diff options
Diffstat (limited to 'include/linux')
733 files changed, 29300 insertions, 13532 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 5b36974ed60a..c749eef1daa1 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -26,6 +26,7 @@ #include <linux/resource_ext.h> #include <linux/device.h> #include <linux/property.h> +#include <linux/uuid.h> #ifndef _LINUX #define _LINUX @@ -56,6 +57,9 @@ static inline acpi_handle acpi_device_handle(struct acpi_device *adev) acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) + +extern const struct fwnode_operations acpi_fwnode_ops; + static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) { struct fwnode_handle *fwnode; @@ -65,6 +69,7 @@ static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) return NULL; fwnode->type = FWNODE_ACPI_STATIC; + fwnode->ops = &acpi_fwnode_ops; return fwnode; } @@ -233,10 +238,6 @@ int acpi_numa_init (void); int acpi_table_init (void); int acpi_table_parse(char *id, acpi_tbl_table_handler handler); -int __init acpi_parse_entries(char *id, unsigned long table_size, - acpi_tbl_entry_handler handler, - struct acpi_table_header *table_header, - int entry_id, unsigned int max_entries); int __init acpi_table_parse_entries(char *id, unsigned long table_size, int entry_id, acpi_tbl_entry_handler handler, @@ -287,17 +288,15 @@ static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) } /* Validate the processor object's proc_id */ -bool acpi_processor_validate_proc_id(int proc_id); +bool acpi_duplicate_processor_id(int proc_id); #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ -int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu); +int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, + int *pcpu); int acpi_unmap_cpu(int cpu); -int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ -void acpi_set_processor_mapping(void); - #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); #endif @@ -463,7 +462,6 @@ struct acpi_osc_context { struct acpi_buffer ret; /* free by caller if success */ }; -acpi_status acpi_str_to_uuid(char *str, u8 *uuid); acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); /* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */ @@ -597,6 +595,13 @@ enum acpi_reconfig_event { int acpi_reconfig_notifier_register(struct notifier_block *nb); int acpi_reconfig_notifier_unregister(struct notifier_block *nb); +#ifdef CONFIG_ACPI_GTDT +int acpi_gtdt_init(struct acpi_table_header *table, int *platform_timer_count); +int acpi_gtdt_map_ppi(int type); +bool acpi_gtdt_c3stop(int type); +int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count); +#endif + #else /* !CONFIG_ACPI */ #define acpi_disabled 1 @@ -613,6 +618,11 @@ static inline bool acpi_dev_found(const char *hid) return false; } +static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) +{ + return false; +} + static inline bool is_acpi_node(struct fwnode_handle *fwnode) { return false; @@ -735,7 +745,7 @@ static inline bool acpi_driver_match_device(struct device *dev, } static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, - const u8 *uuid, + const guid_t *guid, int rev, int func, union acpi_object *argv4) { @@ -764,8 +774,11 @@ static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) return DEV_DMA_NOT_SUPPORTED; } -static inline void acpi_dma_configure(struct device *dev, - enum dev_dma_attr attr) { } +static inline int acpi_dma_configure(struct device *dev, + enum dev_dma_attr attr) +{ + return 0; +} static inline void acpi_dma_deconfigure(struct device *dev) { } @@ -951,6 +964,12 @@ static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) adev->driver_gpios = NULL; } +int devm_acpi_dev_add_driver_gpios(struct device *dev, + const struct acpi_gpio_mapping *gpios); +void devm_acpi_dev_remove_driver_gpios(struct device *dev); + +bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index); #else static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, @@ -960,6 +979,18 @@ static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, } static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) {} +static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, + const struct acpi_gpio_mapping *gpios) +{ + return -ENXIO; +} +static inline void devm_acpi_dev_remove_driver_gpios(struct device *dev) {} + +static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio) +{ + return false; +} static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { return -ENXIO; @@ -999,8 +1030,16 @@ int acpi_node_prop_read(struct fwnode_handle *fwnode, const char *propname, int acpi_dev_prop_read(struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val, size_t nval); -struct fwnode_handle *acpi_get_next_subnode(struct device *dev, - struct fwnode_handle *subnode); +struct fwnode_handle *acpi_get_next_subnode(struct fwnode_handle *fwnode, + struct fwnode_handle *child); +struct fwnode_handle *acpi_node_get_parent(struct fwnode_handle *fwnode); + +struct fwnode_handle *acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode, + struct fwnode_handle *prev); +int acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode, + struct fwnode_handle **remote, + struct fwnode_handle **port, + struct fwnode_handle **endpoint); struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, @@ -1117,12 +1156,34 @@ static inline int acpi_dev_prop_read(struct acpi_device *adev, return -ENXIO; } -static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev, - struct fwnode_handle *subnode) +static inline struct fwnode_handle * +acpi_get_next_subnode(struct fwnode_handle *fwnode, struct fwnode_handle *child) +{ + return NULL; +} + +static inline struct fwnode_handle * +acpi_node_get_parent(struct fwnode_handle *fwnode) { return NULL; } +static inline struct fwnode_handle * +acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode, + struct fwnode_handle *prev) +{ + return ERR_PTR(-ENXIO); +} + +static inline int +acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode, + struct fwnode_handle **remote, + struct fwnode_handle **port, + struct fwnode_handle **endpoint) +{ + return -ENXIO; +} + #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ static const void * __acpi_table_##name[] \ __attribute__((unused)) \ @@ -1153,4 +1214,14 @@ int parse_spcr(bool earlycon); static inline int parse_spcr(bool earlycon) { return 0; } #endif +#if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) +int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res); +#else +static inline +int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) +{ + return -EINVAL; +} +#endif + #endif /*_LINUX_ACPI_H*/ diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 77e08099e554..8379d406ad2e 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -31,20 +31,21 @@ void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); #ifdef CONFIG_ACPI_IORT void acpi_iort_init(void); -bool iort_node_match(u8 type); u32 iort_msi_map_rid(struct device *dev, u32 req_id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); +void acpi_configure_pmsi_domain(struct device *dev); +int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ void iort_set_dma_mask(struct device *dev); const struct iommu_ops *iort_iommu_configure(struct device *dev); #else static inline void acpi_iort_init(void) { } -static inline bool iort_node_match(u8 type) { return false; } static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) { return req_id; } static inline struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id) { return NULL; } +static inline void acpi_configure_pmsi_domain(struct device *dev) { } /* IOMMU interface */ static inline void iort_set_dma_mask(struct device *dev) { } static inline @@ -52,7 +53,4 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev) { return NULL; } #endif -#define IORT_ACPI_DECLARE(name, table_id, fn) \ - ACPI_DECLARE_PROBE_ENTRY(iort, name, table_id, 0, NULL, 0, fn) - #endif /* __ACPI_IORT_H__ */ diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h new file mode 100644 index 000000000000..516a6fda83c5 --- /dev/null +++ b/include/linux/amba/clcd-regs.h @@ -0,0 +1,86 @@ +/* + * David A Rusling + * + * Copyright (C) 2001 ARM Limited + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ + +#ifndef AMBA_CLCD_REGS_H +#define AMBA_CLCD_REGS_H + +/* + * CLCD Controller Internal Register addresses + */ +#define CLCD_TIM0 0x00000000 +#define CLCD_TIM1 0x00000004 +#define CLCD_TIM2 0x00000008 +#define CLCD_TIM3 0x0000000c +#define CLCD_UBAS 0x00000010 +#define CLCD_LBAS 0x00000014 + +#define CLCD_PL110_IENB 0x00000018 +#define CLCD_PL110_CNTL 0x0000001c +#define CLCD_PL110_STAT 0x00000020 +#define CLCD_PL110_INTR 0x00000024 +#define CLCD_PL110_UCUR 0x00000028 +#define CLCD_PL110_LCUR 0x0000002C + +#define CLCD_PL111_CNTL 0x00000018 +#define CLCD_PL111_IENB 0x0000001c +#define CLCD_PL111_RIS 0x00000020 +#define CLCD_PL111_MIS 0x00000024 +#define CLCD_PL111_ICR 0x00000028 +#define CLCD_PL111_UCUR 0x0000002c +#define CLCD_PL111_LCUR 0x00000030 + +#define CLCD_PALL 0x00000200 +#define CLCD_PALETTE 0x00000200 + +#define TIM2_PCD_LO_MASK GENMASK(4, 0) +#define TIM2_PCD_LO_BITS 5 +#define TIM2_CLKSEL (1 << 5) +#define TIM2_IVS (1 << 11) +#define TIM2_IHS (1 << 12) +#define TIM2_IPC (1 << 13) +#define TIM2_IOE (1 << 14) +#define TIM2_BCD (1 << 26) +#define TIM2_PCD_HI_MASK GENMASK(31, 27) +#define TIM2_PCD_HI_BITS 5 +#define TIM2_PCD_HI_SHIFT 27 + +#define CNTL_LCDEN (1 << 0) +#define CNTL_LCDBPP1 (0 << 1) +#define CNTL_LCDBPP2 (1 << 1) +#define CNTL_LCDBPP4 (2 << 1) +#define CNTL_LCDBPP8 (3 << 1) +#define CNTL_LCDBPP16 (4 << 1) +#define CNTL_LCDBPP16_565 (6 << 1) +#define CNTL_LCDBPP16_444 (7 << 1) +#define CNTL_LCDBPP24 (5 << 1) +#define CNTL_LCDBW (1 << 4) +#define CNTL_LCDTFT (1 << 5) +#define CNTL_LCDMONO8 (1 << 6) +#define CNTL_LCDDUAL (1 << 7) +#define CNTL_BGR (1 << 8) +#define CNTL_BEBO (1 << 9) +#define CNTL_BEPO (1 << 10) +#define CNTL_LCDPWR (1 << 11) +#define CNTL_LCDVCOMP(x) ((x) << 12) +#define CNTL_LDMAFIFOTIME (1 << 15) +#define CNTL_WATERMARK (1 << 16) + +/* ST Microelectronics variant bits */ +#define CNTL_ST_1XBPP_444 0x0 +#define CNTL_ST_1XBPP_5551 (1 << 17) +#define CNTL_ST_1XBPP_565 (1 << 18) +#define CNTL_ST_CDWID_12 0x0 +#define CNTL_ST_CDWID_16 (1 << 19) +#define CNTL_ST_CDWID_18 (1 << 20) +#define CNTL_ST_CDWID_24 ((1 << 19)|(1 << 20)) +#define CNTL_ST_CEAEN (1 << 21) +#define CNTL_ST_LCDBPP24_PACKED (6 << 1) + +#endif /* AMBA_CLCD_REGS_H */ diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h index 1035879b322c..d0c3be77c18e 100644 --- a/include/linux/amba/clcd.h +++ b/include/linux/amba/clcd.h @@ -10,73 +10,7 @@ * for more details. */ #include <linux/fb.h> - -/* - * CLCD Controller Internal Register addresses - */ -#define CLCD_TIM0 0x00000000 -#define CLCD_TIM1 0x00000004 -#define CLCD_TIM2 0x00000008 -#define CLCD_TIM3 0x0000000c -#define CLCD_UBAS 0x00000010 -#define CLCD_LBAS 0x00000014 - -#define CLCD_PL110_IENB 0x00000018 -#define CLCD_PL110_CNTL 0x0000001c -#define CLCD_PL110_STAT 0x00000020 -#define CLCD_PL110_INTR 0x00000024 -#define CLCD_PL110_UCUR 0x00000028 -#define CLCD_PL110_LCUR 0x0000002C - -#define CLCD_PL111_CNTL 0x00000018 -#define CLCD_PL111_IENB 0x0000001c -#define CLCD_PL111_RIS 0x00000020 -#define CLCD_PL111_MIS 0x00000024 -#define CLCD_PL111_ICR 0x00000028 -#define CLCD_PL111_UCUR 0x0000002c -#define CLCD_PL111_LCUR 0x00000030 - -#define CLCD_PALL 0x00000200 -#define CLCD_PALETTE 0x00000200 - -#define TIM2_CLKSEL (1 << 5) -#define TIM2_IVS (1 << 11) -#define TIM2_IHS (1 << 12) -#define TIM2_IPC (1 << 13) -#define TIM2_IOE (1 << 14) -#define TIM2_BCD (1 << 26) - -#define CNTL_LCDEN (1 << 0) -#define CNTL_LCDBPP1 (0 << 1) -#define CNTL_LCDBPP2 (1 << 1) -#define CNTL_LCDBPP4 (2 << 1) -#define CNTL_LCDBPP8 (3 << 1) -#define CNTL_LCDBPP16 (4 << 1) -#define CNTL_LCDBPP16_565 (6 << 1) -#define CNTL_LCDBPP16_444 (7 << 1) -#define CNTL_LCDBPP24 (5 << 1) -#define CNTL_LCDBW (1 << 4) -#define CNTL_LCDTFT (1 << 5) -#define CNTL_LCDMONO8 (1 << 6) -#define CNTL_LCDDUAL (1 << 7) -#define CNTL_BGR (1 << 8) -#define CNTL_BEBO (1 << 9) -#define CNTL_BEPO (1 << 10) -#define CNTL_LCDPWR (1 << 11) -#define CNTL_LCDVCOMP(x) ((x) << 12) -#define CNTL_LDMAFIFOTIME (1 << 15) -#define CNTL_WATERMARK (1 << 16) - -/* ST Microelectronics variant bits */ -#define CNTL_ST_1XBPP_444 0x0 -#define CNTL_ST_1XBPP_5551 (1 << 17) -#define CNTL_ST_1XBPP_565 (1 << 18) -#define CNTL_ST_CDWID_12 0x0 -#define CNTL_ST_CDWID_16 (1 << 19) -#define CNTL_ST_CDWID_18 (1 << 20) -#define CNTL_ST_CDWID_24 ((1 << 19)|(1 << 20)) -#define CNTL_ST_CEAEN (1 << 21) -#define CNTL_ST_LCDBPP24_PACKED (6 << 1) +#include <linux/amba/clcd-regs.h> enum { /* individual formats */ diff --git a/include/linux/amba/pl080.h b/include/linux/amba/pl080.h index 91b84a7f0539..ab036b6b1804 100644 --- a/include/linux/amba/pl080.h +++ b/include/linux/amba/pl080.h @@ -38,24 +38,23 @@ #define PL080_SOFT_LSREQ (0x2C) #define PL080_CONFIG (0x30) -#define PL080_CONFIG_M2_BE (1 << 2) -#define PL080_CONFIG_M1_BE (1 << 1) -#define PL080_CONFIG_ENABLE (1 << 0) +#define PL080_CONFIG_M2_BE BIT(2) +#define PL080_CONFIG_M1_BE BIT(1) +#define PL080_CONFIG_ENABLE BIT(0) #define PL080_SYNC (0x34) -/* Per channel configuration registers */ +/* The Faraday Technology FTDMAC020 variant registers */ +#define FTDMAC020_CH_BUSY (0x20) +/* Identical to PL080_CONFIG */ +#define FTDMAC020_CSR (0x24) +/* Identical to PL080_SYNC */ +#define FTDMAC020_SYNC (0x2C) +#define FTDMAC020_REVISION (0x30) +#define FTDMAC020_FEATURE (0x34) -#define PL080_Cx_STRIDE (0x20) +/* Per channel configuration registers */ #define PL080_Cx_BASE(x) ((0x100 + (x * 0x20))) -#define PL080_Cx_SRC_ADDR(x) ((0x100 + (x * 0x20))) -#define PL080_Cx_DST_ADDR(x) ((0x104 + (x * 0x20))) -#define PL080_Cx_LLI(x) ((0x108 + (x * 0x20))) -#define PL080_Cx_CONTROL(x) ((0x10C + (x * 0x20))) -#define PL080_Cx_CONFIG(x) ((0x110 + (x * 0x20))) -#define PL080S_Cx_CONTROL2(x) ((0x110 + (x * 0x20))) -#define PL080S_Cx_CONFIG(x) ((0x114 + (x * 0x20))) - #define PL080_CH_SRC_ADDR (0x00) #define PL080_CH_DST_ADDR (0x04) #define PL080_CH_LLI (0x08) @@ -63,31 +62,38 @@ #define PL080_CH_CONFIG (0x10) #define PL080S_CH_CONTROL2 (0x10) #define PL080S_CH_CONFIG (0x14) - -#define PL080_LLI_ADDR_MASK (0x3fffffff << 2) +/* The Faraday FTDMAC020 derivative shuffles the registers around */ +#define FTDMAC020_CH_CSR (0x00) +#define FTDMAC020_CH_CFG (0x04) +#define FTDMAC020_CH_SRC_ADDR (0x08) +#define FTDMAC020_CH_DST_ADDR (0x0C) +#define FTDMAC020_CH_LLP (0x10) +#define FTDMAC020_CH_SIZE (0x14) + +#define PL080_LLI_ADDR_MASK GENMASK(31, 2) #define PL080_LLI_ADDR_SHIFT (2) -#define PL080_LLI_LM_AHB2 (1 << 0) +#define PL080_LLI_LM_AHB2 BIT(0) -#define PL080_CONTROL_TC_IRQ_EN (1 << 31) -#define PL080_CONTROL_PROT_MASK (0x7 << 28) +#define PL080_CONTROL_TC_IRQ_EN BIT(31) +#define PL080_CONTROL_PROT_MASK GENMASK(30, 28) #define PL080_CONTROL_PROT_SHIFT (28) -#define PL080_CONTROL_PROT_CACHE (1 << 30) -#define PL080_CONTROL_PROT_BUFF (1 << 29) -#define PL080_CONTROL_PROT_SYS (1 << 28) -#define PL080_CONTROL_DST_INCR (1 << 27) -#define PL080_CONTROL_SRC_INCR (1 << 26) -#define PL080_CONTROL_DST_AHB2 (1 << 25) -#define PL080_CONTROL_SRC_AHB2 (1 << 24) -#define PL080_CONTROL_DWIDTH_MASK (0x7 << 21) +#define PL080_CONTROL_PROT_CACHE BIT(30) +#define PL080_CONTROL_PROT_BUFF BIT(29) +#define PL080_CONTROL_PROT_SYS BIT(28) +#define PL080_CONTROL_DST_INCR BIT(27) +#define PL080_CONTROL_SRC_INCR BIT(26) +#define PL080_CONTROL_DST_AHB2 BIT(25) +#define PL080_CONTROL_SRC_AHB2 BIT(24) +#define PL080_CONTROL_DWIDTH_MASK GENMASK(23, 21) #define PL080_CONTROL_DWIDTH_SHIFT (21) -#define PL080_CONTROL_SWIDTH_MASK (0x7 << 18) +#define PL080_CONTROL_SWIDTH_MASK GENMASK(20, 18) #define PL080_CONTROL_SWIDTH_SHIFT (18) -#define PL080_CONTROL_DB_SIZE_MASK (0x7 << 15) +#define PL080_CONTROL_DB_SIZE_MASK GENMASK(17, 15) #define PL080_CONTROL_DB_SIZE_SHIFT (15) -#define PL080_CONTROL_SB_SIZE_MASK (0x7 << 12) +#define PL080_CONTROL_SB_SIZE_MASK GENMASK(14, 12) #define PL080_CONTROL_SB_SIZE_SHIFT (12) -#define PL080_CONTROL_TRANSFER_SIZE_MASK (0xfff << 0) -#define PL080S_CONTROL_TRANSFER_SIZE_MASK (0x1ffffff << 0) +#define PL080_CONTROL_TRANSFER_SIZE_MASK GENMASK(11, 0) +#define PL080S_CONTROL_TRANSFER_SIZE_MASK GENMASK(24, 0) #define PL080_CONTROL_TRANSFER_SIZE_SHIFT (0) #define PL080_BSIZE_1 (0x0) @@ -103,20 +109,20 @@ #define PL080_WIDTH_16BIT (0x1) #define PL080_WIDTH_32BIT (0x2) -#define PL080N_CONFIG_ITPROT (1 << 20) -#define PL080N_CONFIG_SECPROT (1 << 19) -#define PL080_CONFIG_HALT (1 << 18) -#define PL080_CONFIG_ACTIVE (1 << 17) /* RO */ -#define PL080_CONFIG_LOCK (1 << 16) -#define PL080_CONFIG_TC_IRQ_MASK (1 << 15) -#define PL080_CONFIG_ERR_IRQ_MASK (1 << 14) -#define PL080_CONFIG_FLOW_CONTROL_MASK (0x7 << 11) +#define PL080N_CONFIG_ITPROT BIT(20) +#define PL080N_CONFIG_SECPROT BIT(19) +#define PL080_CONFIG_HALT BIT(18) +#define PL080_CONFIG_ACTIVE BIT(17) /* RO */ +#define PL080_CONFIG_LOCK BIT(16) +#define PL080_CONFIG_TC_IRQ_MASK BIT(15) +#define PL080_CONFIG_ERR_IRQ_MASK BIT(14) +#define PL080_CONFIG_FLOW_CONTROL_MASK GENMASK(13, 11) #define PL080_CONFIG_FLOW_CONTROL_SHIFT (11) -#define PL080_CONFIG_DST_SEL_MASK (0xf << 6) +#define PL080_CONFIG_DST_SEL_MASK GENMASK(9, 6) #define PL080_CONFIG_DST_SEL_SHIFT (6) -#define PL080_CONFIG_SRC_SEL_MASK (0xf << 1) +#define PL080_CONFIG_SRC_SEL_MASK GENMASK(4, 1) #define PL080_CONFIG_SRC_SEL_SHIFT (1) -#define PL080_CONFIG_ENABLE (1 << 0) +#define PL080_CONFIG_ENABLE BIT(0) #define PL080_FLOW_MEM2MEM (0x0) #define PL080_FLOW_MEM2PER (0x1) @@ -127,6 +133,73 @@ #define PL080_FLOW_PER2MEM_PER (0x6) #define PL080_FLOW_SRC2DST_SRC (0x7) +#define FTDMAC020_CH_CSR_TC_MSK BIT(31) +/* Later versions have a threshold in bits 24..26, */ +#define FTDMAC020_CH_CSR_FIFOTH_MSK GENMASK(26, 24) +#define FTDMAC020_CH_CSR_FIFOTH_SHIFT (24) +#define FTDMAC020_CH_CSR_CHPR1_MSK GENMASK(23, 22) +#define FTDMAC020_CH_CSR_PROT3 BIT(21) +#define FTDMAC020_CH_CSR_PROT2 BIT(20) +#define FTDMAC020_CH_CSR_PROT1 BIT(19) +#define FTDMAC020_CH_CSR_SRC_SIZE_MSK GENMASK(18, 16) +#define FTDMAC020_CH_CSR_SRC_SIZE_SHIFT (16) +#define FTDMAC020_CH_CSR_ABT BIT(15) +#define FTDMAC020_CH_CSR_SRC_WIDTH_MSK GENMASK(13, 11) +#define FTDMAC020_CH_CSR_SRC_WIDTH_SHIFT (11) +#define FTDMAC020_CH_CSR_DST_WIDTH_MSK GENMASK(10, 8) +#define FTDMAC020_CH_CSR_DST_WIDTH_SHIFT (8) +#define FTDMAC020_CH_CSR_MODE BIT(7) +/* 00 = increase, 01 = decrease, 10 = fix */ +#define FTDMAC020_CH_CSR_SRCAD_CTL_MSK GENMASK(6, 5) +#define FTDMAC020_CH_CSR_SRCAD_CTL_SHIFT (5) +#define FTDMAC020_CH_CSR_DSTAD_CTL_MSK GENMASK(4, 3) +#define FTDMAC020_CH_CSR_DSTAD_CTL_SHIFT (3) +#define FTDMAC020_CH_CSR_SRC_SEL BIT(2) +#define FTDMAC020_CH_CSR_DST_SEL BIT(1) +#define FTDMAC020_CH_CSR_EN BIT(0) + +/* FIFO threshold setting */ +#define FTDMAC020_CH_CSR_FIFOTH_1 (0x0) +#define FTDMAC020_CH_CSR_FIFOTH_2 (0x1) +#define FTDMAC020_CH_CSR_FIFOTH_4 (0x2) +#define FTDMAC020_CH_CSR_FIFOTH_8 (0x3) +#define FTDMAC020_CH_CSR_FIFOTH_16 (0x4) +/* The FTDMAC020 supports 64bit wide transfers */ +#define FTDMAC020_WIDTH_64BIT (0x3) +/* Address can be increased, decreased or fixed */ +#define FTDMAC020_CH_CSR_SRCAD_CTL_INC (0x0) +#define FTDMAC020_CH_CSR_SRCAD_CTL_DEC (0x1) +#define FTDMAC020_CH_CSR_SRCAD_CTL_FIXED (0x2) + +#define FTDMAC020_CH_CFG_LLP_CNT_MASK GENMASK(19, 16) +#define FTDMAC020_CH_CFG_LLP_CNT_SHIFT (16) +#define FTDMAC020_CH_CFG_BUSY BIT(8) +#define FTDMAC020_CH_CFG_INT_ABT_MASK BIT(2) +#define FTDMAC020_CH_CFG_INT_ERR_MASK BIT(1) +#define FTDMAC020_CH_CFG_INT_TC_MASK BIT(0) + +/* Inside the LLIs, the applicable CSR fields are mapped differently */ +#define FTDMAC020_LLI_TC_MSK BIT(28) +#define FTDMAC020_LLI_SRC_WIDTH_MSK GENMASK(27, 25) +#define FTDMAC020_LLI_SRC_WIDTH_SHIFT (25) +#define FTDMAC020_LLI_DST_WIDTH_MSK GENMASK(24, 22) +#define FTDMAC020_LLI_DST_WIDTH_SHIFT (22) +#define FTDMAC020_LLI_SRCAD_CTL_MSK GENMASK(21, 20) +#define FTDMAC020_LLI_SRCAD_CTL_SHIFT (20) +#define FTDMAC020_LLI_DSTAD_CTL_MSK GENMASK(19, 18) +#define FTDMAC020_LLI_DSTAD_CTL_SHIFT (18) +#define FTDMAC020_LLI_SRC_SEL BIT(17) +#define FTDMAC020_LLI_DST_SEL BIT(16) +#define FTDMAC020_LLI_TRANSFER_SIZE_MASK GENMASK(11, 0) +#define FTDMAC020_LLI_TRANSFER_SIZE_SHIFT (0) + +#define FTDMAC020_CFG_LLP_CNT_MASK GENMASK(19, 16) +#define FTDMAC020_CFG_LLP_CNT_SHIFT (16) +#define FTDMAC020_CFG_BUSY BIT(8) +#define FTDMAC020_CFG_INT_ABT_MSK BIT(2) +#define FTDMAC020_CFG_INT_ERR_MSK BIT(1) +#define FTDMAC020_CFG_INT_TC_MSK BIT(0) + /* DMA linked list chain structure */ struct pl080_lli { diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 5308eae9ce35..79d1bcee738d 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -47,8 +47,6 @@ enum { * devices with static assignments * @muxval: a number usually used to poke into some mux regiser to * mux in the signal to this channel - * @cctl_memcpy: options for the channel control register for memcpy - * *** not used for slave channels *** * @addr: source/target address in physical memory for this DMA channel, * can be the address of a FIFO register for burst requests for example. * This can be left undefined if the PrimeCell API is used for configuring @@ -63,12 +61,28 @@ struct pl08x_channel_data { int min_signal; int max_signal; u32 muxval; - u32 cctl_memcpy; dma_addr_t addr; bool single; u8 periph_buses; }; +enum pl08x_burst_size { + PL08X_BURST_SZ_1, + PL08X_BURST_SZ_4, + PL08X_BURST_SZ_8, + PL08X_BURST_SZ_16, + PL08X_BURST_SZ_32, + PL08X_BURST_SZ_64, + PL08X_BURST_SZ_128, + PL08X_BURST_SZ_256, +}; + +enum pl08x_bus_width { + PL08X_BUS_WIDTH_8_BITS, + PL08X_BUS_WIDTH_16_BITS, + PL08X_BUS_WIDTH_32_BITS, +}; + /** * struct pl08x_platform_data - the platform configuration for the PL08x * PrimeCells. @@ -76,6 +90,11 @@ struct pl08x_channel_data { * platform, all inclusive, including multiplexed channels. The available * physical channels will be multiplexed around these signals as they are * requested, just enumerate all possible channels. + * @num_slave_channels: number of elements in the slave channel array + * @memcpy_burst_size: the appropriate burst size for memcpy operations + * @memcpy_bus_width: memory bus width + * @memcpy_prot_buff: whether memcpy DMA is bufferable + * @memcpy_prot_cache: whether memcpy DMA is cacheable * @get_xfer_signal: request a physical signal to be used for a DMA transfer * immediately: if there is some multiplexing or similar blocking the use * of the channel the transfer can be denied by returning less than zero, @@ -90,7 +109,10 @@ struct pl08x_channel_data { struct pl08x_platform_data { struct pl08x_channel_data *slave_channels; unsigned int num_slave_channels; - struct pl08x_channel_data memcpy_channel; + enum pl08x_burst_size memcpy_burst_size; + enum pl08x_bus_width memcpy_bus_width; + bool memcpy_prot_buff; + bool memcpy_prot_cache; int (*get_xfer_signal)(const struct pl08x_channel_data *); void (*put_xfer_signal)(const struct pl08x_channel_data *, int); u8 lli_buses; diff --git a/include/linux/amba/pl330.h b/include/linux/amba/pl330.h deleted file mode 100644 index fe93758e8403..000000000000 --- a/include/linux/amba/pl330.h +++ /dev/null @@ -1,35 +0,0 @@ -/* linux/include/linux/amba/pl330.h - * - * Copyright (C) 2010 Samsung Electronics Co. Ltd. - * Jaswinder Singh <jassi.brar@samsung.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#ifndef __AMBA_PL330_H_ -#define __AMBA_PL330_H_ - -#include <linux/dmaengine.h> - -struct dma_pl330_platdata { - /* - * Number of valid peripherals connected to DMAC. - * This may be different from the value read from - * CR0, as the PL330 implementation might have 'holes' - * in the peri list or the peri could also be reached - * from another DMAC which the platform prefers. - */ - u8 nr_valid_peri; - /* Array of valid peripherals */ - u8 *peri_id; - /* Operational capabilities */ - dma_cap_mask_t cap_mask; - /* Bytes to allocate for MC buffer */ - unsigned mcbuf_sz; -}; - -extern bool pl330_filter(struct dma_chan *chan, void *param); -#endif /* __AMBA_PL330_H_ */ diff --git a/include/linux/amigaffs.h b/include/linux/amigaffs.h deleted file mode 100644 index 43b41c06aa37..000000000000 --- a/include/linux/amigaffs.h +++ /dev/null @@ -1,144 +0,0 @@ -#ifndef AMIGAFFS_H -#define AMIGAFFS_H - -#include <linux/types.h> -#include <asm/byteorder.h> - -#define FS_OFS 0x444F5300 -#define FS_FFS 0x444F5301 -#define FS_INTLOFS 0x444F5302 -#define FS_INTLFFS 0x444F5303 -#define FS_DCOFS 0x444F5304 -#define FS_DCFFS 0x444F5305 -#define MUFS_FS 0x6d754653 /* 'muFS' */ -#define MUFS_OFS 0x6d754600 /* 'muF\0' */ -#define MUFS_FFS 0x6d754601 /* 'muF\1' */ -#define MUFS_INTLOFS 0x6d754602 /* 'muF\2' */ -#define MUFS_INTLFFS 0x6d754603 /* 'muF\3' */ -#define MUFS_DCOFS 0x6d754604 /* 'muF\4' */ -#define MUFS_DCFFS 0x6d754605 /* 'muF\5' */ - -#define T_SHORT 2 -#define T_LIST 16 -#define T_DATA 8 - -#define ST_LINKFILE -4 -#define ST_FILE -3 -#define ST_ROOT 1 -#define ST_USERDIR 2 -#define ST_SOFTLINK 3 -#define ST_LINKDIR 4 - -#define AFFS_ROOT_BMAPS 25 - -struct affs_date { - __be32 days; - __be32 mins; - __be32 ticks; -}; - -struct affs_short_date { - __be16 days; - __be16 mins; - __be16 ticks; -}; - -struct affs_root_head { - __be32 ptype; - __be32 spare1; - __be32 spare2; - __be32 hash_size; - __be32 spare3; - __be32 checksum; - __be32 hashtable[1]; -}; - -struct affs_root_tail { - __be32 bm_flag; - __be32 bm_blk[AFFS_ROOT_BMAPS]; - __be32 bm_ext; - struct affs_date root_change; - u8 disk_name[32]; - __be32 spare1; - __be32 spare2; - struct affs_date disk_change; - struct affs_date disk_create; - __be32 spare3; - __be32 spare4; - __be32 dcache; - __be32 stype; -}; - -struct affs_head { - __be32 ptype; - __be32 key; - __be32 block_count; - __be32 spare1; - __be32 first_data; - __be32 checksum; - __be32 table[1]; -}; - -struct affs_tail { - __be32 spare1; - __be16 uid; - __be16 gid; - __be32 protect; - __be32 size; - u8 comment[92]; - struct affs_date change; - u8 name[32]; - __be32 spare2; - __be32 original; - __be32 link_chain; - __be32 spare[5]; - __be32 hash_chain; - __be32 parent; - __be32 extension; - __be32 stype; -}; - -struct slink_front -{ - __be32 ptype; - __be32 key; - __be32 spare1[3]; - __be32 checksum; - u8 symname[1]; /* depends on block size */ -}; - -struct affs_data_head -{ - __be32 ptype; - __be32 key; - __be32 sequence; - __be32 size; - __be32 next; - __be32 checksum; - u8 data[1]; /* depends on block size */ -}; - -/* Permission bits */ - -#define FIBF_OTR_READ 0x8000 -#define FIBF_OTR_WRITE 0x4000 -#define FIBF_OTR_EXECUTE 0x2000 -#define FIBF_OTR_DELETE 0x1000 -#define FIBF_GRP_READ 0x0800 -#define FIBF_GRP_WRITE 0x0400 -#define FIBF_GRP_EXECUTE 0x0200 -#define FIBF_GRP_DELETE 0x0100 - -#define FIBF_HIDDEN 0x0080 -#define FIBF_SCRIPT 0x0040 -#define FIBF_PURE 0x0020 /* no use under linux */ -#define FIBF_ARCHIVED 0x0010 /* never set, always cleared on write */ -#define FIBF_NOREAD 0x0008 /* 0 means allowed */ -#define FIBF_NOWRITE 0x0004 /* 0 means allowed */ -#define FIBF_NOEXECUTE 0x0002 /* 0 means allowed, ignored under linux */ -#define FIBF_NODELETE 0x0001 /* 0 means allowed */ - -#define FIBF_OWNER 0x000F /* Bits pertaining to owner */ -#define FIBF_MASK 0xEE0E /* Bits modified by Linux */ - -#endif diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h new file mode 100644 index 000000000000..9af3c174c03a --- /dev/null +++ b/include/linux/arch_topology.h @@ -0,0 +1,17 @@ +/* + * include/linux/arch_topology.h - arch specific cpu topology information + */ +#ifndef _LINUX_ARCH_TOPOLOGY_H_ +#define _LINUX_ARCH_TOPOLOGY_H_ + +void topology_normalize_cpu_scale(void); + +struct device_node; +int topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); + +struct sched_domain; +unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu); + +void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity); + +#endif /* _LINUX_ARCH_TOPOLOGY_H_ */ diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index b5abfda80465..4c5bca38c653 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -14,9 +14,6 @@ #ifndef __LINUX_ARM_SMCCC_H #define __LINUX_ARM_SMCCC_H -#include <linux/linkage.h> -#include <linux/types.h> - /* * This file provides common defines for ARM SMC Calling Convention as * specified in @@ -60,6 +57,13 @@ #define ARM_SMCCC_OWNER_TRUSTED_OS 50 #define ARM_SMCCC_OWNER_TRUSTED_OS_END 63 +#define ARM_SMCCC_QUIRK_NONE 0 +#define ARM_SMCCC_QUIRK_QCOM_A6 1 /* Save/restore register a6 */ + +#ifndef __ASSEMBLY__ + +#include <linux/linkage.h> +#include <linux/types.h> /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 @@ -72,33 +76,59 @@ struct arm_smccc_res { }; /** - * arm_smccc_smc() - make SMC calls + * struct arm_smccc_quirk - Contains quirk information + * @id: quirk identification + * @state: quirk specific information + * @a6: Qualcomm quirk entry for returning post-smc call contents of a6 + */ +struct arm_smccc_quirk { + int id; + union { + unsigned long a6; + } state; +}; + +/** + * __arm_smccc_smc() - make SMC calls * @a0-a7: arguments passed in registers 0 to 7 * @res: result values from registers 0 to 3 + * @quirk: points to an arm_smccc_quirk, or NULL when no quirks are required. * * This function is used to make SMC calls following SMC Calling Convention. * The content of the supplied param are copied to registers 0 to 7 prior * to the SMC instruction. The return values are updated with the content - * from register 0 to 3 on return from the SMC instruction. + * from register 0 to 3 on return from the SMC instruction. An optional + * quirk structure provides vendor specific behavior. */ -asmlinkage void arm_smccc_smc(unsigned long a0, unsigned long a1, +asmlinkage void __arm_smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3, unsigned long a4, unsigned long a5, unsigned long a6, unsigned long a7, - struct arm_smccc_res *res); + struct arm_smccc_res *res, struct arm_smccc_quirk *quirk); /** - * arm_smccc_hvc() - make HVC calls + * __arm_smccc_hvc() - make HVC calls * @a0-a7: arguments passed in registers 0 to 7 * @res: result values from registers 0 to 3 + * @quirk: points to an arm_smccc_quirk, or NULL when no quirks are required. * * This function is used to make HVC calls following SMC Calling * Convention. The content of the supplied param are copied to registers 0 * to 7 prior to the HVC instruction. The return values are updated with - * the content from register 0 to 3 on return from the HVC instruction. + * the content from register 0 to 3 on return from the HVC instruction. An + * optional quirk structure provides vendor specific behavior. */ -asmlinkage void arm_smccc_hvc(unsigned long a0, unsigned long a1, +asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3, unsigned long a4, unsigned long a5, unsigned long a6, unsigned long a7, - struct arm_smccc_res *res); + struct arm_smccc_res *res, struct arm_smccc_quirk *quirk); + +#define arm_smccc_smc(...) __arm_smccc_smc(__VA_ARGS__, NULL) + +#define arm_smccc_smc_quirk(...) __arm_smccc_smc(__VA_ARGS__) + +#define arm_smccc_hvc(...) __arm_smccc_hvc(__VA_ARGS__, NULL) + +#define arm_smccc_hvc_quirk(...) __arm_smccc_hvc(__VA_ARGS__) +#endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 388574ea38ed..28e3cf1465ab 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -87,7 +87,7 @@ struct async_submit_ctl { void *scribble; }; -#ifdef CONFIG_DMA_ENGINE +#if defined(CONFIG_DMA_ENGINE) && !defined(CONFIG_ASYNC_TX_CHANNEL_SWITCH) #define async_tx_issue_pending_all dma_issue_pending_all /** diff --git a/include/linux/ata.h b/include/linux/ata.h index af6859b3a93d..e65ae4b2ed48 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -20,7 +20,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * * Hardware documentation available from http://www.t13.org/ * @@ -336,11 +336,16 @@ enum { /* READ_LOG_EXT pages */ ATA_LOG_DIRECTORY = 0x0, ATA_LOG_SATA_NCQ = 0x10, - ATA_LOG_NCQ_NON_DATA = 0x12, - ATA_LOG_NCQ_SEND_RECV = 0x13, - ATA_LOG_SATA_ID_DEV_DATA = 0x30, + ATA_LOG_NCQ_NON_DATA = 0x12, + ATA_LOG_NCQ_SEND_RECV = 0x13, + ATA_LOG_IDENTIFY_DEVICE = 0x30, + + /* Identify device log pages: */ + ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, + + /* Identify device SATA settings log:*/ ATA_LOG_DEVSLP_OFFSET = 0x30, ATA_LOG_DEVSLP_SIZE = 0x08, ATA_LOG_DEVSLP_MDAT = 0x00, @@ -817,11 +822,6 @@ static inline bool ata_id_sct_error_recovery_ctrl(const u16 *id) return id[ATA_ID_SCT_CMD_XPORT] & (1 << 3) ? true : false; } -static inline bool ata_id_sct_write_same(const u16 *id) -{ - return id[ATA_ID_SCT_CMD_XPORT] & (1 << 2) ? true : false; -} - static inline bool ata_id_sct_long_sector_access(const u16 *id) { return id[ATA_ID_SCT_CMD_XPORT] & (1 << 1) ? true : false; diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index c1da539f5e28..0ec9bdb1cc9f 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -11,6 +11,7 @@ #include <linux/uio.h> #include <net/sock.h> #include <linux/atomic.h> +#include <linux/refcount.h> #include <uapi/linux/atmdev.h> #ifdef CONFIG_PROC_FS @@ -158,7 +159,7 @@ struct atm_dev { struct k_atm_dev_stats stats; /* statistics */ char signal; /* signal status (ATM_PHY_SIG_*) */ int link_rate; /* link rate (default: OC3) */ - atomic_t refcnt; /* reference count */ + refcount_t refcnt; /* reference count */ spinlock_t lock; /* protect internal members */ #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; /* proc entry */ @@ -254,20 +255,20 @@ static inline void atm_return(struct atm_vcc *vcc,int truesize) static inline int atm_may_send(struct atm_vcc *vcc,unsigned int size) { - return (size + atomic_read(&sk_atm(vcc)->sk_wmem_alloc)) < + return (size + refcount_read(&sk_atm(vcc)->sk_wmem_alloc)) < sk_atm(vcc)->sk_sndbuf; } static inline void atm_dev_hold(struct atm_dev *dev) { - atomic_inc(&dev->refcnt); + refcount_inc(&dev->refcnt); } static inline void atm_dev_put(struct atm_dev *dev) { - if (atomic_dec_and_test(&dev->refcnt)) { + if (refcount_dec_and_test(&dev->refcnt)) { BUG_ON(!test_bit(ATM_DF_REMOVED, &dev->flags)); if (dev->ops->dev_close) dev->ops->dev_close(dev); diff --git a/include/linux/atmel-ssc.h b/include/linux/atmel-ssc.h index 7c0f6549898b..fdb545101ede 100644 --- a/include/linux/atmel-ssc.h +++ b/include/linux/atmel-ssc.h @@ -20,6 +20,7 @@ struct ssc_device { int user; int irq; bool clk_from_rk_pin; + bool sound_dai; }; struct ssc_device * __must_check ssc_request(unsigned int ssc_num); diff --git a/include/linux/atmel_serial.h b/include/linux/atmel_serial.h deleted file mode 100644 index bd2560502f3c..000000000000 --- a/include/linux/atmel_serial.h +++ /dev/null @@ -1,169 +0,0 @@ -/* - * include/linux/atmel_serial.h - * - * Copyright (C) 2005 Ivan Kokshaysky - * Copyright (C) SAN People - * - * USART registers. - * Based on AT91RM9200 datasheet revision E. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#ifndef ATMEL_SERIAL_H -#define ATMEL_SERIAL_H - -#define ATMEL_US_CR 0x00 /* Control Register */ -#define ATMEL_US_RSTRX BIT(2) /* Reset Receiver */ -#define ATMEL_US_RSTTX BIT(3) /* Reset Transmitter */ -#define ATMEL_US_RXEN BIT(4) /* Receiver Enable */ -#define ATMEL_US_RXDIS BIT(5) /* Receiver Disable */ -#define ATMEL_US_TXEN BIT(6) /* Transmitter Enable */ -#define ATMEL_US_TXDIS BIT(7) /* Transmitter Disable */ -#define ATMEL_US_RSTSTA BIT(8) /* Reset Status Bits */ -#define ATMEL_US_STTBRK BIT(9) /* Start Break */ -#define ATMEL_US_STPBRK BIT(10) /* Stop Break */ -#define ATMEL_US_STTTO BIT(11) /* Start Time-out */ -#define ATMEL_US_SENDA BIT(12) /* Send Address */ -#define ATMEL_US_RSTIT BIT(13) /* Reset Iterations */ -#define ATMEL_US_RSTNACK BIT(14) /* Reset Non Acknowledge */ -#define ATMEL_US_RETTO BIT(15) /* Rearm Time-out */ -#define ATMEL_US_DTREN BIT(16) /* Data Terminal Ready Enable */ -#define ATMEL_US_DTRDIS BIT(17) /* Data Terminal Ready Disable */ -#define ATMEL_US_RTSEN BIT(18) /* Request To Send Enable */ -#define ATMEL_US_RTSDIS BIT(19) /* Request To Send Disable */ -#define ATMEL_US_TXFCLR BIT(24) /* Transmit FIFO Clear */ -#define ATMEL_US_RXFCLR BIT(25) /* Receive FIFO Clear */ -#define ATMEL_US_TXFLCLR BIT(26) /* Transmit FIFO Lock Clear */ -#define ATMEL_US_FIFOEN BIT(30) /* FIFO enable */ -#define ATMEL_US_FIFODIS BIT(31) /* FIFO disable */ - -#define ATMEL_US_MR 0x04 /* Mode Register */ -#define ATMEL_US_USMODE GENMASK(3, 0) /* Mode of the USART */ -#define ATMEL_US_USMODE_NORMAL 0 -#define ATMEL_US_USMODE_RS485 1 -#define ATMEL_US_USMODE_HWHS 2 -#define ATMEL_US_USMODE_MODEM 3 -#define ATMEL_US_USMODE_ISO7816_T0 4 -#define ATMEL_US_USMODE_ISO7816_T1 6 -#define ATMEL_US_USMODE_IRDA 8 -#define ATMEL_US_USCLKS GENMASK(5, 4) /* Clock Selection */ -#define ATMEL_US_USCLKS_MCK (0 << 4) -#define ATMEL_US_USCLKS_MCK_DIV8 (1 << 4) -#define ATMEL_US_USCLKS_SCK (3 << 4) -#define ATMEL_US_CHRL GENMASK(7, 6) /* Character Length */ -#define ATMEL_US_CHRL_5 (0 << 6) -#define ATMEL_US_CHRL_6 (1 << 6) -#define ATMEL_US_CHRL_7 (2 << 6) -#define ATMEL_US_CHRL_8 (3 << 6) -#define ATMEL_US_SYNC BIT(8) /* Synchronous Mode Select */ -#define ATMEL_US_PAR GENMASK(11, 9) /* Parity Type */ -#define ATMEL_US_PAR_EVEN (0 << 9) -#define ATMEL_US_PAR_ODD (1 << 9) -#define ATMEL_US_PAR_SPACE (2 << 9) -#define ATMEL_US_PAR_MARK (3 << 9) -#define ATMEL_US_PAR_NONE (4 << 9) -#define ATMEL_US_PAR_MULTI_DROP (6 << 9) -#define ATMEL_US_NBSTOP GENMASK(13, 12) /* Number of Stop Bits */ -#define ATMEL_US_NBSTOP_1 (0 << 12) -#define ATMEL_US_NBSTOP_1_5 (1 << 12) -#define ATMEL_US_NBSTOP_2 (2 << 12) -#define ATMEL_US_CHMODE GENMASK(15, 14) /* Channel Mode */ -#define ATMEL_US_CHMODE_NORMAL (0 << 14) -#define ATMEL_US_CHMODE_ECHO (1 << 14) -#define ATMEL_US_CHMODE_LOC_LOOP (2 << 14) -#define ATMEL_US_CHMODE_REM_LOOP (3 << 14) -#define ATMEL_US_MSBF BIT(16) /* Bit Order */ -#define ATMEL_US_MODE9 BIT(17) /* 9-bit Character Length */ -#define ATMEL_US_CLKO BIT(18) /* Clock Output Select */ -#define ATMEL_US_OVER BIT(19) /* Oversampling Mode */ -#define ATMEL_US_INACK BIT(20) /* Inhibit Non Acknowledge */ -#define ATMEL_US_DSNACK BIT(21) /* Disable Successive NACK */ -#define ATMEL_US_MAX_ITER GENMASK(26, 24) /* Max Iterations */ -#define ATMEL_US_FILTER BIT(28) /* Infrared Receive Line Filter */ - -#define ATMEL_US_IER 0x08 /* Interrupt Enable Register */ -#define ATMEL_US_RXRDY BIT(0) /* Receiver Ready */ -#define ATMEL_US_TXRDY BIT(1) /* Transmitter Ready */ -#define ATMEL_US_RXBRK BIT(2) /* Break Received / End of Break */ -#define ATMEL_US_ENDRX BIT(3) /* End of Receiver Transfer */ -#define ATMEL_US_ENDTX BIT(4) /* End of Transmitter Transfer */ -#define ATMEL_US_OVRE BIT(5) /* Overrun Error */ -#define ATMEL_US_FRAME BIT(6) /* Framing Error */ -#define ATMEL_US_PARE BIT(7) /* Parity Error */ -#define ATMEL_US_TIMEOUT BIT(8) /* Receiver Time-out */ -#define ATMEL_US_TXEMPTY BIT(9) /* Transmitter Empty */ -#define ATMEL_US_ITERATION BIT(10) /* Max number of Repetitions Reached */ -#define ATMEL_US_TXBUFE BIT(11) /* Transmission Buffer Empty */ -#define ATMEL_US_RXBUFF BIT(12) /* Reception Buffer Full */ -#define ATMEL_US_NACK BIT(13) /* Non Acknowledge */ -#define ATMEL_US_RIIC BIT(16) /* Ring Indicator Input Change */ -#define ATMEL_US_DSRIC BIT(17) /* Data Set Ready Input Change */ -#define ATMEL_US_DCDIC BIT(18) /* Data Carrier Detect Input Change */ -#define ATMEL_US_CTSIC BIT(19) /* Clear to Send Input Change */ -#define ATMEL_US_RI BIT(20) /* RI */ -#define ATMEL_US_DSR BIT(21) /* DSR */ -#define ATMEL_US_DCD BIT(22) /* DCD */ -#define ATMEL_US_CTS BIT(23) /* CTS */ - -#define ATMEL_US_IDR 0x0c /* Interrupt Disable Register */ -#define ATMEL_US_IMR 0x10 /* Interrupt Mask Register */ -#define ATMEL_US_CSR 0x14 /* Channel Status Register */ -#define ATMEL_US_RHR 0x18 /* Receiver Holding Register */ -#define ATMEL_US_THR 0x1c /* Transmitter Holding Register */ -#define ATMEL_US_SYNH BIT(15) /* Transmit/Receive Sync */ - -#define ATMEL_US_BRGR 0x20 /* Baud Rate Generator Register */ -#define ATMEL_US_CD GENMASK(15, 0) /* Clock Divider */ -#define ATMEL_US_FP_OFFSET 16 /* Fractional Part */ -#define ATMEL_US_FP_MASK 0x7 - -#define ATMEL_US_RTOR 0x24 /* Receiver Time-out Register for USART */ -#define ATMEL_UA_RTOR 0x28 /* Receiver Time-out Register for UART */ -#define ATMEL_US_TO GENMASK(15, 0) /* Time-out Value */ - -#define ATMEL_US_TTGR 0x28 /* Transmitter Timeguard Register */ -#define ATMEL_US_TG GENMASK(7, 0) /* Timeguard Value */ - -#define ATMEL_US_FIDI 0x40 /* FI DI Ratio Register */ -#define ATMEL_US_NER 0x44 /* Number of Errors Register */ -#define ATMEL_US_IF 0x4c /* IrDA Filter Register */ - -#define ATMEL_US_CMPR 0x90 /* Comparaison Register */ -#define ATMEL_US_FMR 0xa0 /* FIFO Mode Register */ -#define ATMEL_US_TXRDYM(data) (((data) & 0x3) << 0) /* TX Ready Mode */ -#define ATMEL_US_RXRDYM(data) (((data) & 0x3) << 4) /* RX Ready Mode */ -#define ATMEL_US_ONE_DATA 0x0 -#define ATMEL_US_TWO_DATA 0x1 -#define ATMEL_US_FOUR_DATA 0x2 -#define ATMEL_US_FRTSC BIT(7) /* FIFO RTS pin Control */ -#define ATMEL_US_TXFTHRES(thr) (((thr) & 0x3f) << 8) /* TX FIFO Threshold */ -#define ATMEL_US_RXFTHRES(thr) (((thr) & 0x3f) << 16) /* RX FIFO Threshold */ -#define ATMEL_US_RXFTHRES2(thr) (((thr) & 0x3f) << 24) /* RX FIFO Threshold2 */ - -#define ATMEL_US_FLR 0xa4 /* FIFO Level Register */ -#define ATMEL_US_TXFL(reg) (((reg) >> 0) & 0x3f) /* TX FIFO Level */ -#define ATMEL_US_RXFL(reg) (((reg) >> 16) & 0x3f) /* RX FIFO Level */ - -#define ATMEL_US_FIER 0xa8 /* FIFO Interrupt Enable Register */ -#define ATMEL_US_FIDR 0xac /* FIFO Interrupt Disable Register */ -#define ATMEL_US_FIMR 0xb0 /* FIFO Interrupt Mask Register */ -#define ATMEL_US_FESR 0xb4 /* FIFO Event Status Register */ -#define ATMEL_US_TXFEF BIT(0) /* Transmit FIFO Empty Flag */ -#define ATMEL_US_TXFFF BIT(1) /* Transmit FIFO Full Flag */ -#define ATMEL_US_TXFTHF BIT(2) /* Transmit FIFO Threshold Flag */ -#define ATMEL_US_RXFEF BIT(3) /* Receive FIFO Empty Flag */ -#define ATMEL_US_RXFFF BIT(4) /* Receive FIFO Full Flag */ -#define ATMEL_US_RXFTHF BIT(5) /* Receive FIFO Threshold Flag */ -#define ATMEL_US_TXFPTEF BIT(6) /* Transmit FIFO Pointer Error Flag */ -#define ATMEL_US_RXFPTEF BIT(7) /* Receive FIFO Pointer Error Flag */ -#define ATMEL_US_TXFLOCK BIT(8) /* Transmit FIFO Lock (FESR only) */ -#define ATMEL_US_RXFTHF2 BIT(9) /* Receive FIFO Threshold Flag 2 */ - -#define ATMEL_US_NAME 0xf0 /* Ip Name */ -#define ATMEL_US_VERSION 0xfc /* Ip Version */ - -#endif diff --git a/include/linux/atomic.h b/include/linux/atomic.h index e71835bf60a9..c56be7410130 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -423,6 +423,29 @@ #endif #endif /* atomic_cmpxchg_relaxed */ +#ifndef atomic_try_cmpxchg + +#define __atomic_try_cmpxchg(type, _p, _po, _n) \ +({ \ + typeof(_po) __po = (_po); \ + typeof(*(_po)) __r, __o = *__po; \ + __r = atomic_cmpxchg##type((_p), __o, (_n)); \ + if (unlikely(__r != __o)) \ + *__po = __r; \ + likely(__r == __o); \ +}) + +#define atomic_try_cmpxchg(_p, _po, _n) __atomic_try_cmpxchg(, _p, _po, _n) +#define atomic_try_cmpxchg_relaxed(_p, _po, _n) __atomic_try_cmpxchg(_relaxed, _p, _po, _n) +#define atomic_try_cmpxchg_acquire(_p, _po, _n) __atomic_try_cmpxchg(_acquire, _p, _po, _n) +#define atomic_try_cmpxchg_release(_p, _po, _n) __atomic_try_cmpxchg(_release, _p, _po, _n) + +#else /* atomic_try_cmpxchg */ +#define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg +#define atomic_try_cmpxchg_acquire atomic_try_cmpxchg +#define atomic_try_cmpxchg_release atomic_try_cmpxchg +#endif /* atomic_try_cmpxchg */ + /* cmpxchg_relaxed */ #ifndef cmpxchg_relaxed #define cmpxchg_relaxed cmpxchg @@ -996,6 +1019,29 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_cmpxchg_relaxed */ +#ifndef atomic64_try_cmpxchg + +#define __atomic64_try_cmpxchg(type, _p, _po, _n) \ +({ \ + typeof(_po) __po = (_po); \ + typeof(*(_po)) __r, __o = *__po; \ + __r = atomic64_cmpxchg##type((_p), __o, (_n)); \ + if (unlikely(__r != __o)) \ + *__po = __r; \ + likely(__r == __o); \ +}) + +#define atomic64_try_cmpxchg(_p, _po, _n) __atomic64_try_cmpxchg(, _p, _po, _n) +#define atomic64_try_cmpxchg_relaxed(_p, _po, _n) __atomic64_try_cmpxchg(_relaxed, _p, _po, _n) +#define atomic64_try_cmpxchg_acquire(_p, _po, _n) __atomic64_try_cmpxchg(_acquire, _p, _po, _n) +#define atomic64_try_cmpxchg_release(_p, _po, _n) __atomic64_try_cmpxchg(_release, _p, _po, _n) + +#else /* atomic64_try_cmpxchg */ +#define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg +#define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg +#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg +#endif /* atomic64_try_cmpxchg */ + #ifndef atomic64_andnot static inline void atomic64_andnot(long long i, atomic64_t *v) { diff --git a/include/linux/audit.h b/include/linux/audit.h index f51fca8d0b6f..2150bdccfbab 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -163,8 +163,7 @@ extern void audit_log_task_info(struct audit_buffer *ab, extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ -extern int audit_rule_change(int type, __u32 portid, int seq, - void *data, size_t datasz); +extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern u32 audit_enabled; @@ -332,7 +331,7 @@ static inline void audit_ptrace(struct task_struct *t) /* Private API (for audit.c only) */ extern unsigned int audit_serial(void); extern int auditsc_get_stamp(struct audit_context *ctx, - struct timespec *t, unsigned int *serial); + struct timespec64 *t, unsigned int *serial); extern int audit_set_loginuid(kuid_t loginuid); static inline kuid_t audit_get_loginuid(struct task_struct *tsk) @@ -360,6 +359,7 @@ extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); +extern void __audit_log_kern_module(char *name); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { @@ -387,6 +387,20 @@ static inline int audit_socketcall(int nargs, unsigned long *args) return __audit_socketcall(nargs, args); return 0; } + +static inline int audit_socketcall_compat(int nargs, u32 *args) +{ + unsigned long a[AUDITSC_ARGS]; + int i; + + if (audit_dummy_context()) + return 0; + + for (i = 0; i < nargs; i++) + a[i] = (unsigned long)args[i]; + return __audit_socketcall(nargs, a); +} + static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) @@ -436,6 +450,12 @@ static inline void audit_mmap_fd(int fd, int flags) __audit_mmap_fd(fd, flags); } +static inline void audit_log_kern_module(char *name) +{ + if (!audit_dummy_context()) + __audit_log_kern_module(name); +} + extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ @@ -490,7 +510,7 @@ static inline void __audit_seccomp(unsigned long syscall, long signr, int code) static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline int auditsc_get_stamp(struct audit_context *ctx, - struct timespec *t, unsigned int *serial) + struct timespec64 *t, unsigned int *serial) { return 0; } @@ -513,6 +533,12 @@ static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } + +static inline int audit_socketcall_compat(int nargs, u32 *args) +{ + return 0; +} + static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) @@ -541,6 +567,11 @@ static inline void audit_log_capset(const struct cred *new, { } static inline void audit_mmap_fd(int fd, int flags) { } + +static inline void audit_log_kern_module(char *name) +{ +} + static inline void audit_ptrace(struct task_struct *t) { } #define audit_n_rules 0 diff --git a/include/linux/average.h b/include/linux/average.h index d04aa58280de..7ddaf340d2ac 100644 --- a/include/linux/average.h +++ b/include/linux/average.h @@ -1,45 +1,66 @@ #ifndef _LINUX_AVERAGE_H #define _LINUX_AVERAGE_H -/* Exponentially weighted moving average (EWMA) */ +/* + * Exponentially weighted moving average (EWMA) + * + * This implements a fixed-precision EWMA algorithm, with both the + * precision and fall-off coefficient determined at compile-time + * and built into the generated helper funtions. + * + * The first argument to the macro is the name that will be used + * for the struct and helper functions. + * + * The second argument, the precision, expresses how many bits are + * used for the fractional part of the fixed-precision values. + * + * The third argument, the weight reciprocal, determines how the + * new values will be weighed vs. the old state, new values will + * get weight 1/weight_rcp and old values 1-1/weight_rcp. Note + * that this parameter must be a power of two for efficiency. + */ -#define DECLARE_EWMA(name, _factor, _weight) \ +#define DECLARE_EWMA(name, _precision, _weight_rcp) \ struct ewma_##name { \ unsigned long internal; \ }; \ static inline void ewma_##name##_init(struct ewma_##name *e) \ { \ - BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ - BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ - BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ - BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + BUILD_BUG_ON(!__builtin_constant_p(_precision)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight_rcp)); \ + /* \ + * Even if you want to feed it just 0/1 you should have \ + * some bits for the non-fractional part... \ + */ \ + BUILD_BUG_ON((_precision) > 30); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight_rcp); \ e->internal = 0; \ } \ static inline unsigned long \ ewma_##name##_read(struct ewma_##name *e) \ { \ - BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ - BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ - BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ - BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ - return e->internal >> ilog2(_factor); \ + BUILD_BUG_ON(!__builtin_constant_p(_precision)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight_rcp)); \ + BUILD_BUG_ON((_precision) > 30); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight_rcp); \ + return e->internal >> (_precision); \ } \ static inline void ewma_##name##_add(struct ewma_##name *e, \ unsigned long val) \ { \ unsigned long internal = ACCESS_ONCE(e->internal); \ - unsigned long weight = ilog2(_weight); \ - unsigned long factor = ilog2(_factor); \ + unsigned long weight_rcp = ilog2(_weight_rcp); \ + unsigned long precision = _precision; \ \ - BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ - BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ - BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ - BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + BUILD_BUG_ON(!__builtin_constant_p(_precision)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight_rcp)); \ + BUILD_BUG_ON((_precision) > 30); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight_rcp); \ \ ACCESS_ONCE(e->internal) = internal ? \ - (((internal << weight) - internal) + \ - (val << factor)) >> weight : \ - (val << factor); \ + (((internal << weight_rcp) - internal) + \ + (val << precision)) >> weight_rcp : \ + (val << precision); \ } #endif /* _LINUX_AVERAGE_H */ diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h new file mode 100644 index 000000000000..c893b9520a67 --- /dev/null +++ b/include/linux/avf/virtchnl.h @@ -0,0 +1,701 @@ +/******************************************************************************* + * + * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver + * Copyright(c) 2013 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along + * with this program. If not, see <http://www.gnu.org/licenses/>. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + ******************************************************************************/ + +#ifndef _VIRTCHNL_H_ +#define _VIRTCHNL_H_ + +/* Description: + * This header file describes the VF-PF communication protocol used + * by the drivers for all devices starting from our 40G product line + * + * Admin queue buffer usage: + * desc->opcode is always aqc_opc_send_msg_to_pf + * flags, retval, datalen, and data addr are all used normally. + * The Firmware copies the cookie fields when sending messages between the + * PF and VF, but uses all other fields internally. Due to this limitation, + * we must send all messages as "indirect", i.e. using an external buffer. + * + * All the VSI indexes are relative to the VF. Each VF can have maximum of + * three VSIs. All the queue indexes are relative to the VSI. Each VF can + * have a maximum of sixteen queues for all of its VSIs. + * + * The PF is required to return a status code in v_retval for all messages + * except RESET_VF, which does not require any response. The return value + * is of status_code type, defined in the shared type.h. + * + * In general, VF driver initialization should roughly follow the order of + * these opcodes. The VF driver must first validate the API version of the + * PF driver, then request a reset, then get resources, then configure + * queues and interrupts. After these operations are complete, the VF + * driver may start its queues, optionally add MAC and VLAN filters, and + * process traffic. + */ + +/* START GENERIC DEFINES + * Need to ensure the following enums and defines hold the same meaning and + * value in current and future projects + */ + +/* Error Codes */ +enum virtchnl_status_code { + VIRTCHNL_STATUS_SUCCESS = 0, + VIRTCHNL_ERR_PARAM = -5, + VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH = -38, + VIRTCHNL_STATUS_ERR_CQP_COMPL_ERROR = -39, + VIRTCHNL_STATUS_ERR_INVALID_VF_ID = -40, + VIRTCHNL_STATUS_NOT_SUPPORTED = -64, +}; + +#define VIRTCHNL_LINK_SPEED_100MB_SHIFT 0x1 +#define VIRTCHNL_LINK_SPEED_1000MB_SHIFT 0x2 +#define VIRTCHNL_LINK_SPEED_10GB_SHIFT 0x3 +#define VIRTCHNL_LINK_SPEED_40GB_SHIFT 0x4 +#define VIRTCHNL_LINK_SPEED_20GB_SHIFT 0x5 +#define VIRTCHNL_LINK_SPEED_25GB_SHIFT 0x6 + +enum virtchnl_link_speed { + VIRTCHNL_LINK_SPEED_UNKNOWN = 0, + VIRTCHNL_LINK_SPEED_100MB = BIT(VIRTCHNL_LINK_SPEED_100MB_SHIFT), + VIRTCHNL_LINK_SPEED_1GB = BIT(VIRTCHNL_LINK_SPEED_1000MB_SHIFT), + VIRTCHNL_LINK_SPEED_10GB = BIT(VIRTCHNL_LINK_SPEED_10GB_SHIFT), + VIRTCHNL_LINK_SPEED_40GB = BIT(VIRTCHNL_LINK_SPEED_40GB_SHIFT), + VIRTCHNL_LINK_SPEED_20GB = BIT(VIRTCHNL_LINK_SPEED_20GB_SHIFT), + VIRTCHNL_LINK_SPEED_25GB = BIT(VIRTCHNL_LINK_SPEED_25GB_SHIFT), +}; + +/* for hsplit_0 field of Rx HMC context */ +/* deprecated with AVF 1.0 */ +enum virtchnl_rx_hsplit { + VIRTCHNL_RX_HSPLIT_NO_SPLIT = 0, + VIRTCHNL_RX_HSPLIT_SPLIT_L2 = 1, + VIRTCHNL_RX_HSPLIT_SPLIT_IP = 2, + VIRTCHNL_RX_HSPLIT_SPLIT_TCP_UDP = 4, + VIRTCHNL_RX_HSPLIT_SPLIT_SCTP = 8, +}; + +/* END GENERIC DEFINES */ + +/* Opcodes for VF-PF communication. These are placed in the v_opcode field + * of the virtchnl_msg structure. + */ +enum virtchnl_ops { +/* The PF sends status change events to VFs using + * the VIRTCHNL_OP_EVENT opcode. + * VFs send requests to the PF using the other ops. + * Use of "advanced opcode" features must be negotiated as part of capabilities + * exchange and are not considered part of base mode feature set. + */ + VIRTCHNL_OP_UNKNOWN = 0, + VIRTCHNL_OP_VERSION = 1, /* must ALWAYS be 1 */ + VIRTCHNL_OP_RESET_VF = 2, + VIRTCHNL_OP_GET_VF_RESOURCES = 3, + VIRTCHNL_OP_CONFIG_TX_QUEUE = 4, + VIRTCHNL_OP_CONFIG_RX_QUEUE = 5, + VIRTCHNL_OP_CONFIG_VSI_QUEUES = 6, + VIRTCHNL_OP_CONFIG_IRQ_MAP = 7, + VIRTCHNL_OP_ENABLE_QUEUES = 8, + VIRTCHNL_OP_DISABLE_QUEUES = 9, + VIRTCHNL_OP_ADD_ETH_ADDR = 10, + VIRTCHNL_OP_DEL_ETH_ADDR = 11, + VIRTCHNL_OP_ADD_VLAN = 12, + VIRTCHNL_OP_DEL_VLAN = 13, + VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE = 14, + VIRTCHNL_OP_GET_STATS = 15, + VIRTCHNL_OP_RSVD = 16, + VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */ + VIRTCHNL_OP_IWARP = 20, /* advanced opcode */ + VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP = 21, /* advanced opcode */ + VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP = 22, /* advanced opcode */ + VIRTCHNL_OP_CONFIG_RSS_KEY = 23, + VIRTCHNL_OP_CONFIG_RSS_LUT = 24, + VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25, + VIRTCHNL_OP_SET_RSS_HENA = 26, +}; + +/* This macro is used to generate a compilation error if a structure + * is not exactly the correct length. It gives a divide by zero error if the + * structure is not of the correct size, otherwise it creates an enum that is + * never used. + */ +#define VIRTCHNL_CHECK_STRUCT_LEN(n, X) enum virtchnl_static_assert_enum_##X \ + { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } + +/* Virtual channel message descriptor. This overlays the admin queue + * descriptor. All other data is passed in external buffers. + */ + +struct virtchnl_msg { + u8 pad[8]; /* AQ flags/opcode/len/retval fields */ + enum virtchnl_ops v_opcode; /* avoid confusion with desc->opcode */ + enum virtchnl_status_code v_retval; /* ditto for desc->retval */ + u32 vfid; /* used by PF when sending to VF */ +}; + +VIRTCHNL_CHECK_STRUCT_LEN(20, virtchnl_msg); + +/* Message descriptions and data structures.*/ + +/* VIRTCHNL_OP_VERSION + * VF posts its version number to the PF. PF responds with its version number + * in the same format, along with a return code. + * Reply from PF has its major/minor versions also in param0 and param1. + * If there is a major version mismatch, then the VF cannot operate. + * If there is a minor version mismatch, then the VF can operate but should + * add a warning to the system log. + * + * This enum element MUST always be specified as == 1, regardless of other + * changes in the API. The PF must always respond to this message without + * error regardless of version mismatch. + */ +#define VIRTCHNL_VERSION_MAJOR 1 +#define VIRTCHNL_VERSION_MINOR 1 +#define VIRTCHNL_VERSION_MINOR_NO_VF_CAPS 0 + +struct virtchnl_version_info { + u32 major; + u32 minor; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_version_info); + +#define VF_IS_V10(_v) (((_v)->major == 1) && ((_v)->minor == 0)) +#define VF_IS_V11(_ver) (((_ver)->major == 1) && ((_ver)->minor == 1)) + +/* VIRTCHNL_OP_RESET_VF + * VF sends this request to PF with no parameters + * PF does NOT respond! VF driver must delay then poll VFGEN_RSTAT register + * until reset completion is indicated. The admin queue must be reinitialized + * after this operation. + * + * When reset is complete, PF must ensure that all queues in all VSIs associated + * with the VF are stopped, all queue configurations in the HMC are set to 0, + * and all MAC and VLAN filters (except the default MAC address) on all VSIs + * are cleared. + */ + +/* VSI types that use VIRTCHNL interface for VF-PF communication. VSI_SRIOV + * vsi_type should always be 6 for backward compatibility. Add other fields + * as needed. + */ +enum virtchnl_vsi_type { + VIRTCHNL_VSI_TYPE_INVALID = 0, + VIRTCHNL_VSI_SRIOV = 6, +}; + +/* VIRTCHNL_OP_GET_VF_RESOURCES + * Version 1.0 VF sends this request to PF with no parameters + * Version 1.1 VF sends this request to PF with u32 bitmap of its capabilities + * PF responds with an indirect message containing + * virtchnl_vf_resource and one or more + * virtchnl_vsi_resource structures. + */ + +struct virtchnl_vsi_resource { + u16 vsi_id; + u16 num_queue_pairs; + enum virtchnl_vsi_type vsi_type; + u16 qset_handle; + u8 default_mac_addr[ETH_ALEN]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); + +/* VF offload flags + * VIRTCHNL_VF_OFFLOAD_L2 flag is inclusive of base mode L2 offloads including + * TX/RX Checksum offloading and TSO for non-tunnelled packets. + */ +#define VIRTCHNL_VF_OFFLOAD_L2 0x00000001 +#define VIRTCHNL_VF_OFFLOAD_IWARP 0x00000002 +#define VIRTCHNL_VF_OFFLOAD_RSVD 0x00000004 +#define VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 +#define VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 +#define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 +#define VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 +#define VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 +#define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 +#define VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000 +#define VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000 +#define VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000 +#define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000 + +#define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ + VIRTCHNL_VF_OFFLOAD_VLAN | \ + VIRTCHNL_VF_OFFLOAD_RSS_PF) + +struct virtchnl_vf_resource { + u16 num_vsis; + u16 num_queue_pairs; + u16 max_vectors; + u16 max_mtu; + + u32 vf_offload_flags; + u32 rss_key_size; + u32 rss_lut_size; + + struct virtchnl_vsi_resource vsi_res[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(36, virtchnl_vf_resource); + +/* VIRTCHNL_OP_CONFIG_TX_QUEUE + * VF sends this message to set up parameters for one TX queue. + * External data buffer contains one instance of virtchnl_txq_info. + * PF configures requested queue and returns a status code. + */ + +/* Tx queue config info */ +struct virtchnl_txq_info { + u16 vsi_id; + u16 queue_id; + u16 ring_len; /* number of descriptors, multiple of 8 */ + u16 headwb_enabled; /* deprecated with AVF 1.0 */ + u64 dma_ring_addr; + u64 dma_headwb_addr; /* deprecated with AVF 1.0 */ +}; + +VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_txq_info); + +/* VIRTCHNL_OP_CONFIG_RX_QUEUE + * VF sends this message to set up parameters for one RX queue. + * External data buffer contains one instance of virtchnl_rxq_info. + * PF configures requested queue and returns a status code. + */ + +/* Rx queue config info */ +struct virtchnl_rxq_info { + u16 vsi_id; + u16 queue_id; + u32 ring_len; /* number of descriptors, multiple of 32 */ + u16 hdr_size; + u16 splithdr_enabled; /* deprecated with AVF 1.0 */ + u32 databuffer_size; + u32 max_pkt_size; + u32 pad1; + u64 dma_ring_addr; + enum virtchnl_rx_hsplit rx_split_pos; /* deprecated with AVF 1.0 */ + u32 pad2; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_rxq_info); + +/* VIRTCHNL_OP_CONFIG_VSI_QUEUES + * VF sends this message to set parameters for all active TX and RX queues + * associated with the specified VSI. + * PF configures queues and returns status. + * If the number of queues specified is greater than the number of queues + * associated with the VSI, an error is returned and no queues are configured. + */ +struct virtchnl_queue_pair_info { + /* NOTE: vsi_id and queue_id should be identical for both queues. */ + struct virtchnl_txq_info txq; + struct virtchnl_rxq_info rxq; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(64, virtchnl_queue_pair_info); + +struct virtchnl_vsi_queue_config_info { + u16 vsi_id; + u16 num_queue_pairs; + u32 pad; + struct virtchnl_queue_pair_info qpair[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); + +/* VIRTCHNL_OP_CONFIG_IRQ_MAP + * VF uses this message to map vectors to queues. + * The rxq_map and txq_map fields are bitmaps used to indicate which queues + * are to be associated with the specified vector. + * The "other" causes are always mapped to vector 0. + * PF configures interrupt mapping and returns status. + */ +struct virtchnl_vector_map { + u16 vsi_id; + u16 vector_id; + u16 rxq_map; + u16 txq_map; + u16 rxitr_idx; + u16 txitr_idx; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_vector_map); + +struct virtchnl_irq_map_info { + u16 num_vectors; + struct virtchnl_vector_map vecmap[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(14, virtchnl_irq_map_info); + +/* VIRTCHNL_OP_ENABLE_QUEUES + * VIRTCHNL_OP_DISABLE_QUEUES + * VF sends these message to enable or disable TX/RX queue pairs. + * The queues fields are bitmaps indicating which queues to act upon. + * (Currently, we only support 16 queues per VF, but we make the field + * u32 to allow for expansion.) + * PF performs requested action and returns status. + */ +struct virtchnl_queue_select { + u16 vsi_id; + u16 pad; + u32 rx_queues; + u32 tx_queues; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_select); + +/* VIRTCHNL_OP_ADD_ETH_ADDR + * VF sends this message in order to add one or more unicast or multicast + * address filters for the specified VSI. + * PF adds the filters and returns status. + */ + +/* VIRTCHNL_OP_DEL_ETH_ADDR + * VF sends this message in order to remove one or more unicast or multicast + * filters for the specified VSI. + * PF removes the filters and returns status. + */ + +struct virtchnl_ether_addr { + u8 addr[ETH_ALEN]; + u8 pad[2]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr); + +struct virtchnl_ether_addr_list { + u16 vsi_id; + u16 num_elements; + struct virtchnl_ether_addr list[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_ether_addr_list); + +/* VIRTCHNL_OP_ADD_VLAN + * VF sends this message to add one or more VLAN tag filters for receives. + * PF adds the filters and returns status. + * If a port VLAN is configured by the PF, this operation will return an + * error to the VF. + */ + +/* VIRTCHNL_OP_DEL_VLAN + * VF sends this message to remove one or more VLAN tag filters for receives. + * PF removes the filters and returns status. + * If a port VLAN is configured by the PF, this operation will return an + * error to the VF. + */ + +struct virtchnl_vlan_filter_list { + u16 vsi_id; + u16 num_elements; + u16 vlan_id[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_vlan_filter_list); + +/* VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE + * VF sends VSI id and flags. + * PF returns status code in retval. + * Note: we assume that broadcast accept mode is always enabled. + */ +struct virtchnl_promisc_info { + u16 vsi_id; + u16 flags; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_promisc_info); + +#define FLAG_VF_UNICAST_PROMISC 0x00000001 +#define FLAG_VF_MULTICAST_PROMISC 0x00000002 + +/* VIRTCHNL_OP_GET_STATS + * VF sends this message to request stats for the selected VSI. VF uses + * the virtchnl_queue_select struct to specify the VSI. The queue_id + * field is ignored by the PF. + * + * PF replies with struct eth_stats in an external buffer. + */ + +/* VIRTCHNL_OP_CONFIG_RSS_KEY + * VIRTCHNL_OP_CONFIG_RSS_LUT + * VF sends these messages to configure RSS. Only supported if both PF + * and VF drivers set the VIRTCHNL_VF_OFFLOAD_RSS_PF bit during + * configuration negotiation. If this is the case, then the RSS fields in + * the VF resource struct are valid. + * Both the key and LUT are initialized to 0 by the PF, meaning that + * RSS is effectively disabled until set up by the VF. + */ +struct virtchnl_rss_key { + u16 vsi_id; + u16 key_len; + u8 key[1]; /* RSS hash key, packed bytes */ +}; + +VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key); + +struct virtchnl_rss_lut { + u16 vsi_id; + u16 lut_entries; + u8 lut[1]; /* RSS lookup table*/ +}; + +VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut); + +/* VIRTCHNL_OP_GET_RSS_HENA_CAPS + * VIRTCHNL_OP_SET_RSS_HENA + * VF sends these messages to get and set the hash filter enable bits for RSS. + * By default, the PF sets these to all possible traffic types that the + * hardware supports. The VF can query this value if it wants to change the + * traffic types that are hashed by the hardware. + */ +struct virtchnl_rss_hena { + u64 hena; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena); + +/* VIRTCHNL_OP_EVENT + * PF sends this message to inform the VF driver of events that may affect it. + * No direct response is expected from the VF, though it may generate other + * messages in response to this one. + */ +enum virtchnl_event_codes { + VIRTCHNL_EVENT_UNKNOWN = 0, + VIRTCHNL_EVENT_LINK_CHANGE, + VIRTCHNL_EVENT_RESET_IMPENDING, + VIRTCHNL_EVENT_PF_DRIVER_CLOSE, +}; + +#define PF_EVENT_SEVERITY_INFO 0 +#define PF_EVENT_SEVERITY_CERTAIN_DOOM 255 + +struct virtchnl_pf_event { + enum virtchnl_event_codes event; + union { + struct { + enum virtchnl_link_speed link_speed; + bool link_status; + } link_event; + } event_data; + + int severity; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_pf_event); + +/* VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP + * VF uses this message to request PF to map IWARP vectors to IWARP queues. + * The request for this originates from the VF IWARP driver through + * a client interface between VF LAN and VF IWARP driver. + * A vector could have an AEQ and CEQ attached to it although + * there is a single AEQ per VF IWARP instance in which case + * most vectors will have an INVALID_IDX for aeq and valid idx for ceq. + * There will never be a case where there will be multiple CEQs attached + * to a single vector. + * PF configures interrupt mapping and returns status. + */ + +struct virtchnl_iwarp_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_iwarp_qv_info); + +struct virtchnl_iwarp_qvlist_info { + u32 num_vectors; + struct virtchnl_iwarp_qv_info qv_info[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_iwarp_qvlist_info); + +/* VF reset states - these are written into the RSTAT register: + * VFGEN_RSTAT on the VF + * When the PF initiates a reset, it writes 0 + * When the reset is complete, it writes 1 + * When the PF detects that the VF has recovered, it writes 2 + * VF checks this register periodically to determine if a reset has occurred, + * then polls it to know when the reset is complete. + * If either the PF or VF reads the register while the hardware + * is in a reset state, it will return DEADBEEF, which, when masked + * will result in 3. + */ +enum virtchnl_vfr_states { + VIRTCHNL_VFR_INPROGRESS = 0, + VIRTCHNL_VFR_COMPLETED, + VIRTCHNL_VFR_VFACTIVE, +}; + +/** + * virtchnl_vc_validate_vf_msg + * @ver: Virtchnl version info + * @v_opcode: Opcode for the message + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * validate msg format against struct for each opcode + */ +static inline int +virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, + u8 *msg, u16 msglen) +{ + bool err_msg_format = false; + int valid_len = 0; + + /* Validate message length. */ + switch (v_opcode) { + case VIRTCHNL_OP_VERSION: + valid_len = sizeof(struct virtchnl_version_info); + break; + case VIRTCHNL_OP_RESET_VF: + break; + case VIRTCHNL_OP_GET_VF_RESOURCES: + if (VF_IS_V11(ver)) + valid_len = sizeof(u32); + break; + case VIRTCHNL_OP_CONFIG_TX_QUEUE: + valid_len = sizeof(struct virtchnl_txq_info); + break; + case VIRTCHNL_OP_CONFIG_RX_QUEUE: + valid_len = sizeof(struct virtchnl_rxq_info); + break; + case VIRTCHNL_OP_CONFIG_VSI_QUEUES: + valid_len = sizeof(struct virtchnl_vsi_queue_config_info); + if (msglen >= valid_len) { + struct virtchnl_vsi_queue_config_info *vqc = + (struct virtchnl_vsi_queue_config_info *)msg; + valid_len += (vqc->num_queue_pairs * + sizeof(struct + virtchnl_queue_pair_info)); + if (vqc->num_queue_pairs == 0) + err_msg_format = true; + } + break; + case VIRTCHNL_OP_CONFIG_IRQ_MAP: + valid_len = sizeof(struct virtchnl_irq_map_info); + if (msglen >= valid_len) { + struct virtchnl_irq_map_info *vimi = + (struct virtchnl_irq_map_info *)msg; + valid_len += (vimi->num_vectors * + sizeof(struct virtchnl_vector_map)); + if (vimi->num_vectors == 0) + err_msg_format = true; + } + break; + case VIRTCHNL_OP_ENABLE_QUEUES: + case VIRTCHNL_OP_DISABLE_QUEUES: + valid_len = sizeof(struct virtchnl_queue_select); + break; + case VIRTCHNL_OP_ADD_ETH_ADDR: + case VIRTCHNL_OP_DEL_ETH_ADDR: + valid_len = sizeof(struct virtchnl_ether_addr_list); + if (msglen >= valid_len) { + struct virtchnl_ether_addr_list *veal = + (struct virtchnl_ether_addr_list *)msg; + valid_len += veal->num_elements * + sizeof(struct virtchnl_ether_addr); + if (veal->num_elements == 0) + err_msg_format = true; + } + break; + case VIRTCHNL_OP_ADD_VLAN: + case VIRTCHNL_OP_DEL_VLAN: + valid_len = sizeof(struct virtchnl_vlan_filter_list); + if (msglen >= valid_len) { + struct virtchnl_vlan_filter_list *vfl = + (struct virtchnl_vlan_filter_list *)msg; + valid_len += vfl->num_elements * sizeof(u16); + if (vfl->num_elements == 0) + err_msg_format = true; + } + break; + case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE: + valid_len = sizeof(struct virtchnl_promisc_info); + break; + case VIRTCHNL_OP_GET_STATS: + valid_len = sizeof(struct virtchnl_queue_select); + break; + case VIRTCHNL_OP_IWARP: + /* These messages are opaque to us and will be validated in + * the RDMA client code. We just need to check for nonzero + * length. The firmware will enforce max length restrictions. + */ + if (msglen) + valid_len = msglen; + else + err_msg_format = true; + break; + case VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP: + break; + case VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP: + valid_len = sizeof(struct virtchnl_iwarp_qvlist_info); + if (msglen >= valid_len) { + struct virtchnl_iwarp_qvlist_info *qv = + (struct virtchnl_iwarp_qvlist_info *)msg; + if (qv->num_vectors == 0) { + err_msg_format = true; + break; + } + valid_len += ((qv->num_vectors - 1) * + sizeof(struct virtchnl_iwarp_qv_info)); + } + break; + case VIRTCHNL_OP_CONFIG_RSS_KEY: + valid_len = sizeof(struct virtchnl_rss_key); + if (msglen >= valid_len) { + struct virtchnl_rss_key *vrk = + (struct virtchnl_rss_key *)msg; + valid_len += vrk->key_len - 1; + } + break; + case VIRTCHNL_OP_CONFIG_RSS_LUT: + valid_len = sizeof(struct virtchnl_rss_lut); + if (msglen >= valid_len) { + struct virtchnl_rss_lut *vrl = + (struct virtchnl_rss_lut *)msg; + valid_len += vrl->lut_entries - 1; + } + break; + case VIRTCHNL_OP_GET_RSS_HENA_CAPS: + break; + case VIRTCHNL_OP_SET_RSS_HENA: + valid_len = sizeof(struct virtchnl_rss_hena); + break; + /* These are always errors coming from the VF. */ + case VIRTCHNL_OP_EVENT: + case VIRTCHNL_OP_UNKNOWN: + default: + return VIRTCHNL_ERR_PARAM; + } + /* few more checks */ + if ((valid_len != msglen) || (err_msg_format)) + return VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH; + + return 0; +} +#endif /* _VIRTCHNL_H_ */ diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index e850e76acaaf..866c433e7d32 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -10,6 +10,7 @@ #include <linux/flex_proportions.h> #include <linux/timer.h> #include <linux/workqueue.h> +#include <linux/kref.h> struct page; struct device; @@ -20,6 +21,7 @@ struct dentry; */ enum wb_state { WB_registered, /* bdi_register() was done */ + WB_shutting_down, /* wb_shutdown() in progress */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ }; @@ -53,7 +55,9 @@ struct bdi_writeback_congested { atomic_t refcnt; /* nr of attached wb's and blkg */ #ifdef CONFIG_CGROUP_WRITEBACK - struct backing_dev_info *bdi; /* the associated bdi */ + struct backing_dev_info *__bdi; /* the associated bdi, set to NULL + * on bdi unregistration. For memcg-wb + * internal use only! */ int blkcg_id; /* ID of the associated blkcg */ struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */ #endif @@ -142,8 +146,9 @@ struct backing_dev_info { congested_fn *congested_fn; /* Function pointer if device is md/dm */ void *congested_data; /* Pointer to aux data for congested func */ - char *name; + const char *name; + struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; @@ -159,7 +164,6 @@ struct backing_dev_info { #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ - atomic_t usage_cnt; /* counts both cgwbs and cgwb_contested's */ #else struct bdi_writeback_congested *wb_congested; #endif diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 43b93a947e61..854e1bdd0b2a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -17,18 +17,26 @@ #include <linux/backing-dev-defs.h> #include <linux/slab.h> -int __must_check bdi_init(struct backing_dev_info *bdi); -void bdi_exit(struct backing_dev_info *bdi); +static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) +{ + kref_get(&bdi->refcnt); + return bdi; +} + +void bdi_put(struct backing_dev_info *bdi); -__printf(3, 4) -int bdi_register(struct backing_dev_info *bdi, struct device *parent, - const char *fmt, ...); -int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); +__printf(2, 3) +int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); +int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, + va_list args); int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); -int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); -void bdi_destroy(struct backing_dev_info *bdi); +struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id); +static inline struct backing_dev_info *bdi_alloc(gfp_t gfp_mask) +{ + return bdi_alloc_node(gfp_mask, NUMA_NO_NODE); +} void wb_start_writeback(struct bdi_writeback *wb, long nr_pages, bool range_cyclic, enum wb_reason reason); @@ -58,37 +66,17 @@ static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) static inline void __add_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { - __percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH); -} - -static inline void __inc_wb_stat(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - __add_wb_stat(wb, item, 1); + percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - unsigned long flags; - - local_irq_save(flags); - __inc_wb_stat(wb, item); - local_irq_restore(flags); -} - -static inline void __dec_wb_stat(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - __add_wb_stat(wb, item, -1); + __add_wb_stat(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - unsigned long flags; - - local_irq_save(flags); - __dec_wb_stat(wb, item); - local_irq_restore(flags); + __add_wb_stat(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) @@ -96,22 +84,9 @@ static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) return percpu_counter_read_positive(&wb->stat[item]); } -static inline s64 __wb_stat_sum(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - return percpu_counter_sum_positive(&wb->stat[item]); -} - static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { - s64 sum; - unsigned long flags; - - local_irq_save(flags); - sum = __wb_stat_sum(wb, item); - local_irq_restore(flags); - - return sum; + return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); @@ -183,7 +158,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) - return blk_get_backing_dev_info(I_BDEV(inode)); + return I_BDEV(inode)->bd_bdi; #endif return sb->s_bdi; } diff --git a/include/linux/bcm47xx_nvram.h b/include/linux/bcm47xx_nvram.h index 2793652fbf66..a414a2b53e41 100644 --- a/include/linux/bcm47xx_nvram.h +++ b/include/linux/bcm47xx_nvram.h @@ -8,6 +8,7 @@ #ifndef __BCM47XX_NVRAM_H #define __BCM47XX_NVRAM_H +#include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/vmalloc.h> diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index b20e3d56253f..2f1c690a3e66 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -593,9 +593,6 @@ struct bcma_sflash { u32 blocksize; u16 numblocks; u32 size; - - struct mtd_info *mtd; - void *priv; }; #endif diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 9657f11d48a7..bca6a5e4ca3d 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -80,7 +80,7 @@ struct pci_dev; #define BCMA_CORE_PCI_MDIODATA_DEV_TX 0x1e /* SERDES TX Dev */ #define BCMA_CORE_PCI_MDIODATA_DEV_RX 0x1f /* SERDES RX Dev */ #define BCMA_CORE_PCI_PCIEIND_ADDR 0x0130 /* indirect access to the internal register */ -#define BCMA_CORE_PCI_PCIEIND_DATA 0x0134 /* Data to/from the internal regsiter */ +#define BCMA_CORE_PCI_PCIEIND_DATA 0x0134 /* Data to/from the internal register */ #define BCMA_CORE_PCI_CLKREQENCTRL 0x0138 /* >= rev 6, Clkreq rdma control */ #define BCMA_CORE_PCI_PCICFG0 0x0400 /* PCI config space 0 (rev >= 8) */ #define BCMA_CORE_PCI_PCICFG1 0x0500 /* PCI config space 1 (rev >= 8) */ diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 1303b570b18c..3ae9013eeaaa 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -6,6 +6,8 @@ #include <asm/exec.h> #include <uapi/linux/binfmts.h> +struct filename; + #define CORENAME_MAX_SIZE 128 /* @@ -44,7 +46,7 @@ struct linux_binprm { unsigned interp_flags; unsigned interp_data; unsigned long loader, exec; -}; +} __randomize_layout; #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT) @@ -79,7 +81,7 @@ struct linux_binfmt { int (*load_shlib)(struct file *); int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ -}; +} __randomize_layout; extern void __register_binfmt(struct linux_binfmt *fmt, int insert); @@ -123,4 +125,12 @@ extern void install_exec_creds(struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); +extern int do_execve(struct filename *, + const char __user * const __user *, + const char __user * const __user *); +extern int do_execveat(int, struct filename *, + const char __user * const __user *, + const char __user * const __user *, + int); + #endif /* _LINUX_BINFMTS_H */ diff --git a/include/linux/bio.h b/include/linux/bio.h index 7cf8a6c70a3f..7b1cf4ba0902 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -118,7 +118,6 @@ static inline void *bio_data(struct bio *bio) /* * will die */ -#define bio_to_phys(bio) (page_to_phys(bio_page((bio))) + (unsigned long) bio_offset((bio))) #define bvec_to_phys(bv) (page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset) /* @@ -166,10 +165,27 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, { iter->bi_sector += bytes >> 9; - if (bio_no_advance_iter(bio)) + if (bio_no_advance_iter(bio)) { iter->bi_size -= bytes; - else + iter->bi_done += bytes; + } else { bvec_iter_advance(bio->bi_io_vec, iter, bytes); + /* TODO: It is reasonable to complete bio with error here. */ + } +} + +static inline bool bio_rewind_iter(struct bio *bio, struct bvec_iter *iter, + unsigned int bytes) +{ + iter->bi_sector -= bytes >> 9; + + if (bio_no_advance_iter(bio)) { + iter->bi_size += bytes; + iter->bi_done -= bytes; + return true; + } + + return bvec_iter_rewind(bio->bi_io_vec, iter, bytes); } #define __bio_for_each_segment(bvl, bio, iter, start) \ @@ -304,8 +320,6 @@ struct bio_integrity_payload { struct bvec_iter bip_iter; - bio_end_io_t *bip_end_io; /* saved I/O completion fn */ - unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_max_vcnt; /* integrity bio_vec slots */ @@ -373,12 +387,15 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors, return bio_split(bio, sectors, gfp, bs); } -extern struct bio_set *bioset_create(unsigned int, unsigned int); -extern struct bio_set *bioset_create_nobvec(unsigned int, unsigned int); +extern struct bio_set *bioset_create(unsigned int, unsigned int, int flags); +enum { + BIOSET_NEED_BVECS = BIT(0), + BIOSET_NEED_RESCUER = BIT(1), +}; extern void bioset_free(struct bio_set *); extern mempool_t *biovec_create_pool(int pool_entries); -extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *); +extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *); extern void bio_put(struct bio *); extern void __bio_clone_fast(struct bio *, struct bio *); @@ -392,11 +409,6 @@ static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set); } -static inline struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask) -{ - return bio_clone_bioset(bio, gfp_mask, fs_bio_set); -} - static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs) { return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL); @@ -414,7 +426,13 @@ extern void bio_endio(struct bio *); static inline void bio_io_error(struct bio *bio) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; + bio_endio(bio); +} + +static inline void bio_wouldblock_error(struct bio *bio) +{ + bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); } @@ -426,6 +444,7 @@ extern void bio_advance(struct bio *, unsigned); extern void bio_init(struct bio *bio, struct bio_vec *table, unsigned short max_vecs); +extern void bio_uninit(struct bio *); extern void bio_reset(struct bio *); void bio_chain(struct bio *, struct bio *); @@ -718,13 +737,10 @@ struct biovec_slab { bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); -extern void bio_integrity_free(struct bio *); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); -extern bool bio_integrity_enabled(struct bio *bio); -extern int bio_integrity_prep(struct bio *); -extern void bio_integrity_endio(struct bio *); +extern bool bio_integrity_prep(struct bio *); extern void bio_integrity_advance(struct bio *, unsigned int); -extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int); +extern void bio_integrity_trim(struct bio *); extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); extern int bioset_integrity_create(struct bio_set *, int); extern void bioset_integrity_free(struct bio_set *); @@ -737,11 +753,6 @@ static inline void *bio_integrity(struct bio *bio) return NULL; } -static inline bool bio_integrity_enabled(struct bio *bio) -{ - return false; -} - static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) { return 0; @@ -752,14 +763,9 @@ static inline void bioset_integrity_free (struct bio_set *bs) return; } -static inline int bio_integrity_prep(struct bio *bio) +static inline bool bio_integrity_prep(struct bio *bio) { - return 0; -} - -static inline void bio_integrity_free(struct bio *bio) -{ - return; + return true; } static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, @@ -774,8 +780,7 @@ static inline void bio_integrity_advance(struct bio *bio, return; } -static inline void bio_integrity_trim(struct bio *bio, unsigned int offset, - unsigned int sectors) +static inline void bio_integrity_trim(struct bio *bio) { return; } diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index f6505d83069d..8b9d6fff002d 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -63,6 +63,19 @@ }) /** + * FIELD_FIT() - check if value fits in the field + * @_mask: shifted mask defining the field's length and position + * @_val: value to test against the field + * + * Return: true if @_val can fit inside @_mask, false if @_val is too big. + */ +#define FIELD_FIT(_mask, _val) \ + ({ \ + __BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_FIT: "); \ + !((((typeof(_mask))_val) << __bf_shf(_mask)) & ~(_mask)); \ + }) + +/** * FIELD_PREP() - prepare a bitfield element * @_mask: shifted mask defining the field's length and position * @_val: value to put in the field diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 3b77588a9360..5797ca6fdfe2 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -112,9 +112,8 @@ extern int __bitmap_intersects(const unsigned long *bitmap1, extern int __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); - -extern void bitmap_set(unsigned long *map, unsigned int start, int len); -extern void bitmap_clear(unsigned long *map, unsigned int start, int len); +extern void __bitmap_set(unsigned long *map, unsigned int start, int len); +extern void __bitmap_clear(unsigned long *map, unsigned int start, int len); extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, @@ -267,10 +266,8 @@ static inline int bitmap_equal(const unsigned long *src1, { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); -#ifdef CONFIG_S390 - if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0) + if (__builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) return !memcmp(src1, src2, nbits / 8); -#endif return __bitmap_equal(src1, src2, nbits); } @@ -315,6 +312,30 @@ static __always_inline int bitmap_weight(const unsigned long *src, unsigned int return __bitmap_weight(src, nbits); } +static __always_inline void bitmap_set(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __set_bit(start, map); + else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && + __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + memset((char *)map + start / 8, 0xff, nbits / 8); + else + __bitmap_set(map, start, nbits); +} + +static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __clear_bit(start, map); + else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && + __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + memset((char *)map + start / 8, 0, nbits / 8); + else + __bitmap_clear(map, start, nbits); +} + static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, int nbits) { diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 01b62e7bac74..7104bea8dab1 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -518,7 +518,7 @@ static inline void blkg_stat_exit(struct blkg_stat *stat) */ static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val) { - __percpu_counter_add(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH); + percpu_counter_add_batch(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH); } /** @@ -597,14 +597,14 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; - __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); if (op_is_sync(op)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; - __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); } /** diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h new file mode 100644 index 000000000000..b1ef6e14744f --- /dev/null +++ b/include/linux/blk-mq-virtio.h @@ -0,0 +1,10 @@ +#ifndef _LINUX_BLK_MQ_VIRTIO_H +#define _LINUX_BLK_MQ_VIRTIO_H + +struct blk_mq_tag_set; +struct virtio_device; + +int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set, + struct virtio_device *vdev, int first_vec); + +#endif /* _LINUX_BLK_MQ_VIRTIO_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 4a2ab5d99ff7..14542308d25b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -15,13 +15,14 @@ struct blk_mq_hw_ctx { unsigned long state; /* BLK_MQ_S_* flags */ } ____cacheline_aligned_in_smp; - struct work_struct run_work; + struct delayed_work run_work; cpumask_var_t cpumask; int next_cpu; int next_cpu_batch; unsigned long flags; /* BLK_MQ_F_* flags */ + void *sched_data; struct request_queue *queue; struct blk_flush_queue *fq; @@ -32,11 +33,11 @@ struct blk_mq_hw_ctx { struct blk_mq_ctx **ctxs; unsigned int nr_ctx; + wait_queue_entry_t dispatch_wait; atomic_t wait_index; struct blk_mq_tags *tags; - - struct srcu_struct queue_rq_srcu; + struct blk_mq_tags *sched_tags; unsigned long queued; unsigned long run; @@ -48,19 +49,25 @@ struct blk_mq_hw_ctx { atomic_t nr_active; - struct delayed_work delay_work; - struct hlist_node cpuhp_dead; struct kobject kobj; unsigned long poll_considered; unsigned long poll_invoked; unsigned long poll_success; + +#ifdef CONFIG_BLK_DEBUG_FS + struct dentry *debugfs_dir; + struct dentry *sched_debugfs_dir; +#endif + + /* Must be the last member - see also blk_mq_hw_ctx_size(). */ + struct srcu_struct queue_rq_srcu[0]; }; struct blk_mq_tag_set { unsigned int *mq_map; - struct blk_mq_ops *ops; + const struct blk_mq_ops *ops; unsigned int nr_hw_queues; unsigned int queue_depth; /* max hw supported */ unsigned int reserved_tags; @@ -78,17 +85,17 @@ struct blk_mq_tag_set { struct blk_mq_queue_data { struct request *rq; - struct list_head *list; bool last; }; -typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, + const struct blk_mq_queue_data *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int); typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int); -typedef int (init_request_fn)(void *, struct request *, unsigned int, +typedef int (init_request_fn)(struct blk_mq_tag_set *set, struct request *, unsigned int, unsigned int); -typedef void (exit_request_fn)(void *, struct request *, unsigned int, +typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *, unsigned int); typedef int (reinit_request_fn)(void *, struct request *); @@ -137,25 +144,34 @@ struct blk_mq_ops { init_request_fn *init_request; exit_request_fn *exit_request; reinit_request_fn *reinit_request; + /* Called from inside blk_get_request() */ + void (*initialize_rq_fn)(struct request *rq); map_queues_fn *map_queues; + +#ifdef CONFIG_BLK_DEBUG_FS + /* + * Used by the debugfs implementation to show driver-specific + * information about a request. + */ + void (*show_rq)(struct seq_file *m, struct request *rq); +#endif }; enum { - BLK_MQ_RQ_QUEUE_OK = 0, /* queued fine */ - BLK_MQ_RQ_QUEUE_BUSY = 1, /* requeue IO for later */ - BLK_MQ_RQ_QUEUE_ERROR = 2, /* end IO with error */ - BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_SHARED = 1 << 1, BLK_MQ_F_SG_MERGE = 1 << 2, - BLK_MQ_F_DEFER_ISSUE = 1 << 4, BLK_MQ_F_BLOCKING = 1 << 5, + BLK_MQ_F_NO_SCHED = 1 << 6, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, BLK_MQ_F_ALLOC_POLICY_BITS = 1, BLK_MQ_S_STOPPED = 0, BLK_MQ_S_TAG_ACTIVE = 1, + BLK_MQ_S_SCHED_RESTART = 2, + BLK_MQ_S_TAG_WAITING = 3, + BLK_MQ_S_START_ON_RUN = 4, BLK_MQ_MAX_DEPTH = 10240, @@ -179,20 +195,19 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); -void blk_mq_insert_request(struct request *, bool, bool, bool); void blk_mq_free_request(struct request *rq); -void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq); bool blk_mq_can_queue(struct blk_mq_hw_ctx *); enum { BLK_MQ_REQ_NOWAIT = (1 << 0), /* return when out of requests */ BLK_MQ_REQ_RESERVED = (1 << 1), /* allocate from reserved pool */ + BLK_MQ_REQ_INTERNAL = (1 << 2), /* allocate internal/sched tag */ }; -struct request *blk_mq_alloc_request(struct request_queue *q, int rw, +struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, unsigned int flags); -struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int op, - unsigned int flags, unsigned int hctx_idx); +struct request *blk_mq_alloc_request_hctx(struct request_queue *q, + unsigned int op, unsigned int flags, unsigned int hctx_idx); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); enum { @@ -215,16 +230,15 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) int blk_mq_request_started(struct request *rq); void blk_mq_start_request(struct request *rq); -void blk_mq_end_request(struct request *rq, int error); -void __blk_mq_end_request(struct request *rq, int error); +void blk_mq_end_request(struct request *rq, blk_status_t error); +void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); -void blk_mq_abort_requeue_list(struct request_queue *q); -void blk_mq_complete_request(struct request *rq, int error); +void blk_mq_complete_request(struct request *rq); bool blk_mq_queue_stopped(struct request_queue *q); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); @@ -233,18 +247,27 @@ void blk_mq_stop_hw_queues(struct request_queue *q); void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); +void blk_mq_quiesce_queue(struct request_queue *q); +void blk_mq_unquiesce_queue(struct request_queue *q); +void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); +void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_unfreeze_queue(struct request_queue *q); -void blk_mq_freeze_queue_start(struct request_queue *q); +void blk_freeze_queue_start(struct request_queue *q); +void blk_mq_freeze_queue_wait(struct request_queue *q); +int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, + unsigned long timeout); int blk_mq_reinit_tagset(struct blk_mq_tag_set *set); int blk_mq_map_queues(struct blk_mq_tag_set *set); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); +void blk_mq_quiesce_queue_nowait(struct request_queue *q); + /* * Driver command data is immediately after the request. So subtract request * size to get back to the original request, add request size to get the PDU. diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 519ea2c9df61..d2eb87c84d82 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -18,19 +18,45 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); /* + * Block error status values. See block/blk-core:blk_errors for the details. + */ +typedef u8 __bitwise blk_status_t; +#define BLK_STS_OK 0 +#define BLK_STS_NOTSUPP ((__force blk_status_t)1) +#define BLK_STS_TIMEOUT ((__force blk_status_t)2) +#define BLK_STS_NOSPC ((__force blk_status_t)3) +#define BLK_STS_TRANSPORT ((__force blk_status_t)4) +#define BLK_STS_TARGET ((__force blk_status_t)5) +#define BLK_STS_NEXUS ((__force blk_status_t)6) +#define BLK_STS_MEDIUM ((__force blk_status_t)7) +#define BLK_STS_PROTECTION ((__force blk_status_t)8) +#define BLK_STS_RESOURCE ((__force blk_status_t)9) +#define BLK_STS_IOERR ((__force blk_status_t)10) + +/* hack for device mapper, don't use elsewhere: */ +#define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) + +#define BLK_STS_AGAIN ((__force blk_status_t)12) + +struct blk_issue_stat { + u64 stat; +}; + +/* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) */ struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - int bi_error; + blk_status_t bi_status; unsigned int bi_opf; /* bottom bits req flags, * top bits REQ_OP. Use * accessors. */ - unsigned short bi_flags; /* status, command, etc */ + unsigned short bi_flags; /* status, etc and bvec pool number */ unsigned short bi_ioprio; + unsigned short bi_write_hint; struct bvec_iter bi_iter; @@ -58,6 +84,10 @@ struct bio { */ struct io_context *bi_ioc; struct cgroup_subsys_state *bi_css; +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW + void *bi_cg_private; + struct blk_issue_stat bi_issue_stat; +#endif #endif union { #if defined(CONFIG_BLK_DEV_INTEGRITY) @@ -102,12 +132,9 @@ struct bio { #define BIO_REFFED 8 /* bio has elevated ->bi_cnt */ #define BIO_THROTTLED 9 /* This bio has already been subjected to * throttling rules. Don't do it again. */ - -/* - * Flags starting here get preserved by bio_reset() - this includes - * BVEC_POOL_IDX() - */ -#define BIO_RESET_BITS 10 +#define BIO_TRACE_COMPLETION 10 /* bio_endio() should trace the final completion + * of this bio. */ +/* See BVEC_POOL_OFFSET below before adding new flags */ /* * We support 6 different bvec pools, the last one is magic in that it @@ -117,13 +144,22 @@ struct bio { #define BVEC_POOL_MAX (BVEC_POOL_NR - 1) /* - * Top 4 bits of bio flags indicate the pool the bvecs came from. We add + * Top 3 bits of bio flags indicate the pool the bvecs came from. We add * 1 to the actual index so that 0 indicates that there are no bvecs to be * freed. */ -#define BVEC_POOL_BITS (4) +#define BVEC_POOL_BITS (3) #define BVEC_POOL_OFFSET (16 - BVEC_POOL_BITS) #define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET) +#if (1<< BVEC_POOL_BITS) < (BVEC_POOL_NR+1) +# error "BVEC_POOL_BITS is too small" +#endif + +/* + * Flags starting here get preserved by bio_reset() - this includes + * only BVEC_POOL_IDX() + */ +#define BIO_RESET_BITS BVEC_POOL_OFFSET /* * Operations and flags common to the bio and request structures. @@ -160,7 +196,14 @@ enum req_opf { /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, /* write the zero filled sector many times */ - REQ_OP_WRITE_ZEROES = 8, + REQ_OP_WRITE_ZEROES = 9, + + /* SCSI passthrough using struct scsi_request */ + REQ_OP_SCSI_IN = 32, + REQ_OP_SCSI_OUT = 33, + /* Driver private requests */ + REQ_OP_DRV_IN = 34, + REQ_OP_DRV_OUT = 35, REQ_OP_LAST, }; @@ -180,6 +223,11 @@ enum req_flag_bits { __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ + + /* command specific flags for REQ_OP_WRITE_ZEROES: */ + __REQ_NOUNMAP, /* do not free blocks when zeroing */ + + __REQ_NOWAIT, /* Don't wait if request will block */ __REQ_NR_BITS, /* stops here */ }; @@ -197,6 +245,9 @@ enum req_flag_bits { #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) +#define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) +#define REQ_NOWAIT (1ULL << __REQ_NOWAIT) + #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) @@ -221,6 +272,15 @@ static inline bool op_is_write(unsigned int op) } /* + * Check if the bio or request is one that needs special treatment in the + * flush state machine. + */ +static inline bool op_is_flush(unsigned int op) +{ + return op & (REQ_FUA | REQ_PREFLUSH); +} + +/* * Reads are always treated as synchronous, as are requests with the FUA or * PREFLUSH flag. Other operations may be marked as synchronous using the * REQ_SYNC flag. @@ -232,22 +292,29 @@ static inline bool op_is_sync(unsigned int op) } typedef unsigned int blk_qc_t; -#define BLK_QC_T_NONE -1U -#define BLK_QC_T_SHIFT 16 +#define BLK_QC_T_NONE -1U +#define BLK_QC_T_SHIFT 16 +#define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { return cookie != BLK_QC_T_NONE; } -static inline blk_qc_t blk_tag_to_qc_t(unsigned int tag, unsigned int queue_num) +static inline blk_qc_t blk_tag_to_qc_t(unsigned int tag, unsigned int queue_num, + bool internal) { - return tag | (queue_num << BLK_QC_T_SHIFT); + blk_qc_t ret = tag | (queue_num << BLK_QC_T_SHIFT); + + if (internal) + ret |= BLK_QC_T_INTERNAL; + + return ret; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) { - return cookie >> BLK_QC_T_SHIFT; + return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT; } static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) @@ -255,11 +322,10 @@ static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) return cookie & ((1u << BLK_QC_T_SHIFT) - 1); } -struct blk_issue_stat { - u64 time; -}; - -#define BLK_RQ_STAT_BATCH 64 +static inline bool blk_qc_t_is_internal(blk_qc_t cookie) +{ + return (cookie & BLK_QC_T_INTERNAL) != 0; +} struct blk_rq_stat { s64 mean; @@ -268,7 +334,6 @@ struct blk_rq_stat { s32 nr_samples; s32 nr_batch; u64 batch; - s64 time; }; #endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1ca8e8fd1078..25f6a0cb27d3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -2,6 +2,7 @@ #define _LINUX_BLKDEV_H #include <linux/sched.h> +#include <linux/sched/clock.h> #ifdef CONFIG_BLOCK @@ -39,17 +40,22 @@ struct blkcg_gq; struct blk_flush_queue; struct pr_ops; struct rq_wb; +struct blk_queue_stats; +struct blk_stat_callback; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ +/* Must be consisitent with blk_mq_poll_stats_bkt() */ +#define BLK_MQ_POLL_STATS_BKTS 16 + /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 2 +#define BLKCG_MAX_POLS 3 -typedef void (rq_end_io_fn)(struct request *, int); +typedef void (rq_end_io_fn)(struct request *, blk_status_t); #define BLK_RL_SYNCFULL (1U << 0) #define BLK_RL_ASYNCFULL (1U << 1) @@ -71,15 +77,6 @@ struct request_list { }; /* - * request command types - */ -enum rq_cmd_type_bits { - REQ_TYPE_FS = 1, /* fs request */ - REQ_TYPE_BLOCK_PC, /* scsi command */ - REQ_TYPE_DRV_PRIV, /* driver defined types from here */ -}; - -/* * request flags */ typedef __u32 __bitwise req_flags_t; @@ -128,8 +125,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) -#define BLK_MAX_CDB 16 - /* * Try to put the fields that are referenced together in the same cacheline. * @@ -147,13 +142,16 @@ struct request { struct blk_mq_ctx *mq_ctx; int cpu; - unsigned cmd_type; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; + + int internal_tag; + unsigned long atomic_flags; /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ + int tag; sector_t __sector; /* sector cursor */ struct bio *bio; @@ -180,6 +178,7 @@ struct request { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; + int error_count; /* for legacy drivers, don't use */ }; /* @@ -220,27 +219,16 @@ struct request { unsigned short ioprio; - void *special; /* opaque pointer available for LLD use */ - - int tag; - int errors; + unsigned int timeout; - /* - * when request is used as a packet command carrier - */ - unsigned char __cmd[BLK_MAX_CDB]; - unsigned char *cmd; - unsigned short cmd_len; + void *special; /* opaque pointer available for LLD use */ unsigned int extra_len; /* length of alignment and padding */ - unsigned int sense_len; - unsigned int resid_len; /* residual count */ - void *sense; + + unsigned short write_hint; unsigned long deadline; struct list_head timeout_list; - unsigned int timeout; - int retries; /* * completion callback. @@ -252,6 +240,21 @@ struct request { struct request *next_rq; }; +static inline bool blk_rq_is_scsi(struct request *rq) +{ + return req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT; +} + +static inline bool blk_rq_is_private(struct request *rq) +{ + return req_op(rq) == REQ_OP_DRV_IN || req_op(rq) == REQ_OP_DRV_OUT; +} + +static inline bool blk_rq_is_passthrough(struct request *rq) +{ + return blk_rq_is_scsi(rq) || blk_rq_is_private(rq); +} + static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; @@ -271,6 +274,8 @@ typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); typedef int (lld_busy_fn) (struct request_queue *q); typedef int (bsg_job_fn) (struct bsg_job *); +typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); +typedef void (exit_rq_fn)(struct request_queue *, struct request *); enum blk_eh_timer_return { BLK_EH_NOT_HANDLED, @@ -333,11 +338,11 @@ struct queue_limits { unsigned short logical_block_size; unsigned short max_segments; unsigned short max_integrity_segments; + unsigned short max_discard_segments; unsigned char misaligned; unsigned char discard_misaligned; unsigned char cluster; - unsigned char discard_zeroes_data; unsigned char raid_partial_stripes_expensive; enum blk_zoned_model zoned; }; @@ -388,6 +393,9 @@ struct request_queue { int nr_rqs[2]; /* # allocated [a]sync rqs */ int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ + atomic_t shared_hctx_restart; + + struct blk_queue_stats *stats; struct rq_wb *rq_wb; /* @@ -406,8 +414,14 @@ struct request_queue { rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; lld_busy_fn *lld_busy_fn; + /* Called just after a request is allocated */ + init_rq_fn *init_rq_fn; + /* Called just before a request is freed */ + exit_rq_fn *exit_rq_fn; + /* Called from inside blk_get_request() */ + void (*initialize_rq_fn)(struct request *rq); - struct blk_mq_ops *mq_ops; + const struct blk_mq_ops *mq_ops; unsigned int *mq_map; @@ -432,7 +446,7 @@ struct request_queue { */ struct delayed_work delay_work; - struct backing_dev_info backing_dev_info; + struct backing_dev_info *backing_dev_info; /* * The queue owner gets to use this for whatever they like. @@ -503,8 +517,6 @@ struct request_queue { unsigned int nr_sorted; unsigned int in_flight[2]; - struct blk_rq_stat rq_stats[2]; - /* * Number of active block driver functions for which blk_drain_queue() * must wait. Must be incremented around functions that unlock the @@ -514,6 +526,10 @@ struct request_queue { unsigned int rq_timeout; int poll_nsec; + + struct blk_stat_callback *poll_cb; + struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS]; + struct timer_list timeout; struct work_struct timeout_work; struct list_head timeout_list; @@ -569,7 +585,20 @@ struct request_queue { struct list_head tag_set_list; struct bio_set *bio_split; +#ifdef CONFIG_BLK_DEBUG_FS + struct dentry *debugfs_dir; + struct dentry *sched_debugfs_dir; +#endif + bool mq_sysfs_init_done; + + size_t cmd_size; + void *rq_alloc_data; + + struct work_struct release_work; + +#define BLK_MAX_WRITE_HINTS 5 + u64 write_hints[BLK_MAX_WRITE_HINTS]; }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ @@ -600,6 +629,10 @@ struct request_queue { #define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */ #define QUEUE_FLAG_DAX 26 /* device supports DAX */ #define QUEUE_FLAG_STATS 27 /* track rq completion times */ +#define QUEUE_FLAG_POLL_STATS 28 /* collecting stats for hybrid polling */ +#define QUEUE_FLAG_REGISTERED 29 /* queue has been registered to a disk */ +#define QUEUE_FLAG_SCSI_PASSTHROUGH 30 /* queue supports SCSI commands */ +#define QUEUE_FLAG_QUIESCED 31 /* queue has been quiesced */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -611,6 +644,13 @@ struct request_queue { (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_POLL)) +/* + * @q->queue_lock is set while a queue is being initialized. Since we know + * that no other threads access the queue object before @q->queue_lock has + * been set, it is safe to manipulate queue flags without holding the + * queue_lock if @q->queue_lock == NULL. See also blk_alloc_queue_node() and + * blk_init_allocated_queue(). + */ static inline void queue_lockdep_assert_held(struct request_queue *q) { if (q->queue_lock) @@ -690,14 +730,18 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_secure_erase(q) \ (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) +#define blk_queue_scsi_passthrough(q) \ + test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) +#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) -#define blk_account_rq(rq) \ - (((rq)->rq_flags & RQF_STARTED) && \ - ((rq)->cmd_type == REQ_TYPE_FS)) +static inline bool blk_account_rq(struct request *rq) +{ + return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); +} #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) @@ -772,7 +816,7 @@ static inline void blk_clear_rl_full(struct request_list *rl, bool sync) static inline bool rq_mergeable(struct request *rq) { - if (rq->cmd_type != REQ_TYPE_FS) + if (blk_rq_is_passthrough(rq)) return false; if (req_op(rq) == REQ_OP_FLUSH) @@ -791,7 +835,8 @@ static inline bool rq_mergeable(struct request *rq) static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) { - if (bio_data(a) == bio_data(b)) + if (bio_page(a) == bio_page(b) && + bio_offset(a) == bio_offset(b)) return true; return false; @@ -839,19 +884,6 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) #define BLK_MIN_SG_TIMEOUT (7 * HZ) -#ifdef CONFIG_BOUNCE -extern int init_emergency_isa_pool(void); -extern void blk_queue_bounce(struct request_queue *q, struct bio **bio); -#else -static inline int init_emergency_isa_pool(void) -{ - return 0; -} -static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio) -{ -} -#endif /* CONFIG_MMU */ - struct rq_map_data { struct page **pages; int page_order; @@ -907,10 +939,11 @@ extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern blk_qc_t generic_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); +extern void blk_init_request_from_bio(struct request *req, struct bio *bio); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); -extern struct request *blk_get_request(struct request_queue *, int, gfp_t); -extern void blk_rq_set_block_pc(struct request *); +extern struct request *blk_get_request(struct request_queue *, unsigned int op, + gfp_t gfp_mask); extern void blk_requeue_request(struct request_queue *, struct request *); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, @@ -918,12 +951,11 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); extern void blk_rq_unprep_clone(struct request *rq); -extern int blk_insert_cloned_request(struct request_queue *q, +extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_delay_queue(struct request_queue *, unsigned long); -extern void blk_queue_split(struct request_queue *, struct bio **, - struct bio_set *); +extern void blk_queue_split(struct request_queue *, struct bio **); extern void blk_recount_segments(struct request_queue *, struct bio *); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, @@ -944,7 +976,6 @@ extern void __blk_run_queue(struct request_queue *q); extern void __blk_run_queue_uncond(struct request_queue *q); extern void blk_run_queue(struct request_queue *); extern void blk_run_queue_async(struct request_queue *q); -extern void blk_mq_quiesce_queue(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); @@ -953,11 +984,14 @@ extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, uns extern int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); -extern int blk_execute_rq(struct request_queue *, struct gendisk *, +extern void blk_execute_rq(struct request_queue *, struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, struct request *, int, rq_end_io_fn *); +int blk_status_to_errno(blk_status_t status); +blk_status_t errno_to_blk_status(int errno); + bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) @@ -1047,7 +1081,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, { struct request_queue *q = rq->q; - if (unlikely(rq->cmd_type != REQ_TYPE_FS)) + if (blk_rq_is_passthrough(rq)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || @@ -1071,20 +1105,6 @@ static inline unsigned int blk_rq_count_bios(struct request *rq) } /* - * blk_rq_set_prio - associate a request with prio from ioc - * @rq: request of interest - * @ioc: target iocontext - * - * Assocate request prio with ioc prio so request based drivers - * can leverage priority information. - */ -static inline void blk_rq_set_prio(struct request *rq, struct io_context *ioc) -{ - if (ioc) - rq->ioprio = ioc->ioprio; -} - -/* * Request issue related functions. */ extern struct request *blk_peek_request(struct request_queue *q); @@ -1104,19 +1124,16 @@ extern struct request *blk_fetch_request(struct request_queue *q); * blk_end_request() for parts of the original function. * This prevents code duplication in drivers. */ -extern bool blk_update_request(struct request *rq, int error, +extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void blk_finish_request(struct request *rq, int error); -extern bool blk_end_request(struct request *rq, int error, +extern void blk_finish_request(struct request *rq, blk_status_t error); +extern bool blk_end_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void blk_end_request_all(struct request *rq, int error); -extern bool blk_end_request_cur(struct request *rq, int error); -extern bool blk_end_request_err(struct request *rq, int error); -extern bool __blk_end_request(struct request *rq, int error, +extern void blk_end_request_all(struct request *rq, blk_status_t error); +extern bool __blk_end_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void __blk_end_request_all(struct request *rq, int error); -extern bool __blk_end_request_cur(struct request *rq, int error); -extern bool __blk_end_request_err(struct request *rq, int error); +extern void __blk_end_request_all(struct request *rq, blk_status_t error); +extern bool __blk_end_request_cur(struct request *rq, blk_status_t error); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); @@ -1129,14 +1146,15 @@ extern void blk_unprep_request(struct request *); extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id); extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); -extern struct request_queue *blk_init_allocated_queue(struct request_queue *, - request_fn_proc *, spinlock_t *); +extern int blk_init_allocated_queue(struct request_queue *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); +extern void blk_queue_max_discard_segments(struct request_queue *, + unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1179,8 +1197,16 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); -extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); +/* + * Number of physical segments as sent to the device. + * + * Normally this is the number of discontiguous data segments sent by the + * submitter. But for data-less command like discard we might have no + * actual data segments submitted, but the driver might have to add it's + * own special payload. In that case we still return 1 here so that this + * special payload will be mapped. + */ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) @@ -1188,6 +1214,15 @@ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) return rq->nr_phys_segments; } +/* + * Number of discard segments (or ranges) the driver needs to fill in. + * Each discard bio merged into a request is counted as one segment. + */ +static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) +{ + return max_t(unsigned short, rq->nr_phys_segments, 1); +} + extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); @@ -1301,23 +1336,27 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, return bqt->tag_index[tag]; } +extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); +extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct page *page); #define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ -#define BLKDEV_DISCARD_ZERO (1 << 1) /* must reliably zero data */ -extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, int flags, struct bio **biop); -extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, struct page *page); + +#define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ +#define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ + extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, - bool discard); + unsigned flags); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, bool discard); + sector_t nr_sects, gfp_t gfp_mask, unsigned flags); + static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) { @@ -1331,7 +1370,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, return blkdev_issue_zeroout(sb->s_bdev, block << (sb->s_blocksize_bits - 9), nr_blocks << (sb->s_blocksize_bits - 9), - gfp_mask, true); + gfp_mask, 0); } extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); @@ -1346,11 +1385,6 @@ enum blk_default_limits { #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) -static inline unsigned long queue_bounce_pfn(struct request_queue *q) -{ - return q->limits.bounce_pfn; -} - static inline unsigned long queue_segment_boundary(struct request_queue *q) { return q->limits.seg_boundary_mask; @@ -1376,6 +1410,11 @@ static inline unsigned short queue_max_segments(struct request_queue *q) return q->limits.max_segments; } +static inline unsigned short queue_max_discard_segments(struct request_queue *q) +{ + return q->limits.max_discard_segments; +} + static inline unsigned int queue_max_segment_size(struct request_queue *q) { return q->limits.max_segment_size; @@ -1496,19 +1535,6 @@ static inline int bdev_discard_alignment(struct block_device *bdev) return q->limits.discard_alignment; } -static inline unsigned int queue_discard_zeroes_data(struct request_queue *q) -{ - if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1) - return 1; - - return 0; -} - -static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev) -{ - return queue_discard_zeroes_data(bdev_get_queue(bdev)); -} - static inline unsigned int bdev_write_same(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); @@ -1620,16 +1646,60 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, return __bvec_gap_to_prev(q, bprv, offset); } -static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, - struct bio *next) +/* + * Check if the two bvecs from two bios can be merged to one segment. + * If yes, no need to check gap between the two bios since the 1st bio + * and the 1st bvec in the 2nd bio can be handled in one segment. + */ +static inline bool bios_segs_mergeable(struct request_queue *q, + struct bio *prev, struct bio_vec *prev_last_bv, + struct bio_vec *next_first_bv) +{ + if (!BIOVEC_PHYS_MERGEABLE(prev_last_bv, next_first_bv)) + return false; + if (!BIOVEC_SEG_BOUNDARY(q, prev_last_bv, next_first_bv)) + return false; + if (prev->bi_seg_back_size + next_first_bv->bv_len > + queue_max_segment_size(q)) + return false; + return true; +} + +static inline bool bio_will_gap(struct request_queue *q, + struct request *prev_rq, + struct bio *prev, + struct bio *next) { if (bio_has_data(prev) && queue_virt_boundary(q)) { struct bio_vec pb, nb; + /* + * don't merge if the 1st bio starts with non-zero + * offset, otherwise it is quite difficult to respect + * sg gap limit. We work hard to merge a huge number of small + * single bios in case of mkfs. + */ + if (prev_rq) + bio_get_first_bvec(prev_rq->bio, &pb); + else + bio_get_first_bvec(prev, &pb); + if (pb.bv_offset) + return true; + + /* + * We don't need to worry about the situation that the + * merged segment ends in unaligned virt boundary: + * + * - if 'pb' ends aligned, the merged segment ends aligned + * - if 'pb' ends unaligned, the next bio must include + * one single bvec of 'nb', otherwise the 'nb' can't + * merge with 'pb' + */ bio_get_last_bvec(prev, &pb); bio_get_first_bvec(next, &nb); - return __bvec_gap_to_prev(q, &pb, nb.bv_offset); + if (!bios_segs_mergeable(q, prev, &pb, &nb)) + return __bvec_gap_to_prev(q, &pb, nb.bv_offset); } return false; @@ -1637,18 +1707,19 @@ static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, static inline bool req_gap_back_merge(struct request *req, struct bio *bio) { - return bio_will_gap(req->q, req->biotail, bio); + return bio_will_gap(req->q, req, req->biotail, bio); } static inline bool req_gap_front_merge(struct request *req, struct bio *bio) { - return bio_will_gap(req->q, bio, req->bio); + return bio_will_gap(req->q, NULL, bio, req->bio); } int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay); int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); +int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #ifdef CONFIG_BLK_CGROUP /* @@ -1715,7 +1786,7 @@ struct blk_integrity_iter { const char *disk_name; }; -typedef int (integrity_processing_fn) (struct blk_integrity_iter *); +typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); struct blk_integrity_profile { integrity_processing_fn *generate_fn; @@ -1862,28 +1933,12 @@ static inline bool integrity_req_gap_front_merge(struct request *req, #endif /* CONFIG_BLK_DEV_INTEGRITY */ -/** - * struct blk_dax_ctl - control and output parameters for ->direct_access - * @sector: (input) offset relative to a block_device - * @addr: (output) kernel virtual address for @sector populated by driver - * @pfn: (output) page frame number for @addr populated by driver - * @size: (input) number of bytes requested - */ -struct blk_dax_ctl { - sector_t sector; - void *addr; - long size; - pfn_t pfn; -}; - struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); int (*rw_page)(struct block_device *, sector_t, struct page *, bool); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); - long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *, - long); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); /* ->media_changed() is DEPRECATED, use ->check_events() instead */ @@ -1902,9 +1957,6 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); -extern long bdev_direct_access(struct block_device *, struct blk_dax_ctl *); -extern int bdev_dax_supported(struct super_block *, int); -extern bool bdev_dax_capable(struct block_device *); #else /* CONFIG_BLOCK */ struct block_device; diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index e417f080219a..d2e908586e3d 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -30,9 +30,6 @@ struct blk_trace { extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); -extern int do_blk_trace_setup(struct request_queue *q, char *name, - dev_t dev, struct block_device *bdev, - struct blk_user_trace_setup *buts); extern __printf(2, 3) void __trace_note_message(struct blk_trace *, const char *fmt, ...); @@ -80,7 +77,6 @@ extern struct attribute_group blk_trace_attr_group; #else /* !CONFIG_BLK_DEV_IO_TRACE */ # define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY) # define blk_trace_shutdown(q) do { } while (0) -# define do_blk_trace_setup(q, name, dev, bdev, buts) (-ENOTTY) # define blk_add_driver_data(q, rq, data, len) do {} while (0) # define blk_trace_setup(q, name, dev, bdev, arg) (-ENOTTY) # define blk_trace_startstop(q, start) (-ENOTTY) @@ -110,16 +106,16 @@ struct compat_blk_user_trace_setup { #endif -#if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK) +extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); -static inline int blk_cmd_buf_len(struct request *rq) +static inline sector_t blk_rq_trace_sector(struct request *rq) { - return (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? rq->cmd_len * 3 : 1; + return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq); } -extern void blk_dump_cmd(char *buf, struct request *rq); -extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); - -#endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */ +static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq) +{ + return blk_rq_is_passthrough(rq) ? 0 : blk_rq_sectors(rq); +} #endif diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 962164d36506..e223d91b6439 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -358,6 +358,7 @@ extern void *alloc_large_system_hash(const char *tablename, #define HASH_EARLY 0x00000001 /* Allocating during early boot? */ #define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min * shift passed via *_hash_shift */ +#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ /* Only NUMA needs hash distribution. 64bit NUMA architectures have * sufficient vmalloc space. diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 92bc89ae7e20..d41d40ac3efd 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -7,6 +7,7 @@ struct sock; struct cgroup; struct sk_buff; +struct bpf_sock_ops_kern; #ifdef CONFIG_CGROUP_BPF @@ -21,20 +22,19 @@ struct cgroup_bpf { */ struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE]; struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE]; + bool disallow_override[MAX_BPF_ATTACH_TYPE]; }; void cgroup_bpf_put(struct cgroup *cgrp); void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent); -void __cgroup_bpf_update(struct cgroup *cgrp, - struct cgroup *parent, - struct bpf_prog *prog, - enum bpf_attach_type type); +int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, + struct bpf_prog *prog, enum bpf_attach_type type, + bool overridable); /* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */ -void cgroup_bpf_update(struct cgroup *cgrp, - struct bpf_prog *prog, - enum bpf_attach_type type); +int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, bool overridable); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, @@ -43,6 +43,10 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, int __cgroup_bpf_run_filter_sk(struct sock *sk, enum bpf_attach_type type); +int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, + struct bpf_sock_ops_kern *sock_ops, + enum bpf_attach_type type); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -76,6 +80,18 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, __ret; \ }) +#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled && (sock_ops)->sk) { \ + typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ + if (__sk && sk_fullsock(__sk)) \ + __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ + sock_ops, \ + BPF_CGROUP_SOCK_OPS); \ + } \ + __ret; \ +}) #else struct cgroup_bpf {}; @@ -86,6 +102,7 @@ static inline void cgroup_bpf_inherit(struct cgroup *cgrp, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #endif /* CONFIG_CGROUP_BPF */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3ed1f3b1d594..b69e7a5869ff 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -8,10 +8,12 @@ #define _LINUX_BPF_H 1 #include <uapi/linux/bpf.h> + #include <linux/workqueue.h> #include <linux/file.h> #include <linux/percpu.h> #include <linux/err.h> +#include <linux/rbtree_latch.h> struct perf_event; struct bpf_map; @@ -33,6 +35,8 @@ struct bpf_map_ops { void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); void (*map_fd_put_ptr)(void *ptr); + u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); + u32 (*map_fd_sys_lookup_elem)(void *ptr); }; struct bpf_map { @@ -43,16 +47,12 @@ struct bpf_map { u32 max_entries; u32 map_flags; u32 pages; + u32 id; struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; atomic_t usercnt; -}; - -struct bpf_map_type_list { - struct list_head list_node; - const struct bpf_map_ops *ops; - enum bpf_map_type type; + struct bpf_map *inner_map_meta; }; /* function argument constraints */ @@ -69,14 +69,14 @@ enum bpf_arg_type { /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack */ - ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */ - ARG_PTR_TO_RAW_STACK, /* any pointer to eBPF program stack, area does not - * need to be initialized, helper function must fill - * all bytes or clear them in error case. + ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ + ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized, + * helper function must fill all bytes or clear + * them in error case. */ - ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */ - ARG_CONST_STACK_SIZE_OR_ZERO, /* number of bytes accessed from stack or 0 */ + ARG_CONST_SIZE, /* number of bytes accessed from memory */ + ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ @@ -150,6 +150,20 @@ enum bpf_reg_type { struct bpf_prog; +/* The information passed from prog-specific *_is_valid_access + * back to the verifier. + */ +struct bpf_insn_access_aux { + enum bpf_reg_type reg_type; + int ctx_field_size; +}; + +static inline void +bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) +{ + aux->ctx_field_size = size; +} + struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); @@ -158,24 +172,25 @@ struct bpf_verifier_ops { * with 'type' (read or write) is allowed */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type, - enum bpf_reg_type *reg_type); + struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); - u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg, - int src_reg, int ctx_off, - struct bpf_insn *insn, struct bpf_prog *prog); -}; - -struct bpf_prog_type_list { - struct list_head list_node; - const struct bpf_verifier_ops *ops; - enum bpf_prog_type type; + u32 (*convert_ctx_access)(enum bpf_access_type type, + const struct bpf_insn *src, + struct bpf_insn *dst, + struct bpf_prog *prog, u32 *target_size); + int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); }; struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; u32 max_ctx_offset; + u32 stack_depth; + u32 id; + struct latch_tree_node ksym_tnode; + struct list_head ksym_lnode; const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; @@ -226,11 +241,21 @@ typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); +int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); + #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); -void bpf_register_prog_type(struct bpf_prog_type_list *tl); -void bpf_register_map_type(struct bpf_map_type_list *tl); +#define BPF_PROG_TYPE(_id, _ops) \ + extern const struct bpf_verifier_ops _ops; +#define BPF_MAP_TYPE(_id, _ops) \ + extern const struct bpf_map_ops _ops; +#include <linux/bpf_types.h> +#undef BPF_PROG_TYPE +#undef BPF_MAP_TYPE struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); @@ -269,7 +294,11 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); +int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); void bpf_fd_array_map_clear(struct bpf_map *map); +int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, + void *key, void *value, u64 map_flags); +int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. @@ -290,10 +319,6 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else -static inline void bpf_register_prog_type(struct bpf_prog_type_list *tl) -{ -} - static inline struct bpf_prog *bpf_prog_get(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); diff --git a/include/linux/bpf_trace.h b/include/linux/bpf_trace.h new file mode 100644 index 000000000000..b22efbdd2eb4 --- /dev/null +++ b/include/linux/bpf_trace.h @@ -0,0 +1,7 @@ +#ifndef __LINUX_BPF_TRACE_H__ +#define __LINUX_BPF_TRACE_H__ + +#include <trace/events/bpf.h> +#include <trace/events/xdp.h> + +#endif /* __LINUX_BPF_TRACE_H__ */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h new file mode 100644 index 000000000000..3d137c33d664 --- /dev/null +++ b/include/linux/bpf_types.h @@ -0,0 +1,37 @@ +/* internal file - do not include directly */ + +#ifdef CONFIG_NET +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops) +#endif +#ifdef CONFIG_BPF_EVENTS +BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event_prog_ops) +#endif + +BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_PROG_ARRAY, prog_array_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops) +#ifdef CONFIG_CGROUPS +BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops) +#endif +BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, htab_lru_percpu_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_LPM_TRIE, trie_map_ops) +#ifdef CONFIG_PERF_EVENTS +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops) +#endif +BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index a13b031dc6b8..8e5d31f6faef 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -40,6 +40,10 @@ struct bpf_reg_state { */ s64 min_value; u64 max_value; + u32 min_align; + u32 aux_off; + u32 aux_off_align; + bool value_from_signed; }; enum bpf_stack_slot_type { @@ -66,7 +70,12 @@ struct bpf_verifier_state_list { }; struct bpf_insn_aux_data { - enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ + union { + enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ + struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */ + }; + int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ + int converted_op_size; /* the valid value width after perceived conversion */ }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ @@ -84,6 +93,7 @@ struct bpf_verifier_env { struct bpf_prog *prog; /* eBPF program being verified */ struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ + bool strict_alignment; /* perform strict pointer alignment checks */ struct bpf_verifier_state cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */ diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 4f7d8be9ddbf..abcda9b458ab 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -17,6 +17,7 @@ #define PHY_ID_BCM5482 0x0143bcb0 #define PHY_ID_BCM5411 0x00206070 #define PHY_ID_BCM5421 0x002060e0 +#define PHY_ID_BCM54210E 0x600d84a0 #define PHY_ID_BCM5464 0x002060b0 #define PHY_ID_BCM5461 0x002060c0 #define PHY_ID_BCM54612E 0x03625e60 @@ -24,6 +25,10 @@ #define PHY_ID_BCM57780 0x03625d90 #define PHY_ID_BCM7250 0xae025280 +#define PHY_ID_BCM7260 0xae025190 +#define PHY_ID_BCM7268 0xae025090 +#define PHY_ID_BCM7271 0xae0253b0 +#define PHY_ID_BCM7278 0xae0251a0 #define PHY_ID_BCM7364 0xae025260 #define PHY_ID_BCM7366 0x600d8490 #define PHY_ID_BCM7346 0x600d8650 @@ -31,6 +36,7 @@ #define PHY_ID_BCM7425 0x600d86b0 #define PHY_ID_BCM7429 0x600d8730 #define PHY_ID_BCM7435 0x600d8750 +#define PHY_ID_BCM74371 0xae0252e0 #define PHY_ID_BCM7439 0x600d8480 #define PHY_ID_BCM7439_2 0xae025080 #define PHY_ID_BCM7445 0x600d8510 @@ -103,19 +109,17 @@ /* * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18) */ -#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000 +#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x00 #define MII_BCM54XX_AUXCTL_ACTL_TX_6DB 0x0400 #define MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA 0x0800 -#define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000 -#define MII_BCM54XX_AUXCTL_MISC_RXD_RXC_SKEW 0x0100 -#define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 -#define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000 -#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007 -#define MII_BCM54XX_AUXCTL_SHDWSEL_READ_SHIFT 12 -#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN (1 << 8) -#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_WIRESPEED_EN (1 << 4) +#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x07 +#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_WIRESPEED_EN 0x0010 +#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN 0x0100 +#define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 +#define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000 +#define MII_BCM54XX_AUXCTL_SHDWSEL_READ_SHIFT 12 #define MII_BCM54XX_AUXCTL_SHDWSEL_MASK 0x0007 /* diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 657a718c27d2..e34dde2da0ef 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -66,9 +66,8 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); -int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name, - bsg_job_fn *job_fn, int dd_job_size); -void bsg_request_fn(struct request_queue *q); +struct request_queue *bsg_setup_queue(struct device *dev, char *name, + bsg_job_fn *job_fn, int dd_job_size); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 79591c3660cc..c8dae555eccf 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -149,6 +149,7 @@ void buffer_check_dirty_writeback(struct page *page, */ void mark_buffer_dirty(struct buffer_head *bh); +void mark_buffer_write_io_error(struct buffer_head *bh); void init_buffer(struct buffer_head *, bh_end_io_t *, void *); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, @@ -196,13 +197,13 @@ void ll_rw_block(int, int, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, int op_flags); void write_dirty_buffer(struct buffer_head *bh, int op_flags); -int _submit_bh(int op, int op_flags, struct buffer_head *bh, - unsigned long bio_flags); int submit_bh(int, int, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int bh_submit_read(struct buffer_head *bh); +loff_t page_cache_seek_hole_data(struct inode *inode, loff_t offset, + loff_t length, int whence); extern int buffer_heads_over_limit; diff --git a/include/linux/bug.h b/include/linux/bug.h index baff2e8fc8a8..5d5554c874fd 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -3,6 +3,7 @@ #include <asm/bug.h> #include <linux/compiler.h> +#include <linux/build_bug.h> enum bug_trap_type { BUG_TRAP_TYPE_NONE = 0, @@ -13,80 +14,9 @@ enum bug_trap_type { struct pt_regs; #ifdef __CHECKER__ -#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) -#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) -#define BUILD_BUG_ON_ZERO(e) (0) -#define BUILD_BUG_ON_NULL(e) ((void*)0) -#define BUILD_BUG_ON_INVALID(e) (0) -#define BUILD_BUG_ON_MSG(cond, msg) (0) -#define BUILD_BUG_ON(condition) (0) -#define BUILD_BUG() (0) #define MAYBE_BUILD_BUG_ON(cond) (0) #else /* __CHECKER__ */ -/* Force a compilation error if a constant expression is not a power of 2 */ -#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ - BUILD_BUG_ON(((n) & ((n) - 1)) != 0) -#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ - BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) - -/* Force a compilation error if condition is true, but also produce a - result (of value 0 and type size_t), so the expression can be used - e.g. in a structure initializer (or where-ever else comma expressions - aren't permitted). */ -#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) -#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); })) - -/* - * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the - * expression but avoids the generation of any code, even if that expression - * has side-effects. - */ -#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) - -/** - * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied - * error message. - * @condition: the condition which the compiler should know is false. - * - * See BUILD_BUG_ON for description. - */ -#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) - -/** - * BUILD_BUG_ON - break compile if a condition is true. - * @condition: the condition which the compiler should know is false. - * - * If you have some code which relies on certain constants being equal, or - * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to - * detect if someone changes it. - * - * The implementation uses gcc's reluctance to create a negative array, but gcc - * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to - * inline functions). Luckily, in 4.3 they added the "error" function - * attribute just for this type of case. Thus, we use a negative sized array - * (should always create an error on gcc versions older than 4.4) and then call - * an undefined function with the error attribute (should always create an - * error on gcc 4.3 and later). If for some reason, neither creates a - * compile-time error, we'll still have a link-time error, which is harder to - * track down. - */ -#ifndef __OPTIMIZE__ -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) -#else -#define BUILD_BUG_ON(condition) \ - BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) -#endif - -/** - * BUILD_BUG - break compile if used. - * - * If you have some code that you expect the compiler to eliminate at - * build time, you should use BUILD_BUG to detect if it is - * unexpectedly used. - */ -#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") - #define MAYBE_BUILD_BUG_ON(cond) \ do { \ if (__builtin_constant_p((cond))) \ @@ -105,7 +35,7 @@ static inline int is_warning_bug(const struct bug_entry *bug) return bug->flags & BUGFLAG_WARNING; } -const struct bug_entry *find_bug(unsigned long bugaddr); +struct bug_entry *find_bug(unsigned long bugaddr); enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs); @@ -124,18 +54,20 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr, /* * Since detected data corruption should stop operation on the affected - * structures, this returns false if the corruption condition is found. + * structures. Return value must be checked and sanely acted on by caller. */ +static inline __must_check bool check_data_corruption(bool v) { return v; } #define CHECK_DATA_CORRUPTION(condition, fmt, ...) \ - do { \ - if (unlikely(condition)) { \ + check_data_corruption(({ \ + bool corruption = unlikely(condition); \ + if (corruption) { \ if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \ pr_err(fmt, ##__VA_ARGS__); \ BUG(); \ } else \ WARN(1, fmt, ##__VA_ARGS__); \ - return false; \ } \ - } while (0) + corruption; \ + })) #endif /* _LINUX_BUG_H */ diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h new file mode 100644 index 000000000000..b7d22d60008a --- /dev/null +++ b/include/linux/build_bug.h @@ -0,0 +1,84 @@ +#ifndef _LINUX_BUILD_BUG_H +#define _LINUX_BUILD_BUG_H + +#include <linux/compiler.h> + +#ifdef __CHECKER__ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) +#define BUILD_BUG_ON_ZERO(e) (0) +#define BUILD_BUG_ON_NULL(e) ((void *)0) +#define BUILD_BUG_ON_INVALID(e) (0) +#define BUILD_BUG_ON_MSG(cond, msg) (0) +#define BUILD_BUG_ON(condition) (0) +#define BUILD_BUG() (0) +#else /* __CHECKER__ */ + +/* Force a compilation error if a constant expression is not a power of 2 */ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON(((n) & ((n) - 1)) != 0) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) + +/* + * Force a compilation error if condition is true, but also produce a + * result (of value 0 and type size_t), so the expression can be used + * e.g. in a structure initializer (or where-ever else comma expressions + * aren't permitted). + */ +#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); })) +#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:(-!!(e)); })) + +/* + * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the + * expression but avoids the generation of any code, even if that expression + * has side-effects. + */ +#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) + +/** + * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied + * error message. + * @condition: the condition which the compiler should know is false. + * + * See BUILD_BUG_ON for description. + */ +#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) + +/** + * BUILD_BUG_ON - break compile if a condition is true. + * @condition: the condition which the compiler should know is false. + * + * If you have some code which relies on certain constants being equal, or + * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to + * detect if someone changes it. + * + * The implementation uses gcc's reluctance to create a negative array, but gcc + * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to + * inline functions). Luckily, in 4.3 they added the "error" function + * attribute just for this type of case. Thus, we use a negative sized array + * (should always create an error on gcc versions older than 4.4) and then call + * an undefined function with the error attribute (should always create an + * error on gcc 4.3 and later). If for some reason, neither creates a + * compile-time error, we'll still have a link-time error, which is harder to + * track down. + */ +#ifndef __OPTIMIZE__ +#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) +#else +#define BUILD_BUG_ON(condition) \ + BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) +#endif + +/** + * BUILD_BUG - break compile if used. + * + * If you have some code that you expect the compiler to eliminate at + * build time, you should use BUILD_BUG to detect if it is + * unexpectedly used. + */ +#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") + +#endif /* __CHECKER__ */ + +#endif /* _LINUX_BUILD_BUG_H */ diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 89b65b82d98f..ec8a4d7af6bd 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -22,6 +22,7 @@ #include <linux/kernel.h> #include <linux/bug.h> +#include <linux/errno.h> /* * was unsigned short, but we might as well be ready for > 64kB I/O pages @@ -39,6 +40,8 @@ struct bvec_iter { unsigned int bi_idx; /* current index into bvl_vec */ + unsigned int bi_done; /* number of bytes completed */ + unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ }; @@ -66,12 +69,14 @@ struct bvec_iter { .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) -static inline void bvec_iter_advance(const struct bio_vec *bv, - struct bvec_iter *iter, - unsigned bytes) +static inline bool bvec_iter_advance(const struct bio_vec *bv, + struct bvec_iter *iter, unsigned bytes) { - WARN_ONCE(bytes > iter->bi_size, - "Attempted to advance past end of bvec iter\n"); + if (WARN_ONCE(bytes > iter->bi_size, + "Attempted to advance past end of bvec iter\n")) { + iter->bi_size = 0; + return false; + } while (bytes) { unsigned iter_len = bvec_iter_len(bv, *iter); @@ -80,12 +85,38 @@ static inline void bvec_iter_advance(const struct bio_vec *bv, bytes -= len; iter->bi_size -= len; iter->bi_bvec_done += len; + iter->bi_done += len; if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) { iter->bi_bvec_done = 0; iter->bi_idx++; } } + return true; +} + +static inline bool bvec_iter_rewind(const struct bio_vec *bv, + struct bvec_iter *iter, + unsigned int bytes) +{ + while (bytes) { + unsigned len = min(bytes, iter->bi_bvec_done); + + if (iter->bi_bvec_done == 0) { + if (WARN_ONCE(iter->bi_idx == 0, + "Attempted to rewind iter beyond " + "bvec's boundaries\n")) { + return false; + } + iter->bi_idx--; + iter->bi_bvec_done = __bvec_iter_bvec(bv, *iter)->bv_len; + continue; + } + bytes -= len; + iter->bi_size += len; + iter->bi_bvec_done -= len; + } + return true; } #define for_each_bvec(bvl, bio_vec, iter, start) \ diff --git a/include/linux/can/core.h b/include/linux/can/core.h index df08a41d5be5..c9a17bb1221c 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -5,7 +5,7 @@ * * Authors: Oliver Hartkopp <oliver.hartkopp@volkswagen.de> * Urs Thuermann <urs.thuermann@volkswagen.de> - * Copyright (c) 2002-2007 Volkswagen Group Electronic Research + * Copyright (c) 2002-2017 Volkswagen Group Electronic Research * All rights reserved. * */ @@ -17,7 +17,7 @@ #include <linux/skbuff.h> #include <linux/netdevice.h> -#define CAN_VERSION "20120528" +#define CAN_VERSION "20170425" /* increment this number each time you change some user-space interface */ #define CAN_ABI_VERSION "9" @@ -45,12 +45,13 @@ struct can_proto { extern int can_proto_register(const struct can_proto *cp); extern void can_proto_unregister(const struct can_proto *cp); -int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask, +int can_rx_register(struct net *net, struct net_device *dev, + canid_t can_id, canid_t mask, void (*func)(struct sk_buff *, void *), void *data, char *ident, struct sock *sk); -extern void can_rx_unregister(struct net_device *dev, canid_t can_id, - canid_t mask, +extern void can_rx_unregister(struct net *net, struct net_device *dev, + canid_t can_id, canid_t mask, void (*func)(struct sk_buff *, void *), void *data); diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 5f5270941ba0..141b05aade81 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -38,6 +38,13 @@ struct can_priv { struct can_bittiming bittiming, data_bittiming; const struct can_bittiming_const *bittiming_const, *data_bittiming_const; + const u16 *termination_const; + unsigned int termination_const_cnt; + u16 termination; + const u32 *bitrate_const; + unsigned int bitrate_const_cnt; + const u32 *data_bitrate_const; + unsigned int data_bitrate_const_cnt; struct can_clock clock; enum can_state state; @@ -53,6 +60,7 @@ struct can_priv { int (*do_set_bittiming)(struct net_device *dev); int (*do_set_data_bittiming)(struct net_device *dev); int (*do_set_mode)(struct net_device *dev, enum can_mode mode); + int (*do_set_termination)(struct net_device *dev, u16 term); int (*do_get_state)(const struct net_device *dev, enum can_state *state); int (*do_get_berr_counter)(const struct net_device *dev, diff --git a/include/linux/can/dev/peak_canfd.h b/include/linux/can/dev/peak_canfd.h new file mode 100644 index 000000000000..46dceef2cfa6 --- /dev/null +++ b/include/linux/can/dev/peak_canfd.h @@ -0,0 +1,308 @@ +/* + * CAN driver for PEAK System micro-CAN based adapters + * + * Copyright (C) 2003-2011 PEAK System-Technik GmbH + * Copyright (C) 2011-2013 Stephane Grosjean <s.grosjean@peak-system.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published + * by the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#ifndef PUCAN_H +#define PUCAN_H + +/* uCAN commands opcodes list (low-order 10 bits) */ +#define PUCAN_CMD_NOP 0x000 +#define PUCAN_CMD_RESET_MODE 0x001 +#define PUCAN_CMD_NORMAL_MODE 0x002 +#define PUCAN_CMD_LISTEN_ONLY_MODE 0x003 +#define PUCAN_CMD_TIMING_SLOW 0x004 +#define PUCAN_CMD_TIMING_FAST 0x005 +#define PUCAN_CMD_SET_STD_FILTER 0x006 +#define PUCAN_CMD_RESERVED2 0x007 +#define PUCAN_CMD_FILTER_STD 0x008 +#define PUCAN_CMD_TX_ABORT 0x009 +#define PUCAN_CMD_WR_ERR_CNT 0x00a +#define PUCAN_CMD_SET_EN_OPTION 0x00b +#define PUCAN_CMD_CLR_DIS_OPTION 0x00c +#define PUCAN_CMD_RX_BARRIER 0x010 +#define PUCAN_CMD_END_OF_COLLECTION 0x3ff + +/* uCAN received messages list */ +#define PUCAN_MSG_CAN_RX 0x0001 +#define PUCAN_MSG_ERROR 0x0002 +#define PUCAN_MSG_STATUS 0x0003 +#define PUCAN_MSG_BUSLOAD 0x0004 + +#define PUCAN_MSG_CACHE_CRITICAL 0x0102 + +/* uCAN transmitted messages */ +#define PUCAN_MSG_CAN_TX 0x1000 + +/* uCAN command common header */ +struct __packed pucan_command { + __le16 opcode_channel; + u16 args[3]; +}; + +/* return the opcode from the opcode_channel field of a command */ +static inline u16 pucan_cmd_get_opcode(struct pucan_command *c) +{ + return le16_to_cpu(c->opcode_channel) & 0x3ff; +} + +#define PUCAN_TSLOW_BRP_BITS 10 +#define PUCAN_TSLOW_TSGEG1_BITS 8 +#define PUCAN_TSLOW_TSGEG2_BITS 7 +#define PUCAN_TSLOW_SJW_BITS 7 + +#define PUCAN_TSLOW_BRP_MASK ((1 << PUCAN_TSLOW_BRP_BITS) - 1) +#define PUCAN_TSLOW_TSEG1_MASK ((1 << PUCAN_TSLOW_TSGEG1_BITS) - 1) +#define PUCAN_TSLOW_TSEG2_MASK ((1 << PUCAN_TSLOW_TSGEG2_BITS) - 1) +#define PUCAN_TSLOW_SJW_MASK ((1 << PUCAN_TSLOW_SJW_BITS) - 1) + +/* uCAN TIMING_SLOW command fields */ +#define PUCAN_TSLOW_SJW_T(s, t) (((s) & PUCAN_TSLOW_SJW_MASK) | \ + ((!!(t)) << 7)) +#define PUCAN_TSLOW_TSEG2(t) ((t) & PUCAN_TSLOW_TSEG2_MASK) +#define PUCAN_TSLOW_TSEG1(t) ((t) & PUCAN_TSLOW_TSEG1_MASK) +#define PUCAN_TSLOW_BRP(b) ((b) & PUCAN_TSLOW_BRP_MASK) + +struct __packed pucan_timing_slow { + __le16 opcode_channel; + + u8 ewl; /* Error Warning limit */ + u8 sjw_t; /* Sync Jump Width + Triple sampling */ + u8 tseg2; /* Timing SEGment 2 */ + u8 tseg1; /* Timing SEGment 1 */ + + __le16 brp; /* BaudRate Prescaler */ +}; + +#define PUCAN_TFAST_BRP_BITS 10 +#define PUCAN_TFAST_TSGEG1_BITS 5 +#define PUCAN_TFAST_TSGEG2_BITS 4 +#define PUCAN_TFAST_SJW_BITS 4 + +#define PUCAN_TFAST_BRP_MASK ((1 << PUCAN_TFAST_BRP_BITS) - 1) +#define PUCAN_TFAST_TSEG1_MASK ((1 << PUCAN_TFAST_TSGEG1_BITS) - 1) +#define PUCAN_TFAST_TSEG2_MASK ((1 << PUCAN_TFAST_TSGEG2_BITS) - 1) +#define PUCAN_TFAST_SJW_MASK ((1 << PUCAN_TFAST_SJW_BITS) - 1) + +/* uCAN TIMING_FAST command fields */ +#define PUCAN_TFAST_SJW(s) ((s) & PUCAN_TFAST_SJW_MASK) +#define PUCAN_TFAST_TSEG2(t) ((t) & PUCAN_TFAST_TSEG2_MASK) +#define PUCAN_TFAST_TSEG1(t) ((t) & PUCAN_TFAST_TSEG1_MASK) +#define PUCAN_TFAST_BRP(b) ((b) & PUCAN_TFAST_BRP_MASK) + +struct __packed pucan_timing_fast { + __le16 opcode_channel; + + u8 unused; + u8 sjw; /* Sync Jump Width */ + u8 tseg2; /* Timing SEGment 2 */ + u8 tseg1; /* Timing SEGment 1 */ + + __le16 brp; /* BaudRate Prescaler */ +}; + +/* uCAN FILTER_STD command fields */ +#define PUCAN_FLTSTD_ROW_IDX_BITS 6 + +struct __packed pucan_filter_std { + __le16 opcode_channel; + + __le16 idx; + __le32 mask; /* CAN-ID bitmask in idx range */ +}; + +#define PUCAN_FLTSTD_ROW_IDX_MAX ((1 << PUCAN_FLTSTD_ROW_IDX_BITS) - 1) + +/* uCAN SET_STD_FILTER command fields */ +struct __packed pucan_std_filter { + __le16 opcode_channel; + + u8 unused; + u8 idx; + __le32 mask; /* CAN-ID bitmask in idx range */ +}; + +/* uCAN TX_ABORT commands fields */ +#define PUCAN_TX_ABORT_FLUSH 0x0001 + +struct __packed pucan_tx_abort { + __le16 opcode_channel; + + __le16 flags; + u32 unused; +}; + +/* uCAN WR_ERR_CNT command fields */ +#define PUCAN_WRERRCNT_TE 0x4000 /* Tx error cntr write Enable */ +#define PUCAN_WRERRCNT_RE 0x8000 /* Rx error cntr write Enable */ + +struct __packed pucan_wr_err_cnt { + __le16 opcode_channel; + + __le16 sel_mask; + u8 tx_counter; /* Tx error counter new value */ + u8 rx_counter; /* Rx error counter new value */ + + u16 unused; +}; + +/* uCAN SET_EN/CLR_DIS _OPTION command fields */ +#define PUCAN_OPTION_ERROR 0x0001 +#define PUCAN_OPTION_BUSLOAD 0x0002 +#define PUCAN_OPTION_CANDFDISO 0x0004 + +struct __packed pucan_options { + __le16 opcode_channel; + + __le16 options; + u32 unused; +}; + +/* uCAN received messages global format */ +struct __packed pucan_msg { + __le16 size; + __le16 type; + __le32 ts_low; + __le32 ts_high; +}; + +/* uCAN flags for CAN/CANFD messages */ +#define PUCAN_MSG_SELF_RECEIVE 0x80 +#define PUCAN_MSG_ERROR_STATE_IND 0x40 /* error state indicator */ +#define PUCAN_MSG_BITRATE_SWITCH 0x20 /* bitrate switch */ +#define PUCAN_MSG_EXT_DATA_LEN 0x10 /* extended data length */ +#define PUCAN_MSG_SINGLE_SHOT 0x08 +#define PUCAN_MSG_LOOPED_BACK 0x04 +#define PUCAN_MSG_EXT_ID 0x02 +#define PUCAN_MSG_RTR 0x01 + +struct __packed pucan_rx_msg { + __le16 size; + __le16 type; + __le32 ts_low; + __le32 ts_high; + __le32 tag_low; + __le32 tag_high; + u8 channel_dlc; + u8 client; + __le16 flags; + __le32 can_id; + u8 d[0]; +}; + +/* uCAN error types */ +#define PUCAN_ERMSG_BIT_ERROR 0 +#define PUCAN_ERMSG_FORM_ERROR 1 +#define PUCAN_ERMSG_STUFF_ERROR 2 +#define PUCAN_ERMSG_OTHER_ERROR 3 +#define PUCAN_ERMSG_ERR_CNT_DEC 4 + +struct __packed pucan_error_msg { + __le16 size; + __le16 type; + __le32 ts_low; + __le32 ts_high; + u8 channel_type_d; + u8 code_g; + u8 tx_err_cnt; + u8 rx_err_cnt; +}; + +static inline int pucan_error_get_channel(const struct pucan_error_msg *msg) +{ + return msg->channel_type_d & 0x0f; +} + +#define PUCAN_RX_BARRIER 0x10 +#define PUCAN_BUS_PASSIVE 0x20 +#define PUCAN_BUS_WARNING 0x40 +#define PUCAN_BUS_BUSOFF 0x80 + +struct __packed pucan_status_msg { + __le16 size; + __le16 type; + __le32 ts_low; + __le32 ts_high; + u8 channel_p_w_b; + u8 unused[3]; +}; + +static inline int pucan_status_get_channel(const struct pucan_status_msg *msg) +{ + return msg->channel_p_w_b & 0x0f; +} + +static inline int pucan_status_is_rx_barrier(const struct pucan_status_msg *msg) +{ + return msg->channel_p_w_b & PUCAN_RX_BARRIER; +} + +static inline int pucan_status_is_passive(const struct pucan_status_msg *msg) +{ + return msg->channel_p_w_b & PUCAN_BUS_PASSIVE; +} + +static inline int pucan_status_is_warning(const struct pucan_status_msg *msg) +{ + return msg->channel_p_w_b & PUCAN_BUS_WARNING; +} + +static inline int pucan_status_is_busoff(const struct pucan_status_msg *msg) +{ + return msg->channel_p_w_b & PUCAN_BUS_BUSOFF; +} + +/* uCAN transmitted message format */ +#define PUCAN_MSG_CHANNEL_DLC(c, d) (((c) & 0xf) | ((d) << 4)) + +struct __packed pucan_tx_msg { + __le16 size; + __le16 type; + __le32 tag_low; + __le32 tag_high; + u8 channel_dlc; + u8 client; + __le16 flags; + __le32 can_id; + u8 d[0]; +}; + +/* build the cmd opcode_channel field with respect to the correct endianness */ +static inline __le16 pucan_cmd_opcode_channel(int index, int opcode) +{ + return cpu_to_le16(((index) << 12) | ((opcode) & 0x3ff)); +} + +/* return the channel number part from any received message channel_dlc field */ +static inline int pucan_msg_get_channel(const struct pucan_rx_msg *msg) +{ + return msg->channel_dlc & 0xf; +} + +/* return the dlc value from any received message channel_dlc field */ +static inline int pucan_msg_get_dlc(const struct pucan_rx_msg *msg) +{ + return msg->channel_dlc >> 4; +} + +static inline int pucan_ermsg_get_channel(const struct pucan_error_msg *msg) +{ + return msg->channel_type_d & 0x0f; +} + +static inline int pucan_stmsg_get_channel(const struct pucan_status_msg *msg) +{ + return msg->channel_p_w_b & 0x0f; +} + +#endif diff --git a/include/linux/can/platform/ti_hecc.h b/include/linux/can/platform/ti_hecc.h deleted file mode 100644 index a52f47ca6c8a..000000000000 --- a/include/linux/can/platform/ti_hecc.h +++ /dev/null @@ -1,44 +0,0 @@ -#ifndef _CAN_PLATFORM_TI_HECC_H -#define _CAN_PLATFORM_TI_HECC_H - -/* - * TI HECC (High End CAN Controller) driver platform header - * - * Copyright (C) 2009 Texas Instruments Incorporated - http://www.ti.com/ - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed as is WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -/** - * struct hecc_platform_data - HECC Platform Data - * - * @scc_hecc_offset: mostly 0 - should really never change - * @scc_ram_offset: SCC RAM offset - * @hecc_ram_offset: HECC RAM offset - * @mbx_offset: Mailbox RAM offset - * @int_line: Interrupt line to use - 0 or 1 - * @version: version for future use - * @transceiver_switch: platform specific callback fn for transceiver control - * - * Platform data structure to get all platform specific settings. - * this structure also accounts the fact that the IP may have different - * RAM and mailbox offsets for different SOC's - */ -struct ti_hecc_platform_data { - u32 scc_hecc_offset; - u32 scc_ram_offset; - u32 hecc_ram_offset; - u32 mbx_offset; - u32 int_line; - u32 version; - void (*transceiver_switch) (int); -}; -#endif /* !