2ef..91140bc0541f 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -538,6 +538,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); + if (sk_is_stream_unix(sk)) + return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true; } diff --git a/net/core/stream.c b/net/core/stream.c index 051aa71a8ad0..30e7deff4c55 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -79,7 +79,7 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending--; } while (!done); - return 0; + return done < 0 ? done : 0; } EXPORT_SYMBOL(sk_stream_wait_connect); diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 3aced951d5ab..26a9d8434c23 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -91,7 +91,6 @@ const struct cred *dns_resolver_cache; static int dns_resolver_preparse(struct key_preparsed_payload *prep) { - const struct dns_payload_header *bin; struct user_key_payload *upayload; unsigned long derrno; int ret; @@ -102,26 +101,34 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) return -EINVAL; if (data[0] == 0) { + const struct dns_server_list_v1_header *v1; + /* It may be a server list. */ - if (datalen <= sizeof(*bin)) + if (datalen < sizeof(*v1)) return -EINVAL; - bin = (const struct dns_payload_header *)data; - kenter("[%u,%u],%u", bin->content, bin->version, datalen); - if (bin->content != DNS_PAYLOAD_IS_SERVER_LIST) { + v1 = (const struct dns_server_list_v1_header *)data; + kenter("[%u,%u],%u", v1->hdr.content, v1->hdr.version, datalen); + if (v1->hdr.content != DNS_PAYLOAD_IS_SERVER_LIST) { pr_warn_ratelimited( "dns_resolver: Unsupported content type (%u)\n", - bin->content); + v1->hdr.content); return -EINVAL; } - if (bin->version != 1) { + if (v1->hdr.version != 1) { pr_warn_ratelimited( "dns_resolver: Unsupported server list version (%u)\n", - bin->version); + v1->hdr.version); return -EINVAL; } + if ((v1->status != DNS_LOOKUP_GOOD && + v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) { + if (prep->expiry == TIME64_MAX) + prep->expiry = ktime_get_real_seconds() + 1; + } + result_len = datalen; goto store_result; } @@ -314,7 +321,7 @@ static long dns_resolver_read(const struct key *key, struct key_type key_type_dns_resolver = { .name = "dns_resolver", - .flags = KEY_TYPE_NET_DOMAIN, + .flags = KEY_TYPE_NET_DOMAIN | KEY_TYPE_INSTANT_REAP, .preparse = dns_resolver_preparse, .free_preparse = dns_resolver_free_preparse, .instantiate = generic_key_instantiate, diff --git a/net/ethtool/features.c b/net/ethtool/features.c index 55d449a2d3fc..090e493f592e 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -234,17 +234,20 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) dev = req_info.dev; rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; ethnl_features_to_bitmap(old_active, dev->features); ethnl_features_to_bitmap(old_wanted, dev->wanted_features); ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT, tb[ETHTOOL_A_FEATURES_WANTED], netdev_features_strings, info->extack); if (ret < 0) - goto out_rtnl; + goto out_ops; if (ethnl_bitmap_to_features(req_mask) & ~NETIF_F_ETHTOOL_BITS) { GENL_SET_ERR_MSG(info, "attempt to change non-ethtool features"); ret = -EINVAL; - goto out_rtnl; + goto out_ops; } /* set req_wanted bits not in req_mask from old_wanted */ @@ -281,6 +284,8 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) if (mod) netdev_features_change(dev); +out_ops: + ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); ethnl_parse_header_dev_put(&req_info); diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 1a4c11356c96..fc4ccecf9495 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -509,7 +509,7 @@ lock_and_cont: cont: idx++; } - + ret = 0; } rtnl_unlock(); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 1965559e22c1..aecb5c8b378f 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -308,7 +308,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "HSR: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); return; } @@ -355,7 +355,7 @@ static void send_prp_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "PRP: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } diff --git a/net/ife/ife.c b/net/ife/ife.c index 13bbf8cb6a39..be05b690b9ef 100644 --- a/net/ife/ife.c +++ b/net/ife/ife.c @@ -82,6 +82,7 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen) if (unlikely(!pskb_may_pull(skb, total_pull))) return NULL; + ifehdr = (struct ifeheadr *)(skb->data + skb->dev->hard_header_len); skb_set_mac_header(skb, total_pull); __skb_pull(skb, total_pull); *metalen = ifehdrln - IFE_METAHDRLEN; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5d379df90c82..9408dc3bb42d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -324,6 +324,9 @@ lookup_protocol: if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; + if (INET_PROTOSW_ICSK & answer_flags) + inet_init_csk_locks(sk); + inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; @@ -838,6 +841,21 @@ int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } EXPORT_SYMBOL(inet_sendmsg); +void inet_splice_eof(struct socket *sock) +{ + const struct proto *prot; + struct sock *sk = sock->sk; + + if (unlikely(inet_send_prepare(sk))) + return; + + /* IPV6_ADDRFORM can change sk->sk_prot under us. */ + prot = READ_ONCE(sk->sk_prot); + if (prot->splice_eof) + prot->splice_eof(sock); +} +EXPORT_SYMBOL_GPL(inet_splice_eof); + ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { @@ -1057,6 +1075,7 @@ const struct proto_ops inet_stream_ops = { #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, @@ -1091,6 +1110,7 @@ const struct proto_ops inet_dgram_ops = { .read_skb = udp_read_skb, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT @@ -1122,6 +1142,7 @@ static const struct proto_ops inet_sockraw_ops = { .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, @@ -1616,14 +1637,17 @@ EXPORT_SYMBOL(inet_current_timestamp); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { - if (sk->sk_family == AF_INET) + unsigned int family = READ_ONCE(sk->sk_family); + + if (family == AF_INET) return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) + if (family == AF_INET6) return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len); #endif return -EINVAL; } +EXPORT_SYMBOL(inet_recv_error); int inet_gro_complete(struct sk_buff *skb, int nhoff) { diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 9456f5bb35e5..ccff96820a70 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1125,7 +1125,8 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) if (neigh) { if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) { read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); + memcpy(r->arp_ha.sa_data, neigh->ha, + min(dev->addr_len, (unsigned char)sizeof(r->arp_ha.sa_data_min))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); r->arp_ha.sa_family = dev->type; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 35d6e74be840..bb0d1252cad8 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1804,6 +1804,21 @@ done: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv4.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; @@ -1855,8 +1870,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; head = &tgt_net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^ - tgt_net->dev_base_seq; + cb->seq = inet_base_seq(tgt_net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -2257,8 +2271,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 80ce0112e24b..79fa19a36bbd 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -727,6 +727,10 @@ out: } if (req) reqsk_put(req); + + if (newsk) + inet_init_csk_locks(newsk); + return newsk; out_err: newsk = NULL; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index f2ed2aed08ab..56776e1b1de5 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1111,10 +1111,33 @@ ok: return 0; error: + if (sk_hashed(sk)) { + spinlock_t *lock = inet_ehash_lockp(hinfo, sk->sk_hash); + + sock_prot_inuse_add(net, sk->sk_prot, -1); + + spin_lock(lock); + sk_nulls_del_node_init_rcu(sk); + spin_unlock(lock); + + sk->sk_hash = 0; + inet_sk(sk)->inet_sport = 0; + inet_sk(sk)->inet_num = 0; + + if (tw) + inet_twsk_bind_unhash(tw, hinfo); + } + spin_unlock(&head2->lock); if (tb_created) inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); - spin_unlock_bh(&head->lock); + spin_unlock(&head->lock); + + if (tw) + inet_twsk_deschedule_put(tw); + + local_bh_enable(); + return -ENOMEM; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 493c679ea54f..a6d460aaee79 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -990,8 +990,8 @@ static int __ip_append_data(struct sock *sk, mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; - if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && - sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + if (cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1268,6 +1268,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, if (unlikely(!rt)) return -EFAULT; + cork->fragsize = ip_sk_use_pmtu(sk) ? + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; + /* * setup for corking. */ @@ -1284,12 +1290,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); - - if (!inetdev_valid_mtu(cork->fragsize)) - return -ENETUNREACH; - cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 63aa52becd88..a00ba2d51e1b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -509,7 +509,7 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk, * or without payload (SOF_TIMESTAMPING_OPT_TSONLY). */ info = PKTINFO_SKB_CB(skb); - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) || + if (!(READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_CMSG) || !info->ipi_ifindex) return false; @@ -1406,12 +1406,13 @@ e_inval: * ipv4_pktinfo_prepare - transfer some info from rtable to skb * @sk: socket * @skb: buffer + * @drop_dst: if true, drops skb dst * * To support IP_CMSG_PKTINFO option, we store rt_iif and specific * destination in skb->cb[] before dst drop. * This way, receiver doesn't make cache line misses to read rtable. */ -void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) +void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) || @@ -1440,7 +1441,8 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) pktinfo->ipi_ifindex = 0; pktinfo->ipi_spec_dst.s_addr = 0; } - skb_dst_drop(skb); + if (drop_dst) + skb_dst_drop(skb); } int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 586b1b3e35b8..80ccd6661aa3 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -332,7 +332,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) }; skb_reset_network_header(skb); - csum = csum_partial(icmp6h, len, 0); + csum = skb_checksum(skb, skb_transport_offset(skb), len, 0); icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len, IPPROTO_ICMPV6, csum); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index e04544ac4b45..d5421c38c2aa 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1025,6 +1025,10 @@ static int ipmr_cache_report(const struct mr_table *mrt, struct sk_buff *skb; int ret; + mroute_sk = rcu_dereference(mrt->mroute_sk); + if (!mroute_sk) + return -EINVAL; + if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) skb = skb_realloc_headroom(pkt, sizeof(struct iphdr)); else @@ -1069,7 +1073,8 @@ static int ipmr_cache_report(const struct mr_table *mrt, msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; msg->im_vif_hi = vifi >> 8; - skb_dst_set(skb, dst_clone(skb_dst(pkt))); + ipv4_pktinfo_prepare(mroute_sk, pkt, false); + memcpy(skb->cb, pkt->cb, sizeof(skb->cb)); /* Add our header */ igmp = skb_put(skb, sizeof(struct igmphdr)); igmp->type = assert; @@ -1079,12 +1084,6 @@ static int ipmr_cache_report(const struct mr_table *mrt, skb->transport_header = skb->network_header; } - mroute_sk = rcu_dereference(mrt->mroute_sk); - if (!mroute_sk) { - kfree_skb(skb); - return -EINVAL; - } - igmpmsg_netlink_event(mrt, skb); /* Deliver to mrouted */ diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index d640adcaf1b1..4073762996e2 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -239,7 +239,6 @@ static int nf_reject_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct net_device *br_indev __maybe_unused; struct sk_buff *nskb; struct iphdr *niph; const struct tcphdr *oth; @@ -288,9 +287,13 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ - br_indev = nf_bridge_get_physindev(oldskb); - if (br_indev) { + if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(oldskb, net); + if (!br_indev) + goto free_nskb; nskb->dev = br_indev; niph->tot_len = htons(nskb->len); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 639aa5abda9d..7c63b91edbf7 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -286,11 +286,13 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason; + /* Charge it to the socket. */ - ipv4_pktinfo_prepare(sk, skb); - if (sock_queue_rcv_skb(sk, skb) < 0) { - kfree_skb(skb); + ipv4_pktinfo_prepare(sk, skb, true); + if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { + kfree_skb_reason(skb, reason); return NET_RX_DROP; } @@ -301,7 +303,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) { if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 58409ea2da0a..86e7695d91ad 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -718,6 +718,7 @@ void tcp_push(struct sock *sk, int flags, int mss_now, if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); + smp_mb__after_atomic(); } /* It is possible TX completion already happened * before we set TSQ_THROTTLED. @@ -1492,6 +1493,22 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) } EXPORT_SYMBOL(tcp_sendmsg); +void tcp_splice_eof(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct tcp_sock *tp = tcp_sk(sk); + int mss_now, size_goal; + + if (!tcp_write_queue_tail(sk)) + return; + + lock_sock(sk); + mss_now = tcp_send_mss(sk, &size_goal, 0); + tcp_push(sk, 0, mss_now, tp->nonagle, size_goal); + release_sock(sk); +} +EXPORT_SYMBOL_GPL(tcp_splice_eof); + /* * Handle reading urgent data. BSD has very simple semantics for * this, no blocking and very strange errors 8) @@ -1917,7 +1934,17 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, static bool can_map_frag(const skb_frag_t *frag) { - return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag); + struct page *page; + + if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) + return false; + + page = skb_frag_page(frag); + + if (PageCompound(page) || page->mapping) + return false; + + return true; } static int find_next_mappable_frag(const skb_frag_t *frag, @@ -2359,14 +2386,14 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, } } - if (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) + if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE) has_timestamping = true; else tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { - if (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) + if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE) has_timestamping = true; else tss->ts[2] = (struct timespec64) {0}; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7ebbbe561e40..be2c807eed15 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3067,6 +3067,7 @@ struct proto tcp_prot = { .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, + .splice_eof = tcp_splice_eof, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 65abc92a81bd..87d759bab001 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -733,7 +733,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) iph->saddr, uh->source, skb->dev->ifindex, inet_sdif(skb), udptable, NULL); - if (!sk || udp_sk(sk)->encap_type) { + if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) { /* No socket for error: try tunnels before discarding */ if (static_branch_unlikely(&udp_encap_needed_key)) { sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb, @@ -823,7 +823,7 @@ void udp_flush_pending_frames(struct sock *sk) if (up->pending) { up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); ip_flush_pending_frames(sk); } } @@ -1010,7 +1010,7 @@ int udp_push_pending_frames(struct sock *sk) out: up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); return err; } EXPORT_SYMBOL(udp_push_pending_frames); @@ -1068,7 +1068,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) __be16 dport; u8 tos; int err, is_udplite = IS_UDPLITE(sk); - int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; + int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; struct ip_options_data opt_copy; @@ -1086,7 +1086,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; fl4 = &inet->cork.fl.u.ip4; - if (up->pending) { + if (READ_ONCE(up->pending)) { /* * There are pending frames. * The socket lock must be held while it's corked. @@ -1287,7 +1287,7 @@ back_from_confirm: fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = inet->inet_sport; - up->pending = AF_INET; + WRITE_ONCE(up->pending, AF_INET); do_append_data: up->len += ulen; @@ -1299,7 +1299,7 @@ do_append_data: else if (!corkreq) err = udp_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) - up->pending = 0; + WRITE_ONCE(up->pending, 0); release_sock(sk); out: @@ -1332,57 +1332,33 @@ do_confirm: } EXPORT_SYMBOL(udp_sendmsg); -int udp_sendpage(struct sock *sk, struct page *page, int offset, - size_t size, int flags) +void udp_splice_eof(struct socket *sock) { - struct inet_sock *inet = inet_sk(sk); + struct sock *sk = sock->sk; struct udp_sock *up = udp_sk(sk); - int ret; - - if (flags & MSG_SENDPAGE_NOTLAST) - flags |= MSG_MORE; - - if (!up->pending) { - struct msghdr msg = { .msg_flags = flags|MSG_MORE }; - /* Call udp_sendmsg to specify destination address which - * sendpage interface can't pass. - * This will succeed only when the socket is connected. - */ - ret = udp_sendmsg(sk, &msg, 0); - if (ret < 0) - return ret; - } + if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk)) + return; lock_sock(sk); + if (up->pending && !udp_test_bit(CORK, sk)) + udp_push_pending_frames(sk); + release_sock(sk); +} +EXPORT_SYMBOL_GPL(udp_splice_eof); - if (unlikely(!up->pending)) { - release_sock(sk); - - net_dbg_ratelimited("cork failed\n"); - return -EINVAL; - } +int udp_sendpage(struct sock *sk, struct page *page, int offset, + size_t size, int flags) +{ + struct bio_vec bvec; + struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES }; - ret = ip_append_page(sk, &inet->cork.fl.u.ip4, - page, offset, size, flags); - if (ret == -EOPNOTSUPP) { - release_sock(sk); - return sock_no_sendpage(sk->sk_socket, page, offset, - size, flags); - } - if (ret < 0) { - udp_flush_pending_frames(sk); - goto out; - } + if (flags & MSG_SENDPAGE_NOTLAST) + msg.msg_flags |= MSG_MORE; - up->len += size; - if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE))) - ret = udp_push_pending_frames(sk); - if (!ret) - ret = size; -out: - release_sock(sk); - return ret; + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + return udp_sendmsg(sk, &msg, size); } #define UDP_SKB_IS_STATELESS 0x80000000 @@ -1925,7 +1901,7 @@ try_again: (struct sockaddr *)sin); } - if (udp_sk(sk)->gro_enabled) + if (udp_test_bit(GRO_ENABLED, sk)) udp_cmsg_recv(msg, sk, skb); if (inet->cmsg_flags) @@ -2138,7 +2114,8 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) } nf_reset_ct(skb); - if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { + if (static_branch_unlikely(&udp_encap_needed_key) && + READ_ONCE(up->encap_type)) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -2219,7 +2196,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) udp_csum_pull_header(skb); - ipv4_pktinfo_prepare(sk, skb); + ipv4_pktinfo_prepare(sk, skb, true); return __udp_queue_rcv_skb(sk, skb); csum_error: @@ -2669,7 +2646,7 @@ void udp_destroy_sock(struct sock *sk) if (encap_destroy) encap_destroy(sk); } - if (up->encap_enabled) + if (udp_test_bit(ENCAP_ENABLED, sk)) static_branch_dec(&udp_encap_needed_key); } } @@ -2697,9 +2674,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: if (val != 0) { - WRITE_ONCE(up->corkflag, 1); + udp_set_bit(CORK, sk); } else { - WRITE_ONCE(up->corkflag, 0); + udp_clear_bit(CORK, sk); lock_sock(sk); push_pending_frames(sk); release_sock(sk); @@ -2723,10 +2700,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, #endif fallthrough; case UDP_ENCAP_L2TPINUDP: - up->encap_type = val; - lock_sock(sk); - udp_tunnel_encap_enable(sk->sk_socket); - release_sock(sk); + WRITE_ONCE(up->encap_type, val); + udp_tunnel_encap_enable(sk); break; default: err = -ENOPROTOOPT; @@ -2735,11 +2710,11 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, break; case UDP_NO_CHECK6_TX: - up->no_check6_tx = valbool; + udp_set_no_check6_tx(sk, valbool); break; case UDP_NO_CHECK6_RX: - up->no_check6_rx = valbool; + udp_set_no_check6_rx(sk, valbool); break; case UDP_SEGMENT: @@ -2749,14 +2724,12 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, break; case UDP_GRO: - lock_sock(sk); /* when enabling GRO, accept the related GSO packet type */ if (valbool) - udp_tunnel_encap_enable(sk->sk_socket); - up->gro_enabled = valbool; - up->accept_udp_l4 = valbool; - release_sock(sk); + udp_tunnel_encap_enable(sk); + udp_assign_bit(GRO_ENABLED, sk, valbool); + udp_assign_bit(ACCEPT_L4, sk, valbool); break; /* @@ -2824,19 +2797,19 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: - val = READ_ONCE(up->corkflag); + val = udp_test_bit(CORK, sk); break; case UDP_ENCAP: - val = up->encap_type; + val = READ_ONCE(up->encap_type); break; case UDP_NO_CHECK6_TX: - val = up->no_check6_tx; + val = udp_get_no_check6_tx(sk); break; case UDP_NO_CHECK6_RX: - val = up->no_check6_rx; + val = udp_get_no_check6_rx(sk); break; case UDP_SEGMENT: @@ -2844,7 +2817,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, break; case UDP_GRO: - val = up->gro_enabled; + val = udp_test_bit(GRO_ENABLED, sk); break; /* The following two cannot be changed on UDP sockets, the return is @@ -2946,6 +2919,7 @@ struct proto udp_prot = { .getsockopt = udp_getsockopt, .sendmsg = udp_sendmsg, .recvmsg = udp_recvmsg, + .splice_eof = udp_splice_eof, .sendpage = udp_sendpage, .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6d1a4bec2614..8096576fd9bd 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -549,10 +549,10 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { if (skb->dev->features & NETIF_F_GRO_FRAGLIST) - NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled : 1; + NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1; if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || - (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) + (sk && udp_test_bit(GRO_ENABLED, sk)) || NAPI_GRO_CB(skb)->is_flist) return call_gro_receive(udp_gro_receive_segment, head, skb); /* no GRO, be sure flush the current packet */ diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 5f8104cf082d..732e21b75ba2 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -78,7 +78,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, udp_sk(sk)->gro_receive = cfg->gro_receive; udp_sk(sk)->gro_complete = cfg->gro_complete; - udp_tunnel_encap_enable(sock); + udp_tunnel_encap_enable(sk); } EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index eac206a290d0..183f6dc37242 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -85,11 +85,11 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) struct udphdr *uh; struct iphdr *iph; int iphlen, len; - __u8 *udpdata; __be32 *udpdata32; - __u16 encap_type = up->encap_type; + u16 encap_type; + encap_type = READ_ONCE(up->encap_type); /* if this is not encapsulated socket, then just return now */ if (!encap_type) return 1; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b8dc20fe7a4e..46527b5cc8f0 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -706,6 +706,22 @@ errout: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet6_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv6.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + + static int inet6_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { @@ -739,8 +755,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet6_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -5326,7 +5341,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, } rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq; + cb->seq = inet6_base_seq(tgt_net); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &tgt_net->dev_index_head[h]; diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 507a8353a6bd..c008d21925d7 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -220,19 +220,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ -const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; +const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) + = IN6ADDR_LOOPBACK_INIT; EXPORT_SYMBOL(in6addr_loopback); -const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; +const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) + = IN6ADDR_ANY_INIT; EXPORT_SYMBOL(in6addr_any); -const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_linklocal_allnodes); -const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_linklocal_allrouters); -const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); -const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); -const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_sitelocal_allrouters); static void snmp6_free_dev(struct inet6_dev *idev) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b5309ae87fd7..0b42eb8c55aa 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -199,6 +199,9 @@ lookup_protocol: if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; + if (INET_PROTOSW_ICSK & answer_flags) + inet_init_csk_locks(sk); + inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; @@ -711,6 +714,7 @@ const struct proto_ops inet6_stream_ops = { #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, .sendmsg_locked = tcp_sendmsg_locked, .sendpage_locked = tcp_sendpage_locked, diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 5fa0e37305d9..1cfdd9d95012 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -180,6 +180,8 @@ static bool ip6_parse_tlv(bool hopbyhop, case IPV6_TLV_IOAM: if (!ipv6_hop_ioam(skb, off)) return false; + + nh = skb_network_header(skb); break; case IPV6_TLV_JUMBO: if (!ipv6_hop_jumbo(skb, off)) @@ -974,6 +976,14 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) if (!skb_valid_dst(skb)) ip6_route_input(skb); + /* About to mangle packet header */ + if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) + goto drop; + + /* Trace pointer may have changed */ + trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) + + optoff + sizeof(*hdr)); + ioam6_fill_trace_data(skb, ns, trace, true); break; default: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3c2b2a85de36..e9ae084d038d 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1506,8 +1506,8 @@ static int __ip6_append_data(struct sock *sk, mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; - if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && - sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + if (cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index afc922c88d17..2699915bb85b 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -399,7 +399,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw; unsigned int nhoff = raw - skb->data; unsigned int off = nhoff + sizeof(*ipv6h); - u8 next, nexthdr = ipv6h->nexthdr; + u8 nexthdr = ipv6h->nexthdr; while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) { struct ipv6_opt_hdr *hdr; @@ -410,25 +410,25 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { - struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr; - if (frag_hdr->frag_off) - break; optlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { optlen = ipv6_authlen(hdr); } else { optlen = ipv6_optlen(hdr); } - /* cache hdr->nexthdr, since pskb_may_pull() might - * invalidate hdr - */ - next = hdr->nexthdr; - if (nexthdr == NEXTHDR_DEST) { - u16 i = 2; - /* Remember : hdr is no longer valid at this point. */ - if (!pskb_may_pull(skb, off + optlen)) + if (!pskb_may_pull(skb, off + optlen)) + break; + + hdr = (struct ipv6_opt_hdr *)(skb->data + off); + if (nexthdr == NEXTHDR_FRAGMENT) { + struct frag_hdr *frag_hdr = (struct frag_hdr *)hdr; + + if (frag_hdr->frag_off) break; + } + if (nexthdr == NEXTHDR_DEST) { + u16 i = 2; while (1) { struct ipv6_tlv_tnl_enc_lim *tel; @@ -449,7 +449,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) i++; } } - nexthdr = next; + nexthdr = hdr->nexthdr; off += optlen; } return 0; @@ -796,8 +796,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, struct sk_buff *skb), bool log_ecn_err) { - const struct ipv6hdr *ipv6h = ipv6_hdr(skb); - int err; + const struct ipv6hdr *ipv6h; + int nh, err; if ((!(tpi->flags & TUNNEL_CSUM) && (tunnel->parms.i_flags & TUNNEL_CSUM)) || @@ -829,7 +829,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, goto drop; } - ipv6h = ipv6_hdr(skb); skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { @@ -837,7 +836,23 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, skb_reset_mac_header(skb); } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + ipv6h = (struct ipv6hdr *)(skb->head + nh); + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7860383295d8..566f3b7b957e 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2725,8 +2725,12 @@ void ipv6_mc_down(struct inet6_dev *idev) synchronize_net(); mld_query_stop_work(idev); mld_report_stop_work(idev); + + mutex_lock(&idev->mc_lock); mld_ifc_stop_work(idev); mld_gq_stop_work(idev); + mutex_unlock(&idev->mc_lock); + mld_dad_stop_work(idev); } diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index f61d4f18e1cf..433d98bbe33f 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -278,7 +278,6 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct net_device *br_indev __maybe_unused; struct sk_buff *nskb; struct tcphdr _otcph; const struct tcphdr *otcph; @@ -353,9 +352,15 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ - br_indev = nf_bridge_get_physindev(oldskb); - if (br_indev) { + if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(oldskb, net); + if (!br_indev) { + kfree_skb(nskb); + return; + } nskb->dev = br_indev; nskb->protocol = htons(ETH_P_IPV6); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 4d5a27dd9a4b..a5d7d1915ba7 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -119,7 +119,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) return -EINVAL; ipcm6_init_sk(&ipc6, np); - ipc6.sockc.tsflags = sk->sk_tsflags; + ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = READ_ONCE(sk->sk_mark); fl6.flowi6_oif = oif; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index df3abd9e5237..dc31752a7edc 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -776,7 +776,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); - ipc6.sockc.tsflags = sk->sk_tsflags; + ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = fl6.flowi6_mark; if (sin6) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0bcdb675ba2c..7f65dc750feb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -91,7 +91,7 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); -static int ip6_dst_gc(struct dst_ops *ops); +static void ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); @@ -3288,11 +3288,10 @@ out: return dst; } -static int ip6_dst_gc(struct dst_ops *ops) +static void ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; - int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; @@ -3300,11 +3299,10 @@ static int ip6_dst_gc(struct dst_ops *ops) int entries; entries = dst_entries_get_fast(ops); - if (entries > rt_max_size) + if (entries > ops->gc_thresh) entries = dst_entries_get_slow(ops); - if (time_after(rt_last_gc + rt_min_interval, jiffies) && - entries <= rt_max_size) + if (time_after(rt_last_gc + rt_min_interval, jiffies)) goto out; fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); @@ -3314,7 +3312,6 @@ static int ip6_dst_gc(struct dst_ops *ops) out: val = atomic_read(&net->ipv6.ip6_rt_gc_expire); atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); - return entries > rt_max_size; } static int ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg, @@ -6517,7 +6514,7 @@ static int __net_init ip6_route_net_init(struct net *net) #endif net->ipv6.sysctl.flush_delay = 0; - net->ipv6.sysctl.ip6_rt_max_size = 4096; + net->ipv6.sysctl.ip6_rt_max_size = INT_MAX; net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 29346a6eec9f..35508abd76f4 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -512,22 +512,24 @@ int __init seg6_init(void) { int err; - err = genl_register_family(&seg6_genl_family); + err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; - err = register_pernet_subsys(&ip6_segments_ops); + err = genl_register_family(&seg6_genl_family); if (err) - goto out_unregister_genl; + goto out_unregister_pernet; #ifdef CONFIG_IPV6_SEG6_LWTUNNEL err = seg6_iptunnel_init(); if (err) - goto out_unregister_pernet; + goto out_unregister_genl; err = seg6_local_init(); - if (err) - goto out_unregister_pernet; + if (err) { + seg6_iptunnel_exit(); + goto out_unregister_genl; + } #endif #ifdef CONFIG_IPV6_SEG6_HMAC @@ -548,11 +550,11 @@ out_unregister_iptun: #endif #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL -out_unregister_pernet: - unregister_pernet_subsys(&ip6_segments_ops); -#endif out_unregister_genl: genl_unregister_family(&seg6_genl_family); +#endif +out_unregister_pernet: + unregister_pernet_subsys(&ip6_segments_ops); goto out; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7be89dcfd5fc..ba9a22db5805 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2158,6 +2158,7 @@ struct proto tcpv6_prot = { .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, + .splice_eof = tcp_splice_eof, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 64b36c2ba774..c2c02dea6c38 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -440,7 +440,7 @@ try_again: (struct sockaddr *)sin6); } - if (udp_sk(sk)->gro_enabled) + if (udp_test_bit(GRO_ENABLED, sk)) udp_cmsg_recv(msg, sk, skb); if (np->rxopt.all) @@ -598,7 +598,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), inet6_sdif(skb), udptable, NULL); - if (!sk || udp_sk(sk)->encap_type) { + if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) { /* No socket for error: try tunnels before discarding */ if (static_branch_unlikely(&udpv6_encap_needed_key)) { sk = __udp6_lib_err_encap(net, hdr, offset, uh, @@ -712,7 +712,8 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) } nf_reset_ct(skb); - if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) { + if (static_branch_unlikely(&udpv6_encap_needed_key) && + READ_ONCE(up->encap_type)) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -882,7 +883,7 @@ start_lookup: /* If zero checksum and no_check is not on for * the socket then skip it. */ - if (!uh->check && !udp_sk(sk)->no_check6_rx) + if (!uh->check && !udp_get_no_check6_rx(sk)) continue; if (!first) { first = sk; @@ -1000,7 +1001,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp6_sk_rx_dst_set(sk, dst); - if (!uh->check && !udp_sk(sk)->no_check6_rx) { + if (!uh->check && !udp_get_no_check6_rx(sk)) { if (refcounted) sock_put(sk); goto report_csum_error; @@ -1022,7 +1023,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, /* Unicast */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { - if (!uh->check && !udp_sk(sk)->no_check6_rx) + if (!uh->check && !udp_get_no_check6_rx(sk)) goto report_csum_error; return udp6_unicast_rcv_skb(sk, skb, uh); } @@ -1151,7 +1152,7 @@ static void udp_v6_flush_pending_frames(struct sock *sk) udp_flush_pending_frames(sk); else if (up->pending) { up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); ip6_flush_pending_frames(sk); } } @@ -1260,7 +1261,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, kfree_skb(skb); return -EINVAL; } - if (udp_sk(sk)->no_check6_tx) { + if (udp_get_no_check6_tx(sk)) { kfree_skb(skb); return -EINVAL; } @@ -1281,7 +1282,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, if (is_udplite) csum = udplite_csum(skb); - else if (udp_sk(sk)->no_check6_tx) { /* UDP csum disabled */ + else if (udp_get_no_check6_tx(sk)) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ @@ -1329,7 +1330,7 @@ static int udp_v6_push_pending_frames(struct sock *sk) &inet_sk(sk)->cork.base); out: up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); return err; } @@ -1351,14 +1352,14 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int addr_len = msg->msg_namelen; bool connected = false; int ulen = len; - int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; + int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE; int err; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); ipcm6_init(&ipc6); ipc6.gso_size = READ_ONCE(up->gso_size); - ipc6.sockc.tsflags = sk->sk_tsflags; + ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = READ_ONCE(sk->sk_mark); /* destination address check */ @@ -1386,7 +1387,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) default: return -EINVAL; } - } else if (!up->pending) { + } else if (!READ_ONCE(up->pending)) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; @@ -1417,8 +1418,8 @@ do_udp_sendmsg: return -EMSGSIZE; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; - if (up->pending) { - if (up->pending == AF_INET) + if (READ_ONCE(up->pending)) { + if (READ_ONCE(up->pending) == AF_INET) return udp_sendmsg(sk, msg, len); /* * There are pending frames. @@ -1608,7 +1609,7 @@ back_from_confirm: goto out; } - up->pending = AF_INET6; + WRITE_ONCE(up->pending, AF_INET6); do_append_data: if (ipc6.dontfrag < 0) @@ -1622,7 +1623,7 @@ do_append_data: else if (!corkreq) err = udp_v6_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) - up->pending = 0; + WRITE_ONCE(up->pending, 0); if (err > 0) err = np->recverr ? net_xmit_errno(err) : 0; @@ -1657,6 +1658,20 @@ do_confirm: goto out; } +static void udpv6_splice_eof(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct udp_sock *up = udp_sk(sk); + + if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk)) + return; + + lock_sock(sk); + if (up->pending && !udp_test_bit(CORK, sk)) + udp_v6_push_pending_frames(sk); + release_sock(sk); +} + void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); @@ -1674,7 +1689,7 @@ void udpv6_destroy_sock(struct sock *sk) if (encap_destroy) encap_destroy(sk); } - if (up->encap_enabled) { + if (udp_test_bit(ENCAP_ENABLED, sk)) { static_branch_dec(&udpv6_encap_needed_key); udp_encap_disable(); } @@ -1768,6 +1783,7 @@ struct proto udpv6_prot = { .getsockopt = udpv6_getsockopt, .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, + .splice_eof = udpv6_splice_eof, .release_cb = ip6_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 4907ab241d6b..4156387248e4 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -81,14 +81,14 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) struct ipv6hdr *ip6h; int len; int ip6hlen = sizeof(struct ipv6hdr); - __u8 *udpdata; __be32 *udpdata32; - __u16 encap_type = up->encap_type; + u16 encap_type; if (skb->protocol == htons(ETH_P_IP)) return xfrm4_udp_encap_rcv(sk, skb); + encap_type = READ_ONCE(up->encap_type); /* if this is not encapsulated socket, then just return now */ if (!encap_type) return 1; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 03608d3ded4b..8d21ff25f160 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1139,9 +1139,9 @@ static void l2tp_tunnel_destruct(struct sock *sk) switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* No longer an encapsulation socket. See net/ipv4/udp.c */ - (udp_sk(sk))->encap_type = 0; - (udp_sk(sk))->encap_rcv = NULL; - (udp_sk(sk))->encap_destroy = NULL; + WRITE_ONCE(udp_sk(sk)->encap_type, 0); + udp_sk(sk)->encap_rcv = NULL; + udp_sk(sk)->encap_destroy = NULL; break; case L2TP_ENCAPTYPE_IP: break; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 314ec3a51e8d..bb92dc8b82f3 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -630,7 +630,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); - ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; + ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0); err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 9ffbc667be6c..8e3be0009f60 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -226,6 +226,8 @@ static int llc_ui_release(struct socket *sock) } netdev_put(llc->dev, &llc->dev_tracker); sock_put(sk); + sock_orphan(sk); + sock->sk = NULL; llc_sk_free(sk); out: return 0; @@ -928,14 +930,15 @@ copy_uaddr: */ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { + DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; + int rc = -EINVAL, copied = 0, hdrlen, hh_len; struct sk_buff *skb = NULL; + struct net_device *dev; size_t size = 0; - int rc = -EINVAL, copied = 0, hdrlen; dprintk("%s: sending from %02X to %02X\n", __func__, llc->laddr.lsap, llc->daddr.lsap); @@ -955,22 +958,29 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (rc) goto out; } - hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr); + dev = llc->dev; + hh_len = LL_RESERVED_SPACE(dev); + hdrlen = llc_ui_header_len(sk, addr); size = hdrlen + len; - if (size > llc->dev->mtu) - size = llc->dev->mtu; + size = min_t(size_t, size, READ_ONCE(dev->mtu)); copied = size - hdrlen; rc = -EINVAL; if (copied < 0) goto out; release_sock(sk); - skb = sock_alloc_send_skb(sk, size, noblock, &rc); + skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc); lock_sock(sk); if (!skb) goto out; - skb->dev = llc->dev; + if (sock_flag(sk, SOCK_ZAPPED) || + llc->dev != dev || + hdrlen != llc_ui_header_len(sk, addr) || + hh_len != LL_RESERVED_SPACE(dev) || + size > READ_ONCE(dev->mtu)) + goto out; + skb->dev = dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); - skb_reserve(skb, hdrlen); + skb_reserve(skb, hh_len + hdrlen); rc = memcpy_from_msg(skb_put(skb, copied), msg, copied); if (rc) goto out; diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 6e387aadffce..4f16d9c88350 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -135,22 +135,15 @@ static struct packet_type llc_packet_type __read_mostly = { .func = llc_rcv, }; -static struct packet_type llc_tr_packet_type __read_mostly = { - .type = cpu_to_be16(ETH_P_TR_802_2), - .func = llc_rcv, -}; - static int __init llc_init(void) { dev_add_pack(&llc_packet_type); - dev_add_pack(&llc_tr_packet_type); return 0; } static void __exit llc_exit(void) { dev_remove_pack(&llc_packet_type); - dev_remove_pack(&llc_tr_packet_type); } module_init(llc_init); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 2ca442f48513..6cf0b77839d1 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1694,10 +1694,10 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, lockdep_is_held(&local->sta_mtx)); /* - * If there are no changes, then accept a link that doesn't exist, + * If there are no changes, then accept a link that exist, * unless it's a new link. */ - if (params->link_id < 0 && !new_link && + if (params->link_id >= 0 && !new_link && !params->link_mac && !params->txpwr_set && !params->supported_rates_len && !params->ht_capa && !params->vht_capa && @@ -1775,6 +1775,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, sband->band); } + ieee80211_sta_set_rx_nss(link_sta); + return ret; } diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index ae42e956eff5..9bfe128ada47 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -271,6 +271,7 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, case NL80211_CHAN_WIDTH_80: case NL80211_CHAN_WIDTH_80P80: case NL80211_CHAN_WIDTH_160: + case NL80211_CHAN_WIDTH_320: bw = ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20; break; diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index bd0b7c189adf..711c3377f428 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -1051,8 +1051,8 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, case WLAN_SP_MESH_PEERING_OPEN: if (!matches_local) event = OPN_RJCT; - if (!mesh_plink_free_count(sdata) || - (sta->mesh->plid && sta->mesh->plid != plid)) + else if (!mesh_plink_free_count(sdata) || + (sta->mesh->plid && sta->mesh->plid != plid)) event = OPN_IGNR; else event = OPN_ACPT; @@ -1060,9 +1060,9 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, case WLAN_SP_MESH_PEERING_CONFIRM: if (!matches_local) event = CNF_RJCT; - if (!mesh_plink_free_count(sdata) || - sta->mesh->llid != llid || - (sta->mesh->plid && sta->mesh->plid != plid)) + else if (!mesh_plink_free_count(sdata) || + sta->mesh->llid != llid || + (sta->mesh->plid && sta->mesh->plid != plid)) event = CNF_IGNR; else event = CNF_ACPT; @@ -1230,6 +1230,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, return; } elems = ieee802_11_parse_elems(baseaddr, len - baselen, true, NULL); - mesh_process_plink_frame(sdata, mgmt, elems, rx_status); - kfree(elems); + if (elems) { + mesh_process_plink_frame(sdata, mgmt, elems, rx_status); + kfree(elems); + } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index c07645c999f9..f25dc6931a5b 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -7221,8 +7221,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); beacon_ies = rcu_dereference(req->bss->beacon_ies); - - if (beacon_ies) { + if (!beacon_ies) { /* * Wait up to one beacon interval ... * should this be more if we miss one? @@ -7295,6 +7294,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, req->reason_code, false); + drv_mgd_complete_tx(sdata->local, sdata, &info); return 0; } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 49b71453dec3..bd56015b2925 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -396,7 +396,10 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) int i; for (i = 0; i < ARRAY_SIZE(sta->link); i++) { - if (!