_CAN_PLATFORM_TI_HECC_H */ diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h new file mode 100644 index 000000000000..cb31683bbe15 --- /dev/null +++ b/include/linux/can/rx-offload.h @@ -0,0 +1,59 @@ +/* + * linux/can/rx-offload.h + * + * Copyright (c) 2014 David Jander, Protonic Holland + * Copyright (c) 2014-2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the version 2 of the GNU General Public License + * as published by the Free Software Foundation + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _CAN_RX_OFFLOAD_H +#define _CAN_RX_OFFLOAD_H + +#include <linux/netdevice.h> +#include <linux/can.h> + +struct can_rx_offload { + struct net_device *dev; + + unsigned int (*mailbox_read)(struct can_rx_offload *offload, struct can_frame *cf, + u32 *timestamp, unsigned int mb); + + struct sk_buff_head skb_queue; + u32 skb_queue_len_max; + + unsigned int mb_first; + unsigned int mb_last; + + struct napi_struct napi; + + bool inc; +}; + +int can_rx_offload_add_timestamp(struct net_device *dev, struct can_rx_offload *offload); +int can_rx_offload_add_fifo(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight); +int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 reg); +int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); +int can_rx_offload_irq_queue_err_skb(struct can_rx_offload *offload, struct sk_buff *skb); +void can_rx_offload_reset(struct can_rx_offload *offload); +void can_rx_offload_del(struct can_rx_offload *offload); +void can_rx_offload_enable(struct can_rx_offload *offload); + +static inline void can_rx_offload_schedule(struct can_rx_offload *offload) +{ + napi_schedule(&offload->napi); +} + +static inline void can_rx_offload_disable(struct can_rx_offload *offload) +{ + napi_disable(&offload->napi); +} + +#endif /* !_CAN_RX_OFFLOAD_H */ diff --git a/include/linux/ccp.h b/include/linux/ccp.h index c71dd8fa5764..3285c944194a 100644 --- a/include/linux/ccp.h +++ b/include/linux/ccp.h @@ -123,6 +123,10 @@ enum ccp_aes_mode { CCP_AES_MODE_CFB, CCP_AES_MODE_CTR, CCP_AES_MODE_CMAC, + CCP_AES_MODE_GHASH, + CCP_AES_MODE_GCTR, + CCP_AES_MODE_GCM, + CCP_AES_MODE_GMAC, CCP_AES_MODE__LAST, }; @@ -137,6 +141,9 @@ enum ccp_aes_action { CCP_AES_ACTION_ENCRYPT, CCP_AES_ACTION__LAST, }; +/* Overloaded field */ +#define CCP_AES_GHASHAAD CCP_AES_ACTION_DECRYPT +#define CCP_AES_GHASHFINAL CCP_AES_ACTION_ENCRYPT /** * struct ccp_aes_engine - CCP AES operation @@ -181,6 +188,8 @@ struct ccp_aes_engine { struct scatterlist *cmac_key; /* K1/K2 cmac key required for * final cmac cmd */ u32 cmac_key_len; /* In bytes */ + + u32 aad_len; /* In bytes */ }; /***** XTS-AES engine *****/ @@ -249,6 +258,8 @@ enum ccp_sha_type { CCP_SHA_TYPE_1 = 1, CCP_SHA_TYPE_224, CCP_SHA_TYPE_256, + CCP_SHA_TYPE_384, + CCP_SHA_TYPE_512, CCP_SHA_TYPE__LAST, }; @@ -290,6 +301,60 @@ struct ccp_sha_engine { * final sha cmd */ }; +/***** 3DES engine *****/ +enum ccp_des3_mode { + CCP_DES3_MODE_ECB = 0, + CCP_DES3_MODE_CBC, + CCP_DES3_MODE_CFB, + CCP_DES3_MODE__LAST, +}; + +enum ccp_des3_type { + CCP_DES3_TYPE_168 = 1, + CCP_DES3_TYPE__LAST, + }; + +enum ccp_des3_action { + CCP_DES3_ACTION_DECRYPT = 0, + CCP_DES3_ACTION_ENCRYPT, + CCP_DES3_ACTION__LAST, +}; + +/** + * struct ccp_des3_engine - CCP SHA operation + * @type: Type of 3DES operation + * @mode: cipher mode + * @action: 3DES operation (decrypt/encrypt) + * @key: key to be used for this 3DES operation + * @key_len: length of key (in bytes) + * @iv: IV to be used for this AES operation + * @iv_len: length in bytes of iv + * @src: input data to be used for this operation + * @src_len: length of input data used for this operation (in bytes) + * @dst: output data produced by this operation + * + * Variables required to be set when calling ccp_enqueue_cmd(): + * - type, mode, action, key, key_len, src, dst, src_len + * - iv, iv_len for any mode other than ECB + * + * The iv variable is used as both input and output. On completion of the + * 3DES operation the new IV overwrites the old IV. + */ +struct ccp_des3_engine { + enum ccp_des3_type type; + enum ccp_des3_mode mode; + enum ccp_des3_action action; + + struct scatterlist *key; + u32 key_len; /* In bytes */ + + struct scatterlist *iv; + u32 iv_len; /* In bytes */ + + struct scatterlist *src, *dst; + u64 src_len; /* In bytes */ +}; + /***** RSA engine *****/ /** * struct ccp_rsa_engine - CCP RSA operation @@ -539,7 +604,7 @@ struct ccp_ecc_engine { enum ccp_engine { CCP_ENGINE_AES = 0, CCP_ENGINE_XTS_AES_128, - CCP_ENGINE_RSVD1, + CCP_ENGINE_DES3, CCP_ENGINE_SHA, CCP_ENGINE_RSA, CCP_ENGINE_PASSTHRU, @@ -556,7 +621,7 @@ enum ccp_engine { * struct ccp_cmd - CCP operation request * @entry: list element (ccp driver use only) * @work: work element used for callbacks (ccp driver use only) - * @ccp: CCP device to be run on (ccp driver use only) + * @ccp: CCP device to be run on * @ret: operation return code (ccp driver use only) * @flags: cmd processing flags * @engine: CCP operation to perform @@ -587,6 +652,7 @@ struct ccp_cmd { union { struct ccp_aes_engine aes; struct ccp_xts_aes_engine xts; + struct ccp_des3_engine des3; struct ccp_sha_engine sha; struct ccp_rsa_engine rsa; struct ccp_passthru_engine passthru; diff --git a/include/linux/cdev.h b/include/linux/cdev.h index f8763615a5f2..cb28eb21e3ca 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -4,6 +4,7 @@ #include <linux/kobject.h> #include <linux/kdev_t.h> #include <linux/list.h> +#include <linux/device.h> struct file_operations; struct inode; @@ -16,7 +17,7 @@ struct cdev { struct list_head list; dev_t dev; unsigned int count; -}; +} __randomize_layout; void cdev_init(struct cdev *, const struct file_operations *); @@ -26,6 +27,10 @@ void cdev_put(struct cdev *p); int cdev_add(struct cdev *, dev_t, unsigned); +void cdev_set_parent(struct cdev *p, struct kobject *kobj); +int cdev_device_add(struct cdev *cdev, struct device *dev); +void cdev_device_del(struct cdev *cdev, struct device *dev); + void cdev_del(struct cdev *); void cd_forget(struct inode *); diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 8609d577bb66..6e8f209a6dff 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -36,7 +36,7 @@ struct packet_command /* Uniform cdrom data structures for cdrom.c */ struct cdrom_device_info { - struct cdrom_device_ops *ops; /* link to device_ops */ + const struct cdrom_device_ops *ops; /* link to device_ops */ struct list_head list; /* linked list of all device_info */ struct gendisk *disk; /* matching block layer disk */ void *handle; /* driver-dependent data */ @@ -87,7 +87,6 @@ struct cdrom_device_ops { /* driver specifications */ const int capability; /* capability flags */ - int n_minors; /* number of active minor devices */ /* handle uniform packets for scsi type devices (scsi,atapi) */ int (*generic_packet) (struct cdrom_device_info *, struct packet_command *); @@ -123,6 +122,8 @@ extern int cdrom_mode_sense(struct cdrom_device_info *cdi, int page_code, int page_control); extern void init_cdrom_command(struct packet_command *cgc, void *buffer, int len, int type); +extern int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi, + struct packet_command *cgc); /* The SCSI spec says there could be 256 slots. */ #define CDROM_MAX_SLOTS 256 diff --git a/include/linux/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h index aa2e19182d99..51c5bd64bd00 100644 --- a/include/linux/ceph/ceph_debug.h +++ b/include/linux/ceph/ceph_debug.h @@ -3,6 +3,8 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/string.h> + #ifdef CONFIG_CEPH_LIB_PRETTYDEBUG /* @@ -12,12 +14,10 @@ */ # if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) -extern const char *ceph_file_part(const char *s, int len); # define dout(fmt, ...) \ pr_debug("%.*s %12.12s:%-4d : " fmt, \ 8 - (int)sizeof(KBUILD_MODNAME), " ", \ - ceph_file_part(__FILE__, sizeof(__FILE__)), \ - __LINE__, ##__VA_ARGS__) + kbasename(__FILE__), __LINE__, ##__VA_ARGS__) # else /* faux printk call just to see any compiler warnings. */ # define dout(fmt, ...) do { \ diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index ae2f66833762..040dd105c3e7 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -2,127 +2,211 @@ #define __CEPH_FEATURES /* - * feature bits + * Each time we reclaim bits for reuse we need to specify another bit + * that, if present, indicates we have the new incarnation of that + * feature. Base case is 1 (first use). */ -#define CEPH_FEATURE_UID (1ULL<<0) -#define CEPH_FEATURE_NOSRCADDR (1ULL<<1) -#define CEPH_FEATURE_MONCLOCKCHECK (1ULL<<2) -#define CEPH_FEATURE_FLOCK (1ULL<<3) -#define CEPH_FEATURE_SUBSCRIBE2 (1ULL<<4) -#define CEPH_FEATURE_MONNAMES (1ULL<<5) -#define CEPH_FEATURE_RECONNECT_SEQ (1ULL<<6) -#define CEPH_FEATURE_DIRLAYOUTHASH (1ULL<<7) -#define CEPH_FEATURE_OBJECTLOCATOR (1ULL<<8) -#define CEPH_FEATURE_PGID64 (1ULL<<9) -#define CEPH_FEATURE_INCSUBOSDMAP (1ULL<<10) -#define CEPH_FEATURE_PGPOOL3 (1ULL<<11) -#define CEPH_FEATURE_OSDREPLYMUX (1ULL<<12) -#define CEPH_FEATURE_OSDENC (1ULL<<13) -#define CEPH_FEATURE_OMAP (1ULL<<14) -#define CEPH_FEATURE_MONENC (1ULL<<15) -#define CEPH_FEATURE_QUERY_T (1ULL<<16) -#define CEPH_FEATURE_INDEP_PG_MAP (1ULL<<17) -#define CEPH_FEATURE_CRUSH_TUNABLES (1ULL<<18) -#define CEPH_FEATURE_CHUNKY_SCRUB (1ULL<<19) -#define CEPH_FEATURE_MON_NULLROUTE (1ULL<<20) -#define CEPH_FEATURE_MON_GV (1ULL<<21) -#define CEPH_FEATURE_BACKFILL_RESERVATION (1ULL<<22) -#define CEPH_FEATURE_MSG_AUTH (1ULL<<23) -#define CEPH_FEATURE_RECOVERY_RESERVATION (1ULL<<24) -#define CEPH_FEATURE_CRUSH_TUNABLES2 (1ULL<<25) -#define CEPH_FEATURE_CREATEPOOLID (1ULL<<26) -#define CEPH_FEATURE_REPLY_CREATE_INODE (1ULL<<27) -#define CEPH_FEATURE_OSD_HBMSGS (1ULL<<28) -#define CEPH_FEATURE_MDSENC (1ULL<<29) -#define CEPH_FEATURE_OSDHASHPSPOOL (1ULL<<30) -#define CEPH_FEATURE_MON_SINGLE_PAXOS (1ULL<<31) -#define CEPH_FEATURE_OSD_SNAPMAPPER (1ULL<<32) -#define CEPH_FEATURE_MON_SCRUB (1ULL<<33) -#define CEPH_FEATURE_OSD_PACKED_RECOVERY (1ULL<<34) -#define CEPH_FEATURE_OSD_CACHEPOOL (1ULL<<35) -#define CEPH_FEATURE_CRUSH_V2 (1ULL<<36) /* new indep; SET_* steps */ -#define CEPH_FEATURE_EXPORT_PEER (1ULL<<37) -#define CEPH_FEATURE_OSD_ERASURE_CODES (1ULL<<38) -#define CEPH_FEATURE_OSD_TMAP2OMAP (1ULL<<38) /* overlap with EC */ -/* The process supports new-style OSDMap encoding. Monitors also use - this bit to determine if peers support NAK messages. */ -#define CEPH_FEATURE_OSDMAP_ENC (1ULL<<39) -#define CEPH_FEATURE_MDS_INLINE_DATA (1ULL<<40) -#define CEPH_FEATURE_CRUSH_TUNABLES3 (1ULL<<41) -#define CEPH_FEATURE_OSD_PRIMARY_AFFINITY (1ULL<<41) /* overlap w/ tunables3 */ -#define CEPH_FEATURE_MSGR_KEEPALIVE2 (1ULL<<42) -#define CEPH_FEATURE_OSD_POOLRESEND (1ULL<<43) -#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V2 (1ULL<<44) -#define CEPH_FEATURE_OSD_SET_ALLOC_HINT (1ULL<<45) -#define CEPH_FEATURE_OSD_FADVISE_FLAGS (1ULL<<46) -#define CEPH_FEATURE_OSD_REPOP (1ULL<<46) /* overlap with fadvise */ -#define CEPH_FEATURE_OSD_OBJECT_DIGEST (1ULL<<46) /* overlap with fadvise */ -#define CEPH_FEATURE_OSD_TRANSACTION_MAY_LAYOUT (1ULL<<46) /* overlap w/ fadvise */ -#define CEPH_FEATURE_MDS_QUOTA (1ULL<<47) -#define CEPH_FEATURE_CRUSH_V4 (1ULL<<48) /* straw2 buckets */ -#define CEPH_FEATURE_OSD_MIN_SIZE_RECOVERY (1ULL<<49) -// duplicated since it was introduced at the same time as MIN_SIZE_RECOVERY -#define CEPH_FEATURE_OSD_PROXY_FEATURES (1ULL<<49) /* overlap w/ above */ -#define CEPH_FEATURE_MON_METADATA (1ULL<<50) -#define CEPH_FEATURE_OSD_BITWISE_HOBJ_SORT (1ULL<<51) /* can sort objs bitwise */ -#define CEPH_FEATURE_OSD_PROXY_WRITE_FEATURES (1ULL<<52) -#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V3 (1ULL<<53) -#define CEPH_FEATURE_OSD_HITSET_GMT (1ULL<<54) -#define CEPH_FEATURE_HAMMER_0_94_4 (1ULL<<55) -#define CEPH_FEATURE_NEW_OSDOP_ENCODING (1ULL<<56) /* New, v7 encoding */ -#define CEPH_FEATURE_MON_STATEFUL_SUB (1ULL<<57) /* stateful mon subscription */ -#define CEPH_FEATURE_MON_ROUTE_OSDMAP (1ULL<<57) /* peon sends osdmaps */ -#define CEPH_FEATURE_CRUSH_TUNABLES5 (1ULL<<58) /* chooseleaf stable mode */ -// duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5 -#define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING (1ULL<<58) /* New, v7 encoding */ -#define CEPH_FEATURE_FS_FILE_LAYOUT_V2 (1ULL<<58) /* file_layout_t */ +#define CEPH_FEATURE_INCARNATION_1 (0ull) +#define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL + +#define DEFINE_CEPH_FEATURE(bit, incarnation, name) \ + static const uint64_t CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t CEPH_FEATUREMASK_##name = \ + (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); + +/* this bit is ignored but still advertised by release *when* */ +#define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \ + static const uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t DEPRECATED_CEPH_FEATUREMASK_##name = \ + (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* - * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature - * vector to evaluate to 64 bit ~0. To cope, we designate 1ULL << 63 - * to mean 33 bit ~0, and introduce a helper below to do the - * translation. + * this bit is ignored by release *unused* and not advertised by + * release *unadvertised* + */ +#define DEFINE_CEPH_FEATURE_RETIRED(bit, inc, name, unused, unadvertised) + + +/* + * test for a feature. this test is safer than a typical mask against + * the bit because it ensures that we have the bit AND the marker for the + * bit's incarnation. this must be used in any case where the features + * bits may include an old meaning of the bit. + */ +#define CEPH_HAVE_FEATURE(x, name) \ + (((x) & (CEPH_FEATUREMASK_##name)) == (CEPH_FEATUREMASK_##name)) + + +/* + * Notes on deprecation: + * + * A *major* release is a release through which all upgrades must pass + * (e.g., jewel). For example, no pre-jewel server will ever talk to + * a post-jewel server (mon, osd, etc). + * + * For feature bits used *only* on the server-side: + * + * - In the first phase we indicate that a feature is DEPRECATED as of + * a particular release. This is the first major release X (say, + * jewel) that does not depend on its peers advertising the feature. + * That is, it safely assumes its peers all have the feature. We + * indicate this with the DEPRECATED macro. For example, + * + * DEFINE_CEPH_FEATURE_DEPRECATED( 2, 1, MONCLOCKCHECK, JEWEL) + * + * because 10.2.z (jewel) did not care if its peers advertised this + * feature bit. + * + * - In the second phase we stop advertising the the bit and call it + * RETIRED. This can normally be done in the *next* major release + * following the one in which we marked the feature DEPRECATED. In + * the above example, for 12.0.z (luminous) we can say: + * + * DEFINE_CEPH_FEATURE_RETIRED( 2, 1, MONCLOCKCHECK, JEWEL, LUMINOUS) * - * This was introduced by ceph.git commit - * 9ea02b84104045c2ffd7e7f4e7af512953855ecd v0.58-657-g9ea02b8 - * and fixed by ceph.git commit - * 4255b5c2fb54ae40c53284b3ab700fdfc7e61748 v0.65-263-g4255b5c + * - The bit can be reused in the first post-luminous release, 13.0.z + * (m). + * + * This ensures that no two versions who have different meanings for + * the bit ever speak to each other. */ -#define CEPH_FEATURE_RESERVED (1ULL<<63) - -static inline u64 ceph_sanitize_features(u64 features) -{ - if (features & CEPH_FEATURE_RESERVED) { - /* everything through OSD_SNAPMAPPER */ - return 0x1ffffffffull; - } else { - return features; - } -} + +DEFINE_CEPH_FEATURE( 0, 1, UID) +DEFINE_CEPH_FEATURE( 1, 1, NOSRCADDR) +DEFINE_CEPH_FEATURE_RETIRED( 2, 1, MONCLOCKCHECK, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE( 3, 1, FLOCK) +DEFINE_CEPH_FEATURE( 4, 1, SUBSCRIBE2) +DEFINE_CEPH_FEATURE( 5, 1, MONNAMES) +DEFINE_CEPH_FEATURE( 6, 1, RECONNECT_SEQ) +DEFINE_CEPH_FEATURE( 7, 1, DIRLAYOUTHASH) +DEFINE_CEPH_FEATURE( 8, 1, OBJECTLOCATOR) +DEFINE_CEPH_FEATURE( 9, 1, PGID64) +DEFINE_CEPH_FEATURE(10, 1, INCSUBOSDMAP) +DEFINE_CEPH_FEATURE(11, 1, PGPOOL3) +DEFINE_CEPH_FEATURE(12, 1, OSDREPLYMUX) +DEFINE_CEPH_FEATURE(13, 1, OSDENC) +DEFINE_CEPH_FEATURE_RETIRED(14, 1, OMAP, HAMMER, JEWEL) +DEFINE_CEPH_FEATURE(14, 2, SERVER_KRAKEN) +DEFINE_CEPH_FEATURE(15, 1, MONENC) +DEFINE_CEPH_FEATURE_RETIRED(16, 1, QUERY_T, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(17, 1, INDEP_PG_MAP, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(18, 1, CRUSH_TUNABLES) +DEFINE_CEPH_FEATURE_RETIRED(19, 1, CHUNKY_SCRUB, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(20, 1, MON_NULLROUTE, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(21, 1, MON_GV, HAMMER, JEWEL) +DEFINE_CEPH_FEATURE(21, 2, SERVER_LUMINOUS) +DEFINE_CEPH_FEATURE(21, 2, RESEND_ON_SPLIT) // overlap +DEFINE_CEPH_FEATURE(21, 2, RADOS_BACKOFF) // overlap +DEFINE_CEPH_FEATURE(21, 2, OSDMAP_PG_UPMAP) // overlap +DEFINE_CEPH_FEATURE(21, 2, CRUSH_CHOOSE_ARGS) // overlap +DEFINE_CEPH_FEATURE_RETIRED(22, 1, BACKFILL_RESERVATION, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(23, 1, MSG_AUTH) +DEFINE_CEPH_FEATURE_RETIRED(24, 1, RECOVERY_RESERVATION, JEWEL, LUNINOUS) + +DEFINE_CEPH_FEATURE(25, 1, CRUSH_TUNABLES2) +DEFINE_CEPH_FEATURE(26, 1, CREATEPOOLID) +DEFINE_CEPH_FEATURE(27, 1, REPLY_CREATE_INODE) +DEFINE_CEPH_FEATURE_RETIRED(28, 1, OSD_HBMSGS, HAMMER, JEWEL) +DEFINE_CEPH_FEATURE(28, 2, SERVER_M) +DEFINE_CEPH_FEATURE(29, 1, MDSENC) +DEFINE_CEPH_FEATURE(30, 1, OSDHASHPSPOOL) +DEFINE_CEPH_FEATURE(31, 1, MON_SINGLE_PAXOS) // deprecate me +DEFINE_CEPH_FEATURE_RETIRED(32, 1, OSD_SNAPMAPPER, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(33, 1, MON_SCRUB, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(34, 1, OSD_PACKED_RECOVERY, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(35, 1, OSD_CACHEPOOL) +DEFINE_CEPH_FEATURE(36, 1, CRUSH_V2) +DEFINE_CEPH_FEATURE(37, 1, EXPORT_PEER) +DEFINE_CEPH_FEATURE(38, 1, OSD_ERASURE_CODES) +DEFINE_CEPH_FEATURE(38, 1, OSD_OSD_TMAP2OMAP) // overlap +DEFINE_CEPH_FEATURE(39, 1, OSDMAP_ENC) +DEFINE_CEPH_FEATURE(40, 1, MDS_INLINE_DATA) +DEFINE_CEPH_FEATURE(41, 1, CRUSH_TUNABLES3) +DEFINE_CEPH_FEATURE(41, 1, OSD_PRIMARY_AFFINITY) // overlap +DEFINE_CEPH_FEATURE(42, 1, MSGR_KEEPALIVE2) +DEFINE_CEPH_FEATURE(43, 1, OSD_POOLRESEND) +DEFINE_CEPH_FEATURE(44, 1, ERASURE_CODE_PLUGINS_V2) +DEFINE_CEPH_FEATURE_RETIRED(45, 1, OSD_SET_ALLOC_HINT, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(46, 1, OSD_FADVISE_FLAGS) +DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_REPOP, JEWEL, LUMINOUS) // overlap +DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_OBJECT_DIGEST, JEWEL, LUMINOUS) // overlap +DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_TRANSACTION_MAY_LAYOUT, JEWEL, LUMINOUS) // overlap + +DEFINE_CEPH_FEATURE(47, 1, MDS_QUOTA) +DEFINE_CEPH_FEATURE(48, 1, CRUSH_V4) +DEFINE_CEPH_FEATURE_RETIRED(49, 1, OSD_MIN_SIZE_RECOVERY, JEWEL, LUMINOUS) +DEFINE_CEPH_FEATURE_RETIRED(49, 1, OSD_PROXY_FEATURES, JEWEL, LUMINOUS) // overlap + +DEFINE_CEPH_FEATURE(50, 1, MON_METADATA) +DEFINE_CEPH_FEATURE(51, 1, OSD_BITWISE_HOBJ_SORT) +DEFINE_CEPH_FEATURE(52, 1, OSD_PROXY_WRITE_FEATURES) +DEFINE_CEPH_FEATURE(53, 1, ERASURE_CODE_PLUGINS_V3) +DEFINE_CEPH_FEATURE(54, 1, OSD_HITSET_GMT) +DEFINE_CEPH_FEATURE(55, 1, HAMMER_0_94_4) +DEFINE_CEPH_FEATURE(56, 1, NEW_OSDOP_ENCODING) +DEFINE_CEPH_FEATURE(57, 1, MON_STATEFUL_SUB) +DEFINE_CEPH_FEATURE(57, 1, MON_ROUTE_OSDMAP) // overlap +DEFINE_CEPH_FEATURE(57, 1, OSDSUBOP_NO_SNAPCONTEXT) // overlap +DEFINE_CEPH_FEATURE(57, 1, SERVER_JEWEL) // overlap +DEFINE_CEPH_FEATURE(58, 1, CRUSH_TUNABLES5) +DEFINE_CEPH_FEATURE(58, 1, NEW_OSDOPREPLY_ENCODING) // overlap +DEFINE_CEPH_FEATURE(58, 1, FS_FILE_LAYOUT_V2) // overlap +DEFINE_CEPH_FEATURE(59, 1, FS_BTIME) +DEFINE_CEPH_FEATURE(59, 1, FS_CHANGE_ATTR) // overlap +DEFINE_CEPH_FEATURE(59, 1, MSG_ADDR2) // overlap +DEFINE_CEPH_FEATURE(60, 1, BLKIN_TRACING) // *do not share this bit* + +DEFINE_CEPH_FEATURE(61, 1, RESERVED2) // unused, but slow down! +DEFINE_CEPH_FEATURE(62, 1, RESERVED) // do not use; used as a sentinal +DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facing + /* * Features supported. */ #define CEPH_FEATURES_SUPPORTED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ + CEPH_FEATURE_FLOCK | \ CEPH_FEATURE_SUBSCRIBE2 | \ CEPH_FEATURE_RECONNECT_SEQ | \ + CEPH_FEATURE_DIRLAYOUTHASH | \ CEPH_FEATURE_PGID64 | \ CEPH_FEATURE_PGPOOL3 | \ CEPH_FEATURE_OSDENC | \ CEPH_FEATURE_CRUSH_TUNABLES | \ + CEPH_FEATURE_SERVER_LUMINOUS | \ + CEPH_FEATURE_RESEND_ON_SPLIT | \ + CEPH_FEATURE_RADOS_BACKOFF | \ + CEPH_FEATURE_OSDMAP_PG_UPMAP | \ + CEPH_FEATURE_CRUSH_CHOOSE_ARGS | \ CEPH_FEATURE_MSG_AUTH | \ CEPH_FEATURE_CRUSH_TUNABLES2 | \ CEPH_FEATURE_REPLY_CREATE_INODE | \ + CEPH_FEATURE_MDSENC | \ CEPH_FEATURE_OSDHASHPSPOOL | \ CEPH_FEATURE_OSD_CACHEPOOL | \ CEPH_FEATURE_CRUSH_V2 | \ CEPH_FEATURE_EXPORT_PEER | \ CEPH_FEATURE_OSDMAP_ENC | \ + CEPH_FEATURE_MDS_INLINE_DATA | \ CEPH_FEATURE_CRUSH_TUNABLES3 | \ CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ CEPH_FEATURE_MSGR_KEEPALIVE2 | \ + CEPH_FEATURE_OSD_POOLRESEND | \ CEPH_FEATURE_CRUSH_V4 | \ + CEPH_FEATURE_NEW_OSDOP_ENCODING | \ + CEPH_FEATURE_SERVER_JEWEL | \ + CEPH_FEATURE_MON_STATEFUL_SUB | \ CEPH_FEATURE_CRUSH_TUNABLES5 | \ CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING) diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index f4b2ee18f38c..edf5b04b918a 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -147,6 +147,7 @@ struct ceph_dir_layout { #define CEPH_MSG_OSD_OP 42 #define CEPH_MSG_OSD_OPREPLY 43 #define CEPH_MSG_WATCH_NOTIFY 44 +#define CEPH_MSG_OSD_BACKOFF 61 /* watch-notify operations */ @@ -365,6 +366,19 @@ extern const char *ceph_mds_op_name(int op); #define CEPH_READDIR_FRAG_END (1<<0) #define CEPH_READDIR_FRAG_COMPLETE (1<<8) #define CEPH_READDIR_HASH_ORDER (1<<9) +#define CEPH_READDIR_OFFSET_HASH (1<<10) + +/* + * open request flags + */ +#define CEPH_O_RDONLY 00000000 +#define CEPH_O_WRONLY 00000001 +#define CEPH_O_RDWR 00000002 +#define CEPH_O_CREAT 00000100 +#define CEPH_O_EXCL 00000200 +#define CEPH_O_TRUNC 00001000 +#define CEPH_O_DIRECTORY 00200000 +#define CEPH_O_NOFOLLOW 00400000 union ceph_mds_request_args { struct { @@ -384,6 +398,7 @@ union ceph_mds_request_args { __le32 max_entries; /* how many dentries to grab */ __le32 max_bytes; __le16 flags; + __le32 offset_hash; } __attribute__ ((packed)) readdir; struct { __le32 mode; diff --git a/include/linux/ceph/cls_lock_client.h b/include/linux/ceph/cls_lock_client.h index 84884d8d4710..0594d3bba774 100644 --- a/include/linux/ceph/cls_lock_client.h +++ b/include/linux/ceph/cls_lock_client.h @@ -37,6 +37,11 @@ int ceph_cls_break_lock(struct ceph_osd_client *osdc, struct ceph_object_locator *oloc, char *lock_name, char *cookie, struct ceph_entity_name *locker); +int ceph_cls_set_cookie(struct ceph_osd_client *osdc, + struct ceph_object_id *oid, + struct ceph_object_locator *oloc, + char *lock_name, u8 type, char *old_cookie, + char *tag, char *new_cookie); void ceph_free_lockers(struct ceph_locker *lockers, u32 num_lockers); diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index f990f2cc907a..14af9b70d301 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -133,6 +133,66 @@ bad: } /* + * skip helpers + */ +#define ceph_decode_skip_n(p, end, n, bad) \ + do { \ + ceph_decode_need(p, end, n, bad); \ + *p += n; \ + } while (0) + +#define ceph_decode_skip_64(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u64), bad) + +#define ceph_decode_skip_32(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u32), bad) + +#define ceph_decode_skip_16(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u16), bad) + +#define ceph_decode_skip_8(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u8), bad) + +#define ceph_decode_skip_string(p, end, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + ceph_decode_skip_n(p, end, len, bad); \ + } while (0) + +#define ceph_decode_skip_set(p, end, type, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + while (len--) \ + ceph_decode_skip_##type(p, end, bad); \ + } while (0) + +#define ceph_decode_skip_map(p, end, ktype, vtype, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + while (len--) { \ + ceph_decode_skip_##ktype(p, end, bad); \ + ceph_decode_skip_##vtype(p, end, bad); \ + } \ + } while (0) + +#define ceph_decode_skip_map_of_map(p, end, ktype1, ktype2, vtype2, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + while (len--) { \ + ceph_decode_skip_##ktype1(p, end, bad); \ + ceph_decode_skip_map(p, end, ktype2, vtype2, bad); \ + } \ + } while (0) + +/* * struct ceph_timespec <-> struct timespec */ static inline void ceph_decode_timespec(struct timespec *ts, diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 1816c5e26581..8a79587e1317 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -14,6 +14,7 @@ #include <linux/wait.h> #include <linux/writeback.h> #include <linux/slab.h> +#include <linux/refcount.h> #include <linux/ceph/types.h> #include <linux/ceph/messenger.h> @@ -48,6 +49,7 @@ struct ceph_options { unsigned long mount_timeout; /* jiffies */ unsigned long osd_idle_ttl; /* jiffies */ unsigned long osd_keepalive_timeout; /* jiffies */ + unsigned long osd_request_timeout; /* jiffies */ /* * any type that can't be simply compared or doesn't need need @@ -68,6 +70,7 @@ struct ceph_options { #define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0 /* no timeout */ #define CEPH_MONC_HUNT_INTERVAL msecs_to_jiffies(3 * 1000) #define CEPH_MONC_PING_INTERVAL msecs_to_jiffies(10 * 1000) @@ -159,7 +162,7 @@ struct ceph_client { * dirtied. */ struct ceph_snap_context { - atomic_t nref; + refcount_t nref; u64 seq; u32 num_snaps; u64 snaps[]; @@ -181,10 +184,11 @@ static inline int calc_pages_for(u64 off, u64 len) (off >> PAGE_SHIFT); } -/* - * These are not meant to be generic - an integer key is assumed. - */ -#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \ +#define RB_BYVAL(a) (a) +#define RB_BYPTR(a) (&(a)) +#define RB_CMP3WAY(a, b) ((a) < (b) ? -1 : (a) > (b)) + +#define DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \ static void insert_##name(struct rb_root *root, type *t) \ { \ struct rb_node **n = &root->rb_node; \ @@ -194,11 +198,13 @@ static void insert_##name(struct rb_root *root, type *t) \ \ while (*n) { \ type *cur = rb_entry(*n, type, nodefld); \ + int cmp; \ \ parent = *n; \ - if (t->keyfld < cur->keyfld) \ + cmp = cmpexp(keyexp(t->keyfld), keyexp(cur->keyfld)); \ + if (cmp < 0) \ n = &(*n)->rb_left; \ - else if (t->keyfld > cur->keyfld) \ + else if (cmp > 0) \ n = &(*n)->rb_right; \ else \ BUG(); \ @@ -214,19 +220,24 @@ static void erase_##name(struct rb_root *root, type *t) \ RB_CLEAR_NODE(&t->nodefld); \ } -#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) \ -extern type __lookup_##name##_key; \ -static type *lookup_##name(struct rb_root *root, \ - typeof(__lookup_##name##_key.keyfld) key) \ +/* + * @lookup_param_type is a parameter and not constructed from (@type, + * @keyfld) with typeof() because adding const is too unwieldy. + */ +#define DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, cmpexp, keyexp, \ + lookup_param_type, nodefld) \ +static type *lookup_##name(struct rb_root *root, lookup_param_type key) \ { \ struct rb_node *n = root->rb_node; \ \ while (n) { \ type *cur = rb_entry(n, type, nodefld); \ + int cmp; \ \ - if (key < cur->keyfld) \ + cmp = cmpexp(key, keyexp(cur->keyfld)); \ + if (cmp < 0) \ n = n->rb_left; \ - else if (key > cur->keyfld) \ + else if (cmp > 0) \ n = n->rb_right; \ else \ return cur; \ @@ -235,6 +246,23 @@ static type *lookup_##name(struct rb_root *root, \ return NULL; \ } +#define DEFINE_RB_FUNCS2(name, type, keyfld, cmpexp, keyexp, \ + lookup_param_type, nodefld) \ +DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \ +DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, cmpexp, keyexp, \ + lookup_param_type, nodefld) + +/* + * Shorthands for integer keys. + */ +#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \ +DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, RB_CMP3WAY, RB_BYVAL, nodefld) + +#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) \ +extern type __lookup_##name##_key; \ +DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, RB_CMP3WAY, RB_BYVAL, \ + typeof(__lookup_##name##_key.keyfld), nodefld) + #define DEFINE_RB_FUNCS(name, type, keyfld, nodefld) \ DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \ DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) @@ -260,10 +288,7 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client); extern void ceph_destroy_options(struct ceph_options *opt); extern int ceph_compare_options(struct ceph_options *new_opt, struct ceph_client *client); -extern struct ceph_client *ceph_create_client(struct ceph_options *opt, - void *private, - u64 supported_features, - u64 required_features); +struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private); struct ceph_entity_addr *ceph_client_addr(struct ceph_client *client); u64 ceph_client_gid(struct ceph_client *client); extern void ceph_destroy_client(struct ceph_client *client); diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h index 8ed5dc505fbb..d5f783f3226a 100644 --- a/include/linux/ceph/mdsmap.h +++ b/include/linux/ceph/mdsmap.h @@ -25,6 +25,7 @@ struct ceph_mdsmap { u32 m_session_autoclose; /* seconds */ u64 m_max_file_size; u32 m_max_mds; /* size of m_addr, m_state arrays */ + int m_num_mds; struct ceph_mds_info *m_info; /* which object pools file data can be stored in */ @@ -40,7 +41,7 @@ struct ceph_mdsmap { static inline struct ceph_entity_addr * ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w) { - if (w >= m->m_max_mds) + if (w >= m->m_num_mds) return NULL; return &m->m_info[w].addr; } @@ -48,14 +49,14 @@ ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w) static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w) { BUG_ON(w < 0); - if (w >= m->m_max_mds) + if (w >= m->m_num_mds) return CEPH_MDS_STATE_DNE; return m->m_info[w].state; } static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w) { - if (w >= 0 && w < m->m_max_mds) + if (w >= 0 && w < m->m_num_mds) return m->m_info[w].laggy; return false; } diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c5c4c713e00f..fbd94d9fa5dd 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -44,6 +44,8 @@ struct ceph_connection_operations { struct ceph_msg_header *hdr, int *skip); + void (*reencode_message) (struct ceph_msg *msg); + int (*sign_message) (struct ceph_msg *msg); int (*check_message_signature) (struct ceph_msg *msg); }; diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 03a6653d329a..c6d96a5f46fd 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -1,10 +1,12 @@ #ifndef _FS_CEPH_OSD_CLIENT_H #define _FS_CEPH_OSD_CLIENT_H +#include <linux/bitrev.h> #include <linux/completion.h> #include <linux/kref.h> #include <linux/mempool.h> #include <linux/rbtree.h> +#include <linux/refcount.h> #include <linux/ceph/types.h> #include <linux/ceph/osdmap.h> @@ -22,13 +24,12 @@ struct ceph_osd_client; * completion callback for async writepages */ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *); -typedef void (*ceph_osdc_unsafe_callback_t)(struct ceph_osd_request *, bool); #define CEPH_HOMELESS_OSD -1 /* a given osd we're communicating with */ struct ceph_osd { - atomic_t o_ref; + refcount_t o_ref; struct ceph_osd_client *o_osdc; int o_osd; int o_incarnation; @@ -36,6 +37,8 @@ struct ceph_osd { struct ceph_connection o_con; struct rb_root o_requests; struct rb_root o_linger_requests; + struct rb_root o_backoff_mappings; + struct rb_root o_backoffs_by_id; struct list_head o_osd_lru; struct ceph_auth_handshake o_auth; unsigned long lru_ttl; @@ -136,7 +139,8 @@ struct ceph_osd_request_target { struct ceph_object_id target_oid; struct ceph_object_locator target_oloc; - struct ceph_pg pgid; + struct ceph_pg pgid; /* last raw pg we mapped to */ + struct ceph_spg spgid; /* last actual spg we mapped to */ u32 pg_num; u32 pg_num_mask; struct ceph_osds acting; @@ -148,6 +152,9 @@ struct ceph_osd_request_target { unsigned int flags; /* CEPH_OSD_FLAG_* */ bool paused; + u32 epoch; + u32 last_force_resend; + int osd; }; @@ -170,15 +177,12 @@ struct ceph_osd_request { unsigned int r_num_ops; int r_result; - bool r_got_reply; struct ceph_osd_client *r_osdc; struct kref r_kref; bool r_mempool; - struct completion r_completion; - struct completion r_done_completion; /* fsync waiter */ + struct completion r_completion; /* private to osd_client.c */ ceph_osdc_callback_t r_callback; - ceph_osdc_unsafe_callback_t r_unsafe_callback; struct list_head r_unsafe_item; struct inode *r_inode; /* for use by callbacks */ @@ -190,12 +194,12 @@ struct ceph_osd_request { struct timespec r_mtime; /* ditto */ u64 r_data_offset; /* ditto */ bool r_linger; /* don't resend on failure */ + bool r_abort_on_full; /* return ENOSPC when full */ /* internal */ unsigned long r_stamp; /* jiffies, send or check time */ + unsigned long r_start_stamp; /* jiffies */ int r_attempts; - struct ceph_eversion r_replay_version; /* aka reassert_version */ - u32 r_last_force_resend; u32 r_map_dne_bound; struct ceph_osd_req_op r_ops[]; @@ -205,6 +209,23 @@ struct ceph_request_redirect { struct ceph_object_locator oloc; }; +/* + * osd request identifier + * + * caller name + incarnation# + tid to unique identify this request + */ +struct ceph_osd_reqid { + struct ceph_entity_name name; + __le64 tid; + __le32 inc; +} __packed; + +struct ceph_blkin_trace_info { + __le64 trace_id; + __le64 span_id; + __le64 parent_span_id; +} __packed; + typedef void (*rados_watchcb2_t)(void *arg, u64 notify_id, u64 cookie, u64 notifier_id, void *data, size_t data_len); typedef void (*rados_watcherrcb_t)(void *arg, u64 cookie, int err); @@ -223,7 +244,6 @@ struct ceph_osd_linger_request { struct list_head pending_lworks; struct ceph_osd_request_target t; - u32 last_force_resend; u32 map_dne_bound; struct timespec mtime; @@ -258,6 +278,48 @@ struct ceph_watch_item { struct ceph_entity_addr addr; }; +struct ceph_spg_mapping { + struct rb_node node; + struct ceph_spg spgid; + + struct rb_root backoffs; +}; + +struct ceph_hobject_id { + void *key; + size_t key_len; + void *oid; + size_t oid_len; + u64 snapid; + u32 hash; + u8 is_max; + void *nspace; + size_t nspace_len; + s64 pool; + + /* cache */ + u32 hash_reverse_bits; +}; + +static inline void ceph_hoid_build_hash_cache(struct ceph_hobject_id *hoid) +{ + hoid->hash_reverse_bits = bitrev32(hoid->hash); +} + +/* + * PG-wide backoff: [begin, end) + * per-object backoff: begin == end + */ +struct ceph_osd_backoff { + struct rb_node spg_node; + struct rb_node id_node; + + struct ceph_spg spgid; + u64 id; + struct ceph_hobject_id *begin; + struct ceph_hobject_id *end; +}; + #define CEPH_LINGER_ID_START 0xffff000000000000ULL struct ceph_osd_client { @@ -269,6 +331,7 @@ struct ceph_osd_client { struct rb_root osds; /* osds */ struct list_head osd_lru; /* idle osds */ spinlock_t osd_lru_lock; + u32 epoch_barrier; struct ceph_osd homeless_osd; atomic64_t last_tid; /* tid of last request */ u64 last_linger_id; @@ -307,6 +370,7 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg); extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); +void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb); extern void osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u32 flags); diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 9a9041784dcf..a0996cb9faed 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -24,7 +24,15 @@ struct ceph_pg { uint32_t seed; }; +#define CEPH_SPG_NOSHARD -1 + +struct ceph_spg { + struct ceph_pg pgid; + s8 shard; +}; + int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs); +int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs); #define CEPH_POOL_FLAG_HASHPSPOOL (1ULL << 0) /* hash pg seed and pool id together */ @@ -57,7 +65,7 @@ static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool) case CEPH_POOL_TYPE_EC: return false; default: - BUG_ON(1); + BUG(); } } @@ -82,13 +90,6 @@ void ceph_oloc_copy(struct ceph_object_locator *dest, void ceph_oloc_destroy(struct ceph_object_locator *oloc); /* - * Maximum supported by kernel client object name length - * - * (probably outdated: must be >= RBD_MAX_MD_NAME_LEN -- currently 100) - */ -#define CEPH_MAX_OID_NAME_LEN 100 - -/* * 51-char inline_name is long enough for all cephfs and all but one * rbd requests: <imgname> in "<imgname>.rbd"/"rbd_id.<imgname>" can be * arbitrarily long (~PAGE_SIZE). It's done once during rbd map; all @@ -142,10 +143,14 @@ struct ceph_pg_mapping { struct { int len; int osds[]; - } pg_temp; + } pg_temp, pg_upmap; struct { int osd; } primary_temp; + struct { + int len; + int from_to[][2]; + } pg_upmap_items; }; }; @@ -157,13 +162,17 @@ struct ceph_osdmap { u32 flags; /* CEPH_OSDMAP_* */ u32 max_osd; /* size of osd_state, _offload, _addr arrays */ - u8 *osd_state; /* CEPH_OSD_* */ + u32 *osd_state; /* CEPH_OSD_* */ u32 *osd_weight; /* 0 = failed, 0x10000 = 100% normal */ struct ceph_entity_addr *osd_addr; struct rb_root pg_temp; struct rb_root primary_temp; + /* remap (post-CRUSH, pre-up) */ + struct rb_root pg_upmap; /* PG := raw set */ + struct rb_root pg_upmap_items; /* from -> to within raw set */ + u32 *osd_primary_affinity; struct rb_root pg_pools; @@ -173,8 +182,8 @@ struct ceph_osdmap { * the list of osds that store+replicate them. */ struct crush_map *crush; - struct mutex crush_scratch_mutex; - int crush_scratch_ary[CEPH_PG_MAX_SIZE * 3]; + struct mutex crush_workspace_mutex; + void *crush_workspace; }; static inline bool ceph_osd_exists(struct ceph_osdmap *map, int osd) @@ -194,7 +203,7 @@ static inline bool ceph_osd_is_down(struct ceph_osdmap *map, int osd) return !ceph_osd_is_up(map, osd); } -extern char *ceph_osdmap_state_str(char *str, int len, int state); +char *ceph_osdmap_state_str(char *str, int len, u32 state); extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd); static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, @@ -205,11 +214,13 @@ static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, return &map->osd_addr[osd]; } +#define CEPH_PGID_ENCODING_LEN (1 + 8 + 4 + 4) + static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid) { __u8 version; - if (!ceph_has_room(p, end, 1 + 8 + 4 + 4)) { + if (!ceph_has_room(p, end, CEPH_PGID_ENCODING_LEN)) { pr_warn("incomplete pg encoding\n"); return -EINVAL; } @@ -247,6 +258,8 @@ static inline void ceph_osds_init(struct ceph_osds *set) void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src); +bool ceph_pg_is_split(const struct ceph_pg *pgid, u32 old_pg_num, + u32 new_pg_num); bool ceph_is_new_interval(const struct ceph_osds *old_acting, const struct ceph_osds *new_acting, const struct ceph_osds *old_up, @@ -269,15 +282,24 @@ extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, u64 off, u64 len, u64 *bno, u64 *oxoff, u64 *oxlen); +int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, + struct ceph_pg *raw_pgid); int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap, - struct ceph_object_id *oid, - struct ceph_object_locator *oloc, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, struct ceph_pg *raw_pgid); void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, const struct ceph_pg *raw_pgid, struct ceph_osds *up, struct ceph_osds *acting); +bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + const struct ceph_pg *raw_pgid, + struct ceph_spg *spgid); int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap, const struct ceph_pg *raw_pgid); diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h index 13d71fe18b0c..75a7db21457d 100644 --- a/include/linux/ceph/pagelist.h +++ b/include/linux/ceph/pagelist.h @@ -2,7 +2,7 @@ #define __FS_CEPH_PAGELIST_H #include <asm/byteorder.h> -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/list.h> #include <linux/types.h> @@ -13,7 +13,7 @@ struct ceph_pagelist { size_t room; struct list_head free_list; size_t num_pages_free; - atomic_t refcnt; + refcount_t refcnt; }; struct ceph_pagelist_cursor { @@ -30,7 +30,7 @@ static inline void ceph_pagelist_init(struct ceph_pagelist *pl) pl->room = 0; INIT_LIST_HEAD(&pl->free_list); pl->num_pages_free = 0; - atomic_set(&pl->refcnt, 1); + refcount_set(&pl->refcnt, 1); } extern void ceph_pagelist_release(struct ceph_pagelist *pl); diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 5c0da61cb763..385db08bb8b2 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -50,7 +50,7 @@ struct ceph_timespec { #define CEPH_PG_LAYOUT_LINEAR 2 #define CEPH_PG_LAYOUT_HYBRID 3 -#define CEPH_PG_MAX_SIZE 16 /* max # osds in a single pg */ +#define CEPH_PG_MAX_SIZE 32 /* max # osds in a single pg */ /* * placement group. @@ -439,6 +439,12 @@ enum { const char *ceph_osd_watch_op_name(int o); +enum { + CEPH_OSD_BACKOFF_OP_BLOCK = 1, + CEPH_OSD_BACKOFF_OP_ACK_BLOCK = 2, + CEPH_OSD_BACKOFF_OP_UNBLOCK = 3, +}; + /* * an individual object operation. each may be accompanied by some data * payload diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 861b4677fc5b..09f4c7df1478 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -13,6 +13,7 @@ #include <linux/wait.h> #include <linux/mutex.h> #include <linux/rcupdate.h> +#include <linux/refcount.h> #include <linux/percpu-refcount.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> @@ -47,6 +48,7 @@ enum { CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ CSS_VISIBLE = (1 << 3), /* css is visible to userland */ + CSS_DYING = (1 << 4), /* css is dying */ }; /* bits in struct cgroup flags field */ @@ -65,12 +67,21 @@ enum { enum { CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ + + /* + * Consider namespaces as delegation boundaries. If this flag is + * set, controller specific interface files in a namespace root + * aren't writeable from inside the namespace. + */ + CGRP_ROOT_NS_DELEGATE = (1 << 3), }; /* cftype->flags */ enum { CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ + CFTYPE_NS_DELEGATABLE = (1 << 2), /* writeable beyond delegation boundaries */ + CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ @@ -106,9 +117,6 @@ struct cgroup_subsys_state { /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; - /* PI: the parent css */ - struct cgroup_subsys_state *parent; - /* siblings list anchored at the parent's ->children */ struct list_head sibling; struct list_head children; @@ -138,6 +146,12 @@ struct cgroup_subsys_state { /* percpu_ref killing and RCU release */ struct rcu_head rcu_head; struct work_struct destroy_work; + + /* + * PI: the parent css. Placed here for cache proximity to following + * fields of the containing structure. + */ + struct cgroup_subsys_state *parent; }; /* @@ -148,14 +162,21 @@ struct cgroup_subsys_state { * set for a task. */ struct css_set { - /* Reference count */ - atomic_t refcount; - /* - * List running through all cgroup groups in the same hash - * slot. Protected by css_set_lock + * Set of subsystem states, one for each subsystem. This array is + * immutable after creation apart from the init_css_set during + * subsystem registration (at boot time). */ - struct hlist_node hlist; + struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + + /* reference count */ + refcount_t refcount; + + /* the default cgroup associated with this css_set */ + struct cgroup *dfl_cgrp; + + /* internal task count, protected by css_set_lock */ + int nr_tasks; /* * Lists running through all tasks using this cgroup group. @@ -167,21 +188,29 @@ struct css_set { struct list_head tasks; struct list_head mg_tasks; + /* all css_task_iters currently walking this cset */ + struct list_head task_iters; + /* - * List of cgrp_cset_links pointing at cgroups referenced from this - * css_set. Protected by css_set_lock. + * On the default hierarhcy, ->subsys[ssid] may point to a css + * attached to an ancestor instead of the cgroup this css_set is + * associated with. The following node is anchored at + * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to + * iterate through all css's attached to a given cgroup. */ - struct list_head cgrp_links; + struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; - /* the default cgroup associated with this css_set */ - struct cgroup *dfl_cgrp; + /* + * List running through all cgroup groups in the same hash + * slot. Protected by css_set_lock + */ + struct hlist_node hlist; /* - * Set of subsystem states, one for each subsystem. This array is - * immutable after creation apart from the init_css_set during - * subsystem registration (at boot time). + * List of cgrp_cset_links pointing at cgroups referenced from this + * css_set. Protected by css_set_lock. */ - struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + struct list_head cgrp_links; /* * List of csets participating in the on-going migration either as @@ -201,18 +230,6 @@ struct css_set { struct cgroup *mg_dst_cgrp; struct css_set *mg_dst_cset; - /* - * On the default hierarhcy, ->subsys[ssid] may point to a css - * attached to an ancestor instead of the cgroup this css_set is - * associated with. The following node is anchored at - * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to - * iterate through all css's attached to a given cgroup. - */ - struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; - - /* all css_task_iters currently walking this cset */ - struct list_head task_iters; - /* dead and being drained, ignore for migration */ bool dead; @@ -388,6 +405,9 @@ struct cftype { struct list_head node; /* anchored at ss->cfts */ struct kernfs_ops *kf_ops; + int (*open)(struct kernfs_open_file *of); + void (*release)(struct kernfs_open_file *of); + /* * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() @@ -528,8 +548,8 @@ extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups * @tsk: target task * - * Called from threadgroup_change_begin() and allows cgroup operations to - * synchronize against threadgroup changes using a percpu_rw_semaphore. + * Allows cgroup operations to synchronize against threadgroup changes + * using a percpu_rw_semaphore. */ static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) { @@ -540,8 +560,7 @@ static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups * @tsk: target task * - * Called from threadgroup_change_end(). Counterpart of - * cgroup_threadcgroup_change_begin(). + * Counterpart of cgroup_threadcgroup_change_begin(). */ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) { @@ -552,7 +571,11 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) #define CGROUP_SUBSYS_COUNT 0 -static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) {} +static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) +{ + might_sleep(); +} + static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} #endif /* CONFIG_CGROUPS */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c83c23f0577b..710a005c6b7a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -17,11 +17,11 @@ #include <linux/seq_file.h> #include <linux/kernfs.h> #include <linux/jump_label.h> -#include <linux/nsproxy.h> #include <linux/types.h> #include <linux/ns_common.h> #include <linux/nsproxy.h> #include <linux/user_namespace.h> +#include <linux/refcount.h> #include <linux/cgroup-defs.h> @@ -266,7 +266,7 @@ void css_task_iter_end(struct css_task_iter *it); * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor * @dst_css: the destination css - * @tset: takset to iterate + * @tset: taskset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. @@ -344,6 +344,26 @@ static inline bool css_tryget_online(struct cgroup_subsys_state *css) } /** + * css_is_dying - test whether the specified css is dying + * @css: target css + * + * Test whether @css is in the process of offlining or already offline. In + * most cases, ->css_online() and ->css_offline() callbacks should be + * enough; however, the actual offline operations are RCU delayed and this + * test returns %true also when @css is scheduled to be offlined. + * + * This is useful, for example, when the use case requires synchronous + * behavior with respect to cgroup removal. cgroup removal schedules css + * offlining but the css can seem alive while the operation is being + * delayed. If the delay affects user visible semantics, this test can be + * used to resolve the situation. + */ +static inline bool css_is_dying(struct cgroup_subsys_state *css) +{ + return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt); +} + +/** * css_put - put a css reference * @css: target css * @@ -570,6 +590,25 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } +static inline void cgroup_init_kthreadd(void) +{ + /* + * kthreadd is inherited by all kthreads, keep it in the root so + * that the new kthreads are guaranteed to stay in the root until + * initialization is finished. + */ + current->no_cgroup_migration = 1; +} + +static inline void cgroup_kthread_ready(void) +{ + /* + * This kthread finished initialization. The creator should have + * set PF_NO_SETAFFINITY if this kthread should stay in the root. + */ + current->no_cgroup_migration = 0; +} + #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -590,6 +629,8 @@ static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } +static inline void cgroup_init_kthreadd(void) {} +static inline void cgroup_kthread_ready(void) {} static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) @@ -640,7 +681,7 @@ static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ struct cgroup_namespace { - atomic_t count; + refcount_t count; struct ns_common ns; struct user_namespace *user_ns; struct ucounts *ucounts; @@ -675,12 +716,12 @@ copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, static inline void get_cgroup_ns(struct cgroup_namespace *ns) { if (ns) - atomic_inc(&ns->count); + refcount_inc(&ns->count); } static inline void put_cgroup_ns(struct cgroup_namespace *ns) { - if (ns && atomic_dec_and_test(&ns->count)) + if (ns && refcount_dec_and_test(&ns->count)) free_cgroup_ns(ns); } diff --git a/include/linux/cgroup_rdma.h b/include/linux/cgroup_rdma.h new file mode 100644 index 000000000000..e94290b29e99 --- /dev/null +++ b/include/linux/cgroup_rdma.h @@ -0,0 +1,53 @@ +/* + * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com> + * + * This file is subject to the terms and conditions of version 2 of the GNU + * General Public License. See the file COPYING in the main directory of the + * Linux distribution for more details. + */ + +#ifndef _CGROUP_RDMA_H +#define _CGROUP_RDMA_H + +#include <linux/cgroup.h> + +enum rdmacg_resource_type { + RDMACG_RESOURCE_HCA_HANDLE, + RDMACG_RESOURCE_HCA_OBJECT, + RDMACG_RESOURCE_MAX, +}; + +#ifdef CONFIG_CGROUP_RDMA + +struct rdma_cgroup { + struct cgroup_subsys_state css; + + /* + * head to keep track of all resource pools + * that belongs to this cgroup. + */ + struct list_head rpools; +}; + +struct rdmacg_device { + struct list_head dev_node; + struct list_head rpools; + char *name; +}; + +/* + * APIs for RDMA/IB stack to publish when a device wants to + * participate in resource accounting + */ +int rdmacg_register_device(struct rdmacg_device *device); +void rdmacg_unregister_device(struct rdmacg_device *device); + +/* APIs for RDMA/IB stack to charge/uncharge pool specific resources */ +int rdmacg_try_charge(struct rdma_cgroup **rdmacg, + struct rdmacg_device *device, + enum rdmacg_resource_type index); +void rdmacg_uncharge(struct rdma_cgroup *cg, + struct rdmacg_device *device, + enum rdmacg_resource_type index); +#endif /* CONFIG_CGROUP_RDMA */ +#endif /* _CGROUP_RDMA_H */ diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 0df0336acee9..d0e597c44585 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -56,6 +56,10 @@ SUBSYS(hugetlb) SUBSYS(pids) #endif +#if IS_ENABLED(CONFIG_CGROUP_RDMA) +SUBSYS(rdma) +#endif + /* * The following subsystems are not supported on the default hierarchy. */ diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h index fccf7f44139d..bbb3712dd892 100644 --- a/include/linux/cleancache.h +++ b/include/linux/cleancache.h @@ -27,7 +27,7 @@ struct cleancache_filekey { struct cleancache_ops { int (*init_fs)(size_t); - int (*init_shared_fs)(char *uuid, size_t); + int (*init_shared_fs)(uuid_t *uuid, size_t); int (*get_page)(int, struct cleancache_filekey, pgoff_t, struct page *); void (*put_page)(int, struct cleancache_filekey, diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index a428aec36ace..c59c62571e4f 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -412,9 +412,10 @@ extern const struct clk_ops clk_divider_ro_ops; unsigned long divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate, unsigned int val, const struct clk_div_table *table, unsigned long flags); -long divider_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate, const struct clk_div_table *table, - u8 width, unsigned long flags); +long divider_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent, + unsigned long rate, unsigned long *prate, + const struct clk_div_table *table, + u8 width, unsigned long flags); int divider_get_val(unsigned long rate, unsigned long parent_rate, const struct clk_div_table *table, u8 width, unsigned long flags); @@ -757,6 +758,15 @@ static inline void __clk_hw_set_clk(struct clk_hw *dst, struct clk_hw *src) dst->core = src->core; } +static inline long divider_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate, + const struct clk_div_table *table, + u8 width, unsigned long flags) +{ + return divider_round_rate_parent(hw, clk_hw_get_parent(hw), + rate, prate, table, width, flags); +} + /* * FIXME clock api without lock protection */ diff --git a/include/linux/clk.h b/include/linux/clk.h index e9d36b3e49de..12c96d94d1fa 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -77,6 +77,21 @@ struct clk_notifier_data { unsigned long new_rate; }; +/** + * struct clk_bulk_data - Data used for bulk clk operations. + * + * @id: clock consumer ID + * @clk: struct clk * to store the associated clock + * + * The CLK APIs provide a series of clk_bulk_() API calls as + * a convenience to consumers which require multiple clks. This + * structure is used to manage data for these calls. + */ +struct clk_bulk_data { + const char *id; + struct clk *clk; +}; + #ifdef CONFIG_COMMON_CLK /** @@ -132,8 +147,8 @@ int clk_get_phase(struct clk *clk); * @q: clk compared against p * * Returns true if the two struct clk pointers both point to the same hardware - * clock node. Put differently, returns true if struct clk *p and struct clk *q - * share the same struct clk_core object. + * clock node. Put differently, returns true if @p and @q + * share the same &struct clk_core object. * * Returns false otherwise. Note that two NULL clks are treated as matching. */ @@ -185,12 +200,20 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q) */ #ifdef CONFIG_HAVE_CLK_PREPARE int clk_prepare(struct clk *clk); +int __must_check clk_bulk_prepare(int num_clks, + const struct clk_bulk_data *clks); #else static inline int clk_prepare(struct clk *clk) { might_sleep(); return 0; } + +static inline int clk_bulk_prepare(int num_clks, struct clk_bulk_data *clks) +{ + might_sleep(); + return 0; +} #endif /** @@ -204,11 +227,16 @@ static inline int clk_prepare(struct clk *clk) */ #ifdef CONFIG_HAVE_CLK_PREPARE void clk_unprepare(struct clk *clk); +void clk_bulk_unprepare(int num_clks, const struct clk_bulk_data *clks); #else static inline void clk_unprepare(struct clk *clk) { might_sleep(); } +static inline void clk_bulk_unprepare(int num_clks, struct clk_bulk_data *clks) +{ + might_sleep(); +} #endif #ifdef CONFIG_HAVE_CLK @@ -230,6 +258,44 @@ static inline void clk_unprepare(struct clk *clk) struct clk *clk_get(struct device *dev, const char *id); /** + * clk_bulk_get - lookup and obtain a number of references to clock producer. + * @dev: device for clock "consumer" + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * This helper function allows drivers to get several clk consumers in one + * operation. If any of the clk cannot be acquired then any clks + * that were obtained will be freed before returning to the caller. + * + * Returns 0 if all clocks specified in clk_bulk_data table are obtained + * successfully, or valid IS_ERR() condition containing errno. + * The implementation uses @dev and @clk_bulk_data.id to determine the + * clock consumer, and thereby the clock producer. + * The clock returned is stored in each @clk_bulk_data.clk field. + * + * Drivers must assume that the clock source is not enabled. + * + * clk_bulk_get should not be called from within interrupt context. + */ +int __must_check clk_bulk_get(struct device *dev, int num_clks, + struct clk_bulk_data *clks); + +/** + * devm_clk_bulk_get - managed get multiple clk consumers + * @dev: device for clock "consumer" + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * Return 0 on success, an errno on failure. + * + * This helper function allows drivers to get several clk + * consumers in one operation with management, the clks will + * automatically be freed when the device is unbound. + */ +int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, + struct clk_bulk_data *clks); + +/** * devm_clk_get - lookup and obtain a managed reference to a clock producer. * @dev: device for clock "consumer" * @id: clock consumer ID @@ -279,6 +345,18 @@ struct clk *devm_get_clk_from_child(struct device *dev, int clk_enable(struct clk *clk); /** + * clk_bulk_enable - inform the system when the set of clks should be running. + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * May be called from atomic contexts. + * + * Returns success (0) or negative errno. + */ +int __must_check clk_bulk_enable(int num_clks, + const struct clk_bulk_data *clks); + +/** * clk_disable - inform the system when the clock source is no longer required. * @clk: clock source * @@ -295,6 +373,24 @@ int clk_enable(struct clk *clk); void clk_disable(struct clk *clk); /** + * clk_bulk_disable - inform the system when the set of clks is no + * longer required. + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * Inform the system that a set of clks is no longer required by + * a driver and may be shut down. + * + * May be called from atomic contexts. + * + * Implementation detail: if the set of clks is shared between + * multiple drivers, clk_bulk_enable() calls must be balanced by the + * same number of clk_bulk_disable() calls for the clock source to be + * disabled. + */ +void clk_bulk_disable(int num_clks, const struct clk_bulk_data *clks); + +/** * clk_get_rate - obtain the current clock rate (in Hz) for a clock source. * This is only valid once the clock source has been enabled. * @clk: clock source @@ -314,6 +410,19 @@ unsigned long clk_get_rate(struct clk *clk); void clk_put(struct clk *clk); /** + * clk_bulk_put - "free" the clock source + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * Note: drivers must ensure that all clk_bulk_enable calls made on this + * clock source are balanced by clk_bulk_disable calls prior to calling + * this function. + * + * clk_bulk_put should not be called from within interrupt context. + */ +void clk_bulk_put(int num_clks, struct clk_bulk_data *clks); + +/** * devm_clk_put - "free" a managed clock source * @dev: device used to acquire the clock * @clk: clock source acquired with devm_clk_get() @@ -445,11 +554,23 @@ static inline struct clk *clk_get(struct device *dev, const char *id) return NULL; } +static inline int clk_bulk_get(struct device *dev, int num_clks, + struct clk_bulk_data *clks) +{ + return 0; +} + static inline struct clk *devm_clk_get(struct device *dev, const char *id) { return NULL; } +static inline int devm_clk_bulk_get(struct device *dev, int num_clks, + struct clk_bulk_data *clks) +{ + return 0; +} + static inline struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id) { @@ -458,6 +579,8 @@ static inline struct clk *devm_get_clk_from_child(struct device *dev, static inline void clk_put(struct clk *clk) {} +static inline void clk_bulk_put(int num_clks, struct clk_bulk_data *clks) {} + static inline void devm_clk_put(struct device *dev, struct clk *clk) {} static inline int clk_enable(struct clk *clk) @@ -465,8 +588,17 @@ static inline int clk_enable(struct clk *clk) return 0; } +static inline int clk_bulk_enable(int num_clks, struct clk_bulk_data *clks) +{ + return 0; +} + static inline void clk_disable(struct clk *clk) {} + +static inline void clk_bulk_disable(int num_clks, + struct clk_bulk_data *clks) {} + static inline unsigned long clk_get_rate(struct clk *clk) { return 0; @@ -525,6 +657,28 @@ static inline void clk_disable_unprepare(struct clk *clk) clk_unprepare(clk); } +static inline int clk_bulk_prepare_enable(int num_clks, + struct clk_bulk_data *clks) +{ + int ret; + + ret = clk_bulk_prepare(num_clks, clks); + if (ret) + return ret; + ret = clk_bulk_enable(num_clks, clks); + if (ret) + clk_bulk_unprepare(num_clks, clks); + + return ret; +} + +static inline void clk_bulk_disable_unprepare(int num_clks, + struct clk_bulk_data *clks) +{ + clk_bulk_disable(num_clks, clks); + clk_bulk_unprepare(num_clks, clks); +} + #if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK) struct clk *of_clk_get(struct device_node *np, int index); struct clk *of_clk_get_by_name(struct device_node *np, const char *name); @@ -539,6 +693,10 @@ static inline struct clk *of_clk_get_by_name(struct device_node *np, { return ERR_PTR(-ENOENT); } +static inline struct clk *of_clk_get_from_provider(struct of_phandle_args *clkspec) +{ + return ERR_PTR(-ENOENT); +} #endif #endif diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index 7007a5f48080..d23c9cf26993 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -125,5 +125,8 @@ extern void tegra210_xusb_pll_hw_control_enable(void); extern void tegra210_xusb_pll_hw_sequence_start(void); extern void tegra210_sata_pll_hw_control_enable(void); extern void tegra210_sata_pll_hw_sequence_start(void); +extern void tegra210_set_sata_pll_seq_sw(bool state); +extern void tegra210_put_utmipll_in_iddq(void); +extern void tegra210_put_utmipll_out_iddq(void); #endif /* __LINUX_CLK_TEGRA_H_ */ diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 6110fe09ed18..d18da839b810 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -19,6 +19,18 @@ #include <linux/clkdev.h> /** + * struct clk_omap_reg - OMAP register declaration + * @offset: offset from the master IP module base address + * @index: index of the master IP module + */ +struct clk_omap_reg { + void __iomem *ptr; + u16 offset; + u8 index; + u8 flags; +}; + +/** * struct dpll_data - DPLL registers and integration data * @mult_div1_reg: register containing the DPLL M and N bitfields * @mult_mask: mask of the DPLL M bitfield in @mult_div1_reg @@ -67,12 +79,12 @@ * can be placed into read-only space. */ struct dpll_data { - void __iomem *mult_div1_reg; + struct clk_omap_reg mult_div1_reg; u32 mult_mask; u32 div1_mask; struct clk_hw *clk_bypass; struct clk_hw *clk_ref; - void __iomem *control_reg; + struct clk_omap_reg control_reg; u32 enable_mask; unsigned long last_rounded_rate; u16 last_rounded_m; @@ -84,8 +96,8 @@ struct dpll_data { u16 max_divider; unsigned long max_rate; u8 modes; - void __iomem *autoidle_reg; - void __iomem *idlest_reg; + struct clk_omap_reg autoidle_reg; + struct clk_omap_reg idlest_reg; u32 autoidle_mask; u32 freqsel_mask; u32 idlest_mask; @@ -113,10 +125,10 @@ struct clk_hw_omap; */ struct clk_hw_omap_ops { void (*find_idlest)(struct clk_hw_omap *oclk, - void __iomem **idlest_reg, + struct clk_omap_reg *idlest_reg, u8 *idlest_bit, u8 *idlest_val); void (*find_companion)(struct clk_hw_omap *oclk, - void __iomem **other_reg, + struct clk_omap_reg *other_reg, u8 *other_bit); void (*allow_idle)(struct clk_hw_omap *oclk); void (*deny_idle)(struct clk_hw_omap *oclk); @@ -129,8 +141,6 @@ struct clk_hw_omap_ops { * @enable_bit: bitshift to write to enable/disable the clock (see @enable_reg) * @flags: see "struct clk.flags possibilities" above * @clksel_reg: for clksel clks, register va containing src/divisor select - * @clksel_mask: bitmask in @clksel_reg for the src/divisor selector - * @clksel: for clksel clks, pointer to struct clksel for this clock * @dpll_data: for DPLLs, pointer to struct dpll_data for this clock * @clkdm_name: clockdomain name that this clock is contained in * @clkdm: pointer to struct clockdomain, resolved from @clkdm_name at runtime @@ -141,12 +151,10 @@ struct clk_hw_omap { struct list_head node; unsigned long fixed_rate; u8 fixed_div; - void __iomem *enable_reg; + struct clk_omap_reg enable_reg; u8 enable_bit; u8 flags; - void __iomem *clksel_reg; - u32 clksel_mask; - const struct clksel *clksel; + struct clk_omap_reg clksel_reg; struct dpll_data *dpll_data; const char *clkdm_name; struct clockdomain *clkdm; @@ -172,7 +180,6 @@ struct clk_hw_omap { * should be used. This is a temporary solution - a better approach * would be to associate clock type-specific data with the clock, * similar to the struct dpll_data approach. - * MEMMAP_ADDRESSING: Use memmap addressing to access clock registers. */ #define ENABLE_REG_32BIT (1 << 0) /* Use 32-bit access */ #define CLOCK_IDLE_CONTROL (1 << 1) @@ -180,7 +187,6 @@ struct clk_hw_omap { #define ENABLE_ON_INIT (1 << 3) /* Enable upon framework init */ #define INVERT_ENABLE (1 << 4) /* 0 enables, 1 disables */ #define CLOCK_CLKOUTX2 (1 << 5) -#define MEMMAP_ADDRESSING (1 << 6) /* CM_CLKEN_PLL*.EN* bit values - not all are available for every DPLL */ #define DPLL_LOW_POWER_STOP 0x1 @@ -202,21 +208,12 @@ enum { }; /** - * struct clk_omap_reg - OMAP register declaration - * @offset: offset from the master IP module base address - * @index: index of the master IP module - */ -struct clk_omap_reg { - u16 offset; - u16 index; -}; - -/** * struct ti_clk_ll_ops - low-level ops for clocks * @clk_readl: pointer to register read function * @clk_writel: pointer to register write function * @clkdm_clk_enable: pointer to clockdomain enable function * @clkdm_clk_disable: pointer to clockdomain disable function + * @clkdm_lookup: pointer to clockdomain lookup function * @cm_wait_module_ready: pointer to CM module wait ready function * @cm_split_idlest_reg: pointer to CM module function to split idlest reg * @@ -227,20 +224,20 @@ struct clk_omap_reg { * operations not provided directly by clock drivers. */ struct ti_clk_ll_ops { - u32 (*clk_readl)(void __iomem *reg); - void (*clk_writel)(u32 val, void __iomem *reg); + u32 (*clk_readl)(const struct clk_omap_reg *reg); + void (*clk_writel)(u32 val, const struct clk_omap_reg *reg); int (*clkdm_clk_enable)(struct clockdomain *clkdm, struct clk *clk); int (*clkdm_clk_disable)(struct clockdomain *clkdm, struct clk *clk); + struct clockdomain * (*clkdm_lookup)(const char *name); int (*cm_wait_module_ready)(u8 part, s16 prcm_mod, u16 idlest_reg, u8 idlest_shift); - int (*cm_split_idlest_reg)(void __iomem *idlest_reg, s16 *prcm_inst, - u8 *idlest_reg_id); + int (*cm_split_idlest_reg)(struct clk_omap_reg *idlest_reg, + s16 *prcm_inst, u8 *idlest_reg_id); }; #define to_clk_hw_omap(_hw) container_of(_hw, struct clk_hw_omap, hw) -void omap2_init_clk_clkdm(struct clk_hw *clk); int omap2_clk_disable_autoidle_all(void); int omap2_clk_enable_autoidle_all(void); int omap2_clk_allow_idle(struct clk *clk); diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 0d442e34c349..a116926598fd 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -182,7 +182,6 @@ extern u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *e extern void clockevents_register_device(struct clock_event_device *dev); extern int clockevents_unbind_device(struct clock_event_device *ced, int cpu); -extern void clockevents_config(struct clock_event_device *dev, u32 freq); extern void clockevents_config_and_register(struct clock_event_device *dev, u32 freq, unsigned long min_delta, unsigned long max_delta); diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index e315d04a2fd9..a78cb1848e65 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -62,6 +62,8 @@ struct module; * @archdata: arch-specific data * @suspend: suspend function for the clocksource, if necessary * @resume: resume function for the clocksource, if necessary + * @mark_unstable: Optional function to inform the clocksource driver that + * the watchdog marked the clocksource unstable * @owner: module reference, must be set by clocksource in modules * * Note: This struct is not used in hotpathes of the timekeeping code @@ -93,6 +95,8 @@ struct clocksource { unsigned long flags; void (*suspend)(struct clocksource *cs); void (*resume)(struct clocksource *cs); + void (*mark_unstable)(struct clocksource *cs); + void (*tick_stable)(struct clocksource *cs); /* private: */ #ifdef CONFIG_CLOCKSOURCE_WATCHDOG @@ -117,7 +121,7 @@ struct clocksource { #define CLOCK_SOURCE_RESELECT 0x100 /* simplify initialization of mask field */ -#define CLOCKSOURCE_MASK(bits) (u64)((bits) < 64 ? ((1ULL<<(bits))-1) : -1) +#define CLOCKSOURCE_MASK(bits) GENMASK_ULL((bits) - 1, 0) static inline u32 clocksource_freq2mult(u32 freq, u32 shift_constant, u64 from) { @@ -246,16 +250,19 @@ extern int clocksource_mmio_init(void __iomem *, const char *, extern int clocksource_i8253_init(void); +#define TIMER_OF_DECLARE(name, compat, fn) \ + OF_DECLARE_1_RET(timer, name, compat, fn) + #define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ - OF_DECLARE_1_RET(clksrc, name, compat, fn) + TIMER_OF_DECLARE(name, compat, fn) -#ifdef CONFIG_CLKSRC_PROBE -extern void clocksource_probe(void); +#ifdef CONFIG_TIMER_PROBE +extern void timer_probe(void); #else -static inline void clocksource_probe(void) {} +static inline void timer_probe(void) {} #endif -#define CLOCKSOURCE_ACPI_DECLARE(name, table_id, fn) \ - ACPI_DECLARE_PROBE_ENTRY(clksrc, name, table_id, 0, NULL, 0, fn) +#define TIMER_ACPI_DECLARE(name, table_id, fn) \ + ACPI_DECLARE_PROBE_ENTRY(timer, name, table_id, 0, NULL, 0, fn) #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/include/linux/cma.h b/include/linux/cma.h index 6f0a91b37f68..3e8fbf5a5c73 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -21,14 +21,19 @@ struct cma; extern unsigned long totalcma_pages; extern phys_addr_t cma_get_base(const struct cma *cma); extern unsigned long cma_get_size(const struct cma *cma); +extern const char *cma_get_name(const struct cma *cma); extern int __init cma_declare_contiguous(phys_addr_t base, phys_addr_t size, phys_addr_t limit, phys_addr_t alignment, unsigned int order_per_bit, - bool fixed, struct cma **res_cma); + bool fixed, const char *name, struct cma **res_cma); extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, unsigned int order_per_bit, + const char *name, struct cma **res_cma); -extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align); +extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, + gfp_t gfp_mask); extern bool cma_release(struct cma *cma, const struct page *pages, unsigned int count); + +extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); #endif diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h index 5b8721efa948..31e4e1f1547c 100644 --- a/include/linux/coda_psdev.h +++ b/include/linux/coda_psdev.h @@ -15,7 +15,6 @@ struct venus_comm { struct list_head vc_processing; int vc_inuse; struct super_block *vc_sb; - struct backing_dev_info bdi; struct mutex vc_mutex; }; diff --git a/include/linux/compat.h b/include/linux/compat.h index 63609398ef9f..5a6a109b4a50 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -94,6 +94,10 @@ struct compat_itimerval { struct compat_timeval it_value; }; +struct itimerval; +int get_compat_itimerval(struct itimerval *, const struct compat_itimerval __user *); +int put_compat_itimerval(struct compat_itimerval __user *, const struct itimerval *); + struct compat_tms { compat_clock_t tms_utime; compat_clock_t tms_stime; @@ -128,6 +132,10 @@ struct compat_timex { compat_int_t:32; compat_int_t:32; compat_int_t:32; }; +struct timex; +int compat_get_timex(struct timex *, const struct compat_timex __user *); +int compat_put_timex(struct compat_timex __user *, const struct timex *); + #define _COMPAT_NSIG_WORDS (_COMPAT_NSIG / _COMPAT_NSIG_BPW) typedef struct { @@ -156,6 +164,12 @@ extern int compat_get_timespec(struct timespec *, const void __user *); extern int compat_put_timespec(const struct timespec *, void __user *); extern int compat_get_timeval(struct timeval *, const void __user *); extern int compat_put_timeval(const struct timeval *, void __user *); +extern int compat_get_timespec64(struct timespec64 *, const void __user *); +extern int compat_put_timespec64(const struct timespec64 *, void __user *); +extern int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits); +extern int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits); /* * This function convert a timespec if necessary and returns a *user @@ -295,6 +309,13 @@ struct compat_old_sigaction { }; #endif +struct compat_keyctl_kdf_params { + compat_uptr_t hashname; + compat_uptr_t otherinfo; + __u32 otherinfolen; + __u32 __spare[8]; +}; + struct compat_statfs; struct compat_statfs64; struct compat_old_linux_dirent; @@ -381,8 +402,7 @@ asmlinkage long compat_sys_wait4(compat_pid_t pid, #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) -#define BITS_TO_COMPAT_LONGS(bits) \ - (((bits)+BITS_PER_COMPAT_LONG-1)/BITS_PER_COMPAT_LONG) +#define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); @@ -528,11 +548,6 @@ asmlinkage long compat_sys_old_readdir(unsigned int fd, asmlinkage long compat_sys_getdents(unsigned int fd, struct compat_linux_dirent __user *dirent, unsigned int count); -#ifdef __ARCH_WANT_COMPAT_SYS_GETDENTS64 -asmlinkage long compat_sys_getdents64(unsigned int fd, - struct linux_dirent64 __user *dirent, - unsigned int count); -#endif asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *, unsigned int nr_segs, unsigned int flags); asmlinkage long compat_sys_open(const char __user *filename, int flags, @@ -711,8 +726,10 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); compat_stack_t __user *__uss = uss; \ struct task_struct *t = current; \ put_user_ex(ptr_to_compat((void __user *)t->sas_ss_sp), &__uss->ss_sp); \ - put_user_ex(sas_ss_flags(sp), &__uss->ss_flags); \ + put_user_ex(t->sas_ss_flags, &__uss->ss_flags); \ put_user_ex(t->sas_ss_size, &__uss->ss_size); \ + if (t->sas_ss_flags & SS_AUTODISARM) \ + sas_ss_reset(t); \ } while (0); asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, @@ -721,6 +738,8 @@ asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, int, const char __user *); +asmlinkage long compat_sys_arch_prctl(int option, unsigned long arg2); + /* * For most but not all architectures, "am I in a compat syscall?" and * "am I a compat task?" are the same question. For architectures on which @@ -731,7 +750,25 @@ asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, static inline bool in_compat_syscall(void) { return is_compat_task(); } #endif -#else +/** + * ns_to_compat_timeval - Compat version of ns_to_timeval + * @nsec: the nanoseconds value to be converted + * + * Returns the compat_timeval representation of the nsec parameter. + */ +static inline struct compat_timeval ns_to_compat_timeval(s64 nsec) +{ + struct timeval tv; + struct compat_timeval ctv; + + tv = ns_to_timeval(nsec); + ctv.tv_sec = tv.tv_sec; + ctv.tv_usec = tv.tv_usec; + + return ctv; +} + +#else /* !CONFIG_COMPAT */ #define is_compat_task() (0) static inline bool in_compat_syscall(void) { return false; } diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 0444b1336268..bdb80c4aef6e 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,18 +66,22 @@ /* * Force always-inline if the user requests it so via the .config, - * or if gcc is too old: + * or if gcc is too old. + * GCC does not warn about unused static inline functions for + * -Wunused-function. This turns out to avoid the need for complex #ifdef + * directives. Suppress the warning in clang as well by using "unused" + * function attribute, which is redundant but not harmful for gcc. */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) -#define inline inline __attribute__((always_inline)) notrace -#define __inline__ __inline__ __attribute__((always_inline)) notrace -#define __inline __inline __attribute__((always_inline)) notrace +#define inline inline __attribute__((always_inline,unused)) notrace +#define __inline__ __inline__ __attribute__((always_inline,unused)) notrace +#define __inline __inline __attribute__((always_inline,unused)) notrace #else /* A lot of inline functions can cause havoc with function tracing */ -#define inline inline notrace -#define __inline__ __inline__ notrace -#define __inline __inline notrace +#define inline inline __attribute__((unused)) notrace +#define __inline__ __inline__ __attribute__((unused)) notrace +#define __inline __inline __attribute__((unused)) notrace #endif #define __always_inline inline __attribute__((always_inline)) @@ -116,11 +120,13 @@ */ #define __pure __attribute__((pure)) #define __aligned(x) __attribute__((aligned(x))) +#define __aligned_largest __attribute__((aligned)) #define __printf(a, b) __attribute__((format(printf, a, b))) #define __scanf(a, b) __attribute__((format(scanf, a, b))) #define __attribute_const__ __attribute__((__const__)) #define __maybe_unused __attribute__((unused)) #define __always_unused __attribute__((unused)) +#define __mode(x) __attribute__((mode(x))) /* gcc version specific checks */ @@ -195,6 +201,17 @@ #endif #endif +#ifdef CONFIG_STACK_VALIDATION +#define annotate_unreachable() ({ \ + asm("%c0:\t\n" \ + ".pushsection .discard.unreachable\t\n" \ + ".long %c0b - .\t\n" \ + ".popsection\t\n" : : "i" (__LINE__)); \ +}) +#else +#define annotate_unreachable() +#endif + /* * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer @@ -204,14 +221,21 @@ * this in the preprocessor, but we can live with this because they're * unreleased. Really, we need to have autoconf for the kernel. */ -#define unreachable() __builtin_unreachable() +#define unreachable() \ + do { annotate_unreachable(); __builtin_unreachable(); } while (0) /* Mark a function definition as prohibited from being cloned. */ #define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) +#ifdef RANDSTRUCT_PLUGIN +#define __randomize_layout __attribute__((randomize_layout)) +#define __no_randomize_layout __attribute__((no_randomize_layout)) +#endif + #endif /* GCC_VERSION >= 40500 */ #if GCC_VERSION >= 40600 + /* * When used with Link Time Optimization, gcc can optimize away C functions or * variables which are referenced only from assembly code. __visible tells the @@ -219,7 +243,17 @@ * this. */ #define __visible __attribute__((externally_visible)) -#endif + +/* + * RANDSTRUCT_PLUGIN wants to use an anonymous struct, but it is only + * possible since GCC 4.6. To provide as much build testing coverage + * as possible, this is used for all GCC 4.6+ builds, and not just on + * RANDSTRUCT_PLUGIN builds. + */ +#define randomized_struct_fields_start struct { +#define randomized_struct_fields_end } __randomize_layout; + +#endif /* GCC_VERSION >= 40600 */ #if GCC_VERSION >= 40900 && !defined(__CHECKER__) @@ -280,6 +314,14 @@ #define __no_sanitize_address __attribute__((no_sanitize_address)) #endif +#if GCC_VERSION >= 50100 +/* + * Mark structures as requiring designated initializers. + * https://gcc.gnu.org/onlinedocs/gcc/Designated-Inits.html + */ +#define __designated_init __attribute__((designated_init)) +#endif + #endif /* gcc version >= 40000 specific checks */ #if !defined(__noclone) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index cf0fa5d86059..eca8ad75e28b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -17,17 +17,17 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) -#ifdef CONFIG_SPARSE_RCU_POINTER # define __rcu __attribute__((noderef, address_space(4))) -#else /* CONFIG_SPARSE_RCU_POINTER */ -# define __rcu -#endif /* CONFIG_SPARSE_RCU_POINTER */ # define __private __attribute__((noderef)) extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); # define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member)) #else /* __CHECKER__ */ -# define __user +# ifdef STRUCTLEAK_PLUGIN +# define __user __attribute__((user)) +# else +# define __user +# endif # define __kernel # define __safe # define __force @@ -101,29 +101,36 @@ struct ftrace_branch_data { }; }; +struct ftrace_likely_data { + struct ftrace_branch_data data; + unsigned long constant; +}; + /* * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. */ #if defined(CONFIG_TRACE_BRANCH_PROFILING) \ && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) -void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); +void ftrace_likely_update(struct ftrace_likely_data *f, int val, + int expect, int is_constant); #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) -#define __branch_check__(x, expect) ({ \ +#define __branch_check__(x, expect, is_constant) ({ \ int ______r; \ - static struct ftrace_branch_data \ + static struct ftrace_likely_data \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_annotated_branch"))) \ ______f = { \ - .func = __func__, \ - .file = __FILE__, \ - .line = __LINE__, \ + .data.func = __func__, \ + .data.file = __FILE__, \ + .data.line = __LINE__, \ }; \ - ______r = likely_notrace(x); \ - ftrace_likely_update(&______f, ______r, expect); \ + ______r = __builtin_expect(!!(x), expect); \ + ftrace_likely_update(&______f, ______r, \ + expect, is_constant); \ ______r; \ }) @@ -133,10 +140,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); * written by Daniel Walker. */ # ifndef likely -# define likely(x) (__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 1)) +# define likely(x) (__branch_check__(x, 1, __builtin_constant_p(x))) # endif # ifndef unlikely -# define unlikely(x) (__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 0)) +# define unlikely(x) (__branch_check__(x, 0, __builtin_constant_p(x))) # endif #ifdef CONFIG_PROFILE_ALL_BRANCHES @@ -429,10 +436,27 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s # define __attribute_const__ /* unimplemented */ #endif +#ifndef __designated_init +# define __designated_init +#endif + #ifndef __latent_entropy # define __latent_entropy #endif +#ifndef __randomize_layout +# define __randomize_layout __designated_init +#endif + +#ifndef __no_randomize_layout +# define __no_randomize_layout +#endif + +#ifndef randomized_struct_fields_start +# define randomized_struct_fields_start +# define randomized_struct_fields_end +#endif + /* * Tell gcc if a function is cold. The compiler will assume any path * directly leading to the call is unlikely. @@ -566,12 +590,4 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s (_________p1); \ }) -/* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */ -#ifdef CONFIG_KPROBES -# define __kprobes __attribute__((__section__(".kprobes.text"))) -# define nokprobe_inline __always_inline -#else -# define __kprobes -# define nokprobe_inline inline -#endif #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 2319b8c108e8..c96709049683 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -74,7 +74,8 @@ extern void config_item_init_type_name(struct config_item *item, const char *name, struct config_item_type *type); -extern struct config_item * config_item_get(struct config_item *); +extern struct config_item *config_item_get(struct config_item *); +extern struct config_item *config_item_get_unless_zero(struct config_item *); extern void config_item_put(struct config_item *); struct config_item_type { diff --git a/include/linux/console.h b/include/linux/console.h index 9c26c6685587..b8920a031a3e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -73,6 +73,10 @@ struct consw { u16 *(*con_screen_pos)(struct vc_data *, int); unsigned long (*con_getxy)(struct vc_data *, unsigned long, int *, int *); /* + * Flush the video console driver's scrollback buffer + */ + void (*con_flush_scrollback)(struct vc_data *); + /* * Prepare the console for the debugger. This includes, but is not * limited to, unblanking the console, loading an appropriate * palette, and allowing debugger generated output. @@ -208,4 +212,6 @@ extern bool vgacon_text_force(void); static inline bool vgacon_text_force(void) { return false; } #endif +extern void console_init(void); + #endif /* _LINUX_CONSOLE_H */ diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 2a5982c37dfb..d950dad5056a 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -201,7 +201,7 @@ struct coresight_ops_sink { void *sink_config); unsigned long (*reset_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, - void *sink_config, bool *lost); + void *sink_config); void (*update_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config); @@ -263,11 +263,15 @@ static inline int coresight_timeout(void __iomem *addr, u32 offset, #endif #ifdef CONFIG_OF -extern struct coresight_platform_data *of_get_coresight_platform_data( - struct device *dev, struct device_node *node); +extern int of_coresight_get_cpu(const struct device_node *node); +extern struct coresight_platform_data * +of_get_coresight_platform_data(struct device *dev, + const struct device_node *node); #else +static inline int of_coresight_get_cpu(const struct device_node *node) +{ return 0; } static inline struct coresight_platform_data *of_get_coresight_platform_data( - struct device *dev, struct device_node *node) { return NULL; } + struct device *dev, const struct device_node *node) { return NULL; } #endif #ifdef CONFIG_PID_NS diff --git a/include/linux/cper.h b/include/linux/cper.h index dcacb1a72e26..4c671fc2081e 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -180,6 +180,10 @@ enum { #define CPER_SEC_PROC_IPF \ UUID_LE(0xE429FAF1, 0x3CB7, 0x11D4, 0x0B, 0xCA, 0x07, 0x00, \ 0x80, 0xC7, 0x3C, 0x88, 0x81) +/* Processor Specific: ARM */ +#define CPER_SEC_PROC_ARM \ + UUID_LE(0xE19E3D16, 0xBC11, 0x11E4, 0x9C, 0xAA, 0xC2, 0x05, \ + 0x1D, 0x5D, 0x46, 0xB0) /* Platform Memory */ #define CPER_SEC_PLATFORM_MEM \ UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ @@ -255,6 +259,22 @@ enum { #define CPER_PCIE_SLOT_SHIFT 3 +#define CPER_ARM_VALID_MPIDR BIT(0) +#define CPER_ARM_VALID_AFFINITY_LEVEL BIT(1) +#define CPER_ARM_VALID_RUNNING_STATE BIT(2) +#define CPER_ARM_VALID_VENDOR_INFO BIT(3) + +#define CPER_ARM_INFO_VALID_MULTI_ERR BIT(0) +#define CPER_ARM_INFO_VALID_FLAGS BIT(1) +#define CPER_ARM_INFO_VALID_ERR_INFO BIT(2) +#define CPER_ARM_INFO_VALID_VIRT_ADDR BIT(3) +#define CPER_ARM_INFO_VALID_PHYSICAL_ADDR BIT(4) + +#define CPER_ARM_INFO_FLAGS_FIRST BIT(0) +#define CPER_ARM_INFO_FLAGS_LAST BIT(1) +#define CPER_ARM_INFO_FLAGS_PROPAGATED BIT(2) +#define CPER_ARM_INFO_FLAGS_OVERFLOW BIT(3) + /* * All tables and structs must be byte-packed to match CPER * specification, since the tables are provided by the system BIOS @@ -340,6 +360,40 @@ struct cper_ia_proc_ctx { __u64 mm_reg_addr; }; +/* ARM Processor Error Section */ +struct cper_sec_proc_arm { + __u32 validation_bits; + __u16 err_info_num; /* Number of Processor Error Info */ + __u16 context_info_num; /* Number of Processor Context Info Records*/ + __u32 section_length; + __u8 affinity_level; + __u8 reserved[3]; /* must be zero */ + __u64 mpidr; + __u64 midr; + __u32 running_state; /* Bit 0 set - Processor running. PSCI = 0 */ + __u32 psci_state; +}; + +/* ARM Processor Error Information Structure */ +struct cper_arm_err_info { + __u8 version; + __u8 length; + __u16 validation_bits; + __u8 type; + __u16 multiple_error; + __u8 flags; + __u64 error_info; + __u64 virt_fault_addr; + __u64 physical_fault_addr; +}; + +/* ARM Processor Context Information Structure */ +struct cper_arm_ctx_info { + __u16 version; + __u16 type; + __u32 size; +}; + /* Old Memory Error Section UEFI 2.1, 2.2 */ struct cper_sec_mem_err_old { __u64 validation_bits; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 21f9c74496e7..ca73bc1563f4 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -30,6 +30,8 @@ struct cpu { extern void boot_cpu_init(void); extern void boot_cpu_state_init(void); +extern void cpu_init(void); +extern void trap_init(void); extern int register_cpu(struct cpu *cpu, int num); extern struct device *get_cpu_device(unsigned cpu); @@ -97,26 +99,32 @@ static inline void cpu_maps_update_done(void) extern struct bus_type cpu_subsys; #ifdef CONFIG_HOTPLUG_CPU -/* Stop CPUs going up and down. */ - -extern void cpu_hotplug_begin(void); -extern void cpu_hotplug_done(void); -extern void get_online_cpus(void); -extern void put_online_cpus(void); +extern void cpus_write_lock(void); +extern void cpus_write_unlock(void); +extern void cpus_read_lock(void); +extern void cpus_read_unlock(void); +extern void lockdep_assert_cpus_held(void); extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); void clear_tasks_mm_cpumask(int cpu); int cpu_down(unsigned int cpu); -#else /* CONFIG_HOTPLUG_CPU */ - -static inline void cpu_hotplug_begin(void) {} -static inline void cpu_hotplug_done(void) {} -#define get_online_cpus() do { } while (0) -#define put_online_cpus() do { } while (0) -#define cpu_hotplug_disable() do { } while (0) -#define cpu_hotplug_enable() do { } while (0) -#endif /* CONFIG_HOTPLUG_CPU */ +#else /* CONFIG_HOTPLUG_CPU */ + +static inline void cpus_write_lock(void) { } +static inline void cpus_write_unlock(void) { } +static inline void cpus_read_lock(void) { } +static inline void cpus_read_unlock(void) { } +static inline void lockdep_assert_cpus_held(void) { } +static inline void cpu_hotplug_disable(void) { } +static inline void cpu_hotplug_enable(void) { } +#endif /* !CONFIG_HOTPLUG_CPU */ + +/* Wrappers which go away once all code is converted */ +static inline void cpu_hotplug_begin(void) { cpus_write_lock(); } +static inline void cpu_hotplug_done(void) { cpus_write_unlock(); } +static inline void get_online_cpus(void) { cpus_read_lock(); } +static inline void put_online_cpus(void) { cpus_read_unlock(); } #ifdef CONFIG_PM_SLEEP_SMP extern int freeze_secondary_cpus(int primary); diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index c156f5082758..d4292ebc5c8b 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -28,47 +28,49 @@ #include <linux/thermal.h> #include <linux/cpumask.h> +struct cpufreq_policy; + typedef int (*get_static_t)(cpumask_t *cpumask, int interval, unsigned long voltage, u32 *power); #ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy. */ struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus); +cpufreq_cooling_register(struct cpufreq_policy *policy); struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func); /** * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. * @np: a valid struct device_node to the cooling device device tree node. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy. */ #ifdef CONFIG_THERMAL_OF struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus); + struct cpufreq_policy *policy); struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func); #else static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { @@ -82,15 +84,14 @@ of_cpufreq_power_cooling_register(struct device_node *np, */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq); #else /* !CONFIG_CPU_THERMAL */ static inline struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus) +cpufreq_cooling_register(struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { return NULL; @@ -98,14 +99,14 @@ cpufreq_power_cooling_register(const struct cpumask *clip_cpus, static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { @@ -117,11 +118,6 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { return; } -static inline -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq) -{ - return THERMAL_CSTATE_INVALID; -} #endif /* CONFIG_CPU_THERMAL */ #endif /* __CPU_COOLING_H__ */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 7e05c5e4e45c..f10a9b3761cd 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -31,7 +31,7 @@ #define CPUFREQ_ETERNAL (-1) #define CPUFREQ_NAME_LEN 16 -/* Print length for names. Extra 1 space for accomodating '\n' in prints */ +/* Print length for names. Extra 1 space for accommodating '\n' in prints */ #define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1) struct cpufreq_governor; @@ -115,11 +115,18 @@ struct cpufreq_policy { * guarantee that frequency can be changed on any CPU sharing the * policy and that the change will affect all of the policy CPUs then. * - fast_switch_enabled is to be set by governors that support fast - * freqnency switching with the help of cpufreq_enable_fast_switch(). + * frequency switching with the help of cpufreq_enable_fast_switch(). */ bool fast_switch_possible; bool fast_switch_enabled; + /* + * Preferred average time interval between consecutive invocations of + * the driver to set the frequency for this policy. To be set by the + * scaling driver (0, which is the default, means no preference). + */ + unsigned int transition_delay_us; + /* Cached frequency lookup from cpufreq_driver_resolve_freq. */ unsigned int cached_target_freq; int cached_resolved_idx; @@ -415,9 +422,6 @@ static inline void cpufreq_resume(void) {} /* Policy Notifiers */ #define CPUFREQ_ADJUST (0) #define CPUFREQ_NOTIFY (1) -#define CPUFREQ_START (2) -#define CPUFREQ_CREATE_POLICY (3) -#define CPUFREQ_REMOVE_POLICY (4) #ifdef CONFIG_CPU_FREQ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); @@ -858,6 +862,20 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, return -EINVAL; } } + +static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy *policy) +{ + struct cpufreq_frequency_table *pos; + int count = 0; + + if (unlikely(!policy->freq_table)) + return 0; + + cpufreq_for_each_valid_entry(pos, policy->freq_table) + count++; + + return count; +} #else static inline int cpufreq_boost_trigger_state(int state) { @@ -879,6 +897,8 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) } #endif +extern unsigned int arch_freq_get_on_cpu(int cpu); + /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 921acaaa1601..b56573bf440d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -26,7 +26,6 @@ enum cpuhp_state { CPUHP_ARM_OMAP_WAKE_DEAD, CPUHP_IRQ_POLL_DEAD, CPUHP_BLOCK_SOFTIRQ_DEAD, - CPUHP_VIRT_SCSI_DEAD, CPUHP_ACPI_CPUDRV_DEAD, CPUHP_S390_PFAULT_DEAD, CPUHP_BLK_MQ_DEAD, @@ -59,7 +58,6 @@ enum cpuhp_state { CPUHP_XEN_EVTCHN_PREPARE, CPUHP_ARM_SHMOBILE_SCU_PREPARE, CPUHP_SH_SH3X_PREPARE, - CPUHP_BLK_MQ_PREPARE, CPUHP_NET_FLOW_PREPARE, CPUHP_TOPOLOGY_PREPARE, CPUHP_NET_IUCV_PREPARE, @@ -95,6 +93,7 @@ enum cpuhp_state { CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, + CPUHP_AP_PERF_ARM_ACPI_STARTING, CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, @@ -124,6 +123,7 @@ enum cpuhp_state { CPUHP_AP_ONLINE_IDLE, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, + CPUHP_AP_IRQ_AFFINITY_ONLINE, CPUHP_AP_PERF_ONLINE, CPUHP_AP_PERF_X86_ONLINE, CPUHP_AP_PERF_X86_UNCORE_ONLINE, @@ -137,6 +137,8 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, CPUHP_AP_PERF_ARM_L2X0_ONLINE, + CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, + CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, @@ -151,6 +153,11 @@ int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance); +int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, + bool invoke, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu), + bool multi_instance); /** * cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks * @state: The state for which the calls are installed @@ -169,6 +176,15 @@ static inline int cpuhp_setup_state(enum cpuhp_state state, return __cpuhp_setup_state(state, name, true, startup, teardown, false); } +static inline int cpuhp_setup_state_cpuslocked(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + return __cpuhp_setup_state_cpuslocked(state, name, true, startup, + teardown, false); +} + /** * cpuhp_setup_state_nocalls - Setup hotplug state callbacks without calling the * callbacks @@ -189,6 +205,15 @@ static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state, false); } +static inline int cpuhp_setup_state_nocalls_cpuslocked(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + return __cpuhp_setup_state_cpuslocked(state, name, false, startup, + teardown, false); +} + /** * cpuhp_setup_state_multi - Add callbacks for multi state * @state: The state for which the calls are installed @@ -215,6 +240,8 @@ static inline int cpuhp_setup_state_multi(enum cpuhp_state state, int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke); +int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, + struct hlist_node *node, bool invoke); /** * cpuhp_state_add_instance - Add an instance for a state and invoke startup @@ -247,7 +274,15 @@ static inline int cpuhp_state_add_instance_nocalls(enum cpuhp_state state, return __cpuhp_state_add_instance(state, node, false); } +static inline int +cpuhp_state_add_instance_nocalls_cpuslocked(enum cpuhp_state state, + struct hlist_node *node) +{ + return __cpuhp_state_add_instance_cpuslocked(state, node, false); +} + void __cpuhp_remove_state(enum cpuhp_state state, bool invoke); +void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke); /** * cpuhp_remove_state - Remove hotplug state callbacks and invoke the teardown @@ -271,6 +306,11 @@ static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state) __cpuhp_remove_state(state, false); } +static inline void cpuhp_remove_state_nocalls_cpuslocked(enum cpuhp_state state) +{ + __cpuhp_remove_state_cpuslocked(state, false); +} + /** * cpuhp_remove_multi_state - Remove hotplug multi state callback * @state: The state for which the calls are removed diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index da346f2817a8..fc1e5d7fc1c7 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -62,6 +62,7 @@ struct cpuidle_state { }; /* Idle State Flags */ +#define CPUIDLE_FLAG_NONE (0x00) #define CPUIDLE_FLAG_COUPLED (0x02) /* state applies to multiple cpus */ #define CPUIDLE_FLAG_TIMER_STOP (0x04) /* timer is stopped on this state */ diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b3d2c1a89ac4..4bf4479a3a80 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -40,9 +40,9 @@ extern int nr_cpu_ids; #ifdef CONFIG_CPUMASK_OFFSTACK /* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, * not all bits may be allocated. */ -#define nr_cpumask_bits nr_cpu_ids +#define nr_cpumask_bits ((unsigned int)nr_cpu_ids) #else -#define nr_cpumask_bits NR_CPUS +#define nr_cpumask_bits ((unsigned int)NR_CPUS) #endif /* @@ -236,6 +236,23 @@ unsigned int cpumask_local_spread(unsigned int i, int node); (cpu) = cpumask_next_zero((cpu), (mask)), \ (cpu) < nr_cpu_ids;) +extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); + +/** + * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location + * @cpu: the (optionally unsigned) integer iterator + * @mask: the cpumask poiter + * @start: the start location + * + * The implementation does not assume any bit in @mask is set (including @start). + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_wrap(cpu, mask, start) \ + for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false); \ + (cpu) < nr_cpumask_bits; \ + (cpu) = cpumask_next_wrap((cpu), (mask), (start), true)) + /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator @@ -276,6 +293,12 @@ static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } +static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +{ + __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); +} + + /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) @@ -286,6 +309,11 @@ static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } +static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) +{ + __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); +} + /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) @@ -649,11 +677,15 @@ static inline size_t cpumask_size(void) * used. Please use this_cpu_cpumask_var_t in those cases. The direct use * of this_cpu_ptr() or this_cpu_read() will lead to failures when the * other type of cpumask_var_t implementation is configured. + * + * Please also note that __cpumask_var_read_mostly can be used to declare + * a cpumask_var_t variable itself (not its content) as read mostly. */ #ifdef CONFIG_CPUMASK_OFFSTACK typedef struct cpumask *cpumask_var_t; -#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) +#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) +#define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); @@ -663,10 +695,16 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); +static inline bool cpumask_available(cpumask_var_t mask) +{ + return mask != NULL; +} + #else typedef struct cpumask cpumask_var_t[1]; #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) +#define __cpumask_var_read_mostly static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { @@ -703,6 +741,11 @@ static inline void free_cpumask_var(cpumask_var_t mask) static inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } + +static inline bool cpumask_available(cpumask_var_t mask) +{ + return true; +} #endif /* CONFIG_CPUMASK_OFFSTACK */ /* It's common to want to use cpu_all_mask in struct member initializers, diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index bfc204e70338..119a3f9604b0 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -9,6 +9,8 @@ */ #include <linux/sched.h> +#include <linux/sched/topology.h> +#include <linux/sched/task.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> @@ -40,7 +42,7 @@ static inline void cpuset_dec(void) extern int cpuset_init(void); extern void cpuset_init_smp(void); -extern void cpuset_update_active_cpus(bool cpu_online); +extern void cpuset_update_active_cpus(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern void cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -153,7 +155,7 @@ static inline bool cpusets_enabled(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} -static inline void cpuset_update_active_cpus(bool cpu_online) +static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } diff --git a/include/linux/cputime.h b/include/linux/cputime.h deleted file mode 100644 index f2eb2ee535ca..000000000000 --- a/include/linux/cputime.h +++ /dev/null @@ -1,16 +0,0 @@ -#ifndef __LINUX_CPUTIME_H -#define __LINUX_CPUTIME_H - -#include <asm/cputime.h> - -#ifndef cputime_to_nsecs -# define cputime_to_nsecs(__ct) \ - (cputime_to_usecs(__ct) * NSEC_PER_USEC) -#endif - -#ifndef nsecs_to_cputime -# define nsecs_to_cputime(__nsecs) \ - usecs_to_cputime((__nsecs) / NSEC_PER_USEC) -#endif - -#endif /* __LINUX_CPUTIME_H */ diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h new file mode 100644 index 000000000000..2df2118fbe13 --- /dev/null +++ b/include/linux/crash_core.h @@ -0,0 +1,73 @@ +#ifndef LINUX_CRASH_CORE_H +#define LINUX_CRASH_CORE_H + +#include <linux/linkage.h> +#include <linux/elfcore.h> +#include <linux/elf.h> + +#define CRASH_CORE_NOTE_NAME "CORE" +#define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) +#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4) +#define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4) + +/* + * The per-cpu notes area is a list of notes terminated by a "NULL" + * note header. For kdump, the code in vmcore.c runs in the context + * of the second kernel to combine them into one note. + */ +#define CRASH_CORE_NOTE_BYTES ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ + CRASH_CORE_NOTE_NAME_BYTES + \ + CRASH_CORE_NOTE_DESC_BYTES) + +#define VMCOREINFO_BYTES PAGE_SIZE +#define VMCOREINFO_NOTE_NAME "VMCOREINFO" +#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) +#define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ + VMCOREINFO_NOTE_NAME_BYTES + \ + VMCOREINFO_BYTES) + +typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4]; + +void crash_update_vmcoreinfo_safecopy(void *ptr); +void crash_save_vmcoreinfo(void); +void arch_crash_save_vmcoreinfo(void); +__printf(1, 2) +void vmcoreinfo_append_str(const char *fmt, ...); +phys_addr_t paddr_vmcoreinfo_note(void); + +#define VMCOREINFO_OSRELEASE(value) \ + vmcoreinfo_append_str("OSRELEASE=%s\n", value) +#define VMCOREINFO_PAGESIZE(value) \ + vmcoreinfo_append_str("PAGESIZE=%ld\n", value) +#define VMCOREINFO_SYMBOL(name) \ + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) +#define VMCOREINFO_SIZE(name) \ + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ + (unsigned long)sizeof(name)) +#define VMCOREINFO_STRUCT_SIZE(name) \ + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ + (unsigned long)sizeof(struct name)) +#define VMCOREINFO_OFFSET(name, field) \ + vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ + (unsigned long)offsetof(struct name, field)) +#define VMCOREINFO_LENGTH(name, value) \ + vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) +#define VMCOREINFO_NUMBER(name) \ + vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) +#define VMCOREINFO_CONFIG(name) \ + vmcoreinfo_append_str("CONFIG_%s=y\n", #name) + +extern u32 *vmcoreinfo_note; + +Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, + void *data, size_t data_len); +void final_note(Elf_Word *buf); + +int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); +int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); +int parse_crashkernel_low(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); + +#endif /* LINUX_CRASH_CORE_H */ diff --git a/include/linux/crc4.h b/include/linux/crc4.h new file mode 100644 index 000000000000..8f739f1d794f --- /dev/null +++ b/include/linux/crc4.h @@ -0,0 +1,8 @@ +#ifndef _LINUX_CRC4_H +#define _LINUX_CRC4_H + +#include <linux/types.h> + +extern uint8_t crc4(uint8_t c, uint64_t x, int bits); + +#endif /* _LINUX_CRC4_H */ diff --git a/include/linux/cred.h b/include/linux/cred.h index f0e70a1bb3ac..099058e1178b 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -1,4 +1,4 @@ -/* Credentials management - see Documentation/security/credentials.txt +/* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) @@ -18,8 +18,9 @@ #include <linux/selinux.h> #include <linux/atomic.h> #include <linux/uidgid.h> +#include <linux/sched.h> +#include <linux/sched/user.h> -struct user_struct; struct cred; struct inode; @@ -30,7 +31,7 @@ struct group_info { atomic_t usage; int ngroups; kgid_t gid[0]; -}; +} __randomize_layout; /** * get_group_info - Get a reference to a group info structure @@ -144,7 +145,7 @@ struct cred { struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ struct rcu_head rcu; /* RCU deletion hook */ -}; +} __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index be8f12b8f195..92e165d417a6 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -2,6 +2,7 @@ #define CEPH_CRUSH_CRUSH_H #ifdef __KERNEL__ +# include <linux/rbtree.h> # include <linux/types.h> #else # include "crush_compat.h" @@ -135,13 +136,68 @@ struct crush_bucket { __u32 size; /* num items */ __s32 *items; - /* - * cached random permutation: used for uniform bucket and for - * the linear search fallback for the other bucket types. - */ - __u32 perm_x; /* @x for which *perm is defined */ - __u32 perm_n; /* num elements of *perm that are permuted/defined */ - __u32 *perm; +}; + +/** @ingroup API + * + * Replacement weights for each item in a bucket. The size of the + * array must be exactly the size of the straw2 bucket, just as the + * item_weights array. + * + */ +struct crush_weight_set { + __u32 *weights; /*!< 16.16 fixed point weights + in the same order as items */ + __u32 size; /*!< size of the __weights__ array */ +}; + +/** @ingroup API + * + * Replacement weights and ids for a given straw2 bucket, for + * placement purposes. + * + * When crush_do_rule() chooses the Nth item from a straw2 bucket, the + * replacement weights found at __weight_set[N]__ are used instead of + * the weights from __item_weights__. If __N__ is greater than + * __weight_set_size__, the weights found at __weight_set_size-1__ are + * used instead. For instance if __weight_set__ is: + * + * [ [ 0x10000, 0x20000 ], // position 0 + * [ 0x20000, 0x40000 ] ] // position 1 + * + * choosing the 0th item will use position 0 weights [ 0x10000, 0x20000 ] + * choosing the 1th item will use position 1 weights [ 0x20000, 0x40000 ] + * choosing the 2th item will use position 1 weights [ 0x20000, 0x40000 ] + * etc. + * + */ +struct crush_choose_arg { + __s32 *ids; /*!< values to use instead of items */ + __u32 ids_size; /*!< size of the __ids__ array */ + struct crush_weight_set *weight_set; /*!< weight replacements for + a given position */ + __u32 weight_set_size; /*!< size of the __weight_set__ array */ +}; + +/** @ingroup API + * + * Replacement weights and ids for each bucket in the crushmap. The + * __size__ of the __args__ array must be exactly the same as the + * __map->max_buckets__. + * + * The __crush_choose_arg__ at index N will be used when choosing + * an item from the bucket __map->buckets[N]__ bucket, provided it + * is a straw2 bucket. + * + */ +struct crush_choose_arg_map { +#ifdef __KERNEL__ + struct rb_node node; + u64 choose_args_index; +#endif + struct crush_choose_arg *args; /*!< replacement for each bucket + in the crushmap */ + __u32 size; /*!< size of the __args__ array */ }; struct crush_bucket_uniform { @@ -211,6 +267,21 @@ struct crush_map { * device fails. */ __u8 chooseleaf_stable; + /* + * This value is calculated after decode or construction by + * the builder. It is exposed here (rather than having a + * 'build CRUSH working space' function) so that callers can + * reserve a static buffer, allocate space on the stack, or + * otherwise avoid calling into the heap allocator if they + * want to. The size of the working space depends on the map, + * while the size of the scratch vector passed to the mapper + * depends on the size of the desired result set. + * + * Nothing stops the caller from allocating both in one swell + * foop and passing in two points, though. + */ + size_t working_size; + #ifndef __KERNEL__ /* * version 0 (original) of straw_calc has various flaws. version 1 @@ -228,6 +299,9 @@ struct crush_map { __u32 allowed_bucket_algs; __u32 *choose_tries; +#else + /* CrushWrapper::choose_args */ + struct rb_root choose_args; #endif }; @@ -248,4 +322,23 @@ static inline int crush_calc_tree_node(int i) return ((i+1) << 1)-1; } +/* + * These data structures are private to the CRUSH implementation. They + * are exposed in this header file because builder needs their + * definitions to calculate the total working size. + * + * Moving this out of the crush map allow us to treat the CRUSH map as + * immutable within the mapper and removes the requirement for a CRUSH + * map lock. + */ +struct crush_work_bucket { + __u32 perm_x; /* @x for which *perm is defined */ + __u32 perm_n; /* num elements of *perm that are permuted/defined */ + __u32 *perm; /* Permutation of the bucket's items */ +}; + +struct crush_work { + struct crush_work_bucket **work; /* Per-bucket working store */ +}; + #endif diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h index 5dfd5b1125d2..141edabb947e 100644 --- a/include/linux/crush/mapper.h +++ b/include/linux/crush/mapper.h @@ -11,10 +11,23 @@ #include "crush.h" extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size); -extern int crush_do_rule(const struct crush_map *map, - int ruleno, - int x, int *result, int result_max, - const __u32 *weights, int weight_max, - int *scratch); +int crush_do_rule(const struct crush_map *map, + int ruleno, int x, int *result, int result_max, + const __u32 *weight, int weight_max, + void *cwin, const struct crush_choose_arg *choose_args); + +/* + * Returns the exact amount of workspace that will need to be used + * for a given combination of crush_map and result_max. The caller can + * then allocate this much on its own, either on the stack, in a + * per-thread long-lived buffer, or however it likes. + */ +static inline size_t crush_work_size(const struct crush_map *map, + int result_max) +{ + return map->working_size + result_max * 3 * sizeof(__u32); +} + +void crush_init_workspace(const struct crush_map *map, void *v); #endif diff --git a/include/linux/crypto.h b/include/linux/crypto.h index c0b0cf3d2d2f..84da9978e951 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -123,7 +123,7 @@ /* * Miscellaneous stuff. */ -#define CRYPTO_MAX_ALG_NAME 64 +#define CRYPTO_MAX_ALG_NAME 128 /* * The macro CRYPTO_MINALIGN_ATTR (along with the void * type in the actual diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h index f4754282c9c2..df4d3e943d28 100644 --- a/include/linux/cryptohash.h +++ b/include/linux/cryptohash.h @@ -10,11 +10,4 @@ void sha_init(__u32 *buf); void sha_transform(__u32 *digest, const char *data, __u32 *W); -#define MD5_DIGEST_WORDS 4 -#define MD5_MESSAGE_BYTES 64 - -void md5_transform(__u32 *hash, __u32 const *in); - -__u32 half_md4_transform(__u32 buf[4], __u32 const in[8]); - #endif diff --git a/include/linux/dax.h b/include/linux/dax.h index 24ad71173995..794811875732 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -7,6 +7,86 @@ #include <asm/pgtable.h> struct iomap_ops; +struct dax_device; +struct dax_operations { + /* + * direct_access: translate a device-relative + * logical-page-offset into an absolute physical pfn. Return the + * number of pages available for DAX at that pfn. + */ + long (*direct_access)(struct dax_device *, pgoff_t, long, + void **, pfn_t *); + /* copy_from_iter: required operation for fs-dax direct-i/o */ + size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, + struct iov_iter *); + /* flush: optional driver-specific cache management after writes */ + void (*flush)(struct dax_device *, pgoff_t, void *, size_t); +}; + +extern struct attribute_group dax_attribute_group; + +#if IS_ENABLED(CONFIG_DAX) +struct dax_device *dax_get_by_host(const char *host); +void put_dax(struct dax_device *dax_dev); +#else +static inline struct dax_device *dax_get_by_host(const char *host) +{ + return NULL; +} + +static inline void put_dax(struct dax_device *dax_dev) +{ +} +#endif + +int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); +#if IS_ENABLED(CONFIG_FS_DAX) +int __bdev_dax_supported(struct super_block *sb, int blocksize); +static inline int bdev_dax_supported(struct super_block *sb, int blocksize) +{ + return __bdev_dax_supported(sb, blocksize); +} + +static inline struct dax_device *fs_dax_get_by_host(const char *host) +{ + return dax_get_by_host(host); +} + +static inline void fs_put_dax(struct dax_device *dax_dev) +{ + put_dax(dax_dev); +} + +#else +static inline int bdev_dax_supported(struct super_block *sb, int blocksize) +{ + return -EOPNOTSUPP; +} + +static inline struct dax_device *fs_dax_get_by_host(const char *host) +{ + return NULL; +} + +static inline void fs_put_dax(struct dax_device *dax_dev) +{ +} +#endif + +int dax_read_lock(void); +void dax_read_unlock(int id); +struct dax_device *alloc_dax(void *private, const char *host, + const struct dax_operations *ops); +bool dax_alive(struct dax_device *dax_dev); +void kill_dax(struct dax_device *dax_dev); +void *dax_get_private(struct dax_device *dax_dev); +long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, + void **kaddr, pfn_t *pfn); +size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t bytes, struct iov_iter *i); +void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t size); +void dax_write_cache(struct dax_device *dax_dev, bool wc); /* * We use lowest available bit in exceptional entry for locking, one bit for @@ -37,28 +117,23 @@ static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags) } ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, - struct iomap_ops *ops); -int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf, - struct iomap_ops *ops); + const struct iomap_ops *ops); +int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, + const struct iomap_ops *ops); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); -int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); void dax_wake_mapping_entry_waiter(struct address_space *mapping, pgoff_t index, void *entry, bool wake_all); #ifdef CONFIG_FS_DAX -struct page *read_dax_sector(struct block_device *bdev, sector_t n); -int __dax_zero_page_range(struct block_device *bdev, sector_t sector, +int __dax_zero_page_range(struct block_device *bdev, + struct dax_device *dax_dev, sector_t sector, unsigned int offset, unsigned int length); #else -static inline struct page *read_dax_sector(struct block_device *bdev, - sector_t n) -{ - return ERR_PTR(-ENXIO); -} static inline int __dax_zero_page_range(struct block_device *bdev, - sector_t sector, unsigned int offset, unsigned int length) + struct dax_device *dax_dev, sector_t sector, + unsigned int offset, unsigned int length) { return -ENXIO; } @@ -71,26 +146,13 @@ static inline unsigned int dax_radix_order(void *entry) return PMD_SHIFT - PAGE_SHIFT; return 0; } -int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmd, unsigned int flags, struct iomap_ops *ops); #else static inline unsigned int dax_radix_order(void *entry) { return 0; } -static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, unsigned int flags, - struct iomap_ops *ops) -{ - return VM_FAULT_FALLBACK; -} #endif -int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); - -static inline bool vma_is_dax(struct vm_area_struct *vma) -{ - return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); -} +int dax_pfn_mkwrite(struct vm_fault *vmf); static inline bool dax_mapping(struct address_space *mapping) { diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c965e4469499..aae1cdb76851 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -11,6 +11,7 @@ #include <linux/rcupdate.h> #include <linux/lockref.h> #include <linux/stringhash.h> +#include <linux/wait.h> struct path; struct vfsmount; @@ -54,6 +55,11 @@ struct qstr { #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } +extern const char empty_string[]; +extern const struct qstr empty_name; +extern const char slash_string[]; +extern const struct qstr slash_name; + struct dentry_stat_t { long nr_dentry; long nr_unused; @@ -112,7 +118,7 @@ struct dentry { struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; -}; +} __randomize_layout; /* * dentry->d_lock spinlock nesting subclasses: @@ -562,7 +568,7 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) * @inode: inode to select the dentry from multiple layers (can be NULL) * @flags: open flags to control copy-up behavior * - * If dentry is on an union/overlay, then return the underlying, real dentry. + * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. * * See also: Documentation/filesystems/vfs.txt @@ -581,7 +587,7 @@ static inline struct dentry *d_real(struct dentry *dentry, * d_real_inode - Return the real inode * @dentry: The dentry to query * - * If dentry is on an union/overlay, then return the underlying, real inode. + * If dentry is on a union/overlay, then return the underlying, real inode. * Otherwise return d_inode(). */ static inline struct inode *d_real_inode(const struct dentry *dentry) @@ -590,5 +596,11 @@ static inline struct inode *d_real_inode(const struct dentry *dentry) return d_backing_inode(d_real((struct dentry *) dentry, NULL, 0)); } +struct name_snapshot { + const unsigned char *name; + unsigned char inline_name[DNAME_INLINE_LEN]; +}; +void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); +void release_dentry_name_snapshot(struct name_snapshot *); #endif /* __LINUX_DCACHE_H */ diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 61d042bbbf60..68449293c4b6 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -163,6 +163,7 @@ struct dccp_request_sock { __u64 dreq_isr; __u64 dreq_gsr; __be32 dreq_service; + spinlock_t dreq_lock; struct list_head dreq_featneg; __u32 dreq_timestamp_echo; __u32 dreq_timestamp_time; diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 014cc564d1c4..aa86e6d8c1aa 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -9,7 +9,7 @@ * 2 as published by the Free Software Foundation. * * debugfs is for people to use instead of /proc or /sys. - * See Documentation/DocBook/filesystems for more details. + * See Documentation/filesystems/ for more details. */ #ifndef _DEBUGFS_H_ @@ -52,8 +52,7 @@ extern struct srcu_struct debugfs_srcu; * Must only be called under the protection established by * debugfs_use_file_start(). */ -static inline const struct file_operations * -debugfs_real_fops(const struct file *filp) +static inline const struct file_operations *debugfs_real_fops(const struct file *filp) __must_hold(&debugfs_srcu) { /* @@ -75,11 +74,13 @@ static const struct file_operations __fops = { \ .release = simple_attr_release, \ .read = debugfs_attr_read, \ .write = debugfs_attr_write, \ - .llseek = generic_file_llseek, \ + .llseek = no_llseek, \ } #if defined(CONFIG_DEBUG_FS) +struct dentry *debugfs_lookup(const char *name, struct dentry *parent); + struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); @@ -97,9 +98,10 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent); struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *dest); +typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, - struct vfsmount *(*f)(void *), + debugfs_automount_t f, void *data); void debugfs_remove(struct dentry *dentry); @@ -181,6 +183,12 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, * want to duplicate the design decision mistakes of procfs and devfs again. */ +static inline struct dentry *debugfs_lookup(const char *name, + struct dentry *parent) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) diff --git a/include/linux/delay.h b/include/linux/delay.h index a6ecb34cf547..2ecb3c46b20a 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -5,6 +5,17 @@ * Copyright (C) 1993 Linus Torvalds * * Delay routines, using a pre-computed "loops_per_jiffy" value. + * + * Please note that ndelay(), udelay() and mdelay() may return early for + * several reasons: + * 1. computed loops_per_jiffy too low (due to the time taken to + * execute the timer interrupt.) + * 2. cache behaviour affecting the time it takes to execute the + * loop function. + * 3. CPU clock rate changes. + * + * Please see this thread: + * http://lists.openwall.net/linux-kernel/2011/01/09/56 */ #include <linux/kernel.h> diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 6cee17c22313..4178d2493547 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -17,8 +17,7 @@ #ifndef _LINUX_DELAYACCT_H #define _LINUX_DELAYACCT_H -#include <linux/sched.h> -#include <linux/slab.h> +#include <uapi/linux/taskstats.h> /* * Per-task flags relevant to delay accounting @@ -29,7 +28,43 @@ #define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */ #ifdef CONFIG_TASK_DELAY_ACCT +struct task_delay_info { + spinlock_t lock; + unsigned int flags; /* Private per-task flags */ + + /* For each stat XXX, add following, aligned appropriately + * + * struct timespec XXX_start, XXX_end; + * u64 XXX_delay; + * u32 XXX_count; + * + * Atomicity of updates to XXX_delay, XXX_count protected by + * single lock above (split into XXX_lock if contention is an issue). + */ + + /* + * XXX_count is incremented on every XXX operation, the delay + * associated with the operation is added to XXX_delay. + * XXX_delay contains the accumulated delay time in nanoseconds. + */ + u64 blkio_start; /* Shared by blkio, swapin */ + u64 blkio_delay; /* wait for sync block io completion */ + u64 swapin_delay; /* wait for swapin block io completion */ + u32 blkio_count; /* total count of the number of sync block */ + /* io operations performed */ + u32 swapin_count; /* total count of the number of swapin block */ + /* io operations performed */ + + u64 freepages_start; + u64 freepages_delay; /* wait for memory reclaim */ + u32 freepages_count; /* total count of memory reclaim */ +}; +#endif +#include <linux/sched.h> +#include <linux/slab.h> + +#ifdef CONFIG_TASK_DELAY_ACCT extern int delayacct_on; /* Delay accounting turned on/off */ extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); diff --git a/include/linux/dell-led.h b/include/linux/dell-led.h index 7009b8bec77b..3f033c48071e 100644 --- a/include/linux/dell-led.h +++ b/include/linux/dell-led.h @@ -1,10 +1,6 @@ #ifndef __DELL_LED_H__ #define __DELL_LED_H__ -enum { - DELL_LED_MICMUTE, -}; - -int dell_app_wmi_led_set(int whichled, int on); +int dell_micmute_led_set(int on); #endif diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 2de4e2eea180..6c220e4ebb6b 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -27,6 +27,7 @@ #define DEVFREQ_POSTCHANGE (1) struct devfreq; +struct devfreq_governor; /** * struct devfreq_dev_status - Data given from devfreq user device to @@ -101,32 +102,6 @@ struct devfreq_dev_profile { }; /** - * struct devfreq_governor - Devfreq policy governor - * @node: list node - contains registered devfreq governors - * @name: Governor's name - * @get_target_freq: Returns desired operating frequency for the device. - * Basically, get_target_freq will run - * devfreq_dev_profile.get_dev_status() to get the - * status of the device (load = busy_time / total_time). - * If no_central_polling is set, this callback is called - * only with update_devfreq() notified by OPP. - * @event_handler: Callback for devfreq core framework to notify events - * to governors. Events include per device governor - * init and exit, opp changes out of devfreq, suspend - * and resume of per device devfreq during device idle. - * - * Note that the callbacks are called with devfreq->lock locked by devfreq. - */ -struct devfreq_governor { - struct list_head node; - - const char name[DEVFREQ_NAME_LEN]; - int (*get_target_freq)(struct devfreq *this, unsigned long *freq); - int (*event_handler)(struct devfreq *devfreq, - unsigned int event, void *data); -}; - -/** * struct devfreq - Device devfreq structure * @node: list node - contains the devices with devfreq that have been * registered. diff --git a/include/linux/devfreq_cooling.h b/include/linux/devfreq_cooling.h index c35d0c0e0ada..4635f95000a4 100644 --- a/include/linux/devfreq_cooling.h +++ b/include/linux/devfreq_cooling.h @@ -34,6 +34,23 @@ * If get_dynamic_power() is NULL, then the * dynamic power is calculated as * @dyn_power_coeff * frequency * voltage^2 + * @get_real_power: When this is set, the framework uses it to ask the + * device driver for the actual power. + * Some devices have more sophisticated methods + * (like power counters) to approximate the actual power + * that they use. + * This function provides more accurate data to the + * thermal governor. When the driver does not provide + * such function, framework just uses pre-calculated + * table and scale the power by 'utilization' + * (based on 'busy_time' and 'total_time' taken from + * devfreq 'last_status'). + * The value returned by this function must be lower + * or equal than the maximum power value + * for the current state + * (which can be found in power_table[state]). + * When this interface is used, the power_table holds + * max total (static + dynamic) power value for each OPP. */ struct devfreq_cooling_power { unsigned long (*get_static_power)(struct devfreq *devfreq, @@ -41,6 +58,8 @@ struct devfreq_cooling_power { unsigned long (*get_dynamic_power)(struct devfreq *devfreq, unsigned long freq, unsigned long voltage); + int (*get_real_power)(struct devfreq *df, u32 *power, + unsigned long freq, unsigned long voltage); unsigned long dyn_power_coeff; }; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index ef7962e84444..1473455d0341 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -22,11 +22,13 @@ struct bio_vec; /* * Type of table, mapped_device's mempool and request_queue */ -#define DM_TYPE_NONE 0 -#define DM_TYPE_BIO_BASED 1 -#define DM_TYPE_REQUEST_BASED 2 -#define DM_TYPE_MQ_REQUEST_BASED 3 -#define DM_TYPE_DAX_BIO_BASED 4 +enum dm_queue_mode { + DM_TYPE_NONE = 0, + DM_TYPE_BIO_BASED = 1, + DM_TYPE_REQUEST_BASED = 2, + DM_TYPE_MQ_REQUEST_BASED = 3, + DM_TYPE_DAX_BIO_BASED = 4, +}; typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t; @@ -55,8 +57,6 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti); * = 2: The target wants to push back the io */ typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio); -typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone, - union map_info *map_context); typedef int (*dm_clone_and_map_request_fn) (struct dm_target *ti, struct request *rq, union map_info *map_context, @@ -72,9 +72,9 @@ typedef void (*dm_release_clone_request_fn) (struct request *clone); * 2 : The target wants to push back the io */ typedef int (*dm_endio_fn) (struct dm_target *ti, - struct bio *bio, int error); + struct bio *bio, blk_status_t *error); typedef int (*dm_request_endio_fn) (struct dm_target *ti, - struct request *clone, int error, + struct request *clone, blk_status_t error, union map_info *map_context); typedef void (*dm_presuspend_fn) (struct dm_target *ti); @@ -130,13 +130,19 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); * < 0 : error * >= 0 : the number of bytes accessible at the address */ -typedef long (*dm_direct_access_fn) (struct dm_target *ti, sector_t sector, - void **kaddr, pfn_t *pfn, long size); +typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn); +typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); +typedef void (*dm_dax_flush_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, + size_t size); +#define PAGE_SECTORS (PAGE_SIZE / 512) void dm_error(const char *message); struct dm_dev { struct block_device *bdev; + struct dax_device *dax_dev; fmode_t mode; char name[16]; }; @@ -163,7 +169,6 @@ struct target_type { dm_ctr_fn ctr; dm_dtr_fn dtr; dm_map_fn map; - dm_map_request_fn map_rq; dm_clone_and_map_request_fn clone_and_map_rq; dm_release_clone_request_fn release_clone_rq; dm_endio_fn end_io; @@ -179,7 +184,9 @@ struct target_type { dm_busy_fn busy; dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; - dm_direct_access_fn direct_access; + dm_dax_direct_access_fn direct_access; + dm_dax_copy_from_iter_fn dax_copy_from_iter; + dm_dax_flush_fn dax_flush; /* For internal device-mapper use. */ struct list_head list; @@ -224,6 +231,24 @@ struct target_type { */ typedef unsigned (*dm_num_write_bios_fn) (struct dm_target *ti, struct bio *bio); +/* + * A target implements own bio data integrity. + */ +#define DM_TARGET_INTEGRITY 0x00000010 +#define dm_target_has_integrity(type) ((type)->features & DM_TARGET_INTEGRITY) + +/* + * A target passes integrity data to the lower device. + */ +#define DM_TARGET_PASSES_INTEGRITY 0x00000020 +#define dm_target_passes_integrity(type) ((type)->features & DM_TARGET_PASSES_INTEGRITY) + +/* + * Indicates that a target supports host-managed zoned block devices. + */ +#define DM_TARGET_ZONED_HM 0x00000040 +#define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM) + struct dm_target { struct dm_table *table; struct target_type *type; @@ -258,6 +283,12 @@ struct dm_target { unsigned num_write_same_bios; /* + * The number of WRITE ZEROES bios that will be submitted to the target. + * The bio number can be accessed with dm_bio_get_target_bio_nr. + */ + unsigned num_write_zeroes_bios; + + /* * The minimum number of extra bytes allocated in each io for the * target to use. */ @@ -293,11 +324,6 @@ struct dm_target { * on max_io_len boundary. */ bool split_discard_bios:1; - - /* - * Set if this target does not return zeroes on discarded blocks. - */ - bool discard_zeroes_data_unsupported:1; }; /* Each target can link one of these into the table */ @@ -430,6 +456,8 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); +void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, + sector_t start); union map_info *dm_get_rq_mapinfo(struct request *rq); struct queue_limits *dm_get_queue_limits(struct mapped_device *md); @@ -467,7 +495,7 @@ void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callback * Useful for "hybrid" target (supports both bio-based * and request-based). */ -void dm_table_set_type(struct dm_table *t, unsigned type); +void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type); /* * Finally call this to make the table ready for use. @@ -529,48 +557,41 @@ extern struct ratelimit_state dm_ratelimit_state; #define dm_ratelimit() 0 #endif -#define DMCRIT(f, arg...) \ - printk(KERN_CRIT DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) - -#define DMERR(f, arg...) \ - printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) -#define DMERR_LIMIT(f, arg...) \ - do { \ - if (dm_ratelimit()) \ - printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " \ - f "\n", ## arg); \ - } while (0) - -#define DMWARN(f, arg...) \ - printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) -#define DMWARN_LIMIT(f, arg...) \ - do { \ - if (dm_ratelimit()) \ - printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " \ - f "\n", ## arg); \ - } while (0) - -#define DMINFO(f, arg...) \ - printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) -#define DMINFO_LIMIT(f, arg...) \ - do { \ - if (dm_ratelimit()) \ - printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f \ - "\n", ## arg); \ - } while (0) +#define DM_FMT(fmt) DM_NAME ": " DM_MSG_PREFIX ": " fmt "\n" + +#define DMCRIT(fmt, ...) pr_crit(DM_FMT(fmt), ##__VA_ARGS__) + +#define DMERR(fmt, ...) pr_err(DM_FMT(fmt), ##__VA_ARGS__) +#define DMERR_LIMIT(fmt, ...) \ +do { \ + if (dm_ratelimit()) \ + DMERR(fmt, ##__VA_ARGS__); \ +} while (0) + +#define DMWARN(fmt, ...) pr_warn(DM_FMT(fmt), ##__VA_ARGS__) +#define DMWARN_LIMIT(fmt, ...) \ +do { \ + if (dm_ratelimit()) \ + DMWARN(fmt, ##__VA_ARGS__); \ +} while (0) + +#define DMINFO(fmt, ...) pr_info(DM_FMT(fmt), ##__VA_ARGS__) +#define DMINFO_LIMIT(fmt, ...) \ +do { \ + if (dm_ratelimit()) \ + DMINFO(fmt, ##__VA_ARGS__); \ +} while (0) #ifdef CONFIG_DM_DEBUG -# define DMDEBUG(f, arg...) \ - printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX " DEBUG: " f "\n", ## arg) -# define DMDEBUG_LIMIT(f, arg...) \ - do { \ - if (dm_ratelimit()) \ - printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX ": " f \ - "\n", ## arg); \ - } while (0) +#define DMDEBUG(fmt, ...) printk(KERN_DEBUG DM_FMT(fmt), ##__VA_ARGS__) +#define DMDEBUG_LIMIT(fmt, ...) \ +do { \ + if (dm_ratelimit()) \ + DMDEBUG(fmt, ##__VA_ARGS__); \ +} while (0) #else -# define DMDEBUG(f, arg...) do {} while (0) -# define DMDEBUG_LIMIT(f, arg...) do {} while (0) +#define DMDEBUG(fmt, ...) no_printk(fmt, ##__VA_ARGS__) +#define DMDEBUG_LIMIT(fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif #define DMEMIT(x...) sz += ((sz >= maxlen) ? \ @@ -581,6 +602,7 @@ extern struct ratelimit_state dm_ratelimit_state; /* * Definitions of return values from target end_io function. */ +#define DM_ENDIO_DONE 0 #define DM_ENDIO_INCOMPLETE 1 #define DM_ENDIO_REQUEUE 2 @@ -591,6 +613,7 @@ extern struct ratelimit_state dm_ratelimit_state; #define DM_MAPIO_REMAPPED 1 #define DM_MAPIO_REQUEUE DM_ENDIO_REQUEUE #define DM_MAPIO_DELAY_REQUEUE 3 +#define DM_MAPIO_KILL 4 #define dm_sector_div64(x, y)( \ { \ diff --git a/include/linux/device.h b/include/linux/device.h index 491b4c0ca633..723cd54b94da 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -66,7 +66,6 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @name: The name of the bus. * @dev_name: Used for subsystems to enumerate devices like ("foo%u", dev->id). * @dev_root: Default device to use as the parent. - * @dev_attrs: Default attributes of the devices on the bus. * @bus_groups: Default attributes of the bus. * @dev_groups: Default attributes of the devices on the bus. * @drv_groups: Default attributes of the device drivers on the bus. @@ -88,6 +87,8 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * * @suspend: Called when a device on this bus wants to go to sleep mode. * @resume: Called to bring a device on this bus out of sleep mode. + * @num_vf: Called to find out how many virtual functions a device on this + * bus supports. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU @@ -110,7 +111,6 @@ struct bus_type { const char *name; const char *dev_name; struct device *dev_root; - struct device_attribute *dev_attrs; /* use dev_groups instead */ const struct attribute_group **bus_groups; const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; @@ -127,6 +127,8 @@ struct bus_type { int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); + int (*num_vf)(struct device *dev); + const struct dev_pm_ops *pm; const struct iommu_ops *iommu_ops; @@ -361,7 +363,6 @@ int subsys_virtual_register(struct bus_type *subsys, * struct class - device classes * @name: Name of the class. * @owner: The module owner. - * @class_attrs: Default attributes of this class. * @class_groups: Default attributes of this class. * @dev_groups: Default attributes of the devices that belong to the class. * @dev_kobj: The kobject that represents this class and links it into the hierarchy. @@ -374,6 +375,7 @@ int subsys_virtual_register(struct bus_type *subsys, * @suspend: Used to put the device to sleep mode, usually to a low power * state. * @resume: Used to bring the device from the sleep mode. + * @shutdown: Called at shut-down time to quiesce the device. * @ns_type: Callbacks so sysfs can detemine namespaces. * @namespace: Namespace of the device belongs to this class. * @pm: The default device power management operations of this class. @@ -390,7 +392,6 @@ struct class { const char *name; struct module *owner; - struct class_attribute *class_attrs; const struct attribute_group **class_groups; const struct attribute_group **dev_groups; struct kobject *dev_kobj; @@ -403,6 +404,7 @@ struct class { int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); + int (*shutdown)(struct device *dev); const struct kobj_ns_type_operations *ns_type; const void *(*namespace)(struct device *dev); @@ -461,8 +463,6 @@ struct class_attribute { const char *buf, size_t count); }; -#define CLASS_ATTR(_name, _mode, _show, _store) \ - struct class_attribute class_attr_##_name = __ATTR(_name, _mode, _show, _store) #define CLASS_ATTR_RW(_name) \ struct class_attribute class_attr_##_name = __ATTR_RW(_name) #define CLASS_ATTR_RO(_name) \ @@ -875,6 +875,8 @@ struct dev_links_info { * * @offline_disabled: If set, the device is permanently online. * @offline: Set after successful invocation of bus type's .offline(). + * @of_node_reused: Set if the device-tree node is shared with an ancestor + * device. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -921,6 +923,7 @@ struct device { #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ #endif + const struct dma_map_ops *dma_ops; u64 *dma_mask; /* dma mask (if dma'able device) */ u64 coherent_dma_mask;/* Like dma_mask, but for alloc_coherent mappings as @@ -961,6 +964,7 @@ struct device { bool offline_disabled:1; bool offline:1; + bool of_node_reused:1; }; static inline struct device *kobj_to_dev(struct kobject *kobj) @@ -1139,6 +1143,14 @@ extern int device_offline(struct device *dev); extern int device_online(struct device *dev); extern void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); extern void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); +void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); + +static inline int dev_num_vf(struct device *dev) +{ + if (dev->bus && dev->bus->num_vf) + return dev->bus->num_vf(dev); + return 0; +} /* * Root device objects for grouping under /sys/devices diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index f486d636b82e..cfac8588ed56 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -20,6 +20,7 @@ #define DM_KCOPYD_MAX_REGIONS 8 #define DM_KCOPYD_IGNORE_ERROR 1 +#define DM_KCOPYD_WRITE_SEQ 2 struct dm_kcopyd_throttle { unsigned throttle; diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 8daeb3ce0016..79f27d60ec66 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -39,67 +39,213 @@ struct dma_buf_attachment; /** * struct dma_buf_ops - operations possible on struct dma_buf - * @attach: [optional] allows different devices to 'attach' themselves to the - * given buffer. It might return -EBUSY to signal that backing storage - * is already allocated and incompatible with the requirements - * of requesting device. - * @detach: [optional] detach a given device from this buffer. - * @map_dma_buf: returns list of scatter pages allocated, increases usecount - * of the buffer. Requires atleast one attach to be called - * before. Returned sg list should already be mapped into - * _device_ address space. This call may sleep. May also return - * -EINTR. Should return -EINVAL if attach hasn't been called yet. - * @unmap_dma_buf: decreases usecount of buffer, might deallocate scatter - * pages. - * @release: release this buffer; to be called after the last dma_buf_put. - * @begin_cpu_access: [optional] called before cpu access to invalidate cpu - * caches and allocate backing storage (if not yet done) - * respectively pin the object into memory. - * @end_cpu_access: [optional] called after cpu access to flush caches. - * @kmap_atomic: maps a page from the buffer into kernel address - * space, users may not block until the subsequent unmap call. - * This callback must not sleep. - * @kunmap_atomic: [optional] unmaps a atomically mapped page from the buffer. - * This Callback must not sleep. - * @kmap: maps a page from the buffer into kernel address space. - * @kunmap: [optional] unmaps a page from the buffer. - * @mmap: used to expose the backing storage to userspace. Note that the - * mapping needs to be coherent - if the exporter doesn't directly - * support this, it needs to fake coherency by shooting down any ptes - * when transitioning away from the cpu domain. + * @map_atomic: maps a page from the buffer into kernel address + * space, users may not block until the subsequent unmap call. + * This callback must not sleep. + * @unmap_atomic: [optional] unmaps a atomically mapped page from the buffer. + * This Callback must not sleep. + * @map: maps a page from the buffer into kernel address space. + * @unmap: [optional] unmaps a page from the buffer. * @vmap: [optional] creates a virtual mapping for the buffer into kernel * address space. Same restrictions as for vmap and friends apply. * @vunmap: [optional] unmaps a vmap from the buffer */ struct dma_buf_ops { + /** + * @attach: + * + * This is called from dma_buf_attach() to make sure that a given + * &device can access the provided &dma_buf. Exporters which support + * buffer objects in special locations like VRAM or device-specific + * carveout areas should check whether the buffer could be move to + * system memory (or directly accessed by the provided device), and + * otherwise need to fail the attach operation. + * + * The exporter should also in general check whether the current + * allocation fullfills the DMA constraints of the new device. If this + * is not the case, and the allocation cannot be moved, it should also + * fail the attach operation. + * + * Any exporter-private housekeeping data can be stored in the + * &dma_buf_attachment.priv pointer. + * + * This callback is optional. + * + * Returns: + * + * 0 on success, negative error code on failure. It might return -EBUSY + * to signal that backing storage is already allocated and incompatible + * with the requirements of requesting device. + */ int (*attach)(struct dma_buf *, struct device *, - struct dma_buf_attachment *); + struct dma_buf_attachment *); + /** + * @detach: + * + * This is called by dma_buf_detach() to release a &dma_buf_attachment. + * Provided so that exporters can clean up any housekeeping for an + * &dma_buf_attachment. + * + * This callback is optional. + */ void (*detach)(struct dma_buf *, struct dma_buf_attachment *); - /* For {map,unmap}_dma_buf below, any specific buffer attributes - * required should get added to device_dma_parameters accessible - * via dev->dma_params. + /** + * @map_dma_buf: + * + * This is called by dma_buf_map_attachment() and is used to map a + * shared &dma_buf into device address space, and it is mandatory. It + * can only be called if @attach has been called successfully. This + * essentially pins the DMA buffer into place, and it cannot be moved + * any more + * + * This call may sleep, e.g. when the backing storage first needs to be + * allocated, or moved to a location suitable for all currently attached + * devices. + * + * Note that any specific buffer attributes required for this function + * should get added to device_dma_parameters accessible via + * &device.dma_params from the &dma_buf_attachment. The @attach callback + * should also check these constraints. + * + * If this is being called for the first time, the exporter can now + * choose to scan through the list of attachments for this buffer, + * collate the requirements of the attached devices, and choose an + * appropriate backing storage for the buffer. + * + * Based on enum dma_data_direction, it might be possible to have + * multiple users accessing at the same time (for reading, maybe), or + * any other kind of sharing that the exporter might wish to make + * available to buffer-users. + * + * Returns: + * + * A &sg_table scatter list of or the backing storage of the DMA buffer, + * already mapped into the device address space of the &device attached + * with the provided &dma_buf_attachment. + * + * On failure, returns a negative error value wrapped into a pointer. + * May also return -EINTR when a signal was received while being + * blocked. */ struct sg_table * (*map_dma_buf)(struct dma_buf_attachment *, - enum dma_data_direction); + enum dma_data_direction); + /** + * @unmap_dma_buf: + * + * This is called by dma_buf_unmap_attachment() and should unmap and + * release the &sg_table allocated in @map_dma_buf, and it is mandatory. + * It should also unpin the backing storage if this is the last mapping + * of the DMA buffer, it the exporter supports backing storage + * migration. + */ void (*unmap_dma_buf)(struct dma_buf_attachment *, - struct sg_table *, - enum dma_data_direction); + struct sg_table *, + enum dma_data_direction); + /* TODO: Add try_map_dma_buf version, to return immed with -EBUSY * if the call would block. */ - /* after final dma_buf_put() */ + /** + * @release: + * + * Called after the last dma_buf_put to release the &dma_buf, and + * mandatory. + */ void (*release)(struct dma_buf *); + /** + * @begin_cpu_access: + * + * This is called from dma_buf_begin_cpu_access() and allows the + * exporter to ensure that the memory is actually available for cpu + * access - the exporter might need to allocate or swap-in and pin the + * backing storage. The exporter also needs to ensure that cpu access is + * coherent for the access direction. The direction can be used by the + * exporter to optimize the cache flushing, i.e. access with a different + * direction (read instead of write) might return stale or even bogus + * data (e.g. when the exporter needs to copy the data to temporary + * storage). + * + * This callback is optional. + * + * FIXME: This is both called through the DMA_BUF_IOCTL_SYNC command + * from userspace (where storage shouldn't be pinned to avoid handing + * de-factor mlock rights to userspace) and for the kernel-internal + * users of the various kmap interfaces, where the backing storage must + * be pinned to guarantee that the atomic kmap calls can succeed. Since + * there's no in-kernel users of the kmap interfaces yet this isn't a + * real problem. + * + * Returns: + * + * 0 on success or a negative error code on failure. This can for + * example fail when the backing storage can't be allocated. Can also + * return -ERESTARTSYS or -EINTR when the call has been interrupted and + * needs to be restarted. + */ int (*begin_cpu_access)(struct dma_buf *, enum dma_data_direction); + + /** + * @end_cpu_access: + * + * This is called from dma_buf_end_cpu_access() when the importer is + * done accessing the CPU. The exporter can use this to flush caches and + * unpin any resources pinned in @begin_cpu_access. + * The result of any dma_buf kmap calls after end_cpu_access is + * undefined. + * + * This callback is optional. + * + * Returns: + * + * 0 on success or a negative error code on failure. Can return + * -ERESTARTSYS or -EINTR when the call has been interrupted and needs + * to be restarted. + */ int (*end_cpu_access)(struct dma_buf *, enum dma_data_direction); - void *(*kmap_atomic)(struct dma_buf *, unsigned long); - void (*kunmap_atomic)(struct dma_buf *, unsigned long, void *); - void *(*kmap)(struct dma_buf *, unsigned long); - void (*kunmap)(struct dma_buf *, unsigned long, void *); + void *(*map_atomic)(struct dma_buf *, unsigned long); + void (*unmap_atomic)(struct dma_buf *, unsigned long, void *); + void *(*map)(struct dma_buf *, unsigned long); + void (*unmap)(struct dma_buf *, unsigned long, void *); + /** + * @mmap: + * + * This callback is used by the dma_buf_mmap() function + * + * Note that the mapping needs to be incoherent, userspace is expected + * to braket CPU access using the DMA_BUF_IOCTL_SYNC interface. + * + * Because dma-buf buffers have invariant size over their lifetime, the + * dma-buf core checks whether a vma is too large and rejects such + * mappings. The exporter hence does not need to duplicate this check. + * Drivers do not need to check this themselves. + * + * If an exporter needs to manually flush caches and hence needs to fake + * coherency for mmap support, it needs to be able to zap all the ptes + * pointing at the backing storage. Now linux mm needs a struct + * address_space associated with the struct file stored in vma->vm_file + * to do that with the function unmap_mapping_range. But the dma_buf + * framework only backs every dma_buf fd with the anon_file struct file, + * i.e. all dma_bufs share the same file. + * + * Hence exporters need to setup their own file (and address_space) + * association by setting vma->vm_file and adjusting vma->vm_pgoff in + * the dma_buf mmap callback. In the specific case of a gem driver the + * exporter could use the shmem file already provided by gem (and set + * vm_pgoff = 0). Exporters can then zap ptes by unmapping the + * corresponding range of the struct address_space associated with their + * own file. + * + * This callback is optional. + * + * Returns: + * + * 0 on success or a negative error code on failure. + */ int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); void *(*vmap)(struct dma_buf *); @@ -124,6 +270,15 @@ struct dma_buf_ops { * @poll: for userspace poll support * @cb_excl: for userspace poll support * @cb_shared: for userspace poll support + * + * This represents a shared buffer, created by calling dma_buf_export(). The + * userspace representation is a normal file descriptor, which can be created by + * calling dma_buf_fd(). + * + * Shared dma buffers are reference counted using dma_buf_put() and + * get_dma_buf(). + * + * Device DMA access is handled by the separate &struct dma_buf_attachment. */ struct dma_buf { size_t size; @@ -160,6 +315,11 @@ struct dma_buf { * This structure holds the attachment information between the dma_buf buffer * and its user device(s). The list contains one attachment struct per device * attached to the buffer. + * + * An attachment is created by calling dma_buf_attach(), and released again by + * calling dma_buf_detach(). The DMA mapping itself needed to initiate a + * transfer is created by dma_buf_map_attachment() and freed again by calling + * dma_buf_unmap_attachment(). */ struct dma_buf_attachment { struct dma_buf *dmabuf; @@ -192,9 +352,11 @@ struct dma_buf_export_info { }; /** - * helper macro for exporters; zeros and fills in most common values - * + * DEFINE_DMA_BUF_EXPORT_INFO - helper macro for exporters * @name: export-info name + * + * DEFINE_DMA_BUF_EXPORT_INFO macro defines the &struct dma_buf_export_info, + * zeroes it out and pre-populates exp_name in it. */ #define DEFINE_DMA_BUF_EXPORT_INFO(name) \ struct dma_buf_export_info name = { .exp_name = KBUILD_MODNAME, \ diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index fec734df1524..b67bf6ac907d 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -112,7 +112,7 @@ static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size, } struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, - unsigned int order); + unsigned int order, gfp_t gfp_mask); bool dma_release_from_contiguous(struct device *dev, struct page *pages, int count); @@ -145,7 +145,7 @@ int dma_declare_contiguous(struct device *dev, phys_addr_t size, static inline struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, - unsigned int order) + unsigned int order, gfp_t gfp_mask) { return NULL; } diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index 5900945f962d..332a5420243c 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -83,4 +83,6 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, u64 context, unsigned seqno, bool signal_on_any); +bool dma_fence_match_context(struct dma_fence *fence, u64 context); + #endif /* __LINUX_DMA_FENCE_ARRAY_H */ diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index d51a7d23c358..0a186c4f3981 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -47,7 +47,7 @@ struct dma_fence_cb; * can be compared to decide which fence would be signaled later. * @flags: A mask of DMA_FENCE_FLAG_* defined below * @timestamp: Timestamp when the fence was signaled. - * @status: Optional, only valid if < 0, must be set before calling + * @error: Optional, only valid if < 0, must be set before calling * dma_fence_signal, indicates that the fence has completed with an error. * * the flags member must be manipulated and read using the appropriate @@ -55,6 +55,7 @@ struct dma_fence_cb; * of the time. * * DMA_FENCE_FLAG_SIGNALED_BIT - fence is already signaled + * DMA_FENCE_FLAG_TIMESTAMP_BIT - timestamp recorded for fence signaling * DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT - enable_signaling might have been called * DMA_FENCE_FLAG_USER_BITS - start of the unused bits, can be used by the * implementer of the fence for its own purposes. Can be used in different @@ -79,11 +80,12 @@ struct dma_fence { unsigned seqno; unsigned long flags; ktime_t timestamp; - int status; + int error; }; enum dma_fence_flag_bits { DMA_FENCE_FLAG_SIGNALED_BIT, + DMA_FENCE_FLAG_TIMESTAMP_BIT, DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, DMA_FENCE_FLAG_USER_BITS, /* must always be last member */ }; @@ -133,7 +135,7 @@ struct dma_fence_cb { * or some failure occurred that made it impossible to enable * signaling. True indicates successful enabling. * - * fence->status may be set in enable_signaling, but only when false is + * fence->error may be set in enable_signaling, but only when false is * returned. * * Calling dma_fence_signal before enable_signaling is called allows @@ -145,7 +147,7 @@ struct dma_fence_cb { * the second time will be a noop since it was already signaled. * * Notes on signaled: - * May set fence->status if returning true. + * May set fence->error if returning true. * * Notes on wait: * Must not be NULL, set to dma_fence_default_wait for default implementation. @@ -229,7 +231,7 @@ static inline struct dma_fence *dma_fence_get_rcu(struct dma_fence *fence) * * Function returns NULL if no refcount could be obtained, or the fence. * This function handles acquiring a reference to a fence that may be - * reallocated within the RCU grace period (such as with SLAB_DESTROY_BY_RCU), + * reallocated within the RCU grace period (such as with SLAB_TYPESAFE_BY_RCU), * so long as the caller is using RCU on the pointer to the fence. * * An alternative mechanism is to employ a seqlock to protect a bunch of @@ -257,7 +259,7 @@ dma_fence_get_rcu_safe(struct dma_fence * __rcu *fencep) * have successfully acquire a reference to it. If it no * longer matches, we are holding a reference to some other * reallocated pointer. This is possible if the allocator - * is using a freelist like SLAB_DESTROY_BY_RCU where the + * is using a freelist like SLAB_TYPESAFE_BY_RCU where the * fence remains valid for the RCU grace period, but it * may be reallocated. When using such allocators, we are * responsible for ensuring the reference we get is to @@ -378,6 +380,50 @@ static inline struct dma_fence *dma_fence_later(struct dma_fence *f1, return dma_fence_is_signaled(f2) ? NULL : f2; } +/** + * dma_fence_get_status_locked - returns the status upon completion + * @fence: [in] the dma_fence to query + * + * Drivers can supply an optional error status condition before they signal + * the fence (to indicate whether the fence was completed due to an error + * rather than success). The value of the status condition is only valid + * if the fence has been signaled, dma_fence_get_status_locked() first checks + * the signal state before reporting the error status. + * + * Returns 0 if the fence has not yet been signaled, 1 if the fence has + * been signaled without an error condition, or a negative error code + * if the fence has been completed in err. + */ +static inline int dma_fence_get_status_locked(struct dma_fence *fence) +{ + if (dma_fence_is_signaled_locked(fence)) + return fence->error ?: 1; + else + return 0; +} + +int dma_fence_get_status(struct dma_fence *fence); + +/** + * dma_fence_set_error - flag an error condition on the fence + * @fence: [in] the dma_fence + * @error: [in] the error to store + * + * Drivers can supply an optional error status condition before they signal + * the fence, to indicate that the fence was completed due to an error + * rather than success. This must be set before signaling (so that the value + * is visible before any waiters on the signal callback are woken). This + * helper exists to help catching erroneous setting of #dma_fence.error. + */ +static inline void dma_fence_set_error(struct dma_fence *fence, + int error) +{ + BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)); + BUG_ON(error >= 0 || error < -MAX_ERRNO); + + fence->error = error; +} + signed long dma_fence_wait_timeout(struct dma_fence *, bool intr, signed long timeout); signed long dma_fence_wait_any_timeout(struct dma_fence **fences, diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index 7f7e9a7e3839..92f20832fd28 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -20,6 +20,7 @@ #include <asm/errno.h> #ifdef CONFIG_IOMMU_DMA +#include <linux/dma-mapping.h> #include <linux/iommu.h> #include <linux/msi.h> @@ -27,6 +28,7 @@ int iommu_dma_init(void); /* Domain management interface for IOMMU drivers */ int iommu_get_dma_cookie(struct iommu_domain *domain); +int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); void iommu_put_dma_cookie(struct iommu_domain *domain); /* Setup call for arch DMA mapping code */ @@ -34,7 +36,8 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, u64 size, struct device *dev); /* General helpers for DMA-API <-> IOMMU-API interaction */ -int dma_direction_to_prot(enum dma_data_direction dir, bool coherent); +int dma_info_to_prot(enum dma_data_direction dir, bool coherent, + unsigned long attrs); /* * These implement the bulk of the relevant DMA mapping callbacks, but require @@ -65,16 +68,17 @@ dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs); void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs); -int iommu_dma_supported(struct device *dev, u64 mask); int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); /* The DMA API isn't _quite_ the whole story, though... */ void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg); +void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list); #else struct iommu_domain; struct msi_msg; +struct device; static inline int iommu_dma_init(void) { @@ -86,6 +90,11 @@ static inline int iommu_get_dma_cookie(struct iommu_domain *domain) return -ENODEV; } +static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) +{ + return -ENODEV; +} + static inline void iommu_put_dma_cookie(struct iommu_domain *domain) { } @@ -94,6 +103,10 @@ static inline void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg) { } +static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list) +{ +} + #endif /* CONFIG_IOMMU_DMA */ #endif /* __KERNEL__ */ #endif /* __DMA_IOMMU_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 10c5a17b1f51..843ab866e0f4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -63,6 +63,13 @@ #define DMA_ATTR_NO_WARN (1UL << 8) /* + * DMA_ATTR_PRIVILEGED: used to indicate that the buffer is fully + * accessible at an elevated privilege level (and ideally inaccessible or + * at least read-only at lesser-privileged levels). + */ +#define DMA_ATTR_PRIVILEGED (1UL << 9) + +/* * A dma_addr_t can hold any valid DMA or bus address for the platform. * It can be given to a device to use as a DMA source or target. A CPU cannot * reference a dma_addr_t directly because there may be translation between @@ -120,14 +127,14 @@ struct dma_map_ops { enum dma_data_direction dir); int (*mapping_error)(struct device *dev, dma_addr_t dma_addr); int (*dma_supported)(struct device *dev, u64 mask); - int (*set_dma_mask)(struct device *dev, u64 mask); #ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK u64 (*get_required_mask)(struct device *dev); #endif int is_phys; }; -extern struct dma_map_ops dma_noop_ops; +extern const struct dma_map_ops dma_noop_ops; +extern const struct dma_map_ops dma_virt_ops; #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) @@ -164,14 +171,26 @@ int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma, #ifdef CONFIG_HAS_DMA #include <asm/dma-mapping.h> +static inline const struct dma_map_ops *get_dma_ops(struct device *dev) +{ + if (dev && dev->dma_ops) + return dev->dma_ops; + return get_arch_dma_ops(dev ? dev->bus : NULL); +} + +static inline void set_dma_ops(struct device *dev, + const struct dma_map_ops *dma_ops) +{ + dev->dma_ops = dma_ops; +} #else /* * Define the dma api to allow compilation but not linking of * dma dependent code. Code that depends on the dma-mapping * API needs to set 'depends on HAS_DMA' in its Kconfig */ -extern struct dma_map_ops bad_dma_ops; -static inline struct dma_map_ops *get_dma_ops(struct device *dev) +extern const struct dma_map_ops bad_dma_ops; +static inline const struct dma_map_ops *get_dma_ops(struct device *dev) { return &bad_dma_ops; } @@ -182,7 +201,7 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, enum dma_data_direction dir, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); dma_addr_t addr; kmemcheck_mark_initialized(ptr, size); @@ -201,7 +220,7 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, enum dma_data_direction dir, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); if (ops->unmap_page) @@ -217,7 +236,7 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); int i, ents; struct scatterlist *s; @@ -235,7 +254,7 @@ static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg int nents, enum dma_data_direction dir, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); debug_dma_unmap_sg(dev, sg, nents, dir); @@ -249,7 +268,7 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev, enum dma_data_direction dir, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); dma_addr_t addr; kmemcheck_mark_initialized(page_address(page) + offset, size); @@ -265,7 +284,7 @@ static inline void dma_unmap_page_attrs(struct device *dev, enum dma_data_direction dir, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); if (ops->unmap_page) @@ -279,7 +298,7 @@ static inline dma_addr_t dma_map_resource(struct device *dev, enum dma_data_direction dir, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); dma_addr_t addr; BUG_ON(!valid_dma_direction(dir)); @@ -300,7 +319,7 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); if (ops->unmap_resource) @@ -312,7 +331,7 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_for_cpu) @@ -324,7 +343,7 @@ static inline void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_for_device) @@ -364,7 +383,7 @@ static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); if (ops->sync_sg_for_cpu) @@ -376,7 +395,7 @@ static inline void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(dir)); if (ops->sync_sg_for_device) @@ -421,7 +440,7 @@ static inline int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!ops); if (ops->mmap) return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs); @@ -439,7 +458,7 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!ops); if (ops->get_sgtable) return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, @@ -457,7 +476,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); void *cpu_addr; BUG_ON(!ops); @@ -479,7 +498,7 @@ static inline void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!ops); WARN_ON(irqs_disabled()); @@ -526,18 +545,12 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) if (get_dma_ops(dev)->mapping_error) return get_dma_ops(dev)->mapping_error(dev, dma_addr); - -#ifdef DMA_ERROR_CODE - return dma_addr == DMA_ERROR_CODE; -#else return 0; -#endif } -#ifndef HAVE_ARCH_DMA_SUPPORTED static inline int dma_supported(struct device *dev, u64 mask) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); if (!ops) return 0; @@ -545,16 +558,10 @@ static inline int dma_supported(struct device *dev, u64 mask) return 1; return ops->dma_supported(dev, mask); } -#endif #ifndef HAVE_ARCH_DMA_SET_MASK static inline int dma_set_mask(struct device *dev, u64 mask) { - struct dma_map_ops *ops = get_dma_ops(dev); - - if (ops->set_dma_mask) - return ops->set_dma_mask(dev, mask); - if (!dev->dma_mask || !dma_supported(dev, mask)) return -EIO; *dev->dma_mask = mask; @@ -708,6 +715,18 @@ dma_mark_declared_memory_occupied(struct device *dev, } #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ +#ifdef CONFIG_HAS_DMA +int dma_configure(struct device *dev); +void dma_deconfigure(struct device *dev); +#else +static inline int dma_configure(struct device *dev) +{ + return 0; +} + +static inline void dma_deconfigure(struct device *dev) {} +#endif + /* * Managed DMA API */ @@ -715,10 +734,9 @@ extern void *dmam_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp); extern void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle); -extern void *dmam_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp); -extern void dmam_free_noncoherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle); +extern void *dmam_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, + unsigned long attrs); #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT extern int dmam_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, diff --git a/include/linux/dma/dw.h b/include/linux/dma/dw.h index ccfd0c3777df..e166cac8e870 100644 --- a/include/linux/dma/dw.h +++ b/include/linux/dma/dw.h @@ -23,6 +23,7 @@ struct dw_dma; /** * struct dw_dma_chip - representation of DesignWare DMA controller hardware * @dev: struct device of the DMA controller + * @id: instance ID * @irq: irq line * @regs: memory mapped I/O space * @clk: hclk clock @@ -31,6 +32,7 @@ struct dw_dma; */ struct dw_dma_chip { struct device *dev; + int id; int irq; void __iomem *regs; struct clk *clk; @@ -48,25 +50,4 @@ static inline int dw_dma_probe(struct dw_dma_chip *chip) { return -ENODEV; } static inline int dw_dma_remove(struct dw_dma_chip *chip) { return 0; } #endif /* CONFIG_DW_DMAC_CORE */ -/* DMA API extensions */ -struct dw_desc; - -struct dw_cyclic_desc { - struct dw_desc **desc; - unsigned long periods; - void (*period_callback)(void *param); - void *period_callback_param; -}; - -struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan, - dma_addr_t buf_addr, size_t buf_len, size_t period_len, - enum dma_transfer_direction direction); -void dw_dma_cyclic_free(struct dma_chan *chan); -int dw_dma_cyclic_start(struct dma_chan *chan); -void dw_dma_cyclic_stop(struct dma_chan *chan); - -dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan); - -dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan); - #endif /* _DMA_DW_H */ diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h index 187c10299722..90884072fa73 100644 --- a/include/linux/dma_remapping.h +++ b/include/linux/dma_remapping.h @@ -39,6 +39,7 @@ extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); extern int dmar_disabled; extern int intel_iommu_enabled; +extern int intel_iommu_tboot_noforce; #else static inline int iommu_calculate_agaw(struct intel_iommu *iommu) { diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index feee6ec6a13b..533680860865 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -894,6 +894,17 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memset( len, flags); } +static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy( + struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, + size_t len, unsigned long flags) +{ + if (!chan || !chan->device || !chan->device->device_prep_dma_memcpy) + return NULL; + + return chan->device->device_prep_dma_memcpy(chan, dest, src, + len, flags); +} + static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg( struct dma_chan *chan, struct scatterlist *dst_sg, unsigned int dst_nents, diff --git a/include/linux/dmar.h b/include/linux/dmar.h index e9bc9292bd3a..e8ffba1052d3 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -26,7 +26,7 @@ #include <linux/msi.h> #include <linux/irqreturn.h> #include <linux/rwsem.h> -#include <linux/rcupdate.h> +#include <linux/rculist.h> struct acpi_dmar_header; diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 5e9c74cf8894..9bbf21a516e4 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -136,7 +136,7 @@ static inline int dmi_name_in_vendors(const char *s) { return 0; } static inline int dmi_name_in_serial(const char *s) { return 0; } #define dmi_available 0 static inline int dmi_walk(void (*decode)(const struct dmi_header *, void *), - void *private_data) { return -1; } + void *private_data) { return -ENXIO; } static inline bool dmi_match(enum dmi_field f, const char *str) { return false; } static inline void dmi_memdev_name(u16 handle, const char **bank, diff --git a/include/linux/edac.h b/include/linux/edac.h index 07c52c0af62d..8ae0f45fafd6 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -28,12 +28,10 @@ struct device; #define EDAC_OPSTATE_INT 2 extern int edac_op_state; -extern int edac_err_assert; -extern atomic_t edac_handlers; -extern int edac_handler_set(void); -extern void edac_atomic_assert_error(void); -extern struct bus_type *edac_get_sysfs_subsys(void); +struct bus_type *edac_get_sysfs_subsys(void); +int edac_get_report_status(void); +void edac_set_report_status(int new); enum { EDAC_REPORTING_ENABLED, @@ -41,28 +39,6 @@ enum { EDAC_REPORTING_FORCE }; -extern int edac_report_status; -#ifdef CONFIG_EDAC -static inline int get_edac_report_status(void) -{ - return edac_report_status; -} - -static inline void set_edac_report_status(int new) -{ - edac_report_status = new; -} -#else -static inline int get_edac_report_status(void) -{ - return EDAC_REPORTING_DISABLED; -} - -static inline void set_edac_report_status(int new) -{ -} -#endif - static inline void opstate_init(void) { switch (edac_op_state) { @@ -190,8 +166,8 @@ static inline char *mc_event_error_type(const unsigned int err_type) * part of the memory details to the memory controller. * @MEM_RMBS: Rambus DRAM, used on a few Pentium III/IV controllers. * @MEM_DDR2: DDR2 RAM, as described at JEDEC JESD79-2F. - * Those memories are labed as "PC2-" instead of "PC" to - * differenciate from DDR. + * Those memories are labeled as "PC2-" instead of "PC" to + * differentiate from DDR. * @MEM_FB_DDR2: Fully-Buffered DDR2, as described at JEDEC Std No. 205 * and JESD206. * Those memories are accessed per DIMM slot, and not by diff --git a/include/linux/efi-bgrt.h b/include/linux/efi-bgrt.h index 051b21fedf68..e6f624b53c3d 100644 --- a/include/linux/efi-bgrt.h +++ b/include/linux/efi-bgrt.h @@ -1,20 +1,24 @@ #ifndef _LINUX_EFI_BGRT_H #define _LINUX_EFI_BGRT_H -#ifdef CONFIG_ACPI_BGRT - #include <linux/acpi.h> -void efi_bgrt_init(void); +#ifdef CONFIG_ACPI_BGRT + +void efi_bgrt_init(struct acpi_table_header *table); +int __init acpi_parse_bgrt(struct acpi_table_header *table); /* The BGRT data itself; only valid if bgrt_image != NULL. */ -extern void *bgrt_image; extern size_t bgrt_image_size; -extern struct acpi_table_bgrt *bgrt_tab; +extern struct acpi_table_bgrt bgrt_tab; #else /* !CONFIG_ACPI_BGRT */ -static inline void efi_bgrt_init(void) {} +static inline void efi_bgrt_init(struct acpi_table_header *table) {} +static inline int __init acpi_parse_bgrt(struct acpi_table_header *table) +{ + return 0; +} #endif /* !CONFIG_ACPI_BGRT */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 5b1af30ece55..8269bcb8ccf7 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -137,6 +137,18 @@ struct efi_boot_memmap { #define EFI_CAPSULE_POPULATE_SYSTEM_TABLE 0x00020000 #define EFI_CAPSULE_INITIATE_RESET 0x00040000 +struct capsule_info { + efi_capsule_header_t header; + int reset_type; + long index; + size_t count; + size_t total_size; + phys_addr_t *pages; + size_t page_bytes_remain; +}; + +int __efi_capsule_setup_info(struct capsule_info *cap_info); + /* * Allocation types for calls to boottime->allocate_pages. */ @@ -509,24 +521,6 @@ typedef struct { u64 query_variable_info; } efi_runtime_services_64_t; -typedef struct { - efi_table_hdr_t hdr; - void *get_time; - void *set_time; - void *get_wakeup_time; - void *set_wakeup_time; - void *set_virtual_address_map; - void *convert_pointer; - void *get_variable; - void *get_next_variable; - void *set_variable; - void *get_next_high_mono_count; - void *reset_system; - void *update_capsule; - void *query_capsule_caps; - void *query_variable_info; -} efi_runtime_services_t; - typedef efi_status_t efi_get_time_t (efi_time_t *tm, efi_time_cap_t *tc); typedef efi_status_t efi_set_time_t (efi_time_t *tm); typedef efi_status_t efi_get_wakeup_time_t (efi_bool_t *enabled, efi_bool_t *pending, @@ -561,6 +555,24 @@ typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size, bool nonblocking); +typedef struct { + efi_table_hdr_t hdr; + efi_get_time_t *get_time; + efi_set_time_t *set_time; + efi_get_wakeup_time_t *get_wakeup_time; + efi_set_wakeup_time_t *set_wakeup_time; + efi_set_virtual_address_map_t *set_virtual_address_map; + void *convert_pointer; + efi_get_variable_t *get_variable; + efi_get_next_variable_t *get_next_variable; + efi_set_variable_t *set_variable; + efi_get_next_high_mono_count_t *get_next_high_mono_count; + efi_reset_system_t *reset_system; + efi_update_capsule_t *update_capsule; + efi_query_capsule_caps_t *query_capsule_caps; + efi_query_variable_info_t *query_variable_info; +} efi_runtime_services_t; + void efi_native_runtime_setup(void); /* @@ -611,6 +623,9 @@ void efi_native_runtime_setup(void); #define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define APPLE_PROPERTIES_PROTOCOL_GUID EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb, 0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0) +#define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) +#define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) + /* * This GUID is used to pass to the kernel proper the struct screen_info * structure that was populated by the stub based on the GOP protocol instance @@ -1065,6 +1080,7 @@ extern int __init efi_setup_pcdp_console(char *); #define EFI_ARCH_1 7 /* First arch-specific bit */ #define EFI_DBG 8 /* Print additional debug info at runtime */ #define EFI_NX_PE_DATA 9 /* Can runtime data regions be mapped non-executable? */ +#define EFI_MEM_ATTR 10 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */ #ifdef CONFIG_EFI /* @@ -1240,17 +1256,17 @@ struct efivar_entry { bool deleting; }; -struct efi_simple_text_output_protocol_32 { +typedef struct { u32 reset; u32 output_string; u32 test_string; -}; +} efi_simple_text_output_protocol_32_t; -struct efi_simple_text_output_protocol_64 { +typedef struct { u64 reset; u64 output_string; u64 test_string; -}; +} efi_simple_text_output_protocol_64_t; struct efi_simple_text_output_protocol { void *reset; @@ -1399,7 +1415,7 @@ extern int efi_capsule_supported(efi_guid_t guid, u32 flags, size_t size, int *reset); extern int efi_capsule_update(efi_capsule_header_t *capsule, - struct page **pages); + phys_addr_t *pages); #ifdef CONFIG_EFI_RUNTIME_MAP int efi_runtime_map_init(struct kobject *); @@ -1431,9 +1447,6 @@ static inline int efi_runtime_map_copy(void *buf, size_t bufsz) /* prototypes shared between arch specific and generic stub code */ -#define pr_efi(sys_table, msg) efi_printk(sys_table, "EFI stub: "msg) -#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg) - void efi_printk(efi_system_table_t *sys_table_arg, char *str); void efi_free(efi_system_table_t *sys_table_arg, unsigned long size, @@ -1467,7 +1480,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, unsigned long *load_addr, unsigned long *load_size); -efi_status_t efi_parse_options(char *cmdline); +efi_status_t efi_parse_options(char const *cmdline); efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, struct screen_info *si, efi_guid_t *proto, @@ -1476,6 +1489,14 @@ efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, bool efi_runtime_disabled(void); extern void efi_call_virt_check_flags(unsigned long flags, const char *call); +enum efi_secureboot_mode { + efi_secureboot_mode_unset, + efi_secureboot_mode_unknown, + efi_secureboot_mode_disabled, + efi_secureboot_mode_enabled, +}; +enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table); + /* * Arch code can implement the following three template macros, avoiding * reptition for the void/non-void return cases of {__,}efi_call_virt(): diff --git a/include/linux/elevator.h b/include/linux/elevator.h index b276e9ef0e0b..5bc8f8682a3e 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -8,13 +8,26 @@ struct io_cq; struct elevator_type; +#ifdef CONFIG_BLK_DEBUG_FS +struct blk_mq_debugfs_attr; +#endif -typedef int (elevator_merge_fn) (struct request_queue *, struct request **, +/* + * Return values from elevator merger + */ +enum elv_merge { + ELEVATOR_NO_MERGE = 0, + ELEVATOR_FRONT_MERGE = 1, + ELEVATOR_BACK_MERGE = 2, + ELEVATOR_DISCARD_MERGE = 3, +}; + +typedef enum elv_merge (elevator_merge_fn) (struct request_queue *, struct request **, struct bio *); typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *, struct request *); -typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int); +typedef void (elevator_merged_fn) (struct request_queue *, struct request *, enum elv_merge); typedef int (elevator_allow_bio_merge_fn) (struct request_queue *, struct request *, struct bio *); @@ -77,6 +90,35 @@ struct elevator_ops elevator_registered_fn *elevator_registered_fn; }; +struct blk_mq_alloc_data; +struct blk_mq_hw_ctx; + +struct elevator_mq_ops { + int (*init_sched)(struct request_queue *, struct elevator_type *); + void (*exit_sched)(struct elevator_queue *); + int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); + void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); + + bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); + bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *); + int (*request_merge)(struct request_queue *q, struct request **, struct bio *); + void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); + void (*requests_merged)(struct request_queue *, struct request *, struct request *); + void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *); + void (*prepare_request)(struct request *, struct bio *bio); + void (*finish_request)(struct request *); + void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool); + struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); + bool (*has_work)(struct blk_mq_hw_ctx *); + void (*completed_request)(struct request *); + void (*started_request)(struct request *); + void (*requeue_request)(struct request *); + struct request *(*former_request)(struct request_queue *, struct request *); + struct request *(*next_request)(struct request_queue *, struct request *); + void (*init_icq)(struct io_cq *); + void (*exit_icq)(struct io_cq *); +}; + #define ELV_NAME_MAX (16) struct elv_fs_entry { @@ -94,15 +136,23 @@ struct elevator_type struct kmem_cache *icq_cache; /* fields provided by elevator implementation */ - struct elevator_ops ops; + union { + struct elevator_ops sq; + struct elevator_mq_ops mq; + } ops; size_t icq_size; /* see iocontext.h */ size_t icq_align; /* ditto */ struct elv_fs_entry *elevator_attrs; char elevator_name[ELV_NAME_MAX]; struct module *elevator_owner; + bool uses_mq; +#ifdef CONFIG_BLK_DEBUG_FS + const struct blk_mq_debugfs_attr *queue_debugfs_attrs; + const struct blk_mq_debugfs_attr *hctx_debugfs_attrs; +#endif /* managed by elevator core */ - char icq_cache_name[ELV_NAME_MAX + 5]; /* elvname + "_io_cq" */ + char icq_cache_name[ELV_NAME_MAX + 6]; /* elvname + "_io_cq" */ struct list_head list; }; @@ -123,6 +173,7 @@ struct elevator_queue struct kobject kobj; struct mutex sysfs_lock; unsigned int registered:1; + unsigned int uses_mq:1; DECLARE_HASHTABLE(hash, ELV_HASH_BITS); }; @@ -133,12 +184,15 @@ extern void elv_dispatch_sort(struct request_queue *, struct request *); extern void elv_dispatch_add_tail(struct request_queue *, struct request *); extern void elv_add_request(struct request_queue *, struct request *, int); extern void __elv_add_request(struct request_queue *, struct request *, int); -extern int elv_merge(struct request_queue *, struct request **, struct bio *); +extern enum elv_merge elv_merge(struct request_queue *, struct request **, + struct bio *); extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); -extern void elv_merged_request(struct request_queue *, struct request *, int); +extern void elv_merged_request(struct request_queue *, struct request *, + enum elv_merge); extern void elv_bio_merged(struct request_queue *q, struct request *, struct bio *); +extern bool elv_attempt_insert_merge(struct request_queue *, struct request *); extern void elv_requeue_request(struct request_queue *, struct request *); extern struct request *elv_former_request(struct request_queue *, struct request *); extern struct request *elv_latter_request(struct request_queue *, struct request *); @@ -165,8 +219,7 @@ extern ssize_t elv_iosched_show(struct request_queue *, char *); extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); extern int elevator_init(struct request_queue *, char *); -extern void elevator_exit(struct elevator_queue *); -extern int elevator_change(struct request_queue *, const char *); +extern void elevator_exit(struct request_queue *, struct elevator_queue *); extern bool elv_bio_merge_ok(struct request *, struct bio *); extern struct elevator_queue *elevator_alloc(struct request_queue *, struct elevator_type *); @@ -185,13 +238,6 @@ extern void elv_rb_del(struct rb_root *, struct request *); extern struct request *elv_rb_find(struct rb_root *, sector_t); /* - * Return values from elevator merger - */ -#define ELEVATOR_NO_MERGE 0 -#define ELEVATOR_FRONT_MERGE 1 -#define ELEVATOR_BACK_MERGE 2 - -/* * Insertion selection */ #define ELEVATOR_INSERT_FRONT 1 diff --git a/include/linux/elf.h b/include/linux/elf.h index 20fa8d8ae313..ba069e8f4f78 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -29,6 +29,7 @@ extern Elf32_Dyn _DYNAMIC []; #define elf_note elf32_note #define elf_addr_t Elf32_Off #define Elf_Half Elf32_Half +#define Elf_Word Elf32_Word #else @@ -39,6 +40,7 @@ extern Elf64_Dyn _DYNAMIC []; #define elf_note elf64_note #define elf_addr_t Elf64_Off #define Elf_Half Elf64_Half +#define Elf_Word Elf64_Word #endif diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 698d51a0eea3..c8240a12c42d 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -3,6 +3,8 @@ #include <linux/user.h> #include <linux/bug.h> +#include <linux/sched/task_stack.h> + #include <asm/elf.h> #include <uapi/linux/elfcore.h> diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h index 9ca23fcfb5d7..6fdfc884fdeb 100644 --- a/include/linux/errqueue.h +++ b/include/linux/errqueue.h @@ -20,6 +20,8 @@ struct sock_exterr_skb { struct sock_extended_err ee; u16 addr_offset; __be16 port; + u8 opt_stats:1, + unused:7; }; #endif diff --git a/include/linux/errseq.h b/include/linux/errseq.h new file mode 100644 index 000000000000..9e0d444ac88d --- /dev/null +++ b/include/linux/errseq.h @@ -0,0 +1,19 @@ +#ifndef _LINUX_ERRSEQ_H +#define _LINUX_ERRSEQ_H + +/* See lib/errseq.c for more info */ + +typedef u32 errseq_t; + +errseq_t __errseq_set(errseq_t *eseq, int err); +static inline void errseq_set(errseq_t *eseq, int err) +{ + /* Optimize for the common case of no error */ + if (unlikely(err)) + __errseq_set(eseq, err); +} + +errseq_t errseq_sample(errseq_t *eseq); +int errseq_check(errseq_t *eseq, errseq_t since); +int errseq_check_and_advance(errseq_t *eseq, errseq_t *since); +#endif diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 6fec9e81bd70..2d9f80848d4b 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -54,6 +54,11 @@ struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1) #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count) +struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv, + unsigned int txqs, + unsigned int rxqs); +#define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1) + struct sk_buff **eth_gro_receive(struct sk_buff **head, struct sk_buff *skb); int eth_gro_complete(struct sk_buff *skb, int nhoff); @@ -397,6 +402,51 @@ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, } /** + * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. + * @addr: Pointer to a six-byte array containing the Ethernet address + * + * Return a u64 value of the address + */ +static inline u64 ether_addr_to_u64(const u8 *addr) +{ + u64 u = 0; + int i; + + for (i = 0; i < ETH_ALEN; i++) + u = u << 8 | addr[i]; + + return u; +} + +/** + * u64_to_ether_addr - Convert a u64 to an Ethernet address. + * @u: u64 to convert to an Ethernet MAC address + * @addr: Pointer to a six-byte array to contain the Ethernet address + */ +static inline void u64_to_ether_addr(u64 u, u8 *addr) +{ + int i; + + for (i = ETH_ALEN - 1; i >= 0; i--) { + addr[i] = u & 0xff; + u = u >> 8; + } +} + +/** + * eth_addr_dec - Decrement the given MAC address + * + * @addr: Pointer to a six-byte array containing Ethernet address to decrement + */ +static inline void eth_addr_dec(u8 *addr) +{ + u64 u = ether_addr_to_u64(addr); + + u--; + u64_to_ether_addr(u, addr); +} + +/** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9ded8c6d8176..83cc9863444b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -60,6 +60,7 @@ enum ethtool_phys_id_state { enum { ETH_RSS_HASH_TOP_BIT, /* Configurable RSS hash function - Toeplitz */ ETH_RSS_HASH_XOR_BIT, /* Configurable RSS hash function - Xor */ + ETH_RSS_HASH_CRC32_BIT, /* Configurable RSS hash function - Crc32 */ /* * Add your fresh new hash function bits above and remember to update @@ -73,6 +74,7 @@ enum { #define ETH_RSS_HASH_TOP __ETH_RSS_HASH(TOP) #define ETH_RSS_HASH_XOR __ETH_RSS_HASH(XOR) +#define ETH_RSS_HASH_CRC32 __ETH_RSS_HASH(CRC32) #define ETH_RSS_HASH_UNKNOWN 0 #define ETH_RSS_HASH_NO_CHANGE 0 diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index ff0b981f078e..9e4befd95bc7 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -37,7 +37,7 @@ struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt); -int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait, +int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); #else /* CONFIG_EVENTFD */ @@ -73,7 +73,7 @@ static inline ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, } static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, - wait_queue_t *wait, __u64 *cnt) + wait_queue_entry_t *wait, __u64 *cnt) { return -ENOSYS; } diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 6daf6d4971f6..2f14ac73d01d 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -14,6 +14,7 @@ #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> +#include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ @@ -22,6 +23,10 @@ struct file; #ifdef CONFIG_EPOLL +#ifdef CONFIG_CHECKPOINT_RESTORE +struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); +#endif + /* Used to initialize the epoll bits inside the "struct file" */ static inline void eventpoll_init_file(struct file *file) { diff --git a/include/linux/extable.h b/include/linux/extable.h index 7effea4b257d..28addad0dda7 100644 --- a/include/linux/extable.h +++ b/include/linux/extable.h @@ -2,13 +2,14 @@ #define _LINUX_EXTABLE_H #include <linux/stddef.h> /* for NULL */ +#include <linux/types.h> struct module; struct exception_table_entry; const struct exception_table_entry * -search_extable(const struct exception_table_entry *first, - const struct exception_table_entry *last, +search_extable(const struct exception_table_entry *base, + const size_t num, unsigned long value); void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish); diff --git a/include/linux/extcon.h b/include/linux/extcon.h index b871c0cb1f02..7e206a9f88db 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -46,7 +46,18 @@ #define EXTCON_USB 1 #define EXTCON_USB_HOST 2 -/* Charging external connector */ +/* + * Charging external connector + * + * When one SDP charger connector was reported, we should also report + * the USB connector, which means EXTCON_CHG_USB_SDP should always + * appear together with EXTCON_USB. The same as ACA charger connector, + * EXTCON_CHG_USB_ACA would normally appear with EXTCON_USB_HOST. + * + * The EXTCON_CHG_USB_SLOW connector can provide at least 500mA of + * current at 5V. The EXTCON_CHG_USB_FAST connector can provide at + * least 1A of current at 5V. + */ #define EXTCON_CHG_USB_SDP 5 /* Standard Downstream Port */ #define EXTCON_CHG_USB_DCP 6 /* Dedicated Charging Port */ #define EXTCON_CHG_USB_CDP 7 /* Charging Downstream Port */ @@ -54,6 +65,7 @@ #define EXTCON_CHG_USB_FAST 9 #define EXTCON_CHG_USB_SLOW 10 #define EXTCON_CHG_WPT 11 /* Wireless Power Transfer */ +#define EXTCON_CHG_USB_PD 12 /* USB Power Delivery */ /* Jack external connector */ #define EXTCON_JACK_MICROPHONE 20 @@ -160,62 +172,7 @@ union extcon_property_value { }; struct extcon_cable; - -/** - * struct extcon_dev - An extcon device represents one external connector. - * @name: The name of this extcon device. Parent device name is - * used if NULL. - * @supported_cable: Array of supported cable names ending with EXTCON_NONE. - * If supported_cable is NULL, cable name related APIs - * are disabled. - * @mutually_exclusive: Array of mutually exclusive set of cables that cannot - * be attached simultaneously. The array should be - * ending with NULL or be NULL (no mutually exclusive - * cables). For example, if it is { 0x7, 0x30, 0}, then, - * {0, 1}, {0, 1, 2}, {0, 2}, {1, 2}, or {4, 5} cannot - * be attached simulataneously. {0x7, 0} is equivalent to - * {0x3, 0x6, 0x5, 0}. If it is {0xFFFFFFFF, 0}, there - * can be no simultaneous connections. - * @dev: Device of this extcon. - * @state: Attach/detach state of this extcon. Do not provide at - * register-time. - * @nh: Notifier for the state change events from this extcon - * @entry: To support list of extcon devices so that users can - * search for extcon devices based on the extcon name. - * @lock: - * @max_supported: Internal value to store the number of cables. - * @extcon_dev_type: Device_type struct to provide attribute_groups - * customized for each extcon device. - * @cables: Sysfs subdirectories. Each represents one cable. - * - * In most cases, users only need to provide "User initializing data" of - * this struct when registering an extcon. In some exceptional cases, - * optional callbacks may be needed. However, the values in "internal data" - * are overwritten by register function. - */ -struct extcon_dev { - /* Optional user initializing data */ - const char *name; - const unsigned int *supported_cable; - const u32 *mutually_exclusive; - - /* Internal data. Please do not set. */ - struct device dev; - struct raw_notifier_head *nh; - struct list_head entry; - int max_supported; - spinlock_t lock; /* could be called by irq handler */ - u32 state; - - /* /sys/class/extcon/.../cable.n/... */ - struct device_type extcon_dev_type; - struct extcon_cable *cables; - - /* /sys/class/extcon/.../mutually_exclusive/... */ - struct attribute_group attr_g_muex; - struct attribute **attrs_muex; - struct device_attribute *d_attrs_muex; -}; +struct extcon_dev; #if IS_ENABLED(CONFIG_EXTCON) @@ -279,11 +236,11 @@ extern int extcon_set_property_capability(struct extcon_dev *edev, unsigned int id, unsigned int prop); /* - * Following APIs are to monitor every action of a notifier. - * Registrar gets notified for every external port of a connection device. - * Probably this could be used to debug an action of notifier; however, - * we do not recommend to use this for normal 'notifiee' device drivers who - * want to be notified by a specific external port of the notifier. + * Following APIs are to monitor the status change of the external connectors. + * extcon_register_notifier(*edev, id, *nb) : Register a notifier block + * for specific external connector of the extcon. + * extcon_register_notifier_all(*edev, *nb) : Register a notifier block + * for all supported external connectors of the extcon. */ extern int extcon_register_notifier(struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); @@ -296,6 +253,17 @@ extern void devm_extcon_unregister_notifier(struct device *dev, struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); +extern int extcon_register_notifier_all(struct extcon_dev *edev, + struct notifier_block *nb); +extern int extcon_unregister_notifier_all(struct extcon_dev *edev, + struct notifier_block *nb); +extern int devm_extcon_register_notifier_all(struct device *dev, + struct extcon_dev *edev, + struct notifier_block *nb); +extern void devm_extcon_unregister_notifier_all(struct device *dev, + struct extcon_dev *edev, + struct notifier_block *nb); + /* * Following API get the extcon device from devicetree. * This function use phandle of devicetree to get extcon device directly. diff --git a/include/linux/extcon/extcon-adc-jack.h b/include/linux/extcon/extcon-adc-jack.h index a0e03b13b449..2aa32075bca1 100644 --- a/include/linux/extcon/extcon-adc-jack.h +++ b/include/linux/extcon/extcon-adc-jack.h @@ -59,7 +59,7 @@ struct adc_jack_pdata { const char *name; const char *consumer_channel; - const enum extcon *cable_names; + const unsigned int *cable_names; /* The last entry's state should be 0 */ struct adc_jack_cond *adc_conditions; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index cea41a124a80..b6feed6547ce 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -32,9 +32,15 @@ /* 0, 1(node nid), 2(meta nid) are reserved node id */ #define F2FS_RESERVED_NODE_NUM 3 -#define F2FS_ROOT_INO(sbi) (sbi->root_ino_num) -#define F2FS_NODE_INO(sbi) (sbi->node_ino_num) -#define F2FS_META_INO(sbi) (sbi->meta_ino_num) +#define F2FS_ROOT_INO(sbi) ((sbi)->root_ino_num) +#define F2FS_NODE_INO(sbi) ((sbi)->node_ino_num) +#define F2FS_META_INO(sbi) ((sbi)->meta_ino_num) + +#define F2FS_IO_SIZE(sbi) (1 << (sbi)->write_io_size_bits) /* Blocks */ +#define F2FS_IO_SIZE_KB(sbi) (1 << ((sbi)->write_io_size_bits + 2)) /* KB */ +#define F2FS_IO_SIZE_BYTES(sbi) (1 << ((sbi)->write_io_size_bits + 12)) /* B */ +#define F2FS_IO_SIZE_BITS(sbi) ((sbi)->write_io_size_bits) /* power of 2 */ +#define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1) /* This flag is used by node and meta inodes, and by recovery */ #define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO) @@ -108,6 +114,8 @@ struct f2fs_super_block { /* * For checkpoint */ +#define CP_TRIMMED_FLAG 0x00000100 +#define CP_NAT_BITS_FLAG 0x00000080 #define CP_CRC_RECOVERY_FLAG 0x00000040 #define CP_FASTBOOT_FLAG 0x00000020 #define CP_FSCK_FLAG 0x00000010 @@ -154,7 +162,7 @@ struct f2fs_checkpoint { */ #define F2FS_ORPHANS_PER_BLOCK 1020 -#define GET_ORPHAN_BLOCKS(n) ((n + F2FS_ORPHANS_PER_BLOCK - 1) / \ +#define GET_ORPHAN_BLOCKS(n) (((n) + F2FS_ORPHANS_PER_BLOCK - 1) / \ F2FS_ORPHANS_PER_BLOCK) struct f2fs_orphan_block { @@ -272,6 +280,7 @@ struct f2fs_node { * For NAT entries */ #define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry)) +#define NAT_ENTRY_BITMAP_SIZE ((NAT_ENTRY_PER_BLOCK + 7) / 8) struct f2fs_nat_entry { __u8 version; /* latest version of cached nat entry */ @@ -294,6 +303,12 @@ struct f2fs_nat_block { #define SIT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_sit_entry)) /* + * F2FS uses 4 bytes to represent block address. As a result, supported size of + * disk is 16 TB and it equals to 16 * 1024 * 1024 / 2 segments. + */ +#define F2FS_MAX_SEGMENT ((16 * 1024 * 1024) / 2) + +/* * Note that f2fs_sit_entry->vblocks has the following bit-field information. * [15:10] : allocation type such as CURSEG_XXXX_TYPE * [9:0] : valid block count @@ -441,7 +456,7 @@ typedef __le32 f2fs_hash_t; #define F2FS_SLOT_LEN 8 #define F2FS_SLOT_LEN_BITS 3 -#define GET_DENTRY_SLOTS(x) ((x + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS) +#define GET_DENTRY_SLOTS(x) (((x) + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS) /* MAX level for dir lookup */ #define MAX_DIR_HASH_DEPTH 63 diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 9f4956d8601c..728d4e0292aa 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -61,6 +61,8 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name, #endif /* CONFIG_FAULT_INJECTION */ +struct kmem_cache; + #ifdef CONFIG_FAILSLAB extern bool should_failslab(struct kmem_cache *s, gfp_t gfpflags); #else diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 76ce329e656d..1b48d9c9a561 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -3,6 +3,12 @@ #include <uapi/linux/fcntl.h> +/* list of all valid flags for the open/openat flags argument: */ +#define VALID_OPEN_FLAGS \ + (O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \ + O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \ + FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \ + O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE) #ifndef force_o_largefile #define force_o_largefile() (BITS_PER_LONG != 32) diff --git a/include/linux/filter.h b/include/linux/filter.h index e4eb2546339a..bfef1e5734f8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -7,6 +7,7 @@ #include <stdarg.h> #include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/compat.h> #include <linux/skbuff.h> #include <linux/linkage.h> @@ -15,11 +16,10 @@ #include <linux/sched.h> #include <linux/capability.h> #include <linux/cryptohash.h> +#include <linux/set_memory.h> #include <net/sch_generic.h> -#include <asm/cacheflush.h> - #include <uapi/linux/filter.h> #include <uapi/linux/bpf.h> @@ -54,11 +54,18 @@ struct bpf_prog_aux; #define BPF_REG_AX MAX_BPF_REG #define MAX_BPF_JIT_REG (MAX_BPF_REG + 1) +/* unused opcode to mark special call to bpf_tail_call() helper */ +#define BPF_TAIL_CALL 0xf0 + +/* As per nm, we expose JITed images as text (code) section for + * kallsyms. That way, tools like perf can find it to match + * addresses. + */ +#define BPF_SYM_ELF_TYPE 't' + /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 -#define BPF_TAG_SIZE 8 - /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ @@ -263,6 +270,16 @@ struct bpf_prog_aux; .off = OFF, \ .imm = IMM }) +/* Unconditional jumps, goto pc + off16 */ + +#define BPF_JMP_A(OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_JA, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = 0 }) + /* Function call */ #define BPF_EMIT_CALL(FUNC) \ @@ -317,6 +334,22 @@ struct bpf_prog_aux; bpf_size; \ }) +#define bpf_size_to_bytes(bpf_size) \ +({ \ + int bytes = -EINVAL; \ + \ + if (bpf_size == BPF_B) \ + bytes = sizeof(u8); \ + else if (bpf_size == BPF_H) \ + bytes = sizeof(u16); \ + else if (bpf_size == BPF_W) \ + bytes = sizeof(u32); \ + else if (bpf_size == BPF_DW) \ + bytes = sizeof(u64); \ + \ + bytes; \ +}) + #define BPF_SIZEOF(type) \ ({ \ const int __size = bytes_to_bpf_size(sizeof(type)); \ @@ -331,6 +364,13 @@ struct bpf_prog_aux; __size; \ }) +#define BPF_LDST_BYTES(insn) \ + ({ \ + const int __size = bpf_size_to_bytes(BPF_SIZE(insn->code)); \ + WARN_ON(__size < 0); \ + __size; \ + }) + #define __BPF_MAP_0(m, v, ...) v #define __BPF_MAP_1(m, v, t, a, ...) m(t, a) #define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__) @@ -381,6 +421,18 @@ struct bpf_prog_aux; #define BPF_CALL_4(name, ...) BPF_CALL_x(4, name, __VA_ARGS__) #define BPF_CALL_5(name, ...) BPF_CALL_x(5, name, __VA_ARGS__) +#define bpf_ctx_range(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 +#define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ + offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 + +#define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ + ({ \ + BUILD_BUG_ON(FIELD_SIZEOF(TYPE, MEMBER) != (SIZE)); \ + *(PTR_SIZE) = (SIZE); \ + offsetof(TYPE, MEMBER); \ + }) + #ifdef CONFIG_COMPAT /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { @@ -403,13 +455,14 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ kmemcheck_bitfield_begin(meta); u16 jited:1, /* Is our filter JIT'ed? */ + locked:1, /* Program image locked? */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ - dst_needed:1, /* Do we need dst entry? */ - xdp_adjust_head:1; /* Adjusting pkt head? */ + dst_needed:1; /* Do we need dst entry? */ kmemcheck_bitfield_end(meta); enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ + u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ @@ -423,7 +476,7 @@ struct bpf_prog { }; struct sk_filter { - atomic_t refcnt; + refcount_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; @@ -543,17 +596,46 @@ static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) return prog->type == BPF_PROG_TYPE_UNSPEC; } +static inline bool +bpf_ctx_narrow_access_ok(u32 off, u32 size, const u32 size_default) +{ + bool off_ok; +#ifdef __LITTLE_ENDIAN + off_ok = (off & (size_default - 1)) == 0; +#else + off_ok = (off & (size_default - 1)) + size == size_default; +#endif + return off_ok && size <= size_default && (size & (size - 1)) == 0; +} + #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -#ifdef CONFIG_DEBUG_SET_MODULE_RONX +#ifdef CONFIG_ARCH_HAS_SET_MEMORY static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { - set_memory_ro((unsigned long)fp, fp->pages); + fp->locked = 1; + WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages)); } static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) { - set_memory_rw((unsigned long)fp, fp->pages); + if (fp->locked) { + WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages)); + /* In case set_memory_rw() fails, we want to be the first + * to crash here instead of some random place later on. + */ + fp->locked = 0; + } +} + +static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) +{ + WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages)); +} + +static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) +{ + WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); } #else static inline void bpf_prog_lock_ro(struct bpf_prog *fp) @@ -563,7 +645,24 @@ static inline void bpf_prog_lock_ro(struct bpf_prog *fp) static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) { } -#endif /* CONFIG_DEBUG_SET_MODULE_RONX */ + +static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) +{ +} + +static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) +{ +} +#endif /* CONFIG_ARCH_HAS_SET_MEMORY */ + +static inline struct bpf_binary_header * +bpf_jit_binary_hdr(const struct bpf_prog *fp) +{ + unsigned long real_start = (unsigned long)fp->bpf_func; + unsigned long addr = real_start & PAGE_MASK; + + return (void *)addr; +} int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) @@ -607,6 +706,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); +void bpf_jit_compile(struct bpf_prog *prog); bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, @@ -616,6 +716,7 @@ void bpf_warn_invalid_xdp_action(u32 act); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; +extern int bpf_jit_kallsyms; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); @@ -625,7 +726,6 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_jit_binary_free(struct bpf_binary_header *hdr); -void bpf_jit_compile(struct bpf_prog *fp); void bpf_jit_free(struct bpf_prog *fp); struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); @@ -651,6 +751,16 @@ static inline bool bpf_jit_is_ebpf(void) # endif } +static inline bool ebpf_jit_enabled(void) +{ + return bpf_jit_enable && bpf_jit_is_ebpf(); +} + +static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) +{ + return fp->jited && bpf_jit_is_ebpf(); +} + static inline bool bpf_jit_blinding_enabled(void) { /* These are the prerequisites, should someone ever have the @@ -668,15 +778,96 @@ static inline bool bpf_jit_blinding_enabled(void) return true; } -#else -static inline void bpf_jit_compile(struct bpf_prog *fp) + +static inline bool bpf_jit_kallsyms_enabled(void) +{ + /* There are a couple of corner cases where kallsyms should + * not be enabled f.e. on hardening. + */ + if (bpf_jit_harden) + return false; + if (!bpf_jit_kallsyms) + return false; + if (bpf_jit_kallsyms == 1) + return true; + + return false; +} + +const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, + unsigned long *off, char *sym); +bool is_bpf_text_address(unsigned long addr); +int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, + char *sym); + +static inline const char * +bpf_address_lookup(unsigned long addr, unsigned long *size, + unsigned long *off, char **modname, char *sym) { + const char *ret = __bpf_address_lookup(addr, size, off, sym); + + if (ret && modname) + *modname = NULL; + return ret; +} + +void bpf_prog_kallsyms_add(struct bpf_prog *fp); +void bpf_prog_kallsyms_del(struct bpf_prog *fp); + +#else /* CONFIG_BPF_JIT */ + +static inline bool ebpf_jit_enabled(void) +{ + return false; +} + +static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) +{ + return false; } static inline void bpf_jit_free(struct bpf_prog *fp) { bpf_prog_unlock_free(fp); } + +static inline bool bpf_jit_kallsyms_enabled(void) +{ + return false; +} + +static inline const char * +__bpf_address_lookup(unsigned long addr, unsigned long *size, + unsigned long *off, char *sym) +{ + return NULL; +} + +static inline bool is_bpf_text_address(unsigned long addr) +{ + return false; +} + +static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, + char *type, char *sym) +{ + return -ERANGE; +} + +static inline const char * +bpf_address_lookup(unsigned long addr, unsigned long *size, + unsigned long *off, char **modname, char *sym) +{ + return NULL; +} + +static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) +{ +} + +static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) +{ +} #endif /* CONFIG_BPF_JIT */ #define BPF_ANC BIT(15) @@ -751,4 +942,13 @@ static inline int bpf_tell_extensions(void) return SKF_AD_MAX; } +struct bpf_sock_ops_kern { + struct sock *sk; + u32 op; + union { + u32 reply; + u32 replylong[4]; + }; +}; + #endif /* __LINUX_FILTER_H__ */ diff --git a/include/linux/firmware/meson/meson_sm.h b/include/linux/firmware/meson/meson_sm.h index 8e953c6f394a..37a5eaea69dd 100644 --- a/include/linux/firmware/meson/meson_sm.h +++ b/include/linux/firmware/meson/meson_sm.h @@ -25,7 +25,7 @@ int meson_sm_call(unsigned int cmd_index, u32 *ret, u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4); int meson_sm_call_write(void *buffer, unsigned int b_size, unsigned int cmd_index, u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4); -int meson_sm_call_read(void *buffer, unsigned int cmd_index, u32 arg0, u32 arg1, - u32 arg2, u32 arg3, u32 arg4); +int meson_sm_call_read(void *buffer, unsigned int bsize, unsigned int cmd_index, + u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4); #endif /* _MESON_SM_FW_H_ */ diff --git a/include/linux/flat.h b/include/linux/flat.h index 2c1eb15c4ba4..7d542dfd0def 100644 --- a/include/linux/flat.h +++ b/include/linux/flat.h @@ -9,8 +9,8 @@ #ifndef _LINUX_FLAT_H #define _LINUX_FLAT_H -#include <asm/flat.h> #include <uapi/linux/flat.h> +#include <asm/flat.h> /* * While it would be nice to keep this header clean, users of older diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h index b6efb0c64408..11366b3ff0b4 100644 --- a/include/linux/flex_array.h +++ b/include/linux/flex_array.h @@ -61,16 +61,83 @@ struct flex_array { FLEX_ARRAY_ELEMENTS_PER_PART(__element_size)); \ } +/** + * flex_array_alloc() - Creates a flexible array. + * @element_size: individual object size. + * @total: maximum number of objects which can be stored. + * @flags: GFP flags + * + * Return: Returns an object of structure flex_array. + */ struct flex_array *flex_array_alloc(int element_size, unsigned int total, gfp_t flags); + +/** + * flex_array_prealloc() - Ensures that memory for the elements indexed in the + * range defined by start and nr_elements has been allocated. + * @fa: array to allocate memory to. + * @start: start address + * @nr_elements: number of elements to be allocated. + * @flags: GFP flags + * + */ int flex_array_prealloc(struct flex_array *fa, unsigned int start, unsigned int nr_elements, gfp_t flags); + +/** + * flex_array_free() - Removes all elements of a flexible array. + * @fa: array to be freed. + */ void flex_array_free(struct flex_array *fa); + +/** + * flex_array_free_parts() - Removes all elements of a flexible array, but + * leaves the array itself in place. + * @fa: array to be emptied. + */ void flex_array_free_parts(struct flex_array *fa); + +/** + * flex_array_put() - Stores data into a flexible array. + * @fa: array where element is to be stored. + * @element_nr: position to copy, must be less than the maximum specified when + * the array was created. + * @src: data source to be copied into the array. + * @flags: GFP flags + * + * Return: Returns zero on success, a negative error code otherwise. + */ int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src, gfp_t flags); + +/** + * flex_array_clear() - Clears an individual element in the array, sets the + * given element to FLEX_ARRAY_FREE. + * @element_nr: element position to clear. + * @fa: array to which element to be cleared belongs. + * + * Return: Returns zero on success, -EINVAL otherwise. + */ int flex_array_clear(struct flex_array *fa, unsigned int element_nr); + +/** + * flex_array_get() - Retrieves data into a flexible array. + * + * @element_nr: Element position to retrieve data from. + * @fa: array from which data is to be retrieved. + * + * Return: Returns a pointer to the data element, or NULL if that + * particular element has never been allocated. + */ void *flex_array_get(struct flex_array *fa, unsigned int element_nr); + +/** + * flex_array_shrink() - Reduces the allocated size of an array. + * @fa: array to shrink. + * + * Return: Returns number of pages of memory actually freed. + * + */ int flex_array_shrink(struct flex_array *fa); #define flex_array_put_ptr(fa, nr, src, gfp) \ diff --git a/include/linux/fpga/altera-pr-ip-core.h b/include/linux/fpga/altera-pr-ip-core.h new file mode 100644 index 000000000000..3810a9033f49 --- /dev/null +++ b/include/linux/fpga/altera-pr-ip-core.h @@ -0,0 +1,29 @@ +/* + * Driver for Altera Partial Reconfiguration IP Core + * + * Copyright (C) 2016 Intel Corporation + * + * Based on socfpga-a10.c Copyright (C) 2015-2016 Altera Corporation + * by Alan Tull <atull@opensource.altera.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _ALT_PR_IP_CORE_H +#define _ALT_PR_IP_CORE_H +#include <linux/io.h> + +int alt_pr_register(struct device *dev, void __iomem *reg_base); +int alt_pr_unregister(struct device *dev); + +#endif /* _ALT_PR_IP_CORE_H */ diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 16551d5eac36..b4ac24c4411d 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -22,6 +22,7 @@ #define _LINUX_FPGA_MGR_H struct fpga_manager; +struct sg_table; /** * enum fpga_mgr_states - fpga framework states @@ -69,17 +70,21 @@ enum fpga_mgr_states { */ #define FPGA_MGR_PARTIAL_RECONFIG BIT(0) #define FPGA_MGR_EXTERNAL_CONFIG BIT(1) +#define FPGA_MGR_ENCRYPTED_BITSTREAM BIT(2) /** * struct fpga_image_info - information specific to a FPGA image * @flags: boolean flags as defined above * @enable_timeout_us: maximum time to enable traffic through bridge (uSec) * @disable_timeout_us: maximum time to disable traffic through bridge (uSec) + * @config_complete_timeout_us: maximum time for FPGA to switch to operating + * status in the write_complete op. */ struct fpga_image_info { u32 flags; u32 enable_timeout_us; u32 disable_timeout_us; + u32 config_complete_timeout_us; }; /** @@ -88,6 +93,7 @@ struct fpga_image_info { * @state: returns an enum value of the FPGA's state * @write_init: prepare the FPGA to receive confuration data * @write: write count bytes of configuration data to the FPGA + * @write_sg: write the scatter list of configuration data to the FPGA * @write_complete: set FPGA to operating state after writing is done * @fpga_remove: optional: Set FPGA into a specific state during driver remove * @@ -102,6 +108,7 @@ struct fpga_manager_ops { struct fpga_image_info *info, const char *buf, size_t count); int (*write)(struct fpga_manager *mgr, const char *buf, size_t count); + int (*write_sg)(struct fpga_manager *mgr, struct sg_table *sgt); int (*write_complete)(struct fpga_manager *mgr, struct fpga_image_info *info); void (*fpga_remove)(struct fpga_manager *mgr); @@ -129,6 +136,8 @@ struct fpga_manager { int fpga_mgr_buf_load(struct fpga_manager *mgr, struct fpga_image_info *info, const char *buf, size_t count); +int fpga_mgr_buf_load_sg(struct fpga_manager *mgr, struct fpga_image_info *info, + struct sg_table *sgt); int fpga_mgr_firmware_load(struct fpga_manager *mgr, struct fpga_image_info *info, diff --git a/include/linux/frame.h b/include/linux/frame.h index e6baaba3f1ae..d772c61c31da 100644 --- a/include/linux/frame.h +++ b/include/linux/frame.h @@ -11,7 +11,7 @@ * For more information, see tools/objtool/Documentation/stack-validation.txt. */ #define STACK_FRAME_NON_STANDARD(func) \ - static void __used __section(__func_stack_frame_non_standard) \ + static void __used __section(.discard.func_stack_frame_non_standard) \ *__func_stack_frame_non_standard_##func = func #else /* !CONFIG_STACK_VALIDATION */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 2ba074328894..6e1fd5d21248 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,7 +2,7 @@ #define _LINUX_FS_H #include <linux/linkage.h> -#include <linux/wait.h> +#include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> @@ -18,8 +18,10 @@ #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> +#include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> +#include <linux/fcntl.h> #include <linux/fiemap.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> @@ -29,8 +31,9 @@ #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> -#include <linux/percpu-rwsem.h> #include <linux/delayed_call.h> +#include <linux/uuid.h> +#include <linux/errseq.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -143,6 +146,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +/* File is capable of returning -EAGAIN if AIO will block */ +#define FMODE_AIO_NOWAIT ((__force fmode_t)0x8000000) + /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector * that indicates that they should check the contents of the iovec are @@ -250,9 +256,8 @@ enum positive_aop_returns { AOP_TRUNCATED_PAGE = 0x80001, }; -#define AOP_FLAG_UNINTERRUPTIBLE 0x0001 /* will not do a short write */ -#define AOP_FLAG_CONT_EXPAND 0x0002 /* called from cont_expand */ -#define AOP_FLAG_NOFS 0x0004 /* used by filesystem to direct +#define AOP_FLAG_CONT_EXPAND 0x0001 /* called from cont_expand */ +#define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct * helper code (eg buffer layer) * to clear GFP_FS from alloc */ @@ -263,6 +268,18 @@ struct page; struct address_space; struct writeback_control; +/* + * Write life time hint values. + */ +enum rw_hint { + WRITE_LIFE_NOT_SET = 0, + WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE, + WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT, + WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, + WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, + WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, +}; + #define IOCB_EVENTFD (1 << 0) #define IOCB_APPEND (1 << 1) #define IOCB_DIRECT (1 << 2) @@ -270,6 +287,7 @@ struct writeback_control; #define IOCB_DSYNC (1 << 4) #define IOCB_SYNC (1 << 5) #define IOCB_WRITE (1 << 6) +#define IOCB_NOWAIT (1 << 7) struct kiocb { struct file *ki_filp; @@ -277,23 +295,14 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; -}; + enum rw_hint ki_hint; +} __randomize_layout; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } -static inline int iocb_flags(struct file *file); - -static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) -{ - *kiocb = (struct kiocb) { - .ki_filp = filp, - .ki_flags = iocb_flags(filp), - }; -} - /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet @@ -394,7 +403,8 @@ struct address_space { gfp_t gfp_mask; /* implicit gfp mask for allocations */ struct list_head private_list; /* ditto */ void *private_data; /* ditto */ -} __attribute__((aligned(sizeof(long)))); + errseq_t wb_err; +} __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit @@ -423,6 +433,7 @@ struct block_device { int bd_invalidated; struct gendisk * bd_disk; struct request_queue * bd_queue; + struct backing_dev_info *bd_bdi; struct list_head bd_list; /* * Private data. You must have bd_claim'ed the block_device @@ -436,7 +447,7 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; -}; +} __randomize_layout; /* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache @@ -545,6 +556,8 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 +struct fsnotify_mark_connector; + /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning @@ -591,6 +604,7 @@ struct inode { spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; unsigned int i_blkbits; + enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED @@ -644,7 +658,7 @@ struct inode { #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ - struct hlist_head i_fsnotify_marks; + struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif #if IS_ENABLED(CONFIG_FS_ENCRYPTION) @@ -652,7 +666,12 @@ struct inode { #endif void *i_private; /* fs or device private pointer */ -}; +} __randomize_layout; + +static inline unsigned int i_blocksize(const struct inode *node) +{ + return (1 << node->i_blkbits); +} static inline int inode_unhashed(struct inode *inode) { @@ -840,6 +859,7 @@ struct file { * Must not be taken from IRQ context. */ spinlock_t f_lock; + enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -862,7 +882,9 @@ struct file { struct list_head f_tfile_llink; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; -} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ + errseq_t f_wb_err; +} __randomize_layout + __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; @@ -903,6 +925,8 @@ static inline struct file *get_file(struct file *f) #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ +#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) + /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. @@ -997,7 +1021,7 @@ struct file_lock { int state; /* state of grant or error if -ve */ } afs; } fl_u; -}; +} __randomize_layout; struct file_lock_context { spinlock_t flc_lock; @@ -1013,8 +1037,6 @@ struct file_lock_context { #define OFFT_OFFSET_MAX INT_LIMIT(off_t) #endif -#include <linux/fcntl.h> - extern void send_sigio(struct fown_struct *fown, int fd, int band); /* @@ -1030,14 +1052,14 @@ static inline struct inode *locks_inode(const struct file *f) } #ifdef CONFIG_FILE_LOCKING -extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *); +extern int fcntl_getlk(struct file *, unsigned int, struct flock *); extern int fcntl_setlk(unsigned int, struct file *, unsigned int, - struct flock __user *); + struct flock *); #if BITS_PER_LONG == 32 -extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 __user *); +extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, - struct flock64 __user *); + struct flock64 *); #endif extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); @@ -1241,7 +1263,7 @@ extern void fasync_free(struct fasync_struct *); extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); -extern void f_setown(struct file *filp, unsigned long arg, int force); +extern int f_setown(struct file *filp, unsigned long arg, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); @@ -1320,8 +1342,8 @@ struct super_block { struct sb_writers s_writers; - char s_id[32]; /* Informational name */ - u8 s_uuid[16]; /* UUID */ + char s_id[32]; /* Informational name */ + uuid_t s_uuid; /* UUID */ void *s_fs_info; /* Filesystem private info */ unsigned int s_max_links; @@ -1343,11 +1365,6 @@ struct super_block { */ char *s_subtype; - /* - * Saved mount options for lazy filesystems using - * generic_show_options() - */ - char __rcu *s_options; const struct dentry_operations *s_d_op; /* default d_op for dentries */ /* @@ -1396,7 +1413,7 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ -}; +} __randomize_layout; /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can @@ -1423,7 +1440,6 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); } -extern struct timespec current_fs_time(struct super_block *sb); extern struct timespec current_time(struct inode *inode); /* @@ -1561,6 +1577,9 @@ extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); extern int vfs_whiteout(struct inode *, struct dentry *); +extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, + int open_flag); + /* * VFS file helper functions. */ @@ -1680,7 +1699,7 @@ struct file_operations { u64); ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *, u64); -}; +} __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); @@ -1700,7 +1719,7 @@ struct inode_operations { int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); + int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); @@ -1712,6 +1731,23 @@ struct inode_operations { int (*set_acl)(struct inode *, struct posix_acl *, int); } ____cacheline_aligned; +static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, + struct iov_iter *iter) +{ + return file->f_op->read_iter(kio, iter); +} + +static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio, + struct iov_iter *iter) +{ + return file->f_op->write_iter(kio, iter); +} + +static inline int call_mmap(struct file *file, struct vm_area_struct *vma) +{ + return file->f_op->mmap(file, vma); +} + ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, @@ -1738,19 +1774,6 @@ extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); -static inline int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len) -{ - int ret; - - sb_start_write(file_inode(file_out)->i_sb); - ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len); - sb_end_write(file_inode(file_out)->i_sb); - - return ret; -} - struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); @@ -1853,6 +1876,25 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode) return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid); } +static inline enum rw_hint file_write_hint(struct file *file) +{ + if (file->f_write_hint != WRITE_LIFE_NOT_SET) + return file->f_write_hint; + + return file_inode(file)->i_write_hint; +} + +static inline int iocb_flags(struct file *file); + +static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) +{ + *kiocb = (struct kiocb) { + .ki_filp = filp, + .ki_flags = iocb_flags(filp), + .ki_hint = file_write_hint(filp), + }; +} + /* * Inode state bits. Protected by inode->i_lock * @@ -1909,6 +1951,9 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode) * wb stat updates to grab mapping->tree_lock. See * inode_switch_wb_work_fn() for details. * + * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper + * and work dirs among overlayfs mounts. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -1929,6 +1974,7 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode) #define __I_DIRTY_TIME_EXPIRED 12 #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_WB_SWITCH (1 << 13) +#define I_OVL_INUSE (1 << 14) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) @@ -2102,6 +2148,9 @@ extern int vfs_ustat(dev_t, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); extern bool our_mnt(struct vfsmount *mnt); +extern __printf(2, 3) +int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); +extern int super_setup_bdi(struct super_block *sb); extern int current_umask(void); @@ -2342,6 +2391,7 @@ extern struct kmem_cache *names_cachep; #ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); extern void unregister_blkdev(unsigned int, const char *); +extern void bdev_unhash_inode(dev_t dev); extern struct block_device *bdget(dev_t); extern struct block_device *bdgrab(struct block_device *bdev); extern void bd_set_size(struct block_device *, loff_t size); @@ -2490,9 +2540,11 @@ extern int write_inode_now(struct inode *, int); extern int filemap_fdatawrite(struct address_space *); extern int filemap_flush(struct address_space *); extern int filemap_fdatawait(struct address_space *); -extern void filemap_fdatawait_keep_errors(struct address_space *); +extern int filemap_fdatawait_keep_errors(struct address_space *mapping); extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); +extern bool filemap_range_has_page(struct address_space *, loff_t lstart, + loff_t lend); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); @@ -2502,6 +2554,62 @@ extern int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); extern int filemap_check_errors(struct address_space *mapping); +extern void __filemap_set_wb_err(struct address_space *mapping, int err); +extern int __must_check file_check_and_advance_wb_err(struct file *file); +extern int __must_check file_write_and_wait_range(struct file *file, + loff_t start, loff_t end); + +/** + * filemap_set_wb_err - set a writeback error on an address_space + * @mapping: mapping in which to set writeback error + * @err: error to be set in mapping + * + * When writeback fails in some way, we must record that error so that + * userspace can be informed when fsync and the like are called. We endeavor + * to report errors on any file that was open at the time of the error. Some + * internal callers also need to know when writeback errors have occurred. + * + * When a writeback error occurs, most filesystems will want to call + * filemap_set_wb_err to record the error in the mapping so that it will be + * automatically reported whenever fsync is called on the file. + * + * FIXME: mention FS_* flag here? + */ +static inline void filemap_set_wb_err(struct address_space *mapping, int err) +{ + /* Fastpath for common case of no error */ + if (unlikely(err)) + __filemap_set_wb_err(mapping, err); +} + +/** + * filemap_check_wb_error - has an error occurred since the mark was sampled? + * @mapping: mapping to check for writeback errors + * @since: previously-sampled errseq_t + * + * Grab the errseq_t value from the mapping, and see if it has changed "since" + * the given value was sampled. + * + * If it has then report the latest error set, otherwise return 0. + */ +static inline int filemap_check_wb_err(struct address_space *mapping, + errseq_t since) +{ + return errseq_check(&mapping->wb_err, since); +} + +/** + * filemap_sample_wb_err - sample the current errseq_t to test for later errors + * @mapping: mapping to be sampled + * + * Writeback errors are always reported relative to a particular sample point + * in the past. This function provides those sample points. + */ +static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) +{ + return errseq_sample(&mapping->wb_err); +} + extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); @@ -2561,6 +2669,19 @@ static inline void file_end_write(struct file *file) __sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE); } +static inline int do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 len) +{ + int ret; + + file_start_write(file_out); + ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len); + file_end_write(file_out); + + return ret; +} + /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. @@ -2645,7 +2766,7 @@ static const char * const kernel_read_file_str[] = { static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) { - if (id < 0 || id >= READING_MAX_ID) + if ((unsigned)id >= READING_MAX_ID) return kernel_read_file_str[READING_UNKNOWN]; return kernel_read_file_str[id]; @@ -2752,8 +2873,10 @@ extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); -ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos); -ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos); +ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, + int flags); +ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, + int flags); /* fs/block_dev.c */ extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); @@ -2806,7 +2929,7 @@ enum { DIO_SKIP_DIO_COUNT = 0x08, }; -void dio_end_io(struct bio *bio, int error); +void dio_end_io(struct bio *bio); ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, @@ -2869,8 +2992,8 @@ extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); extern void generic_fillattr(struct inode *, struct kstat *); -int vfs_getattr_nosec(struct path *path, struct kstat *stat); -extern int vfs_getattr(struct path *, struct kstat *); +extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); +extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); @@ -2883,10 +3006,31 @@ extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); -extern int vfs_stat(const char __user *, struct kstat *); -extern int vfs_lstat(const char __user *, struct kstat *); -extern int vfs_fstat(unsigned int, struct kstat *); -extern int vfs_fstatat(int , const char __user *, struct kstat *, int); +extern int vfs_statx(int, const char __user *, int, struct kstat *, u32); +extern int vfs_statx_fd(unsigned int, struct kstat *, u32, unsigned int); + +static inline int vfs_stat(const char __user *filename, struct kstat *stat) +{ + return vfs_statx(AT_FDCWD, filename, AT_NO_AUTOMOUNT, + stat, STATX_BASIC_STATS); +} +static inline int vfs_lstat(const char __user *name, struct kstat *stat) +{ + return vfs_statx(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT, + stat, STATX_BASIC_STATS); +} +static inline int vfs_fstatat(int dfd, const char __user *filename, + struct kstat *stat, int flags) +{ + return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT, + stat, STATX_BASIC_STATS); +} +static inline int vfs_fstat(int fd, struct kstat *stat) +{ + return vfs_statx_fd(fd, stat, STATX_BASIC_STATS, 0); +} + + extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); @@ -2898,7 +3042,7 @@ extern int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, get_block_t *get_block); -extern void get_filesystem(struct file_system_type *fs); +extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); @@ -2916,7 +3060,7 @@ extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); extern int simple_setattr(struct dentry *, struct iattr *); -extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *); +extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); @@ -2944,9 +3088,10 @@ extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; extern void make_empty_dir_inode(struct inode *inode); extern bool is_empty_dir_inode(struct inode *inode); -struct tree_descr { char *name; const struct file_operations *ops; int mode; }; +struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); -extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *); +extern int simple_fill_super(struct super_block *, unsigned long, + const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); @@ -2974,15 +3119,16 @@ extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); -extern int generic_show_options(struct seq_file *m, struct dentry *root); -extern void save_mount_options(struct super_block *sb, char *options); -extern void replace_mount_options(struct super_block *sb, char *options); - static inline bool io_is_direct(struct file *filp) { return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); } +static inline bool vma_is_dax(struct vm_area_struct *vma) +{ + return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); +} + static inline int iocb_flags(struct file *file) { int res = 0; @@ -2997,6 +3143,25 @@ static inline int iocb_flags(struct file *file) return res; } +static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags) +{ + if (unlikely(flags & ~RWF_SUPPORTED)) + return -EOPNOTSUPP; + + if (flags & RWF_NOWAIT) { + if (!(ki->ki_filp->f_mode & FMODE_AIO_NOWAIT)) + return -EOPNOTSUPP; + ki->ki_flags |= IOCB_NOWAIT; + } + if (flags & RWF_HIPRI) + ki->ki_flags |= IOCB_HIPRI; + if (flags & RWF_DSYNC) + ki->ki_flags |= IOCB_DSYNC; + if (flags & RWF_SYNC) + ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC); + return 0; +} + static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 0efc3e62843a..7a026240cbb1 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -12,7 +12,7 @@ struct fs_struct { int umask; int in_exec; struct path root, pwd; -}; +} __randomize_layout; extern struct kmem_cache *fs_cachep; diff --git a/include/linux/fscrypt_common.h b/include/linux/fscrypt_common.h new file mode 100644 index 000000000000..97f738628b36 --- /dev/null +++ b/include/linux/fscrypt_common.h @@ -0,0 +1,141 @@ +/* + * fscrypt_common.h: common declarations for per-file encryption + * + * Copyright (C) 2015, Google, Inc. + * + * Written by Michael Halcrow, 2015. + * Modified by Jaegeuk Kim, 2015. + */ + +#ifndef _LINUX_FSCRYPT_COMMON_H +#define _LINUX_FSCRYPT_COMMON_H + +#include <linux/key.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/bio.h> +#include <linux/dcache.h> +#include <crypto/skcipher.h> +#include <uapi/linux/fs.h> + +#define FS_CRYPTO_BLOCK_SIZE 16 + +struct fscrypt_info; + +struct fscrypt_ctx { + union { + struct { + struct page *bounce_page; /* Ciphertext page */ + struct page *control_page; /* Original page */ + } w; + struct { + struct bio *bio; + struct work_struct work; + } r; + struct list_head free_list; /* Free list */ + }; + u8 flags; /* Flags */ +}; + +/** + * For encrypted symlinks, the ciphertext length is stored at the beginning + * of the string in little-endian format. + */ +struct fscrypt_symlink_data { + __le16 len; + char encrypted_path[1]; +} __packed; + +struct fscrypt_str { + unsigned char *name; + u32 len; +}; + +struct fscrypt_name { + const struct qstr *usr_fname; + struct fscrypt_str disk_name; + u32 hash; + u32 minor_hash; + struct fscrypt_str crypto_buf; +}; + +#define FSTR_INIT(n, l) { .name = n, .len = l } +#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) +#define fname_name(p) ((p)->disk_name.name) +#define fname_len(p) ((p)->disk_name.len) + +/* + * fscrypt superblock flags + */ +#define FS_CFLG_OWN_PAGES (1U << 1) + +/* + * crypto opertions for filesystems + */ +struct fscrypt_operations { + unsigned int flags; + const char *key_prefix; + int (*get_context)(struct inode *, void *, size_t); + int (*set_context)(struct inode *, const void *, size_t, void *); + bool (*dummy_context)(struct inode *); + bool (*is_encrypted)(struct inode *); + bool (*empty_dir)(struct inode *); + unsigned (*max_namelen)(struct inode *); +}; + +/* Maximum value for the third parameter of fscrypt_operations.set_context(). */ +#define FSCRYPT_SET_CONTEXT_MAX_SIZE 28 + +static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +{ + if (inode->i_sb->s_cop->dummy_context && + inode->i_sb->s_cop->dummy_context(inode)) + return true; + return false; +} + +static inline bool fscrypt_valid_enc_modes(u32 contents_mode, + u32 filenames_mode) +{ + if (contents_mode == FS_ENCRYPTION_MODE_AES_128_CBC && + filenames_mode == FS_ENCRYPTION_MODE_AES_128_CTS) + return true; + + if (contents_mode == FS_ENCRYPTION_MODE_AES_256_XTS && + filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS) + return true; + + return false; +} + +static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) +{ + if (str->len == 1 && str->name[0] == '.') + return true; + + if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') + return true; + + return false; +} + +static inline struct page *fscrypt_control_page(struct page *page) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + return ((struct fscrypt_ctx *)page_private(page))->w.control_page; +#else + WARN_ON_ONCE(1); + return ERR_PTR(-EINVAL); +#endif +} + +static inline int fscrypt_has_encryption_key(const struct inode *inode) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + return (inode->i_crypt_info != NULL); +#else + return 0; +#endif +} + +#endif /* _LINUX_FSCRYPT_COMMON_H */ diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h new file mode 100644 index 000000000000..ec406aed2f2f --- /dev/null +++ b/include/linux/fscrypt_notsupp.h @@ -0,0 +1,177 @@ +/* + * fscrypt_notsupp.h + * + * This stubs out the fscrypt functions for filesystems configured without + * encryption support. + */ + +#ifndef _LINUX_FSCRYPT_NOTSUPP_H +#define _LINUX_FSCRYPT_NOTSUPP_H + +#include <linux/fscrypt_common.h> + +/* crypto.c */ +static inline struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, + gfp_t gfp_flags) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx) +{ + return; +} + +static inline struct page *fscrypt_encrypt_page(const struct inode *inode, + struct page *page, + unsigned int len, + unsigned int offs, + u64 lblk_num, gfp_t gfp_flags) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline int fscrypt_decrypt_page(const struct inode *inode, + struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num) +{ + return -EOPNOTSUPP; +} + + +static inline void fscrypt_restore_control_page(struct page *page) +{ + return; +} + +static inline void fscrypt_set_d_op(struct dentry *dentry) +{ + return; +} + +static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) +{ + return; +} + +/* policy.c */ +static inline int fscrypt_ioctl_set_policy(struct file *filp, + const void __user *arg) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_has_permitted_context(struct inode *parent, + struct inode *child) +{ + return 0; +} + +static inline int fscrypt_inherit_context(struct inode *parent, + struct inode *child, + void *fs_data, bool preload) +{ + return -EOPNOTSUPP; +} + +/* keyinfo.c */ +static inline int fscrypt_get_encryption_info(struct inode *inode) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_put_encryption_info(struct inode *inode, + struct fscrypt_info *ci) +{ + return; +} + + /* fname.c */ +static inline int fscrypt_setup_filename(struct inode *dir, + const struct qstr *iname, + int lookup, struct fscrypt_name *fname) +{ + if (dir->i_sb->s_cop->is_encrypted(dir)) + return -EOPNOTSUPP; + + memset(fname, 0, sizeof(struct fscrypt_name)); + fname->usr_fname = iname; + fname->disk_name.name = (unsigned char *)iname->name; + fname->disk_name.len = iname->len; + return 0; +} + +static inline void fscrypt_free_filename(struct fscrypt_name *fname) +{ + return; +} + +static inline u32 fscrypt_fname_encrypted_size(const struct inode *inode, + u32 ilen) +{ + /* never happens */ + WARN_ON(1); + return 0; +} + +static inline int fscrypt_fname_alloc_buffer(const struct inode *inode, + u32 ilen, + struct fscrypt_str *crypto_str) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) +{ + return; +} + +static inline int fscrypt_fname_disk_to_usr(struct inode *inode, + u32 hash, u32 minor_hash, + const struct fscrypt_str *iname, + struct fscrypt_str *oname) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_fname_usr_to_disk(struct inode *inode, + const struct qstr *iname, + struct fscrypt_str *oname) +{ + return -EOPNOTSUPP; +} + +static inline bool fscrypt_match_name(const struct fscrypt_name *fname, + const u8 *de_name, u32 de_name_len) +{ + /* Encryption support disabled; use standard comparison */ + if (de_name_len != fname->disk_name.len) + return false; + return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); +} + +/* bio.c */ +static inline void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, + struct bio *bio) +{ + return; +} + +static inline void fscrypt_pullback_bio_page(struct page **page, bool restore) +{ + return; +} + +static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, + sector_t pblk, unsigned int len) +{ + return -EOPNOTSUPP; +} + +#endif /* _LINUX_FSCRYPT_NOTSUPP_H */ diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h new file mode 100644 index 000000000000..32e2fcf13b01 --- /dev/null +++ b/include/linux/fscrypt_supp.h @@ -0,0 +1,145 @@ +/* + * fscrypt_supp.h + * + * This is included by filesystems configured with encryption support. + */ + +#ifndef _LINUX_FSCRYPT_SUPP_H +#define _LINUX_FSCRYPT_SUPP_H + +#include <linux/fscrypt_common.h> + +/* crypto.c */ +extern struct kmem_cache *fscrypt_info_cachep; +extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); +extern void fscrypt_release_ctx(struct fscrypt_ctx *); +extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, + unsigned int, unsigned int, + u64, gfp_t); +extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int, + unsigned int, u64); +extern void fscrypt_restore_control_page(struct page *); + +extern const struct dentry_operations fscrypt_d_ops; + +static inline void fscrypt_set_d_op(struct dentry *dentry) +{ + d_set_d_op(dentry, &fscrypt_d_ops); +} + +static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY; + spin_unlock(&dentry->d_lock); +} + +/* policy.c */ +extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); +extern int fscrypt_ioctl_get_policy(struct file *, void __user *); +extern int fscrypt_has_permitted_context(struct inode *, struct inode *); +extern int fscrypt_inherit_context(struct inode *, struct inode *, + void *, bool); +/* keyinfo.c */ +extern int fscrypt_get_encryption_info(struct inode *); +extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *); + +/* fname.c */ +extern int fscrypt_setup_filename(struct inode *, const struct qstr *, + int lookup, struct fscrypt_name *); + +static inline void fscrypt_free_filename(struct fscrypt_name *fname) +{ + kfree(fname->crypto_buf.name); +} + +extern u32 fscrypt_fname_encrypted_size(const struct inode *, u32); +extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, + struct fscrypt_str *); +extern void fscrypt_fname_free_buffer(struct fscrypt_str *); +extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32, + const struct fscrypt_str *, struct fscrypt_str *); +extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *, + struct fscrypt_str *); + +#define FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE 32 + +/* Extracts the second-to-last ciphertext block; see explanation below */ +#define FSCRYPT_FNAME_DIGEST(name, len) \ + ((name) + round_down((len) - FS_CRYPTO_BLOCK_SIZE - 1, \ + FS_CRYPTO_BLOCK_SIZE)) + +#define FSCRYPT_FNAME_DIGEST_SIZE FS_CRYPTO_BLOCK_SIZE + +/** + * fscrypt_digested_name - alternate identifier for an on-disk filename + * + * When userspace lists an encrypted directory without access to the key, + * filenames whose ciphertext is longer than FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE + * bytes are shown in this abbreviated form (base64-encoded) rather than as the + * full ciphertext (base64-encoded). This is necessary to allow supporting + * filenames up to NAME_MAX bytes, since base64 encoding expands the length. + * + * To make it possible for filesystems to still find the correct directory entry + * despite not knowing the full on-disk name, we encode any filesystem-specific + * 'hash' and/or 'minor_hash' which the filesystem may need for its lookups, + * followed by the second-to-last ciphertext block of the filename. Due to the + * use of the CBC-CTS encryption mode, the second-to-last ciphertext block + * depends on the full plaintext. (Note that ciphertext stealing causes the + * last two blocks to appear "flipped".) This makes accidental collisions very + * unlikely: just a 1 in 2^128 chance for two filenames to collide even if they + * share the same filesystem-specific hashes. + * + * However, this scheme isn't immune to intentional collisions, which can be + * created by anyone able to create arbitrary plaintext filenames and view them + * without the key. Making the "digest" be a real cryptographic hash like + * SHA-256 over the full ciphertext would prevent this, although it would be + * less efficient and harder to implement, especially since the filesystem would + * need to calculate it for each directory entry examined during a search. + */ +struct fscrypt_digested_name { + u32 hash; + u32 minor_hash; + u8 digest[FSCRYPT_FNAME_DIGEST_SIZE]; +}; + +/** + * fscrypt_match_name() - test whether the given name matches a directory entry + * @fname: the name being searched for + * @de_name: the name from the directory entry + * @de_name_len: the length of @de_name in bytes + * + * Normally @fname->disk_name will be set, and in that case we simply compare + * that to the name stored in the directory entry. The only exception is that + * if we don't have the key for an encrypted directory and a filename in it is + * very long, then we won't have the full disk_name and we'll instead need to + * match against the fscrypt_digested_name. + * + * Return: %true if the name matches, otherwise %false. + */ +static inline bool fscrypt_match_name(const struct fscrypt_name *fname, + const u8 *de_name, u32 de_name_len) +{ + if (unlikely(!fname->disk_name.name)) { + const struct fscrypt_digested_name *n = + (const void *)fname->crypto_buf.name; + if (WARN_ON_ONCE(fname->usr_fname->name[0] != '_')) + return false; + if (de_name_len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) + return false; + return !memcmp(FSCRYPT_FNAME_DIGEST(de_name, de_name_len), + n->digest, FSCRYPT_FNAME_DIGEST_SIZE); + } + + if (de_name_len != fname->disk_name.len) + return false; + return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len); +} + +/* bio.c */ +extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); +extern void fscrypt_pullback_bio_page(struct page **, bool); +extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, + unsigned int); + +#endif /* _LINUX_FSCRYPT_SUPP_H */ diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h deleted file mode 100644 index c074b670aa99..000000000000 --- a/include/linux/fscrypto.h +++ /dev/null @@ -1,345 +0,0 @@ -/* - * General per-file encryption definition - * - * Copyright (C) 2015, Google, Inc. - * - * Written by Michael Halcrow, 2015. - * Modified by Jaegeuk Kim, 2015. - */ - -#ifndef _LINUX_FSCRYPTO_H -#define _LINUX_FSCRYPTO_H - -#include <linux/key.h> -#include <linux/fs.h> -#include <linux/mm.h> -#include <linux/bio.h> -#include <linux/dcache.h> -#include <crypto/skcipher.h> -#include <uapi/linux/fs.h> - -#define FS_CRYPTO_BLOCK_SIZE 16 - -struct fscrypt_info; - -struct fscrypt_ctx { - union { - struct { - struct page *bounce_page; /* Ciphertext page */ - struct page *control_page; /* Original page */ - } w; - struct { - struct bio *bio; - struct work_struct work; - } r; - struct list_head free_list; /* Free list */ - }; - u8 flags; /* Flags */ - u8 mode; /* Encryption mode for tfm */ -}; - -/** - * For encrypted symlinks, the ciphertext length is stored at the beginning - * of the string in little-endian format. - */ -struct fscrypt_symlink_data { - __le16 len; - char encrypted_path[1]; -} __packed; - -/** - * This function is used to calculate the disk space required to - * store a filename of length l in encrypted symlink format. - */ -static inline u32 fscrypt_symlink_data_len(u32 l) -{ - if (l < FS_CRYPTO_BLOCK_SIZE) - l = FS_CRYPTO_BLOCK_SIZE; - return (l + sizeof(struct fscrypt_symlink_data) - 1); -} - -struct fscrypt_str { - unsigned char *name; - u32 len; -}; - -struct fscrypt_name { - const struct qstr *usr_fname; - struct fscrypt_str disk_name; - u32 hash; - u32 minor_hash; - struct fscrypt_str crypto_buf; -}; - -#define FSTR_INIT(n, l) { .name = n, .len = l } -#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) -#define fname_name(p) ((p)->disk_name.name) -#define fname_len(p) ((p)->disk_name.len) - -/* - * fscrypt superblock flags - */ -#define FS_CFLG_OWN_PAGES (1U << 1) - -/* - * crypto opertions for filesystems - */ -struct fscrypt_operations { - unsigned int flags; - int (*get_context)(struct inode *, void *, size_t); - int (*key_prefix)(struct inode *, u8 **); - int (*prepare_context)(struct inode *); - int (*set_context)(struct inode *, const void *, size_t, void *); - int (*dummy_context)(struct inode *); - bool (*is_encrypted)(struct inode *); - bool (*empty_dir)(struct inode *); - unsigned (*max_namelen)(struct inode *); -}; - -static inline bool fscrypt_dummy_context_enabled(struct inode *inode) -{ - if (inode->i_sb->s_cop->dummy_context && - inode->i_sb->s_cop->dummy_context(inode)) - return true; - return false; -} - -static inline bool fscrypt_valid_contents_enc_mode(u32 mode) -{ - return (mode == FS_ENCRYPTION_MODE_AES_256_XTS); -} - -static inline bool fscrypt_valid_filenames_enc_mode(u32 mode) -{ - return (mode == FS_ENCRYPTION_MODE_AES_256_CTS); -} - -static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) -{ - if (str->len == 1 && str->name[0] == '.') - return true; - - if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') - return true; - - return false; -} - -static inline struct page *fscrypt_control_page(struct page *page) -{ -#if IS_ENABLED(CONFIG_FS_ENCRYPTION) - return ((struct fscrypt_ctx *)page_private(page))->w.control_page; -#else - WARN_ON_ONCE(1); - return ERR_PTR(-EINVAL); -#endif -} - -static inline int fscrypt_has_encryption_key(const struct inode *inode) -{ -#if IS_ENABLED(CONFIG_FS_ENCRYPTION) - return (inode->i_crypt_info != NULL); -#else - return 0; -#endif -} - -static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) -{ -#if IS_ENABLED(CONFIG_FS_ENCRYPTION) - spin_lock(&dentry->d_lock); - dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY; - spin_unlock(&dentry->d_lock); -#endif -} - -#if IS_ENABLED(CONFIG_FS_ENCRYPTION) -extern const struct dentry_operations fscrypt_d_ops; -#endif - -static inline void fscrypt_set_d_op(struct dentry *dentry) -{ -#if IS_ENABLED(CONFIG_FS_ENCRYPTION) - d_set_d_op(dentry, &fscrypt_d_ops); -#endif -} - -#if IS_ENABLED(CONFIG_FS_ENCRYPTION) -/* crypto.c */ -extern struct kmem_cache *fscrypt_info_cachep; -extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); -extern void fscrypt_release_ctx(struct fscrypt_ctx *); -extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, - unsigned int, unsigned int, - u64, gfp_t); -extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int, - unsigned int, u64); -extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); -extern void fscrypt_pullback_bio_page(struct page **, bool); -extern void fscrypt_restore_control_page(struct page *); -extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, - unsigned int); -/* policy.c */ -extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); -extern int fscrypt_ioctl_get_policy(struct file *, void __user *); -extern int fscrypt_has_permitted_context(struct inode *, struct inode *); -extern int fscrypt_inherit_context(struct inode *, struct inode *, - void *, bool); -/* keyinfo.c */ -extern int fscrypt_get_encryption_info(struct inode *); -extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *); - -/* fname.c */ -extern int fscrypt_setup_filename(struct inode *, const struct qstr *, - int lookup, struct fscrypt_name *); -extern void fscrypt_free_filename(struct fscrypt_name *); -extern u32 fscrypt_fname_encrypted_size(const struct inode *, u32); -extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, - struct fscrypt_str *); -extern void fscrypt_fname_free_buffer(struct fscrypt_str *); -extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32, - const struct fscrypt_str *, struct fscrypt_str *); -extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *, - struct fscrypt_str *); -#endif - -/* crypto.c */ -static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(const struct inode *i, - gfp_t f) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void fscrypt_notsupp_release_ctx(struct fscrypt_ctx *c) -{ - return; -} - -static inline struct page *fscrypt_notsupp_encrypt_page(const struct inode *i, - struct page *p, - unsigned int len, - unsigned int offs, - u64 lblk_num, gfp_t f) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline int fscrypt_notsupp_decrypt_page(const struct inode *i, struct page *p, - unsigned int len, unsigned int offs, - u64 lblk_num) -{ - return -EOPNOTSUPP; -} - -static inline void fscrypt_notsupp_decrypt_bio_pages(struct fscrypt_ctx *c, - struct bio *b) -{ - return; -} - -static inline void fscrypt_notsupp_pullback_bio_page(struct page **p, bool b) -{ - return; -} - -static inline void fscrypt_notsupp_restore_control_page(struct page *p) -{ - return; -} - -static inline int fscrypt_notsupp_zeroout_range(const struct inode *i, pgoff_t p, - sector_t s, unsigned int f) -{ - return -EOPNOTSUPP; -} - -/* policy.c */ -static inline int fscrypt_notsupp_ioctl_set_policy(struct file *f, - const void __user *arg) -{ - return -EOPNOTSUPP; -} - -static inline int fscrypt_notsupp_ioctl_get_policy(struct file *f, - void __user *arg) -{ - return -EOPNOTSUPP; -} - -static inline int fscrypt_notsupp_has_permitted_context(struct inode *p, - struct inode *i) -{ - return 0; -} - -static inline int fscrypt_notsupp_inherit_context(struct inode *p, - struct inode *i, void *v, bool b) -{ - return -EOPNOTSUPP; -} - -/* keyinfo.c */ -static inline int fscrypt_notsupp_get_encryption_info(struct inode *i) -{ - return -EOPNOTSUPP; -} - -static inline void fscrypt_notsupp_put_encryption_info(struct inode *i, - struct fscrypt_info *f) -{ - return; -} - - /* fname.c */ -static inline int fscrypt_notsupp_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, struct fscrypt_name *fname) -{ - if (dir->i_sb->s_cop->is_encrypted(dir)) - return -EOPNOTSUPP; - - memset(fname, 0, sizeof(struct fscrypt_name)); - fname->usr_fname = iname; - fname->disk_name.name = (unsigned char *)iname->name; - fname->disk_name.len = iname->len; - return 0; -} - -static inline void fscrypt_notsupp_free_filename(struct fscrypt_name *fname) -{ - return; -} - -static inline u32 fscrypt_notsupp_fname_encrypted_size(struct inode *i, u32 s) -{ - /* never happens */ - WARN_ON(1); - return 0; -} - -static inline int fscrypt_notsupp_fname_alloc_buffer(struct inode *inode, - u32 ilen, struct fscrypt_str *crypto_str) -{ - return -EOPNOTSUPP; -} - -static inline void fscrypt_notsupp_fname_free_buffer(struct fscrypt_str *c) -{ - return; -} - -static inline int fscrypt_notsupp_fname_disk_to_usr(struct inode *inode, - u32 hash, u32 minor_hash, - const struct fscrypt_str *iname, - struct fscrypt_str *oname) -{ - return -EOPNOTSUPP; -} - -static inline int fscrypt_notsupp_fname_usr_to_disk(struct inode *inode, - const struct qstr *iname, - struct fscrypt_str *oname) -{ - return -EOPNOTSUPP; -} -#endif /* _LINUX_FSCRYPTO_H */ diff --git a/include/linux/fsi.h b/include/linux/fsi.h new file mode 100644 index 000000000000..141fd38d061f --- /dev/null +++ b/include/linux/fsi.h @@ -0,0 +1,83 @@ +/* FSI device & driver interfaces + * + * Copyright (C) IBM Corporation 2016 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef LINUX_FSI_H +#define LINUX_FSI_H + +#include <linux/device.h> + +struct fsi_device { + struct device dev; + u8 engine_type; + u8 version; + u8 unit; + struct fsi_slave *slave; + uint32_t addr; + uint32_t size; +}; + +extern int fsi_device_read(struct fsi_device *dev, uint32_t addr, + void *val, size_t size); +extern int fsi_device_write(struct fsi_device *dev, uint32_t addr, + const void *val, size_t size); +extern int fsi_device_peek(struct fsi_device *dev, void *val); + +struct fsi_device_id { + u8 engine_type; + u8 version; +}; + +#define FSI_VERSION_ANY 0 + +#define FSI_DEVICE(t) \ + .engine_type = (t), .version = FSI_VERSION_ANY, + +#define FSI_DEVICE_VERSIONED(t, v) \ + .engine_type = (t), .version = (v), + +struct fsi_driver { + struct device_driver drv; + const struct fsi_device_id *id_table; +}; + +#define to_fsi_dev(devp) container_of(devp, struct fsi_device, dev) +#define to_fsi_drv(drvp) container_of(drvp, struct fsi_driver, drv) + +extern int fsi_driver_register(struct fsi_driver *fsi_drv); +extern void fsi_driver_unregister(struct fsi_driver *fsi_drv); + +/* module_fsi_driver() - Helper macro for drivers that don't do + * anything special in module init/exit. This eliminates a lot of + * boilerplate. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit() + */ +#define module_fsi_driver(__fsi_driver) \ + module_driver(__fsi_driver, fsi_driver_register, \ + fsi_driver_unregister) + +/* direct slave API */ +extern int fsi_slave_claim_range(struct fsi_slave *slave, + uint32_t addr, uint32_t size); +extern void fsi_slave_release_range(struct fsi_slave *slave, + uint32_t addr, uint32_t size); +extern int fsi_slave_read(struct fsi_slave *slave, uint32_t addr, + void *val, size_t size); +extern int fsi_slave_write(struct fsi_slave *slave, uint32_t addr, + const void *val, size_t size); + + + +extern struct bus_type fsi_bus_type; + +#endif /* LINUX_FSI_H */ diff --git a/include/linux/fsl-diu-fb.h b/include/linux/fsl-diu-fb.h index a1e8277120c7..c46eab5bc893 100644 --- a/include/linux/fsl-diu-fb.h +++ b/include/linux/fsl-diu-fb.h @@ -73,7 +73,7 @@ struct diu_ad { /* Word 0(32-bit) in DDR memory */ /* __u16 comp; */ /* __u16 pixel_s:2; */ -/* __u16 pallete:1; */ +/* __u16 palette:1; */ /* __u16 red_c:2; */ /* __u16 green_c:2; */ /* __u16 blue_c:2; */ @@ -142,7 +142,7 @@ struct diu_ad { struct diu { __be32 desc[3]; __be32 gamma; - __be32 pallete; + __be32 palette; __be32 cursor; __be32 curs_pos; __be32 diu_mode; diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h index 3f9778cbc79d..c332f0a45607 100644 --- a/include/linux/fsl_ifc.h +++ b/include/linux/fsl_ifc.h @@ -733,8 +733,12 @@ struct fsl_ifc_nand { __be32 nand_erattr1; u32 res19[0x10]; __be32 nand_fsr; - u32 res20[0x3]; - __be32 nand_eccstat[6]; + u32 res20; + /* The V1 nand_eccstat is actually 4 words that overlaps the + * V2 nand_eccstat. + */ + __be32 v1_nand_eccstat[2]; + __be32 v2_nand_eccstat[6]; u32 res21[0x1c]; __be32 nanndcr; u32 res22[0x2]; diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index b43d3f5bd9ea..b78aa7ac77ce 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -293,35 +293,4 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) } } -#if defined(CONFIG_FSNOTIFY) /* notify helpers */ - -/* - * fsnotify_oldname_init - save off the old filename before we change it - */ -static inline const unsigned char *fsnotify_oldname_init(const unsigned char *name) -{ - return kstrdup(name, GFP_KERNEL); -} - -/* - * fsnotify_oldname_free - free the name we got from fsnotify_oldname_init - */ -static inline void fsnotify_oldname_free(const unsigned char *old_name) -{ - kfree(old_name); -} - -#else /* CONFIG_FSNOTIFY */ - -static inline const char *fsnotify_oldname_init(const unsigned char *name) -{ - return NULL; -} - -static inline void fsnotify_oldname_free(const unsigned char *old_name) -{ -} - -#endif /* CONFIG_FSNOTIFY */ - #endif /* _LINUX_FS_NOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 487246546ebe..c6c69318752b 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -16,6 +16,7 @@ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> +#include <linux/user_namespace.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily @@ -79,6 +80,7 @@ struct fsnotify_event; struct fsnotify_mark; struct fsnotify_event_private_data; struct fsnotify_fname; +struct fsnotify_iter_info; /* * Each group much define these ops. The fsnotify infrastructure will call @@ -97,10 +99,13 @@ struct fsnotify_ops { struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, const void *data, int data_type, - const unsigned char *file_name, u32 cookie); + const unsigned char *file_name, u32 cookie, + struct fsnotify_iter_info *iter_info); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_event *event); + /* called on final put+free to free memory */ + void (*free_mark)(struct fsnotify_mark *mark); }; /* @@ -162,6 +167,8 @@ struct fsnotify_group { struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ + atomic_t user_waits; /* Number of tasks waiting for user + * response */ /* groups can define private fields here or use the void *private */ union { @@ -170,7 +177,7 @@ struct fsnotify_group { struct inotify_group_private_data { spinlock_t idr_lock; struct idr idr; - struct user_struct *user; + struct ucounts *ucounts; } inotify_data; #endif #ifdef CONFIG_FANOTIFY @@ -194,6 +201,30 @@ struct fsnotify_group { #define FSNOTIFY_EVENT_INODE 2 /* + * Inode / vfsmount point to this structure which tracks all marks attached to + * the inode / vfsmount. The reference to inode / vfsmount is held by this + * structure. We destroy this structure when there are no more marks attached + * to it. The structure is protected by fsnotify_mark_srcu. + */ +struct fsnotify_mark_connector { + spinlock_t lock; +#define FSNOTIFY_OBJ_TYPE_INODE 0x01 +#define FSNOTIFY_OBJ_TYPE_VFSMOUNT 0x02 +#define FSNOTIFY_OBJ_ALL_TYPES (FSNOTIFY_OBJ_TYPE_INODE | \ + FSNOTIFY_OBJ_TYPE_VFSMOUNT) + unsigned int flags; /* Type of object [lock] */ + union { /* Object pointer [lock] */ + struct inode *inode; + struct vfsmount *mnt; + }; + union { + struct hlist_head list; + /* Used listing heads to free after srcu period expires */ + struct fsnotify_mark_connector *destroy_next; + }; +}; + +/* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. @@ -222,22 +253,16 @@ struct fsnotify_mark { struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; - /* List of marks for inode / vfsmount [obj_lock] */ + /* List of marks for inode / vfsmount [connector->lock, mark ref] */ struct hlist_node obj_list; - union { /* Object pointer [mark->lock, group->mark_mutex] */ - struct inode *inode; /* inode this mark is associated with */ - struct vfsmount *mnt; /* vfsmount this mark is associated with */ - }; + /* Head of list of marks for an object [mark ref] */ + struct fsnotify_mark_connector *connector; /* Events types to ignore [mark->lock, group->mark_mutex] */ __u32 ignored_mask; -#define FSNOTIFY_MARK_FLAG_INODE 0x01 -#define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02 -#define FSNOTIFY_MARK_FLAG_OBJECT_PINNED 0x04 -#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x08 -#define FSNOTIFY_MARK_FLAG_ALIVE 0x10 -#define FSNOTIFY_MARK_FLAG_ATTACHED 0x20 +#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x01 +#define FSNOTIFY_MARK_FLAG_ALIVE 0x02 +#define FSNOTIFY_MARK_FLAG_ATTACHED 0x04 unsigned int flags; /* flags [mark->lock] */ - void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */ }; #ifdef CONFIG_FSNOTIFY @@ -314,23 +339,18 @@ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group /* functions used to manipulate the marks attached to inodes */ -/* run all marks associated with a vfsmount and update mnt->mnt_fsnotify_mask */ -extern void fsnotify_recalc_vfsmount_mask(struct vfsmount *mnt); -/* run all marks associated with an inode and update inode->i_fsnotify_mask */ -extern void fsnotify_recalc_inode_mask(struct inode *inode); -extern void fsnotify_init_mark(struct fsnotify_mark *mark, void (*free_mark)(struct fsnotify_mark *mark)); -/* find (and take a reference) to a mark associated with group and inode */ -extern struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group, struct inode *inode); -/* find (and take a reference) to a mark associated with group and vfsmount */ -extern struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group, struct vfsmount *mnt); -/* set the ignored_mask of a mark */ -extern void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mask); -/* set the mask of a mark (might pin the object into memory */ -extern void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask); -/* attach the mark to both the group and the inode */ -extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, - struct inode *inode, struct vfsmount *mnt, int allow_dups); -extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, struct fsnotify_group *group, +/* Calculate mask of events for a list of marks */ +extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); +extern void fsnotify_init_mark(struct fsnotify_mark *mark, + struct fsnotify_group *group); +/* Find mark belonging to given group in the list of marks */ +extern struct fsnotify_mark *fsnotify_find_mark( + struct fsnotify_mark_connector __rcu **connp, + struct fsnotify_group *group); +/* attach the mark to the inode or vfsmount */ +extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct inode *inode, + struct vfsmount *mnt, int allow_dups); +extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, struct inode *inode, struct vfsmount *mnt, int allow_dups); /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, @@ -339,15 +359,23 @@ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, extern void fsnotify_detach_mark(struct fsnotify_mark *mark); /* free mark */ extern void fsnotify_free_mark(struct fsnotify_mark *mark); +/* run all the marks in a group, and clear all of the marks attached to given object type */ +extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int type); /* run all the marks in a group, and clear all of the vfsmount marks */ -extern void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group); +static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) +{ + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); +} /* run all the marks in a group, and clear all of the inode marks */ -extern void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group); -/* run all the marks in a group, and clear all of the marks where mark->flags & flags is true*/ -extern void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, unsigned int flags); +static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) +{ + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); +} extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); extern void fsnotify_unmount_inodes(struct super_block *sb); +extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); +extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); /* put here because inotify does some weird stuff when destroying watches */ extern void fsnotify_init_event(struct fsnotify_event *event, diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 3633e8beff39..6383115e9d2c 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -42,8 +42,10 @@ /* Main tracing buffer and events set up */ #ifdef CONFIG_TRACING void trace_init(void); +void early_trace_init(void); #else static inline void trace_init(void) { } +static inline void early_trace_init(void) { } #endif struct module; @@ -70,7 +72,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION_SAFE, STUB and * IPMODIFY are a kind of attribute flags which can be set only before * registering the ftrace_ops, and can not be modified while registered. - * Changing those attribute flags after regsitering ftrace_ops will + * Changing those attribute flags after registering ftrace_ops will * cause unexpected results. * * ENABLED - set/unset when ftrace_ops is registered/unregistered @@ -117,6 +119,8 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * for any of the functions that this ops will be registered for, then * this ops will fail to register or set_filter_ip. * PID - Is affected by set_ftrace_pid (allows filtering on those pids) + * RCU - Set when the ops can only be called when RCU is watching. + * TRACE_ARRAY - The ops->private points to a trace_array descriptor. */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -135,15 +139,20 @@ enum { FTRACE_OPS_FL_IPMODIFY = 1 << 13, FTRACE_OPS_FL_PID = 1 << 14, FTRACE_OPS_FL_RCU = 1 << 15, + FTRACE_OPS_FL_TRACE_ARRAY = 1 << 16, }; #ifdef CONFIG_DYNAMIC_FTRACE /* The hash used to know what functions callbacks trace */ struct ftrace_ops_hash { - struct ftrace_hash *notrace_hash; - struct ftrace_hash *filter_hash; + struct ftrace_hash __rcu *notrace_hash; + struct ftrace_hash __rcu *filter_hash; struct mutex regex_lock; }; + +void ftrace_free_init_mem(void); +#else +static inline void ftrace_free_init_mem(void) { } #endif /* @@ -159,7 +168,7 @@ struct ftrace_ops_hash { */ struct ftrace_ops { ftrace_func_t func; - struct ftrace_ops *next; + struct ftrace_ops __rcu *next; unsigned long flags; void *private; ftrace_func_t saved_func; @@ -260,6 +269,7 @@ static inline int ftrace_nr_registered_ops(void) } static inline void clear_ftrace_function(void) { } static inline void ftrace_kill(void) { } +static inline void ftrace_free_init_mem(void) { } #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_STACK_TRACER @@ -279,15 +289,45 @@ int stack_trace_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -#endif -struct ftrace_func_command { - struct list_head list; - char *name; - int (*func)(struct ftrace_hash *hash, - char *func, char *cmd, - char *params, int enable); -}; +/* DO NOT MODIFY THIS VARIABLE DIRECTLY! */ +DECLARE_PER_CPU(int, disable_stack_tracer); + +/** + * stack_tracer_disable - temporarily disable the stack tracer + * + * There's a few locations (namely in RCU) where stack tracing + * cannot be executed. This function is used to disable stack + * tracing during those critical sections. + * + * This function must be called with preemption or interrupts + * disabled and stack_tracer_enable() must be called shortly after + * while preemption or interrupts are still disabled. + */ +static inline void stack_tracer_disable(void) +{ + /* Preemption or interupts must be disabled */ + if (IS_ENABLED(CONFIG_PREEMPT_DEBUG)) + WARN_ON_ONCE(!preempt_count() || !irqs_disabled()); + this_cpu_inc(disable_stack_tracer); +} + +/** + * stack_tracer_enable - re-enable the stack tracer + * + * After stack_tracer_disable() is called, stack_tracer_enable() + * must be called shortly afterward. + */ +static inline void stack_tracer_enable(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_DEBUG)) + WARN_ON_ONCE(!preempt_count() || !irqs_disabled()); + this_cpu_dec(disable_stack_tracer); +} +#else +static inline void stack_tracer_disable(void) { } +static inline void stack_tracer_enable(void) { } +#endif #ifdef CONFIG_DYNAMIC_FTRACE @@ -315,30 +355,6 @@ void ftrace_bug(int err, struct dyn_ftrace *rec); struct seq_file; -struct ftrace_probe_ops { - void (*func)(unsigned long ip, - unsigned long parent_ip, - void **data); - int (*init)(struct ftrace_probe_ops *ops, - unsigned long ip, void **data); - void (*free)(struct ftrace_probe_ops *ops, - unsigned long ip, void **data); - int (*print)(struct seq_file *m, - unsigned long ip, - struct ftrace_probe_ops *ops, - void *data); -}; - -extern int -register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, - void *data); -extern void -unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, - void *data); -extern void -unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops); -extern void unregister_ftrace_function_probe_all(char *glob); - extern int ftrace_text_reserved(const void *start, const void *end); extern int ftrace_nr_registered_ops(void); @@ -400,9 +416,6 @@ void ftrace_set_global_notrace(unsigned char *buf, int len, int reset); void ftrace_free_filter(struct ftrace_ops *ops); void ftrace_ops_set_global_filter(struct ftrace_ops *ops); -int register_ftrace_command(struct ftrace_func_command *cmd); -int unregister_ftrace_command(struct ftrace_func_command *cmd); - enum { FTRACE_UPDATE_CALLS = (1 << 0), FTRACE_DISABLE_CALLS = (1 << 1), @@ -433,9 +446,10 @@ enum { FTRACE_ITER_FILTER = (1 << 0), FTRACE_ITER_NOTRACE = (1 << 1), FTRACE_ITER_PRINTALL = (1 << 2), - FTRACE_ITER_DO_HASH = (1 << 3), - FTRACE_ITER_HASH = (1 << 4), - FTRACE_ITER_ENABLED = (1 << 5), + FTRACE_ITER_DO_PROBES = (1 << 3), + FTRACE_ITER_PROBE = (1 << 4), + FTRACE_ITER_MOD = (1 << 5), + FTRACE_ITER_ENABLED = (1 << 6), }; void arch_ftrace_update_code(int command); @@ -618,14 +632,6 @@ static inline void ftrace_enable_daemon(void) { } static inline void ftrace_module_init(struct module *mod) { } static inline void ftrace_module_enable(struct module *mod) { } static inline void ftrace_release_mod(struct module *mod) { } -static inline __init int register_ftrace_command(struct ftrace_func_command *cmd) -{ - return -EINVAL; -} -static inline __init int unregister_ftrace_command(char *cmd_name) -{ - return -EINVAL; -} static inline int ftrace_text_reserved(const void *start, const void *end) { return 0; diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 8bd28ce6d76e..50893a1646cf 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -12,6 +12,8 @@ #ifndef _LINUX_FWNODE_H_ #define _LINUX_FWNODE_H_ +#include <linux/types.h> + enum fwnode_type { FWNODE_INVALID = 0, FWNODE_OF, @@ -22,9 +24,92 @@ enum fwnode_type { FWNODE_IRQCHIP }; +struct fwnode_operations; + struct fwnode_handle { enum fwnode_type type; struct fwnode_handle *secondary; + const struct fwnode_operations *ops; +}; + +/** + * struct fwnode_endpoint - Fwnode graph endpoint + * @port: Port number + * @id: Endpoint id + * @local_fwnode: reference to the related fwnode + */ +struct fwnode_endpoint { + unsigned int port; + unsigned int id; + const struct fwnode_handle *local_fwnode; }; +/** + * struct fwnode_operations - Operations for fwnode interface + * @get: Get a reference to an fwnode. + * @put: Put a reference to an fwnode. + * @property_present: Return true if a property is present. + * @property_read_integer_array: Read an array of integer properties. Return + * zero on success, a negative error code + * otherwise. + * @property_read_string_array: Read an array of string properties. Return zero + * on success, a negative error code otherwise. + * @get_parent: Return the parent of an fwnode. + * @get_next_child_node: Return the next child node in an iteration. + * @get_named_child_node: Return a child node with a given name. + * @graph_get_next_endpoint: Return an endpoint node in an iteration. + * @graph_get_remote_endpoint: Return the remote endpoint node of a local + * endpoint node. + * @graph_get_port_parent: Return the parent node of a port node. + * @graph_parse_endpoint: Parse endpoint for port and endpoint id. + */ +struct fwnode_operations { + void (*get)(struct fwnode_handle *fwnode); + void (*put)(struct fwnode_handle *fwnode); + bool (*device_is_available)(struct fwnode_handle *fwnode); + bool (*property_present)(struct fwnode_handle *fwnode, + const char *propname); + int (*property_read_int_array)(struct fwnode_handle *fwnode, + const char *propname, + unsigned int elem_size, void *val, + size_t nval); + int (*property_read_string_array)(struct fwnode_handle *fwnode_handle, + const char *propname, + const char **val, size_t nval); + struct fwnode_handle *(*get_parent)(struct fwnode_handle *fwnode); + struct fwnode_handle * + (*get_next_child_node)(struct fwnode_handle *fwnode, + struct fwnode_handle *child); + struct fwnode_handle * + (*get_named_child_node)(struct fwnode_handle *fwnode, const char *name); + struct fwnode_handle * + (*graph_get_next_endpoint)(struct fwnode_handle *fwnode, + struct fwnode_handle *prev); + struct fwnode_handle * + (*graph_get_remote_endpoint)(struct fwnode_handle *fwnode); + struct fwnode_handle * + (*graph_get_port_parent)(struct fwnode_handle *fwnode); + int (*graph_parse_endpoint)(struct fwnode_handle *fwnode, + struct fwnode_endpoint *endpoint); +}; + +#define fwnode_has_op(fwnode, op) \ + ((fwnode) && (fwnode)->ops && (fwnode)->ops->op) +#define fwnode_call_int_op(fwnode, op, ...) \ + (fwnode ? (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \ + -EINVAL) +#define fwnode_call_bool_op(fwnode, op, ...) \ + (fwnode ? (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : false) : \ + false) +#define fwnode_call_ptr_op(fwnode, op, ...) \ + (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : NULL) +#define fwnode_call_void_op(fwnode, op, ...) \ + do { \ + if (fwnode_has_op(fwnode, op)) \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__); \ + } while (false) + #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 76f39754e7b0..e619fae2f037 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -159,11 +159,11 @@ struct badblocks; #if defined(CONFIG_BLK_DEV_INTEGRITY) struct blk_integrity { - struct blk_integrity_profile *profile; - unsigned char flags; - unsigned char tuple_size; - unsigned char interval_exp; - unsigned char tag_size; + const struct blk_integrity_profile *profile; + unsigned char flags; + unsigned char tuple_size; + unsigned char interval_exp; + unsigned char tag_size; }; #endif /* CONFIG_BLK_DEV_INTEGRITY */ @@ -219,12 +219,6 @@ static inline struct gendisk *part_to_disk(struct hd_struct *part) return NULL; } -static inline int blk_part_pack_uuid(const u8 *uuid_str, u8 *to) -{ - uuid_be_to_bin(uuid_str, (uuid_be *)to); - return 0; -} - static inline int disk_max_parts(struct gendisk *disk) { if (disk->flags & GENHD_FL_EXT_DEVT) @@ -722,11 +716,9 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) #if defined(CONFIG_BLK_DEV_INTEGRITY) extern void blk_integrity_add(struct gendisk *); extern void blk_integrity_del(struct gendisk *); -extern void blk_integrity_revalidate(struct gendisk *); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline void blk_integrity_add(struct gendisk *disk) { } static inline void blk_integrity_del(struct gendisk *disk) { } -static inline void blk_integrity_revalidate(struct gendisk *disk) { } #endif /* CONFIG_BLK_DEV_INTEGRITY */ #else /* CONFIG_BLOCK */ @@ -738,11 +730,6 @@ static inline dev_t blk_lookup_devt(const char *name, int partno) dev_t devt = MKDEV(0, 0); return devt; } - -static inline int blk_part_pack_uuid(const u8 *uuid_str, u8 *to) -{ - return -EINVAL; -} #endif /* CONFIG_BLOCK */ #endif /* _LINUX_GENHD_H */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0fe0b6295ab5..bcfb9f7c46f5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -25,7 +25,7 @@ struct vm_area_struct; #define ___GFP_FS 0x80u #define ___GFP_COLD 0x100u #define ___GFP_NOWARN 0x200u -#define ___GFP_REPEAT 0x400u +#define ___GFP_RETRY_MAYFAIL 0x400u #define ___GFP_NOFAIL 0x800u #define ___GFP_NORETRY 0x1000u #define ___GFP_MEMALLOC 0x2000u @@ -40,6 +40,11 @@ struct vm_area_struct; #define ___GFP_DIRECT_RECLAIM 0x400000u #define ___GFP_WRITE 0x800000u #define ___GFP_KSWAPD_RECLAIM 0x1000000u +#ifdef CONFIG_LOCKDEP +#define ___GFP_NOLOCKDEP 0x2000000u +#else +#define ___GFP_NOLOCKDEP 0 +#endif /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* @@ -131,26 +136,56 @@ struct vm_area_struct; * * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * - * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt - * _might_ fail. This depends upon the particular VM implementation. + * The default allocator behavior depends on the request size. We have a concept + * of so called costly allocations (with order > PAGE_ALLOC_COSTLY_ORDER). + * !costly allocations are too essential to fail so they are implicitly + * non-failing by default (with some exceptions like OOM victims might fail so + * the caller still has to check for failures) while costly requests try to be + * not disruptive and back off even without invoking the OOM killer. + * The following three modifiers might be used to override some of these + * implicit rules + * + * __GFP_NORETRY: The VM implementation will try only very lightweight + * memory direct reclaim to get some memory under memory pressure (thus + * it can sleep). It will avoid disruptive actions like OOM killer. The + * caller must handle the failure which is quite likely to happen under + * heavy memory pressure. The flag is suitable when failure can easily be + * handled at small cost, such as reduced throughput + * + * __GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim + * procedures that have previously failed if there is some indication + * that progress has been made else where. It can wait for other + * tasks to attempt high level approaches to freeing memory such as + * compaction (which removes fragmentation) and page-out. + * There is still a definite limit to the number of retries, but it is + * a larger limit than with __GFP_NORETRY. + * Allocations with this flag may fail, but only when there is + * genuinely little unused memory. While these allocations do not + * directly trigger the OOM killer, their failure indicates that + * the system is likely to need to use the OOM killer soon. The + * caller must handle failure, but can reasonably do so by failing + * a higher-level request, or completing it only in a much less + * efficient manner. + * If the allocation does fail, and the caller is in a position to + * free some non-essential memory, doing so could benefit the system + * as a whole. * * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller - * cannot handle allocation failures. New users should be evaluated carefully - * (and the flag should be used only when there is no reasonable failure - * policy) but it is definitely preferable to use the flag rather than - * opencode endless loop around allocator. - * - * __GFP_NORETRY: The VM implementation must not retry indefinitely and will - * return NULL when direct reclaim and memory compaction have failed to allow - * the allocation to succeed. The OOM killer is not called with the current - * implementation. + * cannot handle allocation failures. The allocation could block + * indefinitely but will never return with failure. Testing for + * failure is pointless. + * New users should be evaluated carefully (and the flag should be + * used only when there is no reasonable failure policy) but it is + * definitely preferable to use the flag rather than opencode endless + * loop around allocator. + * Using this flag for costly allocations is _highly_ discouraged. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) #define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ #define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) -#define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT) +#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) @@ -179,8 +214,11 @@ struct vm_area_struct; #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) +/* Disable lockdep for GFP context tracking */ +#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) + /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT 25 +#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /* @@ -202,8 +240,16 @@ struct vm_area_struct; * * GFP_NOIO will use direct reclaim to discard clean pages or slab pages * that do not require the starting of any physical IO. + * Please try to avoid using this flag directly and instead use + * memalloc_noio_{save,restore} to mark the whole scope which cannot + * perform any IO with a short explanation why. All allocation requests + * will inherit GFP_NOIO implicitly. * * GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. + * Please try to avoid using this flag directly and instead use + * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't + * recurse into the FS layer with a short explanation why. All allocation + * requests will inherit GFP_NOFS implicitly. * * GFP_USER is for userspace allocations that also need to be directly * accessibly by the kernel or hardware. It is typically used by hardware @@ -297,8 +343,8 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) /* * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the - * zone to use given the lowest 4 bits of gfp_t. Entries are ZONE_SHIFT long - * and there are 16 of them to cover all possible combinations of + * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT + * bits long and there are 16 of them to cover all possible combinations of * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. @@ -416,14 +462,13 @@ static inline void arch_alloc_page(struct page *page, int order) { } #endif struct page * -__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, nodemask_t *nodemask); +__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, + nodemask_t *nodemask); static inline struct page * -__alloc_pages(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist) +__alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid) { - return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL); + return __alloc_pages_nodemask(gfp_mask, order, preferred_nid, NULL); } /* @@ -436,7 +481,7 @@ __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); VM_WARN_ON(!node_online(nid)); - return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); + return __alloc_pages(gfp_mask, order, nid); } /* @@ -541,7 +586,7 @@ static inline bool pm_suspended_storage(void) #if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA) /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range(unsigned long start, unsigned long end, - unsigned migratetype); + unsigned migratetype, gfp_t gfp_mask); extern void free_contig_range(unsigned long pfn, unsigned nr_pages); #endif diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index fb0fde686cb1..8f702fcbe485 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -135,10 +135,15 @@ int desc_to_gpio(const struct gpio_desc *desc); struct fwnode_handle; struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, - const char *propname); -struct gpio_desc *devm_get_gpiod_from_child(struct device *dev, - const char *con_id, - struct fwnode_handle *child); + const char *propname, int index, + enum gpiod_flags dflags, + const char *label); +struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, + const char *con_id, int index, + struct fwnode_handle *child, + enum gpiod_flags flags, + const char *label); + #else /* CONFIG_GPIOLIB */ static inline int gpiod_count(struct device *dev, const char *con_id) @@ -165,14 +170,14 @@ static inline struct gpio_desc *__must_check gpiod_get_optional(struct device *dev, const char *con_id, enum gpiod_flags flags) { - return ERR_PTR(-ENOSYS); + return NULL; } static inline struct gpio_desc *__must_check gpiod_get_index_optional(struct device *dev, const char *con_id, unsigned int index, enum gpiod_flags flags) { - return ERR_PTR(-ENOSYS); + return NULL; } static inline struct gpio_descs *__must_check @@ -186,7 +191,7 @@ static inline struct gpio_descs *__must_check gpiod_get_array_optional(struct device *dev, const char *con_id, enum gpiod_flags flags) { - return ERR_PTR(-ENOSYS); + return NULL; } static inline void gpiod_put(struct gpio_desc *desc) @@ -226,14 +231,14 @@ static inline struct gpio_desc *__must_check devm_gpiod_get_optional(struct device *dev, const char *con_id, enum gpiod_flags flags) { - return ERR_PTR(-ENOSYS); + return NULL; } static inline struct gpio_desc *__must_check devm_gpiod_get_index_optional(struct device *dev, const char *con_id, unsigned int index, enum gpiod_flags flags) { - return ERR_PTR(-ENOSYS); + return NULL; } static inline struct gpio_descs *__must_check @@ -247,7 +252,7 @@ static inline struct gpio_descs *__must_check devm_gpiod_get_array_optional(struct device *dev, const char *con_id, enum gpiod_flags flags) { - return ERR_PTR(-ENOSYS); + return NULL; } static inline void devm_gpiod_put(struct device *dev, struct gpio_desc *desc) @@ -411,20 +416,38 @@ static inline int desc_to_gpio(const struct gpio_desc *desc) /* Child properties interface */ struct fwnode_handle; -static inline struct gpio_desc *fwnode_get_named_gpiod( - struct fwnode_handle *fwnode, const char *propname) +static inline +struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, + const char *propname, int index, + enum gpiod_flags dflags, + const char *label) { return ERR_PTR(-ENOSYS); } -static inline struct gpio_desc *devm_get_gpiod_from_child( - struct device *dev, const char *con_id, struct fwnode_handle *child) +static inline +struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, + const char *con_id, int index, + struct fwnode_handle *child, + enum gpiod_flags flags, + const char *label) { return ERR_PTR(-ENOSYS); } #endif /* CONFIG_GPIOLIB */ +static inline +struct gpio_desc *devm_fwnode_get_gpiod_from_child(struct device *dev, + const char *con_id, + struct fwnode_handle *child, + enum gpiod_flags flags, + const char *label) +{ + return devm_fwnode_get_index_gpiod_from_child(dev, con_id, 0, child, + flags, label); +} + #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_GPIO_SYSFS) int gpiod_export(struct gpio_desc *desc, bool direction_may_change); diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index e973faba69dc..af20369ec8e7 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -8,6 +8,7 @@ #include <linux/irqdomain.h> #include <linux/lockdep.h> #include <linux/pinctrl/pinctrl.h> +#include <linux/pinctrl/pinconf-generic.h> struct gpio_desc; struct of_phandle_args; @@ -19,18 +20,6 @@ struct module; #ifdef CONFIG_GPIOLIB /** - * enum single_ended_mode - mode for single ended operation - * @LINE_MODE_PUSH_PULL: normal mode for a GPIO line, drive actively high/low - * @LINE_MODE_OPEN_DRAIN: set line to be open drain - * @LINE_MODE_OPEN_SOURCE: set line to be open source - */ -enum single_ended_mode { - LINE_MODE_PUSH_PULL, - LINE_MODE_OPEN_DRAIN, - LINE_MODE_OPEN_SOURCE, -}; - -/** * struct gpio_chip - abstract a GPIO controller * @label: a functional name for the GPIO device, such as a part * number or the name of the SoC IP-block implementing it. @@ -48,16 +37,8 @@ enum single_ended_mode { * @get: returns value for signal "offset", 0=low, 1=high, or negative error * @set: assigns output value for signal "offset" * @set_multiple: assigns output values for multiple signals defined by "mask" - * @set_debounce: optional hook for setting debounce time for specified gpio in - * interrupt triggered gpio chips - * @set_single_ended: optional hook for setting a line as open drain, open - * source, or non-single ended (restore from open drain/source to normal - * push-pull mode) this should be implemented if the hardware supports - * open drain or open source settings. The GPIOlib will otherwise try - * to emulate open drain/source by not actively driving lines high/low - * if a consumer request this. The driver may return -ENOTSUPP if e.g. - * it supports just open drain but not open source and is called - * with LINE_MODE_OPEN_SOURCE as mode argument. + * @set_config: optional hook for all kinds of settings. Uses the same + * packed config format as generic pinconf. * @to_irq: optional hook supporting non-static gpio_to_irq() mappings; * implementation may not sleep * @dbg_show: optional routine to show contents in debugfs; default code @@ -150,13 +131,9 @@ struct gpio_chip { void (*set_multiple)(struct gpio_chip *chip, unsigned long *mask, unsigned long *bits); - int (*set_debounce)(struct gpio_chip *chip, - unsigned offset, - unsigned debounce); - int (*set_single_ended)(struct gpio_chip *chip, - unsigned offset, - enum single_ended_mode mode); - + int (*set_config)(struct gpio_chip *chip, + unsigned offset, + unsigned long config); int (*to_irq)(struct gpio_chip *chip, unsigned offset); @@ -191,7 +168,7 @@ struct gpio_chip { unsigned int irq_base; irq_flow_handler_t irq_handler; unsigned int irq_default_type; - int irq_chained_parent; + unsigned int irq_chained_parent; bool irq_nested; bool irq_need_valid_mask; unsigned long *irq_valid_mask; @@ -236,6 +213,9 @@ bool gpiochip_line_is_irq(struct gpio_chip *chip, unsigned int offset); bool gpiochip_line_is_open_drain(struct gpio_chip *chip, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *chip, unsigned int offset); +/* Sleep persistence inquiry for drivers */ +bool gpiochip_line_is_persistent(struct gpio_chip *chip, unsigned int offset); + /* get driver data */ void *gpiochip_get_data(struct gpio_chip *chip); @@ -267,12 +247,12 @@ int bgpio_init(struct gpio_chip *gc, struct device *dev, void gpiochip_set_chained_irqchip(struct gpio_chip *gpiochip, struct irq_chip *irqchip, - int parent_irq, + unsigned int parent_irq, irq_flow_handler_t parent_handler); void gpiochip_set_nested_irqchip(struct gpio_chip *gpiochip, struct irq_chip *irqchip, - int parent_irq); + unsigned int parent_irq); int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip, struct irq_chip *irqchip, @@ -340,6 +320,8 @@ static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, int gpiochip_generic_request(struct gpio_chip *chip, unsigned offset); void gpiochip_generic_free(struct gpio_chip *chip, unsigned offset); +int gpiochip_generic_config(struct gpio_chip *chip, unsigned offset, + unsigned long config); #ifdef CONFIG_PINCTRL diff --git a/include/linux/gpio/gpio-reg.h b/include/linux/gpio/gpio-reg.h new file mode 100644 index 000000000000..90e0b9060e6d --- /dev/null +++ b/include/linux/gpio/gpio-reg.h @@ -0,0 +1,13 @@ +#ifndef GPIO_REG_H +#define GPIO_REG_H + +struct device; +struct irq_domain; + +struct gpio_chip *gpio_reg_init(struct device *dev, void __iomem *reg, + int base, int num, const char *label, u32 direction, u32 def_out, + const char *const *names, struct irq_domain *irqdom, const int *irqs); + +int gpio_reg_resume(struct gpio_chip *gc); + +#endif diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index c0d712d22b07..6e76b16fcade 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -9,6 +9,8 @@ enum gpio_lookup_flags { GPIO_ACTIVE_LOW = (1 << 0), GPIO_OPEN_DRAIN = (1 << 1), GPIO_OPEN_SOURCE = (1 << 2), + GPIO_SLEEP_MAINTAIN_VALUE = (0 << 3), + GPIO_SLEEP_MAY_LOOSE_VALUE = (1 << 3), }; /** @@ -56,7 +58,14 @@ struct gpiod_lookup_table { .flags = _flags, \ } +#ifdef CONFIG_GPIOLIB void gpiod_add_lookup_table(struct gpiod_lookup_table *table); void gpiod_remove_lookup_table(struct gpiod_lookup_table *table); +#else +static inline +void gpiod_add_lookup_table(struct gpiod_lookup_table *table) {} +static inline +void gpiod_remove_lookup_table(struct gpiod_lookup_table *table) {} +#endif #endif /* __LINUX_GPIO_MACHINE_H */ diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h index 661e5c2a8e2a..082dc1bd0801 100644 --- a/include/linux/hashtable.h +++ b/include/linux/hashtable.h @@ -167,7 +167,6 @@ static inline void hash_del_rcu(struct hlist_node *node) /** * hash_for_each_possible_rcu - iterate over all possible objects hashing to the * same bucket in an rcu enabled hashtable - * in a rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index edbb4fc674ed..d271ff23984f 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -35,6 +35,7 @@ enum hdmi_infoframe_type { }; #define HDMI_IEEE_OUI 0x000c03 +#define HDMI_FORUM_IEEE_OUI 0xc45dd8 #define HDMI_INFOFRAME_HEADER_SIZE 4 #define HDMI_AVI_INFOFRAME_SIZE 13 #define HDMI_SPD_INFOFRAME_SIZE 25 diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index dd85f3503410..fc7aae64dcde 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -231,11 +231,16 @@ struct hid_sensor_common { unsigned usage_id; atomic_t data_ready; atomic_t user_requested_state; + int poll_interval; + int raw_hystersis; + int latency_ms; struct iio_trigger *trigger; + int timestamp_ns_scale; struct hid_sensor_hub_attribute_info poll; struct hid_sensor_hub_attribute_info report_state; struct hid_sensor_hub_attribute_info power_state; struct hid_sensor_hub_attribute_info sensitivity; + struct hid_sensor_hub_attribute_info report_latency; struct work_struct work; }; @@ -271,4 +276,10 @@ int hid_sensor_format_scale(u32 usage_id, s32 hid_sensor_read_poll_value(struct hid_sensor_common *st); +int64_t hid_sensor_convert_timestamp(struct hid_sensor_common *st, + int64_t raw_value); +bool hid_sensor_batch_mode_supported(struct hid_sensor_common *st); +int hid_sensor_set_report_latency(struct hid_sensor_common *st, int latency); +int hid_sensor_get_report_latency(struct hid_sensor_common *st); + #endif diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h index f2ee90aed0c2..76033e0420a7 100644 --- a/include/linux/hid-sensor-ids.h +++ b/include/linux/hid-sensor-ids.h @@ -45,6 +45,14 @@ #define HID_USAGE_SENSOR_DATA_ATMOSPHERIC_PRESSURE 0x200430 #define HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE 0x200431 +/* Tempreture (200033) */ +#define HID_USAGE_SENSOR_TEMPERATURE 0x200033 +#define HID_USAGE_SENSOR_DATA_ENVIRONMENTAL_TEMPERATURE 0x200434 + +/* humidity */ +#define HID_USAGE_SENSOR_HUMIDITY 0x200032 +#define HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY 0x200433 + /* Gyro 3D: (200076) */ #define HID_USAGE_SENSOR_GYRO_3D 0x200076 #define HID_USAGE_SENSOR_DATA_ANGL_VELOCITY 0x200456 @@ -52,6 +60,9 @@ #define HID_USAGE_SENSOR_ANGL_VELOCITY_Y_AXIS 0x200458 #define HID_USAGE_SENSOR_ANGL_VELOCITY_Z_AXIS 0x200459 +/* Gravity vector */ +#define HID_USAGE_SENSOR_GRAVITY_VECTOR 0x20007B + /* ORIENTATION: Compass 3D: (200083) */ #define HID_USAGE_SENSOR_COMPASS_3D 0x200083 #define HID_USAGE_SENSOR_DATA_ORIENTATION 0x200470 @@ -79,6 +90,8 @@ #define HID_USAGE_SENSOR_ORIENT_TILT_Z 0x200481 #define HID_USAGE_SENSOR_DEVICE_ORIENTATION 0x20008A +#define HID_USAGE_SENSOR_RELATIVE_ORIENTATION 0x20008E +#define HID_USAGE_SENSOR_GEOMAGNETIC_ORIENTATION 0x2000C1 #define HID_USAGE_SENSOR_ORIENT_ROTATION_MATRIX 0x200482 #define HID_USAGE_SENSOR_ORIENT_QUATERNION 0x200483 #define HID_USAGE_SENSOR_ORIENT_MAGN_FLUX 0x200484 @@ -95,6 +108,7 @@ #define HID_USAGE_SENSOR_TIME_HOUR 0x200525 #define HID_USAGE_SENSOR_TIME_MINUTE 0x200526 #define HID_USAGE_SENSOR_TIME_SECOND 0x200527 +#define HID_USAGE_SENSOR_TIME_TIMESTAMP 0x200529 /* Units */ #define HID_USAGE_SENSOR_UNITS_NOT_SPECIFIED 0x00 @@ -138,6 +152,9 @@ #define HID_USAGE_SENSOR_PROP_REPORT_STATE 0x200316 #define HID_USAGE_SENSOR_PROY_POWER_STATE 0x200319 +/* Batch mode selectors */ +#define HID_USAGE_SENSOR_PROP_REPORT_LATENCY 0x20031B + /* Per data field properties */ #define HID_USAGE_SENSOR_DATA_MOD_NONE 0x00 #define HID_USAGE_SENSOR_DATA_MOD_CHANGE_SENSITIVITY_ABS 0x1000 diff --git a/include/linux/hid.h b/include/linux/hid.h index 28f38e2b8f30..5006f9b5d837 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -34,6 +34,7 @@ #include <linux/workqueue.h> #include <linux/input.h> #include <linux/semaphore.h> +#include <linux/mutex.h> #include <linux/power_supply.h> #include <uapi/linux/hid.h> @@ -182,6 +183,11 @@ struct hid_item { #define HID_GD_KEYBOARD 0x00010006 #define HID_GD_KEYPAD 0x00010007 #define HID_GD_MULTIAXIS 0x00010008 +/* + * Microsoft Win8 Wireless Radio Controls extensions CA, see: + * http://www.usb.org/developers/hidpage/HUTRR40RadioHIDUsagesFinal.pdf + */ +#define HID_GD_WIRELESS_RADIO_CTLS 0x0001000c #define HID_GD_X 0x00010030 #define HID_GD_Y 0x00010031 #define HID_GD_Z 0x00010032 @@ -210,6 +216,10 @@ struct hid_item { #define HID_GD_DOWN 0x00010091 #define HID_GD_RIGHT 0x00010092 #define HID_GD_LEFT 0x00010093 +/* Microsoft Win8 Wireless Radio Controls CA usage codes */ +#define HID_GD_RFKILL_BTN 0x000100c6 +#define HID_GD_RFKILL_LED 0x000100c7 +#define HID_GD_RFKILL_SWITCH 0x000100c8 #define HID_DC_BATTERYSTRENGTH 0x00060020 @@ -268,6 +278,8 @@ struct hid_item { #define HID_CP_APPLICATIONLAUNCHBUTTONS 0x000c0180 #define HID_CP_GENERICGUIAPPLICATIONCONTROLS 0x000c0200 +#define HID_DG_DEVICECONFIG 0x000d000e +#define HID_DG_DEVICESETTINGS 0x000d0023 #define HID_DG_CONFIDENCE 0x000d0047 #define HID_DG_WIDTH 0x000d0048 #define HID_DG_HEIGHT 0x000d0049 @@ -322,7 +334,7 @@ struct hid_item { #define HID_QUIRK_MULTI_INPUT 0x00000040 #define HID_QUIRK_HIDINPUT_FORCE 0x00000080 #define HID_QUIRK_NO_EMPTY_INPUT 0x00000100 -#define HID_QUIRK_NO_INIT_INPUT_REPORTS 0x00000200 +/* 0x00000200 reserved for backward compatibility, was NO_INIT_INPUT_REPORTS */ #define HID_QUIRK_ALWAYS_POLL 0x00000400 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID 0x00020000 @@ -518,7 +530,10 @@ struct hid_device { /* device report descriptor */ struct semaphore driver_input_lock; /* protects the current driver */ struct device dev; /* device */ struct hid_driver *driver; + struct hid_ll_driver *ll_driver; + struct mutex ll_open_lock; + unsigned int ll_open_count; #ifdef CONFIG_HID_BATTERY_STRENGTH /* @@ -541,9 +556,7 @@ struct hid_device { /* device report descriptor */ struct list_head inputs; /* The list of inputs */ void *hiddev; /* The hiddev structure */ void *hidraw; - int minor; /* Hiddev minor number */ - int open; /* is the device open by anyone? */ char name[128]; /* Device name */ char phys[64]; /* Device physical location */ char uniq[64]; /* Device unique identifier (serial #) */ @@ -936,69 +949,11 @@ static inline int __must_check hid_parse(struct hid_device *hdev) return hid_open_report(hdev); } -/** - * hid_hw_start - start underlaying HW - * - * @hdev: hid device - * @connect_mask: which outputs to connect, see HID_CONNECT_* - * - * Call this in probe function *after* hid_parse. This will setup HW buffers - * and start the device (if not deffered to device open). hid_hw_stop must be - * called if this was successful. - */ -static inline int __must_check hid_hw_start(struct hid_device *hdev, - unsigned int connect_mask) -{ - int ret = hdev->ll_driver->start(hdev); - if (ret || !connect_mask) - return ret; - ret = hid_connect(hdev, connect_mask); - if (ret) - hdev->ll_driver->stop(hdev); - return ret; -} - -/** - * hid_hw_stop - stop underlaying HW - * - * @hdev: hid device - * - * This is usually called from remove function or from probe when something - * failed and hid_hw_start was called already. - */ -static inline void hid_hw_stop(struct hid_device *hdev) -{ - hid_disconnect(hdev); - hdev->ll_driver->stop(hdev); -} - -/** - * hid_hw_open - signal underlaying HW to start delivering events - * - * @hdev: hid device - * - * Tell underlying HW to start delivering events from the device. - * This function should be called sometime after successful call - * to hid_hiw_start(). - */ -static inline int __must_check hid_hw_open(struct hid_device *hdev) -{ - return hdev->ll_driver->open(hdev); -} - -/** - * hid_hw_close - signal underlaying HW to stop delivering events - * - * @hdev: hid device - * - * This function indicates that we are not interested in the events - * from this device anymore. Delivery of events may or may not stop, - * depending on the number of users still outstanding. - */ -static inline void hid_hw_close(struct hid_device *hdev) -{ - hdev->ll_driver->close(hdev); -} +int __must_check hid_hw_start(struct hid_device *hdev, + unsigned int connect_mask); +void hid_hw_stop(struct hid_device *hdev); +int __must_check hid_hw_open(struct hid_device *hdev); +void hid_hw_close(struct hid_device *hdev); /** * hid_hw_power - requests underlying HW to go into given power mode diff --git a/include/linux/hiddev.h b/include/linux/hiddev.h index a5dd8148660b..921622222957 100644 --- a/include/linux/hiddev.h +++ b/include/linux/hiddev.h @@ -32,6 +32,18 @@ * In-kernel definitions. */ +struct hiddev { + int minor; + int exist; + int open; + struct mutex existancelock; + wait_queue_head_t wait; + struct hid_device *hid; + struct list_head list; + spinlock_t list_lock; + bool initialized; +}; + struct hid_device; struct hid_usage; struct hid_field; diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 1ffbf2a8cb99..630b1a98ab58 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -26,16 +26,33 @@ enum host1x_class { HOST1X_CLASS_HOST1X = 0x1, HOST1X_CLASS_GR2D = 0x51, HOST1X_CLASS_GR2D_SB = 0x52, + HOST1X_CLASS_VIC = 0x5D, HOST1X_CLASS_GR3D = 0x60, }; struct host1x_client; +/** + * struct host1x_client_ops - host1x client operations + * @init: host1x client initialization code + * @exit: host1x client tear down code + */ struct host1x_client_ops { int (*init)(struct host1x_client *client); int (*exit)(struct host1x_client *client); }; +/** + * struct host1x_client - host1x client structure + * @list: list node for the host1x client + * @parent: pointer to struct device representing the host1x controller + * @dev: pointer to struct device backing this host1x client + * @ops: host1x client operations + * @class: host1x class represented by this client + * @channel: host1x channel associated with this client + * @syncpts: array of syncpoints requested for this client + * @num_syncpts: number of syncpoints requested for this client + */ struct host1x_client { struct list_head list; struct device *parent; @@ -155,7 +172,6 @@ struct host1x_channel; struct host1x_job; struct host1x_channel *host1x_channel_request(struct device *dev); -void host1x_channel_free(struct host1x_channel *channel); struct host1x_channel *host1x_channel_get(struct host1x_channel *channel); void host1x_channel_put(struct host1x_channel *channel); int host1x_job_submit(struct host1x_job *job); @@ -176,6 +192,13 @@ struct host1x_reloc { unsigned long shift; }; +struct host1x_waitchk { + struct host1x_bo *bo; + u32 offset; + u32 syncpt_id; + u32 thresh; +}; + struct host1x_job { /* When refcount goes to zero, job can be freed */ struct kref ref; @@ -225,7 +248,10 @@ struct host1x_job { u8 *gather_copy_mapped; /* Check if register is marked as an address reg */ - int (*is_addr_reg)(struct device *dev, u32 reg, u32 class); + int (*is_addr_reg)(struct device *dev, u32 class, u32 reg); + + /* Check if class belongs to the unit */ + int (*is_valid_class)(u32 class); /* Request a SETCLASS to this class */ u32 class; @@ -250,6 +276,15 @@ void host1x_job_unpin(struct host1x_job *job); struct host1x_device; +/** + * struct host1x_driver - host1x logical device driver + * @driver: core driver + * @subdevs: table of OF device IDs matching subdevices for this driver + * @list: list node for the driver + * @probe: called when the host1x logical device is probed + * @remove: called when the host1x logical device is removed + * @shutdown: called when the host1x logical device is shut down + */ struct host1x_driver { struct device_driver driver; diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index cdab81ba29f8..012c37fdb688 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -19,7 +19,6 @@ #include <linux/ktime.h> #include <linux/init.h> #include <linux/list.h> -#include <linux/wait.h> #include <linux/percpu.h> #include <linux/timer.h> #include <linux/timerqueue.h> @@ -88,12 +87,6 @@ enum hrtimer_restart { * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) * @is_rel: Set if the timer was armed relative - * @start_pid: timer statistics field to store the pid of the task which - * started the timer - * @start_site: timer statistics field to store the site where the timer - * was started - * @start_comm: timer statistics field to store the name of the process which - * started the timer * * The hrtimer structure must be initialized by hrtimer_init() */ @@ -104,11 +97,6 @@ struct hrtimer { struct hrtimer_clock_base *base; u8 state; u8 is_rel; -#ifdef CONFIG_TIMER_STATS - int start_pid; - void *start_site; - char start_comm[16]; -#endif }; /** @@ -288,8 +276,6 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer) return timer->base->cpu_base->hres_active; } -extern void hrtimer_peek_ahead_timers(void); - /* * The resolution of the clocks. The resolution value is returned in * the clock_getres() system call to give application programmers an @@ -312,8 +298,6 @@ extern unsigned int hrtimer_resolution; #define hrtimer_resolution (unsigned int)LOW_RES_NSEC -static inline void hrtimer_peek_ahead_timers(void) { } - static inline int hrtimer_is_hres_active(struct hrtimer *timer) { return 0; @@ -468,11 +452,11 @@ static inline u64 hrtimer_forward_now(struct hrtimer *timer, } /* Precise sleep: */ -extern long hrtimer_nanosleep(struct timespec *rqtp, - struct timespec __user *rmtp, + +extern int nanosleep_copyout(struct restart_block *, struct timespec64 *); +extern long hrtimer_nanosleep(const struct timespec64 *rqtp, const enum hrtimer_mode mode, const clockid_t clockid); -extern long hrtimer_nanosleep_restart(struct restart_block *restart_block); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *tsk); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 97e478d6b690..ee696347f928 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -1,11 +1,27 @@ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H +#include <linux/sched/coredump.h> + +#include <linux/fs.h> /* only for vma_is_dax() */ + extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf); extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *vma); extern void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); +extern int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pud_t *dst_pud, pud_t *src_pud, unsigned long addr, + struct vm_area_struct *vma); + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +extern void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); +#else +static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) +{ +} +#endif + extern int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -17,6 +33,9 @@ extern bool madvise_free_huge_pmd(struct mmu_gather *tlb, extern int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr); +extern int zap_huge_pud(struct mmu_gather *tlb, + struct vm_area_struct *vma, + pud_t *pud, unsigned long addr); extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec); @@ -26,13 +45,16 @@ extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); -int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *, - pfn_t pfn, bool write); +int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, pfn_t pfn, bool write); +int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, pfn_t pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, + TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, @@ -57,23 +79,42 @@ extern struct kobj_attribute shmem_enabled_attr; #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #ifdef CONFIG_TRANSPARENT_HUGEPAGE -struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags); - #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) +#define HPAGE_PUD_SHIFT PUD_SHIFT +#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) +#define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) + extern bool is_vma_temporary_stack(struct vm_area_struct *vma); -#define transparent_hugepage_enabled(__vma) \ - ((transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_FLAG) || \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) && \ - ((__vma)->vm_flags & VM_HUGEPAGE))) && \ - !