(sta->sta.valid_links & BIT(i))) + struct link_sta_info *link_sta; + + link_sta = rcu_access_pointer(sta->link[i]); + if (!link_sta) continue; sta_remove_link(sta, i, false); @@ -888,6 +891,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_accept_plinks_update(sdata); + ieee80211_check_fast_xmit(sta); + return 0; out_remove: if (sta->sta.valid_links) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 2db103a56a28..3d62e8b71874 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation * * Transmit and frame generation functions. */ @@ -3044,7 +3044,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) sdata->vif.type == NL80211_IFTYPE_STATION) goto out; - if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->uploaded) goto out; if (test_sta_flag(sta, WLAN_STA_PS_STA) || @@ -3838,6 +3838,7 @@ begin: goto begin; skb = __skb_dequeue(&tx.skbs); + info = IEEE80211_SKB_CB(skb); if (!skb_queue_empty(&tx.skbs)) { spin_lock_bh(&fq->lock); @@ -3882,7 +3883,7 @@ begin: } encap_out: - IEEE80211_SKB_CB(skb)->control.vif = vif; + info->control.vif = vif; if (tx.sta && wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { diff --git a/net/mctp/route.c b/net/mctp/route.c index 68be8f2b622d..256bf0b89e6c 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -663,7 +663,7 @@ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, spin_unlock_irqrestore(&mns->keys_lock, flags); if (!tagbits) { - kfree(key); + mctp_key_unref(key); return ERR_PTR(-EBUSY); } diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index a536586742f2..e57c5f47f035 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -13,17 +13,19 @@ #include <uapi/linux/mptcp.h> #include "protocol.h" -static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) +static int subflow_get_info(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *sf; struct nlattr *start; u32 flags = 0; + bool slow; int err; start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP); if (!start) return -EMSGSIZE; + slow = lock_sock_fast(sk); rcu_read_lock(); sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data); if (!sf) { @@ -69,11 +71,13 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) } rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_end(skb, start); return 0; nla_failure: rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_cancel(skb, start); return err; } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 0c786ceda5ee..a718ebcb5bc6 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -103,6 +103,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->suboptions |= OPTION_MPTCP_DSS; mp_opt->use_map = 1; mp_opt->mpc_map = 1; + mp_opt->use_ack = 0; mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; } @@ -117,8 +118,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_JOIN: - mp_opt->suboptions |= OPTIONS_MPTCP_MPJ; if (opsize == TCPOLEN_MPTCP_MPJ_SYN) { + mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; mp_opt->join_id = *ptr++; mp_opt->token = get_unaligned_be32(ptr); @@ -129,6 +130,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->backup, mp_opt->join_id, mp_opt->token, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) { + mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYNACK; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; mp_opt->join_id = *ptr++; mp_opt->thmac = get_unaligned_be64(ptr); @@ -139,11 +141,10 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->backup, mp_opt->join_id, mp_opt->thmac, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) { + mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK; ptr += 2; memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); pr_debug("MP_JOIN hmac"); - } else { - mp_opt->suboptions &= ~OPTIONS_MPTCP_MPJ; } break; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 980050f6b456..70a1025f093c 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -900,7 +900,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) } static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; @@ -942,7 +943,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id) { + if (!entry->addr.id && needs_id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, @@ -953,7 +954,7 @@ find_next: } } - if (!entry->addr.id) + if (!entry->addr.id && needs_id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); @@ -1095,7 +1096,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) entry->ifindex = 0; entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); if (ret < 0) kfree(entry); @@ -1311,6 +1312,18 @@ next: return 0; } +static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr, + struct genl_info *info) +{ + struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; + + if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, + mptcp_pm_addr_policy, info->extack) && + tb[MPTCP_PM_ADDR_ATTR_ID]) + return true; + return false; +} + static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; @@ -1352,7 +1365,8 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) goto out_free; } } - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, + !mptcp_pm_has_addr_attr_id(attr, info)); if (ret < 0) { GENL_SET_ERR_MSG(info, "too many addresses or duplicate one"); goto out_free; diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 38cbdc66d8bf..631fa104617c 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -25,8 +25,9 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk) } } -int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry) +static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *entry, + bool needs_id) { DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); struct mptcp_pm_addr_entry *match = NULL; @@ -41,7 +42,7 @@ int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); - if (addr_match && entry->addr.id == 0) + if (addr_match && entry->addr.id == 0 && needs_id) entry->addr.id = e->addr.id; id_match = (e->addr.id == entry->addr.id); if (addr_match && id_match) { @@ -64,7 +65,7 @@ int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, } *e = *entry; - if (!e->addr.id) + if (!e->addr.id && needs_id) e->addr.id = find_next_zero_bit(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, 1); @@ -132,10 +133,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { - struct mptcp_pm_addr_entry new_entry; + struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry; __be16 msk_sport = ((struct inet_sock *) inet_sk((struct sock *)msk))->inet_sport; + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&e->addr, skc, false)) { + entry = e; + break; + } + } + spin_unlock_bh(&msk->pm.lock); + if (entry) + return entry->addr.id; + memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry)); new_entry.addr = *skc; new_entry.addr.id = 0; @@ -144,7 +156,7 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, if (new_entry.addr.port == msk_sport) new_entry.addr.port = 0; - return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry); + return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) @@ -186,7 +198,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) goto announce_err; } - err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val); + err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto announce_err; @@ -210,6 +222,40 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) return err; } +static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk, + struct genl_info *info) +{ + struct mptcp_rm_list list = { .nr = 0 }; + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + bool has_id_0 = false; + int err = -EINVAL; + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + if (subflow->local_id == 0) { + has_id_0 = true; + break; + } + } + if (!has_id_0) { + GENL_SET_ERR_MSG(info, "address with id 0 not found"); + goto remove_err; + } + + list.ids[list.nr++] = 0; + + spin_lock_bh(&msk->pm.lock); + mptcp_pm_remove_addr(msk, &list); + spin_unlock_bh(&msk->pm.lock); + + err = 0; + +remove_err: + release_sock(sk); + return err; +} + int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; @@ -241,6 +287,11 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) goto remove_err; } + if (id_val == 0) { + err = mptcp_userspace_pm_remove_id_zero_address(msk, info); + goto remove_err; + } + lock_sock((struct sock *)msk); list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { @@ -324,7 +375,7 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) } local.addr = addr_l; - err = mptcp_userspace_pm_append_new_local_addr(msk, &local); + err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto create_err; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 76539d1004eb..859b18cb8e4f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1582,8 +1582,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk, void mptcp_check_and_set_pending(struct sock *sk) { - if (mptcp_send_head(sk)) - mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING); + if (mptcp_send_head(sk)) { + mptcp_data_lock(sk); + mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING); + mptcp_data_unlock(sk); + } } void __mptcp_push_pending(struct sock *sk, unsigned int flags) @@ -2336,9 +2339,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) if (__mptcp_check_fallback(mptcp_sk(sk))) return false; - if (tcp_rtx_and_write_queues_empty(sk)) - return false; - /* the closing socket has some data untransmitted and/or unacked: * some data in the mptcp rtx queue has not really xmitted yet. * keep it simple and re-inject the whole mptcp level rtx queue @@ -2422,7 +2422,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, goto out_release; } - dispose_it = !msk->subflow || ssk != msk->subflow->sk; + dispose_it = msk->free_first || ssk != msk->first; if (dispose_it) list_del(&subflow->node); @@ -2440,7 +2440,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { __mptcp_subflow_disconnect(ssk, subflow, flags); - msk->subflow->state = SS_UNCONNECTED; release_sock(ssk); goto out; @@ -3144,7 +3143,6 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->last_snd = NULL; WRITE_ONCE(msk->flags, 0); msk->cb_flags = 0; - msk->push_pending = 0; msk->recovery = false; msk->can_ack = false; msk->fully_established = false; @@ -3341,10 +3339,10 @@ static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - /* clears msk->subflow, allowing the following to close - * even the initial subflow - */ mptcp_dispose_initial_subflow(msk); + + /* allow the following to close even the initial subflow */ + msk->free_first = 1; mptcp_destroy_common(msk, 0); sk_sockets_allocated_dec(sk); } @@ -3388,8 +3386,7 @@ static void mptcp_release_cb(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); for (;;) { - unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) | - msk->push_pending; + unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); struct list_head join_list; if (!flags) @@ -3405,7 +3402,6 @@ static void mptcp_release_cb(struct sock *sk) * datapath acquires the msk socket spinlock while helding * the subflow socket lock */ - msk->push_pending = 0; msk->cb_flags &= ~flags; spin_unlock_bh(&sk->sk_lock.slock); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 4ec8e0a81b5a..b09220521323 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -272,7 +272,6 @@ struct mptcp_sock { int rmem_released; unsigned long flags; unsigned long cb_flags; - unsigned long push_pending; bool recovery; /* closing subflow write queue reinjected */ bool can_ack; bool fully_established; @@ -287,7 +286,8 @@ struct mptcp_sock { cork:1, nodelay:1, fastopening:1, - in_accept_queue:1; + in_accept_queue:1, + free_first:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -834,8 +834,6 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list); -int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry); void mptcp_free_local_addr_list(struct mptcp_sock *msk); int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info); int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index d611783c2601..45d20e20cfc0 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -156,8 +156,8 @@ static int subflow_check_req(struct request_sock *req, mptcp_get_options(skb, &mp_opt); - opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); - opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); + opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYN); + opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYN); if (opt_mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); @@ -253,8 +253,8 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, subflow_init_req(req, sk_listener); mptcp_get_options(skb, &mp_opt); - opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); - opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); + opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK); + opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK); if (opt_mp_capable && opt_mp_join) return -EINVAL; @@ -415,7 +415,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) mptcp_get_options(skb, &mp_opt); if (subflow->request_mptcp) { - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) { + if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYNACK)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEFALLBACK); mptcp_do_fallback(sk); @@ -438,7 +438,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ)) { + if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYNACK)) { subflow->reset_reason = MPTCP_RST_EMPTCP; goto do_reset; } @@ -713,12 +713,13 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * options. */ mptcp_get_options(skb, &mp_opt); - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) + if (!(mp_opt.suboptions & + (OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_ACK))) fallback = true; } else if (subflow_req->mp_join) { mptcp_get_options(skb, &mp_opt); - if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) || + if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK) || !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); @@ -1899,6 +1900,17 @@ static void tcp_release_cb_override(struct sock *ssk) tcp_release_cb(ssk); } +static int tcp_abort_override(struct sock *ssk, int err) +{ + /* closing a listener subflow requires a great deal of care. + * keep it simple and just prevent such operation + */ + if (inet_sk_state_load(ssk) == TCP_LISTEN) + return -EINVAL; + + return tcp_abort(ssk, err); +} + static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = { .name = "mptcp", .owner = THIS_MODULE, @@ -1942,6 +1954,7 @@ void __init mptcp_subflow_init(void) tcp_prot_override = tcp_prot; tcp_prot_override.release_cb = tcp_release_cb_override; + tcp_prot_override.diag_destroy = tcp_abort_override; #if IS_ENABLED(CONFIG_MPTCP_IPV6) /* In struct mptcp_subflow_request_sock, we assume the TCP request sock @@ -1977,6 +1990,7 @@ void __init mptcp_subflow_init(void) tcpv6_prot_override = tcpv6_prot; tcpv6_prot_override.release_cb = tcp_release_cb_override; + tcpv6_prot_override.diag_destroy = tcp_abort_override; #endif mptcp_diag_subflow_init(&subflow_ulp_ops); diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 03757e76bb6b..374412ed780b 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -105,8 +105,11 @@ enum { struct ncsi_channel_version { - u32 version; /* Supported BCD encoded NCSI version */ - u32 alpha2; /* Supported BCD encoded NCSI version */ + u8 major; /* NCSI version major */ + u8 minor; /* NCSI version minor */ + u8 update; /* NCSI version update */ + char alpha1; /* NCSI version alpha1 */ + char alpha2; /* NCSI version alpha2 */ u8 fw_name[12]; /* Firmware name string */ u32 fw_version; /* Firmware version */ u16 pci_ids[4]; /* PCI identification */ diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index d27f4eccce6d..fe681680b5d9 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -71,8 +71,8 @@ static int ncsi_write_channel_info(struct sk_buff *skb, if (nc == nc->package->preferred_channel) nla_put_flag(skb, NCSI_CHANNEL_ATTR_FORCED); - nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.version); - nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.alpha2); + nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.major); + nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.minor); nla_put_string(skb, NCSI_CHANNEL_ATTR_VERSION_STR, nc->version.fw_name); vid_nest = nla_nest_start_noflag(skb, NCSI_CHANNEL_ATTR_VLAN_LIST); diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h index ba66c7dc3a21..c9d1da34dc4d 100644 --- a/net/ncsi/ncsi-pkt.h +++ b/net/ncsi/ncsi-pkt.h @@ -197,9 +197,12 @@ struct ncsi_rsp_gls_pkt { /* Get Version ID */ struct ncsi_rsp_gvi_pkt { struct ncsi_rsp_pkt_hdr rsp; /* Response header */ - __be32 ncsi_version; /* NCSI version */ + unsigned char major; /* NCSI version major */ + unsigned char minor; /* NCSI version minor */ + unsigned char update; /* NCSI version update */ + unsigned char alpha1; /* NCSI version alpha1 */ unsigned char reserved[3]; /* Reserved */ - unsigned char alpha2; /* NCSI version */ + unsigned char alpha2; /* NCSI version alpha2 */ unsigned char fw_name[12]; /* f/w name string */ __be32 fw_version; /* f/w version */ __be16 pci_ids[4]; /* PCI IDs */ diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 069c2659074b..480e80e3c283 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -19,6 +19,19 @@ #include "ncsi-pkt.h" #include "ncsi-netlink.h" +/* Nibbles within [0xA, 0xF] add zero "0" to the returned value. + * Optional fields (encoded as 0xFF) will default to zero. + */ +static u8 decode_bcd_u8(u8 x) +{ + int lo = x & 0xF; + int hi = x >> 4; + + lo = lo < 0xA ? lo : 0; + hi = hi < 0xA ? hi : 0; + return lo + hi * 10; +} + static int ncsi_validate_rsp_pkt(struct ncsi_request *nr, unsigned short payload) { @@ -755,9 +768,18 @@ static int ncsi_rsp_handler_gvi(struct ncsi_request *nr) if (!nc) return -ENODEV; - /* Update to channel's version info */ + /* Update channel's version info + * + * Major, minor, and update fields are supposed to be + * unsigned integers encoded as packed BCD. + * + * Alpha1 and alpha2 are ISO/IEC 8859-1 characters. + */ ncv = &nc->version; - ncv->version = ntohl(rsp->ncsi_version); + ncv->major = decode_bcd_u8(rsp->major); + ncv->minor = decode_bcd_u8(rsp->minor); + ncv->update = decode_bcd_u8(rsp->update); + ncv->alpha1 = rsp->alpha1; ncv->alpha2 = rsp->alpha2; memcpy(ncv->fw_name, rsp->fw_name, 12); ncv->fw_version = ntohl(rsp->fw_version); diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 26ab0e9612d8..9523104a90da 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -28,6 +28,7 @@ #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype MTYPE #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) @@ -57,9 +58,6 @@ mtype_destroy(struct ip_set *set) { struct mtype *map = set->data; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - if (set->dsize && set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); ip_set_free(map->members); @@ -288,6 +286,15 @@ mtype_gc(struct timer_list *t) add_timer(&map->gc); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct mtype *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant mtype = { .kadt = mtype_kadt, .uadt = mtype_uadt, @@ -301,6 +308,7 @@ static const struct ip_set_type_variant mtype = { .head = mtype_head, .list = mtype_list, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, }; #endif /* __IP_SET_BITMAP_IP_GEN_H */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index d47dfdcb899b..f645da82d826 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1156,6 +1156,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info, return ret; cleanup: + set->variant->cancel_gc(set); set->variant->destroy(set); put_out: module_put(set->type->me); @@ -1184,6 +1185,14 @@ ip_set_destroy_set(struct ip_set *set) kfree(set); } +static void +ip_set_destroy_set_rcu(struct rcu_head *head) +{ + struct ip_set *set = container_of(head, struct ip_set, rcu); + + ip_set_destroy_set(set); +} + static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const attr[]) { @@ -1195,8 +1204,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* Must wait for flush to be really finished in list:set */ - rcu_barrier(); /* Commands are serialized and references are * protected by the ip_set_ref_lock. @@ -1208,8 +1215,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, * counter, so if it's already zero, we can proceed * without holding the lock. */ - read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { + /* Must wait for flush to be really finished in list:set */ + rcu_barrier(); + read_lock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); if (s && (s->ref || s->ref_netlink)) { @@ -1223,6 +1232,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, s = ip_set(inst, i); if (s) { ip_set(inst, i) = NULL; + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); ip_set_destroy_set(s); } } @@ -1230,6 +1241,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, inst->is_destroyed = false; } else { u32 flags = flag_exist(info->nlh); + u16 features = 0; + + read_lock_bh(&ip_set_ref_lock); s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); if (!s) { @@ -1240,10 +1254,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, ret = -IPSET_ERR_BUSY; goto out; } + features = s->type->features; ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); - - ip_set_destroy_set(s); + if (features & IPSET_TYPE_NAME) { + /* Must wait for flush to be really finished */ + rcu_barrier(); + } + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); + call_rcu(&s->rcu, ip_set_destroy_set_rcu); } return 0; out: @@ -1396,9 +1416,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); - /* Make sure all readers of the old set pointers are completed. */ - synchronize_rcu(); - return 0; } @@ -2364,6 +2381,7 @@ ip_set_net_exit(struct net *net) set = ip_set(inst, i); if (set) { ip_set(inst, i) = NULL; + set->variant->cancel_gc(set); ip_set_destroy_set(set); } } @@ -2411,8 +2429,11 @@ ip_set_fini(void) { nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - unregister_pernet_subsys(&ip_set_net_ops); + + /* Wait for call_rcu() in destroy */ + rcu_barrier(); + pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 7499192af586..ef04e556aadb 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -210,6 +210,7 @@ htable_size(u8 hbits) #undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init +#undef mtype_cancel_gc #undef mtype_variant #undef mtype_data_match @@ -254,6 +255,7 @@ htable_size(u8 hbits) #define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) @@ -417,7 +419,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference(hbucket(t, i)); + n = (__force struct hbucket *)hbucket(t, i); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -437,10 +439,7 @@ mtype_destroy(struct ip_set *set) struct htype *h = set->data; struct list_head *l, *lt; - if (SET_WITH_TIMEOUT(set)) - cancel_delayed_work_sync(&h->gc.dwork); - - mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + mtype_ahash_destroy(set, (__force struct htable *)h->table, true); list_for_each_safe(l, lt, &h->ad) { list_del(l); kfree(l); @@ -586,6 +585,15 @@ mtype_gc_init(struct htable_gc *gc) queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct htype *h = set->data; + + if (SET_WITH_TIMEOUT(set)) + cancel_delayed_work_sync(&h->gc.dwork); +} + static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags); @@ -1416,6 +1424,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, .region_lock = true, }; diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 031073286236..bf1a3851ba5a 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -138,9 +138,9 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next, #include "ip_set_hash_gen.h" #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -static const char *get_physindev_name(const struct sk_buff *skb) +static const char *get_physindev_name(const struct sk_buff *skb, struct net *net) { - struct net_device *dev = nf_bridge_get_physindev(skb); + struct net_device *dev = nf_bridge_get_physindev(skb, net); return dev ? dev->name : NULL; } @@ -177,7 +177,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - const char *eiface = SRCDIR ? get_physindev_name(skb) : + const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) : get_physoutdev_name(skb); if (!eiface) @@ -395,7 +395,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - const char *eiface = SRCDIR ? get_physindev_name(skb) : + const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) : get_physoutdev_name(skb); if (!eiface) diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 5a67f7966574..6bc7019982b0 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set) struct list_set *map = set->data; struct set_elem *e, *n; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - list_for_each_entry_safe(e, n, &map->members, list) { list_del(&e->list); ip_set_put_byindex(map->net, e->id); @@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } +static void +list_set_cancel_gc(struct ip_set *set) +{ + struct list_set *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant set_variant = { .kadt = list_set_kadt, .uadt = list_set_uadt, @@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = { .head = list_set_head, .list = list_set_list, .same_set = list_set_same_set, + .cancel_gc = list_set_cancel_gc, }; static void diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 7243079ef354..d40a4ca2b27f 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -271,7 +271,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); - __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return false; } @@ -286,7 +286,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, { if (ip_hdr(skb)->ttl <= 1) { /* Tell the sender its packet died... */ - __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); return false; } @@ -994,7 +994,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, old_dsfield = ipv4_get_dsfield(old_iph); *ttl = old_iph->ttl; if (payload_len) - *payload_len = ntohs(old_iph->tot_len); + *payload_len = skb_ip_totlen(skb); } /* Implement full-functionality option for ECN encapsulation */ diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c94a9971d790..7ffd698497f2 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -299,7 +299,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; - } else { + } else if (sch->type == SCTP_CID_SHUTDOWN_ACK) { /* If it is a shutdown ack OOTB packet, we expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */ pr_debug("Setting vtag %x for new conn OOTB\n", diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3ac1af6f59fc..e0092bf273fd 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -457,7 +457,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender, const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, - u32 end, u32 win) + u32 end, u32 win, + enum ip_conntrack_dir dir) { /* SYN-ACK in reply to a SYN * or SYN from reply direction in simultaneous open. @@ -471,7 +472,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender, * Both sides must send the Window Scale option * to enable window scaling in either direction. */ - if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && + if (dir == IP_CT_DIR_REPLY && + !(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) { sender->td_scale = 0; receiver->td_scale = 0; @@ -542,7 +544,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, if (tcph->syn) { tcp_init_sender(sender, receiver, skb, dataoff, tcph, - end, win); + end, win, dir); if (!tcph->ack) /* Simultaneous open */ return NFCT_TCP_ACCEPT; @@ -585,7 +587,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, */ tcp_init_sender(sender, receiver, skb, dataoff, tcph, - end, win); + end, win, dir); if (dir == IP_CT_DIR_REPLY && !tcph->ack) return NFCT_TCP_ACCEPT; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 81c26a96c30b..99195cf6b265 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -87,12 +87,22 @@ static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple) return 0; } +static struct dst_entry *nft_route_dst_fetch(struct nf_flow_route *route, + enum flow_offload_tuple_dir dir) +{ + struct dst_entry *dst = route->tuple[dir].dst; + + route->tuple[dir].dst = NULL; + + return dst; +} + static int flow_offload_fill_route(struct flow_offload *flow, - const struct nf_flow_route *route, + struct nf_flow_route *route, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; - struct dst_entry *dst = route->tuple[dir].dst; + struct dst_entry *dst = nft_route_dst_fetch(route, dir); int i, j = 0; switch (flow_tuple->l3proto) { @@ -122,12 +132,10 @@ static int flow_offload_fill_route(struct flow_offload *flow, ETH_ALEN); flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex; + dst_release(dst); break; case FLOW_OFFLOAD_XMIT_XFRM: case FLOW_OFFLOAD_XMIT_NEIGH: - if (!dst_hold_safe(route->tuple[dir].dst)) - return -1; - flow_tuple->dst_cache = dst; flow_tuple->dst_cookie = flow_offload_dst_cookie(flow_tuple); break; @@ -148,27 +156,12 @@ static void nft_flow_dst_release(struct flow_offload *flow, dst_release(flow->tuplehash[dir].tuple.dst_cache); } -int flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route) +void flow_offload_route_init(struct flow_offload *flow, + struct nf_flow_route *route) { - int err; - - err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); - if (err < 0) - return err; - - err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); - if (err < 0) - goto err_route_reply; - + flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); + flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); flow->type = NF_FLOW_OFFLOAD_ROUTE; - - return 0; - -err_route_reply: - nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); - - return err; } EXPORT_SYMBOL_GPL(flow_offload_route_init); @@ -314,12 +307,12 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, - struct flow_offload *flow) + struct flow_offload *flow, bool force) { u32 timeout; timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); - if (timeout - READ_ONCE(flow->timeout) > HZ) + if (force || timeout - READ_ONCE(flow->timeout) > HZ) WRITE_ONCE(flow->timeout, timeout); else return; @@ -416,11 +409,18 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } +static bool nf_flow_custom_gc(struct nf_flowtable *flow_table, + const struct flow_offload *flow) +{ + return flow_table->type->gc && flow_table->type->gc(flow); +} + static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || - nf_ct_is_dying(flow->ct)) + nf_ct_is_dying(flow->ct) || + nf_flow_custom_gc(flow_table, flow)) flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 0ccabf3fa6aa..9505f9d188ff 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -39,7 +39,7 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, } static int nf_flow_rule_route_inet(struct net *net, - const struct flow_offload *flow, + struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index b350fe9d00b0..6feaac9ab05c 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -384,7 +384,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; - flow_offload_refresh(flow_table, flow); + flow_offload_refresh(flow_table, flow, false); nf_flow_encap_pop(skb, tuplehash); thoff -= offset; @@ -646,7 +646,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; - flow_offload_refresh(flow_table, flow); + flow_offload_refresh(flow_table, flow, false); nf_flow_encap_pop(skb, tuplehash); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 4d9b99abe37d..1c26f03fc661 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -679,7 +679,7 @@ nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow, return 0; } -int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { @@ -704,7 +704,7 @@ int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, } EXPORT_SYMBOL_GPL(nf_flow_rule_route_ipv4); -int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { @@ -735,7 +735,7 @@ nf_flow_offload_rule_alloc(struct net *net, { const struct nf_flowtable *flowtable = offload->flowtable; const struct flow_offload_tuple *tuple, *other_tuple; - const struct flow_offload *flow = offload->flow; + struct flow_offload *flow = offload->flow; struct dst_entry *other_dst = NULL; struct nf_flow_rule *flow_rule; int err = -ENOMEM; @@ -895,8 +895,9 @@ static int flow_offload_rule_add(struct flow_offload_work *offload, ok_count += flow_offload_tuple_add(offload, flow_rule[0], FLOW_OFFLOAD_DIR_ORIGINAL); - ok_count += flow_offload_tuple_add(offload, flow_rule[1], - FLOW_OFFLOAD_DIR_REPLY); + if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags)) + ok_count += flow_offload_tuple_add(offload, flow_rule[1], + FLOW_OFFLOAD_DIR_REPLY); if (ok_count == 0) return -ENOENT; @@ -926,7 +927,8 @@ static void flow_offload_work_del(struct flow_offload_work *offload) { clear_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL); - flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); + if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags)) + flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); set_bit(NF_FLOW_HW_DEAD, &offload->flow->flags); } @@ -946,7 +948,9 @@ static void flow_offload_work_stats(struct flow_offload_work *offload) u64 lastused; flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_ORIGINAL, &stats[0]); - flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY, &stats[1]); + if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags)) + flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY, + &stats[1]); lastused = max_t(u64, stats[0].lastused, stats[1].lastused); offload->flow->timeout = max_t(u64, offload->flow->timeout, diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 8a29290149bd..be93a02497d6 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -193,11 +193,12 @@ void nf_logger_put(int pf, enum nf_log_type type) return; } - BUG_ON(loggers[pf][type] == NULL); - rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); - module_put(logger->me); + if (!logger) + WARN_ON_ONCE(1); + else + module_put(logger->me); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_logger_put); diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index cb894f0d63e9..58402226045e 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -111,7 +111,8 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, - const struct nf_loginfo *loginfo, const char *prefix) + const struct nf_loginfo *loginfo, const char *prefix, + struct net *net) { const struct net_device *physoutdev __maybe_unused; const struct net_device *physindev __maybe_unused; @@ -121,7 +122,7 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf, in ? in->name : "", out ? out->name : ""); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - physindev = nf_bridge_get_physindev(skb); + physindev = nf_bridge_get_physindev(skb, net); if (physindev && in != physindev) nf_log_buf_add(m, "PHYSIN=%s ", physindev->name); physoutdev = nf_bridge_get_physoutdev(skb); @@ -148,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, - prefix); + prefix, net); dump_arp_packet(m, loginfo, skb, skb_network_offset(skb)); nf_log_buf_close(m); @@ -322,7 +323,7 @@ dump_ipv4_packet(struct net *net, struct nf_log_buf *m, /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ nf_log_buf_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", - ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, + iph_totlen(skb, ih), ih->tos & IPTOS_TOS_MASK, ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); /* Max length: 6 "CE DF MF " */ @@ -845,7 +846,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, - out, loginfo, prefix); + out, loginfo, prefix, net); if (in) dump_mac_header(m, loginfo, skb); @@ -880,7 +881,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, - loginfo, prefix); + loginfo, prefix, net); if (in) dump_mac_header(m, loginfo, skb); @@ -916,7 +917,7 @@ static void nf_log_unknown_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, - prefix); + prefix, net); dump_mac_header(m, loginfo, skb); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 63d1516816b1..e2f334f70281 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -82,11 +82,9 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) const struct sk_buff *skb = entry->skb; - struct nf_bridge_info *nf_bridge; - nf_bridge = nf_bridge_info_get(skb); - if (nf_bridge) { - entry->physin = nf_bridge_get_physindev(skb); + if (nf_bridge_info_exists(skb)) { + entry->physin = nf_bridge_get_physindev(skb, entry->state.net); entry->physout = nf_bridge_get_physoutdev(skb); } else { entry->physin = NULL; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 05fa5141af51..e21ec3ad8093 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -24,6 +24,7 @@ #include <net/sock.h> #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) +#define NFT_SET_MAX_ANONLEN 16 unsigned int nf_tables_net_id __read_mostly; @@ -685,15 +686,16 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; } -static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, - struct nft_flowtable *flowtable) +static struct nft_trans * +nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, + struct nft_flowtable *flowtable) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_flowtable)); if (trans == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); if (msg_type == NFT_MSG_NEWFLOWTABLE) nft_activate_next(ctx->net, flowtable); @@ -702,22 +704,22 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, nft_trans_flowtable(trans) = flowtable; nft_trans_commit_list_add_tail(ctx->net, trans); - return 0; + return trans; } static int nft_delflowtable(struct nft_ctx *ctx, struct nft_flowtable *flowtable) { - int err; + struct nft_trans *trans; - err = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); - if (err < 0) - return err; + trans = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); + if (IS_ERR(trans)) + return PTR_ERR(trans); nft_deactivate_next(ctx->net, flowtable); nft_use_dec(&ctx->table->use); - return err; + return 0; } static void __nft_reg_track_clobber(struct nft_regs_track *track, u8 dreg) @@ -1244,6 +1246,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return 0; err_register_hooks: + ctx->table->flags |= NFT_TABLE_F_DORMANT; nft_trans_destroy(trans); return ret; } @@ -2056,7 +2059,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, struct nft_hook *hook; int err; - hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); + hook = kzalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); if (!hook) { err = -ENOMEM; goto err_hook_alloc; @@ -2457,19 +2460,15 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, RCU_INIT_POINTER(chain->blob_gen_0, blob); RCU_INIT_POINTER(chain->blob_gen_1, blob); - err = nf_tables_register_hook(net, table, chain); - if (err < 0) - goto err_destroy_chain; - if (!nft_use_inc(&table->use)) { err = -EMFILE; - goto err_use; + goto err_destroy_chain; } trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); - goto err_unregister_hook; + goto err_trans; } nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; @@ -2477,17 +2476,22 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, nft_trans_chain_policy(trans) = policy; err = nft_chain_add(table, chain); - if (err < 0) { - nft_trans_destroy(trans); - goto err_unregister_hook; - } + if (err < 0) + goto err_chain_add; + + /* This must be LAST to ensure no packets are walking over this chain. */ + err = nf_tables_register_hook(net, table, chain); + if (err < 0) + goto err_register_hook; return 0; -err_unregister_hook: +err_register_hook: + nft_chain_del(chain); +err_chain_add: + nft_trans_destroy(trans); +err_trans: nft_use_dec_restore(&table->use); -err_use: - nf_tables_unregister_hook(net, table, chain); err_destroy_chain: nf_tables_chain_destroy(ctx); @@ -4127,6 +4131,9 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, if (p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; + if (strnlen(name, NFT_SET_MAX_ANONLEN) >= NFT_SET_MAX_ANONLEN) + return -EINVAL; + inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL); if (inuse == NULL) return -ENOMEM; @@ -4523,8 +4530,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { + u32 num_regs = 0, key_num_regs = 0; struct nlattr *attr; - u32 num_regs = 0; int rem, err, i; nla_for_each_nested(attr, nla, rem) { @@ -4539,6 +4546,10 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, for (i = 0; i < desc->field_count; i++) num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32)); + if (key_num_regs != num_regs) + return -EINVAL; + if (num_regs > NFT_REG32_COUNT) return -E2BIG; @@ -4753,16 +4764,28 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, } desc.policy = NFT_SET_POL_PERFORMANCE; - if (nla[NFTA_SET_POLICY] != NULL) + if (nla[NFTA_SET_POLICY] != NULL) { desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY])); + switch (desc.policy) { + case NFT_SET_POL_PERFORMANCE: + case NFT_SET_POL_MEMORY: + break; + default: + return -EOPNOTSUPP; + } + } if (nla[NFTA_SET_DESC] != NULL) { err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]); if (err < 0) return err; - if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT)) + if (desc.field_count > 1) { + if (!(flags & NFT_SET_CONCAT)) + return -EINVAL; + } else if (flags & NFT_SET_CONCAT) { return -EINVAL; + } } else if (flags & NFT_SET_CONCAT) { return -EINVAL; } @@ -5406,7 +5429,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); struct nft_set_dump_args *args; - if (nft_set_elem_expired(ext)) + if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext)) return 0; args = container_of(iter, struct nft_set_dump_args, iter); @@ -6152,7 +6175,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_is_active(net, ext)) + if (!nft_is_active_next(net, ext)) continue; kfree(elem->priv); @@ -7109,11 +7132,15 @@ nla_put_failure: return -1; } -static const struct nft_object_type *__nft_obj_type_get(u32 objtype) +static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) { const struct nft_object_type *type; list_for_each_entry(type, &nf_tables_objects, list) { + if (type->family != NFPROTO_UNSPEC && + type->family != family) + continue; + if (objtype == type->type) return type; } @@ -7121,11 +7148,11 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype) } static const struct nft_object_type * -nft_obj_type_get(struct net *net, u32 objtype) +nft_obj_type_get(struct net *net, u32 objtype, u8 family) { const struct nft_object_type *type; - type = __nft_obj_type_get(objtype); + type = __nft_obj_type_get(objtype, family); if (type != NULL && try_module_get(type->owner)) return type; @@ -7218,7 +7245,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - type = __nft_obj_type_get(objtype); + type = __nft_obj_type_get(objtype, family); if (WARN_ON_ONCE(!type)) return -ENOENT; @@ -7232,7 +7259,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, if (!nft_use_inc(&table->use)) return -EMFILE; - type = nft_obj_type_get(net, objtype); + type = nft_obj_type_get(net, objtype, family); if (IS_ERR(type)) { err = PTR_ERR(type); goto err_type; @@ -7913,7 +7940,7 @@ err_unregister_net_hooks: return err; } -static void nft_flowtable_hooks_destroy(struct list_head *hook_list) +static void nft_hooks_destroy(struct list_head *hook_list) { struct nft_hook *hook, *next; @@ -8006,9 +8033,9 @@ static int nf_tables_newflowtable(struct sk_buff *skb, u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; struct nft_flowtable *flowtable; - struct nft_hook *hook, *next; struct net *net = info->net; struct nft_table *table; + struct nft_trans *trans; struct nft_ctx ctx; int err; @@ -8088,34 +8115,34 @@ static int nf_tables_newflowtable(struct sk_buff *skb, err = nft_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], &flowtable_hook, flowtable, true); if (err < 0) - goto err4; + goto err_flowtable_parse_hooks; list_splice(&flowtable_hook.list, &flowtable->hook_list); flowtable->data.priority = flowtable_hook.priority; flowtable->hooknum = flowtable_hook.num; + trans = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + goto err_flowtable_trans; + } + + /* This must be LAST to ensure no packets are walking over this flowtable. */ err = nft_register_flowtable_net_hooks(ctx.net, table, &flowtable->hook_list, flowtable); - if (err < 0) { - nft_flowtable_hooks_destroy(&flowtable->hook_list); - goto err4; - } - - err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (err < 0) - goto err5; + goto err_flowtable_hooks; list_add_tail_rcu(&flowtable->list, &table->flowtables); return 0; -err5: - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - nft_unregister_flowtable_hook(net, flowtable, hook); - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } -err4: + +err_flowtable_hooks: + nft_trans_destroy(trans); +err_flowtable_trans: + nft_hooks_destroy(&flowtable->hook_list); +err_flowtable_parse_hooks: flowtable->data.type->free(&flowtable->data); err3: module_put(type->owner); @@ -8868,7 +8895,7 @@ static void nft_commit_release(struct nft_trans *trans) break; case NFT_MSG_DELFLOWTABLE: if (nft_trans_flowtable_update(trans)) - nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; @@ -9480,7 +9507,7 @@ static void nft_set_commit_update(struct list_head *set_update_list) list_for_each_entry_safe(set, next, set_update_list, pending_update) { list_del_init(&set->pending_update); - if (!set->ops->commit) + if (!set->ops->commit || set->dead) continue; set->ops->commit(set); @@ -9825,7 +9852,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) - nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; @@ -9937,6 +9964,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } + nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: @@ -10427,16 +10455,10 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { - default: - switch (data->verdict.code & NF_VERDICT_MASK) { - case NF_ACCEPT: - case NF_DROP: - case NF_QUEUE: - break; - default: - return -EINVAL; - } - fallthrough; + case NF_ACCEPT: + case NF_DROP: + case NF_QUEUE: + break; case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: @@ -10471,6 +10493,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict.chain = chain; break; + default: + return -EINVAL; } desc->len = sizeof(data->verdict); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index cee3e4e905ec..e0c117229ee9 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -141,7 +141,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr, else { if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) return false; - ptr = skb_network_header(skb) + nft_thoff(pkt); + ptr = skb->data + nft_thoff(pkt); } ptr += priv->offset; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index c5ff699e3046..200a82a8f943 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -499,7 +499,7 @@ __build_packet_message(struct nfnl_log_net *log, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { - struct net_device *physindev; + int physinif; /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ @@ -507,10 +507,10 @@ __build_packet_message(struct nfnl_log_net *log, htonl(indev->ifindex))) goto nla_put_failure; - physindev = nf_bridge_get_physindev(skb); - if (physindev && + physinif = nf_bridge_get_physinif(skb); + if (physinif && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, - htonl(physindev->ifindex))) + htonl(physinif))) goto nla_put_failure; } #endif diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 680fe557686e..274b6f7e6bb5 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -357,9 +357,10 @@ static int nf_tables_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nft_base_chain *basechain; struct nftables_pernet *nft_net; - struct nft_table *table; struct nft_chain *chain, *nr; + struct nft_table *table; struct nft_ctx ctx = { .net = dev_net(dev), }; @@ -371,7 +372,8 @@ static int nf_tables_netdev_event(struct notifier_block *this, nft_net = nft_pernet(ctx.net); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { - if (table->family != NFPROTO_NETDEV) + if (table->family != NFPROTO_NETDEV && + table->family != NFPROTO_INET) continue; ctx.family = table->family; @@ -380,6 +382,11 @@ static int nf_tables_netdev_event(struct notifier_block *this, if (!nft_is_base_chain(chain)) continue; + basechain = nft_base_chain(chain); + if (table->family == NFPROTO_INET && + basechain->ops.hooknum != NF_INET_INGRESS) + continue; + ctx.chain = chain; nft_netdev_event(event, dev, &ctx); } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index c16172427622..e1623fbf3654 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -135,7 +135,7 @@ static void nft_target_eval_bridge(const struct nft_expr *expr, static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = { [NFTA_TARGET_NAME] = { .type = NLA_NUL_STRING }, - [NFTA_TARGET_REV] = { .type = NLA_U32 }, + [NFTA_TARGET_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_TARGET_INFO] = { .type = NLA_BINARY }, }; @@ -200,6 +200,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1] static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) { struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1]; + u32 l4proto; u32 flags; int err; @@ -212,12 +213,18 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return -EINVAL; flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS])); - if (flags & ~NFT_RULE_COMPAT_F_MASK) + if (flags & NFT_RULE_COMPAT_F_UNUSED || + flags & ~NFT_RULE_COMPAT_F_MASK) return -EINVAL; if (flags & NFT_RULE_COMPAT_F_INV) *inv = true; - *proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); + l4proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); + if (l4proto > U16_MAX) + return -EINVAL; + + *proto = l4proto; + return 0; } @@ -349,6 +356,12 @@ static int nft_target_validate(const struct nft_ctx *ctx, unsigned int hook_mask = 0; int ret; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_BRIDGE && + ctx->family != NFPROTO_ARP) + return -EOPNOTSUPP; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); @@ -412,7 +425,7 @@ static void nft_match_eval(const struct nft_expr *expr, static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = { [NFTA_MATCH_NAME] = { .type = NLA_NUL_STRING }, - [NFTA_MATCH_REV] = { .type = NLA_U32 }, + [NFTA_MATCH_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_MATCH_INFO] = { .type = NLA_BINARY }, }; @@ -592,6 +605,12 @@ static int nft_match_validate(const struct nft_ctx *ctx, unsigned int hook_mask = 0; int ret; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_BRIDGE && + ctx->family != NFPROTO_ARP) + return -EOPNOTSUPP; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); @@ -709,7 +728,7 @@ out_put: static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = { [NFTA_COMPAT_NAME] = { .type = NLA_NUL_STRING, .len = NFT_COMPAT_NAME_MAX-1 }, - [NFTA_COMPAT_REV] = { .type = NLA_U32 }, + [NFTA_COMPAT_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_COMPAT_TYPE] = { .type = NLA_U32 }, }; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 641dc21f92b4..8df7564f0611 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -484,6 +484,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, break; #endif case NFT_CT_ID: + if (tb[NFTA_CT_DIRECTION]) + return -EINVAL; + len = sizeof(u32); break; default: @@ -1231,7 +1234,31 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_EXPECT_L3PROTO]) priv->l3num = ntohs(nla_get_be16(tb[NFTA_CT_EXPECT_L3PROTO])); + switch (priv->l3num) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + if (priv->l3num != ctx->family) + return -EINVAL; + + fallthrough; + case NFPROTO_INET: + break; + default: + return -EOPNOTSUPP; + } + priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]); + switch (priv->l4proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + case IPPROTO_DCCP: + case IPPROTO_SCTP: + break; + default: + return -EOPNOTSUPP; + } + priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]); priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]); priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 8a43f6f9c90b..7a8707632a81 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -250,9 +250,14 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, break; } + if (!dst_hold_safe(this_dst)) + return -ENOENT; + nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt)); - if (!other_dst) + if (!other_dst) { + dst_release(this_dst); return -ENOENT; + } nft_default_forward_path(route, this_dst, dir); nft_default_forward_path(route, other_dst, !dir); @@ -349,8 +354,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, if (!flow) goto err_flow_alloc; - if (flow_offload_route_init(flow, &route) < 0) - goto err_flow_add; + flow_offload_route_init(flow, &route); if (tcph) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; @@ -361,12 +365,12 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, if (ret < 0) goto err_flow_add; - dst_release(route.tuple[!dir].dst); return; err_flow_add: flow_offload_free(flow); err_flow_alloc: + dst_release(route.tuple[dir].dst); dst_release(route.tuple[!dir].dst); err_flow_route: clear_bit(IPS_OFFLOAD_BIT, &ct->status); @@ -380,6 +384,11 @@ static int nft_flow_offload_validate(const struct nft_ctx *ctx, { unsigned int hook_mask = (1 << NF_INET_FORWARD); + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, hook_mask); } diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 5f59dbab3e93..55fcf0280c5c 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -78,7 +78,7 @@ static int nft_immediate_init(const struct nft_ctx *ctx, case NFT_GOTO: err = nf_tables_bind_chain(ctx, chain); if (err < 0) - return err; + goto err1; break; default: break; diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 981addb2d051..36ded7d43262 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -58,16 +58,19 @@ static inline bool nft_limit_eval(struct nft_limit_priv *priv, u64 cost) static int nft_limit_init(struct nft_limit_priv *priv, const struct nlattr * const tb[], bool pkts) { - u64 unit, tokens; + u64 unit, tokens, rate_with_burst; + bool invert = false; if (tb[NFTA_LIMIT_RATE] == NULL || tb[NFTA_LIMIT_UNIT] == NULL) return -EINVAL; priv->rate = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_RATE])); + if (priv->rate == 0) + return -EINVAL; + unit = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_UNIT])); - priv->nsecs = unit * NSEC_PER_SEC; - if (priv->rate == 0 || priv->nsecs < unit) + if (check_mul_overflow(unit, NSEC_PER_SEC, &priv->nsecs)) return -EOVERFLOW; if (tb[NFTA_LIMIT_BURST]) @@ -76,18 +79,35 @@ static int nft_limit_init(struct nft_limit_priv *priv, if (pkts && priv->burst == 0) priv->burst = NFT_LIMIT_PKT_BURST_DEFAULT; - if (priv->rate + priv->burst < priv->rate) + if (check_add_overflow(priv->rate, priv->burst, &rate_with_burst)) return -EOVERFLOW; if (pkts) { - tokens = div64_u64(priv->nsecs, priv->rate) * priv->burst; + u64 tmp = div64_u64(priv->nsecs, priv->rate); + + if (check_mul_overflow(tmp, priv->burst, &tokens)) + return -EOVERFLOW; } else { + u64 tmp; + /* The token bucket size limits the number of tokens can be * accumulated. tokens_max specifies the bucket size. * tokens_max = unit * (rate + burst) / rate. */ - tokens = div64_u64(priv->nsecs * (priv->rate + priv->burst), - priv->rate); + if (check_mul_overflow(priv->nsecs, rate_with_burst, &tmp)) + return -EOVERFLOW; + + tokens = div64_u64(tmp, priv->rate); + } + + if (tb[NFTA_LIMIT_FLAGS]) { + u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS])); + + if (flags & ~NFT_LIMIT_F_INV) + return -EOPNOTSUPP; + + if (flags & NFT_LIMIT_F_INV) + invert = true; } priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT); @@ -96,13 +116,7 @@ static int nft_limit_init(struct nft_limit_priv *priv, priv->limit->tokens = tokens; priv->tokens_max = priv->limit->tokens; - - if (tb[NFTA_LIMIT_FLAGS]) { - u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS])); - - if (flags & NFT_LIMIT_F_INV) - priv->invert = true; - } + priv->invert = invert; priv->limit->last = ktime_get_ns(); spin_lock_init(&priv->limit->lock); diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 353c090f8891..ba7bcce724ef 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -142,6 +142,11 @@ static int nft_nat_validate(const struct nft_ctx *ctx, struct nft_nat *priv = nft_expr_priv(expr); int err; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); if (err < 0) return err; diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index 71931ec91721..7d21e16499bf 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -166,6 +166,11 @@ static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *exp const struct nft_rt *priv = nft_expr_priv(expr); unsigned int hooks; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + switch (priv->key) { case NFT_RT_NEXTHOP4: case NFT_RT_NEXTHOP6: diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 4e1cc31729b8..e1969209b3ab 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -342,9 +342,6 @@ #include "nft_set_pipapo_avx2.h" #include "nft_set_pipapo.h" -/* Current working bitmap index, toggled between field matches */ -static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index); - /** * pipapo_refill() - For each set bit, set bits from selected mapping table item * @map: Bitmap to be scanned for set bits @@ -412,6 +409,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_scratch *scratch; unsigned long *res_map, *fill_map; u8 genmask = nft_genmask_cur(net); const u8 *rp = (const u8 *)key; @@ -422,15 +420,17 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, local_bh_disable(); - map_index = raw_cpu_read(nft_pipapo_scratch_index); - m = rcu_dereference(priv->match); if (unlikely(!m || !