((__vma)->vm_flags & VM_NOHUGEPAGE) && \ - !is_vma_temporary_stack(__vma)) +extern unsigned long transparent_hugepage_flags; + +static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_NOHUGEPAGE) + return false; + + if (is_vma_temporary_stack(vma)) + return false; + + if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return false; + + if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) + return true; + + if (vma_is_dax(vma)) + return true; + + if (transparent_hugepage_flags & + (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) + return !!(vma->vm_flags & VM_HUGEPAGE); + + return false; +} + #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) @@ -85,8 +126,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); #define transparent_hugepage_debug_cow() 0 #endif /* CONFIG_DEBUG_VM */ -extern unsigned long transparent_hugepage_flags; - extern unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); @@ -94,6 +133,7 @@ extern unsigned long thp_get_unmapped_area(struct file *filp, extern void prep_transhuge_page(struct page *page); extern void free_transhuge_page(struct page *page); +bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { @@ -117,6 +157,17 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page); +void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, + unsigned long address); + +#define split_huge_pud(__vma, __pud, __address) \ + do { \ + pud_t *____pud = (__pud); \ + if (pud_trans_huge(*____pud) \ + || pud_devmap(*____pud)) \ + __split_huge_pud(__vma, __pud, __address); \ + } while (0) + extern int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); extern void vma_adjust_trans_huge(struct vm_area_struct *vma, @@ -125,6 +176,8 @@ extern void vma_adjust_trans_huge(struct vm_area_struct *vma, long adjust_next); extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); +extern spinlock_t *__pud_trans_huge_lock(pud_t *pud, + struct vm_area_struct *vma); /* mmap_sem must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) @@ -135,6 +188,15 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, else return NULL; } +static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, + struct vm_area_struct *vma) +{ + VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); + if (pud_trans_huge(*pud) || pud_devmap(*pud)) + return __pud_trans_huge_lock(pud, vma); + else + return NULL; +} static inline int hpage_nr_pages(struct page *page) { if (unlikely(PageTransHuge(page))) @@ -142,6 +204,11 @@ static inline int hpage_nr_pages(struct page *page) return 1; } +struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, int flags); +struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, int flags); + extern int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *huge_zero_page; @@ -156,6 +223,11 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) return is_huge_zero_page(pmd_page(pmd)); } +static inline bool is_huge_zero_pud(pud_t pud) +{ + return false; +} + struct page *mm_get_huge_zero_page(struct mm_struct *mm); void mm_put_huge_zero_page(struct mm_struct *mm); @@ -166,9 +238,16 @@ void mm_put_huge_zero_page(struct mm_struct *mm); #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; }) +#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) +#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) +#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) + #define hpage_nr_pages(x) 1 -#define transparent_hugepage_enabled(__vma) 0 +static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +{ + return false; +} static inline void prep_transhuge_page(struct page *page) {} @@ -176,6 +255,12 @@ static inline void prep_transhuge_page(struct page *page) {} #define thp_get_unmapped_area NULL +static inline bool +can_split_huge_page(struct page *page, int *pextra_pins) +{ + BUILD_BUG(); + return false; +} static inline int split_huge_page_to_list(struct page *page, struct list_head *list) { @@ -194,6 +279,9 @@ static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page) {} +#define split_huge_pud(__vma, __pmd, __address) \ + do { } while (0) + static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { @@ -211,6 +299,11 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, { return NULL; } +static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, + struct vm_area_struct *vma) +{ + return NULL; +} static inline int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd) { @@ -222,6 +315,11 @@ static inline bool is_huge_zero_page(struct page *page) return false; } +static inline bool is_huge_zero_pud(pud_t pud) +{ + return false; +} + static inline void mm_put_huge_zero_page(struct mm_struct *mm) { return; @@ -232,6 +330,12 @@ static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, { return NULL; } + +static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pud, int flags) +{ + return NULL; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 48c76d612d40..0ed8e41aaf11 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -14,6 +14,30 @@ struct ctl_table; struct user_struct; struct mmu_gather; +#ifndef is_hugepd +/* + * Some architectures requires a hugepage directory format that is + * required to support multiple hugepage sizes. For example + * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables" + * introduced the same on powerpc. This allows for a more flexible hugepage + * pagetable layout. + */ +typedef struct { unsigned long pd; } hugepd_t; +#define is_hugepd(hugepd) (0) +#define __hugepd(x) ((hugepd_t) { (x) }) +static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, + unsigned pdshift, unsigned long end, + int write, struct page **pages, int *nr) +{ + return 0; +} +#else +extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr, + unsigned pdshift, unsigned long end, + int write, struct page **pages, int *nr); +#endif + + #ifdef CONFIG_HUGETLB_PAGE #include <linux/mempolicy.h> @@ -65,7 +89,8 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, - unsigned long *, unsigned long *, long, unsigned int); + unsigned long *, unsigned long *, long, unsigned int, + int *); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *); void __unmap_hugepage_range_final(struct mmu_gather *tlb, @@ -81,12 +106,16 @@ void hugetlb_show_meminfo(void); unsigned long hugetlb_total_pages(void); int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); +int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep); int hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -int dequeue_hwpoisoned_huge_page(struct page *page); bool isolate_huge_page(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); void free_huge_page(struct page *page); @@ -107,19 +136,27 @@ extern struct list_head huge_boot_pages; pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz); -pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr); +pte_t *huge_pte_offset(struct mm_struct *mm, + unsigned long addr, unsigned long sz); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); +struct page *follow_huge_pd(struct vm_area_struct *vma, + unsigned long address, hugepd_t hpd, + int flags, int pdshift); struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags); +struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, + pgd_t *pgd, int flags); + int pmd_huge(pmd_t pmd); -int pud_huge(pud_t pmd); +int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot); +bool is_hugetlb_entry_migration(pte_t pte); #else /* !CONFIG_HUGETLB_PAGE */ static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) @@ -131,7 +168,7 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } -#define follow_hugetlb_page(m,v,p,vs,a,b,i,w) ({ BUG(); 0; }) +#define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; }) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) static inline void hugetlb_report_meminfo(struct seq_file *m) @@ -141,19 +178,19 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) static inline void hugetlb_show_meminfo(void) { } +#define follow_huge_pd(vma, addr, hpd, flags, pdshift) NULL #define follow_huge_pmd(mm, addr, pmd, flags) NULL #define follow_huge_pud(mm, addr, pud, flags) NULL +#define follow_huge_pgd(mm, addr, pgd, flags) NULL #define prepare_hugepage_range(file, addr, len) (-EINVAL) #define pmd_huge(x) 0 #define pud_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) #define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) -#define huge_pte_offset(mm, address) 0 -static inline int dequeue_hwpoisoned_huge_page(struct page *page) -{ - return 0; -} +#define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ + src_addr, pagep) ({ BUG(); 0; }) +#define huge_pte_offset(mm, address, sz) 0 static inline bool isolate_huge_page(struct page *page, struct list_head *list) { @@ -189,6 +226,9 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb, #ifndef pgd_huge #define pgd_huge(x) 0 #endif +#ifndef p4d_huge +#define p4d_huge(x) 0 +#endif #ifndef pgd_write static inline int pgd_write(pgd_t pgd) @@ -206,29 +246,6 @@ static inline int pud_write(pud_t pud) } #endif -#ifndef is_hugepd -/* - * Some architectures requires a hugepage directory format that is - * required to support multiple hugepage sizes. For example - * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables" - * introduced the same on powerpc. This allows for a more flexible hugepage - * pagetable layout. - */ -typedef struct { unsigned long pd; } hugepd_t; -#define is_hugepd(hugepd) (0) -#define __hugepd(x) ((hugepd_t) { (x) }) -static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, - int write, struct page **pages, int *nr) -{ - return 0; -} -#else -extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, - int write, struct page **pages, int *nr); -#endif - #define HUGETLB_ANON_FILE "anon_hugepage" enum { @@ -251,6 +268,9 @@ struct hugetlbfs_sb_info { spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; + kuid_t uid; + kgid_t gid; + umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) @@ -332,6 +352,8 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, struct page *alloc_huge_page_node(struct hstate *h, int nid); struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); +struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, + nodemask_t *nmask); int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); @@ -450,12 +472,17 @@ static inline pgoff_t basepage_index(struct page *page) return __basepage_index(page); } +extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); static inline bool hugepage_migration_supported(struct hstate *h) { #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION - return huge_page_shift(h) == PMD_SHIFT; + if ((huge_page_shift(h) == PMD_SHIFT) || + (huge_page_shift(h) == PGDIR_SHIFT)) + return true; + else + return false; #else return false; #endif @@ -490,10 +517,19 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { atomic_long_sub(l, &mm->hugetlb_usage); } + +#ifndef set_huge_swap_pte_at +static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned long sz) +{ + set_huge_pte_at(mm, addr, ptep, pte); +} +#endif #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page(v, a, r) NULL #define alloc_huge_page_node(h, nid) NULL +#define alloc_huge_page_nodemask(h, preferred_nid, nmask) NULL #define alloc_huge_page_noerr(v, a, r) NULL #define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL @@ -507,19 +543,46 @@ struct hstate {}; #define vma_mmu_pagesize(v) PAGE_SIZE #define huge_page_order(h) 0 #define huge_page_shift(h) PAGE_SHIFT +static inline bool hstate_is_gigantic(struct hstate *h) +{ + return false; +} + static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } -#define hstate_index_to_shift(index) 0 -#define hstate_index(h) 0 + +static inline unsigned hstate_index_to_shift(unsigned index) +{ + return 0; +} + +static inline int hstate_index(struct hstate *h) +{ + return 0; +} static inline pgoff_t basepage_index(struct page *page) { return page->index; } -#define dissolve_free_huge_pages(s, e) 0 -#define hugepage_migration_supported(h) false + +static inline int dissolve_free_huge_page(struct page *page) +{ + return 0; +} + +static inline int dissolve_free_huge_pages(unsigned long start_pfn, + unsigned long end_pfn) +{ + return 0; +} + +static inline bool hugepage_migration_supported(struct hstate *h) +{ + return false; +} static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) @@ -534,6 +597,11 @@ static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } + +static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned long sz) +{ +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 78d59dba563e..ceb751987c40 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -88,6 +88,7 @@ enum hwmon_temp_attributes { #define HWMON_T_CRIT_HYST BIT(hwmon_temp_crit_hyst) #define HWMON_T_EMERGENCY BIT(hwmon_temp_emergency) #define HWMON_T_EMERGENCY_HYST BIT(hwmon_temp_emergency_hyst) +#define HWMON_T_ALARM BIT(hwmon_temp_alarm) #define HWMON_T_MIN_ALARM BIT(hwmon_temp_min_alarm) #define HWMON_T_MAX_ALARM BIT(hwmon_temp_max_alarm) #define HWMON_T_CRIT_ALARM BIT(hwmon_temp_crit_alarm) @@ -336,7 +337,7 @@ struct hwmon_ops { int (*read)(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val); int (*read_string)(struct device *dev, enum hwmon_sensor_types type, - u32 attr, int channel, char **str); + u32 attr, int channel, const char **str); int (*write)(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long val); }; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 183efde54269..b7d7bbec74e0 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -32,11 +32,10 @@ #include <linux/scatterlist.h> #include <linux/list.h> #include <linux/timer.h> -#include <linux/workqueue.h> #include <linux/completion.h> #include <linux/device.h> #include <linux/mod_devicetable.h> - +#include <linux/interrupt.h> #define MAX_PAGE_BUFFER_COUNT 32 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ @@ -139,8 +138,8 @@ struct hv_ring_buffer_info { * for the specified ring buffer */ static inline void -hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, - u32 *read, u32 *write) +hv_get_ringbuffer_availbytes(const struct hv_ring_buffer_info *rbi, + u32 *read, u32 *write) { u32 read_loc, write_loc, dsize; @@ -154,7 +153,7 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, *read = dsize - *write; } -static inline u32 hv_get_bytes_to_read(struct hv_ring_buffer_info *rbi) +static inline u32 hv_get_bytes_to_read(const struct hv_ring_buffer_info *rbi) { u32 read_loc, write_loc, dsize, read; @@ -168,7 +167,7 @@ static inline u32 hv_get_bytes_to_read(struct hv_ring_buffer_info *rbi) return read; } -static inline u32 hv_get_bytes_to_write(struct hv_ring_buffer_info *rbi) +static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi) { u32 read_loc, write_loc, dsize, write; @@ -492,6 +491,12 @@ struct vmbus_channel_rescind_offer { u32 child_relid; } __packed; +static inline u32 +hv_ringbuffer_pending_size(const struct hv_ring_buffer_info *rbi) +{ + return rbi->ring_buffer->pending_send_sz; +} + /* * Request Offer -- no parameters, SynIC message contains the partition ID * Set Snoop -- no parameters, SynIC message contains the partition ID @@ -525,10 +530,10 @@ struct vmbus_channel_open_channel { u32 target_vp; /* - * The upstream ring buffer begins at offset zero in the memory - * described by RingBufferGpadlHandle. The downstream ring buffer - * follows it at this offset (in pages). - */ + * The upstream ring buffer begins at offset zero in the memory + * described by RingBufferGpadlHandle. The downstream ring buffer + * follows it at this offset (in pages). + */ u32 downstream_ringbuffer_pageoffset; /* User-specific data to be passed along to the server endpoint. */ @@ -641,6 +646,7 @@ struct vmbus_channel_msginfo { /* Synchronize the request/response if needed */ struct completion waitevent; + struct vmbus_channel *waiting_channel; union { struct vmbus_channel_version_supported version_supported; struct vmbus_channel_open_result open_result; @@ -683,11 +689,6 @@ struct hv_input_signal_event_buffer { struct hv_input_signal_event event; }; -enum hv_signal_policy { - HV_SIGNAL_POLICY_DEFAULT = 0, - HV_SIGNAL_POLICY_EXPLICIT, -}; - enum hv_numa_policy { HV_BALANCED = 0, HV_LOCALIZED, @@ -743,30 +744,30 @@ struct vmbus_channel { u32 ringbuffer_pagecount; struct hv_ring_buffer_info outbound; /* send to parent */ struct hv_ring_buffer_info inbound; /* receive from parent */ - spinlock_t inbound_lock; struct vmbus_close_msg close_msg; - /* Channel callback are invoked in this workqueue context */ - /* HANDLE dataWorkQueue; */ - + /* Channel callback's invoked in softirq context */ + struct tasklet_struct callback_event; void (*onchannel_callback)(void *context); void *channel_callback_context; /* - * A channel can be marked for efficient (batched) - * reading: - * If batched_reading is set to "true", we read until the - * channel is empty and hold off interrupts from the host - * during the entire read process. - * If batched_reading is set to "false", the client is not - * going to perform batched reading. - * - * By default we will enable batched reading; specific - * drivers that don't want this behavior can turn it off. + * A channel can be marked for one of three modes of reading: + * BATCHED - callback called from taslket and should read + * channel until empty. Interrupts from the host + * are masked while read is in process (default). + * DIRECT - callback called from tasklet (softirq). + * ISR - callback called in interrupt context and must + * invoke its own deferred processing. + * Host interrupts are disabled and must be re-enabled + * when ring is empty. */ - - bool batched_reading; + enum hv_callback_mode { + HV_CALL_BATCHED, + HV_CALL_DIRECT, + HV_CALL_ISR + } callback_mode; bool is_dedicated_interrupt; struct hv_input_signal_event_buffer sig_buf; @@ -849,23 +850,13 @@ struct vmbus_channel { * link up channels based on their CPU affinity. */ struct list_head percpu_list; + /* - * Host signaling policy: The default policy will be - * based on the ring buffer state. We will also support - * a policy where the client driver can have explicit - * signaling control. - */ - enum hv_signal_policy signal_policy; - /* - * On the channel send side, many of the VMBUS - * device drivers explicity serialize access to the - * outgoing ring buffer. Give more control to the - * VMBUS device drivers in terms how to serialize - * accesss to the outgoing ring buffer. - * The default behavior will be to aquire the - * ring lock to preserve the current behavior. + * Defer freeing channel until after all cpu's have + * gone through grace period. */ - bool acquire_ring_lock; + struct rcu_head rcu; + /* * For performance critical channels (storage, networking * etc,), Hyper-V has a mechanism to enhance the throughput @@ -906,32 +897,22 @@ struct vmbus_channel { }; -static inline void set_channel_lock_state(struct vmbus_channel *c, bool state) -{ - c->acquire_ring_lock = state; -} - static inline bool is_hvsock_channel(const struct vmbus_channel *c) { return !!(c->offermsg.offer.chn_flags & VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); } -static inline void set_channel_signal_state(struct vmbus_channel *c, - enum hv_signal_policy policy) -{ - c->signal_policy = policy; -} - static inline void set_channel_affinity_state(struct vmbus_channel *c, enum hv_numa_policy policy) { c->affinity_policy = policy; } -static inline void set_channel_read_state(struct vmbus_channel *c, bool state) +static inline void set_channel_read_mode(struct vmbus_channel *c, + enum hv_callback_mode mode) { - c->batched_reading = state; + c->callback_mode = mode; } static inline void set_per_channel_state(struct vmbus_channel *c, void *s) @@ -1037,7 +1018,7 @@ extern int vmbus_open(struct vmbus_channel *channel, u32 recv_ringbuffersize, void *userdata, u32 userdatalen, - void(*onchannel_callback)(void *context), + void (*onchannel_callback)(void *context), void *context); extern void vmbus_close(struct vmbus_channel *channel); @@ -1054,8 +1035,7 @@ extern int vmbus_sendpacket_ctl(struct vmbus_channel *channel, u32 bufferLen, u64 requestid, enum vmbus_packet_type type, - u32 flags, - bool kick_q); + u32 flags); extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, struct hv_page_buffer pagebuffers[], @@ -1070,8 +1050,7 @@ extern int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, void *buffer, u32 bufferlen, u64 requestid, - u32 flags, - bool kick_q); + u32 flags); extern int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel, struct hv_multipage_buffer *mpb, @@ -1181,6 +1160,17 @@ static inline void *hv_get_drvdata(struct hv_device *dev) return dev_get_drvdata(&dev->device); } +struct hv_ring_buffer_debug_info { + u32 current_interrupt_mask; + u32 current_read_index; + u32 current_write_index; + u32 bytes_avail_toread; + u32 bytes_avail_towrite; +}; + +void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, + struct hv_ring_buffer_debug_info *debug_info); + /* Vmbus interface */ #define vmbus_driver_register(driver) \ __vmbus_driver_register(driver, THIS_MODULE, KBUILD_MODNAME) @@ -1454,16 +1444,14 @@ struct hyperv_service_callback { char *log_msg; uuid_le data; struct vmbus_channel *channel; - void (*callback) (void *context); + void (*callback)(void *context); }; #define MAX_SRV_VER 0x7ffffff -extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *, - struct icmsg_negotiate *, u8 *, int, - int); - -void hv_event_tasklet_disable(struct vmbus_channel *channel); -void hv_event_tasklet_enable(struct vmbus_channel *channel); +extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, + const int *fw_version, int fw_vercnt, + const int *srv_version, int srv_vercnt, + int *nego_fw_version, int *nego_srv_version); void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); @@ -1480,9 +1468,9 @@ void vmbus_set_event(struct vmbus_channel *channel); /* Get the start of the ring buffer. */ static inline void * -hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info) +hv_get_ring_buffer(const struct hv_ring_buffer_info *ring_info) { - return (void *)ring_info->ring_buffer->buffer; + return ring_info->ring_buffer->buffer; } /* @@ -1532,91 +1520,83 @@ static inline void hv_signal_on_read(struct vmbus_channel *channel) cached_write_sz = hv_get_cached_bytes_to_write(rbi); if (cached_write_sz < pending_sz) vmbus_setevent(channel); - - return; } -static inline void -init_cached_read_index(struct vmbus_channel *channel) +/* + * Mask off host interrupt callback notifications + */ +static inline void hv_begin_read(struct hv_ring_buffer_info *rbi) { - struct hv_ring_buffer_info *rbi = &channel->inbound; + rbi->ring_buffer->interrupt_mask = 1; - rbi->cached_read_index = rbi->ring_buffer->read_index; + /* make sure mask update is not reordered */ + virt_mb(); } /* - * An API to support in-place processing of incoming VMBUS packets. + * Re-enable host callback and return number of outstanding bytes */ -#define VMBUS_PKT_TRAILER 8 - -static inline struct vmpacket_descriptor * -get_next_pkt_raw(struct vmbus_channel *channel) +static inline u32 hv_end_read(struct hv_ring_buffer_info *rbi) { - struct hv_ring_buffer_info *ring_info = &channel->inbound; - u32 priv_read_loc = ring_info->priv_read_index; - void *ring_buffer = hv_get_ring_buffer(ring_info); - u32 dsize = ring_info->ring_datasize; - /* - * delta is the difference between what is available to read and - * what was already consumed in place. We commit read index after - * the whole batch is processed. - */ - u32 delta = priv_read_loc >= ring_info->ring_buffer->read_index ? - priv_read_loc - ring_info->ring_buffer->read_index : - (dsize - ring_info->ring_buffer->read_index) + priv_read_loc; - u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta); - if (bytes_avail_toread < sizeof(struct vmpacket_descriptor)) - return NULL; + rbi->ring_buffer->interrupt_mask = 0; + + /* make sure mask update is not reordered */ + virt_mb(); - return ring_buffer + priv_read_loc; + /* + * Now check to see if the ring buffer is still empty. + * If it is not, we raced and we need to process new + * incoming messages. + */ + return hv_get_bytes_to_read(rbi); } /* - * A helper function to step through packets "in-place" - * This API is to be called after each successful call - * get_next_pkt_raw(). + * An API to support in-place processing of incoming VMBUS packets. */ -static inline void put_pkt_raw(struct vmbus_channel *channel, - struct vmpacket_descriptor *desc) + +/* Get data payload associated with descriptor */ +static inline void *hv_pkt_data(const struct vmpacket_descriptor *desc) { - struct hv_ring_buffer_info *ring_info = &channel->inbound; - u32 packetlen = desc->len8 << 3; - u32 dsize = ring_info->ring_datasize; + return (void *)((unsigned long)desc + (desc->offset8 << 3)); +} - /* - * Include the packet trailer. - */ - ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER; - ring_info->priv_read_index %= dsize; +/* Get data size associated with descriptor */ +static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) +{ + return (desc->len8 << 3) - (desc->offset8 << 3); } + +struct vmpacket_descriptor * +hv_pkt_iter_first(struct vmbus_channel *channel); + +struct vmpacket_descriptor * +__hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt); + +void hv_pkt_iter_close(struct vmbus_channel *channel); + /* - * This call commits the read index and potentially signals the host. - * Here is the pattern for using the "in-place" consumption APIs: - * - * init_cached_read_index(); - * - * while (get_next_pkt_raw() { - * process the packet "in-place"; - * put_pkt_raw(); - * } - * if (packets processed in place) - * commit_rd_index(); + * Get next packet descriptor from iterator + * If at end of list, return NULL and update host. */ -static inline void commit_rd_index(struct vmbus_channel *channel) +static inline struct vmpacket_descriptor * +hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) { - struct hv_ring_buffer_info *ring_info = &channel->inbound; - /* - * Make sure all reads are done before we update the read index since - * the writer may start writing to the read area once the read index - * is updated. - */ - virt_rmb(); - ring_info->ring_buffer->read_index = ring_info->priv_read_index; + struct vmpacket_descriptor *nxt; + + nxt = __hv_pkt_iter_next(channel, pkt); + if (!nxt) + hv_pkt_iter_close(channel); - hv_signal_on_read(channel); + return nxt; } +#define foreach_vmbus_pkt(pkt, channel) \ + for (pkt = hv_pkt_iter_first(channel); pkt; \ + pkt = hv_pkt_iter_next(channel, pkt)) #endif /* _HYPERV_H */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 4b45ec46161f..00ca5b86a753 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -30,6 +30,7 @@ #include <linux/device.h> /* for struct device */ #include <linux/sched.h> /* for completion */ #include <linux/mutex.h> +#include <linux/rtmutex.h> #include <linux/irqdomain.h> /* for Host Notify IRQ */ #include <linux/of.h> /* for struct device_node */ #include <linux/swab.h> /* for swab16 */ @@ -37,6 +38,7 @@ extern struct bus_type i2c_bus_type; extern struct device_type i2c_adapter_type; +extern struct device_type i2c_client_type; /* --- General options ------------------------------------------------ */ @@ -51,6 +53,7 @@ enum i2c_slave_event; typedef int (*i2c_slave_cb_t)(struct i2c_client *, enum i2c_slave_event, u8 *); struct module; +struct property_entry; #if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE) /* @@ -147,6 +150,7 @@ enum i2c_alert_protocol { * @detect: Callback for device detection * @address_list: The I2C addresses to probe (for detect) * @clients: List of detected clients we created (for i2c-core use only) + * @disable_i2c_core_irq_mapping: Tell the i2c-core to not do irq-mapping * * The driver.owner field should be set to the module owner of this driver. * The driver.name field should be set to the name of this driver. @@ -210,6 +214,8 @@ struct i2c_driver { int (*detect)(struct i2c_client *, struct i2c_board_info *); const unsigned short *address_list; struct list_head clients; + + bool disable_i2c_core_irq_mapping; }; #define to_i2c_driver(d) container_of(d, struct i2c_driver, driver) @@ -282,12 +288,15 @@ enum i2c_slave_event { extern int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb); extern int i2c_slave_unregister(struct i2c_client *client); +extern bool i2c_detect_slave_mode(struct device *dev); static inline int i2c_slave_event(struct i2c_client *client, enum i2c_slave_event event, u8 *val) { return client->slave_cb(client, event, val); } +#else +static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } #endif /** @@ -299,6 +308,9 @@ static inline int i2c_slave_event(struct i2c_client *client, * @archdata: copied into i2c_client.dev.archdata * @of_node: pointer to OpenFirmware device node * @fwnode: device node supplied by the platform firmware + * @properties: additional device properties for the device + * @resources: resources associated with the device + * @num_resources: number of resources in the @resources array * @irq: stored in i2c_client.irq * * I2C doesn't actually support hardware probing, although controllers and @@ -320,6 +332,9 @@ struct i2c_board_info { struct dev_archdata *archdata; struct device_node *of_node; struct fwnode_handle *fwnode; + const struct property_entry *properties; + const struct resource *resources; + unsigned int num_resources; int irq; }; @@ -819,11 +834,18 @@ static inline const struct of_device_id #if IS_ENABLED(CONFIG_ACPI) u32 i2c_acpi_find_bus_speed(struct device *dev); +struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, + struct i2c_board_info *info); #else static inline u32 i2c_acpi_find_bus_speed(struct device *dev) { return 0; } +static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, + int index, struct i2c_board_info *info) +{ + return NULL; +} #endif /* CONFIG_ACPI */ #endif /* _LINUX_I2C_H */ diff --git a/include/linux/i2c/i2c-sh_mobile.h b/include/linux/i2c/i2c-sh_mobile.h deleted file mode 100644 index 06e3089795fb..000000000000 --- a/include/linux/i2c/i2c-sh_mobile.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef __I2C_SH_MOBILE_H__ -#define __I2C_SH_MOBILE_H__ - -#include <linux/platform_device.h> - -struct i2c_sh_mobile_platform_data { - unsigned long bus_speed; - unsigned int clks_per_count; -}; - -#endif /* __I2C_SH_MOBILE_H__ */ diff --git a/include/linux/i2c/mpr121_touchkey.h b/include/linux/i2c/mpr121_touchkey.h deleted file mode 100644 index f0bcc38bbb97..000000000000 --- a/include/linux/i2c/mpr121_touchkey.h +++ /dev/null @@ -1,20 +0,0 @@ -/* Header file for Freescale MPR121 Capacitive Touch Sensor */ - -#ifndef _MPR121_TOUCHKEY_H -#define _MPR121_TOUCHKEY_H - -/** - * struct mpr121_platform_data - platform data for mpr121 sensor - * @keymap: pointer to array of KEY_* values representing keymap - * @keymap_size: size of the keymap - * @wakeup: configure the button as a wake-up source - * @vdd_uv: VDD voltage in uV - */ -struct mpr121_platform_data { - const unsigned short *keymap; - unsigned int keymap_size; - bool wakeup; - int vdd_uv; -}; - -#endif /* _MPR121_TOUCHKEY_H */ diff --git a/include/linux/i2c/twl4030-madc.h b/include/linux/i2c/twl4030-madc.h deleted file mode 100644 index 1c0134dd3271..000000000000 --- a/include/linux/i2c/twl4030-madc.h +++ /dev/null @@ -1,147 +0,0 @@ -/* - * twl4030_madc.h - Header for TWL4030 MADC - * - * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/ - * J Keerthy <j-keerthy@ti.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - * - */ - -#ifndef _TWL4030_MADC_H -#define _TWL4030_MADC_H - -struct twl4030_madc_conversion_method { - u8 sel; - u8 avg; - u8 rbase; - u8 ctrl; -}; - -#define TWL4030_MADC_MAX_CHANNELS 16 - - -/* - * twl4030_madc_request- madc request packet for channel conversion - * @channels: 16 bit bitmap for individual channels - * @do_avgP: sample the input channel for 4 consecutive cycles - * @method: RT, SW1, SW2 - * @type: Polling or interrupt based method - * @raw: Return raw value, do not convert it - */ - -struct twl4030_madc_request { - unsigned long channels; - bool do_avg; - u16 method; - u16 type; - bool active; - bool result_pending; - bool raw; - int rbuf[TWL4030_MADC_MAX_CHANNELS]; - void (*func_cb)(int len, int channels, int *buf); -}; - -enum conversion_methods { - TWL4030_MADC_RT, - TWL4030_MADC_SW1, - TWL4030_MADC_SW2, - TWL4030_MADC_NUM_METHODS -}; - -enum sample_type { - TWL4030_MADC_WAIT, - TWL4030_MADC_IRQ_ONESHOT, - TWL4030_MADC_IRQ_REARM -}; - -#define TWL4030_MADC_CTRL1 0x00 -#define TWL4030_MADC_CTRL2 0x01 - -#define TWL4030_MADC_RTSELECT_LSB 0x02 -#define TWL4030_MADC_SW1SELECT_LSB 0x06 -#define TWL4030_MADC_SW2SELECT_LSB 0x0A - -#define TWL4030_MADC_RTAVERAGE_LSB 0x04 -#define TWL4030_MADC_SW1AVERAGE_LSB 0x08 -#define TWL4030_MADC_SW2AVERAGE_LSB 0x0C - -#define TWL4030_MADC_CTRL_SW1 0x12 -#define TWL4030_MADC_CTRL_SW2 0x13 - -#define TWL4030_MADC_RTCH0_LSB 0x17 -#define TWL4030_MADC_GPCH0_LSB 0x37 - -#define TWL4030_MADC_MADCON (1 << 0) /* MADC power on */ -#define TWL4030_MADC_BUSY (1 << 0) /* MADC busy */ -/* MADC conversion completion */ -#define TWL4030_MADC_EOC_SW (1 << 1) -/* MADC SWx start conversion */ -#define TWL4030_MADC_SW_START (1 << 5) -#define TWL4030_MADC_ADCIN0 (1 << 0) -#define TWL4030_MADC_ADCIN1 (1 << 1) -#define TWL4030_MADC_ADCIN2 (1 << 2) -#define TWL4030_MADC_ADCIN3 (1 << 3) -#define TWL4030_MADC_ADCIN4 (1 << 4) -#define TWL4030_MADC_ADCIN5 (1 << 5) -#define TWL4030_MADC_ADCIN6 (1 << 6) -#define TWL4030_MADC_ADCIN7 (1 << 7) -#define TWL4030_MADC_ADCIN8 (1 << 8) -#define TWL4030_MADC_ADCIN9 (1 << 9) -#define TWL4030_MADC_ADCIN10 (1 << 10) -#define TWL4030_MADC_ADCIN11 (1 << 11) -#define TWL4030_MADC_ADCIN12 (1 << 12) -#define TWL4030_MADC_ADCIN13 (1 << 13) -#define TWL4030_MADC_ADCIN14 (1 << 14) -#define TWL4030_MADC_ADCIN15 (1 << 15) - -/* Fixed channels */ -#define TWL4030_MADC_BTEMP TWL4030_MADC_ADCIN1 -#define TWL4030_MADC_VBUS TWL4030_MADC_ADCIN8 -#define TWL4030_MADC_VBKB TWL4030_MADC_ADCIN9 -#define TWL4030_MADC_ICHG TWL4030_MADC_ADCIN10 -#define TWL4030_MADC_VCHG TWL4030_MADC_ADCIN11 -#define TWL4030_MADC_VBAT TWL4030_MADC_ADCIN12 - -/* Step size and prescaler ratio */ -#define TEMP_STEP_SIZE 147 -#define TEMP_PSR_R 100 -#define CURR_STEP_SIZE 147 -#define CURR_PSR_R1 44 -#define CURR_PSR_R2 88 - -#define TWL4030_BCI_BCICTL1 0x23 -#define TWL4030_BCI_CGAIN 0x020 -#define TWL4030_BCI_MESBAT (1 << 1) -#define TWL4030_BCI_TYPEN (1 << 4) -#define TWL4030_BCI_ITHEN (1 << 3) - -#define REG_BCICTL2 0x024 -#define TWL4030_BCI_ITHSENS 0x007 - -/* Register and bits for GPBR1 register */ -#define TWL4030_REG_GPBR1 0x0c -#define TWL4030_GPBR1_MADC_HFCLK_EN (1 << 7) - -struct twl4030_madc_user_parms { - int channel; - int average; - int status; - u16 result; -}; - -int twl4030_madc_conversion(struct twl4030_madc_request *conv); -int twl4030_get_madc_conversion(int channel_no); -#endif diff --git a/include/linux/ide.h b/include/linux/ide.h index a633898f36ac..dc152e4b7f73 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -20,6 +20,7 @@ #include <linux/mutex.h> /* for request_sense */ #include <linux/cdrom.h> +#include <scsi/scsi_cmnd.h> #include <asm/byteorder.h> #include <asm/io.h> @@ -39,20 +40,55 @@ struct device; -/* IDE-specific values for req->cmd_type */ -enum ata_cmd_type_bits { - REQ_TYPE_ATA_TASKFILE = REQ_TYPE_DRV_PRIV + 1, - REQ_TYPE_ATA_PC, - REQ_TYPE_ATA_SENSE, /* sense request */ - REQ_TYPE_ATA_PM_SUSPEND,/* suspend request */ - REQ_TYPE_ATA_PM_RESUME, /* resume request */ +/* values for ide_request.type */ +enum ata_priv_type { + ATA_PRIV_MISC, + ATA_PRIV_TASKFILE, + ATA_PRIV_PC, + ATA_PRIV_SENSE, /* sense request */ + ATA_PRIV_PM_SUSPEND, /* suspend request */ + ATA_PRIV_PM_RESUME, /* resume request */ }; -#define ata_pm_request(rq) \ - ((rq)->cmd_type == REQ_TYPE_ATA_PM_SUSPEND || \ - (rq)->cmd_type == REQ_TYPE_ATA_PM_RESUME) +struct ide_request { + struct scsi_request sreq; + u8 sense[SCSI_SENSE_BUFFERSIZE]; + u8 type; +}; + +static inline struct ide_request *ide_req(struct request *rq) +{ + return blk_mq_rq_to_pdu(rq); +} + +static inline bool ata_misc_request(struct request *rq) +{ + return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_MISC; +} + +static inline bool ata_taskfile_request(struct request *rq) +{ + return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_TASKFILE; +} + +static inline bool ata_pc_request(struct request *rq) +{ + return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_PC; +} + +static inline bool ata_sense_request(struct request *rq) +{ + return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_SENSE; +} + +static inline bool ata_pm_request(struct request *rq) +{ + return blk_rq_is_private(rq) && + (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND || + ide_req(rq)->type == ATA_PRIV_PM_RESUME); +} -/* Error codes returned in rq->errors to the higher part of the driver. */ +/* Error codes returned in result to the higher part of the driver. */ enum { IDE_DRV_ERROR_GENERAL = 101, IDE_DRV_ERROR_FILEMARK = 102, @@ -579,7 +615,7 @@ struct ide_drive_s { /* current sense rq and buffer */ bool sense_rq_armed; - struct request sense_rq; + struct request *sense_rq; struct request_sense sense_data; }; @@ -635,7 +671,7 @@ struct ide_port_ops { void (*init_dev)(ide_drive_t *); void (*set_pio_mode)(struct hwif_s *, ide_drive_t *); void (*set_dma_mode)(struct hwif_s *, ide_drive_t *); - int (*reset_poll)(ide_drive_t *); + blk_status_t (*reset_poll)(ide_drive_t *); void (*pre_reset)(ide_drive_t *); void (*resetproc)(ide_drive_t *); void (*maskproc)(ide_drive_t *, int); @@ -1056,7 +1092,7 @@ int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned l extern int ide_vlb_clk; extern int ide_pci_clk; -int ide_end_rq(ide_drive_t *, struct request *, int, unsigned int); +int ide_end_rq(ide_drive_t *, struct request *, blk_status_t, unsigned int); void ide_kill_rq(ide_drive_t *, struct request *); void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); @@ -1087,7 +1123,7 @@ extern int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, int arg); void ide_complete_cmd(ide_drive_t *, struct ide_cmd *, u8, u8); -int ide_complete_rq(ide_drive_t *, int, unsigned int); +int ide_complete_rq(ide_drive_t *, blk_status_t, unsigned int); void ide_tf_readback(ide_drive_t *drive, struct ide_cmd *cmd); void ide_tf_dump(const char *, struct ide_cmd *); diff --git a/include/linux/idr.h b/include/linux/idr.h index 3c01b89aed67..bf70b3ef0a07 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -12,47 +12,29 @@ #ifndef __IDR_H__ #define __IDR_H__ -#include <linux/types.h> -#include <linux/bitops.h> -#include <linux/init.h> -#include <linux/rcupdate.h> +#include <linux/radix-tree.h> +#include <linux/gfp.h> +#include <linux/percpu.h> + +struct idr { + struct radix_tree_root idr_rt; + unsigned int idr_next; +}; /* - * Using 6 bits at each layer allows us to allocate 7 layers out of each page. - * 8 bits only gave us 3 layers out of every pair of pages, which is less - * efficient except for trees with a largest element between 192-255 inclusive. + * The IDR API does not expose the tagging functionality of the radix tree + * to users. Use tag 0 to track whether a node has free space below it. */ -#define IDR_BITS 6 -#define IDR_SIZE (1 << IDR_BITS) -#define IDR_MASK ((1 << IDR_BITS)-1) - -struct idr_layer { - int prefix; /* the ID prefix of this idr_layer */ - int layer; /* distance from leaf */ - struct idr_layer __rcu *ary[1<<IDR_BITS]; - int count; /* When zero, we can release it */ - union { - /* A zero bit means "space here" */ - DECLARE_BITMAP(bitmap, IDR_SIZE); - struct rcu_head rcu_head; - }; -}; +#define IDR_FREE 0 -struct idr { - struct idr_layer __rcu *hint; /* the last layer allocated from */ - struct idr_layer __rcu *top; - int layers; /* only valid w/o concurrent changes */ - int cur; /* current pos for cyclic allocation */ - spinlock_t lock; - int id_free_cnt; - struct idr_layer *id_free; -}; +/* Set the IDR flag and the IDR_FREE tag */ +#define IDR_RT_MARKER ((__force gfp_t)(3 << __GFP_BITS_SHIFT)) -#define IDR_INIT(name) \ +#define IDR_INIT \ { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER) \ } -#define DEFINE_IDR(name) struct idr name = IDR_INIT(name) +#define DEFINE_IDR(name) struct idr name = IDR_INIT /** * idr_get_cursor - Return the current position of the cyclic allocator @@ -62,9 +44,9 @@ struct idr { * idr_alloc_cyclic() if it is free (otherwise the search will start from * this position). */ -static inline unsigned int idr_get_cursor(struct idr *idr) +static inline unsigned int idr_get_cursor(const struct idr *idr) { - return READ_ONCE(idr->cur); + return READ_ONCE(idr->idr_next); } /** @@ -77,7 +59,7 @@ static inline unsigned int idr_get_cursor(struct idr *idr) */ static inline void idr_set_cursor(struct idr *idr, unsigned int val) { - WRITE_ONCE(idr->cur, val); + WRITE_ONCE(idr->idr_next, val); } /** @@ -97,22 +79,31 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val) * period). */ -/* - * This is what we export. - */ - -void *idr_find_slowpath(struct idr *idp, int id); void idr_preload(gfp_t gfp_mask); -int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask); -int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask); -int idr_for_each(struct idr *idp, +int idr_alloc(struct idr *, void *entry, int start, int end, gfp_t); +int idr_alloc_cyclic(struct idr *, void *entry, int start, int end, gfp_t); +int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); -void *idr_get_next(struct idr *idp, int *nextid); -void *idr_replace(struct idr *idp, void *ptr, int id); -void idr_remove(struct idr *idp, int id); -void idr_destroy(struct idr *idp); -void idr_init(struct idr *idp); -bool idr_is_empty(struct idr *idp); +void *idr_get_next(struct idr *, int *nextid); +void *idr_replace(struct idr *, void *, int id); +void idr_destroy(struct idr *); + +static inline void *idr_remove(struct idr *idr, int id) +{ + return radix_tree_delete_item(&idr->idr_rt, id, NULL); +} + +static inline void idr_init(struct idr *idr) +{ + INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); + idr->idr_next = 0; +} + +static inline bool idr_is_empty(const struct idr *idr) +{ + return radix_tree_empty(&idr->idr_rt) && + radix_tree_tagged(&idr->idr_rt, IDR_FREE); +} /** * idr_preload_end - end preload section started with idr_preload() @@ -137,19 +128,14 @@ static inline void idr_preload_end(void) * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. */ -static inline void *idr_find(struct idr *idr, int id) +static inline void *idr_find(const struct idr *idr, int id) { - struct idr_layer *hint = rcu_dereference_raw(idr->hint); - - if (hint && (id & ~IDR_MASK) == hint->prefix) - return rcu_dereference_raw(hint->ary[id & IDR_MASK]); - - return idr_find_slowpath(idr, id); + return radix_tree_lookup(&idr->idr_rt, id); } /** * idr_for_each_entry - iterate over an idr's elements of a given type - * @idp: idr handle + * @idr: idr handle * @entry: the type * to use as cursor * @id: id entry's key * @@ -157,57 +143,60 @@ static inline void *idr_find(struct idr *idr, int id) * after normal terminatinon @entry is left with the value NULL. This * is convenient for a "not found" value. */ -#define idr_for_each_entry(idp, entry, id) \ - for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id) +#define idr_for_each_entry(idr, entry, id) \ + for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) /** - * idr_for_each_entry - continue iteration over an idr's elements of a given type - * @idp: idr handle + * idr_for_each_entry_continue - continue iteration over an idr's elements of a given type + * @idr: idr handle * @entry: the type * to use as cursor * @id: id entry's key * * Continue to iterate over list of given type, continuing after * the current position. */ -#define idr_for_each_entry_continue(idp, entry, id) \ - for ((entry) = idr_get_next((idp), &(id)); \ +#define idr_for_each_entry_continue(idr, entry, id) \ + for ((entry) = idr_get_next((idr), &(id)); \ entry; \ - ++id, (entry) = idr_get_next((idp), &(id))) + ++id, (entry) = idr_get_next((idr), &(id))) /* * IDA - IDR based id allocator, use when translation from id to * pointer isn't necessary. - * - * IDA_BITMAP_LONGS is calculated to be one less to accommodate - * ida_bitmap->nr_busy so that the whole struct fits in 128 bytes. */ #define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */ -#define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long) - 1) +#define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long)) #define IDA_BITMAP_BITS (IDA_BITMAP_LONGS * sizeof(long) * 8) struct ida_bitmap { - long nr_busy; unsigned long bitmap[IDA_BITMAP_LONGS]; }; +DECLARE_PER_CPU(struct ida_bitmap *, ida_bitmap); + struct ida { - struct idr idr; - struct ida_bitmap *free_bitmap; + struct radix_tree_root ida_rt; }; -#define IDA_INIT(name) { .idr = IDR_INIT((name).idr), .free_bitmap = NULL, } -#define DEFINE_IDA(name) struct ida name = IDA_INIT(name) +#define IDA_INIT { \ + .ida_rt = RADIX_TREE_INIT(IDR_RT_MARKER | GFP_NOWAIT), \ +} +#define DEFINE_IDA(name) struct ida name = IDA_INIT int ida_pre_get(struct ida *ida, gfp_t gfp_mask); int ida_get_new_above(struct ida *ida, int starting_id, int *p_id); void ida_remove(struct ida *ida, int id); void ida_destroy(struct ida *ida); -void ida_init(struct ida *ida); int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end, gfp_t gfp_mask); void ida_simple_remove(struct ida *ida, unsigned int id); +static inline void ida_init(struct ida *ida) +{ + INIT_RADIX_TREE(&ida->ida_rt, IDR_RT_MARKER | GFP_NOWAIT); +} + /** * ida_get_new - allocate new ID * @ida: idr handle @@ -220,11 +209,8 @@ static inline int ida_get_new(struct ida *ida, int *p_id) return ida_get_new_above(ida, 0, p_id); } -static inline bool ida_is_empty(struct ida *ida) +static inline bool ida_is_empty(const struct ida *ida) { - return idr_is_empty(&ida->idr); + return radix_tree_empty(&ida->ida_rt); } - -void __init idr_init_cache(void); - #endif /* __IDR_H__ */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index fe849329511a..55a604ad459f 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -7,7 +7,7 @@ * Copyright (c) 2005, Devicescape Software, Inc. * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net> * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH - * Copyright (c) 2016 Intel Deutschland GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -185,6 +185,8 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) /* number of user priorities 802.11 uses */ #define IEEE80211_NUM_UPS 8 +/* number of ACs */ +#define IEEE80211_NUM_ACS 4 #define IEEE80211_QOS_CTL_LEN 2 /* 1d tag mask */ @@ -1041,8 +1043,9 @@ struct ieee80211_mgmt { } u; } __packed __aligned(2); -/* Supported Rates value encodings in 802.11n-2009 7.3.2.2 */ +/* Supported rates membership selectors */ #define BSS_MEMBERSHIP_SELECTOR_HT_PHY 127 +#define BSS_MEMBERSHIP_SELECTOR_VHT_PHY 126 /* mgmt header + 1 byte category code */ #define IEEE80211_MIN_ACTION_SIZE offsetof(struct ieee80211_mgmt, u.action.u) @@ -1408,6 +1411,8 @@ struct ieee80211_ht_operation { #define IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED 3 #define IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT 0x0004 #define IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT 0x0010 +#define IEEE80211_HT_OP_MODE_CCFS2_SHIFT 5 +#define IEEE80211_HT_OP_MODE_CCFS2_MASK 0x1fe0 /* for stbc_param */ #define IEEE80211_HT_STBC_PARAM_DUAL_BEACON 0x0040 @@ -1522,14 +1527,14 @@ enum ieee80211_vht_chanwidth { * This structure is the "VHT operation element" as * described in 802.11ac D3.0 8.4.2.161 * @chan_width: Operating channel width + * @center_freq_seg0_idx: center freq segment 0 index * @center_freq_seg1_idx: center freq segment 1 index - * @center_freq_seg2_idx: center freq segment 2 index * @basic_mcs_set: VHT Basic MCS rate set */ struct ieee80211_vht_operation { u8 chan_width; + u8 center_freq_seg0_idx; u8 center_freq_seg1_idx; - u8 center_freq_seg2_idx; __le16 basic_mcs_set; } __packed; @@ -1718,6 +1723,9 @@ enum ieee80211_statuscode { WLAN_STATUS_REJECT_DSE_BAND = 96, WLAN_STATUS_DENIED_WITH_SUGGESTED_BAND_AND_CHANNEL = 99, WLAN_STATUS_DENIED_DUE_TO_SPECTRUM_MANAGEMENT = 103, + /* 802.11ai */ + WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 108, + WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109, }; @@ -2099,10 +2107,49 @@ enum ieee80211_key_len { #define FILS_NONCE_LEN 16 #define FILS_MAX_KEK_LEN 64 -/* Public action codes */ +#define FILS_ERP_MAX_USERNAME_LEN 16 +#define FILS_ERP_MAX_REALM_LEN 253 +#define FILS_ERP_MAX_RRK_LEN 64 + +#define PMK_MAX_LEN 48 + +/* Public action codes (IEEE Std 802.11-2016, 9.6.8.1, Table 9-307) */ enum ieee80211_pub_actioncode { + WLAN_PUB_ACTION_20_40_BSS_COEX = 0, + WLAN_PUB_ACTION_DSE_ENABLEMENT = 1, + WLAN_PUB_ACTION_DSE_DEENABLEMENT = 2, + WLAN_PUB_ACTION_DSE_REG_LOC_ANN = 3, WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, + WLAN_PUB_ACTION_DSE_MSMT_REQ = 5, + WLAN_PUB_ACTION_DSE_MSMT_RESP = 6, + WLAN_PUB_ACTION_MSMT_PILOT = 7, + WLAN_PUB_ACTION_DSE_PC = 8, + WLAN_PUB_ACTION_VENDOR_SPECIFIC = 9, + WLAN_PUB_ACTION_GAS_INITIAL_REQ = 10, + WLAN_PUB_ACTION_GAS_INITIAL_RESP = 11, + WLAN_PUB_ACTION_GAS_COMEBACK_REQ = 12, + WLAN_PUB_ACTION_GAS_COMEBACK_RESP = 13, WLAN_PUB_ACTION_TDLS_DISCOVER_RES = 14, + WLAN_PUB_ACTION_LOC_TRACK_NOTI = 15, + WLAN_PUB_ACTION_QAB_REQUEST_FRAME = 16, + WLAN_PUB_ACTION_QAB_RESPONSE_FRAME = 17, + WLAN_PUB_ACTION_QMF_POLICY = 18, + WLAN_PUB_ACTION_QMF_POLICY_CHANGE = 19, + WLAN_PUB_ACTION_QLOAD_REQUEST = 20, + WLAN_PUB_ACTION_QLOAD_REPORT = 21, + WLAN_PUB_ACTION_HCCA_TXOP_ADVERT = 22, + WLAN_PUB_ACTION_HCCA_TXOP_RESPONSE = 23, + WLAN_PUB_ACTION_PUBLIC_KEY = 24, + WLAN_PUB_ACTION_CHANNEL_AVAIL_QUERY = 25, + WLAN_PUB_ACTION_CHANNEL_SCHEDULE_MGMT = 26, + WLAN_PUB_ACTION_CONTACT_VERI_SIGNAL = 27, + WLAN_PUB_ACTION_GDD_ENABLEMENT_REQ = 28, + WLAN_PUB_ACTION_GDD_ENABLEMENT_RESP = 29, + WLAN_PUB_ACTION_NETWORK_CHANNEL_CONTROL = 30, + WLAN_PUB_ACTION_WHITE_SPACE_MAP_ANN = 31, + WLAN_PUB_ACTION_FTM_REQUEST = 32, + WLAN_PUB_ACTION_FTM = 33, + WLAN_PUB_ACTION_FILS_DISCOVERY = 34, }; /* TDLS action codes */ @@ -2163,37 +2210,37 @@ enum ieee80211_tdls_actioncode { #define WLAN_BSS_COEX_INFORMATION_REQUEST BIT(0) /** - * enum - mesh synchronization method identifier + * enum ieee80211_mesh_sync_method - mesh synchronization method identifier * * @IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET: the default synchronization method * @IEEE80211_SYNC_METHOD_VENDOR: a vendor specific synchronization method * that will be specified in a vendor specific information element */ -enum { +enum ieee80211_mesh_sync_method { IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET = 1, IEEE80211_SYNC_METHOD_VENDOR = 255, }; /** - * enum - mesh path selection protocol identifier + * enum ieee80211_mesh_path_protocol - mesh path selection protocol identifier * * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will * be specified in a vendor specific information element */ -enum { +enum ieee80211_mesh_path_protocol { IEEE80211_PATH_PROTOCOL_HWMP = 1, IEEE80211_PATH_PROTOCOL_VENDOR = 255, }; /** - * enum - mesh path selection metric identifier + * enum ieee80211_mesh_path_metric - mesh path selection metric identifier * * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be * specified in a vendor specific information element */ -enum { +enum ieee80211_mesh_path_metric { IEEE80211_PATH_METRIC_AIRTIME = 1, IEEE80211_PATH_METRIC_VENDOR = 255, }; @@ -2302,6 +2349,32 @@ struct ieee80211_timeout_interval_ie { __le32 value; } __packed; +/** + * enum ieee80211_idle_options - BSS idle options + * @WLAN_IDLE_OPTIONS_PROTECTED_KEEP_ALIVE: the station should send an RSN + * protected frame to the AP to reset the idle timer at the AP for + * the station. + */ +enum ieee80211_idle_options { + WLAN_IDLE_OPTIONS_PROTECTED_KEEP_ALIVE = BIT(0), +}; + +/** + * struct ieee80211_bss_max_idle_period_ie + * + * This structure refers to "BSS Max idle period element" + * + * @max_idle_period: indicates the time period during which a station can + * refrain from transmitting frames to its associated AP without being + * disassociated. In units of 1000 TUs. + * @idle_options: indicates the options associated with the BSS idle capability + * as specified in &enum ieee80211_idle_options. + */ +struct ieee80211_bss_max_idle_period_ie { + __le16 max_idle_period; + u8 idle_options; +} __packed; + /* BACK action code */ enum ieee80211_back_actioncode { WLAN_ACTION_ADDBA_REQ = 0, @@ -2322,35 +2395,49 @@ enum ieee80211_sa_query_action { }; +#define SUITE(oui, id) (((oui) << 8) | (id)) + /* cipher suite selectors */ -#define WLAN_CIPHER_SUITE_USE_GROUP 0x000FAC00 -#define WLAN_CIPHER_SUITE_WEP40 0x000FAC01 -#define WLAN_CIPHER_SUITE_TKIP 0x000FAC02 -/* reserved: 0x000FAC03 */ -#define WLAN_CIPHER_SUITE_CCMP 0x000FAC04 -#define WLAN_CIPHER_SUITE_WEP104 0x000FAC05 -#define WLAN_CIPHER_SUITE_AES_CMAC 0x000FAC06 -#define WLAN_CIPHER_SUITE_GCMP 0x000FAC08 -#define WLAN_CIPHER_SUITE_GCMP_256 0x000FAC09 -#define WLAN_CIPHER_SUITE_CCMP_256 0x000FAC0A -#define WLAN_CIPHER_SUITE_BIP_GMAC_128 0x000FAC0B -#define WLAN_CIPHER_SUITE_BIP_GMAC_256 0x000FAC0C -#define WLAN_CIPHER_SUITE_BIP_CMAC_256 0x000FAC0D - -#define WLAN_CIPHER_SUITE_SMS4 0x00147201 +#define WLAN_CIPHER_SUITE_USE_GROUP SUITE(0x000FAC, 0) +#define WLAN_CIPHER_SUITE_WEP40 SUITE(0x000FAC, 1) +#define WLAN_CIPHER_SUITE_TKIP SUITE(0x000FAC, 2) +/* reserved: SUITE(0x000FAC, 3) */ +#define WLAN_CIPHER_SUITE_CCMP SUITE(0x000FAC, 4) +#define WLAN_CIPHER_SUITE_WEP104 SUITE(0x000FAC, 5) +#define WLAN_CIPHER_SUITE_AES_CMAC SUITE(0x000FAC, 6) +#define WLAN_CIPHER_SUITE_GCMP SUITE(0x000FAC, 8) +#define WLAN_CIPHER_SUITE_GCMP_256 SUITE(0x000FAC, 9) +#define WLAN_CIPHER_SUITE_CCMP_256 SUITE(0x000FAC, 10) +#define WLAN_CIPHER_SUITE_BIP_GMAC_128 SUITE(0x000FAC, 11) +#define WLAN_CIPHER_SUITE_BIP_GMAC_256 SUITE(0x000FAC, 12) +#define WLAN_CIPHER_SUITE_BIP_CMAC_256 SUITE(0x000FAC, 13) + +#define WLAN_CIPHER_SUITE_SMS4 SUITE(0x001472, 1) /* AKM suite selectors */ -#define WLAN_AKM_SUITE_8021X 0x000FAC01 -#define WLAN_AKM_SUITE_PSK 0x000FAC02 -#define WLAN_AKM_SUITE_8021X_SHA256 0x000FAC05 -#define WLAN_AKM_SUITE_PSK_SHA256 0x000FAC06 -#define WLAN_AKM_SUITE_TDLS 0x000FAC07 -#define WLAN_AKM_SUITE_SAE 0x000FAC08 -#define WLAN_AKM_SUITE_FT_OVER_SAE 0x000FAC09 +#define WLAN_AKM_SUITE_8021X SUITE(0x000FAC, 1) +#define WLAN_AKM_SUITE_PSK SUITE(0x000FAC, 2) +#define WLAN_AKM_SUITE_FT_8021X SUITE(0x000FAC, 3) +#define WLAN_AKM_SUITE_FT_PSK SUITE(0x000FAC, 4) +#define WLAN_AKM_SUITE_8021X_SHA256 SUITE(0x000FAC, 5) +#define WLAN_AKM_SUITE_PSK_SHA256 SUITE(0x000FAC, 6) +#define WLAN_AKM_SUITE_TDLS SUITE(0x000FAC, 7) +#define WLAN_AKM_SUITE_SAE SUITE(0x000FAC, 8) +#define WLAN_AKM_SUITE_FT_OVER_SAE SUITE(0x000FAC, 9) +#define WLAN_AKM_SUITE_8021X_SUITE_B SUITE(0x000FAC, 11) +#define WLAN_AKM_SUITE_8021X_SUITE_B_192 SUITE(0x000FAC, 12) +#define WLAN_AKM_SUITE_FILS_SHA256 SUITE(0x000FAC, 14) +#define WLAN_AKM_SUITE_FILS_SHA384 SUITE(0x000FAC, 15) +#define WLAN_AKM_SUITE_FT_FILS_SHA256 SUITE(0x000FAC, 16) +#define WLAN_AKM_SUITE_FT_FILS_SHA384 SUITE(0x000FAC, 17) #define WLAN_MAX_KEY_LEN 32 +#define WLAN_PMK_NAME_LEN 16 #define WLAN_PMKID_LEN 16 +#define WLAN_PMK_LEN_EAP_LEAP 16 +#define WLAN_PMK_LEN 32 +#define WLAN_PMK_LEN_SUITE_B_192 48 #define WLAN_OUI_WFA 0x506f9a #define WLAN_OUI_TYPE_WFA_P2P 9 diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index c6587c01d951..3cd18ac0697f 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -46,6 +46,9 @@ struct br_ip_list { #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) #define BR_MCAST_FLOOD BIT(11) +#define BR_MULTICAST_TO_UNICAST BIT(12) +#define BR_VLAN_TUNNEL BIT(13) +#define BR_BCAST_FLOOD BIT(14) #define BR_DEFAULT_AGEING_TIME (300 * HZ) @@ -59,6 +62,7 @@ int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list); bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto); bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); +bool br_multicast_enabled(const struct net_device *dev); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -75,6 +79,19 @@ static inline bool br_multicast_has_querier_adjacent(struct net_device *dev, { return false; } +static inline bool br_multicast_enabled(const struct net_device *dev) +{ + return false; +} +#endif + +#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) +bool br_vlan_enabled(const struct net_device *dev); +#else +static inline bool br_vlan_enabled(const struct net_device *dev) +{ + return false; +} #endif #endif diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h index 4316aa173dde..46df7e565d6f 100644 --- a/include/linux/if_frad.h +++ b/include/linux/if_frad.h @@ -66,8 +66,6 @@ struct dlci_local struct frad_local { - struct net_device_stats stats; - /* devices which this FRAD is slaved to */ struct net_device *master[CONFIG_DLCI_MAX]; short dlci[CONFIG_DLCI_MAX]; diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index a4ccc3122f93..c9ec1343d187 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -9,19 +9,6 @@ #include <net/netlink.h> #include <linux/u64_stats_sync.h> -#if IS_ENABLED(CONFIG_MACVTAP) -struct socket *macvtap_get_socket(struct file *); -#else -#include <linux/err.h> -#include <linux/errno.h> -struct file; -struct socket; -static inline struct socket *macvtap_get_socket(struct file *f) -{ - return ERR_PTR(-EINVAL); -} -#endif /* CONFIG_MACVTAP */ - struct macvlan_port; struct macvtap_queue; @@ -29,7 +16,7 @@ struct macvtap_queue; * Maximum times a macvtap device can be opened. This can be used to * configure the number of receive queue, e.g. for multiqueue virtio. */ -#define MAX_MACVTAP_QUEUES 256 +#define MAX_TAP_QUEUES 256 #define MACVLAN_MC_FILTER_BITS 8 #define MACVLAN_MC_FILTER_SZ (1 << MACVLAN_MC_FILTER_BITS) @@ -49,7 +36,7 @@ struct macvlan_dev { enum macvlan_mode mode; u16 flags; /* This array tracks active taps. */ - struct macvtap_queue __rcu *taps[MAX_MACVTAP_QUEUES]; + struct tap_queue __rcu *taps[MAX_TAP_QUEUES]; /* This list tracks all taps (both enabled and disabled) */ struct list_head queue_list; int numvtaps; diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h new file mode 100644 index 000000000000..4837157da0dc --- /dev/null +++ b/include/linux/if_tap.h @@ -0,0 +1,80 @@ +#ifndef _LINUX_IF_TAP_H_ +#define _LINUX_IF_TAP_H_ + +#if IS_ENABLED(CONFIG_TAP) +struct socket *tap_get_socket(struct file *); +struct skb_array *tap_get_skb_array(struct file *file); +#else +#include <linux/err.h> +#include <linux/errno.h> +struct file; +struct socket; +static inline struct socket *tap_get_socket(struct file *f) +{ + return ERR_PTR(-EINVAL); +} +static inline struct skb_array *tap_get_skb_array(struct file *f) +{ + return ERR_PTR(-EINVAL); +} +#endif /* CONFIG_TAP */ + +#include <net/sock.h> +#include <linux/skb_array.h> + +#define MAX_TAP_QUEUES 256 + +struct tap_queue; + +struct tap_dev { + struct net_device *dev; + u16 flags; + /* This array tracks active taps. */ + struct tap_queue __rcu *taps[MAX_TAP_QUEUES]; + /* This list tracks all taps (both enabled and disabled) */ + struct list_head queue_list; + int numvtaps; + int numqueues; + netdev_features_t tap_features; + int minor; + + void (*update_features)(struct tap_dev *tap, netdev_features_t features); + void (*count_tx_dropped)(struct tap_dev *tap); + void (*count_rx_dropped)(struct tap_dev *tap); +}; + +/* + * A tap queue is the central object of tap module, it connects + * an open character device to virtual interface. There can be + * multiple queues on one interface, which map back to queues + * implemented in hardware on the underlying device. + * + * tap_proto is used to allocate queues through the sock allocation + * mechanism. + * + */ + +struct tap_queue { + struct sock sk; + struct socket sock; + struct socket_wq wq; + int vnet_hdr_sz; + struct tap_dev __rcu *tap; + struct file *file; + unsigned int flags; + u16 queue_index; + bool enabled; + struct list_head next; + struct skb_array skb_array; +}; + +rx_handler_result_t tap_handle_frame(struct sk_buff **pskb); +void tap_del_queues(struct tap_dev *tap); +int tap_get_minor(dev_t major, struct tap_dev *tap); +void tap_free_minor(dev_t major, struct tap_dev *tap); +int tap_queue_resize(struct tap_dev *tap); +int tap_create_cdev(struct cdev *tap_cdev, + dev_t *tap_major, const char *device_name); +void tap_destroy_cdev(dev_t major, struct cdev *tap_cdev); + +#endif /*_LINUX_IF_TAP_H_*/ diff --git a/include/linux/if_team.h b/include/linux/if_team.h index c05216a8fbac..30294603526f 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -298,4 +298,6 @@ extern void team_mode_unregister(const struct team_mode *mode); #define TEAM_DEFAULT_NUM_TX_QUEUES 16 #define TEAM_DEFAULT_NUM_RX_QUEUES 16 +#define MODULE_ALIAS_TEAM_MODE(kind) MODULE_ALIAS("team-mode-" kind) + #endif /* _LINUX_IF_TEAM_H_ */ diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index ed6da2e6df90..bf9bdf42d577 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -19,6 +19,7 @@ #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); +struct skb_array *tun_get_skb_array(struct file *file); #else #include <linux/err.h> #include <linux/errno.h> @@ -28,5 +29,9 @@ static inline struct socket *tun_get_socket(struct file *f) { return ERR_PTR(-EINVAL); } +static inline struct skb_array *tun_get_skb_array(struct file *f) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_TUN */ #endif /* __IF_TUN_H */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 8d5fcd6284ce..5e6a2d4dc366 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -318,7 +318,7 @@ static inline int __vlan_insert_tag(struct sk_buff *skb, if (skb_cow_head(skb, VLAN_HLEN) < 0) return -ENOMEM; - veth = (struct vlan_ethhdr *)skb_push(skb, VLAN_HLEN); + veth = skb_push(skb, VLAN_HLEN); /* Move the mac addresses to the beginning of the new header. */ memmove(skb->data, skb->data + VLAN_HLEN, 2 * ETH_ALEN); @@ -614,14 +614,16 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, netdev_features_t features) { - if (skb_vlan_tagged_multi(skb)) - features = netdev_intersect_features(features, - NETIF_F_SG | - NETIF_F_HIGHDMA | - NETIF_F_FRAGLIST | - NETIF_F_HW_CSUM | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX); + if (skb_vlan_tagged_multi(skb)) { + /* In the case of multi-tagged packets, use a direct mask + * instead of using netdev_interesect_features(), to make + * sure that only devices supporting NETIF_F_HW_CSUM will + * have checksum offloading support. + */ + features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | + NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; + } return features; } diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 12f6fba6d21a..97caf1821de8 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -18,6 +18,7 @@ #include <linux/skbuff.h> #include <linux/timer.h> #include <linux/in.h> +#include <linux/refcount.h> #include <uapi/linux/igmp.h> static inline struct igmphdr *igmp_hdr(const struct sk_buff *skb) @@ -84,7 +85,7 @@ struct ip_mc_list { struct ip_mc_list __rcu *next_hash; struct timer_list timer; int users; - atomic_t refcnt; + refcount_t refcnt; spinlock_t lock; char tm_running; char reporter; diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index 70a5164f4728..48767c776119 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -11,139 +11,15 @@ #define _IIO_BUFFER_GENERIC_H_ #include <linux/sysfs.h> #include <linux/iio/iio.h> -#include <linux/kref.h> - -#ifdef CONFIG_IIO_BUFFER struct iio_buffer; -/** - * INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the buffer can not be - * configured. It has a fixed value which will be buffer specific. - */ -#define INDIO_BUFFER_FLAG_FIXED_WATERMARK BIT(0) - -/** - * struct iio_buffer_access_funcs - access functions for buffers. - * @store_to: actually store stuff to the buffer - * @read_first_n: try to get a specified number of bytes (must exist) - * @data_available: indicates how much data is available for reading from - * the buffer. - * @request_update: if a parameter change has been marked, update underlying - * storage. - * @set_bytes_per_datum:set number of bytes per datum - * @set_length: set number of datums in buffer - * @enable: called if the buffer is attached to a device and the - * device starts sampling. Calls are balanced with - * @disable. - * @disable: called if the buffer is attached to a device and the - * device stops sampling. Calles are balanced with @enable. - * @release: called when the last reference to the buffer is dropped, - * should free all resources allocated by the buffer. - * @modes: Supported operating modes by this buffer type - * @flags: A bitmask combination of INDIO_BUFFER_FLAG_* - * - * The purpose of this structure is to make the buffer element - * modular as event for a given driver, different usecases may require - * different buffer designs (space efficiency vs speed for example). - * - * It is worth noting that a given buffer implementation may only support a - * small proportion of these functions. The core code 'should' cope fine with - * any of them not existing. - **/ -struct iio_buffer_access_funcs { - int (*store_to)(struct iio_buffer *buffer, const void *data); - int (*read_first_n)(struct iio_buffer *buffer, - size_t n, - char __user *buf); - size_t (*data_available)(struct iio_buffer *buffer); - - int (*request_update)(struct iio_buffer *buffer); - - int (*set_bytes_per_datum)(struct iio_buffer *buffer, size_t bpd); - int (*set_length)(struct iio_buffer *buffer, int length); - - int (*enable)(struct iio_buffer *buffer, struct iio_dev *indio_dev); - int (*disable)(struct iio_buffer *buffer, struct iio_dev *indio_dev); - - void (*release)(struct iio_buffer *buffer); - - unsigned int modes; - unsigned int flags; -}; - -/** - * struct iio_buffer - general buffer structure - * @length: [DEVICE] number of datums in buffer - * @bytes_per_datum: [DEVICE] size of individual datum including timestamp - * @scan_el_attrs: [DRIVER] control of scan elements if that scan mode - * control method is used - * @scan_mask: [INTERN] bitmask used in masking scan mode elements - * @scan_timestamp: [INTERN] does the scan mode include a timestamp - * @access: [DRIVER] buffer access functions associated with the - * implementation. - * @scan_el_dev_attr_list:[INTERN] list of scan element related attributes. - * @buffer_group: [INTERN] attributes of the buffer group - * @scan_el_group: [DRIVER] attribute group for those attributes not - * created from the iio_chan_info array. - * @pollq: [INTERN] wait queue to allow for polling on the buffer. - * @stufftoread: [INTERN] flag to indicate new data. - * @attrs: [INTERN] standard attributes of the buffer - * @demux_list: [INTERN] list of operations required to demux the scan. - * @demux_bounce: [INTERN] buffer for doing gather from incoming scan. - * @buffer_list: [INTERN] entry in the devices list of current buffers. - * @ref: [INTERN] reference count of the buffer. - * @watermark: [INTERN] number of datums to wait for poll/read. - */ -struct iio_buffer { - int length; - int bytes_per_datum; - struct attribute_group *scan_el_attrs; - long *scan_mask; - bool scan_timestamp; - const struct iio_buffer_access_funcs *access; - struct list_head scan_el_dev_attr_list; - struct attribute_group buffer_group; - struct attribute_group scan_el_group; - wait_queue_head_t pollq; - bool stufftoread; - const struct attribute **attrs; - struct list_head demux_list; - void *demux_bounce; - struct list_head buffer_list; - struct kref ref; - unsigned int watermark; -}; - -/** - * iio_update_buffers() - add or remove buffer from active list - * @indio_dev: device to add buffer to - * @insert_buffer: buffer to insert - * @remove_buffer: buffer_to_remove - * - * Note this will tear down the all buffering and build it up again - */ -int iio_update_buffers(struct iio_dev *indio_dev, - struct iio_buffer *insert_buffer, - struct iio_buffer *remove_buffer); - -/** - * iio_buffer_init() - Initialize the buffer structure - * @buffer: buffer to be initialized - **/ -void iio_buffer_init(struct iio_buffer *buffer); +void iio_buffer_set_attrs(struct iio_buffer *buffer, + const struct attribute **attrs); -int iio_scan_mask_query(struct iio_dev *indio_dev, - struct iio_buffer *buffer, int bit); - -/** - * iio_push_to_buffers() - push to a registered buffer. - * @indio_dev: iio_dev structure for device. - * @data: Full scan. - */ int iio_push_to_buffers(struct iio_dev *indio_dev, const void *data); -/* +/** * iio_push_to_buffers_with_timestamp() - push data and timestamp to buffers * @indio_dev: iio_dev structure for device. * @data: sample data @@ -168,34 +44,10 @@ static inline int iio_push_to_buffers_with_timestamp(struct iio_dev *indio_dev, return iio_push_to_buffers(indio_dev, data); } -int iio_update_demux(struct iio_dev *indio_dev); - bool iio_validate_scan_mask_onehot(struct iio_dev *indio_dev, - const unsigned long *mask); - -struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer); -void iio_buffer_put(struct iio_buffer *buffer); - -/** - * iio_device_attach_buffer - Attach a buffer to a IIO device - * @indio_dev: The device the buffer should be attached to - * @buffer: The buffer to attach to the device - * - * This function attaches a buffer to a IIO device. The buffer stays attached to - * the device until the device is freed. The function should only be called at - * most once per device. - */ -static inline void iio_device_attach_buffer(struct iio_dev *indio_dev, - struct iio_buffer *buffer) -{ - indio_dev->buffer = iio_buffer_get(buffer); -} - -#else /* CONFIG_IIO_BUFFER */ - -static inline void iio_buffer_get(struct iio_buffer *buffer) {} -static inline void iio_buffer_put(struct iio_buffer *buffer) {} + const unsigned long *mask); -#endif /* CONFIG_IIO_BUFFER */ +void iio_device_attach_buffer(struct iio_dev *indio_dev, + struct iio_buffer *buffer); #endif /* _IIO_BUFFER_GENERIC_H_ */ diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h new file mode 100644 index 000000000000..8daba198fafa --- /dev/null +++ b/include/linux/iio/buffer_impl.h @@ -0,0 +1,162 @@ +#ifndef _IIO_BUFFER_GENERIC_IMPL_H_ +#define _IIO_BUFFER_GENERIC_IMPL_H_ +#include <linux/sysfs.h> +#include <linux/kref.h> + +#ifdef CONFIG_IIO_BUFFER + +struct iio_dev; +struct iio_buffer; + +/** + * INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the buffer can not be + * configured. It has a fixed value which will be buffer specific. + */ +#define INDIO_BUFFER_FLAG_FIXED_WATERMARK BIT(0) + +/** + * struct iio_buffer_access_funcs - access functions for buffers. + * @store_to: actually store stuff to the buffer + * @read_first_n: try to get a specified number of bytes (must exist) + * @data_available: indicates how much data is available for reading from + * the buffer. + * @request_update: if a parameter change has been marked, update underlying + * storage. + * @set_bytes_per_datum:set number of bytes per datum + * @set_length: set number of datums in buffer + * @enable: called if the buffer is attached to a device and the + * device starts sampling. Calls are balanced with + * @disable. + * @disable: called if the buffer is attached to a device and the + * device stops sampling. Calles are balanced with @enable. + * @release: called when the last reference to the buffer is dropped, + * should free all resources allocated by the buffer. + * @modes: Supported operating modes by this buffer type + * @flags: A bitmask combination of INDIO_BUFFER_FLAG_* + * + * The purpose of this structure is to make the buffer element + * modular as event for a given driver, different usecases may require + * different buffer designs (space efficiency vs speed for example). + * + * It is worth noting that a given buffer implementation may only support a + * small proportion of these functions. The core code 'should' cope fine with + * any of them not existing. + **/ +struct iio_buffer_access_funcs { + int (*store_to)(struct iio_buffer *buffer, const void *data); + int (*read_first_n)(struct iio_buffer *buffer, + size_t n, + char __user *buf); + size_t (*data_available)(struct iio_buffer *buffer); + + int (*request_update)(struct iio_buffer *buffer); + + int (*set_bytes_per_datum)(struct iio_buffer *buffer, size_t bpd); + int (*set_length)(struct iio_buffer *buffer, int length); + + int (*enable)(struct iio_buffer *buffer, struct iio_dev *indio_dev); + int (*disable)(struct iio_buffer *buffer, struct iio_dev *indio_dev); + + void (*release)(struct iio_buffer *buffer); + + unsigned int modes; + unsigned int flags; +}; + +/** + * struct iio_buffer - general buffer structure + * + * Note that the internals of this structure should only be of interest to + * those writing new buffer implementations. + */ +struct iio_buffer { + /** @length: Number of datums in buffer. */ + int length; + + /** @bytes_per_datum: Size of individual datum including timestamp. */ + int bytes_per_datum; + + /** + * @access: Buffer access functions associated with the + * implementation. + */ + const struct iio_buffer_access_funcs *access; + + /** @scan_mask: Bitmask used in masking scan mode elements. */ + long *scan_mask; + + /** @demux_list: List of operations required to demux the scan. */ + struct list_head demux_list; + + /** @pollq: Wait queue to allow for polling on the buffer. */ + wait_queue_head_t pollq; + + /** @watermark: Number of datums to wait for poll/read. */ + unsigned int watermark; + + /* private: */ + /* + * @scan_el_attrs: Control of scan elements if that scan mode + * control method is used. + */ + struct attribute_group *scan_el_attrs; + + /* @scan_timestamp: Does the scan mode include a timestamp. */ + bool scan_timestamp; + + /* @scan_el_dev_attr_list: List of scan element related attributes. */ + struct list_head scan_el_dev_attr_list; + + /* @buffer_group: Attributes of the buffer group. */ + struct attribute_group buffer_group; + + /* + * @scan_el_group: Attribute group for those attributes not + * created from the iio_chan_info array. + */ + struct attribute_group scan_el_group; + + /* @stufftoread: Flag to indicate new data. */ + bool stufftoread; + + /* @attrs: Standard attributes of the buffer. */ + const struct attribute **attrs; + + /* @demux_bounce: Buffer for doing gather from incoming scan. */ + void *demux_bounce; + + /* @buffer_list: Entry in the devices list of current buffers. */ + struct list_head buffer_list; + + /* @ref: Reference count of the buffer. */ + struct kref ref; +}; + +/** + * iio_update_buffers() - add or remove buffer from active list + * @indio_dev: device to add buffer to + * @insert_buffer: buffer to insert + * @remove_buffer: buffer_to_remove + * + * Note this will tear down the all buffering and build it up again + */ +int iio_update_buffers(struct iio_dev *indio_dev, + struct iio_buffer *insert_buffer, + struct iio_buffer *remove_buffer); + +/** + * iio_buffer_init() - Initialize the buffer structure + * @buffer: buffer to be initialized + **/ +void iio_buffer_init(struct iio_buffer *buffer); + +struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer); +void iio_buffer_put(struct iio_buffer *buffer); + +#else /* CONFIG_IIO_BUFFER */ + +static inline void iio_buffer_get(struct iio_buffer *buffer) {} +static inline void iio_buffer_put(struct iio_buffer *buffer) {} + +#endif /* CONFIG_IIO_BUFFER */ +#endif /* _IIO_BUFFER_GENERIC_IMPL_H_ */ diff --git a/include/linux/iio/common/st_sensors_i2c.h b/include/linux/iio/common/st_sensors_i2c.h index 1796af093368..254de3c7dde8 100644 --- a/include/linux/iio/common/st_sensors_i2c.h +++ b/include/linux/iio/common/st_sensors_i2c.h @@ -28,4 +28,13 @@ static inline void st_sensors_of_i2c_probe(struct i2c_client *client, } #endif +#ifdef CONFIG_ACPI +int st_sensors_match_acpi_device(struct device *dev); +#else +static inline int st_sensors_match_acpi_device(struct device *dev) +{ + return -ENODEV; +} +#endif + #endif /* ST_SENSORS_I2C_H */ diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index 47eeec3218b5..5e347a9805fd 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -312,4 +312,41 @@ int iio_read_channel_scale(struct iio_channel *chan, int *val, int iio_convert_raw_to_processed(struct iio_channel *chan, int raw, int *processed, unsigned int scale); +/** + * iio_get_channel_ext_info_count() - get number of ext_info attributes + * connected to the channel. + * @chan: The channel being queried + * + * Returns the number of ext_info attributes + */ +unsigned int iio_get_channel_ext_info_count(struct iio_channel *chan); + +/** + * iio_read_channel_ext_info() - read ext_info attribute from a given channel + * @chan: The channel being queried. + * @attr: The ext_info attribute to read. + * @buf: Where to store the attribute value. Assumed to hold + * at least PAGE_SIZE bytes. + * + * Returns the number of bytes written to buf (perhaps w/o zero termination; + * it need not even be a string), or an error code. + */ +ssize_t iio_read_channel_ext_info(struct iio_channel *chan, + const char *attr, char *buf); + +/** + * iio_write_channel_ext_info() - write ext_info attribute from a given channel + * @chan: The channel being queried. + * @attr: The ext_info attribute to read. + * @buf: The new attribute value. Strings needs to be zero- + * terminated, but the terminator should not be included + * in the below len. + * @len: The size of the new attribute value. + * + * Returns the number of accepted bytes, which should be the same as len. + * An error code can also be returned. + */ +ssize_t iio_write_channel_ext_info(struct iio_channel *chan, const char *attr, + const char *buf, size_t len); + #endif diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 3f5ea2e9a39e..d68bec297a45 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -352,10 +352,16 @@ unsigned int iio_get_time_res(const struct iio_dev *indio_dev); #define INDIO_BUFFER_SOFTWARE 0x04 #define INDIO_BUFFER_HARDWARE 0x08 #define INDIO_EVENT_TRIGGERED 0x10 +#define INDIO_HARDWARE_TRIGGERED 0x20 #define INDIO_ALL_BUFFER_MODES \ (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE | INDIO_BUFFER_SOFTWARE) +#define INDIO_ALL_TRIGGERED_MODES \ + (INDIO_BUFFER_TRIGGERED \ + | INDIO_EVENT_TRIGGERED \ + | INDIO_HARDWARE_TRIGGERED) + #define INDIO_MAX_RAW_ELEMENTS 4 struct iio_trigger; /* forward declaration */ diff --git a/include/linux/iio/kfifo_buf.h b/include/linux/iio/kfifo_buf.h index 1683bc710d14..027cfa9c3703 100644 --- a/include/linux/iio/kfifo_buf.h +++ b/include/linux/iio/kfifo_buf.h @@ -1,9 +1,8 @@ #ifndef __LINUX_IIO_KFIFO_BUF_H__ #define __LINUX_IIO_KFIFO_BUF_H__ -#include <linux/kfifo.h> -#include <linux/iio/iio.h> -#include <linux/iio/buffer.h> +struct iio_buffer; +struct device; struct iio_buffer *iio_kfifo_allocate(void); void iio_kfifo_free(struct iio_buffer *r); diff --git a/include/linux/iio/sw_device.h b/include/linux/iio/sw_device.h index 23ca41515527..fa7931933067 100644 --- a/include/linux/iio/sw_device.h +++ b/include/linux/iio/sw_device.h @@ -62,7 +62,7 @@ void iio_swd_group_init_type_name(struct iio_sw_device *d, const char *name, struct config_item_type *type) { -#ifdef CONFIG_CONFIGFS_FS +#if IS_ENABLED(CONFIG_CONFIGFS_FS) config_group_init_type_name(&d->group, name, type); #endif } diff --git a/include/linux/iio/timer/stm32-timer-trigger.h b/include/linux/iio/timer/stm32-timer-trigger.h new file mode 100644 index 000000000000..fa7d786ed99e --- /dev/null +++ b/include/linux/iio/timer/stm32-timer-trigger.h @@ -0,0 +1,64 @@ +/* + * Copyright (C) STMicroelectronics 2016 + * + * Author: Benjamin Gaignard <benjamin.gaignard@st.com> + * + * License terms: GNU General Public License (GPL), version 2 + */ + +#ifndef _STM32_TIMER_TRIGGER_H_ +#define _STM32_TIMER_TRIGGER_H_ + +#define TIM1_TRGO "tim1_trgo" +#define TIM1_TRGO2 "tim1_trgo2" +#define TIM1_CH1 "tim1_ch1" +#define TIM1_CH2 "tim1_ch2" +#define TIM1_CH3 "tim1_ch3" +#define TIM1_CH4 "tim1_ch4" + +#define TIM2_TRGO "tim2_trgo" +#define TIM2_CH1 "tim2_ch1" +#define TIM2_CH2 "tim2_ch2" +#define TIM2_CH3 "tim2_ch3" +#define TIM2_CH4 "tim2_ch4" + +#define TIM3_TRGO "tim3_trgo" +#define TIM3_CH1 "tim3_ch1" +#define TIM3_CH2 "tim3_ch2" +#define TIM3_CH3 "tim3_ch3" +#define TIM3_CH4 "tim3_ch4" + +#define TIM4_TRGO "tim4_trgo" +#define TIM4_CH1 "tim4_ch1" +#define TIM4_CH2 "tim4_ch2" +#define TIM4_CH3 "tim4_ch3" +#define TIM4_CH4 "tim4_ch4" + +#define TIM5_TRGO "tim5_trgo" +#define TIM5_CH1 "tim5_ch1" +#define TIM5_CH2 "tim5_ch2" +#define TIM5_CH3 "tim5_ch3" +#define TIM5_CH4 "tim5_ch4" + +#define TIM6_TRGO "tim6_trgo" + +#define TIM7_TRGO "tim7_trgo" + +#define TIM8_TRGO "tim8_trgo" +#define TIM8_TRGO2 "tim8_trgo2" +#define TIM8_CH1 "tim8_ch1" +#define TIM8_CH2 "tim8_ch2" +#define TIM8_CH3 "tim8_ch3" +#define TIM8_CH4 "tim8_ch4" + +#define TIM9_TRGO "tim9_trgo" +#define TIM9_CH1 "tim9_ch1" +#define TIM9_CH2 "tim9_ch2" + +#define TIM12_TRGO "tim12_trgo" +#define TIM12_CH1 "tim12_ch1" +#define TIM12_CH2 "tim12_ch2" + +bool is_stm32_timer_trigger(struct iio_trigger *trig); + +#endif diff --git a/include/linux/ima.h b/include/linux/ima.h index 7f6952f8d6aa..0e4647e0eb60 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -75,11 +75,17 @@ static inline void ima_add_kexec_buffer(struct kimage *image) #endif #ifdef CONFIG_IMA_APPRAISE +extern bool is_ima_appraise_enabled(void); extern void ima_inode_post_setattr(struct dentry *dentry); extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len); extern int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name); #else +static inline bool is_ima_appraise_enabled(void) +{ + return 0; +} + static inline void ima_inode_post_setattr(struct dentry *dentry) { return; diff --git a/include/linux/imx-media.h b/include/linux/imx-media.h new file mode 100644 index 000000000000..77221ecad6fc --- /dev/null +++ b/include/linux/imx-media.h @@ -0,0 +1,29 @@ +/* + * Copyright (c) 2014-2017 Mentor Graphics Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the + * License, or (at your option) any later version + */ + +#ifndef __LINUX_IMX_MEDIA_H__ +#define __LINUX_IMX_MEDIA_H__ + +/* + * events from the subdevs + */ +#define V4L2_EVENT_IMX_CLASS V4L2_EVENT_PRIVATE_START +#define V4L2_EVENT_IMX_FRAME_INTERVAL_ERROR (V4L2_EVENT_IMX_CLASS + 1) + +enum imx_ctrl_id { + V4L2_CID_IMX_FIM_ENABLE = (V4L2_CID_USER_IMX_BASE + 0), + V4L2_CID_IMX_FIM_NUM, + V4L2_CID_IMX_FIM_TOLERANCE_MIN, + V4L2_CID_IMX_FIM_TOLERANCE_MAX, + V4L2_CID_IMX_FIM_NUM_SKIP, + V4L2_CID_IMX_FIM_ICAP_EDGE, + V4L2_CID_IMX_FIM_ICAP_CHANNEL, +}; + +#endif diff --git a/include/linux/inet.h b/include/linux/inet.h index 4cca05c9678e..636ebe87e6f8 100644 --- a/include/linux/inet.h +++ b/include/linux/inet.h @@ -43,6 +43,8 @@ #define _LINUX_INET_H #include <linux/types.h> +#include <net/net_namespace.h> +#include <linux/socket.h> /* * These mimic similar macros defined in user-space for inet_ntop(3). @@ -54,4 +56,8 @@ extern __be32 in_aton(const char *str); extern int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end); extern int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end); + +extern int inet_pton_with_scope(struct net *net, unsigned short af, + const char *src, const char *port, struct sockaddr_storage *addr); + #endif /* _LINUX_INET_H */ diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index ee971f335a8b..fb3f809e34e4 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -11,6 +11,7 @@ #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> +#include <linux/refcount.h> struct ipv4_devconf { void *sysctl; @@ -22,7 +23,7 @@ struct ipv4_devconf { struct in_device { struct net_device *dev; - atomic_t refcnt; + refcount_t refcnt; int dead; struct in_ifaddr *ifa_list; /* IP ifaddr chain */ @@ -150,11 +151,18 @@ struct in_ifaddr { unsigned long ifa_tstamp; /* updated timestamp */ }; +struct in_validator_info { + __be32 ivi_addr; + struct in_device *ivi_dev; +}; + int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); +int register_inetaddr_validator_notifier(struct notifier_block *nb); +int unregister_inetaddr_validator_notifier(struct notifier_block *nb); -void inet_netconf_notify_devconf(struct net *net, int type, int ifindex, - struct ipv4_devconf *devconf); +void inet_netconf_notify_devconf(struct net *net, int event, int type, + int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) @@ -212,7 +220,7 @@ static inline struct in_device *in_dev_get(const struct net_device *dev) rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) - atomic_inc(&in_dev->refcnt); + refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } @@ -233,12 +241,12 @@ void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { - if (atomic_dec_and_test(&idev->refcnt)) + if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } -#define __in_dev_put(idev) atomic_dec(&(idev)->refcnt) -#define in_dev_hold(idev) atomic_inc(&(idev)->refcnt) +#define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) +#define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ diff --git a/include/linux/init.h b/include/linux/init.h index 885c3e6d0f9d..94769d687cf0 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -39,7 +39,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold notrace __latent_entropy +#define __init __section(.init.text) __cold __inittrace __latent_entropy #define __initdata __section(.init.data) #define __initconst __section(.init.rodata) #define __exitdata __section(.exit.data) @@ -68,8 +68,10 @@ #ifdef MODULE #define __exitused +#define __inittrace notrace #else #define __exitused __used +#define __inittrace #endif #define __exit __section(.exit.text) __exitused __cold notrace @@ -126,10 +128,10 @@ void prepare_namespace(void); void __init load_default_modules(void); int __init init_rootfs(void); -#if defined(CONFIG_DEBUG_RODATA) || defined(CONFIG_DEBUG_SET_MODULE_RONX) +#if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX) extern bool rodata_enabled; #endif -#ifdef CONFIG_DEBUG_RODATA +#ifdef CONFIG_STRICT_KERNEL_RWX void mark_rodata_ro(void); #endif diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 325f649d77ff..a2f6707e9fc0 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -12,8 +12,11 @@ #include <linux/securebits.h> #include <linux/seqlock.h> #include <linux/rbtree.h> +#include <linux/sched/autogroup.h> #include <net/net_namespace.h> #include <linux/sched/rt.h> +#include <linux/livepatch.h> +#include <linux/mm_types.h> #include <asm/thread_info.h> @@ -42,6 +45,27 @@ extern struct fs_struct init_fs; #define INIT_PREV_CPUTIME(x) #endif +#ifdef CONFIG_POSIX_TIMERS +#define INIT_POSIX_TIMERS(s) \ + .posix_timers = LIST_HEAD_INIT(s.posix_timers), +#define INIT_CPU_TIMERS(s) \ + .cpu_timers = { \ + LIST_HEAD_INIT(s.cpu_timers[0]), \ + LIST_HEAD_INIT(s.cpu_timers[1]), \ + LIST_HEAD_INIT(s.cpu_timers[2]), \ + }, +#define INIT_CPUTIMER(s) \ + .cputimer = { \ + .cputime_atomic = INIT_CPUTIME_ATOMIC, \ + .running = false, \ + .checking_timer = false, \ + }, +#else +#define INIT_POSIX_TIMERS(s) +#define INIT_CPU_TIMERS(s) +#define INIT_CPUTIMER(s) +#endif + #define INIT_SIGNALS(sig) { \ .nr_threads = 1, \ .thread_head = LIST_HEAD_INIT(init_task.thread_node), \ @@ -49,14 +73,10 @@ extern struct fs_struct init_fs; .shared_pending = { \ .list = LIST_HEAD_INIT(sig.shared_pending.list), \ .signal = {{0}}}, \ - .posix_timers = LIST_HEAD_INIT(sig.posix_timers), \ - .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ + INIT_POSIX_TIMERS(sig) \ + INIT_CPU_TIMERS(sig) \ .rlim = INIT_RLIMITS, \ - .cputimer = { \ - .cputime_atomic = INIT_CPUTIME_ATOMIC, \ - .running = false, \ - .checking_timer = false, \ - }, \ + INIT_CPUTIMER(sig) \ INIT_PREV_CPUTIME(sig) \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ @@ -132,8 +152,6 @@ extern struct group_info init_groups; extern struct cred init_cred; -extern struct task_group root_task_group; - #ifdef CONFIG_CGROUP_SCHED # define INIT_CGROUP_SCHED(tsk) \ .sched_task_group = &root_task_group, @@ -152,9 +170,9 @@ extern struct task_group root_task_group; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN # define INIT_VTIME(tsk) \ - .vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount), \ - .vtime_snap = 0, \ - .vtime_snap_whence = VTIME_SYS, + .vtime.seqcount = SEQCNT_ZERO(tsk.vtime.seqcount), \ + .vtime.starttime = 0, \ + .vtime.state = VTIME_SYS, #else # define INIT_VTIME(tsk) #endif @@ -164,6 +182,7 @@ extern struct task_group root_task_group; #ifdef CONFIG_RT_MUTEXES # define INIT_RT_MUTEXES(tsk) \ .pi_waiters = RB_ROOT, \ + .pi_top_task = NULL, \ .pi_waiters_leftmost = NULL, #else # define INIT_RT_MUTEXES(tsk) @@ -185,6 +204,13 @@ extern struct task_group root_task_group; # define INIT_KASAN(tsk) #endif +#ifdef CONFIG_LIVEPATCH +# define INIT_LIVEPATCH(tsk) \ + .patch_state = KLP_UNDEFINED, +#else +# define INIT_LIVEPATCH(tsk) +#endif + #ifdef CONFIG_THREAD_INFO_IN_TASK # define INIT_TASK_TI(tsk) \ .thread_info = INIT_THREAD_INFO(tsk), \ @@ -193,6 +219,12 @@ extern struct task_group root_task_group; # define INIT_TASK_TI(tsk) #endif +#ifdef CONFIG_SECURITY +#define INIT_TASK_SECURITY .security = NULL, +#else +#define INIT_TASK_SECURITY +#endif + /* * INIT_TASK is used to set up the first task table, touch at * your own risk!. Base=0, limit=0x1fffff (=2MB) @@ -247,7 +279,7 @@ extern struct task_group root_task_group; .blocked = {{0}}, \ .alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \ .journal_info = NULL, \ - .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ + INIT_CPU_TIMERS(tsk) \ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ .timer_slack_ns = 50000, /* 50 usec default slack */ \ .pids = { \ @@ -271,16 +303,11 @@ extern struct task_group root_task_group; INIT_VTIME(tsk) \ INIT_NUMA_BALANCING(tsk) \ INIT_KASAN(tsk) \ + INIT_LIVEPATCH(tsk) \ + INIT_TASK_SECURITY \ } -#define INIT_CPU_TIMERS(cpu_timers) \ -{ \ - LIST_HEAD_INIT(cpu_timers[0]), \ - LIST_HEAD_INIT(cpu_timers[1]), \ - LIST_HEAD_INIT(cpu_timers[2]), \ -} - /* Attach to the init_task data structure for proper alignment */ #define __init_task_data __attribute__((__section__(".data..init_task"))) diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 55289d261b4f..bc67b767f9ce 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -10,6 +10,9 @@ extern int rd_prompt; /* starting block # of image */ extern int rd_image_start; +/* size of a single RAM disk */ +extern unsigned long rd_size; + /* 1 if it is not an error if initrd_start < memory_start */ extern int initrd_below_start_ok; diff --git a/include/linux/input/eeti_ts.h b/include/linux/input/eeti_ts.h deleted file mode 100644 index 16625d799b6f..000000000000 --- a/include/linux/input/eeti_ts.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef LINUX_INPUT_EETI_TS_H -#define LINUX_INPUT_EETI_TS_H - -struct eeti_ts_platform_data { - int irq_gpio; - unsigned int irq_active_high; -}; - -#endif /* LINUX_INPUT_EETI_TS_H */ - diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index 27e06acc509a..6174733a57eb 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -49,6 +49,8 @@ struct matrix_keymap_data { * @wakeup: controls whether the device should be set up as wakeup * source * @no_autorepeat: disable key autorepeat + * @drive_inactive_cols: drive inactive columns during scan, rather than + * making them inputs. * * This structure represents platform-specific data that use used by * matrix_keypad driver to perform proper initialization. @@ -73,6 +75,7 @@ struct matrix_keypad_platform_data { bool active_low; bool wakeup; bool no_autorepeat; + bool drive_inactive_cols; }; int matrix_keypad_build_keymap(const struct matrix_keymap_data *keymap_data, @@ -80,24 +83,9 @@ int matrix_keypad_build_keymap(const struct matrix_keymap_data *keymap_data, unsigned int rows, unsigned int cols, unsigned short *keymap, struct input_dev *input_dev); +int matrix_keypad_parse_properties(struct device *dev, + unsigned int *rows, unsigned int *cols); -#ifdef CONFIG_OF -/** - * matrix_keypad_parse_of_params() - Read parameters from matrix-keypad node - * - * @dev: Device containing of_node - * @rows: Returns number of matrix rows - * @cols: Returns number of matrix columns - * @return 0 if OK, <0 on error - */ -int matrix_keypad_parse_of_params(struct device *dev, - unsigned int *rows, unsigned int *cols); -#else -static inline int matrix_keypad_parse_of_params(struct device *dev, - unsigned int *rows, unsigned int *cols) -{ - return -ENOSYS; -} -#endif /* CONFIG_OF */ +#define matrix_keypad_parse_of_params matrix_keypad_parse_properties #endif /* _MATRIX_KEYPAD_H */ diff --git a/include/linux/input/sparse-keymap.h b/include/linux/input/sparse-keymap.h index 52db62064c6e..c7346e33d958 100644 --- a/include/linux/input/sparse-keymap.h +++ b/include/linux/input/sparse-keymap.h @@ -51,7 +51,6 @@ struct key_entry *sparse_keymap_entry_from_keycode(struct input_dev *dev, int sparse_keymap_setup(struct input_dev *dev, const struct key_entry *keymap, int (*setup)(struct input_dev *, struct key_entry *)); -void sparse_keymap_free(struct input_dev *dev); void sparse_keymap_report_entry(struct input_dev *dev, const struct key_entry *ke, unsigned int value, bool autorelease); diff --git a/include/linux/input/tca8418_keypad.h b/include/linux/input/tca8418_keypad.h deleted file mode 100644 index e71a85dc2cbd..000000000000 --- a/include/linux/input/tca8418_keypad.h +++ /dev/null @@ -1,44 +0,0 @@ -/* - * TCA8418 keypad platform support - * - * Copyright (C) 2011 Fuel7, Inc. All rights reserved. - * - * Author: Kyle Manna <kyle.manna@fuel7.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License v2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * - * If you can't comply with GPLv2, alternative licensing terms may be - * arranged. Please contact Fuel7, Inc. (http://fuel7.com/) for proprietary - * alternative licensing inquiries. - */ - -#ifndef _TCA8418_KEYPAD_H -#define _TCA8418_KEYPAD_H - -#include <linux/types.h> -#include <linux/input/matrix_keypad.h> - -#define TCA8418_I2C_ADDR 0x34 -#define TCA8418_NAME "tca8418_keypad" - -struct tca8418_keypad_platform_data { - const struct matrix_keymap_data *keymap_data; - unsigned rows; - unsigned cols; - bool rep; - bool irq_is_gpio; -}; - -#endif diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index d49e26c6cdc7..485a5b48f038 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -29,6 +29,9 @@ #include <linux/dma_remapping.h> #include <linux/mmu_notifier.h> #include <linux/list.h> +#include <linux/iommu.h> +#include <linux/io-64-nonatomic-lo-hi.h> + #include <asm/cacheflush.h> #include <asm/iommu.h> @@ -71,24 +74,8 @@ #define OFFSET_STRIDE (9) -#ifdef CONFIG_64BIT #define dmar_readq(a) readq(a) #define dmar_writeq(a,v) writeq(v,a) -#else -static inline u64 dmar_readq(void __iomem *addr) -{ - u32 lo, hi; - lo = readl(addr); - hi = readl(addr + 4); - return (((u64) hi) << 32) + lo; -} - -static inline void dmar_writeq(void __iomem *addr, u64 val) -{ - writel((u32)val, addr); - writel((u32)(val >> 32), addr + 4); -} -#endif #define DMAR_VER_MAJOR(v) (((v) & 0xf0) >> 4) #define DMAR_VER_MINOR(v) ((v) & 0x0f) @@ -153,8 +140,8 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60) #define DMA_TLB_DSI_FLUSH (((u64)2) << 60) #define DMA_TLB_PSI_FLUSH (((u64)3) << 60) -#define DMA_TLB_IIRG(type) ((type >> 60) & 7) -#define DMA_TLB_IAIG(val) (((val) >> 57) & 7) +#define DMA_TLB_IIRG(type) ((type >> 60) & 3) +#define DMA_TLB_IAIG(val) (((val) >> 57) & 3) #define DMA_TLB_READ_DRAIN (((u64)1) << 49) #define DMA_TLB_WRITE_DRAIN (((u64)1) << 48) #define DMA_TLB_DID(id) (((u64)((id) & 0xffff)) << 32) @@ -164,9 +151,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) /* INVALID_DESC */ #define DMA_CCMD_INVL_GRANU_OFFSET 61 -#define DMA_ID_TLB_GLOBAL_FLUSH (((u64)1) << 3) -#define DMA_ID_TLB_DSI_FLUSH (((u64)2) << 3) -#define DMA_ID_TLB_PSI_FLUSH (((u64)3) << 3) +#define DMA_ID_TLB_GLOBAL_FLUSH (((u64)1) << 4) +#define DMA_ID_TLB_DSI_FLUSH (((u64)2) << 4) +#define DMA_ID_TLB_PSI_FLUSH (((u64)3) << 4) #define DMA_ID_TLB_READ_DRAIN (((u64)1) << 7) #define DMA_ID_TLB_WRITE_DRAIN (((u64)1) << 6) #define DMA_ID_TLB_DID(id) (((u64)((id & 0xffff) << 16))) @@ -316,8 +303,8 @@ enum { #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) #define QI_DEV_EIOTLB_GLOB(g) ((u64)g) #define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) -#define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32) -#define QI_DEV_EIOTLB_QDEP(qd) (((qd) & 0x1f) << 16) +#define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) +#define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) #define QI_DEV_EIOTLB_MAX_INVS 32 #define QI_PGRP_IDX(idx) (((u64)(idx)) << 55) @@ -439,7 +426,7 @@ struct intel_iommu { struct irq_domain *ir_domain; struct irq_domain *ir_msi_domain; #endif - struct device *iommu_dev; /* IOMMU-sysfs device */ + struct iommu_device iommu; /* IOMMU core code handle */ int node; u32 flags; /* Software defined flags */ }; diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 3c25794042f9..99bc5b3ae26e 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -102,6 +102,21 @@ extern int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, */ extern int intel_svm_unbind_mm(struct device *dev, int pasid); +/** + * intel_svm_is_pasid_valid() - check if pasid is valid + * @dev: Device for which PASID was allocated + * @pasid: PASID value to be checked + * + * This function checks if the specified pasid is still valid. A + * valid pasid means the backing mm is still having a valid user. + * For kernel callers init_mm is always valid. for other mm, if mm->mm_users + * is non-zero, it is valid. + * + * returns -EINVAL if invalid pasid, 0 if pasid ref count is invalid + * 1 if pasid is valid. + */ +extern int intel_svm_is_pasid_valid(struct device *dev, int pasid); + #else /* CONFIG_INTEL_IOMMU_SVM */ static inline int intel_svm_bind_mm(struct device *dev, int *pasid, @@ -114,6 +129,11 @@ static inline int intel_svm_unbind_mm(struct device *dev, int pasid) { BUG(); } + +static int intel_svm_is_pasid_valid(struct device *dev, int pasid) +{ + return -EINVAL; +} #endif /* CONFIG_INTEL_IOMMU_SVM */ #define intel_svm_available(dev) (!intel_svm_bind_mm((dev), NULL, 0, NULL)) diff --git a/include/linux/intel_pmic_gpio.h b/include/linux/intel_pmic_gpio.h deleted file mode 100644 index 920109a29191..000000000000 --- a/include/linux/intel_pmic_gpio.h +++ /dev/null @@ -1,15 +0,0 @@ -#ifndef LINUX_INTEL_PMIC_H -#define LINUX_INTEL_PMIC_H - -struct intel_pmic_gpio_platform_data { - /* the first IRQ of the chip */ - unsigned irq_base; - /* number assigned to the first GPIO */ - unsigned gpio_base; - /* sram address for gpiointr register, the langwell chip will map - * the PMIC spi GPIO expander's GPIOINTR register in sram. - */ - unsigned gpiointr; -}; - -#endif diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 53144e78a369..a2fddddb0d60 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -152,10 +152,19 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id); extern int __must_check +__request_percpu_irq(unsigned int irq, irq_handler_t handler, + unsigned long flags, const char *devname, + void __percpu *percpu_dev_id); + +static inline int __must_check request_percpu_irq(unsigned int irq, irq_handler_t handler, - const char *devname, void __percpu *percpu_dev_id); + const char *devname, void __percpu *percpu_dev_id) +{ + return __request_percpu_irq(irq, handler, 0, + devname, percpu_dev_id); +} -extern void free_irq(unsigned int, void *); +extern const void *free_irq(unsigned int, void *); extern void free_percpu_irq(unsigned int, void __percpu *); struct device; @@ -291,7 +300,7 @@ extern int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); struct cpumask *irq_create_affinity_masks(int nvec, const struct irq_affinity *affd); -int irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd); +int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd); #else /* CONFIG_SMP */ @@ -331,7 +340,7 @@ irq_create_affinity_masks(int nvec, const struct irq_affinity *affd) } static inline int -irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd) +irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd) { return maxvec; } @@ -703,6 +712,12 @@ static inline void init_irq_proc(void) } #endif +#ifdef CONFIG_IRQ_TIMINGS +void irq_timings_enable(void); +void irq_timings_disable(void); +u64 irq_timings_next_event(u64 now); +#endif + struct seq_file; int show_interrupts(struct seq_file *p, void *v); int arch_show_interrupts(struct seq_file *p, int prec); diff --git a/include/linux/io.h b/include/linux/io.h index 82ef36eac8a1..2195d9ea4aaa 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -90,6 +90,27 @@ void devm_memunmap(struct device *dev, void *addr); void *__devm_memremap_pages(struct device *dev, struct resource *res); +#ifdef CONFIG_PCI +/* + * The PCI specifications (Rev 3.0, 3.2.5 "Transaction Ordering and + * Posting") mandate non-posted configuration transactions. There is + * no ioremap API in the kernel that can guarantee non-posted write + * semantics across arches so provide a default implementation for + * mapping PCI config space that defaults to ioremap_nocache(); arches + * should override it if they have memory mapping implementations that + * guarantee non-posted writes semantics to make the memory mapping + * compliant with the PCI specification. + */ +#ifndef pci_remap_cfgspace +#define pci_remap_cfgspace pci_remap_cfgspace +static inline void __iomem *pci_remap_cfgspace(phys_addr_t offset, + size_t size) +{ + return ioremap_nocache(offset, size); +} +#endif +#endif + /* * Some systems do not have legacy ISA devices. * /dev/port is not a valid interface on these systems. diff --git a/include/linux/iomap.h b/include/linux/iomap.h index a4c94b86401e..f64dc6ce5161 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -41,6 +41,7 @@ struct iomap { u16 type; /* type of mapping */ u16 flags; /* flags for mapping */ struct block_device *bdev; /* block device for I/O */ + struct dax_device *dax_dev; /* dax_dev for dax operations */ }; /* @@ -51,6 +52,7 @@ struct iomap { #define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */ #define IOMAP_FAULT (1 << 3) /* mapping for page fault */ #define IOMAP_DIRECT (1 << 4) /* direct I/O */ +#define IOMAP_NOWAIT (1 << 5) /* Don't wait for writeback */ struct iomap_ops { /* @@ -72,17 +74,20 @@ struct iomap_ops { }; ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, - struct iomap_ops *ops); + const struct iomap_ops *ops); int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, - struct iomap_ops *ops); + const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, - bool *did_zero, struct iomap_ops *ops); + bool *did_zero, const struct iomap_ops *ops); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, - struct iomap_ops *ops); -int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, - struct iomap_ops *ops); + const struct iomap_ops *ops); +int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - loff_t start, loff_t len, struct iomap_ops *ops); + loff_t start, loff_t len, const struct iomap_ops *ops); +loff_t iomap_seek_hole(struct inode *inode, loff_t offset, + const struct iomap_ops *ops); +loff_t iomap_seek_data(struct inode *inode, loff_t offset, + const struct iomap_ops *ops); /* * Flags for direct I/O ->end_io: @@ -92,6 +97,6 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, typedef int (iomap_dio_end_io_t)(struct kiocb *iocb, ssize_t ret, unsigned flags); ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, - struct iomap_ops *ops, iomap_dio_end_io_t end_io); + const struct iomap_ops *ops, iomap_dio_end_io_t end_io); #endif /* LINUX_IOMAP_H */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0ff5111f6959..2cb54adc4a33 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -19,18 +19,28 @@ #ifndef __LINUX_IOMMU_H #define __LINUX_IOMMU_H +#include <linux/scatterlist.h> +#include <linux/device.h> +#include <linux/types.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/of.h> -#include <linux/types.h> -#include <linux/scatterlist.h> -#include <trace/events/iommu.h> #define IOMMU_READ (1 << 0) #define IOMMU_WRITE (1 << 1) #define IOMMU_CACHE (1 << 2) /* DMA cache coherency */ #define IOMMU_NOEXEC (1 << 3) #define IOMMU_MMIO (1 << 4) /* e.g. things like MSI doorbells */ +/* + * Where the bus hardware includes a privilege level as part of its access type + * markings, and certain devices are capable of issuing transactions marked as + * either 'supervisor' or 'user', the IOMMU_PRIV flag requests that the other + * given permission flags only apply to accesses at the higher privilege level, + * and that unprivileged transactions should have as little access as possible. + * This would usually imply the same permissions as kernel mappings on the CPU, + * if the IOMMU page table format is equivalent. + */ +#define IOMMU_PRIV (1 << 5) struct iommu_ops; struct iommu_group; @@ -117,18 +127,32 @@ enum iommu_attr { DOMAIN_ATTR_MAX, }; +/* These are the possible reserved region types */ +enum iommu_resv_type { + /* Memory regions which must be mapped 1:1 at all times */ + IOMMU_RESV_DIRECT, + /* Arbitrary "never map this or give it to a device" address ranges */ + IOMMU_RESV_RESERVED, + /* Hardware MSI region (untranslated) */ + IOMMU_RESV_MSI, + /* Software-managed MSI translation window */ + IOMMU_RESV_SW_MSI, +}; + /** - * struct iommu_dm_region - descriptor for a direct mapped memory region + * struct iommu_resv_region - descriptor for a reserved memory region * @list: Linked list pointers * @start: System physical start address of the region * @length: Length of the region in bytes * @prot: IOMMU Protection flags (READ/WRITE/...) + * @type: Type of the reserved region */ -struct iommu_dm_region { +struct iommu_resv_region { struct list_head list; phys_addr_t start; size_t length; int prot; + enum iommu_resv_type type; }; #ifdef CONFIG_IOMMU_API @@ -150,9 +174,9 @@ struct iommu_dm_region { * @device_group: find iommu group for a particular device * @domain_get_attr: Query domain attributes * @domain_set_attr: Change domain attributes - * @get_dm_regions: Request list of direct mapping requirements for a device - * @put_dm_regions: Free list of direct mapping requirements for a device - * @apply_dm_region: Temporary helper call-back for iova reserved ranges + * @get_resv_regions: Request list of reserved regions for a device + * @put_resv_regions: Free list of reserved regions for a device + * @apply_resv_region: Temporary helper call-back for iova reserved ranges * @domain_window_enable: Configure and enable a particular window for a domain * @domain_window_disable: Disable a particular window for a domain * @domain_set_windows: Set the number of windows for a domain @@ -184,11 +208,12 @@ struct iommu_ops { int (*domain_set_attr)(struct iommu_domain *domain, enum iommu_attr attr, void *data); - /* Request/Free a list of direct mapping requirements for a device */ - void (*get_dm_regions)(struct device *dev, struct list_head *list); - void (*put_dm_regions)(struct device *dev, struct list_head *list); - void (*apply_dm_region)(struct device *dev, struct iommu_domain *domain, - struct iommu_dm_region *region); + /* Request/Free a list of reserved regions for a device */ + void (*get_resv_regions)(struct device *dev, struct list_head *list); + void (*put_resv_regions)(struct device *dev, struct list_head *list); + void (*apply_resv_region)(struct device *dev, + struct iommu_domain *domain, + struct iommu_resv_region *region); /* Window handling functions */ int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, @@ -204,6 +229,42 @@ struct iommu_ops { unsigned long pgsize_bitmap; }; +/** + * struct iommu_device - IOMMU core representation of one IOMMU hardware + * instance + * @list: Used by the iommu-core to keep a list of registered iommus + * @ops: iommu-ops for talking to this iommu + * @dev: struct device for sysfs handling + */ +struct iommu_device { + struct list_head list; + const struct iommu_ops *ops; + struct fwnode_handle *fwnode; + struct device dev; +}; + +int iommu_device_register(struct iommu_device *iommu); +void iommu_device_unregister(struct iommu_device *iommu); +int iommu_device_sysfs_add(struct iommu_device *iommu, + struct device *parent, + const struct attribute_group **groups, + const char *fmt, ...) __printf(4, 5); +void iommu_device_sysfs_remove(struct iommu_device *iommu); +int iommu_device_link(struct iommu_device *iommu, struct device *link); +void iommu_device_unlink(struct iommu_device *iommu, struct device *link); + +static inline void iommu_device_set_ops(struct iommu_device *iommu, + const struct iommu_ops *ops) +{ + iommu->ops = ops; +} + +static inline void iommu_device_set_fwnode(struct iommu_device *iommu, + struct fwnode_handle *fwnode) +{ + iommu->fwnode = fwnode; +} + #define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ #define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ #define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ @@ -233,9 +294,14 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); -extern void iommu_get_dm_regions(struct device *dev, struct list_head *list); -extern void iommu_put_dm_regions(struct device *dev, struct list_head *list); +extern void iommu_get_resv_regions(struct device *dev, struct list_head *list); +extern void iommu_put_resv_regions(struct device *dev, struct list_head *list); extern int iommu_request_dm_for_dev(struct device *dev); +extern struct iommu_resv_region * +iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, + enum iommu_resv_type type); +extern int iommu_get_group_resv_regions(struct iommu_group *group, + struct list_head *head); extern int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group); @@ -267,58 +333,15 @@ extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr, void *data); extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, void *data); -struct device *iommu_device_create(struct device *parent, void *drvdata, - const struct attribute_group **groups, - const char *fmt, ...) __printf(4, 5); -void iommu_device_destroy(struct device *dev); -int iommu_device_link(struct device *dev, struct device *link); -void iommu_device_unlink(struct device *dev, struct device *link); /* Window handling function prototypes */ extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t offset, u64 size, int prot); extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr); -/** - * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework - * @domain: the iommu domain where the fault has happened - * @dev: the device where the fault has happened - * @iova: the faulting address - * @flags: mmu fault flags (e.g. IOMMU_FAULT_READ/IOMMU_FAULT_WRITE/...) - * - * This function should be called by the low-level IOMMU implementations - * whenever IOMMU faults happen, to allow high-level users, that are - * interested in such events, to know about them. - * - * This event may be useful for several possible use cases: - * - mere logging of the event - * - dynamic TLB/PTE loading - * - if restarting of the faulting device is required - * - * Returns 0 on success and an appropriate error code otherwise (if dynamic - * PTE/TLB loading will one day be supported, implementations will be able - * to tell whether it succeeded or not according to this return value). - * - * Specifically, -ENOSYS is returned if a fault handler isn't installed - * (though fault handlers can also return -ENOSYS, in case they want to - * elicit the default behavior of the IOMMU drivers). - */ -static inline int report_iommu_fault(struct iommu_domain *domain, - struct device *dev, unsigned long iova, int flags) -{ - int ret = -ENOSYS; - - /* - * if upper layers showed interest and installed a fault handler, - * invoke it. - */ - if (domain->handler) - ret = domain->handler(domain, dev, iova, flags, - domain->handler_token); - trace_io_page_fault(dev, iova, flags); - return ret; -} +extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, + unsigned long iova, int flags); static inline size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, @@ -352,15 +375,14 @@ int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, const struct iommu_ops *ops); void iommu_fwspec_free(struct device *dev); int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids); -void iommu_register_instance(struct fwnode_handle *fwnode, - const struct iommu_ops *ops); -const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode); +const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode); #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; struct iommu_group {}; struct iommu_fwspec {}; +struct iommu_device {}; static inline bool iommu_present(struct bus_type *bus) { @@ -443,16 +465,22 @@ static inline void iommu_set_fault_handler(struct iommu_domain *domain, { } -static inline void iommu_get_dm_regions(struct device *dev, +static inline void iommu_get_resv_regions(struct device *dev, struct list_head *list) { } -static inline void iommu_put_dm_regions(struct device *dev, +static inline void iommu_put_resv_regions(struct device *dev, struct list_head *list) { } +static inline int iommu_get_group_resv_regions(struct iommu_group *group, + struct list_head *head) +{ + return -ENODEV; +} + static inline int iommu_request_dm_for_dev(struct device *dev) { return -ENODEV; @@ -546,15 +574,34 @@ static inline int iommu_domain_set_attr(struct iommu_domain *domain, return -EINVAL; } -static inline struct device *iommu_device_create(struct device *parent, - void *drvdata, - const struct attribute_group **groups, - const char *fmt, ...) +static inline int iommu_device_register(struct iommu_device *iommu) +{ + return -ENODEV; +} + +static inline void iommu_device_set_ops(struct iommu_device *iommu, + const struct iommu_ops *ops) { - return ERR_PTR(-ENODEV); } -static inline void iommu_device_destroy(struct device *dev) +static inline void iommu_device_set_fwnode(struct iommu_device *iommu, + struct fwnode_handle *fwnode) +{ +} + +static inline void iommu_device_unregister(struct iommu_device *iommu) +{ +} + +static inline int iommu_device_sysfs_add(struct iommu_device *iommu, + struct device *parent, + const struct attribute_group **groups, + const char *fmt, ...) +{ + return -ENODEV; +} + +static inline void iommu_device_sysfs_remove(struct iommu_device *iommu) { } @@ -584,13 +631,8 @@ static inline int iommu_fwspec_add_ids(struct device *dev, u32 *ids, return -ENODEV; } -static inline void iommu_register_instance(struct fwnode_handle *fwnode, - const struct iommu_ops *ops) -{ -} - static inline -const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode) +const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) { return NULL; } diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index 1c30014ed176..d29e1e21bf3f 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -17,7 +17,7 @@ #include <linux/kernel.h> #include <linux/types.h> -#include <linux/hrtimer.h> +#include <linux/ktime.h> #include <linux/delay.h> #include <linux/errno.h> #include <linux/io.h> diff --git a/include/linux/iova.h b/include/linux/iova.h index f27bb2c62fca..e0a892ae45c0 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -82,6 +82,7 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) return iova >> iova_shift(iovad); } +#if IS_ENABLED(CONFIG_IOMMU_IOVA) int iova_cache_get(void); void iova_cache_put(void); @@ -106,5 +107,95 @@ void put_iova_domain(struct iova_domain *iovad); struct iova *split_and_remove_iova(struct iova_domain *iovad, struct iova *iova, unsigned long pfn_lo, unsigned long pfn_hi); void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad); +#else +static inline int iova_cache_get(void) +{ + return -ENOTSUPP; +} + +static inline void iova_cache_put(void) +{ +} + +static inline struct iova *alloc_iova_mem(void) +{ + return NULL; +} + +static inline void free_iova_mem(struct iova *iova) +{ +} + +static inline void free_iova(struct iova_domain *iovad, unsigned long pfn) +{ +} + +static inline void __free_iova(struct iova_domain *iovad, struct iova *iova) +{ +} + +static inline struct iova *alloc_iova(struct iova_domain *iovad, + unsigned long size, + unsigned long limit_pfn, + bool size_aligned) +{ + return NULL; +} + +static inline void free_iova_fast(struct iova_domain *iovad, + unsigned long pfn, + unsigned long size) +{ +} + +static inline unsigned long alloc_iova_fast(struct iova_domain *iovad, + unsigned long size, + unsigned long limit_pfn) +{ + return 0; +} + +static inline struct iova *reserve_iova(struct iova_domain *iovad, + unsigned long pfn_lo, + unsigned long pfn_hi) +{ + return NULL; +} + +static inline void copy_reserved_iova(struct iova_domain *from, + struct iova_domain *to) +{ +} + +static inline void init_iova_domain(struct iova_domain *iovad, + unsigned long granule, + unsigned long start_pfn, + unsigned long pfn_32bit) +{ +} + +static inline struct iova *find_iova(struct iova_domain *iovad, + unsigned long pfn) +{ + return NULL; +} + +static inline void put_iova_domain(struct iova_domain *iovad) +{ +} + +static inline struct iova *split_and_remove_iova(struct iova_domain *iovad, + struct iova *iova, + unsigned long pfn_lo, + unsigned long pfn_hi) +{ + return NULL; +} + +static inline void free_cpu_cached_iovas(unsigned int cpu, + struct iova_domain *iovad) +{ +} +#endif #endif diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 9d84942ae2e5..fadd579d577d 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -8,8 +8,7 @@ #define IPCMNI 32768 /* <= MAX_INT limit for ipc arrays (including sysctl changes) */ /* used by in-kernel data structures */ -struct kern_ipc_perm -{ +struct kern_ipc_perm { spinlock_t lock; bool deleted; int id; @@ -18,9 +17,12 @@ struct kern_ipc_perm kgid_t gid; kuid_t cuid; kgid_t cgid; - umode_t mode; + umode_t mode; unsigned long seq; void *security; -}; + + struct rcu_head rcu; + atomic_t refcount; +} ____cacheline_aligned_in_smp __randomize_layout; #endif /* _LINUX_IPC_H */ diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 848e5796400e..65327ee0936b 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -61,7 +61,7 @@ struct ipc_namespace { struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct ipc_namespace init_ipc_ns; extern spinlock_t mq_lock; diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 78c5d5ae3857..f1045b2c6a00 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -100,7 +100,7 @@ struct ipmi_user_hndl { /* Create a new user of the IPMI layer on the given interface number. */ int ipmi_create_user(unsigned int if_num, - struct ipmi_user_hndl *handler, + const struct ipmi_user_hndl *handler, void *handler_data, ipmi_user_t *user); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 671d014e6429..e1b442996f81 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -37,6 +37,7 @@ struct ipv6_devconf { __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; #ifdef CONFIG_IPV6_ROUTE_INFO + __s32 accept_ra_rt_info_min_plen; __s32 accept_ra_rt_info_max_plen; #endif #endif @@ -69,6 +70,8 @@ struct ipv6_devconf { __s32 seg6_require_hmac; #endif __u32 enhanced_dad; + __u32 addr_gen_mode; + __s32 disable_policy; struct ctl_table_header *sysctl_header; }; diff --git a/include/linux/irq.h b/include/linux/irq.h index 39e3254e5769..00db35b61e9e 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -22,6 +22,7 @@ #include <linux/topology.h> #include <linux/wait.h> #include <linux/io.h> +#include <linux/slab.h> #include <asm/irq.h> #include <asm/ptrace.h> @@ -136,6 +137,9 @@ struct irq_domain; * @affinity: IRQ affinity on SMP. If this is an IPI * related irq, then this is the mask of the * CPUs to which an IPI can be sent. + * @effective_affinity: The effective IRQ affinity on SMP as some irq + * chips do not allow multi CPU destinations. + * A subset of @affinity. * @msi_desc: MSI descriptor * @ipi_offset: Offset of first IPI target cpu in @affinity. Optional. */ @@ -147,6 +151,9 @@ struct irq_common_data { void *handler_data; struct msi_desc *msi_desc; cpumask_var_t affinity; +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + cpumask_var_t effective_affinity; +#endif #ifdef CONFIG_GENERIC_IRQ_IPI unsigned int ipi_offset; #endif @@ -199,6 +206,10 @@ struct irq_data { * IRQD_WAKEUP_ARMED - Wakeup mode armed * IRQD_FORWARDED_TO_VCPU - The interrupt is forwarded to a VCPU * IRQD_AFFINITY_MANAGED - Affinity is auto-managed by the kernel + * IRQD_IRQ_STARTED - Startup state of the interrupt + * IRQD_MANAGED_SHUTDOWN - Interrupt was shutdown due to empty affinity + * mask. Applies only to affinity managed irqs. + * IRQD_SINGLE_TARGET - IRQ allows only a single affinity target */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -216,6 +227,9 @@ enum { IRQD_WAKEUP_ARMED = (1 << 19), IRQD_FORWARDED_TO_VCPU = (1 << 20), IRQD_AFFINITY_MANAGED = (1 << 21), + IRQD_IRQ_STARTED = (1 << 22), + IRQD_MANAGED_SHUTDOWN = (1 << 23), + IRQD_SINGLE_TARGET = (1 << 24), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -264,6 +278,20 @@ static inline bool irqd_is_level_type(struct irq_data *d) return __irqd_to_state(d) & IRQD_LEVEL; } +/* + * Must only be called of irqchip.irq_set_affinity() or low level + * hieararchy domain allocation functions. + */ +static inline void irqd_set_single_target(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_SINGLE_TARGET; +} + +static inline bool irqd_is_single_target(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_SINGLE_TARGET; +} + static inline bool irqd_is_wakeup_set(struct irq_data *d) { return __irqd_to_state(d) & IRQD_WAKEUP_STATE; @@ -329,6 +357,16 @@ static inline void irqd_clr_activated(struct irq_data *d) __irqd_to_state(d) &= ~IRQD_ACTIVATED; } +static inline bool irqd_is_started(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_IRQ_STARTED; +} + +static inline bool irqd_is_managed_and_shutdown(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_MANAGED_SHUTDOWN; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) @@ -478,14 +516,21 @@ extern int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask, bool force); extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info); +#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_IRQ_MIGRATION) extern void irq_migrate_all_off_this_cpu(void); +extern int irq_affinity_online_cpu(unsigned int cpu); +#else +# define irq_affinity_online_cpu NULL +#endif #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ) void irq_move_irq(struct irq_data *data); void irq_move_masked_irq(struct irq_data *data); +void irq_force_complete_move(struct irq_desc *desc); #else static inline void irq_move_irq(struct irq_data *data) { } static inline void irq_move_masked_irq(struct irq_data *data) { } +static inline void irq_force_complete_move(struct irq_desc *desc) { } #endif extern int no_irq_affinity; @@ -727,11 +772,38 @@ static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) return d->common->affinity; } +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK +static inline +struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) +{ + return d->common->effective_affinity; +} +static inline void irq_data_update_effective_affinity(struct irq_data *d, + const struct cpumask *m) +{ + cpumask_copy(d->common->effective_affinity, m); +} +#else +static inline void irq_data_update_effective_affinity(struct irq_data *d, + const struct cpumask *m) +{ +} +static inline +struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) +{ + return d->common->affinity; +} +#endif + unsigned int arch_dynirq_lower_bound(unsigned int from); int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, struct module *owner, const struct cpumask *affinity); +int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from, + unsigned int cnt, int node, struct module *owner, + const struct cpumask *affinity); + /* use macros to avoid needing export.h for THIS_MODULE */ #define irq_alloc_descs(irq, from, cnt, node) \ __irq_alloc_descs(irq, from, cnt, node, THIS_MODULE, NULL) @@ -748,6 +820,21 @@ int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, #define irq_alloc_descs_from(from, cnt, node) \ irq_alloc_descs(-1, from, cnt, node) +#define devm_irq_alloc_descs(dev, irq, from, cnt, node) \ + __devm_irq_alloc_descs(dev, irq, from, cnt, node, THIS_MODULE, NULL) + +#define devm_irq_alloc_desc(dev, node) \ + devm_irq_alloc_descs(dev, -1, 0, 1, node) + +#define devm_irq_alloc_desc_at(dev, at, node) \ + devm_irq_alloc_descs(dev, at, at, 1, node) + +#define devm_irq_alloc_desc_from(dev, from, node) \ + devm_irq_alloc_descs(dev, -1, from, 1, node) + +#define devm_irq_alloc_descs_from(dev, from, cnt, node) \ + devm_irq_alloc_descs(dev, -1, from, cnt, node) + void irq_free_descs(unsigned int irq, unsigned int cnt); static inline void irq_free_desc(unsigned int irq) { @@ -932,6 +1019,14 @@ int irq_setup_alt_chip(struct irq_data *d, unsigned int type); void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, unsigned int clr, unsigned int set); +struct irq_chip_generic * +devm_irq_alloc_generic_chip(struct device *dev, const char *name, int num_ct, + unsigned int irq_base, void __iomem *reg_base, + irq_flow_handler_t handler); +int devm_irq_setup_generic_chip(struct device *dev, struct irq_chip_generic *gc, + u32 msk, enum irq_gc_flags flags, + unsigned int clr, unsigned int set); + struct irq_chip_generic *irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq); int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, @@ -948,6 +1043,19 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, handler, clr, set, flags); \ }) +static inline void irq_free_generic_chip(struct irq_chip_generic *gc) +{ + kfree(gc); +} + +static inline void irq_destroy_generic_chip(struct irq_chip_generic *gc, + u32 msk, unsigned int clr, + unsigned int set) +{ + irq_remove_generic_chip(gc, msk, clr, set); + irq_free_generic_chip(gc); +} + static inline struct irq_chip_type *irq_data_get_chip_type(struct irq_data *d) { return container_of(d->chip, struct irq_chip_type, chip); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index e808f8ae6f14..6a1f87ff94e2 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -73,7 +73,6 @@ #define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1) #define GICD_TYPER_IRQS(typer) ((((typer) & 0x1f) + 1) * 32) -#define GICD_TYPER_LPIS (1U << 17) #define GICD_IROUTER_SPI_MODE_ONE (0U << 31) #define GICD_IROUTER_SPI_MODE_ANY (1U << 31) @@ -133,6 +132,9 @@ #define GIC_BASER_SHAREABILITY(reg, type) \ (GIC_BASER_##type << reg##_SHAREABILITY_SHIFT) +/* encode a size field of width @w containing @n - 1 units */ +#define GIC_ENCODE_SZ(n, w) (((unsigned long)(n) - 1) & GENMASK_ULL(((w) - 1), 0)) + #define GICR_PROPBASER_SHAREABILITY_SHIFT (10) #define GICR_PROPBASER_INNER_CACHEABILITY_SHIFT (7) #define GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT (56) @@ -157,6 +159,8 @@ #define GICR_PROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWb) #define GICR_PROPBASER_IDBITS_MASK (0x1f) +#define GICR_PROPBASER_ADDRESS(x) ((x) & GENMASK_ULL(51, 12)) +#define GICR_PENDBASER_ADDRESS(x) ((x) & GENMASK_ULL(51, 16)) #define GICR_PENDBASER_SHAREABILITY_SHIFT (10) #define GICR_PENDBASER_INNER_CACHEABILITY_SHIFT (7) @@ -233,12 +237,18 @@ #define GITS_CTLR_QUIESCENT (1U << 31) #define GITS_TYPER_PLPIS (1UL << 0) +#define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) #define GITS_TYPER_PTA (1UL << 19) #define GITS_TYPER_HWCOLLCNT_SHIFT 24 +#define GITS_IIDR_REV_SHIFT 12 +#define GITS_IIDR_REV_MASK (0xf << GITS_IIDR_REV_SHIFT) +#define GITS_IIDR_REV(r) (((r) >> GITS_IIDR_REV_SHIFT) & 0xf) +#define GITS_IIDR_PRODUCTID_SHIFT 24 + #define GITS_CBASER_VALID (1ULL << 63) #define GITS_CBASER_SHAREABILITY_SHIFT (10) #define GITS_CBASER_INNER_CACHEABILITY_SHIFT (59) @@ -291,6 +301,7 @@ #define GITS_BASER_TYPE(r) (((r) >> GITS_BASER_TYPE_SHIFT) & 7) #define GITS_BASER_ENTRY_SIZE_SHIFT (48) #define GITS_BASER_ENTRY_SIZE(r) ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0x1f) + 1) +#define GITS_BASER_ENTRY_SIZE_MASK GENMASK_ULL(52, 48) #define GITS_BASER_SHAREABILITY_SHIFT (10) #define GITS_BASER_InnerShareable \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) @@ -306,7 +317,7 @@ #define GITS_BASER_TYPE_NONE 0 #define GITS_BASER_TYPE_DEVICE 1 #define GITS_BASER_TYPE_VCPU 2 -#define GITS_BASER_TYPE_CPU 3 +#define GITS_BASER_TYPE_RESERVED3 3 #define GITS_BASER_TYPE_COLLECTION 4 #define GITS_BASER_TYPE_RESERVED5 5 #define GITS_BASER_TYPE_RESERVED6 6 @@ -320,8 +331,6 @@ #define GITS_CMD_MAPD 0x08 #define GITS_CMD_MAPC 0x09 #define GITS_CMD_MAPTI 0x0a -/* older GIC documentation used MAPVI for this command */ -#define GITS_CMD_MAPVI GITS_CMD_MAPTI #define GITS_CMD_MAPI 0x0b #define GITS_CMD_MOVI 0x01 #define GITS_CMD_DISCARD 0x0f @@ -340,9 +349,11 @@ #define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307 #define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507 #define E_ITS_MAPD_DEVICE_OOR 0x010801 +#define E_ITS_MAPD_ITTSIZE_OOR 0x010802 #define E_ITS_MAPC_PROCNUM_OOR 0x010902 #define E_ITS_MAPC_COLLECTION_OOR 0x010903 #define E_ITS_MAPTI_UNMAPPED_DEVICE 0x010a04 +#define E_ITS_MAPTI_ID_OOR 0x010a05 #define E_ITS_MAPTI_PHYSICALID_OOR 0x010a06 #define E_ITS_INV_UNMAPPED_INTERRUPT 0x010c07 #define E_ITS_INVALL_UNMAPPED_COLLECTION 0x010d09 @@ -352,8 +363,32 @@ /* * CPU interface registers */ -#define ICC_CTLR_EL1_EOImode_drop_dir (0U << 1) -#define ICC_CTLR_EL1_EOImode_drop (1U << 1) +#define ICC_CTLR_EL1_EOImode_SHIFT (1) +#define ICC_CTLR_EL1_EOImode_drop_dir (0U << ICC_CTLR_EL1_EOImode_SHIFT) +#define ICC_CTLR_EL1_EOImode_drop (1U << ICC_CTLR_EL1_EOImode_SHIFT) +#define ICC_CTLR_EL1_EOImode_MASK (1 << ICC_CTLR_EL1_EOImode_SHIFT) +#define ICC_CTLR_EL1_CBPR_SHIFT 0 +#define ICC_CTLR_EL1_CBPR_MASK (1 << ICC_CTLR_EL1_CBPR_SHIFT) +#define ICC_CTLR_EL1_PRI_BITS_SHIFT 8 +#define ICC_CTLR_EL1_PRI_BITS_MASK (0x7 << ICC_CTLR_EL1_PRI_BITS_SHIFT) +#define ICC_CTLR_EL1_ID_BITS_SHIFT 11 +#define ICC_CTLR_EL1_ID_BITS_MASK (0x7 << ICC_CTLR_EL1_ID_BITS_SHIFT) +#define ICC_CTLR_EL1_SEIS_SHIFT 14 +#define ICC_CTLR_EL1_SEIS_MASK (0x1 << ICC_CTLR_EL1_SEIS_SHIFT) +#define ICC_CTLR_EL1_A3V_SHIFT 15 +#define ICC_CTLR_EL1_A3V_MASK (0x1 << ICC_CTLR_EL1_A3V_SHIFT) +#define ICC_PMR_EL1_SHIFT 0 +#define ICC_PMR_EL1_MASK (0xff << ICC_PMR_EL1_SHIFT) +#define ICC_BPR0_EL1_SHIFT 0 +#define ICC_BPR0_EL1_MASK (0x7 << ICC_BPR0_EL1_SHIFT) +#define ICC_BPR1_EL1_SHIFT 0 +#define ICC_BPR1_EL1_MASK (0x7 << ICC_BPR1_EL1_SHIFT) +#define ICC_IGRPEN0_EL1_SHIFT 0 +#define ICC_IGRPEN0_EL1_MASK (1 << ICC_IGRPEN0_EL1_SHIFT) +#define ICC_IGRPEN1_EL1_SHIFT 0 +#define ICC_IGRPEN1_EL1_MASK (1 << ICC_IGRPEN1_EL1_SHIFT) +#define ICC_SRE_EL1_DIB (1U << 2) +#define ICC_SRE_EL1_DFB (1U << 1) #define ICC_SRE_EL1_SRE (1U << 0) /* @@ -370,6 +405,7 @@ #define ICH_LR_PHYS_ID_SHIFT 32 #define ICH_LR_PHYS_ID_MASK (0x3ffULL << ICH_LR_PHYS_ID_SHIFT) #define ICH_LR_PRIORITY_SHIFT 48 +#define ICH_LR_PRIORITY_MASK (0xffULL << ICH_LR_PRIORITY_SHIFT) /* These are for GICv2 emulation only */ #define GICH_LR_VIRTUALID (0x3ffUL << 0) @@ -381,15 +417,39 @@ #define ICH_HCR_EN (1 << 0) #define ICH_HCR_UIE (1 << 1) - -#define ICH_VMCR_CTLR_SHIFT 0 -#define ICH_VMCR_CTLR_MASK (0x21f << ICH_VMCR_CTLR_SHIFT) +#define ICH_HCR_TC (1 << 10) +#define ICH_HCR_TALL0 (1 << 11) +#define ICH_HCR_TALL1 (1 << 12) +#define ICH_HCR_EOIcount_SHIFT 27 +#define ICH_HCR_EOIcount_MASK (0x1f << ICH_HCR_EOIcount_SHIFT) + +#define ICH_VMCR_ACK_CTL_SHIFT 2 +#define ICH_VMCR_ACK_CTL_MASK (1 << ICH_VMCR_ACK_CTL_SHIFT) +#define ICH_VMCR_FIQ_EN_SHIFT 3 +#define ICH_VMCR_FIQ_EN_MASK (1 << ICH_VMCR_FIQ_EN_SHIFT) +#define ICH_VMCR_CBPR_SHIFT 4 +#define ICH_VMCR_CBPR_MASK (1 << ICH_VMCR_CBPR_SHIFT) +#define ICH_VMCR_EOIM_SHIFT 9 +#define ICH_VMCR_EOIM_MASK (1 << ICH_VMCR_EOIM_SHIFT) #define ICH_VMCR_BPR1_SHIFT 18 #define ICH_VMCR_BPR1_MASK (7 << ICH_VMCR_BPR1_SHIFT) #define ICH_VMCR_BPR0_SHIFT 21 #define ICH_VMCR_BPR0_MASK (7 << ICH_VMCR_BPR0_SHIFT) #define ICH_VMCR_PMR_SHIFT 24 #define ICH_VMCR_PMR_MASK (0xffUL << ICH_VMCR_PMR_SHIFT) +#define ICH_VMCR_ENG0_SHIFT 0 +#define ICH_VMCR_ENG0_MASK (1 << ICH_VMCR_ENG0_SHIFT) +#define ICH_VMCR_ENG1_SHIFT 1 +#define ICH_VMCR_ENG1_MASK (1 << ICH_VMCR_ENG1_SHIFT) + +#define ICH_VTR_PRI_BITS_SHIFT 29 +#define ICH_VTR_PRI_BITS_MASK (7 << ICH_VTR_PRI_BITS_SHIFT) +#define ICH_VTR_ID_BITS_SHIFT 23 +#define ICH_VTR_ID_BITS_MASK (7 << ICH_VTR_ID_BITS_SHIFT) +#define ICH_VTR_SEIS_SHIFT 22 +#define ICH_VTR_SEIS_MASK (1 << ICH_VTR_SEIS_SHIFT) +#define ICH_VTR_A3V_SHIFT 21 +#define ICH_VTR_A3V_MASK (1 << ICH_VTR_A3V_SHIFT) #define ICC_IAR1_EL1_SPURIOUS 0x3ff diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index eafc965b3eb8..d3453ee072fc 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -25,7 +25,18 @@ #define GICC_ENABLE 0x1 #define GICC_INT_PRI_THRESHOLD 0xf0 -#define GIC_CPU_CTRL_EOImodeNS (1 << 9) +#define GIC_CPU_CTRL_EnableGrp0_SHIFT 0 +#define GIC_CPU_CTRL_EnableGrp0 (1 << GIC_CPU_CTRL_EnableGrp0_SHIFT) +#define GIC_CPU_CTRL_EnableGrp1_SHIFT 1 +#define GIC_CPU_CTRL_EnableGrp1 (1 << GIC_CPU_CTRL_EnableGrp1_SHIFT) +#define GIC_CPU_CTRL_AckCtl_SHIFT 2 +#define GIC_CPU_CTRL_AckCtl (1 << GIC_CPU_CTRL_AckCtl_SHIFT) +#define GIC_CPU_CTRL_FIQEn_SHIFT 3 +#define GIC_CPU_CTRL_FIQEn (1 << GIC_CPU_CTRL_FIQEn_SHIFT) +#define GIC_CPU_CTRL_CBPR_SHIFT 4 +#define GIC_CPU_CTRL_CBPR (1 << GIC_CPU_CTRL_CBPR_SHIFT) +#define GIC_CPU_CTRL_EOImodeNS_SHIFT 9 +#define GIC_CPU_CTRL_EOImodeNS (1 << GIC_CPU_CTRL_EOImodeNS_SHIFT) #define GICC_IAR_INT_ID_MASK 0x3ff #define GICC_INT_SPURIOUS 1023 @@ -84,8 +95,19 @@ #define GICH_LR_EOI (1 << 19) #define GICH_LR_HW (1 << 31) -#define GICH_VMCR_CTRL_SHIFT 0 -#define GICH_VMCR_CTRL_MASK (0x21f << GICH_VMCR_CTRL_SHIFT) +#define GICH_VMCR_ENABLE_GRP0_SHIFT 0 +#define GICH_VMCR_ENABLE_GRP0_MASK (1 << GICH_VMCR_ENABLE_GRP0_SHIFT) +#define GICH_VMCR_ENABLE_GRP1_SHIFT 1 +#define GICH_VMCR_ENABLE_GRP1_MASK (1 << GICH_VMCR_ENABLE_GRP1_SHIFT) +#define GICH_VMCR_ACK_CTL_SHIFT 2 +#define GICH_VMCR_ACK_CTL_MASK (1 << GICH_VMCR_ACK_CTL_SHIFT) +#define GICH_VMCR_FIQ_EN_SHIFT 3 +#define GICH_VMCR_FIQ_EN_MASK (1 << GICH_VMCR_FIQ_EN_SHIFT) +#define GICH_VMCR_CBPR_SHIFT 4 +#define GICH_VMCR_CBPR_MASK (1 << GICH_VMCR_CBPR_SHIFT) +#define GICH_VMCR_EOI_MODE_SHIFT 9 +#define GICH_VMCR_EOI_MODE_MASK (1 << GICH_VMCR_EOI_MODE_SHIFT) + #define GICH_VMCR_PRIMASK_SHIFT 27 #define GICH_VMCR_PRIMASK_MASK (0x1f << GICH_VMCR_PRIMASK_SHIFT) #define GICH_VMCR_BINPOINT_SHIFT 21 @@ -96,6 +118,9 @@ #define GICH_MISR_EOI (1 << 0) #define GICH_MISR_U (1 << 1) +#define GICV_PMR_PRIORITY_SHIFT 3 +#define GICV_PMR_PRIORITY_MASK (0x1f << GICV_PMR_PRIORITY_SHIFT) + #ifndef __ASSEMBLY__ #include <linux/irqdomain.h> diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 7b49c71c968b..2b0e56619e53 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -258,7 +258,6 @@ extern unsigned int gic_present; extern void gic_init(unsigned long gic_base_addr, unsigned long gic_addrspace_size, unsigned int cpu_vec, unsigned int irqbase); -extern void gic_clocksource_init(unsigned int); extern u64 gic_read_count(void); extern unsigned int gic_get_count_width(void); extern u64 gic_read_compare(void); diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index c9be57931b58..3e90a094798d 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -3,6 +3,7 @@ #include <linux/rcupdate.h> #include <linux/kobject.h> +#include <linux/mutex.h> /* * Core internal functions to deal with irq descriptors @@ -45,7 +46,9 @@ struct pt_regs; * IRQF_FORCE_RESUME set * @rcu: rcu head for delayed free * @kobj: kobject used to represent this struct in sysfs + * @request_mutex: mutex to protect request/free before locking desc->lock * @dir: /proc/irq/ procfs entry + * @debugfs_file: dentry for the debugfs file * @name: flow handler name for /proc/interrupts output */ struct irq_desc { @@ -88,10 +91,14 @@ struct irq_desc { #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; #endif +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS + struct dentry *debugfs_file; +#endif #ifdef CONFIG_SPARSE_IRQ struct rcu_head rcu; struct kobject kobj; #endif + struct mutex request_mutex; int parent_irq; struct module *owner; const char *name; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index ffb84604c1de..cac77a5c5555 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -130,6 +130,7 @@ struct irq_domain_chip_generic; * @host_data: private data pointer for use by owner. Not touched by irq_domain * core code. * @flags: host per irq_domain flags + * @mapcount: The number of mapped interrupts * * Optional elements * @of_node: Pointer to device tree nodes associated with the irq_domain. Used @@ -138,6 +139,7 @@ struct irq_domain_chip_generic; * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. * @parent: Pointer to parent irq_domain to support hierarchy irq_domains + * @debugfs_file: dentry for the domain debugfs file * * Revmap data, used internally by irq_domain * @revmap_direct_max_irq: The largest hwirq that can be set for controllers that @@ -152,6 +154,7 @@ struct irq_domain { const struct irq_domain_ops *ops; void *host_data; unsigned int flags; + unsigned int mapcount; /* Optional data */ struct fwnode_handle *fwnode; @@ -160,6 +163,9 @@ struct irq_domain { #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_domain *parent; #endif +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS + struct dentry *debugfs_file; +#endif /* reverse map data. The linear map gets appended to the irq_domain */ irq_hw_number_t hwirq_max; @@ -174,8 +180,8 @@ enum { /* Irq domain is hierarchical */ IRQ_DOMAIN_FLAG_HIERARCHY = (1 << 0), - /* Core calls alloc/free recursive through the domain hierarchy. */ - IRQ_DOMAIN_FLAG_AUTO_RECURSIVE = (1 << 1), + /* Irq domain name was allocated in __irq_domain_add() */ + IRQ_DOMAIN_NAME_ALLOCATED = (1 << 6), /* Irq domain is an IPI domain with virq per cpu */ IRQ_DOMAIN_FLAG_IPI_PER_CPU = (1 << 2), @@ -183,6 +189,12 @@ enum { /* Irq domain is an IPI domain with single virq */ IRQ_DOMAIN_FLAG_IPI_SINGLE = (1 << 3), + /* Irq domain implements MSIs */ + IRQ_DOMAIN_FLAG_MSI = (1 << 4), + + /* Irq domain implements MSI remapping */ + IRQ_DOMAIN_FLAG_MSI_REMAP = (1 << 5), + /* * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved * for implementation specific purposes and ignored by the @@ -197,7 +209,33 @@ static inline struct device_node *irq_domain_get_of_node(struct irq_domain *d) } #ifdef CONFIG_IRQ_DOMAIN -struct fwnode_handle *irq_domain_alloc_fwnode(void *data); +struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id, + const char *name, void *data); + +enum { + IRQCHIP_FWNODE_REAL, + IRQCHIP_FWNODE_NAMED, + IRQCHIP_FWNODE_NAMED_ID, +}; + +static inline +struct fwnode_handle *irq_domain_alloc_named_fwnode(const char *name) +{ + return __irq_domain_alloc_fwnode(IRQCHIP_FWNODE_NAMED, 0, name, NULL); +} + +static inline +struct fwnode_handle *irq_domain_alloc_named_id_fwnode(const char *name, int id) +{ + return __irq_domain_alloc_fwnode(IRQCHIP_FWNODE_NAMED_ID, id, name, + NULL); +} + +static inline struct fwnode_handle *irq_domain_alloc_fwnode(void *data) +{ + return __irq_domain_alloc_fwnode(IRQCHIP_FWNODE_REAL, 0, NULL, data); +} + void irq_domain_free_fwnode(struct fwnode_handle *fwnode); struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, irq_hw_number_t hwirq_max, int direct_max, @@ -216,6 +254,7 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, void *host_data); extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token); +extern bool irq_domain_check_msi_remap(void); extern void irq_set_default_host(struct irq_domain *host); extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, irq_hw_number_t hwirq, int node, @@ -231,6 +270,9 @@ static inline bool is_fwnode_irqchip(struct fwnode_handle *fwnode) return fwnode && fwnode->type == FWNODE_IRQCHIP; } +extern void irq_domain_update_bus_token(struct irq_domain *domain, + enum irq_domain_bus_token bus_token); + static inline struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode, enum irq_domain_bus_token bus_token) @@ -403,7 +445,7 @@ static inline int irq_domain_alloc_irqs(struct irq_domain *domain, NULL); } -extern int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, +extern int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs, void *arg); extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, @@ -446,6 +488,19 @@ static inline bool irq_domain_is_ipi_single(struct irq_domain *domain) { return domain->flags & IRQ_DOMAIN_FLAG_IPI_SINGLE; } + +static inline bool irq_domain_is_msi(struct irq_domain *domain) +{ + return domain->flags & IRQ_DOMAIN_FLAG_MSI; +} + +static inline bool irq_domain_is_msi_remap(struct irq_domain *domain) +{ + return domain->flags & IRQ_DOMAIN_FLAG_MSI_REMAP; +} + +extern bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain); + #else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ static inline void irq_domain_activate_irq(struct irq_data *data) { } static inline void irq_domain_deactivate_irq(struct irq_data *data) { } @@ -477,6 +532,22 @@ static inline bool irq_domain_is_ipi_single(struct irq_domain *domain) { return false; } + +static inline bool irq_domain_is_msi(struct irq_domain *domain) +{ + return false; +} + +static inline bool irq_domain_is_msi_remap(struct irq_domain *domain) +{ + return false; +} + +static inline bool +irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain) +{ + return false; +} #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ #else /* CONFIG_IRQ_DOMAIN */ @@ -488,6 +559,10 @@ static inline struct irq_domain *irq_find_matching_fwnode( { return NULL; } +static inline bool irq_domain_check_msi_remap(void) +{ + return false; +} #endif /* !CONFIG_IRQ_DOMAIN */ #endif /* _LINUX_IRQDOMAIN_H */ diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index dfaa1f4dcb0c..606b6bce3a5b 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -491,6 +491,8 @@ struct jbd2_journal_handle unsigned long h_start_jiffies; unsigned int h_requested_credits; + + unsigned int saved_alloc_context; }; diff --git a/include/linux/jhash.h b/include/linux/jhash.h index 348c6f47e4cc..8037850f3104 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -85,19 +85,18 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) k += 12; } /* Last block: affect all 32 bits of (c) */ - /* All the case statements fall through */ switch (length) { - case 12: c += (u32)k[11]<<24; - case 11: c += (u32)k[10]<<16; - case 10: c += (u32)k[9]<<8; - case 9: c += k[8]; - case 8: b += (u32)k[7]<<24; - case 7: b += (u32)k[6]<<16; - case 6: b += (u32)k[5]<<8; - case 5: b += k[4]; - case 4: a += (u32)k[3]<<24; - case 3: a += (u32)k[2]<<16; - case 2: a += (u32)k[1]<<8; + case 12: c += (u32)k[11]<<24; /* fall through */ + case 11: c += (u32)k[10]<<16; /* fall through */ + case 10: c += (u32)k[9]<<8; /* fall through */ + case 9: c += k[8]; /* fall through */ + case 8: b += (u32)k[7]<<24; /* fall through */ + case 7: b += (u32)k[6]<<16; /* fall through */ + case 6: b += (u32)k[5]<<8; /* fall through */ + case 5: b += k[4]; /* fall through */ + case 4: a += (u32)k[3]<<24; /* fall through */ + case 3: a += (u32)k[2]<<16; /* fall through */ + case 2: a += (u32)k[1]<<8; /* fall through */ case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ @@ -131,10 +130,10 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) k += 3; } - /* Handle the last 3 u32's: all the case statements fall through */ + /* Handle the last 3 u32's */ switch (length) { - case 3: c += k[2]; - case 2: b += k[1]; + case 3: c += k[2]; /* fall through */ + case 2: b += k[1]; /* fall through */ case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 589d14e970ad..734377ad42e9 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -1,6 +1,7 @@ #ifndef _LINUX_JIFFIES_H #define _LINUX_JIFFIES_H +#include <linux/cache.h> #include <linux/math64.h> #include <linux/kernel.h> #include <linux/types.h> @@ -63,19 +64,17 @@ extern int register_refined_jiffies(long clock_tick_rate); /* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ #define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) -/* some arch's have a small-data section that can be accessed register-relative - * but that can only take up to, say, 4-byte variables. jiffies being part of - * an 8-byte variable may not be correctly accessed unless we force the issue - */ -#define __jiffy_data __attribute__((section(".data"))) +#ifndef __jiffy_arch_data +#define __jiffy_arch_data +#endif /* * The 64-bit value is not atomic - you MUST NOT read it * without sampling the sequence number in jiffies_lock. * get_jiffies_64() will do this for you as appropriate. */ -extern u64 __jiffy_data jiffies_64; -extern unsigned long volatile __jiffy_data jiffies; +extern u64 __cacheline_aligned_in_smp jiffies_64; +extern unsigned long volatile __cacheline_aligned_in_smp __jiffy_arch_data jiffies; #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void); @@ -293,6 +292,8 @@ static inline u64 jiffies_to_nsecs(const unsigned long j) return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC; } +extern u64 jiffies64_to_nsecs(u64 j); + extern unsigned long __msecs_to_jiffies(const unsigned int m); #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) /* diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index a0547c571800..2afd74b9d844 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -89,11 +89,24 @@ extern bool static_key_initialized; struct static_key { atomic_t enabled; -/* Set lsb bit to 1 if branch is default true, 0 ot */ - struct jump_entry *entries; -#ifdef CONFIG_MODULES - struct static_key_mod *next; -#endif +/* + * Note: + * To make anonymous unions work with old compilers, the static + * initialization of them requires brackets. This creates a dependency + * on the order of the struct with the initializers. If any fields + * are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need + * to be modified. + * + * bit 0 => 1 if key is initially true + * 0 if initially false + * bit 1 => 1 if points to struct static_key_mod + * 0 if points to struct jump_entry + */ + union { + unsigned long type; + struct jump_entry *entries; + struct static_key_mod *next; + }; }; #else @@ -118,9 +131,10 @@ struct module; #ifdef HAVE_JUMP_LABEL -#define JUMP_TYPE_FALSE 0UL -#define JUMP_TYPE_TRUE 1UL -#define JUMP_TYPE_MASK 1UL +#define JUMP_TYPE_FALSE 0UL +#define JUMP_TYPE_TRUE 1UL +#define JUMP_TYPE_LINKED 2UL +#define JUMP_TYPE_MASK 3UL static __always_inline bool static_key_false(struct static_key *key) { @@ -159,10 +173,10 @@ extern void static_key_disable(struct static_key *key); */ #define STATIC_KEY_INIT_TRUE \ { .enabled = { 1 }, \ - .entries = (void *)JUMP_TYPE_TRUE } + { .entries = (void *)JUMP_TYPE_TRUE } } #define STATIC_KEY_INIT_FALSE \ { .enabled = { 0 }, \ - .entries = (void *)JUMP_TYPE_FALSE } + { .entries = (void *)JUMP_TYPE_FALSE } } #else /* !HAVE_JUMP_LABEL */ @@ -402,6 +416,6 @@ extern bool ____wrong_branch_error(void); #define static_branch_enable(x) static_key_enable(&(x)->key) #define static_branch_disable(x) static_key_disable(&(x)->key) -#endif /* _LINUX_JUMP_LABEL_H */ - #endif /* __ASSEMBLY__ */ + +#endif /* _LINUX_JUMP_LABEL_H */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 820c0ad54a01..a5c7046f26b4 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -1,12 +1,12 @@ #ifndef _LINUX_KASAN_H #define _LINUX_KASAN_H -#include <linux/sched.h> #include <linux/types.h> struct kmem_cache; struct page; struct vm_struct; +struct task_struct; #ifdef CONFIG_KASAN @@ -19,6 +19,7 @@ extern unsigned char kasan_zero_page[PAGE_SIZE]; extern pte_t kasan_zero_pte[PTRS_PER_PTE]; extern pmd_t kasan_zero_pmd[PTRS_PER_PMD]; extern pud_t kasan_zero_pud[PTRS_PER_PUD]; +extern p4d_t kasan_zero_p4d[PTRS_PER_P4D]; void kasan_populate_zero_shadow(const void *shadow_start, const void *shadow_end); @@ -30,16 +31,10 @@ static inline void *kasan_mem_to_shadow(const void *addr) } /* Enable reporting bugs after kasan_disable_current() */ -static inline void kasan_enable_current(void) -{ - current->kasan_depth++; -} +extern void kasan_enable_current(void); /* Disable reporting bugs for current task */ -static inline void kasan_disable_current(void) -{ - current->kasan_depth--; -} +extern void kasan_disable_current(void); void kasan_unpoison_shadow(const void *address, size_t size); @@ -52,7 +47,7 @@ void kasan_free_pages(struct page *page, unsigned int order); void kasan_cache_create(struct kmem_cache *cache, size_t *size, unsigned long *flags); void kasan_cache_shrink(struct kmem_cache *cache); -void kasan_cache_destroy(struct kmem_cache *cache); +void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_poison_slab(struct page *page); void kasan_unpoison_object_data(struct kmem_cache *cache, void *object); @@ -81,6 +76,9 @@ size_t ksize(const void *); static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); } size_t kasan_metadata_size(struct kmem_cache *cache); +bool kasan_save_enable_multi_shot(void); +void kasan_restore_multi_shot(bool enabled); + #else /* CONFIG_KASAN */ static inline void kasan_unpoison_shadow(const void *address, size_t size) {} @@ -98,7 +96,7 @@ static inline void kasan_cache_create(struct kmem_cache *cache, size_t *size, unsigned long *flags) {} static inline void kasan_cache_shrink(struct kmem_cache *cache) {} -static inline void kasan_cache_destroy(struct kmem_cache *cache) {} +static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_poison_slab(struct page *page) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, diff --git a/include/linux/kbuild.h b/include/linux/kbuild.h index 22a72198c14b..4e80f3a9ad58 100644 --- a/include/linux/kbuild.h +++ b/include/linux/kbuild.h @@ -2,14 +2,14 @@ #define __LINUX_KBUILD_H #define DEFINE(sym, val) \ - asm volatile("\n->" #sym " %0 " #val : : "i" (val)) + asm volatile("\n.ascii \"->" #sym " %0 " #val "\"" : : "i" (val)) -#define BLANK() asm volatile("\n->" : : ) +#define BLANK() asm volatile("\n.ascii \"->\"" : : ) #define OFFSET(sym, str, mem) \ DEFINE(sym, offsetof(struct str, mem)) #define COMMENT(x) \ - asm volatile("\n->#" x) + asm volatile("\n.ascii \"->#" x "\"") #endif diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index 8f2e059e4d45..4d748603e818 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -8,7 +8,7 @@ /* * The use of "&&" / "||" is limited in certain expressions. - * The followings enable to calculate "and" / "or" with macro expansion only. + * The following enable to calculate "and" / "or" with macro expansion only. */ #define __and(x, y) ___and(x, y) #define ___and(x, y) ____and(__ARG_PLACEHOLDER_##x, y) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index cb09238f6d32..bd6d96cf80b1 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -11,6 +11,7 @@ #include <linux/log2.h> #include <linux/typecheck.h> #include <linux/printk.h> +#include <linux/build_bug.h> #include <asm/byteorder.h> #include <uapi/linux/kernel.h> @@ -47,6 +48,7 @@ /* @a is a power of 2 value */ #define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) #define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask)) #define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) #define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) @@ -100,16 +102,18 @@ ) /* - * Divide positive or negative dividend by positive divisor and round - * to closest integer. Result is undefined for negative divisors and - * for negative dividends if the divisor variable type is unsigned. + * Divide positive or negative dividend by positive or negative divisor + * and round to closest integer. Result is undefined for negative + * divisors if he dividend variable type is unsigned and for negative + * dividends if the divisor variable type is unsigned. */ #define DIV_ROUND_CLOSEST(x, divisor)( \ { \ typeof(x) __x = x; \ typeof(divisor) __d = divisor; \ (((typeof(x))-1) > 0 || \ - ((typeof(divisor))-1) > 0 || (__x) > 0) ? \ + ((typeof(divisor))-1) > 0 || \ + (((__x) > 0) == ((__d) > 0))) ? \ (((__x) + ((__d) / 2)) / (__d)) : \ (((__x) - ((__d) / 2)) / (__d)); \ } \ @@ -436,6 +440,7 @@ extern int get_option(char **str, int *pint); extern char *get_options(const char *str, int nints, int *ints); extern unsigned long long memparse(const char *ptr, char **retptr); extern bool parse_option_str(const char *str, const char *option); +extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); extern int core_kernel_data(unsigned long addr); @@ -486,9 +491,13 @@ extern int root_mountflags; extern bool early_boot_irqs_disabled; -/* Values used for system_state */ +/* + * Values used for system_state. Ordering of the states must not be changed + * as code checks for <, <=, >, >= STATE. + */ extern enum system_states { SYSTEM_BOOTING, + SYSTEM_SCHEDULING, SYSTEM_RUNNING, SYSTEM_HALT, SYSTEM_POWER_OFF, @@ -846,9 +855,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @member: the name of the member within the struct. * */ -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type,member) );}) +#define container_of(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + ((type *)(__mptr - offsetof(type, member))); }) /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 00f776816aa3..66be8b6beceb 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -9,7 +9,6 @@ #include <linux/sched.h> #include <linux/vtime.h> #include <asm/irq.h> -#include <linux/cputime.h> /* * 'kernel_stat.h' contains the definitions needed for doing @@ -78,15 +77,18 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu) return kstat_cpu(cpu).irqs_sum; } -extern void account_user_time(struct task_struct *, cputime_t); -extern void account_system_time(struct task_struct *, int, cputime_t); -extern void account_steal_time(cputime_t); -extern void account_idle_time(cputime_t); +extern void account_user_time(struct task_struct *, u64); +extern void account_guest_time(struct task_struct *, u64); +extern void account_system_time(struct task_struct *, int, u64); +extern void account_system_index_time(struct task_struct *, u64, + enum cpu_usage_stat); +extern void account_steal_time(u64); +extern void account_idle_time(u64); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE static inline void account_process_tick(struct task_struct *tsk, int user) { - vtime_account_user(tsk); + vtime_flush(tsk); } #else extern void account_process_tick(struct task_struct *, int user); diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 7056238fd9f5..a9b11b8d06f2 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -46,6 +46,7 @@ enum kernfs_node_flag { KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, KERNFS_EMPTY_DIR = 0x1000, + KERNFS_HAS_RELEASE = 0x2000, }; /* @flags for kernfs_create_root() */ @@ -175,6 +176,7 @@ struct kernfs_open_file { /* published fields */ struct kernfs_node *kn; struct file *file; + struct seq_file *seq_file; void *priv; /* private fields, do not use outside kernfs proper */ @@ -185,12 +187,20 @@ struct kernfs_open_file { char *prealloc_buf; size_t atomic_write_len; - bool mmapped; + bool mmapped:1; + bool released:1; const struct vm_operations_struct *vm_ops; }; struct kernfs_ops { /* + * Optional open/release methods. Both are called with + * @of->seq_file populated. + */ + int (*open)(struct kernfs_open_file *of); + void (*release)(struct kernfs_open_file *of); + + /* * Read is handled by either seq_file or raw_read(). * * If seq_show() is present, seq_file path is active. Other seq diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d419d0e51fe5..dd056fab9e35 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -14,17 +14,15 @@ #if !defined(__ASSEMBLY__) +#include <linux/crash_core.h> #include <asm/io.h> #include <uapi/linux/kexec.h> #ifdef CONFIG_KEXEC_CORE #include <linux/list.h> -#include <linux/linkage.h> #include <linux/compat.h> #include <linux/ioport.h> -#include <linux/elfcore.h> -#include <linux/elf.h> #include <linux/module.h> #include <asm/kexec.h> @@ -62,20 +60,7 @@ #define KEXEC_CRASH_MEM_ALIGN PAGE_SIZE #endif -#define KEXEC_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) -#define KEXEC_CORE_NOTE_NAME "CORE" -#define KEXEC_CORE_NOTE_NAME_BYTES ALIGN(sizeof(KEXEC_CORE_NOTE_NAME), 4) -#define KEXEC_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4) -/* - * The per-cpu notes area is a list of notes terminated by a "NULL" - * note header. For kdump, the code in vmcore.c runs in the context - * of the second kernel to combine them into one note. - */ -#ifndef KEXEC_NOTE_BYTES -#define KEXEC_NOTE_BYTES ( (KEXEC_NOTE_HEAD_BYTES * 2) + \ - KEXEC_CORE_NOTE_NAME_BYTES + \ - KEXEC_CORE_NOTE_DESC_BYTES ) -#endif +#define KEXEC_CORE_NOTE_NAME CRASH_CORE_NOTE_NAME /* * This structure is used to hold the arguments that are used when loading @@ -187,6 +172,7 @@ struct kimage { unsigned long start; struct page *control_code_page; struct page *swap_page; + void *vmcoreinfo_data_copy; /* locates in the crash memory */ unsigned long nr_segments; struct kexec_segment segment[KEXEC_SEGMENT_MAX]; @@ -256,33 +242,7 @@ extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); int kexec_crash_loaded(void); void crash_save_cpu(struct pt_regs *regs, int cpu); -void crash_save_vmcoreinfo(void); -void arch_crash_save_vmcoreinfo(void); -__printf(1, 2) -void vmcoreinfo_append_str(const char *fmt, ...); -phys_addr_t paddr_vmcoreinfo_note(void); - -#define VMCOREINFO_OSRELEASE(value) \ - vmcoreinfo_append_str("OSRELEASE=%s\n", value) -#define VMCOREINFO_PAGESIZE(value) \ - vmcoreinfo_append_str("PAGESIZE=%ld\n", value) -#define VMCOREINFO_SYMBOL(name) \ - vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) -#define VMCOREINFO_SIZE(name) \ - vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ - (unsigned long)sizeof(name)) -#define VMCOREINFO_STRUCT_SIZE(name) \ - vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ - (unsigned long)sizeof(struct name)) -#define VMCOREINFO_OFFSET(name, field) \ - vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ - (unsigned long)offsetof(struct name, field)) -#define VMCOREINFO_LENGTH(name, value) \ - vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) -#define VMCOREINFO_NUMBER(name) \ - vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) -#define VMCOREINFO_CONFIG(name) \ - vmcoreinfo_append_str("CONFIG_%s=y\n", #name) +extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; @@ -303,31 +263,15 @@ extern int kexec_load_disabled; #define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \ KEXEC_FILE_NO_INITRAMFS) -#define VMCOREINFO_BYTES (4096) -#define VMCOREINFO_NOTE_NAME "VMCOREINFO" -#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) -#define VMCOREINFO_NOTE_SIZE (KEXEC_NOTE_HEAD_BYTES*2 + VMCOREINFO_BYTES \ - + VMCOREINFO_NOTE_NAME_BYTES) - /* Location of a reserved region to hold the crash kernel. */ extern struct resource crashk_res; extern struct resource crashk_low_res; -typedef u32 note_buf_t[KEXEC_NOTE_BYTES/4]; extern note_buf_t __percpu *crash_notes; -extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; -extern size_t vmcoreinfo_size; -extern size_t vmcoreinfo_max_size; /* flag to track if kexec reboot is in progress */ extern bool kexec_in_progress; -int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, - unsigned long long *crash_size, unsigned long long *crash_base); -int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, - unsigned long long *crash_size, unsigned long long *crash_base); -int parse_crashkernel_low(char *cmdline, unsigned long long system_ram, - unsigned long long *crash_size, unsigned long long *crash_base); int crash_shrink_memory(unsigned long new_size); size_t crash_get_memory_size(void); void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); diff --git a/include/linux/key-type.h b/include/linux/key-type.h index eaee981c5558..9520fc3c3b9a 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -45,7 +45,7 @@ struct key_preparsed_payload { size_t datalen; /* Raw datalen */ size_t quotalen; /* Quota length for proposed payload */ time_t expiry; /* Expiry time of key */ -}; +} __randomize_layout; typedef int (*request_key_actor_t)(struct key_construction *key, const char *op, void *aux); @@ -147,10 +147,18 @@ struct key_type { */ request_key_actor_t request_key; + /* Look up a keyring access restriction (optional) + * + * - NULL is a valid return value (meaning the requested restriction + * is known but will never block addition of a key) + * - should return -EINVAL if the restriction is unknown + */ + struct key_restriction *(*lookup_restriction)(const char *params); + /* internal fields */ struct list_head link; /* link in types list */ struct lock_class_key lock_class; /* key->sem lock class */ -}; +} __randomize_layout; extern struct key_type key_type_keyring; diff --git a/include/linux/key.h b/include/linux/key.h index 722914798f37..044114185120 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -9,7 +9,7 @@ * 2 of the License, or (at your option) any later version. * * - * See Documentation/security/keys.txt for information on keys/keyrings. + * See Documentation/security/keys/core.rst for information on keys/keyrings. */ #ifndef _LINUX_KEY_H @@ -23,6 +23,7 @@ #include <linux/rwsem.h> #include <linux/atomic.h> #include <linux/assoc_array.h> +#include <linux/refcount.h> #ifdef __KERNEL__ #include <linux/uidgid.h> @@ -126,6 +127,17 @@ static inline bool is_key_possessed(const key_ref_t key_ref) return (unsigned long) key_ref & 1UL; } +typedef int (*key_restrict_link_func_t)(struct key *dest_keyring, + const struct key_type *type, + const union key_payload *payload, + struct key *restriction_key); + +struct key_restriction { + key_restrict_link_func_t check; + struct key *key; + struct key_type *keytype; +}; + /*****************************************************************************/ /* * authentication token / access credential / keyring @@ -135,7 +147,7 @@ static inline bool is_key_possessed(const key_ref_t key_ref) * - Kerberos TGTs and tickets */ struct key { - atomic_t usage; /* number of references */ + refcount_t usage; /* number of references */ key_serial_t serial; /* key serial number */ union { struct list_head graveyard_link; @@ -161,7 +173,6 @@ struct key { #ifdef KEY_DEBUGGING unsigned magic; #define KEY_DEBUG_MAGIC 0x18273645u -#define KEY_DEBUG_MAGIC_X 0xf8e9dacbu #endif unsigned long flags; /* status flags (change with bitops) */ @@ -205,18 +216,17 @@ struct key { }; /* This is set on a keyring to restrict the addition of a link to a key - * to it. If this method isn't provided then it is assumed that the + * to it. If this structure isn't provided then it is assumed that the * keyring is open to any addition. It is ignored for non-keyring - * keys. + * keys. Only set this value using keyring_restrict(), keyring_alloc(), + * or key_alloc(). * * This is intended for use with rings of trusted keys whereby addition * to the keyring needs to be controlled. KEY_ALLOC_BYPASS_RESTRICTION * overrides this, allowing the kernel to add extra keys without * restriction. */ - int (*restrict_link)(struct key *keyring, - const struct key_type *type, - const union key_payload *payload); + struct key_restriction *restrict_link; }; extern struct key *key_alloc(struct key_type *type, @@ -225,9 +235,7 @@ extern struct key *key_alloc(struct key_type *type, const struct cred *cred, key_perm_t perm, unsigned long flags, - int (*restrict_link)(struct key *, - const struct key_type *, - const union key_payload *)); + struct key_restriction *restrict_link); #define KEY_ALLOC_IN_QUOTA 0x0000 /* add to quota, reject if would overrun */ @@ -242,7 +250,7 @@ extern void key_put(struct key *key); static inline struct key *__key_get(struct key *key) { - atomic_inc(&key->usage); + refcount_inc(&key->usage); return key; } @@ -303,14 +311,13 @@ extern struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid const struct cred *cred, key_perm_t perm, unsigned long flags, - int (*restrict_link)(struct key *, - const struct key_type *, - const union key_payload *), + struct key_restriction *restrict_link, struct key *dest); extern int restrict_link_reject(struct key *keyring, const struct key_type *type, - const union key_payload *payload); + const union key_payload *payload, + struct key *restriction_key); extern int keyring_clear(struct key *keyring); @@ -321,6 +328,9 @@ extern key_ref_t keyring_search(key_ref_t keyring, extern int keyring_add_key(struct key *keyring, struct key *key); +extern int keyring_restrict(key_ref_t keyring, const char *type, + const char *restriction); + extern struct key *key_lookup(key_serial_t id); static inline key_serial_t key_serial(const struct key *key) @@ -354,7 +364,10 @@ static inline bool key_is_instantiated(const struct key *key) !test_bit(KEY_FLAG_NEGATIVE, &key->flags); } -#define rcu_dereference_key(KEY) \ +#define dereference_key_rcu(KEY) \ + (rcu_dereference((KEY)->payload.rcu_data0)) + +#define dereference_key_locked(KEY) \ (rcu_dereference_protected((KEY)->payload.rcu_data0, \ rwsem_is_locked(&((struct key *)(KEY))->sem))) diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 1e032a1ddb3e..f0d7335336cd 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -1,7 +1,8 @@ #ifndef _LINUX_KHUGEPAGED_H #define _LINUX_KHUGEPAGED_H -#include <linux/sched.h> /* MMF_VM_HUGEPAGE */ +#include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */ + #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; @@ -47,7 +48,8 @@ static inline int khugepaged_enter(struct vm_area_struct *vma, if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) if ((khugepaged_always() || (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && - !(vm_flags & VM_NOHUGEPAGE)) + !(vm_flags & VM_NOHUGEPAGE) && + !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) if (__khugepaged_enter(vma->vm_mm)) return -ENOMEM; return 0; diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 1c2a32829620..590343f6c1b1 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -22,6 +22,7 @@ #define __KMEMLEAK_H #include <linux/slab.h> +#include <linux/vmalloc.h> #ifdef CONFIG_DEBUG_KMEMLEAK @@ -30,6 +31,8 @@ extern void kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp) __ref; extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, gfp_t gfp) __ref; +extern void kmemleak_vmalloc(const struct vm_struct *area, size_t size, + gfp_t gfp) __ref; extern void kmemleak_free(const void *ptr) __ref; extern void kmemleak_free_part(const void *ptr, size_t size) __ref; extern void kmemleak_free_percpu(const void __percpu *ptr) __ref; @@ -81,6 +84,10 @@ static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, gfp_t gfp) { } +static inline void kmemleak_vmalloc(const struct vm_struct *area, size_t size, + gfp_t gfp) +{ +} static inline void kmemleak_free(const void *ptr) { } diff --git a/include/linux/kmod.h b/include/linux/kmod.h index fcfd2bf14d3f..655082c88fd9 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -56,7 +56,7 @@ struct file; struct subprocess_info { struct work_struct work; struct completion *complete; - char *path; + const char *path; char **argv; char **envp; int wait; @@ -64,13 +64,14 @@ struct subprocess_info { int (*init)(struct subprocess_info *info, struct cred *new); void (*cleanup)(struct subprocess_info *info); void *data; -}; +} __randomize_layout; extern int -call_usermodehelper(char *path, char **argv, char **envp, int wait); +call_usermodehelper(const char *path, char **argv, char **envp, int wait); extern struct subprocess_info * -call_usermodehelper_setup(char *path, char **argv, char **envp, gfp_t gfp_mask, +call_usermodehelper_setup(const char *path, char **argv, char **envp, + gfp_t gfp_mask, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *), void *data); diff --git a/include/linux/kobject.h b/include/linux/kobject.h index e6284591599e..4d800c79475a 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -108,6 +108,8 @@ extern int __must_check kobject_rename(struct kobject *, const char *new_name); extern int __must_check kobject_move(struct kobject *, struct kobject *); extern struct kobject *kobject_get(struct kobject *kobj); +extern struct kobject * __must_check kobject_get_unless_zero( + struct kobject *kobj); extern void kobject_put(struct kobject *kobj); extern const void *kobject_namespace(struct kobject *kobj); @@ -170,7 +172,7 @@ struct kset { spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; -}; +} __randomize_layout; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); @@ -215,11 +217,9 @@ extern struct kobject *firmware_kobj; int kobject_uevent(struct kobject *kobj, enum kobject_action action); int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp[]); +int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count); __printf(2, 3) int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...); -int kobject_action_type(const char *buf, size_t count, - enum kobject_action *type); - #endif /* _KOBJECT_H_ */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8f6849084248..bd2684700b74 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -29,7 +29,7 @@ * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi * <prasanna@in.ibm.com> added function-return probes. */ -#include <linux/compiler.h> /* for __kprobes */ +#include <linux/compiler.h> #include <linux/linkage.h> #include <linux/list.h> #include <linux/notifier.h> @@ -40,9 +40,9 @@ #include <linux/rcupdate.h> #include <linux/mutex.h> #include <linux/ftrace.h> +#include <asm/kprobes.h> #ifdef CONFIG_KPROBES -#include <asm/kprobes.h> /* kprobe_status settings */ #define KPROBE_HIT_ACTIVE 0x00000001 @@ -51,6 +51,7 @@ #define KPROBE_HIT_SSDONE 0x00000008 #else /* CONFIG_KPROBES */ +#include <asm-generic/kprobes.h> typedef int kprobe_opcode_t; struct arch_specific_insn { int dummy; @@ -266,6 +267,8 @@ extern int arch_init_kprobes(void); extern void show_registers(struct pt_regs *regs); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); +extern bool arch_kprobe_on_func_entry(unsigned long offset); +extern bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); @@ -278,9 +281,13 @@ struct kprobe_insn_cache { int nr_garbage; }; +#ifdef __ARCH_WANT_KPROBES_INSN_SLOT extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c); extern void __free_insn_slot(struct kprobe_insn_cache *c, kprobe_opcode_t *slot, int dirty); +/* sleep-less address checking routine */ +extern bool __is_insn_slot_addr(struct kprobe_insn_cache *c, + unsigned long addr); #define DEFINE_INSN_CACHE_OPS(__name) \ extern struct kprobe_insn_cache kprobe_##__name##_slots; \ @@ -294,6 +301,18 @@ static inline void free_##__name##_slot(kprobe_opcode_t *slot, int dirty)\ { \ __free_insn_slot(&kprobe_##__name##_slots, slot, dirty); \ } \ + \ +static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ +{ \ + return __is_insn_slot_addr(&kprobe_##__name##_slots, addr); \ +} +#else /* __ARCH_WANT_KPROBES_INSN_SLOT */ +#define DEFINE_INSN_CACHE_OPS(__name) \ +static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ +{ \ + return 0; \ +} +#endif DEFINE_INSN_CACHE_OPS(insn); @@ -330,7 +349,9 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif - +extern void wait_for_kprobe_optimizer(void); +#else +static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, @@ -363,6 +384,7 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) return this_cpu_ptr(&kprobe_ctlblk); } +kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); @@ -481,18 +503,17 @@ static inline int enable_jprobe(struct jprobe *jp) return enable_kprobe(&jp->kp); } -#ifdef CONFIG_KPROBES -/* - * Blacklist ganerating macro. Specify functions which is not probed - * by using this macro. - */ -#define __NOKPROBE_SYMBOL(fname) \ -static unsigned long __used \ - __attribute__((section("_kprobe_blacklist"))) \ - _kbl_addr_##fname = (unsigned long)fname; -#define NOKPROBE_SYMBOL(fname) __NOKPROBE_SYMBOL(fname) -#else -#define NOKPROBE_SYMBOL(fname) +#ifndef CONFIG_KPROBES +static inline bool is_kprobe_insn_slot(unsigned long addr) +{ + return false; +} +#endif +#ifndef CONFIG_OPTPROBES +static inline bool is_kprobe_optinsn_slot(unsigned long addr) +{ + return false; +} #endif #endif /* _LINUX_KPROBES_H */ diff --git a/include/linux/kref.h b/include/linux/kref.h index e15828fd71f1..29220724bf1c 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -15,65 +15,36 @@ #ifndef _KREF_H_ #define _KREF_H_ -#include <linux/bug.h> -#include <linux/atomic.h> -#include <linux/kernel.h> -#include <linux/mutex.h> +#include <linux/spinlock.h> +#include <linux/refcount.h> struct kref { - atomic_t refcount; + refcount_t refcount; }; +#define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } + /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { - atomic_set(&kref->refcount, 1); + refcount_set(&kref->refcount, 1); } -/** - * kref_get - increment refcount for object. - * @kref: object. - */ -static inline void kref_get(struct kref *kref) +static inline unsigned int kref_read(const struct kref *kref) { - /* If refcount was 0 before incrementing then we have a race - * condition when this kref is freeing by some other thread right now. - * In this case one should use kref_get_unless_zero() - */ - WARN_ON_ONCE(atomic_inc_return(&kref->refcount) < 2); + return refcount_read(&kref->refcount); } /** - * kref_sub - subtract a number of refcounts for object. + * kref_get - increment refcount for object. * @kref: object. - * @count: Number of recounts to subtract. - * @release: pointer to the function that will clean up the object when the - * last reference to the object is released. - * This pointer is required, and it is not acceptable to pass kfree - * in as this function. If the caller does pass kfree to this - * function, you will be publicly mocked mercilessly by the kref - * maintainer, and anyone else who happens to notice it. You have - * been warned. - * - * Subtract @count from the refcount, and if 0, call release(). - * Return 1 if the object was removed, otherwise return 0. Beware, if this - * function returns 0, you still can not count on the kref from remaining in - * memory. Only use the return value if you want to see if the kref is now - * gone, not present. */ -static inline int kref_sub(struct kref *kref, unsigned int count, - void (*release)(struct kref *kref)) +static inline void kref_get(struct kref *kref) { - WARN_ON(release == NULL); - - if (atomic_sub_and_test((int) count, &kref->refcount)) { - release(kref); - return 1; - } - return 0; + refcount_inc(&kref->refcount); } /** @@ -95,20 +66,29 @@ static inline int kref_sub(struct kref *kref, unsigned int count, */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { - return kref_sub(kref, 1, release); + if (refcount_dec_and_test(&kref->refcount)) { + release(kref); + return 1; + } + return 0; } static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) { - WARN_ON(release == NULL); - if (unlikely(!atomic_add_unless(&kref->refcount, -1, 1))) { - mutex_lock(lock); - if (unlikely(!atomic_dec_and_test(&kref->refcount))) { - mutex_unlock(lock); - return 0; - } + if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) { + release(kref); + return 1; + } + return 0; +} + +static inline int kref_put_lock(struct kref *kref, + void (*release)(struct kref *kref), + spinlock_t *lock) +{ + if (refcount_dec_and_lock(&kref->refcount, lock)) { release(kref); return 1; } @@ -133,6 +113,6 @@ static inline int kref_put_mutex(struct kref *kref, */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { - return atomic_add_unless(&kref->refcount, 1, 0); + return refcount_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */ diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 481c8c4627ca..78b44a024eaa 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -12,6 +12,7 @@ #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/sched.h> +#include <linux/sched/coredump.h> struct stable_node; struct mem_cgroup; @@ -60,7 +61,7 @@ static inline void set_page_stable_node(struct page *page, struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); void ksm_migrate_page(struct page *newpage, struct page *oldpage); #else /* !CONFIG_KSM */ @@ -93,10 +94,9 @@ static inline int page_referenced_ksm(struct page *page, return 0; } -static inline int rmap_walk_ksm(struct page *page, +static inline void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) { - return 0; } static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1c5190dab2c1..648b34cabb38 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -26,6 +26,7 @@ #include <linux/context_tracking.h> #include <linux/irqbypass.h> #include <linux/swait.h> +#include <linux/refcount.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -45,7 +46,6 @@ * include/linux/kvm_h. */ #define KVM_MEMSLOT_INVALID (1UL << 16) -#define KVM_MEMSLOT_INCOHERENT (1UL << 17) /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS 2 @@ -115,14 +115,24 @@ static inline bool is_error_page(struct page *page) return IS_ERR(page); } +#define KVM_REQUEST_MASK GENMASK(7,0) +#define KVM_REQUEST_NO_WAKEUP BIT(8) +#define KVM_REQUEST_WAIT BIT(9) /* * Architecture-independent vcpu->requests bit members * Bits 4-7 are reserved for more arch-independent bits. */ -#define KVM_REQ_TLB_FLUSH 0 -#define KVM_REQ_MMU_RELOAD 1 -#define KVM_REQ_PENDING_TIMER 2 -#define KVM_REQ_UNHALT 3 +#define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_PENDING_TIMER 2 +#define KVM_REQ_UNHALT 3 +#define KVM_REQUEST_ARCH_BASE 8 + +#define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ + BUILD_BUG_ON((unsigned)(nr) >= 32 - KVM_REQUEST_ARCH_BASE); \ + (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ +}) +#define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -162,8 +172,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); -int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, - struct kvm_io_device *dev); +void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev); struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr); @@ -222,10 +232,9 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; - int fpu_active; int guest_fpu_loaded, guest_xcr0_loaded; struct swait_queue_head wq; - struct pid *pid; + struct pid __rcu *pid; int sigset_active; sigset_t sigset; struct kvm_vcpu_stat stat; @@ -269,6 +278,12 @@ struct kvm_vcpu { static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { + /* + * The memory barrier ensures a previous write to vcpu->requests cannot + * be reordered with the read of vcpu->mode. It pairs with the general + * memory barrier following the write of vcpu->mode in VCPU RUN. + */ + smp_mb__before_atomic(); return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE); } @@ -375,9 +390,7 @@ struct kvm { spinlock_t mmu_lock; struct mutex slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ - struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM]; - struct srcu_struct srcu; - struct srcu_struct irq_srcu; + struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; /* @@ -391,7 +404,7 @@ struct kvm { int last_boosted_vcpu; struct list_head vm_list; struct mutex lock; - struct kvm_io_bus *buses[KVM_NR_BUSES]; + struct kvm_io_bus __rcu *buses[KVM_NR_BUSES]; #ifdef CONFIG_HAVE_KVM_EVENTFD struct { spinlock_t lock; @@ -403,8 +416,8 @@ struct kvm { #endif struct kvm_vm_stat stat; struct kvm_arch arch; - atomic_t users_count; -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET + refcount_t users_count; +#ifdef CONFIG_KVM_MMIO struct kvm_coalesced_mmio_ring *coalesced_mmio_ring; spinlock_t ring_lock; struct list_head coalesced_zones; @@ -430,6 +443,8 @@ struct kvm { struct list_head devices; struct dentry *debugfs_dentry; struct kvm_stat_data **debugfs_stat_data; + struct srcu_struct srcu; + struct srcu_struct irq_srcu; }; #define kvm_err(fmt, ...) \ @@ -458,6 +473,12 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) +{ + return srcu_dereference_check(kvm->buses[idx], &kvm->srcu, + lockdep_is_held(&kvm->slots_lock)); +} + static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case @@ -491,6 +512,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } +static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu *tmp; + int idx; + + kvm_for_each_vcpu(idx, tmp, vcpu->kvm) + if (tmp == vcpu) + return idx; + BUG(); +} + #define kvm_for_each_memslot(memslot, slots) \ for (memslot = &slots->memslots[0]; \ memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\ @@ -503,10 +535,10 @@ int __must_check vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); #ifdef __KVM_HAVE_IOAPIC -void kvm_vcpu_request_scan_ioapic(struct kvm *kvm); +void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm); void kvm_arch_post_irq_routing_update(struct kvm *kvm); #else -static inline void kvm_vcpu_request_scan_ioapic(struct kvm *kvm) +static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm) { } static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm) @@ -536,9 +568,8 @@ void kvm_put_kvm(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { - return rcu_dereference_check(kvm->memslots[as_id], - srcu_read_lock_held(&kvm->srcu) - || lockdep_is_held(&kvm->slots_lock)); + return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, + lockdep_is_held(&kvm->slots_lock)); } static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) @@ -683,7 +714,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); -void kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); +bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); @@ -768,8 +799,6 @@ void kvm_arch_check_processor_compat(void *rtn); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); -void *kvm_kvzalloc(unsigned long size); - #ifndef __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { @@ -878,22 +907,6 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, int kvm_request_irq_source_id(struct kvm *kvm); void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); -#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT -int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot); -void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot); -#else -static inline int kvm_iommu_map_pages(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - return 0; -} - -static inline void kvm_iommu_unmap_pages(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ -} -#endif - /* * search_memslots() and __gfn_to_memslot() are here because they are * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c. @@ -1026,6 +1039,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) #define KVM_MAX_IRQ_ROUTES 1024 #endif +bool kvm_arch_can_set_irq_routing(struct kvm *kvm); int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, @@ -1093,13 +1107,28 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) * caller. Paired with the smp_mb__after_atomic in kvm_check_request. */ smp_wmb(); - set_bit(req, &vcpu->requests); + set_bit(req & KVM_REQUEST_MASK, &vcpu->requests); +} + +static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) +{ + return READ_ONCE(vcpu->requests); +} + +static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu) +{ + return test_bit(req & KVM_REQUEST_MASK, &vcpu->requests); +} + +static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu) +{ + clear_bit(req & KVM_REQUEST_MASK, &vcpu->requests); } static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) { - if (test_bit(req, &vcpu->requests)) { - clear_bit(req, &vcpu->requests); + if (kvm_test_request(req, vcpu)) { + kvm_clear_request(req, vcpu); /* * Ensure the rest of the request is visible to kvm_check_request's @@ -1166,7 +1195,6 @@ int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type); void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; -extern struct kvm_device_ops kvm_xics_ops; extern struct kvm_device_ops kvm_arm_vgic_v2_ops; extern struct kvm_device_ops kvm_arm_vgic_v3_ops; diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h index 0c1de05098c8..76c2fbc59f35 100644 --- a/include/linux/kvm_irqfd.h +++ b/include/linux/kvm_irqfd.h @@ -46,7 +46,7 @@ struct kvm_kernel_irqfd_resampler { struct kvm_kernel_irqfd { /* Used for MSI fast-path */ struct kvm *kvm; - wait_queue_t wait; + wait_queue_entry_t wait; /* Update side is protected by irqfds.lock */ struct kvm_kernel_irq_routing_entry irq_entry; seqcount_t irq_entry_sc; diff --git a/include/linux/leds-pca9532.h b/include/linux/leds-pca9532.h index d215b4561180..5e240b2b4d58 100644 --- a/include/linux/leds-pca9532.h +++ b/include/linux/leds-pca9532.h @@ -22,7 +22,8 @@ enum pca9532_state { PCA9532_OFF = 0x0, PCA9532_ON = 0x1, PCA9532_PWM0 = 0x2, - PCA9532_PWM1 = 0x3 + PCA9532_PWM1 = 0x3, + PCA9532_KEEP = 0xff, }; struct pca9532_led { @@ -44,4 +45,3 @@ struct pca9532_platform_data { }; #endif /* __LINUX_PCA9532_H */ - diff --git a/include/linux/leds.h b/include/linux/leds.h index 569cb531094c..64c56d454f7d 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -13,6 +13,7 @@ #define __LINUX_LEDS_H_INCLUDED #include <linux/device.h> +#include <linux/kernfs.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/rwsem.h> @@ -27,6 +28,7 @@ struct device; enum led_brightness { LED_OFF = 0, + LED_ON = 1, LED_HALF = 127, LED_FULL = 255, }; @@ -46,6 +48,7 @@ struct led_classdev { #define LED_DEV_CAP_FLASH (1 << 18) #define LED_HW_PLUGGABLE (1 << 19) #define LED_PANIC_INDICATOR (1 << 20) +#define LED_BRIGHT_HW_CHANGED (1 << 21) /* set_brightness_work / blink_timer flags, atomic, private. */ unsigned long work_flags; @@ -110,14 +113,25 @@ struct led_classdev { bool activated; #endif +#ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED + int brightness_hw_changed; + struct kernfs_node *brightness_hw_changed_kn; +#endif + /* Ensures consistent access to the LED Flash Class device */ struct mutex led_access; }; -extern int led_classdev_register(struct device *parent, - struct led_classdev *led_cdev); -extern int devm_led_classdev_register(struct device *parent, - struct led_classdev *led_cdev); +extern int of_led_classdev_register(struct device *parent, + struct device_node *np, + struct led_classdev *led_cdev); +#define led_classdev_register(parent, led_cdev) \ + of_led_classdev_register(parent, NULL, led_cdev) +extern int devm_of_led_classdev_register(struct device *parent, + struct device_node *np, + struct led_classdev *led_cdev); +#define devm_led_classdev_register(parent, led_cdev) \ + devm_of_led_classdev_register(parent, NULL, led_cdev) extern void led_classdev_unregister(struct led_classdev *led_cdev); extern void devm_led_classdev_unregister(struct device *parent, struct led_classdev *led_cdev); @@ -422,4 +436,12 @@ static inline void ledtrig_cpu(enum cpu_led_event evt) } #endif +#ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED +extern void led_classdev_notify_brightness_hw_changed( + struct led_classdev *led_cdev, enum led_brightness brightness); +#else +static inline void led_classdev_notify_brightness_hw_changed( + struct led_classdev *led_cdev, enum led_brightness brightness) { } +#endif + #endif /* __LINUX_LEDS_H_INCLUDED */ diff --git a/include/linux/libata.h b/include/linux/libata.h index c170be548b7f..55de3da58b1c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -19,7 +19,7 @@ * * * libata documentation is available via 'make {ps|pdf}docs', - * as Documentation/DocBook/libata.* + * as Documentation/driver-api/libata.rst * */ @@ -156,6 +156,7 @@ enum { ATA_DFLAG_ACPI_PENDING = (1 << 5), /* ACPI resume action pending */ ATA_DFLAG_ACPI_FAILED = (1 << 6), /* ACPI on devcfg has failed */ ATA_DFLAG_AN = (1 << 7), /* AN configured */ + ATA_DFLAG_TRUSTED = (1 << 8), /* device supports trusted send/recv */ ATA_DFLAG_DMADIR = (1 << 10), /* device requires DMADIR */ ATA_DFLAG_CFG_MASK = (1 << 12) - 1, @@ -968,7 +969,7 @@ struct ata_port_operations { void (*sff_tf_read)(struct ata_port *ap, struct ata_taskfile *tf); void (*sff_exec_command)(struct ata_port *ap, const struct ata_taskfile *tf); - unsigned int (*sff_data_xfer)(struct ata_device *dev, + unsigned int (*sff_data_xfer)(struct ata_queued_cmd *qc, unsigned char *buf, unsigned int buflen, int rw); void (*sff_irq_on)(struct ata_port *); bool (*sff_irq_check)(struct ata_port *); @@ -1130,6 +1131,7 @@ extern int ata_sas_port_start(struct ata_port *ap); extern void ata_sas_port_stop(struct ata_port *ap); extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *); extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap); +extern enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd); extern int sata_scr_valid(struct ata_link *link); extern int sata_scr_read(struct ata_link *link, int reg, u32 *val); extern int sata_scr_write(struct ata_link *link, int reg, u32 val); @@ -1355,6 +1357,7 @@ extern struct device_attribute *ata_common_sdev_attrs[]; .proc_name = drv_name, \ .slave_configure = ata_scsi_slave_config, \ .slave_destroy = ata_scsi_slave_destroy, \ + .eh_timed_out = ata_scsi_timed_out, \ .bios_param = ata_std_bios_param, \ .unlock_native_capacity = ata_scsi_unlock_native_capacity, \ .sdev_attrs = ata_common_sdev_attrs @@ -1823,11 +1826,11 @@ extern void ata_sff_tf_load(struct ata_port *ap, const struct ata_taskfile *tf); extern void ata_sff_tf_read(struct ata_port *ap, struct ata_taskfile *tf); extern void ata_sff_exec_command(struct ata_port *ap, const struct ata_taskfile *tf); -extern unsigned int ata_sff_data_xfer(struct ata_device *dev, +extern unsigned int ata_sff_data_xfer(struct ata_queued_cmd *qc, unsigned char *buf, unsigned int buflen, int rw); -extern unsigned int ata_sff_data_xfer32(struct ata_device *dev, +extern unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc, unsigned char *buf, unsigned int buflen, int rw); -extern unsigned int ata_sff_data_xfer_noirq(struct ata_device *dev, +extern unsigned int ata_sff_data_xfer_noirq(struct ata_queued_cmd *qc, unsigned char *buf, unsigned int buflen, int rw); extern void ata_sff_irq_on(struct ata_port *ap); extern void ata_sff_irq_clear(struct ata_port *ap); diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 8458c5351e56..f3d3e6af8838 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -17,12 +17,15 @@ #include <linux/kernel.h> #include <linux/sizes.h> #include <linux/types.h> +#include <linux/uuid.h> enum { /* when a dimm supports both PMEM and BLK access a label is required */ - NDD_ALIASING = 1 << 0, + NDD_ALIASING = 0, /* unarmed memory devices may not persist writes */ - NDD_UNARMED = 1 << 1, + NDD_UNARMED = 1, + /* locked memory devices should not be accessed */ + NDD_LOCKED = 2, /* need to set a limit somewhere, but yes, this is likely overkill */ ND_IOCTL_MAX_BUFLEN = SZ_4M, @@ -52,6 +55,7 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm_bus_descriptor { const struct attribute_group **attr_groups; + unsigned long bus_dsm_mask; unsigned long cmd_mask; struct module *module; char *provider_name; @@ -69,7 +73,14 @@ struct nd_cmd_desc { }; struct nd_interleave_set { - u64 cookie; + /* v1.1 definition of the interleave-set-cookie algorithm */ + u64 cookie1; + /* v1.2 definition of the interleave-set-cookie algorithm */ + u64 cookie2; + /* compatibility with initial buggy Linux implementation */ + u64 altcookie; + + guid_t type_guid; }; struct nd_mapping_desc { @@ -118,7 +129,7 @@ static inline struct nd_blk_region_desc *to_blk_region_desc( } int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length); -void nvdimm_clear_from_poison_list(struct nvdimm_bus *nvdimm_bus, +void nvdimm_forget_poison(struct nvdimm_bus *nvdimm_bus, phys_addr_t start, unsigned int len); struct nvdimm_bus *nvdimm_bus_register(struct device *parent, struct nvdimm_bus_descriptor *nfit_desc); @@ -155,9 +166,11 @@ void *nd_region_provider_data(struct nd_region *nd_region); void *nd_blk_region_provider_data(struct nd_blk_region *ndbr); void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data); struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr); +unsigned long nd_blk_memremap_flags(struct nd_blk_region *ndbr); unsigned int nd_region_acquire_lane(struct nd_region *nd_region); void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); u64 nd_fletcher64(void *addr, size_t len, bool le); void nvdimm_flush(struct nd_region *nd_region); int nvdimm_has_flush(struct nd_region *nd_region); +int nvdimm_has_cache(struct nd_region *nd_region); #endif /* __LIBNVDIMM_H__ */ diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 7c273bbc5351..7dfa56ebbc6d 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -56,7 +56,6 @@ typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32, typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, u8 *); typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct ppa_addr *, int, int); typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); -typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *); typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *); typedef void (nvm_destroy_dma_pool_fn)(void *); typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t, @@ -70,7 +69,6 @@ struct nvm_dev_ops { nvm_op_set_bb_fn *set_bb_tbl; nvm_submit_io_fn *submit_io; - nvm_erase_blk_fn *erase_block; nvm_create_dma_pool_fn *create_dma_pool; nvm_destroy_dma_pool_fn *destroy_dma_pool; @@ -80,8 +78,6 @@ struct nvm_dev_ops { unsigned int max_phys_sect; }; - - #ifdef CONFIG_NVM #include <linux/blkdev.h> @@ -109,6 +105,7 @@ enum { NVM_RSP_ERR_FAILWRITE = 0x40ff, NVM_RSP_ERR_EMPTYPAGE = 0x42ff, NVM_RSP_ERR_FAILECC = 0x4281, + NVM_RSP_ERR_FAILCRC = 0x4004, NVM_RSP_WARN_HIGHECC = 0x4700, /* Device opcodes */ @@ -126,7 +123,7 @@ enum { /* NAND Access Modes */ NVM_IO_SUSPEND = 0x80, NVM_IO_SLC_MODE = 0x100, - NVM_IO_SCRAMBLE_DISABLE = 0x200, + NVM_IO_SCRAMBLE_ENABLE = 0x200, /* Block Types */ NVM_BLK_T_FREE = 0x0, @@ -202,11 +199,10 @@ struct nvm_addr_format { struct nvm_id { u8 ver_id; u8 vmnt; - u8 cgrps; u32 cap; u32 dom; struct nvm_addr_format ppaf; - struct nvm_id_group groups[4]; + struct nvm_id_group grp; } __packed; struct nvm_target { @@ -216,10 +212,6 @@ struct nvm_target { struct gendisk *disk; }; -struct nvm_tgt_instance { - struct nvm_tgt_type *tt; -}; - #define ADDR_EMPTY (~0ULL) #define NVM_VERSION_MAJOR 1 @@ -230,7 +222,6 @@ struct nvm_rq; typedef void (nvm_end_io_fn)(struct nvm_rq *); struct nvm_rq { - struct nvm_tgt_instance *ins; struct nvm_tgt_dev *dev; struct bio *bio; @@ -254,6 +245,8 @@ struct nvm_rq { u64 ppa_status; /* ppa media status */ int error; + + void *private; }; static inline struct nvm_rq *nvm_rq_from_pdu(void *pdu) @@ -272,15 +265,6 @@ enum { NVM_BLK_ST_BAD = 0x8, /* Bad block */ }; -/* system block cpu representation */ -struct nvm_sb_info { - unsigned long seqnr; - unsigned long erase_cnt; - unsigned int version; - char mmtype[NVM_MMTYPE_LEN]; - struct ppa_addr fs_ppa; -}; - /* Device generic information */ struct nvm_geo { int nr_chnls; @@ -308,6 +292,7 @@ struct nvm_geo { int sec_per_lun; }; +/* sub-device structure */ struct nvm_tgt_dev { /* Device information */ struct nvm_geo geo; @@ -329,17 +314,10 @@ struct nvm_dev { struct list_head devices; - /* Media manager */ - struct nvmm_type *mt; - void *mp; - - /* System blocks */ - struct nvm_sb_info sb; - /* Device information */ struct nvm_geo geo; - /* lower page table */ + /* lower page table */ int lps_per_blk; int *lptbl; @@ -359,6 +337,10 @@ struct nvm_dev { struct mutex mlock; spinlock_t lock; + + /* target management */ + struct list_head area_list; + struct list_head targets; }; static inline struct ppa_addr linear_to_generic_addr(struct nvm_geo *geo, @@ -391,10 +373,10 @@ static inline struct ppa_addr linear_to_generic_addr(struct nvm_geo *geo, return l; } -static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev, - struct ppa_addr r) +static inline struct ppa_addr generic_to_dev_addr(struct nvm_tgt_dev *tgt_dev, + struct ppa_addr r) { - struct nvm_geo *geo = &dev->geo; + struct nvm_geo *geo = &tgt_dev->geo; struct ppa_addr l; l.ppa = ((u64)r.g.blk) << geo->ppaf.blk_offset; @@ -407,10 +389,10 @@ static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev, return l; } -static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev, - struct ppa_addr r) +static inline struct ppa_addr dev_to_generic_addr(struct nvm_tgt_dev *tgt_dev, + struct ppa_addr r) { - struct nvm_geo *geo = &dev->geo; + struct nvm_geo *geo = &tgt_dev->geo; struct ppa_addr l; l.ppa = 0; @@ -452,15 +434,13 @@ static inline int ppa_cmp_blk(struct ppa_addr ppa1, struct ppa_addr ppa2) (ppa1.g.blk == ppa2.g.blk)); } -static inline int ppa_to_slc(struct nvm_dev *dev, int slc_pg) -{ - return dev->lptbl[slc_pg]; -} - typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); -typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *); +typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, + int flags); typedef void (nvm_tgt_exit_fn)(void *); +typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *); +typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *); struct nvm_tgt_type { const char *name; @@ -469,12 +449,15 @@ struct nvm_tgt_type { /* target entry points */ nvm_tgt_make_rq_fn *make_rq; nvm_tgt_capacity_fn *capacity; - nvm_end_io_fn *end_io; /* module-specific init/teardown */ nvm_tgt_init_fn *init; nvm_tgt_exit_fn *exit; + /* sysfs */ + nvm_tgt_sysfs_init_fn *sysfs_init; + nvm_tgt_sysfs_exit_fn *sysfs_exit; + /* For internal use */ struct list_head list; }; @@ -487,103 +470,29 @@ extern void nvm_unregister_tgt_type(struct nvm_tgt_type *); extern void *nvm_dev_dma_alloc(struct nvm_dev *, gfp_t, dma_addr_t *); extern void nvm_dev_dma_free(struct nvm_dev *, void *, dma_addr_t); -typedef int (nvmm_register_fn)(struct nvm_dev *); -typedef void (nvmm_unregister_fn)(struct nvm_dev *); - -typedef int (nvmm_create_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_create *); -typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *); -typedef int (nvmm_submit_io_fn)(struct nvm_tgt_dev *, struct nvm_rq *); -typedef int (nvmm_erase_blk_fn)(struct nvm_tgt_dev *, struct ppa_addr *, int); -typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t); -typedef void (nvmm_put_area_fn)(struct nvm_dev *, sector_t); -typedef struct ppa_addr (nvmm_trans_ppa_fn)(struct nvm_tgt_dev *, - struct ppa_addr, int); -typedef void (nvmm_part_to_tgt_fn)(struct nvm_dev *, sector_t*, int); - -enum { - TRANS_TGT_TO_DEV = 0x0, - TRANS_DEV_TO_TGT = 0x1, -}; - -struct nvmm_type { - const char *name; - unsigned int version[3]; - - nvmm_register_fn *register_mgr; - nvmm_unregister_fn *unregister_mgr; - - nvmm_create_tgt_fn *create_tgt; - nvmm_remove_tgt_fn *remove_tgt; - - nvmm_submit_io_fn *submit_io; - nvmm_erase_blk_fn *erase_blk; - - nvmm_get_area_fn *get_area; - nvmm_put_area_fn *put_area; - - nvmm_trans_ppa_fn *trans_ppa; - nvmm_part_to_tgt_fn *part_to_tgt; - - struct list_head list; -}; - -extern int nvm_register_mgr(struct nvmm_type *); -extern void nvm_unregister_mgr(struct nvmm_type *); - extern struct nvm_dev *nvm_alloc_dev(int); extern int nvm_register(struct nvm_dev *); extern void nvm_unregister(struct nvm_dev *); -extern int nvm_set_bb_tbl(struct nvm_dev *, struct ppa_addr *, int, int); extern int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr *, int, int); extern int nvm_max_phys_sects(struct nvm_tgt_dev *); extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *); -extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *); -extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *); -extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *, +extern int nvm_erase_sync(struct nvm_tgt_dev *, struct ppa_addr *, int); +extern int nvm_set_rqd_ppalist(struct nvm_tgt_dev *, struct nvm_rq *, const struct ppa_addr *, int, int); -extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *); -extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int, int); -extern int nvm_erase_blk(struct nvm_tgt_dev *, struct ppa_addr *, int); +extern void nvm_free_rqd_ppalist(struct nvm_tgt_dev *, struct nvm_rq *); extern int nvm_get_l2p_tbl(struct nvm_tgt_dev *, u64, u32, nvm_l2p_update_fn *, void *); extern int nvm_get_area(struct nvm_tgt_dev *, sector_t *, sector_t); extern void nvm_put_area(struct nvm_tgt_dev *, sector_t); -extern void nvm_end_io(struct nvm_rq *, int); -extern int nvm_submit_ppa(struct nvm_dev *, struct ppa_addr *, int, int, int, - void *, int); -extern int nvm_submit_ppa_list(struct nvm_dev *, struct ppa_addr *, int, int, - int, void *, int); +extern void nvm_end_io(struct nvm_rq *); extern int nvm_bb_tbl_fold(struct nvm_dev *, u8 *, int); -extern int nvm_get_bb_tbl(struct nvm_dev *, struct ppa_addr, u8 *); extern int nvm_get_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr, u8 *); -/* sysblk.c */ -#define NVM_SYSBLK_MAGIC 0x4E564D53 /* "NVMS" */ - -/* system block on disk representation */ -struct nvm_system_block { - __be32 magic; /* magic signature */ - __be32 seqnr; /* sequence number */ - __be32 erase_cnt; /* erase count */ - __be16 version; /* version number */ - u8 mmtype[NVM_MMTYPE_LEN]; /* media manager name */ - __be64 fs_ppa; /* PPA for media manager - * superblock */ -}; - -extern int nvm_get_sysblock(struct nvm_dev *, struct nvm_sb_info *); -extern int nvm_update_sysblock(struct nvm_dev *, struct nvm_sb_info *); -extern int nvm_init_sysblock(struct nvm_dev *, struct nvm_sb_info *); - extern int nvm_dev_factory(struct nvm_dev *, int flags); -#define nvm_for_each_lun_ppa(geo, ppa, chid, lunid) \ - for ((chid) = 0, (ppa).ppa = 0; (chid) < (geo)->nr_chnls; \ - (chid)++, (ppa).g.ch = (chid)) \ - for ((lunid) = 0; (lunid) < (geo)->luns_per_chnl; \ - (lunid)++, (ppa).g.lun = (lunid)) +extern void nvm_part_to_tgt(struct nvm_dev *, sector_t *, int); #else /* CONFIG_NVM */ struct nvm_dev_ops; diff --git a/include/linux/list.h b/include/linux/list.h index d1039ecaf94f..ae537fa46216 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -527,6 +527,19 @@ static inline void list_splice_tail_init(struct list_head *list, pos = list_next_entry(pos, member)) /** + * list_for_each_entry_from_reverse - iterate backwards over list of given type + * from the current point + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_head within the struct. + * + * Iterate backwards over list of given type, continuing from current position. + */ +#define list_for_each_entry_from_reverse(pos, head, member) \ + for (; &pos->member != (head); \ + pos = list_prev_entry(pos, member)) + +/** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index cb0ba9f2a9a2..fa7fd03cb5f9 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -44,6 +44,7 @@ struct list_lru_node { /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ struct list_lru_memcg *memcg_lrus; #endif + long nr_items; } ____cacheline_aligned_in_smp; struct list_lru { diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index b01fe1009084..87ff4f58a2f0 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -29,6 +29,11 @@ struct hlist_nulls_node { ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) + +#define hlist_nulls_entry_safe(ptr, type, member) \ + ({ typeof(ptr) ____ptr = (ptr); \ + !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \ + }) /** * ptr_is_a_nulls - Test if a ptr is a nulls * @ptr: ptr to be tested diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 9072f04db616..194991ef9347 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -23,15 +23,16 @@ #include <linux/module.h> #include <linux/ftrace.h> +#include <linux/completion.h> #if IS_ENABLED(CONFIG_LIVEPATCH) #include <asm/livepatch.h> -enum klp_state { - KLP_DISABLED, - KLP_ENABLED -}; +/* task patch states */ +#define KLP_UNDEFINED -1 +#define KLP_UNPATCHED 0 +#define KLP_PATCHED 1 /** * struct klp_func - function structure for live patching @@ -39,10 +40,29 @@ enum klp_state { * @new_func: pointer to the patched function code * @old_sympos: a hint indicating which symbol position the old function * can be found (optional) + * @immediate: patch the func immediately, bypassing safety mechanisms * @old_addr: the address of the function being patched * @kobj: kobject for sysfs resources - * @state: tracks function-level patch application state * @stack_node: list node for klp_ops func_stack list + * @old_size: size of the old function + * @new_size: size of the new function + * @patched: the func has been added to the klp_ops list + * @transition: the func is currently being applied or reverted + * + * The patched and transition variables define the func's patching state. When + * patching, a func is always in one of the following states: + * + * patched=0 transition=0: unpatched + * patched=0 transition=1: unpatched, temporary starting state + * patched=1 transition=1: patched, may be visible to some tasks + * patched=1 transition=0: patched, visible to all tasks + * + * And when unpatching, it goes in the reverse order: + * + * patched=1 transition=0: patched, visible to all tasks + * patched=1 transition=1: patched, may be visible to some tasks + * patched=0 transition=1: unpatched, temporary ending state + * patched=0 transition=0: unpatched */ struct klp_func { /* external */ @@ -56,12 +76,15 @@ struct klp_func { * in kallsyms for the given object is used. */ unsigned long old_sympos; + bool immediate; /* internal */ unsigned long old_addr; struct kobject kobj; - enum klp_state state; struct list_head stack_node; + unsigned long old_size, new_size; + bool patched; + bool transition; }; /** @@ -70,8 +93,8 @@ struct klp_func { * @funcs: function entries for functions to be patched in the object * @kobj: kobject for sysfs resources * @mod: kernel module associated with the patched object - * (NULL for vmlinux) - * @state: tracks object-level patch application state + * (NULL for vmlinux) + * @patched: the object's funcs have been added to the klp_ops list */ struct klp_object { /* external */ @@ -81,26 +104,30 @@ struct klp_object { /* internal */ struct kobject kobj; struct module *mod; - enum klp_state state; + bool patched; }; /** * struct klp_patch - patch structure for live patching * @mod: reference to the live patch module * @objs: object entries for kernel objects to be patched + * @immediate: patch all funcs immediately, bypassing safety mechanisms * @list: list node for global list of registered patches * @kobj: kobject for sysfs resources - * @state: tracks patch-level application state + * @enabled: the patch is enabled (but operation may be incomplete) + * @finish: for waiting till it is safe to remove the patch module */ struct klp_patch { /* external */ struct module *mod; struct klp_object *objs; + bool immediate; /* internal */ struct list_head list; struct kobject kobj; - enum klp_state state; + bool enabled; + struct completion finish; }; #define klp_for_each_object(patch, obj) \ @@ -123,10 +150,27 @@ void arch_klp_init_object_loaded(struct klp_patch *patch, int klp_module_coming(struct module *mod); void klp_module_going(struct module *mod); +void klp_copy_process(struct task_struct *child); +void klp_update_patch_state(struct task_struct *task); + +static inline bool klp_patch_pending(struct task_struct *task) +{ + return test_tsk_thread_flag(task, TIF_PATCH_PENDING); +} + +static inline bool klp_have_reliable_stack(void) +{ + return IS_ENABLED(CONFIG_STACKTRACE) && + IS_ENABLED(CONFIG_HAVE_RELIABLE_STACKTRACE); +} + #else /* !CONFIG_LIVEPATCH */ static inline int klp_module_coming(struct module *mod) { return 0; } -static inline void klp_module_going(struct module *mod) { } +static inline void klp_module_going(struct module *mod) {} +static inline bool klp_patch_pending(struct task_struct *task) { return false; } +static inline void klp_update_patch_state(struct task_struct *task) {} +static inline void klp_copy_process(struct task_struct *child) {} #endif /* CONFIG_LIVEPATCH */ diff --git a/include/linux/llist.h b/include/linux/llist.h index fd4ca0b4fe0f..1957635e6d5f 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -3,28 +3,33 @@ /* * Lock-less NULL terminated single linked list * - * If there are multiple producers and multiple consumers, llist_add - * can be used in producers and llist_del_all can be used in - * consumers. They can work simultaneously without lock. But - * llist_del_first can not be used here. Because llist_del_first - * depends on list->first->next does not changed if list->first is not - * changed during its operation, but llist_del_first, llist_add, - * llist_add (or llist_del_all, llist_add, llist_add) sequence in - * another consumer may violate that. - * - * If there are multiple producers and one consumer, llist_add can be - * used in producers and llist_del_all or llist_del_first can be used - * in the consumer. - * - * This can be summarized as follow: + * Cases where locking is not needed: + * If there are multiple producers and multiple consumers, llist_add can be + * used in producers and llist_del_all can be used in consumers simultaneously + * without locking. Also a single consumer can use llist_del_first while + * multiple producers simultaneously use llist_add, without any locking. + * + * Cases where locking is needed: + * If we have multiple consumers with llist_del_first used in one consumer, and + * llist_del_first or llist_del_all used in other consumers, then a lock is + * needed. This is because llist_del_first depends on list->first->next not + * changing, but without lock protection, there's no way to be sure about that + * if a preemption happens in the middle of the delete operation and on being + * preempted back, the list->first is the same as before causing the cmpxchg in + * llist_del_first to succeed. For example, while a llist_del_first operation + * is in progress in one consumer, then a llist_del_first, llist_add, + * llist_add (or llist_del_all, llist_add, llist_add) sequence in another + * consumer may cause violations. + * + * This can be summarized as follows: * * | add | del_first | del_all * add | - | - | - * del_first | | L | L * del_all | | | - * - * Where "-" stands for no lock is needed, while "L" stands for lock - * is needed. + * Where, a particular row's operation can happen concurrently with a column's + * operation, with "-" being no lock needed, while "L" being lock is needed. * * The list entries deleted via llist_del_all can be traversed with * traversing function such as llist_for_each etc. But the list @@ -88,6 +93,23 @@ static inline void init_llist_head(struct llist_head *list) container_of(ptr, type, member) /** + * member_address_is_nonnull - check whether the member address is not NULL + * @ptr: the object pointer (struct type * that contains the llist_node) + * @member: the name of the llist_node within the struct. + * + * This macro is conceptually the same as + * &ptr->member != NULL + * but it works around the fact that compilers can decide that taking a member + * address is never a NULL pointer. + * + * Real objects that start at a high address and have a member at NULL are + * unlikely to exist, but such pointers may be returned e.g. by the + * container_of() macro. + */ +#define member_address_is_nonnull(ptr, member) \ + ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0) + +/** * llist_for_each - iterate over some deleted entries of a lock-less list * @pos: the &struct llist_node to use as a loop cursor * @node: the first entry of deleted list entries @@ -105,6 +127,25 @@ static inline void init_llist_head(struct llist_head *list) for ((pos) = (node); pos; (pos) = (pos)->next) /** + * llist_for_each_safe - iterate over some deleted entries of a lock-less list + * safe against removal of list entry + * @pos: the &struct llist_node to use as a loop cursor + * @n: another &struct llist_node to use as temporary storage + * @node: the first entry of deleted list entries + * + * In general, some entries of the lock-less list can be traversed + * safely only after being deleted from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each_safe(pos, n, node) \ + for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n)) + +/** * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type * @pos: the type * to use as a loop cursor. * @node: the fist entry of deleted list entries. @@ -121,7 +162,7 @@ static inline void init_llist_head(struct llist_head *list) */ #define llist_for_each_entry(pos, node, member) \ for ((pos) = llist_entry((node), typeof(*(pos)), member); \ - &(pos)->member != NULL; \ + member_address_is_nonnull(pos, member); \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** @@ -143,7 +184,7 @@ static inline void init_llist_head(struct llist_head *list) */ #define llist_for_each_entry_safe(pos, n, node, member) \ for (pos = llist_entry((node), typeof(*pos), member); \ - &pos->member != NULL && \ + member_address_is_nonnull(pos, member) && \ (n = llist_entry(pos->member.next, typeof(*n), member), true); \ pos = n) diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index 140edab64446..05728396a1a1 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -18,6 +18,7 @@ /* Dummy declarations */ struct svc_rqst; +struct rpc_task; /* * This is the set of functions for lockd->nfsd communication @@ -43,6 +44,7 @@ struct nlmclnt_initdata { u32 nfs_version; int noresvport; struct net *net; + const struct nlmclnt_operations *nlmclnt_ops; }; /* @@ -52,8 +54,26 @@ struct nlmclnt_initdata { extern struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init); extern void nlmclnt_done(struct nlm_host *host); -extern int nlmclnt_proc(struct nlm_host *host, int cmd, - struct file_lock *fl); +/* + * NLM client operations provide a means to modify RPC processing of NLM + * requests. Callbacks receive a pointer to data passed into the call to + * nlmclnt_proc(). + */ +struct nlmclnt_operations { + /* Called on successful allocation of nlm_rqst, use for allocation or + * reference counting. */ + void (*nlmclnt_alloc_call)(void *); + + /* Called in rpc_task_prepare for unlock. A return value of true + * indicates the callback has put the task to sleep on a waitqueue + * and NLM should not call rpc_call_start(). */ + bool (*nlmclnt_unlock_prepare)(struct rpc_task*, void *); + + /* Called when the nlm_rqst is freed, callbacks should clean up here */ + void (*nlmclnt_release_call)(void *); +}; + +extern int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl, void *data); extern int lockd_up(struct net *net); extern void lockd_down(struct net *net); diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index c15373894a42..3eca67728366 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -69,6 +69,7 @@ struct nlm_host { char *h_addrbuf; /* address eyecatcher */ struct net *net; /* host net */ char nodename[UNX_MAXNODENAME + 1]; + const struct nlmclnt_operations *h_nlmclnt_ops; /* Callback ops for NLM users */ }; /* @@ -142,6 +143,7 @@ struct nlm_rqst { struct nlm_block * a_block; unsigned int a_retries; /* Retry count */ u8 a_owner[NLMCLNT_OHSIZE]; + void * a_callback_data; /* sent to nlmclnt_operations callbacks */ }; /* @@ -190,9 +192,9 @@ struct nlm_block { * Global variables */ extern const struct rpc_program nlm_program; -extern struct svc_procedure nlmsvc_procedures[]; +extern const struct svc_procedure nlmsvc_procedures[]; #ifdef CONFIG_LOCKD_V4 -extern struct svc_procedure nlmsvc_procedures4[]; +extern const struct svc_procedure nlmsvc_procedures4[]; #endif extern int nlmsvc_grace_period; extern unsigned long nlmsvc_timeout; @@ -355,7 +357,8 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp) static inline int nlm_compare_locks(const struct file_lock *fl1, const struct file_lock *fl2) { - return fl1->fl_pid == fl2->fl_pid + return file_inode(fl1->fl_file) == file_inode(fl2->fl_file) + && fl1->fl_pid == fl2->fl_pid && fl1->fl_owner == fl2->fl_owner && fl1->fl_start == fl2->fl_start && fl1->fl_end == fl2->fl_end diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index d39ed1cc5fbf..7acbecc21a40 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -95,19 +95,19 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *); -int nlmsvc_decode_void(struct svc_rqst *, __be32 *, void *); -int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); +int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); +int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); +int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); +int nlmsvc_encode_res(struct svc_rqst *, __be32 *); +int nlmsvc_decode_res(struct svc_rqst *, __be32 *); +int nlmsvc_encode_void(struct svc_rqst *, __be32 *); +int nlmsvc_decode_void(struct svc_rqst *, __be32 *); +int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); +int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); +int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); +int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index e58c88b52ce1..bf1645609225 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -23,19 +23,19 @@ -int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *); -int nlm4svc_decode_void(struct svc_rqst *, __be32 *, void *); -int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); +int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); +int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); +int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); +int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); +int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); +int nlm4svc_encode_res(struct svc_rqst *, __be32 *); +int nlm4svc_decode_res(struct svc_rqst *, __be32 *); +int nlm4svc_encode_void(struct svc_rqst *, __be32 *); +int nlm4svc_decode_void(struct svc_rqst *, __be32 *); +int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); +int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); +int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); +int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1e327bb80838..fffe49f188e6 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -361,6 +361,8 @@ static inline void lock_set_subclass(struct lockdep_map *lock, lock_set_class(lock, lock->name, lock->key, subclass, ip); } +extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip); + extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask); extern void lockdep_clear_current_reclaim_state(void); extern void lockdep_trace_alloc(gfp_t mask); @@ -411,6 +413,7 @@ static inline void lockdep_on(void) # define lock_acquire(l, s, t, r, c, n, i) do { } while (0) # define lock_release(l, n, i) do { } while (0) +# define lock_downgrade(l, i) do { } while (0) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_set_current_reclaim_state(g) do { } while (0) diff --git a/include/linux/log2.h b/include/linux/log2.h index ef3d4f67118c..c373295f359f 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -16,12 +16,6 @@ #include <linux/bitops.h> /* - * deal with unrepresentable constant logarithms - */ -extern __attribute__((const, noreturn)) -int ____ilog2_NaN(void); - -/* * non-constant log of base 2 calculators * - the arch may override these in asm/bitops.h if they can be implemented * more efficiently than using fls() and fls64() @@ -85,7 +79,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) #define ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ - (n) < 1 ? ____ilog2_NaN() : \ + (n) < 2 ? 0 : \ (n) & (1ULL << 63) ? 63 : \ (n) & (1ULL << 62) ? 62 : \ (n) & (1ULL << 61) ? 61 : \ @@ -148,10 +142,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ - (n) & (1ULL << 1) ? 1 : \ - (n) & (1ULL << 0) ? 0 : \ - ____ilog2_NaN() \ - ) : \ + 1 ) : \ (sizeof(n) <= 4) ? \ __ilog2_u32(n) : \ __ilog2_u64(n) \ diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index e58e577117b6..22b5d4e687ce 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -21,6 +21,7 @@ #include <linux/path.h> #include <linux/key.h> #include <linux/skbuff.h> +#include <rdma/ib_verbs.h> struct lsm_network_audit { int netif; @@ -45,6 +46,16 @@ struct lsm_ioctlop_audit { u16 cmd; }; +struct lsm_ibpkey_audit { + u64 subnet_prefix; + u16 pkey; +}; + +struct lsm_ibendport_audit { + char dev_name[IB_DEVICE_NAME_MAX]; + u8 port; +}; + /* Auxiliary data to use in generating the audit record. */ struct common_audit_data { char type; @@ -60,6 +71,8 @@ struct common_audit_data { #define LSM_AUDIT_DATA_DENTRY 10 #define LSM_AUDIT_DATA_IOCTL_OP 11 #define LSM_AUDIT_DATA_FILE 12 +#define LSM_AUDIT_DATA_IBPKEY 13 +#define LSM_AUDIT_DATA_IBENDPORT 14 union { struct path path; struct dentry *dentry; @@ -77,6 +90,8 @@ struct common_audit_data { char *kmod_name; struct lsm_ioctlop_audit *op; struct file *file; + struct lsm_ibpkey_audit *ibpkey; + struct lsm_ibendport_audit *ibendport; } u; /* this union contains LSM specific data */ union { diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 558adfa5c8a8..3a90febadbe2 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -8,6 +8,7 @@ * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) * Copyright (C) 2015 Intel Corporation. * Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com> + * Copyright (C) 2016 Mellanox Techonologies * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -29,6 +30,8 @@ #include <linux/rculist.h> /** + * union security_list_options - Linux Security Module hook function list + * * Security hooks for program execution operations. * * @bprm_set_creds: @@ -193,8 +196,8 @@ * @value will be set to the allocated attribute value. * @len will be set to the length of the value. * Returns 0 if @name and @value have been successfully set, - * -EOPNOTSUPP if no security attribute is needed, or - * -ENOMEM on memory allocation failure. + * -EOPNOTSUPP if no security attribute is needed, or + * -ENOMEM on memory allocation failure. * @inode_create: * Check permission to create a regular file. * @dir contains inode structure of the parent of the new file. @@ -352,8 +355,7 @@ * Return 0 if permission is granted. * @inode_getattr: * Check permission before obtaining file attributes. - * @mnt is the vfsmount where the dentry was looked up - * @dentry contains the dentry structure for the file. + * @path contains the path structure for the file. * Return 0 if permission is granted. * @inode_setxattr: * Check permission before setting the extended attributes @@ -511,8 +513,7 @@ * process @tsk. Note that this hook is sometimes called from interrupt. * Note that the fown_struct, @fown, is never outside the context of a * struct file, so the file structure (and associated security information) - * can always be obtained: - * container_of(fown, struct file, f_owner) + * can always be obtained: container_of(fown, struct file, f_owner) * @tsk contains the structure of task receiving signal. * @fown contains the file owner information. * @sig is the signal that will be sent. When 0, kernel sends SIGIO. @@ -522,7 +523,7 @@ * to receive an open file descriptor via socket IPC. * @file contains the file structure being received. * Return 0 if permission is granted. - * @file_open + * @file_open: * Save open-time permission checking state for later use upon * file_permission, and recheck access if anything has changed * since inode_permission. @@ -534,8 +535,13 @@ * manual page for definitions of the @clone_flags. * @clone_flags contains the flags indicating what should be shared. * Return 0 if permission is granted. + * @task_alloc: + * @task task being allocated. + * @clone_flags contains the flags indicating what should be shared. + * Handle allocation of task-related resources. + * Returns a zero on success, negative values on failure. * @task_free: - * @task task being freed + * @task task about to be freed. * Handle release of task-related resources. (Note that this can be called * from interrupt context.) * @cred_alloc_blank: @@ -631,10 +637,19 @@ * Check permission before getting the ioprio value of @p. * @p contains the task_struct of process. * Return 0 if permission is granted. + * @task_prlimit: + * Check permission before getting and/or setting the resource limits of + * another task. + * @cred points to the cred structure for the current task. + * @tcred points to the cred structure for the target task. + * @flags contains the LSM_PRLIMIT_* flag bits indicating whether the + * resource limits are being read, modified, or both. + * Return 0 if permission is granted. * @task_setrlimit: - * Check permission before setting the resource limits of the current - * process for @resource to @new_rlim. The old resource limit values can - * be examined by dereferencing (current->signal->rlim + resource). + * Check permission before setting the resource limits of process @p + * for @resource to @new_rlim. The old resource limit values can + * be examined by dereferencing (p->signal->rlim + resource). + * @p points to the task_struct for the target task's group leader. * @resource contains the resource whose limit is being set. * @new_rlim contains the new limits for @resource. * Return 0 if permission is granted. @@ -666,11 +681,6 @@ * @sig contains the signal value. * @secid contains the sid of the process where the signal originated * Return 0 if permission is granted. - * @task_wait: - * Check permission before allowing a process to reap a child process @p - * and collect its status information. - * @p contains the task_struct for process. - * Return 0 if permission is granted. * @task_prctl: * Check permission before performing a process control operation on the * current process. @@ -903,6 +913,26 @@ * associated with the TUN device's security structure. * @security pointer to the TUN devices's security structure. * + * Security hooks for Infiniband + * + * @ib_pkey_access: + * Check permission to access a pkey when modifing a QP. + * @subnet_prefix the subnet prefix of the port being used. + * @pkey the pkey to be accessed. + * @sec pointer to a security structure. + * @ib_endport_manage_subnet: + * Check permissions to send and receive SMPs on a end port. + * @dev_name the IB device name (i.e. mlx4_0). + * @port_num the port number. + * @sec pointer to a security structure. + * @ib_alloc_security: + * Allocate a security structure for Infiniband objects. + * @sec pointer to a security structure pointer. + * Returns 0 on success, non-zero on failure + * @ib_free_security: + * Deallocate an Infiniband security structure. + * @sec contains the security structure to be freed. + * * Security hooks for XFRM operations. * * @xfrm_policy_alloc_security: @@ -1135,7 +1165,7 @@ * @sma contains the semaphore structure. May be NULL. * @cmd contains the operation to be performed. * Return 0 if permission is granted. - * @sem_semop + * @sem_semop: * Check permissions before performing operations on members of the * semaphore set @sma. If the @alter flag is nonzero, the semaphore set * may be modified. @@ -1145,20 +1175,20 @@ * @alter contains the flag indicating whether changes are to be made. * Return 0 if permission is granted. * - * @binder_set_context_mgr + * @binder_set_context_mgr: * Check whether @mgr is allowed to be the binder context manager. * @mgr contains the task_struct for the task being registered. * Return 0 if permission is granted. - * @binder_transaction + * @binder_transaction: * Check whether @from is allowed to invoke a binder transaction call * to @to. * @from contains the task_struct for the sending task. * @to contains the task_struct for the receiving task. - * @binder_transfer_binder + * @binder_transfer_binder: * Check whether @from is allowed to transfer a binder reference to @to. * @from contains the task_struct for the sending task. * @to contains the task_struct for the receiving task. - * @binder_transfer_file + * @binder_transfer_file: * Check whether @from is allowed to transfer @file to @to. * @from contains the task_struct for the sending task. * @file contains the struct file being transferred. @@ -1206,7 +1236,7 @@ * @cred contains the credentials to use. * @ns contains the user namespace we want the capability in * @cap contains the capability <include/linux/capability.h>. - * @audit: Whether to write an audit message or not + * @audit contains whether to write an audit message or not * Return 0 if the capability is granted for @tsk. * @syslog: * Check permission before accessing the kernel message ring or changing @@ -1328,9 +1358,7 @@ * @inode we wish to get the security context of. * @ctx is a pointer in which to place the allocated security context. * @ctxlen points to the place to put the length of @ctx. - * This is the main security structure. */ - union security_list_options { int (*binder_set_context_mgr)(struct task_struct *mgr); int (*binder_transaction)(struct task_struct *from, @@ -1380,7 +1408,9 @@ union security_list_options { unsigned long kern_flags, unsigned long *set_kern_flags); int (*sb_clone_mnt_opts)(const struct super_block *oldsb, - struct super_block *newsb); + struct super_block *newsb, + unsigned long kern_flags, + unsigned long *set_kern_flags); int (*sb_parse_opts_str)(char *options, struct security_mnt_opts *opts); int (*dentry_init_security)(struct dentry *dentry, int mode, const struct qstr *name, void **ctx, @@ -1479,6 +1509,7 @@ union security_list_options { int (*file_open)(struct file *file, const struct cred *cred); int (*task_create)(unsigned long clone_flags); + int (*task_alloc)(struct task_struct *task, unsigned long clone_flags); void (*task_free)(struct task_struct *task); int (*cred_alloc_blank)(struct cred *cred, gfp_t gfp); void (*cred_free)(struct cred *cred); @@ -1500,6 +1531,8 @@ union security_list_options { int (*task_setnice)(struct task_struct *p, int nice); int (*task_setioprio)(struct task_struct *p, int ioprio); int (*task_getioprio)(struct task_struct *p); + int (*task_prlimit)(const struct cred *cred, const struct cred *tcred, + unsigned int flags); int (*task_setrlimit)(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim); int (*task_setscheduler)(struct task_struct *p); @@ -1507,7 +1540,6 @@ union security_list_options { int (*task_movememory)(struct task_struct *p); int (*task_kill)(struct task_struct *p, struct siginfo *info, int sig, u32 secid); - int (*task_wait)(struct task_struct *p); int (*task_prctl)(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); void (*task_to_inode)(struct task_struct *p, struct inode *inode); @@ -1547,8 +1579,7 @@ union security_list_options { void (*d_instantiate)(struct dentry *dentry, struct inode *inode); int (*getprocattr)(struct task_struct *p, char *name, char **value); - int (*setprocattr)(struct task_struct *p, char *name, void *value, - size_t size); + int (*setprocattr)(const char *name, void *value, size_t size); int (*ismaclabel)(const char *name); int (*secid_to_secctx)(u32 secid, char **secdata, u32 *seclen); int (*secctx_to_secid)(const char *secdata, u32 seclen, u32 *secid); @@ -1611,6 +1642,14 @@ union security_list_options { int (*tun_dev_open)(void *security); #endif /* CONFIG_SECURITY_NETWORK */ +#ifdef CONFIG_SECURITY_INFINIBAND + int (*ib_pkey_access)(void *sec, u64 subnet_prefix, u16 pkey); + int (*ib_endport_manage_subnet)(void *sec, const char *dev_name, + u8 port_num); + int (*ib_alloc_security)(void **sec); + void (*ib_free_security)(void *sec); +#endif /* CONFIG_SECURITY_INFINIBAND */ + #ifdef CONFIG_SECURITY_NETWORK_XFRM int (*xfrm_policy_alloc_security)(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, @@ -1745,6 +1784,7 @@ struct security_hook_heads { struct list_head file_receive; struct list_head file_open; struct list_head task_create; + struct list_head task_alloc; struct list_head task_free; struct list_head cred_alloc_blank; struct list_head cred_free; @@ -1763,12 +1803,12 @@ struct security_hook_heads { struct list_head task_setnice; struct list_head task_setioprio; struct list_head task_getioprio; + struct list_head task_prlimit; struct list_head task_setrlimit; struct list_head task_setscheduler; struct list_head task_getscheduler; struct list_head task_movememory; struct list_head task_kill; - struct list_head task_wait; struct list_head task_prctl; struct list_head task_to_inode; struct list_head ipc_permission; @@ -1841,6 +1881,12 @@ struct security_hook_heads { struct list_head tun_dev_attach; struct list_head tun_dev_open; #endif /* CONFIG_SECURITY_NETWORK */ +#ifdef CONFIG_SECURITY_INFINIBAND + struct list_head ib_pkey_access; + struct list_head ib_endport_manage_subnet; + struct list_head ib_alloc_security; + struct list_head ib_free_security; +#endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM struct list_head xfrm_policy_alloc_security; struct list_head xfrm_policy_clone_security; @@ -1866,7 +1912,7 @@ struct security_hook_heads { struct list_head audit_rule_match; struct list_head audit_rule_free; #endif /* CONFIG_AUDIT */ -}; +} __randomize_layout; /* * Security module hook list structure. @@ -1876,7 +1922,8 @@ struct security_hook_list { struct list_head list; struct list_head *head; union security_list_options hook; -}; + char *lsm; +} __randomize_layout; /* * Initializing a security_hook_list structure takes @@ -1888,15 +1935,10 @@ struct security_hook_list { { .head = &security_hook_heads.HEAD, .hook = { .HEAD = HOOK } } extern struct security_hook_heads security_hook_heads; +extern char *lsm_names; -static inline void security_add_hooks(struct security_hook_list *hooks, - int count) -{ - int i; - - for (i = 0; i < count; i++) - list_add_tail_rcu(&hooks[i].list, hooks[i].head); -} +extern void security_add_hooks(struct security_hook_list *hooks, int count, + char *lsm); #ifdef CONFIG_SECURITY_SELINUX_DISABLE /* @@ -1921,6 +1963,13 @@ static inline void security_delete_hooks(struct security_hook_list *hooks, } #endif /* CONFIG_SECURITY_SELINUX_DISABLE */ +/* Currently required to handle SELinux runtime hook disable. */ +#ifdef CONFIG_SECURITY_WRITABLE_HOOKS +#define __lsm_ro_after_init +#else +#define __lsm_ro_after_init __ro_after_init +#endif /* CONFIG_SECURITY_WRITABLE_HOOKS */ + extern int __init security_module_enable(const char *module); extern void __init capability_add_hooks(void); #ifdef CONFIG_SECURITY_YAMA diff --git a/include/linux/lz4.h b/include/linux/lz4.h index 6b784c59f321..394e3d9213b8 100644 --- a/include/linux/lz4.h +++ b/include/linux/lz4.h @@ -1,87 +1,648 @@ -#ifndef __LZ4_H__ -#define __LZ4_H__ -/* - * LZ4 Kernel Interface +/* LZ4 Kernel Interface * * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com> + * Copyright (C) 2016, Sven Schmidt <4sschmid@informatik.uni-hamburg.de> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. + * + * This file is based on the original header file + * for LZ4 - Fast LZ compression algorithm. + * + * LZ4 - Fast LZ compression algorithm + * Copyright (C) 2011-2016, Yann Collet. + * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are + * met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following disclaimer + * in the documentation and/or other materials provided with the + * distribution. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * You can contact the author at : + * - LZ4 homepage : http://www.lz4.org + * - LZ4 source repository : https://github.com/lz4/lz4 */ -#define LZ4_MEM_COMPRESS (16384) -#define LZ4HC_MEM_COMPRESS (262144 + (2 * sizeof(unsigned char *))) +#ifndef __LZ4_H__ +#define __LZ4_H__ + +#include <linux/types.h> +#include <linux/string.h> /* memset, memcpy */ + +/*-************************************************************************ + * CONSTANTS + **************************************************************************/ /* - * lz4_compressbound() - * Provides the maximum size that LZ4 may output in a "worst case" scenario - * (input data not compressible) + * LZ4_MEMORY_USAGE : + * Memory usage formula : N->2^N Bytes + * (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.) + * Increasing memory usage improves compression ratio + * Reduced memory usage can improve speed, due to cache effect + * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */ -static inline size_t lz4_compressbound(size_t isize) -{ - return isize + (isize / 255) + 16; -} +#define LZ4_MEMORY_USAGE 14 + +#define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */ +#define LZ4_COMPRESSBOUND(isize) (\ + (unsigned int)(isize) > (unsigned int)LZ4_MAX_INPUT_SIZE \ + ? 0 \ + : (isize) + ((isize)/255) + 16) + +#define LZ4_ACCELERATION_DEFAULT 1 +#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2) +#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE) +#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG) + +#define LZ4HC_MIN_CLEVEL 3 +#define LZ4HC_DEFAULT_CLEVEL 9 +#define LZ4HC_MAX_CLEVEL 16 + +#define LZ4HC_DICTIONARY_LOGSIZE 16 +#define LZ4HC_MAXD (1<<LZ4HC_DICTIONARY_LOGSIZE) +#define LZ4HC_MAXD_MASK (LZ4HC_MAXD - 1) +#define LZ4HC_HASH_LOG (LZ4HC_DICTIONARY_LOGSIZE - 1) +#define LZ4HC_HASHTABLESIZE (1 << LZ4HC_HASH_LOG) +#define LZ4HC_HASH_MASK (LZ4HC_HASHTABLESIZE - 1) + +/*-************************************************************************ + * STREAMING CONSTANTS AND STRUCTURES + **************************************************************************/ +#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE - 3)) + 4) +#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long)) + +#define LZ4_STREAMHCSIZE 262192 +#define LZ4_STREAMHCSIZE_SIZET (262192 / sizeof(size_t)) + +#define LZ4_STREAMDECODESIZE_U64 4 +#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * \ + sizeof(unsigned long long)) /* - * lz4_compress() - * src : source address of the original data - * src_len : size of the original data - * dst : output buffer address of the compressed data - * This requires 'dst' of size LZ4_COMPRESSBOUND. - * dst_len : is the output size, which is returned after compress done - * workmem : address of the working memory. - * This requires 'workmem' of size LZ4_MEM_COMPRESS. - * return : Success if return 0 - * Error if return (< 0) - * note : Destination buffer and workmem must be already allocated with - * the defined size. - */ -int lz4_compress(const unsigned char *src, size_t src_len, - unsigned char *dst, size_t *dst_len, void *wrkmem); - - /* - * lz4hc_compress() - * src : source address of the original data - * src_len : size of the original data - * dst : output buffer address of the compressed data - * This requires 'dst' of size LZ4_COMPRESSBOUND. - * dst_len : is the output size, which is returned after compress done - * workmem : address of the working memory. - * This requires 'workmem' of size LZ4HC_MEM_COMPRESS. - * return : Success if return 0 - * Error if return (< 0) - * note : Destination buffer and workmem must be already allocated with - * the defined size. - */ -int lz4hc_compress(const unsigned char *src, size_t src_len, - unsigned char *dst, size_t *dst_len, void *wrkmem); + * LZ4_stream_t - information structure to track an LZ4 stream. + */ +typedef struct { + uint32_t hashTable[LZ4_HASH_SIZE_U32]; + uint32_t currentOffset; + uint32_t initCheck; + const uint8_t *dictionary; + uint8_t *bufferStart; + uint32_t dictSize; +} LZ4_stream_t_internal; +typedef union { + unsigned long long table[LZ4_STREAMSIZE_U64]; + LZ4_stream_t_internal internal_donotuse; +} LZ4_stream_t; /* - * lz4_decompress() - * src : source address of the compressed data - * src_len : is the input size, whcih is returned after decompress done - * dest : output buffer address of the decompressed data - * actual_dest_len: is the size of uncompressed data, supposing it's known - * return : Success if return 0 - * Error if return (< 0) - * note : Destination buffer must be already allocated. - * slightly faster than lz4_decompress_unknownoutputsize() - */ -int lz4_decompress(const unsigned char *src, size_t *src_len, - unsigned char *dest, size_t actual_dest_len); + * LZ4_streamHC_t - information structure to track an LZ4HC stream. + */ +typedef struct { + unsigned int hashTable[LZ4HC_HASHTABLESIZE]; + unsigned short chainTable[LZ4HC_MAXD]; + /* next block to continue on current prefix */ + const unsigned char *end; + /* All index relative to this position */ + const unsigned char *base; + /* alternate base for extDict */ + const unsigned char *dictBase; + /* below that point, need extDict */ + unsigned int dictLimit; + /* below that point, no more dict */ + unsigned int lowLimit; + /* index from which to continue dict update */ + unsigned int nextToUpdate; + unsigned int compressionLevel; +} LZ4HC_CCtx_internal; +typedef union { + size_t table[LZ4_STREAMHCSIZE_SIZET]; + LZ4HC_CCtx_internal internal_donotuse; +} LZ4_streamHC_t; /* - * lz4_decompress_unknownoutputsize() - * src : source address of the compressed data - * src_len : is the input size, therefore the compressed size - * dest : output buffer address of the decompressed data - * dest_len: is the max size of the destination buffer, which is - * returned with actual size of decompressed data after - * decompress done - * return : Success if return 0 - * Error if return (< 0) - * note : Destination buffer must be already allocated. - */ -int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len, - unsigned char *dest, size_t *dest_len); + * LZ4_streamDecode_t - information structure to track an + * LZ4 stream during decompression. + * + * init this structure using LZ4_setStreamDecode (or memset()) before first use + */ +typedef struct { + const uint8_t *externalDict; + size_t extDictSize; + const uint8_t *prefixEnd; + size_t prefixSize; +} LZ4_streamDecode_t_internal; +typedef union { + unsigned long long table[LZ4_STREAMDECODESIZE_U64]; + LZ4_streamDecode_t_internal internal_donotuse; +} LZ4_streamDecode_t; + +/*-************************************************************************ + * SIZE OF STATE + **************************************************************************/ +#define LZ4_MEM_COMPRESS LZ4_STREAMSIZE +#define LZ4HC_MEM_COMPRESS LZ4_STREAMHCSIZE + +/*-************************************************************************ + * Compression Functions + **************************************************************************/ + +/** + * LZ4_compressBound() - Max. output size in worst case szenarios + * @isize: Size of the input data + * + * Return: Max. size LZ4 may output in a "worst case" szenario + * (data not compressible) + */ +static inline int LZ4_compressBound(size_t isize) +{ + return LZ4_COMPRESSBOUND(isize); +} + +/** + * LZ4_compress_default() - Compress data from source to dest + * @source: source address of the original data + * @dest: output buffer address of the compressed data + * @inputSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE + * @maxOutputSize: full or partial size of buffer 'dest' + * which must be already allocated + * @wrkmem: address of the working memory. + * This requires 'workmem' of LZ4_MEM_COMPRESS. + * + * Compresses 'sourceSize' bytes from buffer 'source' + * into already allocated 'dest' buffer of size 'maxOutputSize'. + * Compression is guaranteed to succeed if + * 'maxOutputSize' >= LZ4_compressBound(inputSize). + * It also runs faster, so it's a recommended setting. + * If the function cannot compress 'source' into a more limited 'dest' budget, + * compression stops *immediately*, and the function result is zero. + * As a consequence, 'dest' content is not valid. + * + * Return: Number of bytes written into buffer 'dest' + * (necessarily <= maxOutputSize) or 0 if compression fails + */ +int LZ4_compress_default(const char *source, char *dest, int inputSize, + int maxOutputSize, void *wrkmem); + +/** + * LZ4_compress_fast() - As LZ4_compress_default providing an acceleration param + * @source: source address of the original data + * @dest: output buffer address of the compressed data + * @inputSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE + * @maxOutputSize: full or partial size of buffer 'dest' + * which must be already allocated + * @acceleration: acceleration factor + * @wrkmem: address of the working memory. + * This requires 'workmem' of LZ4_MEM_COMPRESS. + * + * Same as LZ4_compress_default(), but allows to select an "acceleration" + * factor. The larger the acceleration value, the faster the algorithm, + * but also the lesser the compression. It's a trade-off. It can be fine tuned, + * with each successive value providing roughly +~3% to speed. + * An acceleration value of "1" is the same as regular LZ4_compress_default() + * Values <= 0 will be replaced by LZ4_ACCELERATION_DEFAULT, which is 1. + * + * Return: Number of bytes written into buffer 'dest' + * (necessarily <= maxOutputSize) or 0 if compression fails + */ +int LZ4_compress_fast(const char *source, char *dest, int inputSize, + int maxOutputSize, int acceleration, void *wrkmem); + +/** + * LZ4_compress_destSize() - Compress as much data as possible + * from source to dest + * @source: source address of the original data + * @dest: output buffer address of the compressed data + * @sourceSizePtr: will be modified to indicate how many bytes where read + * from 'source' to fill 'dest'. New value is necessarily <= old value. + * @targetDestSize: Size of buffer 'dest' which must be already allocated + * @wrkmem: address of the working memory. + * This requires 'workmem' of LZ4_MEM_COMPRESS. + * + * Reverse the logic, by compressing as much data as possible + * from 'source' buffer into already allocated buffer 'dest' + * of size 'targetDestSize'. + * This function either compresses the entire 'source' content into 'dest' + * if it's large enough, or fill 'dest' buffer completely with as much data as + * possible from 'source'. + * + * Return: Number of bytes written into 'dest' (necessarily <= targetDestSize) + * or 0 if compression fails + */ +int LZ4_compress_destSize(const char *source, char *dest, int *sourceSizePtr, + int targetDestSize, void *wrkmem); + +/*-************************************************************************ + * Decompression Functions + **************************************************************************/ + +/** + * LZ4_decompress_fast() - Decompresses data from 'source' into 'dest' + * @source: source address of the compressed data + * @dest: output buffer address of the uncompressed data + * which must be already allocated with 'originalSize' bytes + * @originalSize: is the original and therefore uncompressed size + * + * Decompresses data from 'source' into 'dest'. + * This function fully respect memory boundaries for properly formed + * compressed data. + * It is a bit faster than LZ4_decompress_safe(). + * However, it does not provide any protection against intentionally + * modified data stream (malicious input). + * Use this function in trusted environment only + * (data to decode comes from a trusted source). + * + * Return: number of bytes read from the source buffer + * or a negative result if decompression fails. + */ +int LZ4_decompress_fast(const char *source, char *dest, int originalSize); + +/** + * LZ4_decompress_safe() - Decompression protected against buffer overflow + * @source: source address of the compressed data + * @dest: output buffer address of the uncompressed data + * which must be already allocated + * @compressedSize: is the precise full size of the compressed block + * @maxDecompressedSize: is the size of 'dest' buffer + * + * Decompresses data fom 'source' into 'dest'. + * If the source stream is detected malformed, the function will + * stop decoding and return a negative result. + * This function is protected against buffer overflow exploits, + * including malicious data packets. It never writes outside output buffer, + * nor reads outside input buffer. + * + * Return: number of bytes decompressed into destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + */ +int LZ4_decompress_safe(const char *source, char *dest, int compressedSize, + int maxDecompressedSize); + +/** + * LZ4_decompress_safe_partial() - Decompress a block of size 'compressedSize' + * at position 'source' into buffer 'dest' + * @source: source address of the compressed data + * @dest: output buffer address of the decompressed data which must be + * already allocated + * @compressedSize: is the precise full size of the compressed block. + * @targetOutputSize: the decompression operation will try + * to stop as soon as 'targetOutputSize' has been reached + * @maxDecompressedSize: is the size of destination buffer + * + * This function decompresses a compressed block of size 'compressedSize' + * at position 'source' into destination buffer 'dest' + * of size 'maxDecompressedSize'. + * The function tries to stop decompressing operation as soon as + * 'targetOutputSize' has been reached, reducing decompression time. + * This function never writes outside of output buffer, + * and never reads outside of input buffer. + * It is therefore protected against malicious data packets. + * + * Return: the number of bytes decoded in the destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + * + */ +int LZ4_decompress_safe_partial(const char *source, char *dest, + int compressedSize, int targetOutputSize, int maxDecompressedSize); + +/*-************************************************************************ + * LZ4 HC Compression + **************************************************************************/ + +/** + * LZ4_compress_HC() - Compress data from `src` into `dst`, using HC algorithm + * @src: source address of the original data + * @dst: output buffer address of the compressed data + * @srcSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE + * @dstCapacity: full or partial size of buffer 'dst', + * which must be already allocated + * @compressionLevel: Recommended values are between 4 and 9, although any + * value between 1 and LZ4HC_MAX_CLEVEL will work. + * Values >LZ4HC_MAX_CLEVEL behave the same as 16. + * @wrkmem: address of the working memory. + * This requires 'wrkmem' of size LZ4HC_MEM_COMPRESS. + * + * Compress data from 'src' into 'dst', using the more powerful + * but slower "HC" algorithm. Compression is guaranteed to succeed if + * `dstCapacity >= LZ4_compressBound(srcSize) + * + * Return : the number of bytes written into 'dst' or 0 if compression fails. + */ +int LZ4_compress_HC(const char *src, char *dst, int srcSize, int dstCapacity, + int compressionLevel, void *wrkmem); + +/** + * LZ4_resetStreamHC() - Init an allocated 'LZ4_streamHC_t' structure + * @streamHCPtr: pointer to the 'LZ4_streamHC_t' structure + * @compressionLevel: Recommended values are between 4 and 9, although any + * value between 1 and LZ4HC_MAX_CLEVEL will work. + * Values >LZ4HC_MAX_CLEVEL behave the same as 16. + * + * An LZ4_streamHC_t structure can be allocated once + * and re-used multiple times. + * Use this function to init an allocated `LZ4_streamHC_t` structure + * and start a new compression. + */ +void LZ4_resetStreamHC(LZ4_streamHC_t *streamHCPtr, int compressionLevel); + +/** + * LZ4_loadDictHC() - Load a static dictionary into LZ4_streamHC + * @streamHCPtr: pointer to the LZ4HC_stream_t + * @dictionary: dictionary to load + * @dictSize: size of dictionary + * + * Use this function to load a static dictionary into LZ4HC_stream. + * Any previous data will be forgotten, only 'dictionary' + * will remain in memory. + * Loading a size of 0 is allowed. + * + * Return : dictionary size, in bytes (necessarily <= 64 KB) + */ +int LZ4_loadDictHC(LZ4_streamHC_t *streamHCPtr, const char *dictionary, + int dictSize); + +/** + * LZ4_compress_HC_continue() - Compress 'src' using data from previously + * compressed blocks as a dictionary using the HC algorithm + * @streamHCPtr: Pointer to the previous 'LZ4_streamHC_t' structure + * @src: source address of the original data + * @dst: output buffer address of the compressed data, + * which must be already allocated + * @srcSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE + * @maxDstSize: full or partial size of buffer 'dest' + * which must be already allocated + * + * These functions compress data in successive blocks of any size, using + * previous blocks as dictionary. One key assumption is that previous + * blocks (up to 64 KB) remain read-accessible while + * compressing next blocks. There is an exception for ring buffers, + * which can be smaller than 64 KB. + * Ring buffers scenario is automatically detected and handled by + * LZ4_compress_HC_continue(). + * Before starting compression, state must be properly initialized, + * using LZ4_resetStreamHC(). + * A first "fictional block" can then be designated as + * initial dictionary, using LZ4_loadDictHC() (Optional). + * Then, use LZ4_compress_HC_continue() + * to compress each successive block. Previous memory blocks + * (including initial dictionary when present) must remain accessible + * and unmodified during compression. + * 'dst' buffer should be sized to handle worst case scenarios, using + * LZ4_compressBound(), to ensure operation success. + * If, for any reason, previous data blocks can't be preserved unmodified + * in memory during next compression block, + * you must save it to a safer memory space, using LZ4_saveDictHC(). + * Return value of LZ4_saveDictHC() is the size of dictionary + * effectively saved into 'safeBuffer'. + * + * Return: Number of bytes written into buffer 'dst' or 0 if compression fails + */ +int LZ4_compress_HC_continue(LZ4_streamHC_t *streamHCPtr, const char *src, + char *dst, int srcSize, int maxDstSize); + +/** + * LZ4_saveDictHC() - Save static dictionary from LZ4HC_stream + * @streamHCPtr: pointer to the 'LZ4HC_stream_t' structure + * @safeBuffer: buffer to save dictionary to, must be already allocated + * @maxDictSize: size of 'safeBuffer' + * + * If previously compressed data block is not guaranteed + * to remain available at its memory location, + * save it into a safer place (char *safeBuffer). + * Note : you don't need to call LZ4_loadDictHC() afterwards, + * dictionary is immediately usable, you can therefore call + * LZ4_compress_HC_continue(). + * + * Return : saved dictionary size in bytes (necessarily <= maxDictSize), + * or 0 if error. + */ +int LZ4_saveDictHC(LZ4_streamHC_t *streamHCPtr, char *safeBuffer, + int maxDictSize); + +/*-********************************************* + * Streaming Compression Functions + ***********************************************/ + +/** + * LZ4_resetStream() - Init an allocated 'LZ4_stream_t' structure + * @LZ4_stream: pointer to the 'LZ4_stream_t' structure + * + * An LZ4_stream_t structure can be allocated once + * and re-used multiple times. + * Use this function to init an allocated `LZ4_stream_t` structure + * and start a new compression. + */ +void LZ4_resetStream(LZ4_stream_t *LZ4_stream); + +/** + * LZ4_loadDict() - Load a static dictionary into LZ4_stream + * @streamPtr: pointer to the LZ4_stream_t + * @dictionary: dictionary to load + * @dictSize: size of dictionary + * + * Use this function to load a static dictionary into LZ4_stream. + * Any previous data will be forgotten, only 'dictionary' + * will remain in memory. + * Loading a size of 0 is allowed. + * + * Return : dictionary size, in bytes (necessarily <= 64 KB) + */ +int LZ4_loadDict(LZ4_stream_t *streamPtr, const char *dictionary, + int dictSize); + +/** + * LZ4_saveDict() - Save static dictionary from LZ4_stream + * @streamPtr: pointer to the 'LZ4_stream_t' structure + * @safeBuffer: buffer to save dictionary to, must be already allocated + * @dictSize: size of 'safeBuffer' + * + * If previously compressed data block is not guaranteed + * to remain available at its memory location, + * save it into a safer place (char *safeBuffer). + * Note : you don't need to call LZ4_loadDict() afterwards, + * dictionary is immediately usable, you can therefore call + * LZ4_compress_fast_continue(). + * + * Return : saved dictionary size in bytes (necessarily <= dictSize), + * or 0 if error. + */ +int LZ4_saveDict(LZ4_stream_t *streamPtr, char *safeBuffer, int dictSize); + +/** + * LZ4_compress_fast_continue() - Compress 'src' using data from previously + * compressed blocks as a dictionary + * @streamPtr: Pointer to the previous 'LZ4_stream_t' structure + * @src: source address of the original data + * @dst: output buffer address of the compressed data, + * which must be already allocated + * @srcSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE + * @maxDstSize: full or partial size of buffer 'dest' + * which must be already allocated + * @acceleration: acceleration factor + * + * Compress buffer content 'src', using data from previously compressed blocks + * as dictionary to improve compression ratio. + * Important : Previous data blocks are assumed to still + * be present and unmodified ! + * If maxDstSize >= LZ4_compressBound(srcSize), + * compression is guaranteed to succeed, and runs faster. + * + * Return: Number of bytes written into buffer 'dst' or 0 if compression fails + */ +int LZ4_compress_fast_continue(LZ4_stream_t *streamPtr, const char *src, + char *dst, int srcSize, int maxDstSize, int acceleration); + +/** + * LZ4_setStreamDecode() - Instruct where to find dictionary + * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure + * @dictionary: dictionary to use + * @dictSize: size of dictionary + * + * Use this function to instruct where to find the dictionary. + * Setting a size of 0 is allowed (same effect as reset). + * + * Return: 1 if OK, 0 if error + */ +int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode, + const char *dictionary, int dictSize); + +/** + * LZ4_decompress_fast_continue() - Decompress blocks in streaming mode + * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure + * @source: source address of the compressed data + * @dest: output buffer address of the uncompressed data + * which must be already allocated + * @compressedSize: is the precise full size of the compressed block + * @maxDecompressedSize: is the size of 'dest' buffer + * + * These decoding function allows decompression of multiple blocks + * in "streaming" mode. + * Previously decoded blocks *must* remain available at the memory position + * where they were decoded (up to 64 KB) + * In the case of a ring buffers, decoding buffer must be either : + * - Exactly same size as encoding buffer, with same update rule + * (block boundaries at same positions) In which case, + * the decoding & encoding ring buffer can have any size, + * including very small ones ( < 64 KB). + * - Larger than encoding buffer, by a minimum of maxBlockSize more bytes. + * maxBlockSize is implementation dependent. + * It's the maximum size you intend to compress into a single block. + * In which case, encoding and decoding buffers do not need + * to be synchronized, and encoding ring buffer can have any size, + * including small ones ( < 64 KB). + * - _At least_ 64 KB + 8 bytes + maxBlockSize. + * In which case, encoding and decoding buffers do not need to be + * synchronized, and encoding ring buffer can have any size, + * including larger than decoding buffer. W + * Whenever these conditions are not possible, save the last 64KB of decoded + * data into a safe buffer, and indicate where it is saved + * using LZ4_setStreamDecode() + * + * Return: number of bytes decompressed into destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + */ +int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode, + const char *source, char *dest, int compressedSize, + int maxDecompressedSize); + +/** + * LZ4_decompress_fast_continue() - Decompress blocks in streaming mode + * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure + * @source: source address of the compressed data + * @dest: output buffer address of the uncompressed data + * which must be already allocated with 'originalSize' bytes + * @originalSize: is the original and therefore uncompressed size + * + * These decoding function allows decompression of multiple blocks + * in "streaming" mode. + * Previously decoded blocks *must* remain available at the memory position + * where they were decoded (up to 64 KB) + * In the case of a ring buffers, decoding buffer must be either : + * - Exactly same size as encoding buffer, with same update rule + * (block boundaries at same positions) In which case, + * the decoding & encoding ring buffer can have any size, + * including very small ones ( < 64 KB). + * - Larger than encoding buffer, by a minimum of maxBlockSize more bytes. + * maxBlockSize is implementation dependent. + * It's the maximum size you intend to compress into a single block. + * In which case, encoding and decoding buffers do not need + * to be synchronized, and encoding ring buffer can have any size, + * including small ones ( < 64 KB). + * - _At least_ 64 KB + 8 bytes + maxBlockSize. + * In which case, encoding and decoding buffers do not need to be + * synchronized, and encoding ring buffer can have any size, + * including larger than decoding buffer. W + * Whenever these conditions are not possible, save the last 64KB of decoded + * data into a safe buffer, and indicate where it is saved + * using LZ4_setStreamDecode() + * + * Return: number of bytes decompressed into destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + */ +int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode, + const char *source, char *dest, int originalSize); + +/** + * LZ4_decompress_safe_usingDict() - Same as LZ4_setStreamDecode() + * followed by LZ4_decompress_safe_continue() + * @source: source address of the compressed data + * @dest: output buffer address of the uncompressed data + * which must be already allocated + * @compressedSize: is the precise full size of the compressed block + * @maxDecompressedSize: is the size of 'dest' buffer + * @dictStart: pointer to the start of the dictionary in memory + * @dictSize: size of dictionary + * + * These decoding function works the same as + * a combination of LZ4_setStreamDecode() followed by + * LZ4_decompress_safe_continue() + * It is stand-alone, and don'tn eed a LZ4_streamDecode_t structure. + * + * Return: number of bytes decompressed into destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + */ +int LZ4_decompress_safe_usingDict(const char *source, char *dest, + int compressedSize, int maxDecompressedSize, const char *dictStart, + int dictSize); + +/** + * LZ4_decompress_fast_usingDict() - Same as LZ4_setStreamDecode() + * followed by LZ4_decompress_fast_continue() + * @source: source address of the compressed data + * @dest: output buffer address of the uncompressed data + * which must be already allocated with 'originalSize' bytes + * @originalSize: is the original and therefore uncompressed size + * @dictStart: pointer to the start of the dictionary in memory + * @dictSize: size of dictionary + * + * These decoding function works the same as + * a combination of LZ4_setStreamDecode() followed by + * LZ4_decompress_safe_continue() + * It is stand-alone, and don'tn eed a LZ4_streamDecode_t structure. + * + * Return: number of bytes decompressed into destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + */ +int LZ4_decompress_fast_usingDict(const char *source, char *dest, + int originalSize, const char *dictStart, int dictSize); + #endif diff --git a/include/linux/mISDNif.h b/include/linux/mISDNif.h index ac02c54520e9..a7330eb3ec64 100644 --- a/include/linux/mISDNif.h +++ b/include/linux/mISDNif.h @@ -554,7 +554,7 @@ _alloc_mISDN_skb(u_int prim, u_int id, u_int len, void *dp, gfp_t gfp_mask) if (!skb) return NULL; if (len) - memcpy(skb_put(skb, len), dp, len); + skb_put_data(skb, dp, len); hh = mISDN_HEAD_P(skb); hh->prim = prim; hh->id = id; diff --git a/include/linux/mailbox/brcm-message.h b/include/linux/mailbox/brcm-message.h index 6b55c938b401..c20b4843fc2d 100644 --- a/include/linux/mailbox/brcm-message.h +++ b/include/linux/mailbox/brcm-message.h @@ -16,6 +16,7 @@ enum brcm_message_type { BRCM_MESSAGE_UNKNOWN = 0, + BRCM_MESSAGE_BATCH, BRCM_MESSAGE_SPU, BRCM_MESSAGE_SBA, BRCM_MESSAGE_MAX, @@ -23,24 +24,29 @@ enum brcm_message_type { struct brcm_sba_command { u64 cmd; + u64 *cmd_dma; + dma_addr_t cmd_dma_addr; #define BRCM_SBA_CMD_TYPE_A BIT(0) #define BRCM_SBA_CMD_TYPE_B BIT(1) #define BRCM_SBA_CMD_TYPE_C BIT(2) #define BRCM_SBA_CMD_HAS_RESP BIT(3) #define BRCM_SBA_CMD_HAS_OUTPUT BIT(4) u64 flags; - dma_addr_t input; - size_t input_len; dma_addr_t resp; size_t resp_len; - dma_addr_t output; - size_t output_len; + dma_addr_t data; + size_t data_len; }; struct brcm_message { enum brcm_message_type type; union { struct { + struct brcm_message *msgs; + unsigned int msgs_queued; + unsigned int msgs_count; + } batch; + struct { struct scatterlist *src; struct scatterlist *dst; } spu; diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index a57f0dfb6db7..4055cf8cc978 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -17,8 +17,15 @@ #define MARVELL_PHY_ID_88E1116R 0x01410e40 #define MARVELL_PHY_ID_88E1510 0x01410dd0 #define MARVELL_PHY_ID_88E1540 0x01410eb0 +#define MARVELL_PHY_ID_88E1545 0x01410ea0 #define MARVELL_PHY_ID_88E3016 0x01410e60 +/* The MV88e6390 Ethernet switch contains embedded PHYs. These PHYs do + * not have a model ID. So the switch driver traps reads to the ID2 + * register and returns the switch family ID + */ +#define MARVELL_PHY_ID_88E6390 0x01410f90 + /* struct phy_device dev_flags definitions */ #define MARVELL_PHY_M1145_FLAGS_RESISTANCE 0x00000001 #define MARVELL_PHY_M1118_DNS323_LEDS 0x00000002 diff --git a/include/linux/math64.h b/include/linux/math64.h index 6e8b5b270ffe..80690c96c734 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -133,6 +133,16 @@ __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) return ret; } +#ifndef mul_u32_u32 +/* + * Many a GCC version messes this up and generates a 64x64 mult :-( + */ +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + return (u64)a * b; +} +#endif + #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__) #ifndef mul_u64_u32_shr @@ -160,9 +170,9 @@ static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) al = a; ah = a >> 32; - ret = ((u64)al * mul) >> shift; + ret = mul_u32_u32(al, mul) >> shift; if (ah) - ret += ((u64)ah * mul) << (32 - shift); + ret += mul_u32_u32(ah, mul) << (32 - shift); return ret; } @@ -186,10 +196,10 @@ static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift) a0.ll = a; b0.ll = b; - rl.ll = (u64)a0.l.low * b0.l.low; - rm.ll = (u64)a0.l.low * b0.l.high; - rn.ll = (u64)a0.l.high * b0.l.low; - rh.ll = (u64)a0.l.high * b0.l.high; + rl.ll = mul_u32_u32(a0.l.low, b0.l.low); + rm.ll = mul_u32_u32(a0.l.low, b0.l.high); + rn.ll = mul_u32_u32(a0.l.high, b0.l.low); + rh.ll = mul_u32_u32(a0.l.high, b0.l.high); /* * Each of these lines computes a 64-bit intermediate result into "c", @@ -229,8 +239,8 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } u, rl, rh; u.ll = a; - rl.ll = (u64)u.l.low * mul; - rh.ll = (u64)u.l.high * mul + rl.l.high; + rl.ll = mul_u32_u32(u.l.low, mul); + rh.ll = mul_u32_u32(u.l.high, mul) + rl.l.high; /* Bits 32-63 of the result will be in rh.l.low. */ rl.l.high = do_div(rh.ll, divisor); diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index 86c9a8b480c5..e1bc73414983 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -19,15 +19,15 @@ struct mb_cache_entry { u32 e_key; u32 e_referenced:1; u32 e_reusable:1; - /* Block number of hashed block - stable during lifetime of the entry */ - sector_t e_block; + /* User provided value - stable during lifetime of the entry */ + u64 e_value; }; struct mb_cache *mb_cache_create(int bucket_bits); void mb_cache_destroy(struct mb_cache *cache); int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, - sector_t block, bool reusable); + u64 value, bool reusable); void __mb_cache_entry_free(struct mb_cache_entry *entry); static inline int mb_cache_entry_put(struct mb_cache *cache, struct mb_cache_entry *entry) @@ -38,10 +38,9 @@ static inline int mb_cache_entry_put(struct mb_cache *cache, return 1; } -void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key, - sector_t block); +void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, - sector_t block); + u64 value); struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, u32 key); struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache, diff --git a/include/linux/mdio.h b/include/linux/mdio.h index bf9d1d750693..ca08ab16ecdc 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -10,6 +10,7 @@ #define __LINUX_MDIO_H__ #include <uapi/linux/mdio.h> +#include <linux/mod_devicetable.h> struct mii_bus; @@ -29,6 +30,7 @@ struct mdio_device { const struct dev_pm_ops *pm_ops; struct mii_bus *bus; + char modalias[MDIO_NAME_SIZE]; int (*bus_match)(struct device *dev, struct device_driver *drv); void (*device_free)(struct mdio_device *mdiodev); @@ -71,6 +73,7 @@ int mdio_device_register(struct mdio_device *mdiodev); void mdio_device_remove(struct mdio_device *mdiodev); int mdio_driver_register(struct mdio_driver *drv); void mdio_driver_unregister(struct mdio_driver *drv); +int mdio_device_bus_match(struct device *dev, struct device_driver *drv); static inline bool mdio_phy_id_is_c45(int phy_id) { @@ -130,6 +133,10 @@ extern int mdio45_nway_restart(const struct mdio_if_info *mdio); extern void mdio45_ethtool_gset_npage(const struct mdio_if_info *mdio, struct ethtool_cmd *ecmd, u32 npage_adv, u32 npage_lpa); +extern void +mdio45_ethtool_ksettings_get_npage(const struct mdio_if_info *mdio, + struct ethtool_link_ksettings *cmd, + u32 npage_adv, u32 npage_lpa); /** * mdio45_ethtool_gset - get settings for ETHTOOL_GSET @@ -147,6 +154,23 @@ static inline void mdio45_ethtool_gset(const struct mdio_if_info *mdio, mdio45_ethtool_gset_npage(mdio, ecmd, 0, 0); } +/** + * mdio45_ethtool_ksettings_get - get settings for ETHTOOL_GLINKSETTINGS + * @mdio: MDIO interface + * @cmd: Ethtool request structure + * + * Since the CSRs for auto-negotiation using next pages are not fully + * standardised, this function does not attempt to decode them. Use + * mdio45_ethtool_ksettings_get_npage() to specify advertisement bits + * from next pages. + */ +static inline void +mdio45_ethtool_ksettings_get(const struct mdio_if_info *mdio, + struct ethtool_link_ksettings *cmd) +{ + mdio45_ethtool_ksettings_get_npage(mdio, cmd, 0, 0); +} + extern int mdio_mii_ioctl(const struct mdio_if_info *mdio, struct mii_ioctl_data *mii_data, int cmd); @@ -244,7 +268,7 @@ bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr); /** - * module_mdio_driver() - Helper macro for registering mdio drivers + * mdio_module_driver() - Helper macro for registering mdio drivers * * Helper macro for MDIO drivers which do not do anything special in module * init/exit. Each module may only use this macro once, and calling it diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 5b759c9acf97..77d427974f57 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -42,6 +42,7 @@ struct memblock_type { unsigned long max; /* size of the allocated array */ phys_addr_t total_size; /* size of all regions */ struct memblock_region *regions; + char *name; }; struct memblock { @@ -56,10 +57,6 @@ struct memblock { extern struct memblock memblock; extern int memblock_debug; -#ifdef CONFIG_MOVABLE_NODE -/* If movable_node boot option specified */ -extern bool movable_node_enabled; -#endif /* CONFIG_MOVABLE_NODE */ #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK #define __init_memblock __meminit @@ -92,6 +89,7 @@ int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); +int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); ulong choose_memblock_flags(void); /* Low level functions */ @@ -167,27 +165,11 @@ void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, i != (u64)ULLONG_MAX; \ __next_reserved_mem_region(&i, p_start, p_end)) -#ifdef CONFIG_MOVABLE_NODE static inline bool memblock_is_hotpluggable(struct memblock_region *m) { return m->flags & MEMBLOCK_HOTPLUG; } -static inline bool __init_memblock movable_node_is_enabled(void) -{ - return movable_node_enabled; -} -#else -static inline bool memblock_is_hotpluggable(struct memblock_region *m) -{ - return false; -} -static inline bool movable_node_is_enabled(void) -{ - return false; -} -#endif - static inline bool memblock_is_mirror(struct memblock_region *m) { return m->flags & MEMBLOCK_MIRROR; @@ -203,6 +185,7 @@ int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); +unsigned long memblock_next_valid_pfn(unsigned long pfn, unsigned long max_pfn); /** * for_each_mem_pfn_range - early memory pfn range iterator @@ -293,7 +276,6 @@ phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align); -#ifdef CONFIG_MOVABLE_NODE /* * Set the allocation direction to bottom-up or top-down. */ @@ -311,10 +293,6 @@ static inline bool memblock_bottom_up(void) { return memblock.bottom_up; } -#else -static inline void __init memblock_set_bottom_up(bool enable) {} -static inline bool memblock_bottom_up(void) { return false; } -#endif /* Flags for memblock_alloc_base() amd __memblock_alloc_base() */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) @@ -333,6 +311,7 @@ phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); +void memblock_cap_memory_range(phys_addr_t base, phys_addr_t size); void memblock_mem_limit_remove_map(phys_addr_t limit); bool memblock_is_memory(phys_addr_t addr); int memblock_is_map_memory(phys_addr_t addr); @@ -421,12 +400,20 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) } #endif +extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr, + phys_addr_t end_addr); #else static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align) { return 0; } +static inline unsigned long memblock_reserved_memory_within(phys_addr_t start_addr, + phys_addr_t end_addr) +{ + return 0; +} + #endif /* CONFIG_HAVE_MEMBLOCK */ #endif /* __KERNEL__ */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 254698856b8f..3914e3dd6168 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -26,7 +26,8 @@ #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> -#include <linux/mmzone.h> +#include <linux/mm.h> +#include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> @@ -35,48 +36,41 @@ struct page; struct mm_struct; struct kmem_cache; -/* - * The corresponding mem_cgroup_stat_names is defined in mm/memcontrol.c, - * These two lists should keep in accord with each other. - */ -enum mem_cgroup_stat_index { - /* - * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss. - */ - MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ - MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ - MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */ - MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ - MEM_CGROUP_STAT_DIRTY, /* # of dirty pages in page cache */ - MEM_CGROUP_STAT_WRITEBACK, /* # of pages under writeback */ - MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ - MEM_CGROUP_STAT_NSTATS, - /* default hierarchy stats */ - MEMCG_KERNEL_STACK_KB = MEM_CGROUP_STAT_NSTATS, - MEMCG_SLAB_RECLAIMABLE, - MEMCG_SLAB_UNRECLAIMABLE, +/* Cgroup-specific page state, on top of universal node page state */ +enum memcg_stat_item { + MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS, + MEMCG_RSS, + MEMCG_RSS_HUGE, + MEMCG_SWAP, MEMCG_SOCK, + /* XXX: why are these zone and not node counters? */ + MEMCG_KERNEL_STACK_KB, MEMCG_NR_STAT, }; +/* Cgroup-specific events, on top of universal VM events */ +enum memcg_event_item { + MEMCG_LOW = NR_VM_EVENT_ITEMS, + MEMCG_HIGH, + MEMCG_MAX, + MEMCG_OOM, + MEMCG_NR_EVENTS, +}; + struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; int priority; unsigned int generation; }; -enum mem_cgroup_events_index { - MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */ - MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */ - MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */ - MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */ - MEM_CGROUP_EVENTS_NSTATS, - /* default hierarchy events */ - MEMCG_LOW = MEM_CGROUP_EVENTS_NSTATS, - MEMCG_HIGH, - MEMCG_MAX, - MEMCG_OOM, - MEMCG_NR_EVENTS, +#ifdef CONFIG_MEMCG + +#define MEM_CGROUP_ID_SHIFT 16 +#define MEM_CGROUP_ID_MAX USHRT_MAX + +struct mem_cgroup_id { + int id; + atomic_t ref; }; /* @@ -92,16 +86,6 @@ enum mem_cgroup_events_target { MEM_CGROUP_NTARGETS, }; -#ifdef CONFIG_MEMCG - -#define MEM_CGROUP_ID_SHIFT 16 -#define MEM_CGROUP_ID_MAX USHRT_MAX - -struct mem_cgroup_id { - int id; - atomic_t ref; -}; - struct mem_cgroup_stat_cpu { long count[MEMCG_NR_STAT]; unsigned long events[MEMCG_NR_EVENTS]; @@ -115,11 +99,16 @@ struct mem_cgroup_reclaim_iter { unsigned int generation; }; +struct lruvec_stat { + long count[NR_VM_NODE_STAT_ITEMS]; +}; + /* * per-zone information in memory controller. */ struct mem_cgroup_per_node { struct lruvec lruvec; + struct lruvec_stat __percpu *lruvec_stat; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; @@ -253,6 +242,7 @@ struct mem_cgroup { /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; enum memcg_kmem_state kmem_state; + struct list_head kmem_caches; #endif int last_scanned_node; @@ -282,17 +272,10 @@ static inline bool mem_cgroup_disabled(void) return !cgroup_subsys_enabled(memory_cgrp_subsys); } -/** - * mem_cgroup_events - count memory events against a cgroup - * @memcg: the memory cgroup - * @idx: the event index - * @nr: the number of events to account for - */ -static inline void mem_cgroup_events(struct mem_cgroup *memcg, - enum mem_cgroup_events_index idx, - unsigned int nr) +static inline void mem_cgroup_event(struct mem_cgroup *memcg, + enum memcg_event_item event) { - this_cpu_add(memcg->stat->events[idx], nr); + this_cpu_inc(memcg->stat->events[event]); cgroup_file_notify(&memcg->events_file); } @@ -378,6 +361,17 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); +static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) +{ + struct mem_cgroup_per_node *mz; + + if (mem_cgroup_disabled()) + return NULL; + + mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + return mz->memcg; +} + /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find @@ -493,8 +487,37 @@ extern int do_swap_account; void lock_page_memcg(struct page *page); void unlock_page_memcg(struct page *page); +static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx) +{ + long val = 0; + int cpu; + + for_each_possible_cpu(cpu) + val += per_cpu(memcg->stat->count[idx], cpu); + + if (val < 0) + val = 0; + + return val; +} + +static inline void __mod_memcg_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx, int val) +{ + if (!mem_cgroup_disabled()) + __this_cpu_add(memcg->stat->count[idx], val); +} + +static inline void mod_memcg_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx, int val) +{ + if (!mem_cgroup_disabled()) + this_cpu_add(memcg->stat->count[idx], val); +} + /** - * mem_cgroup_update_page_stat - update page state statistics + * mod_memcg_page_state - update page state statistics * @page: the page * @idx: page state item to account * @val: number of pages (positive or negative) @@ -505,36 +528,118 @@ void unlock_page_memcg(struct page *page); * * lock_page(page) or lock_page_memcg(page) * if (TestClearPageState(page)) - * mem_cgroup_update_page_stat(page, state, -1); + * mod_memcg_page_state(page, state, -1); * unlock_page(page) or unlock_page_memcg(page) + * + * Kernel pages are an exception to this, since they'll never move. */ -static inline void mem_cgroup_update_page_stat(struct page *page, - enum mem_cgroup_stat_index idx, int val) +static inline void __mod_memcg_page_state(struct page *page, + enum memcg_stat_item idx, int val) { - VM_BUG_ON(!(rcu_read_lock_held() || PageLocked(page))); + if (page->mem_cgroup) + __mod_memcg_state(page->mem_cgroup, idx, val); +} +static inline void mod_memcg_page_state(struct page *page, + enum memcg_stat_item idx, int val) +{ if (page->mem_cgroup) - this_cpu_add(page->mem_cgroup->stat->count[idx], val); + mod_memcg_state(page->mem_cgroup, idx, val); } -static inline void mem_cgroup_inc_page_stat(struct page *page, - enum mem_cgroup_stat_index idx) +static inline unsigned long lruvec_page_state(struct lruvec *lruvec, + enum node_stat_item idx) { - mem_cgroup_update_page_stat(page, idx, 1); + struct mem_cgroup_per_node *pn; + long val = 0; + int cpu; + + if (mem_cgroup_disabled()) + return node_page_state(lruvec_pgdat(lruvec), idx); + + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + for_each_possible_cpu(cpu) + val += per_cpu(pn->lruvec_stat->count[idx], cpu); + + if (val < 0) + val = 0; + + return val; } -static inline void mem_cgroup_dec_page_stat(struct page *page, - enum mem_cgroup_stat_index idx) +static inline void __mod_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) { - mem_cgroup_update_page_stat(page, idx, -1); + struct mem_cgroup_per_node *pn; + + __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); + if (mem_cgroup_disabled()) + return; + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + __mod_memcg_state(pn->memcg, idx, val); + __this_cpu_add(pn->lruvec_stat->count[idx], val); +} + +static inline void mod_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) +{ + struct mem_cgroup_per_node *pn; + + mod_node_page_state(lruvec_pgdat(lruvec), idx, val); + if (mem_cgroup_disabled()) + return; + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + mod_memcg_state(pn->memcg, idx, val); + this_cpu_add(pn->lruvec_stat->count[idx], val); +} + +static inline void __mod_lruvec_page_state(struct page *page, + enum node_stat_item idx, int val) +{ + struct mem_cgroup_per_node *pn; + + __mod_node_page_state(page_pgdat(page), idx, val); + if (mem_cgroup_disabled() || !page->mem_cgroup) + return; + __mod_memcg_state(page->mem_cgroup, idx, val); + pn = page->mem_cgroup->nodeinfo[page_to_nid(page)]; + __this_cpu_add(pn->lruvec_stat->count[idx], val); +} + +static inline void mod_lruvec_page_state(struct page *page, + enum node_stat_item idx, int val) +{ + struct mem_cgroup_per_node *pn; + + mod_node_page_state(page_pgdat(page), idx, val); + if (mem_cgroup_disabled() || !page->mem_cgroup) + return; + mod_memcg_state(page->mem_cgroup, idx, val); + pn = page->mem_cgroup->nodeinfo[page_to_nid(page)]; + this_cpu_add(pn->lruvec_stat->count[idx], val); } unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); -static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, - enum vm_event_item idx) +static inline void count_memcg_events(struct mem_cgroup *memcg, + enum vm_event_item idx, + unsigned long count) +{ + if (!mem_cgroup_disabled()) + this_cpu_add(memcg->stat->events[idx], count); +} + +static inline void count_memcg_page_event(struct page *page, + enum memcg_stat_item idx) +{ + if (page->mem_cgroup) + count_memcg_events(page->mem_cgroup, idx, 1); +} + +static inline void count_memcg_event_mm(struct mm_struct *mm, + enum vm_event_item idx) { struct mem_cgroup *memcg; @@ -543,20 +648,11 @@ static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!memcg)) - goto out; - - switch (idx) { - case PGFAULT: - this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]); - break; - case PGMAJFAULT: - this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]); - break; - default: - BUG(); + if (likely(memcg)) { + this_cpu_inc(memcg->stat->events[idx]); + if (idx == OOM_KILL) + cgroup_file_notify(&memcg->events_file); } -out: rcu_read_unlock(); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -575,9 +671,8 @@ static inline bool mem_cgroup_disabled(void) return true; } -static inline void mem_cgroup_events(struct mem_cgroup *memcg, - enum mem_cgroup_events_index idx, - unsigned int nr) +static inline void mem_cgroup_event(struct mem_cgroup *memcg, + enum memcg_event_item event) { } @@ -675,6 +770,11 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) return NULL; } +static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) +{ + return NULL; +} + static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { return true; @@ -739,14 +839,64 @@ static inline bool mem_cgroup_oom_synchronize(bool wait) return false; } -static inline void mem_cgroup_inc_page_stat(struct page *page, - enum mem_cgroup_stat_index idx) +static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx) +{ + return 0; +} + +static inline void __mod_memcg_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx, + int nr) +{ +} + +static inline void mod_memcg_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx, + int nr) +{ +} + +static inline void __mod_memcg_page_state(struct page *page, + enum memcg_stat_item idx, + int nr) +{ +} + +static inline void mod_memcg_page_state(struct page *page, + enum memcg_stat_item idx, + int nr) +{ +} + +static inline unsigned long lruvec_page_state(struct lruvec *lruvec, + enum node_stat_item idx) +{ + return node_page_state(lruvec_pgdat(lruvec), idx); +} + +static inline void __mod_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) { + __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } -static inline void mem_cgroup_dec_page_stat(struct page *page, - enum mem_cgroup_stat_index idx) +static inline void mod_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) { + mod_node_page_state(lruvec_pgdat(lruvec), idx, val); +} + +static inline void __mod_lruvec_page_state(struct page *page, + enum node_stat_item idx, int val) +{ + __mod_node_page_state(page_pgdat(page), idx, val); +} + +static inline void mod_lruvec_page_state(struct page *page, + enum node_stat_item idx, int val) +{ + mod_node_page_state(page_pgdat(page), idx, val); } static inline @@ -761,12 +911,119 @@ static inline void mem_cgroup_split_huge_fixup(struct page *head) { } +static inline void count_memcg_events(struct mem_cgroup *memcg, + enum vm_event_item idx, + unsigned long count) +{ +} + +static inline void count_memcg_page_event(struct page *page, + enum memcg_stat_item idx) +{ +} + static inline -void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) +void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } #endif /* CONFIG_MEMCG */ +static inline void __inc_memcg_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx) +{ + __mod_memcg_state(memcg, idx, 1); +} + +static inline void __dec_memcg_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx) +{ + __mod_memcg_state(memcg, idx, -1); +} + +static inline void __inc_memcg_page_state(struct page *page, + enum memcg_stat_item idx) +{ + __mod_memcg_page_state(page, idx, 1); +} + +static inline void __dec_memcg_page_state(struct page *page, + enum memcg_stat_item idx) +{ + __mod_memcg_page_state(page, idx, -1); +} + +static inline void __inc_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx) +{ + __mod_lruvec_state(lruvec, idx, 1); +} + +static inline void __dec_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx) +{ + __mod_lruvec_state(lruvec, idx, -1); +} + +static inline void __inc_lruvec_page_state(struct page *page, + enum node_stat_item idx) +{ + __mod_lruvec_page_state(page, idx, 1); +} + +static inline void __dec_lruvec_page_state(struct page *page, + enum node_stat_item idx) +{ + __mod_lruvec_page_state(page, idx, -1); +} + +static inline void inc_memcg_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx) +{ + mod_memcg_state(memcg, idx, 1); +} + +static inline void dec_memcg_state(struct mem_cgroup *memcg, + enum memcg_stat_item idx) +{ + mod_memcg_state(memcg, idx, -1); +} + +static inline void inc_memcg_page_state(struct page *page, + enum memcg_stat_item idx) +{ + mod_memcg_page_state(page, idx, 1); +} + +static inline void dec_memcg_page_state(struct page *page, + enum memcg_stat_item idx) +{ + mod_memcg_page_state(page, idx, -1); +} + +static inline void inc_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx) +{ + mod_lruvec_state(lruvec, idx, 1); +} + +static inline void dec_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx) +{ + mod_lruvec_state(lruvec, idx, -1); +} + +static inline void inc_lruvec_page_state(struct page *page, + enum node_stat_item idx) +{ + mod_lruvec_page_state(page, idx, 1); +} + +static inline void dec_lruvec_page_state(struct page *page, + enum node_stat_item idx) +{ + mod_lruvec_page_state(page, idx, -1); +} + #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg); @@ -829,6 +1086,7 @@ void memcg_kmem_uncharge(struct page *page, int order); #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) extern struct static_key_false memcg_kmem_enabled_key; +extern struct workqueue_struct *memcg_kmem_cache_wq; extern int memcg_nr_cache_ids; void memcg_get_cache_ids(void); @@ -857,19 +1115,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -/** - * memcg_kmem_update_page_stat - update kmem page state statistics - * @page: the page - * @idx: page state item to account - * @val: number of pages (positive or negative) - */ -static inline void memcg_kmem_update_page_stat(struct page *page, - enum mem_cgroup_stat_index idx, int val) -{ - if (memcg_kmem_enabled() && page->mem_cgroup) - this_cpu_add(page->mem_cgroup->stat->count[idx], val); -} - #else #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) @@ -892,10 +1137,6 @@ static inline void memcg_put_cache_ids(void) { } -static inline void memcg_kmem_update_page_stat(struct page *page, - enum mem_cgroup_stat_index idx, int val) -{ -} #endif /* CONFIG_MEMCG && !CONFIG_SLOB */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/memory.h b/include/linux/memory.h index 093607f90b91..b723a686fc10 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -109,9 +109,6 @@ extern void unregister_memory_notifier(struct notifier_block *nb); extern int register_memory_isolate_notifier(struct notifier_block *nb); extern void unregister_memory_isolate_notifier(struct notifier_block *nb); extern int register_new_memory(int, struct mem_section *); -extern int memory_block_change_state(struct memory_block *mem, - unsigned long to_state, - unsigned long from_state_req); #ifdef CONFIG_MEMORY_HOTREMOVE extern int unregister_memory_section(struct mem_section *); #endif diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 134a2f69c21a..c8a5056a5ae0 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -14,6 +14,20 @@ struct memory_block; struct resource; #ifdef CONFIG_MEMORY_HOTPLUG +/* + * Return page for the valid pfn only if the page is online. All pfn + * walkers which rely on the fully initialized page->flags and others + * should use this rather than pfn_valid && pfn_to_page + */ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + unsigned long ___nr = pfn_to_section_nr(pfn); \ + \ + if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\ + ___page = pfn_to_page(pfn); \ + ___page; \ +}) /* * Types for free bootmem stored in page->lru.next. These have to be in @@ -101,6 +115,12 @@ extern void __online_page_free(struct page *page); extern int try_online_node(int nid); extern bool memhp_auto_online; +/* If movable_node boot option specified */ +extern bool movable_node_enabled; +static inline bool movable_node_is_enabled(void) +{ + return movable_node_enabled; +} #ifdef CONFIG_MEMORY_HOTREMOVE extern bool is_pageblock_removable_nolock(struct page *page); @@ -109,9 +129,9 @@ extern int __remove_pages(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); #endif /* CONFIG_MEMORY_HOTREMOVE */ -/* reasonably generic interface to expand the physical pages in a zone */ -extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages); +/* reasonably generic interface to expand the physical pages */ +extern int __add_pages(int nid, unsigned long start_pfn, + unsigned long nr_pages, bool want_memblock); #ifdef CONFIG_NUMA extern int memory_add_physaddr_to_nid(u64 start); @@ -203,6 +223,14 @@ extern void set_zone_contiguous(struct zone *zone); extern void clear_zone_contiguous(struct zone *zone); #else /* ! CONFIG_MEMORY_HOTPLUG */ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + if (pfn_valid(pfn)) \ + ___page = pfn_to_page(pfn); \ + ___page; \ + }) + /* * Stub functions for when hotplug is off */ @@ -244,6 +272,10 @@ static inline void put_online_mems(void) {} static inline void mem_hotplug_begin(void) {} static inline void mem_hotplug_done(void) {} +static inline bool movable_node_is_enabled(void) +{ + return false; +} #endif /* ! CONFIG_MEMORY_HOTPLUG */ #ifdef CONFIG_MEMORY_HOTREMOVE @@ -274,18 +306,19 @@ extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource, bool online); -extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default, - bool for_device); -extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device); +extern int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock); +extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern void remove_memory(int nid, u64 start, u64 size); -extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn); +extern int sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, unsigned long map_offset); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); -extern bool zone_can_shift(unsigned long pfn, unsigned long nr_pages, - enum zone_type target, int *zone_shift); - +extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, + int online_type); +extern struct zone *default_zone_for_pfn(int nid, unsigned long pfn, + unsigned long nr_pages); #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5f4d8281832b..3a58b4be1b0c 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -142,11 +142,10 @@ bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); -extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new, - enum mpol_rebind_step step); +extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); -extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, +extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); @@ -260,8 +259,7 @@ static inline void numa_default_policy(void) } static inline void mpol_rebind_task(struct task_struct *tsk, - const nodemask_t *new, - enum mpol_rebind_step step) + const nodemask_t *new) { } @@ -269,13 +267,13 @@ static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } -static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, +static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; - return node_zonelist(0, gfp_flags); + return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h index 552cc1d61cc7..44412c9d26e1 100644 --- a/include/linux/mfd/abx500.h +++ b/include/linux/mfd/abx500.h @@ -45,7 +45,7 @@ enum abx500_adc_therm { * struct abx500_res_to_temp - defines one point in a temp to res curve. To * be used in battery packs that combines the identification resistor with a * NTC resistor. - * @temp: battery pack temperature in Celcius + * @temp: battery pack temperature in Celsius * @resist: NTC resistor net total resistance */ struct abx500_res_to_temp { diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index 12a5b396921e..e63681eb6c62 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -279,7 +279,7 @@ enum bup_vch_sel { * struct res_to_temp - defines one point in a temp to res curve. To * be used in battery packs that combines the identification resistor with a * NTC resistor. - * @temp: battery pack temperature in Celcius + * @temp: battery pack temperature in Celsius * @resist: NTC resistor net total resistance */ struct res_to_temp { @@ -290,7 +290,7 @@ struct res_to_temp { /** * struct batres_vs_temp - defines one point in a temp vs battery internal * resistance curve. - * @temp: battery pack temperature in Celcius + * @temp: battery pack temperature in Celsius * @resist: battery internal reistance in mOhm */ struct batres_vs_temp { diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 64faeeff698c..bfeecf179895 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -12,6 +12,8 @@ #define _ARIZONA_PDATA_H #include <dt-bindings/mfd/arizona.h> +#include <linux/regulator/arizona-ldo1.h> +#include <linux/regulator/arizona-micsupp.h> #define ARIZONA_GPN_DIR_MASK 0x8000 /* GPN_DIR */ #define ARIZONA_GPN_DIR_SHIFT 15 /* GPN_DIR */ @@ -76,13 +78,12 @@ struct arizona_micd_range { struct arizona_pdata { int reset; /** GPIO controlling /RESET, if any */ - int ldoena; /** GPIO controlling LODENA, if any */ /** Regulator configuration for MICVDD */ - struct regulator_init_data *micvdd; + struct arizona_micsupp_pdata micvdd; /** Regulator configuration for LDO1 */ - struct regulator_init_data *ldo1; + struct arizona_ldo1_pdata ldo1; /** If a direct 32kHz clock is provided on an MCLK specify it here */ int clk32k_src; diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index a4860bc9b73d..965b027e31b3 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -13,13 +13,14 @@ #include <linux/regmap.h> -enum { +enum axp20x_variants { AXP152_ID = 0, AXP202_ID, AXP209_ID, AXP221_ID, AXP223_ID, AXP288_ID, + AXP803_ID, AXP806_ID, AXP809_ID, NR_AXP20X_VARIANTS, @@ -118,6 +119,17 @@ enum { #define AXP806_BUS_ADDR_EXT 0xfe #define AXP806_REG_ADDR_EXT 0xff +#define AXP803_POLYPHASE_CTRL 0x14 +#define AXP803_FLDO1_V_OUT 0x1c +#define AXP803_FLDO2_V_OUT 0x1d +#define AXP803_DCDC1_V_OUT 0x20 +#define AXP803_DCDC2_V_OUT 0x21 +#define AXP803_DCDC3_V_OUT 0x22 +#define AXP803_DCDC4_V_OUT 0x23 +#define AXP803_DCDC5_V_OUT 0x24 +#define AXP803_DCDC6_V_OUT 0x25 +#define AXP803_DCDC_FREQ_CTRL 0x3b + /* Interrupt */ #define AXP152_IRQ1_EN 0x40 #define AXP152_IRQ2_EN 0x41 @@ -228,17 +240,27 @@ enum { #define AXP20X_OCV_MAX 0xf /* AXP22X specific registers */ -#define AXP22X_PMIC_ADC_H 0x56 -#define AXP22X_PMIC_ADC_L 0x57 +#define AXP22X_PMIC_TEMP_H 0x56 +#define AXP22X_PMIC_TEMP_L 0x57 #define AXP22X_TS_ADC_H 0x58 #define AXP22X_TS_ADC_L 0x59 #define AXP22X_BATLOW_THRES1 0xe6 -/* AXP288 specific registers */ +/* AXP288/AXP803 specific registers */ +#define AXP288_POWER_REASON 0x02 +#define AXP288_BC_GLOBAL 0x2c +#define AXP288_BC_VBUS_CNTL 0x2d +#define AXP288_BC_USB_STAT 0x2e +#define AXP288_BC_DET_STAT 0x2f #define AXP288_PMIC_ADC_H 0x56 #define AXP288_PMIC_ADC_L 0x57 +#define AXP288_TS_ADC_H 0x58 +#define AXP288_TS_ADC_L 0x59 +#define AXP288_GP_ADC_H 0x5a +#define AXP288_GP_ADC_L 0x5b #define AXP288_ADC_TS_PIN_CTRL 0x84 -#define AXP288_PMIC_ADC_EN 0x84 +#define AXP288_RT_BATT_V_H 0xa0 +#define AXP288_RT_BATT_V_L 0xa1 /* Fuel Gauge */ #define AXP288_FG_RDC1_REG 0xba @@ -339,6 +361,32 @@ enum { AXP809_REG_ID_MAX, }; +enum { + AXP803_DCDC1 = 0, + AXP803_DCDC2, + AXP803_DCDC3, + AXP803_DCDC4, + AXP803_DCDC5, + AXP803_DCDC6, + AXP803_DC1SW, + AXP803_ALDO1, + AXP803_ALDO2, + AXP803_ALDO3, + AXP803_DLDO1, + AXP803_DLDO2, + AXP803_DLDO3, + AXP803_DLDO4, + AXP803_ELDO1, + AXP803_ELDO2, + AXP803_ELDO3, + AXP803_FLDO1, + AXP803_FLDO2, + AXP803_RTC_LDO, + AXP803_LDO_IO0, + AXP803_LDO_IO1, + AXP803_REG_ID_MAX, +}; + /* IRQs */ enum { AXP152_IRQ_LDO0IN_CONNECT = 1, @@ -465,6 +513,43 @@ enum axp288_irqs { AXP288_IRQ_BC_USB_CHNG, }; +enum axp803_irqs { + AXP803_IRQ_ACIN_OVER_V = 1, + AXP803_IRQ_ACIN_PLUGIN, + AXP803_IRQ_ACIN_REMOVAL, + AXP803_IRQ_VBUS_OVER_V, + AXP803_IRQ_VBUS_PLUGIN, + AXP803_IRQ_VBUS_REMOVAL, + AXP803_IRQ_BATT_PLUGIN, + AXP803_IRQ_BATT_REMOVAL, + AXP803_IRQ_BATT_ENT_ACT_MODE, + AXP803_IRQ_BATT_EXIT_ACT_MODE, + AXP803_IRQ_CHARG, + AXP803_IRQ_CHARG_DONE, + AXP803_IRQ_BATT_CHG_TEMP_HIGH, + AXP803_IRQ_BATT_CHG_TEMP_HIGH_END, + AXP803_IRQ_BATT_CHG_TEMP_LOW, + AXP803_IRQ_BATT_CHG_TEMP_LOW_END, + AXP803_IRQ_BATT_ACT_TEMP_HIGH, + AXP803_IRQ_BATT_ACT_TEMP_HIGH_END, + AXP803_IRQ_BATT_ACT_TEMP_LOW, + AXP803_IRQ_BATT_ACT_TEMP_LOW_END, + AXP803_IRQ_DIE_TEMP_HIGH, + AXP803_IRQ_GPADC, + AXP803_IRQ_LOW_PWR_LVL1, + AXP803_IRQ_LOW_PWR_LVL2, + AXP803_IRQ_TIMER, + AXP803_IRQ_PEK_RIS_EDGE, + AXP803_IRQ_PEK_FAL_EDGE, + AXP803_IRQ_PEK_SHORT, + AXP803_IRQ_PEK_LONG, + AXP803_IRQ_PEK_OVER_OFF, + AXP803_IRQ_GPIO1_INPUT, + AXP803_IRQ_GPIO0_INPUT, + AXP803_IRQ_BC_USB_CHNG, + AXP803_IRQ_MV_CHNG, +}; + enum axp806_irqs { AXP806_IRQ_DIE_TEMP_HIGH_LV1, AXP806_IRQ_DIE_TEMP_HIGH_LV2, @@ -515,14 +600,10 @@ enum axp809_irqs { AXP809_IRQ_GPIO0_INPUT, }; -#define AXP288_TS_ADC_H 0x58 -#define AXP288_TS_ADC_L 0x59 -#define AXP288_GP_ADC_H 0x5a -#define AXP288_GP_ADC_L 0x5b - struct axp20x_dev { struct device *dev; int irq; + unsigned long irq_flags; struct regmap *regmap; struct regmap_irq_chip_data *regmap_irqc; long variant; @@ -532,35 +613,6 @@ struct axp20x_dev { const struct regmap_irq_chip *regmap_irq_chip; }; -#define BATTID_LEN 64 -#define OCV_CURVE_SIZE 32 -#define MAX_THERM_CURVE_SIZE 25 -#define PD_DEF_MIN_TEMP 0 -#define PD_DEF_MAX_TEMP 55 - -struct axp20x_fg_pdata { - char battid[BATTID_LEN + 1]; - int design_cap; - int min_volt; - int max_volt; - int max_temp; - int min_temp; - int cap1; - int cap0; - int rdc1; - int rdc0; - int ocv_curve[OCV_CURVE_SIZE]; - int tcsz; - int thermistor_curve[MAX_THERM_CURVE_SIZE][2]; -}; - -struct axp20x_chrg_pdata { - int max_cc; - int max_cv; - int def_cc; - int def_cv; -}; - struct axp288_extcon_pdata { /* GPIO pin control to switch D+/D- lines b/w PMIC and SOC */ struct gpio_desc *gpio_mux_cntl; @@ -611,7 +663,7 @@ int axp20x_match_device(struct axp20x_dev *axp20x); int axp20x_device_probe(struct axp20x_dev *axp20x); /** - * axp20x_device_probe(): Remove a axp20x device + * axp20x_device_remove(): Remove a axp20x device * * @axp20x: axp20x device to remove * diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index f62043a75f43..4e887ba22635 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -35,10 +35,11 @@ * Max bus-specific overhead incurred by request/responses. * I2C requires 1 additional byte for requests. * I2C requires 2 additional bytes for responses. + * SPI requires up to 32 additional bytes for responses. * */ #define EC_PROTO_VERSION_UNKNOWN 0 #define EC_MAX_REQUEST_OVERHEAD 1 -#define EC_MAX_RESPONSE_OVERHEAD 2 +#define EC_MAX_RESPONSE_OVERHEAD 32 /* * Command interface between EC and AP, for LPC, I2C and SPI interfaces. @@ -103,6 +104,7 @@ struct cros_ec_command { * @din_size: size of din buffer to allocate (zero to use static din) * @dout_size: size of dout buffer to allocate (zero to use static dout) * @wake_enabled: true if this device can wake the system from sleep + * @suspended: true if this device had been suspended * @cmd_xfer: send command to EC and get response * Returns the number of bytes received if the communication succeeded, but * that doesn't mean the EC was happy with the command. The caller @@ -136,6 +138,7 @@ struct cros_ec_device { int din_size; int dout_size; bool wake_enabled; + bool suspended; int (*cmd_xfer)(struct cros_ec_device *ec, struct cros_ec_command *msg); int (*pkt_xfer)(struct cros_ec_device *ec, @@ -146,6 +149,7 @@ struct cros_ec_device { struct ec_response_get_next_event event_data; int event_size; + u32 host_event_wake_mask; }; /** @@ -169,6 +173,8 @@ struct cros_ec_platform { u16 cmd_offset; }; +struct cros_ec_debugfs; + /* * struct cros_ec_dev - ChromeOS EC device entry point * @@ -176,6 +182,7 @@ struct cros_ec_platform { * @cdev: Character device structure in /dev * @ec_dev: cros_ec_device structure to talk to the physical device * @dev: pointer to the platform device + * @debug_info: cros_ec_debugfs structure for debugging information * @cmd_offset: offset to apply for each command. */ struct cros_ec_dev { @@ -183,6 +190,7 @@ struct cros_ec_dev { struct cdev cdev; struct cros_ec_device *ec_dev; struct device *dev; + struct cros_ec_debugfs *debug_info; u16 cmd_offset; u32 features[2]; }; @@ -292,14 +300,44 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev); * cros_ec_get_next_event - Fetch next event from the ChromeOS EC * * @ec_dev: Device to fetch event from + * @wake_event: Pointer to a bool set to true upon return if the event might be + * treated as a wake event. Ignored if null. * * Returns: 0 on success, Linux error number on failure */ -int cros_ec_get_next_event(struct cros_ec_device *ec_dev); +int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); + +/** + * cros_ec_get_host_event - Return a mask of event set by the EC. + * + * When MKBP is supported, when the EC raises an interrupt, + * We collect the events raised and call the functions in the ec notifier. + * + * This function is a helper to know which events are raised. + */ +u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); /* sysfs stuff */ extern struct attribute_group cros_ec_attr_group; extern struct attribute_group cros_ec_lightbar_attr_group; extern struct attribute_group cros_ec_vbc_attr_group; +/* ACPI GPE handler */ +#ifdef CONFIG_ACPI + +int cros_ec_acpi_install_gpe_handler(struct device *dev); +void cros_ec_acpi_remove_gpe_handler(void); +void cros_ec_acpi_clear_gpe(void); + +#else /* CONFIG_ACPI */ + +static inline int cros_ec_acpi_install_gpe_handler(struct device *dev) +{ + return -ENODEV; +} +static inline void cros_ec_acpi_remove_gpe_handler(void) {} +static inline void cros_ec_acpi_clear_gpe(void) {} + +#endif /* CONFIG_ACPI */ + #endif /* __LINUX_MFD_CROS_EC_H */ diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 1683003603f3..190c8f4afa02 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -625,6 +625,10 @@ struct ec_params_get_cmd_versions { uint8_t cmd; /* Command to check */ } __packed; +struct ec_params_get_cmd_versions_v1 { + uint16_t cmd; /* Command to check */ +} __packed; + struct ec_response_get_cmd_versions { /* * Mask of supported versions; use EC_VER_MASK() to compare with a @@ -1158,13 +1162,20 @@ struct lightbar_params_v1 { struct rgb_s color[8]; /* 0-3 are Google colors */ } __packed; +/* Lightbar program */ +#define EC_LB_PROG_LEN 192 +struct lightbar_program { + uint8_t size; + uint8_t data[EC_LB_PROG_LEN]; +}; + struct ec_params_lightbar { uint8_t cmd; /* Command (see enum lightbar_command) */ union { struct { /* no args */ } dump, off, on, init, get_seq, get_params_v0, get_params_v1, - version, get_brightness, get_demo; + version, get_brightness, get_demo, suspend, resume; struct { uint8_t num; @@ -1182,8 +1193,13 @@ struct ec_params_lightbar { uint8_t led; } get_rgb; + struct { + uint8_t enable; + } manual_suspend_ctrl; + struct lightbar_params_v0 set_params_v0; struct lightbar_params_v1 set_params_v1; + struct lightbar_program set_program; }; } __packed; @@ -1216,7 +1232,8 @@ struct ec_response_lightbar { struct { /* no return params */ } off, on, init, set_brightness, seq, reg, set_rgb, - demo, set_params_v0, set_params_v1; + demo, set_params_v0, set_params_v1, + set_program, manual_suspend_ctrl, suspend, resume; }; } __packed; @@ -1240,6 +1257,10 @@ enum lightbar_command { LIGHTBAR_CMD_GET_DEMO = 15, LIGHTBAR_CMD_GET_PARAMS_V1 = 16, LIGHTBAR_CMD_SET_PARAMS_V1 = 17, + LIGHTBAR_CMD_SET_PROGRAM = 18, + LIGHTBAR_CMD_MANUAL_SUSPEND_CTRL = 19, + LIGHTBAR_CMD_SUSPEND = 20, + LIGHTBAR_CMD_RESUME = 21, LIGHTBAR_NUM_CMDS }; @@ -1441,7 +1462,8 @@ enum motionsensor_type { MOTIONSENSE_TYPE_PROX = 3, MOTIONSENSE_TYPE_LIGHT = 4, MOTIONSENSE_TYPE_ACTIVITY = 5, - MOTIONSENSE_TYPE_MAX + MOTIONSENSE_TYPE_BARO = 6, + MOTIONSENSE_TYPE_MAX, }; /* List of motion sensor locations. */ @@ -1839,18 +1861,69 @@ struct ec_response_tmp006_get_raw { * * Returns raw data for keyboard cols; see ec_response_mkbp_info.cols for * expected response size. + * + * NOTE: This has been superseded by EC_CMD_MKBP_GET_NEXT_EVENT. If you wish + * to obtain the instantaneous state, use EC_CMD_MKBP_INFO with the type + * EC_MKBP_INFO_CURRENT and event EC_MKBP_EVENT_KEY_MATRIX. */ #define EC_CMD_MKBP_STATE 0x60 -/* Provide information about the matrix : number of rows and columns */ +/* + * Provide information about various MKBP things. See enum ec_mkbp_info_type. + */ #define EC_CMD_MKBP_INFO 0x61 struct ec_response_mkbp_info { uint32_t rows; uint32_t cols; - uint8_t switches; + /* Formerly "switches", which was 0. */ + uint8_t reserved; } __packed; +struct ec_params_mkbp_info { + uint8_t info_type; + uint8_t event_type; +} __packed; + +enum ec_mkbp_info_type { + /* + * Info about the keyboard matrix: number of rows and columns. + * + * Returns struct ec_response_mkbp_info. + */ + EC_MKBP_INFO_KBD = 0, + + /* + * For buttons and switches, info about which specifically are + * supported. event_type must be set to one of the values in enum + * ec_mkbp_event. + * + * For EC_MKBP_EVENT_BUTTON and EC_MKBP_EVENT_SWITCH, returns a 4 byte + * bitmask indicating which buttons or switches are present. See the + * bit inidices below. + */ + EC_MKBP_INFO_SUPPORTED = 1, + + /* + * Instantaneous state of buttons and switches. + * + * event_type must be set to one of the values in enum ec_mkbp_event. + * + * For EC_MKBP_EVENT_KEY_MATRIX, returns uint8_t key_matrix[13] + * indicating the current state of the keyboard matrix. + * + * For EC_MKBP_EVENT_HOST_EVENT, return uint32_t host_event, the raw + * event state. + * + * For EC_MKBP_EVENT_BUTTON, returns uint32_t buttons, indicating the + * state of supported buttons. + * + * For EC_MKBP_EVENT_SWITCH, returns uint32_t switches, indicating the + * state of supported switches. + */ + EC_MKBP_INFO_CURRENT = 2, +}; + /* Simulate key press */ #define EC_CMD_MKBP_SIMULATE_KEY 0x62 @@ -1983,6 +2056,15 @@ enum ec_mkbp_event { /* New Sensor FIFO data. The event data is fifo_info structure. */ EC_MKBP_EVENT_SENSOR_FIFO = 2, + /* The state of the non-matrixed buttons have changed. */ + EC_MKBP_EVENT_BUTTON = 3, + + /* The state of the switches have changed. */ + EC_MKBP_EVENT_SWITCH = 4, + + /* EC sent a sysrq command */ + EC_MKBP_EVENT_SYSRQ = 6, + /* Number of MKBP events */ EC_MKBP_EVENT_COUNT, }; @@ -1992,6 +2074,10 @@ union ec_response_get_next_data { /* Unaligned */ uint32_t host_event; + + uint32_t buttons; + uint32_t switches; + uint32_t sysrq; } __packed; struct ec_response_get_next_event { @@ -2000,6 +2086,16 @@ struct ec_response_get_next_event { union ec_response_get_next_data data; } __packed; +/* Bit indices for buttons and switches.