*raw_cpu_ptr(m->scratch))) goto out; - res_map = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0); - fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max); + scratch = *raw_cpu_ptr(m->scratch); + + map_index = scratch->map_index; + + res_map = scratch->map + (map_index ? m->bsize_max : 0); + fill_map = scratch->map + (map_index ? 0 : m->bsize_max); memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); @@ -460,7 +460,7 @@ next_match: b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt, last); if (b < 0) { - raw_cpu_write(nft_pipapo_scratch_index, map_index); + scratch->map_index = map_index; local_bh_enable(); return false; @@ -477,7 +477,7 @@ next_match: * current inactive bitmap is clean and can be reused as * *next* bitmap (not initial) for the next packet. */ - raw_cpu_write(nft_pipapo_scratch_index, map_index); + scratch->map_index = map_index; local_bh_enable(); return true; @@ -1102,6 +1102,25 @@ static void pipapo_map(struct nft_pipapo_match *m, } /** + * pipapo_free_scratch() - Free per-CPU map at original (not aligned) address + * @m: Matching data + * @cpu: CPU number + */ +static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int cpu) +{ + struct nft_pipapo_scratch *s; + void *mem; + + s = *per_cpu_ptr(m->scratch, cpu); + if (!s) + return; + + mem = s; + mem -= s->align_off; + kfree(mem); +} + +/** * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results * @clone: Copy of matching data with pending insertions and deletions * @bsize_max: Maximum bucket size, scratch maps cover two buckets @@ -1114,12 +1133,13 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, int i; for_each_possible_cpu(i) { - unsigned long *scratch; + struct nft_pipapo_scratch *scratch; #ifdef NFT_PIPAPO_ALIGN - unsigned long *scratch_aligned; + void *scratch_aligned; + u32 align_off; #endif - - scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2 + + scratch = kzalloc_node(struct_size(scratch, map, + bsize_max * 2) + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL, cpu_to_node(i)); if (!scratch) { @@ -1133,14 +1153,25 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, return -ENOMEM; } - kfree(*per_cpu_ptr(clone->scratch, i)); - - *per_cpu_ptr(clone->scratch, i) = scratch; + pipapo_free_scratch(clone, i); #ifdef NFT_PIPAPO_ALIGN - scratch_aligned = NFT_PIPAPO_LT_ALIGN(scratch); - *per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned; + /* Align &scratch->map (not the struct itself): the extra + * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node() + * above guarantee we can waste up to those bytes in order + * to align the map field regardless of its offset within + * the struct. + */ + BUILD_BUG_ON(offsetof(struct nft_pipapo_scratch, map) > NFT_PIPAPO_ALIGN_HEADROOM); + + scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map); + scratch_aligned -= offsetof(struct nft_pipapo_scratch, map); + align_off = scratch_aligned - (void *)scratch; + + scratch = scratch_aligned; + scratch->align_off = align_off; #endif + *per_cpu_ptr(clone->scratch, i) = scratch; } return 0; @@ -1294,11 +1325,6 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) if (!new->scratch) goto out_scratch; -#ifdef NFT_PIPAPO_ALIGN - new->scratch_aligned = alloc_percpu(*new->scratch_aligned); - if (!new->scratch_aligned) - goto out_scratch; -#endif for_each_possible_cpu(i) *per_cpu_ptr(new->scratch, i) = NULL; @@ -1350,10 +1376,7 @@ out_lt: } out_scratch_realloc: for_each_possible_cpu(i) - kfree(*per_cpu_ptr(new->scratch, i)); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(new->scratch_aligned); -#endif + pipapo_free_scratch(new, i); out_scratch: free_percpu(new->scratch); kfree(new); @@ -1638,13 +1661,9 @@ static void pipapo_free_match(struct nft_pipapo_match *m) int i; for_each_possible_cpu(i) - kfree(*per_cpu_ptr(m->scratch, i)); + pipapo_free_scratch(m, i); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif free_percpu(m->scratch); - pipapo_free_fields(m); kfree(m); @@ -2132,7 +2151,7 @@ static int nft_pipapo_init(const struct nft_set *set, m->field_count = field_count; m->bsize_max = 0; - m->scratch = alloc_percpu(unsigned long *); + m->scratch = alloc_percpu(struct nft_pipapo_scratch *); if (!m->scratch) { err = -ENOMEM; goto out_scratch; @@ -2140,16 +2159,6 @@ static int nft_pipapo_init(const struct nft_set *set, for_each_possible_cpu(i) *per_cpu_ptr(m->scratch, i) = NULL; -#ifdef NFT_PIPAPO_ALIGN - m->scratch_aligned = alloc_percpu(unsigned long *); - if (!m->scratch_aligned) { - err = -ENOMEM; - goto out_free; - } - for_each_possible_cpu(i) - *per_cpu_ptr(m->scratch_aligned, i) = NULL; -#endif - rcu_head_init(&m->rcu); nft_pipapo_for_each_field(f, i, m) { @@ -2180,9 +2189,6 @@ static int nft_pipapo_init(const struct nft_set *set, return 0; out_free: -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif free_percpu(m->scratch); out_scratch: kfree(m); @@ -2236,11 +2242,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, nft_set_pipapo_match_destroy(ctx, set, m); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(m->scratch, cpu)); + pipapo_free_scratch(m, cpu); free_percpu(m->scratch); pipapo_free_fields(m); kfree(m); @@ -2253,11 +2256,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (priv->dirty) nft_set_pipapo_match_destroy(ctx, set, m); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(priv->clone->scratch_aligned); -#endif for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(priv->clone->scratch, cpu)); + pipapo_free_scratch(priv->clone, cpu); free_percpu(priv->clone->scratch); pipapo_free_fields(priv->clone); diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 25a75591583e..30a3d092cd84 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -131,20 +131,28 @@ struct nft_pipapo_field { }; /** + * struct nft_pipapo_scratch - percpu data used for lookup and matching + * @map_index: Current working bitmap index, toggled between field matches + * @align_off: Offset to get the originally allocated address + * @map: store partial matching results during lookup + */ +struct nft_pipapo_scratch { + u8 map_index; + u32 align_off; + unsigned long map[]; +}; + +/** * struct nft_pipapo_match - Data used for lookup and matching * @field_count Amount of fields in set * @scratch: Preallocated per-CPU maps for partial matching results - * @scratch_aligned: Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes * @bsize_max: Maximum lookup table bucket size of all fields, in longs * @rcu Matching data is swapped on commits * @f: Fields, with lookup and mapping tables */ struct nft_pipapo_match { int field_count; -#ifdef NFT_PIPAPO_ALIGN - unsigned long * __percpu *scratch_aligned; -#endif - unsigned long * __percpu *scratch; + struct nft_pipapo_scratch * __percpu *scratch; size_t bsize_max; struct rcu_head rcu; struct nft_pipapo_field f[]; diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 52e0d026d30a..a3a8ddca9918 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -57,7 +57,7 @@ /* Jump to label if @reg is zero */ #define NFT_PIPAPO_AVX2_NOMATCH_GOTO(reg, label) \ - asm_volatile_goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \ + asm goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \ "je %l[" #label "]" : : : : label) /* Store 256 bits from YMM register into memory. Contrary to bucket load @@ -71,9 +71,6 @@ #define NFT_PIPAPO_AVX2_ZERO(reg) \ asm volatile("vpxor %ymm" #reg ", %ymm" #reg ", %ymm" #reg) -/* Current working bitmap index, toggled between field matches */ -static DEFINE_PER_CPU(bool, nft_pipapo_avx2_scratch_index); - /** * nft_pipapo_avx2_prepare() - Prepare before main algorithm body * @@ -1120,11 +1117,12 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); - unsigned long *res, *fill, *scratch; + struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); const u8 *rp = (const u8 *)key; struct nft_pipapo_match *m; struct nft_pipapo_field *f; + unsigned long *res, *fill; bool map_index; int i, ret = 0; @@ -1141,15 +1139,16 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, */ kernel_fpu_begin_mask(0); - scratch = *raw_cpu_ptr(m->scratch_aligned); + scratch = *raw_cpu_ptr(m->scratch); if (unlikely(!scratch)) { kernel_fpu_end(); return false; } - map_index = raw_cpu_read(nft_pipapo_avx2_scratch_index); - res = scratch + (map_index ? m->bsize_max : 0); - fill = scratch + (map_index ? 0 : m->bsize_max); + map_index = scratch->map_index; + + res = scratch->map + (map_index ? m->bsize_max : 0); + fill = scratch->map + (map_index ? 0 : m->bsize_max); /* Starting map doesn't need to be set for this implementation */ @@ -1221,7 +1220,7 @@ next_match: out: if (i % 2) - raw_cpu_write(nft_pipapo_avx2_scratch_index, !map_index); + scratch->map_index = !map_index; kernel_fpu_end(); return ret >= 0; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index e34662f4a71e..5bf5572e945c 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -235,7 +235,7 @@ static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, static const struct nft_rbtree_elem * nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe, u8 genmask) + struct nft_rbtree_elem *rbe) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); @@ -254,7 +254,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev) && - nft_set_elem_active(&rbe_prev->ext, genmask)) + nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY)) break; prev = rb_prev(prev); @@ -365,7 +365,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, nft_set_elem_active(&rbe->ext, cur_genmask)) { const struct nft_rbtree_elem *removed_end; - removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask); + removed_end = nft_rbtree_gc_elem(set, priv, rbe); if (IS_ERR(removed_end)) return PTR_ERR(removed_end); diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 777561b71fcb..f28324fd8d71 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -242,6 +242,11 @@ static int nft_socket_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 6cf9a04fbfe2..a450f28a5ef6 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -186,7 +186,6 @@ static int nft_synproxy_do_init(const struct nft_ctx *ctx, break; #endif case NFPROTO_INET: - case NFPROTO_BRIDGE: err = nf_synproxy_ipv4_init(snet, ctx->net); if (err) goto nf_ct_failure; @@ -219,7 +218,6 @@ static void nft_synproxy_do_destroy(const struct nft_ctx *ctx) break; #endif case NFPROTO_INET: - case NFPROTO_BRIDGE: nf_synproxy_ipv4_fini(snet, ctx->net); nf_synproxy_ipv6_fini(snet, ctx->net); break; @@ -253,6 +251,11 @@ static int nft_synproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD)); } diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 62da25ad264b..adb50c39572e 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -316,6 +316,11 @@ static int nft_tproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING); } diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 983ade4be3b3..efb505445eac 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -713,6 +713,7 @@ static const struct nft_object_ops nft_tunnel_obj_ops = { static struct nft_object_type nft_tunnel_obj_type __read_mostly = { .type = NFT_OBJECT_TUNNEL, + .family = NFPROTO_NETDEV, .ops = &nft_tunnel_obj_ops, .maxattr = NFTA_TUNNEL_KEY_MAX, .policy = nft_tunnel_key_policy, diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c index 1c5343c936a8..30259846c352 100644 --- a/net/netfilter/nft_xfrm.c +++ b/net/netfilter/nft_xfrm.c @@ -235,6 +235,11 @@ static int nft_xfrm_validate(const struct nft_ctx *ctx, const struct nft_expr *e const struct nft_xfrm *priv = nft_expr_priv(expr); unsigned int hooks; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + switch (priv->dir) { case XFRM_POLICY_IN: hooks = (1 << NF_INET_FORWARD) | diff --git a/net/netfilter/xt_length.c b/net/netfilter/xt_length.c index 9fbfad13176f..ca730cedb5d4 100644 --- a/net/netfilter/xt_length.c +++ b/net/netfilter/xt_length.c @@ -21,7 +21,7 @@ static bool length_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_length_info *info = par->matchinfo; - u_int16_t pktlen = ntohs(ip_hdr(skb)->tot_len); + u32 pktlen = skb_ip_totlen(skb); return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; } diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index ec6ed6fda96c..343e65f377d4 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -59,7 +59,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par) (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED))) return false; - physdev = nf_bridge_get_physindev(skb); + physdev = nf_bridge_get_physindev(skb, xt_net(par)); indev = physdev ? physdev->name : NULL; if ((info->bitmask & XT_PHYSDEV_OP_ISIN && diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index f1d5b8465217..a07c2216d28b 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -54,6 +54,28 @@ static const struct nla_policy calipso_genl_policy[NLBL_CALIPSO_A_MAX + 1] = { [NLBL_CALIPSO_A_MTYPE] = { .type = NLA_U32 }, }; +static const struct netlbl_calipso_ops *calipso_ops; + +/** + * netlbl_calipso_ops_register - Register the CALIPSO operations + * @ops: ops to register + * + * Description: + * Register the CALIPSO packet engine operations. + * + */ +const struct netlbl_calipso_ops * +netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops) +{ + return xchg(&calipso_ops, ops); +} +EXPORT_SYMBOL(netlbl_calipso_ops_register); + +static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) +{ + return READ_ONCE(calipso_ops); +} + /* NetLabel Command Handlers */ /** @@ -96,15 +118,18 @@ static int netlbl_calipso_add_pass(struct genl_info *info, * */ static int netlbl_calipso_add(struct sk_buff *skb, struct genl_info *info) - { int ret_val = -EINVAL; struct netlbl_audit audit_info; + const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (!info->attrs[NLBL_CALIPSO_A_DOI] || !info->attrs[NLBL_CALIPSO_A_MTYPE]) return -EINVAL; + if (!ops) + return -EOPNOTSUPP; + netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CALIPSO_A_MTYPE])) { case CALIPSO_MAP_PASS: @@ -363,28 +388,6 @@ int __init netlbl_calipso_genl_init(void) return genl_register_family(&netlbl_calipso_gnl_family); } -static const struct netlbl_calipso_ops *calipso_ops; - -/** - * netlbl_calipso_ops_register - Register the CALIPSO operations - * @ops: ops to register - * - * Description: - * Register the CALIPSO packet engine operations. - * - */ -const struct netlbl_calipso_ops * -netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops) -{ - return xchg(&calipso_ops, ops); -} -EXPORT_SYMBOL(netlbl_calipso_ops_register); - -static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) -{ - return READ_ONCE(calipso_ops); -} - /** * calipso_doi_add - Add a new DOI to the CALIPSO protocol engine * @doi_def: the DOI structure diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index cb833302270a..6857a4965fe8 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -374,7 +374,7 @@ static void netlink_skb_destructor(struct sk_buff *skb) if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) - vfree(skb->head); + vfree_atomic(skb->head); skb->head = NULL; } diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 1dac28136e6a..18be13fb9b75 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -145,6 +145,13 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device, static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { + /* Since using nfc_llcp_local may result in usage of nfc_dev, whenever + * we hold a reference to local, we also need to hold a reference to + * the device to avoid UAF. + */ + if (!nfc_get_device(local->dev->idx)) + return NULL; + kref_get(&local->ref); return local; @@ -177,10 +184,18 @@ static void local_release(struct kref *ref) int nfc_llcp_local_put(struct nfc_llcp_local *local) { + struct nfc_dev *dev; + int ret; + if (local == NULL) return 0; - return kref_put(&local->ref, local_release); + dev = local->dev; + + ret = kref_put(&local->ref, local_release); + nfc_put_device(dev); + + return ret; } static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, @@ -959,8 +974,17 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, } new_sock = nfc_llcp_sock(new_sk); - new_sock->dev = local->dev; + new_sock->local = nfc_llcp_local_get(local); + if (!new_sock->local) { + reason = LLCP_DM_REJ; + sock_put(&new_sock->sk); + release_sock(&sock->sk); + sock_put(&sock->sk); + goto fail; + } + + new_sock->dev = local->dev; new_sock->rw = sock->rw; new_sock->miux = sock->miux; new_sock->nfc_protocol = sock->nfc_protocol; @@ -1597,7 +1621,16 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) if (local == NULL) return -ENOMEM; - local->dev = ndev; + /* As we are going to initialize local's refcount, we need to get the + * nfc_dev to avoid UAF, otherwise there is no point in continuing. + * See nfc_llcp_local_get(). + */ + local->dev = nfc_get_device(ndev->idx); + if (!local->dev) { + kfree(local); + return -ENODEV; + } + INIT_LIST_HEAD(&local->list); kref_init(&local->ref); mutex_init(&local->sdp_lock); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 7535afd1537e..b5071a2f597d 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1207,6 +1207,10 @@ void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); nci_hci_deallocate(ndev); + + /* drop partial rx data packet if present */ + if (ndev->rx_data_reassembly) + kfree_skb(ndev->rx_data_reassembly); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c8eaf4234b2e..0591cfb289d5 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1252,7 +1252,7 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, if (err) return err; - nf_conn_act_ct_ext_add(ct); + nf_conn_act_ct_ext_add(skb, ct, ctinfo); } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ead5418c126e..e3c85ceb1f0a 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -47,6 +47,7 @@ struct ovs_len_tbl { #define OVS_ATTR_NESTED -1 #define OVS_ATTR_VARIABLE -2 +#define OVS_COPY_ACTIONS_MAX_DEPTH 16 static bool actions_may_change_flow(const struct nlattr *actions) { @@ -2543,13 +2544,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log); + u32 mpls_label_count, bool log, + u32 depth); static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; @@ -2600,7 +2603,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, return err; err = __ovs_nla_copy_actions(net, actions, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2615,7 +2619,8 @@ static int validate_and_copy_dec_ttl(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; int start, action_start, err, rem; @@ -2658,7 +2663,8 @@ static int validate_and_copy_dec_ttl(struct net *net, return action_start; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, - vlan_tci, mpls_label_count, log); + vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2672,7 +2678,8 @@ static int validate_and_copy_clone(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { int start, err; u32 exec; @@ -2692,7 +2699,8 @@ static int validate_and_copy_clone(struct net *net, return err; err = __ovs_nla_copy_actions(net, attr, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3061,7 +3069,7 @@ static int validate_and_copy_check_pkt_len(struct net *net, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, - bool log, bool last) + bool log, bool last, u32 depth) { const struct nlattr *acts_if_greater, *acts_if_lesser_eq; struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1]; @@ -3109,7 +3117,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3122,7 +3131,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3150,12 +3160,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { u8 mac_proto = ovs_key_mac_proto(key); const struct nlattr *a; int rem, err; + if (depth > OVS_COPY_ACTIONS_MAX_DEPTH) + return -EOVERFLOW; + nla_for_each_nested(a, attr, rem) { /* Expected argument lengths, (u32)-1 for variable length. */ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = { @@ -3350,7 +3364,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_sample(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3421,7 +3435,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_clone(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3435,7 +3449,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, + depth); if (err) return err; skip_copy = true; @@ -3445,7 +3460,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_DEC_TTL: err = validate_and_copy_dec_ttl(net, a, key, sfa, eth_type, vlan_tci, - mpls_label_count, log); + mpls_label_count, log, + depth); if (err) return err; skip_copy = true; @@ -3485,7 +3501,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, (*sfa)->orig_len = nla_len(attr); err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type, - key->eth.vlan.tci, mpls_label_count, log); + key->eth.vlan.tci, mpls_label_count, log, + 0); if (err) ovs_nla_free_flow_actions(*sfa); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 51882f07ef70..c3117350f5fb 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3284,7 +3284,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[sizeof(uaddr->sa_data) + 1]; + char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality @@ -3295,8 +3295,8 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ - memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); - name[sizeof(uaddr->sa_data)] = 0; + memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); + name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } @@ -3566,11 +3566,11 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; - memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); + memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) - strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); + strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index ff5f49ab236e..39a6c5713d0b 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -35,10 +35,10 @@ static int pn_ioctl(struct sock *sk, int cmd, unsigned long arg) switch (cmd) { case SIOCINQ: - lock_sock(sk); + spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); answ = skb ? skb->len : 0; - release_sock(sk); + spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(answ, (int __user *)arg); case SIOCPNADDRESOURCE: diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 83ea13a50690..607f54c23647 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -917,6 +917,37 @@ static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len) return 0; } +static unsigned int pep_first_packet_length(struct sock *sk) +{ + struct pep_sock *pn = pep_sk(sk); + struct sk_buff_head *q; + struct sk_buff *skb; + unsigned int len = 0; + bool found = false; + + if (sock_flag(sk, SOCK_URGINLINE)) { + q = &pn->ctrlreq_queue; + spin_lock_bh(&q->lock); + skb = skb_peek(q); + if (skb) { + len = skb->len; + found = true; + } + spin_unlock_bh(&q->lock); + } + + if (likely(!found)) { + q = &sk->sk_receive_queue; + spin_lock_bh(&q->lock); + skb = skb_peek(q); + if (skb) + len = skb->len; + spin_unlock_bh(&q->lock); + } + + return len; +} + static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct pep_sock *pn = pep_sk(sk); @@ -930,15 +961,7 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) break; } - lock_sock(sk); - if (sock_flag(sk, SOCK_URGINLINE) && - !skb_queue_empty(&pn->ctrlreq_queue)) - answ = skb_peek(&pn->ctrlreq_queue)->len; - else if (!skb_queue_empty(&sk->sk_receive_queue)) - answ = skb_peek(&sk->sk_receive_queue)->len; - else - answ = 0; - release_sock(sk); + answ = pep_first_packet_length(sk); ret = put_user(answ, (int __user *)arg); break; diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 3e40a1ba48f7..4a13b9f7abb4 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -569,7 +569,9 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from, if (!node) return -ENOENT; - return server_del(node, port, true); + server_del(node, port, true); + + return 0; } static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 3ff6995244e5..d107f7605db4 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -419,7 +419,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, sockptr_t optval, rs->rs_rx_traces = trace.rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { - if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) { + if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) { rs->rs_rx_traces = 0; return -EFAULT; } diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 2cc95c8dc4c7..f74baefd855d 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -116,6 +116,14 @@ static int rfkill_gpio_probe(struct platform_device *pdev) return -EINVAL; } + ret = gpiod_direction_output(rfkill->reset_gpio, true); + if (ret) + return ret; + + ret = gpiod_direction_output(rfkill->shutdown_gpio, true); + if (ret) + return ret; + rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev, rfkill->type, &rfkill_gpio_ops, rfkill); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 674937284b8d..29b74a569e0b 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -182,21 +182,47 @@ void rose_kill_by_neigh(struct rose_neigh *neigh) */ static void rose_kill_by_device(struct net_device *dev) { - struct sock *s; + struct sock *sk, *array[16]; + struct rose_sock *rose; + bool rescan; + int i, cnt; +start: + rescan = false; + cnt = 0; spin_lock_bh(&rose_list_lock); - sk_for_each(s, &rose_list) { - struct rose_sock *rose = rose_sk(s); + sk_for_each(sk, &rose_list) { + rose = rose_sk(sk); + if (rose->device == dev) { + if (cnt == ARRAY_SIZE(array)) { + rescan = true; + break; + } + sock_hold(sk); + array[cnt++] = sk; + } + } + spin_unlock_bh(&rose_list_lock); + for (i = 0; i < cnt; i++) { + sk = array[cnt]; + rose = rose_sk(sk); + lock_sock(sk); + spin_lock_bh(&rose_list_lock); if (rose->device == dev) { - rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0); + rose_disconnect(sk, ENETUNREACH, ROSE_OUT_OF_ORDER, 0); if (rose->neighbour) rose->neighbour->use--; netdev_put(rose->device, &rose->dev_tracker); rose->device = NULL; } + spin_unlock_bh(&rose_list_lock); + release_sock(sk); + sock_put(sk); + cond_resched(); } - spin_unlock_bh(&rose_list_lock); + if (rescan) + goto start; } /* @@ -656,7 +682,10 @@ static int rose_release(struct socket *sock) break; } + spin_lock_bh(&rose_list_lock); netdev_put(rose->device, &rose->dev_tracker); + rose->device = NULL; + spin_unlock_bh(&rose_list_lock); sock->sk = NULL; release_sock(sk); sock_put(sk); diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index aab069701398..5d91ef562ff7 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -41,6 +41,14 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, _enter("%d", conn->debug_id); + if (sp && sp->hdr.type == RXRPC_PACKET_TYPE_ACK) { + if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), + &pkt.ack, sizeof(pkt.ack)) < 0) + return; + if (pkt.ack.reason == RXRPC_ACK_PING_RESPONSE) + return; + } + chan = &conn->channels[channel]; /* If the last call got moved on whilst we were waiting to run, just diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 6e6aa02c6f9e..249353417a18 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -31,7 +31,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, struct rxrpc_conn_proto k; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rb_node *p; - unsigned int seq = 0; + unsigned int seq = 1; k.epoch = sp->hdr.epoch; k.cid = sp->hdr.cid & RXRPC_CIDMASK; @@ -41,6 +41,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, * under just the RCU read lock, so we have to check for * changes. */ + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&peer->service_conn_lock, &seq); p = rcu_dereference_raw(peer->service_conns.rb_node); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 24cf0bf7c80e..9c4a80fce794 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -45,23 +45,6 @@ if NET_SCHED comment "Queueing/Scheduling" -config NET_SCH_CBQ - tristate "Class Based Queueing (CBQ)" - help - Say Y here if you want to use the Class-Based Queueing (CBQ) packet - scheduling algorithm. This algorithm classifies the waiting packets - into a tree-like hierarchy of classes; the leaves of this tree are - in turn scheduled by separate algorithms. - - See the top of <file:net/sched/sch_cbq.c> for more details. - - CBQ is a commonly used scheduler, so if you're unsure, you should - say Y here. Then say Y to all the queueing algorithms below that you - want to use as leaf disciplines. - - To compile this code as a module, choose M here: the - module will be called sch_cbq. - config NET_SCH_HTB tristate "Hierarchical Token Bucket (HTB)" help @@ -85,20 +68,6 @@ config NET_SCH_HFSC To compile this code as a module, choose M here: the module will be called sch_hfsc. -config NET_SCH_ATM - tristate "ATM Virtual Circuits (ATM)" - depends on ATM - help - Say Y here if you want to use the ATM pseudo-scheduler. This - provides a framework for invoking classifiers, which in turn - select classes of this queuing discipline. Each class maps - the flow(s) it is handling to a given virtual circuit. - - See the top of <file:net/sched/sch_atm.c> for more details. - - To compile this code as a module, choose M here: the - module will be called sch_atm. - config NET_SCH_PRIO tristate "Multi Band Priority Queueing (PRIO)" help @@ -217,17 +186,6 @@ config NET_SCH_GRED To compile this code as a module, choose M here: the module will be called sch_gred. -config NET_SCH_DSMARK - tristate "Differentiated Services marker (DSMARK)" - help - Say Y if you want to schedule packets according to the - Differentiated Services architecture proposed in RFC 2475. - Technical information on this method, with pointers to associated - RFCs, is available at <http://www.gta.ufrj.br/diffserv/>. - - To compile this code as a module, choose M here: the - module will be called sch_dsmark. - config NET_SCH_NETEM tristate "Network emulator (NETEM)" help diff --git a/net/sched/Makefile b/net/sched/Makefile index 8a33a35fc50d..a66ac1e7b79b 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -33,20 +33,17 @@ obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o obj-$(CONFIG_NET_ACT_CT) += act_ct.o obj-$(CONFIG_NET_ACT_GATE) += act_gate.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o -obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o obj-$(CONFIG_NET_SCH_HFSC) += sch_hfsc.o obj-$(CONFIG_NET_SCH_RED) += sch_red.o obj-$(CONFIG_NET_SCH_GRED) += sch_gred.o obj-$(CONFIG_NET_SCH_INGRESS) += sch_ingress.o -obj-$(CONFIG_NET_SCH_DSMARK) += sch_dsmark.o obj-$(CONFIG_NET_SCH_SFB) += sch_sfb.o obj-$(CONFIG_NET_SCH_SFQ) += sch_sfq.o obj-$(CONFIG_NET_SCH_TBF) += sch_tbf.o obj-$(CONFIG_NET_SCH_TEQL) += sch_teql.o obj-$(CONFIG_NET_SCH_PRIO) += sch_prio.o obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o -obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 4c7f7861ea96..84e15116f18c 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -168,11 +168,11 @@ tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple, static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, enum ip_conntrack_dir dir, + enum ip_conntrack_info ctinfo, struct flow_action *action) { struct nf_conn_labels *ct_labels; struct flow_action_entry *entry; - enum ip_conntrack_info ctinfo; u32 *act_ct_labels; entry = tcf_ct_flow_table_flow_action_get_next(action); @@ -180,8 +180,6 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif - ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED : - IP_CT_ESTABLISHED_REPLY; /* aligns with the CT reference on the SKB nf_ct_set */ entry->ct_metadata.cookie = (unsigned long)ct | ctinfo; entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL; @@ -235,22 +233,26 @@ static int tcf_ct_flow_table_add_action_nat(struct net *net, } static int tcf_ct_flow_table_fill_actions(struct net *net, - const struct flow_offload *flow, + struct flow_offload *flow, enum flow_offload_tuple_dir tdir, struct nf_flow_rule *flow_rule) { struct flow_action *action = &flow_rule->rule->action; int num_entries = action->num_entries; struct nf_conn *ct = flow->ct; + enum ip_conntrack_info ctinfo; enum ip_conntrack_dir dir; int i, err; switch (tdir) { case FLOW_OFFLOAD_DIR_ORIGINAL: dir = IP_CT_DIR_ORIGINAL; + ctinfo = IP_CT_ESTABLISHED; + set_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); break; case FLOW_OFFLOAD_DIR_REPLY: dir = IP_CT_DIR_REPLY; + ctinfo = IP_CT_ESTABLISHED_REPLY; break; default: return -EOPNOTSUPP; @@ -260,7 +262,7 @@ static int tcf_ct_flow_table_fill_actions(struct net *net, if (err) goto err_nat; - tcf_ct_flow_table_add_action_meta(ct, dir, action); + tcf_ct_flow_table_add_action_meta(ct, dir, ctinfo, action); return 0; err_nat: @@ -272,8 +274,39 @@ err_nat: return err; } +static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) +{ + return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && + test_bit(IPS_HW_OFFLOAD_BIT, &flow->ct->status) && + !test_bit(NF_FLOW_HW_PENDING, &flow->flags) && + !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); +} + +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_get(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_get_ref(ct_ft); +} + +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_put(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_put(ct_ft); +} + static struct nf_flowtable_type flowtable_ct = { + .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, + .get = tcf_ct_nf_get, + .put = tcf_ct_nf_put, .owner = THIS_MODULE, }; @@ -322,9 +355,13 @@ err_alloc: return err; } +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft) +{ + refcount_inc(&ct_ft->ref); +} + static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { - struct flow_block_cb *block_cb, *tmp_cb; struct tcf_ct_flow_table *ct_ft; struct flow_block *block; @@ -332,24 +369,18 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) rwork); nf_flow_table_free(&ct_ft->nf_ft); - /* Remove any remaining callbacks before cleanup */ block = &ct_ft->nf_ft.flow_block; down_write(&ct_ft->nf_ft.flow_block_lock); - list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) { - list_del(&block_cb->list); - flow_block_cb_free(block_cb); - } + WARN_ON(!list_empty(&block->cb_list)); up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); module_put(THIS_MODULE); } -static void tcf_ct_flow_table_put(struct tcf_ct_params *params) +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft) { - struct tcf_ct_flow_table *ct_ft = params->ct_ft; - - if (refcount_dec_and_test(¶ms->ct_ft->ref)) { + if (refcount_dec_and_test(&ct_ft->ref)) { rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work); queue_rcu_work(act_ct_wq, &ct_ft->rwork); @@ -363,9 +394,20 @@ static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry, entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir]; } +static void tcf_ct_flow_ct_ext_ifidx_update(struct flow_offload *entry) +{ + struct nf_conn_act_ct_ext *act_ct_ext; + + act_ct_ext = nf_conn_act_ct_ext_find(entry->ct); + if (act_ct_ext) { + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); + } +} + static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, - bool tcp) + bool tcp, bool bidirectional) { struct nf_conn_act_ct_ext *act_ct_ext; struct flow_offload *entry; @@ -384,6 +426,8 @@ static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } + if (bidirectional) + __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &entry->flags); act_ct_ext = nf_conn_act_ct_ext_find(ct); if (act_ct_ext) { @@ -407,26 +451,34 @@ static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - bool tcp = false; - - if ((ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) || - !test_bit(IPS_ASSURED_BIT, &ct->status)) - return; + bool tcp = false, bidirectional = true; switch (nf_ct_protonum(ct)) { case IPPROTO_TCP: - tcp = true; - if (ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED) + if ((ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY) || + !test_bit(IPS_ASSURED_BIT, &ct->status) || + ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED) return; + + tcp = true; break; case IPPROTO_UDP: + if (!nf_ct_is_confirmed(ct)) + return; + if (!test_bit(IPS_ASSURED_BIT, &ct->status)) + bidirectional = false; break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: { struct nf_conntrack_tuple *tuple; - if (ct->status & IPS_NAT_MASK) + if ((ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY) || + !test_bit(IPS_ASSURED_BIT, &ct->status) || + ct->status & IPS_NAT_MASK) return; + tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* No support for GRE v1 */ if (tuple->src.u.gre.key || tuple->dst.u.gre.key) @@ -442,7 +494,7 @@ static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, ct->status & IPS_SEQ_ADJUST) return; - tcf_ct_flow_table_add(ct_ft, ct, tcp); + tcf_ct_flow_table_add(ct_ft, ct, tcp, bidirectional); } static bool @@ -596,6 +648,7 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, struct flow_offload_tuple tuple = {}; enum ip_conntrack_info ctinfo; struct tcphdr *tcph = NULL; + bool force_refresh = false; struct flow_offload *flow; struct nf_conn *ct; u8 dir; @@ -621,15 +674,40 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); ct = flow->ct; + if (dir == FLOW_OFFLOAD_DIR_REPLY && + !test_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags)) { + /* Only offload reply direction after connection became + * assured. + */ + if (test_bit(IPS_ASSURED_BIT, &ct->status)) + set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); + else if (test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags)) + /* If flow_table flow has already been updated to the + * established state, then don't refresh. + */ + return false; + force_refresh = true; + } + if (tcph && (unlikely(tcph->fin || tcph->rst))) { flow_offload_teardown(flow); return false; } - ctinfo = dir == FLOW_OFFLOAD_DIR_ORIGINAL ? IP_CT_ESTABLISHED : - IP_CT_ESTABLISHED_REPLY; + if (dir == FLOW_OFFLOAD_DIR_ORIGINAL) + ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? + IP_CT_ESTABLISHED : IP_CT_NEW; + else + ctinfo = IP_CT_ESTABLISHED_REPLY; + + nf_conn_act_ct_ext_fill(skb, ct, ctinfo); + tcf_ct_flow_ct_ext_ifidx_update(flow); + flow_offload_refresh(nf_ft, flow, force_refresh); + if (!test_bit(IPS_ASSURED_BIT, &ct->status)) { + /* Process this flow in SW to allow promoting to ASSURED */ + return false; + } - flow_offload_refresh(nf_ft, flow); nf_conntrack_get(&ct->ct_general); nf_ct_set(skb, ct, ctinfo); if (nf_ft->flags & NF_FLOWTABLE_COUNTER) @@ -785,7 +863,6 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, if (err || !frag) return err; - skb_get(skb); mru = tc_skb_cb(skb)->mru; if (family == NFPROTO_IPV4) { @@ -832,18 +909,23 @@ out_free: return err; } -static void tcf_ct_params_free(struct rcu_head *head) +static void tcf_ct_params_free(struct tcf_ct_params *params) { - struct tcf_ct_params *params = container_of(head, - struct tcf_ct_params, rcu); - - tcf_ct_flow_table_put(params); - + if (params->ct_ft) + tcf_ct_flow_table_put(params->ct_ft); if (params->tmpl) nf_ct_put(params->tmpl); kfree(params); } +static void tcf_ct_params_free_rcu(struct rcu_head *head) +{ + struct tcf_ct_params *params; + + params = container_of(head, struct tcf_ct_params, rcu); + tcf_ct_params_free(params); +} + #if IS_ENABLED(CONFIG_NF_NAT) /* Modelled after nf_nat_ipv[46]_fn(). * range is only used for new, uninitialized NAT state. @@ -1067,12 +1149,8 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag); - if (err == -EINPROGRESS) { - retval = TC_ACT_STOLEN; - goto out_clear; - } if (err) - goto drop; + goto out_frag; err = tcf_ct_skb_network_trim(skb, family); if (err) @@ -1121,7 +1199,7 @@ do_nat: tcf_ct_act_set_labels(ct, p->labels, p->labels_mask); if (!nf_ct_is_confirmed(ct)) - nf_conn_act_ct_ext_add(ct); + nf_conn_act_ct_ext_add(skb, ct, ctinfo); /* This will take care of sending queued events * even if the connection is already confirmed. @@ -1143,6 +1221,11 @@ out_clear: qdisc_skb_cb(skb)->pkt_len = skb->len; return retval; +out_frag: + if (err != -EINPROGRESS) + tcf_action_inc_drop_qstats(&c->common); + return TC_ACT_CONSUMED; + drop: tcf_action_inc_drop_qstats(&c->common); return TC_ACT_SHOT; @@ -1390,7 +1473,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, err = tcf_ct_flow_table_get(net, params); if (err) - goto cleanup_params; + goto cleanup; spin_lock_bh(&c->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); @@ -1401,17 +1484,15 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params) - call_rcu(¶ms->rcu, tcf_ct_params_free); + call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); return res; -cleanup_params: - if (params->tmpl) - nf_ct_put(params->tmpl); cleanup: if (goto_ch) tcf_chain_put_by_act(goto_ch); - kfree(params); + if (params) + tcf_ct_params_free(params); tcf_idr_release(*a, bind); return err; } @@ -1423,7 +1504,7 @@ static void tcf_ct_cleanup(struct tc_action *a) params = rcu_dereference_protected(c->params, 1); if (params) - call_rcu(¶ms->rcu, tcf_ct_params_free); + call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); } static int tcf_ct_dump_key_val(struct sk_buff *skb, diff --git a/net/sched/em_text.c b/net/sched/em_text.c index 6f3c1fb2fb44..f176afb70559 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -97,8 +97,10 @@ retry: static void em_text_destroy(struct tcf_ematch *m) { - if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) + if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) { textsearch_destroy(EM_TEXT_PRIV(m)->config); + kfree(EM_TEXT_PRIV(m)); + } } static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m) diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c deleted file mode 100644 index 4a981ca90b0b..000000000000 --- a/net/sched/sch_atm.c +++ /dev/null @@ -1,706 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* net/sched/sch_atm.c - ATM VC selection "queueing discipline" */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/atmdev.h> -#include <linux/atmclip.h> -#include <linux/rtnetlink.h> -#include <linux/file.h> /* for fput */ -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> - -/* - * The ATM queuing discipline provides a framework for invoking classifiers - * (aka "filters"), which in turn select classes of this queuing discipline. - * Each class maps the flow(s) it is handling to a given VC. Multiple classes - * may share the same VC. - * - * When creating a class, VCs are specified by passing the number of the open - * socket descriptor by which the calling process references the VC. The kernel - * keeps the VC open at least until all classes using it are removed. - * - * In this file, most functions are named atm_tc_* to avoid confusion with all - * the atm_* in net/atm. This naming convention differs from what's used in the - * rest of net/sched. - * - * Known bugs: - * - sometimes messes up the IP stack - * - any manipulations besides the few operations described in the README, are - * untested and likely to crash the system - * - should lock the flow while there is data in the queue (?) - */ - -#define VCC2FLOW(vcc) ((struct atm_flow_data *) ((vcc)->user_back)) - -struct atm_flow_data { - struct Qdisc_class_common common; - struct Qdisc *q; /* FIFO, TBF, etc. */ - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ - void (*old_pop)(struct atm_vcc *vcc, - struct sk_buff *skb); /* chaining */ - struct atm_qdisc_data *parent; /* parent qdisc */ - struct socket *sock; /* for closing */ - int ref; /* reference count */ - struct gnet_stats_basic_sync bstats; - struct gnet_stats_queue qstats; - struct list_head list; - struct atm_flow_data *excess; /* flow for excess traffic; - NULL to set CLP instead */ - int hdr_len; - unsigned char hdr[]; /* header data; MUST BE LAST */ -}; - -struct atm_qdisc_data { - struct atm_flow_data link; /* unclassified skbs go here */ - struct list_head flows; /* NB: "link" is also on this - list */ - struct tasklet_struct task; /* dequeue tasklet */ -}; - -/* ------------------------- Class/flow operations ------------------------- */ - -static inline struct atm_flow_data *lookup_flow(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - list_for_each_entry(flow, &p->flows, list) { - if (flow->common.classid == classid) - return flow; - } - return NULL; -} - -static int atm_tc_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_graft(sch %p,[qdisc %p],flow %p,new %p,old %p)\n", - sch, p, flow, new, old); - if (list_empty(&flow->list)) - return -EINVAL; - if (!new) - new = &noop_qdisc; - *old = flow->q; - flow->q = new; - if (*old) - qdisc_reset(*old); - return 0; -} - -static struct Qdisc *atm_tc_leaf(struct Qdisc *sch, unsigned long cl) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_leaf(sch %p,flow %p)\n", sch, flow); - return flow ? flow->q : NULL; -} - -static unsigned long atm_tc_find(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", __func__, sch, p, classid); - flow = lookup_flow(sch, classid); - pr_debug("%s: flow %p\n", __func__, flow); - return (unsigned long)flow; -} - -static unsigned long atm_tc_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", __func__, sch, p, classid); - flow = lookup_flow(sch, classid); - if (flow) - flow->ref++; - pr_debug("%s: flow %p\n", __func__, flow); - return (unsigned long)flow; -} - -/* - * atm_tc_put handles all destructions, including the ones that are explicitly - * requested (atm_tc_destroy, etc.). The assumption here is that we never drop - * anything that still seems to be in use. - */ -static void atm_tc_put(struct Qdisc *sch, unsigned long cl) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_put(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (--flow->ref) - return; - pr_debug("atm_tc_put: destroying\n"); - list_del_init(&flow->list); - pr_debug("atm_tc_put: qdisc %p\n", flow->q); - qdisc_put(flow->q); - tcf_block_put(flow->block); - if (flow->sock) { - pr_debug("atm_tc_put: f_count %ld\n", - file_count(flow->sock->file)); - flow->vcc->pop = flow->old_pop; - sockfd_put(flow->sock); - } - if (flow->excess) - atm_tc_put(sch, (unsigned long)flow->excess); - if (flow != &p->link) - kfree(flow); - /* - * If flow == &p->link, the qdisc no longer works at this point and - * needs to be removed. (By the caller of atm_tc_put.) - */ -} - -static void sch_atm_pop(struct atm_vcc *vcc, struct sk_buff *skb) -{ - struct atm_qdisc_data *p = VCC2FLOW(vcc)->parent; - - pr_debug("sch_atm_pop(vcc %p,skb %p,[qdisc %p])\n", vcc, skb, p); - VCC2FLOW(vcc)->old_pop(vcc, skb); - tasklet_schedule(&p->task); -} - -static const u8 llc_oui_ip[] = { - 0xaa, /* DSAP: non-ISO */ - 0xaa, /* SSAP: non-ISO */ - 0x03, /* Ctrl: Unnumbered Information Command PDU */ - 0x00, /* OUI: EtherType */ - 0x00, 0x00, - 0x08, 0x00 -}; /* Ethertype IP (0800) */ - -static const struct nla_policy atm_policy[TCA_ATM_MAX + 1] = { - [TCA_ATM_FD] = { .type = NLA_U32 }, - [TCA_ATM_EXCESS] = { .type = NLA_U32 }, -}; - -static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)*arg; - struct atm_flow_data *excess = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_ATM_MAX + 1]; - struct socket *sock; - int fd, error, hdr_len; - void *hdr; - - pr_debug("atm_tc_change(sch %p,[qdisc %p],classid %x,parent %x," - "flow %p,opt %p)\n", sch, p, classid, parent, flow, opt); - /* - * The concept of parents doesn't apply for this qdisc. - */ - if (parent && parent != TC_H_ROOT && parent != sch->handle) - return -EINVAL; - /* - * ATM classes cannot be changed. In order to change properties of the - * ATM connection, that socket needs to be modified directly (via the - * native ATM API. In order to send a flow to a different VC, the old - * class needs to be removed and a new one added. (This may be changed - * later.) - */ - if (flow) - return -EBUSY; - if (opt == NULL) - return -EINVAL; - - error = nla_parse_nested_deprecated(tb, TCA_ATM_MAX, opt, atm_policy, - NULL); - if (error < 0) - return error; - - if (!tb[TCA_ATM_FD]) - return -EINVAL; - fd = nla_get_u32(tb[TCA_ATM_FD]); - pr_debug("atm_tc_change: fd %d\n", fd); - if (tb[TCA_ATM_HDR]) { - hdr_len = nla_len(tb[TCA_ATM_HDR]); - hdr = nla_data(tb[TCA_ATM_HDR]); - } else { - hdr_len = RFC1483LLC_LEN; - hdr = NULL; /* default LLC/SNAP for IP */ - } - if (!tb[TCA_ATM_EXCESS]) - excess = NULL; - else { - excess = (struct atm_flow_data *) - atm_tc_find(sch, nla_get_u32(tb[TCA_ATM_EXCESS])); - if (!excess) - return -ENOENT; - } - pr_debug("atm_tc_change: type %d, payload %d, hdr_len %d\n", - opt->nla_type, nla_len(opt), hdr_len); - sock = sockfd_lookup(fd, &error); - if (!sock) - return error; /* f_count++ */ - pr_debug("atm_tc_change: f_count %ld\n", file_count(sock->file)); - if (sock->ops->family != PF_ATMSVC && sock->ops->family != PF_ATMPVC) { - error = -EPROTOTYPE; - goto err_out; - } - /* @@@ should check if the socket is really operational or we'll crash - on vcc->send */ - if (classid) { - if (TC_H_MAJ(classid ^ sch->handle)) { - pr_debug("atm_tc_change: classid mismatch\n"); - error = -EINVAL; - goto err_out; - } - } else { - int i; - unsigned long cl; - - for (i = 1; i < 0x8000; i++) { - classid = TC_H_MAKE(sch->handle, 0x8000 | i); - cl = atm_tc_find(sch, classid); - if (!cl) - break; - } - } - pr_debug("atm_tc_change: new id %x\n", classid); - flow = kzalloc(sizeof(struct atm_flow_data) + hdr_len, GFP_KERNEL); - pr_debug("atm_tc_change: flow %p\n", flow); - if (!flow) { - error = -ENOBUFS; - goto err_out; - } - - error = tcf_block_get(&flow->block, &flow->filter_list, sch, - extack); - if (error) { - kfree(flow); - goto err_out; - } - - flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, - extack); - if (!flow->q) - flow->q = &noop_qdisc; - pr_debug("atm_tc_change: qdisc %p\n", flow->q); - flow->sock = sock; - flow->vcc = ATM_SD(sock); /* speedup */ - flow->vcc->user_back = flow; - pr_debug("atm_tc_change: vcc %p\n", flow->vcc); - flow->old_pop = flow->vcc->pop; - flow->parent = p; - flow->vcc->pop = sch_atm_pop; - flow->common.classid = classid; - flow->ref = 1; - flow->excess = excess; - list_add(&flow->list, &p->link.list); - flow->hdr_len = hdr_len; - if (hdr) - memcpy(flow->hdr, hdr, hdr_len); - else - memcpy(flow->hdr, llc_oui_ip, sizeof(llc_oui_ip)); - *arg = (unsigned long)flow; - return 0; -err_out: - sockfd_put(sock); - return error; -} - -static int atm_tc_delete(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (list_empty(&flow->list)) - return -EINVAL; - if (rcu_access_pointer(flow->filter_list) || flow == &p->link) - return -EBUSY; - /* - * Reference count must be 2: one for "keepalive" (set at class - * creation), and one for the reference held when calling delete. - */ - if (flow->ref < 2) { - pr_err("atm_tc_delete: flow->ref == %d\n", flow->ref); - return -EINVAL; - } - if (flow->ref > 2) - return -EBUSY; /* catch references via excess, etc. */ - atm_tc_put(sch, arg); - return 0; -} - -static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); - if (walker->stop) - return; - list_for_each_entry(flow, &p->flows, list) { - if (!tc_qdisc_stats_dump(sch, (unsigned long)flow, walker)) - break; - } -} - -static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - return flow ? flow->block : p->link.block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - struct tcf_result res; - int result; - int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - - pr_debug("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); - result = TC_ACT_OK; /* be nice to gcc */ - flow = NULL; - if (TC_H_MAJ(skb->priority) != sch->handle || - !(flow = (struct atm_flow_data *)atm_tc_find(sch, skb->priority))) { - struct tcf_proto *fl; - - list_for_each_entry(flow, &p->flows, list) { - fl = rcu_dereference_bh(flow->filter_list); - if (fl) { - result = tcf_classify(skb, NULL, fl, &res, true); - if (result < 0) - continue; - if (result == TC_ACT_SHOT) - goto done; - - flow = (struct atm_flow_data *)res.class; - if (!flow) - flow = lookup_flow(sch, res.classid); - goto drop; - } - } - flow = NULL; -done: - ; - } - if (!flow) { - flow = &p->link; - } else { - if (flow->vcc) - ATM_SKB(skb)->atm_options = flow->vcc->atm_options; - /*@@@ looks good ... but it's not supposed to work :-) */ -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - case TC_ACT_SHOT: - __qdisc_drop(skb, to_free); - goto drop; - case TC_ACT_RECLASSIFY: - if (flow->excess) - flow = flow->excess; - else - ATM_SKB(skb)->atm_options |= ATM_ATMOPT_CLP; - break; - } -#endif - } - - ret = qdisc_enqueue(skb, flow->q, to_free); - if (ret != NET_XMIT_SUCCESS) { -drop: __maybe_unused - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - if (flow) - flow->qstats.drops++; - } - return ret; - } - /* - * Okay, this may seem weird. We pretend we've dropped the packet if - * it goes via ATM. The reason for this is that the outer qdisc - * expects to be able to q->dequeue the packet later on if we return - * success at this place. Also, sch->q.qdisc needs to reflect whether - * there is a packet egligible for dequeuing or not. Note that the - * statistics of the outer qdisc are necessarily wrong because of all - * this. There's currently no correct solution for this. - */ - if (flow == &p->link) { - sch->q.qlen++; - return NET_XMIT_SUCCESS; - } - tasklet_schedule(&p->task); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -/* - * Dequeue packets and send them over ATM. Note that we quite deliberately - * avoid checking net_device's flow control here, simply because sch_atm - * uses its own channels, which have nothing to do with any CLIP/LANE/or - * non-ATM interfaces. - */ - -static void sch_atm_dequeue(struct tasklet_struct *t) -{ - struct atm_qdisc_data *p = from_tasklet(p, t, task); - struct Qdisc *sch = qdisc_from_priv(p); - struct atm_flow_data *flow; - struct sk_buff *skb; - - pr_debug("sch_atm_dequeue(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - if (flow == &p->link) - continue; - /* - * If traffic is properly shaped, this won't generate nasty - * little bursts. Otherwise, it may ... (but that's okay) - */ - while ((skb = flow->q->ops->peek(flow->q))) { - if (!atm_may_send(flow->vcc, skb->truesize)) - break; - - skb = qdisc_dequeue_peeked(flow->q); - if (unlikely(!skb)) - break; - - qdisc_bstats_update(sch, skb); - bstats_update(&flow->bstats, skb); - pr_debug("atm_tc_dequeue: sending on class %p\n", flow); - /* remove any LL header somebody else has attached */ - skb_pull(skb, skb_network_offset(skb)); - if (skb_headroom(skb) < flow->hdr_len) { - struct sk_buff *new; - - new = skb_realloc_headroom(skb, flow->hdr_len); - dev_kfree_skb(skb); - if (!new) - continue; - skb = new; - } - pr_debug("sch_atm_dequeue: ip %p, data %p\n", - skb_network_header(skb), skb->data); - ATM_SKB(skb)->vcc = flow->vcc; - memcpy(skb_push(skb, flow->hdr_len), flow->hdr, - flow->hdr_len); - refcount_add(skb->truesize, - &sk_atm(flow->vcc)->sk_wmem_alloc); - /* atm.atm_options are already set by atm_tc_enqueue */ - flow->vcc->send(flow->vcc, skb); - } - } -} - -static struct sk_buff *atm_tc_dequeue(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - - pr_debug("atm_tc_dequeue(sch %p,[qdisc %p])\n", sch, p); - tasklet_schedule(&p->task); - skb = qdisc_dequeue_peeked(p->link.q); - if (skb) - sch->q.qlen--; - return skb; -} - -static struct sk_buff *atm_tc_peek(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - - pr_debug("atm_tc_peek(sch %p,[qdisc %p])\n", sch, p); - - return p->link.q->ops->peek(p->link.q); -} - -static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); - INIT_LIST_HEAD(&p->flows); - INIT_LIST_HEAD(&p->link.list); - gnet_stats_basic_sync_init(&p->link.bstats); - list_add(&p->link.list, &p->flows); - p->link.q = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, sch->handle, extack); - if (!p->link.q) - p->link.q = &noop_qdisc; - pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.common.classid = sch->handle; - p->link.ref = 1; - - err = tcf_block_get(&p->link.block, &p->link.filter_list, sch, - extack); - if (err) - return err; - - tasklet_setup(&p->task, sch_atm_dequeue); - return 0; -} - -static void atm_tc_reset(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_reset(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) - qdisc_reset(flow->q); -} - -static void atm_tc_destroy(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow, *tmp; - - pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - tcf_block_put(flow->block); - flow->block = NULL; - } - - list_for_each_entry_safe(flow, tmp, &p->flows, list) { - if (flow->ref > 1) - pr_err("atm_destroy: %p->ref = %d\n", flow, flow->ref); - atm_tc_put(sch, (unsigned long)flow); - } - tasklet_kill(&p->task); -} - -static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - struct nlattr *nest; - - pr_debug("atm_tc_dump_class(sch %p,[qdisc %p],flow %p,skb %p,tcm %p)\n", - sch, p, flow, skb, tcm); - if (list_empty(&flow->list)) - return -EINVAL; - tcm->tcm_handle = flow->common.classid; - tcm->tcm_info = flow->q->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_ATM_HDR, flow->hdr_len, flow->hdr)) - goto nla_put_failure; - if (flow->vcc) { - struct sockaddr_atmpvc pvc; - int state; - - memset(&pvc, 0, sizeof(pvc)); - pvc.sap_family = AF_ATMPVC; - pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; - pvc.sap_addr.vpi = flow->vcc->vpi; - pvc.sap_addr.vci = flow->vcc->vci; - if (nla_put(skb, TCA_ATM_ADDR, sizeof(pvc), &pvc)) - goto nla_put_failure; - state = ATM_VF2VS(flow->vcc->flags); - if (nla_put_u32(skb, TCA_ATM_STATE, state)) - goto nla_put_failure; - } - if (flow->excess) { - if (nla_put_u32(skb, TCA_ATM_EXCESS, flow->common.classid)) - goto nla_put_failure; - } else { - if (nla_put_u32(skb, TCA_ATM_EXCESS, 0)) - goto nla_put_failure; - } - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} -static int -atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - if (gnet_stats_copy_basic(d, NULL, &flow->bstats, true) < 0 || - gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0) - return -1; - - return 0; -} - -static int atm_tc_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - return 0; -} - -static const struct Qdisc_class_ops atm_class_ops = { - .graft = atm_tc_graft, - .leaf = atm_tc_leaf, - .find = atm_tc_find, - .change = atm_tc_change, - .delete = atm_tc_delete, - .walk = atm_tc_walk, - .tcf_block = atm_tc_tcf_block, - .bind_tcf = atm_tc_bind_filter, - .unbind_tcf = atm_tc_put, - .dump = atm_tc_dump_class, - .dump_stats = atm_tc_dump_class_stats, -}; - -static struct Qdisc_ops atm_qdisc_ops __read_mostly = { - .cl_ops = &atm_class_ops, - .id = "atm", - .priv_size = sizeof(struct atm_qdisc_data), - .enqueue = atm_tc_enqueue, - .dequeue = atm_tc_dequeue, - .peek = atm_tc_peek, - .init = atm_tc_init, - .reset = atm_tc_reset, - .destroy = atm_tc_destroy, - .dump = atm_tc_dump, - .owner = THIS_MODULE, -}; - -static int __init atm_init(void) -{ - return register_qdisc(&atm_qdisc_ops); -} - -static void __exit atm_exit(void) -{ - unregister_qdisc(&atm_qdisc_ops); -} - -module_init(atm_init) -module_exit(atm_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c deleted file mode 100644 index 36db5f6782f2..000000000000 --- a/net/sched/sch_cbq.c +++ /dev/null @@ -1,1727 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/sch_cbq.c Class-Based Queueing discipline. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> - - -/* Class-Based Queueing (CBQ) algorithm. - ======================================= - - Sources: [1] Sally Floyd and Van Jacobson, "Link-sharing and Resource - Management Models for Packet Networks", - IEEE/ACM Transactions on Networking, Vol.3, No.4, 1995 - - [2] Sally Floyd, "Notes on CBQ and Guaranteed Service", 1995 - - [3] Sally Floyd, "Notes on Class-Based Queueing: Setting - Parameters", 1996 - - [4] Sally Floyd and Michael Speer, "Experimental Results - for Class-Based Queueing", 1998, not published. - - ----------------------------------------------------------------------- - - Algorithm skeleton was taken from NS simulator cbq.cc. - If someone wants to check this code against the LBL version, - he should take into account that ONLY the skeleton was borrowed, - the implementation is different. Particularly: - - --- The WRR algorithm is different. Our version looks more - reasonable (I hope) and works when quanta are allowed to be - less than MTU, which is always the case when real time classes - have small rates. Note, that the statement of [3] is - incomplete, delay may actually be estimated even if class - per-round allotment is less than MTU. Namely, if per-round - allotment is W*r_i, and r_1+...+r_k = r < 1 - - delay_i <= ([MTU/(W*r_i)]*W*r + W*r + k*MTU)/B - - In the worst case we have IntServ estimate with D = W*r+k*MTU - and C = MTU*r. The proof (if correct at all) is trivial. - - - --- It seems that cbq-2.0 is not very accurate. At least, I cannot - interpret some places, which look like wrong translations - from NS. Anyone is advised to find these differences - and explain to me, why I am wrong 8). - - --- Linux has no EOI event, so that we cannot estimate true class - idle time. Workaround is to consider the next dequeue event - as sign that previous packet is finished. This is wrong because of - internal device queueing, but on a permanently loaded link it is true. - Moreover, combined with clock integrator, this scheme looks - very close to an ideal solution. */ - -struct cbq_sched_data; - - -struct cbq_class { - struct Qdisc_class_common common; - struct cbq_class *next_alive; /* next class with backlog in this priority band */ - -/* Parameters */ - unsigned char priority; /* class priority */ - unsigned char priority2; /* priority to be used after overlimit */ - unsigned char ewma_log; /* time constant for idle time calculation */ - - u32 defmap; - - /* Link-sharing scheduler parameters */ - long maxidle; /* Class parameters: see below. */ - long offtime; - long minidle; - u32 avpkt; - struct qdisc_rate_table *R_tab; - - /* General scheduler (WRR) parameters */ - long allot; - long quantum; /* Allotment per WRR round */ - long weight; /* Relative allotment: see below */ - - struct Qdisc *qdisc; /* Ptr to CBQ discipline */ - struct cbq_class *split; /* Ptr to split node */ - struct cbq_class *share; /* Ptr to LS parent in the class tree */ - struct cbq_class *tparent; /* Ptr to tree parent in the class tree */ - struct cbq_class *borrow; /* NULL if class is bandwidth limited; - parent otherwise */ - struct cbq_class *sibling; /* Sibling chain */ - struct cbq_class *children; /* Pointer to children chain */ - - struct Qdisc *q; /* Elementary queueing discipline */ - - -/* Variables */ - unsigned char cpriority; /* Effective priority */ - unsigned char delayed; - unsigned char level; /* level of the class in hierarchy: - 0 for leaf classes, and maximal - level of children + 1 for nodes. - */ - - psched_time_t last; /* Last end of service */ - psched_time_t undertime; - long avgidle; - long deficit; /* Saved deficit for WRR */ - psched_time_t penalized; - struct gnet_stats_basic_sync bstats; - struct gnet_stats_queue qstats; - struct net_rate_estimator __rcu *rate_est; - struct tc_cbq_xstats xstats; - - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - - int filters; - - struct cbq_class *defaults[TC_PRIO_MAX + 1]; -}; - -struct cbq_sched_data { - struct Qdisc_class_hash clhash; /* Hash table of all classes */ - int nclasses[TC_CBQ_MAXPRIO + 1]; - unsigned int quanta[TC_CBQ_MAXPRIO + 1]; - - struct cbq_class link; - - unsigned int activemask; - struct cbq_class *active[TC_CBQ_MAXPRIO + 1]; /* List of all classes - with backlog */ - -#ifdef CONFIG_NET_CLS_ACT - struct cbq_class *rx_class; -#endif - struct cbq_class *tx_class; - struct cbq_class *tx_borrowed; - int tx_len; - psched_time_t now; /* Cached timestamp */ - unsigned int pmask; - - struct qdisc_watchdog watchdog; /* Watchdog timer, - started when CBQ has - backlog, but cannot - transmit just now */ - psched_tdiff_t wd_expires; - int toplevel; - u32 hgenerator; -}; - - -#define L2T(cl, len) qdisc_l2t((cl)->R_tab, len) - -static inline struct cbq_class * -cbq_class_lookup(struct cbq_sched_data *q, u32 classid) -{ - struct Qdisc_class_common *clc; - - clc = qdisc_class_find(&q->clhash, classid); - if (clc == NULL) - return NULL; - return container_of(clc, struct cbq_class, common); -} - -#ifdef CONFIG_NET_CLS_ACT - -static struct cbq_class * -cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) -{ - struct cbq_class *cl; - - for (cl = this->tparent; cl; cl = cl->tparent) { - struct cbq_class *new = cl->defaults[TC_PRIO_BESTEFFORT]; - - if (new != NULL && new != this) - return new; - } - return NULL; -} - -#endif - -/* Classify packet. The procedure is pretty complicated, but - * it allows us to combine link sharing and priority scheduling - * transparently. - * - * Namely, you can put link sharing rules (f.e. route based) at root of CBQ, - * so that it resolves to split nodes. Then packets are classified - * by logical priority, or a more specific classifier may be attached - * to the split node. - */ - -static struct cbq_class * -cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *head = &q->link; - struct cbq_class **defmap; - struct cbq_class *cl = NULL; - u32 prio = skb->priority; - struct tcf_proto *fl; - struct tcf_result res; - - /* - * Step 1. If skb->priority points to one of our classes, use it. - */ - if (TC_H_MAJ(prio ^ sch->handle) == 0 && - (cl = cbq_class_lookup(q, prio)) != NULL) - return cl; - - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - for (;;) { - int result = 0; - defmap = head->defaults; - - fl = rcu_dereference_bh(head->filter_list); - /* - * Step 2+n. Apply classifier. - */ - result = tcf_classify(skb, NULL, fl, &res, true); - if (!fl || result < 0) - goto fallback; - if (result == TC_ACT_SHOT) - return NULL; - - cl = (void *)res.class; - if (!cl) { - if (TC_H_MAJ(res.classid)) - cl = cbq_class_lookup(q, res.classid); - else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL) - cl = defmap[TC_PRIO_BESTEFFORT]; - - if (cl == NULL) - goto fallback; - } - if (cl->level >= head->level) - goto fallback; -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - fallthrough; - case TC_ACT_RECLASSIFY: - return cbq_reclassify(skb, cl); - } -#endif - if (cl->level == 0) - return cl; - - /* - * Step 3+n. If classifier selected a link sharing class, - * apply agency specific classifier. - * Repeat this procedure until we hit a leaf node. - */ - head = cl; - } - -fallback: - cl = head; - - /* - * Step 4. No success... - */ - if (TC_H_MAJ(prio) == 0 && - !(cl = head->defaults[prio & TC_PRIO_MAX]) && - !(cl = head->defaults[TC_PRIO_BESTEFFORT])) - return head; - - return cl; -} - -/* - * A packet has just been enqueued on the empty class. - * cbq_activate_class adds it to the tail of active class list - * of its priority band. - */ - -static inline void cbq_activate_class(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - int prio = cl->cpriority; - struct cbq_class *cl_tail; - - cl_tail = q->active[prio]; - q->active[prio] = cl; - - if (cl_tail != NULL) { - cl->next_alive = cl_tail->next_alive; - cl_tail->next_alive = cl; - } else { - cl->next_alive = cl; - q->activemask |= (1<<prio); - } -} - -/* - * Unlink class from active chain. - * Note that this same procedure is done directly in cbq_dequeue* - * during round-robin procedure. - */ - -static void cbq_deactivate_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - int prio = this->cpriority; - struct cbq_class *cl; - struct cbq_class *cl_prev = q->active[prio]; - - do { - cl = cl_prev->next_alive; - if (cl == this) { - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - if (cl == q->active[prio]) { - q->active[prio] = cl_prev; - if (cl == q->active[prio]) { - q->active[prio] = NULL; - q->activemask &= ~(1<<prio); - return; - } - } - return; - } - } while ((cl_prev = cl) != q->active[prio]); -} - -static void -cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) -{ - int toplevel = q->toplevel; - - if (toplevel > cl->level) { - psched_time_t now = psched_get_time(); - - do { - if (cl->undertime < now) { - q->toplevel = cl->level; - return; - } - } while ((cl = cl->borrow) != NULL && toplevel > cl->level); - } -} - -static int -cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - int ret; - struct cbq_class *cl = cbq_classify(skb, sch, &ret); - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = cl; -#endif - if (cl == NULL) { - if (ret & __NET_XMIT_BYPASS) - qdisc_qstats_drop(sch); - __qdisc_drop(skb, to_free); - return ret; - } - - ret = qdisc_enqueue(skb, cl->q, to_free); - if (ret == NET_XMIT_SUCCESS) { - sch->q.qlen++; - cbq_mark_toplevel(q, cl); - if (!cl->next_alive) - cbq_activate_class(cl); - return ret; - } - - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - cbq_mark_toplevel(q, cl); - cl->qstats.drops++; - } - return ret; -} - -/* Overlimit action: penalize leaf class by adding offtime */ -static void cbq_overlimit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - psched_tdiff_t delay = cl->undertime - q->now; - - if (!cl->delayed) { - delay += cl->offtime; - - /* - * Class goes to sleep, so that it will have no - * chance to work avgidle. Let's forgive it 8) - * - * BTW cbq-2.0 has a crap in this - * place, apparently they forgot to shift it by cl->ewma_log. - */ - if (cl->avgidle < 0) - delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log); - if (cl->avgidle < cl->minidle) - cl->avgidle = cl->minidle; - if (delay <= 0) - delay = 1; - cl->undertime = q->now + delay; - - cl->xstats.overactions++; - cl->delayed = 1; - } - if (q->wd_expires == 0 || q->wd_expires > delay) - q->wd_expires = delay; - - /* Dirty work! We must schedule wakeups based on - * real available rate, rather than leaf rate, - * which may be tiny (even zero). - */ - if (q->toplevel == TC_CBQ_MAXLEVEL) { - struct cbq_class *b; - psched_tdiff_t base_delay = q->wd_expires; - - for (b = cl->borrow; b; b = b->borrow) { - delay = b->undertime - q->now; - if (delay < base_delay) { - if (delay <= 0) - delay = 1; - base_delay = delay; - } - } - - q->wd_expires = base_delay; - } -} - -/* - * It is mission critical procedure. - * - * We "regenerate" toplevel cutoff, if transmitting class - * has backlog and it is not regulated. It is not part of - * original CBQ description, but looks more reasonable. - * Probably, it is wrong. This question needs further investigation. - */ - -static inline void -cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, - struct cbq_class *borrowed) -{ - if (cl && q->toplevel >= borrowed->level) { - if (cl->q->q.qlen > 1) { - do { - if (borrowed->undertime == PSCHED_PASTPERFECT) { - q->toplevel = borrowed->level; - return; - } - } while ((borrowed = borrowed->borrow) != NULL); - } -#if 0 - /* It is not necessary now. Uncommenting it - will save CPU cycles, but decrease fairness. - */ - q->toplevel = TC_CBQ_MAXLEVEL; -#endif - } -} - -static void -cbq_update(struct cbq_sched_data *q) -{ - struct cbq_class *this = q->tx_class; - struct cbq_class *cl = this; - int len = q->tx_len; - psched_time_t now; - - q->tx_class = NULL; - /* Time integrator. We calculate EOS time - * by adding expected packet transmission time. - */ - now = q->now + L2T(&q->link, len); - - for ( ; cl; cl = cl->share) { - long avgidle = cl->avgidle; - long idle; - - _bstats_update(&cl->bstats, len, 1); - - /* - * (now - last) is total time between packet right edges. - * (last_pktlen/rate) is "virtual" busy time, so that - * - * idle = (now - last) - last_pktlen/rate - */ - - idle = now - cl->last; - if ((unsigned long)idle > 128*1024*1024) { - avgidle = cl->maxidle; - } else { - idle -= L2T(cl, len); - - /* true_avgidle := (1-W)*true_avgidle + W*idle, - * where W=2^{-ewma_log}. But cl->avgidle is scaled: - * cl->avgidle == true_avgidle/W, - * hence: - */ - avgidle += idle - (avgidle>>cl->ewma_log); - } - - if (avgidle <= 0) { - /* Overlimit or at-limit */ - - if (avgidle < cl->minidle) - avgidle = cl->minidle; - - cl->avgidle = avgidle; - - /* Calculate expected time, when this class - * will be allowed to send. - * It will occur, when: - * (1-W)*true_avgidle + W*delay = 0, i.e. - * idle = (1/W - 1)*(-true_avgidle) - * or - * idle = (1 - W)*(-cl->avgidle); - */ - idle = (-avgidle) - ((-avgidle) >> cl->ewma_log); - - /* - * That is not all. - * To maintain the rate allocated to the class, - * we add to undertime virtual clock, - * necessary to complete transmitted packet. - * (len/phys_bandwidth has been already passed - * to the moment of cbq_update) - */ - - idle -= L2T(&q->link, len); - idle += L2T(cl, len); - - cl->undertime = now + idle; - } else { - /* Underlimit */ - - cl->undertime = PSCHED_PASTPERFECT; - if (avgidle > cl->maxidle) - cl->avgidle = cl->maxidle; - else - cl->avgidle = avgidle; - } - if ((s64)(now - cl->last) > 0) - cl->last = now; - } - - cbq_update_toplevel(q, this, q->tx_borrowed); -} - -static inline struct cbq_class * -cbq_under_limit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *this_cl = cl; - - if (cl->tparent == NULL) - return cl; - - if (cl->undertime == PSCHED_PASTPERFECT || q->now >= cl->undertime) { - cl->delayed = 0; - return cl; - } - - do { - /* It is very suspicious place. Now overlimit - * action is generated for not bounded classes - * only if link is completely congested. - * Though it is in agree with ancestor-only paradigm, - * it looks very stupid. Particularly, - * it means that this chunk of code will either - * never be called or result in strong amplification - * of burstiness. Dangerous, silly, and, however, - * no another solution exists. - */ - cl = cl->borrow; - if (!cl) { - this_cl->qstats.overlimits++; - cbq_overlimit(this_cl); - return NULL; - } - if (cl->level > q->toplevel) - return NULL; - } while (cl->undertime != PSCHED_PASTPERFECT && q->now < cl->undertime); - - cl->delayed = 0; - return cl; -} - -static inline struct sk_buff * -cbq_dequeue_prio(struct Qdisc *sch, int prio) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl_tail, *cl_prev, *cl; - struct sk_buff *skb; - int deficit; - - cl_tail = cl_prev = q->active[prio]; - cl = cl_prev->next_alive; - - do { - deficit = 0; - - /* Start round */ - do { - struct cbq_class *borrow = cl; - - if (cl->q->q.qlen && - (borrow = cbq_under_limit(cl)) == NULL) - goto skip_class; - - if (cl->deficit <= 0) { - /* Class exhausted its allotment per - * this round. Switch to the next one. - */ - deficit = 1; - cl->deficit += cl->quantum; - goto next_class; - } - - skb = cl->q->dequeue(cl->q); - - /* Class did not give us any skb :-( - * It could occur even if cl->q->q.qlen != 0 - * f.e. if cl->q == "tbf" - */ - if (skb == NULL) - goto skip_class; - - cl->deficit -= qdisc_pkt_len(skb); - q->tx_class = cl; - q->tx_borrowed = borrow; - if (borrow != cl) { -#ifndef CBQ_XSTATS_BORROWS_BYTES - borrow->xstats.borrows++; - cl->xstats.borrows++; -#else - borrow->xstats.borrows += qdisc_pkt_len(skb); - cl->xstats.borrows += qdisc_pkt_len(skb); -#endif - } - q->tx_len = qdisc_pkt_len(skb); - - if (cl->deficit <= 0) { - q->active[prio] = cl; - cl = cl->next_alive; - cl->deficit += cl->quantum; - } - return skb; - -skip_class: - if (cl->q->q.qlen == 0 || prio != cl->cpriority) { - /* Class is empty or penalized. - * Unlink it from active chain. - */ - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - /* Did cl_tail point to it? */ - if (cl == cl_tail) { - /* Repair it! */ - cl_tail = cl_prev; - - /* Was it the last class in this band? */ - if (cl == cl_tail) { - /* Kill the band! */ - q->active[prio] = NULL; - q->activemask &= ~(1<<prio); - if (cl->q->q.qlen) - cbq_activate_class(cl); - return NULL; - } - - q->active[prio] = cl_tail; - } - if (cl->q->q.qlen) - cbq_activate_class(cl); - - cl = cl_prev; - } - -next_class: - cl_prev = cl; - cl = cl->next_alive; - } while (cl_prev != cl_tail); - } while (deficit); - - q->active[prio] = cl_prev; - - return NULL; -} - -static inline struct sk_buff * -cbq_dequeue_1(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct sk_buff *skb; - unsigned int activemask; - - activemask = q->activemask & 0xFF; - while (activemask) { - int prio = ffz(~activemask); - activemask &= ~(1<<prio); - skb = cbq_dequeue_prio(sch, prio); - if (skb) - return skb; - } - return NULL; -} - -static struct sk_buff * -cbq_dequeue(struct Qdisc *sch) -{ - struct sk_buff *skb; - struct cbq_sched_data *q = qdisc_priv(sch); - psched_time_t now; - - now = psched_get_time(); - - if (q->tx_class) - cbq_update(q); - - q->now = now; - - for (;;) { - q->wd_expires = 0; - - skb = cbq_dequeue_1(sch); - if (skb) { - qdisc_bstats_update(sch, skb); - sch->q.qlen--; - return skb; - } - - /* All the classes are overlimit. - * - * It is possible, if: - * - * 1. Scheduler is empty. - * 2. Toplevel cutoff inhibited borrowing. - * 3. Root class is overlimit. - * - * Reset 2d and 3d conditions and retry. - * - * Note, that NS and cbq-2.0 are buggy, peeking - * an arbitrary class is appropriate for ancestor-only - * sharing, but not for toplevel algorithm. - * - * Our version is better, but slower, because it requires - * two passes, but it is unavoidable with top-level sharing. - */ - - if (q->toplevel == TC_CBQ_MAXLEVEL && - q->link.undertime == PSCHED_PASTPERFECT) - break; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->link.undertime = PSCHED_PASTPERFECT; - } - - /* No packets in scheduler or nobody wants to give them to us :-( - * Sigh... start watchdog timer in the last case. - */ - - if (sch->q.qlen) { - qdisc_qstats_overlimit(sch); - if (q->wd_expires) - qdisc_watchdog_schedule(&q->watchdog, - now + q->wd_expires); - } - return NULL; -} - -/* CBQ class maintenance routines */ - -static void cbq_adjust_levels(struct cbq_class *this) -{ - if (this == NULL) - return; - - do { - int level = 0; - struct cbq_class *cl; - - cl = this->children; - if (cl) { - do { - if (cl->level > level) - level = cl->level; - } while ((cl = cl->sibling) != this->children); - } - this->level = level + 1; - } while ((this = this->tparent) != NULL); -} - -static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) -{ - struct cbq_class *cl; - unsigned int h; - - if (q->quanta[prio] == 0) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - /* BUGGGG... Beware! This expression suffer of - * arithmetic overflows! - */ - if (cl->priority == prio) { - cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/ - q->quanta[prio]; - } - if (cl->quantum <= 0 || - cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) { - pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n", - cl->common.classid, cl->quantum); - cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; - } - } - } -} - -static void cbq_sync_defmap(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *split = cl->split; - unsigned int h; - int i; - - if (split == NULL) - return; - - for (i = 0; i <= TC_PRIO_MAX; i++) { - if (split->defaults[i] == cl && !(cl->defmap & (1<<i))) - split->defaults[i] = NULL; - } - - for (i = 0; i <= TC_PRIO_MAX; i++) { - int level = split->level; - - if (split->defaults[i]) - continue; - - for (h = 0; h < q->clhash.hashsize; h++) { - struct cbq_class *c; - - hlist_for_each_entry(c, &q->clhash.hash[h], - common.hnode) { - if (c->split == split && c->level < level && - c->defmap & (1<<i)) { - split->defaults[i] = c; - level = c->level; - } - } - } - } -} - -static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 mask) -{ - struct cbq_class *split = NULL; - - if (splitid == 0) { - split = cl->split; - if (!split) - return; - splitid = split->common.classid; - } - - if (split == NULL || split->common.classid != splitid) { - for (split = cl->tparent; split; split = split->tparent) - if (split->common.classid == splitid) - break; - } - - if (split == NULL) - return; - - if (cl->split != split) { - cl->defmap = 0; - cbq_sync_defmap(cl); - cl->split = split; - cl->defmap = def & mask; - } else - cl->defmap = (cl->defmap & ~mask) | (def & mask); - - cbq_sync_defmap(cl); -} - -static void cbq_unlink_class(struct cbq_class *this) -{ - struct cbq_class *cl, **clp; - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - - qdisc_class_hash_remove(&q->clhash, &this->common); - - if (this->tparent) { - clp = &this->sibling; - cl = *clp; - do { - if (cl == this) { - *clp = cl->sibling; - break; - } - clp = &cl->sibling; - } while ((cl = *clp) != this->sibling); - - if (this->tparent->children == this) { - this->tparent->children = this->sibling; - if (this->sibling == this) - this->tparent->children = NULL; - } - } else { - WARN_ON(this->sibling != this); - } -} - -static void cbq_link_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - struct cbq_class *parent = this->tparent; - - this->sibling = this; - qdisc_class_hash_insert(&q->clhash, &this->common); - - if (parent == NULL) - return; - - if (parent->children == NULL) { - parent->children = this; - } else { - this->sibling = parent->children->sibling; - parent->children->sibling = this; - } -} - -static void -cbq_reset(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - int prio; - unsigned int h; - - q->activemask = 0; - q->pmask = 0; - q->tx_class = NULL; - q->tx_borrowed = NULL; - qdisc_watchdog_cancel(&q->watchdog); - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - for (prio = 0; prio <= TC_CBQ_MAXPRIO; prio++) - q->active[prio] = NULL; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - qdisc_reset(cl->q); - - cl->next_alive = NULL; - cl->undertime = PSCHED_PASTPERFECT; - cl->avgidle = cl->maxidle; - cl->deficit = cl->quantum; - cl->cpriority = cl->priority; - } - } -} - - -static void cbq_set_lss(struct cbq_class *cl, struct tc_cbq_lssopt *lss) -{ - if (lss->change & TCF_CBQ_LSS_FLAGS) { - cl->share = (lss->flags & TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; - cl->borrow = (lss->flags & TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; - } - if (lss->change & TCF_CBQ_LSS_EWMA) - cl->ewma_log = lss->ewma_log; - if (lss->change & TCF_CBQ_LSS_AVPKT) - cl->avpkt = lss->avpkt; - if (lss->change & TCF_CBQ_LSS_MINIDLE) - cl->minidle = -(long)lss->minidle; - if (lss->change & TCF_CBQ_LSS_MAXIDLE) { - cl->maxidle = lss->maxidle; - cl->avgidle = lss->maxidle; - } - if (lss->change & TCF_CBQ_LSS_OFFTIME) - cl->offtime = lss->offtime; -} - -static void cbq_rmprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]--; - q->quanta[cl->priority] -= cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static void cbq_addprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]++; - q->quanta[cl->priority] += cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - - if (wrr->allot) - cl->allot = wrr->allot; - if (wrr->weight) - cl->weight = wrr->weight; - if (wrr->priority) { - cl->priority = wrr->priority - 1; - cl->cpriority = cl->priority; - if (cl->priority >= cl->priority2) - cl->priority2 = TC_CBQ_MAXPRIO - 1; - } - - cbq_addprio(q, cl); - return 0; -} - -static int cbq_set_fopt(struct cbq_class *cl, struct tc_cbq_fopt *fopt) -{ - cbq_change_defmap(cl, fopt->split, fopt->defmap, fopt->defchange); - return 0; -} - -static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = { - [TCA_CBQ_LSSOPT] = { .len = sizeof(struct tc_cbq_lssopt) }, - [TCA_CBQ_WRROPT] = { .len = sizeof(struct tc_cbq_wrropt) }, - [TCA_CBQ_FOPT] = { .len = sizeof(struct tc_cbq_fopt) }, - [TCA_CBQ_OVL_STRATEGY] = { .len = sizeof(struct tc_cbq_ovl) }, - [TCA_CBQ_RATE] = { .len = sizeof(struct tc_ratespec) }, - [TCA_CBQ_RTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, - [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, -}; - -static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1], - struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - int err; - - if (!opt) { - NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, - cbq_policy, extack); - if (err < 0) - return err; - - if (tb[TCA_CBQ_WRROPT]) { - const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]); - - if (wrr->priority > TC_CBQ_MAXPRIO) { - NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO"); - err = -EINVAL; - } - } - return err; -} - -static int cbq_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct tc_ratespec *r; - int err; - - qdisc_watchdog_init(&q->watchdog, sch); - - err = cbq_opt_parse(tb, opt, extack); - if (err < 0) - return err; - - if (!tb[TCA_CBQ_RTAB] || !tb[TCA_CBQ_RATE]) { - NL_SET_ERR_MSG(extack, "Rate specification missing or incomplete"); - return -EINVAL; - } - - r = nla_data(tb[TCA_CBQ_RATE]); - - q->link.R_tab = qdisc_get_rtab(r, tb[TCA_CBQ_RTAB], extack); - if (!q->link.R_tab) - return -EINVAL; - - err = tcf_block_get(&q->link.block, &q->link.filter_list, sch, extack); - if (err) - goto put_rtab; - - err = qdisc_class_hash_init(&q->clhash); - if (err < 0) - goto put_block; - - q->link.sibling = &q->link; - q->link.common.classid = sch->handle; - q->link.qdisc = sch; - q->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle, NULL); - if (!q->link.q) - q->link.q = &noop_qdisc; - else - qdisc_hash_add(q->link.q, true); - - q->link.priority = TC_CBQ_MAXPRIO - 1; - q->link.priority2 = TC_CBQ_MAXPRIO - 1; - q->link.cpriority = TC_CBQ_MAXPRIO - 1; - q->link.allot = psched_mtu(qdisc_dev(sch)); - q->link.quantum = q->link.allot; - q->link.weight = q->link.R_tab->rate.rate; - - q->link.ewma_log = TC_CBQ_DEF_EWMA; - q->link.avpkt = q->link.allot/2; - q->link.minidle = -0x7FFFFFFF; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - cbq_link_class(&q->link); - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(&q->link, nla_data(tb[TCA_CBQ_LSSOPT])); - - cbq_addprio(q, &q->link); - return 0; - -put_block: - tcf_block_put(q->link.block); - -put_rtab: - qdisc_put_rtab(q->link.R_tab); - return err; -} - -static int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - - if (nla_put(skb, TCA_CBQ_RATE, sizeof(cl->R_tab->rate), &cl->R_tab->rate)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_lssopt opt; - - opt.flags = 0; - if (cl->borrow == NULL) - opt.flags |= TCF_CBQ_LSS_BOUNDED; - if (cl->share == NULL) - opt.flags |= TCF_CBQ_LSS_ISOLATED; - opt.ewma_log = cl->ewma_log; - opt.level = cl->level; - opt.avpkt = cl->avpkt; - opt.maxidle = cl->maxidle; - opt.minidle = (u32)(-cl->minidle); - opt.offtime = cl->offtime; - opt.change = ~0; - if (nla_put(skb, TCA_CBQ_LSSOPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_wrropt opt; - - memset(&opt, 0, sizeof(opt)); - opt.flags = 0; - opt.allot = cl->allot; - opt.priority = cl->priority + 1; - opt.cpriority = cl->cpriority + 1; - opt.weight = cl->weight; - if (nla_put(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_fopt opt; - - if (cl->split || cl->defmap) { - opt.split = cl->split ? cl->split->common.classid : 0; - opt.defmap = cl->defmap; - opt.defchange = ~0; - if (nla_put(skb, TCA_CBQ_FOPT, sizeof(opt), &opt)) - goto nla_put_failure; - } - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl) -{ - if (cbq_dump_lss(skb, cl) < 0 || - cbq_dump_rate(skb, cl) < 0 || - cbq_dump_wrr(skb, cl) < 0 || - cbq_dump_fopt(skb, cl) < 0) - return -1; - return 0; -} - -static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *nest; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, &q->link) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - q->link.xstats.avgidle = q->link.avgidle; - return gnet_stats_copy_app(d, &q->link.xstats, sizeof(q->link.xstats)); -} - -static int -cbq_dump_class(struct Qdisc *sch, unsigned long arg, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - struct nlattr *nest; - - if (cl->tparent) - tcm->tcm_parent = cl->tparent->common.classid; - else - tcm->tcm_parent = TC_H_ROOT; - tcm->tcm_handle = cl->common.classid; - tcm->tcm_info = cl->q->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, cl) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - __u32 qlen; - - cl->xstats.avgidle = cl->avgidle; - cl->xstats.undertime = 0; - qdisc_qstats_qlen_backlog(cl->q, &qlen, &cl->qstats.backlog); - - if (cl->undertime != PSCHED_PASTPERFECT) - cl->xstats.undertime = cl->undertime - q->now; - - if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || - gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) - return -1; - - return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats)); -} - -static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old, struct netlink_ext_ack *extack) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->common.classid, extack); - if (new == NULL) - return -ENOBUFS; - } - - *old = qdisc_replace(sch, new, &cl->q); - return 0; -} - -static struct Qdisc *cbq_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - return cl->q; -} - -static void cbq_qlen_notify(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cbq_deactivate_class(cl); -} - -static unsigned long cbq_find(struct Qdisc *sch, u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - return (unsigned long)cbq_class_lookup(q, classid); -} - -static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - WARN_ON(cl->filters); - - tcf_block_put(cl->block); - qdisc_put(cl->q); - qdisc_put_rtab(cl->R_tab); - gen_kill_estimator(&cl->rate_est); - if (cl != &q->link) - kfree(cl); -} - -static void cbq_destroy(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct hlist_node *next; - struct cbq_class *cl; - unsigned int h; - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = NULL; -#endif - /* - * Filters must be destroyed first because we don't destroy the - * classes from root to leafs which means that filters can still - * be bound to classes which have been destroyed already. --TGR '04 - */ - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - tcf_block_put(cl->block); - cl->block = NULL; - } - } - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], - common.hnode) - cbq_destroy_class(sch, cl); - } - qdisc_class_hash_destroy(&q->clhash); -} - -static int -cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, - unsigned long *arg, struct netlink_ext_ack *extack) -{ - int err; - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)*arg; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct cbq_class *parent; - struct qdisc_rate_table *rtab = NULL; - - err = cbq_opt_parse(tb, opt, extack); - if (err < 0) - return err; - - if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE]) { - NL_SET_ERR_MSG(extack, "Neither overlimit strategy nor policing attributes can be used for changing class params"); - return -EOPNOTSUPP; - } - - if (cl) { - /* Check parent */ - if (parentid) { - if (cl->tparent && - cl->tparent->common.classid != parentid) { - NL_SET_ERR_MSG(extack, "Invalid parent id"); - return -EINVAL; - } - if (!cl->tparent && parentid != TC_H_ROOT) { - NL_SET_ERR_MSG(extack, "Parent must be root"); - return -EINVAL; - } - } - - if (tb[TCA_CBQ_RATE]) { - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), - tb[TCA_CBQ_RTAB], extack); - if (rtab == NULL) - return -EINVAL; - } - - if (tca[TCA_RATE]) { - err = gen_replace_estimator(&cl->bstats, NULL, - &cl->rate_est, - NULL, - true, - tca[TCA_RATE]); - if (err) { - NL_SET_ERR_MSG(extack, "Failed to replace specified rate estimator"); - qdisc_put_rtab(rtab); - return err; - } - } - - /* Change class parameters */ - sch_tree_lock(sch); - - if (cl->next_alive != NULL) - cbq_deactivate_class(cl); - - if (rtab) { - qdisc_put_rtab(cl->R_tab); - cl->R_tab = rtab; - } - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - - if (tb[TCA_CBQ_WRROPT]) { - cbq_rmprio(q, cl); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - } - - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - - if (cl->q->q.qlen) - cbq_activate_class(cl); - - sch_tree_unlock(sch); - - return 0; - } - - if (parentid == TC_H_ROOT) - return -EINVAL; - - if (!tb[TCA_CBQ_WRROPT] || !tb[TCA_CBQ_RATE] || !tb[TCA_CBQ_LSSOPT]) { - NL_SET_ERR_MSG(extack, "One of the following attributes MUST be specified: WRR, rate or link sharing"); - return -EINVAL; - } - - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), tb[TCA_CBQ_RTAB], - extack); - if (rtab == NULL) - return -EINVAL; - - if (classid) { - err = -EINVAL; - if (TC_H_MAJ(classid ^ sch->handle) || - cbq_class_lookup(q, classid)) { - NL_SET_ERR_MSG(extack, "Specified class not found"); - goto failure; - } - } else { - int i; - classid = TC_H_MAKE(sch->handle, 0x8000); - - for (i = 0; i < 0x8000; i++) { - if (++q->hgenerator >= 0x8000) - q->hgenerator = 1; - if (cbq_class_lookup(q, classid|q->hgenerator) == NULL) - break; - } - err = -ENOSR; - if (i >= 0x8000) { - NL_SET_ERR_MSG(extack, "Unable to generate classid"); - goto failure; - } - classid = classid|q->hgenerator; - } - - parent = &q->link; - if (parentid) { - parent = cbq_class_lookup(q, parentid); - err = -EINVAL; - if (!parent) { - NL_SET_ERR_MSG(extack, "Failed to find parentid"); - goto failure; - } - } - - err = -ENOBUFS; - cl = kzalloc(sizeof(*cl), GFP_KERNEL); - if (cl == NULL) - goto failure; - - gnet_stats_basic_sync_init(&cl->bstats); - err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); - if (err) { - kfree(cl); - goto failure; - } - - if (tca[TCA_RATE]) { - err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, true, tca[TCA_RATE]); - if (err) { - NL_SET_ERR_MSG(extack, "Couldn't create new estimator"); - tcf_block_put(cl->block); - kfree(cl); - goto failure; - } - } - - cl->R_tab = rtab; - rtab = NULL; - cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, - NULL); - if (!cl->q) - cl->q = &noop_qdisc; - else - qdisc_hash_add(cl->q, true); - - cl->common.classid = classid; - cl->tparent = parent; - cl->qdisc = sch; - cl->allot = parent->allot; - cl->quantum = cl->allot; - cl->weight = cl->R_tab->rate.rate; - - sch_tree_lock(sch); - cbq_link_class(cl); - cl->borrow = cl->tparent; - if (cl->tparent != &q->link) - cl->share = cl->tparent; - cbq_adjust_levels(parent); - cl->minidle = -0x7FFFFFFF; - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - if (cl->ewma_log == 0) - cl->ewma_log = q->link.ewma_log; - if (cl->maxidle == 0) - cl->maxidle = q->link.maxidle; - if (cl->avpkt == 0) - cl->avpkt = q->link.avpkt; - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); - - *arg = (unsigned long)cl; - return 0; - -failure: - qdisc_put_rtab(rtab); - return err; -} - -static int cbq_delete(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl->filters || cl->children || cl == &q->link) - return -EBUSY; - - sch_tree_lock(sch); - - qdisc_purge_queue(cl->q); - - if (cl->next_alive) - cbq_deactivate_class(cl); - - if (q->tx_borrowed == cl) - q->tx_borrowed = q->tx_class; - if (q->tx_class == cl) { - q->tx_class = NULL; - q->tx_borrowed = NULL; - } -#ifdef CONFIG_NET_CLS_ACT - if (q->rx_class == cl) - q->rx_class = NULL; -#endif - - cbq_unlink_class(cl); - cbq_adjust_levels(cl->tparent); - cl->defmap = 0; - cbq_sync_defmap(cl); - - cbq_rmprio(q, cl); - sch_tree_unlock(sch); - - cbq_destroy_class(sch, cl); - return 0; -} - -static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl == NULL) - cl = &q->link; - - return cl->block; -} - -static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, - u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *p = (struct cbq_class *)parent; - struct cbq_class *cl = cbq_class_lookup(q, classid); - - if (cl) { - if (p && p->level <= cl->level) - return 0; - cl->filters++; - return (unsigned long)cl; - } - return 0; -} - -static void cbq_unbind_filter(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cl->filters--; -} - -static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - unsigned int h; - - if (arg->stop) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg)) - return; - } - } -} - -static const struct Qdisc_class_ops cbq_class_ops = { - .graft = cbq_graft, - .leaf = cbq_leaf, - .qlen_notify = cbq_qlen_notify, - .find = cbq_find, - .change = cbq_change_class, - .delete = cbq_delete, - .walk = cbq_walk, - .tcf_block = cbq_tcf_block, - .bind_tcf = cbq_bind_filter, - .unbind_tcf = cbq_unbind_filter, - .dump = cbq_dump_class, - .dump_stats = cbq_dump_class_stats, -}; - -static struct Qdisc_ops cbq_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &cbq_class_ops, - .id = "cbq", - .priv_size = sizeof(struct cbq_sched_data), - .enqueue = cbq_enqueue, - .dequeue = cbq_dequeue, - .peek = qdisc_peek_dequeued, - .init = cbq_init, - .reset = cbq_reset, - .destroy = cbq_destroy, - .change = NULL, - .dump = cbq_dump, - .dump_stats = cbq_dump_stats, - .owner = THIS_MODULE, -}; - -static int __init cbq_module_init(void) -{ - return register_qdisc(&cbq_qdisc_ops); -} -static void __exit cbq_module_exit(void) -{ - unregister_qdisc(&cbq_qdisc_ops); -} -module_init(cbq_module_init) -module_exit(cbq_module_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c deleted file mode 100644 index 401ffaf87d62..000000000000 --- a/net/sched/sch_dsmark.c +++ /dev/null @@ -1,518 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* net/sched/sch_dsmark.c - Differentiated Services field marker */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/rtnetlink.h> -#include <linux/bitops.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <asm/byteorder.h> - -/* - * classid class marking - * ------- ----- ------- - * n/a 0 n/a - * x:0 1 use entry [0] - * ... ... ... - * x:y y>0 y+1 use entry [y] - * ... ... ... - * x:indices-1 indices use entry [indices-1] - * ... ... ... - * x:y y+1 use entry [y & (indices-1)] - * ... ... ... - * 0xffff 0x10000 use entry [indices-1] - */ - - -#define NO_DEFAULT_INDEX (1 << 16) - -struct mask_value { - u8 mask; - u8 value; -}; - -struct dsmark_qdisc_data { - struct Qdisc *q; - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct mask_value *mv; - u16 indices; - u8 set_tc_index; - u32 default_index; /* index range is 0...0xffff */ -#define DSMARK_EMBEDDED_SZ 16 - struct mask_value embedded[DSMARK_EMBEDDED_SZ]; -}; - -static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) -{ - return index <= p->indices && index > 0; -} - -/* ------------------------- Class/flow operations ------------------------- */ - -static int dsmark_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n", - __func__, sch, p, new, old); - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle, NULL); - if (new == NULL) - new = &noop_qdisc; - } - - *old = qdisc_replace(sch, new, &p->q); - return 0; -} - -static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - return p->q; -} - -static unsigned long dsmark_find(struct Qdisc *sch, u32 classid) -{ - return TC_H_MIN(classid) + 1; -} - -static unsigned long dsmark_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", - __func__, sch, qdisc_priv(sch), classid); - - return dsmark_find(sch, classid); -} - -static void dsmark_unbind_filter(struct Qdisc *sch, unsigned long cl) -{ -} - -static const struct nla_policy dsmark_policy[TCA_DSMARK_MAX + 1] = { - [TCA_DSMARK_INDICES] = { .type = NLA_U16 }, - [TCA_DSMARK_DEFAULT_INDEX] = { .type = NLA_U16 }, - [TCA_DSMARK_SET_TC_INDEX] = { .type = NLA_FLAG }, - [TCA_DSMARK_MASK] = { .type = NLA_U8 }, - [TCA_DSMARK_VALUE] = { .type = NLA_U8 }, -}; - -static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - - pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n", - __func__, sch, p, classid, parent, *arg); - - if (!dsmark_valid_index(p, *arg)) { - err = -ENOENT; - goto errout; - } - - if (!opt) - goto errout; - - err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt, - dsmark_policy, NULL); - if (err < 0) - goto errout; - - if (tb[TCA_DSMARK_VALUE]) - p->mv[*arg - 1].value = nla_get_u8(tb[TCA_DSMARK_VALUE]); - - if (tb[TCA_DSMARK_MASK]) - p->mv[*arg - 1].mask = nla_get_u8(tb[TCA_DSMARK_MASK]); - - err = 0; - -errout: - return err; -} - -static int dsmark_delete(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - if (!dsmark_valid_index(p, arg)) - return -EINVAL; - - p->mv[arg - 1].mask = 0xff; - p->mv[arg - 1].value = 0; - - return 0; -} - -static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int i; - - pr_debug("%s(sch %p,[qdisc %p],walker %p)\n", - __func__, sch, p, walker); - - if (walker->stop) - return; - - for (i = 0; i < p->indices; i++) { - if (p->mv[i].mask == 0xff && !p->mv[i].value) { - walker->count++; - continue; - } - if (!tc_qdisc_stats_dump(sch, i + 1, walker)) - break; - } -} - -static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - return p->block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - unsigned int len = qdisc_pkt_len(skb); - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p); - - if (p->set_tc_index) { - int wlen = skb_network_offset(skb); - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv4_get_dsfield(ip_hdr(skb)) - & ~INET_ECN_MASK; - break; - - case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb)) - & ~INET_ECN_MASK; - break; - default: - skb->tc_index = 0; - break; - } - } - - if (TC_H_MAJ(skb->priority) == sch->handle) - skb->tc_index = TC_H_MIN(skb->priority); - else { - struct tcf_result res; - struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tcf_classify(skb, NULL, fl, &res, false); - - pr_debug("result %d class 0x%04x\n", result, res.classid); - - switch (result) { -#ifdef CONFIG_NET_CLS_ACT - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - - case TC_ACT_SHOT: - goto drop; -#endif - case TC_ACT_OK: - skb->tc_index = TC_H_MIN(res.classid); - break; - - default: - if (p->default_index != NO_DEFAULT_INDEX) - skb->tc_index = p->default_index; - break; - } - } - - err = qdisc_enqueue(skb, p->q, to_free); - if (err != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(err)) - qdisc_qstats_drop(sch); - return err; - } - - sch->qstats.backlog += len; - sch->q.qlen++; - - return NET_XMIT_SUCCESS; - -drop: - qdisc_drop(skb, sch, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - u32 index; - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - skb = qdisc_dequeue_peeked(p->q); - if (skb == NULL) - return NULL; - - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - index = skb->tc_index & (p->indices - 1); - pr_debug("index %d->%d\n", skb->tc_index, index); - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - case htons(ETH_P_IPV6): - ipv6_change_dsfield(ipv6_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - default: - /* - * Only complain if a change was actually attempted. - * This way, we can send non-IP traffic through dsmark - * and don't need yet another qdisc as a bypass. - */ - if (p->mv[index].mask != 0xff || p->mv[index].value) - pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(skb_protocol(skb, true))); - break; - } - - return skb; -} - -static struct sk_buff *dsmark_peek(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - return p->q->ops->peek(p->q); -} - -static int dsmark_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - u32 default_index = NO_DEFAULT_INDEX; - u16 indices; - int i; - - pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt); - - if (!opt) - goto errout; - - err = tcf_block_get(&p->block, &p->filter_list, sch, extack); - if (err) - return err; - - err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt, - dsmark_policy, NULL); - if (err < 0) - goto errout; - - err = -EINVAL; - if (!tb[TCA_DSMARK_INDICES]) - goto errout; - indices = nla_get_u16(tb[TCA_DSMARK_INDICES]); - - if (hweight32(indices) != 1) - goto errout; - - if (tb[TCA_DSMARK_DEFAULT_INDEX]) - default_index = nla_get_u16(tb[TCA_DSMARK_DEFAULT_INDEX]); - - if (indices <= DSMARK_EMBEDDED_SZ) - p->mv = p->embedded; - else - p->mv = kmalloc_array(indices, sizeof(*p->mv), GFP_KERNEL); - if (!p->mv) { - err = -ENOMEM; - goto errout; - } - for (i = 0; i < indices; i++) { - p->mv[i].mask = 0xff; - p->mv[i].value = 0; - } - p->indices = indices; - p->default_index = default_index; - p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]); - - p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, - NULL); - if (p->q == NULL) - p->q = &noop_qdisc; - else - qdisc_hash_add(p->q, true); - - pr_debug("%s: qdisc %p\n", __func__, p->q); - - err = 0; -errout: - return err; -} - -static void dsmark_reset(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - if (p->q) - qdisc_reset(p->q); -} - -static void dsmark_destroy(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - tcf_block_put(p->block); - qdisc_put(p->q); - if (p->mv != p->embedded) - kfree(p->mv); -} - -static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl); - - if (!dsmark_valid_index(p, cl)) - return -EINVAL; - - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1); - tcm->tcm_info = p->q->handle; - - opts = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) || - nla_put_u8(skb, TCA_DSMARK_VALUE, p->mv[cl - 1].value)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - opts = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices)) - goto nla_put_failure; - - if (p->default_index != NO_DEFAULT_INDEX && - nla_put_u16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index)) - goto nla_put_failure; - - if (p->set_tc_index && - nla_put_flag(skb, TCA_DSMARK_SET_TC_INDEX)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static const struct Qdisc_class_ops dsmark_class_ops = { - .graft = dsmark_graft, - .leaf = dsmark_leaf, - .find = dsmark_find, - .change = dsmark_change, - .delete = dsmark_delete, - .walk = dsmark_walk, - .tcf_block = dsmark_tcf_block, - .bind_tcf = dsmark_bind_filter, - .unbind_tcf = dsmark_unbind_filter, - .dump = dsmark_dump_class, -}; - -static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &dsmark_class_ops, - .id = "dsmark", - .priv_size = sizeof(struct dsmark_qdisc_data), - .enqueue = dsmark_enqueue, - .dequeue = dsmark_dequeue, - .peek = dsmark_peek, - .init = dsmark_init, - .reset = dsmark_reset, - .destroy = dsmark_destroy, - .change = NULL, - .dump = dsmark_dump, - .owner = THIS_MODULE, -}; - -static int __init dsmark_module_init(void) -{ - return register_qdisc(&dsmark_qdisc_ops); -} - -static void __exit dsmark_module_exit(void) -{ - unregister_qdisc(&dsmark_qdisc_ops); -} - -module_init(dsmark_module_init) -module_exit(dsmark_module_exit) - -MODULE_LICENSE("GPL"); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e25dc1709131..237a6b04adf6 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2098,6 +2098,13 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, pr_debug("%s: sk:%p, msghdr:%p, len:%zd, flags:0x%x, addr_len:%p)\n", __func__, sk, msg, len, flags, addr_len); + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + + if (sk_can_busy_loop(sk) && + skb_queue_empty_lockless(&sk->sk_receive_queue)) + sk_busy_loop(sk, flags & MSG_DONTWAIT); + lock_sock(sk); if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED) && @@ -9038,12 +9045,6 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, int *err) if (sk->sk_shutdown & RCV_SHUTDOWN) break; - if (sk_can_busy_loop(sk)) { - sk_busy_loop(sk, flags & MSG_DONTWAIT); - - if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) - continue; - } /* User doesn't want to wait. */ error = -EAGAIN; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 9b8999e2afca..867df4522815 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -155,10 +155,12 @@ static int smc_clc_ueid_remove(char *ueid) rc = 0; } } +#if IS_ENABLED(CONFIG_S390) if (!rc && !smc_clc_eid_table.ueid_cnt) { smc_clc_eid_table.seid_enabled = 1; rc = -EAGAIN; /* indicate success and enabling of seid */ } +#endif write_unlock(&smc_clc_eid_table.lock); return rc; } @@ -273,22 +275,30 @@ err: int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info) { +#if IS_ENABLED(CONFIG_S390) write_lock(&smc_clc_eid_table.lock); smc_clc_eid_table.seid_enabled = 1; write_unlock(&smc_clc_eid_table.lock); return 0; +#else + return -EOPNOTSUPP; +#endif } int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info) { int rc = 0; +#if IS_ENABLED(CONFIG_S390) write_lock(&smc_clc_eid_table.lock); if (!smc_clc_eid_table.ueid_cnt) rc = -ENOENT; else smc_clc_eid_table.seid_enabled = 0; write_unlock(&smc_clc_eid_table.lock); +#else + rc = -EOPNOTSUPP; +#endif return rc; } @@ -1168,7 +1178,11 @@ void __init smc_clc_init(void) INIT_LIST_HEAD(&smc_clc_eid_table.list); rwlock_init(&smc_clc_eid_table.lock); smc_clc_eid_table.ueid_cnt = 0; +#if IS_ENABLED(CONFIG_S390) smc_clc_eid_table.seid_enabled = 1; +#else + smc_clc_eid_table.seid_enabled = 0; +#endif } void smc_clc_exit(void) diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 80ea7d954ece..7a907186a33a 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -153,8 +153,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, .lnk[0].link_id = link->link_id, }; - memcpy(linfo.lnk[0].ibname, - smc->conn.lgr->lnk[0].smcibdev->ibdev->name, + memcpy(linfo.lnk[0].ibname, link->smcibdev->ibdev->name, sizeof(link->smcibdev->ibdev->name)); smc_gid_be16_convert(linfo.lnk[0].gid, link->gid); smc_gid_be16_convert(linfo.lnk[0].peer_gid, link->peer_gid); @@ -164,7 +163,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, } if (smc_conn_lgr_valid(&smc->conn) && smc->conn.lgr->is_smcd && (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && - !list_empty(&smc->conn.lgr->list)) { + !list_empty(&smc->conn.lgr->list) && smc->conn.rmb_desc) { struct smc_connection *conn = &smc->conn; struct smcd_diag_dmbinfo dinfo; diff --git a/net/socket.c b/net/socket.c index 04cba91c7cbe..639d76f20384 100644 --- a/net/socket.c +++ b/net/socket.c @@ -130,6 +130,7 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +static void sock_splice_eof(struct file *file); #ifdef CONFIG_PROC_FS static void sock_show_fdinfo(struct seq_file *m, struct file *f) @@ -164,6 +165,7 @@ static const struct file_operations socket_file_ops = { .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, .splice_read = sock_splice_read, + .splice_eof = sock_splice_eof, .show_fdinfo = sock_show_fdinfo, }; @@ -740,6 +742,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; struct sockaddr_storage address; + int save_len = msg->msg_namelen; int ret; if (msg->msg_name) { @@ -749,6 +752,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg) ret = __sock_sendmsg(sock, msg); msg->msg_name = save_addr; + msg->msg_namelen = save_len; return ret; } @@ -826,7 +830,7 @@ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index) { - bool cycles = sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC; + bool cycles = READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); struct net_device *orig_dev; ktime_t hwtstamp; @@ -878,12 +882,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); struct scm_timestamping_internal tss; - int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); int if_index; ktime_t hwtstamp; + u32 tsflags; /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ @@ -925,11 +929,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, } memset(&tss, 0, sizeof(tss)); - if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) && + tsflags = READ_ONCE(sk->sk_tsflags); + if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && - (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && + (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && !skb_is_swtx_tstamp(skb, false_tstamp)) { if_index = 0; if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) @@ -937,14 +942,14 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, else hwtstamp = shhwtstamps->hwtstamp; - if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC) + if (tsflags & SOF_TIMESTAMPING_BIND_PHC) hwtstamp = ptp_convert_timestamp(&hwtstamp, - sk->sk_bind_phc); + READ_ONCE(sk->sk_bind_phc)); if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) { empty = 0; - if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && + if ((tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && !skb_is_err_queue(skb)) put_ts_pktinfo(msg, skb, if_index); } @@ -1088,6 +1093,14 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, return sock->ops->splice_read(sock, ppos, pipe, len, flags); } +static void sock_splice_eof(struct file *file) +{ + struct socket *sock = file->private_data; + + if (sock->ops->splice_eof) + sock->ops->splice_eof(sock); +} + static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; @@ -2128,6 +2141,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = addr_len; } + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; @@ -2479,6 +2493,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, msg_sys->msg_control = ctl_buf; msg_sys->msg_control_is_user = false; } + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg_sys->msg_flags = flags; if (sock->file->f_flags & O_NONBLOCK) diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c index 701250b305db..720d3ba742ec 100644 --- a/net/sunrpc/xprtmultipath.c +++ b/net/sunrpc/xprtmultipath.c @@ -284,7 +284,7 @@ struct rpc_xprt *_xprt_switch_find_current_entry(struct list_head *head, if (cur == pos) found = true; if (found && ((find_active && xprt_is_active(pos)) || - (!find_active && xprt_is_active(pos)))) + (!find_active && !xprt_is_active(pos)))) return pos; } return NULL; @@ -336,8 +336,9 @@ struct rpc_xprt *xprt_iter_current_entry_offline(struct rpc_xprt_iter *xpi) xprt_switch_find_current_entry_offline); } -bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, - const struct sockaddr *sap) +static +bool __rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap) { struct list_head *head; struct rpc_xprt *pos; @@ -356,6 +357,18 @@ bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, return false; } +bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap) +{ + bool res; + + rcu_read_lock(); + res = __rpc_xprt_switch_has_addr(xps, sap); + rcu_read_unlock(); + + return res; +} + static struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head, const struct rpc_xprt *cur, bool check_active) diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8cc42aea19c7..2e14d4c37e2d 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -19,6 +19,35 @@ #include <linux/rtnetlink.h> #include <net/switchdev.h> +static bool switchdev_obj_eq(const struct switchdev_obj *a, + const struct switchdev_obj *b) +{ + const struct switchdev_obj_port_vlan *va, *vb; + const struct switchdev_obj_port_mdb *ma, *mb; + + if (a->id != b->id || a->orig_dev != b->orig_dev) + return false; + + switch (a->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + va = SWITCHDEV_OBJ_PORT_VLAN(a); + vb = SWITCHDEV_OBJ_PORT_VLAN(b); + return va->flags == vb->flags && + va->vid == vb->vid && + va->changed == vb->changed; + case SWITCHDEV_OBJ_ID_PORT_MDB: + case SWITCHDEV_OBJ_ID_HOST_MDB: + ma = SWITCHDEV_OBJ_PORT_MDB(a); + mb = SWITCHDEV_OBJ_PORT_MDB(b); + return ma->vid == mb->vid && + ether_addr_equal(ma->addr, mb->addr); + default: + break; + } + + BUG(); +} + static LIST_HEAD(deferred); static DEFINE_SPINLOCK(deferred_lock); @@ -307,6 +336,50 @@ int switchdev_port_obj_del(struct net_device *dev, } EXPORT_SYMBOL_GPL(switchdev_port_obj_del); +/** + * switchdev_port_obj_act_is_deferred - Is object action pending? + * + * @dev: port device + * @nt: type of action; add or delete + * @obj: object to test + * + * Returns true if a deferred item is pending, which is + * equivalent to the action @nt on an object @obj. + * + * rtnl_lock must be held. + */ +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj) +{ + struct switchdev_deferred_item *dfitem; + bool found = false; + + ASSERT_RTNL(); + + spin_lock_bh(&deferred_lock); + + list_for_each_entry(dfitem, &deferred, list) { + if (dfitem->dev != dev) + continue; + + if ((dfitem->func == switchdev_port_obj_add_deferred && + nt == SWITCHDEV_PORT_OBJ_ADD) || + (dfitem->func == switchdev_port_obj_del_deferred && + nt == SWITCHDEV_PORT_OBJ_DEL)) { + if (switchdev_obj_eq((const void *)dfitem->data, obj)) { + found = true; + break; + } + } + } + + spin_unlock_bh(&deferred_lock); + + return found; +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred); + static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index cdcd2731860b..1cb993562088 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1088,6 +1088,12 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_TIPC_MEDIA_UDP if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) { + if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { + rtnl_unlock(); + NL_SET_ERR_MSG(info->extack, "UDP option is unsupported"); + return -EINVAL; + } + err = tipc_udp_nl_bearer_add(b, attrs[TIPC_NLA_BEARER_UDP_OPTS]); if (err) { diff --git a/net/tls/tls.h b/net/tls/tls.h index 0672acab2773..4922668fefaa 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -97,6 +97,7 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +void tls_sw_splice_eof(struct socket *sock); int tls_sw_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tls_sw_sendpage(struct sock *sk, struct page *page, diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 338a443fa47b..6b7189a520af 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -922,6 +922,7 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG] ops[TLS_BASE][TLS_BASE] = *base; ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_SW ][TLS_BASE].splice_eof = tls_sw_splice_eof; ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked; ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; @@ -990,6 +991,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg; + prot[TLS_SW][TLS_BASE].splice_eof = tls_sw_splice_eof; prot[TLS_SW][TLS_BASE].sendpage = tls_sw_sendpage; prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE]; @@ -1096,7 +1098,7 @@ static u16 tls_user_config(struct tls_context *ctx, bool tx) return 0; } -static int tls_get_info(const struct sock *sk, struct sk_buff *skb) +static int tls_get_info(struct sock *sk, struct sk_buff *skb) { u16 version, cipher_type; struct tls_context *ctx; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 0323040d34bc..93e1bfa72d79 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -62,6 +62,7 @@ struct tls_decrypt_ctx { u8 iv[MAX_IV_SIZE]; u8 aad[TLS_MAX_AAD_SIZE]; u8 tail; + bool free_sgout; struct scatterlist sg[]; }; @@ -186,7 +187,6 @@ static void tls_decrypt_done(crypto_completion_data_t *data, int err) struct aead_request *aead_req = crypto_get_completion_data(data); struct crypto_aead *aead = crypto_aead_reqtfm(aead_req); struct scatterlist *sgout = aead_req->dst; - struct scatterlist *sgin = aead_req->src; struct tls_sw_context_rx *ctx; struct tls_decrypt_ctx *dctx; struct tls_context *tls_ctx; @@ -212,7 +212,7 @@ static void tls_decrypt_done(crypto_completion_data_t *data, int err) } /* Free the destination pages if skb was not decrypted inplace */ - if (sgout != sgin) { + if (dctx->free_sgout) { /* Skip the first S/G entry as it points to AAD */ for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { if (!sg) @@ -223,10 +223,17 @@ static void tls_decrypt_done(crypto_completion_data_t *data, int err) kfree(aead_req); - spin_lock_bh(&ctx->decrypt_compl_lock); - if (!atomic_dec_return(&ctx->decrypt_pending)) + if (atomic_dec_and_test(&ctx->decrypt_pending)) complete(&ctx->async_wait.completion); - spin_unlock_bh(&ctx->decrypt_compl_lock); +} + +static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx) +{ + if (!atomic_dec_and_test(&ctx->decrypt_pending)) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + atomic_inc(&ctx->decrypt_pending); + + return ctx->async_wait.err; } static int tls_do_decryption(struct sock *sk, @@ -252,6 +259,7 @@ static int tls_do_decryption(struct sock *sk, aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, tls_decrypt_done, aead_req); + DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->decrypt_pending) < 1); atomic_inc(&ctx->decrypt_pending); } else { aead_request_set_callback(aead_req, @@ -441,7 +449,6 @@ static void tls_encrypt_done(crypto_completion_data_t *data, int err) struct tls_rec *rec; bool ready = false; struct sock *sk; - int pending; rec = container_of(aead_req, struct tls_rec, aead_req); msg_en = &rec->msg_encrypted; @@ -481,12 +488,8 @@ static void tls_encrypt_done(crypto_completion_data_t *data, int err) ready = true; } - spin_lock_bh(&ctx->encrypt_compl_lock); - pending = atomic_dec_return(&ctx->encrypt_pending); - - if (!pending && ctx->async_notify) + if (atomic_dec_and_test(&ctx->encrypt_pending)) complete(&ctx->async_wait.completion); - spin_unlock_bh(&ctx->encrypt_compl_lock); if (!ready) return; @@ -496,6 +499,15 @@ static void tls_encrypt_done(crypto_completion_data_t *data, int err) schedule_delayed_work(&ctx->tx_work.work, 1); } +static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx) +{ + if (!atomic_dec_and_test(&ctx->encrypt_pending)) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + atomic_inc(&ctx->encrypt_pending); + + return ctx->async_wait.err; +} + static int tls_do_encryption(struct sock *sk, struct tls_context *tls_ctx, struct tls_sw_context_tx *ctx, @@ -542,6 +554,7 @@ static int tls_do_encryption(struct sock *sk, /* Add the record in tx_list */ list_add_tail((struct list_head *)&rec->list, &ctx->tx_list); + DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->encrypt_pending) < 1); atomic_inc(&ctx->encrypt_pending); rc = crypto_aead_encrypt(aead_req); @@ -953,7 +966,6 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int num_zc = 0; int orig_size; int ret = 0; - int pending; if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_CMSG_COMPAT)) @@ -1122,24 +1134,12 @@ trim_sgl: if (!num_async) { goto send_end; } else if (num_zc) { - /* Wait for pending encryptions to get completed */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - else - reinit_completion(&ctx->async_wait.completion); - - /* There can be no concurrent accesses, since we have no - * pending encrypt operations - */ - WRITE_ONCE(ctx->async_notify, false); + int err; - if (ctx->async_wait.err) { - ret = ctx->async_wait.err; + /* Wait for pending encryptions to get completed */ + err = tls_encrypt_async_wait(ctx); + if (err) { + ret = err; copied = 0; } } @@ -1158,6 +1158,67 @@ send_end: return copied > 0 ? copied : ret; } +/* + * Handle unexpected EOF during splice without SPLICE_F_MORE set. + */ +void tls_sw_splice_eof(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec; + struct sk_msg *msg_pl; + ssize_t copied = 0; + bool retrying = false; + int ret = 0; + + if (!ctx->open_rec) + return; + + mutex_lock(&tls_ctx->tx_lock); + lock_sock(sk); + +retry: + /* same checks as in tls_sw_push_pending_record() */ + rec = ctx->open_rec; + if (!rec) + goto unlock; + + msg_pl = &rec->msg_plaintext; + if (msg_pl->sg.size == 0) + goto unlock; + + /* Check the BPF advisor and perform transmission. */ + ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA, + &copied, 0); + switch (ret) { + case 0: + case -EAGAIN: + if (retrying) + goto unlock; + retrying = true; + goto retry; + case -EINPROGRESS: + break; + default: + goto unlock; + } + + /* Wait for pending encryptions to get completed */ + if (tls_encrypt_async_wait(ctx)) + goto unlock; + + /* Transmit if any encryptions have completed */ + if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) { + cancel_delayed_work(&ctx->tx_work.work); + tls_tx_records(sk, 0); + } + +unlock: + release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); +} + static int tls_sw_do_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -1595,6 +1656,7 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov, } else if (out_sg) { memcpy(sgout, out_sg, n_sgout * sizeof(*sgout)); } + dctx->free_sgout = !!pages; /* Prepare and submit AEAD request */ err = tls_do_decryption(sk, sgin, sgout, dctx->iv, @@ -1783,7 +1845,8 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, u8 *control, size_t skip, size_t len, - bool is_peek) + bool is_peek, + bool *more) { struct sk_buff *skb = skb_peek(&ctx->rx_list); struct tls_msg *tlm; @@ -1796,7 +1859,7 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, err = tls_record_content_type(msg, tlm, control); if (err <= 0) - goto out; + goto more; if (skip < rxm->full_len) break; @@ -1814,12 +1877,12 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, err = tls_record_content_type(msg, tlm, control); if (err <= 0) - goto out; + goto more; err = skb_copy_datagram_msg(skb, rxm->offset + skip, msg, chunk); if (err < 0) - goto out; + goto more; len = len - chunk; copied = copied + chunk; @@ -1855,6 +1918,10 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, out: return copied ? : err; +more: + if (more) + *more = true; + goto out; } static bool @@ -1958,6 +2025,7 @@ int tls_sw_recvmsg(struct sock *sk, int target, err; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool is_peek = flags & MSG_PEEK; + bool rx_more = false; bool released = true; bool bpf_strp_enabled; bool zc_capable; @@ -1977,12 +2045,12 @@ int tls_sw_recvmsg(struct sock *sk, goto end; /* Process pending decrypted records. It must be non-zero-copy */ - err = process_rx_list(ctx, msg, &control, 0, len, is_peek); + err = process_rx_list(ctx, msg, &control, 0, len, is_peek, &rx_more); if (err < 0) goto end; copied = err; - if (len <= copied) + if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more) goto end; target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); @@ -2075,6 +2143,8 @@ put_on_rx_list: decrypted += chunk; len -= chunk; __skb_queue_tail(&ctx->rx_list, skb); + if (unlikely(control != TLS_RECORD_TYPE_DATA)) + break; continue; } @@ -2123,16 +2193,10 @@ put_on_rx_list: recv_end: if (async) { - int ret, pending; + int ret; /* Wait for all previously submitted records to be decrypted */ - spin_lock_bh(&ctx->decrypt_compl_lock); - reinit_completion(&ctx->async_wait.completion); - pending = atomic_read(&ctx->decrypt_pending); - spin_unlock_bh(&ctx->decrypt_compl_lock); - ret = 0; - if (pending) - ret = crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + ret = tls_decrypt_async_wait(ctx); __skb_queue_purge(&ctx->async_hold); if (ret) { @@ -2145,11 +2209,10 @@ recv_end: /* Drain records from the rx_list & copy if required */ if (is_peek || is_kvec) err = process_rx_list(ctx, msg, &control, copied, - decrypted, is_peek); + decrypted, is_peek, NULL); else err = process_rx_list(ctx, msg, &control, 0, - async_copy_bytes, is_peek); - decrypted += max(err, 0); + async_copy_bytes, is_peek, NULL); } copied += decrypted; @@ -2351,16 +2414,9 @@ void tls_sw_release_resources_tx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec, *tmp; - int pending; /* Wait for any pending async encryptions to complete */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + tls_encrypt_async_wait(ctx); tls_tx_records(sk, -1); @@ -2513,6 +2569,48 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx) tls_ctx->prot_info.version != TLS_1_3_VERSION; } +static struct tls_sw_context_tx *init_ctx_tx(struct tls_context *ctx, struct sock *sk) +{ + struct tls_sw_context_tx *sw_ctx_tx; + + if (!ctx->priv_ctx_tx) { + sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL); + if (!sw_ctx_tx) + return NULL; + } else { + sw_ctx_tx = ctx->priv_ctx_tx; + } + + crypto_init_wait(&sw_ctx_tx->async_wait); + atomic_set(&sw_ctx_tx->encrypt_pending, 1); + INIT_LIST_HEAD(&sw_ctx_tx->tx_list); + INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler); + sw_ctx_tx->tx_work.sk = sk; + + return sw_ctx_tx; +} + +static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx) +{ + struct tls_sw_context_rx *sw_ctx_rx; + + if (!ctx->priv_ctx_rx) { + sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL); + if (!sw_ctx_rx) + return NULL; + } else { + sw_ctx_rx = ctx->priv_ctx_rx; + } + + crypto_init_wait(&sw_ctx_rx->async_wait); + atomic_set(&sw_ctx_rx->decrypt_pending, 1); + init_waitqueue_head(&sw_ctx_rx->wq); + skb_queue_head_init(&sw_ctx_rx->rx_list); + skb_queue_head_init(&sw_ctx_rx->async_hold); + + return sw_ctx_rx; +} + int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -2534,48 +2632,22 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) } if (tx) { - if (!ctx->priv_ctx_tx) { - sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL); - if (!sw_ctx_tx) { - rc = -ENOMEM; - goto out; - } - ctx->priv_ctx_tx = sw_ctx_tx; - } else { - sw_ctx_tx = - (struct tls_sw_context_tx *)ctx->priv_ctx_tx; - } - } else { - if (!ctx->priv_ctx_rx) { - sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL); - if (!sw_ctx_rx) { - rc = -ENOMEM; - goto out; - } - ctx->priv_ctx_rx = sw_ctx_rx; - } else { - sw_ctx_rx = - (struct tls_sw_context_rx *)ctx->priv_ctx_rx; - } - } + ctx->priv_ctx_tx = init_ctx_tx(ctx, sk); + if (!ctx->priv_ctx_tx) + return -ENOMEM; - if (tx) { - crypto_init_wait(&sw_ctx_tx->async_wait); - spin_lock_init(&sw_ctx_tx->encrypt_compl_lock); + sw_ctx_tx = ctx->priv_ctx_tx; crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; - INIT_LIST_HEAD(&sw_ctx_tx->tx_list); - INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler); - sw_ctx_tx->tx_work.sk = sk; } else { - crypto_init_wait(&sw_ctx_rx->async_wait); - spin_lock_init(&sw_ctx_rx->decrypt_compl_lock); - init_waitqueue_head(&sw_ctx_rx->wq); + ctx->priv_ctx_rx = init_ctx_rx(ctx); + if (!ctx->priv_ctx_rx) + return -ENOMEM; + + sw_ctx_rx = ctx->priv_ctx_rx; crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; - skb_queue_head_init(&sw_ctx_rx->rx_list); - skb_queue_head_init(&sw_ctx_rx->async_hold); aead = &sw_ctx_rx->aead_recv; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 6dbeb8007333..e1af94393789 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -211,8 +211,6 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb) } #endif /* CONFIG_SECURITY_NETWORK */ -#define unix_peer(sk) (unix_sk(sk)->peer) - static inline int unix_our_peer(struct sock *sk, struct sock *osk) { return unix_peer(osk) == sk; @@ -1324,13 +1322,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) unix_state_lock(sk1); return; } - if (sk1 < sk2) { - unix_state_lock(sk1); - unix_state_lock_nested(sk2); - } else { - unix_state_lock(sk2); - unix_state_lock_nested(sk1); - } + if (sk1 > sk2) + swap(sk1, sk2); + + unix_state_lock(sk1); + unix_state_lock_nested(sk2, U_LOCK_SECOND); } static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) @@ -1561,7 +1557,7 @@ restart: goto out_unlock; } - unix_state_lock_nested(sk); + unix_state_lock_nested(sk, U_LOCK_SECOND); if (sk->sk_state != st) { unix_state_unlock(sk); diff --git a/net/unix/diag.c b/net/unix/diag.c index 616b55c5b890..3438b7af09af 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -84,7 +84,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) * queue lock. With the other's queue locked it's * OK to lock the state. */ - unix_state_lock_nested(req); + unix_state_lock_nested(req, U_LOCK_DIAG); peer = unix_sk(req)->peer; buf[i++] = (peer ? sock_i_ino(peer) : 0); unix_state_unlock(req); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index dc2763540393..767b338a7a2d 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -314,6 +314,17 @@ void unix_gc(void) /* Here we are. Hitlist is filled. Die. */ __skb_queue_purge(&hitlist); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + list_for_each_entry_safe(u, next, &gc_candidates, link) { + struct sk_buff *skb = u->oob_skb; + + if (skb) { + u->oob_skb = NULL; + kfree_skb(skb); + } + } +#endif + spin_lock(&unix_gc_lock); /* There could be io_uring registered files, just push them back to diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index 2f9d8271c6ec..bd84785bf8d6 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -159,12 +159,32 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { + struct sock *sk_pair; + + /* Restore does not decrement the sk_pair reference yet because we must + * keep the a reference to the socket until after an RCU grace period + * and any pending sends have completed. + */ if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } + /* psock_update_sk_prot can be called multiple times if psock is + * added to multiple maps and/or slots in the same map. There is + * also an edge case where replacing a psock with itself can trigger + * an extra psock_update_sk_prot during the insert process. So it + * must be safe to do multiple calls. Here we need to ensure we don't + * increment the refcnt through sock_hold many times. There will only + * be a single matching destroy operation. + */ + if (!psock->sk_pair) { + sk_pair = unix_peer(sk); + sock_hold(sk_pair); + psock->sk_pair = sk_pair; + } + unix_stream_bpf_check_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &unix_stream_bpf_prot); return 0; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 2e25890ca52d..9983b833b55d 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -366,6 +366,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, struct virtio_vsock_sock *vvs = vsk->trans; size_t bytes, total = 0; struct sk_buff *skb; + u32 fwd_cnt_delta; + bool low_rx_bytes; int err = -EFAULT; u32 free_space; @@ -400,7 +402,10 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, } } - free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt); + fwd_cnt_delta = vvs->fwd_cnt - vvs->last_fwd_cnt; + free_space = vvs->buf_alloc - fwd_cnt_delta; + low_rx_bytes = (vvs->rx_bytes < + sock_rcvlowat(sk_vsock(vsk), 0, INT_MAX)); spin_unlock_bh(&vvs->rx_lock); @@ -410,9 +415,11 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, * too high causes extra messages. Too low causes transmitter * stalls. As stalls are in theory more expensive than extra * messages, we set the limit to a high value. TODO: experiment - * with different values. + * with different values. Also send credit update message when + * number of bytes in rx queue is not enough to wake up reader. */ - if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) + if (fwd_cnt_delta && + (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE || low_rx_bytes)) virtio_transport_send_credit_update(vsk); return total; diff --git a/net/wireless/core.c b/net/wireless/core.c index 63d75fecc2c5..3fcddc8687ed 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -216,7 +216,9 @@ static void cfg80211_rfkill_poll(struct rfkill *rfkill, void *data) { struct cfg80211_registered_device *rdev = data; + wiphy_lock(&rdev->wiphy); rdev_rfkill_poll(rdev); + wiphy_unlock(&rdev->wiphy); } void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, @@ -1669,6 +1671,7 @@ void wiphy_delayed_work_queue(struct wiphy *wiphy, unsigned long delay) { if (!delay) { + del_timer(&dwork->timer); wiphy_work_queue(wiphy, &dwork->work); return; } diff --git a/net/wireless/core.h b/net/wireless/core.h index e1accacc6f23..ee980965a7cf 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -297,6 +297,7 @@ struct cfg80211_cqm_config { u32 rssi_hyst; s32 last_rssi_event_value; enum nl80211_cqm_rssi_threshold_event last_rssi_event_type; + bool use_range_api; int n_rssi_thresholds; s32 rssi_thresholds[]; }; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b19b5acfaf3a..c259d3227a9e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3960,6 +3960,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * if_idx++; } + if_start = 0; wp_idx++; } out: @@ -12574,10 +12575,6 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, int i, n, low_index; int err; - /* RSSI reporting disabled? */ - if (!cqm_config) - return rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0); - /* * Obtain current RSSI value if possible, if not and no RSSI threshold * event has been received yet, we should receive an event after a @@ -12652,18 +12649,6 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) return -EOPNOTSUPP; - if (n_thresholds <= 1 && rdev->ops->set_cqm_rssi_config) { - if (n_thresholds == 0 || thresholds[0] == 0) /* Disabling */ - return rdev_set_cqm_rssi_config(rdev, dev, 0, 0); - - return rdev_set_cqm_rssi_config(rdev, dev, - thresholds[0], hysteresis); - } - - if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_CQM_RSSI_LIST)) - return -EOPNOTSUPP; - if (n_thresholds == 1 && thresholds[0] == 0) /* Disabling */ n_thresholds = 0; @@ -12671,6 +12656,26 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, old = rcu_dereference_protected(wdev->cqm_config, lockdep_is_held(&wdev->mtx)); + /* if already disabled just succeed */ + if (!n_thresholds && !old) { + err = 0; + goto unlock; + } + + if (n_thresholds > 1) { + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_CQM_RSSI_LIST) || + !rdev->ops->set_cqm_rssi_range_config) { + err = -EOPNOTSUPP; + goto unlock; + } + } else { + if (!rdev->ops->set_cqm_rssi_config) { + err = -EOPNOTSUPP; + goto unlock; + } + } + if (n_thresholds) { cqm_config = kzalloc(struct_size(cqm_config, rssi_thresholds, n_thresholds), @@ -12685,13 +12690,26 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, memcpy(cqm_config->rssi_thresholds, thresholds, flex_array_size(cqm_config, rssi_thresholds, n_thresholds)); + cqm_config->use_range_api = n_thresholds > 1 || + !rdev->ops->set_cqm_rssi_config; rcu_assign_pointer(wdev->cqm_config, cqm_config); + + if (cqm_config->use_range_api) + err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config); + else + err = rdev_set_cqm_rssi_config(rdev, dev, + thresholds[0], + hysteresis); } else { RCU_INIT_POINTER(wdev->cqm_config, NULL); + /* if enabled as range also disable via range */ + if (old->use_range_api) + err = rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0); + else + err = rdev_set_cqm_rssi_config(rdev, dev, 0, 0); } - err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config); if (err) { rcu_assign_pointer(wdev->cqm_config, old); kfree_rcu(cqm_config, rcu_head); @@ -18758,10 +18776,11 @@ void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, struct wiphy_work *work) wdev_lock(wdev); cqm_config = rcu_dereference_protected(wdev->cqm_config, lockdep_is_held(&wdev->mtx)); - if (!wdev->cqm_config) + if (!cqm_config) goto unlock; - cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config); + if (cqm_config->use_range_api) + cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config); rssi_level = cqm_config->last_rssi_event_value; rssi_event = cqm_config->last_rssi_event_type; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index b7e1631b3d80..3ad4c1032c03 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1810,8 +1810,12 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, list_add(&new->hidden_list, &hidden->hidden_list); hidden->refcount++; + + ies = (void *)rcu_access_pointer(new->pub.beacon_ies); rcu_assign_pointer(new->pub.beacon_ies, hidden->pub.beacon_ies); + if (ies) + kfree_rcu(ies, rcu_head); } } else { /* diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index ac1a645afa8d..d0320e35accb 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -180,6 +180,8 @@ static int xfrm4_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb) int optlen = 0; int err = -EINVAL; + skb->protocol = htons(ETH_P_IP); + if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) { struct ip_beet_phdr *ph; int phlen; @@ -232,8 +234,7 @@ static int xfrm4_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; - if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) - goto out; + skb->protocol = htons(ETH_P_IP); if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; @@ -270,8 +271,8 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; - if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) - goto out; + skb->protocol = htons(ETH_P_IPV6); + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; @@ -301,6 +302,8 @@ static int xfrm6_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb) int size = sizeof(struct ipv6hdr); int err; + skb->protocol = htons(ETH_P_IPV6); + err = skb_cow_head(skb, size + skb->mac_len); if (err) goto out; @@ -332,22 +335,26 @@ out: */ static int xfrm_inner_mode_encap_remove(struct xfrm_state *x, - const struct xfrm_mode *inner_mode, struct sk_buff *skb) { - switch (inner_mode->encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: - if (inner_mode->family == AF_INET) + switch (x->sel.family) { + case AF_INET: return xfrm4_remove_beet_encap(x, skb); - if (inner_mode->family == AF_INET6) + case AF_INET6: return xfrm6_remove_beet_encap(x, skb); + } break; case XFRM_MODE_TUNNEL: - if (inner_mode->family == AF_INET) + switch (XFRM_MODE_SKB_CB(skb)->protocol) { + case IPPROTO_IPIP: return xfrm4_remove_tunnel_encap(x, skb); - if (inner_mode->family == AF_INET6) + case IPPROTO_IPV6: return xfrm6_remove_tunnel_encap(x, skb); break; + } + return -EINVAL; } WARN_ON_ONCE(1); @@ -356,9 +363,7 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x, static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) { - const struct xfrm_mode *inner_mode = &x->inner_mode; - - switch (x->outer_mode.family) { + switch (x->props.family) { case AF_INET: xfrm4_extract_header(skb); break; @@ -370,25 +375,7 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) return -EAFNOSUPPORT; } - if (x->sel.family == AF_UNSPEC) { - inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); - if (!inner_mode) - return -EAFNOSUPPORT; - } - - switch (inner_mode->family) { - case AF_INET: - skb->protocol = htons(ETH_P_IP); - break; - case AF_INET6: - skb->protocol = htons(ETH_P_IPV6); - break; - default: - WARN_ON_ONCE(1); - break; - } - - return xfrm_inner_mode_encap_remove(x, inner_mode, skb); + return xfrm_inner_mode_encap_remove(x, skb); } /* Remove encapsulation header. @@ -434,17 +421,16 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) } static int xfrm_inner_mode_input(struct xfrm_state *x, - const struct xfrm_mode *inner_mode, struct sk_buff *skb) { - switch (inner_mode->encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: case XFRM_MODE_TUNNEL: return xfrm_prepare_input(x, skb); case XFRM_MODE_TRANSPORT: - if (inner_mode->family == AF_INET) + if (x->props.family == AF_INET) return xfrm4_transport_input(x, skb); - if (inner_mode->family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_transport_input(x, skb); break; case XFRM_MODE_ROUTEOPTIMIZATION: @@ -462,7 +448,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { const struct xfrm_state_afinfo *afinfo; struct net *net = dev_net(skb->dev); - const struct xfrm_mode *inner_mode; int err; __be32 seq; __be32 seq_hi; @@ -492,7 +477,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } - family = x->outer_mode.family; + family = x->props.family; /* An encap_type of -1 indicates async resumption. */ if (encap_type == -1) { @@ -676,17 +661,7 @@ resume: XFRM_MODE_SKB_CB(skb)->protocol = nexthdr; - inner_mode = &x->inner_mode; - - if (x->sel.family == AF_UNSPEC) { - inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); - if (inner_mode == NULL) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); - goto drop; - } - } - - if (xfrm_inner_mode_input(x, inner_mode, skb)) { + if (xfrm_inner_mode_input(x, skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } @@ -701,7 +676,7 @@ resume: * transport mode so the outer address is identical. */ daddr = &x->id.daddr; - family = x->outer_mode.family; + family = x->props.family; err = xfrm_parse_spi(skb, nexthdr, &spi, &seq); if (err < 0) { @@ -732,7 +707,7 @@ resume: err = -EAFNOSUPPORT; rcu_read_lock(); - afinfo = xfrm_state_afinfo_get_rcu(x->inner_mode.family); + afinfo = xfrm_state_afinfo_get_rcu(x->props.family); if (likely(afinfo)) err = afinfo->transport_finish(skb, xfrm_gro || async); rcu_read_unlock(); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 9a5e79a38c67..07a7ee43b8ae 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -414,7 +414,7 @@ static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; skb->protocol = htons(ETH_P_IP); - switch (x->outer_mode.encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: return xfrm4_beet_encap_add(x, skb); case XFRM_MODE_TUNNEL: @@ -437,7 +437,7 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) skb->ignore_df = 1; skb->protocol = htons(ETH_P_IPV6); - switch (x->outer_mode.encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: return xfrm6_beet_encap_add(x, skb); case XFRM_MODE_TUNNEL: @@ -453,22 +453,22 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb) { - switch (x->outer_mode.encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: case XFRM_MODE_TUNNEL: - if (x->outer_mode.family == AF_INET) + if (x->props.family == AF_INET) return xfrm4_prepare_output(x, skb); - if (x->outer_mode.family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_prepare_output(x, skb); break; case XFRM_MODE_TRANSPORT: - if (x->outer_mode.family == AF_INET) + if (x->props.family == AF_INET) return xfrm4_transport_output(x, skb); - if (x->outer_mode.family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_transport_output(x, skb); break; case XFRM_MODE_ROUTEOPTIMIZATION: - if (x->outer_mode.family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_ro_output(x, skb); WARN_ON_ONCE(1); break; @@ -866,21 +866,10 @@ static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) { - const struct xfrm_mode *inner_mode; - - if (x->sel.family == AF_UNSPEC) - inner_mode = xfrm_ip2inner_mode(x, - xfrm_af2proto(skb_dst(skb)->ops->family)); - else - inner_mode = &x->inner_mode; - - if (inner_mode == NULL) - return -EAFNOSUPPORT; - - switch (inner_mode->family) { - case AF_INET: + switch (skb->protocol) { + case htons(ETH_P_IP): return xfrm4_extract_output(x, skb); - case AF_INET6: + case htons(ETH_P_IPV6): return xfrm6_extract_output(x, skb); } diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h index 7048bb3594d6..634e81d83efd 100644 --- a/samples/bpf/asm_goto_workaround.h +++ b/samples/bpf/asm_goto_workaround.h @@ -4,14 +4,14 @@ #define __ASM_GOTO_WORKAROUND_H /* - * This will bring in asm_volatile_goto and asm_inline macro definitions + * This will bring in asm_goto_output and asm_inline macro definitions * if enabled by compiler and config options. */ #include <linux/types.h> -#ifdef asm_volatile_goto -#undef asm_volatile_goto -#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto") +#ifdef asm_goto_output +#undef asm_goto_output +#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output") #endif /* diff --git a/scripts/Makefile.compiler b/scripts/Makefile.compiler index 158c57f2acfd..87589a7ba27f 100644 --- a/scripts/Makefile.compiler +++ b/scripts/Makefile.compiler @@ -72,7 +72,3 @@ clang-min-version = $(shell [ $(CONFIG_CLANG_VERSION)0 -ge $(1)0 ] && echo y) # ld-option # Usage: KBUILD_LDFLAGS += $(call ld-option, -X, -Y) ld-option = $(call try-run, $(LD) $(KBUILD_LDFLAGS) $(1) -v,$(1),$(2),$(3)) - -# ld-ifversion -# Usage: $(call ld-ifversion, -ge, 22252, y) -ld-ifversion = $(shell [ $(CONFIG_LD_VERSION)0 $(1) $(2)0 ] && echo $(3) || echo $(4)) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index e41dee64d429..39aea753d0bd 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -44,6 +44,7 @@ modpost-args = \ $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ $(if $(KBUILD_NSDEPS),-d $(MODULES_NSDEPS)) \ $(if $(CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS)$(KBUILD_NSDEPS),-N) \ + $(if $(findstring 1, $(KBUILD_EXTRA_WARN)),-W) \ -o $@ # 'make -i -k' ignores compile errors, and builds as many modules as possible. diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index d5c389df6045..4de98b7bbea9 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -495,7 +495,7 @@ eBPF programs can have an associated license, passed along with the bytecode instructions to the kernel when the programs are loaded. The format for that string is identical to the one in use for kernel modules (Dual licenses, such as "Dual BSD/GPL", may be used). Some helper functions are only accessible to -programs that are compatible with the GNU Privacy License (GPL). +programs that are compatible with the GNU General Public License (GNU GPL). In order to use such helpers, the eBPF program must be loaded with the correct license string passed (via **attr**) to the **bpf**\ () system call, and this diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 1e5e66ae5a52..ecf4250b0d2d 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -4971,7 +4971,7 @@ sub process { if|for|while|switch|return|case| volatile|__volatile__| __attribute__|format|__extension__| - asm|__asm__)$/x) + asm|__asm__|scoped_guard)$/x) { # cpp #define statements have non-optional spaces, ie # if there is a space between the name and the open diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index 564c5632e1a2..bfe5a4082d8e 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -16,6 +16,21 @@ elif type c++filt >/dev/null 2>&1 ; then cppfilt_opts=-i fi +UTIL_SUFFIX= +if [[ -z ${LLVM:-} ]]; then + UTIL_PREFIX=${CROSS_COMPILE:-} +else + UTIL_PREFIX=llvm- + if [[ ${LLVM} == */ ]]; then + UTIL_PREFIX=${LLVM}${UTIL_PREFIX} + elif [[ ${LLVM} == -* ]]; then + UTIL_SUFFIX=${LLVM} + fi +fi + +READELF=${UTIL_PREFIX}readelf${UTIL_SUFFIX} +ADDR2LINE=${UTIL_PREFIX}addr2line${UTIL_SUFFIX} + if [[ $1 == "-r" ]] ; then vmlinux="" basepath="auto" @@ -75,7 +90,7 @@ find_module() { if [[ "$modpath" != "" ]] ; then for fn in $(find "$modpath" -name "${module//_/[-_]}.ko*") ; do - if readelf -WS "$fn" | grep -qwF .debug_line ; then + if ${READELF} -WS "$fn" | grep -qwF .debug_line ; then echo $fn return fi @@ -169,7 +184,7 @@ parse_symbol() { if [[ $aarray_support == true && "${cache[$module,$address]+isset}" == "isset" ]]; then local code=${cache[$module,$address]} else - local code=$(${CROSS_COMPILE}addr2line -i -e "$objfile" "$address" 2>/dev/null) + local code=$(${ADDR2LINE} -i -e "$objfile" "$address" 2>/dev/null) if [[ $aarray_support == true ]]; then cache[$module,$address]=$code fi diff --git a/scripts/get_abi.pl b/scripts/get_abi.pl index 0ffd5531242a..408bfd0216da 100755 --- a/scripts/get_abi.pl +++ b/scripts/get_abi.pl @@ -98,7 +98,7 @@ sub parse_abi { $name =~ s,.*/,,; my $fn = $file; - $fn =~ s,Documentation/ABI/,,; + $fn =~ s,.*Documentation/ABI/,,; my $nametag = "File $fn"; $data{$nametag}->{what} = "File $name"; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 32e573943cf0..458b2948b580 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -135,8 +135,13 @@ gen_btf() ${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \ --strip-all ${1} ${2} 2>/dev/null # Change e_type to ET_REL so that it can be used to link final vmlinux. - # Unlike GNU ld, lld does not allow an ET_EXEC input. - printf '\1' | dd of=${2} conv=notrunc bs=1 seek=16 status=none + # GNU ld 2.35+ and lld do not allow an ET_EXEC input. + if is_enabled CONFIG_CPU_BIG_ENDIAN; then + et_rel='\0\1' + else + et_rel='\1\0' + fi + printf "${et_rel}" | dd of=${2} conv=notrunc bs=1 seek=16 status=none } # Create ${2} .S file with all symbols from the ${1} object file diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index e6be7fc2625f..686eed37f978 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -41,6 +41,8 @@ static bool allow_missing_ns_imports; static bool error_occurred; +static bool extra_warn; + /* * Cut off the warnings when there are too many. This typically occurs when * vmlinux is missing. ('make modules' without building vmlinux.) @@ -809,7 +811,7 @@ static void check_section(const char *modname, struct elf_info *elf, #define ALL_INIT_TEXT_SECTIONS \ ".init.text", ".meminit.text" #define ALL_EXIT_TEXT_SECTIONS \ - ".exit.text", ".memexit.text" + ".exit.text" #define ALL_PCI_INIT_SECTIONS \ ".pci_fixup_early", ".pci_fixup_header", ".pci_fixup_final", \ @@ -817,23 +819,22 @@ static void check_section(const char *modname, struct elf_info *elf, ".pci_fixup_resume_early", ".pci_fixup_suspend" #define ALL_XXXINIT_SECTIONS MEM_INIT_SECTIONS -#define ALL_XXXEXIT_SECTIONS MEM_EXIT_SECTIONS #define ALL_INIT_SECTIONS INIT_SECTIONS, ALL_XXXINIT_SECTIONS -#define ALL_EXIT_SECTIONS EXIT_SECTIONS, ALL_XXXEXIT_SECTIONS +#define ALL_EXIT_SECTIONS EXIT_SECTIONS #define DATA_SECTIONS ".data", ".data.rel" -#define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \ - ".kprobes.text", ".cpuidle.text", ".noinstr.text" +#define TEXT_SECTIONS ".text", ".text.*", ".sched.text", \ + ".kprobes.text", ".cpuidle.text", ".noinstr.text", \ + ".ltext", ".ltext.*" #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \ - ".fixup", ".entry.text", ".exception.text", ".text.*", \ + ".fixup", ".entry.text", ".exception.text", \ ".coldtext", ".softirqentry.text" #define INIT_SECTIONS ".init.*" #define MEM_INIT_SECTIONS ".meminit.*" #define EXIT_SECTIONS ".exit.*" -#define MEM_EXIT_SECTIONS ".memexit.*" #define ALL_TEXT_SECTIONS ALL_INIT_TEXT_SECTIONS, ALL_EXIT_TEXT_SECTIONS, \ TEXT_SECTIONS, OTHER_TEXT_SECTIONS @@ -862,7 +863,6 @@ enum mismatch { TEXT_TO_ANY_EXIT, DATA_TO_ANY_EXIT, XXXINIT_TO_SOME_INIT, - XXXEXIT_TO_SOME_EXIT, ANY_INIT_TO_ANY_EXIT, ANY_EXIT_TO_ANY_INIT, EXPORT_TO_INIT_EXIT, @@ -937,12 +937,6 @@ static const struct sectioncheck sectioncheck[] = { .bad_tosec = { INIT_SECTIONS, NULL }, .mismatch = XXXINIT_TO_SOME_INIT, }, -/* Do not reference exit code/data from memexit code/data */ -{ - .fromsec = { ALL_XXXEXIT_SECTIONS, NULL }, - .bad_tosec = { EXIT_SECTIONS, NULL }, - .mismatch = XXXEXIT_TO_SOME_EXIT, -}, /* Do not use exit code/data from init code */ { .fromsec = { ALL_INIT_SECTIONS, NULL }, @@ -1085,9 +1079,20 @@ static int secref_whitelist(const struct sectioncheck *mismatch, "*_console"))) return 0; - /* symbols in data sections that may refer to meminit/exit sections */ + /* symbols in data sections that may refer to meminit sections */ if (match(fromsec, PATTERNS(DATA_SECTIONS)) && - match(tosec, PATTERNS(ALL_XXXINIT_SECTIONS, ALL_EXIT_SECTIONS)) && + match(tosec, PATTERNS(ALL_XXXINIT_SECTIONS)) && + match(fromsym, PATTERNS("*driver"))) + return 0; + + /* + * symbols in data sections must not refer to .exit.*, but there are + * quite a few offenders, so hide these unless for W=1 builds until + * these are fixed. + */ + if (!extra_warn && + match(fromsec, PATTERNS(DATA_SECTIONS)) && + match(tosec, PATTERNS(EXIT_SECTIONS)) && match(fromsym, PATTERNS("*driver"))) return 0; @@ -1254,7 +1259,6 @@ static void report_sec_mismatch(const char *modname, case TEXT_TO_ANY_EXIT: case DATA_TO_ANY_EXIT: case XXXINIT_TO_SOME_INIT: - case XXXEXIT_TO_SOME_EXIT: case ANY_INIT_TO_ANY_EXIT: case ANY_EXIT_TO_ANY_INIT: warn("%s: section mismatch in reference: %s (section: %s) -> %s (section: %s)\n", @@ -2290,7 +2294,7 @@ int main(int argc, char **argv) LIST_HEAD(dump_lists); struct dump_list *dl, *dl2; - while ((opt = getopt(argc, argv, "ei:mnT:o:awENd:")) != -1) { + while ((opt = getopt(argc, argv, "ei:mnT:o:aWwENd:")) != -1) { switch (opt) { case 'e': external_module = true; @@ -2315,6 +2319,9 @@ int main(int argc, char **argv) case 'T': files_source = optarg; break; + case 'W': + extra_warn = true; + break; case 'w': warn_unresolved = true; break; diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c index 6bf9caca0968..a72e6cf61a1f 100644 --- a/scripts/mod/sumversion.c +++ b/scripts/mod/sumversion.c @@ -326,7 +326,12 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md) /* Sum all files in the same dir or subdirs. */ while ((line = get_line(&pos))) { - char* p = line; + char* p; + + /* trim the leading spaces away */ + while (isspace(*line)) + line++; + p = line; if (strncmp(line, "source_", sizeof("source_")-1) == 0) { p = strrchr(line, ' '); diff --git a/scripts/pahole-flags.sh b/scripts/pahole-flags.sh index 0d99ef17e4a5..728d55190d97 100755 --- a/scripts/pahole-flags.sh +++ b/scripts/pahole-flags.sh @@ -19,5 +19,12 @@ fi if [ "${pahole_ver}" -ge "122" ]; then extra_paholeopt="${extra_paholeopt} -j" fi +if [ "${pahole_ver}" -ge "124" ]; then + # see PAHOLE_HAS_LANG_EXCLUDE + extra_paholeopt="${extra_paholeopt} --lang_exclude=rust" +fi +if [ "${pahole_ver}" -ge "125" ]; then + extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_inconsistent_proto --btf_gen_optimized" +fi echo ${extra_paholeopt} diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h index f42359f58eb5..d468c8b90298 100644 --- a/security/apparmor/include/lib.h +++ b/security/apparmor/include/lib.h @@ -226,7 +226,7 @@ void aa_policy_destroy(struct aa_policy *policy); */ #define fn_label_build(L, P, GFP, FN) \ ({ \ - __label__ __cleanup, __done; \ + __label__ __do_cleanup, __done; \ struct aa_label *__new_; \ \ if ((L)->size > 1) { \ @@ -244,7 +244,7 @@ void aa_policy_destroy(struct aa_policy *policy); __new_ = (FN); \ AA_BUG(!__new_); \ if (IS_ERR(__new_)) \ - goto __cleanup; \ + goto __do_cleanup; \ __lvec[__j++] = __new_; \ } \ for (__j = __count = 0; __j < (L)->size; __j++) \ @@ -266,7 +266,7 @@ void aa_policy_destroy(struct aa_policy *policy); vec_cleanup(profile, __pvec, __count); \ } else \ __new_ = NULL; \ -__cleanup: \ +__do_cleanup: \ vec_cleanup(label, __lvec, (L)->size); \ } else { \ (P) = labels_profile(L); \ diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 7012fd82f1bb..633e778ec369 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -674,6 +674,10 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) tmpname = aa_splitn_fqname(name, strlen(name), &tmpns, &ns_len); if (tmpns) { + if (!tmpname) { + info = "empty profile name"; + goto fail; + } *ns_name = kstrndup(tmpns, ns_len, GFP_KERNEL); if (!*ns_name) { info = "out of memory"; diff --git a/security/keys/gc.c b/security/keys/gc.c index 3c90807476eb..eaddaceda14e 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -67,6 +67,19 @@ void key_schedule_gc(time64_t gc_at) } /* + * Set the expiration time on a key. + */ +void key_set_expiry(struct key *key, time64_t expiry) +{ + key->expiry = expiry; + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + key_schedule_gc(expiry); + } +} + +/* * Schedule a dead links collection run. */ void key_schedule_gc_links(void) @@ -176,7 +189,6 @@ static void key_garbage_collector(struct work_struct *work) static u8 gc_state; /* Internal persistent state */ #define KEY_GC_REAP_AGAIN 0x01 /* - Need another cycle */ #define KEY_GC_REAPING_LINKS 0x02 /* - We need to reap links */ -#define KEY_GC_SET_TIMER 0x04 /* - We need to restart the timer */ #define KEY_GC_REAPING_DEAD_1 0x10 /* - We need to mark dead keys */ #define KEY_GC_REAPING_DEAD_2 0x20 /* - We need to reap dead key links */ #define KEY_GC_REAPING_DEAD_3 0x40 /* - We need to reap dead keys */ @@ -184,21 +196,17 @@ static void key_garbage_collector(struct work_struct *work) struct rb_node *cursor; struct key *key; - time64_t new_timer, limit; + time64_t new_timer, limit, expiry; kenter("[%lx,%x]", key_gc_flags, gc_state); limit = ktime_get_real_seconds(); - if (limit > key_gc_delay) - limit -= key_gc_delay; - else - limit = key_gc_delay; /* Work out what we're going to be doing in this pass */ gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2; gc_state <<= 1; if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags)) - gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER; + gc_state |= KEY_GC_REAPING_LINKS; if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags)) gc_state |= KEY_GC_REAPING_DEAD_1; @@ -233,8 +241,11 @@ continue_scanning: } } - if (gc_state & KEY_GC_SET_TIMER) { - if (key->expiry > limit && key->expiry < new_timer) { + expiry = key->expiry; + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + if (expiry > limit && expiry < new_timer) { kdebug("will expire %x in %lld", key_serial(key), key->expiry - limit); new_timer = key->expiry; @@ -276,7 +287,7 @@ maybe_resched: */ kdebug("pass complete"); - if (gc_state & KEY_GC_SET_TIMER && new_timer != (time64_t)TIME64_MAX) { + if (new_timer != TIME64_MAX) { new_timer += key_gc_delay; key_schedule_gc(new_timer); } diff --git a/security/keys/internal.h b/security/keys/internal.h index 3c1e7122076b..ec2ec335b613 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -174,6 +174,7 @@ extern unsigned key_gc_delay; extern void keyring_gc(struct key *keyring, time64_t limit); extern void keyring_restriction_gc(struct key *keyring, struct key_type *dead_type); +void key_set_expiry(struct key *key, time64_t expiry); extern void key_schedule_gc(time64_t gc_at); extern void key_schedule_gc_links(void); extern void key_gc_keytype(struct key_type *ktype); @@ -222,10 +223,18 @@ extern struct key *key_get_instantiation_authkey(key_serial_t target_id); */ static inline bool key_is_dead(const struct key *key, time64_t limit) { + time64_t expiry = key->expiry; + + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + if (expiry <= limit) + return true; + } + return key->flags & ((1 << KEY_FLAG_DEAD) | (1 << KEY_FLAG_INVALIDATED)) || - (key->expiry > 0 && key->expiry <= limit) || key->domain_tag->removed; } diff --git a/security/keys/key.c b/security/keys/key.c index c45afdd1dfbb..e65240641ca5 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -294,6 +294,7 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->uid = uid; key->gid = gid; key->perm = perm; + key->expiry = TIME64_MAX; key->restrict_link = restrict_link; key->last_used_at = ktime_get_real_seconds(); @@ -463,10 +464,7 @@ static int __key_instantiate_and_link(struct key *key, if (authkey) key_invalidate(authkey); - if (prep->expiry != TIME64_MAX) { - key->expiry = prep->expiry; - key_schedule_gc(prep->expiry + key_gc_delay); - } + key_set_expiry(key, prep->expiry); } } @@ -606,8 +604,7 @@ int key_reject_and_link(struct key *key, atomic_inc(&key->user->nikeys); mark_key_instantiated(key, -error); notify_key(key, NOTIFY_KEY_INSTANTIATED, -error); - key->expiry = ktime_get_real_seconds() + timeout; - key_schedule_gc(key->expiry + key_gc_delay); + key_set_expiry(key, ktime_get_real_seconds() + timeout); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; @@ -722,16 +719,14 @@ found_kernel_type: void key_set_timeout(struct key *key, unsigned timeout) { - time64_t expiry = 0; + time64_t expiry = TIME64_MAX; /* make the changes with the locks held to prevent races */ down_write(&key->sem); if (timeout > 0) expiry = ktime_get_real_seconds() + timeout; - - key->expiry = expiry; - key_schedule_gc(key->expiry + key_gc_delay); + key_set_expiry(key, expiry); up_write(&key->sem); } diff --git a/security/keys/proc.c b/security/keys/proc.c index d0cde6685627..4f4e2c1824f1 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -198,7 +198,7 @@ static int proc_keys_show(struct seq_file *m, void *v) /* come up with a suitable timeout value */ expiry = READ_ONCE(key->expiry); - if (expiry == 0) { + if (expiry == TIME64_MAX) { memcpy(xbuf, "perm", 5); } else if (now >= expiry) { memcpy(xbuf, "expd", 5); diff --git a/security/security.c b/security/security.c index 5fa286ae9908..1b504c296551 100644 --- a/security/security.c +++ b/security/security.c @@ -1569,6 +1569,24 @@ int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } EXPORT_SYMBOL_GPL(security_file_ioctl); +/** + * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode + * @file: associated file + * @cmd: ioctl cmd + * @arg: ioctl arguments + * + * Compat version of security_file_ioctl() that correctly handles 32-bit + * processes running on 64-bit kernels. + * + * Return: Returns 0 if permission is granted. + */ +int security_file_ioctl_compat(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return call_int_hook(file_ioctl_compat, 0, file, cmd, arg); +} +EXPORT_SYMBOL_GPL(security_file_ioctl_compat); + static inline unsigned long mmap_prot(struct file *file, unsigned long prot) { /* @@ -2168,7 +2186,19 @@ EXPORT_SYMBOL(security_inode_setsecctx); int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { - return call_int_hook(inode_getsecctx, -EOPNOTSUPP, inode, ctx, ctxlen); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) { + rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen); + if (rc != LSM_RET_DEFAULT(inode_getsecctx)) + return rc; + } + + return LSM_RET_DEFAULT(inode_getsecctx); } EXPORT_SYMBOL(security_inode_getsecctx); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index d88c399b0e86..78f3da39b031 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3718,6 +3718,33 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd, return error; } +static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd, + unsigned long arg) +{ + /* + * If we are in a 64-bit kernel running 32-bit userspace, we need to + * make sure we don't compare 32-bit flags to 64-bit flags. + */ + switch (cmd) { + case FS_IOC32_GETFLAGS: + cmd = FS_IOC_GETFLAGS; + break; + case FS_IOC32_SETFLAGS: + cmd = FS_IOC_SETFLAGS; + break; + case FS_IOC32_GETVERSION: + cmd = FS_IOC_GETVERSION; + break; + case FS_IOC32_SETVERSION: + cmd = FS_IOC_SETVERSION; + break; + default: + break; + } + + return selinux_file_ioctl(file, cmd, arg); +} + static int default_noexec __ro_after_init; static int file_map_prot_check(struct file *file, unsigned long prot, int shared) @@ -4690,6 +4717,13 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in return -EINVAL; addr4 = (struct sockaddr_in *)address; if (family_sa == AF_UNSPEC) { + if (family == PF_INET6) { + /* Length check from inet6_bind_sk() */ + if (addrlen < SIN6_LEN_RFC2133) + return -EINVAL; + /* Family check from __inet6_bind() */ + goto err_af; + } /* see __inet_bind(), we only want to allow * AF_UNSPEC if the address is INADDR_ANY */ @@ -7128,6 +7162,7 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(file_permission, selinux_file_permission), LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl), + LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat), LSM_HOOK_INIT(mmap_file, selinux_mmap_file), LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr), LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect), diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index cd6a03e945eb..fbadc61feedd 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4905,6 +4905,7 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(file_alloc_security, smack_file_alloc_security), LSM_HOOK_INIT(file_ioctl, smack_file_ioctl), + LSM_HOOK_INIT(file_ioctl_compat, smack_file_ioctl), LSM_HOOK_INIT(file_lock, smack_file_lock), LSM_HOOK_INIT(file_fcntl, smack_file_fcntl), LSM_HOOK_INIT(mmap_file, smack_mmap_file), diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 71e82d855ebf..fb599401bc7d 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -555,6 +555,7 @@ static struct security_hook_list tomoyo_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(path_rename, tomoyo_path_rename), LSM_HOOK_INIT(inode_getattr, tomoyo_inode_getattr), LSM_HOOK_INIT(file_ioctl, tomoyo_file_ioctl), + LSM_HOOK_INIT(file_ioctl_compat, tomoyo_file_ioctl), LSM_HOOK_INIT(path_chmod, tomoyo_path_chmod), LSM_HOOK_INIT(path_chown, tomoyo_path_chown), LSM_HOOK_INIT(path_chroot, tomoyo_path_chroot), diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index 741a5d17ae4c..ecd3aec57c87 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -629,17 +629,15 @@ void snd_hdac_stream_timecounter_init(struct hdac_stream *azx_dev, struct hdac_stream *s; bool inited = false; u64 cycle_last = 0; - int i = 0; list_for_each_entry(s, &bus->stream_list, list) { - if (streams & (1 << i)) { + if ((streams & (1 << s->index))) { azx_timecounter_init(s, inited, cycle_last); if (!inited) { inited = true; cycle_last = s->tc.cycle_last; } } - i++; } snd_pcm_gettime(runtime, &runtime->trigger_tstamp); @@ -684,14 +682,13 @@ void snd_hdac_stream_sync(struct hdac_stream *azx_dev, bool start, unsigned int streams) { struct hdac_bus *bus = azx_dev->bus; - int i, nwait, timeout; + int nwait, timeout; struct hdac_stream *s; for (timeout = 5000; timeout; timeout--) { nwait = 0; - i = 0; list_for_each_entry(s, &bus->stream_list, list) { - if (!(streams & (1 << i++))) + if (!(streams & (1 << s->index))) continue; if (start) { diff --git a/sound/hda/intel-nhlt.c b/sound/hda/intel-nhlt.c index 2c4dfc0b7e34..696a958d93e9 100644 --- a/sound/hda/intel-nhlt.c +++ b/sound/hda/intel-nhlt.c @@ -238,7 +238,7 @@ EXPORT_SYMBOL(intel_nhlt_ssp_mclk_mask); static struct nhlt_specific_cfg * nhlt_get_specific_cfg(struct device *dev, struct nhlt_fmt *fmt, u8 num_ch, - u32 rate, u8 vbps, u8 bps) + u32 rate, u8 vbps, u8 bps, bool ignore_vbps) { struct nhlt_fmt_cfg *cfg = fmt->fmt_config; struct wav_fmt *wfmt; @@ -255,8 +255,12 @@ nhlt_get_specific_cfg(struct device *dev, struct nhlt_fmt *fmt, u8 num_ch, dev_dbg(dev, "Endpoint format: ch=%d fmt=%d/%d rate=%d\n", wfmt->channels, _vbps, _bps, wfmt->samples_per_sec); + /* + * When looking for exact match of configuration ignore the vbps + * from NHLT table when ignore_vbps is true + */ if (wfmt->channels == num_ch && wfmt->samples_per_sec == rate && - vbps == _vbps && bps == _bps) + (ignore_vbps || vbps == _vbps) && bps == _bps) return &cfg->config; cfg = (struct nhlt_fmt_cfg *)(cfg->config.caps + cfg->config.size); @@ -289,6 +293,7 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt, { struct nhlt_specific_cfg *cfg; struct nhlt_endpoint *epnt; + bool ignore_vbps = false; struct nhlt_fmt *fmt; int i; @@ -298,7 +303,26 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt, dev_dbg(dev, "Looking for configuration:\n"); dev_dbg(dev, " vbus_id=%d link_type=%d dir=%d, dev_type=%d\n", bus_id, link_type, dir, dev_type); - dev_dbg(dev, " ch=%d fmt=%d/%d rate=%d\n", num_ch, vbps, bps, rate); + if (link_type == NHLT_LINK_DMIC && bps == 32 && (vbps == 24 || vbps == 32)) { + /* + * The DMIC hardware supports only one type of 32 bits sample + * size, which is 24 bit sampling on the MSB side and bits[1:0] + * are used for indicating the channel number. + * It has been observed that some NHLT tables have the vbps + * specified as 32 while some uses 24. + * The format these variations describe are identical, the + * hardware is configured and behaves the same way. + * Note: when the samples assumed to be vbps=32 then the 'noise' + * introduced by the lower two bits (channel number) have no + * real life implication on audio quality. + */ + dev_dbg(dev, + " ch=%d fmt=%d rate=%d (vbps is ignored for DMIC 32bit format)\n", + num_ch, bps, rate); + ignore_vbps = true; + } else { + dev_dbg(dev, " ch=%d fmt=%d/%d rate=%d\n", num_ch, vbps, bps, rate); + } dev_dbg(dev, "Endpoint count=%d\n", nhlt->endpoint_count); epnt = (struct nhlt_endpoint *)nhlt->desc; @@ -307,7 +331,8 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt, if (nhlt_check_ep_match(dev, epnt, bus_id, link_type, dir, dev_type)) { fmt = (struct nhlt_fmt *)(epnt->config.caps + epnt->config.size); - cfg = nhlt_get_specific_cfg(dev, fmt, num_ch, rate, vbps, bps); + cfg = nhlt_get_specific_cfg(dev, fmt, num_ch, rate, + vbps, bps, ignore_vbps); if (cfg) return cfg; } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 5aaf3dcecf27..a26f2a2d44cf 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2549,6 +2549,8 @@ static const struct pci_device_id azx_ids[] = { /* Lunarlake-P */ { PCI_DEVICE(0x8086, 0xa828), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Arrow Lake */ + { PCI_DEVICE_DATA(INTEL, HDA_ARL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE) }, /* Broxton-P(Apollolake) */ { PCI_DEVICE(0x8086, 0x5a98), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON }, diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index a889cccdd607..e8209178d87b 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -21,6 +21,12 @@ #include "hda_jack.h" #include "hda_generic.h" +enum { + CX_HEADSET_NOPRESENT = 0, + CX_HEADSET_PARTPRESENT, + CX_HEADSET_ALLPRESENT, +}; + struct conexant_spec { struct hda_gen_spec gen; @@ -42,7 +48,8 @@ struct conexant_spec { unsigned int gpio_led; unsigned int gpio_mute_led_mask; unsigned int gpio_mic_led_mask; - + unsigned int headset_present_flag; + bool is_cx8070_sn6140; }; @@ -164,6 +171,27 @@ static void cxt_init_gpio_led(struct hda_codec *codec) } } +static void cx_fixup_headset_recog(struct hda_codec *codec) +{ + unsigned int mic_persent; + + /* fix some headset type recognize fail issue, such as EDIFIER headset */ + /* set micbiasd output current comparator threshold from 66% to 55%. */ + snd_hda_codec_write(codec, 0x1c, 0, 0x320, 0x010); + /* set OFF voltage for DFET from -1.2V to -0.8V, set headset micbias registor + * value adjustment trim from 2.2K ohms to 2.0K ohms. + */ + snd_hda_codec_write(codec, 0x1c, 0, 0x3b0, 0xe10); + /* fix reboot headset type recognize fail issue */ + mic_persent = snd_hda_codec_read(codec, 0x19, 0, AC_VERB_GET_PIN_SENSE, 0x0); + if (mic_persent & AC_PINSENSE_PRESENCE) + /* enable headset mic VREF */ + snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x24); + else + /* disable headset mic VREF */ + snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x20); +} + static int cx_auto_init(struct hda_codec *codec) { struct conexant_spec *spec = codec->spec; @@ -174,6 +202,9 @@ static int cx_auto_init(struct hda_codec *codec) cxt_init_gpio_led(codec); snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_INIT); + if (spec->is_cx8070_sn6140) + cx_fixup_headset_recog(codec); + return 0; } @@ -192,6 +223,77 @@ static void cx_auto_free(struct hda_codec *codec) snd_hda_gen_free(codec); } +static void cx_process_headset_plugin(struct hda_codec *codec) +{ + unsigned int val; + unsigned int count = 0; + + /* Wait headset detect done. */ + do { + val = snd_hda_codec_read(codec, 0x1c, 0, 0xca0, 0x0); + if (val & 0x080) { + codec_dbg(codec, "headset type detect done!\n"); + break; + } + msleep(20); + count++; + } while (count < 3); + val = snd_hda_codec_read(codec, 0x1c, 0, 0xcb0, 0x0); + if (val & 0x800) { + codec_dbg(codec, "headset plugin, type is CTIA\n"); + snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x24); + } else if (val & 0x400) { + codec_dbg(codec, "headset plugin, type is OMTP\n"); + snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x24); + } else { + codec_dbg(codec, "headphone plugin\n"); + } +} + +static void cx_update_headset_mic_vref(struct hda_codec *codec, unsigned int res) +{ + unsigned int phone_present, mic_persent, phone_tag, mic_tag; + struct conexant_spec *spec = codec->spec; + + /* In cx8070 and sn6140, the node 16 can only be config to headphone or disabled, + * the node 19 can only be config to microphone or disabled. + * Check hp&mic tag to process headset pulgin&plugout. + */ + phone_tag = snd_hda_codec_read(codec, 0x16, 0, AC_VERB_GET_UNSOLICITED_RESPONSE, 0x0); + mic_tag = snd_hda_codec_read(codec, 0x19, 0, AC_VERB_GET_UNSOLICITED_RESPONSE, 0x0); + if ((phone_tag & (res >> AC_UNSOL_RES_TAG_SHIFT)) || + (mic_tag & (res >> AC_UNSOL_RES_TAG_SHIFT))) { + phone_present = snd_hda_codec_read(codec, 0x16, 0, AC_VERB_GET_PIN_SENSE, 0x0); + if (!(phone_present & AC_PINSENSE_PRESENCE)) {/* headphone plugout */ + spec->headset_present_flag = CX_HEADSET_NOPRESENT; + snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x20); + return; + } + if (spec->headset_present_flag == CX_HEADSET_NOPRESENT) { + spec->headset_present_flag = CX_HEADSET_PARTPRESENT; + } else if (spec->headset_present_flag == CX_HEADSET_PARTPRESENT) { + mic_persent = snd_hda_codec_read(codec, 0x19, 0, + AC_VERB_GET_PIN_SENSE, 0x0); + /* headset is present */ + if ((phone_present & AC_PINSENSE_PRESENCE) && + (mic_persent & AC_PINSENSE_PRESENCE)) { + cx_process_headset_plugin(codec); + spec->headset_present_flag = CX_HEADSET_ALLPRESENT; + } + } + } +} + +static void cx_jack_unsol_event(struct hda_codec *codec, unsigned int res) +{ + struct conexant_spec *spec = codec->spec; + + if (spec->is_cx8070_sn6140) + cx_update_headset_mic_vref(codec, res); + + snd_hda_jack_unsol_event(codec, res); +} + #ifdef CONFIG_PM static int cx_auto_suspend(struct hda_codec *codec) { @@ -205,7 +307,7 @@ static const struct hda_codec_ops cx_auto_patch_ops = { .build_pcms = snd_hda_gen_build_pcms, .init = cx_auto_init, .free = cx_auto_free, - .unsol_event = snd_hda_jack_unsol_event, + .unsol_event = cx_jack_unsol_event, #ifdef CONFIG_PM .suspend = cx_auto_suspend, .check_power_status = snd_hda_gen_check_power_status, @@ -242,6 +344,7 @@ enum { CXT_FIXUP_HP_ZBOOK_MUTE_LED, CXT_FIXUP_HEADSET_MIC, CXT_FIXUP_HP_MIC_NO_PRESENCE, + CXT_PINCFG_SWS_JS201D, }; /* for hda_fixup_thinkpad_acpi() */ @@ -739,6 +842,17 @@ static const struct hda_pintbl cxt_pincfg_lemote[] = { {} }; +/* SuoWoSi/South-holding JS201D with sn6140 */ +static const struct hda_pintbl cxt_pincfg_sws_js201d[] = { + { 0x16, 0x03211040 }, /* hp out */ + { 0x17, 0x91170110 }, /* SPK/Class_D */ + { 0x18, 0x95a70130 }, /* Internal mic */ + { 0x19, 0x03a11020 }, /* Headset Mic */ + { 0x1a, 0x40f001f0 }, /* Not used */ + { 0x21, 0x40f001f0 }, /* Not used */ + {} +}; + static const struct hda_fixup cxt_fixups[] = { [CXT_PINCFG_LENOVO_X200] = { .type = HDA_FIXUP_PINS, @@ -894,6 +1008,10 @@ static const struct hda_fixup cxt_fixups[] = { .chained = true, .chain_id = CXT_FIXUP_HEADSET_MIC, }, + [CXT_PINCFG_SWS_JS201D] = { + .type = HDA_FIXUP_PINS, + .v.pins = cxt_pincfg_sws_js201d, + }, }; static const struct snd_pci_quirk cxt5045_fixups[] = { @@ -967,6 +1085,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8458, "HP Z2 G4 mini premium", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN), + SND_PCI_QUIRK(0x14f1, 0x0265, "SWS JS201D", CXT_PINCFG_SWS_JS201D), SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410), @@ -1007,6 +1126,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = { { .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" }, { .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" }, { .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" }, + { .id = CXT_PINCFG_SWS_JS201D, .name = "sws-js201d" }, {} }; @@ -1042,6 +1162,15 @@ static int patch_conexant_auto(struct hda_codec *codec) codec->spec = spec; codec->patch_ops = cx_auto_patch_ops; + /* init cx8070/sn6140 flag and reset headset_present_flag */ + switch (codec->core.vendor_id) { + case 0x14f11f86: + case 0x14f11f87: + spec->is_cx8070_sn6140 = true; + spec->headset_present_flag = CX_HEADSET_NOPRESENT; + break; + } + cx_auto_parse_eapd(codec); spec->gen.own_eapd_ctl = 1; diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index 627899959ffe..e41316e2e983 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -1371,6 +1371,7 @@ void dolphin_fixups(struct hda_codec *codec, const struct hda_fixup *fix, int ac spec->scodecs[CS8409_CODEC1] = &dolphin_cs42l42_1; spec->scodecs[CS8409_CODEC1]->codec = codec; spec->num_scodecs = 2; + spec->gen.suppress_vmaster = 1; codec->patch_ops = cs8409_dolphin_patch_ops; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a7c361e0daeb..92a656fb5321 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7108,6 +7108,7 @@ enum { ALC290_FIXUP_SUBWOOFER_HSJACK, ALC269_FIXUP_THINKPAD_ACPI, ALC269_FIXUP_DMIC_THINKPAD_ACPI, + ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO, ALC255_FIXUP_ACER_MIC_NO_PRESENCE, ALC255_FIXUP_ASUS_MIC_NO_PRESENCE, ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, @@ -7454,6 +7455,14 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc269_fixup_pincfg_U7x7_headset_mic, }, + [ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x18, 0x03a19020 }, /* headset mic */ + { 0x1b, 0x90170150 }, /* speaker */ + { } + }, + }, [ALC269_FIXUP_AMIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -9368,7 +9377,7 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_i2c_two, .chained = true, - .chain_id = ALC269_FIXUP_THINKPAD_ACPI, + .chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, }, [ALC245_FIXUP_HP_MUTE_LED_COEFBIT] = { .type = HDA_FIXUP_FUNC, @@ -9383,6 +9392,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC287_FIXUP_THINKPAD_I2S_SPK] = { .type = HDA_FIXUP_FUNC, .v.func = alc287_fixup_bind_dacs, + .chained = true, + .chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, }, [ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD] = { .type = HDA_FIXUP_FUNC, @@ -9422,6 +9433,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1269, "Acer SWIFT SF314-54", ALC256_FIXUP_ACER_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x126a, "Acer Swift SF114-32", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), @@ -9581,6 +9593,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN), SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), + SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), @@ -9597,6 +9610,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8735, "HP ProBook 435 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x876e, "HP ENVY x360 Convertible 13-ay0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8780, "HP ZBook Fury 17 G7 Mobile Workstation", @@ -9606,6 +9620,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8786, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8787, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e7, "HP ProBook 450 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -9615,6 +9630,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f6, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), + SND_PCI_QUIRK(0x103c, 0x87fe, "HP Laptop 15s-fq2xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8805, "HP ProBook 650 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x880d, "HP EliteBook 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8811, "HP Spectre x360 15-eb1xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), @@ -9663,6 +9679,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x89d3, "HP EliteBook 645 G9 (MB 89D2)", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8a0f, "HP Pavilion 14-ec1xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8a25, "HP Victus 16-d1xxx (MB 8A25)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), @@ -9673,6 +9690,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b0f, "HP Elite mt645 G7 Mobile Thin Client U81", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9680,6 +9698,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b45, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b46, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b59, "HP Elite mt645 G7 Mobile Thin Client U89", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -9707,6 +9726,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c97, "HP ZBook", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8ca1, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -9735,6 +9758,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), + SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZV", ALC285_FIXUP_ASUS_HEADSET_MIC), @@ -9766,17 +9790,20 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS ROG Strix G17 2023 (G713PV)", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE), + SND_PCI_QUIRK(0x1043, 0x1da2, "ASUS UP6502ZA/ZD", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), - SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS), SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f12, "ASUS UM5302", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC245_FIXUP_CS35L41_SPI_2), @@ -9903,6 +9930,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0xc019, "Clevo NH77D[BE]Q", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xc022, "Clevo NH77[DC][QW]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), + SND_PCI_QUIRK(0x17aa, 0x3882, "Lenovo Yoga Pro 7 14APH8", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), @@ -9960,6 +9988,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340), + SND_PCI_QUIRK(0x17aa, 0x334b, "Lenovo ThinkCentre M70 Gen5", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3801, "Lenovo Yoga9 14IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga DuetITL 2021", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), @@ -10027,6 +10056,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), + SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), + SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), diff --git a/sound/pci/oxygen/oxygen_mixer.c b/sound/pci/oxygen/oxygen_mixer.c index 46705ec77b48..eb3aca16359c 100644 --- a/sound/pci/oxygen/oxygen_mixer.c +++ b/sound/pci/oxygen/oxygen_mixer.c @@ -718,7 +718,7 @@ static int ac97_fp_rec_volume_put(struct snd_kcontrol *ctl, oldreg = oxygen_read_ac97(chip, 1, AC97_REC_GAIN); newreg = oldreg & ~0x0707; newreg = newreg | (value->value.integer.value[0] & 7); - newreg = newreg | ((value->value.integer.value[0] & 7) << 8); + newreg = newreg | ((value->value.integer.value[1] & 7) << 8); change = newreg != oldreg; if (change) oxygen_write_ac97(chip, 1, AC97_REC_GAIN, newreg); diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 1dde1f3196ac..28da4e1858d7 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -245,6 +245,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83AS"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "82UG"), } }, @@ -300,6 +307,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), + DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 C7VF"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Razer"), DMI_MATCH(DMI_PRODUCT_NAME, "Blade 14 (2022) - RZ09-0427"), } @@ -353,6 +367,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "pang12"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "System76"), + DMI_MATCH(DMI_PRODUCT_VERSION, "pang13"), + } + }, {} }; diff --git a/sound/soc/codecs/cs35l33.c b/sound/soc/codecs/cs35l33.c index 15e79168d256..c3b7046fd29b 100644 --- a/sound/soc/codecs/cs35l33.c +++ b/sound/soc/codecs/cs35l33.c @@ -22,13 +22,11 @@ #include <sound/soc-dapm.h> #include <sound/initval.h> #include <sound/tlv.h> -#include <linux/gpio.h> #include <linux/gpio/consumer.h> #include <sound/cs35l33.h> #include <linux/pm_runtime.h> #include <linux/regulator/consumer.h> #include <linux/regulator/machine.h> -#include <linux/of_gpio.