*/ +/* Buttons */ +#define EC_MKBP_POWER_BUTTON 0 +#define EC_MKBP_VOL_UP 1 +#define EC_MKBP_VOL_DOWN 2 + +/* Switches */ +#define EC_MKBP_LID_OPEN 0 +#define EC_MKBP_TABLET_MODE 1 + /*****************************************************************************/ /* Temperature sensor commands */ @@ -2210,13 +2306,28 @@ struct ec_params_charge_control { #define EC_CMD_CONSOLE_SNAPSHOT 0x97 /* - * Read next chunk of data from saved snapshot. + * Read data from the saved snapshot. If the subcmd parameter is + * CONSOLE_READ_NEXT, this will return data starting from the beginning of + * the latest snapshot. If it is CONSOLE_READ_RECENT, it will start from the + * end of the previous snapshot. + * + * The params are only looked at in version >= 1 of this command. Prior + * versions will just default to CONSOLE_READ_NEXT behavior. * * Response is null-terminated string. Empty string, if there is no more * remaining output. */ #define EC_CMD_CONSOLE_READ 0x98 +enum ec_console_read_subcmd { + CONSOLE_READ_NEXT = 0, + CONSOLE_READ_RECENT +}; + +struct ec_params_console_read_v1 { + uint8_t subcmd; /* enum ec_console_read_subcmd */ +} __packed; + /*****************************************************************************/ /* @@ -2477,6 +2588,20 @@ struct ec_params_ext_power_current_limit { uint32_t limit; /* in mA */ } __packed; +/* Inform the EC when entering a sleep state */ +#define EC_CMD_HOST_SLEEP_EVENT 0xa9 + +enum host_sleep_event { + HOST_SLEEP_EVENT_S3_SUSPEND = 1, + HOST_SLEEP_EVENT_S3_RESUME = 2, + HOST_SLEEP_EVENT_S0IX_SUSPEND = 3, + HOST_SLEEP_EVENT_S0IX_RESUME = 4 +}; + +struct ec_params_host_sleep_event { + uint8_t sleep_event; +} __packed; + /*****************************************************************************/ /* Smart battery pass-through */ diff --git a/include/linux/mfd/cros_ec_lpc_mec.h b/include/linux/mfd/cros_ec_lpc_mec.h new file mode 100644 index 000000000000..176496ddc66c --- /dev/null +++ b/include/linux/mfd/cros_ec_lpc_mec.h @@ -0,0 +1,90 @@ +/* + * cros_ec_lpc_mec - LPC variant I/O for Microchip EC + * + * Copyright (C) 2016 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This driver uses the Chrome OS EC byte-level message-based protocol for + * communicating the keyboard state (which keys are pressed) from a keyboard EC + * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, + * but everything else (including deghosting) is done here. The main + * motivation for this is to keep the EC firmware as simple as possible, since + * it cannot be easily upgraded and EC flash/IRAM space is relatively + * expensive. + */ + +#ifndef __LINUX_MFD_CROS_EC_MEC_H +#define __LINUX_MFD_CROS_EC_MEC_H + +#include <linux/mfd/cros_ec_commands.h> + +enum cros_ec_lpc_mec_emi_access_mode { + /* 8-bit access */ + ACCESS_TYPE_BYTE = 0x0, + /* 16-bit access */ + ACCESS_TYPE_WORD = 0x1, + /* 32-bit access */ + ACCESS_TYPE_LONG = 0x2, + /* + * 32-bit access, read or write of MEC_EMI_EC_DATA_B3 causes the + * EC data register to be incremented. + */ + ACCESS_TYPE_LONG_AUTO_INCREMENT = 0x3, +}; + +enum cros_ec_lpc_mec_io_type { + MEC_IO_READ, + MEC_IO_WRITE, +}; + +/* Access IO ranges 0x800 thru 0x9ff using EMI interface instead of LPC */ +#define MEC_EMI_RANGE_START EC_HOST_CMD_REGION0 +#define MEC_EMI_RANGE_END (EC_LPC_ADDR_MEMMAP + EC_MEMMAP_SIZE) + +/* EMI registers are relative to base */ +#define MEC_EMI_BASE 0x800 +#define MEC_EMI_HOST_TO_EC (MEC_EMI_BASE + 0) +#define MEC_EMI_EC_TO_HOST (MEC_EMI_BASE + 1) +#define MEC_EMI_EC_ADDRESS_B0 (MEC_EMI_BASE + 2) +#define MEC_EMI_EC_ADDRESS_B1 (MEC_EMI_BASE + 3) +#define MEC_EMI_EC_DATA_B0 (MEC_EMI_BASE + 4) +#define MEC_EMI_EC_DATA_B1 (MEC_EMI_BASE + 5) +#define MEC_EMI_EC_DATA_B2 (MEC_EMI_BASE + 6) +#define MEC_EMI_EC_DATA_B3 (MEC_EMI_BASE + 7) + +/* + * cros_ec_lpc_mec_init + * + * Initialize MEC I/O. + */ +void cros_ec_lpc_mec_init(void); + +/* + * cros_ec_lpc_mec_destroy + * + * Cleanup MEC I/O. + */ +void cros_ec_lpc_mec_destroy(void); + +/** + * cros_ec_lpc_io_bytes_mec - Read / write bytes to MEC EMI port + * + * @io_type: MEC_IO_READ or MEC_IO_WRITE, depending on request + * @offset: Base read / write address + * @length: Number of bytes to read / write + * @buf: Destination / source buffer + * + * @return 8-bit checksum of all bytes read / written + */ +u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type, + unsigned int offset, unsigned int length, u8 *buf); + +#endif /* __LINUX_MFD_CROS_EC_MEC_H */ diff --git a/include/linux/mfd/cros_ec_lpc_reg.h b/include/linux/mfd/cros_ec_lpc_reg.h new file mode 100644 index 000000000000..5560bef63c2b --- /dev/null +++ b/include/linux/mfd/cros_ec_lpc_reg.h @@ -0,0 +1,61 @@ +/* + * cros_ec_lpc_reg - LPC access to the Chrome OS Embedded Controller + * + * Copyright (C) 2016 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This driver uses the Chrome OS EC byte-level message-based protocol for + * communicating the keyboard state (which keys are pressed) from a keyboard EC + * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, + * but everything else (including deghosting) is done here. The main + * motivation for this is to keep the EC firmware as simple as possible, since + * it cannot be easily upgraded and EC flash/IRAM space is relatively + * expensive. + */ + +#ifndef __LINUX_MFD_CROS_EC_REG_H +#define __LINUX_MFD_CROS_EC_REG_H + +/** + * cros_ec_lpc_read_bytes - Read bytes from a given LPC-mapped address. + * Returns 8-bit checksum of all bytes read. + * + * @offset: Base read address + * @length: Number of bytes to read + * @dest: Destination buffer + */ +u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest); + +/** + * cros_ec_lpc_write_bytes - Write bytes to a given LPC-mapped address. + * Returns 8-bit checksum of all bytes written. + * + * @offset: Base write address + * @length: Number of bytes to write + * @msg: Write data buffer + */ +u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg); + +/** + * cros_ec_lpc_reg_init + * + * Initialize register I/O. + */ +void cros_ec_lpc_reg_init(void); + +/** + * cros_ec_lpc_reg_destroy + * + * Cleanup reg I/O. + */ +void cros_ec_lpc_reg_destroy(void); + +#endif /* __LINUX_MFD_CROS_EC_REG_H */ diff --git a/include/linux/mfd/da9062/core.h b/include/linux/mfd/da9062/core.h index 376ba84366a0..74d33a01ddae 100644 --- a/include/linux/mfd/da9062/core.h +++ b/include/linux/mfd/da9062/core.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015 Dialog Semiconductor Ltd. + * Copyright (C) 2015-2017 Dialog Semiconductor * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -18,7 +18,31 @@ #include <linux/interrupt.h> #include <linux/mfd/da9062/registers.h> -/* Interrupts */ +enum da9062_compatible_types { + COMPAT_TYPE_DA9061 = 1, + COMPAT_TYPE_DA9062, +}; + +enum da9061_irqs { + /* IRQ A */ + DA9061_IRQ_ONKEY, + DA9061_IRQ_WDG_WARN, + DA9061_IRQ_SEQ_RDY, + /* IRQ B*/ + DA9061_IRQ_TEMP, + DA9061_IRQ_LDO_LIM, + DA9061_IRQ_DVC_RDY, + DA9061_IRQ_VDD_WARN, + /* IRQ C */ + DA9061_IRQ_GPI0, + DA9061_IRQ_GPI1, + DA9061_IRQ_GPI2, + DA9061_IRQ_GPI3, + DA9061_IRQ_GPI4, + + DA9061_NUM_IRQ, +}; + enum da9062_irqs { /* IRQ A */ DA9062_IRQ_ONKEY, @@ -45,6 +69,7 @@ struct da9062 { struct device *dev; struct regmap *regmap; struct regmap_irq_chip_data *regmap_irq; + enum da9062_compatible_types chip_type; }; #endif /* __MFD_DA9062_CORE_H__ */ diff --git a/include/linux/mfd/da9062/registers.h b/include/linux/mfd/da9062/registers.h index 97790d1b02c5..18d576aed902 100644 --- a/include/linux/mfd/da9062/registers.h +++ b/include/linux/mfd/da9062/registers.h @@ -1,6 +1,5 @@ /* - * registers.h - REGISTERS H for DA9062 - * Copyright (C) 2015 Dialog Semiconductor Ltd. + * Copyright (C) 2015-2017 Dialog Semiconductor * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -18,6 +17,8 @@ #define DA9062_PMIC_DEVICE_ID 0x62 #define DA9062_PMIC_VARIANT_MRC_AA 0x01 +#define DA9062_PMIC_VARIANT_VRC_DA9061 0x01 +#define DA9062_PMIC_VARIANT_VRC_DA9062 0x02 #define DA9062_I2C_PAGE_SEL_SHIFT 1 diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 956caa0628f5..5aacdb017a9f 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -25,8 +25,11 @@ struct intel_soc_pmic { int irq; struct regmap *regmap; struct regmap_irq_chip_data *irq_chip_data; - struct regmap_irq_chip_data *irq_chip_data_level2; struct regmap_irq_chip_data *irq_chip_data_tmu; + struct regmap_irq_chip_data *irq_chip_data_bcu; + struct regmap_irq_chip_data *irq_chip_data_adc; + struct regmap_irq_chip_data *irq_chip_data_chgr; + struct regmap_irq_chip_data *irq_chip_data_crit; struct device *dev; }; diff --git a/include/linux/mfd/intel_bxtwc.h b/include/linux/mfd/intel_soc_pmic_bxtwc.h index 1a0ee9d6efe9..0c351bc85d2d 100644 --- a/include/linux/mfd/intel_bxtwc.h +++ b/include/linux/mfd/intel_soc_pmic_bxtwc.h @@ -1,5 +1,5 @@ /* - * intel_bxtwc.h - Header file for Intel Broxton Whiskey Cove PMIC + * Header file for Intel Broxton Whiskey Cove PMIC * * Copyright (C) 2015 Intel Corporation. All rights reserved. * @@ -13,8 +13,6 @@ * more details. */ -#include <linux/mfd/intel_soc_pmic.h> - #ifndef __INTEL_BXTWC_H__ #define __INTEL_BXTWC_H__ diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h new file mode 100644 index 000000000000..d0c91ba65525 --- /dev/null +++ b/include/linux/mfd/lp87565.h @@ -0,0 +1,270 @@ +/* + * Functions to access LP87565 power management chip. + * + * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + */ + +#ifndef __LINUX_MFD_LP87565_H +#define __LINUX_MFD_LP87565_H + +#include <linux/i2c.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> + +enum lp87565_device_type { + LP87565_DEVICE_TYPE_UNKNOWN = 0, + LP87565_DEVICE_TYPE_LP87565_Q1, +}; + +/* All register addresses */ +#define LP87565_REG_DEV_REV 0X00 +#define LP87565_REG_OTP_REV 0X01 +#define LP87565_REG_BUCK0_CTRL_1 0X02 +#define LP87565_REG_BUCK0_CTRL_2 0X03 + +#define LP87565_REG_BUCK1_CTRL_1 0X04 +#define LP87565_REG_BUCK1_CTRL_2 0X05 + +#define LP87565_REG_BUCK2_CTRL_1 0X06 +#define LP87565_REG_BUCK2_CTRL_2 0X07 + +#define LP87565_REG_BUCK3_CTRL_1 0X08 +#define LP87565_REG_BUCK3_CTRL_2 0X09 + +#define LP87565_REG_BUCK0_VOUT 0X0A +#define LP87565_REG_BUCK0_FLOOR_VOUT 0X0B + +#define LP87565_REG_BUCK1_VOUT 0X0C +#define LP87565_REG_BUCK1_FLOOR_VOUT 0X0D + +#define LP87565_REG_BUCK2_VOUT 0X0E +#define LP87565_REG_BUCK2_FLOOR_VOUT 0X0F + +#define LP87565_REG_BUCK3_VOUT 0X10 +#define LP87565_REG_BUCK3_FLOOR_VOUT 0X11 + +#define LP87565_REG_BUCK0_DELAY 0X12 +#define LP87565_REG_BUCK1_DELAY 0X13 + +#define LP87565_REG_BUCK2_DELAY 0X14 +#define LP87565_REG_BUCK3_DELAY 0X15 + +#define LP87565_REG_GPO2_DELAY 0X16 +#define LP87565_REG_GPO3_DELAY 0X17 +#define LP87565_REG_RESET 0X18 +#define LP87565_REG_CONFIG 0X19 + +#define LP87565_REG_INT_TOP_1 0X1A +#define LP87565_REG_INT_TOP_2 0X1B + +#define LP87565_REG_INT_BUCK_0_1 0X1C +#define LP87565_REG_INT_BUCK_2_3 0X1D +#define LP87565_REG_TOP_STAT 0X1E +#define LP87565_REG_BUCK_0_1_STAT 0X1F +#define LP87565_REG_BUCK_2_3_STAT 0x20 + +#define LP87565_REG_TOP_MASK_1 0x21 +#define LP87565_REG_TOP_MASK_2 0x22 + +#define LP87565_REG_BUCK_0_1_MASK 0x23 +#define LP87565_REG_BUCK_2_3_MASK 0x24 +#define LP87565_REG_SEL_I_LOAD 0x25 + +#define LP87565_REG_I_LOAD_2 0x26 +#define LP87565_REG_I_LOAD_1 0x27 + +#define LP87565_REG_PGOOD_CTRL1 0x28 +#define LP87565_REG_PGOOD_CTRL2 0x29 +#define LP87565_REG_PGOOD_FLT 0x2A +#define LP87565_REG_PLL_CTRL 0x2B +#define LP87565_REG_PIN_FUNCTION 0x2C +#define LP87565_REG_GPIO_CONFIG 0x2D +#define LP87565_REG_GPIO_IN 0x2E +#define LP87565_REG_GPIO_OUT 0x2F + +#define LP87565_REG_MAX LP87565_REG_GPIO_OUT + +/* Register field definitions */ +#define LP87565_DEV_REV_DEV_ID 0xC0 +#define LP87565_DEV_REV_ALL_LAYER 0x30 +#define LP87565_DEV_REV_METAL_LAYER 0x0F + +#define LP87565_OTP_REV_OTP_ID 0xFF + +#define LP87565_BUCK_CTRL_1_EN BIT(7) +#define LP87565_BUCK_CTRL_1_EN_PIN_CTRL BIT(6) +#define LP87565_BUCK_CTRL_1_PIN_SELECT_EN 0x30 + +#define LP87565_BUCK_CTRL_1_ROOF_FLOOR_EN BIT(3) +#define LP87565_BUCK_CTRL_1_RDIS_EN BIT(2) +#define LP87565_BUCK_CTRL_1_FPWM BIT(1) +/* Bit0 is reserved for BUCK1 and BUCK3 and valid only for BUCK0 and BUCK2 */ +#define LP87565_BUCK_CTRL_1_FPWM_MP_0_2 BIT(0) + +#define LP87565_BUCK_CTRL_2_ILIM 0x38 +#define LP87565_BUCK_CTRL_2_SLEW_RATE 0x07 + +#define LP87565_BUCK_VSET 0xFF +#define LP87565_BUCK_FLOOR_VSET 0xFF + +#define LP87565_BUCK_SHUTDOWN_DELAY 0xF0 +#define LP87565_BUCK_STARTUP_DELAY 0x0F + +#define LP87565_GPIO_SHUTDOWN_DELAY 0xF0 +#define LP87565_GPIO_STARTUP_DELAY 0x0F + +#define LP87565_RESET_SW_RESET BIT(0) + +#define LP87565_CONFIG_DOUBLE_DELAY BIT(7) +#define LP87565_CONFIG_CLKIN_PD BIT(6) +#define LP87565_CONFIG_EN4_PD BIT(5) +#define LP87565_CONFIG_EN3_PD BIT(4) +#define LP87565_CONFIG_TDIE_WARN_LEVEL BIT(3) +#define LP87565_CONFIG_EN2_PD BIT(2) +#define LP87565_CONFIG_EN1_PD BIT(1) + +#define LP87565_INT_GPIO BIT(7) +#define LP87565_INT_BUCK23 BIT(6) +#define LP87565_INT_BUCK01 BIT(5) +#define LP87565_NO_SYNC_CLK BIT(4) +#define LP87565_TDIE_SD BIT(3) +#define LP87565_TDIE_WARN BIT(2) +#define LP87565_INT_OVP BIT(1) +#define LP87565_I_LOAD_READY BIT(0) + +#define LP87565_INT_TOP2_RESET_REG BIT(0) + +#define LP87565_BUCK1_PG_INT BIT(6) +#define LP87565_BUCK1_SC_INT BIT(5) +#define LP87565_BUCK1_ILIM_INT BIT(4) +#define LP87565_BUCK0_PG_INT BIT(2) +#define LP87565_BUCK0_SC_INT BIT(1) +#define LP87565_BUCK0_ILIM_INT BIT(0) + +#define LP87565_BUCK3_PG_INT BIT(6) +#define LP87565_BUCK3_SC_INT BIT(5) +#define LP87565_BUCK3_ILIM_INT BIT(4) +#define LP87565_BUCK2_PG_INT BIT(2) +#define LP87565_BUCK2_SC_INT BIT(1) +#define LP87565_BUCK2_ILIM_INT BIT(0) + +#define LP87565_SYNC_CLK_STAT BIT(4) +#define LP87565_TDIE_SD_STAT BIT(3) +#define LP87565_TDIE_WARN_STAT BIT(2) +#define LP87565_OVP_STAT BIT(1) + +#define LP87565_BUCK1_STAT BIT(7) +#define LP87565_BUCK1_PG_STAT BIT(6) +#define LP87565_BUCK1_ILIM_STAT BIT(4) +#define LP87565_BUCK0_STAT BIT(3) +#define LP87565_BUCK0_PG_STAT BIT(2) +#define LP87565_BUCK0_ILIM_STAT BIT(0) + +#define LP87565_BUCK3_STAT BIT(7) +#define LP87565_BUCK3_PG_STAT BIT(6) +#define LP87565_BUCK3_ILIM_STAT BIT(4) +#define LP87565_BUCK2_STAT BIT(3) +#define LP87565_BUCK2_PG_STAT BIT(2) +#define LP87565_BUCK2_ILIM_STAT BIT(0) + +#define LPL87565_GPIO_MASK BIT(7) +#define LPL87565_SYNC_CLK_MASK BIT(4) +#define LPL87565_TDIE_WARN_MASK BIT(2) +#define LPL87565_I_LOAD_READY_MASK BIT(0) + +#define LPL87565_RESET_REG_MASK BIT(0) + +#define LPL87565_BUCK1_PG_MASK BIT(6) +#define LPL87565_BUCK1_ILIM_MASK BIT(4) +#define LPL87565_BUCK0_PG_MASK BIT(2) +#define LPL87565_BUCK0_ILIM_MASK BIT(0) + +#define LPL87565_BUCK3_PG_MASK BIT(6) +#define LPL87565_BUCK3_ILIM_MASK BIT(4) +#define LPL87565_BUCK2_PG_MASK BIT(2) +#define LPL87565_BUCK2_ILIM_MASK BIT(0) + +#define LP87565_LOAD_CURRENT_BUCK_SELECT 0x3 + +#define LP87565_I_LOAD2_BUCK_LOAD_CURRENT 0x3 +#define LP87565_I_LOAD1_BUCK_LOAD_CURRENT 0xFF + +#define LP87565_PG3_SEL 0xC0 +#define LP87565_PG2_SEL 0x30 +#define LP87565_PG1_SEL 0x0C +#define LP87565_PG0_SEL 0x03 + +#define LP87565_HALF_DAY BIT(7) +#define LP87565_EN_PG0_NINT BIT(6) +#define LP87565_PGOOD_SET_DELAY BIT(5) +#define LP87565_EN_PGFLT_STAT BIT(4) +#define LP87565_PGOOD_WINDOW BIT(2) +#define LP87565_PGOOD_OD BIT(1) +#define LP87565_PGOOD_POL BIT(0) + +#define LP87565_PG3_FLT BIT(3) +#define LP87565_PG2_FLT BIT(2) +#define LP87565_PG1_FLT BIT(1) +#define LP87565_PG0_FLT BIT(0) + +#define LP87565_PLL_MODE 0xC0 +#define LP87565_EXT_CLK_FREQ 0x1F + +#define LP87565_EN_SPREAD_SPEC BIT(7) +#define LP87565_EN_PIN_CTRL_GPIO3 BIT(6) +#define LP87565_EN_PIN_SELECT_GPIO3 BIT(5) +#define LP87565_EN_PIN_CTRL_GPIO2 BIT(4) +#define LP87565_EN_PIN_SELECT_GPIO2 BIT(3) +#define LP87565_GPIO3_SEL BIT(2) +#define LP87565_GPIO2_SEL BIT(1) +#define LP87565_GPIO1_SEL BIT(0) + +#define LP87565_GOIO3_OD BIT(6) +#define LP87565_GOIO2_OD BIT(5) +#define LP87565_GOIO1_OD BIT(4) +#define LP87565_GOIO3_DIR BIT(2) +#define LP87565_GOIO2_DIR BIT(1) +#define LP87565_GOIO1_DIR BIT(0) + +#define LP87565_GOIO3_IN BIT(2) +#define LP87565_GOIO2_IN BIT(1) +#define LP87565_GOIO1_IN BIT(0) + +#define LP87565_GOIO3_OUT BIT(2) +#define LP87565_GOIO2_OUT BIT(1) +#define LP87565_GOIO1_OUT BIT(0) + +/* Number of step-down converters available */ +#define LP87565_NUM_BUCK 6 + +enum LP87565_regulator_id { + /* BUCK's */ + LP87565_BUCK_0, + LP87565_BUCK_1, + LP87565_BUCK_2, + LP87565_BUCK_3, + LP87565_BUCK_10, + LP87565_BUCK_23, +}; + +/** + * struct LP87565 - state holder for the LP87565 driver + * @dev: struct device pointer for MFD device + * @rev: revision of the LP87565 + * @dev_type: The device type for example lp87565-q1 + * @lock: lock guarding the data structure + * @regmap: register map of the LP87565 PMIC + * + * Device data may be used to access the LP87565 chip + */ +struct lp87565 { + struct device *dev; + u8 rev; + u8 dev_type; + struct regmap *regmap; +}; +#endif /* __LINUX_MFD_LP87565_H */ diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h index 2b300b44f994..fba8fcb54f8c 100644 --- a/include/linux/mfd/lpc_ich.h +++ b/include/linux/mfd/lpc_ich.h @@ -20,6 +20,8 @@ #ifndef LPC_ICH_H #define LPC_ICH_H +#include <linux/platform_data/intel-spi.h> + /* GPIO resources */ #define ICH_RES_GPIO 0 #define ICH_RES_GPE0 1 @@ -40,6 +42,7 @@ struct lpc_ich_info { char name[32]; unsigned int iTCO_version; unsigned int gpio_version; + enum intel_spi_type spi_type; u8 use_gpio; }; diff --git a/include/linux/mfd/motorola-cpcap.h b/include/linux/mfd/motorola-cpcap.h new file mode 100644 index 000000000000..aefc49cb7ba9 --- /dev/null +++ b/include/linux/mfd/motorola-cpcap.h @@ -0,0 +1,297 @@ +/* + * The register defines are based on earlier cpcap.h in Motorola Linux kernel + * tree. + * + * Copyright (C) 2007-2009 Motorola, Inc. + * + * Rewritten for the real register offsets instead of enumeration + * to make the defines usable with Linux kernel regmap support + * + * Copyright (C) 2016 Tony Lindgren <tony@atomide.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/device.h> +#include <linux/regmap.h> + +#define CPCAP_VENDOR_ST 0 +#define CPCAP_VENDOR_TI 1 + +#define CPCAP_REVISION_MAJOR(r) (((r) >> 4) + 1) +#define CPCAP_REVISION_MINOR(r) ((r) & 0xf) + +#define CPCAP_REVISION_1_0 0x08 +#define CPCAP_REVISION_1_1 0x09 +#define CPCAP_REVISION_2_0 0x10 +#define CPCAP_REVISION_2_1 0x11 + +/* CPCAP registers */ +#define CPCAP_REG_INT1 0x0000 /* Interrupt 1 */ +#define CPCAP_REG_INT2 0x0004 /* Interrupt 2 */ +#define CPCAP_REG_INT3 0x0008 /* Interrupt 3 */ +#define CPCAP_REG_INT4 0x000c /* Interrupt 4 */ +#define CPCAP_REG_INTM1 0x0010 /* Interrupt Mask 1 */ +#define CPCAP_REG_INTM2 0x0014 /* Interrupt Mask 2 */ +#define CPCAP_REG_INTM3 0x0018 /* Interrupt Mask 3 */ +#define CPCAP_REG_INTM4 0x001c /* Interrupt Mask 4 */ +#define CPCAP_REG_INTS1 0x0020 /* Interrupt Sense 1 */ +#define CPCAP_REG_INTS2 0x0024 /* Interrupt Sense 2 */ +#define CPCAP_REG_INTS3 0x0028 /* Interrupt Sense 3 */ +#define CPCAP_REG_INTS4 0x002c /* Interrupt Sense 4 */ +#define CPCAP_REG_ASSIGN1 0x0030 /* Resource Assignment 1 */ +#define CPCAP_REG_ASSIGN2 0x0034 /* Resource Assignment 2 */ +#define CPCAP_REG_ASSIGN3 0x0038 /* Resource Assignment 3 */ +#define CPCAP_REG_ASSIGN4 0x003c /* Resource Assignment 4 */ +#define CPCAP_REG_ASSIGN5 0x0040 /* Resource Assignment 5 */ +#define CPCAP_REG_ASSIGN6 0x0044 /* Resource Assignment 6 */ +#define CPCAP_REG_VERSC1 0x0048 /* Version Control 1 */ +#define CPCAP_REG_VERSC2 0x004c /* Version Control 2 */ + +#define CPCAP_REG_MI1 0x0200 /* Macro Interrupt 1 */ +#define CPCAP_REG_MIM1 0x0204 /* Macro Interrupt Mask 1 */ +#define CPCAP_REG_MI2 0x0208 /* Macro Interrupt 2 */ +#define CPCAP_REG_MIM2 0x020c /* Macro Interrupt Mask 2 */ +#define CPCAP_REG_UCC1 0x0210 /* UC Control 1 */ +#define CPCAP_REG_UCC2 0x0214 /* UC Control 2 */ + +#define CPCAP_REG_PC1 0x021c /* Power Cut 1 */ +#define CPCAP_REG_PC2 0x0220 /* Power Cut 2 */ +#define CPCAP_REG_BPEOL 0x0224 /* BP and EOL */ +#define CPCAP_REG_PGC 0x0228 /* Power Gate and Control */ +#define CPCAP_REG_MT1 0x022c /* Memory Transfer 1 */ +#define CPCAP_REG_MT2 0x0230 /* Memory Transfer 2 */ +#define CPCAP_REG_MT3 0x0234 /* Memory Transfer 3 */ +#define CPCAP_REG_PF 0x0238 /* Print Format */ + +#define CPCAP_REG_SCC 0x0400 /* System Clock Control */ +#define CPCAP_REG_SW1 0x0404 /* Stop Watch 1 */ +#define CPCAP_REG_SW2 0x0408 /* Stop Watch 2 */ +#define CPCAP_REG_UCTM 0x040c /* UC Turbo Mode */ +#define CPCAP_REG_TOD1 0x0410 /* Time of Day 1 */ +#define CPCAP_REG_TOD2 0x0414 /* Time of Day 2 */ +#define CPCAP_REG_TODA1 0x0418 /* Time of Day Alarm 1 */ +#define CPCAP_REG_TODA2 0x041c /* Time of Day Alarm 2 */ +#define CPCAP_REG_DAY 0x0420 /* Day */ +#define CPCAP_REG_DAYA 0x0424 /* Day Alarm */ +#define CPCAP_REG_VAL1 0x0428 /* Validity 1 */ +#define CPCAP_REG_VAL2 0x042c /* Validity 2 */ + +#define CPCAP_REG_SDVSPLL 0x0600 /* Switcher DVS and PLL */ +#define CPCAP_REG_SI2CC1 0x0604 /* Switcher I2C Control 1 */ +#define CPCAP_REG_Si2CC2 0x0608 /* Switcher I2C Control 2 */ +#define CPCAP_REG_S1C1 0x060c /* Switcher 1 Control 1 */ +#define CPCAP_REG_S1C2 0x0610 /* Switcher 1 Control 2 */ +#define CPCAP_REG_S2C1 0x0614 /* Switcher 2 Control 1 */ +#define CPCAP_REG_S2C2 0x0618 /* Switcher 2 Control 2 */ +#define CPCAP_REG_S3C 0x061c /* Switcher 3 Control */ +#define CPCAP_REG_S4C1 0x0620 /* Switcher 4 Control 1 */ +#define CPCAP_REG_S4C2 0x0624 /* Switcher 4 Control 2 */ +#define CPCAP_REG_S5C 0x0628 /* Switcher 5 Control */ +#define CPCAP_REG_S6C 0x062c /* Switcher 6 Control */ +#define CPCAP_REG_VCAMC 0x0630 /* VCAM Control */ +#define CPCAP_REG_VCSIC 0x0634 /* VCSI Control */ +#define CPCAP_REG_VDACC 0x0638 /* VDAC Control */ +#define CPCAP_REG_VDIGC 0x063c /* VDIG Control */ +#define CPCAP_REG_VFUSEC 0x0640 /* VFUSE Control */ +#define CPCAP_REG_VHVIOC 0x0644 /* VHVIO Control */ +#define CPCAP_REG_VSDIOC 0x0648 /* VSDIO Control */ +#define CPCAP_REG_VPLLC 0x064c /* VPLL Control */ +#define CPCAP_REG_VRF1C 0x0650 /* VRF1 Control */ +#define CPCAP_REG_VRF2C 0x0654 /* VRF2 Control */ +#define CPCAP_REG_VRFREFC 0x0658 /* VRFREF Control */ +#define CPCAP_REG_VWLAN1C 0x065c /* VWLAN1 Control */ +#define CPCAP_REG_VWLAN2C 0x0660 /* VWLAN2 Control */ +#define CPCAP_REG_VSIMC 0x0664 /* VSIM Control */ +#define CPCAP_REG_VVIBC 0x0668 /* VVIB Control */ +#define CPCAP_REG_VUSBC 0x066c /* VUSB Control */ +#define CPCAP_REG_VUSBINT1C 0x0670 /* VUSBINT1 Control */ +#define CPCAP_REG_VUSBINT2C 0x0674 /* VUSBINT2 Control */ +#define CPCAP_REG_URT 0x0678 /* Useroff Regulator Trigger */ +#define CPCAP_REG_URM1 0x067c /* Useroff Regulator Mask 1 */ +#define CPCAP_REG_URM2 0x0680 /* Useroff Regulator Mask 2 */ + +#define CPCAP_REG_VAUDIOC 0x0800 /* VAUDIO Control */ +#define CPCAP_REG_CC 0x0804 /* Codec Control */ +#define CPCAP_REG_CDI 0x0808 /* Codec Digital Interface */ +#define CPCAP_REG_SDAC 0x080c /* Stereo DAC */ +#define CPCAP_REG_SDACDI 0x0810 /* Stereo DAC Digital Interface */ +#define CPCAP_REG_TXI 0x0814 /* TX Inputs */ +#define CPCAP_REG_TXMP 0x0818 /* TX MIC PGA's */ +#define CPCAP_REG_RXOA 0x081c /* RX Output Amplifiers */ +#define CPCAP_REG_RXVC 0x0820 /* RX Volume Control */ +#define CPCAP_REG_RXCOA 0x0824 /* RX Codec to Output Amps */ +#define CPCAP_REG_RXSDOA 0x0828 /* RX Stereo DAC to Output Amps */ +#define CPCAP_REG_RXEPOA 0x082c /* RX External PGA to Output Amps */ +#define CPCAP_REG_RXLL 0x0830 /* RX Low Latency */ +#define CPCAP_REG_A2LA 0x0834 /* A2 Loudspeaker Amplifier */ +#define CPCAP_REG_MIPIS1 0x0838 /* MIPI Slimbus 1 */ +#define CPCAP_REG_MIPIS2 0x083c /* MIPI Slimbus 2 */ +#define CPCAP_REG_MIPIS3 0x0840 /* MIPI Slimbus 3. */ +#define CPCAP_REG_LVAB 0x0844 /* LMR Volume and A4 Balanced. */ + +#define CPCAP_REG_CCC1 0x0a00 /* Coulomb Counter Control 1 */ +#define CPCAP_REG_CRM 0x0a04 /* Charger and Reverse Mode */ +#define CPCAP_REG_CCCC2 0x0a08 /* Coincell and Coulomb Ctr Ctrl 2 */ +#define CPCAP_REG_CCS1 0x0a0c /* Coulomb Counter Sample 1 */ +#define CPCAP_REG_CCS2 0x0a10 /* Coulomb Counter Sample 2 */ +#define CPCAP_REG_CCA1 0x0a14 /* Coulomb Counter Accumulator 1 */ +#define CPCAP_REG_CCA2 0x0a18 /* Coulomb Counter Accumulator 2 */ +#define CPCAP_REG_CCM 0x0a1c /* Coulomb Counter Mode */ +#define CPCAP_REG_CCO 0x0a20 /* Coulomb Counter Offset */ +#define CPCAP_REG_CCI 0x0a24 /* Coulomb Counter Integrator */ + +#define CPCAP_REG_ADCC1 0x0c00 /* A/D Converter Configuration 1 */ +#define CPCAP_REG_ADCC2 0x0c04 /* A/D Converter Configuration 2 */ +#define CPCAP_REG_ADCD0 0x0c08 /* A/D Converter Data 0 */ +#define CPCAP_REG_ADCD1 0x0c0c /* A/D Converter Data 1 */ +#define CPCAP_REG_ADCD2 0x0c10 /* A/D Converter Data 2 */ +#define CPCAP_REG_ADCD3 0x0c14 /* A/D Converter Data 3 */ +#define CPCAP_REG_ADCD4 0x0c18 /* A/D Converter Data 4 */ +#define CPCAP_REG_ADCD5 0x0c1c /* A/D Converter Data 5 */ +#define CPCAP_REG_ADCD6 0x0c20 /* A/D Converter Data 6 */ +#define CPCAP_REG_ADCD7 0x0c24 /* A/D Converter Data 7 */ +#define CPCAP_REG_ADCAL1 0x0c28 /* A/D Converter Calibration 1 */ +#define CPCAP_REG_ADCAL2 0x0c2c /* A/D Converter Calibration 2 */ + +#define CPCAP_REG_USBC1 0x0e00 /* USB Control 1 */ +#define CPCAP_REG_USBC2 0x0e04 /* USB Control 2 */ +#define CPCAP_REG_USBC3 0x0e08 /* USB Control 3 */ +#define CPCAP_REG_UVIDL 0x0e0c /* ULPI Vendor ID Low */ +#define CPCAP_REG_UVIDH 0x0e10 /* ULPI Vendor ID High */ +#define CPCAP_REG_UPIDL 0x0e14 /* ULPI Product ID Low */ +#define CPCAP_REG_UPIDH 0x0e18 /* ULPI Product ID High */ +#define CPCAP_REG_UFC1 0x0e1c /* ULPI Function Control 1 */ +#define CPCAP_REG_UFC2 0x0e20 /* ULPI Function Control 2 */ +#define CPCAP_REG_UFC3 0x0e24 /* ULPI Function Control 3 */ +#define CPCAP_REG_UIC1 0x0e28 /* ULPI Interface Control 1 */ +#define CPCAP_REG_UIC2 0x0e2c /* ULPI Interface Control 2 */ +#define CPCAP_REG_UIC3 0x0e30 /* ULPI Interface Control 3 */ +#define CPCAP_REG_USBOTG1 0x0e34 /* USB OTG Control 1 */ +#define CPCAP_REG_USBOTG2 0x0e38 /* USB OTG Control 2 */ +#define CPCAP_REG_USBOTG3 0x0e3c /* USB OTG Control 3 */ +#define CPCAP_REG_UIER1 0x0e40 /* USB Interrupt Enable Rising 1 */ +#define CPCAP_REG_UIER2 0x0e44 /* USB Interrupt Enable Rising 2 */ +#define CPCAP_REG_UIER3 0x0e48 /* USB Interrupt Enable Rising 3 */ +#define CPCAP_REG_UIEF1 0x0e4c /* USB Interrupt Enable Falling 1 */ +#define CPCAP_REG_UIEF2 0x0e50 /* USB Interrupt Enable Falling 1 */ +#define CPCAP_REG_UIEF3 0x0e54 /* USB Interrupt Enable Falling 1 */ +#define CPCAP_REG_UIS 0x0e58 /* USB Interrupt Status */ +#define CPCAP_REG_UIL 0x0e5c /* USB Interrupt Latch */ +#define CPCAP_REG_USBD 0x0e60 /* USB Debug */ +#define CPCAP_REG_SCR1 0x0e64 /* Scratch 1 */ +#define CPCAP_REG_SCR2 0x0e68 /* Scratch 2 */ +#define CPCAP_REG_SCR3 0x0e6c /* Scratch 3 */ + +#define CPCAP_REG_VMC 0x0eac /* Video Mux Control */ +#define CPCAP_REG_OWDC 0x0eb0 /* One Wire Device Control */ +#define CPCAP_REG_GPIO0 0x0eb4 /* GPIO 0 Control */ + +#define CPCAP_REG_GPIO1 0x0ebc /* GPIO 1 Control */ + +#define CPCAP_REG_GPIO2 0x0ec4 /* GPIO 2 Control */ + +#define CPCAP_REG_GPIO3 0x0ecc /* GPIO 3 Control */ + +#define CPCAP_REG_GPIO4 0x0ed4 /* GPIO 4 Control */ + +#define CPCAP_REG_GPIO5 0x0edc /* GPIO 5 Control */ + +#define CPCAP_REG_GPIO6 0x0ee4 /* GPIO 6 Control */ + +#define CPCAP_REG_MDLC 0x1000 /* Main Display Lighting Control */ +#define CPCAP_REG_KLC 0x1004 /* Keypad Lighting Control */ +#define CPCAP_REG_ADLC 0x1008 /* Aux Display Lighting Control */ +#define CPCAP_REG_REDC 0x100c /* Red Triode Control */ +#define CPCAP_REG_GREENC 0x1010 /* Green Triode Control */ +#define CPCAP_REG_BLUEC 0x1014 /* Blue Triode Control */ +#define CPCAP_REG_CFC 0x1018 /* Camera Flash Control */ +#define CPCAP_REG_ABC 0x101c /* Adaptive Boost Control */ +#define CPCAP_REG_BLEDC 0x1020 /* Bluetooth LED Control */ +#define CPCAP_REG_CLEDC 0x1024 /* Camera Privacy LED Control */ + +#define CPCAP_REG_OW1C 0x1200 /* One Wire 1 Command */ +#define CPCAP_REG_OW1D 0x1204 /* One Wire 1 Data */ +#define CPCAP_REG_OW1I 0x1208 /* One Wire 1 Interrupt */ +#define CPCAP_REG_OW1IE 0x120c /* One Wire 1 Interrupt Enable */ + +#define CPCAP_REG_OW1 0x1214 /* One Wire 1 Control */ + +#define CPCAP_REG_OW2C 0x1220 /* One Wire 2 Command */ +#define CPCAP_REG_OW2D 0x1224 /* One Wire 2 Data */ +#define CPCAP_REG_OW2I 0x1228 /* One Wire 2 Interrupt */ +#define CPCAP_REG_OW2IE 0x122c /* One Wire 2 Interrupt Enable */ + +#define CPCAP_REG_OW2 0x1234 /* One Wire 2 Control */ + +#define CPCAP_REG_OW3C 0x1240 /* One Wire 3 Command */ +#define CPCAP_REG_OW3D 0x1244 /* One Wire 3 Data */ +#define CPCAP_REG_OW3I 0x1248 /* One Wire 3 Interrupt */ +#define CPCAP_REG_OW3IE 0x124c /* One Wire 3 Interrupt Enable */ + +#define CPCAP_REG_OW3 0x1254 /* One Wire 3 Control */ +#define CPCAP_REG_GCAIC 0x1258 /* GCAI Clock Control */ +#define CPCAP_REG_GCAIM 0x125c /* GCAI GPIO Mode */ +#define CPCAP_REG_LGDIR 0x1260 /* LMR GCAI GPIO Direction */ +#define CPCAP_REG_LGPU 0x1264 /* LMR GCAI GPIO Pull-up */ +#define CPCAP_REG_LGPIN 0x1268 /* LMR GCAI GPIO Pin */ +#define CPCAP_REG_LGMASK 0x126c /* LMR GCAI GPIO Mask */ +#define CPCAP_REG_LDEB 0x1270 /* LMR Debounce Settings */ +#define CPCAP_REG_LGDET 0x1274 /* LMR GCAI Detach Detect */ +#define CPCAP_REG_LMISC 0x1278 /* LMR Misc Bits */ +#define CPCAP_REG_LMACE 0x127c /* LMR Mace IC Support */ + +#define CPCAP_REG_TEST 0x7c00 /* Test */ + +#define CPCAP_REG_ST_TEST1 0x7d08 /* ST Test1 */ + +#define CPCAP_REG_ST_TEST2 0x7d18 /* ST Test2 */ + +/* + * Helpers for child devices to check the revision and vendor. + * + * REVISIT: No documentation for the bits below, please update + * to use proper names for defines when available. + */ + +static inline int cpcap_get_revision(struct device *dev, + struct regmap *regmap, + u16 *revision) +{ + unsigned int val; + int ret; + + ret = regmap_read(regmap, CPCAP_REG_VERSC1, &val); + if (ret) { + dev_err(dev, "Could not read revision\n"); + + return ret; + } + + *revision = ((val >> 3) & 0x7) | ((val << 3) & 0x38); + + return 0; +} + +static inline int cpcap_get_vendor(struct device *dev, + struct regmap *regmap, + u16 *vendor) +{ + unsigned int val; + int ret; + + ret = regmap_read(regmap, CPCAP_REG_VERSC1, &val); + if (ret) { + dev_err(dev, "Could not read vendor\n"); + + return ret; + } + + *vendor = (val >> 6) & 0x7; + + return 0; +} + +extern int cpcap_sense_virq(struct regmap *regmap, int virq); diff --git a/include/linux/mfd/mxs-lradc.h b/include/linux/mfd/mxs-lradc.h new file mode 100644 index 000000000000..661a4521f723 --- /dev/null +++ b/include/linux/mfd/mxs-lradc.h @@ -0,0 +1,187 @@ +/* + * Freescale MXS Low Resolution Analog-to-Digital Converter driver + * + * Copyright (c) 2012 DENX Software Engineering, GmbH. + * Copyright (c) 2016 Ksenija Stanojevic <ksenija.stanojevic@gmail.com> + * + * Author: Marek Vasut <marex@denx.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __MFD_MXS_LRADC_H +#define __MFD_MXS_LRADC_H + +#include <linux/bitops.h> +#include <linux/io.h> +#include <linux/stmp_device.h> + +#define LRADC_MAX_DELAY_CHANS 4 +#define LRADC_MAX_MAPPED_CHANS 8 +#define LRADC_MAX_TOTAL_CHANS 16 + +#define LRADC_DELAY_TIMER_HZ 2000 + +#define LRADC_CTRL0 0x00 +# define LRADC_CTRL0_MX28_TOUCH_DETECT_ENABLE BIT(23) +# define LRADC_CTRL0_MX28_TOUCH_SCREEN_TYPE BIT(22) +# define LRADC_CTRL0_MX28_YNNSW /* YM */ BIT(21) +# define LRADC_CTRL0_MX28_YPNSW /* YP */ BIT(20) +# define LRADC_CTRL0_MX28_YPPSW /* YP */ BIT(19) +# define LRADC_CTRL0_MX28_XNNSW /* XM */ BIT(18) +# define LRADC_CTRL0_MX28_XNPSW /* XM */ BIT(17) +# define LRADC_CTRL0_MX28_XPPSW /* XP */ BIT(16) + +# define LRADC_CTRL0_MX23_TOUCH_DETECT_ENABLE BIT(20) +# define LRADC_CTRL0_MX23_YM BIT(19) +# define LRADC_CTRL0_MX23_XM BIT(18) +# define LRADC_CTRL0_MX23_YP BIT(17) +# define LRADC_CTRL0_MX23_XP BIT(16) + +# define LRADC_CTRL0_MX28_PLATE_MASK \ + (LRADC_CTRL0_MX28_TOUCH_DETECT_ENABLE | \ + LRADC_CTRL0_MX28_YNNSW | LRADC_CTRL0_MX28_YPNSW | \ + LRADC_CTRL0_MX28_YPPSW | LRADC_CTRL0_MX28_XNNSW | \ + LRADC_CTRL0_MX28_XNPSW | LRADC_CTRL0_MX28_XPPSW) + +# define LRADC_CTRL0_MX23_PLATE_MASK \ + (LRADC_CTRL0_MX23_TOUCH_DETECT_ENABLE | \ + LRADC_CTRL0_MX23_YM | LRADC_CTRL0_MX23_XM | \ + LRADC_CTRL0_MX23_YP | LRADC_CTRL0_MX23_XP) + +#define LRADC_CTRL1 0x10 +#define LRADC_CTRL1_TOUCH_DETECT_IRQ_EN BIT(24) +#define LRADC_CTRL1_LRADC_IRQ_EN(n) (1 << ((n) + 16)) +#define LRADC_CTRL1_MX28_LRADC_IRQ_EN_MASK (0x1fff << 16) +#define LRADC_CTRL1_MX23_LRADC_IRQ_EN_MASK (0x01ff << 16) +#define LRADC_CTRL1_LRADC_IRQ_EN_OFFSET 16 +#define LRADC_CTRL1_TOUCH_DETECT_IRQ BIT(8) +#define LRADC_CTRL1_LRADC_IRQ(n) BIT(n) +#define LRADC_CTRL1_MX28_LRADC_IRQ_MASK 0x1fff +#define LRADC_CTRL1_MX23_LRADC_IRQ_MASK 0x01ff +#define LRADC_CTRL1_LRADC_IRQ_OFFSET 0 + +#define LRADC_CTRL2 0x20 +#define LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET 24 +#define LRADC_CTRL2_TEMPSENSE_PWD BIT(15) + +#define LRADC_STATUS 0x40 +#define LRADC_STATUS_TOUCH_DETECT_RAW BIT(0) + +#define LRADC_CH(n) (0x50 + (0x10 * (n))) +#define LRADC_CH_ACCUMULATE BIT(29) +#define LRADC_CH_NUM_SAMPLES_MASK (0x1f << 24) +#define LRADC_CH_NUM_SAMPLES_OFFSET 24 +#define LRADC_CH_NUM_SAMPLES(x) \ + ((x) << LRADC_CH_NUM_SAMPLES_OFFSET) +#define LRADC_CH_VALUE_MASK 0x3ffff +#define LRADC_CH_VALUE_OFFSET 0 + +#define LRADC_DELAY(n) (0xd0 + (0x10 * (n))) +#define LRADC_DELAY_TRIGGER_LRADCS_MASK (0xffUL << 24) +#define LRADC_DELAY_TRIGGER_LRADCS_OFFSET 24 +#define LRADC_DELAY_TRIGGER(x) \ + (((x) << LRADC_DELAY_TRIGGER_LRADCS_OFFSET) & \ + LRADC_DELAY_TRIGGER_LRADCS_MASK) +#define LRADC_DELAY_KICK BIT(20) +#define LRADC_DELAY_TRIGGER_DELAYS_MASK (0xf << 16) +#define LRADC_DELAY_TRIGGER_DELAYS_OFFSET 16 +#define LRADC_DELAY_TRIGGER_DELAYS(x) \ + (((x) << LRADC_DELAY_TRIGGER_DELAYS_OFFSET) & \ + LRADC_DELAY_TRIGGER_DELAYS_MASK) +#define LRADC_DELAY_LOOP_COUNT_MASK (0x1f << 11) +#define LRADC_DELAY_LOOP_COUNT_OFFSET 11 +#define LRADC_DELAY_LOOP(x) \ + (((x) << LRADC_DELAY_LOOP_COUNT_OFFSET) & \ + LRADC_DELAY_LOOP_COUNT_MASK) +#define LRADC_DELAY_DELAY_MASK 0x7ff +#define LRADC_DELAY_DELAY_OFFSET 0 +#define LRADC_DELAY_DELAY(x) \ + (((x) << LRADC_DELAY_DELAY_OFFSET) & \ + LRADC_DELAY_DELAY_MASK) + +#define LRADC_CTRL4 0x140 +#define LRADC_CTRL4_LRADCSELECT_MASK(n) (0xf << ((n) * 4)) +#define LRADC_CTRL4_LRADCSELECT_OFFSET(n) ((n) * 4) +#define LRADC_CTRL4_LRADCSELECT(n, x) \ + (((x) << LRADC_CTRL4_LRADCSELECT_OFFSET(n)) & \ + LRADC_CTRL4_LRADCSELECT_MASK(n)) + +#define LRADC_RESOLUTION 12 +#define LRADC_SINGLE_SAMPLE_MASK ((1 << LRADC_RESOLUTION) - 1) + +#define BUFFER_VCHANS_LIMITED 0x3f +#define BUFFER_VCHANS_ALL 0xff + + /* + * Certain LRADC channels are shared between touchscreen + * and/or touch-buttons and generic LRADC block. Therefore when using + * either of these, these channels are not available for the regular + * sampling. The shared channels are as follows: + * + * CH0 -- Touch button #0 + * CH1 -- Touch button #1 + * CH2 -- Touch screen XPUL + * CH3 -- Touch screen YPLL + * CH4 -- Touch screen XNUL + * CH5 -- Touch screen YNLR + * CH6 -- Touch screen WIPER (5-wire only) + * + * The bit fields below represents which parts of the LRADC block are + * switched into special mode of operation. These channels can not + * be sampled as regular LRADC channels. The driver will refuse any + * attempt to sample these channels. + */ +#define CHAN_MASK_TOUCHBUTTON (BIT(1) | BIT(0)) +#define CHAN_MASK_TOUCHSCREEN_4WIRE (0xf << 2) +#define CHAN_MASK_TOUCHSCREEN_5WIRE (0x1f << 2) + +enum mxs_lradc_id { + IMX23_LRADC, + IMX28_LRADC, +}; + +enum mxs_lradc_ts_wires { + MXS_LRADC_TOUCHSCREEN_NONE = 0, + MXS_LRADC_TOUCHSCREEN_4WIRE, + MXS_LRADC_TOUCHSCREEN_5WIRE, +}; + +/** + * struct mxs_lradc + * @soc: soc type (IMX23 or IMX28) + * @clk: 2 kHz clock for delay units + * @buffer_vchans: channels that can be used during buffered capture + * @touchscreen_wire: touchscreen type (4-wire or 5-wire) + * @use_touchbutton: button state (on or off) + */ +struct mxs_lradc { + enum mxs_lradc_id soc; + struct clk *clk; + u8 buffer_vchans; + + enum mxs_lradc_ts_wires touchscreen_wire; + bool use_touchbutton; +}; + +static inline u32 mxs_lradc_irq_mask(struct mxs_lradc *lradc) +{ + switch (lradc->soc) { + case IMX23_LRADC: + return LRADC_CTRL1_MX23_LRADC_IRQ_MASK; + case IMX28_LRADC: + return LRADC_CTRL1_MX28_LRADC_IRQ_MASK; + default: + return 0; + } +} + +#endif /* __MXS_LRADC_H */ diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 5c9a1d44c125..6dec43826303 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -250,6 +250,7 @@ enum tps65917_regulators { TPS65917_REG_SMPS3, TPS65917_REG_SMPS4, TPS65917_REG_SMPS5, + TPS65917_REG_SMPS12, /* LDO regulators */ TPS65917_REG_LDO1, TPS65917_REG_LDO2, @@ -317,6 +318,7 @@ enum tps65917_external_requestor_id { TPS65917_EXTERNAL_REQSTR_ID_SMPS3, TPS65917_EXTERNAL_REQSTR_ID_SMPS4, TPS65917_EXTERNAL_REQSTR_ID_SMPS5, + TPS65917_EXTERNAL_REQSTR_ID_SMPS12, TPS65917_EXTERNAL_REQSTR_ID_LDO1, TPS65917_EXTERNAL_REQSTR_ID_LDO2, TPS65917_EXTERNAL_REQSTR_ID_LDO3, diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 7eb7cbac0a9a..116816fb9110 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -850,6 +850,9 @@ #define rtsx_pci_init_cmd(pcr) ((pcr)->ci = 0) +#define RTS5227_DEVICE_ID 0x5227 +#define RTS_MAX_TIMES_FREQ_REDUCTION 8 + struct rtsx_pcr; struct pcr_handle { @@ -957,6 +960,8 @@ struct rtsx_pcr { int num_slots; struct rtsx_slot *slots; + + u8 dma_error_count; }; #define CHK_PCI_PID(pcr, pid) ((pcr)->pci->device == (pid)) diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h new file mode 100644 index 000000000000..ce7346e7f77a --- /dev/null +++ b/include/linux/mfd/stm32-timers.h @@ -0,0 +1,75 @@ +/* + * Copyright (C) STMicroelectronics 2016 + * + * Author: Benjamin Gaignard <benjamin.gaignard@st.com> + * + * License terms: GNU General Public License (GPL), version 2 + */ + +#ifndef _LINUX_STM32_GPTIMER_H_ +#define _LINUX_STM32_GPTIMER_H_ + +#include <linux/clk.h> +#include <linux/regmap.h> + +#define TIM_CR1 0x00 /* Control Register 1 */ +#define TIM_CR2 0x04 /* Control Register 2 */ +#define TIM_SMCR 0x08 /* Slave mode control reg */ +#define TIM_DIER 0x0C /* DMA/interrupt register */ +#define TIM_SR 0x10 /* Status register */ +#define TIM_EGR 0x14 /* Event Generation Reg */ +#define TIM_CCMR1 0x18 /* Capt/Comp 1 Mode Reg */ +#define TIM_CCMR2 0x1C /* Capt/Comp 2 Mode Reg */ +#define TIM_CCER 0x20 /* Capt/Comp Enable Reg */ +#define TIM_CNT 0x24 /* Counter */ +#define TIM_PSC 0x28 /* Prescaler */ +#define TIM_ARR 0x2c /* Auto-Reload Register */ +#define TIM_CCR1 0x34 /* Capt/Comp Register 1 */ +#define TIM_CCR2 0x38 /* Capt/Comp Register 2 */ +#define TIM_CCR3 0x3C /* Capt/Comp Register 3 */ +#define TIM_CCR4 0x40 /* Capt/Comp Register 4 */ +#define TIM_BDTR 0x44 /* Break and Dead-Time Reg */ + +#define TIM_CR1_CEN BIT(0) /* Counter Enable */ +#define TIM_CR1_DIR BIT(4) /* Counter Direction */ +#define TIM_CR1_ARPE BIT(7) /* Auto-reload Preload Ena */ +#define TIM_CR2_MMS (BIT(4) | BIT(5) | BIT(6)) /* Master mode selection */ +#define TIM_CR2_MMS2 GENMASK(23, 20) /* Master mode selection 2 */ +#define TIM_SMCR_SMS (BIT(0) | BIT(1) | BIT(2)) /* Slave mode selection */ +#define TIM_SMCR_TS (BIT(4) | BIT(5) | BIT(6)) /* Trigger selection */ +#define TIM_DIER_UIE BIT(0) /* Update interrupt */ +#define TIM_SR_UIF BIT(0) /* Update interrupt flag */ +#define TIM_EGR_UG BIT(0) /* Update Generation */ +#define TIM_CCMR_PE BIT(3) /* Channel Preload Enable */ +#define TIM_CCMR_M1 (BIT(6) | BIT(5)) /* Channel PWM Mode 1 */ +#define TIM_CCER_CC1E BIT(0) /* Capt/Comp 1 out Ena */ +#define TIM_CCER_CC1P BIT(1) /* Capt/Comp 1 Polarity */ +#define TIM_CCER_CC1NE BIT(2) /* Capt/Comp 1N out Ena */ +#define TIM_CCER_CC1NP BIT(3) /* Capt/Comp 1N Polarity */ +#define TIM_CCER_CC2E BIT(4) /* Capt/Comp 2 out Ena */ +#define TIM_CCER_CC3E BIT(8) /* Capt/Comp 3 out Ena */ +#define TIM_CCER_CC4E BIT(12) /* Capt/Comp 4 out Ena */ +#define TIM_CCER_CCXE (BIT(0) | BIT(4) | BIT(8) | BIT(12)) +#define TIM_BDTR_BKE BIT(12) /* Break input enable */ +#define TIM_BDTR_BKP BIT(13) /* Break input polarity */ +#define TIM_BDTR_AOE BIT(14) /* Automatic Output Enable */ +#define TIM_BDTR_MOE BIT(15) /* Main Output Enable */ +#define TIM_BDTR_BKF (BIT(16) | BIT(17) | BIT(18) | BIT(19)) +#define TIM_BDTR_BK2F (BIT(20) | BIT(21) | BIT(22) | BIT(23)) +#define TIM_BDTR_BK2E BIT(24) /* Break 2 input enable */ +#define TIM_BDTR_BK2P BIT(25) /* Break 2 input polarity */ + +#define MAX_TIM_PSC 0xFFFF +#define TIM_CR2_MMS_SHIFT 4 +#define TIM_CR2_MMS2_SHIFT 20 +#define TIM_SMCR_TS_SHIFT 4 +#define TIM_BDTR_BKF_MASK 0xF +#define TIM_BDTR_BKF_SHIFT 16 +#define TIM_BDTR_BK2F_SHIFT 20 + +struct stm32_timers { + struct clk *clk; + struct regmap *regmap; + u32 max_arr; +}; +#endif diff --git a/include/linux/mfd/sun4i-gpadc.h b/include/linux/mfd/sun4i-gpadc.h index d7a29f246d64..139872c2e0fe 100644 --- a/include/linux/mfd/sun4i-gpadc.h +++ b/include/linux/mfd/sun4i-gpadc.h @@ -28,6 +28,7 @@ #define SUN4I_GPADC_CTRL1_TP_MODE_EN BIT(4) #define SUN4I_GPADC_CTRL1_TP_ADC_SELECT BIT(3) #define SUN4I_GPADC_CTRL1_ADC_CHAN_SELECT(x) (GENMASK(2, 0) & (x)) +#define SUN4I_GPADC_CTRL1_ADC_CHAN_MASK GENMASK(2, 0) /* TP_CTRL1 bits for sun6i SOCs */ #define SUN6I_GPADC_CTRL1_TOUCH_PAN_CALI_EN BIT(7) @@ -35,6 +36,11 @@ #define SUN6I_GPADC_CTRL1_TP_MODE_EN BIT(5) #define SUN6I_GPADC_CTRL1_TP_ADC_SELECT BIT(4) #define SUN6I_GPADC_CTRL1_ADC_CHAN_SELECT(x) (GENMASK(3, 0) & BIT(x)) +#define SUN6I_GPADC_CTRL1_ADC_CHAN_MASK GENMASK(3, 0) + +/* TP_CTRL1 bits for sun8i SoCs */ +#define SUN8I_GPADC_CTRL1_CHOP_TEMP_EN BIT(8) +#define SUN8I_GPADC_CTRL1_GPADC_CALI_EN BIT(7) #define SUN4I_GPADC_CTRL2 0x08 diff --git a/include/linux/mfd/syscon/atmel-smc.h b/include/linux/mfd/syscon/atmel-smc.h index be6ebe64eebe..afa266169800 100644 --- a/include/linux/mfd/syscon/atmel-smc.h +++ b/include/linux/mfd/syscon/atmel-smc.h @@ -17,157 +17,92 @@ #include <linux/kernel.h> #include <linux/regmap.h> -#define AT91SAM9_SMC_GENERIC 0x00 -#define AT91SAM9_SMC_GENERIC_BLK_SZ 0x10 - -#define SAMA5_SMC_GENERIC 0x600 -#define SAMA5_SMC_GENERIC_BLK_SZ 0x14 - -#define AT91SAM9_SMC_SETUP(o) ((o) + 0x00) -#define AT91SAM9_SMC_NWESETUP(x) (x) -#define AT91SAM9_SMC_NCS_WRSETUP(x) ((x) << 8) -#define AT91SAM9_SMC_NRDSETUP(x) ((x) << 16) -#define AT91SAM9_SMC_NCS_NRDSETUP(x) ((x) << 24) - -#define AT91SAM9_SMC_PULSE(o) ((o) + 0x04) -#define AT91SAM9_SMC_NWEPULSE(x) (x) -#define AT91SAM9_SMC_NCS_WRPULSE(x) ((x) << 8) -#define AT91SAM9_SMC_NRDPULSE(x) ((x) << 16) -#define AT91SAM9_SMC_NCS_NRDPULSE(x) ((x) << 24) - -#define AT91SAM9_SMC_CYCLE(o) ((o) + 0x08) -#define AT91SAM9_SMC_NWECYCLE(x) (x) -#define AT91SAM9_SMC_NRDCYCLE(x) ((x) << 16) - -#define AT91SAM9_SMC_MODE(o) ((o) + 0x0c) -#define SAMA5_SMC_MODE(o) ((o) + 0x10) -#define AT91_SMC_READMODE BIT(0) -#define AT91_SMC_READMODE_NCS (0 << 0) -#define AT91_SMC_READMODE_NRD (1 << 0) -#define AT91_SMC_WRITEMODE BIT(1) -#define AT91_SMC_WRITEMODE_NCS (0 << 1) -#define AT91_SMC_WRITEMODE_NWE (1 << 1) -#define AT91_SMC_EXNWMODE GENMASK(5, 4) -#define AT91_SMC_EXNWMODE_DISABLE (0 << 4) -#define AT91_SMC_EXNWMODE_FROZEN (2 << 4) -#define AT91_SMC_EXNWMODE_READY (3 << 4) -#define AT91_SMC_BAT BIT(8) -#define AT91_SMC_BAT_SELECT (0 << 8) -#define AT91_SMC_BAT_WRITE (1 << 8) -#define AT91_SMC_DBW GENMASK(13, 12) -#define AT91_SMC_DBW_8 (0 << 12) -#define AT91_SMC_DBW_16 (1 << 12) -#define AT91_SMC_DBW_32 (2 << 12) -#define AT91_SMC_TDF GENMASK(19, 16) -#define AT91_SMC_TDF_(x) ((((x) - 1) << 16) & AT91_SMC_TDF) -#define AT91_SMC_TDF_MAX 16 -#define AT91_SMC_TDFMODE_OPTIMIZED BIT(20) -#define AT91_SMC_PMEN BIT(24) -#define AT91_SMC_PS GENMASK(29, 28) -#define AT91_SMC_PS_4 (0 << 28) -#define AT91_SMC_PS_8 (1 << 28) -#define AT91_SMC_PS_16 (2 << 28) -#define AT91_SMC_PS_32 (3 << 28) - - -/* - * This function converts a setup timing expressed in nanoseconds into an - * encoded value that can be written in the SMC_SETUP register. - * - * The following formula is described in atmel datasheets (section - * "SMC Setup Register"): - * - * setup length = (128* SETUP[5] + SETUP[4:0]) - * - * where setup length is the timing expressed in cycles. - */ -static inline u32 at91sam9_smc_setup_ns_to_cycles(unsigned int clk_rate, - u32 timing_ns) -{ - u32 clk_period = DIV_ROUND_UP(NSEC_PER_SEC, clk_rate); - u32 coded_cycles = 0; - u32 cycles; - - cycles = DIV_ROUND_UP(timing_ns, clk_period); - if (cycles / 32) { - coded_cycles |= 1 << 5; - if (cycles < 128) - cycles = 0; - } - - coded_cycles |= cycles % 32; - - return coded_cycles; -} - -/* - * This function converts a pulse timing expressed in nanoseconds into an - * encoded value that can be written in the SMC_PULSE register. - * - * The following formula is described in atmel datasheets (section - * "SMC Pulse Register"): - * - * pulse length = (256* PULSE[6] + PULSE[5:0]) - * - * where pulse length is the timing expressed in cycles. +#define ATMEL_SMC_SETUP(cs) (((cs) * 0x10)) +#define ATMEL_HSMC_SETUP(cs) (0x600 + ((cs) * 0x14)) +#define ATMEL_SMC_PULSE(cs) (((cs) * 0x10) + 0x4) +#define ATMEL_HSMC_PULSE(cs) (0x600 + ((cs) * 0x14) + 0x4) +#define ATMEL_SMC_CYCLE(cs) (((cs) * 0x10) + 0x8) +#define ATMEL_HSMC_CYCLE(cs) (0x600 + ((cs) * 0x14) + 0x8) +#define ATMEL_SMC_NWE_SHIFT 0 +#define ATMEL_SMC_NCS_WR_SHIFT 8 +#define ATMEL_SMC_NRD_SHIFT 16 +#define ATMEL_SMC_NCS_RD_SHIFT 24 + +#define ATMEL_SMC_MODE(cs) (((cs) * 0x10) + 0xc) +#define ATMEL_HSMC_MODE(cs) (0x600 + ((cs) * 0x14) + 0x10) +#define ATMEL_SMC_MODE_READMODE_MASK BIT(0) +#define ATMEL_SMC_MODE_READMODE_NCS (0 << 0) +#define ATMEL_SMC_MODE_READMODE_NRD (1 << 0) +#define ATMEL_SMC_MODE_WRITEMODE_MASK BIT(1) +#define ATMEL_SMC_MODE_WRITEMODE_NCS (0 << 1) +#define ATMEL_SMC_MODE_WRITEMODE_NWE (1 << 1) +#define ATMEL_SMC_MODE_EXNWMODE_MASK GENMASK(5, 4) +#define ATMEL_SMC_MODE_EXNWMODE_DISABLE (0 << 4) +#define ATMEL_SMC_MODE_EXNWMODE_FROZEN (2 << 4) +#define ATMEL_SMC_MODE_EXNWMODE_READY (3 << 4) +#define ATMEL_SMC_MODE_BAT_MASK BIT(8) +#define ATMEL_SMC_MODE_BAT_SELECT (0 << 8) +#define ATMEL_SMC_MODE_BAT_WRITE (1 << 8) +#define ATMEL_SMC_MODE_DBW_MASK GENMASK(13, 12) +#define ATMEL_SMC_MODE_DBW_8 (0 << 12) +#define ATMEL_SMC_MODE_DBW_16 (1 << 12) +#define ATMEL_SMC_MODE_DBW_32 (2 << 12) +#define ATMEL_SMC_MODE_TDF_MASK GENMASK(19, 16) +#define ATMEL_SMC_MODE_TDF(x) (((x) - 1) << 16) +#define ATMEL_SMC_MODE_TDF_MAX 16 +#define ATMEL_SMC_MODE_TDF_MIN 1 +#define ATMEL_SMC_MODE_TDFMODE_OPTIMIZED BIT(20) +#define ATMEL_SMC_MODE_PMEN BIT(24) +#define ATMEL_SMC_MODE_PS_MASK GENMASK(29, 28) +#define ATMEL_SMC_MODE_PS_4 (0 << 28) +#define ATMEL_SMC_MODE_PS_8 (1 << 28) +#define ATMEL_SMC_MODE_PS_16 (2 << 28) +#define ATMEL_SMC_MODE_PS_32 (3 << 28) + +#define ATMEL_HSMC_TIMINGS(cs) (0x600 + ((cs) * 0x14) + 0xc) +#define ATMEL_HSMC_TIMINGS_OCMS BIT(12) +#define ATMEL_HSMC_TIMINGS_RBNSEL(x) ((x) << 28) +#define ATMEL_HSMC_TIMINGS_NFSEL BIT(31) +#define ATMEL_HSMC_TIMINGS_TCLR_SHIFT 0 +#define ATMEL_HSMC_TIMINGS_TADL_SHIFT 4 +#define ATMEL_HSMC_TIMINGS_TAR_SHIFT 8 +#define ATMEL_HSMC_TIMINGS_TRR_SHIFT 16 +#define ATMEL_HSMC_TIMINGS_TWB_SHIFT 24 + +/** + * struct atmel_smc_cs_conf - SMC CS config as described in the datasheet. + * @setup: NCS/NWE/NRD setup timings (not applicable to at91rm9200) + * @pulse: NCS/NWE/NRD pulse timings (not applicable to at91rm9200) + * @cycle: NWE/NRD cycle timings (not applicable to at91rm9200) + * @timings: advanced NAND related timings (only applicable to HSMC) + * @mode: all kind of config parameters (see the fields definition above). + * The mode fields are different on at91rm9200 */ -static inline u32 at91sam9_smc_pulse_ns_to_cycles(unsigned int clk_rate, - u32 timing_ns) -{ - u32 clk_period = DIV_ROUND_UP(NSEC_PER_SEC, clk_rate); - u32 coded_cycles = 0; - u32 cycles; - - cycles = DIV_ROUND_UP(timing_ns, clk_period); - if (cycles / 64) { - coded_cycles |= 1 << 6; - if (cycles < 256) - cycles = 0; - } - - coded_cycles |= cycles % 64; - - return coded_cycles; -} - -/* - * This function converts a cycle timing expressed in nanoseconds into an - * encoded value that can be written in the SMC_CYCLE register. - * - * The following formula is described in atmel datasheets (section - * "SMC Cycle Register"): - * - * cycle length = (CYCLE[8:7]*256 + CYCLE[6:0]) - * - * where cycle length is the timing expressed in cycles. - */ -static inline u32 at91sam9_smc_cycle_ns_to_cycles(unsigned int clk_rate, - u32 timing_ns) -{ - u32 clk_period = DIV_ROUND_UP(NSEC_PER_SEC, clk_rate); - u32 coded_cycles = 0; - u32 cycles; - - cycles = DIV_ROUND_UP(timing_ns, clk_period); - if (cycles / 128) { - coded_cycles = cycles / 256; - cycles %= 256; - if (cycles >= 128) { - coded_cycles++; - cycles = 0; - } - - if (coded_cycles > 0x3) { - coded_cycles = 0x3; - cycles = 0x7f; - } - - coded_cycles <<= 7; - } - - coded_cycles |= cycles % 128; - - return coded_cycles; -} +struct atmel_smc_cs_conf { + u32 setup; + u32 pulse; + u32 cycle; + u32 timings; + u32 mode; +}; + +void atmel_smc_cs_conf_init(struct atmel_smc_cs_conf *conf); +int atmel_smc_cs_conf_set_timing(struct atmel_smc_cs_conf *conf, + unsigned int shift, + unsigned int ncycles); +int atmel_smc_cs_conf_set_setup(struct atmel_smc_cs_conf *conf, + unsigned int shift, unsigned int ncycles); +int atmel_smc_cs_conf_set_pulse(struct atmel_smc_cs_conf *conf, + unsigned int shift, unsigned int ncycles); +int atmel_smc_cs_conf_set_cycle(struct atmel_smc_cs_conf *conf, + unsigned int shift, unsigned int ncycles); +void atmel_smc_cs_conf_apply(struct regmap *regmap, int cs, + const struct atmel_smc_cs_conf *conf); +void atmel_hsmc_cs_conf_apply(struct regmap *regmap, int cs, + const struct atmel_smc_cs_conf *conf); +void atmel_smc_cs_conf_get(struct regmap *regmap, int cs, + struct atmel_smc_cs_conf *conf); +void atmel_hsmc_cs_conf_get(struct regmap *regmap, int cs, + struct atmel_smc_cs_conf *conf); #endif /* _LINUX_MFD_SYSCON_ATMEL_SMC_H_ */ diff --git a/include/linux/mfd/syscon/exynos5-pmu.h b/include/linux/mfd/syscon/exynos5-pmu.h index c28ff21ca4d2..b4942a32b81d 100644 --- a/include/linux/mfd/syscon/exynos5-pmu.h +++ b/include/linux/mfd/syscon/exynos5-pmu.h @@ -12,41 +12,8 @@ #ifndef _LINUX_MFD_SYSCON_PMU_EXYNOS5_H_ #define _LINUX_MFD_SYSCON_PMU_EXYNOS5_H_ -/* Exynos5 PMU register definitions */ -#define EXYNOS5_HDMI_PHY_CONTROL (0x700) -#define EXYNOS5_USBDRD_PHY_CONTROL (0x704) - -/* Exynos5250 specific register definitions */ -#define EXYNOS5_USBHOST_PHY_CONTROL (0x708) -#define EXYNOS5_EFNAND_PHY_CONTROL (0x70c) -#define EXYNOS5_MIPI_PHY0_CONTROL (0x710) -#define EXYNOS5_MIPI_PHY1_CONTROL (0x714) -#define EXYNOS5_ADC_PHY_CONTROL (0x718) -#define EXYNOS5_MTCADC_PHY_CONTROL (0x71c) -#define EXYNOS5_DPTX_PHY_CONTROL (0x720) -#define EXYNOS5_SATA_PHY_CONTROL (0x724) - -/* Exynos5420 specific register definitions */ -#define EXYNOS5420_USBDRD1_PHY_CONTROL (0x708) -#define EXYNOS5420_USBHOST_PHY_CONTROL (0x70c) -#define EXYNOS5420_MIPI_PHY0_CONTROL (0x714) -#define EXYNOS5420_MIPI_PHY1_CONTROL (0x718) -#define EXYNOS5420_MIPI_PHY2_CONTROL (0x71c) -#define EXYNOS5420_ADC_PHY_CONTROL (0x720) -#define EXYNOS5420_MTCADC_PHY_CONTROL (0x724) -#define EXYNOS5420_DPTX_PHY_CONTROL (0x728) - -/* Exynos5433 specific register definitions */ -#define EXYNOS5433_USBHOST30_PHY_CONTROL (0x728) -#define EXYNOS5433_MIPI_PHY0_CONTROL (0x710) -#define EXYNOS5433_MIPI_PHY1_CONTROL (0x714) -#define EXYNOS5433_MIPI_PHY2_CONTROL (0x718) - #define EXYNOS5_PHY_ENABLE BIT(0) #define EXYNOS5_MIPI_PHY_S_RESETN BIT(1) #define EXYNOS5_MIPI_PHY_M_RESETN BIT(2) -#define EXYNOS5433_PAD_RETENTION_AUD_OPTION (0x3028) -#define EXYNOS5433_PAD_INITIATE_WAKEUP_FROM_LOWPWR BIT(28) - #endif /* _LINUX_MFD_SYSCON_PMU_EXYNOS5_H_ */ diff --git a/include/linux/mfd/syscon/imx7-iomuxc-gpr.h b/include/linux/mfd/syscon/imx7-iomuxc-gpr.h index 4585d6105d68..abbd52466573 100644 --- a/include/linux/mfd/syscon/imx7-iomuxc-gpr.h +++ b/include/linux/mfd/syscon/imx7-iomuxc-gpr.h @@ -44,4 +44,8 @@ #define IMX7D_GPR5_CSI_MUX_CONTROL_MIPI (0x1 << 4) +#define IMX7D_GPR12_PCIE_PHY_REFCLK_SEL BIT(5) + +#define IMX7D_GPR22_PCIE_PHY_PLL_LOCKED BIT(31) + #endif /* __LINUX_IMX7_IOMUXC_GPR_H */ diff --git a/include/linux/mfd/ti-lmu-register.h b/include/linux/mfd/ti-lmu-register.h new file mode 100644 index 000000000000..2125c7c02818 --- /dev/null +++ b/include/linux/mfd/ti-lmu-register.h @@ -0,0 +1,280 @@ +/* + * TI LMU (Lighting Management Unit) Device Register Map + * + * Copyright 2017 Texas Instruments + * + * Author: Milo Kim <milo.kim@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __MFD_TI_LMU_REGISTER_H__ +#define __MFD_TI_LMU_REGISTER_H__ + +#include <linux/bitops.h> + +/* LM3532 */ +#define LM3532_REG_OUTPUT_CFG 0x10 +#define LM3532_ILED1_CFG_MASK 0x03 +#define LM3532_ILED2_CFG_MASK 0x0C +#define LM3532_ILED3_CFG_MASK 0x30 +#define LM3532_ILED1_CFG_SHIFT 0 +#define LM3532_ILED2_CFG_SHIFT 2 +#define LM3532_ILED3_CFG_SHIFT 4 + +#define LM3532_REG_RAMPUP 0x12 +#define LM3532_REG_RAMPDN LM3532_REG_RAMPUP +#define LM3532_RAMPUP_MASK 0x07 +#define LM3532_RAMPUP_SHIFT 0 +#define LM3532_RAMPDN_MASK 0x38 +#define LM3532_RAMPDN_SHIFT 3 + +#define LM3532_REG_ENABLE 0x1D + +#define LM3532_REG_PWM_A_CFG 0x13 +#define LM3532_PWM_A_MASK 0x05 /* zone 0 */ +#define LM3532_PWM_ZONE_0 BIT(2) + +#define LM3532_REG_PWM_B_CFG 0x14 +#define LM3532_PWM_B_MASK 0x09 /* zone 1 */ +#define LM3532_PWM_ZONE_1 BIT(3) + +#define LM3532_REG_PWM_C_CFG 0x15 +#define LM3532_PWM_C_MASK 0x11 /* zone 2 */ +#define LM3532_PWM_ZONE_2 BIT(4) + +#define LM3532_REG_ZONE_CFG_A 0x16 +#define LM3532_REG_ZONE_CFG_B 0x18 +#define LM3532_REG_ZONE_CFG_C 0x1A +#define LM3532_ZONE_MASK (BIT(2) | BIT(3) | BIT(4)) +#define LM3532_ZONE_0 0 +#define LM3532_ZONE_1 BIT(2) +#define LM3532_ZONE_2 BIT(3) + +#define LM3532_REG_BRT_A 0x70 /* zone 0 */ +#define LM3532_REG_BRT_B 0x76 /* zone 1 */ +#define LM3532_REG_BRT_C 0x7C /* zone 2 */ + +#define LM3532_MAX_REG 0x7E + +/* LM3631 */ +#define LM3631_REG_DEVCTRL 0x00 +#define LM3631_LCD_EN_MASK BIT(1) +#define LM3631_BL_EN_MASK BIT(0) + +#define LM3631_REG_BRT_LSB 0x01 +#define LM3631_REG_BRT_MSB 0x02 + +#define LM3631_REG_BL_CFG 0x06 +#define LM3631_BL_CHANNEL_MASK BIT(3) +#define LM3631_BL_DUAL_CHANNEL 0 +#define LM3631_BL_SINGLE_CHANNEL BIT(3) +#define LM3631_MAP_MASK BIT(5) +#define LM3631_EXPONENTIAL_MAP 0 + +#define LM3631_REG_BRT_MODE 0x08 +#define LM3631_MODE_MASK (BIT(1) | BIT(2) | BIT(3)) +#define LM3631_DEFAULT_MODE (BIT(1) | BIT(3)) + +#define LM3631_REG_SLOPE 0x09 +#define LM3631_SLOPE_MASK 0xF0 +#define LM3631_SLOPE_SHIFT 4 + +#define LM3631_REG_LDO_CTRL1 0x0A +#define LM3631_EN_OREF_MASK BIT(0) +#define LM3631_EN_VNEG_MASK BIT(1) +#define LM3631_EN_VPOS_MASK BIT(2) + +#define LM3631_REG_LDO_CTRL2 0x0B +#define LM3631_EN_CONT_MASK BIT(0) + +#define LM3631_REG_VOUT_CONT 0x0C +#define LM3631_VOUT_CONT_MASK (BIT(6) | BIT(7)) + +#define LM3631_REG_VOUT_BOOST 0x0C +#define LM3631_REG_VOUT_POS 0x0D +#define LM3631_REG_VOUT_NEG 0x0E +#define LM3631_REG_VOUT_OREF 0x0F +#define LM3631_VOUT_MASK 0x3F + +#define LM3631_REG_ENTIME_VCONT 0x0B +#define LM3631_ENTIME_CONT_MASK 0x70 + +#define LM3631_REG_ENTIME_VOREF 0x0F +#define LM3631_REG_ENTIME_VPOS 0x10 +#define LM3631_REG_ENTIME_VNEG 0x11 +#define LM3631_ENTIME_MASK 0xF0 +#define LM3631_ENTIME_SHIFT 4 + +#define LM3631_MAX_REG 0x16 + +/* LM3632 */ +#define LM3632_REG_CONFIG1 0x02 +#define LM3632_OVP_MASK (BIT(5) | BIT(6) | BIT(7)) +#define LM3632_OVP_25V BIT(6) + +#define LM3632_REG_CONFIG2 0x03 +#define LM3632_SWFREQ_MASK BIT(7) +#define LM3632_SWFREQ_1MHZ BIT(7) + +#define LM3632_REG_BRT_LSB 0x04 +#define LM3632_REG_BRT_MSB 0x05 + +#define LM3632_REG_IO_CTRL 0x09 +#define LM3632_PWM_MASK BIT(6) +#define LM3632_I2C_MODE 0 +#define LM3632_PWM_MODE BIT(6) + +#define LM3632_REG_ENABLE 0x0A +#define LM3632_BL_EN_MASK BIT(0) +#define LM3632_BL_CHANNEL_MASK (BIT(3) | BIT(4)) +#define LM3632_BL_SINGLE_CHANNEL BIT(4) +#define LM3632_BL_DUAL_CHANNEL BIT(3) + +#define LM3632_REG_BIAS_CONFIG 0x0C +#define LM3632_EXT_EN_MASK BIT(0) +#define LM3632_EN_VNEG_MASK BIT(1) +#define LM3632_EN_VPOS_MASK BIT(2) + +#define LM3632_REG_VOUT_BOOST 0x0D +#define LM3632_REG_VOUT_POS 0x0E +#define LM3632_REG_VOUT_NEG 0x0F +#define LM3632_VOUT_MASK 0x3F + +#define LM3632_MAX_REG 0x10 + +/* LM3633 */ +#define LM3633_REG_HVLED_OUTPUT_CFG 0x10 +#define LM3633_HVLED1_CFG_MASK BIT(0) +#define LM3633_HVLED2_CFG_MASK BIT(1) +#define LM3633_HVLED3_CFG_MASK BIT(2) +#define LM3633_HVLED1_CFG_SHIFT 0 +#define LM3633_HVLED2_CFG_SHIFT 1 +#define LM3633_HVLED3_CFG_SHIFT 2 + +#define LM3633_REG_BANK_SEL 0x11 + +#define LM3633_REG_BL0_RAMP 0x12 +#define LM3633_REG_BL1_RAMP 0x13 +#define LM3633_BL_RAMPUP_MASK 0xF0 +#define LM3633_BL_RAMPUP_SHIFT 4 +#define LM3633_BL_RAMPDN_MASK 0x0F +#define LM3633_BL_RAMPDN_SHIFT 0 + +#define LM3633_REG_BL_RAMP_CONF 0x1B +#define LM3633_BL_RAMP_MASK 0x0F +#define LM3633_BL_RAMP_EACH 0x05 + +#define LM3633_REG_PTN0_RAMP 0x1C +#define LM3633_REG_PTN1_RAMP 0x1D +#define LM3633_PTN_RAMPUP_MASK 0x70 +#define LM3633_PTN_RAMPUP_SHIFT 4 +#define LM3633_PTN_RAMPDN_MASK 0x07 +#define LM3633_PTN_RAMPDN_SHIFT 0 + +#define LM3633_REG_LED_MAPPING_MODE 0x1F +#define LM3633_LED_EXPONENTIAL BIT(1) + +#define LM3633_REG_IMAX_HVLED_A 0x20 +#define LM3633_REG_IMAX_HVLED_B 0x21 +#define LM3633_REG_IMAX_LVLED_BASE 0x22 + +#define LM3633_REG_BL_FEEDBACK_ENABLE 0x28 + +#define LM3633_REG_ENABLE 0x2B +#define LM3633_LED_BANK_OFFSET 2 + +#define LM3633_REG_PATTERN 0x2C + +#define LM3633_REG_BOOST_CFG 0x2D +#define LM3633_OVP_MASK (BIT(1) | BIT(2)) +#define LM3633_OVP_40V 0x6 + +#define LM3633_REG_PWM_CFG 0x2F +#define LM3633_PWM_A_MASK BIT(0) +#define LM3633_PWM_B_MASK BIT(1) + +#define LM3633_REG_BRT_HVLED_A_LSB 0x40 +#define LM3633_REG_BRT_HVLED_A_MSB 0x41 +#define LM3633_REG_BRT_HVLED_B_LSB 0x42 +#define LM3633_REG_BRT_HVLED_B_MSB 0x43 + +#define LM3633_REG_BRT_LVLED_BASE 0x44 + +#define LM3633_REG_PTN_DELAY 0x50 + +#define LM3633_REG_PTN_LOWTIME 0x51 + +#define LM3633_REG_PTN_HIGHTIME 0x52 + +#define LM3633_REG_PTN_LOWBRT 0x53 + +#define LM3633_REG_PTN_HIGHBRT LM3633_REG_BRT_LVLED_BASE + +#define LM3633_REG_BL_OPEN_FAULT_STATUS 0xB0 + +#define LM3633_REG_BL_SHORT_FAULT_STATUS 0xB2 + +#define LM3633_REG_MONITOR_ENABLE 0xB4 + +#define LM3633_MAX_REG 0xB4 + +/* LM3695 */ +#define LM3695_REG_GP 0x10 +#define LM3695_BL_CHANNEL_MASK BIT(3) +#define LM3695_BL_DUAL_CHANNEL 0 +#define LM3695_BL_SINGLE_CHANNEL BIT(3) +#define LM3695_BRT_RW_MASK BIT(2) +#define LM3695_BL_EN_MASK BIT(0) + +#define LM3695_REG_BRT_LSB 0x13 +#define LM3695_REG_BRT_MSB 0x14 + +#define LM3695_MAX_REG 0x14 + +/* LM3697 */ +#define LM3697_REG_HVLED_OUTPUT_CFG 0x10 +#define LM3697_HVLED1_CFG_MASK BIT(0) +#define LM3697_HVLED2_CFG_MASK BIT(1) +#define LM3697_HVLED3_CFG_MASK BIT(2) +#define LM3697_HVLED1_CFG_SHIFT 0 +#define LM3697_HVLED2_CFG_SHIFT 1 +#define LM3697_HVLED3_CFG_SHIFT 2 + +#define LM3697_REG_BL0_RAMP 0x11 +#define LM3697_REG_BL1_RAMP 0x12 +#define LM3697_RAMPUP_MASK 0xF0 +#define LM3697_RAMPUP_SHIFT 4 +#define LM3697_RAMPDN_MASK 0x0F +#define LM3697_RAMPDN_SHIFT 0 + +#define LM3697_REG_RAMP_CONF 0x14 +#define LM3697_RAMP_MASK 0x0F +#define LM3697_RAMP_EACH 0x05 + +#define LM3697_REG_PWM_CFG 0x1C +#define LM3697_PWM_A_MASK BIT(0) +#define LM3697_PWM_B_MASK BIT(1) + +#define LM3697_REG_IMAX_A 0x17 +#define LM3697_REG_IMAX_B 0x18 + +#define LM3697_REG_FEEDBACK_ENABLE 0x19 + +#define LM3697_REG_BRT_A_LSB 0x20 +#define LM3697_REG_BRT_A_MSB 0x21 +#define LM3697_REG_BRT_B_LSB 0x22 +#define LM3697_REG_BRT_B_MSB 0x23 + +#define LM3697_REG_ENABLE 0x24 + +#define LM3697_REG_OPEN_FAULT_STATUS 0xB0 + +#define LM3697_REG_SHORT_FAULT_STATUS 0xB2 + +#define LM3697_REG_MONITOR_ENABLE 0xB4 + +#define LM3697_MAX_REG 0xB4 +#endif diff --git a/include/linux/mfd/ti-lmu.h b/include/linux/mfd/ti-lmu.h new file mode 100644 index 000000000000..09d5f30384e5 --- /dev/null +++ b/include/linux/mfd/ti-lmu.h @@ -0,0 +1,87 @@ +/* + * TI LMU (Lighting Management Unit) Devices + * + * Copyright 2017 Texas Instruments + * + * Author: Milo Kim <milo.kim@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __MFD_TI_LMU_H__ +#define __MFD_TI_LMU_H__ + +#include <linux/gpio.h> +#include <linux/notifier.h> +#include <linux/regmap.h> + +/* Notifier event */ +#define LMU_EVENT_MONITOR_DONE 0x01 + +enum ti_lmu_id { + LM3532, + LM3631, + LM3632, + LM3633, + LM3695, + LM3697, + LMU_MAX_ID, +}; + +enum ti_lmu_max_current { + LMU_IMAX_5mA, + LMU_IMAX_6mA, + LMU_IMAX_7mA = 0x03, + LMU_IMAX_8mA, + LMU_IMAX_9mA, + LMU_IMAX_10mA = 0x07, + LMU_IMAX_11mA, + LMU_IMAX_12mA, + LMU_IMAX_13mA, + LMU_IMAX_14mA, + LMU_IMAX_15mA = 0x0D, + LMU_IMAX_16mA, + LMU_IMAX_17mA, + LMU_IMAX_18mA, + LMU_IMAX_19mA, + LMU_IMAX_20mA = 0x13, + LMU_IMAX_21mA, + LMU_IMAX_22mA, + LMU_IMAX_23mA = 0x17, + LMU_IMAX_24mA, + LMU_IMAX_25mA, + LMU_IMAX_26mA, + LMU_IMAX_27mA = 0x1C, + LMU_IMAX_28mA, + LMU_IMAX_29mA, + LMU_IMAX_30mA, +}; + +enum lm363x_regulator_id { + LM3631_BOOST, /* Boost output */ + LM3631_LDO_CONT, /* Display panel controller */ + LM3631_LDO_OREF, /* Gamma reference */ + LM3631_LDO_POS, /* Positive display bias output */ + LM3631_LDO_NEG, /* Negative display bias output */ + LM3632_BOOST, /* Boost output */ + LM3632_LDO_POS, /* Positive display bias output */ + LM3632_LDO_NEG, /* Negative display bias output */ +}; + +/** + * struct ti_lmu + * + * @dev: Parent device pointer + * @regmap: Used for i2c communcation on accessing registers + * @en_gpio: GPIO for HWEN pin [Optional] + * @notifier: Notifier for reporting hwmon event + */ +struct ti_lmu { + struct device *dev; + struct regmap *regmap; + int en_gpio; + struct blocking_notifier_head notifier; +}; +#endif diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index fba44abd05ba..26e8f8c0a6db 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -13,15 +13,15 @@ #define tmio_ioread16(addr) readw(addr) #define tmio_ioread16_rep(r, b, l) readsw(r, b, l) #define tmio_ioread32(addr) \ - (((u32) readw((addr))) | (((u32) readw((addr) + 2)) << 16)) + (((u32)readw((addr))) | (((u32)readw((addr) + 2)) << 16)) #define tmio_iowrite8(val, addr) writeb((val), (addr)) #define tmio_iowrite16(val, addr) writew((val), (addr)) #define tmio_iowrite16_rep(r, b, l) writesw(r, b, l) #define tmio_iowrite32(val, addr) \ do { \ - writew((val), (addr)); \ - writew((val) >> 16, (addr) + 2); \ + writew((val), (addr)); \ + writew((val) >> 16, (addr) + 2); \ } while (0) #define CNF_CMD 0x04 @@ -55,59 +55,57 @@ } while (0) /* tmio MMC platform flags */ -#define TMIO_MMC_WRPROTECT_DISABLE (1 << 0) +#define TMIO_MMC_WRPROTECT_DISABLE BIT(0) /* * Some controllers can support a 2-byte block size when the bus width * is configured in 4-bit mode. */ -#define TMIO_MMC_BLKSZ_2BYTES (1 << 1) +#define TMIO_MMC_BLKSZ_2BYTES BIT(1) /* * Some controllers can support SDIO IRQ signalling. */ -#define TMIO_MMC_SDIO_IRQ (1 << 2) +#define TMIO_MMC_SDIO_IRQ BIT(2) -/* Some features are only available or tested on RCar Gen2 or later */ -#define TMIO_MMC_MIN_RCAR2 (1 << 3) +/* Some features are only available or tested on R-Car Gen2 or later */ +#define TMIO_MMC_MIN_RCAR2 BIT(3) /* * Some controllers require waiting for the SD bus to become * idle before writing to some registers. */ -#define TMIO_MMC_HAS_IDLE_WAIT (1 << 4) +#define TMIO_MMC_HAS_IDLE_WAIT BIT(4) /* * A GPIO is used for card hotplug detection. We need an extra flag for this, * because 0 is a valid GPIO number too, and requiring users to specify * cd_gpio < 0 to disable GPIO hotplug would break backwards compatibility. */ -#define TMIO_MMC_USE_GPIO_CD (1 << 5) +#define TMIO_MMC_USE_GPIO_CD BIT(5) /* * Some controllers doesn't have over 0x100 register. * it is used to checking accessibility of * CTL_SD_CARD_CLK_CTL / CTL_CLK_AND_WAIT_CTL */ -#define TMIO_MMC_HAVE_HIGH_REG (1 << 6) +#define TMIO_MMC_HAVE_HIGH_REG BIT(6) /* * Some controllers have CMD12 automatically * issue/non-issue register */ -#define TMIO_MMC_HAVE_CMD12_CTRL (1 << 7) +#define TMIO_MMC_HAVE_CMD12_CTRL BIT(7) -/* - * Some controllers needs to set 1 on SDIO status reserved bits - */ -#define TMIO_MMC_SDIO_STATUS_QUIRK (1 << 8) +/* Controller has some SDIO status bits which must be 1 */ +#define TMIO_MMC_SDIO_STATUS_SETBITS BIT(8) /* * Some controllers have a 32-bit wide data port register */ -#define TMIO_MMC_32BIT_DATA_PORT (1 << 9) +#define TMIO_MMC_32BIT_DATA_PORT BIT(9) /* * Some controllers allows to set SDx actual clock */ -#define TMIO_MMC_CLK_ACTUAL (1 << 10) +#define TMIO_MMC_CLK_ACTUAL BIT(10) int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); @@ -148,9 +146,9 @@ struct tmio_nand_data { struct tmio_fb_data { int (*lcd_set_power)(struct platform_device *fb_dev, - bool on); + bool on); int (*lcd_mode)(struct platform_device *fb_dev, - const struct fb_videomode *mode); + const struct fb_videomode *mode); int num_modes; struct fb_videomode *modes; @@ -159,5 +157,4 @@ struct tmio_fb_data { int width; }; - #endif diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index 6483a6fdce59..deffdcd0236f 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -134,6 +134,7 @@ /* RTC_CTRL_REG bitfields */ #define TPS65910_RTC_CTRL_STOP_RTC 0x01 /*0=stop, 1=run */ +#define TPS65910_RTC_CTRL_AUTO_COMP 0x04 #define TPS65910_RTC_CTRL_GET_TIME 0x40 /* RTC_STATUS_REG bitfields */ @@ -878,7 +879,7 @@ struct tps65910_board { bool en_ck32k_xtal; bool en_dev_slp; bool pm_off; - struct tps65910_sleep_keepon_data *slp_keepon; + struct tps65910_sleep_keepon_data slp_keepon; bool en_gpio_sleep[TPS6591X_MAX_NUM_GPIO]; unsigned long regulator_ext_sleep_control[TPS65910_NUM_REGS]; struct regulator_init_data *tps65910_pmic_init_data[TPS65910_NUM_REGS]; diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 76c22648436f..b49fa67612f1 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -21,6 +21,8 @@ #include <linux/list.h> #include <linux/regmap.h> #include <linux/mfd/wm831x/auxadc.h> +#include <linux/mfd/wm831x/pdata.h> +#include <linux/of.h> /* * Register values. @@ -367,6 +369,9 @@ struct wm831x { struct regmap *regmap; + struct wm831x_pdata pdata; + enum wm831x_parent type; + int irq; /* Our chip IRQ */ struct mutex irq_lock; struct irq_domain *irq_domain; @@ -412,7 +417,7 @@ int wm831x_set_bits(struct wm831x *wm831x, unsigned short reg, int wm831x_bulk_read(struct wm831x *wm831x, unsigned short reg, int count, u16 *buf); -int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq); +int wm831x_device_init(struct wm831x *wm831x, int irq); void wm831x_device_exit(struct wm831x *wm831x); int wm831x_device_suspend(struct wm831x *wm831x); void wm831x_device_shutdown(struct wm831x *wm831x); @@ -427,4 +432,6 @@ static inline int wm831x_irq(struct wm831x *wm831x, int irq) extern struct regmap_config wm831x_regmap_config; +extern const struct of_device_id wm831x_of_match[]; + #endif diff --git a/include/linux/mg_disk.h b/include/linux/mg_disk.h deleted file mode 100644 index e11f4d9f1c2e..000000000000 --- a/include/linux/mg_disk.h +++ /dev/null @@ -1,45 +0,0 @@ -/* - * include/linux/mg_disk.c - * - * Private data for mflash platform driver - * - * (c) 2008 mGine Co.,LTD - * (c) 2008 unsik Kim <donari75@gmail.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __MG_DISK_H__ -#define __MG_DISK_H__ - -/* name for platform device */ -#define MG_DEV_NAME "mg_disk" - -/* names of GPIO resource */ -#define MG_RST_PIN "mg_rst" -/* except MG_BOOT_DEV, reset-out pin should be assigned */ -#define MG_RSTOUT_PIN "mg_rstout" - -/* device attribution */ -/* use mflash as boot device */ -#define MG_BOOT_DEV (1 << 0) -/* use mflash as storage device */ -#define MG_STORAGE_DEV (1 << 1) -/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */ -#define MG_STORAGE_DEV_SKIP_RST (1 << 2) - -/* private driver data */ -struct mg_drv_data { - /* disk resource */ - u32 use_polling; - - /* device attribution */ - u32 dev_attr; - - /* internally used */ - void *host; -}; - -#endif diff --git a/include/linux/mic_bus.h b/include/linux/mic_bus.h index 27d7c95fd0da..504d54c71bdb 100644 --- a/include/linux/mic_bus.h +++ b/include/linux/mic_bus.h @@ -90,7 +90,7 @@ struct mbus_hw_ops { }; struct mbus_device * -mbus_register_device(struct device *pdev, int id, struct dma_map_ops *dma_ops, +mbus_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops, struct mbus_hw_ops *hw_ops, int index, void __iomem *mmio_va); void mbus_unregister_device(struct mbus_device *mbdev); diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index f541da68d1e7..472fa4d4ea62 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -37,6 +37,8 @@ #define PHY_ID_KSZ8795 0x00221550 +#define PHY_ID_KSZ9477 0x00221631 + /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 #define MICREL_PHY_FXEN 0x00000002 diff --git a/include/linux/migrate.h b/include/linux/migrate.h index ae8d475a9385..3e0d405dc842 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -4,6 +4,7 @@ #include <linux/mm.h> #include <linux/mempolicy.h> #include <linux/migrate_mode.h> +#include <linux/hugetlb.h> typedef struct page *new_page_t(struct page *page, unsigned long private, int **reason); @@ -30,14 +31,30 @@ enum migrate_reason { /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ extern char *migrate_reason_names[MR_TYPES]; +static inline struct page *new_page_nodemask(struct page *page, + int preferred_nid, nodemask_t *nodemask) +{ + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; + + if (PageHuge(page)) + return alloc_huge_page_nodemask(page_hstate(compound_head(page)), + preferred_nid, nodemask); + + if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) + gfp_mask |= __GFP_HIGHMEM; + + return __alloc_pages_nodemask(gfp_mask, 0, preferred_nid, nodemask); +} + #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); -extern int migrate_page(struct address_space *, - struct page *, struct page *, enum migrate_mode); +extern int migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page, + enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); -extern bool isolate_movable_page(struct page *page, isolate_mode_t mode); +extern int isolate_movable_page(struct page *page, isolate_mode_t mode); extern void putback_movable_page(struct page *page); extern int migrate_prep(void); @@ -56,6 +73,8 @@ static inline int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason) { return -ENOSYS; } +static inline int isolate_movable_page(struct page *page, isolate_mode_t mode) + { return -EBUSY; } static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } diff --git a/include/linux/mii.h b/include/linux/mii.h index 1629a0c32679..e870bfa6abfe 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -31,7 +31,7 @@ struct mii_if_info { extern int mii_link_ok (struct mii_if_info *mii); extern int mii_nway_restart (struct mii_if_info *mii); extern int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); -extern int mii_ethtool_get_link_ksettings( +extern void mii_ethtool_get_link_ksettings( struct mii_if_info *mii, struct ethtool_link_ksettings *cmd); extern int mii_ethtool_sset(struct mii_if_info *mii, struct ethtool_cmd *ecmd); extern int mii_ethtool_set_link_ksettings( diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index ed30d5d713e3..58751eae5f77 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -22,6 +22,7 @@ /*#define ADB_MOUSE_MINOR 10 FIXME OBSOLETE */ #define WATCHDOG_MINOR 130 /* Watchdog timer */ #define TEMP_MINOR 131 /* Temperature Sensor */ +#define APM_MINOR_DEV 134 #define RTC_MINOR 135 #define EFI_RTC_MINOR 136 /* EFI Time services */ #define VHCI_MINOR 137 @@ -31,6 +32,7 @@ #define SGI_MMTIMER 153 #define STORE_QUEUE_MINOR 155 /* unused */ #define I2O_MINOR 166 +#define HWRNG_MINOR 183 #define MICROCODE_MINOR 184 #define IRNET_MINOR 187 #define VFIO_MINOR 196 @@ -52,6 +54,7 @@ #define VHOST_NET_MINOR 238 #define UHID_MINOR 239 #define USERIO_MINOR 240 +#define VHOST_VSOCK_MINOR 241 #define MISC_DYNAMIC_MINOR 255 struct device; diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 1f3568694a57..7b74afcbbab2 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -308,7 +308,7 @@ int mlx4_get_counter_stats(struct mlx4_dev *dev, int counter_index, int mlx4_get_vf_stats(struct mlx4_dev *dev, int port, int vf_idx, struct ifla_vf_stats *vf_stats); u32 mlx4_comm_get_version(void); -int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); +int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u8 *mac); int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos, __be16 proto); int mlx4_set_vf_rate(struct mlx4_dev *dev, int port, int vf, int min_tx_rate, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6533c16e27ad..aad5d81dfb44 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -108,7 +108,7 @@ enum { MLX4_MFUNC_EQE_MASK = (MLX4_MFUNC_MAX_EQES - 1) }; -/* Driver supports 3 diffrent device methods to manage traffic steering: +/* Driver supports 3 different device methods to manage traffic steering: * -device managed - High level API for ib and eth flow steering. FW is * managing flow steering tables. * - B0 steering mode - Common low level API for ib and (if supported) eth. @@ -476,6 +476,7 @@ enum { enum { MLX4_INTERFACE_STATE_UP = 1 << 0, MLX4_INTERFACE_STATE_DELETION = 1 << 1, + MLX4_INTERFACE_STATE_NOWAIT = 1 << 2, }; #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \ @@ -1010,8 +1011,7 @@ struct mlx4_mad_ifc { #define mlx4_foreach_ib_transport_port(port, dev) \ for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \ if (((dev)->caps.port_mask[port] == MLX4_PORT_TYPE_IB) || \ - ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE) || \ - ((dev)->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2)) + ((dev)->caps.port_mask[port] == MLX4_PORT_TYPE_ETH)) #define MLX4_INVALID_SLAVE_ID 0xFF #define MLX4_SINK_COUNTER_INDEX(dev) (dev->caps.max_counters - 1) @@ -1068,7 +1068,7 @@ static inline int mlx4_is_eth(struct mlx4_dev *dev, int port) } int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct, - struct mlx4_buf *buf, gfp_t gfp); + struct mlx4_buf *buf); void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf); static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset) { @@ -1105,10 +1105,9 @@ int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw); int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, int start_index, int npages, u64 *page_list); int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, - struct mlx4_buf *buf, gfp_t gfp); + struct mlx4_buf *buf); -int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order, - gfp_t gfp); +int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order); void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db); int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres, @@ -1124,8 +1123,7 @@ int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base, u8 flags); void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt); -int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp, - gfp_t gfp); +int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp); void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp); int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcdn, @@ -1374,6 +1372,7 @@ int mlx4_get_base_qpn(struct mlx4_dev *dev, u8 port); int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac); int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu, u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx); +int mlx4_SET_PORT_user_mtu(struct mlx4_dev *dev, u8 port, u16 user_mtu); int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, u8 promisc); int mlx4_SET_PORT_BEACON(struct mlx4_dev *dev, u8 port, u16 time); @@ -1539,8 +1538,13 @@ enum mlx4_ptys_proto { MLX4_PTYS_EN = 1<<2, }; +enum mlx4_ptys_flags { + MLX4_PTYS_AN_DISABLE_CAP = 1 << 5, + MLX4_PTYS_AN_DISABLE_ADMIN = 1 << 6, +}; + struct mlx4_ptys_reg { - u8 resrvd1; + u8 flags; u8 local_port; u8 resrvd2; u8 proto_mask; diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index bd0e7075ea6d..a858bcb6220b 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -104,4 +104,14 @@ static inline u64 mlx4_mac_to_u64(u8 *addr) return mac; } +static inline void mlx4_u64_to_mac(u8 *addr, u64 mac) +{ + int i; + + for (i = ETH_ALEN; i > 0; i--) { + addr[i - 1] = mac & 0xFF; + mac >>= 8; + } +} + #endif /* MLX4_DRIVER_H */ diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index b4ee8f62ce8d..8e2828d48d7f 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -470,6 +470,7 @@ struct mlx4_update_qp_params { u16 rate_val; }; +struct mlx4_qp *mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn); int mlx4_update_qp(struct mlx4_dev *dev, u32 qpn, enum mlx4_update_qp_attr attr, struct mlx4_update_qp_params *params); diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 7c3c0d3aca37..95898847c7d4 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -42,13 +42,13 @@ struct mlx5_core_cq { int cqe_sz; __be32 *set_ci_db; __be32 *arm_db; + struct mlx5_uars_page *uar; atomic_t refcount; struct completion free; unsigned vector; unsigned int irqn; void (*comp) (struct mlx5_core_cq *); void (*event) (struct mlx5_core_cq *, enum mlx5_event); - struct mlx5_uar *uar; u32 cons_index; unsigned arm_sn; struct mlx5_rsc_debug *dbg; @@ -144,7 +144,6 @@ enum { static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd, void __iomem *uar_page, - spinlock_t *doorbell_lock, u32 cons_index) { __be32 doorbell[2]; @@ -164,7 +163,7 @@ static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd, doorbell[0] = cpu_to_be32(sn << 28 | cmd | ci); doorbell[1] = cpu_to_be32(cq->cqn); - mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, doorbell_lock); + mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, NULL); } int mlx5_init_cq_table(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 52b437431c6a..f31a0b5377e1 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -67,10 +67,11 @@ /* insert a value to a struct */ #define MLX5_SET(typ, p, fld, v) do { \ + u32 _v = v; \ BUILD_BUG_ON(__mlx5_st_sz_bits(typ) % 32); \ *((__be32 *)(p) + __mlx5_dw_off(typ, fld)) = \ cpu_to_be32((be32_to_cpu(*((__be32 *)(p) + __mlx5_dw_off(typ, fld))) & \ - (~__mlx5_dw_mask(typ, fld))) | (((v) & __mlx5_mask(typ, fld)) \ + (~__mlx5_dw_mask(typ, fld))) | (((_v) & __mlx5_mask(typ, fld)) \ << __mlx5_dw_bit_off(typ, fld))); \ } while (0) @@ -212,10 +213,20 @@ enum { }; enum { - MLX5_BF_REGS_PER_PAGE = 4, - MLX5_MAX_UAR_PAGES = 1 << 8, - MLX5_NON_FP_BF_REGS_PER_PAGE = 2, - MLX5_MAX_UUARS = MLX5_MAX_UAR_PAGES * MLX5_NON_FP_BF_REGS_PER_PAGE, + MLX5_ADAPTER_PAGE_SHIFT = 12, + MLX5_ADAPTER_PAGE_SIZE = 1 << MLX5_ADAPTER_PAGE_SHIFT, +}; + +enum { + MLX5_BFREGS_PER_UAR = 4, + MLX5_MAX_UARS = 1 << 8, + MLX5_NON_FP_BFREGS_PER_UAR = 2, + MLX5_FP_BFREGS_PER_UAR = MLX5_BFREGS_PER_UAR - + MLX5_NON_FP_BFREGS_PER_UAR, + MLX5_MAX_BFREGS = MLX5_MAX_UARS * + MLX5_NON_FP_BFREGS_PER_UAR, + MLX5_UARS_IN_PAGE = PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE, + MLX5_NON_FP_BFREGS_IN_PAGE = MLX5_NON_FP_BFREGS_PER_UAR * MLX5_UARS_IN_PAGE, }; enum { @@ -279,6 +290,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_GPIO_EVENT = 0x15, MLX5_EVENT_TYPE_PORT_MODULE_EVENT = 0x16, MLX5_EVENT_TYPE_REMOTE_CONFIG = 0x19, + MLX5_EVENT_TYPE_PPS_EVENT = 0x25, MLX5_EVENT_TYPE_DB_BF_CONGESTION = 0x1a, MLX5_EVENT_TYPE_STALL_EVENT = 0x1b, @@ -288,6 +300,8 @@ enum mlx5_event { MLX5_EVENT_TYPE_PAGE_FAULT = 0xc, MLX5_EVENT_TYPE_NIC_VPORT_CHANGE = 0xd, + + MLX5_EVENT_TYPE_FPGA_ERROR = 0x20, }; enum { @@ -389,11 +403,6 @@ enum { }; enum { - MLX5_ADAPTER_PAGE_SHIFT = 12, - MLX5_ADAPTER_PAGE_SIZE = 1 << MLX5_ADAPTER_PAGE_SHIFT, -}; - -enum { MLX5_CAP_OFF_CMDIF_CSUM = 46, }; @@ -534,7 +543,9 @@ struct mlx5_eqe_page_fault { __be16 wqe_index; u16 reserved2; __be16 packet_length; - u8 reserved3[12]; + __be32 token; + u8 reserved4[8]; + __be32 pftype_wq; } __packed wqe; struct { __be32 r_key; @@ -542,9 +553,9 @@ struct mlx5_eqe_page_fault { __be16 packet_length; __be32 rdma_op_len; __be64 rdma_va; + __be32 pftype_token; } __packed rdma; } __packed; - __be32 flags_qpn; } __packed; struct mlx5_eqe_vport_change { @@ -562,6 +573,22 @@ struct mlx5_eqe_port_module { u8 error_type; } __packed; +struct mlx5_eqe_pps { + u8 rsvd0[3]; + u8 pin; + u8 rsvd1[4]; + union { + struct { + __be32 time_sec; + __be32 time_nsec; + }; + struct { + __be64 time_stamp; + }; + }; + u8 rsvd2[12]; +} __packed; + union ev_data { __be32 raw[7]; struct mlx5_eqe_cmd cmd; @@ -576,6 +603,7 @@ union ev_data { struct mlx5_eqe_page_fault page_fault; struct mlx5_eqe_vport_change vport_change; struct mlx5_eqe_port_module port_module; + struct mlx5_eqe_pps pps; } __packed; struct mlx5_eqe { @@ -761,8 +789,14 @@ enum { }; enum { - CQE_RSS_HTYPE_IP = 0x3 << 6, - CQE_RSS_HTYPE_L4 = 0x3 << 2, + CQE_RSS_HTYPE_IP = 0x3 << 2, + /* cqe->rss_hash_type[3:2] - IP destination selected for hash + * (00 = none, 01 = IPv4, 10 = IPv6, 11 = Reserved) + */ + CQE_RSS_HTYPE_L4 = 0x3 << 6, + /* cqe->rss_hash_type[7:6] - L4 destination selected for hash + * (00 = none, 01 = TCP. 10 = UDP, 11 = IPSEC.SPI + */ }; enum { @@ -941,42 +975,59 @@ enum mlx5_cap_type { MLX5_CAP_RESERVED, MLX5_CAP_VECTOR_CALC, MLX5_CAP_QOS, + MLX5_CAP_FPGA, /* NUM OF CAP Types */ MLX5_CAP_NUM }; +enum mlx5_pcam_reg_groups { + MLX5_PCAM_REGS_5000_TO_507F = 0x0, +}; + +enum mlx5_pcam_feature_groups { + MLX5_PCAM_FEATURE_ENHANCED_FEATURES = 0x0, +}; + +enum mlx5_mcam_reg_groups { + MLX5_MCAM_REGS_FIRST_128 = 0x0, +}; + +enum mlx5_mcam_feature_groups { + MLX5_MCAM_FEATURE_ENHANCED_FEATURES = 0x0, +}; + /* GET Dev Caps macros */ #define MLX5_CAP_GEN(mdev, cap) \ - MLX5_GET(cmd_hca_cap, mdev->hca_caps_cur[MLX5_CAP_GENERAL], cap) + MLX5_GET(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap) #define MLX5_CAP_GEN_MAX(mdev, cap) \ - MLX5_GET(cmd_hca_cap, mdev->hca_caps_max[MLX5_CAP_GENERAL], cap) + MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap) #define MLX5_CAP_ETH(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->hca_caps_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) + mdev->caps.hca_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) #define MLX5_CAP_ETH_MAX(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ - mdev->hca_caps_max[MLX5_CAP_ETHERNET_OFFLOADS], cap) + mdev->caps.hca_max[MLX5_CAP_ETHERNET_OFFLOADS], cap) #define MLX5_CAP_ROCE(mdev, cap) \ - MLX5_GET(roce_cap, mdev->hca_caps_cur[MLX5_CAP_ROCE], cap) + MLX5_GET(roce_cap, mdev->caps.hca_cur[MLX5_CAP_ROCE], cap) #define MLX5_CAP_ROCE_MAX(mdev, cap) \ - MLX5_GET(roce_cap, mdev->hca_caps_max[MLX5_CAP_ROCE], cap) + MLX5_GET(roce_cap, mdev->caps.hca_max[MLX5_CAP_ROCE], cap) #define MLX5_CAP_ATOMIC(mdev, cap) \ - MLX5_GET(atomic_caps, mdev->hca_caps_cur[MLX5_CAP_ATOMIC], cap) + MLX5_GET(atomic_caps, mdev->caps.hca_cur[MLX5_CAP_ATOMIC], cap) #define MLX5_CAP_ATOMIC_MAX(mdev, cap) \ - MLX5_GET(atomic_caps, mdev->hca_caps_max[MLX5_CAP_ATOMIC], cap) + MLX5_GET(atomic_caps, mdev->caps.hca_max[MLX5_CAP_ATOMIC], cap) #define MLX5_CAP_FLOWTABLE(mdev, cap) \ - MLX5_GET(flow_table_nic_cap, mdev->hca_caps_cur[MLX5_CAP_FLOW_TABLE], cap) + MLX5_GET(flow_table_nic_cap, mdev->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap) #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ - MLX5_GET(flow_table_nic_cap, mdev->hca_caps_max[MLX5_CAP_FLOW_TABLE], cap) + MLX5_GET(flow_table_nic_cap, mdev->caps.hca_max[MLX5_CAP_FLOW_TABLE], cap) #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap) @@ -998,11 +1049,11 @@ enum mlx5_cap_type { #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ - mdev->hca_caps_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + mdev->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) #define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ - mdev->hca_caps_max[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + mdev->caps.hca_max[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap) @@ -1024,21 +1075,36 @@ enum mlx5_cap_type { #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ - mdev->hca_caps_cur[MLX5_CAP_ESWITCH], cap) + mdev->caps.hca_cur[MLX5_CAP_ESWITCH], cap) #define MLX5_CAP_ESW_MAX(mdev, cap) \ MLX5_GET(e_switch_cap, \ - mdev->hca_caps_max[MLX5_CAP_ESWITCH], cap) + mdev->caps.hca_max[MLX5_CAP_ESWITCH], cap) #define MLX5_CAP_ODP(mdev, cap)\ - MLX5_GET(odp_cap, mdev->hca_caps_cur[MLX5_CAP_ODP], cap) + MLX5_GET(odp_cap, mdev->caps.hca_cur[MLX5_CAP_ODP], cap) #define MLX5_CAP_VECTOR_CALC(mdev, cap) \ MLX5_GET(vector_calc_cap, \ - mdev->hca_caps_cur[MLX5_CAP_VECTOR_CALC], cap) + mdev->caps.hca_cur[MLX5_CAP_VECTOR_CALC], cap) #define MLX5_CAP_QOS(mdev, cap)\ - MLX5_GET(qos_cap, mdev->hca_caps_cur[MLX5_CAP_QOS], cap) + MLX5_GET(qos_cap, mdev->caps.hca_cur[MLX5_CAP_QOS], cap) + +#define MLX5_CAP_PCAM_FEATURE(mdev, fld) \ + MLX5_GET(pcam_reg, (mdev)->caps.pcam, feature_cap_mask.enhanced_features.fld) + +#define MLX5_CAP_MCAM_REG(mdev, reg) \ + MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_access_reg_cap_mask.access_regs.reg) + +#define MLX5_CAP_MCAM_FEATURE(mdev, fld) \ + MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) + +#define MLX5_CAP_FPGA(mdev, cap) \ + MLX5_GET(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap) + +#define MLX5_CAP64_FPGA(mdev, cap) \ + MLX5_GET64(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap) enum { MLX5_CMD_STAT_OK = 0x0, @@ -1068,9 +1134,14 @@ enum { MLX5_PER_PRIORITY_COUNTERS_GROUP = 0x10, MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP = 0x11, MLX5_PHYSICAL_LAYER_COUNTERS_GROUP = 0x12, + MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP = 0x16, MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20, }; +enum { + MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP = 0x0, +}; + static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) { if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE) diff --git a/include/linux/mlx5/doorbell.h b/include/linux/mlx5/doorbell.h index afc78a3f4462..0787de28f2fc 100644 --- a/include/linux/mlx5/doorbell.h +++ b/include/linux/mlx5/doorbell.h @@ -68,10 +68,12 @@ static inline void mlx5_write64(__be32 val[2], void __iomem *dest, { unsigned long flags; - spin_lock_irqsave(doorbell_lock, flags); + if (doorbell_lock) + spin_lock_irqsave(doorbell_lock, flags); __raw_writel((__force u32) val[0], dest); __raw_writel((__force u32) val[1], dest + 4); - spin_unlock_irqrestore(doorbell_lock, flags); + if (doorbell_lock) + spin_unlock_irqrestore(doorbell_lock, flags); } #endif diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 735b36335f29..df6ce59a1f95 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -42,7 +42,9 @@ #include <linux/vmalloc.h> #include <linux/radix-tree.h> #include <linux/workqueue.h> +#include <linux/mempool.h> #include <linux/interrupt.h> +#include <linux/idr.h> #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> @@ -83,6 +85,7 @@ enum { MLX5_EQ_VEC_PAGES = 0, MLX5_EQ_VEC_CMD = 1, MLX5_EQ_VEC_ASYNC = 2, + MLX5_EQ_VEC_PFAULT = 3, MLX5_EQ_VEC_COMP_BASE, }; @@ -106,6 +109,9 @@ enum { MLX5_REG_QTCT = 0x400a, MLX5_REG_DCBX_PARAM = 0x4020, MLX5_REG_DCBX_APP = 0x4021, + MLX5_REG_FPGA_CAP = 0x4022, + MLX5_REG_FPGA_CTRL = 0x4023, + MLX5_REG_FPGA_ACCESS_REG = 0x4024, MLX5_REG_PCAP = 0x5001, MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, @@ -119,10 +125,18 @@ enum { MLX5_REG_PVLC = 0x500f, MLX5_REG_PCMR = 0x5041, MLX5_REG_PMLP = 0x5002, + MLX5_REG_PCAM = 0x507f, MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, MLX5_REG_MCIA = 0x9014, MLX5_REG_MLCR = 0x902b, + MLX5_REG_MPCNT = 0x9051, + MLX5_REG_MTPPS = 0x9053, + MLX5_REG_MTPPSE = 0x9054, + MLX5_REG_MCQI = 0x9061, + MLX5_REG_MCC = 0x9062, + MLX5_REG_MCDA = 0x9063, + MLX5_REG_MCAM = 0x907f, }; enum mlx5_dcbx_oper_mode { @@ -170,6 +184,7 @@ enum mlx5_dev_event { MLX5_DEV_EVENT_PKEY_CHANGE, MLX5_DEV_EVENT_GUID_CHANGE, MLX5_DEV_EVENT_CLIENT_REREG, + MLX5_DEV_EVENT_PPS, }; enum mlx5_port_status { @@ -177,36 +192,26 @@ enum mlx5_port_status { MLX5_PORT_DOWN = 2, }; -struct mlx5_uuar_info { - struct mlx5_uar *uars; - int num_uars; - int num_low_latency_uuars; - unsigned long *bitmap; +enum mlx5_eq_type { + MLX5_EQ_TYPE_COMP, + MLX5_EQ_TYPE_ASYNC, +#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING + MLX5_EQ_TYPE_PF, +#endif +}; + +struct mlx5_bfreg_info { + u32 *sys_pages; + int num_low_latency_bfregs; unsigned int *count; - struct mlx5_bf *bfs; /* - * protect uuar allocation data structs + * protect bfreg allocation data structs */ struct mutex lock; u32 ver; -}; - -struct mlx5_bf { - void __iomem *reg; - void __iomem *regreg; - int buf_size; - struct mlx5_uar *uar; - unsigned long offset; - int need_lock; - /* protect blue flame buffer selection when needed - */ - spinlock_t lock; - - /* serialize 64 bit writes when done as two 32 bit accesses - */ - spinlock_t lock32; - int uuarn; + bool lib_uar_4k; + u32 num_sys_pages; }; struct mlx5_cmd_first { @@ -297,6 +302,7 @@ struct mlx5_port_caps { int gid_table_len; int pkey_table_len; u8 ext_port_cap; + bool has_smi; }; struct mlx5_cmd_mailbox { @@ -332,6 +338,14 @@ struct mlx5_eq_tasklet { spinlock_t lock; }; +struct mlx5_eq_pagefault { + struct work_struct work; + /* Pagefaults lock */ + spinlock_t lock; + struct workqueue_struct *wq; + mempool_t *pool; +}; + struct mlx5_eq { struct mlx5_core_dev *dev; __be32 __iomem *doorbell; @@ -345,7 +359,13 @@ struct mlx5_eq { struct list_head list; int index; struct mlx5_rsc_debug *dbg; - struct mlx5_eq_tasklet tasklet_ctx; + enum mlx5_eq_type type; + union { + struct mlx5_eq_tasklet tasklet_ctx; +#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING + struct mlx5_eq_pagefault pf_ctx; +#endif + }; }; struct mlx5_core_psv { @@ -369,13 +389,21 @@ struct mlx5_core_sig_ctx { u32 sigerr_count; }; +enum { + MLX5_MKEY_MR = 1, + MLX5_MKEY_MW, +}; + struct mlx5_core_mkey { u64 iova; u64 size; u32 key; u32 pd; + u32 type; }; +#define MLX5_24BIT_MASK ((1 << 24) - 1) + enum mlx5_res_type { MLX5_RES_QP = MLX5_EVENT_QUEUE_TYPE_QP, MLX5_RES_RQ = MLX5_EVENT_QUEUE_TYPE_RQ, @@ -410,20 +438,47 @@ struct mlx5_eq_table { struct mlx5_eq pages_eq; struct mlx5_eq async_eq; struct mlx5_eq cmd_eq; +#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING + struct mlx5_eq pfault_eq; +#endif int num_comp_vectors; /* protect EQs list */ spinlock_t lock; }; -struct mlx5_uar { - u32 index; - struct list_head bf_list; - unsigned free_bf_bmap; - void __iomem *bf_map; +struct mlx5_uars_page { void __iomem *map; + bool wc; + u32 index; + struct list_head list; + unsigned int bfregs; + unsigned long *reg_bitmap; /* for non fast path bf regs */ + unsigned long *fp_bitmap; + unsigned int reg_avail; + unsigned int fp_avail; + struct kref ref_count; + struct mlx5_core_dev *mdev; +}; + +struct mlx5_bfreg_head { + /* protect blue flame registers allocations */ + struct mutex lock; + struct list_head list; +}; + +struct mlx5_bfreg_data { + struct mlx5_bfreg_head reg_head; + struct mlx5_bfreg_head wc_head; }; +struct mlx5_sq_bfreg { + void __iomem *map; + struct mlx5_uars_page *up; + bool wc; + u32 index; + unsigned int offset; +}; struct mlx5_core_health { struct health_buffer __iomem *health; @@ -492,10 +547,12 @@ struct mlx5_fc_stats { struct workqueue_struct *wq; struct delayed_work work; unsigned long next_query; + unsigned long sampling_interval; /* jiffies */ }; struct mlx5_eswitch; struct mlx5_lag; +struct mlx5_pagefault; struct mlx5_rl_entry { u32 rate; @@ -542,8 +599,6 @@ struct mlx5_priv { struct mlx5_eq_table eq_table; struct msix_entry *msix_arr; struct mlx5_irq_info *irq_info; - struct mlx5_uuar_info uuari; - MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock); /* pages stuff */ struct workqueue_struct *pg_wq; @@ -600,6 +655,16 @@ struct mlx5_priv { struct mlx5_rl_table rl_table; struct mlx5_port_module_event_stats pme_stats; + +#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING + void (*pfault)(struct mlx5_core_dev *dev, + void *context, + struct mlx5_pagefault *pfault); + void *pfault_ctx; + struct srcu_struct pfault_srcu; +#endif + struct mlx5_bfreg_data bfregs; + struct mlx5_uars_page *uar; }; enum mlx5_device_state { @@ -618,16 +683,68 @@ enum mlx5_pci_status { MLX5_PCI_STATUS_ENABLED, }; +enum mlx5_pagefault_type_flags { + MLX5_PFAULT_REQUESTOR = 1 << 0, + MLX5_PFAULT_WRITE = 1 << 1, + MLX5_PFAULT_RDMA = 1 << 2, +}; + +/* Contains the details of a pagefault. */ +struct mlx5_pagefault { + u32 bytes_committed; + u32 token; + u8 event_subtype; + u8 type; + union { + /* Initiator or send message responder pagefault details. */ + struct { + /* Received packet size, only valid for responders. */ + u32 packet_size; + /* + * Number of resource holding WQE, depends on type. + */ + u32 wq_num; + /* + * WQE index. Refers to either the send queue or + * receive queue, according to event_subtype. + */ + u16 wqe_index; + } wqe; + /* RDMA responder pagefault details */ + struct { + u32 r_key; + /* + * Received packet size, minimal size page fault + * resolution required for forward progress. + */ + u32 packet_size; + u32 rdma_op_len; + u64 rdma_va; + } rdma; + }; + + struct mlx5_eq *eq; + struct work_struct work; +}; + struct mlx5_td { struct list_head tirs_list; u32 tdn; }; struct mlx5e_resources { - struct mlx5_uar cq_uar; u32 pdn; struct mlx5_td td; struct mlx5_core_mkey mkey; + struct mlx5_sq_bfreg bfreg; +}; + +#define MLX5_MAX_RESERVED_GIDS 8 + +struct mlx5_rsvd_gids { + unsigned int start; + unsigned int count; + struct ida ida; }; struct mlx5_core_dev { @@ -639,8 +756,12 @@ struct mlx5_core_dev { char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; struct mlx5_port_caps port_caps[MLX5_MAX_PORTS]; - u32 hca_caps_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; - u32 hca_caps_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; + struct { + u32 hca_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; + u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; + u32 pcam[MLX5_ST_SZ_DW(pcam_reg)]; + u32 mcam[MLX5_ST_SZ_DW(mcam_reg)]; + } caps; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; enum mlx5_device_state state; @@ -655,6 +776,13 @@ struct mlx5_core_dev { atomic_t num_qps; u32 issi; struct mlx5e_resources mlx5e_res; + struct { + struct mlx5_rsvd_gids reserved_gids; + atomic_t roce_en; + } roce; +#ifdef CONFIG_MLX5_FPGA + struct mlx5_fpga_device *fpga; +#endif #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap; #endif @@ -681,7 +809,12 @@ enum { typedef void (*mlx5_cmd_cbk_t)(int status, void *context); +enum { + MLX5_CMD_ENT_STATE_PENDING_COMP, +}; + struct mlx5_cmd_work_ent { + unsigned long state; struct mlx5_cmd_msg *in; struct mlx5_cmd_msg *out; void *uout; @@ -701,6 +834,7 @@ struct mlx5_cmd_work_ent { u64 ts1; u64 ts2; u16 op; + bool polling; }; struct mlx5_pas { @@ -784,16 +918,6 @@ static inline u16 cmdif_rev(struct mlx5_core_dev *dev) return ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16; } -static inline void *mlx5_vzalloc(unsigned long size) -{ - void *rtn; - - rtn = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); - if (!rtn) - rtn = vzalloc(size); - return rtn; -} - static inline u32 mlx5_base_mkey(const u32 key) { return key & 0xffffff00u; @@ -809,21 +933,20 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size, mlx5_cmd_cbk_t callback, void *context); +int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, + void *out, int out_size); void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); -int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); -int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); -int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar, - bool map_wc); -void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); +void mlx5_trigger_health_work(struct mlx5_core_dev *dev); +void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf, int node); int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf); @@ -878,15 +1001,13 @@ void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn); void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type); -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING -void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); -#endif void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type); struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn); -void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec); +void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced); void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type); int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, - int nent, u64 mask, const char *name, struct mlx5_uar *uar); + int nent, u64 mask, const char *name, + enum mlx5_eq_type type); int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_start_eqs(struct mlx5_core_dev *dev); int mlx5_stop_eqs(struct mlx5_core_dev *dev); @@ -925,12 +1046,24 @@ int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev, u8 port_num, void *out, size_t sz); +#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING +int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token, + u32 wq_num, u8 type, int error); +#endif int mlx5_init_rl_table(struct mlx5_core_dev *dev); void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev); int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index); void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate); bool mlx5_rl_is_in_range(struct mlx5_core_dev *dev, u32 rate); +int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg, + bool map_wc, bool fast_path); +void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg); + +unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev); +int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index, + u8 roce_version, u8 roce_l3_type, const u8 *gid, + const u8 *mac, bool vlan, u16 vlan_id); static inline int fw_initializing(struct mlx5_core_dev *dev) { @@ -958,7 +1091,10 @@ enum { }; enum { - MAX_MR_CACHE_ENTRIES = 16, + MAX_UMR_CACHE_ENTRY = 20, + MLX5_IMR_MTT_CACHE_ENTRY, + MLX5_IMR_KSM_CACHE_ENTRY, + MAX_MR_CACHE_ENTRIES }; enum { @@ -973,6 +1109,9 @@ struct mlx5_interface { void (*detach)(struct mlx5_core_dev *dev, void *context); void (*event)(struct mlx5_core_dev *dev, void *context, enum mlx5_dev_event event, unsigned long param); + void (*pfault)(struct mlx5_core_dev *dev, + void *context, + struct mlx5_pagefault *pfault); void * (*get_dev)(void *context); int protocol; struct list_head list; @@ -987,6 +1126,27 @@ int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev); int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); +struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); +void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); + +#ifndef CONFIG_MLX5_CORE_IPOIB +static inline +struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, + struct ib_device *ibdev, + const char *name, + void (*setup)(struct net_device *)) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void mlx5_rdma_netdev_free(struct net_device *netdev) {} +#else +struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, + struct ib_device *ibdev, + const char *name, + void (*setup)(struct net_device *)); +void mlx5_rdma_netdev_free(struct net_device *netdev); +#endif /* CONFIG_MLX5_CORE_IPOIB */ struct mlx5_profile { u64 mask; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 949b24b6c479..b25e7baa273e 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -104,12 +104,17 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, u32 level, u32 flags); +struct mlx5_flow_table_attr { + int prio; + int max_fte; + u32 level; + u32 flags; +}; + struct mlx5_flow_table * mlx5_create_flow_table(struct mlx5_flow_namespace *ns, - int prio, - int num_flow_table_entries, - u32 level, - u32 flags); + struct mlx5_flow_table_attr *ft_attr); + struct mlx5_flow_table * mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns, int prio, @@ -134,8 +139,13 @@ struct mlx5_flow_act { u32 action; u32 flow_tag; u32 encap_id; + u32 modify_id; }; +#define MLX5_DECLARE_FLOW_ACT(name) \ + struct mlx5_flow_act name = {MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ + MLX5_FS_DEFAULT_FLOW_TAG, 0, 0} + /* Single destination per rule. * Group ID is implied by the match criteria. */ @@ -156,5 +166,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); +int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); +int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); #endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a852e9db6f0d..87869c04849a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -32,6 +32,8 @@ #ifndef MLX5_IFC_H #define MLX5_IFC_H +#include "mlx5_ifc_fpga.h" + enum { MLX5_EVENT_TYPE_CODING_COMPLETION_EVENTS = 0x0, MLX5_EVENT_TYPE_CODING_PATH_MIGRATED_SUCCEEDED = 0x1, @@ -56,7 +58,8 @@ enum { MLX5_EVENT_TYPE_CODING_STALL_VL_EVENT = 0x1b, MLX5_EVENT_TYPE_CODING_DROPPED_PACKET_LOGGED_EVENT = 0x1f, MLX5_EVENT_TYPE_CODING_COMMAND_INTERFACE_COMPLETION = 0xa, - MLX5_EVENT_TYPE_CODING_PAGE_REQUEST = 0xb + MLX5_EVENT_TYPE_CODING_PAGE_REQUEST = 0xb, + MLX5_EVENT_TYPE_CODING_FPGA_ERROR = 0x20, }; enum { @@ -227,6 +230,13 @@ enum { MLX5_CMD_OP_MODIFY_FLOW_TABLE = 0x93c, MLX5_CMD_OP_ALLOC_ENCAP_HEADER = 0x93d, MLX5_CMD_OP_DEALLOC_ENCAP_HEADER = 0x93e, + MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT = 0x940, + MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941, + MLX5_CMD_OP_FPGA_CREATE_QP = 0x960, + MLX5_CMD_OP_FPGA_MODIFY_QP = 0x961, + MLX5_CMD_OP_FPGA_QUERY_QP = 0x962, + MLX5_CMD_OP_FPGA_DESTROY_QP = 0x963, + MLX5_CMD_OP_FPGA_QUERY_QP_COUNTERS = 0x964, MLX5_CMD_OP_MAX }; @@ -234,11 +244,11 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_dmac[0x1]; u8 outer_smac[0x1]; u8 outer_ether_type[0x1]; - u8 reserved_at_3[0x1]; + u8 outer_ip_version[0x1]; u8 outer_first_prio[0x1]; u8 outer_first_cfi[0x1]; u8 outer_first_vid[0x1]; - u8 reserved_at_7[0x1]; + u8 outer_ipv4_ttl[0x1]; u8 outer_second_prio[0x1]; u8 outer_second_cfi[0x1]; u8 outer_second_vid[0x1]; @@ -263,7 +273,7 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 inner_dmac[0x1]; u8 inner_smac[0x1]; u8 inner_ether_type[0x1]; - u8 reserved_at_23[0x1]; + u8 inner_ip_version[0x1]; u8 inner_first_prio[0x1]; u8 inner_first_cfi[0x1]; u8 inner_first_vid[0x1]; @@ -302,7 +312,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; - u8 reserved_at_28[0x10]; + u8 log_max_modify_header_context[0x8]; + u8 max_modify_header_actions[0x8]; u8 max_ft_level[0x8]; u8 reserved_at_40[0x20]; @@ -328,7 +339,7 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 receive[0x1]; u8 write[0x1]; u8 read[0x1]; - u8 reserved_at_4[0x1]; + u8 atomic[0x1]; u8 srq_receive[0x1]; u8 reserved_at_6[0x1a]; }; @@ -365,16 +376,17 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 ip_protocol[0x8]; u8 ip_dscp[0x6]; u8 ip_ecn[0x2]; - u8 vlan_tag[0x1]; - u8 reserved_at_91[0x1]; + u8 cvlan_tag[0x1]; + u8 svlan_tag[0x1]; u8 frag[0x1]; - u8 reserved_at_93[0x4]; + u8 ip_version[0x4]; u8 tcp_flags[0x9]; u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_at_c0[0x20]; + u8 reserved_at_c0[0x18]; + u8 ttl_hoplimit[0x8]; u8 udp_sport[0x10]; u8 udp_dport[0x10]; @@ -398,9 +410,11 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 inner_second_cfi[0x1]; u8 inner_second_vid[0xc]; - u8 outer_second_vlan_tag[0x1]; - u8 inner_second_vlan_tag[0x1]; - u8 reserved_at_62[0xe]; + u8 outer_second_cvlan_tag[0x1]; + u8 inner_second_cvlan_tag[0x1]; + u8 outer_second_svlan_tag[0x1]; + u8 inner_second_svlan_tag[0x1]; + u8 reserved_at_64[0xc]; u8 gre_protocol[0x10]; u8 gre_key_h[0x18]; @@ -545,7 +559,9 @@ struct mlx5_ifc_e_switch_cap_bits { struct mlx5_ifc_qos_cap_bits { u8 packet_pacing[0x1]; u8 esw_scheduling[0x1]; - u8 reserved_at_2[0x1e]; + u8 esw_bw_share[0x1]; + u8 esw_rate_limit[0x1]; + u8 reserved_at_4[0x1c]; u8 reserved_at_20[0x20]; @@ -573,7 +589,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 lro_cap[0x1]; u8 lro_psh_flag[0x1]; u8 lro_time_stamp[0x1]; - u8 reserved_at_5[0x3]; + u8 reserved_at_5[0x2]; + u8 wqe_vlan_insert[0x1]; u8 self_lb_en_modifiable[0x1]; u8 reserved_at_9[0x2]; u8 max_lso_cap[0x5]; @@ -588,7 +605,10 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 tunnel_statless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; - u8 reserved_at_20[0x20]; + u8 swp[0x1]; + u8 swp_csum[0x1]; + u8 swp_lso[0x1]; + u8 reserved_at_23[0x1d]; u8 reserved_at_40[0x10]; u8 lro_min_mss_size[0x10]; @@ -650,9 +670,9 @@ enum { struct mlx5_ifc_atomic_caps_bits { u8 reserved_at_0[0x40]; - u8 atomic_req_8B_endianess_mode[0x2]; + u8 atomic_req_8B_endianness_mode[0x2]; u8 reserved_at_42[0x4]; - u8 supported_atomic_req_8B_endianess_mode_1[0x1]; + u8 supported_atomic_req_8B_endianness_mode_1[0x1]; u8 reserved_at_47[0x19]; @@ -758,6 +778,12 @@ enum { MLX5_CAP_PORT_TYPE_ETH = 0x1, }; +enum { + MLX5_CAP_UMR_FENCE_STRONG = 0x0, + MLX5_CAP_UMR_FENCE_SMALL = 0x1, + MLX5_CAP_UMR_FENCE_NONE = 0x2, +}; + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x80]; @@ -782,11 +808,13 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_eq[0x4]; u8 max_indirection[0x8]; - u8 reserved_at_108[0x1]; + u8 fixed_buffer_size[0x1]; u8 log_max_mrw_sz[0x7]; - u8 reserved_at_110[0x2]; + u8 force_teardown[0x1]; + u8 reserved_at_111[0x1]; u8 log_max_bsf_list_size[0x6]; - u8 reserved_at_118[0x2]; + u8 umr_extended_translation_offset[0x1]; + u8 null_mkey[0x1]; u8 log_max_klm_list_size[0x6]; u8 reserved_at_120[0xa]; @@ -799,10 +827,12 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_150[0xa]; u8 log_max_ra_res_qp[0x6]; - u8 pad_cap[0x1]; + u8 end_pad[0x1]; u8 cc_query_allowed[0x1]; u8 cc_modify_allowed[0x1]; - u8 reserved_at_163[0xd]; + u8 start_pad[0x1]; + u8 cache_line_128byte[0x1]; + u8 reserved_at_165[0xb]; u8 gid_table_size[0x10]; u8 out_of_seq_cnt[0x1]; @@ -823,24 +853,28 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 nic_flow_table[0x1]; u8 eswitch_flow_table[0x1]; u8 early_vf_enable[0x1]; - u8 reserved_at_1a9[0x2]; + u8 mcam_reg[0x1]; + u8 pcam_reg[0x1]; u8 local_ca_ack_delay[0x5]; u8 port_module_event[0x1]; - u8 reserved_at_1b0[0x1]; + u8 reserved_at_1b1[0x1]; u8 ports_check[0x1]; - u8 reserved_at_1b2[0x1]; + u8 reserved_at_1b3[0x1]; u8 disable_link_up[0x1]; u8 beacon_led[0x1]; u8 port_type[0x2]; u8 num_ports[0x8]; - u8 reserved_at_1c0[0x3]; + u8 reserved_at_1c0[0x1]; + u8 pps[0x1]; + u8 pps_modify[0x1]; u8 log_max_msg[0x5]; u8 reserved_at_1c8[0x4]; u8 max_tc[0x4]; u8 reserved_at_1d0[0x1]; u8 dcbx[0x1]; - u8 reserved_at_1d2[0x4]; + u8 reserved_at_1d2[0x3]; + u8 fpga[0x1]; u8 rol_s[0x1]; u8 rol_g[0x1]; u8 reserved_at_1d8[0x1]; @@ -858,9 +892,12 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 compact_address_vector[0x1]; u8 striding_rq[0x1]; - u8 reserved_at_201[0x2]; + u8 reserved_at_202[0x1]; + u8 ipoib_enhanced_offloads[0x1]; u8 ipoib_basic_offloads[0x1]; - u8 reserved_at_205[0xa]; + u8 reserved_at_205[0x5]; + u8 umr_fence[0x2]; + u8 reserved_at_20c[0x3]; u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; @@ -904,7 +941,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 uc[0x1]; u8 rc[0x1]; - u8 reserved_at_240[0xa]; + u8 uar_4k[0x1]; + u8 reserved_at_241[0x9]; u8 uar_sz[0x6]; u8 reserved_at_250[0x8]; u8 log_pg_sz[0x8]; @@ -996,7 +1034,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 device_frequency_mhz[0x20]; u8 device_frequency_khz[0x20]; - u8 reserved_at_500[0x80]; + u8 reserved_at_500[0x20]; + u8 num_of_uars_per_page[0x20]; + u8 reserved_at_540[0x40]; u8 reserved_at_580[0x3f]; u8 cqe_compression[0x1]; @@ -1009,10 +1049,10 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 rndv_offload_rc[0x1]; u8 rndv_offload_dc[0x1]; u8 log_tag_matching_list_sz[0x5]; - u8 reserved_at_5e8[0x3]; + u8 reserved_at_5f8[0x3]; u8 log_max_xrq[0x5]; - u8 reserved_at_5f0[0x200]; + u8 reserved_at_600[0x200]; }; enum mlx5_flow_destination_type { @@ -1375,6 +1415,42 @@ struct mlx5_ifc_phys_layer_cntrs_bits { u8 reserved_at_640[0x180]; }; +struct mlx5_ifc_phys_layer_statistical_cntrs_bits { + u8 time_since_last_clear_high[0x20]; + + u8 time_since_last_clear_low[0x20]; + + u8 phy_received_bits_high[0x20]; + + u8 phy_received_bits_low[0x20]; + + u8 phy_symbol_errors_high[0x20]; + + u8 phy_symbol_errors_low[0x20]; + + u8 phy_corrected_bits_high[0x20]; + + u8 phy_corrected_bits_low[0x20]; + + u8 phy_corrected_bits_lane0_high[0x20]; + + u8 phy_corrected_bits_lane0_low[0x20]; + + u8 phy_corrected_bits_lane1_high[0x20]; + + u8 phy_corrected_bits_lane1_low[0x20]; + + u8 phy_corrected_bits_lane2_high[0x20]; + + u8 phy_corrected_bits_lane2_low[0x20]; + + u8 phy_corrected_bits_lane3_high[0x20]; + + u8 phy_corrected_bits_lane3_low[0x20]; + + u8 reserved_at_200[0x5c0]; +}; + struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits { u8 symbol_error_counter[0x10]; @@ -1402,7 +1478,9 @@ struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits { u8 vl_15_dropped[0x10]; - u8 reserved_at_a0[0xa0]; + u8 reserved_at_a0[0x80]; + + u8 port_xmit_wait[0x20]; }; struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { @@ -1757,6 +1835,30 @@ struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits { u8 reserved_at_4c0[0x300]; }; +struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits { + u8 life_time_counter_high[0x20]; + + u8 life_time_counter_low[0x20]; + + u8 rx_errors[0x20]; + + u8 tx_errors[0x20]; + + u8 l0_to_recovery_eieos[0x20]; + + u8 l0_to_recovery_ts[0x20]; + + u8 l0_to_recovery_framing[0x20]; + + u8 l0_to_recovery_retrain[0x20]; + + u8 crc_error_dllp[0x20]; + + u8 crc_error_tlp[0x20]; + + u8 reserved_at_140[0x680]; +}; + struct mlx5_ifc_cmd_inter_comp_event_bits { u8 command_completion_vector[0x20]; @@ -2106,6 +2208,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_e_switch_cap_bits e_switch_cap; struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; struct mlx5_ifc_qos_cap_bits qos_cap; + struct mlx5_ifc_fpga_cap_bits fpga_cap; u8 reserved_at_0[0x8000]; }; @@ -2116,6 +2219,7 @@ enum { MLX5_FLOW_CONTEXT_ACTION_COUNT = 0x8, MLX5_FLOW_CONTEXT_ACTION_ENCAP = 0x10, MLX5_FLOW_CONTEXT_ACTION_DECAP = 0x20, + MLX5_FLOW_CONTEXT_ACTION_MOD_HDR = 0x40, }; struct mlx5_ifc_flow_context_bits { @@ -2137,7 +2241,9 @@ struct mlx5_ifc_flow_context_bits { u8 encap_id[0x20]; - u8 reserved_at_e0[0x120]; + u8 modify_header_id[0x20]; + + u8 reserved_at_100[0x100]; struct mlx5_ifc_fte_match_param_bits match_value; @@ -2213,7 +2319,9 @@ struct mlx5_ifc_tisc_bits { u8 reserved_at_120[0x8]; u8 transport_domain[0x18]; - u8 reserved_at_140[0x3c0]; + u8 reserved_at_140[0x8]; + u8 underlay_qpn[0x18]; + u8 reserved_at_160[0x3a0]; }; enum { @@ -2333,7 +2441,8 @@ struct mlx5_ifc_sqc_bits { u8 min_wqe_inline_mode[0x3]; u8 state[0x4]; u8 reg_umr[0x1]; - u8 reserved_at_d[0x13]; + u8 allow_swp[0x1]; + u8 reserved_at_e[0x12]; u8 reserved_at_20[0x8]; u8 user_index[0x18]; @@ -2495,6 +2604,7 @@ enum { MLX5_MKC_ACCESS_MODE_PA = 0x0, MLX5_MKC_ACCESS_MODE_MTT = 0x1, MLX5_MKC_ACCESS_MODE_KLMS = 0x2, + MLX5_MKC_ACCESS_MODE_KSM = 0x3, }; struct mlx5_ifc_mkc_bits { @@ -2918,6 +3028,12 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; + struct mlx5_ifc_phys_layer_statistical_cntrs_bits phys_layer_statistical_cntrs; + u8 reserved_at_0[0x7c0]; +}; + +union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits { + struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits pcie_perf_cntrs_grp_data_layout; u8 reserved_at_0[0x7c0]; }; @@ -2989,18 +3105,25 @@ struct mlx5_ifc_tsar_element_bits { u8 reserved_at_10[0x10]; }; +enum { + MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_SUCCESS = 0x0, + MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL = 0x1, +}; + struct mlx5_ifc_teardown_hca_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x3f]; + + u8 force_state[0x1]; }; enum { MLX5_TEARDOWN_HCA_IN_PROFILE_GRACEFUL_CLOSE = 0x0, - MLX5_TEARDOWN_HCA_IN_PROFILE_PANIC_CLOSE = 0x1, + MLX5_TEARDOWN_HCA_IN_PROFILE_FORCE_CLOSE = 0x1, }; struct mlx5_ifc_teardown_hca_in_bits { @@ -3597,6 +3720,10 @@ struct mlx5_ifc_query_special_contexts_out_bits { u8 dump_fill_mkey[0x20]; u8 resd_lkey[0x20]; + + u8 null_mkey[0x20]; + + u8 reserved_at_a0[0x60]; }; struct mlx5_ifc_query_special_contexts_in_bits { @@ -4449,6 +4576,110 @@ struct mlx5_ifc_dealloc_encap_header_in_bits { u8 reserved_60[0x20]; }; +struct mlx5_ifc_set_action_in_bits { + u8 action_type[0x4]; + u8 field[0xc]; + u8 reserved_at_10[0x3]; + u8 offset[0x5]; + u8 reserved_at_18[0x3]; + u8 length[0x5]; + + u8 data[0x20]; +}; + +struct mlx5_ifc_add_action_in_bits { + u8 action_type[0x4]; + u8 field[0xc]; + u8 reserved_at_10[0x10]; + + u8 data[0x20]; +}; + +union mlx5_ifc_set_action_in_add_action_in_auto_bits { + struct mlx5_ifc_set_action_in_bits set_action_in; + struct mlx5_ifc_add_action_in_bits add_action_in; + u8 reserved_at_0[0x40]; +}; + +enum { + MLX5_ACTION_TYPE_SET = 0x1, + MLX5_ACTION_TYPE_ADD = 0x2, +}; + +enum { + MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16 = 0x1, + MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0 = 0x2, + MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE = 0x3, + MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16 = 0x4, + MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0 = 0x5, + MLX5_ACTION_IN_FIELD_OUT_IP_DSCP = 0x6, + MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS = 0x7, + MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT = 0x8, + MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT = 0x9, + MLX5_ACTION_IN_FIELD_OUT_IP_TTL = 0xa, + MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT = 0xb, + MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT = 0xc, + MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96 = 0xd, + MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64 = 0xe, + MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32 = 0xf, + MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0 = 0x10, + MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96 = 0x11, + MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64 = 0x12, + MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32 = 0x13, + MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0 = 0x14, + MLX5_ACTION_IN_FIELD_OUT_SIPV4 = 0x15, + MLX5_ACTION_IN_FIELD_OUT_DIPV4 = 0x16, + MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47, +}; + +struct mlx5_ifc_alloc_modify_header_context_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 modify_header_id[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_alloc_modify_header_context_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x20]; + + u8 table_type[0x8]; + u8 reserved_at_68[0x10]; + u8 num_of_actions[0x8]; + + union mlx5_ifc_set_action_in_add_action_in_auto_bits actions[0]; +}; + +struct mlx5_ifc_dealloc_modify_header_context_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_dealloc_modify_header_context_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 modify_header_id[0x20]; + + u8 reserved_at_60[0x20]; +}; + struct mlx5_ifc_query_dct_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -4538,17 +4769,17 @@ struct mlx5_ifc_query_cong_statistics_out_bits { u8 reserved_at_40[0x40]; - u8 cur_flows[0x20]; + u8 rp_cur_flows[0x20]; u8 sum_flows[0x20]; - u8 cnp_ignored_high[0x20]; + u8 rp_cnp_ignored_high[0x20]; - u8 cnp_ignored_low[0x20]; + u8 rp_cnp_ignored_low[0x20]; - u8 cnp_handled_high[0x20]; + u8 rp_cnp_handled_high[0x20]; - u8 cnp_handled_low[0x20]; + u8 rp_cnp_handled_low[0x20]; u8 reserved_at_140[0x100]; @@ -4558,13 +4789,13 @@ struct mlx5_ifc_query_cong_statistics_out_bits { u8 accumulators_period[0x20]; - u8 ecn_marked_roce_packets_high[0x20]; + u8 np_ecn_marked_roce_packets_high[0x20]; - u8 ecn_marked_roce_packets_low[0x20]; + u8 np_ecn_marked_roce_packets_low[0x20]; - u8 cnps_sent_high[0x20]; + u8 np_cnp_sent_high[0x20]; - u8 cnps_sent_low[0x20]; + u8 np_cnp_sent_low[0x20]; u8 reserved_at_320[0x560]; }; @@ -4689,12 +4920,11 @@ struct mlx5_ifc_page_fault_resume_in_bits { u8 error[0x1]; u8 reserved_at_41[0x4]; - u8 rdma[0x1]; - u8 read_write[0x1]; - u8 req_res[0x1]; - u8 qpn[0x18]; + u8 page_fault_type[0x3]; + u8 wq_number[0x18]; - u8 reserved_at_60[0x20]; + u8 reserved_at_60[0x8]; + u8 token[0x18]; }; struct mlx5_ifc_nop_out_bits { @@ -4929,7 +5159,8 @@ struct mlx5_ifc_modify_rq_out_bits { enum { MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_VSD = 1ULL << 1, - MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_MODIFY_RQ_COUNTER_SET_ID = 1ULL << 3, + MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS = 1ULL << 2, + MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_RQ_COUNTER_SET_ID = 1ULL << 3, }; struct mlx5_ifc_modify_rq_in_bits { @@ -6415,6 +6646,24 @@ struct mlx5_ifc_create_flow_table_out_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_flow_table_context_bits { + u8 encap_en[0x1]; + u8 decap_en[0x1]; + u8 reserved_at_2[0x2]; + u8 table_miss_action[0x4]; + u8 level[0x8]; + u8 reserved_at_10[0x8]; + u8 log_size[0x8]; + + u8 reserved_at_20[0x8]; + u8 table_miss_id[0x18]; + + u8 reserved_at_40[0x8]; + u8 lag_master_next_table_id[0x18]; + + u8 reserved_at_60[0xe0]; +}; + struct mlx5_ifc_create_flow_table_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -6433,21 +6682,7 @@ struct mlx5_ifc_create_flow_table_in_bits { u8 reserved_at_a0[0x20]; - u8 encap_en[0x1]; - u8 decap_en[0x1]; - u8 reserved_at_c2[0x2]; - u8 table_miss_mode[0x4]; - u8 level[0x8]; - u8 reserved_at_d0[0x8]; - u8 log_size[0x8]; - - u8 reserved_at_e0[0x8]; - u8 table_miss_id[0x18]; - - u8 reserved_at_100[0x8]; - u8 lag_master_next_table_id[0x18]; - - u8 reserved_at_120[0x80]; + struct mlx5_ifc_flow_table_context_bits flow_table_context; }; struct mlx5_ifc_create_flow_group_out_bits { @@ -7079,7 +7314,8 @@ struct mlx5_ifc_ptys_reg_bits { u8 ib_link_width_oper[0x10]; u8 ib_proto_oper[0x10]; - u8 reserved_at_160[0x20]; + u8 reserved_at_160[0x1c]; + u8 connector_type[0x4]; u8 eth_proto_lp_advertise[0x20]; @@ -7240,6 +7476,18 @@ struct mlx5_ifc_ppcnt_reg_bits { union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; }; +struct mlx5_ifc_mpcnt_reg_bits { + u8 reserved_at_0[0x8]; + u8 pcie_index[0x8]; + u8 reserved_at_10[0xa]; + u8 grp[0x6]; + + u8 clr[0x1]; + u8 reserved_at_21[0x1f]; + + union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits counter_set; +}; + struct mlx5_ifc_ppad_reg_bits { u8 reserved_at_0[0x3]; u8 single_mac[0x1]; @@ -7469,6 +7717,78 @@ struct mlx5_ifc_peir_reg_bits { u8 error_type[0x8]; }; +struct mlx5_ifc_pcam_enhanced_features_bits { + u8 reserved_at_0[0x7c]; + + u8 ptys_connector_type[0x1]; + u8 reserved_at_7d[0x1]; + u8 ppcnt_discard_group[0x1]; + u8 ppcnt_statistical_group[0x1]; +}; + +struct mlx5_ifc_pcam_reg_bits { + u8 reserved_at_0[0x8]; + u8 feature_group[0x8]; + u8 reserved_at_10[0x8]; + u8 access_reg_group[0x8]; + + u8 reserved_at_20[0x20]; + + union { + u8 reserved_at_0[0x80]; + } port_access_reg_cap_mask; + + u8 reserved_at_c0[0x80]; + + union { + struct mlx5_ifc_pcam_enhanced_features_bits enhanced_features; + u8 reserved_at_0[0x80]; + } feature_cap_mask; + + u8 reserved_at_1c0[0xc0]; +}; + +struct mlx5_ifc_mcam_enhanced_features_bits { + u8 reserved_at_0[0x7f]; + + u8 pcie_performance_group[0x1]; +}; + +struct mlx5_ifc_mcam_access_reg_bits { + u8 reserved_at_0[0x1c]; + u8 mcda[0x1]; + u8 mcc[0x1]; + u8 mcqi[0x1]; + u8 reserved_at_1f[0x1]; + + u8 regs_95_to_64[0x20]; + u8 regs_63_to_32[0x20]; + u8 regs_31_to_0[0x20]; +}; + +struct mlx5_ifc_mcam_reg_bits { + u8 reserved_at_0[0x8]; + u8 feature_group[0x8]; + u8 reserved_at_10[0x8]; + u8 access_reg_group[0x8]; + + u8 reserved_at_20[0x20]; + + union { + struct mlx5_ifc_mcam_access_reg_bits access_regs; + u8 reserved_at_0[0x80]; + } mng_access_reg_cap_mask; + + u8 reserved_at_c0[0x80]; + + union { + struct mlx5_ifc_mcam_enhanced_features_bits enhanced_features; + u8 reserved_at_0[0x80]; + } mng_feature_cap_mask; + + u8 reserved_at_1c0[0x80]; +}; + struct mlx5_ifc_pcap_reg_bits { u8 reserved_at_0[0x8]; u8 local_port[0x8]; @@ -7813,6 +8133,139 @@ struct mlx5_ifc_initial_seg_bits { u8 reserved_at_80a0[0x17fc0]; }; +struct mlx5_ifc_mtpps_reg_bits { + u8 reserved_at_0[0xc]; + u8 cap_number_of_pps_pins[0x4]; + u8 reserved_at_10[0x4]; + u8 cap_max_num_of_pps_in_pins[0x4]; + u8 reserved_at_18[0x4]; + u8 cap_max_num_of_pps_out_pins[0x4]; + + u8 reserved_at_20[0x24]; + u8 cap_pin_3_mode[0x4]; + u8 reserved_at_48[0x4]; + u8 cap_pin_2_mode[0x4]; + u8 reserved_at_50[0x4]; + u8 cap_pin_1_mode[0x4]; + u8 reserved_at_58[0x4]; + u8 cap_pin_0_mode[0x4]; + + u8 reserved_at_60[0x4]; + u8 cap_pin_7_mode[0x4]; + u8 reserved_at_68[0x4]; + u8 cap_pin_6_mode[0x4]; + u8 reserved_at_70[0x4]; + u8 cap_pin_5_mode[0x4]; + u8 reserved_at_78[0x4]; + u8 cap_pin_4_mode[0x4]; + + u8 reserved_at_80[0x80]; + + u8 enable[0x1]; + u8 reserved_at_101[0xb]; + u8 pattern[0x4]; + u8 reserved_at_110[0x4]; + u8 pin_mode[0x4]; + u8 pin[0x8]; + + u8 reserved_at_120[0x20]; + + u8 time_stamp[0x40]; + + u8 out_pulse_duration[0x10]; + u8 out_periodic_adjustment[0x10]; + + u8 reserved_at_1a0[0x60]; +}; + +struct mlx5_ifc_mtppse_reg_bits { + u8 reserved_at_0[0x18]; + u8 pin[0x8]; + u8 event_arm[0x1]; + u8 reserved_at_21[0x1b]; + u8 event_generation_mode[0x4]; + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_mcqi_cap_bits { + u8 supported_info_bitmask[0x20]; + + u8 component_size[0x20]; + + u8 max_component_size[0x20]; + + u8 log_mcda_word_size[0x4]; + u8 reserved_at_64[0xc]; + u8 mcda_max_write_size[0x10]; + + u8 rd_en[0x1]; + u8 reserved_at_81[0x1]; + u8 match_chip_id[0x1]; + u8 match_psid[0x1]; + u8 check_user_timestamp[0x1]; + u8 match_base_guid_mac[0x1]; + u8 reserved_at_86[0x1a]; +}; + +struct mlx5_ifc_mcqi_reg_bits { + u8 read_pending_component[0x1]; + u8 reserved_at_1[0xf]; + u8 component_index[0x10]; + + u8 reserved_at_20[0x20]; + + u8 reserved_at_40[0x1b]; + u8 info_type[0x5]; + + u8 info_size[0x20]; + + u8 offset[0x20]; + + u8 reserved_at_a0[0x10]; + u8 data_size[0x10]; + + u8 data[0][0x20]; +}; + +struct mlx5_ifc_mcc_reg_bits { + u8 reserved_at_0[0x4]; + u8 time_elapsed_since_last_cmd[0xc]; + u8 reserved_at_10[0x8]; + u8 instruction[0x8]; + + u8 reserved_at_20[0x10]; + u8 component_index[0x10]; + + u8 reserved_at_40[0x8]; + u8 update_handle[0x18]; + + u8 handle_owner_type[0x4]; + u8 handle_owner_host_id[0x4]; + u8 reserved_at_68[0x1]; + u8 control_progress[0x7]; + u8 error_code[0x8]; + u8 reserved_at_78[0x4]; + u8 control_state[0x4]; + + u8 component_size[0x20]; + + u8 reserved_at_a0[0x60]; +}; + +struct mlx5_ifc_mcda_reg_bits { + u8 reserved_at_0[0x8]; + u8 update_handle[0x18]; + + u8 offset[0x20]; + + u8 reserved_at_40[0x10]; + u8 size[0x10]; + + u8 reserved_at_60[0x20]; + + u8 data[0][0x20]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -7845,6 +8298,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_pmtu_reg_bits pmtu_reg; struct mlx5_ifc_ppad_reg_bits ppad_reg; struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg; + struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg; struct mlx5_ifc_pplm_reg_bits pplm_reg; struct mlx5_ifc_pplr_reg_bits pplr_reg; struct mlx5_ifc_ppsc_reg_bits ppsc_reg; @@ -7857,6 +8311,14 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_pvlc_reg_bits pvlc_reg; struct mlx5_ifc_slrg_reg_bits slrg_reg; struct mlx5_ifc_sltp_reg_bits sltp_reg; + struct mlx5_ifc_mtpps_reg_bits mtpps_reg; + struct mlx5_ifc_mtppse_reg_bits mtppse_reg; + struct mlx5_ifc_fpga_access_reg_bits fpga_access_reg; + struct mlx5_ifc_fpga_ctrl_bits fpga_ctrl_bits; + struct mlx5_ifc_fpga_cap_bits fpga_cap_bits; + struct mlx5_ifc_mcqi_reg_bits mcqi_reg; + struct mlx5_ifc_mcc_reg_bits mcc_reg; + struct mlx5_ifc_mcda_reg_bits mcda_reg; u8 reserved_at_0[0x60e0]; }; @@ -7898,7 +8360,9 @@ struct mlx5_ifc_set_flow_table_root_in_bits { u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_at_c0[0x140]; + u8 reserved_at_c0[0x8]; + u8 underlay_qpn[0x18]; + u8 reserved_at_e0[0x120]; }; enum { @@ -7935,17 +8399,7 @@ struct mlx5_ifc_modify_flow_table_in_bits { u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_at_c0[0x4]; - u8 table_miss_mode[0x4]; - u8 reserved_at_c8[0x18]; - - u8 reserved_at_e0[0x8]; - u8 table_miss_id[0x18]; - - u8 reserved_at_100[0x8]; - u8 lag_master_next_table_id[0x18]; - - u8 reserved_at_120[0x80]; + struct mlx5_ifc_flow_table_context_bits flow_table_context; }; struct mlx5_ifc_ets_tcn_config_reg_bits { diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h new file mode 100644 index 000000000000..255a88d08078 --- /dev/null +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -0,0 +1,432 @@ +/* + * Copyright (c) 2017, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef MLX5_IFC_FPGA_H +#define MLX5_IFC_FPGA_H + +enum { + MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX = 0x2c9, +}; + +enum { + MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC = 0x2, +}; + +struct mlx5_ifc_fpga_shell_caps_bits { + u8 max_num_qps[0x10]; + u8 reserved_at_10[0x8]; + u8 total_rcv_credits[0x8]; + + u8 reserved_at_20[0xe]; + u8 qp_type[0x2]; + u8 reserved_at_30[0x5]; + u8 rae[0x1]; + u8 rwe[0x1]; + u8 rre[0x1]; + u8 reserved_at_38[0x4]; + u8 dc[0x1]; + u8 ud[0x1]; + u8 uc[0x1]; + u8 rc[0x1]; + + u8 reserved_at_40[0x1a]; + u8 log_ddr_size[0x6]; + + u8 max_fpga_qp_msg_size[0x20]; + + u8 reserved_at_80[0x180]; +}; + +struct mlx5_ifc_fpga_cap_bits { + u8 fpga_id[0x8]; + u8 fpga_device[0x18]; + + u8 register_file_ver[0x20]; + + u8 fpga_ctrl_modify[0x1]; + u8 reserved_at_41[0x5]; + u8 access_reg_query_mode[0x2]; + u8 reserved_at_48[0x6]; + u8 access_reg_modify_mode[0x2]; + u8 reserved_at_50[0x10]; + + u8 reserved_at_60[0x20]; + + u8 image_version[0x20]; + + u8 image_date[0x20]; + + u8 image_time[0x20]; + + u8 shell_version[0x20]; + + u8 reserved_at_100[0x80]; + + struct mlx5_ifc_fpga_shell_caps_bits shell_caps; + + u8 reserved_at_380[0x8]; + u8 ieee_vendor_id[0x18]; + + u8 sandbox_product_version[0x10]; + u8 sandbox_product_id[0x10]; + + u8 sandbox_basic_caps[0x20]; + + u8 reserved_at_3e0[0x10]; + u8 sandbox_extended_caps_len[0x10]; + + u8 sandbox_extended_caps_addr[0x40]; + + u8 fpga_ddr_start_addr[0x40]; + + u8 fpga_cr_space_start_addr[0x40]; + + u8 fpga_ddr_size[0x20]; + + u8 fpga_cr_space_size[0x20]; + + u8 reserved_at_500[0x300]; +}; + +enum { + MLX5_FPGA_CTRL_OPERATION_LOAD = 0x1, + MLX5_FPGA_CTRL_OPERATION_RESET = 0x2, + MLX5_FPGA_CTRL_OPERATION_FLASH_SELECT = 0x3, + MLX5_FPGA_CTRL_OPERATION_SANDBOX_BYPASS_ON = 0x4, + MLX5_FPGA_CTRL_OPERATION_SANDBOX_BYPASS_OFF = 0x5, + MLX5_FPGA_CTRL_OPERATION_RESET_SANDBOX = 0x6, +}; + +struct mlx5_ifc_fpga_ctrl_bits { + u8 reserved_at_0[0x8]; + u8 operation[0x8]; + u8 reserved_at_10[0x8]; + u8 status[0x8]; + + u8 reserved_at_20[0x8]; + u8 flash_select_admin[0x8]; + u8 reserved_at_30[0x8]; + u8 flash_select_oper[0x8]; + + u8 reserved_at_40[0x40]; +}; + +enum { + MLX5_FPGA_ERROR_EVENT_SYNDROME_CORRUPTED_DDR = 0x1, + MLX5_FPGA_ERROR_EVENT_SYNDROME_FLASH_TIMEOUT = 0x2, + MLX5_FPGA_ERROR_EVENT_SYNDROME_INTERNAL_LINK_ERROR = 0x3, + MLX5_FPGA_ERROR_EVENT_SYNDROME_WATCHDOG_FAILURE = 0x4, + MLX5_FPGA_ERROR_EVENT_SYNDROME_I2C_FAILURE = 0x5, + MLX5_FPGA_ERROR_EVENT_SYNDROME_IMAGE_CHANGED = 0x6, + MLX5_FPGA_ERROR_EVENT_SYNDROME_TEMPERATURE_CRITICAL = 0x7, +}; + +struct mlx5_ifc_fpga_error_event_bits { + u8 reserved_at_0[0x40]; + + u8 reserved_at_40[0x18]; + u8 syndrome[0x8]; + + u8 reserved_at_60[0x80]; +}; + +#define MLX5_FPGA_ACCESS_REG_SIZE_MAX 64 + +struct mlx5_ifc_fpga_access_reg_bits { + u8 reserved_at_0[0x20]; + + u8 reserved_at_20[0x10]; + u8 size[0x10]; + + u8 address[0x40]; + + u8 data[0][0x8]; +}; + +enum mlx5_ifc_fpga_qp_state { + MLX5_FPGA_QPC_STATE_INIT = 0x0, + MLX5_FPGA_QPC_STATE_ACTIVE = 0x1, + MLX5_FPGA_QPC_STATE_ERROR = 0x2, +}; + +enum mlx5_ifc_fpga_qp_type { + MLX5_FPGA_QPC_QP_TYPE_SHELL_QP = 0x0, + MLX5_FPGA_QPC_QP_TYPE_SANDBOX_QP = 0x1, +}; + +enum mlx5_ifc_fpga_qp_service_type { + MLX5_FPGA_QPC_ST_RC = 0x0, +}; + +struct mlx5_ifc_fpga_qpc_bits { + u8 state[0x4]; + u8 reserved_at_4[0x1b]; + u8 qp_type[0x1]; + + u8 reserved_at_20[0x4]; + u8 st[0x4]; + u8 reserved_at_28[0x10]; + u8 traffic_class[0x8]; + + u8 ether_type[0x10]; + u8 prio[0x3]; + u8 dei[0x1]; + u8 vid[0xc]; + + u8 reserved_at_60[0x20]; + + u8 reserved_at_80[0x8]; + u8 next_rcv_psn[0x18]; + + u8 reserved_at_a0[0x8]; + u8 next_send_psn[0x18]; + + u8 reserved_at_c0[0x10]; + u8 pkey[0x10]; + + u8 reserved_at_e0[0x8]; + u8 remote_qpn[0x18]; + + u8 reserved_at_100[0x15]; + u8 rnr_retry[0x3]; + u8 reserved_at_118[0x5]; + u8 retry_count[0x3]; + + u8 reserved_at_120[0x20]; + + u8 reserved_at_140[0x10]; + u8 remote_mac_47_32[0x10]; + + u8 remote_mac_31_0[0x20]; + + u8 remote_ip[16][0x8]; + + u8 reserved_at_200[0x40]; + + u8 reserved_at_240[0x10]; + u8 fpga_mac_47_32[0x10]; + + u8 fpga_mac_31_0[0x20]; + + u8 fpga_ip[16][0x8]; +}; + +struct mlx5_ifc_fpga_create_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; + + struct mlx5_ifc_fpga_qpc_bits fpga_qpc; +}; + +struct mlx5_ifc_fpga_create_qp_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x8]; + u8 fpga_qpn[0x18]; + + u8 reserved_at_60[0x20]; + + struct mlx5_ifc_fpga_qpc_bits fpga_qpc; +}; + +struct mlx5_ifc_fpga_modify_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x8]; + u8 fpga_qpn[0x18]; + + u8 field_select[0x20]; + + struct mlx5_ifc_fpga_qpc_bits fpga_qpc; +}; + +struct mlx5_ifc_fpga_modify_qp_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_fpga_query_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x8]; + u8 fpga_qpn[0x18]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_fpga_query_qp_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + struct mlx5_ifc_fpga_qpc_bits fpga_qpc; +}; + +struct mlx5_ifc_fpga_query_qp_counters_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 clear[0x1]; + u8 reserved_at_41[0x7]; + u8 fpga_qpn[0x18]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_fpga_query_qp_counters_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + u8 rx_ack_packets[0x40]; + + u8 rx_send_packets[0x40]; + + u8 tx_ack_packets[0x40]; + + u8 tx_send_packets[0x40]; + + u8 rx_total_drop[0x40]; + + u8 reserved_at_1c0[0x1c0]; +}; + +struct mlx5_ifc_fpga_destroy_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x8]; + u8 fpga_qpn[0x18]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_fpga_destroy_qp_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_ipsec_extended_cap_bits { + u8 encapsulation[0x20]; + + u8 reserved_0[0x15]; + u8 ipv4_fragment[0x1]; + u8 ipv6[0x1]; + u8 esn[0x1]; + u8 lso[0x1]; + u8 transport_and_tunnel_mode[0x1]; + u8 tunnel_mode[0x1]; + u8 transport_mode[0x1]; + u8 ah_esp[0x1]; + u8 esp[0x1]; + u8 ah[0x1]; + u8 ipv4_options[0x1]; + + u8 auth_alg[0x20]; + + u8 enc_alg[0x20]; + + u8 sa_cap[0x20]; + + u8 reserved_1[0x10]; + u8 number_of_ipsec_counters[0x10]; + + u8 ipsec_counters_addr_low[0x20]; + u8 ipsec_counters_addr_high[0x20]; +}; + +struct mlx5_ifc_ipsec_counters_bits { + u8 dec_in_packets[0x40]; + + u8 dec_out_packets[0x40]; + + u8 dec_bypass_packets[0x40]; + + u8 enc_in_packets[0x40]; + + u8 enc_out_packets[0x40]; + + u8 enc_bypass_packets[0x40]; + + u8 drop_dec_packets[0x40]; + + u8 failed_auth_dec_packets[0x40]; + + u8 drop_enc_packets[0x40]; + + u8 success_add_sa[0x40]; + + u8 fail_add_sa[0x40]; + + u8 success_delete_sa[0x40]; + + u8 fail_delete_sa[0x40]; + + u8 dropped_cmd[0x40]; +}; + +#endif /* MLX5_IFC_FPGA_H */ diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index e527732fb31b..c57d4b7de3a8 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -92,6 +92,19 @@ enum mlx5e_link_mode { MLX5E_LINK_MODES_NUMBER, }; +enum mlx5e_connector_type { + MLX5E_PORT_UNKNOWN = 0, + MLX5E_PORT_NONE = 1, + MLX5E_PORT_TP = 2, + MLX5E_PORT_AUI = 3, + MLX5E_PORT_BNC = 4, + MLX5E_PORT_MII = 5, + MLX5E_PORT_FIBRE = 6, + MLX5E_PORT_DA = 7, + MLX5E_PORT_OTHER = 8, + MLX5E_CONNECTOR_TYPE_NUMBER, +}; + #define MLX5E_PROT_MASK(link_mode) (1 << link_mode) #define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 0aacb2a7480d..6f41270d80c0 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -50,9 +50,6 @@ #define MLX5_BSF_APPTAG_ESCAPE 0x1 #define MLX5_BSF_APPREF_ESCAPE 0x2 -#define MLX5_QPN_BITS 24 -#define MLX5_QPN_MASK ((1 << MLX5_QPN_BITS) - 1) - enum mlx5_qp_optpar { MLX5_QP_OPTPAR_ALT_ADDR_PATH = 1 << 0, MLX5_QP_OPTPAR_RRE = 1 << 1, @@ -215,6 +212,7 @@ struct mlx5_wqe_ctrl_seg { #define MLX5_WQE_CTRL_OPCODE_MASK 0xff #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8 +#define MLX5_WQE_AV_EXT 0x80000000 enum { MLX5_ETH_WQE_L3_INNER_CSUM = 1 << 4, @@ -223,14 +221,36 @@ enum { MLX5_ETH_WQE_L4_CSUM = 1 << 7, }; +enum { + MLX5_ETH_WQE_INSERT_VLAN = 1 << 15, +}; + +enum { + MLX5_ETH_WQE_SWP_INNER_L3_IPV6 = 1 << 0, + MLX5_ETH_WQE_SWP_INNER_L4_UDP = 1 << 1, + MLX5_ETH_WQE_SWP_OUTER_L3_IPV6 = 1 << 4, + MLX5_ETH_WQE_SWP_OUTER_L4_UDP = 1 << 5, +}; + struct mlx5_wqe_eth_seg { - u8 rsvd0[4]; + u8 swp_outer_l4_offset; + u8 swp_outer_l3_offset; + u8 swp_inner_l4_offset; + u8 swp_inner_l3_offset; u8 cs_flags; - u8 rsvd1; + u8 swp_flags; __be16 mss; __be32 rsvd2; - __be16 inline_hdr_sz; - u8 inline_hdr_start[2]; + union { + struct { + __be16 sz; + u8 start[2]; + } inline_hdr; + struct { + __be16 type; + __be16 vlan_tci; + } insert; + }; }; struct mlx5_wqe_xrc_seg { @@ -245,6 +265,23 @@ struct mlx5_wqe_masked_atomic_seg { __be64 compare_mask; }; +struct mlx5_base_av { + union { + struct { + __be32 qkey; + __be32 reserved; + } qkey; + __be64 dc_key; + } key; + __be32 dqp_dct; + u8 stat_rate_sl; + u8 fl_mlid; + union { + __be16 rlid; + __be16 udp_sport; + }; +}; + struct mlx5_av { union { struct { @@ -268,6 +305,16 @@ struct mlx5_av { u8 rgid[16]; }; +struct mlx5_ib_ah { + struct ib_ah ibah; + struct mlx5_av av; +}; + +static inline struct mlx5_ib_ah *to_mah(struct ib_ah *ibah) +{ + return container_of(ibah, struct mlx5_ib_ah, ibah); +} + struct mlx5_wqe_datagram_seg { struct mlx5_av av; }; @@ -292,10 +339,14 @@ struct mlx5_wqe_data_seg { struct mlx5_wqe_umr_ctrl_seg { u8 flags; u8 rsvd0[3]; - __be16 klm_octowords; - __be16 bsf_octowords; + __be16 xlt_octowords; + union { + __be16 xlt_offset; + __be16 bsf_octowords; + }; __be64 mkey_mask; - u8 rsvd1[32]; + __be32 xlt_offset_47_16; + u8 rsvd1[28]; }; struct mlx5_seg_set_psv { @@ -389,6 +440,10 @@ struct mlx5_bsf { struct mlx5_bsf_inl m_inl; }; +struct mlx5_mtt { + __be64 ptag; +}; + struct mlx5_klm { __be32 bcount; __be32 key; @@ -410,46 +465,9 @@ struct mlx5_stride_block_ctrl_seg { __be16 num_entries; }; -enum mlx5_pagefault_flags { - MLX5_PFAULT_REQUESTOR = 1 << 0, - MLX5_PFAULT_WRITE = 1 << 1, - MLX5_PFAULT_RDMA = 1 << 2, -}; - -/* Contains the details of a pagefault. */ -struct mlx5_pagefault { - u32 bytes_committed; - u8 event_subtype; - enum mlx5_pagefault_flags flags; - union { - /* Initiator or send message responder pagefault details. */ - struct { - /* Received packet size, only valid for responders. */ - u32 packet_size; - /* - * WQE index. Refers to either the send queue or - * receive queue, according to event_subtype. - */ - u16 wqe_index; - } wqe; - /* RDMA responder pagefault details */ - struct { - u32 r_key; - /* - * Received packet size, minimal size page fault - * resolution required for forward progress. - */ - u32 packet_size; - u32 rdma_op_len; - u64 rdma_va; - } rdma; - }; -}; - struct mlx5_core_qp { struct mlx5_core_rsc_common common; /* must be first */ void (*event) (struct mlx5_core_qp *, int); - void (*pfault_handler)(struct mlx5_core_qp *, struct mlx5_pagefault *); int qpn; struct mlx5_rsc_debug *dbg; int pid; @@ -549,10 +567,6 @@ void mlx5_init_qp_table(struct mlx5_core_dev *dev); void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev); int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING -int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 qpn, - u8 context, int error); -#endif int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, struct mlx5_core_qp *rq); void mlx5_core_destroy_rq_tracked(struct mlx5_core_dev *dev, @@ -565,8 +579,6 @@ int mlx5_core_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id); int mlx5_core_dealloc_q_counter(struct mlx5_core_dev *dev, u16 counter_id); int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id, int reset, void *out, int out_size); -int mlx5_core_query_out_of_buffer(struct mlx5_core_dev *dev, u16 counter_id, - u32 *out_of_buffer); static inline const char *mlx5_qp_type_str(int type) { diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index ec35157ea725..656c70b65dd2 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -51,6 +51,7 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u16 vport, u8 *addr); int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, u16 vport, u8 *min_inline); +void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline); int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev, u16 vport, u8 min_inline); int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev, diff --git a/include/linux/mm.h b/include/linux/mm.h index b84615b0f64c..46b9ac5e8569 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -32,6 +32,8 @@ struct user_struct; struct writeback_control; struct bdi_writeback; +void init_mm_internals(void); + #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; @@ -76,6 +78,10 @@ extern int mmap_rnd_compat_bits __read_mostly; #define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x))) #endif +#ifndef lm_alias +#define lm_alias(x) __va(__pa_symbol(x)) +#endif + /* * To prevent common memory management code establishing * a zero page mapping on a read fault. @@ -281,6 +287,17 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */ #define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */ +#define FAULT_FLAG_TRACE \ + { FAULT_FLAG_WRITE, "WRITE" }, \ + { FAULT_FLAG_MKWRITE, "MKWRITE" }, \ + { FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \ + { FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \ + { FAULT_FLAG_KILLABLE, "KILLABLE" }, \ + { FAULT_FLAG_TRIED, "TRIED" }, \ + { FAULT_FLAG_USER, "USER" }, \ + { FAULT_FLAG_REMOTE, "REMOTE" }, \ + { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" } + /* * vm_fault is filled by the the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask @@ -299,6 +316,9 @@ struct vm_fault { unsigned long address; /* Faulting virtual address */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ + pud_t *pud; /* Pointer to pud entry matching + * the 'address' + */ pte_t orig_pte; /* Value of PTE at the time of fault */ struct page *cow_page; /* Page handler may use for COW fault */ @@ -326,6 +346,13 @@ struct vm_fault { */ }; +/* page entry size for vm->huge_fault() */ +enum page_entry_size { + PE_SIZE_PTE = 0, + PE_SIZE_PMD, + PE_SIZE_PUD, +}; + /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer @@ -335,18 +362,17 @@ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*mremap)(struct vm_area_struct * area); - int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); - int (*pmd_fault)(struct vm_area_struct *, unsigned long address, - pmd_t *, unsigned int flags); + int (*fault)(struct vm_fault *vmf); + int (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size); void (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ - int (*page_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf); + int (*page_mkwrite)(struct vm_fault *vmf); /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ - int (*pfn_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf); + int (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs that can switch between memory and hardware @@ -402,6 +428,14 @@ static inline int pmd_devmap(pmd_t pmd) { return 0; } +static inline int pud_devmap(pud_t pud) +{ + return 0; +} +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} #endif /* @@ -484,6 +518,28 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif +extern void *kvmalloc_node(size_t size, gfp_t flags, int node); +static inline void *kvmalloc(size_t size, gfp_t flags) +{ + return kvmalloc_node(size, flags, NUMA_NO_NODE); +} +static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) +{ + return kvmalloc_node(size, flags | __GFP_ZERO, node); +} +static inline void *kvzalloc(size_t size, gfp_t flags) +{ + return kvmalloc(size, flags | __GFP_ZERO); +} + +static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +{ + if (size != 0 && n > SIZE_MAX / size) + return NULL; + + return kvmalloc(n * size, flags); +} + extern void kvfree(const void *addr); static inline atomic_t *compound_mapcount_ptr(struct page *page) @@ -728,19 +784,11 @@ static inline enum zone_type page_zonenum(const struct page *page) } #ifdef CONFIG_ZONE_DEVICE -void get_zone_device_page(struct page *page); -void put_zone_device_page(struct page *page); static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } #else -static inline void get_zone_device_page(struct page *page) -{ -} -static inline void put_zone_device_page(struct page *page) -{ -} static inline bool is_zone_device_page(const struct page *page) { return false; @@ -756,9 +804,6 @@ static inline void get_page(struct page *page) */ VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page); page_ref_inc(page); - - if (unlikely(is_zone_device_page(page))) - get_zone_device_page(page); } static inline void put_page(struct page *page) @@ -767,9 +812,6 @@ static inline void put_page(struct page *page) if (put_page_testzero(page)) __put_page(page); - - if (unlikely(is_zone_device_page(page))) - put_zone_device_page(page); } #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) @@ -1107,6 +1149,20 @@ static inline void clear_page_pfmemalloc(struct page *page) VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \ VM_FAULT_FALLBACK) +#define VM_FAULT_RESULT_TRACE \ + { VM_FAULT_OOM, "OOM" }, \ + { VM_FAULT_SIGBUS, "SIGBUS" }, \ + { VM_FAULT_MAJOR, "MAJOR" }, \ + { VM_FAULT_WRITE, "WRITE" }, \ + { VM_FAULT_HWPOISON, "HWPOISON" }, \ + { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ + { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ + { VM_FAULT_NOPAGE, "NOPAGE" }, \ + { VM_FAULT_LOCKED, "LOCKED" }, \ + { VM_FAULT_RETRY, "RETRY" }, \ + { VM_FAULT_FALLBACK, "FALLBACK" }, \ + { VM_FAULT_DONE_COW, "DONE_COW" } + /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((x) << 12) #define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf) @@ -1124,18 +1180,7 @@ extern void pagefault_out_of_memory(void); */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ -extern void show_free_areas(unsigned int flags); -extern bool skip_free_areas_node(unsigned int flags, int nid); - -int shmem_zero_setup(struct vm_area_struct *); -#ifdef CONFIG_SHMEM -bool shmem_mapping(struct address_space *mapping); -#else -static inline bool shmem_mapping(struct address_space *mapping) -{ - return false; -} -#endif +extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); extern bool can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); @@ -1148,8 +1193,6 @@ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ - bool ignore_dirty; /* Ignore dirty pages */ - bool check_swap_entries; /* Check also swap entries */ }; struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, @@ -1160,12 +1203,16 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, - unsigned long size, struct zap_details *); + unsigned long size); void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); /** * mm_walk - callbacks for walk_page_range + * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry + * this handler should only handle pud_trans_huge() puds. + * the pmd_entry or pte_entry callbacks will be used for + * regular PUDs. * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to @@ -1185,6 +1232,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * (see the comment on walk_page_range() for more details) */ struct mm_walk { + int (*pud_entry)(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk); int (*pmd_entry)(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pte_entry)(pte_t *pte, unsigned long addr, @@ -1344,38 +1393,20 @@ int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); -/* Is the vma a continuation of the stack vma above it? */ -static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr) -{ - return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); -} - static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; } -static inline int stack_guard_page_start(struct vm_area_struct *vma, - unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSDOWN) && - (vma->vm_start == addr) && - !vma_growsdown(vma->vm_prev, addr); -} - -/* Is the vma a continuation of the stack vma below it? */ -static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr) -{ - return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP); -} - -static inline int stack_guard_page_end(struct vm_area_struct *vma, - unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSUP) && - (vma->vm_end == addr) && - !vma_growsup(vma->vm_next, addr); -} +#ifdef CONFIG_SHMEM +/* + * The vma_is_shmem is not inline because it is used only by slow + * paths in userfault. + */ +bool vma_is_shmem(struct vm_area_struct *vma); +#else +static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } +#endif int vma_is_stack_for_current(struct vm_area_struct *vma); @@ -1515,14 +1546,24 @@ static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, return ptep; } +#ifdef __PAGETABLE_P4D_FOLDED +static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, + unsigned long address) +{ + return 0; +} +#else +int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); +#endif + #ifdef __PAGETABLE_PUD_FOLDED -static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, +static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return 0; } #else -int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); +int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); #endif #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) @@ -1574,11 +1615,22 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address); * Remove it when 4level-fixup.h has been removed. */ #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) -static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) + +#ifndef __ARCH_HAS_5LEVEL_HACK +static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, + unsigned long address) +{ + return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? + NULL : p4d_offset(pgd, address); +} + +static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, + unsigned long address) { - return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))? - NULL: pud_offset(pgd, address); + return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? + NULL : pud_offset(p4d, address); } +#endif /* !