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/of_irq.h> @@ -1167,7 +1165,7 @@ static int cs35l33_i2c_probe(struct i2c_client *i2c_client) /* We could issue !RST or skip it based on AMP topology */ cs35l33->reset_gpio = devm_gpiod_get_optional(&i2c_client->dev, - "reset-gpios", GPIOD_OUT_HIGH); + "reset", GPIOD_OUT_HIGH); if (IS_ERR(cs35l33->reset_gpio)) { dev_err(&i2c_client->dev, "%s ERROR: Can't get reset GPIO\n", __func__); diff --git a/sound/soc/codecs/cs35l34.c b/sound/soc/codecs/cs35l34.c index b3f98023e6a7..57d125c03fad 100644 --- a/sound/soc/codecs/cs35l34.c +++ b/sound/soc/codecs/cs35l34.c @@ -20,14 +20,12 @@ #include <linux/regulator/machine.h> #include <linux/pm_runtime.h> #include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/of_irq.h> #include <sound/core.h> #include <sound/pcm.h> #include <sound/pcm_params.h> #include <sound/soc.h> #include <sound/soc-dapm.h> -#include <linux/gpio.h> #include <linux/gpio/consumer.h> #include <sound/initval.h> #include <sound/tlv.h> @@ -1061,7 +1059,7 @@ static int cs35l34_i2c_probe(struct i2c_client *i2c_client) dev_err(&i2c_client->dev, "Failed to request IRQ: %d\n", ret); cs35l34->reset_gpio = devm_gpiod_get_optional(&i2c_client->dev, - "reset-gpios", GPIOD_OUT_LOW); + "reset", GPIOD_OUT_LOW); if (IS_ERR(cs35l34->reset_gpio)) { ret = PTR_ERR(cs35l34->reset_gpio); goto err_regulator; diff --git a/sound/soc/codecs/cs43130.c b/sound/soc/codecs/cs43130.c index db39abb2a31b..0b8ecd917a08 100644 --- a/sound/soc/codecs/cs43130.c +++ b/sound/soc/codecs/cs43130.c @@ -579,7 +579,7 @@ static int cs43130_set_sp_fmt(int dai_id, unsigned int bitwidth_sclk, break; case SND_SOC_DAIFMT_LEFT_J: hi_size = bitwidth_sclk; - frm_delay = 2; + frm_delay = 0; frm_phase = 1; break; case SND_SOC_DAIFMT_DSP_A: @@ -1683,7 +1683,7 @@ static ssize_t hpload_dc_r_show(struct device *dev, return cs43130_show_dc(dev, buf, HP_RIGHT); } -static u16 const cs43130_ac_freq[CS43130_AC_FREQ] = { +static const u16 cs43130_ac_freq[CS43130_AC_FREQ] = { 24, 43, 93, @@ -2363,7 +2363,7 @@ static const struct regmap_config cs43130_regmap = { .use_single_write = true, }; -static u16 const cs43130_dc_threshold[CS43130_DC_THRESHOLD] = { +static const u16 cs43130_dc_threshold[CS43130_DC_THRESHOLD] = { 50, 120, }; diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c index 9251490548e8..c8410769188a 100644 --- a/sound/soc/codecs/da7219-aad.c +++ b/sound/soc/codecs/da7219-aad.c @@ -663,7 +663,7 @@ static struct da7219_aad_pdata *da7219_aad_fw_to_pdata(struct device *dev) aad_pdata->mic_det_thr = da7219_aad_fw_mic_det_thr(dev, fw_val32); else - aad_pdata->mic_det_thr = DA7219_AAD_MIC_DET_THR_500_OHMS; + aad_pdata->mic_det_thr = DA7219_AAD_MIC_DET_THR_200_OHMS; if (fwnode_property_read_u32(aad_np, "dlg,jack-ins-deb", &fw_val32) >= 0) aad_pdata->jack_ins_deb = diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c index 8af434e14bfb..21a00c86a139 100644 --- a/sound/soc/codecs/hdac_hda.c +++ b/sound/soc/codecs/hdac_hda.c @@ -124,6 +124,9 @@ static struct snd_soc_dai_driver hdac_hda_dais[] = { .sig_bits = 24, }, }, +}; + +static struct snd_soc_dai_driver hdac_hda_hdmi_dais[] = { { .id = HDAC_HDMI_0_DAI_ID, .name = "intel-hdmi-hifi1", @@ -578,8 +581,16 @@ static const struct snd_soc_component_driver hdac_hda_codec = { .endianness = 1, }; +static const struct snd_soc_component_driver hdac_hda_hdmi_codec = { + .probe = hdac_hda_codec_probe, + .remove = hdac_hda_codec_remove, + .idle_bias_on = false, + .endianness = 1, +}; + static int hdac_hda_dev_probe(struct hdac_device *hdev) { + struct hdac_hda_priv *hda_pvt = dev_get_drvdata(&hdev->dev); struct hdac_ext_link *hlink; int ret; @@ -592,9 +603,15 @@ static int hdac_hda_dev_probe(struct hdac_device *hdev) snd_hdac_ext_bus_link_get(hdev->bus, hlink); /* ASoC specific initialization */ - ret = devm_snd_soc_register_component(&hdev->dev, - &hdac_hda_codec, hdac_hda_dais, - ARRAY_SIZE(hdac_hda_dais)); + if (hda_pvt->need_display_power) + ret = devm_snd_soc_register_component(&hdev->dev, + &hdac_hda_hdmi_codec, hdac_hda_hdmi_dais, + ARRAY_SIZE(hdac_hda_hdmi_dais)); + else + ret = devm_snd_soc_register_component(&hdev->dev, + &hdac_hda_codec, hdac_hda_dais, + ARRAY_SIZE(hdac_hda_dais)); + if (ret < 0) { dev_err(&hdev->dev, "failed to register HDA codec %d\n", ret); return ret; diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index 4d3c3365488a..d8259afc60b0 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -834,8 +834,9 @@ static int hdmi_dai_probe(struct snd_soc_dai *dai) static void hdmi_codec_jack_report(struct hdmi_codec_priv *hcp, unsigned int jack_status) { - if (hcp->jack && jack_status != hcp->jack_status) { - snd_soc_jack_report(hcp->jack, jack_status, SND_JACK_LINEOUT); + if (jack_status != hcp->jack_status) { + if (hcp->jack) + snd_soc_jack_report(hcp->jack, jack_status, SND_JACK_LINEOUT); hcp->jack_status = jack_status; } } @@ -864,6 +865,13 @@ static int hdmi_codec_set_jack(struct snd_soc_component *component, if (hcp->hcd.ops->hook_plugged_cb) { hcp->jack = jack; + + /* + * Report the initial jack status which may have been provided + * by the parent hdmi driver while the hpd hook was registered. + */ + snd_soc_jack_report(jack, hcp->jack_status, SND_JACK_LINEOUT); + return 0; } diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c index 2ccc68513f7c..bb9de5767ebc 100644 --- a/sound/soc/codecs/lpass-wsa-macro.c +++ b/sound/soc/codecs/lpass-wsa-macro.c @@ -1581,7 +1581,6 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w, u16 gain_reg; u16 reg; int val; - int offset_val = 0; struct wsa_macro *wsa = snd_soc_component_get_drvdata(component); if (w->shift == WSA_MACRO_COMP1) { @@ -1620,10 +1619,8 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w, CDC_WSA_RX1_RX_PATH_MIX_SEC0, CDC_WSA_RX_PGA_HALF_DB_MASK, CDC_WSA_RX_PGA_HALF_DB_ENABLE); - offset_val = -2; } val = snd_soc_component_read(component, gain_reg); - val += offset_val; snd_soc_component_write(component, gain_reg, val); wsa_macro_config_ear_spkr_gain(component, wsa, event, gain_reg); @@ -1651,10 +1648,6 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w, CDC_WSA_RX1_RX_PATH_MIX_SEC0, CDC_WSA_RX_PGA_HALF_DB_MASK, CDC_WSA_RX_PGA_HALF_DB_DISABLE); - offset_val = 2; - val = snd_soc_component_read(component, gain_reg); - val += offset_val; - snd_soc_component_write(component, gain_reg, val); } wsa_macro_config_ear_spkr_gain(component, wsa, event, gain_reg); diff --git a/sound/soc/codecs/nau8822.c b/sound/soc/codecs/nau8822.c index 1aef281a9972..cd5053cfd521 100644 --- a/sound/soc/codecs/nau8822.c +++ b/sound/soc/codecs/nau8822.c @@ -184,6 +184,7 @@ static int nau8822_eq_get(struct snd_kcontrol *kcontrol, struct soc_bytes_ext *params = (void *)kcontrol->private_value; int i, reg; u16 reg_val, *val; + __be16 tmp; val = (u16 *)ucontrol->value.bytes.data; reg = NAU8822_REG_EQ1; @@ -192,8 +193,8 @@ static int nau8822_eq_get(struct snd_kcontrol *kcontrol, /* conversion of 16-bit integers between native CPU format * and big endian format */ - reg_val = cpu_to_be16(reg_val); - memcpy(val + i, ®_val, sizeof(reg_val)); + tmp = cpu_to_be16(reg_val); + memcpy(val + i, &tmp, sizeof(tmp)); } return 0; @@ -216,6 +217,7 @@ static int nau8822_eq_put(struct snd_kcontrol *kcontrol, void *data; u16 *val, value; int i, reg, ret; + __be16 *tmp; data = kmemdup(ucontrol->value.bytes.data, params->max, GFP_KERNEL | GFP_DMA); @@ -228,7 +230,8 @@ static int nau8822_eq_put(struct snd_kcontrol *kcontrol, /* conversion of 16-bit integers between native CPU format * and big endian format */ - value = be16_to_cpu(*(val + i)); + tmp = (__be16 *)(val + i); + value = be16_to_cpup(tmp); ret = snd_soc_component_write(component, reg + i, value); if (ret) { dev_err(component->dev, diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index f86fc7cd104d..844d14d4c9a5 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -448,6 +448,7 @@ struct rt5645_priv { struct regulator_bulk_data supplies[ARRAY_SIZE(rt5645_supply_names)]; struct rt5645_eq_param_s *eq_param; struct timer_list btn_check_timer; + struct mutex jd_mutex; int codec_type; int sysclk; @@ -3189,6 +3190,8 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse rt5645_enable_push_button_irq(component, true); } } else { + if (rt5645->en_button_func) + rt5645_enable_push_button_irq(component, false); snd_soc_dapm_disable_pin(dapm, "Mic Det Power"); snd_soc_dapm_sync(dapm); rt5645->jack_type = SND_JACK_HEADPHONE; @@ -3269,6 +3272,8 @@ static void rt5645_jack_detect_work(struct work_struct *work) if (!rt5645->component) return; + mutex_lock(&rt5645->jd_mutex); + switch (rt5645->pdata.jd_mode) { case 0: /* Not using rt5645 JD */ if (rt5645->gpiod_hp_det) { @@ -3283,6 +3288,7 @@ static void rt5645_jack_detect_work(struct work_struct *work) report, SND_JACK_HEADPHONE); snd_soc_jack_report(rt5645->mic_jack, report, SND_JACK_MICROPHONE); + mutex_unlock(&rt5645->jd_mutex); return; case 4: val = snd_soc_component_read(rt5645->component, RT5645_A_JD_CTRL1) & 0x0020; @@ -3295,7 +3301,7 @@ static void rt5645_jack_detect_work(struct work_struct *work) if (!val && (rt5645->jack_type == 0)) { /* jack in */ report = rt5645_jack_detect(rt5645->component, 1); - } else if (!val && rt5645->jack_type != 0) { + } else if (!val && rt5645->jack_type == SND_JACK_HEADSET) { /* for push button and jack out */ btn_type = 0; if (snd_soc_component_read(rt5645->component, RT5645_INT_IRQ_ST) & 0x4) { @@ -3351,6 +3357,8 @@ static void rt5645_jack_detect_work(struct work_struct *work) rt5645_jack_detect(rt5645->component, 0); } + mutex_unlock(&rt5645->jd_mutex); + snd_soc_jack_report(rt5645->hp_jack, report, SND_JACK_HEADPHONE); snd_soc_jack_report(rt5645->mic_jack, report, SND_JACK_MICROPHONE); if (rt5645->en_button_func) @@ -3820,14 +3828,6 @@ static const struct dmi_system_id dmi_platform_data[] = { }, .driver_data = (void *)&ecs_ef20_platform_data, }, - { - .ident = "EF20EA", - .callback = cht_rt5645_ef20_quirk_cb, - .matches = { - DMI_MATCH(DMI_PRODUCT_NAME, "EF20EA"), - }, - .driver_data = (void *)&ecs_ef20_platform_data, - }, { } }; @@ -4119,6 +4119,7 @@ static int rt5645_i2c_probe(struct i2c_client *i2c) } timer_setup(&rt5645->btn_check_timer, rt5645_btn_check_callback, 0); + mutex_init(&rt5645->jd_mutex); INIT_DELAYED_WORK(&rt5645->jack_detect_work, rt5645_jack_detect_work); INIT_DELAYED_WORK(&rt5645->rcclock_work, rt5645_rcclock_work); diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c index a2abd1a11161..e80be4e4fa8b 100644 --- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -3588,7 +3588,7 @@ static int wcd938x_probe(struct platform_device *pdev) ret = wcd938x_populate_dt_data(wcd938x, dev); if (ret) { dev_err(dev, "%s: Fail to obtain platform data\n", __func__); - return -EINVAL; + return ret; } ret = wcd938x_add_slave_components(wcd938x, dev, &match); diff --git a/sound/soc/codecs/wm8974.c b/sound/soc/codecs/wm8974.c index 010a394c705c..1becbf2c6ffa 100644 --- a/sound/soc/codecs/wm8974.c +++ b/sound/soc/codecs/wm8974.c @@ -186,7 +186,7 @@ SOC_DAPM_SINGLE("PCM Playback Switch", WM8974_MONOMIX, 0, 1, 0), /* Boost mixer */ static const struct snd_kcontrol_new wm8974_boost_mixer[] = { -SOC_DAPM_SINGLE("Aux Switch", WM8974_INPPGA, 6, 1, 1), +SOC_DAPM_SINGLE("PGA Switch", WM8974_INPPGA, 6, 1, 1), }; /* Input PGA */ @@ -246,8 +246,8 @@ static const struct snd_soc_dapm_route wm8974_dapm_routes[] = { /* Boost Mixer */ {"ADC", NULL, "Boost Mixer"}, - {"Boost Mixer", "Aux Switch", "Aux Input"}, - {"Boost Mixer", NULL, "Input PGA"}, + {"Boost Mixer", NULL, "Aux Input"}, + {"Boost Mixer", "PGA Switch", "Input PGA"}, {"Boost Mixer", NULL, "MICP"}, /* Input PGA */ diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 2cfca78f0401..47a4c363227c 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -740,19 +740,25 @@ static int wm_adsp_request_firmware_file(struct wm_adsp *dsp, const char *filetype) { struct cs_dsp *cs_dsp = &dsp->cs_dsp; + const char *fwf; char *s, c; int ret = 0; + if (dsp->fwf_name) + fwf = dsp->fwf_name; + else + fwf = dsp->cs_dsp.name; + if (system_name && asoc_component_prefix) *filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s-%s-%s.%s", dir, dsp->part, - dsp->fwf_name, wm_adsp_fw[dsp->fw].file, system_name, + fwf, wm_adsp_fw[dsp->fw].file, system_name, asoc_component_prefix, filetype); else if (system_name) *filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s-%s.%s", dir, dsp->part, - dsp->fwf_name, wm_adsp_fw[dsp->fw].file, system_name, + fwf, wm_adsp_fw[dsp->fw].file, system_name, filetype); else - *filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s.%s", dir, dsp->part, dsp->fwf_name, + *filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s.%s", dir, dsp->part, fwf, wm_adsp_fw[dsp->fw].file, filetype); if (*filename == NULL) @@ -842,29 +848,18 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp, } adsp_err(dsp, "Failed to request firmware <%s>%s-%s-%s<-%s<%s>>.wmfw\n", - cirrus_dir, dsp->part, dsp->fwf_name, wm_adsp_fw[dsp->fw].file, - system_name, asoc_component_prefix); + cirrus_dir, dsp->part, + dsp->fwf_name ? dsp->fwf_name : dsp->cs_dsp.name, + wm_adsp_fw[dsp->fw].file, system_name, asoc_component_prefix); return -ENOENT; } static int wm_adsp_common_init(struct wm_adsp *dsp) { - char *p; - INIT_LIST_HEAD(&dsp->compr_list); INIT_LIST_HEAD(&dsp->buffer_list); - if (!dsp->fwf_name) { - p = devm_kstrdup(dsp->cs_dsp.dev, dsp->cs_dsp.name, GFP_KERNEL); - if (!p) - return -ENOMEM; - - dsp->fwf_name = p; - for (; *p != 0; ++p) - *p = tolower(*p); - } - return 0; } diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c index b152f4e5c4f2..cd96c35a150c 100644 --- a/sound/soc/codecs/wsa883x.c +++ b/sound/soc/codecs/wsa883x.c @@ -1102,7 +1102,11 @@ static int wsa_dev_mode_put(struct snd_kcontrol *kcontrol, return 1; } -static const DECLARE_TLV_DB_SCALE(pa_gain, -300, 150, -300); +static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(pa_gain, + 0, 14, TLV_DB_SCALE_ITEM(-300, 0, 0), + 15, 29, TLV_DB_SCALE_ITEM(-300, 150, 0), + 30, 31, TLV_DB_SCALE_ITEM(1800, 0, 0), +); static int wsa883x_get_swr_port(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) diff --git a/sound/soc/fsl/fsl_rpmsg.c b/sound/soc/fsl/fsl_rpmsg.c index bf94838bdbef..5c07a8ff0c9c 100644 --- a/sound/soc/fsl/fsl_rpmsg.c +++ b/sound/soc/fsl/fsl_rpmsg.c @@ -231,7 +231,7 @@ static int fsl_rpmsg_probe(struct platform_device *pdev) ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, &fsl_rpmsg_dai, 1); if (ret) - return ret; + goto err_pm_disable; rpmsg->card_pdev = platform_device_register_data(&pdev->dev, "imx-audio-rpmsg", @@ -241,16 +241,22 @@ static int fsl_rpmsg_probe(struct platform_device *pdev) if (IS_ERR(rpmsg->card_pdev)) { dev_err(&pdev->dev, "failed to register rpmsg card\n"); ret = PTR_ERR(rpmsg->card_pdev); - return ret; + goto err_pm_disable; } return 0; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + return ret; } static int fsl_rpmsg_remove(struct platform_device *pdev) { struct fsl_rpmsg *rpmsg = platform_get_drvdata(pdev); + pm_runtime_disable(&pdev->dev); + if (rpmsg->card_pdev) platform_device_unregister(rpmsg->card_pdev); diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 6364d9be28fb..cf1cd0460ad9 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -715,6 +715,9 @@ static int fsl_sai_hw_free(struct snd_pcm_substream *substream, bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; unsigned int ofs = sai->soc_data->reg_offset; + /* Clear xMR to avoid channel swap with mclk_with_tere enabled case */ + regmap_write(sai->regmap, FSL_SAI_xMR(tx), 0); + regmap_update_bits(sai->regmap, FSL_SAI_xCR3(tx, ofs), FSL_SAI_CR3_TRCE_MASK, 0); diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 783c20125992..797d0a48d606 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -83,6 +83,7 @@ enum { #define BYT_RT5640_HSMIC2_ON_IN1 BIT(27) #define BYT_RT5640_JD_HP_ELITEP_1000G2 BIT(28) #define BYT_RT5640_USE_AMCR0F28 BIT(29) +#define BYT_RT5640_SWAPPED_SPEAKERS BIT(30) #define BYTCR_INPUT_DEFAULTS \ (BYT_RT5640_IN3_MAP | \ @@ -157,6 +158,8 @@ static void log_quirks(struct device *dev) dev_info(dev, "quirk MONO_SPEAKER enabled\n"); if (byt_rt5640_quirk & BYT_RT5640_NO_SPEAKERS) dev_info(dev, "quirk NO_SPEAKERS enabled\n"); + if (byt_rt5640_quirk & BYT_RT5640_SWAPPED_SPEAKERS) + dev_info(dev, "quirk SWAPPED_SPEAKERS enabled\n"); if (byt_rt5640_quirk & BYT_RT5640_LINEOUT) dev_info(dev, "quirk LINEOUT enabled\n"); if (byt_rt5640_quirk & BYT_RT5640_LINEOUT_AS_HP2) @@ -884,6 +887,19 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { + /* Medion Lifetab S10346 */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"), + /* Above strings are much too generic, also match on BIOS date */ + DMI_MATCH(DMI_BIOS_DATE, "10/22/2015"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_SWAPPED_SPEAKERS | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* Mele PCG03 Mini PC */ .matches = { DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Mini PC"), @@ -1609,11 +1625,11 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) const char *platform_name; struct acpi_device *adev; struct device *codec_dev; + const char *cfg_spk; bool sof_parent; int ret_val = 0; int dai_index = 0; - int i, cfg_spk; - int aif; + int i, aif; is_bytcr = false; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -1773,13 +1789,16 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) } if (byt_rt5640_quirk & BYT_RT5640_NO_SPEAKERS) { - cfg_spk = 0; + cfg_spk = "0"; spk_type = "none"; } else if (byt_rt5640_quirk & BYT_RT5640_MONO_SPEAKER) { - cfg_spk = 1; + cfg_spk = "1"; spk_type = "mono"; + } else if (byt_rt5640_quirk & BYT_RT5640_SWAPPED_SPEAKERS) { + cfg_spk = "swapped"; + spk_type = "swapped"; } else { - cfg_spk = 2; + cfg_spk = "2"; spk_type = "stereo"; } @@ -1794,7 +1813,7 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) headset2_string = " cfg-hs2:in1"; snprintf(byt_rt5640_components, sizeof(byt_rt5640_components), - "cfg-spk:%d cfg-mic:%s aif:%d%s%s", cfg_spk, + "cfg-spk:%s cfg-mic:%s aif:%d%s%s", cfg_spk, map_name[BYT_RT5640_MAP(byt_rt5640_quirk)], aif, lineout_string, headset2_string); byt_rt5640_card.components = byt_rt5640_components; diff --git a/sound/soc/intel/boards/skl_hda_dsp_generic.c b/sound/soc/intel/boards/skl_hda_dsp_generic.c index 879ebba52832..463ffb85121d 100644 --- a/sound/soc/intel/boards/skl_hda_dsp_generic.c +++ b/sound/soc/intel/boards/skl_hda_dsp_generic.c @@ -157,6 +157,8 @@ static int skl_hda_fill_card_info(struct snd_soc_acpi_mach_params *mach_params) card->dapm_widgets = skl_hda_widgets; card->num_dapm_widgets = ARRAY_SIZE(skl_hda_widgets); if (!ctx->idisp_codec) { + card->dapm_routes = &skl_hda_map[IDISP_ROUTE_COUNT]; + num_route -= IDISP_ROUTE_COUNT; for (i = 0; i < IDISP_DAI_COUNT; i++) { skl_hda_be_dai_links[i].codecs = dummy_codec; skl_hda_be_dai_links[i].num_codecs = diff --git a/sound/soc/intel/common/soc-acpi-intel-glk-match.c b/sound/soc/intel/common/soc-acpi-intel-glk-match.c index 387e73100884..8911c90bbaf6 100644 --- a/sound/soc/intel/common/soc-acpi-intel-glk-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-glk-match.c @@ -19,6 +19,11 @@ static const struct snd_soc_acpi_codecs glk_codecs = { .codecs = {"MX98357A"} }; +static const struct snd_soc_acpi_codecs glk_rt5682_rt5682s_hp = { + .num_codecs = 2, + .codecs = {"10EC5682", "RTL5682"}, +}; + struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[] = { { .id = "INT343A", @@ -35,7 +40,7 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[] = { .sof_tplg_filename = "sof-glk-da7219.tplg", }, { - .id = "10EC5682", + .comp_ids = &glk_rt5682_rt5682s_hp, .drv_name = "glk_rt5682_mx98357a", .fw_filename = "intel/dsp_fw_glk.bin", .machine_quirk = snd_soc_acpi_codec_list, @@ -43,13 +48,6 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[] = { .sof_tplg_filename = "sof-glk-rt5682.tplg", }, { - .id = "RTL5682", - .drv_name = "glk_rt5682_max98357a", - .machine_quirk = snd_soc_acpi_codec_list, - .quirk_data = &glk_codecs, - .sof_tplg_filename = "sof-glk-rt5682.tplg", - }, - { .id = "10134242", .drv_name = "glk_cs4242_mx98357a", .fw_filename = "intel/dsp_fw_glk.bin", diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c index 1015716f9336..adee4be2dea7 100644 --- a/sound/soc/intel/skylake/skl-pcm.c +++ b/sound/soc/intel/skylake/skl-pcm.c @@ -251,8 +251,10 @@ static int skl_pcm_open(struct snd_pcm_substream *substream, snd_pcm_set_sync(substream); mconfig = skl_tplg_fe_get_cpr_module(dai, substream->stream); - if (!mconfig) + if (!mconfig) { + kfree(dma_params); return -EINVAL; + } skl_tplg_d0i3_get(skl, mconfig->d0i3_caps); @@ -1471,6 +1473,7 @@ int skl_platform_register(struct device *dev) dais = krealloc(skl->dais, sizeof(skl_fe_dai) + sizeof(skl_platform_dai), GFP_KERNEL); if (!dais) { + kfree(skl->dais); ret = -ENOMEM; goto err; } @@ -1483,8 +1486,10 @@ int skl_platform_register(struct device *dev) ret = devm_snd_soc_register_component(dev, &skl_component, skl->dais, num_dais); - if (ret) + if (ret) { + kfree(skl->dais); dev_err(dev, "soc component registration failed %d\n", ret); + } err: return ret; } diff --git a/sound/soc/intel/skylake/skl-sst-ipc.c b/sound/soc/intel/skylake/skl-sst-ipc.c index 7a425271b08b..fd9624ad5f72 100644 --- a/sound/soc/intel/skylake/skl-sst-ipc.c +++ b/sound/soc/intel/skylake/skl-sst-ipc.c @@ -1003,8 +1003,10 @@ int skl_ipc_get_large_config(struct sst_generic_ipc *ipc, reply.size = (reply.header >> 32) & IPC_DATA_OFFSET_SZ_MASK; buf = krealloc(reply.data, reply.size, GFP_KERNEL); - if (!buf) + if (!buf) { + kfree(reply.data); return -ENOMEM; + } *payload = buf; *bytes = reply.size; diff --git a/sound/soc/mediatek/common/mtk-dsp-sof-common.c b/sound/soc/mediatek/common/mtk-dsp-sof-common.c index 8b1b623207be..d4d1d3b9572a 100644 --- a/sound/soc/mediatek/common/mtk-dsp-sof-common.c +++ b/sound/soc/mediatek/common/mtk-dsp-sof-common.c @@ -24,7 +24,7 @@ int mtk_sof_dai_link_fixup(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai_link *sof_dai_link = NULL; const struct sof_conn_stream *conn = &sof_priv->conn_streams[i]; - if (strcmp(rtd->dai_link->name, conn->normal_link)) + if (conn->normal_link && strcmp(rtd->dai_link->name, conn->normal_link)) continue; for_each_card_rtds(card, runtime) { diff --git a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c index 094402470dc2..858b95b199dc 100644 --- a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c +++ b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c @@ -499,7 +499,7 @@ static const struct snd_soc_dapm_widget mtk_dai_adda_widgets[] = { SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD), SND_SOC_DAPM_SUPPLY_S("AUD_PAD_TOP", SUPPLY_SEQ_ADDA_AUD_PAD_TOP, - 0, 0, 0, + AFE_AUD_PAD_TOP, RG_RX_FIFO_ON_SFT, 0, mtk_adda_pad_top_event, SND_SOC_DAPM_PRE_PMU), SND_SOC_DAPM_SUPPLY_S("ADDA_MTKAIF_CFG", SUPPLY_SEQ_ADDA_MTKAIF_CFG, diff --git a/sound/soc/meson/g12a-toacodec.c b/sound/soc/meson/g12a-toacodec.c index ddc667956cf5..8d8d848ebd58 100644 --- a/sound/soc/meson/g12a-toacodec.c +++ b/sound/soc/meson/g12a-toacodec.c @@ -71,6 +71,9 @@ static int g12a_toacodec_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, reg; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); regmap_field_read(priv->field_dat_sel, ®); @@ -101,7 +104,7 @@ static int g12a_toacodec_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(g12a_toacodec_mux_enum, TOACODEC_CTRL0, diff --git a/sound/soc/meson/g12a-tohdmitx.c b/sound/soc/meson/g12a-tohdmitx.c index 579a04ad4d19..154c324fdd42 100644 --- a/sound/soc/meson/g12a-tohdmitx.c +++ b/sound/soc/meson/g12a-tohdmitx.c @@ -45,6 +45,9 @@ static int g12a_tohdmitx_i2s_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, changed; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); changed = snd_soc_component_test_bits(component, e->reg, CTRL0_I2S_DAT_SEL, @@ -93,6 +96,9 @@ static int g12a_tohdmitx_spdif_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, changed; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); changed = snd_soc_component_test_bits(component, TOHDMITX_CTRL0, CTRL0_SPDIF_SEL, @@ -112,7 +118,7 @@ static int g12a_tohdmitx_spdif_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(g12a_tohdmitx_spdif_mux_enum, TOHDMITX_CTRL0, diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 55b009d3c681..2d25748ca706 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -661,7 +661,7 @@ int snd_soc_limit_volume(struct snd_soc_card *card, kctl = snd_soc_card_get_kcontrol(card, name); if (kctl) { struct soc_mixer_control *mc = (struct soc_mixer_control *)kctl->private_value; - if (max <= mc->max) { + if (max <= mc->max - mc->min) { mc->platform_max = max; ret = 0; } diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index f2ec2a6c2e0f..a0dfd7de431f 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -54,8 +54,16 @@ static int request_codec_module(struct hda_codec *codec) static int hda_codec_load_module(struct hda_codec *codec) { - int ret = request_codec_module(codec); + int ret; + + ret = snd_hdac_device_register(&codec->core); + if (ret) { + dev_err(&codec->core.dev, "failed to register hdac device\n"); + put_device(&codec->core.dev); + return ret; + } + ret = request_codec_module(codec); if (ret <= 0) { codec->probe_id = HDA_CODEC_ID_GENERIC; ret = request_codec_module(codec); @@ -112,7 +120,6 @@ EXPORT_SYMBOL_NS(hda_codec_jack_check, SND_SOC_SOF_HDA_AUDIO_CODEC); static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, int type) { struct hda_codec *codec; - int ret; codec = snd_hda_codec_device_init(to_hda_bus(bus), addr, "ehdaudio%dD%d", bus->idx, addr); if (IS_ERR(codec)) { @@ -122,13 +129,6 @@ static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, i codec->core.type = type; - ret = snd_hdac_device_register(&codec->core); - if (ret) { - dev_err(bus->dev, "failed to register hdac device\n"); - put_device(&codec->core.dev); - return ERR_PTR(ret); - } - return codec; } diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c index bcceebca915a..484b0e7c2def 100644 --- a/sound/soc/sunxi/sun4i-spdif.c +++ b/sound/soc/sunxi/sun4i-spdif.c @@ -578,6 +578,11 @@ static const struct of_device_id sun4i_spdif_of_match[] = { .compatible = "allwinner,sun50i-h6-spdif", .data = &sun50i_h6_spdif_quirks, }, + { + .compatible = "allwinner,sun50i-h616-spdif", + /* Essentially the same as the H6, but without RX */ + .data = &sun50i_h6_spdif_quirks, + }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, sun4i_spdif_of_match); diff --git a/sound/usb/clock.c b/sound/usb/clock.c index 33db334e6556..a676ad093d18 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -328,8 +328,16 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, if (chip->quirk_flags & QUIRK_FLAG_SKIP_CLOCK_SELECTOR) return ret; err = uac_clock_selector_set_val(chip, entity_id, cur); - if (err < 0) + if (err < 0) { + if (pins == 1) { + usb_audio_dbg(chip, + "%s(): selector returned an error, " + "assuming a firmware bug, id %d, ret %d\n", + __func__, clock_id, err); + return ret; + } return err; + } } if (!validate || ret > 0 || !chip->autoclock) diff --git a/sound/usb/format.c b/sound/usb/format.c index ab5fed9f55b6..3b45d0ee7693 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -470,9 +470,11 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip, int clock) { struct usb_device *dev = chip->dev; + struct usb_host_interface *alts; unsigned int *table; unsigned int nr_rates; int i, err; + u32 bmControls; /* performing the rate verification may lead to unexpected USB bus * behavior afterwards by some unknown reason. Do this only for the @@ -481,6 +483,24 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip, if (!(chip->quirk_flags & QUIRK_FLAG_VALIDATE_RATES)) return 0; /* don't perform the validation as default */ + alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting); + if (!alts) + return 0; + + if (fp->protocol == UAC_VERSION_3) { + struct uac3_as_header_descriptor *as = snd_usb_find_csint_desc( + alts->extra, alts->extralen, NULL, UAC_AS_GENERAL); + bmControls = le32_to_cpu(as->bmControls); + } else { + struct uac2_as_header_descriptor *as = snd_usb_find_csint_desc( + alts->extra, alts->extralen, NULL, UAC_AS_GENERAL); + bmControls = as->bmControls; + } + + if (!uac_v2v3_control_is_readable(bmControls, + UAC2_AS_VAL_ALT_SETTINGS)) + return 0; + table = kcalloc(fp->nr_rates, sizeof(*table), GFP_KERNEL); if (!table) return -ENOMEM; diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c index 9d11bb08667e..1bcb05c73e0a 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett_gen2.c @@ -1337,9 +1337,11 @@ static void scarlett2_config_save(struct usb_mixer_interface *mixer) { __le32 req = cpu_to_le32(SCARLETT2_USB_CONFIG_SAVE); - scarlett2_usb(mixer, SCARLETT2_USB_DATA_CMD, - &req, sizeof(u32), - NULL, 0); + int err = scarlett2_usb(mixer, SCARLETT2_USB_DATA_CMD, + &req, sizeof(u32), + NULL, 0); + if (err < 0) + usb_audio_err(mixer->chip, "config save failed: %d\n", err); } /* Delayed work to save config */ @@ -1388,7 +1390,10 @@ static int scarlett2_usb_set_config( size = 1; offset = config_item->offset; - scarlett2_usb_get(mixer, offset, &tmp, 1); + err = scarlett2_usb_get(mixer, offset, &tmp, 1); + if (err < 0) + return err; + if (value) tmp |= (1 << index); else @@ -1793,14 +1798,20 @@ static int scarlett2_sync_ctl_get(struct snd_kcontrol *kctl, struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; + int err = 0; mutex_lock(&private->data_mutex); - if (private->sync_updated) - scarlett2_update_sync(mixer); + + if (private->sync_updated) { + err = scarlett2_update_sync(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.enumerated.item[0] = private->sync; - mutex_unlock(&private->data_mutex); - return 0; +unlock: + mutex_unlock(&private->data_mutex); + return err; } static const struct snd_kcontrol_new scarlett2_sync_ctl = { @@ -1883,22 +1894,35 @@ static int scarlett2_master_volume_ctl_get(struct snd_kcontrol *kctl, struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; + int err = 0; mutex_lock(&private->data_mutex); - if (private->vol_updated) - scarlett2_update_volumes(mixer); - mutex_unlock(&private->data_mutex); + if (private->vol_updated) { + err = scarlett2_update_volumes(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.integer.value[0] = private->master_vol; - return 0; + +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int line_out_remap(struct scarlett2_data *private, int index) { const struct scarlett2_device_info *info = private->info; + const int (*port_count)[SCARLETT2_PORT_DIRNS] = info->port_count; + int line_out_count = + port_count[SCARLETT2_PORT_TYPE_ANALOGUE][SCARLETT2_PORT_OUT]; if (!info->line_out_remap_enable) return index; + + if (index >= line_out_count) + return index; + return info->line_out_remap[index]; } @@ -1909,14 +1933,20 @@ static int scarlett2_volume_ctl_get(struct snd_kcontrol *kctl, struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; int index = line_out_remap(private, elem->control); + int err = 0; mutex_lock(&private->data_mutex); - if (private->vol_updated) - scarlett2_update_volumes(mixer); - mutex_unlock(&private->data_mutex); + if (private->vol_updated) { + err = scarlett2_update_volumes(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.integer.value[0] = private->vol[index]; - return 0; + +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int scarlett2_volume_ctl_put(struct snd_kcontrol *kctl, @@ -1983,14 +2013,20 @@ static int scarlett2_mute_ctl_get(struct snd_kcontrol *kctl, struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; int index = line_out_remap(private, elem->control); + int err = 0; mutex_lock(&private->data_mutex); - if (private->vol_updated) - scarlett2_update_volumes(mixer); - mutex_unlock(&private->data_mutex); + if (private->vol_updated) { + err = scarlett2_update_volumes(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.integer.value[0] = private->mute_switch[index]; - return 0; + +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int scarlett2_mute_ctl_put(struct snd_kcontrol *kctl, @@ -2236,14 +2272,20 @@ static int scarlett2_level_enum_ctl_get(struct snd_kcontrol *kctl, const struct scarlett2_device_info *info = private->info; int index = elem->control + info->level_input_first; + int err = 0; mutex_lock(&private->data_mutex); - if (private->input_other_updated) - scarlett2_update_input_other(mixer); + + if (private->input_other_updated) { + err = scarlett2_update_input_other(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.enumerated.item[0] = private->level_switch[index]; - mutex_unlock(&private->data_mutex); - return 0; +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int scarlett2_level_enum_ctl_put(struct snd_kcontrol *kctl, @@ -2294,15 +2336,21 @@ static int scarlett2_pad_ctl_get(struct snd_kcontrol *kctl, struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; + int err = 0; mutex_lock(&private->data_mutex); - if (private->input_other_updated) - scarlett2_update_input_other(mixer); + + if (private->input_other_updated) { + err = scarlett2_update_input_other(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.integer.value[0] = private->pad_switch[elem->control]; - mutex_unlock(&private->data_mutex); - return 0; +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int scarlett2_pad_ctl_put(struct snd_kcontrol *kctl, @@ -2352,14 +2400,20 @@ static int scarlett2_air_ctl_get(struct snd_kcontrol *kctl, struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; + int err = 0; mutex_lock(&private->data_mutex); - if (private->input_other_updated) - scarlett2_update_input_other(mixer); + + if (private->input_other_updated) { + err = scarlett2_update_input_other(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.integer.value[0] = private->air_switch[elem->control]; - mutex_unlock(&private->data_mutex); - return 0; +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int scarlett2_air_ctl_put(struct snd_kcontrol *kctl, @@ -2409,15 +2463,21 @@ static int scarlett2_phantom_ctl_get(struct snd_kcontrol *kctl, struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; + int err = 0; mutex_lock(&private->data_mutex); - if (private->input_other_updated) - scarlett2_update_input_other(mixer); + + if (private->input_other_updated) { + err = scarlett2_update_input_other(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.integer.value[0] = private->phantom_switch[elem->control]; - mutex_unlock(&private->data_mutex); - return 0; +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int scarlett2_phantom_ctl_put(struct snd_kcontrol *kctl, @@ -2589,14 +2649,20 @@ static int scarlett2_direct_monitor_ctl_get( struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = elem->head.mixer->private_data; + int err = 0; mutex_lock(&private->data_mutex); - if (private->monitor_other_updated) - scarlett2_update_monitor_other(mixer); + + if (private->monitor_other_updated) { + err = scarlett2_update_monitor_other(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.enumerated.item[0] = private->direct_monitor_switch; - mutex_unlock(&private->data_mutex); - return 0; +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int scarlett2_direct_monitor_ctl_put( @@ -2696,14 +2762,20 @@ static int scarlett2_speaker_switch_enum_ctl_get( struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; + int err = 0; mutex_lock(&private->data_mutex); - if (private->monitor_other_updated) - scarlett2_update_monitor_other(mixer); + + if (private->monitor_other_updated) { + err = scarlett2_update_monitor_other(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.enumerated.item[0] = private->speaker_switching_switch; - mutex_unlock(&private->data_mutex); - return 0; +unlock: + mutex_unlock(&private->data_mutex); + return err; } /* when speaker switching gets enabled, switch the main/alt speakers @@ -2851,14 +2923,20 @@ static int scarlett2_talkback_enum_ctl_get( struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; + int err = 0; mutex_lock(&private->data_mutex); - if (private->monitor_other_updated) - scarlett2_update_monitor_other(mixer); + + if (private->monitor_other_updated) { + err = scarlett2_update_monitor_other(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.enumerated.item[0] = private->talkback_switch; - mutex_unlock(&private->data_mutex); - return 0; +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int scarlett2_talkback_enum_ctl_put( @@ -3006,14 +3084,20 @@ static int scarlett2_dim_mute_ctl_get(struct snd_kcontrol *kctl, struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; + int err = 0; mutex_lock(&private->data_mutex); - if (private->vol_updated) - scarlett2_update_volumes(mixer); - mutex_unlock(&private->data_mutex); + if (private->vol_updated) { + err = scarlett2_update_volumes(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.integer.value[0] = private->dim_mute[elem->control]; - return 0; + +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int scarlett2_dim_mute_ctl_put(struct snd_kcontrol *kctl, @@ -3277,7 +3361,8 @@ static int scarlett2_mixer_ctl_put(struct snd_kcontrol *kctl, mutex_lock(&private->data_mutex); oval = private->mix[index]; - val = ucontrol->value.integer.value[0]; + val = clamp(ucontrol->value.integer.value[0], + 0L, (long)SCARLETT2_MIXER_MAX_VALUE); num_mixer_in = port_count[SCARLETT2_PORT_TYPE_MIX][SCARLETT2_PORT_OUT]; mix_num = index / num_mixer_in; @@ -3383,22 +3468,21 @@ static int scarlett2_mux_src_enum_ctl_get(struct snd_kcontrol *kctl, struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; - const struct scarlett2_device_info *info = private->info; - const int (*port_count)[SCARLETT2_PORT_DIRNS] = info->port_count; - int line_out_count = - port_count[SCARLETT2_PORT_TYPE_ANALOGUE][SCARLETT2_PORT_OUT]; - int index = elem->control; - - if (index < line_out_count) - index = line_out_remap(private, index); + int index = line_out_remap(private, elem->control); + int err = 0; mutex_lock(&private->data_mutex); - if (private->mux_updated) - scarlett2_usb_get_mux(mixer); + + if (private->mux_updated) { + err = scarlett2_usb_get_mux(mixer); + if (err < 0) + goto unlock; + } ucontrol->value.enumerated.item[0] = private->mux[index]; - mutex_unlock(&private->data_mutex); - return 0; +unlock: + mutex_unlock(&private->data_mutex); + return err; } static int scarlett2_mux_src_enum_ctl_put(struct snd_kcontrol *kctl, @@ -3407,16 +3491,9 @@ static int scarlett2_mux_src_enum_ctl_put(struct snd_kcontrol *kctl, struct usb_mixer_elem_info *elem = kctl->private_data; struct usb_mixer_interface *mixer = elem->head.mixer; struct scarlett2_data *private = mixer->private_data; - const struct scarlett2_device_info *info = private->info; - const int (*port_count)[SCARLETT2_PORT_DIRNS] = info->port_count; - int line_out_count = - port_count[SCARLETT2_PORT_TYPE_ANALOGUE][SCARLETT2_PORT_OUT]; - int index = elem->control; + int index = line_out_remap(private, elem->control); int oval, val, err = 0; - if (index < line_out_count) - index = line_out_remap(private, index); - mutex_lock(&private->data_mutex); oval = private->mux[index]; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index f458328f9ec4..b8a474a2e4d5 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1385,7 +1385,7 @@ free_buf: static int snd_usb_motu_m_series_boot_quirk(struct usb_device *dev) { - msleep(2000); + msleep(4000); return 0; } @@ -1628,7 +1628,7 @@ int snd_usb_apply_boot_quirk_once(struct usb_device *dev, unsigned int id) { switch (id) { - case USB_ID(0x07fd, 0x0008): /* MOTU M Series */ + case USB_ID(0x07fd, 0x0008): /* MOTU M Series, 1st hardware version */ return snd_usb_motu_m_series_boot_quirk(dev); } @@ -2029,10 +2029,14 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x0499, 0x1509, /* Steinberg UR22 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x0499, 0x3108, /* Yamaha YIT-W12TX */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x04d8, 0xfeea, /* Benchmark DAC1 Pre */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x04e8, 0xa051, /* Samsung USBC Headset (AKG) */ QUIRK_FLAG_SKIP_CLOCK_SELECTOR | QUIRK_FLAG_CTL_MSG_DELAY_5M), + DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */ + QUIRK_FLAG_IFACE_SKIP_CLOSE), DEVICE_FLG(0x054c, 0x0b8c, /* Sony WALKMAN NW-A45 DAC */ QUIRK_FLAG_SET_IFACE_FIRST), DEVICE_FLG(0x0556, 0x0014, /* Phoenix Audio TMX320VC */ @@ -2071,14 +2075,22 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0763, 0x2031, /* M-Audio Fast Track C600 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x07fd, 0x000b, /* MOTU M Series 2nd hardware revision */ + QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x08bb, 0x2702, /* LineX FM Transmitter */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x0951, 0x16ad, /* Kingston HyperX */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x0b0e, 0x0349, /* Jabra 550a */ QUIRK_FLAG_CTL_MSG_DELAY_1M), + DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */ + QUIRK_FLAG_FIXED_RATE), + DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */ + QUIRK_FLAG_FIXED_RATE), DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), + DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x1397, 0x0507, /* Behringer UMC202HD */ @@ -2111,6 +2123,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x1901, 0x0191, /* GE B850V3 CP2114 audio interface */ QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x19f7, 0x0035, /* RODE NT-USB+ */ + QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x2040, 0x7200, /* Hauppauge HVR-950Q */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x2040, 0x7201, /* Hauppauge HVR-950Q-MXL */ @@ -2153,6 +2169,12 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */ QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */ + QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */ + QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */ + QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */ @@ -2161,22 +2183,6 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x534d, 0x2109, /* MacroSilicon MS2109 */ QUIRK_FLAG_ALIGN_TRANSFER), - DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */ - QUIRK_FLAG_GET_SAMPLE_RATE), - DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */ - QUIRK_FLAG_GENERIC_IMPLICIT_FB), - DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */ - QUIRK_FLAG_GENERIC_IMPLICIT_FB), - DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */ - QUIRK_FLAG_GENERIC_IMPLICIT_FB), - DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */ - QUIRK_FLAG_IFACE_SKIP_CLOSE), - DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */ - QUIRK_FLAG_FIXED_RATE), - DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */ - QUIRK_FLAG_FIXED_RATE), - DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */ - QUIRK_FLAG_GET_SAMPLE_RATE), /* Vendor matches */ VENDOR_FLG(0x045e, /* MS Lifecam */ diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h index 11ff975242ca..e2ff22b379a4 100644 --- a/tools/arch/x86/include/asm/rmwcc.h +++ b/tools/arch/x86/include/asm/rmwcc.h @@ -4,7 +4,7 @@ #define __GEN_RMWcc(fullop, var, cc, ...) \ do { \ - asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \ + asm goto (fullop "; j" cc " %l[cc_label]" \ : : "m" (var), ## __VA_ARGS__ \ : "memory" : cc_label); \ return 0; \ diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c index eb6303ff446e..4cfcef9da3e4 100644 --- a/tools/build/feature/test-libopencsd.c +++ b/tools/build/feature/test-libopencsd.c @@ -4,9 +4,9 @@ /* * Check OpenCSD library version is sufficient to provide required features */ -#define OCSD_MIN_VER ((1 << 16) | (1 << 8) | (1)) +#define OCSD_MIN_VER ((1 << 16) | (2 << 8) | (1)) #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER) -#error "OpenCSD >= 1.1.1 is required" +#error "OpenCSD >= 1.2.1 is required" #endif int main(void) diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h index 1bdd834bdd57..d09f9dc172a4 100644 --- a/tools/include/linux/compiler_types.h +++ b/tools/include/linux/compiler_types.h @@ -36,8 +36,8 @@ #include <linux/compiler-gcc.h> #endif -#ifndef asm_volatile_goto -#define asm_volatile_goto(x...) asm goto(x) +#ifndef asm_goto_output +#define asm_goto_output(x...) asm goto(x) #endif #endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 92dbe89dafbf..201dc77ebbd7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4353,6 +4353,8 @@ union bpf_attr { * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags) * Description * Return a user or a kernel stack in bpf program provided buffer. + * Note: the user stack will only be populated if the *task* is + * the current task; all other tasks will return -EOPNOTSUPP. * To achieve this, the helper needs *task*, which is a valid * pointer to **struct task_struct**. To store the stacktrace, the * bpf program provides *buf* with a nonnegative *size*. @@ -4364,6 +4366,7 @@ union bpf_attr { * * **BPF_F_USER_STACK** * Collect a user space stack instead of a kernel stack. + * The *task* must be the current task. * **BPF_F_USER_BUILD_ID** * Collect buildid+offset instead of ips for user stack, * only valid if **BPF_F_USER_STACK** is also specified. diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h index 777c20f6b604..458acd294237 100644 --- a/tools/lib/api/io.h +++ b/tools/lib/api/io.h @@ -9,6 +9,7 @@ #include <stdlib.h> #include <unistd.h> +#include <linux/types.h> struct io { /* File descriptor being read/ */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 10f15a3e3a95..e2014b1250ea 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4157,6 +4157,8 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Dat scn = elf_sec_by_idx(obj, sec_idx); scn_data = elf_sec_data(obj, scn); + if (!scn_data) + return -LIBBPF_ERRNO__FORMAT; relo_sec_name = elf_sec_str(obj, shdr->sh_name); sec_name = elf_sec_name(obj, scn); diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c index bf02d62a3b2b..42f57b640f11 100644 --- a/tools/lib/subcmd/help.c +++ b/tools/lib/subcmd/help.c @@ -50,11 +50,21 @@ void uniq(struct cmdnames *cmds) if (!cmds->cnt) return; - for (i = j = 1; i < cmds->cnt; i++) - if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name)) - cmds->names[j++] = cmds->names[i]; - + for (i = 1; i < cmds->cnt; i++) { + if (!strcmp(cmds->names[i]->name, cmds->names[i-1]->name)) + zfree(&cmds->names[i - 1]); + } + for (i = 0, j = 0; i < cmds->cnt; i++) { + if (cmds->names[i]) { + if (i == j) + j++; + else + cmds->names[j++] = cmds->names[i]; + } + } cmds->cnt = j; + while (j < i) + cmds->names[j++] = NULL; } void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index cc7c1f90cf62..91c7bfa82a50 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -606,9 +606,9 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env) return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env); } -void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, - struct perf_env *env, - FILE *fp) +void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, + struct perf_env *env, + FILE *fp) { __u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens); __u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms); @@ -624,7 +624,7 @@ void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, if (info->btf_id) { struct btf_node *node; - node = perf_env__find_btf(env, info->btf_id); + node = __perf_env__find_btf(env, info->btf_id); if (node) btf = btf__new((__u8 *)(node->data), node->data_size); diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index 1bcbd4fb6c66..e2f0420905f5 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -33,9 +33,9 @@ struct btf_node { int machine__process_bpf(struct machine *machine, union perf_event *event, struct perf_sample *sample); int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env); -void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, - struct perf_env *env, - FILE *fp); +void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, + struct perf_env *env, + FILE *fp); #else static inline int machine__process_bpf(struct machine *machine __maybe_unused, union perf_event *event __maybe_unused, @@ -50,9 +50,9 @@ static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused, return 0; } -static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused, - struct perf_env *env __maybe_unused, - FILE *fp __maybe_unused) +static inline void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused, + struct perf_env *env __maybe_unused, + FILE *fp __maybe_unused) { } diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 5b8cf6a421a4..5d878bae7d9a 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -22,12 +22,18 @@ struct perf_env perf_env; void perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) { + down_write(&env->bpf_progs.lock); + __perf_env__insert_bpf_prog_info(env, info_node); + up_write(&env->bpf_progs.lock); +} + +void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) +{ __u32 prog_id = info_node->info_linear->info.id; struct bpf_prog_info_node *node; struct rb_node *parent = NULL; struct rb_node **p; - down_write(&env->bpf_progs.lock); p = &env->bpf_progs.infos.rb_node; while (*p != NULL) { @@ -39,15 +45,13 @@ void perf_env__insert_bpf_prog_info(struct perf_env *env, p = &(*p)->rb_right; } else { pr_debug("duplicated bpf prog info %u\n", prog_id); - goto out; + return; } } rb_link_node(&info_node->rb_node, parent, p); rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos); env->bpf_progs.infos_cnt++; -out: - up_write(&env->bpf_progs.lock); } struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, @@ -77,13 +81,21 @@ out: bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) { + bool ret; + + down_write(&env->bpf_progs.lock); + ret = __perf_env__insert_btf(env, btf_node); + up_write(&env->bpf_progs.lock); + return ret; +} + +bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) +{ struct rb_node *parent = NULL; __u32 btf_id = btf_node->id; struct btf_node *node; struct rb_node **p; - bool ret = true; - down_write(&env->bpf_progs.lock); p = &env->bpf_progs.btfs.rb_node; while (*p != NULL) { @@ -95,25 +107,31 @@ bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) p = &(*p)->rb_right; } else { pr_debug("duplicated btf %u\n", btf_id); - ret = false; - goto out; + return false; } } rb_link_node(&btf_node->rb_node, parent, p); rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs); env->bpf_progs.btfs_cnt++; -out: - up_write(&env->bpf_progs.lock); - return ret; + return true; } struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id) { + struct btf_node *res; + + down_read(&env->bpf_progs.lock); + res = __perf_env__find_btf(env, btf_id); + up_read(&env->bpf_progs.lock); + return res; +} + +struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id) +{ struct btf_node *node = NULL; struct rb_node *n; - down_read(&env->bpf_progs.lock); n = env->bpf_progs.btfs.rb_node; while (n) { @@ -123,13 +141,9 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id) else if (btf_id > node->id) n = n->rb_right; else - goto out; + return node; } - node = NULL; - -out: - up_read(&env->bpf_progs.lock); - return node; + return NULL; } /* purge data in bpf_progs.infos tree */ diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 4566c51f2fd9..359eff51cb85 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -164,12 +164,16 @@ const char *perf_env__raw_arch(struct perf_env *env); int perf_env__nr_cpus_avail(struct perf_env *env); void perf_env__init(struct perf_env *env); +void __perf_env__insert_bpf_prog_info(struct perf_env *env, + struct bpf_prog_info_node *info_node); void perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node); struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, __u32 prog_id); bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); +bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id); +struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id); int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu); char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name, diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index fefc72066c4e..ac17a3cb59dc 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -293,9 +293,9 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, */ phdr = elf_newphdr(e, 1); phdr[0].p_type = PT_LOAD; - phdr[0].p_offset = 0; - phdr[0].p_vaddr = 0; - phdr[0].p_paddr = 0; + phdr[0].p_offset = GEN_ELF_TEXT_OFFSET; + phdr[0].p_vaddr = GEN_ELF_TEXT_OFFSET; + phdr[0].p_paddr = GEN_ELF_TEXT_OFFSET; phdr[0].p_filesz = csize; phdr[0].p_memsz = csize; phdr[0].p_flags = PF_X | PF_R; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 9e2dce70b130..b2b0293567f0 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1809,8 +1809,8 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) node = rb_entry(next, struct bpf_prog_info_node, rb_node); next = rb_next(&node->rb_node); - bpf_event__print_bpf_prog_info(&node->info_linear->info, - env, fp); + __bpf_event__print_bpf_prog_info(&node->info_linear->info, + env, fp); } up_read(&env->bpf_progs.lock); @@ -3136,7 +3136,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) /* after reading from file, translate offset to address */ bpil_offs_to_addr(info_linear); info_node->info_linear = info_linear; - perf_env__insert_bpf_prog_info(env, info_node); + __perf_env__insert_bpf_prog_info(env, info_node); } up_write(&env->bpf_progs.lock); @@ -3183,7 +3183,7 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) if (__do_read(ff, node->data, data_size)) goto out; - perf_env__insert_btf(env, node); + __perf_env__insert_btf(env, node); node = NULL; } @@ -4314,9 +4314,10 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) ret += fprintf(fp, "... "); map = cpu_map__new_data(&ev->cpus.cpus); - if (map) + if (map) { ret += cpu_map__fprintf(map, fp); - else + perf_cpu_map__put(map); + } else ret += fprintf(fp, "failed to get cpus\n"); break; default: diff --git a/tools/perf/util/hisi-ptt.c b/tools/perf/util/hisi-ptt.c index 45b614bb73bf..764d660d30e2 100644 --- a/tools/perf/util/hisi-ptt.c +++ b/tools/perf/util/hisi-ptt.c @@ -121,6 +121,7 @@ static int hisi_ptt_process_auxtrace_event(struct perf_session *session, if (dump_trace) hisi_ptt_dump_event(ptt, data, size); + free(data); return 0; } diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index a38b89c28030..9ad39db32d14 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -177,7 +177,7 @@ static void find_controls(void) err = snd_ctl_elem_info(card_data->handle, ctl_data->info); if (err < 0) { - ksft_print_msg("%s getting info for %d\n", + ksft_print_msg("%s getting info for %s\n", snd_strerror(err), ctl_data->name); } @@ -205,7 +205,7 @@ static void find_controls(void) err = snd_ctl_poll_descriptors(card_data->handle, &card_data->pollfd, 1); if (err != 1) { - ksft_exit_fail_msg("snd_ctl_poll_descriptors() failed for %d\n", + ksft_exit_fail_msg("snd_ctl_poll_descriptors() failed for card %d: %d\n", card, err); } @@ -358,7 +358,7 @@ static bool ctl_value_index_valid(struct ctl_data *ctl, } if (int64_val > snd_ctl_elem_info_get_max64(ctl->info)) { - ksft_print_msg("%s.%d value %lld more than maximum %lld\n", + ksft_print_msg("%s.%d value %lld more than maximum %ld\n", ctl->name, index, int64_val, snd_ctl_elem_info_get_max(ctl->info)); return false; diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index e914cc45b766..6f00bee917a0 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -467,10 +467,20 @@ int setup_classid_environment(void) return 1; } - if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls") && - errno != EBUSY) { - log_err("mount cgroup net_cls"); - return 1; + if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls")) { + if (errno != EBUSY) { + log_err("mount cgroup net_cls"); + return 1; + } + + if (rmdir(NETCLS_MOUNT_PATH)) { + log_err("rmdir cgroup net_cls"); + return 1; + } + if (umount(CGROUP_MOUNT_DFLT)) { + log_err("umount cgroup base"); + return 1; + } } cleanup_classid_environment(); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index ecde236047fe..0c67a4e28eff 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -338,6 +338,8 @@ static void test_task_stack(void) do_dummy_read(skel->progs.dump_task_stack); do_dummy_read(skel->progs.get_task_user_stacks); + ASSERT_EQ(skel->bss->num_user_stacks, 1, "num_user_stacks"); + bpf_iter_task_stack__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index d711f4bea98e..47cb753ef1e3 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -5211,6 +5211,7 @@ static size_t get_pprint_mapv_size(enum pprint_mapv_kind_t mapv_kind) #endif assert(0); + return 0; } static void set_pprint_mapv(enum pprint_mapv_kind_t mapv_kind, diff --git a/tools/testing/selftests/bpf/prog_tests/time_tai.c b/tools/testing/selftests/bpf/prog_tests/time_tai.c index a31119823666..f45af1b0ef2c 100644 --- a/tools/testing/selftests/bpf/prog_tests/time_tai.c +++ b/tools/testing/selftests/bpf/prog_tests/time_tai.c @@ -56,7 +56,7 @@ void test_time_tai(void) ASSERT_NEQ(ts2, 0, "tai_ts2"); /* TAI is moving forward only */ - ASSERT_GT(ts2, ts1, "tai_forward"); + ASSERT_GE(ts2, ts1, "tai_forward"); /* Check for future */ ret = clock_gettime(CLOCK_TAI, &now_tai); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c index f2b8167b72a8..442f4ca39fd7 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c @@ -35,6 +35,8 @@ int dump_task_stack(struct bpf_iter__task *ctx) return 0; } +int num_user_stacks = 0; + SEC("iter/task") int get_task_user_stacks(struct bpf_iter__task *ctx) { @@ -51,6 +53,9 @@ int get_task_user_stacks(struct bpf_iter__task *ctx) if (res <= 0) return 0; + /* Only one task, the current one, should succeed */ + ++num_user_stacks; + buf_sz += res; /* If the verifier doesn't refine bpf_get_task_stack res, and instead diff --git a/tools/testing/selftests/bpf/progs/pyperf180.c b/tools/testing/selftests/bpf/progs/pyperf180.c index c39f559d3100..42c4a8b62e36 100644 --- a/tools/testing/selftests/bpf/progs/pyperf180.c +++ b/tools/testing/selftests/bpf/progs/pyperf180.c @@ -1,4 +1,26 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #define STACK_MAX_LEN 180 + +/* llvm upstream commit at clang18 + * https://github.com/llvm/llvm-project/commit/1a2e77cf9e11dbf56b5720c607313a566eebb16e + * changed inlining behavior and caused compilation failure as some branch + * target distance exceeded 16bit representation which is the maximum for + * cpu v1/v2/v3. Macro __BPF_CPU_VERSION__ is later implemented in clang18 + * to specify which cpu version is used for compilation. So a smaller + * unroll_count can be set if __BPF_CPU_VERSION__ is less than 4, which + * reduced some branch target distances and resolved the compilation failure. + * + * To capture the case where a developer/ci uses clang18 but the corresponding + * repo checkpoint does not have __BPF_CPU_VERSION__, a smaller unroll_count + * will be set as well to prevent potential compilation failures. + */ +#ifdef __BPF_CPU_VERSION__ +#if __BPF_CPU_VERSION__ < 4 +#define UNROLL_COUNT 90 +#endif +#elif __clang_major__ == 18 +#define UNROLL_COUNT 90 +#endif + #include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c index 736686e903f6..26bfbc73d129 100644 --- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -447,13 +447,13 @@ static __always_inline int tcp_lookup(void *ctx, struct header_pointers *hdr, bo unsigned long status = ct->status; bpf_ct_release(ct); - if (status & IPS_CONFIRMED_BIT) + if (status & IPS_CONFIRMED) return XDP_PASS; } else if (ct_lookup_opts.error != -ENOENT) { return XDP_ABORTED; } - /* error == -ENOENT || !(status & IPS_CONFIRMED_BIT) */ + /* error == -ENOENT || !(status & IPS_CONFIRMED) */ return XDP_TX; } diff --git a/tools/testing/selftests/bpf/verifier/ld_imm64.c b/tools/testing/selftests/bpf/verifier/ld_imm64.c index f9297900cea6..78f19c255f20 100644 --- a/tools/testing/selftests/bpf/verifier/ld_imm64.c +++ b/tools/testing/selftests/bpf/verifier/ld_imm64.c @@ -9,8 +9,8 @@ BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .errstr = "invalid BPF_LD_IMM insn", - .errstr_unpriv = "R1 pointer comparison", + .errstr = "jump into the middle of ldimm64 insn 1", + .errstr_unpriv = "jump into the middle of ldimm64 insn 1", .result = REJECT, }, { @@ -23,8 +23,8 @@ BPF_LD_IMM64(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .errstr = "invalid BPF_LD_IMM insn", - .errstr_unpriv = "R1 pointer comparison", + .errstr = "jump into the middle of ldimm64 insn 1", + .errstr_unpriv = "jump into the middle of ldimm64 insn 1", .result = REJECT, }, { diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh index 71c00bfafbc9..2ff58fed76e2 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -33,16 +33,16 @@ ip netns add "client" ip link set dev link1_1 netns client down name eth0 ip netns exec client ip link add dev bond0 down type bond mode 1 \ miimon 100 all_slaves_active 1 -ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev eth0 master bond0 ip netns exec client ip link set dev bond0 up ip netns exec client ip addr add ${client_ip4}/24 dev bond0 ip netns exec client ping -c 5 $server_ip4 >/dev/null -ip netns exec client ip link set dev eth0 down nomaster +ip netns exec client ip link set dev eth0 nomaster ip netns exec client ip link set dev bond0 down ip netns exec client ip link set dev bond0 type bond mode 0 \ arp_interval 1000 arp_ip_target "+${server_ip4}" -ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev eth0 master bond0 ip netns exec client ip link set dev bond0 up ip netns exec client ping -c 5 $server_ip4 >/dev/null diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh index 16c7fb858ac1..696ef9bf3afc 100644 --- a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh +++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh @@ -46,6 +46,17 @@ test_LAG_cleanup() ip link add mv0 link "$name" up address "$ucaddr" type macvlan # Used to test dev->mc handling ip address add "$addr6" dev "$name" + + # Check that addresses were added as expected + (grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy1 || + grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy2) >/dev/null + check_err $? "macvlan unicast address not found on a slave" + + # mcaddr is added asynchronously by addrconf_dad_work(), use busywait + (busywait 10000 grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy1 || + grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy2) >/dev/null + check_err $? "IPv6 solicited-node multicast mac address not found on a slave" + ip link set dev "$name" down ip link del "$name" diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh index f9858e221996..6a3002fbcf43 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh @@ -121,6 +121,9 @@ h2_destroy() switch_create() { + local lanes_swp4 + local pg1_size + # pools # ----- @@ -230,7 +233,20 @@ switch_create() dcb pfc set dev $swp4 prio-pfc all:off 1:on # PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which # is (-2*MTU) about 80K of delay provision. - dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB + pg1_size=$_100KB + + setup_wait_dev_with_timeout $swp4 + + lanes_swp4=$(ethtool $swp4 | grep 'Lanes:') + lanes_swp4=${lanes_swp4#*"Lanes: "} + + # 8-lane ports use two buffers among which the configured buffer + # is split, so double the size to get twice (20K + 80K). + if [[ $lanes_swp4 -eq 8 ]]; then + pg1_size=$((pg1_size * 2)) + fi + + dcb buffer set dev $swp4 buffer-size all:0 1:$pg1_size # bridges # ------- diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh index fb850e0ec837..616d3581419c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh @@ -10,7 +10,8 @@ lib_dir=$(dirname $0)/../../../../net/forwarding ALL_TESTS="single_mask_test identical_filters_test two_masks_test \ multiple_masks_test ctcam_edge_cases_test delta_simple_test \ delta_two_masks_one_key_test delta_simple_rehash_test \ - bloom_simple_test bloom_complex_test bloom_delta_test" + bloom_simple_test bloom_complex_test bloom_delta_test \ + max_erp_entries_test max_group_size_test" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/tc_common.sh @@ -983,6 +984,109 @@ bloom_delta_test() log_test "bloom delta test ($tcflags)" } +max_erp_entries_test() +{ + # The number of eRP entries is limited. Once the maximum number of eRPs + # has been reached, filters cannot be added. This test verifies that + # when this limit is reached, inserstion fails without crashing. + + RET=0 + + local num_masks=32 + local num_regions=15 + local chain_failed + local mask_failed + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + for ((i=1; i < $num_regions; i++)); do + for ((j=$num_masks; j >= 0; j--)); do + tc filter add dev $h2 ingress chain $i protocol ip \ + pref $i handle $j flower $tcflags \ + dst_ip 192.1.0.0/$j &> /dev/null + ret=$? + + if [ $ret -ne 0 ]; then + chain_failed=$i + mask_failed=$j + break 2 + fi + done + done + + # We expect to exceed the maximum number of eRP entries, so that + # insertion eventually fails. Otherwise, the test should be adjusted to + # add more filters. + check_fail $ret "expected to exceed number of eRP entries" + + for ((; i >= 1; i--)); do + for ((j=0; j <= $num_masks; j++)); do + tc filter del dev $h2 ingress chain $i protocol ip \ + pref $i handle $j flower &> /dev/null + done + done + + log_test "max eRP entries test ($tcflags). " \ + "max chain $chain_failed, mask $mask_failed" +} + +max_group_size_test() +{ + # The number of ACLs in an ACL group is limited. Once the maximum + # number of ACLs has been reached, filters cannot be added. This test + # verifies that when this limit is reached, insertion fails without + # crashing. + + RET=0 + + local num_acls=32 + local max_size + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + for ((i=1; i < $num_acls; i++)); do + if [[ $(( i % 2 )) == 1 ]]; then + tc filter add dev $h2 ingress pref $i proto ipv4 \ + flower $tcflags dst_ip 198.51.100.1/32 \ + ip_proto tcp tcp_flags 0x01/0x01 \ + action drop &> /dev/null + else + tc filter add dev $h2 ingress pref $i proto ipv6 \ + flower $tcflags dst_ip 2001:db8:1::1/128 \ + action drop &> /dev/null + fi + + ret=$? + [[ $ret -ne 0 ]] && max_size=$((i - 1)) && break + done + + # We expect to exceed the maximum number of ACLs in a group, so that + # insertion eventually fails. Otherwise, the test should be adjusted to + # add more filters. + check_fail $ret "expected to exceed number of ACLs in a group" + + for ((; i >= 1; i--)); do + if [[ $(( i % 2 )) == 1 ]]; then + tc filter del dev $h2 ingress pref $i proto ipv4 \ + flower $tcflags dst_ip 198.51.100.1/32 \ + ip_proto tcp tcp_flags 0x01/0x01 \ + action drop &> /dev/null + else + tc filter del dev $h2 ingress pref $i proto ipv6 \ + flower $tcflags dst_ip 2001:db8:1::1/128 \ + action drop &> /dev/null + fi + done + + log_test "max ACL group size test ($tcflags). max size $max_size" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 1b08e042cf94..185b02d2d4cd 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -269,6 +269,7 @@ for port in 0 1; do echo 1 > $NSIM_DEV_SYS/new_port fi NSIM_NETDEV=`get_netdev_name old_netdevs` + ifconfig $NSIM_NETDEV up msg="new NIC device created" exp0=( 0 0 0 0 ) @@ -430,6 +431,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "overflow NIC table" @@ -487,6 +489,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "overflow NIC table" @@ -543,6 +546,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "destroy NIC" @@ -572,6 +576,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -632,6 +637,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error @@ -687,6 +693,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -746,6 +753,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -876,6 +884,7 @@ msg="re-add a port" echo 2 > $NSIM_DEV_SYS/del_port echo 2 > $NSIM_DEV_SYS/new_port +NSIM_NETDEV=`get_netdev_name old_netdevs` check_tables msg="replace VxLAN in overflow table" diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config index 265b6882cc21..b5e3a3aad4bf 100644 --- a/tools/testing/selftests/drivers/net/team/config +++ b/tools/testing/selftests/drivers/net/team/config @@ -1,3 +1,5 @@ +CONFIG_DUMMY=y +CONFIG_IPV6=y +CONFIG_MACVLAN=y CONFIG_NET_TEAM=y CONFIG_NET_TEAM_MODE_LOADBALANCE=y -CONFIG_MACVLAN=y diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index b5234d6efbe1..ec40a33c29fd 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -226,13 +226,15 @@ static void clear_log_create_vm_done(struct kvm_vm *vm) } static void dirty_log_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages) + void *bitmap, uint32_t num_pages, + uint32_t *unused) { kvm_vm_get_dirty_log(vcpu->vm, slot, bitmap); } static void clear_log_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages) + void *bitmap, uint32_t num_pages, + uint32_t *unused) { kvm_vm_get_dirty_log(vcpu->vm, slot, bitmap); kvm_vm_clear_dirty_log(vcpu->vm, slot, bitmap, 0, num_pages); @@ -329,10 +331,9 @@ static void dirty_ring_continue_vcpu(void) } static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages) + void *bitmap, uint32_t num_pages, + uint32_t *ring_buf_idx) { - /* We only have one vcpu */ - static uint32_t fetch_index = 0; uint32_t count = 0, cleared; bool continued_vcpu = false; @@ -349,11 +350,15 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, /* Only have one vcpu */ count = dirty_ring_collect_one(vcpu_map_dirty_ring(vcpu), - slot, bitmap, num_pages, &fetch_index); + slot, bitmap, num_pages, + ring_buf_idx); cleared = kvm_vm_reset_dirty_ring(vcpu->vm); - /* Cleared pages should be the same as collected */ + /* + * Cleared pages should be the same as collected, as KVM is supposed to + * clear only the entries that have been harvested. + */ TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch " "with collected (%u)", cleared, count); @@ -392,12 +397,6 @@ static void dirty_ring_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) } } -static void dirty_ring_before_vcpu_join(void) -{ - /* Kick another round of vcpu just to make sure it will quit */ - sem_post(&sem_vcpu_cont); -} - struct log_mode { const char *name; /* Return true if this mode is supported, otherwise false */ @@ -406,10 +405,10 @@ struct log_mode { void (*create_vm_done)(struct kvm_vm *vm); /* Hook to collect the dirty pages into the bitmap provided */ void (*collect_dirty_pages) (struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages); + void *bitmap, uint32_t num_pages, + uint32_t *ring_buf_idx); /* Hook to call when after each vcpu run */ void (*after_vcpu_run)(struct kvm_vcpu *vcpu, int ret, int err); - void (*before_vcpu_join) (void); } log_modes[LOG_MODE_NUM] = { { .name = "dirty-log", @@ -428,7 +427,6 @@ struct log_mode { .supported = dirty_ring_supported, .create_vm_done = dirty_ring_create_vm_done, .collect_dirty_pages = dirty_ring_collect_dirty_pages, - .before_vcpu_join = dirty_ring_before_vcpu_join, .after_vcpu_run = dirty_ring_after_vcpu_run, }, }; @@ -471,13 +469,14 @@ static void log_mode_create_vm_done(struct kvm_vm *vm) } static void log_mode_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages) + void *bitmap, uint32_t num_pages, + uint32_t *ring_buf_idx) { struct log_mode *mode = &log_modes[host_log_mode]; TEST_ASSERT(mode->collect_dirty_pages != NULL, "collect_dirty_pages() is required for any log mode!"); - mode->collect_dirty_pages(vcpu, slot, bitmap, num_pages); + mode->collect_dirty_pages(vcpu, slot, bitmap, num_pages, ring_buf_idx); } static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) @@ -488,14 +487,6 @@ static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) mode->after_vcpu_run(vcpu, ret, err); } -static void log_mode_before_vcpu_join(void) -{ - struct log_mode *mode = &log_modes[host_log_mode]; - - if (mode->before_vcpu_join) - mode->before_vcpu_join(); -} - static void generate_random_array(uint64_t *guest_array, uint64_t size) { uint64_t i; @@ -696,6 +687,8 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct kvm_vcpu *vcpu; struct kvm_vm *vm; unsigned long *bmap; + uint32_t ring_buf_idx = 0; + int sem_val; if (!log_mode_supported()) { print_skip("Log mode '%s' not supported", @@ -767,10 +760,21 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Start the iterations */ iteration = 1; sync_global_to_guest(vm, iteration); - host_quit = false; + WRITE_ONCE(host_quit, false); host_dirty_count = 0; host_clear_count = 0; host_track_next_count = 0; + WRITE_ONCE(dirty_ring_vcpu_ring_full, false); + + /* + * Ensure the previous iteration didn't leave a dangling semaphore, i.e. + * that the main task and vCPU worker were synchronized and completed + * verification of all iterations. + */ + sem_getvalue(&sem_vcpu_stop, &sem_val); + TEST_ASSERT_EQ(sem_val, 0); + sem_getvalue(&sem_vcpu_cont, &sem_val); + TEST_ASSERT_EQ(sem_val, 0); pthread_create(&vcpu_thread, NULL, vcpu_worker, vcpu); @@ -778,7 +782,8 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Give the vcpu thread some time to dirty some pages */ usleep(p->interval * 1000); log_mode_collect_dirty_pages(vcpu, TEST_MEM_SLOT_INDEX, - bmap, host_num_pages); + bmap, host_num_pages, + &ring_buf_idx); /* * See vcpu_sync_stop_requested definition for details on why @@ -796,15 +801,21 @@ static void run_test(enum vm_guest_mode mode, void *arg) assert(host_log_mode == LOG_MODE_DIRTY_RING || atomic_read(&vcpu_sync_stop_requested) == false); vm_dirty_log_verify(mode, bmap); - sem_post(&sem_vcpu_cont); - iteration++; + /* + * Set host_quit before sem_vcpu_cont in the final iteration to + * ensure that the vCPU worker doesn't resume the guest. As + * above, the dirty ring test may stop and wait even when not + * explicitly request to do so, i.e. would hang waiting for a + * "continue" if it's allowed to resume the guest. + */ + if (++iteration == p->iterations) + WRITE_ONCE(host_quit, true); + + sem_post(&sem_vcpu_cont); sync_global_to_guest(vm, iteration); } - /* Tell the vcpu thread to quit */ - host_quit = true; - log_mode_before_vcpu_join(); pthread_join(vcpu_thread, NULL); pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), " diff --git a/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh b/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh index c899b446acb6..327427ec10f5 100755 --- a/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh +++ b/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh @@ -150,7 +150,7 @@ arp_test_gratuitous() { fi # Supply arp_accept option to set up which sets it in sysctl setup ${arp_accept} - ip netns exec ${HOST_NS} arping -A -U ${HOST_ADDR} -c1 2>&1 >/dev/null + ip netns exec ${HOST_NS} arping -A -I ${HOST_INTF} -U ${HOST_ADDR} -c1 2>&1 >/dev/null if verify_arp $1 $2; then printf " TEST: %-60s [ OK ]\n" "${test_msg[*]}" diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh index 330d0b1ceced..c921750ca118 100755 --- a/tools/testing/selftests/net/cmsg_ipv6.sh +++ b/tools/testing/selftests/net/cmsg_ipv6.sh @@ -91,7 +91,7 @@ for ovr in setsock cmsg both diff; do check_result $? 0 "TCLASS $prot $ovr - pass" while [ -d /proc/$BG ]; do - $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234 done tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null @@ -128,7 +128,7 @@ for ovr in setsock cmsg both diff; do check_result $? 0 "HOPLIMIT $prot $ovr - pass" while [ -d /proc/$BG ]; do - $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234 done tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index bd89198cd817..ec097f245726 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -13,6 +13,7 @@ CONFIG_IPV6_VTI=y CONFIG_DUMMY=y CONFIG_BRIDGE=y CONFIG_VLAN_8021Q=y +CONFIG_GENEVE=m CONFIG_IFB=y CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y diff --git a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh index 51df5e305855..b52d59547fc5 100755 --- a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh +++ b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh @@ -209,12 +209,12 @@ validate_v6_exception() echo "Route get" ip -netns h0 -6 ro get ${dst} echo "Searching for:" - echo " ${dst} from :: via ${r1} dev eth0 src ${h0} .* mtu ${mtu}" + echo " ${dst}.* via ${r1} dev eth0 src ${h0} .* mtu ${mtu}" echo fi ip -netns h0 -6 ro get ${dst} | \ - grep -q "${dst} from :: via ${r1} dev eth0 src ${h0} .* mtu ${mtu}" + grep -q "${dst}.* via ${r1} dev eth0 src ${h0} .* mtu ${mtu}" rc=$? log_test $rc 0 "IPv6: host 0 to host ${i}, mtu ${mtu}" diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index e317c2e44dae..4f80014cae49 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -22,8 +22,11 @@ CONFIG_NFT_TPROXY=m CONFIG_NFT_SOCKET=m CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IP6_NF_FILTER=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_CLS_ACT=y diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index ea6fc59e9f62..2107579e2939 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2167,9 +2167,9 @@ link_failure_tests() pm_nl_set_limits $ns1 0 2 pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 2 - FAILING_LINKS="1" pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 1 + FAILING_LINKS="1" \ + run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_link_usage $ns2 ns2eth3 $cinsent 0 @@ -2183,8 +2183,8 @@ link_failure_tests() pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 1 + FAILING_LINKS="1 2" \ + run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_stale_nr $ns2 2 4 2 @@ -2199,8 +2199,8 @@ link_failure_tests() pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 2 + FAILING_LINKS="1 2" \ + run_tests $ns1 $ns2 10.0.1.1 2 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_stale_nr $ns2 1 -1 2 @@ -2652,7 +2652,7 @@ backup_tests() fi if reset "mpc backup" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr 0 0 0 @@ -2660,7 +2660,7 @@ backup_tests() fi if reset "mpc backup both sides" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow @@ -2669,7 +2669,7 @@ backup_tests() fi if reset "mpc switch to backup" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup chk_join_nr 0 0 0 @@ -2677,7 +2677,7 @@ backup_tests() fi if reset "mpc switch to backup both sides" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup @@ -3041,7 +3041,7 @@ fastclose_tests() if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_server - chk_join_nr 0 0 0 + chk_join_nr 0 0 0 0 0 0 1 chk_fclose_nr 1 1 invert chk_rst_nr 1 1 fi diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings index 79b65bdf05db..abc5648b59ab 100644 --- a/tools/testing/selftests/net/mptcp/settings +++ b/tools/testing/selftests/net/mptcp/settings @@ -1 +1 @@ -timeout=1200 +timeout=1800 diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 0d705fdcf3b7..00ab4c6e4044 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -713,23 +713,23 @@ setup_xfrm6() { } setup_xfrm4udp() { - setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 4 4500 + setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 4 4500 } setup_xfrm6udp() { - setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 6 4500 + setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 6 4500 } setup_xfrm4udprouted() { - setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 4 4500 + setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 4 4500 } setup_xfrm6udprouted() { - setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 6 4500 + setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 6 4500 } setup_routing_old() { @@ -1928,6 +1928,13 @@ check_command() { return 0 } +check_running() { + pid=${1} + cmd=${2} + + [ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ] +} + test_cleanup_vxlanX_exception() { outer="${1}" encap="vxlan" @@ -1958,11 +1965,12 @@ test_cleanup_vxlanX_exception() { ${ns_a} ip link del dev veth_A-R1 & iplink_pid=$! - sleep 1 - if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then - err " can't delete veth device in a timely manner, PMTU dst likely leaked" - return 1 - fi + for i in $(seq 1 20); do + check_running ${iplink_pid} "iplinkdeldevveth_A-R1" || return 0 + sleep 0.1 + done + err " can't delete veth device in a timely manner, PMTU dst likely leaked" + return 1 } test_cleanup_ipv6_exception() { diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh index 1003ddf7b3b2..227fd1076f21 100644 --- a/tools/testing/selftests/net/setup_veth.sh +++ b/tools/testing/selftests/net/setup_veth.sh @@ -8,7 +8,7 @@ setup_veth_ns() { local -r ns_mac="$4" [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" - echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" + echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535 ip -netns "${ns_name}" link set dev "${ns_dev}" up diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index c079565add39..9690a5d7ffd7 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -37,6 +37,10 @@ create_ns() { for ns in $NS_SRC $NS_DST; do ip netns add $ns ip -n $ns link set dev lo up + + # disable route solicitations to decrease 'noise' traffic + ip netns exec $ns sysctl -qw net.ipv6.conf.default.router_solicitations=0 + ip netns exec $ns sysctl -qw net.ipv6.conf.all.router_solicitations=0 done ip link add name veth$SRC type veth peer name veth$DST @@ -78,6 +82,12 @@ create_vxlan_pair() { create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V6$((3 - $ns)) vxlan6$ns 6 ip -n $BASE$ns addr add dev vxlan6$ns $OL_NET_V6$ns/24 nodad done + + # preload neighbur cache, do avoid some noisy traffic + local addr_dst=$(ip -j -n $BASE$DST link show dev vxlan6$DST |jq -r '.[]["address"]') + local addr_src=$(ip -j -n $BASE$SRC link show dev vxlan6$SRC |jq -r '.[]["address"]') + ip -n $BASE$DST neigh add dev vxlan6$DST lladdr $addr_src $OL_NET_V6$SRC + ip -n $BASE$SRC neigh add dev vxlan6$SRC lladdr $addr_dst $OL_NET_V6$DST } is_ipv6() { @@ -117,7 +127,7 @@ run_test() { # not enable GRO ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 4789 ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000 - ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args & + ip netns exec $NS_DST ./udpgso_bench_rx -C 2000 -R 100 -n 10 -l 1300 $rx_args & local spid=$! sleep 0.1 ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst @@ -166,7 +176,7 @@ run_bench() { # bind the sender and the receiver to different CPUs to try # get reproducible results ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus" - ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10 & + ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 2000 -R 100 & local spid=$! sleep 0.1 ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index f35a924d4a30..1cbadd267c96 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -375,7 +375,7 @@ static void do_recv(void) do_flush_udp(fd); tnow = gettimeofday_ms(); - if (tnow > treport) { + if (!cfg_expected_pkt_nr && tnow > treport) { if (packets) fprintf(stderr, "%s rx: %6lu MB/s %8lu calls/s\n", diff --git a/tools/testing/selftests/powerpc/math/fpu_preempt.c b/tools/testing/selftests/powerpc/math/fpu_preempt.c index 5235bdc8c0b1..3e5b5663d244 100644 --- a/tools/testing/selftests/powerpc/math/fpu_preempt.c +++ b/tools/testing/selftests/powerpc/math/fpu_preempt.c @@ -37,19 +37,20 @@ __thread double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0, int threads_starting; int running; -extern void preempt_fpu(double *darray, int *threads_starting, int *running); +extern int preempt_fpu(double *darray, int *threads_starting, int *running); void *preempt_fpu_c(void *p) { + long rc; int i; + srand(pthread_self()); for (i = 0; i < 21; i++) darray[i] = rand(); - /* Test failed if it ever returns */ - preempt_fpu(darray, &threads_starting, &running); + rc = preempt_fpu(darray, &threads_starting, &running); - return p; + return (void *)rc; } int test_preempt_fpu(void) diff --git a/tools/testing/selftests/powerpc/math/vmx_preempt.c b/tools/testing/selftests/powerpc/math/vmx_preempt.c index 6761d6ce30ec..6f7cf400c687 100644 --- a/tools/testing/selftests/powerpc/math/vmx_preempt.c +++ b/tools/testing/selftests/powerpc/math/vmx_preempt.c @@ -37,19 +37,21 @@ __thread vector int varray[] = {{1, 2, 3, 4}, {5, 6, 7, 8}, {9, 10,11,12}, int threads_starting; int running; -extern void preempt_vmx(vector int *varray, int *threads_starting, int *running); +extern int preempt_vmx(vector int *varray, int *threads_starting, int *running); void *preempt_vmx_c(void *p) { int i, j; + long rc; + srand(pthread_self()); for (i = 0; i < 12; i++) for (j = 0; j < 4; j++) varray[i][j] = rand(); - /* Test fails if it ever returns */ - preempt_vmx(varray, &threads_starting, &running); - return p; + rc = preempt_vmx(varray, &threads_starting, &running); + + return (void *)rc; } int test_preempt_vmx(void) diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 75af864e07b6..04ee17d3d394 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -16,9 +16,9 @@ HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC -z noexecstack ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ -fno-stack-protector -mrdrnd $(INCLUDES) +ifeq ($(CAN_BUILD_X86_64), 1) TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx -ifeq ($(CAN_BUILD_X86_64), 1) all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf endif diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c index 94bdeac1cf04..c9f658e44de6 100644 --- a/tools/testing/selftests/sgx/load.c +++ b/tools/testing/selftests/sgx/load.c @@ -136,11 +136,11 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg) */ uint64_t encl_get_entry(struct encl *encl, const char *symbol) { + Elf64_Sym *symtab = NULL; + char *sym_names = NULL; Elf64_Shdr *sections; - Elf64_Sym *symtab; Elf64_Ehdr *ehdr; - char *sym_names; - int num_sym; + int num_sym = 0; int i; ehdr = encl->bin; @@ -161,6 +161,9 @@ uint64_t encl_get_entry(struct encl *encl, const char *symbol) } } + if (!symtab || !sym_names) + return 0; + for (i = 0; i < num_sym; i++) { Elf64_Sym *sym = &symtab[i]; diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c index a07896a46364..d73b29becf5b 100644 --- a/tools/testing/selftests/sgx/sigstruct.c +++ b/tools/testing/selftests/sgx/sigstruct.c @@ -318,9 +318,9 @@ bool encl_measure(struct encl *encl) struct sgx_sigstruct *sigstruct = &encl->sigstruct; struct sgx_sigstruct_payload payload; uint8_t digest[SHA256_DIGEST_LENGTH]; + EVP_MD_CTX *ctx = NULL; unsigned int siglen; RSA *key = NULL; - EVP_MD_CTX *ctx; int i; memset(sigstruct, 0, sizeof(*sigstruct)); @@ -384,7 +384,8 @@ bool encl_measure(struct encl *encl) return true; err: - EVP_MD_CTX_destroy(ctx); + if (ctx) + EVP_MD_CTX_destroy(ctx); RSA_free(key); return false; } diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c index c0d6397295e3..ae791df3e5a5 100644 --- a/tools/testing/selftests/sgx/test_encl.c +++ b/tools/testing/selftests/sgx/test_encl.c @@ -24,10 +24,11 @@ static void do_encl_emodpe(void *_op) secinfo.flags = op->flags; asm volatile(".byte 0x0f, 0x01, 0xd7" - : + : /* no outputs */ : "a" (EMODPE), "b" (&secinfo), - "c" (op->epc_addr)); + "c" (op->epc_addr) + : "memory" /* read from secinfo pointer */); } static void do_encl_eaccept(void *_op) @@ -42,7 +43,8 @@ static void do_encl_eaccept(void *_op) : "=a" (rax) : "a" (EACCEPT), "b" (&secinfo), - "c" (op->epc_addr)); + "c" (op->epc_addr) + : "memory" /* read from secinfo pointer */); op->ret = rax; } diff --git a/tools/testing/selftests/sgx/test_encl.lds b/tools/testing/selftests/sgx/test_encl.lds index a1ec64f7d91f..108bc11d1d8c 100644 --- a/tools/testing/selftests/sgx/test_encl.lds +++ b/tools/testing/selftests/sgx/test_encl.lds @@ -34,8 +34,4 @@ SECTIONS } } -ASSERT(!DEFINED(.altinstructions), "ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.altinstr_replacement), "ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.discard.retpoline_safe), "RETPOLINE ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.discard.nospec), "RETPOLINE ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.got.plt), "Libcalls are not supported in enclaves") +ASSERT(!DEFINED(_GLOBAL_OFFSET_TABLE_), "Libcalls through GOT are not supported in enclaves") diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/atm.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/atm.json deleted file mode 100644 index f5bc8670a67d..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/atm.json +++ /dev/null @@ -1,94 +0,0 @@ -[ - { - "id": "7628", - "name": "Create ATM with default setting", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root atm", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc atm 1: root refcnt", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "390a", - "name": "Delete ATM with valid handle", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true", - "$TC qdisc add dev $DUMMY handle 1: root atm" - ], - "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc atm 1: root refcnt", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "32a0", - "name": "Show ATM class", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root atm", - "expExitCode": "0", - "verifyCmd": "$TC class show dev $DUMMY", - "matchPattern": "class atm 1: parent 1:", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "6310", - "name": "Dump ATM stats", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root atm", - "expExitCode": "0", - "verifyCmd": "$TC -s qdisc show dev $DUMMY", - "matchPattern": "qdisc atm 1: root refcnt", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - } -] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbq.json deleted file mode 100644 index 1ab21c83a122..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbq.json +++ /dev/null @@ -1,184 +0,0 @@ -[ - { - "id": "3460", - "name": "Create CBQ with default setting", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "0592", - "name": "Create CBQ with mpu", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 mpu 1000", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4684", - "name": "Create CBQ with valid cell num", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 cell 128", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4345", - "name": "Create CBQ with invalid cell num", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 cell 100", - "expExitCode": "1", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4525", - "name": "Create CBQ with valid ewma", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 ewma 16", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "6784", - "name": "Create CBQ with invalid ewma", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 ewma 128", - "expExitCode": "1", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "5468", - "name": "Delete CBQ with handle", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true", - "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000" - ], - "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "492a", - "name": "Show CBQ class", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000", - "expExitCode": "0", - "verifyCmd": "$TC class show dev $DUMMY", - "matchPattern": "class cbq 1: root rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - } -] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dsmark.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dsmark.json deleted file mode 100644 index c030795f9c37..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dsmark.json +++ /dev/null @@ -1,140 +0,0 @@ -[ - { - "id": "6345", - "name": "Create DSMARK with default setting", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "3462", - "name": "Create DSMARK with default_index setting", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 default_index 512", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400 default_index 0x0200", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "ca95", - "name": "Create DSMARK with set_tc_index flag", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 set_tc_index", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400 set_tc_index", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "a950", - "name": "Create DSMARK with multiple setting", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 default_index 1024 set_tc_index", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400 default_index 0x0400 set_tc_index", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4092", - "name": "Delete DSMARK with handle", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true", - "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 default_index 1024" - ], - "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "5930", - "name": "Show DSMARK class", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024", - "expExitCode": "0", - "verifyCmd": "$TC class show dev $DUMMY", - "matchPattern": "class dsmark 1:", - "matchCount": "0", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - } -] diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c index 0d85be2350fa..a81165930785 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/vm/ksm_tests.c @@ -470,7 +470,7 @@ static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t m if (map_ptr_orig == MAP_FAILED) err(2, "initial mmap"); - if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE)) + if (madvise(map_ptr, len, MADV_HUGEPAGE)) err(2, "MADV_HUGEPAGE"); pagemap_fd = open("/proc/self/pagemap", O_RDONLY); diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/vm/memfd_secret.c index 957b9e18c729..9b298f6a04b3 100644 --- a/tools/testing/selftests/vm/memfd_secret.c +++ b/tools/testing/selftests/vm/memfd_secret.c @@ -62,6 +62,9 @@ static void test_mlock_limit(int fd) char *mem; len = mlock_limit_cur; + if (len % page_size != 0) + len = (len/page_size) * page_size; + mem = mmap(NULL, len, prot, mode, fd, 0); if (mem == MAP_FAILED) { fail("unable to mmap secret memory\n"); diff --git a/tools/testing/selftests/vm/va_128TBswitch.sh b/tools/testing/selftests/vm/va_128TBswitch.sh index 41580751dc51..231622b3a232 100755 --- a/tools/testing/selftests/vm/va_128TBswitch.sh +++ b/tools/testing/selftests/vm/va_128TBswitch.sh @@ -29,9 +29,15 @@ check_supported_x86_64() # See man 1 gzip under '-f'. local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2) + local cpu_supports_pl5=$(awk '/^flags/ {if (/la57/) {print 0;} + else {print 1}; exit}' /proc/cpuinfo 2>/dev/null) + if [[ "${pg_table_levels}" -lt 5 ]]; then echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" exit $ksft_skip + elif [[ "${cpu_supports_pl5}" -ne 0 ]]; then + echo "$0: CPU does not have the necessary la57 flag to support page table level 5" + exit $ksft_skip fi } diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index 22e28b76f800..6912e9577b65 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \ -fasynchronous-unwind-tables -fstack-clash-protection WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized +ifeq ($(CC),clang) + FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS)) + WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS)) +endif + TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs) CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -LDFLAGS := -ggdb $(EXTRA_LDFLAGS) +LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS) LIBS := $$($(PKG_CONFIG) --libs libtracefs) SRC := $(wildcard src/*.c) diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index fe34452fc4ec..b9658f213cb5 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -129,8 +129,7 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu, if (params->output_divisor) duration = duration / params->output_divisor; - if (data->bucket_size) - bucket = duration / data->bucket_size; + bucket = duration / data->bucket_size; total_duration = duration * count; @@ -472,7 +471,11 @@ static void osnoise_hist_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index 76479bfb2922..6c07f360de72 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -282,7 +282,11 @@ void osnoise_top_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 4b48af8a8309..ed08295bfa12 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -151,8 +151,7 @@ timerlat_hist_update(struct osnoise_tool *tool, int cpu, if (params->output_divisor) latency = latency / params->output_divisor; - if (data->bucket_size) - bucket = latency / data->bucket_size; + bucket = latency / data->bucket_size; if (!thread) { hist = data->hist[cpu].irq; @@ -475,7 +474,11 @@ static void timerlat_hist_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 334271935222..8fc0f6aa19da 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -305,7 +305,11 @@ static void timerlat_top_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index 663a047f794d..8c8d63c7196c 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -243,12 +243,6 @@ static inline int sched_setattr(pid_t pid, const struct sched_attr *attr, return syscall(__NR_sched_setattr, pid, attr, flags); } -static inline int sched_getattr(pid_t pid, struct sched_attr *attr, - unsigned int size, unsigned int flags) -{ - return syscall(__NR_sched_getattr, pid, attr, size, flags); -} - int __set_sched_attr(int pid, struct sched_attr *attr) { int flags = 0; @@ -484,13 +478,13 @@ int parse_prio(char *arg, struct sched_attr *sched_param) if (prio == INVALID_VAL) return -1; - if (prio < sched_get_priority_min(SCHED_OTHER)) + if (prio < MIN_NICE) return -1; - if (prio > sched_get_priority_max(SCHED_OTHER)) + if (prio > MAX_NICE) return -1; sched_param->sched_policy = SCHED_OTHER; - sched_param->sched_priority = prio; + sched_param->sched_nice = prio; break; default: return -1; diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h index 5571afd3b549..92da41aaf4c4 100644 --- a/tools/tracing/rtla/src/utils.h +++ b/tools/tracing/rtla/src/utils.h @@ -7,6 +7,8 @@ */ #define BUFF_U64_STR_SIZE 24 #define MAX_PATH 1024 +#define MAX_NICE 20 +#define MIN_NICE -19 #define container_of(ptr, type, member)({ \ const typeof(((type *)0)->member) *__mptr = (ptr); \ |