__ARCH_HAS_5LEVEL_HACK */ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { @@ -1758,8 +1810,26 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } -extern void __init pagecache_init(void); +/* + * No scalability reason to split PUD locks yet, but follow the same pattern + * as the PMD locks to make it easier if we decide to. The VM should not be + * considered ready to switch to split PUD locks yet; there may be places + * which need to be converted from page_table_lock. + */ +static inline spinlock_t *pud_lockptr(struct mm_struct *mm, pud_t *pud) +{ + return &mm->page_table_lock; +} + +static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) +{ + spinlock_t *ptl = pud_lockptr(mm, pud); + + spin_lock(ptl); + return ptl; +} +extern void __init pagecache_init(void); extern void free_area_init(unsigned long * zones_size); extern void free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); @@ -1896,7 +1966,7 @@ extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); -extern void show_mem(unsigned int flags); +extern void show_mem(unsigned int flags, nodemask_t *nodemask); extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); @@ -1904,8 +1974,8 @@ extern void si_meminfo_node(struct sysinfo *val, int nid); extern unsigned long arch_reserved_kernel_pages(void); #endif -extern __printf(2, 3) -void warn_alloc(gfp_t gfp_mask, const char *fmt, ...); +extern __printf(3, 4) +void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); @@ -1968,8 +2038,10 @@ extern struct vm_area_struct *vma_merge(struct mm_struct *, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); -extern int split_vma(struct mm_struct *, - struct vm_area_struct *, unsigned long addr, int new_below); +extern int __split_vma(struct mm_struct *, struct vm_area_struct *, + unsigned long addr, int new_below); +extern int split_vma(struct mm_struct *, struct vm_area_struct *, + unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *, struct rb_node **, struct rb_node *); @@ -2017,18 +2089,22 @@ extern int install_special_mapping(struct mm_struct *mm, extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, vm_flags_t vm_flags, unsigned long pgoff); + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, - vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate); -extern int do_munmap(struct mm_struct *, unsigned long, size_t); + vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, + struct list_head *uf); +extern int do_munmap(struct mm_struct *, unsigned long, size_t, + struct list_head *uf); static inline unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, - unsigned long pgoff, unsigned long *populate) + unsigned long pgoff, unsigned long *populate, + struct list_head *uf) { - return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate); + return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate, uf); } #ifdef CONFIG_MMU @@ -2045,6 +2121,7 @@ static inline void mm_populate(unsigned long addr, unsigned long len) {} /* These take the mm semaphore themselves */ extern int __must_check vm_brk(unsigned long, unsigned long); +extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); extern unsigned long __must_check vm_mmap(struct file *, unsigned long, unsigned long, unsigned long, @@ -2088,13 +2165,13 @@ extern void truncate_inode_pages_range(struct address_space *, extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ -extern int filemap_fault(struct vm_area_struct *, struct vm_fault *); +extern int filemap_fault(struct vm_fault *vmf); extern void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); -extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); +extern int filemap_page_mkwrite(struct vm_fault *vmf); /* mm/page-writeback.c */ -int write_one_page(struct page *page, int wait); +int __must_check write_one_page(struct page *page); void task_dirty_inc(struct task_struct *tsk); /* readahead.c */ @@ -2117,6 +2194,7 @@ void page_cache_async_readahead(struct address_space *mapping, pgoff_t offset, unsigned long size); +extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); @@ -2145,6 +2223,30 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m return vma; } +static inline unsigned long vm_start_gap(struct vm_area_struct *vma) +{ + unsigned long vm_start = vma->vm_start; + + if (vma->vm_flags & VM_GROWSDOWN) { + vm_start -= stack_guard_gap; + if (vm_start > vma->vm_start) + vm_start = 0; + } + return vm_start; +} + +static inline unsigned long vm_end_gap(struct vm_area_struct *vma) +{ + unsigned long vm_end = vma->vm_end; + + if (vma->vm_flags & VM_GROWSUP) { + vm_end += stack_guard_gap; + if (vm_end < vma->vm_end) + vm_end = -PAGE_SIZE; + } + return vm_end; +} + static inline unsigned long vma_pages(struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; @@ -2222,6 +2324,17 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ +static inline int vm_fault_to_errno(int vm_fault, int foll_flags) +{ + if (vm_fault & VM_FAULT_OOM) + return -ENOMEM; + if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) + return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT; + if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) + return -EFAULT; + return 0; +} + typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, @@ -2315,7 +2428,8 @@ void sparse_mem_maps_populate_node(struct page **map_map, struct page *sparse_mem_map_populate(unsigned long pnum, int nid); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); -pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node); +p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); +pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); void *vmemmap_alloc_block(unsigned long size, int node); @@ -2396,10 +2510,13 @@ extern void clear_huge_page(struct page *page, extern void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma, unsigned int pages_per_huge_page); +extern long copy_huge_page_from_user(struct page *dst_page, + const void __user *usr_src, + unsigned int pages_per_huge_page, + bool allow_pagefault); #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ extern struct page_ext_operations debug_guardpage_ops; -extern struct page_ext_operations page_poisoning_ops; #ifdef CONFIG_DEBUG_PAGEALLOC extern unsigned int _debug_guardpage_minorder; diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 41d376e7116d..e030a68ead7e 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -50,6 +50,13 @@ static __always_inline void add_page_to_lru_list(struct page *page, list_add(&page->lru, &lruvec->lists[lru]); } +static __always_inline void add_page_to_lru_list_tail(struct page *page, + struct lruvec *lruvec, enum lru_list lru) +{ + update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page)); + list_add_tail(&page->lru, &lruvec->lists[lru]); +} + static __always_inline void del_page_from_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 808751d7b737..ff151814a02d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1,9 +1,9 @@ #ifndef _LINUX_MM_TYPES_H #define _LINUX_MM_TYPES_H +#include <linux/mm_types_task.h> + #include <linux/auxvec.h> -#include <linux/types.h> -#include <linux/threads.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rbtree.h> @@ -13,7 +13,7 @@ #include <linux/uprobes.h> #include <linux/page-flags-layout.h> #include <linux/workqueue.h> -#include <asm/page.h> + #include <asm/mmu.h> #ifndef AT_VECTOR_SIZE_ARCH @@ -24,11 +24,6 @@ struct address_space; struct mem_cgroup; -#define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) -#define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ - IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) -#define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) - /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the @@ -231,17 +226,6 @@ struct page { #endif ; -struct page_frag { - struct page *page; -#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) - __u32 offset; - __u32 size; -#else - __u16 offset; - __u16 size; -#endif -}; - #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) @@ -358,7 +342,7 @@ struct vm_area_struct { struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; -}; +} __randomize_layout; struct core_thread { struct task_struct *task; @@ -371,27 +355,6 @@ struct core_state { struct completion startup; }; -enum { - MM_FILEPAGES, /* Resident file mapping pages */ - MM_ANONPAGES, /* Resident anonymous pages */ - MM_SWAPENTS, /* Anonymous swap entries */ - MM_SHMEMPAGES, /* Resident shared memory pages */ - NR_MM_COUNTERS -}; - -#if USE_SPLIT_PTE_PTLOCKS && defined(CONFIG_MMU) -#define SPLIT_RSS_COUNTING -/* per-thread cached information, */ -struct task_rss_stat { - int events; /* for synchronization threshold */ - int count[NR_MM_COUNTERS]; -}; -#endif /* USE_SPLIT_PTE_PTLOCKS */ - -struct mm_rss_stat { - atomic_long_t count[NR_MM_COUNTERS]; -}; - struct kioctx_table; struct mm_struct { struct vm_area_struct *mmap; /* list of VMAs */ @@ -404,11 +367,35 @@ struct mm_struct { #endif unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ +#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES + /* Base adresses for compatible mmap() */ + unsigned long mmap_compat_base; + unsigned long mmap_compat_legacy_base; +#endif unsigned long task_size; /* size of task vm space */ unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; - atomic_t mm_users; /* How many users with user space? */ - atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ + + /** + * @mm_users: The number of users including userspace. + * + * Use mmget()/mmget_not_zero()/mmput() to modify. When this drops + * to 0 (i.e. when the task exits and there are no other temporary + * reference holders), we also release a reference on @mm_count + * (which may then free the &struct mm_struct if @mm_count also + * drops to 0). + */ + atomic_t mm_users; + + /** + * @mm_count: The number of references to &struct mm_struct + * (@mm_users count as 1). + * + * Use mmgrab()/mmdrop() to modify. When this drops to 0, the + * &struct mm_struct is freed. + */ + atomic_t mm_count; + atomic_long_t nr_ptes; /* PTE page table pages */ #if CONFIG_PGTABLE_LEVELS > 2 atomic_long_t nr_pmds; /* PMD page table pages */ @@ -513,7 +500,9 @@ struct mm_struct { atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; -}; +} __randomize_layout; + +extern struct mm_struct init_mm; static inline void mm_init_cpumask(struct mm_struct *mm) { diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h new file mode 100644 index 000000000000..fc412fbd80bd --- /dev/null +++ b/include/linux/mm_types_task.h @@ -0,0 +1,94 @@ +#ifndef _LINUX_MM_TYPES_TASK_H +#define _LINUX_MM_TYPES_TASK_H + +/* + * Here are the definitions of the MM data types that are embedded in 'struct task_struct'. + * + * (These are defined separately to decouple sched.h from mm_types.h as much as possible.) + */ + +#include <linux/types.h> +#include <linux/threads.h> +#include <linux/atomic.h> +#include <linux/cpumask.h> + +#include <asm/page.h> + +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH +#include <asm/tlbbatch.h> +#endif + +#define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) +#define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ + IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) +#define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) + +/* + * The per task VMA cache array: + */ +#define VMACACHE_BITS 2 +#define VMACACHE_SIZE (1U << VMACACHE_BITS) +#define VMACACHE_MASK (VMACACHE_SIZE - 1) + +struct vmacache { + u32 seqnum; + struct vm_area_struct *vmas[VMACACHE_SIZE]; +}; + +enum { + MM_FILEPAGES, /* Resident file mapping pages */ + MM_ANONPAGES, /* Resident anonymous pages */ + MM_SWAPENTS, /* Anonymous swap entries */ + MM_SHMEMPAGES, /* Resident shared memory pages */ + NR_MM_COUNTERS +}; + +#if USE_SPLIT_PTE_PTLOCKS && defined(CONFIG_MMU) +#define SPLIT_RSS_COUNTING +/* per-thread cached information, */ +struct task_rss_stat { + int events; /* for synchronization threshold */ + int count[NR_MM_COUNTERS]; +}; +#endif /* USE_SPLIT_PTE_PTLOCKS */ + +struct mm_rss_stat { + atomic_long_t count[NR_MM_COUNTERS]; +}; + +struct page_frag { + struct page *page; +#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) + __u32 offset; + __u32 size; +#else + __u16 offset; + __u16 size; +#endif +}; + +/* Track pages that require TLB flushes */ +struct tlbflush_unmap_batch { +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH + /* + * The arch code makes the following promise: generic code can modify a + * PTE, then call arch_tlbbatch_add_mm() (which internally provides all + * needed barriers), then call arch_tlbbatch_flush(), and the entries + * will be flushed on all CPUs by the time that arch_tlbbatch_flush() + * returns. + */ + struct arch_tlbflush_unmap_batch arch; + + /* True if a flush is needed. */ + bool flush_required; + + /* + * If true then the PTE was dirty when unmapped. The entry must be + * flushed before IO is initiated or a stale TLB entry potentially + * allows an update without redirtying the page. + */ + bool writable; +#endif +}; + +#endif /* _LINUX_MM_TYPES_TASK_H */ diff --git a/include/linux/mman.h b/include/linux/mman.h index 634c4c51fe3a..c8367041fafd 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -22,7 +22,7 @@ unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { - __percpu_counter_add(&vm_committed_as, pages, vm_committed_as_batch); + percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) diff --git a/include/linux/mmc/boot.h b/include/linux/mmc/boot.h deleted file mode 100644 index 23acc3baa07d..000000000000 --- a/include/linux/mmc/boot.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef LINUX_MMC_BOOT_H -#define LINUX_MMC_BOOT_H - -enum { MMC_PROGRESS_ENTER, MMC_PROGRESS_INIT, - MMC_PROGRESS_LOAD, MMC_PROGRESS_DONE }; - -#endif /* LINUX_MMC_BOOT_H */ diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 95d69d498296..46c73e97e61f 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -11,7 +11,6 @@ #define LINUX_MMC_CARD_H #include <linux/device.h> -#include <linux/mmc/core.h> #include <linux/mod_devicetable.h> struct mmc_cid { @@ -84,11 +83,13 @@ struct mmc_ext_csd { unsigned int hpi_cmd; /* cmd used as HPI */ bool bkops; /* background support bit */ bool man_bkops_en; /* manual bkops enable bit */ + bool auto_bkops_en; /* auto bkops enable bit */ unsigned int data_sector_size; /* 512 bytes or 4KB */ unsigned int data_tag_unit_size; /* DATA TAG UNIT size */ unsigned int boot_ro_lock; /* ro lock support */ bool boot_ro_lockable; bool ffu_capable; /* Firmware upgrade support */ + bool cmdq_en; /* Command Queue enabled */ bool cmdq_support; /* Command Queue supported */ unsigned int cmdq_depth; /* Command Queue depth */ #define MMC_FIRMWARE_LEN 8 @@ -121,6 +122,9 @@ struct mmc_ext_csd { u8 raw_pwr_cl_ddr_200_360; /* 253 */ u8 raw_bkops_status; /* 246 */ u8 raw_sectors[4]; /* 212 - 4 bytes */ + u8 pre_eol_info; /* 267 */ + u8 device_life_time_est_typ_a; /* 268 */ + u8 device_life_time_est_typ_b; /* 269 */ unsigned int feature_support; #define MMC_DISCARD_FEATURE BIT(0) /* CMD38 feature */ @@ -203,9 +207,9 @@ struct sdio_cis { }; struct mmc_host; -struct mmc_ios; struct sdio_func; struct sdio_func_tuple; +struct mmc_queue_req; #define SDIO_MAX_FUNCS 7 @@ -247,13 +251,6 @@ struct mmc_card { #define MMC_TYPE_SDIO 2 /* SDIO card */ #define MMC_TYPE_SD_COMBO 3 /* SD combo (IO+mem) card */ unsigned int state; /* (our) card state */ -#define MMC_STATE_PRESENT (1<<0) /* present in sysfs */ -#define MMC_STATE_READONLY (1<<1) /* card is read-only */ -#define MMC_STATE_BLOCKADDR (1<<2) /* card uses block-addressing */ -#define MMC_CARD_SDXC (1<<3) /* card is SDXC */ -#define MMC_CARD_REMOVED (1<<4) /* card has been removed */ -#define MMC_STATE_DOING_BKOPS (1<<5) /* card is doing BKOPS */ -#define MMC_STATE_SUSPENDED (1<<6) /* card is suspended */ unsigned int quirks; /* card quirks */ #define MMC_QUIRK_LENIENT_FN0 (1<<0) /* allow SDIO FN0 writes outside of the VS CCCR range */ #define MMC_QUIRK_BLKSZ_FOR_BYTE_MODE (1<<1) /* use func->cur_blksize */ @@ -272,6 +269,7 @@ struct mmc_card { #define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ #define MMC_QUIRK_BROKEN_HPI (1<<13) /* Disable broken HPI support */ + bool reenable_cmdq; /* Re-enable Command Queue */ unsigned int erase_size; /* erase size in sectors */ unsigned int erase_shift; /* if erase unit is power 2 */ @@ -306,247 +304,19 @@ struct mmc_card { struct dentry *debugfs_root; struct mmc_part part[MMC_NUM_PHY_PARTITION]; /* physical partitions */ unsigned int nr_parts; -}; -/* - * This function fill contents in mmc_part. - */ -static inline void mmc_part_add(struct mmc_card *card, unsigned int size, - unsigned int part_cfg, char *name, int idx, bool ro, - int area_type) -{ - card->part[card->nr_parts].size = size; - card->part[card->nr_parts].part_cfg = part_cfg; - sprintf(card->part[card->nr_parts].name, name, idx); - card->part[card->nr_parts].force_ro = ro; - card->part[card->nr_parts].area_type = area_type; - card->nr_parts++; -} + unsigned int bouncesz; /* Bounce buffer size */ +}; static inline bool mmc_large_sector(struct mmc_card *card) { return card->ext_csd.data_sector_size == 4096; } -/* - * The world is not perfect and supplies us with broken mmc/sdio devices. - * For at least some of these bugs we need a work-around. - */ - -struct mmc_fixup { - /* CID-specific fields. */ - const char *name; - - /* Valid revision range */ - u64 rev_start, rev_end; - - unsigned int manfid; - unsigned short oemid; - - /* SDIO-specfic fields. You can use SDIO_ANY_ID here of course */ - u16 cis_vendor, cis_device; - - /* for MMC cards */ - unsigned int ext_csd_rev; - - void (*vendor_fixup)(struct mmc_card *card, int data); - int data; -}; - -#define CID_MANFID_ANY (-1u) -#define CID_OEMID_ANY ((unsigned short) -1) -#define CID_NAME_ANY (NULL) - -#define EXT_CSD_REV_ANY (-1u) - -#define CID_MANFID_SANDISK 0x2 -#define CID_MANFID_TOSHIBA 0x11 -#define CID_MANFID_MICRON 0x13 -#define CID_MANFID_SAMSUNG 0x15 -#define CID_MANFID_KINGSTON 0x70 -#define CID_MANFID_HYNIX 0x90 - -#define END_FIXUP { NULL } - -#define _FIXUP_EXT(_name, _manfid, _oemid, _rev_start, _rev_end, \ - _cis_vendor, _cis_device, \ - _fixup, _data, _ext_csd_rev) \ - { \ - .name = (_name), \ - .manfid = (_manfid), \ - .oemid = (_oemid), \ - .rev_start = (_rev_start), \ - .rev_end = (_rev_end), \ - .cis_vendor = (_cis_vendor), \ - .cis_device = (_cis_device), \ - .vendor_fixup = (_fixup), \ - .data = (_data), \ - .ext_csd_rev = (_ext_csd_rev), \ - } - -#define MMC_FIXUP_REV(_name, _manfid, _oemid, _rev_start, _rev_end, \ - _fixup, _data, _ext_csd_rev) \ - _FIXUP_EXT(_name, _manfid, \ - _oemid, _rev_start, _rev_end, \ - SDIO_ANY_ID, SDIO_ANY_ID, \ - _fixup, _data, _ext_csd_rev) \ - -#define MMC_FIXUP(_name, _manfid, _oemid, _fixup, _data) \ - MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data, \ - EXT_CSD_REV_ANY) - -#define MMC_FIXUP_EXT_CSD_REV(_name, _manfid, _oemid, _fixup, _data, \ - _ext_csd_rev) \ - MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data, \ - _ext_csd_rev) - -#define SDIO_FIXUP(_vendor, _device, _fixup, _data) \ - _FIXUP_EXT(CID_NAME_ANY, CID_MANFID_ANY, \ - CID_OEMID_ANY, 0, -1ull, \ - _vendor, _device, \ - _fixup, _data, EXT_CSD_REV_ANY) \ - -#define cid_rev(hwrev, fwrev, year, month) \ - (((u64) hwrev) << 40 | \ - ((u64) fwrev) << 32 | \ - ((u64) year) << 16 | \ - ((u64) month)) - -#define cid_rev_card(card) \ - cid_rev(card->cid.hwrev, \ - card->cid.fwrev, \ - card->cid.year, \ - card->cid.month) - -/* - * Unconditionally quirk add/remove. - */ - -static inline void __maybe_unused add_quirk(struct mmc_card *card, int data) -{ - card->quirks |= data; -} - -static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data) -{ - card->quirks &= ~data; -} +bool mmc_card_is_blockaddr(struct mmc_card *card); #define mmc_card_mmc(c) ((c)->type == MMC_TYPE_MMC) #define mmc_card_sd(c) ((c)->type == MMC_TYPE_SD) #define mmc_card_sdio(c) ((c)->type == MMC_TYPE_SDIO) -#define mmc_card_present(c) ((c)->state & MMC_STATE_PRESENT) -#define mmc_card_readonly(c) ((c)->state & MMC_STATE_READONLY) -#define mmc_card_blockaddr(c) ((c)->state & MMC_STATE_BLOCKADDR) -#define mmc_card_ext_capacity(c) ((c)->state & MMC_CARD_SDXC) -#define mmc_card_removed(c) ((c) && ((c)->state & MMC_CARD_REMOVED)) -#define mmc_card_doing_bkops(c) ((c)->state & MMC_STATE_DOING_BKOPS) -#define mmc_card_suspended(c) ((c)->state & MMC_STATE_SUSPENDED) - -#define mmc_card_set_present(c) ((c)->state |= MMC_STATE_PRESENT) -#define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY) -#define mmc_card_set_blockaddr(c) ((c)->state |= MMC_STATE_BLOCKADDR) -#define mmc_card_set_ext_capacity(c) ((c)->state |= MMC_CARD_SDXC) -#define mmc_card_set_removed(c) ((c)->state |= MMC_CARD_REMOVED) -#define mmc_card_set_doing_bkops(c) ((c)->state |= MMC_STATE_DOING_BKOPS) -#define mmc_card_clr_doing_bkops(c) ((c)->state &= ~MMC_STATE_DOING_BKOPS) -#define mmc_card_set_suspended(c) ((c)->state |= MMC_STATE_SUSPENDED) -#define mmc_card_clr_suspended(c) ((c)->state &= ~MMC_STATE_SUSPENDED) - -/* - * Quirk add/remove for MMC products. - */ - -static inline void __maybe_unused add_quirk_mmc(struct mmc_card *card, int data) -{ - if (mmc_card_mmc(card)) - card->quirks |= data; -} - -static inline void __maybe_unused remove_quirk_mmc(struct mmc_card *card, - int data) -{ - if (mmc_card_mmc(card)) - card->quirks &= ~data; -} - -/* - * Quirk add/remove for SD products. - */ - -static inline void __maybe_unused add_quirk_sd(struct mmc_card *card, int data) -{ - if (mmc_card_sd(card)) - card->quirks |= data; -} - -static inline void __maybe_unused remove_quirk_sd(struct mmc_card *card, - int data) -{ - if (mmc_card_sd(card)) - card->quirks &= ~data; -} - -static inline int mmc_card_lenient_fn0(const struct mmc_card *c) -{ - return c->quirks & MMC_QUIRK_LENIENT_FN0; -} - -static inline int mmc_blksz_for_byte_mode(const struct mmc_card *c) -{ - return c->quirks & MMC_QUIRK_BLKSZ_FOR_BYTE_MODE; -} - -static inline int mmc_card_disable_cd(const struct mmc_card *c) -{ - return c->quirks & MMC_QUIRK_DISABLE_CD; -} - -static inline int mmc_card_nonstd_func_interface(const struct mmc_card *c) -{ - return c->quirks & MMC_QUIRK_NONSTD_FUNC_IF; -} - -static inline int mmc_card_broken_byte_mode_512(const struct mmc_card *c) -{ - return c->quirks & MMC_QUIRK_BROKEN_BYTE_MODE_512; -} - -static inline int mmc_card_long_read_time(const struct mmc_card *c) -{ - return c->quirks & MMC_QUIRK_LONG_READ_TIME; -} - -static inline int mmc_card_broken_irq_polling(const struct mmc_card *c) -{ - return c->quirks & MMC_QUIRK_BROKEN_IRQ_POLLING; -} - -static inline int mmc_card_broken_hpi(const struct mmc_card *c) -{ - return c->quirks & MMC_QUIRK_BROKEN_HPI; -} - -#define mmc_card_name(c) ((c)->cid.prod_name) -#define mmc_card_id(c) (dev_name(&(c)->dev)) - -#define mmc_dev_to_card(d) container_of(d, struct mmc_card, dev) - -/* - * MMC device driver (e.g., Flash card, I/O card...) - */ -struct mmc_driver { - struct device_driver drv; - int (*probe)(struct mmc_card *); - void (*remove)(struct mmc_card *); - void (*shutdown)(struct mmc_card *); -}; - -extern int mmc_register_driver(struct mmc_driver *); -extern void mmc_unregister_driver(struct mmc_driver *); - -extern void mmc_fixup_device(struct mmc_card *card, - const struct mmc_fixup *table); - #endif /* LINUX_MMC_CARD_H */ diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index e33cc748dcfe..a0c63ea28796 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -8,10 +8,9 @@ #ifndef LINUX_MMC_CORE_H #define LINUX_MMC_CORE_H -#include <linux/interrupt.h> #include <linux/completion.h> +#include <linux/types.h> -struct request; struct mmc_data; struct mmc_request; @@ -159,79 +158,14 @@ struct mmc_request { struct mmc_card; struct mmc_async_req; -extern int mmc_stop_bkops(struct mmc_card *); -extern int mmc_read_bkops_status(struct mmc_card *); -extern struct mmc_async_req *mmc_start_req(struct mmc_host *, - struct mmc_async_req *, - enum mmc_blk_status *); -extern int mmc_interrupt_hpi(struct mmc_card *); -extern void mmc_wait_for_req(struct mmc_host *, struct mmc_request *); -extern void mmc_wait_for_req_done(struct mmc_host *host, - struct mmc_request *mrq); -extern bool mmc_is_req_done(struct mmc_host *host, struct mmc_request *mrq); -extern int mmc_wait_for_cmd(struct mmc_host *, struct mmc_command *, int); -extern int mmc_app_cmd(struct mmc_host *, struct mmc_card *); -extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *, - struct mmc_command *, int); -extern void mmc_start_bkops(struct mmc_card *card, bool from_exception); -extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int); -extern int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); -extern int mmc_abort_tuning(struct mmc_host *host, u32 opcode); -extern int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd); - -#define MMC_ERASE_ARG 0x00000000 -#define MMC_SECURE_ERASE_ARG 0x80000000 -#define MMC_TRIM_ARG 0x00000001 -#define MMC_DISCARD_ARG 0x00000003 -#define MMC_SECURE_TRIM1_ARG 0x80000001 -#define MMC_SECURE_TRIM2_ARG 0x80008000 - -#define MMC_SECURE_ARGS 0x80000000 -#define MMC_TRIM_ARGS 0x00008001 - -extern int mmc_erase(struct mmc_card *card, unsigned int from, unsigned int nr, - unsigned int arg); -extern int mmc_can_erase(struct mmc_card *card); -extern int mmc_can_trim(struct mmc_card *card); -extern int mmc_can_discard(struct mmc_card *card); -extern int mmc_can_sanitize(struct mmc_card *card); -extern int mmc_can_secure_erase_trim(struct mmc_card *card); -extern int mmc_erase_group_aligned(struct mmc_card *card, unsigned int from, - unsigned int nr); -extern unsigned int mmc_calc_max_discard(struct mmc_card *card); - -extern int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen); -extern int mmc_set_blockcount(struct mmc_card *card, unsigned int blockcount, - bool is_rel_write); -extern int mmc_hw_reset(struct mmc_host *host); -extern int mmc_can_reset(struct mmc_card *card); - -extern void mmc_set_data_timeout(struct mmc_data *, const struct mmc_card *); -extern unsigned int mmc_align_data_size(struct mmc_card *, unsigned int); - -extern int __mmc_claim_host(struct mmc_host *host, atomic_t *abort); -extern void mmc_release_host(struct mmc_host *host); - -extern void mmc_get_card(struct mmc_card *card); -extern void mmc_put_card(struct mmc_card *card); - -extern int mmc_flush_cache(struct mmc_card *); - -extern int mmc_detect_card_removed(struct mmc_host *host); - -/** - * mmc_claim_host - exclusively claim a host - * @host: mmc host to claim - * - * Claim a host for a set of operations. - */ -static inline void mmc_claim_host(struct mmc_host *host) -{ - __mmc_claim_host(host, NULL); -} - -struct device_node; -extern u32 mmc_vddrange_to_ocrmask(int vdd_min, int vdd_max); -extern int mmc_of_parse_voltage(struct device_node *np, u32 *mask); +struct mmc_async_req *mmc_start_areq(struct mmc_host *host, + struct mmc_async_req *areq, + enum mmc_blk_status *ret_stat); +void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq); +int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, + int retries); + +int mmc_hw_reset(struct mmc_host *host); +void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); #endif /* LINUX_MMC_CORE_H */ diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h deleted file mode 100644 index 15db6f83f53f..000000000000 --- a/include/linux/mmc/dw_mmc.h +++ /dev/null @@ -1,274 +0,0 @@ -/* - * Synopsys DesignWare Multimedia Card Interface driver - * (Based on NXP driver for lpc 31xx) - * - * Copyright (C) 2009 NXP Semiconductors - * Copyright (C) 2009, 2010 Imagination Technologies Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#ifndef LINUX_MMC_DW_MMC_H -#define LINUX_MMC_DW_MMC_H - -#include <linux/scatterlist.h> -#include <linux/mmc/core.h> -#include <linux/dmaengine.h> -#include <linux/reset.h> - -#define MAX_MCI_SLOTS 2 - -enum dw_mci_state { - STATE_IDLE = 0, - STATE_SENDING_CMD, - STATE_SENDING_DATA, - STATE_DATA_BUSY, - STATE_SENDING_STOP, - STATE_DATA_ERROR, - STATE_SENDING_CMD11, - STATE_WAITING_CMD11_DONE, -}; - -enum { - EVENT_CMD_COMPLETE = 0, - EVENT_XFER_COMPLETE, - EVENT_DATA_COMPLETE, - EVENT_DATA_ERROR, -}; - -enum dw_mci_cookie { - COOKIE_UNMAPPED, - COOKIE_PRE_MAPPED, /* mapped by pre_req() of dwmmc */ - COOKIE_MAPPED, /* mapped by prepare_data() of dwmmc */ -}; - -struct mmc_data; - -enum { - TRANS_MODE_PIO = 0, - TRANS_MODE_IDMAC, - TRANS_MODE_EDMAC -}; - -struct dw_mci_dma_slave { - struct dma_chan *ch; - enum dma_transfer_direction direction; -}; - -/** - * struct dw_mci - MMC controller state shared between all slots - * @lock: Spinlock protecting the queue and associated data. - * @irq_lock: Spinlock protecting the INTMASK setting. - * @regs: Pointer to MMIO registers. - * @fifo_reg: Pointer to MMIO registers for data FIFO - * @sg: Scatterlist entry currently being processed by PIO code, if any. - * @sg_miter: PIO mapping scatterlist iterator. - * @cur_slot: The slot which is currently using the controller. - * @mrq: The request currently being processed on @cur_slot, - * or NULL if the controller is idle. - * @cmd: The command currently being sent to the card, or NULL. - * @data: The data currently being transferred, or NULL if no data - * transfer is in progress. - * @stop_abort: The command currently prepared for stoping transfer. - * @prev_blksz: The former transfer blksz record. - * @timing: Record of current ios timing. - * @use_dma: Whether DMA channel is initialized or not. - * @using_dma: Whether DMA is in use for the current transfer. - * @dma_64bit_address: Whether DMA supports 64-bit address mode or not. - * @sg_dma: Bus address of DMA buffer. - * @sg_cpu: Virtual address of DMA buffer. - * @dma_ops: Pointer to platform-specific DMA callbacks. - * @cmd_status: Snapshot of SR taken upon completion of the current - * @ring_size: Buffer size for idma descriptors. - * command. Only valid when EVENT_CMD_COMPLETE is pending. - * @dms: structure of slave-dma private data. - * @phy_regs: physical address of controller's register map - * @data_status: Snapshot of SR taken upon completion of the current - * data transfer. Only valid when EVENT_DATA_COMPLETE or - * EVENT_DATA_ERROR is pending. - * @stop_cmdr: Value to be loaded into CMDR when the stop command is - * to be sent. - * @dir_status: Direction of current transfer. - * @tasklet: Tasklet running the request state machine. - * @pending_events: Bitmask of events flagged by the interrupt handler - * to be processed by the tasklet. - * @completed_events: Bitmask of events which the state machine has - * processed. - * @state: Tasklet state. - * @queue: List of slots waiting for access to the controller. - * @bus_hz: The rate of @mck in Hz. This forms the basis for MMC bus - * rate and timeout calculations. - * @current_speed: Configured rate of the controller. - * @num_slots: Number of slots available. - * @fifoth_val: The value of FIFOTH register. - * @verid: Denote Version ID. - * @dev: Device associated with the MMC controller. - * @pdata: Platform data associated with the MMC controller. - * @drv_data: Driver specific data for identified variant of the controller - * @priv: Implementation defined private data. - * @biu_clk: Pointer to bus interface unit clock instance. - * @ciu_clk: Pointer to card interface unit clock instance. - * @slot: Slots sharing this MMC controller. - * @fifo_depth: depth of FIFO. - * @data_shift: log2 of FIFO item size. - * @part_buf_start: Start index in part_buf. - * @part_buf_count: Bytes of partial data in part_buf. - * @part_buf: Simple buffer for partial fifo reads/writes. - * @push_data: Pointer to FIFO push function. - * @pull_data: Pointer to FIFO pull function. - * @vqmmc_enabled: Status of vqmmc, should be true or false. - * @irq_flags: The flags to be passed to request_irq. - * @irq: The irq value to be passed to request_irq. - * @sdio_id0: Number of slot0 in the SDIO interrupt registers. - * @cmd11_timer: Timer for SD3.0 voltage switch over scheme. - * @dto_timer: Timer for broken data transfer over scheme. - * - * Locking - * ======= - * - * @lock is a softirq-safe spinlock protecting @queue as well as - * @cur_slot, @mrq and @state. These must always be updated - * at the same time while holding @lock. - * - * @irq_lock is an irq-safe spinlock protecting the INTMASK register - * to allow the interrupt handler to modify it directly. Held for only long - * enough to read-modify-write INTMASK and no other locks are grabbed when - * holding this one. - * - * The @mrq field of struct dw_mci_slot is also protected by @lock, - * and must always be written at the same time as the slot is added to - * @queue. - * - * @pending_events and @completed_events are accessed using atomic bit - * operations, so they don't need any locking. - * - * None of the fields touched by the interrupt handler need any - * locking. However, ordering is important: Before EVENT_DATA_ERROR or - * EVENT_DATA_COMPLETE is set in @pending_events, all data-related - * interrupts must be disabled and @data_status updated with a - * snapshot of SR. Similarly, before EVENT_CMD_COMPLETE is set, the - * CMDRDY interrupt must be disabled and @cmd_status updated with a - * snapshot of SR, and before EVENT_XFER_COMPLETE can be set, the - * bytes_xfered field of @data must be written. This is ensured by - * using barriers. - */ -struct dw_mci { - spinlock_t lock; - spinlock_t irq_lock; - void __iomem *regs; - void __iomem *fifo_reg; - - struct scatterlist *sg; - struct sg_mapping_iter sg_miter; - - struct dw_mci_slot *cur_slot; - struct mmc_request *mrq; - struct mmc_command *cmd; - struct mmc_data *data; - struct mmc_command stop_abort; - unsigned int prev_blksz; - unsigned char timing; - - /* DMA interface members*/ - int use_dma; - int using_dma; - int dma_64bit_address; - - dma_addr_t sg_dma; - void *sg_cpu; - const struct dw_mci_dma_ops *dma_ops; - /* For idmac */ - unsigned int ring_size; - - /* For edmac */ - struct dw_mci_dma_slave *dms; - /* Registers's physical base address */ - resource_size_t phy_regs; - - u32 cmd_status; - u32 data_status; - u32 stop_cmdr; - u32 dir_status; - struct tasklet_struct tasklet; - unsigned long pending_events; - unsigned long completed_events; - enum dw_mci_state state; - struct list_head queue; - - u32 bus_hz; - u32 current_speed; - u32 num_slots; - u32 fifoth_val; - u16 verid; - struct device *dev; - struct dw_mci_board *pdata; - const struct dw_mci_drv_data *drv_data; - void *priv; - struct clk *biu_clk; - struct clk *ciu_clk; - struct dw_mci_slot *slot[MAX_MCI_SLOTS]; - - /* FIFO push and pull */ - int fifo_depth; - int data_shift; - u8 part_buf_start; - u8 part_buf_count; - union { - u16 part_buf16; - u32 part_buf32; - u64 part_buf; - }; - void (*push_data)(struct dw_mci *host, void *buf, int cnt); - void (*pull_data)(struct dw_mci *host, void *buf, int cnt); - - bool vqmmc_enabled; - unsigned long irq_flags; /* IRQ flags */ - int irq; - - int sdio_id0; - - struct timer_list cmd11_timer; - struct timer_list dto_timer; -}; - -/* DMA ops for Internal/External DMAC interface */ -struct dw_mci_dma_ops { - /* DMA Ops */ - int (*init)(struct dw_mci *host); - int (*start)(struct dw_mci *host, unsigned int sg_len); - void (*complete)(void *host); - void (*stop)(struct dw_mci *host); - void (*cleanup)(struct dw_mci *host); - void (*exit)(struct dw_mci *host); -}; - -struct dma_pdata; - -/* Board platform data */ -struct dw_mci_board { - u32 num_slots; - - unsigned int bus_hz; /* Clock speed at the cclk_in pad */ - - u32 caps; /* Capabilities */ - u32 caps2; /* More capabilities */ - u32 pm_caps; /* PM capabilities */ - /* - * Override fifo depth. If 0, autodetect it from the FIFOTH register, - * but note that this may not be reliable after a bootloader has used - * it. - */ - unsigned int fifo_depth; - - /* delay in mS before detecting cards after interrupt */ - u32 detect_delay_ms; - - struct reset_control *rstc; - struct dw_mci_dma_ops *dma_ops; - struct dma_pdata *data; -}; - -#endif /* LINUX_MMC_DW_MMC_H */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 8bc884121465..ebd1cebbef0c 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -10,17 +10,14 @@ #ifndef LINUX_MMC_HOST_H #define LINUX_MMC_HOST_H -#include <linux/leds.h> -#include <linux/mutex.h> -#include <linux/timer.h> #include <linux/sched.h> #include <linux/device.h> #include <linux/fault-inject.h> #include <linux/mmc/core.h> #include <linux/mmc/card.h> -#include <linux/mmc/mmc.h> #include <linux/mmc/pm.h> +#include <linux/dma-direction.h> struct mmc_ios { unsigned int clock; /* clock rate */ @@ -82,6 +79,8 @@ struct mmc_ios { bool enhanced_strobe; /* hs400es selection */ }; +struct mmc_host; + struct mmc_host_ops { /* * It is optional for the host to implement pre_req and post_req in @@ -131,6 +130,7 @@ struct mmc_host_ops { int (*get_cd)(struct mmc_host *host); void (*enable_sdio_irq)(struct mmc_host *host, int enable); + void (*ack_sdio_irq)(struct mmc_host *host); /* optional callback for HC quirks */ void (*init_card)(struct mmc_host *host, struct mmc_card *card); @@ -162,9 +162,6 @@ struct mmc_host_ops { unsigned int direction, int blk_size); }; -struct mmc_card; -struct device; - struct mmc_async_req { /* active mmc request */ struct mmc_request *mrq; @@ -188,6 +185,7 @@ struct mmc_async_req { */ struct mmc_slot { int cd_irq; + bool cd_wake_enabled; void *handler_priv; }; @@ -264,20 +262,21 @@ struct mmc_host { #define MMC_CAP_NONREMOVABLE (1 << 8) /* Nonremovable e.g. eMMC */ #define MMC_CAP_WAIT_WHILE_BUSY (1 << 9) /* Waits while card is busy */ #define MMC_CAP_ERASE (1 << 10) /* Allow erase/trim commands */ -#define MMC_CAP_1_8V_DDR (1 << 11) /* can support */ - /* DDR mode at 1.8V */ -#define MMC_CAP_1_2V_DDR (1 << 12) /* can support */ - /* DDR mode at 1.2V */ -#define MMC_CAP_POWER_OFF_CARD (1 << 13) /* Can power off after boot */ -#define MMC_CAP_BUS_WIDTH_TEST (1 << 14) /* CMD14/CMD19 bus width ok */ -#define MMC_CAP_UHS_SDR12 (1 << 15) /* Host supports UHS SDR12 mode */ -#define MMC_CAP_UHS_SDR25 (1 << 16) /* Host supports UHS SDR25 mode */ -#define MMC_CAP_UHS_SDR50 (1 << 17) /* Host supports UHS SDR50 mode */ -#define MMC_CAP_UHS_SDR104 (1 << 18) /* Host supports UHS SDR104 mode */ -#define MMC_CAP_UHS_DDR50 (1 << 19) /* Host supports UHS DDR50 mode */ +#define MMC_CAP_3_3V_DDR (1 << 11) /* Host supports eMMC DDR 3.3V */ +#define MMC_CAP_1_8V_DDR (1 << 12) /* Host supports eMMC DDR 1.8V */ +#define MMC_CAP_1_2V_DDR (1 << 13) /* Host supports eMMC DDR 1.2V */ +#define MMC_CAP_POWER_OFF_CARD (1 << 14) /* Can power off after boot */ +#define MMC_CAP_BUS_WIDTH_TEST (1 << 15) /* CMD14/CMD19 bus width ok */ +#define MMC_CAP_UHS_SDR12 (1 << 16) /* Host supports UHS SDR12 mode */ +#define MMC_CAP_UHS_SDR25 (1 << 17) /* Host supports UHS SDR25 mode */ +#define MMC_CAP_UHS_SDR50 (1 << 18) /* Host supports UHS SDR50 mode */ +#define MMC_CAP_UHS_SDR104 (1 << 19) /* Host supports UHS SDR104 mode */ +#define MMC_CAP_UHS_DDR50 (1 << 20) /* Host supports UHS DDR50 mode */ +#define MMC_CAP_NO_BOUNCE_BUFF (1 << 21) /* Disable bounce buffers on host */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ +#define MMC_CAP_CD_WAKE (1 << 28) /* Enable card detect wake */ #define MMC_CAP_CMD_DURING_TFR (1 << 29) /* Commands during data transfer */ #define MMC_CAP_CMD23 (1 << 30) /* CMD23 supported. */ #define MMC_CAP_HW_RESET (1 << 31) /* Hardware reset */ @@ -290,7 +289,6 @@ struct mmc_host { #define MMC_CAP2_HS200_1_2V_SDR (1 << 6) /* can support */ #define MMC_CAP2_HS200 (MMC_CAP2_HS200_1_8V_SDR | \ MMC_CAP2_HS200_1_2V_SDR) -#define MMC_CAP2_HC_ERASE_SZ (1 << 9) /* High-capacity erase size */ #define MMC_CAP2_CD_ACTIVE_HIGH (1 << 10) /* Card-detect signal active high */ #define MMC_CAP2_RO_ACTIVE_HIGH (1 << 11) /* Write-protect signal active high */ #define MMC_CAP2_PACKED_RD (1 << 12) /* Allow packed read */ @@ -363,6 +361,7 @@ struct mmc_host { unsigned int sdio_irqs; struct task_struct *sdio_irq_thread; + struct delayed_work sdio_irq_work; bool sdio_irq_pending; atomic_t sdio_irq_thread_abort; @@ -397,11 +396,14 @@ struct mmc_host { unsigned long private[0] ____cacheline_aligned; }; +struct device_node; + struct mmc_host *mmc_alloc_host(int extra, struct device *); int mmc_add_host(struct mmc_host *); void mmc_remove_host(struct mmc_host *); void mmc_free_host(struct mmc_host *); int mmc_of_parse(struct mmc_host *host); +int mmc_of_parse_voltage(struct device_node *np, u32 *mask); static inline void *mmc_priv(struct mmc_host *host) { @@ -430,6 +432,7 @@ static inline void mmc_signal_sdio_irq(struct mmc_host *host) } void sdio_run_irqs(struct mmc_host *host); +void sdio_signal_irq(struct mmc_host *host); #ifdef CONFIG_REGULATOR int mmc_regulator_get_ocrmask(struct regulator *supply); @@ -457,6 +460,7 @@ static inline int mmc_regulator_set_vqmmc(struct mmc_host *mmc, } #endif +u32 mmc_vddrange_to_ocrmask(int vdd_min, int vdd_max); int mmc_regulator_get_supply(struct mmc_host *mmc); static inline int mmc_card_is_removable(struct mmc_host *host) @@ -474,56 +478,20 @@ static inline int mmc_card_wake_sdio_irq(struct mmc_host *host) return host->pm_flags & MMC_PM_WAKE_SDIO_IRQ; } -static inline int mmc_host_cmd23(struct mmc_host *host) -{ - return host->caps & MMC_CAP_CMD23; -} - -static inline int mmc_boot_partition_access(struct mmc_host *host) -{ - return !(host->caps2 & MMC_CAP2_BOOTPART_NOACC); -} - -static inline int mmc_host_uhs(struct mmc_host *host) -{ - return host->caps & - (MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 | - MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | - MMC_CAP_UHS_DDR50); -} - +/* TODO: Move to private header */ static inline int mmc_card_hs(struct mmc_card *card) { return card->host->ios.timing == MMC_TIMING_SD_HS || card->host->ios.timing == MMC_TIMING_MMC_HS; } +/* TODO: Move to private header */ static inline int mmc_card_uhs(struct mmc_card *card) { return card->host->ios.timing >= MMC_TIMING_UHS_SDR12 && card->host->ios.timing <= MMC_TIMING_UHS_DDR50; } -static inline bool mmc_card_hs200(struct mmc_card *card) -{ - return card->host->ios.timing == MMC_TIMING_MMC_HS200; -} - -static inline bool mmc_card_ddr52(struct mmc_card *card) -{ - return card->host->ios.timing == MMC_TIMING_MMC_DDR52; -} - -static inline bool mmc_card_hs400(struct mmc_card *card) -{ - return card->host->ios.timing == MMC_TIMING_MMC_HS400; -} - -static inline bool mmc_card_hs400es(struct mmc_card *card) -{ - return card->host->ios.enhanced_strobe; -} - void mmc_retune_timer_stop(struct mmc_host *host); static inline void mmc_retune_needed(struct mmc_host *host) @@ -532,18 +500,17 @@ static inline void mmc_retune_needed(struct mmc_host *host) host->need_retune = 1; } -static inline void mmc_retune_recheck(struct mmc_host *host) +static inline bool mmc_can_retune(struct mmc_host *host) { - if (host->hold_retune <= 1) - host->retune_now = 1; + return host->can_retune == 1; } -static inline bool mmc_can_retune(struct mmc_host *host) +static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data) { - return host->can_retune == 1; + return data->flags & MMC_DATA_WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE; } -void mmc_retune_pause(struct mmc_host *host); -void mmc_retune_unpause(struct mmc_host *host); +int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); +int mmc_abort_tuning(struct mmc_host *host, u32 opcode); #endif /* LINUX_MMC_HOST_H */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 672730acc705..3ffc27aaeeaf 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -24,6 +24,8 @@ #ifndef LINUX_MMC_MMC_H #define LINUX_MMC_MMC_H +#include <linux/types.h> + /* Standard MMC commands (4.1) type argument response */ /* class 1 */ #define MMC_GO_IDLE_STATE 0 /* bc */ @@ -182,50 +184,6 @@ static inline bool mmc_op_multi(u32 opcode) #define R2_SPI_OUT_OF_RANGE (1 << 15) /* or CSD overwrite */ #define R2_SPI_CSD_OVERWRITE R2_SPI_OUT_OF_RANGE -/* These are unpacked versions of the actual responses */ - -struct _mmc_csd { - u8 csd_structure; - u8 spec_vers; - u8 taac; - u8 nsac; - u8 tran_speed; - u16 ccc; - u8 read_bl_len; - u8 read_bl_partial; - u8 write_blk_misalign; - u8 read_blk_misalign; - u8 dsr_imp; - u16 c_size; - u8 vdd_r_curr_min; - u8 vdd_r_curr_max; - u8 vdd_w_curr_min; - u8 vdd_w_curr_max; - u8 c_size_mult; - union { - struct { /* MMC system specification version 3.1 */ - u8 erase_grp_size; - u8 erase_grp_mult; - } v31; - struct { /* MMC system specification version 2.2 */ - u8 sector_size; - u8 erase_grp_size; - } v22; - } erase; - u8 wp_grp_size; - u8 wp_grp_enable; - u8 default_ecc; - u8 r2w_factor; - u8 write_bl_len; - u8 write_bl_partial; - u8 file_format_grp; - u8 copy; - u8 perm_write_protect; - u8 tmp_write_protect; - u8 file_format; - u8 ecc; -}; - /* * OCR bits are mostly in host.h */ @@ -339,6 +297,9 @@ struct _mmc_csd { #define EXT_CSD_CACHE_SIZE 249 /* RO, 4 bytes */ #define EXT_CSD_PWR_CL_DDR_200_360 253 /* RO */ #define EXT_CSD_FIRMWARE_VERSION 254 /* RO, 8 bytes */ +#define EXT_CSD_PRE_EOL_INFO 267 /* RO */ +#define EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_A 268 /* RO */ +#define EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_B 269 /* RO */ #define EXT_CSD_CMDQ_DEPTH 307 /* RO */ #define EXT_CSD_CMDQ_SUPPORT 308 /* RO */ #define EXT_CSD_SUPPORTED_MODE 493 /* RO */ @@ -446,6 +407,7 @@ struct _mmc_csd { * BKOPS modes */ #define EXT_CSD_MANUAL_BKOPS_MASK 0x01 +#define EXT_CSD_AUTO_BKOPS_MASK 0x02 /* * Command Queue @@ -457,12 +419,23 @@ struct _mmc_csd { /* * MMC_SWITCH access modes */ - #define MMC_SWITCH_MODE_CMD_SET 0x00 /* Change the command set */ #define MMC_SWITCH_MODE_SET_BITS 0x01 /* Set bits which are 1 in value */ #define MMC_SWITCH_MODE_CLEAR_BITS 0x02 /* Clear bits which are 1 in value */ #define MMC_SWITCH_MODE_WRITE_BYTE 0x03 /* Set target to value */ +/* + * Erase/trim/discard + */ +#define MMC_ERASE_ARG 0x00000000 +#define MMC_SECURE_ERASE_ARG 0x80000000 +#define MMC_TRIM_ARG 0x00000001 +#define MMC_DISCARD_ARG 0x00000003 +#define MMC_SECURE_TRIM1_ARG 0x80000001 +#define MMC_SECURE_TRIM2_ARG 0x80008000 +#define MMC_SECURE_ARGS 0x80000000 +#define MMC_TRIM_ARGS 0x00008001 + #define mmc_driver_type_mask(n) (1 << (n)) #endif /* LINUX_MMC_MMC_H */ diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index aab032a6ae61..97ca105347a6 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -53,7 +53,7 @@ struct sdio_func { unsigned int state; /* function state */ #define SDIO_STATE_PRESENT (1<<0) /* present in sysfs */ - u8 tmpbuf[4]; /* DMA:able scratch buffer */ + u8 *tmpbuf; /* DMA:able scratch buffer */ unsigned num_info; /* number of info strings */ const char **info; /* info strings */ diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index d43ef96bf075..b733eb404ffc 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -36,6 +36,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 #define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 #define SDIO_DEVICE_ID_BROADCOM_4345 0x4345 +#define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 #define SDIO_DEVICE_ID_BROADCOM_4356 0x4356 @@ -51,6 +52,7 @@ #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 #define SDIO_DEVICE_ID_MARVELL_8688WLAN 0x9104 #define SDIO_DEVICE_ID_MARVELL_8688BT 0x9105 +#define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 @@ -60,4 +62,10 @@ #define SDIO_DEVICE_ID_SIANO_NOVA_A0 0x1100 #define SDIO_DEVICE_ID_SIANO_STELLAR 0x5347 +#define SDIO_VENDOR_ID_TI 0x0097 +#define SDIO_DEVICE_ID_TI_WL1271 0x4076 + +#define SDIO_VENDOR_ID_STE 0x0020 +#define SDIO_DEVICE_ID_STE_CW1200 0x2280 + #endif /* LINUX_MMC_SDIO_IDS_H */ diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index ccd8fb2cad52..a7baa29484c3 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -32,13 +32,8 @@ */ struct sh_mmcif_plat_data { - int (*get_cd)(struct platform_device *pdef); unsigned int slave_id_tx; /* embedded slave_id_[tr]x */ unsigned int slave_id_rx; - bool use_cd_gpio : 1; - bool ccs_unsupported : 1; - bool clk_ctrl2_present : 1; - unsigned int cd_gpio; u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ unsigned long caps; u32 ocr; diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index a7972cd3bc14..82f0d289f110 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -11,6 +11,9 @@ #ifndef MMC_SLOT_GPIO_H #define MMC_SLOT_GPIO_H +#include <linux/types.h> +#include <linux/irqreturn.h> + struct mmc_host; int mmc_gpio_get_ro(struct mmc_host *host); diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index a1a210d59961..c91b3bcd158f 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -381,16 +381,17 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) ___pmd; \ }) -#define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd) \ +#define pudp_huge_clear_flush_notify(__vma, __haddr, __pud) \ ({ \ - unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ - pmd_t ___pmd; \ + unsigned long ___haddr = __haddr & HPAGE_PUD_MASK; \ + struct mm_struct *___mm = (__vma)->vm_mm; \ + pud_t ___pud; \ \ - ___pmd = pmdp_huge_get_and_clear(__mm, __haddr, __pmd); \ - mmu_notifier_invalidate_range(__mm, ___haddr, \ - ___haddr + HPAGE_PMD_SIZE); \ + ___pud = pudp_huge_clear_flush(__vma, __haddr, __pud); \ + mmu_notifier_invalidate_range(___mm, ___haddr, \ + ___haddr + HPAGE_PUD_SIZE); \ \ - ___pmd; \ + ___pud; \ }) /* @@ -475,7 +476,7 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) #define pmdp_clear_young_notify pmdp_test_and_clear_young #define ptep_clear_flush_notify ptep_clear_flush #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush -#define pmdp_huge_get_and_clear_notify pmdp_huge_get_and_clear +#define pudp_huge_clear_flush_notify pudp_huge_clear_flush #define set_pte_at_notify set_pte_at #endif /* CONFIG_MMU_NOTIFIER */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f4aac87adcc3..fc14b8b3f6ce 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -35,7 +35,7 @@ */ #define PAGE_ALLOC_COSTLY_ORDER 3 -enum { +enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, @@ -74,6 +74,11 @@ extern char * const migratetype_names[MIGRATE_TYPES]; # define is_migrate_cma_page(_page) false #endif +static inline bool is_migrate_movable(int mt) +{ + return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; +} + #define for_each_migratetype_order(order, type) \ for (order = 0; order < MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) @@ -120,8 +125,6 @@ enum zone_stat_item { NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ - NR_SLAB_RECLAIMABLE, - NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ NR_KERNEL_STACK_KB, /* measured in KiB */ /* Second 128 byte cacheline */ @@ -147,9 +150,10 @@ enum node_stat_item { NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ + NR_SLAB_RECLAIMABLE, + NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ - NR_PAGES_SCANNED, /* pages scanned since last reclaim */ WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, WORKINGSET_NODERECLAIM, @@ -226,6 +230,8 @@ struct lruvec { struct zone_reclaim_stat reclaim_stat; /* Evictions & activations on the inactive file list */ atomic_long_t inactive_age; + /* Refaults at the time of last reclaim cycle */ + unsigned long refaults; #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif @@ -236,8 +242,6 @@ struct lruvec { #define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON)) #define LRU_ALL ((1 << NR_LRU_LISTS) - 1) -/* Isolate clean file */ -#define ISOLATE_CLEAN ((__force isolate_mode_t)0x1) /* Isolate unmapped file */ #define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2) /* Isolate for asynchronous migration */ @@ -529,6 +533,22 @@ static inline bool zone_is_empty(struct zone *zone) } /* + * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty + * intersection with the given zone + */ +static inline bool zone_intersects(struct zone *zone, + unsigned long start_pfn, unsigned long nr_pages) +{ + if (zone_is_empty(zone)) + return false; + if (start_pfn >= zone_end_pfn(zone) || + start_pfn + nr_pages <= zone->zone_start_pfn) + return false; + + return true; +} + +/* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. @@ -583,12 +603,9 @@ extern struct page *mem_map; #endif /* - * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM - * (mostly NUMA machines?) to denote a higher-level memory zone than the - * zone denotes. - * * On NUMA machines, each NUMA node would have a pg_data_t to describe - * it's memory layout. + * it's memory layout. On UMA machines there is a single pglist_data which + * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. @@ -632,6 +649,8 @@ typedef struct pglist_data { int kswapd_order; enum zone_type kswapd_classzone_idx; + int kswapd_failures; /* Number of 'reclaimed == 0' runs */ + #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_classzone_idx; @@ -672,6 +691,7 @@ typedef struct pglist_data { * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; + unsigned long static_init_size; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -765,7 +785,7 @@ enum memmap_context { MEMMAP_EARLY, MEMMAP_HOTPLUG, }; -extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, +extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); @@ -779,7 +799,7 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) #endif } -extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru); +extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx); #ifdef CONFIG_HAVE_MEMORY_PRESENT void memory_present(int nid, unsigned long start, unsigned long end); @@ -1035,6 +1055,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) static inline unsigned long early_pfn_to_nid(unsigned long pfn) { + BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); return 0; } #endif @@ -1137,9 +1158,10 @@ extern unsigned long usemap_size(void); */ #define SECTION_MARKED_PRESENT (1UL<<0) #define SECTION_HAS_MEM_MAP (1UL<<1) -#define SECTION_MAP_LAST_BIT (1UL<<2) +#define SECTION_IS_ONLINE (1UL<<2) +#define SECTION_MAP_LAST_BIT (1UL<<3) #define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) -#define SECTION_NID_SHIFT 2 +#define SECTION_NID_SHIFT 3 static inline struct page *__section_mem_map_addr(struct mem_section *section) { @@ -1168,11 +1190,30 @@ static inline int valid_section_nr(unsigned long nr) return valid_section(__nr_to_section(nr)); } +static inline int online_section(struct mem_section *section) +{ + return (section && (section->section_mem_map & SECTION_IS_ONLINE)); +} + +static inline int online_section_nr(unsigned long nr) +{ + return online_section(__nr_to_section(nr)); +} + +#ifdef CONFIG_MEMORY_HOTPLUG +void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); +#ifdef CONFIG_MEMORY_HOTREMOVE +void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); +#endif +#endif + static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } +extern int __highest_present_section_nr; + #ifndef CONFIG_HAVE_ARCH_PFN_VALID static inline int pfn_valid(unsigned long pfn) { @@ -1244,10 +1285,15 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); #ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL /* * pfn_valid() is meant to be able to tell if a given PFN has valid memmap - * associated with it or not. In FLATMEM, it is expected that holes always - * have valid memmap as long as there is valid PFNs either side of the hole. - * In SPARSEMEM, it is assumed that a valid section has a memmap for the - * entire section. + * associated with it or not. This means that a struct page exists for this + * pfn. The caller cannot assume the page is fully initialized in general. + * Hotplugable pages might not have been onlined yet. pfn_to_online_page() + * will ensure the struct page is fully online and initialized. Special pages + * (e.g. ZONE_DEVICE) are never onlined and should be treated accordingly. + * + * In FLATMEM, it is expected that holes always have valid memmap as long as + * there is valid PFNs either side of the hole. In SPARSEMEM, it is assumed + * that a valid section has a memmap for the entire section. * * However, an ARM, and maybe other embedded architectures in the future * free memmap backing holes to save memory on the assumption the memmap is diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 8a57f0b1242d..3f74ef2281e8 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -428,6 +428,16 @@ struct i2c_device_id { kernel_ulong_t driver_data; /* Data private to the driver */ }; +/* pci_epf */ + +#define PCI_EPF_NAME_SIZE 20 +#define PCI_EPF_MODULE_PREFIX "pci_epf:" + +struct pci_epf_device_id { + char name[PCI_EPF_NAME_SIZE]; + kernel_ulong_t driver_data; +}; + /* spi */ #define SPI_NAME_SIZE 32 @@ -457,6 +467,7 @@ enum dmi_field { DMI_PRODUCT_VERSION, DMI_PRODUCT_SERIAL, DMI_PRODUCT_UUID, + DMI_PRODUCT_FAMILY, DMI_BOARD_VENDOR, DMI_BOARD_NAME, DMI_BOARD_VERSION, @@ -501,6 +512,7 @@ struct platform_device_id { kernel_ulong_t driver_data; }; +#define MDIO_NAME_SIZE 32 #define MDIO_MODULE_PREFIX "mdio:" #define MDIO_ID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d" diff --git a/include/linux/module.h b/include/linux/module.h index cc7cba219b20..e7bdd549e527 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -18,7 +18,6 @@ #include <linux/moduleparam.h> #include <linux/jump_label.h> #include <linux/export.h> -#include <linux/extable.h> /* only as arch move module.h -> extable.h */ #include <linux/rbtree_latch.h> #include <linux/percpu.h> @@ -46,7 +45,7 @@ struct module_kobject { struct kobject *drivers_dir; struct module_param_attrs *mp; struct completion *kobj_completion; -}; +} __randomize_layout; struct module_attribute { struct attribute attr; @@ -127,13 +126,13 @@ extern void cleanup_module(void); /* Each module must use one module_init(). */ #define module_init(initfn) \ - static inline initcall_t __inittest(void) \ + static inline initcall_t __maybe_unused __inittest(void) \ { return initfn; } \ int init_module(void) __attribute__((alias(#initfn))); /* This is only required if you want to be unloadable. */ #define module_exit(exitfn) \ - static inline exitcall_t __exittest(void) \ + static inline exitcall_t __maybe_unused __exittest(void) \ { return exitfn; } \ void cleanup_module(void) __attribute__((alias(#exitfn))); @@ -282,8 +281,6 @@ enum module_state { MODULE_STATE_UNFORMED, /* Still setting it up. */ }; -struct module; - struct mod_tree_node { struct module *mod; struct latch_tree_node node; @@ -445,8 +442,8 @@ struct module { #ifdef CONFIG_EVENT_TRACING struct trace_event_call **trace_events; unsigned int num_trace_events; - struct trace_enum_map **trace_enums; - unsigned int num_trace_enums; + struct trace_eval_map **trace_evals; + unsigned int num_trace_evals; #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD unsigned int num_ftrace_callsites; @@ -478,7 +475,7 @@ struct module { ctor_fn_t *ctors; unsigned int num_ctors; #endif -} ____cacheline_aligned; +} ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif @@ -496,6 +493,7 @@ static inline int module_is_live(struct module *mod) struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); +bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr); bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); @@ -585,7 +583,7 @@ extern bool try_module_get(struct module *module); extern void module_put(struct module *module); #else /*!CONFIG_MODULE_UNLOAD*/ -static inline int try_module_get(struct module *module) +static inline bool try_module_get(struct module *module) { return !module || module_is_live(module); } @@ -663,6 +661,11 @@ static inline bool is_module_percpu_address(unsigned long addr) return false; } +static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) +{ + return false; +} + static inline bool is_module_text_address(unsigned long addr) { return false; @@ -677,9 +680,9 @@ static inline void __module_get(struct module *module) { } -static inline int try_module_get(struct module *module) +static inline bool try_module_get(struct module *module) { - return 1; + return true; } static inline void module_put(struct module *module) @@ -764,7 +767,7 @@ extern int module_sysfs_initialized; #define __MODULE_STRING(x) __stringify(x) -#ifdef CONFIG_DEBUG_SET_MODULE_RONX +#ifdef CONFIG_STRICT_MODULE_RWX extern void set_all_modules_text_rw(void); extern void set_all_modules_text_ro(void); extern void module_enable_ro(const struct module *mod, bool after_init); diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 52666d90ca94..1ee7b30dafec 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -60,9 +60,11 @@ struct kernel_param_ops { * Flags available for kernel_param * * UNSAFE - the parameter is dangerous and setting it will taint the kernel + * HWPARAM - Hardware param not permitted in lockdown mode */ enum { - KERNEL_PARAM_FL_UNSAFE = (1 << 0) + KERNEL_PARAM_FL_UNSAFE = (1 << 0), + KERNEL_PARAM_FL_HWPARAM = (1 << 1), }; struct kernel_param { @@ -451,6 +453,67 @@ extern int param_set_bint(const char *val, const struct kernel_param *kp); perm, -1, 0); \ __MODULE_PARM_TYPE(name, "array of " #type) +enum hwparam_type { + hwparam_ioport, /* Module parameter configures an I/O port */ + hwparam_iomem, /* Module parameter configures an I/O mem address */ + hwparam_ioport_or_iomem, /* Module parameter could be either, depending on other option */ + hwparam_irq, /* Module parameter configures an IRQ */ + hwparam_dma, /* Module parameter configures a DMA channel */ + hwparam_dma_addr, /* Module parameter configures a DMA buffer address */ + hwparam_other, /* Module parameter configures some other value */ +}; + +/** + * module_param_hw_named - A parameter representing a hw parameters + * @name: a valid C identifier which is the parameter name. + * @value: the actual lvalue to alter. + * @type: the type of the parameter + * @hwtype: what the value represents (enum hwparam_type) + * @perm: visibility in sysfs. + * + * Usually it's a good idea to have variable names and user-exposed names the + * same, but that's harder if the variable must be non-static or is inside a + * structure. This allows exposure under a different name. + */ +#define module_param_hw_named(name, value, type, hwtype, perm) \ + param_check_##type(name, &(value)); \ + __module_param_call(MODULE_PARAM_PREFIX, name, \ + ¶m_ops_##type, &value, \ + perm, -1, \ + KERNEL_PARAM_FL_HWPARAM | (hwparam_##hwtype & 0)); \ + __MODULE_PARM_TYPE(name, #type) + +#define module_param_hw(name, type, hwtype, perm) \ + module_param_hw_named(name, name, type, hwtype, perm) + +/** + * module_param_hw_array - A parameter representing an array of hw parameters + * @name: the name of the array variable + * @type: the type, as per module_param() + * @hwtype: what the value represents (enum hwparam_type) + * @nump: optional pointer filled in with the number written + * @perm: visibility in sysfs + * + * Input and output are as comma-separated values. Commas inside values + * don't work properly (eg. an array of charp). + * + * ARRAY_SIZE(@name) is used to determine the number of elements in the + * array, so the definition must be visible. + */ +#define module_param_hw_array(name, type, hwtype, nump, perm) \ + param_check_##type(name, &(name)[0]); \ + static const struct kparam_array __param_arr_##name \ + = { .max = ARRAY_SIZE(name), .num = nump, \ + .ops = ¶m_ops_##type, \ + .elemsize = sizeof(name[0]), .elem = name }; \ + __module_param_call(MODULE_PARAM_PREFIX, name, \ + ¶m_array_ops, \ + .arr = &__param_arr_##name, \ + perm, -1, \ + KERNEL_PARAM_FL_HWPARAM | (hwparam_##hwtype & 0)); \ + __MODULE_PARM_TYPE(name, "array of " #type) + + extern const struct kernel_param_ops param_array_ops; extern const struct kernel_param_ops param_ops_string; diff --git a/include/linux/mount.h b/include/linux/mount.h index c6f55158d5e5..1ce85e6fd95f 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -67,7 +67,7 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; -}; +} __randomize_layout; struct file; /* forward dec */ struct path; @@ -90,6 +90,9 @@ struct file_system_type; extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data); +extern struct vfsmount *vfs_submount(const struct dentry *mountpoint, + struct file_system_type *type, + const char *name, void *data); extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); diff --git a/include/linux/mpls.h b/include/linux/mpls.h index 9999145bc190..384fb22b6c43 100644 --- a/include/linux/mpls.h +++ b/include/linux/mpls.h @@ -3,4 +3,9 @@ #include <uapi/linux/mpls.h> +#define MPLS_TTL_MASK (MPLS_LS_TTL_MASK >> MPLS_LS_TTL_SHIFT) +#define MPLS_BOS_MASK (MPLS_LS_S_MASK >> MPLS_LS_S_SHIFT) +#define MPLS_TC_MASK (MPLS_LS_TC_MASK >> MPLS_LS_TC_SHIFT) +#define MPLS_LABEL_MASK (MPLS_LS_LABEL_MASK >> MPLS_LS_LABEL_SHIFT) + #endif /* _LINUX_MPLS_H */ diff --git a/include/linux/mroute.h b/include/linux/mroute.h index e5fb81376e92..d7f63339ef0b 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -3,6 +3,7 @@ #include <linux/in.h> #include <linux/pim.h> +#include <linux/rhashtable.h> #include <net/sock.h> #include <uapi/linux/mroute.h> @@ -60,7 +61,6 @@ struct vif_device { #define VIFF_STATIC 0x8000 #define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL) -#define MFC_LINES 64 struct mr_table { struct list_head list; @@ -69,8 +69,9 @@ struct mr_table { struct sock __rcu *mroute_sk; struct timer_list ipmr_expire_timer; struct list_head mfc_unres_queue; - struct list_head mfc_cache_array[MFC_LINES]; struct vif_device vif_table[MAXVIFS]; + struct rhltable mfc_hash; + struct list_head mfc_cache_list; int maxvif; atomic_t cache_resolve_queue_len; bool mroute_do_assert; @@ -85,17 +86,48 @@ enum { MFC_STATIC = BIT(0), }; +struct mfc_cache_cmp_arg { + __be32 mfc_mcastgrp; + __be32 mfc_origin; +}; + +/** + * struct mfc_cache - multicast routing entries + * @mnode: rhashtable list + * @mfc_mcastgrp: destination multicast group address + * @mfc_origin: source address + * @cmparg: used for rhashtable comparisons + * @mfc_parent: source interface (iif) + * @mfc_flags: entry flags + * @expires: unresolved entry expire time + * @unresolved: unresolved cached skbs + * @last_assert: time of last assert + * @minvif: minimum VIF id + * @maxvif: maximum VIF id + * @bytes: bytes that have passed for this entry + * @pkt: packets that have passed for this entry + * @wrong_if: number of wrong source interface hits + * @lastuse: time of last use of the group (traffic or update) + * @ttls: OIF TTL threshold array + * @list: global entry list + * @rcu: used for entry destruction + */ struct mfc_cache { - struct list_head list; - __be32 mfc_mcastgrp; /* Group the entry belongs to */ - __be32 mfc_origin; /* Source of packet */ - vifi_t mfc_parent; /* Source interface */ - int mfc_flags; /* Flags on line */ + struct rhlist_head mnode; + union { + struct { + __be32 mfc_mcastgrp; + __be32 mfc_origin; + }; + struct mfc_cache_cmp_arg cmparg; + }; + vifi_t mfc_parent; + int mfc_flags; union { struct { unsigned long expires; - struct sk_buff_head unresolved; /* Unresolved buffers */ + struct sk_buff_head unresolved; } unres; struct { unsigned long last_assert; @@ -105,20 +137,15 @@ struct mfc_cache { unsigned long pkt; unsigned long wrong_if; unsigned long lastuse; - unsigned char ttls[MAXVIFS]; /* TTL thresholds */ + unsigned char ttls[MAXVIFS]; } res; } mfc_un; + struct list_head list; struct rcu_head rcu; }; -#ifdef __BIG_ENDIAN -#define MFC_HASH(a,b) (((((__force u32)(__be32)a)>>24)^(((__force u32)(__be32)b)>>26))&(MFC_LINES-1)) -#else -#define MFC_HASH(a,b) ((((__force u32)(__be32)a)^(((__force u32)(__be32)b)>>2))&(MFC_LINES-1)) -#endif - struct rtmsg; int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, - struct rtmsg *rtm, int nowait, u32 portid); + struct rtmsg *rtm, u32 portid); #endif diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 19a1c0c2993b..ce44e3e96d27 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -116,7 +116,7 @@ struct mfc6_cache { struct rtmsg; extern int ip6mr_get_route(struct net *net, struct sk_buff *skb, - struct rtmsg *rtm, int nowait, u32 portid); + struct rtmsg *rtm, u32 portid); #ifdef CONFIG_IPV6_MROUTE extern struct sock *mroute6_socket(struct net *net, struct sk_buff *skb); diff --git a/include/linux/msg.h b/include/linux/msg.h index f3f302f9c197..a001305f5a79 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -29,7 +29,7 @@ struct msg_queue { struct list_head q_messages; struct list_head q_receivers; struct list_head q_senders; -}; +} __randomize_layout; /* Helper routines for sys_msgsnd and sys_msgrcv */ extern long do_msgsnd(int msqid, long mtype, void __user *mtext, diff --git a/include/linux/msi.h b/include/linux/msi.h index 0db320b7bb15..df6d59201d31 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -17,7 +17,13 @@ struct msi_desc; struct pci_dev; struct platform_msi_priv_data; void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); +#ifdef CONFIG_GENERIC_MSI_IRQ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); +#else +static inline void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) +{ +} +#endif typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc, struct msi_msg *msg); @@ -116,11 +122,15 @@ struct msi_desc { struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); void *msi_desc_to_pci_sysdata(struct msi_desc *desc); +void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); #else /* CONFIG_PCI_MSI */ static inline void *msi_desc_to_pci_sysdata(struct msi_desc *desc) { return NULL; } +static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) +{ +} #endif /* CONFIG_PCI_MSI */ struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, @@ -128,7 +138,6 @@ struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, void free_msi_entry(struct msi_desc *entry); void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); -void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag); u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); @@ -316,12 +325,6 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg); struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); -int pci_msi_domain_alloc_irqs(struct irq_domain *domain, struct pci_dev *dev, - int nvec, int type); -void pci_msi_domain_free_irqs(struct irq_domain *domain, struct pci_dev *dev); -struct irq_domain *pci_msi_create_default_irq_domain(struct fwnode_handle *fwnode, - struct msi_domain_info *info, struct irq_domain *parent); - irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev, struct msi_desc *desc); int pci_msi_domain_check_cap(struct irq_domain *domain, diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h deleted file mode 100644 index ad3c3488073c..000000000000 --- a/include/linux/mtd/fsmc.h +++ /dev/null @@ -1,156 +0,0 @@ -/* - * incude/mtd/fsmc.h - * - * ST Microelectronics - * Flexible Static Memory Controller (FSMC) - * platform data interface and header file - * - * Copyright © 2010 ST Microelectronics - * Vipin Kumar <vipin.kumar@st.com> - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - */ - -#ifndef __MTD_FSMC_H -#define __MTD_FSMC_H - -#include <linux/io.h> -#include <linux/platform_device.h> -#include <linux/mtd/physmap.h> -#include <linux/types.h> -#include <linux/mtd/partitions.h> -#include <asm/param.h> - -#define FSMC_NAND_BW8 1 -#define FSMC_NAND_BW16 2 - -#define FSMC_MAX_NOR_BANKS 4 -#define FSMC_MAX_NAND_BANKS 4 - -#define FSMC_FLASH_WIDTH8 1 -#define FSMC_FLASH_WIDTH16 2 - -/* fsmc controller registers for NOR flash */ -#define CTRL 0x0 - /* ctrl register definitions */ - #define BANK_ENABLE (1 << 0) - #define MUXED (1 << 1) - #define NOR_DEV (2 << 2) - #define WIDTH_8 (0 << 4) - #define WIDTH_16 (1 << 4) - #define RSTPWRDWN (1 << 6) - #define WPROT (1 << 7) - #define WRT_ENABLE (1 << 12) - #define WAIT_ENB (1 << 13) - -#define CTRL_TIM 0x4 - /* ctrl_tim register definitions */ - -#define FSMC_NOR_BANK_SZ 0x8 -#define FSMC_NOR_REG_SIZE 0x40 - -#define FSMC_NOR_REG(base, bank, reg) (base + \ - FSMC_NOR_BANK_SZ * (bank) + \ - reg) - -/* fsmc controller registers for NAND flash */ -#define PC 0x00 - /* pc register definitions */ - #define FSMC_RESET (1 << 0) - #define FSMC_WAITON (1 << 1) - #define FSMC_ENABLE (1 << 2) - #define FSMC_DEVTYPE_NAND (1 << 3) - #define FSMC_DEVWID_8 (0 << 4) - #define FSMC_DEVWID_16 (1 << 4) - #define FSMC_ECCEN (1 << 6) - #define FSMC_ECCPLEN_512 (0 << 7) - #define FSMC_ECCPLEN_256 (1 << 7) - #define FSMC_TCLR_1 (1) - #define FSMC_TCLR_SHIFT (9) - #define FSMC_TCLR_MASK (0xF) - #define FSMC_TAR_1 (1) - #define FSMC_TAR_SHIFT (13) - #define FSMC_TAR_MASK (0xF) -#define STS 0x04 - /* sts register definitions */ - #define FSMC_CODE_RDY (1 << 15) -#define COMM 0x08 - /* comm register definitions */ - #define FSMC_TSET_0 0 - #define FSMC_TSET_SHIFT 0 - #define FSMC_TSET_MASK 0xFF - #define FSMC_TWAIT_6 6 - #define FSMC_TWAIT_SHIFT 8 - #define FSMC_TWAIT_MASK 0xFF - #define FSMC_THOLD_4 4 - #define FSMC_THOLD_SHIFT 16 - #define FSMC_THOLD_MASK 0xFF - #define FSMC_THIZ_1 1 - #define FSMC_THIZ_SHIFT 24 - #define FSMC_THIZ_MASK 0xFF -#define ATTRIB 0x0C -#define IOATA 0x10 -#define ECC1 0x14 -#define ECC2 0x18 -#define ECC3 0x1C -#define FSMC_NAND_BANK_SZ 0x20 - -#define FSMC_NAND_REG(base, bank, reg) (base + FSMC_NOR_REG_SIZE + \ - (FSMC_NAND_BANK_SZ * (bank)) + \ - reg) - -#define FSMC_BUSY_WAIT_TIMEOUT (1 * HZ) - -struct fsmc_nand_timings { - uint8_t tclr; - uint8_t tar; - uint8_t thiz; - uint8_t thold; - uint8_t twait; - uint8_t tset; -}; - -enum access_mode { - USE_DMA_ACCESS = 1, - USE_WORD_ACCESS, -}; - -/** - * fsmc_nand_platform_data - platform specific NAND controller config - * @nand_timings: timing setup for the physical NAND interface - * @partitions: partition table for the platform, use a default fallback - * if this is NULL - * @nr_partitions: the number of partitions in the previous entry - * @options: different options for the driver - * @width: bus width - * @bank: default bank - * @select_bank: callback to select a certain bank, this is - * platform-specific. If the controller only supports one bank - * this may be set to NULL - */ -struct fsmc_nand_platform_data { - struct fsmc_nand_timings *nand_timings; - struct mtd_partition *partitions; - unsigned int nr_partitions; - unsigned int options; - unsigned int width; - unsigned int bank; - - enum access_mode mode; - - void (*select_bank)(uint32_t bank, uint32_t busw); - - /* priv structures for dma accesses */ - void *read_dma_priv; - void *write_dma_priv; -}; - -extern int __init fsmc_nor_init(struct platform_device *pdev, - unsigned long base, uint32_t bank, uint32_t width); -extern void __init fsmc_init_board_info(struct platform_device *pdev, - struct mtd_partition *partitions, unsigned int nr_partitions, - unsigned int width); - -#endif /* __MTD_FSMC_H */ diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 13f8052b9ff9..f8a2ef239c60 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -24,6 +24,7 @@ #include <linux/uio.h> #include <linux/notifier.h> #include <linux/device.h> +#include <linux/of.h> #include <mtd/mtd-abi.h> @@ -322,6 +323,7 @@ struct mtd_info { int (*_block_isreserved) (struct mtd_info *mtd, loff_t ofs); int (*_block_isbad) (struct mtd_info *mtd, loff_t ofs); int (*_block_markbad) (struct mtd_info *mtd, loff_t ofs); + int (*_max_bad_blocks) (struct mtd_info *mtd, loff_t ofs, size_t len); int (*_suspend) (struct mtd_info *mtd); void (*_resume) (struct mtd_info *mtd); void (*_reboot) (struct mtd_info *mtd); @@ -332,11 +334,6 @@ struct mtd_info { int (*_get_device) (struct mtd_info *mtd); void (*_put_device) (struct mtd_info *mtd); - /* Backing device capabilities for this device - * - provides mmap capabilities - */ - struct backing_dev_info *backing_dev_info; - struct notifier_block reboot_notifier; /* default mode before reboot */ /* ECC status information */ @@ -385,11 +382,13 @@ static inline void mtd_set_of_node(struct mtd_info *mtd, struct device_node *np) { mtd->dev.of_node = np; + if (!mtd->name) + of_property_read_string(np, "label", &mtd->name); } static inline struct device_node *mtd_get_of_node(struct mtd_info *mtd) { - return mtd->dev.of_node; + return dev_of_node(&mtd->dev); } static inline int mtd_oobavail(struct mtd_info *mtd, struct mtd_oob_ops *ops) @@ -397,6 +396,18 @@ static inline int mtd_oobavail(struct mtd_info *mtd, struct mtd_oob_ops *ops) return ops->mode == MTD_OPS_AUTO_OOB ? mtd->oobavail : mtd->oobsize; } +static inline int mtd_max_bad_blocks(struct mtd_info *mtd, + loff_t ofs, size_t len) +{ + if (!mtd->_max_bad_blocks) + return -ENOTSUPP; + + if (mtd->size < (len + ofs) || ofs < 0) + return -EINVAL; + + return mtd->_max_bad_blocks(mtd, ofs, len); +} + int mtd_wunit_to_pairing_info(struct mtd_info *mtd, int wunit, struct mtd_pairing_info *info); int mtd_pairing_info_to_wunit(struct mtd_info *mtd, diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index c5f3a012ae62..892148c448cc 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -107,6 +107,8 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_STATUS_READY 0x40 #define NAND_STATUS_WP 0x80 +#define NAND_DATA_IFACE_CHECK_ONLY -1 + /* * Constants for ECC_MODES */ @@ -116,6 +118,7 @@ typedef enum { NAND_ECC_HW, NAND_ECC_HW_SYNDROME, NAND_ECC_HW_OOB_FIRST, + NAND_ECC_ON_DIE, } nand_ecc_modes_t; enum nand_ecc_algo { @@ -257,6 +260,8 @@ struct nand_chip; /* Vendor-specific feature address (Micron) */ #define ONFI_FEATURE_ADDR_READ_RETRY 0x89 +#define ONFI_FEATURE_ON_DIE_ECC 0x90 +#define ONFI_FEATURE_ON_DIE_ECC_EN BIT(3) /* ONFI subfeature parameters length */ #define ONFI_SUBFEATURE_PARAM_LEN 4 @@ -366,26 +371,6 @@ struct onfi_ext_param_page { */ } __packed; -struct nand_onfi_vendor_micron { - u8 two_plane_read; - u8 read_cache; - u8 read_unique_id; - u8 dq_imped; - u8 dq_imped_num_settings; - u8 dq_imped_feat_addr; - u8 rb_pulldown_strength; - u8 rb_pulldown_strength_feat_addr; - u8 rb_pulldown_strength_num_settings; - u8 otp_mode; - u8 otp_page_start; - u8 otp_data_prot_addr; - u8 otp_num_pages; - u8 otp_feat_addr; - u8 read_retry_options; - u8 reserved[72]; - u8 param_revision; -} __packed; - struct jedec_ecc_info { u8 ecc_bits; u8 codeword_size; @@ -465,6 +450,17 @@ struct nand_jedec_params { } __packed; /** + * struct nand_id - NAND id structure + * @data: buffer containing the id bytes. Currently 8 bytes large, but can + * be extended if required. + * @len: ID length. + */ +struct nand_id { + u8 data[8]; + int len; +}; + +/** * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices * @lock: protection lock * @active: the mtd device which holds the controller currently @@ -486,6 +482,44 @@ static inline void nand_hw_control_init(struct nand_hw_control *nfc) } /** + * struct nand_ecc_step_info - ECC step information of ECC engine + * @stepsize: data bytes per ECC step + * @strengths: array of supported strengths + * @nstrengths: number of supported strengths + */ +struct nand_ecc_step_info { + int stepsize; + const int *strengths; + int nstrengths; +}; + +/** + * struct nand_ecc_caps - capability of ECC engine + * @stepinfos: array of ECC step information + * @nstepinfos: number of ECC step information + * @calc_ecc_bytes: driver's hook to calculate ECC bytes per step + */ +struct nand_ecc_caps { + const struct nand_ecc_step_info *stepinfos; + int nstepinfos; + int (*calc_ecc_bytes)(int step_size, int strength); +}; + +/* a shorthand to generate struct nand_ecc_caps with only one ECC stepsize */ +#define NAND_ECC_CAPS_SINGLE(__name, __calc, __step, ...) \ +static const int __name##_strengths[] = { __VA_ARGS__ }; \ +static const struct nand_ecc_step_info __name##_stepinfo = { \ + .stepsize = __step, \ + .strengths = __name##_strengths, \ + .nstrengths = ARRAY_SIZE(__name##_strengths), \ +}; \ +static const struct nand_ecc_caps __name = { \ + .stepinfos = &__name##_stepinfo, \ + .nstepinfos = 1, \ + .calc_ecc_bytes = __calc, \ +} + +/** * struct nand_ecc_ctrl - Control structure for ECC * @mode: ECC mode * @algo: ECC algorithm @@ -525,7 +559,7 @@ static inline void nand_hw_control_init(struct nand_hw_control *nfc) * out-of-band data). * @read_page: function to read a page according to the ECC generator * requirements; returns maximum number of bitflips corrected in - * any single ECC step, 0 if bitflips uncorrectable, -EIO hw error + * any single ECC step, -EIO hw error * @read_subpage: function to read parts of the page covered by ECC; * returns same as read_page() * @write_subpage: function to write parts of the page covered by ECC. @@ -615,7 +649,7 @@ struct nand_buffers { * @tALS_min: ALE setup time * @tAR_min: ALE to RE# delay * @tCEA_max: CE# access time - * @tCEH_min: + * @tCEH_min: CE# high hold time * @tCH_min: CE# hold time * @tCHZ_max: CE# high to output hi-Z * @tCLH_min: CLE hold time @@ -721,6 +755,20 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) } /** + * struct nand_manufacturer_ops - NAND Manufacturer operations + * @detect: detect the NAND memory organization and capabilities + * @init: initialize all vendor specific fields (like the ->read_retry() + * implementation) if any. + * @cleanup: the ->init() function may have allocated resources, ->cleanup() + * is here to let vendor specific code release those resources. + */ +struct nand_manufacturer_ops { + void (*detect)(struct nand_chip *chip); + int (*init)(struct nand_chip *chip); + void (*cleanup)(struct nand_chip *chip); +}; + +/** * struct nand_chip - NAND Private Flash Chip Data * @mtd: MTD device registered to the MTD framework * @IO_ADDR_R: [BOARDSPECIFIC] address to read the 8 I/O lines of the @@ -750,6 +798,7 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure * @buffers: buffer structure for read/write + * @buf_align: minimum buffer alignment required by a platform * @hwcontrol: platform-specific hardware control structure * @erase: [REPLACEABLE] erase function * @scan_bbt: [REPLACEABLE] function to scan bad block table @@ -779,7 +828,7 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) * Minimum amount of bit errors per @ecc_step_ds guaranteed * to be correctable. If unknown, set to zero. * @ecc_step_ds: [INTERN] ECC step required by the @ecc_strength_ds, - * also from the datasheet. It is the recommended ECC step + * also from the datasheet. It is the recommended ECC step * size, if known; if unknown, set to zero. * @onfi_timing_mode_default: [INTERN] default ONFI timing mode. This field is * set to the actually used ONFI mode if the chip is @@ -793,6 +842,7 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) * @pagebuf_bitflips: [INTERN] holds the bitflip count for the page which is * currently in data_buf. * @subpagesize: [INTERN] holds the subpagesize + * @id: [INTERN] holds NAND ID * @onfi_version: [INTERN] holds the chip ONFI version (BCD encoded), * non 0 if ONFI supported. * @jedec_version: [INTERN] holds the chip JEDEC version (BCD encoded), @@ -801,10 +851,17 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) * supported, 0 otherwise. * @jedec_params: [INTERN] holds the JEDEC parameter page when JEDEC is * supported, 0 otherwise. + * @max_bb_per_die: [INTERN] the max number of bad blocks each die of a + * this nand device will encounter their life times. + * @blocks_per_die: [INTERN] The number of PEBs in a die + * @data_interface: [INTERN] NAND interface timing information * @read_retries: [INTERN] the number of read retry modes supported * @onfi_set_features: [REPLACEABLE] set the features for ONFI nand * @onfi_get_features: [REPLACEABLE] get the features for ONFI nand - * @setup_data_interface: [OPTIONAL] setup the data interface and timing + * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If + * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this + * means the configuration should not be applied but + * only checked. * @bbt: [INTERN] bad block table pointer * @bbt_td: [REPLACEABLE] bad block table descriptor for flash * lookup. @@ -815,10 +872,7 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) * structure which is shared among multiple independent * devices. * @priv: [OPTIONAL] pointer to private chip data - * @errstat: [OPTIONAL] hardware specific function to perform - * additional error status checks (determine if errors are - * correctable). - * @write_page: [REPLACEABLE] High-level page write function + * @manufacturer: [INTERN] Contains manufacturer information */ struct nand_chip { @@ -841,19 +895,13 @@ struct nand_chip { int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); int (*erase)(struct mtd_info *mtd, int page); int (*scan_bbt)(struct mtd_info *mtd); - int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state, - int status, int page); - int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, - uint32_t offset, int data_len, const uint8_t *buf, - int oob_required, int page, int cached, int raw); int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); - int (*setup_data_interface)(struct mtd_info *mtd, - const struct nand_data_interface *conf, - bool check_only); + int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, + const struct nand_data_interface *conf); int chip_delay; @@ -877,12 +925,15 @@ struct nand_chip { int badblockpos; int badblockbits; + struct nand_id id; int onfi_version; int jedec_version; union { struct nand_onfi_params onfi_params; struct nand_jedec_params jedec_params; }; + u16 max_bb_per_die; + u32 blocks_per_die; struct nand_data_interface *data_interface; @@ -895,6 +946,7 @@ struct nand_chip { struct nand_ecc_ctrl ecc; struct nand_buffers *buffers; + unsigned long buf_align; struct nand_hw_control hwcontrol; uint8_t *bbt; @@ -904,6 +956,11 @@ struct nand_chip { struct nand_bbt_descr *badblock_pattern; void *priv; + + struct { + const struct nand_manufacturer *desc; + void *priv; + } manufacturer; }; extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops; @@ -940,6 +997,17 @@ static inline void nand_set_controller_data(struct nand_chip *chip, void *priv) chip->priv = priv; } +static inline void nand_set_manufacturer_data(struct nand_chip *chip, + void *priv) +{ + chip->manufacturer.priv = priv; +} + +static inline void *nand_get_manufacturer_data(struct nand_chip *chip) +{ + return chip->manufacturer.priv; +} + /* * NAND Flash Manufacturer ID Codes */ @@ -958,6 +1026,7 @@ static inline void nand_set_controller_data(struct nand_chip *chip, void *priv) #define NAND_MFR_SANDISK 0x45 #define NAND_MFR_INTEL 0x89 #define NAND_MFR_ATO 0x9b +#define NAND_MFR_WINBOND 0xef /* The maximum expected count of bytes in the NAND ID sequence */ #define NAND_MAX_ID_LEN 8 @@ -1042,17 +1111,33 @@ struct nand_flash_dev { }; /** - * struct nand_manufacturers - NAND Flash Manufacturer ID Structure + * struct nand_manufacturer - NAND Flash Manufacturer structure * @name: Manufacturer name * @id: manufacturer ID code of device. + * @ops: manufacturer operations */ -struct nand_manufacturers { +struct nand_manufacturer { int id; char *name; + const struct nand_manufacturer_ops *ops; }; +const struct nand_manufacturer *nand_get_manufacturer(u8 id); + +static inline const char * +nand_manufacturer_name(const struct nand_manufacturer *manufacturer) +{ + return manufacturer ? manufacturer->name : "Unknown"; +} + extern struct nand_flash_dev nand_flash_ids[]; -extern struct nand_manufacturers nand_manuf_ids[]; + +extern const struct nand_manufacturer_ops toshiba_nand_manuf_ops; +extern const struct nand_manufacturer_ops samsung_nand_manuf_ops; +extern const struct nand_manufacturer_ops hynix_nand_manuf_ops; +extern const struct nand_manufacturer_ops micron_nand_manuf_ops; +extern const struct nand_manufacturer_ops amd_nand_manuf_ops; +extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; int nand_default_bbt(struct mtd_info *mtd); int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs); @@ -1199,6 +1284,15 @@ int nand_check_erased_ecc_chunk(void *data, int datalen, void *extraoob, int extraooblen, int threshold); +int nand_check_ecc_caps(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +int nand_match_ecc_req(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +int nand_maximize_ecc(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + /* Default write_oob implementation */ int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); @@ -1213,10 +1307,25 @@ int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, int page); +/* Stub used by drivers that do not support GET/SET FEATURES operations */ +int nand_onfi_get_set_features_notsupp(struct mtd_info *mtd, + struct nand_chip *chip, int addr, + u8 *subfeature_param); + +/* Default read_page_raw implementation */ +int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, int page); + +/* Default write_page_raw implementation */ +int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int oob_required, int page); + /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); /* Free resources held by the NAND device */ void nand_cleanup(struct nand_chip *chip); +/* Default extended ID decoding function */ +void nand_decode_ext_id(struct nand_chip *chip); #endif /* __LINUX_MTD_NAND_H */ diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 70736e1e6c8f..c4beb70dacbd 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -20,6 +20,12 @@ * * For each partition, these fields are available: * name: string that will be used to label the partition's MTD device. + * types: some partitions can be containers using specific format to describe + * embedded subpartitions / volumes. E.g. many home routers use "firmware" + * partition that contains at least kernel and rootfs. In such case an + * extra parser is needed that will detect these dynamic partitions and + * report them to the MTD subsystem. If set this property stores an array + * of parser names to use when looking for subpartitions. * size: the partition size; if defined as MTDPART_SIZ_FULL, the partition * will extend to the end of the master MTD device. * offset: absolute starting position within the master MTD device; if @@ -38,9 +44,11 @@ struct mtd_partition { const char *name; /* identifier string */ + const char *const *types; /* names of parsers to use if any */ uint64_t size; /* partition size */ uint64_t offset; /* offset within the master MTD space */ uint32_t mask_flags; /* master MTD flags to mask out for this partition */ + struct device_node *of_node; }; #define MTDPART_OFS_RETAIN (-3) diff --git a/include/linux/mtd/qinfo.h b/include/linux/mtd/qinfo.h index 7b3d487d8b3f..b532ce524dae 100644 --- a/include/linux/mtd/qinfo.h +++ b/include/linux/mtd/qinfo.h @@ -14,7 +14,7 @@ * @DevId - Chip Device ID * @qinfo - pointer to qinfo records describing the chip * @numchips - number of chips including virual RWW partitions - * @chipshift - Chip/partiton size 2^chipshift + * @chipshift - Chip/partition size 2^chipshift * @chips - per-chip data structure */ struct lpddr_private { diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index c425c7b4c2a0..55faa2f07cca 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -43,9 +43,13 @@ #define SPINOR_OP_WRSR 0x01 /* Write status register 1 byte */ #define SPINOR_OP_READ 0x03 /* Read data bytes (low frequency) */ #define SPINOR_OP_READ_FAST 0x0b /* Read data bytes (high frequency) */ -#define SPINOR_OP_READ_1_1_2 0x3b /* Read data bytes (Dual SPI) */ -#define SPINOR_OP_READ_1_1_4 0x6b /* Read data bytes (Quad SPI) */ +#define SPINOR_OP_READ_1_1_2 0x3b /* Read data bytes (Dual Output SPI) */ +#define SPINOR_OP_READ_1_2_2 0xbb /* Read data bytes (Dual I/O SPI) */ +#define SPINOR_OP_READ_1_1_4 0x6b /* Read data bytes (Quad Output SPI) */ +#define SPINOR_OP_READ_1_4_4 0xeb /* Read data bytes (Quad I/O SPI) */ #define SPINOR_OP_PP 0x02 /* Page program (up to 256 bytes) */ +#define SPINOR_OP_PP_1_1_4 0x32 /* Quad page program */ +#define SPINOR_OP_PP_1_4_4 0x38 /* Quad page program */ #define SPINOR_OP_BE_4K 0x20 /* Erase 4KiB block */ #define SPINOR_OP_BE_4K_PMC 0xd7 /* Erase 4KiB block on PMC chips */ #define SPINOR_OP_BE_32K 0x52 /* Erase 32KiB block */ @@ -56,18 +60,42 @@ #define SPINOR_OP_RDFSR 0x70 /* Read flag status register */ /* 4-byte address opcodes - used on Spansion and some Macronix flashes. */ -#define SPINOR_OP_READ4 0x13 /* Read data bytes (low frequency) */ -#define SPINOR_OP_READ4_FAST 0x0c /* Read data bytes (high frequency) */ -#define SPINOR_OP_READ4_1_1_2 0x3c /* Read data bytes (Dual SPI) */ -#define SPINOR_OP_READ4_1_1_4 0x6c /* Read data bytes (Quad SPI) */ +#define SPINOR_OP_READ_4B 0x13 /* Read data bytes (low frequency) */ +#define SPINOR_OP_READ_FAST_4B 0x0c /* Read data bytes (high frequency) */ +#define SPINOR_OP_READ_1_1_2_4B 0x3c /* Read data bytes (Dual Output SPI) */ +#define SPINOR_OP_READ_1_2_2_4B 0xbc /* Read data bytes (Dual I/O SPI) */ +#define SPINOR_OP_READ_1_1_4_4B 0x6c /* Read data bytes (Quad Output SPI) */ +#define SPINOR_OP_READ_1_4_4_4B 0xec /* Read data bytes (Quad I/O SPI) */ #define SPINOR_OP_PP_4B 0x12 /* Page program (up to 256 bytes) */ +#define SPINOR_OP_PP_1_1_4_4B 0x34 /* Quad page program */ +#define SPINOR_OP_PP_1_4_4_4B 0x3e /* Quad page program */ +#define SPINOR_OP_BE_4K_4B 0x21 /* Erase 4KiB block */ +#define SPINOR_OP_BE_32K_4B 0x5c /* Erase 32KiB block */ #define SPINOR_OP_SE_4B 0xdc /* Sector erase (usually 64KiB) */ +/* Double Transfer Rate opcodes - defined in JEDEC JESD216B. */ +#define SPINOR_OP_READ_1_1_1_DTR 0x0d +#define SPINOR_OP_READ_1_2_2_DTR 0xbd +#define SPINOR_OP_READ_1_4_4_DTR 0xed + +#define SPINOR_OP_READ_1_1_1_DTR_4B 0x0e +#define SPINOR_OP_READ_1_2_2_DTR_4B 0xbe +#define SPINOR_OP_READ_1_4_4_DTR_4B 0xee + /* Used for SST flashes only. */ #define SPINOR_OP_BP 0x02 /* Byte program */ #define SPINOR_OP_WRDI 0x04 /* Write disable */ #define SPINOR_OP_AAI_WP 0xad /* Auto address increment word program */ +/* Used for S3AN flashes only */ +#define SPINOR_OP_XSE 0x50 /* Sector erase */ +#define SPINOR_OP_XPP 0x82 /* Page program */ +#define SPINOR_OP_XRDSR 0xd7 /* Read status register */ + +#define XSR_PAGESIZE BIT(0) /* Page size in Po2 or Linear */ +#define XSR_RDY BIT(7) /* Ready */ + + /* Used for Macronix and Winbond flashes. */ #define SPINOR_OP_EN4B 0xb7 /* Enter 4-byte mode */ #define SPINOR_OP_EX4B 0xe9 /* Exit 4-byte mode */ @@ -100,13 +128,81 @@ /* Configuration Register bits. */ #define CR_QUAD_EN_SPAN BIT(1) /* Spansion Quad I/O */ -enum read_mode { - SPI_NOR_NORMAL = 0, - SPI_NOR_FAST, - SPI_NOR_DUAL, - SPI_NOR_QUAD, +/* Supported SPI protocols */ +#define SNOR_PROTO_INST_MASK GENMASK(23, 16) +#define SNOR_PROTO_INST_SHIFT 16 +#define SNOR_PROTO_INST(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_INST_SHIFT) & \ + SNOR_PROTO_INST_MASK) + +#define SNOR_PROTO_ADDR_MASK GENMASK(15, 8) +#define SNOR_PROTO_ADDR_SHIFT 8 +#define SNOR_PROTO_ADDR(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_ADDR_SHIFT) & \ + SNOR_PROTO_ADDR_MASK) + +#define SNOR_PROTO_DATA_MASK GENMASK(7, 0) +#define SNOR_PROTO_DATA_SHIFT 0 +#define SNOR_PROTO_DATA(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_DATA_SHIFT) & \ + SNOR_PROTO_DATA_MASK) + +#define SNOR_PROTO_IS_DTR BIT(24) /* Double Transfer Rate */ + +#define SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits) \ + (SNOR_PROTO_INST(_inst_nbits) | \ + SNOR_PROTO_ADDR(_addr_nbits) | \ + SNOR_PROTO_DATA(_data_nbits)) +#define SNOR_PROTO_DTR(_inst_nbits, _addr_nbits, _data_nbits) \ + (SNOR_PROTO_IS_DTR | \ + SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits)) + +enum spi_nor_protocol { + SNOR_PROTO_1_1_1 = SNOR_PROTO_STR(1, 1, 1), + SNOR_PROTO_1_1_2 = SNOR_PROTO_STR(1, 1, 2), + SNOR_PROTO_1_1_4 = SNOR_PROTO_STR(1, 1, 4), + SNOR_PROTO_1_1_8 = SNOR_PROTO_STR(1, 1, 8), + SNOR_PROTO_1_2_2 = SNOR_PROTO_STR(1, 2, 2), + SNOR_PROTO_1_4_4 = SNOR_PROTO_STR(1, 4, 4), + SNOR_PROTO_1_8_8 = SNOR_PROTO_STR(1, 8, 8), + SNOR_PROTO_2_2_2 = SNOR_PROTO_STR(2, 2, 2), + SNOR_PROTO_4_4_4 = SNOR_PROTO_STR(4, 4, 4), + SNOR_PROTO_8_8_8 = SNOR_PROTO_STR(8, 8, 8), + + SNOR_PROTO_1_1_1_DTR = SNOR_PROTO_DTR(1, 1, 1), + SNOR_PROTO_1_2_2_DTR = SNOR_PROTO_DTR(1, 2, 2), + SNOR_PROTO_1_4_4_DTR = SNOR_PROTO_DTR(1, 4, 4), + SNOR_PROTO_1_8_8_DTR = SNOR_PROTO_DTR(1, 8, 8), }; +static inline bool spi_nor_protocol_is_dtr(enum spi_nor_protocol proto) +{ + return !!(proto & SNOR_PROTO_IS_DTR); +} + +static inline u8 spi_nor_get_protocol_inst_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_INST_MASK)) >> + SNOR_PROTO_INST_SHIFT; +} + +static inline u8 spi_nor_get_protocol_addr_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_ADDR_MASK)) >> + SNOR_PROTO_ADDR_SHIFT; +} + +static inline u8 spi_nor_get_protocol_data_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_DATA_MASK)) >> + SNOR_PROTO_DATA_SHIFT; +} + +static inline u8 spi_nor_get_protocol_width(enum spi_nor_protocol proto) +{ + return spi_nor_get_protocol_data_nbits(proto); +} + #define SPI_NOR_MAX_CMD_SIZE 8 enum spi_nor_ops { SPI_NOR_OPS_READ = 0, @@ -119,6 +215,9 @@ enum spi_nor_ops { enum spi_nor_option_flags { SNOR_F_USE_FSR = BIT(0), SNOR_F_HAS_SR_TB = BIT(1), + SNOR_F_NO_OP_CHIP_ERASE = BIT(2), + SNOR_F_S3AN_ADDR_DEFAULT = BIT(3), + SNOR_F_READY_XSR_RDY = BIT(4), }; /** @@ -132,9 +231,11 @@ enum spi_nor_option_flags { * @read_opcode: the read opcode * @read_dummy: the dummy needed by the read operation * @program_opcode: the program opcode - * @flash_read: the mode of the read * @sst_write_second: used by the SST write operation * @flags: flag options for the current SPI-NOR (SNOR_F_*) + * @read_proto: the SPI protocol for read operations + * @write_proto: the SPI protocol for write operations + * @reg_proto the SPI protocol for read_reg/write_reg/erase operations * @cmd_buf: used by the write_reg * @prepare: [OPTIONAL] do some preparations for the * read/write/erase/lock/unlock operations @@ -163,7 +264,9 @@ struct spi_nor { u8 read_opcode; u8 read_dummy; u8 program_opcode; - enum read_mode flash_read; + enum spi_nor_protocol read_proto; + enum spi_nor_protocol write_proto; + enum spi_nor_protocol reg_proto; bool sst_write_second; u32 flags; u8 cmd_buf[SPI_NOR_MAX_CMD_SIZE]; @@ -198,10 +301,71 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) } /** + * struct spi_nor_hwcaps - Structure for describing the hardware capabilies + * supported by the SPI controller (bus master). + * @mask: the bitmask listing all the supported hw capabilies + */ +struct spi_nor_hwcaps { + u32 mask; +}; + +/* + *(Fast) Read capabilities. + * MUST be ordered by priority: the higher bit position, the higher priority. + * As a matter of performances, it is relevant to use Octo SPI protocols first, + * then Quad SPI protocols before Dual SPI protocols, Fast Read and lastly + * (Slow) Read. + */ +#define SNOR_HWCAPS_READ_MASK GENMASK(14, 0) +#define SNOR_HWCAPS_READ BIT(0) +#define SNOR_HWCAPS_READ_FAST BIT(1) +#define SNOR_HWCAPS_READ_1_1_1_DTR BIT(2) + +#define SNOR_HWCAPS_READ_DUAL GENMASK(6, 3) +#define SNOR_HWCAPS_READ_1_1_2 BIT(3) +#define SNOR_HWCAPS_READ_1_2_2 BIT(4) +#define SNOR_HWCAPS_READ_2_2_2 BIT(5) +#define SNOR_HWCAPS_READ_1_2_2_DTR BIT(6) + +#define SNOR_HWCAPS_READ_QUAD GENMASK(10, 7) +#define SNOR_HWCAPS_READ_1_1_4 BIT(7) +#define SNOR_HWCAPS_READ_1_4_4 BIT(8) +#define SNOR_HWCAPS_READ_4_4_4 BIT(9) +#define SNOR_HWCAPS_READ_1_4_4_DTR BIT(10) + +#define SNOR_HWCPAS_READ_OCTO GENMASK(14, 11) +#define SNOR_HWCAPS_READ_1_1_8 BIT(11) +#define SNOR_HWCAPS_READ_1_8_8 BIT(12) +#define SNOR_HWCAPS_READ_8_8_8 BIT(13) +#define SNOR_HWCAPS_READ_1_8_8_DTR BIT(14) + +/* + * Page Program capabilities. + * MUST be ordered by priority: the higher bit position, the higher priority. + * Like (Fast) Read capabilities, Octo/Quad SPI protocols are preferred to the + * legacy SPI 1-1-1 protocol. + * Note that Dual Page Programs are not supported because there is no existing + * JEDEC/SFDP standard to define them. Also at this moment no SPI flash memory + * implements such commands. + */ +#define SNOR_HWCAPS_PP_MASK GENMASK(22, 16) +#define SNOR_HWCAPS_PP BIT(16) + +#define SNOR_HWCAPS_PP_QUAD GENMASK(19, 17) +#define SNOR_HWCAPS_PP_1_1_4 BIT(17) +#define SNOR_HWCAPS_PP_1_4_4 BIT(18) +#define SNOR_HWCAPS_PP_4_4_4 BIT(19) + +#define SNOR_HWCAPS_PP_OCTO GENMASK(22, 20) +#define SNOR_HWCAPS_PP_1_1_8 BIT(20) +#define SNOR_HWCAPS_PP_1_8_8 BIT(21) +#define SNOR_HWCAPS_PP_8_8_8 BIT(22) + +/** * spi_nor_scan() - scan the SPI NOR * @nor: the spi_nor structure * @name: the chip type name - * @mode: the read mode supported by the driver + * @hwcaps: the hardware capabilities supported by the controller driver * * The drivers can use this fuction to scan the SPI NOR. * In the scanning, it will try to get all the necessary information to @@ -211,6 +375,7 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) * * Return: 0 for success, others for failure. */ -int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode); +int spi_nor_scan(struct spi_nor *nor, const char *name, + const struct spi_nor_hwcaps *hwcaps); #endif diff --git a/include/linux/mutex.h b/include/linux/mutex.h index b97870f2debd..ffcba1f337da 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -20,6 +20,8 @@ #include <linux/osq_lock.h> #include <linux/debug_locks.h> +struct ww_acquire_ctx; + /* * Simple, straightforward mutexes with strict semantics: * @@ -65,7 +67,7 @@ struct mutex { static inline struct task_struct *__mutex_owner(struct mutex *lock) { - return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x03); + return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x07); } /* @@ -75,6 +77,7 @@ static inline struct task_struct *__mutex_owner(struct mutex *lock) struct mutex_waiter { struct list_head list; struct task_struct *task; + struct ww_acquire_ctx *ww_ctx; #ifdef CONFIG_DEBUG_MUTEXES void *magic; #endif @@ -156,10 +159,12 @@ extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass); extern int __must_check mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass); +extern void mutex_lock_io_nested(struct mutex *lock, unsigned int subclass); #define mutex_lock(lock) mutex_lock_nested(lock, 0) #define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0) #define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0) +#define mutex_lock_io(lock) mutex_lock_io_nested(lock, 0) #define mutex_lock_nest_lock(lock, nest_lock) \ do { \ @@ -171,11 +176,13 @@ do { \ extern void mutex_lock(struct mutex *lock); extern int __must_check mutex_lock_interruptible(struct mutex *lock); extern int __must_check mutex_lock_killable(struct mutex *lock); +extern void mutex_lock_io(struct mutex *lock); # define mutex_lock_nested(lock, subclass) mutex_lock(lock) # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock) # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock) # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) +# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock) #endif /* @@ -207,9 +214,9 @@ enum mutex_trylock_recursive_enum { * raisins, and once those are gone this will be removed. * * Returns: - * MUTEX_TRYLOCK_FAILED - trylock failed, - * MUTEX_TRYLOCK_SUCCESS - lock acquired, - * MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. + * - MUTEX_TRYLOCK_FAILED - trylock failed, + * - MUTEX_TRYLOCK_SUCCESS - lock acquired, + * - MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. */ static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum mutex_trylock_recursive(struct mutex *lock) diff --git a/include/linux/mux/consumer.h b/include/linux/mux/consumer.h new file mode 100644 index 000000000000..5577e1b773c4 --- /dev/null +++ b/include/linux/mux/consumer.h @@ -0,0 +1,32 @@ +/* + * mux/consumer.h - definitions for the multiplexer consumer interface + * + * Copyright (C) 2017 Axentia Technologies AB + * + * Author: Peter Rosin <peda@axentia.se> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_MUX_CONSUMER_H +#define _LINUX_MUX_CONSUMER_H + +struct device; +struct mux_control; + +unsigned int mux_control_states(struct mux_control *mux); +int __must_check mux_control_select(struct mux_control *mux, + unsigned int state); +int __must_check mux_control_try_select(struct mux_control *mux, + unsigned int state); +int mux_control_deselect(struct mux_control *mux); + +struct mux_control *mux_control_get(struct device *dev, const char *mux_name); +void mux_control_put(struct mux_control *mux); + +struct mux_control *devm_mux_control_get(struct device *dev, + const char *mux_name); + +#endif /* _LINUX_MUX_CONSUMER_H */ diff --git a/include/linux/mux/driver.h b/include/linux/mux/driver.h new file mode 100644 index 000000000000..35c3579c3304 --- /dev/null +++ b/include/linux/mux/driver.h @@ -0,0 +1,108 @@ +/* + * mux/driver.h - definitions for the multiplexer driver interface + * + * Copyright (C) 2017 Axentia Technologies AB + * + * Author: Peter Rosin <peda@axentia.se> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_MUX_DRIVER_H +#define _LINUX_MUX_DRIVER_H + +#include <dt-bindings/mux/mux.h> +#include <linux/device.h> +#include <linux/semaphore.h> + +struct mux_chip; +struct mux_control; + +/** + * struct mux_control_ops - Mux controller operations for a mux chip. + * @set: Set the state of the given mux controller. + */ +struct mux_control_ops { + int (*set)(struct mux_control *mux, int state); +}; + +/** + * struct mux_control - Represents a mux controller. + * @lock: Protects the mux controller state. + * @chip: The mux chip that is handling this mux controller. + * @cached_state: The current mux controller state, or -1 if none. + * @states: The number of mux controller states. + * @idle_state: The mux controller state to use when inactive, or one + * of MUX_IDLE_AS_IS and MUX_IDLE_DISCONNECT. + * + * Mux drivers may only change @states and @idle_state, and may only do so + * between allocation and registration of the mux controller. Specifically, + * @cached_state is internal to the mux core and should never be written by + * mux drivers. + */ +struct mux_control { + struct semaphore lock; /* protects the state of the mux */ + + struct mux_chip *chip; + int cached_state; + + unsigned int states; + int idle_state; +}; + +/** + * struct mux_chip - Represents a chip holding mux controllers. + * @controllers: Number of mux controllers handled by the chip. + * @mux: Array of mux controllers that are handled. + * @dev: Device structure. + * @id: Used to identify the device internally. + * @ops: Mux controller operations. + */ +struct mux_chip { + unsigned int controllers; + struct mux_control *mux; + struct device dev; + int id; + + const struct mux_control_ops *ops; +}; + +#define to_mux_chip(x) container_of((x), struct mux_chip, dev) + +/** + * mux_chip_priv() - Get the extra memory reserved by mux_chip_alloc(). + * @mux_chip: The mux-chip to get the private memory from. + * + * Return: Pointer to the private memory reserved by the allocator. + */ +static inline void *mux_chip_priv(struct mux_chip *mux_chip) +{ + return &mux_chip->mux[mux_chip->controllers]; +} + +struct mux_chip *mux_chip_alloc(struct device *dev, + unsigned int controllers, size_t sizeof_priv); +int mux_chip_register(struct mux_chip *mux_chip); +void mux_chip_unregister(struct mux_chip *mux_chip); +void mux_chip_free(struct mux_chip *mux_chip); + +struct mux_chip *devm_mux_chip_alloc(struct device *dev, + unsigned int controllers, + size_t sizeof_priv); +int devm_mux_chip_register(struct device *dev, struct mux_chip *mux_chip); + +/** + * mux_control_get_index() - Get the index of the given mux controller + * @mux: The mux-control to get the index for. + * + * Return: The index of the mux controller within the mux chip the mux + * controller is a part of. + */ +static inline unsigned int mux_control_get_index(struct mux_control *mux) +{ + return mux - mux->chip->mux; +} + +#endif /* _LINUX_MUX_DRIVER_H */ diff --git a/include/linux/namei.h b/include/linux/namei.h index f29abda31e6d..8b4794e83196 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -44,6 +44,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_JUMPED 0x1000 #define LOOKUP_ROOT 0x2000 #define LOOKUP_EMPTY 0x4000 +#define LOOKUP_DOWN 0x8000 extern int path_pts(struct path *path); diff --git a/include/linux/nd.h b/include/linux/nd.h index fa66aeed441a..5dc6b695437d 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -21,6 +21,15 @@ enum nvdimm_event { NVDIMM_REVALIDATE_POISON, }; +enum nvdimm_claim_class { + NVDIMM_CCLASS_NONE, + NVDIMM_CCLASS_BTT, + NVDIMM_CCLASS_BTT2, + NVDIMM_CCLASS_PFN, + NVDIMM_CCLASS_DAX, + NVDIMM_CCLASS_UNKNOWN, +}; + struct nd_device_driver { struct device_driver drv; unsigned long type; @@ -41,14 +50,16 @@ static inline struct nd_device_driver *to_nd_device_driver( * @force_raw: ignore other personalities for the namespace (e.g. btt) * @dev: device model node * @claim: when set a another personality has taken ownership of the namespace + * @claim_class: restrict claim type to a given class * @rw_bytes: access the raw namespace capacity with byte-aligned transfers */ struct nd_namespace_common { int force_raw; struct device dev; struct device *claim; + enum nvdimm_claim_class claim_class; int (*rw_bytes)(struct nd_namespace_common *, resource_size_t offset, - void *buf, size_t size, int rw); + void *buf, size_t size, int rw, unsigned long flags); }; static inline struct nd_namespace_common *to_ndns(struct device *dev) @@ -75,12 +86,14 @@ struct nd_namespace_io { /** * struct nd_namespace_pmem - namespace device for dimm-backed interleaved memory * @nsio: device and system physical address range to drive + * @lbasize: logical sector size for the namespace in block-device-mode * @alt_name: namespace name supplied in the dimm label * @uuid: namespace name supplied in the dimm label * @id: ida allocated id */ struct nd_namespace_pmem { struct nd_namespace_io nsio; + unsigned long lbasize; char *alt_name; u8 *uuid; int id; @@ -134,9 +147,10 @@ static inline struct nd_namespace_blk *to_nd_namespace_blk(const struct device * * @buf is up-to-date upon return from this routine. */ static inline int nvdimm_read_bytes(struct nd_namespace_common *ndns, - resource_size_t offset, void *buf, size_t size) + resource_size_t offset, void *buf, size_t size, + unsigned long flags) { - return ndns->rw_bytes(ndns, offset, buf, size, READ); + return ndns->rw_bytes(ndns, offset, buf, size, READ, flags); } /** @@ -152,9 +166,10 @@ static inline int nvdimm_read_bytes(struct nd_namespace_common *ndns, * to media is handled internal to the @ndns driver, if at all. */ static inline int nvdimm_write_bytes(struct nd_namespace_common *ndns, - resource_size_t offset, void *buf, size_t size) + resource_size_t offset, void *buf, size_t size, + unsigned long flags) { - return ndns->rw_bytes(ndns, offset, buf, size, WRITE); + return ndns->rw_bytes(ndns, offset, buf, size, WRITE, flags); } #define MODULE_ALIAS_ND_DEVICE(type) \ diff --git a/include/linux/net.h b/include/linux/net.h index cd0c8bd0a1de..dda2cc939a53 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -146,7 +146,7 @@ struct proto_ops { int (*socketpair)(struct socket *sock1, struct socket *sock2); int (*accept) (struct socket *sock, - struct socket *newsock, int flags); + struct socket *newsock, int flags, bool kern); int (*getname) (struct socket *sock, struct sockaddr *addr, int *sockaddr_len, int peer); @@ -274,6 +274,8 @@ do { \ #define net_get_random_once(buf, nbytes) \ get_random_once((buf), (nbytes)) +#define net_get_random_once_wait(buf, nbytes) \ + get_random_once_wait((buf), (nbytes)) int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); @@ -298,6 +300,9 @@ int kernel_sendpage(struct socket *sock, struct page *page, int offset, int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); +/* Routine returns the IP overhead imposed by a (caller-protected) socket. */ +u32 kernel_sock_ip_overhead(struct sock *sk); + #define MODULE_ALIAS_NETPROTO(proto) \ MODULE_ALIAS("net-pf-" __stringify(proto)) diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 9c6c8ef2e9e7..1d4737cffc71 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -54,8 +54,9 @@ enum { */ NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */ NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */ + NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ - NETIF_F_GSO_SCTP_BIT, + NETIF_F_GSO_ESP_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ @@ -71,9 +72,10 @@ enum { NETIF_F_HW_VLAN_STAG_RX_BIT, /* Receive VLAN STAG HW acceleration */ NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ - NETIF_F_BUSY_POLL_BIT, /* Busy poll */ NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */ + NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */ + NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ /* * Add your fresh new feature above and remember to update @@ -130,12 +132,14 @@ enum { #define NETIF_F_GSO_PARTIAL __NETIF_F(GSO_PARTIAL) #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM) #define NETIF_F_GSO_SCTP __NETIF_F(GSO_SCTP) +#define NETIF_F_GSO_ESP __NETIF_F(GSO_ESP) #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) #define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) -#define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) #define NETIF_F_HW_TC __NETIF_F(HW_TC) +#define NETIF_F_HW_ESP __NETIF_F(HW_ESP) +#define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 70ad0291d517..779b23595596 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -41,7 +41,6 @@ #include <linux/ethtool.h> #include <net/net_namespace.h> -#include <net/dsa.h> #ifdef CONFIG_DCB #include <net/dcbnl.h> #endif @@ -57,6 +56,8 @@ struct netpoll_info; struct device; struct phy_device; +struct dsa_switch_tree; + /* 802.11 specific */ struct wireless_dev; /* 802.15.4 specific */ @@ -236,8 +237,7 @@ struct netdev_hw_addr_list { netdev_hw_addr_list_for_each(ha, &(dev)->mc) struct hh_cache { - u16 hh_len; - u16 __pad; + unsigned int hh_len; seqlock_t hh_lock; /* cached hardware header; allow for machine alignment needs. */ @@ -330,6 +330,7 @@ struct napi_struct { enum { NAPI_STATE_SCHED, /* Poll is scheduled */ + NAPI_STATE_MISSED, /* reschedule a napi */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ @@ -338,12 +339,13 @@ enum { }; enum { - NAPIF_STATE_SCHED = (1UL << NAPI_STATE_SCHED), - NAPIF_STATE_DISABLE = (1UL << NAPI_STATE_DISABLE), - NAPIF_STATE_NPSVC = (1UL << NAPI_STATE_NPSVC), - NAPIF_STATE_HASHED = (1UL << NAPI_STATE_HASHED), - NAPIF_STATE_NO_BUSY_POLL = (1UL << NAPI_STATE_NO_BUSY_POLL), - NAPIF_STATE_IN_BUSY_POLL = (1UL << NAPI_STATE_IN_BUSY_POLL), + NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), + NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), + NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), + NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), + NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED), + NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), + NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), }; enum gro_result { @@ -352,6 +354,7 @@ enum gro_result { GRO_HELD, GRO_NORMAL, GRO_DROP, + GRO_CONSUMED, }; typedef enum gro_result gro_result_t; @@ -413,20 +416,7 @@ static inline bool napi_disable_pending(struct napi_struct *n) return test_bit(NAPI_STATE_DISABLE, &n->state); } -/** - * napi_schedule_prep - check if NAPI can be scheduled - * @n: NAPI context - * - * Test if NAPI routine is already running, and if not mark - * it as running. This is used as a condition variable to - * insure only one NAPI poll instance runs. We also make - * sure there is no pending NAPI disable. - */ -static inline bool napi_schedule_prep(struct napi_struct *n) -{ - return !napi_disable_pending(n) && - !test_and_set_bit(NAPI_STATE_SCHED, &n->state); -} +bool napi_schedule_prep(struct napi_struct *n); /** * napi_schedule - schedule NAPI poll @@ -463,7 +453,6 @@ static inline bool napi_reschedule(struct napi_struct *napi) return false; } -bool __napi_complete(struct napi_struct *n); bool napi_complete_done(struct napi_struct *n, int work_done); /** * napi_complete - NAPI processing complete @@ -797,11 +786,11 @@ struct tc_cls_u32_offload; struct tc_to_netdev { unsigned int type; union { - u8 tc; struct tc_cls_u32_offload *cls_u32; struct tc_cls_flower_offload *cls_flower; struct tc_cls_matchall_offload *cls_mall; struct tc_cls_bpf_offload *cls_bpf; + struct tc_mqprio_qopt *mqprio; }; bool egress_dev; }; @@ -818,22 +807,43 @@ enum xdp_netdev_command { * when it is no longer used. */ XDP_SETUP_PROG, + XDP_SETUP_PROG_HW, /* Check if a bpf program is set on the device. The callee should - * return true if a program is currently attached and running. + * set @prog_attached to one of XDP_ATTACHED_* values, note that "true" + * is equivalent to XDP_ATTACHED_DRV. */ XDP_QUERY_PROG, }; +struct netlink_ext_ack; + struct netdev_xdp { enum xdp_netdev_command command; union { /* XDP_SETUP_PROG */ - struct bpf_prog *prog; + struct { + u32 flags; + struct bpf_prog *prog; + struct netlink_ext_ack *extack; + }; /* XDP_QUERY_PROG */ - bool prog_attached; + struct { + u8 prog_attached; + u32 prog_id; + }; }; }; +#ifdef CONFIG_XFRM_OFFLOAD +struct xfrmdev_ops { + int (*xdo_dev_state_add) (struct xfrm_state *x); + void (*xdo_dev_state_delete) (struct xfrm_state *x); + void (*xdo_dev_state_free) (struct xfrm_state *x); + bool (*xdo_dev_offload_ok) (struct sk_buff *skb, + struct xfrm_state *x); +}; +#endif + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -910,15 +920,14 @@ struct netdev_xdp { * * int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); * Called when a user wants to change the Maximum Transfer Unit - * of a device. If not defined, any request to change MTU will - * will return an error. + * of a device. * * void (*ndo_tx_timeout)(struct net_device *dev); * Callback used when the transmitter has not made any progress * for dev->watchdog ticks. * - * struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, - * struct rtnl_link_stats64 *storage); + * void (*ndo_get_stats64)(struct net_device *dev, + * struct rtnl_link_stats64 *storage); * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); * Called when a user wants to get the network device usage * statistics. Drivers must do one of the following: @@ -968,11 +977,12 @@ struct netdev_xdp { * with PF and querying it may introduce a theoretical security risk. * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); - * int (*ndo_setup_tc)(struct net_device *dev, u8 tc) - * Called to setup 'tc' number of traffic classes in the net device. This - * is always called from the stack with the rtnl lock held and netif tx - * queues stopped. This allows the netdevice to perform queue management - * safely. + * int (*ndo_setup_tc)(struct net_device *dev, u32 handle, u32 chain_index, + * __be16 protocol, struct tc_to_netdev *tc); + * Called to setup any 'tc' scheduler, classifier or action on @dev. + * This is always called from the stack with the rtnl lock held and netif + * tx queues stopped. This allows the netdevice to perform queue + * management safely. * * Fiber Channel over Ethernet (FCoE) offload functions. * int (*ndo_fcoe_enable)(struct net_device *dev); @@ -1104,12 +1114,6 @@ struct netdev_xdp { * by 'ndo_dfwd_add_station'. 'pdev' is the net device backing * the station and priv is the structure returned by the add * operation. - * netdev_tx_t (*ndo_dfwd_start_xmit)(struct sk_buff *skb, - * struct net_device *dev, - * void *priv); - * Callback to use for xmit over the accelerated station. This - * is used in place of ndo_start_xmit on accelerated net - * devices. * int (*ndo_set_tx_maxrate)(struct net_device *dev, * int queue_index, u32 maxrate); * Called when a user wants to set a max-rate limitation of specific @@ -1166,8 +1170,8 @@ struct net_device_ops { struct neigh_parms *); void (*ndo_tx_timeout) (struct net_device *dev); - struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, - struct rtnl_link_stats64 *storage); + void (*ndo_get_stats64)(struct net_device *dev, + struct rtnl_link_stats64 *storage); bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id); int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, @@ -1184,9 +1188,6 @@ struct net_device_ops { struct netpoll_info *info); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif -#ifdef CONFIG_NET_RX_BUSY_POLL - int (*ndo_busy_poll)(struct napi_struct *dev); -#endif int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, @@ -1220,7 +1221,7 @@ struct net_device_ops { struct net_device *dev, int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, - u32 handle, + u32 handle, u32 chain_index, __be16 protocol, struct tc_to_netdev *tc); #if IS_ENABLED(CONFIG_FCOE) @@ -1309,9 +1310,6 @@ struct net_device_ops { void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); - netdev_tx_t (*ndo_dfwd_start_xmit) (struct sk_buff *skb, - struct net_device *dev, - void *priv); int (*ndo_get_lock_subclass)(struct net_device *dev); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, @@ -1431,13 +1429,14 @@ enum netdev_priv_flags { /** * struct net_device - The DEVICE structure. - * Actually, this whole structure is a big mistake. It mixes I/O - * data with strictly "high-level" data, and it has to know about - * almost every data structure used in the INET module. + * + * Actually, this whole structure is a big mistake. It mixes I/O + * data with strictly "high-level" data, and it has to know about + * almost every data structure used in the INET module. * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name - * of the interface. + * of the interface. * * @name_hlist: Device name hash chain, please keep it close to name[] * @ifalias: SNMP alias @@ -1511,6 +1510,7 @@ enum netdev_priv_flags { * @max_mtu: Interface Maximum MTU value * @type: Interface hardware type * @hard_header_len: Maximum hardware header length. + * @min_header_len: Minimum hardware header length * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -1552,7 +1552,6 @@ enum netdev_priv_flags { * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * - * @last_rx: Time of last Rx * @dev_addr: Hw address (before bcast, * because most packets are unicast) * @@ -1594,8 +1593,8 @@ enum netdev_priv_flags { * @rtnl_link_state: This enum represents the phases of creating * a new link * - * @destructor: Called from unregister, - * can be used to call free_netdev + * @needs_free_netdev: Should unregister perform free_netdev? + * @priv_destructor: Called from unregister * @npinfo: XXX: need comments on this one * @nd_net: Network namespace this network device is inside * @@ -1709,6 +1708,10 @@ struct net_device { const struct ndisc_ops *ndisc_ops; #endif +#ifdef CONFIG_XFRM + const struct xfrmdev_ops *xfrmdev_ops; +#endif + const struct header_ops *header_ops; unsigned int flags; @@ -1728,6 +1731,7 @@ struct net_device { unsigned int max_mtu; unsigned short type; unsigned short hard_header_len; + unsigned char min_header_len; unsigned short needed_headroom; unsigned short needed_tailroom; @@ -1778,8 +1782,6 @@ struct net_device { /* * Cache lines mostly used on receive path (including eth_type_trans()) */ - unsigned long last_rx; - /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; @@ -1790,6 +1792,7 @@ struct net_device { unsigned int real_num_rx_queues; #endif + struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -1818,7 +1821,7 @@ struct net_device { #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); #endif - unsigned long tx_queue_len; + unsigned int tx_queue_len; spinlock_t tx_global_lock; int watchdog_timeo; @@ -1852,7 +1855,8 @@ struct net_device { RTNL_LINK_INITIALIZING, } rtnl_link_state:16; - void (*destructor)(struct net_device *dev); + bool needs_free_netdev; + void (*priv_destructor)(struct net_device *dev); #ifdef CONFIG_NETPOLL struct netpoll_info __rcu *npinfo; @@ -1869,8 +1873,12 @@ struct net_device { struct pcpu_vstats __percpu *vstats; }; +#if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; +#endif +#if IS_ENABLED(CONFIG_MRP) struct mrp_port __rcu *mrp_port; +#endif struct device dev; const struct attribute_group *sysfs_groups[4]; @@ -1904,6 +1912,13 @@ struct net_device { }; #define to_net_dev(d) container_of(d, struct net_device, dev) +static inline bool netif_elide_gro(const struct net_device *dev) +{ + if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog) + return true; + return false; +} + #define NETDEV_ALIGN 32 static inline @@ -2014,15 +2029,6 @@ void dev_net_set(struct net_device *dev, struct net *net) write_pnet(&dev->nd_net, net); } -static inline bool netdev_uses_dsa(struct net_device *dev) -{ -#if IS_ENABLED(CONFIG_NET_DSA) - if (dev->dsa_ptr != NULL) - return dsa_uses_tagged_protocol(dev->dsa_ptr); -#endif - return false; -} - /** * netdev_priv - access network device private data * @dev: network device @@ -2448,6 +2454,7 @@ static inline int dev_recursion_level(void) struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); +struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); @@ -2565,9 +2572,7 @@ static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_gro_checksum_validate_complete(skb, \ compute_pseudo(skb, proto)); \ - if (__ret) \ - __skb_mark_checksum_bad(skb); \ - else \ + if (!__ret) \ skb_gro_incr_csum_unnecessary(skb); \ __ret; \ }) @@ -2667,6 +2672,19 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, remcsum_unadjust((__sum16 *)ptr, grc->delta); } +#ifdef CONFIG_XFRM_OFFLOAD +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +{ + if (PTR_ERR(pp) != -EINPROGRESS) + NAPI_GRO_CB(skb)->flush |= flush; +} +#else +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +{ + NAPI_GRO_CB(skb)->flush |= flush; +} +#endif + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -2694,6 +2712,8 @@ static inline bool dev_validate_header(const struct net_device *dev, { if (likely(len >= dev->hard_header_len)) return true; + if (len < dev->min_header_len) + return false; if (capable(CAP_SYS_RAWIO)) { memset(ll_header + len, 0, dev->hard_header_len - len); @@ -3107,7 +3127,19 @@ static inline bool netif_subqueue_stopped(const struct net_device *dev, return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); } -void netif_wake_subqueue(struct net_device *dev, u16 queue_index); +/** + * netif_wake_subqueue - allow sending packets on subqueue + * @dev: network device + * @queue_index: sub queue index + * + * Resume individual transmit queue of a device with multiple transmit queues. + */ +static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) +{ + struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); + + netif_tx_wake_queue(txq); +} #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, @@ -3252,6 +3284,7 @@ void __dev_notify_flags(struct net_device *, unsigned int old_flags, int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); +int __dev_set_mtu(struct net_device *, int); int dev_set_mtu(struct net_device *, int); void dev_set_group(struct net_device *, int); int dev_set_mac_address(struct net_device *, struct sockaddr *); @@ -3261,10 +3294,15 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); + +typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp); +int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, + int fd, u32 flags); +u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id); + int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, @@ -3288,6 +3326,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern int netdev_budget; +extern unsigned int netdev_budget_usecs; /* Called by rtnetlink.c:rtnl_unlock() */ void netdev_run_todo(void); @@ -3377,10 +3416,10 @@ static inline void netif_dormant_off(struct net_device *dev) } /** - * netif_dormant - test if carrier present + * netif_dormant - test if device is dormant * @dev: network device * - * Check if carrier is present on device + * Check if device is dormant. */ static inline bool netif_dormant(const struct net_device *dev) { @@ -3801,6 +3840,10 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, extern int netdev_max_backlog; extern int netdev_tstamp_prequeue; extern int weight_p; +extern int dev_weight_rx_bias; +extern int dev_weight_tx_bias; +extern int dev_rx_weight; +extern int dev_tx_weight; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, @@ -3878,10 +3921,6 @@ void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info); -int netdev_default_l2upper_neigh_construct(struct net_device *dev, - struct neighbour *n); -void netdev_default_l2upper_neigh_destroy(struct net_device *dev, - struct neighbour *n); /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 @@ -3890,6 +3929,10 @@ void netdev_rss_key_fill(void *buffer, size_t len); int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); +int skb_crc32c_csum_help(struct sk_buff *skb); +int skb_csum_hwoffload_help(struct sk_buff *skb, + const netdev_features_t features); + struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, @@ -4061,6 +4104,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } @@ -4163,6 +4207,11 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } +static inline bool netif_is_ovs_port(const struct net_device *dev) +{ + return dev->priv_flags & IFF_OVS_DATAPATH; +} + static inline bool netif_is_team_master(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM; @@ -4214,6 +4263,11 @@ static inline const char *netdev_name(const struct net_device *dev) return dev->name; } +static inline bool netdev_unregistering(const struct net_device *dev) +{ + return dev->reg_state == NETREG_UNREGISTERING; +} + static inline const char *netdev_reg_state(const struct net_device *dev) { switch (dev->reg_state) { @@ -4334,6 +4388,15 @@ do { \ }) #endif +/* if @cond then downgrade to debug, else print at @level */ +#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ + do { \ + if (cond) \ + netif_dbg(priv, type, netdev, fmt, ##args); \ + else \ + netif_ ## level(priv, type, netdev, fmt, ##args); \ + } while (0) + #if defined(VERBOSE_DEBUG) #define netif_vdbg netif_dbg #else diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index a4b97be30b28..22f081065d49 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -61,8 +61,6 @@ typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); struct nf_hook_ops { - struct list_head list; - /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; @@ -160,13 +158,6 @@ int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n); -int nf_register_hook(struct nf_hook_ops *reg); -void nf_unregister_hook(struct nf_hook_ops *reg); -int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); -void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); -int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); -void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); - /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ int nf_register_sockopt(struct nf_sockopt_ops *reg); diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 1d82dd5e9a08..41d04e9d088a 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -1,7 +1,6 @@ #ifndef _NFNETLINK_H #define _NFNETLINK_H - #include <linux/netlink.h> #include <linux/capability.h> #include <net/netlink.h> @@ -10,13 +9,16 @@ struct nfnl_callback { int (*call)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]); + const struct nlattr * const cda[], + struct netlink_ext_ack *extack); int (*call_rcu)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]); + const struct nlattr * const cda[], + struct netlink_ext_ack *extack); int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[]); + const struct nlattr * const cda[], + struct netlink_ext_ack *extack); const struct nla_policy *policy; /* netlink attribute policy */ const u_int16_t attr_count; /* number of nlattr's */ }; @@ -28,6 +30,7 @@ struct nfnetlink_subsystem { const struct nfnl_callback *cb; /* callback for individual types */ int (*commit)(struct net *net, struct sk_buff *skb); int (*abort)(struct net *net, struct sk_buff *skb); + bool (*valid_genid)(struct net *net, u32 genid); }; int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n); @@ -40,6 +43,11 @@ int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, int flags); +static inline u16 nfnl_msg_type(u8 subsys, u8 msg_type) +{ + return subsys << 8 | msg_type; +} + void nfnl_lock(__u8 subsys_id); void nfnl_unlock(__u8 subsys_id); #ifdef CONFIG_PROVE_LOCKING diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 5117e4d2ddfa..b3044c2c62cb 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -167,6 +167,7 @@ struct xt_match { const char *table; unsigned int matchsize; + unsigned int usersize; #ifdef CONFIG_COMPAT unsigned int compatsize; #endif @@ -207,6 +208,7 @@ struct xt_target { const char *table; unsigned int targetsize; + unsigned int usersize; #ifdef CONFIG_COMPAT unsigned int compatsize; #endif @@ -287,6 +289,13 @@ int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto, int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto, bool inv_proto); +int xt_match_to_user(const struct xt_entry_match *m, + struct xt_entry_match __user *u); +int xt_target_to_user(const struct xt_entry_target *t, + struct xt_entry_target __user *u); +int xt_data_to_user(void __user *dst, const void *src, + int usersize, int size, int aligned_size); + void *xt_copy_counters_from_user(const void __user *user, unsigned int len, struct xt_counters_info *info, bool compat); diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 984b2112c77b..2c2a5514b0df 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -109,8 +109,10 @@ struct ebt_table { #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ ~(__alignof__(struct _xt_align)-1)) extern struct ebt_table *ebt_register_table(struct net *net, - const struct ebt_table *table); -extern void ebt_unregister_table(struct net *net, struct ebt_table *table); + const struct ebt_table *table, + const struct nf_hook_ops *); +extern void ebt_unregister_table(struct net *net, struct ebt_table *table, + const struct nf_hook_ops *); extern unsigned int ebt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct ebt_table *table); @@ -120,7 +122,10 @@ extern unsigned int ebt_do_table(struct sk_buff *skb, #define BASE_CHAIN (par->hook_mask & (1 << NF_BR_NUMHOOKS)) /* Clear the bit in the hook mask that tells if the rule is on a base chain */ #define CLEAR_BASE_CHAIN_BIT (par->hook_mask &= ~(1 << NF_BR_NUMHOOKS)) -/* True if the target is not a standard target */ -#define INVALID_TARGET (info->target < -NUM_STANDARD_TARGETS || info->target >= 0) + +static inline bool ebt_invalid_target(int target) +{ + return (target < -NUM_STANDARD_TARGETS || target >= 0); +} #endif diff --git a/include/linux/netlink.h b/include/linux/netlink.h index da14ab61f363..8664fd26eb5d 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -62,11 +62,62 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg) return __netlink_kernel_create(net, unit, THIS_MODULE, cfg); } +/* this can be increased when necessary - don't expose to userland */ +#define NETLINK_MAX_COOKIE_LEN 20 + +/** + * struct netlink_ext_ack - netlink extended ACK report struct + * @_msg: message string to report - don't access directly, use + * %NL_SET_ERR_MSG + * @bad_attr: attribute with error + * @cookie: cookie data to return to userspace (for success) + * @cookie_len: actual cookie data length + */ +struct netlink_ext_ack { + const char *_msg; + const struct nlattr *bad_attr; + u8 cookie[NETLINK_MAX_COOKIE_LEN]; + u8 cookie_len; +}; + +/* Always use this macro, this allows later putting the + * message into a separate section or such for things + * like translation or listing all possible messages. + * Currently string formatting is not supported (due + * to the lack of an output buffer.) + */ +#define NL_SET_ERR_MSG(extack, msg) do { \ + static const char __msg[] = (msg); \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (__extack) \ + __extack->_msg = __msg; \ +} while (0) + +#define NL_SET_ERR_MSG_MOD(extack, msg) \ + NL_SET_ERR_MSG((extack), KBUILD_MODNAME ": " msg) + +#define NL_SET_BAD_ATTR(extack, attr) do { \ + if ((extack)) \ + (extack)->bad_attr = (attr); \ +} while (0) + +#define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do { \ + static const char __msg[] = (msg); \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (__extack) { \ + __extack->_msg = __msg; \ + __extack->bad_attr = (attr); \ + } \ +} while (0) + extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group); -extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); +extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, + const struct netlink_ext_ack *extack); extern int netlink_has_listeners(struct sock *sk, unsigned int group); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 1828900c9411..27c0aaa22cb0 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -11,6 +11,7 @@ #include <linux/interrupt.h> #include <linux/rcupdate.h> #include <linux/list.h> +#include <linux/refcount.h> union inet_addr { __u32 all[4]; @@ -34,7 +35,7 @@ struct netpoll { }; struct netpoll_info { - atomic_t refcnt; + refcount_t refcnt; struct semaphore dev_lock; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 1b1ca04820a3..47239c336688 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -479,6 +479,7 @@ enum { NFSPROC4_CLNT_ACCESS, NFSPROC4_CLNT_GETATTR, NFSPROC4_CLNT_LOOKUP, + NFSPROC4_CLNT_LOOKUPP, NFSPROC4_CLNT_LOOKUP_ROOT, NFSPROC4_CLNT_REMOVE, NFSPROC4_CLNT_RENAME, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f1da8c8dd473..5cc91d6381a3 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -51,7 +51,7 @@ struct nfs_access_entry { struct list_head lru; unsigned long jiffies; struct rpc_cred * cred; - int mask; + __u32 mask; struct rcu_head rcu_head; }; @@ -76,6 +76,7 @@ struct nfs_open_context { #define NFS_CONTEXT_ERROR_WRITE (0) #define NFS_CONTEXT_RESEND_WRITES (1) #define NFS_CONTEXT_BAD (2) +#define NFS_CONTEXT_UNLOCK (3) int error; struct list_head list; @@ -331,11 +332,12 @@ extern void nfs_zap_caches(struct inode *); extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); +struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); -extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); +extern int nfs_getattr(const struct path *, struct kstat *, u32, unsigned int); extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct inode *, int); @@ -499,25 +501,13 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned */ extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); -extern int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder); +extern int nfs_wb_page(struct inode *inode, struct page *page); extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); -extern struct nfs_commit_data *nfs_commitdata_alloc(void); +extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); extern void nfs_commit_free(struct nfs_commit_data *data); static inline int -nfs_wb_launder_page(struct inode *inode, struct page *page) -{ - return nfs_wb_single_page(inode, page, true); -} - -static inline int -nfs_wb_page(struct inode *inode, struct page *page) -{ - return nfs_wb_single_page(inode, page, false); -} - -static inline int nfs_have_writebacks(struct inode *inode) { return NFS_I(inode)->nrequests != 0; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index b34097c67848..74c44665e6d3 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -42,6 +42,7 @@ struct nfs_client { #define NFS_CS_MIGRATION 2 /* - transparent state migr */ #define NFS_CS_INFINITE_SLOTS 3 /* - don't limit TCP slots */ #define NFS_CS_NO_RETRANS_TIMEOUT 4 /* - Disable retransmit timeouts */ +#define NFS_CS_TSM_POSSIBLE 5 /* - Maybe state migration */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ @@ -133,7 +134,6 @@ struct nfs_server { struct rpc_clnt * client_acl; /* ACL RPC client handle */ struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats __percpu *io_stats; /* I/O statistics */ - struct backing_dev_info backing_dev_info; atomic_long_t writeback; /* number of writeback pages */ int flags; /* various flags */ unsigned int caps; /* server capabilities */ @@ -211,6 +211,7 @@ struct nfs_server { unsigned long mig_status; #define NFS_MIG_IN_TRANSITION (1) #define NFS_MIG_FAILED (2) +#define NFS_MIG_TSM_POSSIBLE (3) void (*destroy)(struct nfs_server *); @@ -222,6 +223,7 @@ struct nfs_server { u32 mountd_version; unsigned short mountd_port; unsigned short mountd_protocol; + struct rpc_wait_queue uoc_rpcwaitq; }; /* Server capabilities */ diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 957049f72290..d67b67ae6c8b 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -33,6 +33,8 @@ enum { PG_UPTODATE, /* page group sync bit in read path */ PG_WB_END, /* page group sync bit in write path */ PG_REMOVE, /* page group sync bit in write path */ + PG_CONTENDED1, /* Is someone waiting for a lock? */ + PG_CONTENDED2, /* Is someone waiting for a lock? */ }; struct nfs_inode; @@ -64,7 +66,6 @@ struct nfs_pageio_ops { }; struct nfs_rw_ops { - const fmode_t rw_mode; struct nfs_pgio_header *(*rw_alloc_header)(void); void (*rw_free_header)(struct nfs_pgio_header *); int (*rw_done)(struct rpc_task *, struct nfs_pgio_header *, @@ -94,8 +95,8 @@ struct nfs_pageio_descriptor { const struct rpc_call_ops *pg_rpc_callops; const struct nfs_pgio_completion_ops *pg_completion_ops; struct pnfs_layout_segment *pg_lseg; + struct nfs_io_completion *pg_io_completion; struct nfs_direct_req *pg_dreq; - void *pg_layout_private; unsigned int pg_bsize; /* default bsize for mirrors */ u32 pg_mirror_count; @@ -124,7 +125,8 @@ extern void nfs_pageio_init(struct nfs_pageio_descriptor *desc, const struct nfs_pgio_completion_ops *compl_ops, const struct nfs_rw_ops *rw_ops, size_t bsize, - int how); + int how, + gfp_t gfp_flags); extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *, struct nfs_page *); extern int nfs_pageio_resend(struct nfs_pageio_descriptor *, @@ -141,6 +143,7 @@ extern int nfs_page_group_lock(struct nfs_page *, bool); extern void nfs_page_group_lock_wait(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); +extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *); /* * Lock the page of an asynchronous request diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 348f7c158084..ca3bcc4ed4e5 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -878,7 +878,7 @@ struct nfs3_readdirargs { struct nfs_fh * fh; __u64 cookie; __be32 verf[2]; - int plus; + bool plus; unsigned int count; struct page ** pages; }; @@ -909,7 +909,7 @@ struct nfs3_linkres { struct nfs3_readdirres { struct nfs_fattr * dir_attr; __be32 * verf; - int plus; + bool plus; }; struct nfs3_getaclres { @@ -1012,7 +1012,6 @@ struct nfs4_link_res { struct nfs_fattr * dir_attr; }; - struct nfs4_lookup_arg { struct nfs4_sequence_args seq_args; const struct nfs_fh * dir_fh; @@ -1028,6 +1027,20 @@ struct nfs4_lookup_res { struct nfs4_label *label; }; +struct nfs4_lookupp_arg { + struct nfs4_sequence_args seq_args; + const struct nfs_fh *fh; + const u32 *bitmask; +}; + +struct nfs4_lookupp_res { + struct nfs4_sequence_res seq_res; + const struct nfs_server *server; + struct nfs_fattr *fattr; + struct nfs_fh *fh; + struct nfs4_label *label; +}; + struct nfs4_lookup_root_arg { struct nfs4_sequence_args seq_args; const u32 * bitmask; @@ -1053,7 +1066,7 @@ struct nfs4_readdir_arg { struct page ** pages; /* zero-copy data */ unsigned int pgbase; /* zero-copy data */ const u32 * bitmask; - int plus; + bool plus; }; struct nfs4_readdir_res { @@ -1383,6 +1396,7 @@ struct nfs42_copy_res { struct nfs42_write_res write_res; bool consecutive; bool synchronous; + struct nfs_commitres commit_res; }; struct nfs42_seek_args { @@ -1421,20 +1435,22 @@ enum { NFS_IOHDR_STAT, }; +struct nfs_io_completion; struct nfs_pgio_header { struct inode *inode; struct rpc_cred *cred; struct list_head pages; struct nfs_page *req; struct nfs_writeverf verf; /* Used for writes */ + fmode_t rw_mode; struct pnfs_layout_segment *lseg; loff_t io_start; const struct rpc_call_ops *mds_ops; void (*release) (struct nfs_pgio_header *hdr); const struct nfs_pgio_completion_ops *completion_ops; const struct nfs_rw_ops *rw_ops; + struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; - void *layout_private; spinlock_t lock; /* fields protected by lock */ int pnfs_error; @@ -1531,6 +1547,7 @@ struct nfs_renamedata { struct nfs_fattr new_fattr; void (*complete)(struct rpc_task *, struct nfs_renamedata *); long timeout; + bool cancelled; }; struct nfs_access_entry; @@ -1550,6 +1567,7 @@ struct nfs_rpc_ops { const struct inode_operations *dir_inode_ops; const struct inode_operations *file_inode_ops; const struct file_operations *file_ops; + const struct nlmclnt_operations *nlmclnt_ops; int (*getroot) (struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); @@ -1564,6 +1582,8 @@ struct nfs_rpc_ops { int (*lookup) (struct inode *, const struct qstr *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); + int (*lookupp) (struct inode *, struct nfs_fh *, + struct nfs_fattr *, struct nfs4_label *); int (*access) (struct inode *, struct nfs_access_entry *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); @@ -1582,7 +1602,7 @@ struct nfs_rpc_ops { int (*mkdir) (struct inode *, struct dentry *, struct iattr *); int (*rmdir) (struct inode *, const struct qstr *); int (*readdir) (struct dentry *, struct rpc_cred *, - u64, struct page **, unsigned int, int); + u64, struct page **, unsigned int, bool); int (*mknod) (struct inode *, struct dentry *, struct iattr *, dev_t); int (*statfs) (struct nfs_server *, struct nfs_fh *, @@ -1592,7 +1612,7 @@ struct nfs_rpc_ops { int (*pathconf) (struct nfs_server *, struct nfs_fh *, struct nfs_pathconf *); int (*set_capabilities)(struct nfs_server *, struct nfs_fh *); - int (*decode_dirent)(struct xdr_stream *, struct nfs_entry *, int); + int (*decode_dirent)(struct xdr_stream *, struct nfs_entry *, bool); int (*pgio_rpc_prepare)(struct rpc_task *, struct nfs_pgio_header *); void (*read_setup)(struct nfs_pgio_header *, struct rpc_message *); diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 0a3fadc32693..8aa01fd859fb 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -6,6 +6,48 @@ #include <linux/sched.h> #include <asm/irq.h> +#if defined(CONFIG_HAVE_NMI_WATCHDOG) +#include <asm/nmi.h> +#endif + +#ifdef CONFIG_LOCKUP_DETECTOR +void lockup_detector_init(void); +#else +static inline void lockup_detector_init(void) +{ +} +#endif + +#ifdef CONFIG_SOFTLOCKUP_DETECTOR +extern void touch_softlockup_watchdog_sched(void); +extern void touch_softlockup_watchdog(void); +extern void touch_softlockup_watchdog_sync(void); +extern void touch_all_softlockup_watchdogs(void); +extern unsigned int softlockup_panic; +extern int soft_watchdog_enabled; +extern atomic_t watchdog_park_in_progress; +#else +static inline void touch_softlockup_watchdog_sched(void) +{ +} +static inline void touch_softlockup_watchdog(void) +{ +} +static inline void touch_softlockup_watchdog_sync(void) +{ +} +static inline void touch_all_softlockup_watchdogs(void) +{ +} +#endif + +#ifdef CONFIG_DETECT_HUNG_TASK +void reset_hung_task_detector(void); +#else +static inline void reset_hung_task_detector(void) +{ +} +#endif /* * The run state of the lockup detectors is controlled by the content of the @@ -24,6 +66,21 @@ #define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT) #define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT) +#if defined(CONFIG_HARDLOCKUP_DETECTOR) +extern void hardlockup_detector_disable(void); +extern unsigned int hardlockup_panic; +#else +static inline void hardlockup_detector_disable(void) {} +#endif + +#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) +extern void arch_touch_nmi_watchdog(void); +#else +#if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline void arch_touch_nmi_watchdog(void) {} +#endif +#endif + /** * touch_nmi_watchdog - restart NMI watchdog timeout. * @@ -31,21 +88,11 @@ * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. */ -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) -#include <asm/nmi.h> -extern void touch_nmi_watchdog(void); -#else static inline void touch_nmi_watchdog(void) { + arch_touch_nmi_watchdog(); touch_softlockup_watchdog(); } -#endif - -#if defined(CONFIG_HARDLOCKUP_DETECTOR) -extern void hardlockup_detector_disable(void); -#else -static inline void hardlockup_detector_disable(void) {} -#endif /* * Create trigger_all_cpu_backtrace() out of the arch-provided @@ -102,15 +149,18 @@ static inline bool trigger_single_cpu_backtrace(int cpu) } #endif -#ifdef CONFIG_LOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF u64 hw_nmi_get_sample_period(int watchdog_thresh); +#endif + +#ifdef CONFIG_LOCKUP_DETECTOR extern int nmi_watchdog_enabled; -extern int soft_watchdog_enabled; extern int watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; +extern struct cpumask watchdog_cpumask; extern unsigned long *watchdog_cpumask_bits; -extern atomic_t watchdog_park_in_progress; +extern int __read_mostly watchdog_suspended; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; diff --git a/include/linux/node.h b/include/linux/node.h index 2115ad5d6f19..d1751beb462c 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -30,9 +30,38 @@ struct memory_block; extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); +#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) +extern int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages); +#else +static inline int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages) +{ + return 0; +} +#endif + extern void unregister_node(struct node *node); #ifdef CONFIG_NUMA -extern int register_one_node(int nid); +/* Core of the node registration - only memory hotplug should use this */ +extern int __register_one_node(int nid); + +/* Registers an online node */ +static inline int register_one_node(int nid) +{ + int error = 0; + + if (node_online(nid)) { + struct pglist_data *pgdat = NODE_DATA(nid); + + error = __register_one_node(nid); + if (error) + return error; + /* link memory sections under this node */ + error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages); + } + + return error; +} + extern void unregister_one_node(int nid); extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); @@ -46,6 +75,10 @@ extern void register_hugetlbfs_with_node(node_registration_func_t doregister, node_registration_func_t unregister); #endif #else +static inline int __register_one_node(int nid) +{ + return 0; +} static inline int register_one_node(int nid) { return 0; diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index f746e44d4046..cf0b91c3ec12 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -387,11 +387,7 @@ enum node_states { #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif -#ifdef CONFIG_MOVABLE_NODE N_MEMORY, /* The node has memory(regular, high, movable) */ -#else - N_MEMORY = N_HIGH_MEMORY, -#endif N_CPU, /* The node has one or more cpus */ NR_NODE_STATES }; diff --git a/include/linux/ntb.h b/include/linux/ntb.h index de87ceac110e..609e232c00da 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -5,6 +5,7 @@ * GPL LICENSE SUMMARY * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -18,6 +19,7 @@ * BSD LICENSE * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -106,6 +108,7 @@ static inline char *ntb_topo_string(enum ntb_topo topo) * @NTB_SPEED_GEN1: Link is trained to gen1 speed. * @NTB_SPEED_GEN2: Link is trained to gen2 speed. * @NTB_SPEED_GEN3: Link is trained to gen3 speed. + * @NTB_SPEED_GEN4: Link is trained to gen4 speed. */ enum ntb_speed { NTB_SPEED_AUTO = -1, @@ -113,6 +116,7 @@ enum ntb_speed { NTB_SPEED_GEN1 = 1, NTB_SPEED_GEN2 = 2, NTB_SPEED_GEN3 = 3, + NTB_SPEED_GEN4 = 4 }; /** @@ -140,6 +144,20 @@ enum ntb_width { }; /** + * enum ntb_default_port - NTB default port number + * @NTB_PORT_PRI_USD: Default port of the NTB_TOPO_PRI/NTB_TOPO_B2B_USD + * topologies + * @NTB_PORT_SEC_DSD: Default port of the NTB_TOPO_SEC/NTB_TOPO_B2B_DSD + * topologies + */ +enum ntb_default_port { + NTB_PORT_PRI_USD, + NTB_PORT_SEC_DSD +}; +#define NTB_DEF_PEER_CNT (1) +#define NTB_DEF_PEER_IDX (0) + +/** * struct ntb_client_ops - ntb client operations * @probe: Notify client of a new device. * @remove: Notify client to remove a device. @@ -162,10 +180,12 @@ static inline int ntb_client_ops_is_valid(const struct ntb_client_ops *ops) * struct ntb_ctx_ops - ntb driver context operations * @link_event: See ntb_link_event(). * @db_event: See ntb_db_event(). + * @msg_event: See ntb_msg_event(). */ struct ntb_ctx_ops { void (*link_event)(void *ctx); void (*db_event)(void *ctx, int db_vector); + void (*msg_event)(void *ctx); }; static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) @@ -174,18 +194,27 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) return /* ops->link_event && */ /* ops->db_event && */ + /* ops->msg_event && */ 1; } /** * struct ntb_ctx_ops - ntb device operations - * @mw_count: See ntb_mw_count(). - * @mw_get_range: See ntb_mw_get_range(). - * @mw_set_trans: See ntb_mw_set_trans(). - * @mw_clear_trans: See ntb_mw_clear_trans(). + * @port_number: See ntb_port_number(). + * @peer_port_count: See ntb_peer_port_count(). + * @peer_port_number: See ntb_peer_port_number(). + * @peer_port_idx: See ntb_peer_port_idx(). * @link_is_up: See ntb_link_is_up(). * @link_enable: See ntb_link_enable(). * @link_disable: See ntb_link_disable(). + * @mw_count: See ntb_mw_count(). + * @mw_get_align: See ntb_mw_get_align(). + * @mw_set_trans: See ntb_mw_set_trans(). + * @mw_clear_trans: See ntb_mw_clear_trans(). + * @peer_mw_count: See ntb_peer_mw_count(). + * @peer_mw_get_addr: See ntb_peer_mw_get_addr(). + * @peer_mw_set_trans: See ntb_peer_mw_set_trans(). + * @peer_mw_clear_trans:See ntb_peer_mw_clear_trans(). * @db_is_unsafe: See ntb_db_is_unsafe(). * @db_valid_mask: See ntb_db_valid_mask(). * @db_vector_count: See ntb_db_vector_count(). @@ -210,22 +239,43 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) * @peer_spad_addr: See ntb_peer_spad_addr(). * @peer_spad_read: See ntb_peer_spad_read(). * @peer_spad_write: See ntb_peer_spad_write(). + * @msg_count: See ntb_msg_count(). + * @msg_inbits: See ntb_msg_inbits(). + * @msg_outbits: See ntb_msg_outbits(). + * @msg_read_sts: See ntb_msg_read_sts(). + * @msg_clear_sts: See ntb_msg_clear_sts(). + * @msg_set_mask: See ntb_msg_set_mask(). + * @msg_clear_mask: See ntb_msg_clear_mask(). + * @msg_read: See ntb_msg_read(). + * @msg_write: See ntb_msg_write(). */ struct ntb_dev_ops { - int (*mw_count)(struct ntb_dev *ntb); - int (*mw_get_range)(struct ntb_dev *ntb, int idx, - phys_addr_t *base, resource_size_t *size, - resource_size_t *align, resource_size_t *align_size); - int (*mw_set_trans)(struct ntb_dev *ntb, int idx, - dma_addr_t addr, resource_size_t size); - int (*mw_clear_trans)(struct ntb_dev *ntb, int idx); + int (*port_number)(struct ntb_dev *ntb); + int (*peer_port_count)(struct ntb_dev *ntb); + int (*peer_port_number)(struct ntb_dev *ntb, int pidx); + int (*peer_port_idx)(struct ntb_dev *ntb, int port); - int (*link_is_up)(struct ntb_dev *ntb, + u64 (*link_is_up)(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width); int (*link_enable)(struct ntb_dev *ntb, enum ntb_speed max_speed, enum ntb_width max_width); int (*link_disable)(struct ntb_dev *ntb); + int (*mw_count)(struct ntb_dev *ntb, int pidx); + int (*mw_get_align)(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max); + int (*mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx, + dma_addr_t addr, resource_size_t size); + int (*mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx); + int (*peer_mw_count)(struct ntb_dev *ntb); + int (*peer_mw_get_addr)(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size); + int (*peer_mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size); + int (*peer_mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx); + int (*db_is_unsafe)(struct ntb_dev *ntb); u64 (*db_valid_mask)(struct ntb_dev *ntb); int (*db_vector_count)(struct ntb_dev *ntb); @@ -252,32 +302,55 @@ struct ntb_dev_ops { int (*spad_is_unsafe)(struct ntb_dev *ntb); int (*spad_count)(struct ntb_dev *ntb); - u32 (*spad_read)(struct ntb_dev *ntb, int idx); - int (*spad_write)(struct ntb_dev *ntb, int idx, u32 val); + u32 (*spad_read)(struct ntb_dev *ntb, int sidx); + int (*spad_write)(struct ntb_dev *ntb, int sidx, u32 val); - int (*peer_spad_addr)(struct ntb_dev *ntb, int idx, + int (*peer_spad_addr)(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr); - u32 (*peer_spad_read)(struct ntb_dev *ntb, int idx); - int (*peer_spad_write)(struct ntb_dev *ntb, int idx, u32 val); + u32 (*peer_spad_read)(struct ntb_dev *ntb, int pidx, int sidx); + int (*peer_spad_write)(struct ntb_dev *ntb, int pidx, int sidx, + u32 val); + + int (*msg_count)(struct ntb_dev *ntb); + u64 (*msg_inbits)(struct ntb_dev *ntb); + u64 (*msg_outbits)(struct ntb_dev *ntb); + u64 (*msg_read_sts)(struct ntb_dev *ntb); + int (*msg_clear_sts)(struct ntb_dev *ntb, u64 sts_bits); + int (*msg_set_mask)(struct ntb_dev *ntb, u64 mask_bits); + int (*msg_clear_mask)(struct ntb_dev *ntb, u64 mask_bits); + int (*msg_read)(struct ntb_dev *ntb, int midx, int *pidx, u32 *msg); + int (*msg_write)(struct ntb_dev *ntb, int midx, int pidx, u32 msg); }; static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) { /* commented callbacks are not required: */ return - ops->mw_count && - ops->mw_get_range && - ops->mw_set_trans && - /* ops->mw_clear_trans && */ + /* Port operations are required for multiport devices */ + !ops->peer_port_count == !ops->port_number && + !ops->peer_port_number == !ops->port_number && + !ops->peer_port_idx == !ops->port_number && + + /* Link operations are required */ ops->link_is_up && ops->link_enable && ops->link_disable && + + /* One or both MW interfaces should be developed */ + ops->mw_count && + ops->mw_get_align && + (ops->mw_set_trans || + ops->peer_mw_set_trans) && + /* ops->mw_clear_trans && */ + ops->peer_mw_count && + ops->peer_mw_get_addr && + /* ops->peer_mw_clear_trans && */ + + /* Doorbell operations are mostly required */ /* ops->db_is_unsafe && */ ops->db_valid_mask && - /* both set, or both unset */ - (!ops->db_vector_count == !ops->db_vector_mask) && - + (!ops->db_vector_count == !ops->db_vector_mask) && ops->db_read && /* ops->db_set && */ ops->db_clear && @@ -291,13 +364,24 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) /* ops->peer_db_read_mask && */ /* ops->peer_db_set_mask && */ /* ops->peer_db_clear_mask && */ - /* ops->spad_is_unsafe && */ - ops->spad_count && - ops->spad_read && - ops->spad_write && - /* ops->peer_spad_addr && */ - /* ops->peer_spad_read && */ - ops->peer_spad_write && + + /* Scrachpads interface is optional */ + /* !ops->spad_is_unsafe == !ops->spad_count && */ + !ops->spad_read == !ops->spad_count && + !ops->spad_write == !ops->spad_count && + /* !ops->peer_spad_addr == !ops->spad_count && */ + /* !ops->peer_spad_read == !ops->spad_count && */ + !ops->peer_spad_write == !ops->spad_count && + + /* Messaging interface is optional */ + !ops->msg_inbits == !ops->msg_count && + !ops->msg_outbits == !ops->msg_count && + !ops->msg_read_sts == !ops->msg_count && + !ops->msg_clear_sts == !ops->msg_count && + /* !ops->msg_set_mask == !ops->msg_count && */ + /* !ops->msg_clear_mask == !ops->msg_count && */ + !ops->msg_read == !ops->msg_count && + !ops->msg_write == !ops->msg_count && 1; } @@ -310,13 +394,12 @@ struct ntb_client { struct device_driver drv; const struct ntb_client_ops ops; }; - #define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv) /** * struct ntb_device - ntb device * @dev: Linux device object. - * @pdev: Pci device entry of the ntb. + * @pdev: PCI device entry of the ntb. * @topo: Detected topology of the ntb. * @ops: See &ntb_dev_ops. * @ctx: See &ntb_ctx_ops. @@ -337,7 +420,6 @@ struct ntb_dev { /* block unregister until device is fully released */ struct completion released; }; - #define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev) /** @@ -434,86 +516,152 @@ void ntb_link_event(struct ntb_dev *ntb); * multiple interrupt vectors for doorbells, the vector number indicates which * vector received the interrupt. The vector number is relative to the first * vector used for doorbells, starting at zero, and must be less than - ** ntb_db_vector_count(). The driver may call ntb_db_read() to check which + * ntb_db_vector_count(). The driver may call ntb_db_read() to check which * doorbell bits need service, and ntb_db_vector_mask() to determine which of * those bits are associated with the vector number. */ void ntb_db_event(struct ntb_dev *ntb, int vector); /** - * ntb_mw_count() - get the number of memory windows + * ntb_msg_event() - notify driver context of a message event * @ntb: NTB device context. * - * Hardware and topology may support a different number of memory windows. + * Notify the driver context of a message event. If hardware supports + * message registers, this event indicates, that a new message arrived in + * some incoming message register or last sent message couldn't be delivered. + * The events can be masked/unmasked by the methods ntb_msg_set_mask() and + * ntb_msg_clear_mask(). + */ +void ntb_msg_event(struct ntb_dev *ntb); + +/** + * ntb_default_port_number() - get the default local port number + * @ntb: NTB device context. * - * Return: the number of memory windows. + * If hardware driver doesn't specify port_number() callback method, the NTB + * is considered with just two ports. So this method returns default local + * port number in compliance with topology. + * + * NOTE Don't call this method directly. The ntb_port_number() function should + * be used instead. + * + * Return: the default local port number + */ +int ntb_default_port_number(struct ntb_dev *ntb); + +/** + * ntb_default_port_count() - get the default number of peer device ports + * @ntb: NTB device context. + * + * By default hardware driver supports just one peer device. + * + * NOTE Don't call this method directly. The ntb_peer_port_count() function + * should be used instead. + * + * Return: the default number of peer ports + */ +int ntb_default_peer_port_count(struct ntb_dev *ntb); + +/** + * ntb_default_peer_port_number() - get the default peer port by given index + * @ntb: NTB device context. + * @idx: Peer port index (should not differ from zero). + * + * By default hardware driver supports just one peer device, so this method + * shall return the corresponding value from enum ntb_default_port. + * + * NOTE Don't call this method directly. The ntb_peer_port_number() function + * should be used instead. + * + * Return: the peer device port or negative value indicating an error + */ +int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx); + +/** + * ntb_default_peer_port_idx() - get the default peer device port index by + * given port number + * @ntb: NTB device context. + * @port: Peer port number (should be one of enum ntb_default_port). + * + * By default hardware driver supports just one peer device, so while + * specified port-argument indicates peer port from enum ntb_default_port, + * the return value shall be zero. + * + * NOTE Don't call this method directly. The ntb_peer_port_idx() function + * should be used instead. + * + * Return: the peer port index or negative value indicating an error + */ +int ntb_default_peer_port_idx(struct ntb_dev *ntb, int port); + +/** + * ntb_port_number() - get the local port number + * @ntb: NTB device context. + * + * Hardware must support at least simple two-ports ntb connection + * + * Return: the local port number */ -static inline int ntb_mw_count(struct ntb_dev *ntb) +static inline int ntb_port_number(struct ntb_dev *ntb) { - return ntb->ops->mw_count(ntb); + if (!ntb->ops->port_number) + return ntb_default_port_number(ntb); + + return ntb->ops->port_number(ntb); } /** - * ntb_mw_get_range() - get the range of a memory window + * ntb_peer_port_count() - get the number of peer device ports * @ntb: NTB device context. - * @idx: Memory window number. - * @base: OUT - the base address for mapping the memory window - * @size: OUT - the size for mapping the memory window - * @align: OUT - the base alignment for translating the memory window - * @align_size: OUT - the size alignment for translating the memory window * - * Get the range of a memory window. NULL may be given for any output - * parameter if the value is not needed. The base and size may be used for - * mapping the memory window, to access the peer memory. The alignment and - * size may be used for translating the memory window, for the peer to access - * memory on the local system. + * Hardware may support an access to memory of several remote domains + * over multi-port NTB devices. This method returns the number of peers, + * local device can have shared memory with. * - * Return: Zero on success, otherwise an error number. + * Return: the number of peer ports */ -static inline int ntb_mw_get_range(struct ntb_dev *ntb, int idx, - phys_addr_t *base, resource_size_t *size, - resource_size_t *align, resource_size_t *align_size) +static inline int ntb_peer_port_count(struct ntb_dev *ntb) { - return ntb->ops->mw_get_range(ntb, idx, base, size, - align, align_size); + if (!ntb->ops->peer_port_count) + return ntb_default_peer_port_count(ntb); + + return ntb->ops->peer_port_count(ntb); } /** - * ntb_mw_set_trans() - set the translation of a memory window + * ntb_peer_port_number() - get the peer port by given index * @ntb: NTB device context. - * @idx: Memory window number. - * @addr: The dma address local memory to expose to the peer. - * @size: The size of the local memory to expose to the peer. + * @pidx: Peer port index. * - * Set the translation of a memory window. The peer may access local memory - * through the window starting at the address, up to the size. The address - * must be aligned to the alignment specified by ntb_mw_get_range(). The size - * must be aligned to the size alignment specified by ntb_mw_get_range(). + * Peer ports are continuously enumerated by NTB API logic, so this method + * lets to retrieve port real number by its index. * - * Return: Zero on success, otherwise an error number. + * Return: the peer device port or negative value indicating an error */ -static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int idx, - dma_addr_t addr, resource_size_t size) +static inline int ntb_peer_port_number(struct ntb_dev *ntb, int pidx) { - return ntb->ops->mw_set_trans(ntb, idx, addr, size); + if (!ntb->ops->peer_port_number) + return ntb_default_peer_port_number(ntb, pidx); + + return ntb->ops->peer_port_number(ntb, pidx); } /** - * ntb_mw_clear_trans() - clear the translation of a memory window + * ntb_peer_port_idx() - get the peer device port index by given port number * @ntb: NTB device context. - * @idx: Memory window number. + * @port: Peer port number. * - * Clear the translation of a memory window. The peer may no longer access - * local memory through the window. + * Inverse operation of ntb_peer_port_number(), so one can get port index + * by specified port number. * - * Return: Zero on success, otherwise an error number. + * Return: the peer port index or negative value indicating an error */ -static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) +static inline int ntb_peer_port_idx(struct ntb_dev *ntb, int port) { - if (!ntb->ops->mw_clear_trans) - return ntb->ops->mw_set_trans(ntb, idx, 0, 0); + if (!ntb->ops->peer_port_idx) + return ntb_default_peer_port_idx(ntb, port); - return ntb->ops->mw_clear_trans(ntb, idx); + return ntb->ops->peer_port_idx(ntb, port); } /** @@ -526,25 +674,26 @@ static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) * state once after every link event. It is safe to query the link state in * the context of the link event callback. * - * Return: One if the link is up, zero if the link is down, otherwise a - * negative value indicating the error number. + * Return: bitfield of indexed ports link state: bit is set/cleared if the + * link is up/down respectively. */ -static inline int ntb_link_is_up(struct ntb_dev *ntb, +static inline u64 ntb_link_is_up(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width) { return ntb->ops->link_is_up(ntb, speed, width); } /** - * ntb_link_enable() - enable the link on the secondary side of the ntb + * ntb_link_enable() - enable the local port ntb connection * @ntb: NTB device context. * @max_speed: The maximum link speed expressed as PCIe generation number. * @max_width: The maximum link width expressed as the number of PCIe lanes. * - * Enable the link on the secondary side of the ntb. This can only be done - * from the primary side of the ntb in primary or b2b topology. The ntb device - * should train the link to its maximum speed and width, or the requested speed - * and width, whichever is smaller, if supported. + * Enable the NTB/PCIe link on the local or remote (for bridge-to-bridge + * topology) side of the bridge. If it's supported the ntb device should train + * the link to its maximum speed and width, or the requested speed and width, + * whichever is smaller. Some hardware doesn't support PCIe link training, so + * the last two arguments will be ignored then. * * Return: Zero on success, otherwise an error number. */ @@ -556,14 +705,14 @@ static inline int ntb_link_enable(struct ntb_dev *ntb, } /** - * ntb_link_disable() - disable the link on the secondary side of the ntb + * ntb_link_disable() - disable the local port ntb connection * @ntb: NTB device context. * - * Disable the link on the secondary side of the ntb. This can only be - * done from the primary side of the ntb in primary or b2b topology. The ntb - * device should disable the link. Returning from this call must indicate that - * a barrier has passed, though with no more writes may pass in either - * direction across the link, except if this call returns an error number. + * Disable the link on the local or remote (for b2b topology) of the ntb. + * The ntb device should disable the link. Returning from this call must + * indicate that a barrier has passed, though with no more writes may pass in + * either direction across the link, except if this call returns an error + * number. * * Return: Zero on success, otherwise an error number. */ @@ -573,6 +722,183 @@ static inline int ntb_link_disable(struct ntb_dev *ntb) } /** + * ntb_mw_count() - get the number of inbound memory windows, which could + * be created for a specified peer device + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * + * Hardware and topology may support a different number of memory windows. + * Moreover different peer devices can support different number of memory + * windows. Simply speaking this method returns the number of possible inbound + * memory windows to share with specified peer device. + * + * Return: the number of memory windows. + */ +static inline int ntb_mw_count(struct ntb_dev *ntb, int pidx) +{ + return ntb->ops->mw_count(ntb, pidx); +} + +/** + * ntb_mw_get_align() - get the restriction parameters of inbound memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr_align: OUT - the base alignment for translating the memory window + * @size_align: OUT - the size alignment for translating the memory window + * @size_max: OUT - the maximum size of the memory window + * + * Get the alignments of an inbound memory window with specified index. + * NULL may be given for any output parameter if the value is not needed. + * The alignment and size parameters may be used for allocation of proper + * shared memory. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) +{ + return ntb->ops->mw_get_align(ntb, pidx, widx, addr_align, size_align, + size_max); +} + +/** + * ntb_mw_set_trans() - set the translation of an inbound memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr: The dma address of local memory to expose to the peer. + * @size: The size of the local memory to expose to the peer. + * + * Set the translation of a memory window. The peer may access local memory + * through the window starting at the address, up to the size. The address + * and size must be aligned in compliance with restrictions of + * ntb_mw_get_align(). The region size should not exceed the size_max parameter + * of that method. + * + * This method may not be implemented due to the hardware specific memory + * windows interface. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + dma_addr_t addr, resource_size_t size) +{ + if (!ntb->ops->mw_set_trans) + return 0; + + return ntb->ops->mw_set_trans(ntb, pidx, widx, addr, size); +} + +/** + * ntb_mw_clear_trans() - clear the translation address of an inbound memory + * window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * Clear the translation of an inbound memory window. The peer may no longer + * access local memory through the window. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int pidx, int widx) +{ + if (!ntb->ops->mw_clear_trans) + return ntb_mw_set_trans(ntb, pidx, widx, 0, 0); + + return ntb->ops->mw_clear_trans(ntb, pidx, widx); +} + +/** + * ntb_peer_mw_count() - get the number of outbound memory windows, which could + * be mapped to access a shared memory + * @ntb: NTB device context. + * + * Hardware and topology may support a different number of memory windows. + * This method returns the number of outbound memory windows supported by + * local device. + * + * Return: the number of memory windows. + */ +static inline int ntb_peer_mw_count(struct ntb_dev *ntb) +{ + return ntb->ops->peer_mw_count(ntb); +} + +/** + * ntb_peer_mw_get_addr() - get map address of an outbound memory window + * @ntb: NTB device context. + * @widx: Memory window index (within ntb_peer_mw_count() return value). + * @base: OUT - the base address of mapping region. + * @size: OUT - the size of mapping region. + * + * Get base and size of memory region to map. NULL may be given for any output + * parameter if the value is not needed. The base and size may be used for + * mapping the memory window, to access the peer memory. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_peer_mw_get_addr(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size) +{ + return ntb->ops->peer_mw_get_addr(ntb, widx, base, size); +} + +/** + * ntb_peer_mw_set_trans() - set a translation address of a memory window + * retrieved from a peer device + * @ntb: NTB device context. + * @pidx: Port index of peer device the translation address received from. + * @widx: Memory window index. + * @addr: The dma address of the shared memory to access. + * @size: The size of the shared memory to access. + * + * Set the translation of an outbound memory window. The local device may + * access shared memory allocated by a peer device sent the address. + * + * This method may not be implemented due to the hardware specific memory + * windows interface, so a translation address can be only set on the side, + * where shared memory (inbound memory windows) is allocated. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size) +{ + if (!ntb->ops->peer_mw_set_trans) + return 0; + + return ntb->ops->peer_mw_set_trans(ntb, pidx, widx, addr, size); +} + +/** + * ntb_peer_mw_clear_trans() - clear the translation address of an outbound + * memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * Clear the translation of a outbound memory window. The local device may no + * longer access a shared memory through the window. + * + * This method may not be implemented due to the hardware specific memory + * windows interface. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx, + int widx) +{ + if (!ntb->ops->peer_mw_clear_trans) + return ntb_peer_mw_set_trans(ntb, pidx, widx, 0, 0); + + return ntb->ops->peer_mw_clear_trans(ntb, pidx, widx); +} + +/** * ntb_db_is_unsafe() - check if it is safe to use hardware doorbell * @ntb: NTB device context. * @@ -900,47 +1226,58 @@ static inline int ntb_spad_is_unsafe(struct ntb_dev *ntb) * @ntb: NTB device context. * * Hardware and topology may support a different number of scratchpads. + * Although it must be the same for all ports per NTB device. * * Return: the number of scratchpads. */ static inline int ntb_spad_count(struct ntb_dev *ntb) { + if (!ntb->ops->spad_count) + return 0; + return ntb->ops->spad_count(ntb); } /** * ntb_spad_read() - read the local scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @sidx: Scratchpad index. * * Read the local scratchpad register, and return the value. * * Return: The value of the local scratchpad register. */ -static inline u32 ntb_spad_read(struct ntb_dev *ntb, int idx) +static inline u32 ntb_spad_read(struct ntb_dev *ntb, int sidx) { - return ntb->ops->spad_read(ntb, idx); + if (!ntb->ops->spad_read) + return ~(u32)0; + + return ntb->ops->spad_read(ntb, sidx); } /** * ntb_spad_write() - write the local scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @sidx: Scratchpad index. * @val: Scratchpad value. * * Write the value to the local scratchpad register. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) +static inline int ntb_spad_write(struct ntb_dev *ntb, int sidx, u32 val) { - return ntb->ops->spad_write(ntb, idx, val); + if (!ntb->ops->spad_write) + return -EINVAL; + + return ntb->ops->spad_write(ntb, sidx, val); } /** * ntb_peer_spad_addr() - address of the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * @spad_addr: OUT - The address of the peer scratchpad register. * * Return the address of the peer doorbell register. This may be used, for @@ -948,45 +1285,213 @@ static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, +static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr) { if (!ntb->ops->peer_spad_addr) return -EINVAL; - return ntb->ops->peer_spad_addr(ntb, idx, spad_addr); + return ntb->ops->peer_spad_addr(ntb, pidx, sidx, spad_addr); } /** * ntb_peer_spad_read() - read the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * * Read the peer scratchpad register, and return the value. * * Return: The value of the local scratchpad register. */ -static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { if (!ntb->ops->peer_spad_read) - return 0; + return ~(u32)0; - return ntb->ops->peer_spad_read(ntb, idx); + return ntb->ops->peer_spad_read(ntb, pidx, sidx); } /** * ntb_peer_spad_write() - write the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * @val: Scratchpad value. * * Write the value to the peer scratchpad register. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int idx, u32 val) +static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, int sidx, + u32 val) +{ + if (!ntb->ops->peer_spad_write) + return -EINVAL; + + return ntb->ops->peer_spad_write(ntb, pidx, sidx, val); +} + +/** + * ntb_msg_count() - get the number of message registers + * @ntb: NTB device context. + * + * Hardware may support a different number of message registers. + * + * Return: the number of message registers. + */ +static inline int ntb_msg_count(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_count) + return 0; + + return ntb->ops->msg_count(ntb); +} + +/** + * ntb_msg_inbits() - get a bitfield of inbound message registers status + * @ntb: NTB device context. + * + * The method returns the bitfield of status and mask registers, which related + * to inbound message registers. + * + * Return: bitfield of inbound message registers. + */ +static inline u64 ntb_msg_inbits(struct ntb_dev *ntb) { - return ntb->ops->peer_spad_write(ntb, idx, val); + if (!ntb->ops->msg_inbits) + return 0; + + return ntb->ops->msg_inbits(ntb); +} + +/** + * ntb_msg_outbits() - get a bitfield of outbound message registers status + * @ntb: NTB device context. + * + * The method returns the bitfield of status and mask registers, which related + * to outbound message registers. + * + * Return: bitfield of outbound message registers. + */ +static inline u64 ntb_msg_outbits(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_outbits) + return 0; + + return ntb->ops->msg_outbits(ntb); +} + +/** + * ntb_msg_read_sts() - read the message registers status + * @ntb: NTB device context. + * + * Read the status of message register. Inbound and outbound message registers + * related bits can be filtered by masks retrieved from ntb_msg_inbits() and + * ntb_msg_outbits(). + * + * Return: status bits of message registers + */ +static inline u64 ntb_msg_read_sts(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_read_sts) + return 0; + + return ntb->ops->msg_read_sts(ntb); +} + +/** + * ntb_msg_clear_sts() - clear status bits of message registers + * @ntb: NTB device context. + * @sts_bits: Status bits to clear. + * + * Clear bits in the status register. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_clear_sts(struct ntb_dev *ntb, u64 sts_bits) +{ + if (!ntb->ops->msg_clear_sts) + return -EINVAL; + + return ntb->ops->msg_clear_sts(ntb, sts_bits); +} + +/** + * ntb_msg_set_mask() - set mask of message register status bits + * @ntb: NTB device context. + * @mask_bits: Mask bits. + * + * Mask the message registers status bits from raising the message event. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_set_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + if (!ntb->ops->msg_set_mask) + return -EINVAL; + + return ntb->ops->msg_set_mask(ntb, mask_bits); +} + +/** + * ntb_msg_clear_mask() - clear message registers mask + * @ntb: NTB device context. + * @mask_bits: Mask bits to clear. + * + * Clear bits in the message events mask register. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_clear_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + if (!ntb->ops->msg_clear_mask) + return -EINVAL; + + return ntb->ops->msg_clear_mask(ntb, mask_bits); +} + +/** + * ntb_msg_read() - read message register with specified index + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: OUT - Port index of peer device a message retrieved from + * @msg: OUT - Data + * + * Read data from the specified message register. Source port index of a + * message is retrieved as well. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_read(struct ntb_dev *ntb, int midx, int *pidx, + u32 *msg) +{ + if (!ntb->ops->msg_read) + return -EINVAL; + + return ntb->ops->msg_read(ntb, midx, pidx, msg); +} + +/** + * ntb_msg_write() - write data to the specified message register + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: Port index of peer device a message being sent to + * @msg: Data to send + * + * Send data to a specified peer device using the defined message register. + * Message event can be raised if the midx registers isn't empty while + * calling this method and the corresponding interrupt isn't masked. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_write(struct ntb_dev *ntb, int midx, int pidx, + u32 msg) +{ + if (!ntb->ops->msg_write) + return -EINVAL; + + return ntb->ops->msg_write(ntb, midx, pidx, msg); } #endif diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index f21471f7ee40..6c8c5d8041b7 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -27,8 +27,8 @@ /* FC Port role bitmask - can merge with FC Port Roles in fc transport */ #define FC_PORT_ROLE_NVME_INITIATOR 0x10 -#define FC_PORT_ROLE_NVME_TARGET 0x11 -#define FC_PORT_ROLE_NVME_DISCOVERY 0x12 +#define FC_PORT_ROLE_NVME_TARGET 0x20 +#define FC_PORT_ROLE_NVME_DISCOVERY 0x40 /** @@ -137,9 +137,9 @@ enum nvmefc_fcp_datadir { * transferred. Should equal payload_length on success. * @rcv_rsplen: length, in bytes, of the FCP RSP IU received. * @status: Completion status of the FCP operation. must be 0 upon success, - * NVME_SC_FC_xxx value upon failure. Note: this is NOT a - * reflection of the NVME CQE completion status. Only the status - * of the FCP operation at the NVME-FC level. + * negative errno value upon failure (ex: -EIO). Note: this is + * NOT a reflection of the NVME CQE completion status. Only the + * status of the FCP operation at the NVME-FC level. */ struct nvmefc_fcp_req { void *cmdaddr; @@ -533,9 +533,6 @@ enum { * rsp as well */ NVMET_FCOP_RSP = 4, /* send rsp frame */ - NVMET_FCOP_ABORT = 5, /* abort exchange via ABTS */ - NVMET_FCOP_BA_ACC = 6, /* send BA_ACC */ - NVMET_FCOP_BA_RJT = 7, /* send BA_RJT */ }; /** @@ -572,8 +569,6 @@ enum { * upon compeletion of the operation. The nvmet-fc layer will also set a * private pointer for its own use in the done routine. * - * Note: the LLDD must never fail a NVMET_FCOP_ABORT request !! - * * Values set by the NVMET-FC layer prior to calling the LLDD fcp_op * entrypoint. * @op: Indicates the FCP IU operation to perform (see NVMET_FCOP_xxx) @@ -647,13 +642,21 @@ enum { * sequence in one LLDD operation. Errors during Data * sequence transmit must not allow RSP sequence to be sent. */ - NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED = (1 << 1), - /* Bit 1: When 0, the LLDD will deliver FCP CMD - * on the CPU it should be affinitized to. Thus work will - * be scheduled on the cpu received on. When 1, the LLDD - * may not deliver the CMD on the CPU it should be worked - * on. The transport should pick a cpu to schedule the work - * on. + NVMET_FCTGTFEAT_CMD_IN_ISR = (1 << 1), + /* Bit 2: When 0, the LLDD is calling the cmd rcv handler + * in a non-isr context, allowing the transport to finish + * op completion in the calling context. When 1, the LLDD + * is calling the cmd rcv handler in an ISR context, + * requiring the transport to transition to a workqueue + * for op completion. + */ + NVMET_FCTGTFEAT_OPDONE_IN_ISR = (1 << 2), + /* Bit 3: When 0, the LLDD is calling the op done handler + * in a non-isr context, allowing the transport to finish + * op completion in the calling context. When 1, the LLDD + * is calling the op done handler in an ISR context, + * requiring the transport to transition to a workqueue + * for op completion. */ }; @@ -725,12 +728,12 @@ struct nvmet_fc_target_port { * be freed/released. * Entrypoint is Mandatory. * - * @fcp_op: Called to perform a data transfer, transmit a response, or - * abort an FCP opertion. The nvmefc_tgt_fcp_req structure is the same - * LLDD-supplied exchange structure specified in the - * nvmet_fc_rcv_fcp_req() call made when the FCP CMD IU was received. - * The op field in the structure shall indicate the operation for - * the LLDD to perform relative to the io. + * @fcp_op: Called to perform a data transfer or transmit a response. + * The nvmefc_tgt_fcp_req structure is the same LLDD-supplied + * exchange structure specified in the nvmet_fc_rcv_fcp_req() call + * made when the FCP CMD IU was received. The op field in the + * structure shall indicate the operation for the LLDD to perform + * relative to the io. * NVMET_FCOP_READDATA operation: the LLDD is to send the * payload data (described by sglist) to the host in 1 or * more FC sequences (preferrably 1). Note: the fc-nvme layer @@ -752,29 +755,31 @@ struct nvmet_fc_target_port { * successfully, the LLDD is to update the nvmefc_tgt_fcp_req * transferred_length field and may subsequently transmit the * FCP_RSP iu payload (described by rspbuf, rspdma, rsplen). - * The LLDD is to await FCP_CONF reception to confirm the RSP - * reception by the host. The LLDD may retramsit the FCP_RSP iu - * if necessary per FC-NVME. Upon reception of FCP_CONF, or upon - * FCP_CONF failure, the LLDD is to set the nvmefc_tgt_fcp_req - * fcp_error field and consider the operation complete.. + * If FCP_CONF is supported, the LLDD is to await FCP_CONF + * reception to confirm the RSP reception by the host. The LLDD + * may retramsit the FCP_RSP iu if necessary per FC-NVME. Upon + * transmission of the FCP_RSP iu if FCP_CONF is not supported, + * or upon success/failure of FCP_CONF if it is supported, the + * LLDD is to set the nvmefc_tgt_fcp_req fcp_error field and + * consider the operation complete. * NVMET_FCOP_RSP: the LLDD is to transmit the FCP_RSP iu payload - * (described by rspbuf, rspdma, rsplen). The LLDD is to await - * FCP_CONF reception to confirm the RSP reception by the host. - * The LLDD may retramsit the FCP_RSP iu if necessary per FC-NVME. - * Upon reception of FCP_CONF, or upon FCP_CONF failure, the + * (described by rspbuf, rspdma, rsplen). If FCP_CONF is + * supported, the LLDD is to await FCP_CONF reception to confirm + * the RSP reception by the host. The LLDD may retramsit the + * FCP_RSP iu if FCP_CONF is not received per FC-NVME. Upon + * transmission of the FCP_RSP iu if FCP_CONF is not supported, + * or upon success/failure of FCP_CONF if it is supported, the * LLDD is to set the nvmefc_tgt_fcp_req fcp_error field and - * consider the operation complete.. - * NVMET_FCOP_ABORT: the LLDD is to terminate the exchange - * corresponding to the fcp operation. The LLDD shall send - * ABTS and follow FC exchange abort-multi rules, including - * ABTS retries and possible logout. + * consider the operation complete. * Upon completing the indicated operation, the LLDD is to set the * status fields for the operation (tranferred_length and fcp_error - * status) in the request, then all the "done" routine - * indicated in the fcp request. Upon return from the "done" - * routine for either a NVMET_FCOP_RSP or NVMET_FCOP_ABORT operation - * the fc-nvme layer will not longer reference the fcp request, - * allowing the LLDD to free/release the fcp request. + * status) in the request, then call the "done" routine + * indicated in the fcp request. After the operation completes, + * regardless of whether the FCP_RSP iu was successfully transmit, + * the LLDD-supplied exchange structure must remain valid until the + * transport calls the fcp_req_release() callback to return ownership + * of the exchange structure back to the LLDD so that it may be used + * for another fcp command. * Note: when calling the done routine for READDATA or WRITEDATA * operations, the fc-nvme layer may immediate convert, in the same * thread and before returning to the LLDD, the fcp operation to @@ -786,6 +791,22 @@ struct nvmet_fc_target_port { * Returns 0 on success, -<errno> on failure (Ex: -EIO) * Entrypoint is Mandatory. * + * @fcp_abort: Called by the transport to abort an active command. + * The command may be in-between operations (nothing active in LLDD) + * or may have an active WRITEDATA operation pending. The LLDD is to + * initiate the ABTS process for the command and return from the + * callback. The ABTS does not need to be complete on the command. + * The fcp_abort callback inherently cannot fail. After the + * fcp_abort() callback completes, the transport will wait for any + * outstanding operation (if there was one) to complete, then will + * call the fcp_req_release() callback to return the command's + * exchange context back to the LLDD. + * + * @fcp_req_release: Called by the transport to return a nvmefc_tgt_fcp_req + * to the LLDD after all operations on the fcp operation are complete. + * This may be due to the command completing or upon completion of + * abort cleanup. + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -820,7 +841,11 @@ struct nvmet_fc_target_template { int (*xmt_ls_rsp)(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_ls_req *tls_req); int (*fcp_op)(struct nvmet_fc_target_port *tgtport, - struct nvmefc_tgt_fcp_req *); + struct nvmefc_tgt_fcp_req *fcpreq); + void (*fcp_abort)(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_fcp_req *fcpreq); + void (*fcp_req_release)(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_fcp_req *fcpreq); u32 max_hw_queues; u16 max_sgl_segments; @@ -848,4 +873,7 @@ int nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq, void *cmdiubuf, u32 cmdiubuf_len); +void nvmet_fc_rcv_fcp_abort(struct nvmet_fc_target_port *tgtport, + struct nvmefc_tgt_fcp_req *fcpreq); + #endif /* _NVME_FC_DRIVER_H */ diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index 4b45226bd604..21c37e39e41a 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -16,8 +16,8 @@ */ /* - * This file contains definitions relative to FC-NVME r1.11 and a few - * newer items + * This file contains definitions relative to FC-NVME r1.14 (16-020vB). + * The fcnvme_lsdesc_cr_assoc_cmd struct reflects expected r1.16 content. */ #ifndef _NVME_FC_H @@ -47,8 +47,15 @@ struct nvme_fc_cmd_iu { #define NVME_FC_SIZEOF_ZEROS_RSP 12 +enum { + FCNVME_SC_SUCCESS = 0, + FCNVME_SC_INVALID_FIELD = 1, + FCNVME_SC_INVALID_CONNID = 2, +}; + struct nvme_fc_ersp_iu { - __u8 rsvd0[2]; + __u8 status_code; + __u8 rsvd1; __be16 iu_len; __be32 rsn; __be32 xfrd_len; @@ -58,7 +65,7 @@ struct nvme_fc_ersp_iu { }; -/* FC-NVME r1.03/16-119v0 NVME Link Services */ +/* FC-NVME Link Services */ enum { FCNVME_LS_RSVD = 0, FCNVME_LS_RJT = 1, @@ -68,7 +75,7 @@ enum { FCNVME_LS_DISCONNECT = 5, }; -/* FC-NVME r1.03/16-119v0 NVME Link Service Descriptors */ +/* FC-NVME Link Service Descriptors */ enum { FCNVME_LSDESC_RSVD = 0x0, FCNVME_LSDESC_RQST = 0x1, @@ -92,7 +99,6 @@ static inline __be32 fcnvme_lsdesc_len(size_t sz) return cpu_to_be32(sz - (2 * sizeof(u32))); } - struct fcnvme_ls_rqst_w0 { u8 ls_cmd; /* FCNVME_LS_xxx */ u8 zeros[3]; @@ -106,8 +112,53 @@ struct fcnvme_lsdesc_rqst { __be32 rsvd12; }; +/* FC-NVME LS RJT reason_code values */ +enum fcnvme_ls_rjt_reason { + FCNVME_RJT_RC_NONE = 0, + /* no reason - not to be sent */ + + FCNVME_RJT_RC_INVAL = 0x01, + /* invalid NVMe_LS command code */ + + FCNVME_RJT_RC_LOGIC = 0x03, + /* logical error */ + + FCNVME_RJT_RC_UNAB = 0x09, + /* unable to perform command request */ + + FCNVME_RJT_RC_UNSUP = 0x0b, + /* command not supported */ + + FCNVME_RJT_RC_INPROG = 0x0e, + /* command already in progress */ + + FCNVME_RJT_RC_INV_ASSOC = 0x40, + /* Invalid Association ID*/ + + FCNVME_RJT_RC_INV_CONN = 0x41, + /* Invalid Connection ID*/ + + FCNVME_RJT_RC_VENDOR = 0xff, + /* vendor specific error */ +}; + +/* FC-NVME LS RJT reason_explanation values */ +enum fcnvme_ls_rjt_explan { + FCNVME_RJT_EXP_NONE = 0x00, + /* No additional explanation */ + + FCNVME_RJT_EXP_OXID_RXID = 0x17, + /* invalid OX_ID-RX_ID combination */ + FCNVME_RJT_EXP_INSUF_RES = 0x29, + /* insufficient resources */ + FCNVME_RJT_EXP_UNAB_DATA = 0x2a, + /* unable to supply requested data */ + + FCNVME_RJT_EXP_INV_LEN = 0x2d, + /* Invalid payload length */ +}; /* FCNVME_LSDESC_RJT */ struct fcnvme_lsdesc_rjt { @@ -119,15 +170,14 @@ struct fcnvme_lsdesc_rjt { * Reject reason and explanaction codes are generic * to ELs's from LS-3. */ - u8 reason_code; - u8 reason_explanation; + u8 reason_code; /* fcnvme_ls_rjt_reason */ + u8 reason_explanation; /* fcnvme_ls_rjt_explan */ u8 vendor; __be32 rsvd12; }; -#define FCNVME_ASSOC_HOSTID_LEN 64 #define FCNVME_ASSOC_HOSTNQN_LEN 256 #define FCNVME_ASSOC_SUBNQN_LEN 256 @@ -141,12 +191,24 @@ struct fcnvme_lsdesc_cr_assoc_cmd { __be16 cntlid; __be16 sqsize; __be32 rsvd52; - u8 hostid[FCNVME_ASSOC_HOSTID_LEN]; + uuid_t hostid; u8 hostnqn[FCNVME_ASSOC_HOSTNQN_LEN]; u8 subnqn[FCNVME_ASSOC_SUBNQN_LEN]; - u8 rsvd632[384]; + __be32 rsvd584[108]; /* pad to 1016 bytes, + * which makes overall LS rqst + * payload 1024 bytes + */ }; +#define FCNVME_LSDESC_CRA_CMD_DESC_MINLEN \ + offsetof(struct fcnvme_lsdesc_cr_assoc_cmd, rsvd584) + +#define FCNVME_LSDESC_CRA_CMD_DESC_MIN_DESCLEN \ + (FCNVME_LSDESC_CRA_CMD_DESC_MINLEN - \ + offsetof(struct fcnvme_lsdesc_cr_assoc_cmd, ersp_ratio)) + + + /* FCNVME_LSDESC_CREATE_CONN_CMD */ struct fcnvme_lsdesc_cr_conn_cmd { __be32 desc_tag; /* FCNVME_LSDESC_xxx */ @@ -224,6 +286,14 @@ struct fcnvme_ls_cr_assoc_rqst { struct fcnvme_lsdesc_cr_assoc_cmd assoc_cmd; }; +#define FCNVME_LSDESC_CRA_RQST_MINLEN \ + (offsetof(struct fcnvme_ls_cr_assoc_rqst, assoc_cmd) + \ + FCNVME_LSDESC_CRA_CMD_DESC_MINLEN) + +#define FCNVME_LSDESC_CRA_RQST_MIN_LISTLEN \ + FCNVME_LSDESC_CRA_CMD_DESC_MINLEN + + struct fcnvme_ls_cr_assoc_acc { struct fcnvme_ls_acc_hdr hdr; struct fcnvme_lsdesc_assoc_id associd; diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h index bf240a3cbf99..a72fd04aa5e1 100644 --- a/include/linux/nvme-rdma.h +++ b/include/linux/nvme-rdma.h @@ -29,6 +29,30 @@ enum nvme_rdma_cm_status { NVME_RDMA_CM_INVALID_ORD = 0x08, }; +static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status) +{ + switch (status) { + case NVME_RDMA_CM_INVALID_LEN: + return "invalid length"; + case NVME_RDMA_CM_INVALID_RECFMT: + return "invalid record format"; + case NVME_RDMA_CM_INVALID_QID: + return "invalid queue ID"; + case NVME_RDMA_CM_INVALID_HSQSIZE: + return "invalid host SQ size"; + case NVME_RDMA_CM_INVALID_HRQSIZE: + return "invalid host RQ size"; + case NVME_RDMA_CM_NO_RSC: + return "resource not found"; + case NVME_RDMA_CM_INVALID_IRD: + return "invalid IRD"; + case NVME_RDMA_CM_INVALID_ORD: + return "Invalid ORD"; + default: + return "unrecognized reason"; + } +} + /** * struct nvme_rdma_cm_req - rdma connect request * diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 3d1c6f1b15c9..bc74da018bdc 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -16,6 +16,7 @@ #define _LINUX_NVME_H #include <linux/types.h> +#include <linux/uuid.h> /* NQN names in commands fields specified one size */ #define NVMF_NQN_FIELD_LEN 256 @@ -64,29 +65,29 @@ enum { * RDMA_QPTYPE field */ enum { - NVMF_RDMA_QPTYPE_CONNECTED = 0, /* Reliable Connected */ - NVMF_RDMA_QPTYPE_DATAGRAM = 1, /* Reliable Datagram */ + NVMF_RDMA_QPTYPE_CONNECTED = 1, /* Reliable Connected */ + NVMF_RDMA_QPTYPE_DATAGRAM = 2, /* Reliable Datagram */ }; /* RDMA QP Service Type codes for Discovery Log Page entry TSAS * RDMA_QPTYPE field */ enum { - NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 0, /* No Provider Specified */ - NVMF_RDMA_PRTYPE_IB = 1, /* InfiniBand */ - NVMF_RDMA_PRTYPE_ROCE = 2, /* InfiniBand RoCE */ - NVMF_RDMA_PRTYPE_ROCEV2 = 3, /* InfiniBand RoCEV2 */ - NVMF_RDMA_PRTYPE_IWARP = 4, /* IWARP */ + NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 1, /* No Provider Specified */ + NVMF_RDMA_PRTYPE_IB = 2, /* InfiniBand */ + NVMF_RDMA_PRTYPE_ROCE = 3, /* InfiniBand RoCE */ + NVMF_RDMA_PRTYPE_ROCEV2 = 4, /* InfiniBand RoCEV2 */ + NVMF_RDMA_PRTYPE_IWARP = 5, /* IWARP */ }; /* RDMA Connection Management Service Type codes for Discovery Log Page * entry TSAS RDMA_CMS field */ enum { - NVMF_RDMA_CMS_RDMA_CM = 0, /* Sockets based enpoint addressing */ + NVMF_RDMA_CMS_RDMA_CM = 1, /* Sockets based endpoint addressing */ }; -#define NVMF_AQ_DEPTH 32 +#define NVME_AQ_DEPTH 32 enum { NVME_REG_CAP = 0x0000, /* Controller Capabilities */ @@ -101,6 +102,7 @@ enum { NVME_REG_ACQ = 0x0030, /* Admin CQ Base Address */ NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ NVME_REG_CMBSZ = 0x003c, /* Controller Memory Buffer Size */ + NVME_REG_DBS = 0x1000, /* SQ 0 Tail Doorbell */ }; #define NVME_CAP_MQES(cap) ((cap) & 0xffff) @@ -207,9 +209,15 @@ struct nvme_id_ctrl { __u8 tnvmcap[16]; __u8 unvmcap[16]; __le32 rpmbs; - __u8 rsvd316[4]; + __le16 edstt; + __u8 dsto; + __u8 fwug; __le16 kas; - __u8 rsvd322[190]; + __le16 hctma; + __le16 mntmt; + __le16 mxtmt; + __le32 sanicap; + __u8 rsvd332[180]; __u8 sqes; __u8 cqes; __le16 maxcmd; @@ -244,6 +252,9 @@ enum { NVME_CTRL_ONCS_DSM = 1 << 2, NVME_CTRL_ONCS_WRITE_ZEROES = 1 << 3, NVME_CTRL_VWC_PRESENT = 1 << 0, + NVME_CTRL_OACS_SEC_SUPP = 1 << 0, + NVME_CTRL_OACS_DIRECTIVES = 1 << 5, + NVME_CTRL_OACS_DBBUF_SUPP = 1 << 7, }; struct nvme_lbaf { @@ -272,7 +283,7 @@ struct nvme_id_ns { __le16 nabsn; __le16 nabo; __le16 nabspf; - __u16 rsvd46; + __le16 noiob; __u8 nvmcap[16]; __u8 rsvd64[40]; __u8 nguid[16]; @@ -286,6 +297,7 @@ enum { NVME_ID_CNS_NS = 0x00, NVME_ID_CNS_CTRL = 0x01, NVME_ID_CNS_NS_ACTIVE_LIST = 0x02, + NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -293,6 +305,19 @@ enum { }; enum { + NVME_DIR_IDENTIFY = 0x00, + NVME_DIR_STREAMS = 0x01, + NVME_DIR_SND_ID_OP_ENABLE = 0x01, + NVME_DIR_SND_ST_OP_REL_ID = 0x01, + NVME_DIR_SND_ST_OP_REL_RSC = 0x02, + NVME_DIR_RCV_ID_OP_PARAM = 0x01, + NVME_DIR_RCV_ST_OP_PARAM = 0x01, + NVME_DIR_RCV_ST_OP_STATUS = 0x02, + NVME_DIR_RCV_ST_OP_RESOURCE = 0x03, + NVME_DIR_ENDIR = 0x01, +}; + +enum { NVME_NS_FEAT_THIN = 1 << 0, NVME_NS_FLBAS_LBA_MASK = 0xf, NVME_NS_FLBAS_META_EXT = 0x10, @@ -312,6 +337,22 @@ enum { NVME_NS_DPS_PI_TYPE3 = 3, }; +struct nvme_ns_id_desc { + __u8 nidt; + __u8 nidl; + __le16 reserved; +}; + +#define NVME_NIDT_EUI64_LEN 8 +#define NVME_NIDT_NGUID_LEN 16 +#define NVME_NIDT_UUID_LEN 16 + +enum { + NVME_NIDT_EUI64 = 0x01, + NVME_NIDT_NGUID = 0x02, + NVME_NIDT_UUID = 0x03, +}; + struct nvme_smart_log { __u8 critical_warning; __u8 temperature[2]; @@ -533,6 +574,7 @@ enum { NVME_RW_PRINFO_PRCHK_APP = 1 << 11, NVME_RW_PRINFO_PRCHK_GUARD = 1 << 12, NVME_RW_PRINFO_PRACT = 1 << 13, + NVME_RW_DTYPE_STREAMS = 1 << 4, }; struct nvme_dsm_cmd { @@ -553,6 +595,8 @@ enum { NVME_DSMGMT_AD = 1 << 2, }; +#define NVME_DSM_MAX_RANGES 256 + struct nvme_dsm_range { __le32 cattr; __le32 nlb; @@ -576,6 +620,17 @@ struct nvme_write_zeroes_cmd { __le16 appmask; }; +/* Features */ + +struct nvme_feat_auto_pst { + __le64 entries[32]; +}; + +enum { + NVME_HOST_MEM_ENABLE = (1 << 0), + NVME_HOST_MEM_RETURN = (1 << 1), +}; + /* Admin commands */ enum nvme_admin_opcode { @@ -594,6 +649,9 @@ enum nvme_admin_opcode { nvme_admin_download_fw = 0x11, nvme_admin_ns_attach = 0x15, nvme_admin_keep_alive = 0x18, + nvme_admin_directive_send = 0x19, + nvme_admin_directive_recv = 0x1a, + nvme_admin_dbbuf = 0x7C, nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, nvme_admin_security_recv = 0x82, @@ -641,10 +699,14 @@ struct nvme_identify { __le32 nsid; __u64 rsvd2[2]; union nvme_data_ptr dptr; - __le32 cns; + __u8 cns; + __u8 rsvd3; + __le16 ctrlid; __u32 rsvd11[5]; }; +#define NVME_IDENTIFY_DATA_SIZE 4096 + struct nvme_features { __u8 opcode; __u8 flags; @@ -654,7 +716,16 @@ struct nvme_features { union nvme_data_ptr dptr; __le32 fid; __le32 dword11; - __u32 rsvd12[4]; + __le32 dword12; + __le32 dword13; + __le32 dword14; + __le32 dword15; +}; + +struct nvme_host_mem_buf_desc { + __le64 addr; + __le32 size; + __u32 rsvd; }; struct nvme_create_cq { @@ -743,6 +814,24 @@ struct nvme_get_log_page_command { __u32 rsvd14[2]; }; +struct nvme_directive_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + union nvme_data_ptr dptr; + __le32 numd; + __u8 doper; + __u8 dtype; + __le16 dspec; + __u8 endir; + __u8 tdtype; + __u16 rsvd15; + + __u32 rsvd16[3]; +}; + /* * Fabrics subcommands. */ @@ -830,7 +919,7 @@ struct nvmf_connect_command { }; struct nvmf_connect_data { - __u8 hostid[16]; + uuid_t hostid; __le16 cntlid; char resv4[238]; char subsysnqn[NVMF_NQN_FIELD_LEN]; @@ -863,6 +952,28 @@ struct nvmf_property_get_command { __u8 resv4[16]; }; +struct nvme_dbbuf { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __le64 prp2; + __u32 rsvd12[6]; +}; + +struct streams_directive_params { + __le16 msl; + __le16 nssa; + __le16 nsso; + __u8 rsvd[10]; + __le32 sws; + __le16 sgs; + __le16 nsa; + __le16 nso; + __u8 rsvd2[6]; +}; + struct nvme_command { union { struct nvme_common_command common; @@ -882,6 +993,8 @@ struct nvme_command { struct nvmf_connect_command connect; struct nvmf_property_set_command prop_set; struct nvmf_property_get_command prop_get; + struct nvme_dbbuf dbbuf; + struct nvme_directive_cmd directive; }; }; @@ -1026,4 +1139,8 @@ struct nvme_completion { #define NVME_VS(major, minor, tertiary) \ (((major) << 16) | ((minor) << 8) | (tertiary)) +#define NVME_MAJOR(ver) ((ver) >> 16) +#define NVME_MINOR(ver) (((ver) >> 8) & 0xff) +#define NVME_TERTIARY(ver) ((ver) & 0xff) + #endif /* _LINUX_NVME_H */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index cd93416d762e..497706f5adca 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -12,6 +12,9 @@ #ifndef _LINUX_NVMEM_PROVIDER_H #define _LINUX_NVMEM_PROVIDER_H +#include <linux/err.h> +#include <linux/errno.h> + struct nvmem_device; struct nvmem_cell_info; typedef int (*nvmem_reg_read_t)(void *priv, unsigned int offset, diff --git a/include/linux/of.h b/include/linux/of.h index d72f01009297..4a8a70916237 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -100,10 +100,12 @@ struct of_reconfig_data { /* initialize a node */ extern struct kobj_type of_node_ktype; +extern const struct fwnode_operations of_fwnode_ops; static inline void of_node_init(struct device_node *node) { kobject_init(&node->kobj, &of_node_ktype); node->fwnode.type = FWNODE_OF; + node->fwnode.ops = &of_fwnode_ops; } /* true when node is initialized */ @@ -148,16 +150,28 @@ extern raw_spinlock_t devtree_lock; #ifdef CONFIG_OF void of_core_init(void); -static inline bool is_of_node(struct fwnode_handle *fwnode) +static inline bool is_of_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_OF; } -static inline struct device_node *to_of_node(struct fwnode_handle *fwnode) -{ - return is_of_node(fwnode) ? - container_of(fwnode, struct device_node, fwnode) : NULL; -} +#define to_of_node(__fwnode) \ + ({ \ + typeof(__fwnode) __to_of_node_fwnode = (__fwnode); \ + \ + is_of_node(__to_of_node_fwnode) ? \ + container_of(__to_of_node_fwnode, \ + struct device_node, fwnode) : \ + NULL; \ + }) + +#define of_fwnode_handle(node) \ + ({ \ + typeof(node) __of_fwnode_handle_node = (node); \ + \ + __of_fwnode_handle_node ? \ + &__of_fwnode_handle_node->fwnode : NULL; \ + }) static inline bool of_have_populated_dt(void) { @@ -280,6 +294,7 @@ extern struct device_node *of_get_child_by_name(const struct device_node *node, /* cache lookup */ extern struct device_node *of_find_next_cache_node(const struct device_node *); +extern int of_find_last_cache_level(unsigned int cpu); extern struct device_node *of_find_node_with_property( struct device_node *from, const char *prop_name); @@ -291,6 +306,9 @@ extern int of_property_count_elems_of_size(const struct device_node *np, extern int of_property_read_u32_index(const struct device_node *np, const char *propname, u32 index, u32 *out_value); +extern int of_property_read_u64_index(const struct device_node *np, + const char *propname, + u32 index, u64 *out_value); extern int of_property_read_variable_u8_array(const struct device_node *np, const char *propname, u8 *out_values, size_t sz_min, size_t sz_max); @@ -527,12 +545,12 @@ static inline void of_core_init(void) { } -static inline bool is_of_node(struct fwnode_handle *fwnode) +static inline bool is_of_node(const struct fwnode_handle *fwnode) { return false; } -static inline struct device_node *to_of_node(struct fwnode_handle *fwnode) +static inline struct device_node *to_of_node(const struct fwnode_handle *fwnode) { return NULL; } @@ -601,6 +619,8 @@ static inline struct device_node *of_find_node_with_property( return NULL; } +#define of_fwnode_handle(node) NULL + static inline bool of_have_populated_dt(void) { return false; @@ -619,6 +639,12 @@ static inline int of_device_is_compatible(const struct device_node *device, return 0; } +static inline int of_device_compatible_match(struct device_node *device, + const char *const *compat) +{ + return 0; +} + static inline bool of_device_is_available(const struct device_node *device) { return false; diff --git a/include/linux/of_device.h b/include/linux/of_device.h index cc7dd687a89d..b4ad8b4f8506 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -13,7 +13,6 @@ struct device; #ifdef CONFIG_OF extern const struct of_device_id *of_match_device( const struct of_device_id *matches, const struct device *dev); -extern void of_device_make_bus_id(struct device *dev); /** * of_driver_match_device - Tell if a driver's of_match_table matches a device. @@ -35,8 +34,8 @@ extern void of_device_unregister(struct platform_device *ofdev); extern const void *of_device_get_match_data(const struct device *dev); -extern ssize_t of_device_get_modalias(struct device *dev, - char *str, ssize_t len); +extern ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len); +extern int of_device_request_module(struct device *dev); extern void of_device_uevent(struct device *dev, struct kobj_uevent_env *env); extern int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env); @@ -55,7 +54,8 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) return of_node_get(cpu_dev->of_node); } -void of_dma_configure(struct device *dev, struct device_node *np); +int of_dma_configure(struct device *dev, struct device_node *np); +void of_dma_deconfigure(struct device *dev); #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, @@ -72,8 +72,13 @@ static inline const void *of_device_get_match_data(const struct device *dev) return NULL; } -static inline int of_device_get_modalias(struct device *dev, - char *str, ssize_t len) +static inline int of_device_modalias(struct device *dev, + char *str, ssize_t len) +{ + return -ENODEV; +} + +static inline int of_device_request_module(struct device *dev) { return -ENODEV; } @@ -98,7 +103,12 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) { return NULL; } -static inline void of_dma_configure(struct device *dev, struct device_node *np) + +static inline int of_dma_configure(struct device *dev, struct device_node *np) +{ + return 0; +} +static inline void of_dma_deconfigure(struct device *dev) {} #endif /* CONFIG_OF */ diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 271b3fdf0070..013c5418aeec 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -31,9 +31,6 @@ extern void *of_fdt_get_property(const void *blob, unsigned long node, const char *name, int *size); -extern int of_fdt_is_compatible(const void *blob, - unsigned long node, - const char *compat); extern bool of_fdt_is_big_endian(const void *blob, unsigned long node); extern int of_fdt_match(const void *blob, unsigned long node, @@ -54,6 +51,11 @@ extern char __dtb_end[]; extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname, int depth, void *data), void *data); +extern int of_scan_flat_dt_subnodes(unsigned long node, + int (*it)(unsigned long node, + const char *uname, + void *data), + void *data); extern int of_get_flat_dt_subnode_by_name(unsigned long node, const char *uname); extern const void *of_get_flat_dt_prop(unsigned long node, const char *name, @@ -62,6 +64,7 @@ extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern int of_flat_dt_match(unsigned long node, const char *const *matches); extern unsigned long of_get_flat_dt_root(void); extern int of_get_flat_dt_size(void); +extern uint32_t of_get_flat_dt_phandle(unsigned long node); extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, int depth, void *data); diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index 3f87ea5b8bee..ca10f43564de 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -30,6 +30,8 @@ struct device_node; enum of_gpio_flags { OF_GPIO_ACTIVE_LOW = 0x1, OF_GPIO_SINGLE_ENDED = 0x2, + OF_GPIO_OPEN_DRAIN = 0x4, + OF_GPIO_SLEEP_MAY_LOOSE_VALUE = 0x8, }; #ifdef CONFIG_OF_GPIO diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h index bb3a5a2cd570..3e058f05ab04 100644 --- a/include/linux/of_graph.h +++ b/include/linux/of_graph.h @@ -43,14 +43,20 @@ struct of_endpoint { #ifdef CONFIG_OF int of_graph_parse_endpoint(const struct device_node *node, struct of_endpoint *endpoint); +int of_graph_get_endpoint_count(const struct device_node *np); struct device_node *of_graph_get_port_by_id(struct device_node *node, u32 id); struct device_node *of_graph_get_next_endpoint(const struct device_node *parent, struct device_node *previous); struct device_node *of_graph_get_endpoint_by_regs( const struct device_node *parent, int port_reg, int reg); +struct device_node *of_graph_get_remote_endpoint( + const struct device_node *node); +struct device_node *of_graph_get_port_parent(struct device_node *node); struct device_node *of_graph_get_remote_port_parent( const struct device_node *node); struct device_node *of_graph_get_remote_port(const struct device_node *node); +struct device_node *of_graph_get_remote_node(const struct device_node *node, + u32 port, u32 endpoint); #else static inline int of_graph_parse_endpoint(const struct device_node *node, @@ -59,6 +65,11 @@ static inline int of_graph_parse_endpoint(const struct device_node *node, return -ENOSYS; } +static inline int of_graph_get_endpoint_count(const struct device_node *np) +{ + return 0; +} + static inline struct device_node *of_graph_get_port_by_id( struct device_node *node, u32 id) { @@ -78,6 +89,18 @@ static inline struct device_node *of_graph_get_endpoint_by_regs( return NULL; } +static inline struct device_node *of_graph_get_remote_endpoint( + const struct device_node *node) +{ + return NULL; +} + +static inline struct device_node *of_graph_get_port_parent( + struct device_node *node) +{ + return NULL; +} + static inline struct device_node *of_graph_get_remote_port_parent( const struct device_node *node) { @@ -89,6 +112,12 @@ static inline struct device_node *of_graph_get_remote_port( { return NULL; } +static inline struct device_node *of_graph_get_remote_node( + const struct device_node *node, + u32 port, u32 endpoint) +{ + return NULL; +} #endif /* CONFIG_OF */ diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index 6a7fc5051099..13394ac83c66 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -31,17 +31,6 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev, #endif /* CONFIG_OF_IOMMU */ -static inline void of_iommu_set_ops(struct device_node *np, - const struct iommu_ops *ops) -{ - iommu_register_instance(&np->fwnode, ops); -} - -static inline const struct iommu_ops *of_iommu_get_ops(struct device_node *np) -{ - return iommu_get_instance(&np->fwnode); -} - extern struct of_device_id __iommu_of_table; typedef int (*of_iommu_init_fn)(struct device_node *); diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index a58cca8bcb29..f5db93bcd069 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -12,7 +12,7 @@ #include <linux/phy.h> #include <linux/of.h> -#ifdef CONFIG_OF +#if IS_ENABLED(CONFIG_OF_MDIO) extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); extern struct phy_device *of_phy_find_device(struct device_node *phy_np); extern struct phy_device *of_phy_connect(struct net_device *dev, @@ -27,12 +27,34 @@ struct phy_device *of_phy_attach(struct net_device *dev, phy_interface_t iface); extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); -extern int of_mdio_parse_addr(struct device *dev, const struct device_node *np); extern int of_phy_register_fixed_link(struct device_node *np); extern void of_phy_deregister_fixed_link(struct device_node *np); extern bool of_phy_is_fixed_link(struct device_node *np); -#else /* CONFIG_OF */ + +static inline int of_mdio_parse_addr(struct device *dev, + const struct device_node *np) +{ + u32 addr; + int ret; + + ret = of_property_read_u32(np, "reg", &addr); + if (ret < 0) { + dev_err(dev, "%s has invalid PHY address\n", np->full_name); + return ret; + } + + /* A PHY must have a reg property in the range [0-31] */ + if (addr >= PHY_MAX_ADDR) { + dev_err(dev, "%s PHY address %i is too large\n", + np->full_name, addr); + return -EINVAL; + } + + return addr; +} + +#else /* CONFIG_OF_MDIO */ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) { /* diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 0e0974eceb80..518c8d20647a 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -85,15 +85,4 @@ static inline int of_pci_get_host_bridge_resources(struct device_node *dev, } #endif -#if defined(CONFIG_OF) && defined(CONFIG_PCI_MSI) -int of_pci_msi_chip_add(struct msi_controller *chip); -void of_pci_msi_chip_remove(struct msi_controller *chip); -struct msi_controller *of_pci_find_msi_chip_by_node(struct device_node *of_node); -#else -static inline int of_pci_msi_chip_add(struct msi_controller *chip) { return -EINVAL; } -static inline void of_pci_msi_chip_remove(struct msi_controller *chip) { } -static inline struct msi_controller * -of_pci_find_msi_chip_by_node(struct device_node *of_node) { return NULL; } -#endif - #endif diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 956a1006aefc..e0d1946270f3 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -64,6 +64,7 @@ extern struct platform_device *of_platform_device_create(struct device_node *np, const char *bus_id, struct device *parent); +extern int of_platform_device_destroy(struct device *dev, void *data); extern int of_platform_bus_probe(struct device_node *root, const struct of_device_id *matches, struct device *parent); @@ -76,6 +77,10 @@ extern int of_platform_default_populate(struct device_node *root, const struct of_dev_auxdata *lookup, struct device *parent); extern void of_platform_depopulate(struct device *parent); + +extern int devm_of_platform_populate(struct device *dev); + +extern void devm_of_platform_depopulate(struct device *dev); #else static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, @@ -91,6 +96,13 @@ static inline int of_platform_default_populate(struct device_node *root, return -ENODEV; } static inline void of_platform_depopulate(struct device *parent) { } + +static inline int devm_of_platform_populate(struct device *dev) +{ + return -ENODEV; +} + +static inline void devm_of_platform_depopulate(struct device *dev) { } #endif #if defined(CONFIG_OF_DYNAMIC) && defined(CONFIG_OF_ADDRESS) diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h index 35d0fd7a4948..fd0de00c0d77 100644 --- a/include/linux/omap-gpmc.h +++ b/include/linux/omap-gpmc.h @@ -76,22 +76,12 @@ struct gpmc_timings; struct omap_nand_platform_data; struct omap_onenand_platform_data; -#if IS_ENABLED(CONFIG_MTD_NAND_OMAP2) -extern int gpmc_nand_init(struct omap_nand_platform_data *d, - struct gpmc_timings *gpmc_t); -#else -static inline int gpmc_nand_init(struct omap_nand_platform_data *d, - struct gpmc_timings *gpmc_t) -{ - return 0; -} -#endif - #if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2) -extern void gpmc_onenand_init(struct omap_onenand_platform_data *d); +extern int gpmc_onenand_init(struct omap_onenand_platform_data *d); #else #define board_onenand_data NULL -static inline void gpmc_onenand_init(struct omap_onenand_platform_data *d) +static inline int gpmc_onenand_init(struct omap_onenand_platform_data *d) { + return 0; } #endif diff --git a/include/linux/once.h b/include/linux/once.h index 285f12cb40e6..9c98aaa87cbc 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -53,5 +53,7 @@ void __do_once_done(bool *done, struct static_key *once_key, #define get_random_once(buf, nbytes) \ DO_ONCE(get_random_bytes, (buf), (nbytes)) +#define get_random_once_wait(buf, nbytes) \ + DO_ONCE(get_random_bytes_wait, (buf), (nbytes)) \ #endif /* _LINUX_ONCE_H */ diff --git a/include/linux/oom.h b/include/linux/oom.h index b4e36e92bc87..8a266e2be5a6 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -2,7 +2,7 @@ #define __INCLUDE_LINUX_OOM_H -#include <linux/sched.h> +#include <linux/sched/signal.h> #include <linux/types.h> #include <linux/nodemask.h> #include <uapi/linux/oom.h> diff --git a/include/linux/padata.h b/include/linux/padata.h index 0f9e567d5e15..2f9c1f93b1ce 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -166,9 +166,6 @@ struct padata_instance { extern struct padata_instance *padata_alloc_possible( struct workqueue_struct *wq); -extern struct padata_instance *padata_alloc(struct workqueue_struct *wq, - const struct cpumask *pcpumask, - const struct cpumask *cbcpumask); extern void padata_free(struct padata_instance *pinst); extern int padata_do_parallel(struct padata_instance *pinst, struct padata_priv *padata, int cb_cpu); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 6b5818d6de32..d33e3280c8ad 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -326,11 +326,14 @@ PAGEFLAG_FALSE(HighMem) #ifdef CONFIG_SWAP static __always_inline int PageSwapCache(struct page *page) { +#ifdef CONFIG_THP_SWAP + page = compound_head(page); +#endif return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags); } -SETPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND) -CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND) +SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) +CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) #else PAGEFLAG_FALSE(SwapCache) #endif diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 047d64706f2a..d4cd2014fa6f 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,10 +33,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, bool skip_hwpoisoned_pages); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, - int migratetype); -int move_freepages(struct zone *zone, - struct page *start_page, struct page *end_page, - int migratetype); + int migratetype, int *num_movable); /* * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE. diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 610e13271918..1fd71733aa68 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -174,6 +174,7 @@ static inline void page_ref_unfreeze(struct page *page, int count) VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); + smp_mb(); atomic_set(&page->_refcount, count); if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze)) __page_ref_unfreeze(page, count); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 324c8dbad1e1..baa9344dcd10 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -28,14 +28,33 @@ enum mapping_flags { AS_NO_WRITEBACK_TAGS = 5, }; +/** + * mapping_set_error - record a writeback error in the address_space + * @mapping - the mapping in which an error should be set + * @error - the error to set in the mapping + * + * When writeback fails in some way, we must record that error so that + * userspace can be informed when fsync and the like are called. We endeavor + * to report errors on any file that was open at the time of the error. Some + * internal callers also need to know when writeback errors have occurred. + * + * When a writeback error occurs, most filesystems will want to call + * mapping_set_error to record the error in the mapping so that it can be + * reported when the application calls fsync(2). + */ static inline void mapping_set_error(struct address_space *mapping, int error) { - if (unlikely(error)) { - if (error == -ENOSPC) - set_bit(AS_ENOSPC, &mapping->flags); - else - set_bit(AS_EIO, &mapping->flags); - } + if (likely(!error)) + return; + + /* Record in wb_err for checkers using errseq_t based tracking */ + filemap_set_wb_err(mapping, error); + + /* Record it in flags for now, for legacy callers */ + if (error == -ENOSPC) + set_bit(AS_ENOSPC, &mapping->flags); + else + set_bit(AS_EIO, &mapping->flags); } static inline void mapping_set_unevictable(struct address_space *mapping) @@ -148,7 +167,7 @@ static inline int page_cache_get_speculative(struct page *page) #ifdef CONFIG_TINY_RCU # ifdef CONFIG_PREEMPT_COUNT - VM_BUG_ON(!in_atomic()); + VM_BUG_ON(!in_atomic() && !irqs_disabled()); # endif /* * Preempt must be disabled here - we rely on rcu_read_lock doing @@ -186,7 +205,7 @@ static inline int page_cache_add_speculative(struct page *page, int count) #if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU) # ifdef CONFIG_PREEMPT_COUNT - VM_BUG_ON(!in_atomic()); + VM_BUG_ON(!in_atomic() && !irqs_disabled()); # endif VM_BUG_ON_PAGE(page_count(page) == 0, page); page_ref_add(page, count); @@ -266,7 +285,6 @@ static inline struct page *find_get_page_flags(struct address_space *mapping, /** * find_lock_page - locate, pin and lock a pagecache page - * pagecache_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * @@ -482,19 +500,11 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, } /* - * This is exported only for wait_on_page_locked/wait_on_page_writeback, - * and for filesystems which need to wait on PG_private. + * This is exported only for wait_on_page_locked/wait_on_page_writeback, etc., + * and should not be used directly. */ extern void wait_on_page_bit(struct page *page, int bit_nr); extern int wait_on_page_bit_killable(struct page *page, int bit_nr); -extern void wake_up_page_bit(struct page *page, int bit_nr); - -static inline void wake_up_page(struct page *page, int bit) -{ - if (!PageWaiters(page)) - return; - wake_up_page_bit(page, bit); -} /* * Wait for a page to be unlocked. @@ -533,7 +543,7 @@ void page_endio(struct page *page, bool is_write, int err); /* * Add an arbitrary waiter to a page's wait queue */ -extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter); +extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter); /* * Fault everything in given userspace address range in. diff --git a/include/linux/parman.h b/include/linux/parman.h new file mode 100644 index 000000000000..3c8cccc7d4da --- /dev/null +++ b/include/linux/parman.h @@ -0,0 +1,76 @@ +/* + * include/linux/parman.h - Manager for linear priority array areas + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _PARMAN_H +#define _PARMAN_H + +#include <linux/list.h> + +enum parman_algo_type { + PARMAN_ALGO_TYPE_LSORT, +}; + +struct parman_item { + struct list_head list; + unsigned long index; +}; + +struct parman_prio { + struct list_head list; + struct list_head item_list; + unsigned long priority; +}; + +struct parman_ops { + unsigned long base_count; + unsigned long resize_step; + int (*resize)(void *priv, unsigned long new_count); + void (*move)(void *priv, unsigned long from_index, + unsigned long to_index, unsigned long count); + enum parman_algo_type algo; +}; + +struct parman; + +struct parman *parman_create(const struct parman_ops *ops, void *priv); +void parman_destroy(struct parman *parman); +void parman_prio_init(struct parman *parman, struct parman_prio *prio, + unsigned long priority); +void parman_prio_fini(struct parman_prio *prio); +int parman_item_add(struct parman *parman, struct parman_prio *prio, + struct parman_item *item); +void parman_item_remove(struct parman *parman, struct parman_prio *prio, + struct parman_item *item); + +#endif diff --git a/include/linux/path.h b/include/linux/path.h index d1372186f431..cde895cc4af4 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -7,7 +7,7 @@ struct vfsmount; struct path { struct vfsmount *mnt; struct dentry *dentry; -}; +} __randomize_layout; extern void path_get(const struct path *); extern void path_put(const struct path *); diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 7a4e83a8c89c..dd86c97f2454 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -105,7 +105,7 @@ static inline void acpiphp_remove_slots(struct pci_bus *bus) { } static inline void acpiphp_check_host_bridge(struct acpi_device *adev) { } #endif -extern const u8 pci_acpi_dsm_uuid[]; +extern const guid_t pci_acpi_dsm_guid; #define DEVICE_LABEL_DSM 0x07 #define RESET_DELAY_DSM 0x08 #define FUNCTION_DELAY_DSM 0x09 diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 57e0b8250947..782fb8e0755f 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -7,6 +7,7 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs); void pci_disable_pri(struct pci_dev *pdev); +void pci_restore_pri_state(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); #else /* CONFIG_PCI_PRI */ @@ -20,6 +21,10 @@ static inline void pci_disable_pri(struct pci_dev *pdev) { } +static inline void pci_restore_pri_state(struct pci_dev *pdev) +{ +} + static inline int pci_reset_pri(struct pci_dev *pdev) { return -ENODEV; @@ -31,6 +36,7 @@ static inline int pci_reset_pri(struct pci_dev *pdev) int pci_enable_pasid(struct pci_dev *pdev, int features); void pci_disable_pasid(struct pci_dev *pdev); +void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); @@ -45,6 +51,10 @@ static inline void pci_disable_pasid(struct pci_dev *pdev) { } +static inline void pci_restore_pasid_state(struct pci_dev *pdev) +{ +} + static inline int pci_pasid_features(struct pci_dev *pdev) { return -EINVAL; diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index f0d2b9451270..809c2f1873ac 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -16,6 +16,7 @@ #ifndef DRIVERS_PCI_ECAM_H #define DRIVERS_PCI_ECAM_H +#include <linux/pci.h> #include <linux/kernel.h> #include <linux/platform_device.h> @@ -68,7 +69,7 @@ extern struct pci_ecam_ops xgene_v1_pcie_ecam_ops; /* APM X-Gene PCIe v1 */ extern struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */ #endif -#ifdef CONFIG_PCI_HOST_GENERIC +#ifdef CONFIG_PCI_HOST_COMMON /* for DT-based PCI controllers that support ECAM */ int pci_host_common_probe(struct platform_device *pdev, struct pci_ecam_ops *ops); diff --git a/include/linux/pci-ep-cfs.h b/include/linux/pci-ep-cfs.h new file mode 100644 index 000000000000..263b89ea5705 --- /dev/null +++ b/include/linux/pci-ep-cfs.h @@ -0,0 +1,41 @@ +/** + * PCI Endpoint ConfigFS header file + * + * Copyright (C) 2017 Texas Instruments + * Author: Kishon Vijay Abraham I <kishon@ti.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 of + * the License as published by the Free Software Foundation. + */ + +#ifndef __LINUX_PCI_EP_CFS_H +#define __LINUX_PCI_EP_CFS_H + +#include <linux/configfs.h> + +#ifdef CONFIG_PCI_ENDPOINT_CONFIGFS +struct config_group *pci_ep_cfs_add_epc_group(const char *name); +void pci_ep_cfs_remove_epc_group(struct config_group *group); +struct config_group *pci_ep_cfs_add_epf_group(const char *name); +void pci_ep_cfs_remove_epf_group(struct config_group *group); +#else +static inline struct config_group *pci_ep_cfs_add_epc_group(const char *name) +{ + return 0; +} + +static inline void pci_ep_cfs_remove_epc_group(struct config_group *group) +{ +} + +static inline struct config_group *pci_ep_cfs_add_epf_group(const char *name) +{ + return 0; +} + +static inline void pci_ep_cfs_remove_epf_group(struct config_group *group) +{ +} +#endif +#endif /* __LINUX_PCI_EP_CFS_H */ diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h new file mode 100644 index 000000000000..af5edbf3eea3 --- /dev/null +++ b/include/linux/pci-epc.h @@ -0,0 +1,144 @@ +/** + * PCI Endpoint *Controller* (EPC) header file + * + * Copyright (C) 2017 Texas Instruments + * Author: Kishon Vijay Abraham I <kishon@ti.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 of + * the License as published by the Free Software Foundation. + */ + +#ifndef __LINUX_PCI_EPC_H +#define __LINUX_PCI_EPC_H + +#include <linux/pci-epf.h> + +struct pci_epc; + +enum pci_epc_irq_type { + PCI_EPC_IRQ_UNKNOWN, + PCI_EPC_IRQ_LEGACY, + PCI_EPC_IRQ_MSI, +}; + +/** + * struct pci_epc_ops - set of function pointers for performing EPC operations + * @write_header: ops to populate configuration space header + * @set_bar: ops to configure the BAR + * @clear_bar: ops to reset the BAR + * @map_addr: ops to map CPU address to PCI address + * @unmap_addr: ops to unmap CPU address and PCI address + * @set_msi: ops to set the requested number of MSI interrupts in the MSI + * capability register + * @get_msi: ops to get the number of MSI interrupts allocated by the RC from + * the MSI capability register + * @raise_irq: ops to raise a legacy or MSI interrupt + * @start: ops to start the PCI link + * @stop: ops to stop the PCI link + * @owner: the module owner containing the ops + */ +struct pci_epc_ops { + int (*write_header)(struct pci_epc *pci_epc, + struct pci_epf_header *hdr); + int (*set_bar)(struct pci_epc *epc, enum pci_barno bar, + dma_addr_t bar_phys, size_t size, int flags); + void (*clear_bar)(struct pci_epc *epc, enum pci_barno bar); + int (*map_addr)(struct pci_epc *epc, phys_addr_t addr, + u64 pci_addr, size_t size); + void (*unmap_addr)(struct pci_epc *epc, phys_addr_t addr); + int (*set_msi)(struct pci_epc *epc, u8 interrupts); + int (*get_msi)(struct pci_epc *epc); + int (*raise_irq)(struct pci_epc *pci_epc, + enum pci_epc_irq_type type, u8 interrupt_num); + int (*start)(struct pci_epc *epc); + void (*stop)(struct pci_epc *epc); + struct module *owner; +}; + +/** + * struct pci_epc_mem - address space of the endpoint controller + * @phys_base: physical base address of the PCI address space + * @size: the size of the PCI address space + * @bitmap: bitmap to manage the PCI address space + * @pages: number of bits representing the address region + */ +struct pci_epc_mem { + phys_addr_t phys_base; + size_t size; + unsigned long *bitmap; + int pages; +}; + +/** + * struct pci_epc - represents the PCI EPC device + * @dev: PCI EPC device + * @pci_epf: list of endpoint functions present in this EPC device + * @ops: function pointers for performing endpoint operations + * @mem: address space of the endpoint controller + * @max_functions: max number of functions that can be configured in this EPC + * @group: configfs group representing the PCI EPC device + * @lock: spinlock to protect pci_epc ops + */ +struct pci_epc { + struct device dev; + struct list_head pci_epf; + const struct pci_epc_ops *ops; + struct pci_epc_mem *mem; + u8 max_functions; + struct config_group *group; + /* spinlock to protect against concurrent access of EP controller */ + spinlock_t lock; +}; + +#define to_pci_epc(device) container_of((device), struct pci_epc, dev) + +#define pci_epc_create(dev, ops) \ + __pci_epc_create((dev), (ops), THIS_MODULE) +#define devm_pci_epc_create(dev, ops) \ + __devm_pci_epc_create((dev), (ops), THIS_MODULE) + +static inline void epc_set_drvdata(struct pci_epc *epc, void *data) +{ + dev_set_drvdata(&epc->dev, data); +} + +static inline void *epc_get_drvdata(struct pci_epc *epc) +{ + return dev_get_drvdata(&epc->dev); +} + +struct pci_epc * +__devm_pci_epc_create(struct device *dev, const struct pci_epc_ops *ops, + struct module *owner); +struct pci_epc * +__pci_epc_create(struct device *dev, const struct pci_epc_ops *ops, + struct module *owner); +void devm_pci_epc_destroy(struct device *dev, struct pci_epc *epc); +void pci_epc_destroy(struct pci_epc *epc); +int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf); +void pci_epc_linkup(struct pci_epc *epc); +void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf); +int pci_epc_write_header(struct pci_epc *epc, struct pci_epf_header *hdr); +int pci_epc_set_bar(struct pci_epc *epc, enum pci_barno bar, + dma_addr_t bar_phys, size_t size, int flags); +void pci_epc_clear_bar(struct pci_epc *epc, int bar); +int pci_epc_map_addr(struct pci_epc *epc, phys_addr_t phys_addr, + u64 pci_addr, size_t size); +void pci_epc_unmap_addr(struct pci_epc *epc, phys_addr_t phys_addr); +int pci_epc_set_msi(struct pci_epc *epc, u8 interrupts); +int pci_epc_get_msi(struct pci_epc *epc); +int pci_epc_raise_irq(struct pci_epc *epc, enum pci_epc_irq_type type, + u8 interrupt_num); +int pci_epc_start(struct pci_epc *epc); +void pci_epc_stop(struct pci_epc *epc); +struct pci_epc *pci_epc_get(const char *epc_name); +void pci_epc_put(struct pci_epc *epc); + +int pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_addr, size_t size); +void pci_epc_mem_exit(struct pci_epc *epc); +void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc, + phys_addr_t *phys_addr, size_t size); +void pci_epc_mem_free_addr(struct pci_epc *epc, phys_addr_t phys_addr, + void __iomem *virt_addr, size_t size); +#endif /* __LINUX_PCI_EPC_H */ diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h new file mode 100644 index 000000000000..0d529cb90143 --- /dev/null +++ b/include/linux/pci-epf.h @@ -0,0 +1,162 @@ +/** + * PCI Endpoint *Function* (EPF) header file + * + * Copyright (C) 2017 Texas Instruments + * Author: Kishon Vijay Abraham I <kishon@ti.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 of + * the License as published by the Free Software Foundation. + */ + +#ifndef __LINUX_PCI_EPF_H +#define __LINUX_PCI_EPF_H + +#include <linux/device.h> +#include <linux/mod_devicetable.h> + +struct pci_epf; + +enum pci_interrupt_pin { + PCI_INTERRUPT_UNKNOWN, + PCI_INTERRUPT_INTA, + PCI_INTERRUPT_INTB, + PCI_INTERRUPT_INTC, + PCI_INTERRUPT_INTD, +}; + +enum pci_barno { + BAR_0, + BAR_1, + BAR_2, + BAR_3, + BAR_4, + BAR_5, +}; + +/** + * struct pci_epf_header - represents standard configuration header + * @vendorid: identifies device manufacturer + * @deviceid: identifies a particular device + * @revid: specifies a device-specific revision identifier + * @progif_code: identifies a specific register-level programming interface + * @subclass_code: identifies more specifically the function of the device + * @baseclass_code: broadly classifies the type of function the device performs + * @cache_line_size: specifies the system cacheline size in units of DWORDs + * @subsys_vendor_id: vendor of the add-in card or subsystem + * @subsys_id: id specific to vendor + * @interrupt_pin: interrupt pin the device (or device function) uses + */ +struct pci_epf_header { + u16 vendorid; + u16 deviceid; + u8 revid; + u8 progif_code; + u8 subclass_code; + u8 baseclass_code; + u8 cache_line_size; + u16 subsys_vendor_id; + u16 subsys_id; + enum pci_interrupt_pin interrupt_pin; +}; + +/** + * struct pci_epf_ops - set of function pointers for performing EPF operations + * @bind: ops to perform when a EPC device has been bound to EPF device + * @unbind: ops to perform when a binding has been lost between a EPC device + * and EPF device + * @linkup: ops to perform when the EPC device has established a connection with + * a host system + */ +struct pci_epf_ops { + int (*bind)(struct pci_epf *epf); + void (*unbind)(struct pci_epf *epf); + void (*linkup)(struct pci_epf *epf); +}; + +/** + * struct pci_epf_driver - represents the PCI EPF driver + * @probe: ops to perform when a new EPF device has been bound to the EPF driver + * @remove: ops to perform when the binding between the EPF device and EPF + * driver is broken + * @driver: PCI EPF driver + * @ops: set of function pointers for performing EPF operations + * @owner: the owner of the module that registers the PCI EPF driver + * @group: configfs group corresponding to the PCI EPF driver + * @id_table: identifies EPF devices for probing + */ +struct pci_epf_driver { + int (*probe)(struct pci_epf *epf); + int (*remove)(struct pci_epf *epf); + + struct device_driver driver; + struct pci_epf_ops *ops; + struct module *owner; + struct config_group *group; + const struct pci_epf_device_id *id_table; +}; + +#define to_pci_epf_driver(drv) (container_of((drv), struct pci_epf_driver, \ + driver)) + +/** + * struct pci_epf_bar - represents the BAR of EPF device + * @phys_addr: physical address that should be mapped to the BAR + * @size: the size of the address space present in BAR + */ +struct pci_epf_bar { + dma_addr_t phys_addr; + size_t size; +}; + +/** + * struct pci_epf - represents the PCI EPF device + * @dev: the PCI EPF device + * @name: the name of the PCI EPF device + * @header: represents standard configuration header + * @bar: represents the BAR of EPF device + * @msi_interrupts: number of MSI interrupts required by this function + * @func_no: unique function number within this endpoint device + * @epc: the EPC device to which this EPF device is bound + * @driver: the EPF driver to which this EPF device is bound + * @list: to add pci_epf as a list of PCI endpoint functions to pci_epc + */ +struct pci_epf { + struct device dev; + const char *name; + struct pci_epf_header *header; + struct pci_epf_bar bar[6]; + u8 msi_interrupts; + u8 func_no; + + struct pci_epc *epc; + struct pci_epf_driver *driver; + struct list_head list; +}; + +#define to_pci_epf(epf_dev) container_of((epf_dev), struct pci_epf, dev) + +#define pci_epf_register_driver(driver) \ + __pci_epf_register_driver((driver), THIS_MODULE) + +static inline void epf_set_drvdata(struct pci_epf *epf, void *data) +{ + dev_set_drvdata(&epf->dev, data); +} + +static inline void *epf_get_drvdata(struct pci_epf *epf) +{ + return dev_get_drvdata(&epf->dev); +} + +struct pci_epf *pci_epf_create(const char *name); +void pci_epf_destroy(struct pci_epf *epf); +int __pci_epf_register_driver(struct pci_epf_driver *driver, + struct module *owner); +void pci_epf_unregister_driver(struct pci_epf_driver *driver); +void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar); +void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar); +int pci_epf_bind(struct pci_epf *epf); +void pci_epf_unbind(struct pci_epf *epf); +void pci_epf_linkup(struct pci_epf *epf); +#endif /* __LINUX_PCI_EPF_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index e2d1a124216a..4869e66dd659 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -28,6 +28,7 @@ #include <linux/kobject.h> #include <linux/atomic.h> #include <linux/device.h> +#include <linux/interrupt.h> #include <linux/io.h> #include <linux/resource_ext.h> #include <uapi/linux/pci.h> @@ -178,6 +179,15 @@ enum pci_dev_flags { PCI_DEV_FLAGS_NO_PM_RESET = (__force pci_dev_flags_t) (1 << 7), /* Get VPD from function 0 VPD */ PCI_DEV_FLAGS_VPD_REF_F0 = (__force pci_dev_flags_t) (1 << 8), + /* a non-root bridge where translation occurs, stop alias search here */ + PCI_DEV_FLAGS_BRIDGE_XLATE_ROOT = (__force pci_dev_flags_t) (1 << 9), + /* Do not use FLR even if device advertises PCI_AF_CAP */ + PCI_DEV_FLAGS_NO_FLR_RESET = (__force pci_dev_flags_t) (1 << 10), + /* + * Resume before calling the driver's system suspend hooks, disabling + * the direct_complete optimization. + */ + PCI_DEV_FLAGS_NEEDS_RESUME = (__force pci_dev_flags_t) (1 << 11), }; enum pci_irq_reroute_variant { @@ -297,7 +307,6 @@ struct pci_dev { u8 pm_cap; /* PM capability offset */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ - unsigned int pme_interrupt:1; unsigned int pme_poll:1; /* Poll device's PME status bit */ unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ @@ -351,6 +360,8 @@ struct pci_dev { unsigned int msix_enabled:1; unsigned int ari_enabled:1; /* ARI forwarding */ unsigned int ats_enabled:1; /* Address Translation Service */ + unsigned int pasid_enabled:1; /* Process Address Space ID */ + unsigned int pri_enabled:1; /* Page Request Interface */ unsigned int is_managed:1; unsigned int needs_freset:1; /* Dev requires fundamental reset */ unsigned int state_saved:1; @@ -358,13 +369,15 @@ struct pci_dev { unsigned int is_virtfn:1; unsigned int reset_fn:1; unsigned int is_hotplug_bridge:1; + unsigned int is_thunderbolt:1; /* Thunderbolt controller */ unsigned int __aer_firmware_first_valid:1; unsigned int __aer_firmware_first:1; - unsigned int broken_intx_masking:1; + unsigned int broken_intx_masking:1; /* INTx masking can't be used */ unsigned int io_window_1k:1; /* Intel P2P bridge 1K I/O windows */ unsigned int irq_managed:1; unsigned int has_secondary_link:1; unsigned int non_compliant_bars:1; /* broken BARs; ignore them */ + unsigned int is_probed:1; /* device probing in progress */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -393,9 +406,17 @@ struct pci_dev { u8 ats_stu; /* ATS Smallest Translation Unit */ atomic_t ats_ref_cnt; /* number of VFs with ATS enabled */ #endif +#ifdef CONFIG_PCI_PRI + u32 pri_reqs_alloc; /* Number of PRI requests allocated */ +#endif +#ifdef CONFIG_PCI_PASID + u16 pasid_features; +#endif phys_addr_t rom; /* Physical address of ROM if it's not from the BAR */ size_t romlen; /* Length of ROM if it's not from the BAR */ char *driver_override; /* Driver name to force a match */ + + unsigned long priv_flags; /* Private flags for the pci driver */ }; static inline struct pci_dev *pci_physfn(struct pci_dev *dev) @@ -424,6 +445,8 @@ struct pci_host_bridge { void *sysdata; int busnr; struct list_head windows; /* resource_entry */ + u8 (*swizzle_irq)(struct pci_dev *, u8 *); /* platform IRQ swizzler */ + int (*map_irq)(const struct pci_dev *, u8, u8); void (*release_fn)(struct pci_host_bridge *); void *release_data; struct msi_controller *msi; @@ -450,7 +473,9 @@ static inline struct pci_host_bridge *pci_host_bridge_from_priv(void *priv) } struct pci_host_bridge *pci_alloc_host_bridge(size_t priv); -int pci_register_host_bridge(struct pci_host_bridge *bridge); +struct pci_host_bridge *devm_pci_alloc_host_bridge(struct device *dev, + size_t priv); +void pci_free_host_bridge(struct pci_host_bridge *bridge); struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus); void pci_set_host_bridge_release(struct pci_host_bridge *bridge, @@ -678,14 +703,12 @@ struct pci_error_handlers { /* MMIO has been re-enabled, but not DMA */ pci_ers_result_t (*mmio_enabled)(struct pci_dev *dev); - /* PCI Express link has been reset */ - pci_ers_result_t (*link_reset)(struct pci_dev *dev); - /* PCI slot has been reset */ pci_ers_result_t (*slot_reset)(struct pci_dev *dev); /* PCI function reset prepare or completed */ - void (*reset_notify)(struct pci_dev *dev, bool prepare); + void (*reset_prepare)(struct pci_dev *dev); + void (*reset_done)(struct pci_dev *dev); /* Device driver may resume normal operations */ void (*resume)(struct pci_dev *dev); @@ -842,13 +865,10 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, int pci_bus_insert_busn_res(struct pci_bus *b, int bus, int busmax); int pci_bus_update_busn_res_end(struct pci_bus *b, int busmax); void pci_bus_release_busn_res(struct pci_bus *b); -struct pci_bus *pci_scan_root_bus_msi(struct device *parent, int bus, - struct pci_ops *ops, void *sysdata, - struct list_head *resources, - struct msi_controller *msi); struct pci_bus *pci_scan_root_bus(struct device *parent, int bus, struct pci_ops *ops, void *sysdata, struct list_head *resources); +int pci_scan_root_bus_bridge(struct pci_host_bridge *bridge); struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, int busnr); void pcie_update_link_speed(struct pci_bus *bus, u16 link_status); @@ -885,7 +905,6 @@ void pcibios_setup_bridge(struct pci_bus *bus, unsigned long type); void pci_sort_breadthfirst(void); #define dev_is_pci(d) ((d)->bus == &pci_bus_type) #define dev_is_pf(d) ((dev_is_pci(d) ? to_pci_dev(d)->is_physfn : false)) -#define dev_num_vf(d) ((dev_is_pci(d) ? pci_num_vf(to_pci_dev(d)) : 0)) /* Generic PCI functions exported to card drivers */ @@ -944,32 +963,12 @@ int pci_generic_config_write32(struct pci_bus *bus, unsigned int devfn, struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops); -static inline int pci_read_config_byte(const struct pci_dev *dev, int where, u8 *val) -{ - return pci_bus_read_config_byte(dev->bus, dev->devfn, where, val); -} -static inline int pci_read_config_word(const struct pci_dev *dev, int where, u16 *val) -{ - return pci_bus_read_config_word(dev->bus, dev->devfn, where, val); -} -static inline int pci_read_config_dword(const struct pci_dev *dev, int where, - u32 *val) -{ - return pci_bus_read_config_dword(dev->bus, dev->devfn, where, val); -} -static inline int pci_write_config_byte(const struct pci_dev *dev, int where, u8 val) -{ - return pci_bus_write_config_byte(dev->bus, dev->devfn, where, val); -} -static inline int pci_write_config_word(const struct pci_dev *dev, int where, u16 val) -{ - return pci_bus_write_config_word(dev->bus, dev->devfn, where, val); -} -static inline int pci_write_config_dword(const struct pci_dev *dev, int where, - u32 val) -{ - return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val); -} +int pci_read_config_byte(const struct pci_dev *dev, int where, u8 *val); +int pci_read_config_word(const struct pci_dev *dev, int where, u16 *val); +int pci_read_config_dword(const struct pci_dev *dev, int where, u32 *val); +int pci_write_config_byte(const struct pci_dev *dev, int where, u8 val); +int pci_write_config_word(const struct pci_dev *dev, int where, u16 val); +int pci_write_config_dword(const struct pci_dev *dev, int where, u32 val); int pcie_capability_read_word(struct pci_dev *dev, int pos, u16 *val); int pcie_capability_read_dword(struct pci_dev *dev, int pos, u32 *val); @@ -1019,6 +1018,15 @@ int __must_check pci_reenable_device(struct pci_dev *); int __must_check pcim_enable_device(struct pci_dev *pdev); void pcim_pin_device(struct pci_dev *pdev); +static inline bool pci_intx_mask_supported(struct pci_dev *pdev) +{ + /* + * INTx masking is supported if PCI_COMMAND_INTX_DISABLE is + * writable and no quirk has marked the feature broken. + */ + return !pdev->broken_intx_masking; +} + static inline int pci_is_enabled(struct pci_dev *pdev) { return (atomic_read(&pdev->enable_cnt) > 0); @@ -1042,7 +1050,6 @@ int __must_check pci_set_mwi(struct pci_dev *dev); int pci_try_set_mwi(struct pci_dev *dev); void pci_clear_mwi(struct pci_dev *dev); void pci_intx(struct pci_dev *dev, int enable); -bool pci_intx_mask_supported(struct pci_dev *dev); bool pci_check_and_mask_intx(struct pci_dev *dev); bool pci_check_and_unmask_intx(struct pci_dev *dev); int pci_wait_for_pending(struct pci_dev *dev, int pos, u16 mask); @@ -1056,6 +1063,7 @@ int pcie_get_mps(struct pci_dev *dev); int pcie_set_mps(struct pci_dev *dev, int mps); int pcie_get_minimum_link(struct pci_dev *dev, enum pci_bus_speed *speed, enum pcie_link_width *width); +void pcie_flr(struct pci_dev *dev); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); @@ -1076,6 +1084,11 @@ int pci_select_bars(struct pci_dev *dev, unsigned long flags); bool pci_device_is_present(struct pci_dev *pdev); void pci_ignore_hotplug(struct pci_dev *dev); +int __printf(6, 7) pci_request_irq(struct pci_dev *dev, unsigned int nr, + irq_handler_t handler, irq_handler_t thread_fn, void *dev_id, + const char *fmt, ...); +void pci_free_irq(struct pci_dev *dev, unsigned int nr, void *dev_id); + /* ROM control related routines */ int pci_enable_rom(struct pci_dev *pdev); void pci_disable_rom(struct pci_dev *pdev); @@ -1103,8 +1116,7 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); void pci_pme_active(struct pci_dev *dev, bool enable); -int __pci_enable_wake(struct pci_dev *dev, pci_power_t state, - bool runtime, bool enable); +int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable); int pci_wake_from_d3(struct pci_dev *dev, bool enable); int pci_prepare_to_sleep(struct pci_dev *dev); int pci_back_from_sleep(struct pci_dev *dev); @@ -1114,12 +1126,6 @@ void pci_pme_wakeup_bus(struct pci_bus *bus); void pci_d3cold_enable(struct pci_dev *dev); void pci_d3cold_disable(struct pci_dev *dev); -static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state, - bool enable) -{ - return __pci_enable_wake(dev, state, false, enable); -} - /* PCI Virtual Channel */ int pci_save_vc_state(struct pci_dev *dev); void pci_restore_vc_state(struct pci_dev *dev); @@ -1156,6 +1162,7 @@ void pdev_enable_device(struct pci_dev *); int pci_enable_resources(struct pci_dev *, int mask); void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *), int (*)(const struct pci_dev *, u8, u8)); +void pci_assign_irq(struct pci_dev *dev); struct resource *pci_find_resource(struct pci_dev *dev, struct resource *res); #define HAVE_PCI_REQ_REGIONS 2 int __must_check pci_request_regions(struct pci_dev *, const char *); @@ -1203,6 +1210,11 @@ unsigned long pci_address_to_pio(phys_addr_t addr); phys_addr_t pci_pio_to_address(unsigned long pio); int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr); void pci_unmap_iospace(struct resource *res); +void __iomem *devm_pci_remap_cfgspace(struct device *dev, + resource_size_t offset, + resource_size_t size); +void __iomem *devm_pci_remap_cfg_resource(struct device *dev, + struct resource *res); static inline pci_bus_addr_t pci_bus_address(struct pci_dev *pdev, int bar) { @@ -1301,22 +1313,12 @@ struct msix_entry { #ifdef CONFIG_PCI_MSI int pci_msi_vec_count(struct pci_dev *dev); -void pci_msi_shutdown(struct pci_dev *dev); void pci_disable_msi(struct pci_dev *dev); int pci_msix_vec_count(struct pci_dev *dev); -int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec); -void pci_msix_shutdown(struct pci_dev *dev); void pci_disable_msix(struct pci_dev *dev); void pci_restore_msi_state(struct pci_dev *dev); int pci_msi_enabled(void); -int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec); -static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec) -{ - int rc = pci_enable_msi_range(dev, nvec, nvec); - if (rc < 0) - return rc; - return 0; -} +int pci_enable_msi(struct pci_dev *dev); int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec); static inline int pci_enable_msix_exact(struct pci_dev *dev, @@ -1334,23 +1336,16 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, void pci_free_irq_vectors(struct pci_dev *dev); int pci_irq_vector(struct pci_dev *dev, unsigned int nr); const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec); +int pci_irq_get_node(struct pci_dev *pdev, int vec); #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } -static inline void pci_msi_shutdown(struct pci_dev *dev) { } static inline void pci_disable_msi(struct pci_dev *dev) { } static inline int pci_msix_vec_count(struct pci_dev *dev) { return -ENOSYS; } -static inline int pci_enable_msix(struct pci_dev *dev, - struct msix_entry *entries, int nvec) -{ return -ENOSYS; } -static inline void pci_msix_shutdown(struct pci_dev *dev) { } static inline void pci_disable_msix(struct pci_dev *dev) { } static inline void pci_restore_msi_state(struct pci_dev *dev) { } static inline int pci_msi_enabled(void) { return 0; } -static inline int pci_enable_msi_range(struct pci_dev *dev, int minvec, - int maxvec) -{ return -ENOSYS; } -static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec) +static inline int pci_enable_msi(struct pci_dev *dev) { return -ENOSYS; } static inline int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec) @@ -1364,9 +1359,9 @@ pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, unsigned int max_vecs, unsigned int flags, const struct irq_affinity *aff_desc) { - if (min_vecs > 1) - return -EINVAL; - return 1; + if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1 && dev->irq) + return 1; + return -ENOSPC; } static inline void pci_free_irq_vectors(struct pci_dev *dev) @@ -1384,6 +1379,11 @@ static inline const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, { return cpu_possible_mask; } + +static inline int pci_irq_get_node(struct pci_dev *pdev, int vec) +{ + return first_online_node; +} #endif static inline int @@ -1426,8 +1426,6 @@ static inline void pcie_set_ecrc_checking(struct pci_dev *dev) { } static inline void pcie_ecrc_get_policy(char *str) { } #endif -#define pci_enable_msi(pdev) pci_enable_msi_exact(pdev, 1) - #ifdef CONFIG_HT_IRQ /* The functions a driver should call */ int ht_create_irq(struct pci_dev *dev, int idx); @@ -1630,13 +1628,42 @@ static inline int pci_get_new_domain_nr(void) { return -ENOSYS; } #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) -#define dev_num_vf(d) (0) #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ #include <asm/pci.h> +/* These two functions provide almost identical functionality. Depennding + * on the architecture, one will be implemented as a wrapper around the + * other (in drivers/pci/mmap.c). + * + * pci_mmap_resource_range() maps a specific BAR, and vm->vm_pgoff + * is expected to be an offset within that region. + * + * pci_mmap_page_range() is the legacy architecture-specific interface, + * which accepts a "user visible" resource address converted by + * pci_resource_to_user(), as used in the legacy mmap() interface in + * /proc/bus/pci/. + */ +int pci_mmap_resource_range(struct pci_dev *dev, int bar, + struct vm_area_struct *vma, + enum pci_mmap_state mmap_state, int write_combine); +int pci_mmap_page_range(struct pci_dev *pdev, int bar, + struct vm_area_struct *vma, + enum pci_mmap_state mmap_state, int write_combine); + +#ifndef arch_can_pci_mmap_wc +#define arch_can_pci_mmap_wc() 0 +#endif + +#ifndef arch_can_pci_mmap_io +#define arch_can_pci_mmap_io() 0 +#define pci_iobar_pfn(pdev, bar, vma) (-EINVAL) +#else +int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma); +#endif + #ifndef pci_root_bus_fwnode #define pci_root_bus_fwnode(bus) NULL #endif @@ -2171,6 +2198,28 @@ static inline bool pci_ari_enabled(struct pci_bus *bus) return bus->self && bus->self->ari_enabled; } +/** + * pci_is_thunderbolt_attached - whether device is on a Thunderbolt daisy chain + * @pdev: PCI device to check + * + * Walk upwards from @pdev and check for each encountered bridge if it's part + * of a Thunderbolt controller. Reaching the host bridge means @pdev is not + * Thunderbolt-attached. (But rather soldered to the mainboard usually.) + */ +static inline bool pci_is_thunderbolt_attached(struct pci_dev *pdev) +{ + struct pci_dev *parent = pdev; + + if (pdev->is_thunderbolt) + return true; + + while ((parent = pci_upstream_bridge(parent))) + if (parent->is_thunderbolt) + return true; + + return false; +} + /* provide the legacy pci_dma_* API */ #include <linux/pci-dma-compat.h> diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 73dda0edcb97..c71e532da458 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -862,6 +862,8 @@ #define PCI_DEVICE_ID_TI_X620 0xac8d #define PCI_DEVICE_ID_TI_X420 0xac8e #define PCI_DEVICE_ID_TI_XX20_FM 0xac8f +#define PCI_DEVICE_ID_TI_DRA74x 0xb500 +#define PCI_DEVICE_ID_TI_DRA72x 0xb501 #define PCI_VENDOR_ID_SONY 0x104d @@ -1371,6 +1373,8 @@ #define PCI_DEVICE_ID_TTI_HPT374 0x0008 #define PCI_DEVICE_ID_TTI_HPT372N 0x0009 /* apparently a 372N variant? */ +#define PCI_VENDOR_ID_SIGMA 0x1105 + #define PCI_VENDOR_ID_VIA 0x1106 #define PCI_DEVICE_ID_VIA_8763_0 0x0198 #define PCI_DEVICE_ID_VIA_8380_0 0x0204 @@ -2516,6 +2520,8 @@ #define PCI_DEVICE_ID_KORENIX_JETCARDF2 0x1700 #define PCI_DEVICE_ID_KORENIX_JETCARDF3 0x17ff +#define PCI_VENDOR_ID_HUAWEI 0x19e5 + #define PCI_VENDOR_ID_NETRONOME 0x19ee #define PCI_DEVICE_ID_NETRONOME_NFP3200 0x3200 #define PCI_DEVICE_ID_NETRONOME_NFP3240 0x3240 diff --git a/include/linux/pe.h b/include/linux/pe.h index e170b95e763b..143ce75be5f0 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -23,34 +23,6 @@ #define MZ_MAGIC 0x5a4d /* "MZ" */ -struct mz_hdr { - uint16_t magic; /* MZ_MAGIC */ - uint16_t lbsize; /* size of last used block */ - uint16_t blocks; /* pages in file, 0x3 */ - uint16_t relocs; /* relocations */ - uint16_t hdrsize; /* header size in "paragraphs" */ - uint16_t min_extra_pps; /* .bss */ - uint16_t max_extra_pps; /* runtime limit for the arena size */ - uint16_t ss; /* relative stack segment */ - uint16_t sp; /* initial %sp register */ - uint16_t checksum; /* word checksum */ - uint16_t ip; /* initial %ip register */ - uint16_t cs; /* initial %cs relative to load segment */ - uint16_t reloc_table_offset; /* offset of the first relocation */ - uint16_t overlay_num; /* overlay number. set to 0. */ - uint16_t reserved0[4]; /* reserved */ - uint16_t oem_id; /* oem identifier */ - uint16_t oem_info; /* oem specific */ - uint16_t reserved1[10]; /* reserved */ - uint32_t peaddr; /* address of pe header */ - char message[64]; /* message to print */ -}; - -struct mz_reloc { - uint16_t offset; - uint16_t segment; -}; - #define PE_MAGIC 0x00004550 /* "PE\0\0" */ #define PE_OPT_MAGIC_PE32 0x010b #define PE_OPT_MAGIC_PE32_ROM 0x0107 @@ -62,6 +34,7 @@ struct mz_reloc { #define IMAGE_FILE_MACHINE_AMD64 0x8664 #define IMAGE_FILE_MACHINE_ARM 0x01c0 #define IMAGE_FILE_MACHINE_ARMV7 0x01c4 +#define IMAGE_FILE_MACHINE_ARM64 0xaa64 #define IMAGE_FILE_MACHINE_EBC 0x0ebc #define IMAGE_FILE_MACHINE_I386 0x014c #define IMAGE_FILE_MACHINE_IA64 0x0200 @@ -98,17 +71,6 @@ struct mz_reloc { #define IMAGE_FILE_UP_SYSTEM_ONLY 0x4000 #define IMAGE_FILE_BYTES_REVERSED_HI 0x8000 -struct pe_hdr { - uint32_t magic; /* PE magic */ - uint16_t machine; /* machine type */ - uint16_t sections; /* number of sections */ - uint32_t timestamp; /* time_t */ - uint32_t symbol_table; /* symbol table offset */ - uint32_t symbols; /* number of symbols */ - uint16_t opt_hdr_size; /* size of optional header */ - uint16_t flags; /* flags */ -}; - #define IMAGE_FILE_OPT_ROM_MAGIC 0x107 #define IMAGE_FILE_OPT_PE32_MAGIC 0x10b #define IMAGE_FILE_OPT_PE32_PLUS_MAGIC 0x20b @@ -134,6 +96,95 @@ struct pe_hdr { #define IMAGE_DLLCHARACTERISTICS_WDM_DRIVER 0x2000 #define IMAGE_DLLCHARACTERISTICS_TERMINAL_SERVER_AWARE 0x8000 +/* they actually defined 0x00000000 as well, but I think we'll skip that one. */ +#define IMAGE_SCN_RESERVED_0 0x00000001 +#define IMAGE_SCN_RESERVED_1 0x00000002 +#define IMAGE_SCN_RESERVED_2 0x00000004 +#define IMAGE_SCN_TYPE_NO_PAD 0x00000008 /* don't pad - obsolete */ +#define IMAGE_SCN_RESERVED_3 0x00000010 +#define IMAGE_SCN_CNT_CODE 0x00000020 /* .text */ +#define IMAGE_SCN_CNT_INITIALIZED_DATA 0x00000040 /* .data */ +#define IMAGE_SCN_CNT_UNINITIALIZED_DATA 0x00000080 /* .bss */ +#define IMAGE_SCN_LNK_OTHER 0x00000100 /* reserved */ +#define IMAGE_SCN_LNK_INFO 0x00000200 /* .drectve comments */ +#define IMAGE_SCN_RESERVED_4 0x00000400 +#define IMAGE_SCN_LNK_REMOVE 0x00000800 /* .o only - scn to be rm'd*/ +#define IMAGE_SCN_LNK_COMDAT 0x00001000 /* .o only - COMDAT data */ +#define IMAGE_SCN_RESERVED_5 0x00002000 /* spec omits this */ +#define IMAGE_SCN_RESERVED_6 0x00004000 /* spec omits this */ +#define IMAGE_SCN_GPREL 0x00008000 /* global pointer referenced data */ +/* spec lists 0x20000 twice, I suspect they meant 0x10000 for one of them */ +#define IMAGE_SCN_MEM_PURGEABLE 0x00010000 /* reserved for "future" use */ +#define IMAGE_SCN_16BIT 0x00020000 /* reserved for "future" use */ +#define IMAGE_SCN_LOCKED 0x00040000 /* reserved for "future" use */ +#define IMAGE_SCN_PRELOAD 0x00080000 /* reserved for "future" use */ +/* and here they just stuck a 1-byte integer in the middle of a bitfield */ +#define IMAGE_SCN_ALIGN_1BYTES 0x00100000 /* it does what it says on the box */ +#define IMAGE_SCN_ALIGN_2BYTES 0x00200000 +#define IMAGE_SCN_ALIGN_4BYTES 0x00300000 +#define IMAGE_SCN_ALIGN_8BYTES 0x00400000 +#define IMAGE_SCN_ALIGN_16BYTES 0x00500000 +#define IMAGE_SCN_ALIGN_32BYTES 0x00600000 +#define IMAGE_SCN_ALIGN_64BYTES 0x00700000 +#define IMAGE_SCN_ALIGN_128BYTES 0x00800000 +#define IMAGE_SCN_ALIGN_256BYTES 0x00900000 +#define IMAGE_SCN_ALIGN_512BYTES 0x00a00000 +#define IMAGE_SCN_ALIGN_1024BYTES 0x00b00000 +#define IMAGE_SCN_ALIGN_2048BYTES 0x00c00000 +#define IMAGE_SCN_ALIGN_4096BYTES 0x00d00000 +#define IMAGE_SCN_ALIGN_8192BYTES 0x00e00000 +#define IMAGE_SCN_LNK_NRELOC_OVFL 0x01000000 /* extended relocations */ +#define IMAGE_SCN_MEM_DISCARDABLE 0x02000000 /* scn can be discarded */ +#define IMAGE_SCN_MEM_NOT_CACHED 0x04000000 /* cannot be cached */ +#define IMAGE_SCN_MEM_NOT_PAGED 0x08000000 /* not pageable */ +#define IMAGE_SCN_MEM_SHARED 0x10000000 /* can be shared */ +#define IMAGE_SCN_MEM_EXECUTE 0x20000000 /* can be executed as code */ +#define IMAGE_SCN_MEM_READ 0x40000000 /* readable */ +#define IMAGE_SCN_MEM_WRITE 0x80000000 /* writeable */ + +#define IMAGE_DEBUG_TYPE_CODEVIEW 2 + +#ifndef __ASSEMBLY__ + +struct mz_hdr { + uint16_t magic; /* MZ_MAGIC */ + uint16_t lbsize; /* size of last used block */ + uint16_t blocks; /* pages in file, 0x3 */ + uint16_t relocs; /* relocations */ + uint16_t hdrsize; /* header size in "paragraphs" */ + uint16_t min_extra_pps; /* .bss */ + uint16_t max_extra_pps; /* runtime limit for the arena size */ + uint16_t ss; /* relative stack segment */ + uint16_t sp; /* initial %sp register */ + uint16_t checksum; /* word checksum */ + uint16_t ip; /* initial %ip register */ + uint16_t cs; /* initial %cs relative to load segment */ + uint16_t reloc_table_offset; /* offset of the first relocation */ + uint16_t overlay_num; /* overlay number. set to 0. */ + uint16_t reserved0[4]; /* reserved */ + uint16_t oem_id; /* oem identifier */ + uint16_t oem_info; /* oem specific */ + uint16_t reserved1[10]; /* reserved */ + uint32_t peaddr; /* address of pe header */ + char message[64]; /* message to print */ +}; + +struct mz_reloc { + uint16_t offset; + uint16_t segment; +}; + +struct pe_hdr { + uint32_t magic; /* PE magic */ + uint16_t machine; /* machine type */ + uint16_t sections; /* number of sections */ + uint32_t timestamp; /* time_t */ + uint32_t symbol_table; /* symbol table offset */ + uint32_t symbols; /* number of symbols */ + uint16_t opt_hdr_size; /* size of optional header */ + uint16_t flags; /* flags */ +}; + /* the fact that pe32 isn't padded where pe32+ is 64-bit means union won't * work right. vomit. */ struct pe32_opt_hdr { @@ -243,52 +294,6 @@ struct section_header { uint32_t flags; }; -/* they actually defined 0x00000000 as well, but I think we'll skip that one. */ -#define IMAGE_SCN_RESERVED_0 0x00000001 -#define IMAGE_SCN_RESERVED_1 0x00000002 -#define IMAGE_SCN_RESERVED_2 0x00000004 -#define IMAGE_SCN_TYPE_NO_PAD 0x00000008 /* don't pad - obsolete */ -#define IMAGE_SCN_RESERVED_3 0x00000010 -#define IMAGE_SCN_CNT_CODE 0x00000020 /* .text */ -#define IMAGE_SCN_CNT_INITIALIZED_DATA 0x00000040 /* .data */ -#define IMAGE_SCN_CNT_UNINITIALIZED_DATA 0x00000080 /* .bss */ -#define IMAGE_SCN_LNK_OTHER 0x00000100 /* reserved */ -#define IMAGE_SCN_LNK_INFO 0x00000200 /* .drectve comments */ -#define IMAGE_SCN_RESERVED_4 0x00000400 -#define IMAGE_SCN_LNK_REMOVE 0x00000800 /* .o only - scn to be rm'd*/ -#define IMAGE_SCN_LNK_COMDAT 0x00001000 /* .o only - COMDAT data */ -#define IMAGE_SCN_RESERVED_5 0x00002000 /* spec omits this */ -#define IMAGE_SCN_RESERVED_6 0x00004000 /* spec omits this */ -#define IMAGE_SCN_GPREL 0x00008000 /* global pointer referenced data */ -/* spec lists 0x20000 twice, I suspect they meant 0x10000 for one of them */ -#define IMAGE_SCN_MEM_PURGEABLE 0x00010000 /* reserved for "future" use */ -#define IMAGE_SCN_16BIT 0x00020000 /* reserved for "future" use */ -#define IMAGE_SCN_LOCKED 0x00040000 /* reserved for "future" use */ -#define IMAGE_SCN_PRELOAD 0x00080000 /* reserved for "future" use */ -/* and here they just stuck a 1-byte integer in the middle of a bitfield */ -#define IMAGE_SCN_ALIGN_1BYTES 0x00100000 /* it does what it says on the box */ -#define IMAGE_SCN_ALIGN_2BYTES 0x00200000 -#define IMAGE_SCN_ALIGN_4BYTES 0x00300000 -#define IMAGE_SCN_ALIGN_8BYTES 0x00400000 -#define IMAGE_SCN_ALIGN_16BYTES 0x00500000 -#define IMAGE_SCN_ALIGN_32BYTES 0x00600000 -#define IMAGE_SCN_ALIGN_64BYTES 0x00700000 -#define IMAGE_SCN_ALIGN_128BYTES 0x00800000 -#define IMAGE_SCN_ALIGN_256BYTES 0x00900000 -#define IMAGE_SCN_ALIGN_512BYTES 0x00a00000 -#define IMAGE_SCN_ALIGN_1024BYTES 0x00b00000 -#define IMAGE_SCN_ALIGN_2048BYTES 0x00c00000 -#define IMAGE_SCN_ALIGN_4096BYTES 0x00d00000 -#define IMAGE_SCN_ALIGN_8192BYTES 0x00e00000 -#define IMAGE_SCN_LNK_NRELOC_OVFL 0x01000000 /* extended relocations */ -#define IMAGE_SCN_MEM_DISCARDABLE 0x02000000 /* scn can be discarded */ -#define IMAGE_SCN_MEM_NOT_CACHED 0x04000000 /* cannot be cached */ -#define IMAGE_SCN_MEM_NOT_PAGED 0x08000000 /* not pageable */ -#define IMAGE_SCN_MEM_SHARED 0x10000000 /* can be shared */ -#define IMAGE_SCN_MEM_EXECUTE 0x20000000 /* can be executed as code */ -#define IMAGE_SCN_MEM_READ 0x40000000 /* readable */ -#define IMAGE_SCN_MEM_WRITE 0x80000000 /* writeable */ - enum x64_coff_reloc_type { IMAGE_REL_AMD64_ABSOLUTE = 0, IMAGE_REL_AMD64_ADDR64, @@ -445,4 +450,6 @@ struct win_certificate { uint16_t cert_type; }; +#endif /* !__ASSEMBLY__ */ + #endif /* __LINUX_PE_H */ diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 3a481a49546e..c13dceb87b60 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -99,6 +99,7 @@ int __must_check percpu_ref_init(struct percpu_ref *ref, void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch); +void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 5b2e6159b744..93664f022ecf 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -4,15 +4,15 @@ #include <linux/atomic.h> #include <linux/rwsem.h> #include <linux/percpu.h> -#include <linux/wait.h> +#include <linux/rcuwait.h> #include <linux/rcu_sync.h> #include <linux/lockdep.h> struct percpu_rw_semaphore { struct rcu_sync rss; unsigned int __percpu *read_count; - struct rw_semaphore rw_sem; - wait_queue_head_t writer; + struct rw_semaphore rw_sem; /* slowpath */ + struct rcuwait writer; /* blocked writer */ int readers_block; }; @@ -22,7 +22,7 @@ static struct percpu_rw_semaphore name = { \ .rss = __RCU_SYNC_INITIALIZER(name.rss, RCU_SCHED_SYNC), \ .read_count = &__percpu_rwsem_rc_##name, \ .rw_sem = __RWSEM_INITIALIZER(name.rw_sem), \ - .writer = __WAIT_QUEUE_HEAD_INITIALIZER(name.writer), \ + .writer = __RCUWAIT_INITIALIZER(name.writer), \ } extern int __percpu_down_read(struct percpu_rw_semaphore *, int); diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 56939d3f6e53..491b3f5a5f8a 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -110,6 +110,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, #endif extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); +extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr); extern bool is_kernel_percpu_address(unsigned long addr); #if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 84a109449610..ec065387f443 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -39,7 +39,8 @@ int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); -void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); +void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, + s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); @@ -50,7 +51,7 @@ static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { - __percpu_counter_add(fbc, amount, percpu_counter_batch); + percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) @@ -136,7 +137,7 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount) } static inline void -__percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch) +percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { percpu_counter_add(fbc, amount); } diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 8462da266089..1360dd6d5e61 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -75,6 +75,8 @@ struct pmu_hw_events { * already have to allocate this struct per cpu. */ struct arm_pmu *percpu_pmu; + + int irq; }; enum armpmu_attr_groups { @@ -88,7 +90,6 @@ struct arm_pmu { struct pmu pmu; cpumask_t active_irqs; cpumask_t supported_cpus; - int *irq_affinity; char *name; irqreturn_t (*handle_irq)(int irq_num, void *dev); void (*enable)(struct perf_event *event); @@ -104,12 +105,8 @@ struct arm_pmu { void (*start)(struct arm_pmu *); void (*stop)(struct arm_pmu *); void (*reset)(void *); - int (*request_irq)(struct arm_pmu *, irq_handler_t handler); - void (*free_irq)(struct arm_pmu *); int (*map_event)(struct perf_event *event); int num_events; - atomic_t active_events; - struct mutex reserve_mutex; u64 max_period; bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 @@ -120,6 +117,9 @@ struct arm_pmu { struct notifier_block cpu_pm_nb; /* the attr_groups array must be NULL-terminated */ const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1]; + + /* Only to be used by ACPI probing code */ + unsigned long acpi_cpuid; }; #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) @@ -135,10 +135,12 @@ int armpmu_map_event(struct perf_event *event, [PERF_COUNT_HW_CACHE_RESULT_MAX], u32 raw_event_mask); +typedef int (*armpmu_init_fn)(struct arm_pmu *); + struct pmu_probe_info { unsigned int cpuid; unsigned int mask; - int (*init)(struct arm_pmu *); + armpmu_init_fn init; }; #define PMU_PROBE(_cpuid, _mask, _fn) \ @@ -160,6 +162,21 @@ int arm_pmu_device_probe(struct platform_device *pdev, const struct of_device_id *of_table, const struct pmu_probe_info *probe_table); +#ifdef CONFIG_ACPI +int arm_pmu_acpi_probe(armpmu_init_fn init_fn); +#else +static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; } +#endif + +/* Internal functions only for core arm_pmu code */ +struct arm_pmu *armpmu_alloc(void); +void armpmu_free(struct arm_pmu *pmu); +int armpmu_register(struct arm_pmu *pmu); +int armpmu_request_irqs(struct arm_pmu *armpmu); +void armpmu_free_irqs(struct arm_pmu *armpmu); +int armpmu_request_irq(struct arm_pmu *armpmu, int cpu); +void armpmu_free_irq(struct arm_pmu *armpmu, int cpu); + #define ARMV8_PMU_PDEV_NAME "armv8-pmu" #endif /* CONFIG_ARM_PMU */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 78ed8105e64d..a3b873fc59e4 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -165,6 +165,13 @@ struct hw_perf_event { struct list_head bp_list; }; #endif + struct { /* amd_iommu */ + u8 iommu_bank; + u8 iommu_cntr; + u16 padding; + u64 conf; + u64 conf1; + }; }; /* * If the event is a per task event, this will point to the task in @@ -482,6 +489,7 @@ struct perf_addr_filter { * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. + * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). @@ -489,6 +497,7 @@ struct perf_addr_filter { struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; + unsigned int nr_file_filters; }; /** @@ -785,13 +794,15 @@ struct perf_cpu_context { ktime_t hrtimer_interval; unsigned int hrtimer_active; - struct pmu *unique_pmu; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; + struct list_head cgrp_cpuctx_entry; #endif struct list_head sched_cb_entry; int sched_cb_usage; + + int online; }; struct perf_output_handle { @@ -799,6 +810,7 @@ struct perf_output_handle { struct ring_buffer *rb; unsigned long wakeup; unsigned long size; + u64 aux_flags; union { void *addr; unsigned long head; @@ -847,10 +859,11 @@ perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, - unsigned long size, bool truncated); + unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); +extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); @@ -885,7 +898,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); -extern u64 perf_event_read_local(struct perf_event *event); +int perf_event_read_local(struct perf_event *event, u64 *value); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -1110,6 +1123,7 @@ extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); +extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); /* Callchains */ @@ -1265,8 +1279,8 @@ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void -perf_aux_output_end(struct perf_output_handle *handle, unsigned long size, - bool truncated) { } +perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) + { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } @@ -1289,7 +1303,10 @@ static inline const struct perf_event_attr *perf_event_attrs(struct perf_event * { return ERR_PTR(-EINVAL); } -static inline u64 perf_event_read_local(struct perf_event *event) { return -EINVAL; } +static inline int perf_event_read_local(struct perf_event *event, u64 *value) +{ + return -EINVAL; +} static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } @@ -1313,6 +1330,7 @@ static inline int perf_unregister_guest_info_callbacks static inline void perf_event_mmap(struct vm_area_struct *vma) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } +static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h index a5f98d53d732..9b7dd59fe28d 100644 --- a/include/linux/perf_regs.h +++ b/include/linux/perf_regs.h @@ -1,6 +1,8 @@ #ifndef _LINUX_PERF_REGS_H #define _LINUX_PERF_REGS_H +#include <linux/sched/task_stack.h> + struct perf_regs { __u64 abi; struct pt_regs *regs; diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index a3d90b9da18d..a49b3259cad7 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -15,6 +15,12 @@ #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) #define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4)) +#define PFN_FLAGS_TRACE \ + { PFN_SG_CHAIN, "SG_CHAIN" }, \ + { PFN_SG_LAST, "SG_LAST" }, \ + { PFN_DEV, "DEV" }, \ + { PFN_MAP, "MAP" } + static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags) { pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), }; @@ -84,6 +90,13 @@ static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot) { return pfn_pmd(pfn_t_to_pfn(pfn), pgprot); } + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static inline pud_t pfn_t_pud(pfn_t pfn, pgprot_t pgprot) +{ + return pfn_pud(pfn_t_to_pfn(pfn), pgprot); +} +#endif #endif #ifdef __HAVE_ARCH_PTE_DEVMAP @@ -100,5 +113,10 @@ static inline bool pfn_t_devmap(pfn_t pfn) } pte_t pte_mkdevmap(pte_t pte); pmd_t pmd_mkdevmap(pmd_t pmd); +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) +pud_t pud_mkdevmap(pud_t pud); #endif +#endif /* __HAVE_ARCH_PTE_DEVMAP */ + #endif /* _LINUX_PFN_T_H_ */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 7fc1105605bf..2a9567bb8186 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -58,13 +58,13 @@ #define PHY_IGNORE_INTERRUPT -2 #define PHY_HAS_INTERRUPT 0x00000001 -#define PHY_HAS_MAGICANEG 0x00000002 -#define PHY_IS_INTERNAL 0x00000004 +#define PHY_IS_INTERNAL 0x00000002 #define MDIO_DEVICE_IS_PHY 0x80000000 /* Interface Mode definitions */ typedef enum { PHY_INTERFACE_MODE_NA, + PHY_INTERFACE_MODE_INTERNAL, PHY_INTERFACE_MODE_MII, PHY_INTERFACE_MODE_GMII, PHY_INTERFACE_MODE_SGMII, @@ -81,6 +81,12 @@ typedef enum { PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, + PHY_INTERFACE_MODE_1000BASEX, + PHY_INTERFACE_MODE_2500BASEX, + PHY_INTERFACE_MODE_RXAUI, + PHY_INTERFACE_MODE_XAUI, + /* 10GBASE-KR, XFI, SFI - single lane 10G Serdes */ + PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -109,6 +115,8 @@ static inline const char *phy_modes(phy_interface_t interface) switch (interface) { case PHY_INTERFACE_MODE_NA: return ""; + case PHY_INTERFACE_MODE_INTERNAL: + return "internal"; case PHY_INTERFACE_MODE_MII: return "mii"; case PHY_INTERFACE_MODE_GMII: @@ -141,6 +149,16 @@ static inline const char *phy_modes(phy_interface_t interface) return "qsgmii"; case PHY_INTERFACE_MODE_TRGMII: return "trgmii"; + case PHY_INTERFACE_MODE_1000BASEX: + return "1000base-x"; + case PHY_INTERFACE_MODE_2500BASEX: + return "2500base-x"; + case PHY_INTERFACE_MODE_RXAUI: + return "rxaui"; + case PHY_INTERFACE_MODE_XAUI: + return "xaui"; + case PHY_INTERFACE_MODE_10GKR: + return "10gbase-kr"; default: return "unknown"; } @@ -157,11 +175,7 @@ static inline const char *phy_modes(phy_interface_t interface) /* Used when trying to connect to a specific phy (mii bus id:phy device id) */ #define PHY_ID_FMT "%s:%02x" -/* - * Need to be a little smaller than phydev->dev.bus_id to leave room - * for the ":%02x" - */ -#define MII_BUS_ID_SIZE (20 - 3) +#define MII_BUS_ID_SIZE 61 /* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit IEEE 802.3ae clause 45 addressing mode used by 10GIGE phy chips. */ @@ -212,6 +226,11 @@ struct mii_bus { * matching its address */ int irq[PHY_MAX_ADDR]; + + /* GPIO reset pulse width in microseconds */ + int reset_delay_us; + /* RESET GPIO descriptor pointer */ + struct gpio_desc *reset_gpiod; }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) @@ -352,6 +371,8 @@ struct phy_c45_device_ids { * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc. * has_fixups: Set to true if this phy has fixups/quirks. * suspended: Set to true if this phy has been suspended successfully. + * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. + * loopback_enabled: Set true if this phy has been loopbacked successfully. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. * link_timeout: The number of timer firings to wait before the @@ -388,6 +409,8 @@ struct phy_device { bool is_pseudo_fixed_link; bool has_fixups; bool suspended; + bool sysfs_links; + bool loopback_enabled; enum phy_state state; @@ -582,23 +605,29 @@ struct phy_driver { */ void (*link_change_notify)(struct phy_device *dev); - /* A function provided by a phy specific driver to override the - * the PHY driver framework support for reading a MMD register - * from the PHY. If not supported, return -1. This function is - * optional for PHY specific drivers, if not provided then the - * default MMD read function is used by the PHY framework. + /* + * Phy specific driver override for reading a MMD register. + * This function is optional for PHY specific drivers. When + * not provided, the default MMD read function will be used + * by phy_read_mmd(), which will use either a direct read for + * Clause 45 PHYs or an indirect read for Clause 22 PHYs. + * devnum is the MMD device number within the PHY device, + * regnum is the register within the selected MMD device. */ - int (*read_mmd_indirect)(struct phy_device *dev, int ptrad, - int devnum, int regnum); - - /* A function provided by a phy specific driver to override the - * the PHY driver framework support for writing a MMD register - * from the PHY. This function is optional for PHY specific drivers, - * if not provided then the default MMD read function is used by - * the PHY framework. + int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum); + + /* + * Phy specific driver override for writing a MMD register. + * This function is optional for PHY specific drivers. When + * not provided, the default MMD write function will be used + * by phy_write_mmd(), which will use either a direct write for + * Clause 45 PHYs, or an indirect write for Clause 22 PHYs. + * devnum is the MMD device number within the PHY device, + * regnum is the register within the selected MMD device. + * val is the value to be written. */ - void (*write_mmd_indirect)(struct phy_device *dev, int ptrad, - int devnum, int regnum, u32 val); + int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum, + u16 val); /* Get the size and type of the eeprom contained within a plug-in * module */ @@ -621,6 +650,7 @@ struct phy_driver { int (*set_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, const void *data); + int (*set_loopback)(struct phy_device *dev, bool enable); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) @@ -631,7 +661,7 @@ struct phy_driver { /* A Structure for boards to register fixups with the PHY Lib */ struct phy_fixup { struct list_head list; - char bus_id[20]; + char bus_id[MII_BUS_ID_SIZE + 3]; u32 phy_uid; u32 phy_uid_mask; int (*run)(struct phy_device *phydev); @@ -646,25 +676,7 @@ struct phy_fixup { * * Same rules as for phy_read(); */ -static inline int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) -{ - if (!phydev->is_c45) - return -EOPNOTSUPP; - - return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, - MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff)); -} - -/** - * phy_read_mmd_indirect - reads data from the MMD registers - * @phydev: The PHY device bus - * @prtad: MMD Address - * @addr: PHY address on the MII bus - * - * Description: it reads data from the MMD registers (clause 22 to access to - * clause 45) of the specified phy address. - */ -int phy_read_mmd_indirect(struct phy_device *phydev, int prtad, int devad); +int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /** * phy_read - Convenience function for reading a given PHY register @@ -717,14 +729,24 @@ static inline bool phy_is_internal(struct phy_device *phydev) } /** + * phy_interface_mode_is_rgmii - Convenience function for testing if a + * PHY interface mode is RGMII (all variants) + * @mode: the phy_interface_t enum + */ +static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode) +{ + return mode >= PHY_INTERFACE_MODE_RGMII && + mode <= PHY_INTERFACE_MODE_RGMII_TXID; +}; + +/** * phy_interface_is_rgmii - Convenience function for testing if a PHY interface * is RGMII (all variants) * @phydev: the phy_device struct */ static inline bool phy_interface_is_rgmii(struct phy_device *phydev) { - return phydev->interface >= PHY_INTERFACE_MODE_RGMII && - phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID; + return phy_interface_mode_is_rgmii(phydev->interface); }; /* @@ -747,39 +769,34 @@ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) * * Same rules as for phy_write(); */ -static inline int phy_write_mmd(struct phy_device *phydev, int devad, - u32 regnum, u16 val) -{ - if (!phydev->is_c45) - return -EOPNOTSUPP; - - regnum = MII_ADDR_C45 | ((devad & 0x1f) << 16) | (regnum & 0xffff); - - return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); -} - -/** - * phy_write_mmd_indirect - writes data to the MMD registers - * @phydev: The PHY device - * @prtad: MMD Address - * @devad: MMD DEVAD - * @data: data to write in the MMD register - * - * Description: Write data from the MMD registers of the specified - * phy address. - */ -void phy_write_mmd_indirect(struct phy_device *phydev, int prtad, - int devad, u32 data); +int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); +#if IS_ENABLED(CONFIG_PHYLIB) struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); +void phy_device_free(struct phy_device *phydev); +#else +static inline +struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) +{ + return NULL; +} + +static inline int phy_device_register(struct phy_device *phy) +{ + return 0; +} + +static inline void phy_device_free(struct phy_device *phydev) { } +#endif /* CONFIG_PHYLIB */ void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); +int phy_loopback(struct phy_device *phydev, bool enable); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); @@ -799,9 +816,13 @@ int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); int phy_stop_interrupts(struct phy_device *phydev); +int phy_restart_aneg(struct phy_device *phydev); static inline int phy_read_status(struct phy_device *phydev) { + if (!phydev->drv) + return -EIO; + return phydev->drv->read_status(phydev); } @@ -819,6 +840,8 @@ static inline const char *phydev_name(const struct phy_device *phydev) void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) __printf(2, 3); void phy_attached_info(struct phy_device *phydev); + +/* Clause 22 PHY */ int genphy_config_init(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); @@ -828,7 +851,22 @@ int genphy_update_link(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); +int genphy_loopback(struct phy_device *phydev, bool enable); int genphy_soft_reset(struct phy_device *phydev); +static inline int genphy_no_soft_reset(struct phy_device *phydev) +{ + return 0; +} + +/* Clause 45 PHY */ +int genphy_c45_restart_aneg(struct phy_device *phydev); +int genphy_c45_aneg_done(struct phy_device *phydev); +int genphy_c45_read_link(struct phy_device *phydev, u32 mmd_mask); +int genphy_c45_read_lpa(struct phy_device *phydev); +int genphy_c45_read_pma(struct phy_device *phydev); +int genphy_c45_pma_setup_forced(struct phy_device *phydev); +int genphy_c45_an_disable_aneg(struct phy_device *phydev); + void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver, struct module *owner); @@ -840,16 +878,15 @@ void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev, int new_link); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); +void phy_trigger_machine(struct phy_device *phydev, bool sync); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); -int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd); -int phy_ethtool_ksettings_get(struct phy_device *phydev, - struct ethtool_link_ksettings *cmd); +void phy_ethtool_ksettings_get(struct phy_device *phydev, + struct ethtool_link_ksettings *cmd); int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -void phy_device_free(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, @@ -876,11 +913,32 @@ int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); +#if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); +#endif extern struct bus_type mdio_bus_type; +struct mdio_board_info { + const char *bus_id; + char modalias[MDIO_NAME_SIZE]; + int mdio_addr; + const void *platform_data; +}; + +#if IS_ENABLED(CONFIG_MDIO_DEVICE) +int mdiobus_register_board_info(const struct mdio_board_info *info, + unsigned int n); +#else +static inline int mdiobus_register_board_info(const struct mdio_board_info *i, + unsigned int n) +{ + return 0; +} +#endif + + /** * module_phy_driver() - Helper macro for registering PHY drivers * @__phy_drivers: array of PHY drivers to register diff --git a/include/linux/phy/ulpi_phy.h b/include/linux/phy/ulpi_phy.h new file mode 100644 index 000000000000..f2ebe490a4bc --- /dev/null +++ b/include/linux/phy/ulpi_phy.h @@ -0,0 +1,31 @@ +#include <linux/phy/phy.h> + +/** + * Helper that registers PHY for a ULPI device and adds a lookup for binding it + * and it's controller, which is always the parent. + */ +static inline struct phy +*ulpi_phy_create(struct ulpi *ulpi, const struct phy_ops *ops) +{ + struct phy *phy; + int ret; + + phy = phy_create(&ulpi->dev, NULL, ops); + if (IS_ERR(phy)) + return phy; + + ret = phy_create_lookup(phy, "usb2-phy", dev_name(ulpi->dev.parent)); + if (ret) { + phy_destroy(phy); + return ERR_PTR(ret); + } + + return phy; +} + +/* Remove a PHY that was created with ulpi_phy_create() and it's lookup. */ +static inline void ulpi_phy_destroy(struct ulpi *ulpi, struct phy *phy) +{ + phy_remove_lookup(phy, "usb2-phy", dev_name(ulpi->dev.parent)); + phy_destroy(phy); +} diff --git a/include/linux/pid.h b/include/linux/pid.h index 23705a53abba..4d179316e431 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -1,7 +1,7 @@ #ifndef _LINUX_PID_H #define _LINUX_PID_H -#include <linux/rcupdate.h> +#include <linux/rculist.h> enum pid_type { @@ -191,10 +191,10 @@ pid_t pid_vnr(struct pid *pid); #define do_each_pid_thread(pid, type, task) \ do_each_pid_task(pid, type, task) { \ struct task_struct *tg___ = task; \ - do { + for_each_thread(tg___, task) { #define while_each_pid_thread(pid, type, task) \ - } while_each_thread(tg___, task); \ + } \ task = tg___; \ } while_each_pid_task(pid, type, task) #endif /* _LINUX_PID_H */ diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 34cce96741bc..b09136f88cf4 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -21,6 +21,12 @@ struct pidmap { struct fs_pin; +enum { /* definitions for pid_namespace's hide_pid field */ + HIDEPID_OFF = 0, + HIDEPID_NO_ACCESS = 1, + HIDEPID_INVISIBLE = 2, +}; + struct pid_namespace { struct kref kref; struct pidmap pidmap[PIDMAP_ENTRIES]; @@ -46,7 +52,7 @@ struct pid_namespace { int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; -}; +} __randomize_layout; extern struct pid_namespace init_pid_ns; diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h index d7e5d608faa7..a0f2aba72fa9 100644 --- a/include/linux/pinctrl/consumer.h +++ b/include/linux/pinctrl/consumer.h @@ -29,6 +29,7 @@ extern int pinctrl_request_gpio(unsigned gpio); extern void pinctrl_free_gpio(unsigned gpio); extern int pinctrl_gpio_direction_input(unsigned gpio); extern int pinctrl_gpio_direction_output(unsigned gpio); +extern int pinctrl_gpio_set_config(unsigned gpio, unsigned long config); extern struct pinctrl * __must_check pinctrl_get(struct device *dev); extern void pinctrl_put(struct pinctrl *p); @@ -80,6 +81,11 @@ static inline int pinctrl_gpio_direction_output(unsigned gpio) return 0; } +static inline int pinctrl_gpio_set_config(unsigned gpio, unsigned long config) +{ + return 0; +} + static inline struct pinctrl * __must_check pinctrl_get(struct device *dev) { return NULL; diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 12343caa114e..231d3075815a 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -12,12 +12,6 @@ #ifndef __LINUX_PINCTRL_PINCONF_GENERIC_H #define __LINUX_PINCTRL_PINCONF_GENERIC_H -/* - * You shouldn't even be able to compile with these enums etc unless you're - * using generic pin config. That is why this is defined out. - */ -#ifdef CONFIG_GENERIC_PINCONF - /** * enum pin_config_param - possible pin configuration parameters * @PIN_CONFIG_BIAS_BUS_HOLD: the pin will be set to weakly latch so that it @@ -79,10 +73,16 @@ * operation, if several modes of operation are supported these can be * passed in the argument on a custom form, else just use argument 1 * to indicate low power mode, argument 0 turns low power mode off. - * @PIN_CONFIG_OUTPUT: this will configure the pin as an output. Use argument - * 1 to indicate high level, argument 0 to indicate low level. (Please - * see Documentation/pinctrl.txt, section "GPIO mode pitfalls" for a - * discussion around this parameter.) + * @PIN_CONFIG_OUTPUT_ENABLE: this will enable the pin's output mode + * without driving a value there. For most platforms this reduces to + * enable the output buffers and then let the pin controller current + * configuration (eg. the currently selected mux function) drive values on + * the line. Use argument 1 to enable output mode, argument 0 to disable + * it. + * @PIN_CONFIG_OUTPUT: this will configure the pin as an output and drive a + * value on the line. Use argument 1 to indicate high level, argument 0 to + * indicate low level. (Please see Documentation/pinctrl.txt, section + * "GPIO mode pitfalls" for a discussion around this parameter.) * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells * the driver which alternative power source to use. @@ -92,6 +92,8 @@ * @PIN_CONFIG_END: this is the last enumerator for pin configurations, if * you need to pass in custom configurations to the pin controller, use * PIN_CONFIG_END+1 as the base offset. + * @PIN_CONFIG_MAX: this is the maximum configuration value that can be + * presented using the packed format. */ enum pin_config_param { PIN_CONFIG_BIAS_BUS_HOLD, @@ -109,52 +111,57 @@ enum pin_config_param { PIN_CONFIG_INPUT_SCHMITT, PIN_CONFIG_INPUT_SCHMITT_ENABLE, PIN_CONFIG_LOW_POWER_MODE, + PIN_CONFIG_OUTPUT_ENABLE, PIN_CONFIG_OUTPUT, PIN_CONFIG_POWER_SOURCE, PIN_CONFIG_SLEW_RATE, - PIN_CONFIG_END = 0x7FFF, -}; - -#ifdef CONFIG_DEBUG_FS -#define PCONFDUMP(a, b, c, d) { .param = a, .display = b, .format = c, \ - .has_arg = d } - -struct pin_config_item { - const enum pin_config_param param; - const char * const display; - const char * const format; - bool has_arg; + PIN_CONFIG_END = 0x7F, + PIN_CONFIG_MAX = 0xFF, }; -#endif /* CONFIG_DEBUG_FS */ /* * Helpful configuration macro to be used in tables etc. */ -#define PIN_CONF_PACKED(p, a) ((a << 16) | ((unsigned long) p & 0xffffUL)) +#define PIN_CONF_PACKED(p, a) ((a << 8) | ((unsigned long) p & 0xffUL)) /* * The following inlines stuffs a configuration parameter and data value * into and out of an unsigned long argument, as used by the generic pin config - * system. We put the parameter in the lower 16 bits and the argument in the - * upper 16 bits. + * system. We put the parameter in the lower 8 bits and the argument in the + * upper 24 bits. */ static inline enum pin_config_param pinconf_to_config_param(unsigned long config) { - return (enum pin_config_param) (config & 0xffffUL); + return (enum pin_config_param) (config & 0xffUL); } -static inline u16 pinconf_to_config_argument(unsigned long config) +static inline u32 pinconf_to_config_argument(unsigned long config) { - return (enum pin_config_param) ((config >> 16) & 0xffffUL); + return (u32) ((config >> 8) & 0xffffffUL); } static inline unsigned long pinconf_to_config_packed(enum pin_config_param param, - u16 argument) + u32 argument) { return PIN_CONF_PACKED(param, argument); } +#ifdef CONFIG_GENERIC_PINCONF + +#ifdef CONFIG_DEBUG_FS +#define PCONFDUMP(a, b, c, d) { \ + .param = a, .display = b, .format = c, .has_arg = d \ + } + +struct pin_config_item { + const enum pin_config_param param; + const char * const display; + const char * const format; + bool has_arg; +}; +#endif /* CONFIG_DEBUG_FS */ + #ifdef CONFIG_OF #include <linux/device.h> diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index a42e57da270d..5e45385c5bdc 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -141,12 +141,28 @@ struct pinctrl_desc { }; /* External interface to pin controller */ + +extern int pinctrl_register_and_init(struct pinctrl_desc *pctldesc, + struct device *dev, void *driver_data, + struct pinctrl_dev **pctldev); +extern int pinctrl_enable(struct pinctrl_dev *pctldev); + +/* Please use pinctrl_register_and_init() and pinctrl_enable() instead */ extern struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data); + extern void pinctrl_unregister(struct pinctrl_dev *pctldev); + +extern int devm_pinctrl_register_and_init(struct device *dev, + struct pinctrl_desc *pctldesc, + void *driver_data, + struct pinctrl_dev **pctldev); + +/* Please use devm_pinctrl_register_and_init() instead */ extern struct pinctrl_dev *devm_pinctrl_register(struct device *dev, struct pinctrl_desc *pctldesc, void *driver_data); + extern void devm_pinctrl_unregister(struct device *dev, struct pinctrl_dev *pctldev); diff --git a/include/linux/i2c/adp5588.h b/include/linux/platform_data/adp5588.h index c2153049cfbd..c2153049cfbd 100644 --- a/include/linux/i2c/adp5588.h +++ b/include/linux/platform_data/adp5588.h diff --git a/include/linux/i2c/adp8860.h b/include/linux/platform_data/adp8860.h index 0b4d39855c91..0b4d39855c91 100644 --- a/include/linux/i2c/adp8860.h +++ b/include/linux/platform_data/adp8860.h diff --git a/include/linux/i2c/adp8870.h b/include/linux/platform_data/adp8870.h index 624dceccbd5b..624dceccbd5b 100644 --- a/include/linux/i2c/adp8870.h +++ b/include/linux/platform_data/adp8870.h diff --git a/include/linux/i2c/ads1015.h b/include/linux/platform_data/ads1015.h index d5aa2a045669..d5aa2a045669 100644 --- a/include/linux/i2c/ads1015.h +++ b/include/linux/platform_data/ads1015.h diff --git a/include/linux/i2c/apds990x.h b/include/linux/platform_data/apds990x.h index d186fcc5d257..d186fcc5d257 100644 --- a/include/linux/i2c/apds990x.h +++ b/include/linux/platform_data/apds990x.h diff --git a/include/linux/platform_data/asoc-s3c.h b/include/linux/platform_data/asoc-s3c.h index 15bf56ee8af7..90641a5daaf0 100644 --- a/include/linux/platform_data/asoc-s3c.h +++ b/include/linux/platform_data/asoc-s3c.h @@ -18,7 +18,7 @@ extern void s3c64xx_ac97_setup_gpio(int); -struct samsung_i2s { +struct samsung_i2s_type { /* If the Primary DAI has 5.1 Channels */ #define QUIRK_PRI_6CHAN (1 << 0) /* If the I2S block has a Stereo Overlay Channel */ @@ -47,7 +47,5 @@ struct s3c_audio_pdata { void *dma_capture; void *dma_play_sec; void *dma_capture_mic; - union { - struct samsung_i2s i2s; - } type; + struct samsung_i2s_type type; }; diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h index 3c8825b67298..cdceb4d4ef9d 100644 --- a/include/linux/platform_data/atmel.h +++ b/include/linux/platform_data/atmel.h @@ -7,10 +7,6 @@ #ifndef __ATMEL_H__ #define __ATMEL_H__ -#include <linux/mtd/nand.h> -#include <linux/mtd/partitions.h> -#include <linux/serial.h> - /* Compact Flash */ struct at91_cf_data { int irq_pin; /* I/O IRQ */ @@ -23,35 +19,14 @@ struct at91_cf_data { #define AT91_IDE_SWAP_A0_A2 0x02 }; - /* NAND / SmartMedia */ -struct atmel_nand_data { - int enable_pin; /* chip enable */ - int det_pin; /* card detect */ - int rdy_pin; /* ready/busy */ - u8 rdy_pin_active_low; /* rdy_pin value is inverted */ - u8 ale; /* address line number connected to ALE */ - u8 cle; /* address line number connected to CLE */ - u8 bus_width_16; /* buswidth is 16 bit */ - u8 ecc_mode; /* ecc mode */ - u8 on_flash_bbt; /* bbt on flash */ - struct mtd_partition *parts; - unsigned int num_parts; - bool has_dma; /* support dma transfer */ - - /* default is false, only for at32ap7000 chip is true */ - bool need_reset_workaround; -}; - - /* Serial */ -struct atmel_uart_data { - int num; /* port num */ - short use_dma_tx; /* use transmit DMA? */ - short use_dma_rx; /* use receive DMA? */ - void __iomem *regs; /* virt. base address, if any */ - struct serial_rs485 rs485; /* rs485 settings */ -}; - /* FIXME: this needs a better location, but gets stuff building again */ +#ifdef CONFIG_ATMEL_PM extern int at91_suspend_entering_slow_clock(void); +#else +static inline int at91_suspend_entering_slow_clock(void) +{ + return 0; +} +#endif #endif /* __ATMEL_H__ */ diff --git a/include/linux/i2c/bh1770glc.h b/include/linux/platform_data/bh1770glc.h index 8b5e2df36c72..8b5e2df36c72 100644 --- a/include/linux/i2c/bh1770glc.h +++ b/include/linux/platform_data/bh1770glc.h diff --git a/include/linux/platform_data/clk-realview.h b/include/linux/platform_data/clk-realview.h deleted file mode 100644 index 2e426a7dbc51..000000000000 --- a/include/linux/platform_data/clk-realview.h +++ /dev/null @@ -1 +0,0 @@ -void realview_clk_init(void __iomem *sysbase, bool is_pb1176); diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index e69e415d0d98..896cb71a382c 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -41,6 +41,7 @@ struct dw_dma_slave { * @is_private: The device channels should be marked as private and not for * by the general purpose DMA channel allocator. * @is_memcpy: The device channels do support memory-to-memory transfers. + * @is_idma32: The type of the DMA controller is iDMA32 * @chan_allocation_order: Allocate channels starting from 0 or 7 * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0. * @block_size: Maximum block size supported by the controller @@ -53,6 +54,7 @@ struct dw_dma_platform_data { unsigned int nr_channels; bool is_private; bool is_memcpy; + bool is_idma32; #define CHAN_ALLOCATION_ASCENDING 0 /* zero to seven */ #define CHAN_ALLOCATION_DESCENDING 1 /* seven to zero */ unsigned char chan_allocation_order; diff --git a/include/linux/i2c/ds620.h b/include/linux/platform_data/ds620.h index 736bb87ac0fc..736bb87ac0fc 100644 --- a/include/linux/i2c/ds620.h +++ b/include/linux/platform_data/ds620.h diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index 6ace3fd32b6a..90ae19ca828f 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -21,23 +21,28 @@ #include <asm-generic/gpio.h> +#define MAX_REGS_BANKS 5 + struct davinci_gpio_platform_data { u32 ngpio; u32 gpio_unbanked; }; +struct davinci_gpio_irq_data { + void __iomem *regs; + struct davinci_gpio_controller *chip; + int bank_num; +}; struct davinci_gpio_controller { struct gpio_chip chip; struct irq_domain *irq_domain; /* Serialize access to GPIO registers */ spinlock_t lock; - void __iomem *regs; - void __iomem *set_data; - void __iomem *clr_data; - void __iomem *in_data; + void __iomem *regs[MAX_REGS_BANKS]; int gpio_unbanked; - unsigned gpio_irq; + unsigned int base_irq; + unsigned int base; }; /* diff --git a/include/linux/i2c/i2c-hid.h b/include/linux/platform_data/i2c-hid.h index 7aa901d92058..1fb088239d12 100644 --- a/include/linux/i2c/i2c-hid.h +++ b/include/linux/platform_data/i2c-hid.h @@ -14,9 +14,13 @@ #include <linux/types.h> +struct regulator; + /** * struct i2chid_platform_data - used by hid over i2c implementation. * @hid_descriptor_address: i2c register where the HID descriptor is stored. + * @supply: regulator for powering on the device. + * @post_power_delay_ms: delay after powering on before device is usable. * * Note that it is the responsibility of the platform driver (or the acpi 5.0 * driver, or the flattened device tree) to setup the irq related to the gpio in @@ -31,6 +35,8 @@ */ struct i2c_hid_platform_data { u16 hid_descriptor_address; + struct regulator *supply; + int post_power_delay_ms; }; #endif /* __LINUX_I2C_HID_H */ diff --git a/include/linux/platform_data/intel-spi.h b/include/linux/platform_data/intel-spi.h new file mode 100644 index 000000000000..942b0c3f8f08 --- /dev/null +++ b/include/linux/platform_data/intel-spi.h @@ -0,0 +1,31 @@ +/* + * Intel PCH/PCU SPI flash driver. + * + * Copyright (C) 2016, Intel Corporation + * Author: Mika Westerberg <mika.westerberg@linux.intel.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef INTEL_SPI_PDATA_H +#define INTEL_SPI_PDATA_H + +enum intel_spi_type { + INTEL_SPI_BYT = 1, + INTEL_SPI_LPT, + INTEL_SPI_BXT, +}; + +/** + * struct intel_spi_boardinfo - Board specific data for Intel SPI driver + * @type: Type which this controller is compatible with + * @writeable: The chip is writeable + */ +struct intel_spi_boardinfo { + enum intel_spi_type type; + bool writeable; +}; + +#endif /* INTEL_SPI_PDATA_H */ diff --git a/include/linux/platform_data/iommu-omap.h b/include/linux/platform_data/iommu-omap.h index 0496d171700a..e8b12dbf6170 100644 --- a/include/linux/platform_data/iommu-omap.h +++ b/include/linux/platform_data/iommu-omap.h @@ -12,28 +12,8 @@ #include <linux/platform_device.h> -#define MMU_REG_SIZE 256 - -/** - * struct iommu_arch_data - omap iommu private data - * @name: name of the iommu device - * @iommu_dev: handle of the iommu device - * - * This is an omap iommu private data object, which binds an iommu user - * to its iommu device. This object should be placed at the iommu user's - * dev_archdata so generic IOMMU API can be used without having to - * utilize omap-specific plumbing anymore. - */ -struct omap_iommu_arch_data { - const char *name; - struct omap_iommu *iommu_dev; -}; - struct iommu_platform_data { - const char *name; const char *reset_name; - int nr_tlb_entries; - int (*assert_reset)(struct platform_device *pdev, const char *name); int (*deassert_reset)(struct platform_device *pdev, const char *name); }; diff --git a/include/linux/platform_data/isl9305.h b/include/linux/platform_data/isl9305.h index 1419133fa69e..4ac1a070af0a 100644 --- a/include/linux/platform_data/isl9305.h +++ b/include/linux/platform_data/isl9305.h @@ -24,7 +24,7 @@ struct regulator_init_data; struct isl9305_pdata { - struct regulator_init_data *init_data[ISL9305_MAX_REGULATOR]; + struct regulator_init_data *init_data[ISL9305_MAX_REGULATOR + 1]; }; #endif diff --git a/include/linux/platform_data/itco_wdt.h b/include/linux/platform_data/itco_wdt.h index f16542c77ff7..0e95527edf25 100644 --- a/include/linux/platform_data/itco_wdt.h +++ b/include/linux/platform_data/itco_wdt.h @@ -14,6 +14,10 @@ struct itco_wdt_platform_data { char name[32]; unsigned int version; + /* private data to be passed to update_no_reboot_bit API */ + void *no_reboot_priv; + /* pointer for platform specific no reboot update function */ + int (*update_no_reboot_bit)(void *priv, bool set); }; #endif /* _ITCO_WDT_H_ */ diff --git a/include/linux/platform_data/leds-pca963x.h b/include/linux/platform_data/leds-pca963x.h index e731f0036329..54e845ffb5ed 100644 --- a/include/linux/platform_data/leds-pca963x.h +++ b/include/linux/platform_data/leds-pca963x.h @@ -33,10 +33,16 @@ enum pca963x_blink_type { PCA963X_HW_BLINK, }; +enum pca963x_direction { + PCA963X_NORMAL, + PCA963X_INVERTED, +}; + struct pca963x_platform_data { struct led_platform_data leds; enum pca963x_outdrv outdrv; enum pca963x_blink_type blink_type; + enum pca963x_direction dir; }; #endif /* __LINUX_PCA963X_H*/ diff --git a/include/linux/i2c/lm8323.h b/include/linux/platform_data/lm8323.h index 478d668bc590..478d668bc590 100644 --- a/include/linux/i2c/lm8323.h +++ b/include/linux/platform_data/lm8323.h diff --git a/include/linux/i2c/ltc4245.h b/include/linux/platform_data/ltc4245.h index 56bda4be0016..56bda4be0016 100644 --- a/include/linux/i2c/ltc4245.h +++ b/include/linux/platform_data/ltc4245.h diff --git a/include/linux/i2c/max6639.h b/include/linux/platform_data/max6639.h index 6011c42034da..6011c42034da 100644 --- a/include/linux/i2c/max6639.h +++ b/include/linux/platform_data/max6639.h diff --git a/include/linux/i2c/max732x.h b/include/linux/platform_data/max732x.h index c04bac8bf2fe..c04bac8bf2fe 100644 --- a/include/linux/i2c/max732x.h +++ b/include/linux/platform_data/max732x.h diff --git a/include/linux/i2c/mcs.h b/include/linux/platform_data/mcs.h index 61bb18a4fd3c..61bb18a4fd3c 100644 --- a/include/linux/i2c/mcs.h +++ b/include/linux/platform_data/mcs.h diff --git a/include/linux/platform_data/media/ir-rx51.h b/include/linux/platform_data/media/ir-rx51.h index 812d87307877..2c94ab568bfa 100644 --- a/include/linux/platform_data/media/ir-rx51.h +++ b/include/linux/platform_data/media/ir-rx51.h @@ -1,7 +1,7 @@ -#ifndef _LIRC_RX51_H -#define _LIRC_RX51_H +#ifndef _IR_RX51_H +#define _IR_RX51_H -struct lirc_rx51_platform_data { +struct ir_rx51_platform_data { int(*set_max_mpu_wakeup_lat)(struct device *dev, long t); }; diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h new file mode 100644 index 000000000000..84789ca634aa --- /dev/null +++ b/include/linux/platform_data/microchip-ksz.h @@ -0,0 +1,29 @@ +/* + * Microchip KSZ series switch platform data + * + * Copyright (C) 2017 + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#ifndef __MICROCHIP_KSZ_H +#define __MICROCHIP_KSZ_H + +#include <linux/kernel.h> + +struct ksz_platform_data { + u32 chip_id; + u16 enabled_ports; +}; + +#endif diff --git a/include/linux/platform_data/mmc-mxcmmc.h b/include/linux/platform_data/mmc-mxcmmc.h index 29115f405af9..b0fdaa9bd185 100644 --- a/include/linux/platform_data/mmc-mxcmmc.h +++ b/include/linux/platform_data/mmc-mxcmmc.h @@ -1,6 +1,7 @@ #ifndef ASMARM_ARCH_MMC_H #define ASMARM_ARCH_MMC_H +#include <linux/interrupt.h> #include <linux/mmc/host.h> struct device; diff --git a/include/linux/i2c/mms114.h b/include/linux/platform_data/mms114.h index 5722ebfb2738..5722ebfb2738 100644 --- a/include/linux/i2c/mms114.h +++ b/include/linux/platform_data/mms114.h diff --git a/include/linux/platform_data/nfcmrvl.h b/include/linux/platform_data/nfcmrvl.h index a6f9d633f5be..9e75ac8d19be 100644 --- a/include/linux/platform_data/nfcmrvl.h +++ b/include/linux/platform_data/nfcmrvl.h @@ -23,7 +23,7 @@ struct nfcmrvl_platform_data { */ /* GPIO that is wired to RESET_N signal */ - unsigned int reset_n_io; + int reset_n_io; /* Tell if transport is muxed in HCI one */ unsigned int hci_muxed; diff --git a/include/linux/platform_data/omapdss.h b/include/linux/platform_data/omapdss.h index 679177929045..7feb011ed500 100644 --- a/include/linux/platform_data/omapdss.h +++ b/include/linux/platform_data/omapdss.h @@ -27,7 +27,6 @@ enum omapdss_version { /* Board specific data */ struct omap_dss_board_info { - const char *default_display_name; int (*dsi_enable_pads)(int dsi_id, unsigned int lane_mask); void (*dsi_disable_pads)(int dsi_id, unsigned int lane_mask); int (*set_min_bus_tput)(struct device *dev, unsigned long r); diff --git a/include/linux/i2c/pcf857x.h b/include/linux/platform_data/pcf857x.h index 0767a2a6b2f1..0767a2a6b2f1 100644 --- a/include/linux/i2c/pcf857x.h +++ b/include/linux/platform_data/pcf857x.h diff --git a/include/linux/platform_data/pn544.h b/include/linux/platform_data/pn544.h deleted file mode 100644 index 5ce1ab983f44..000000000000 --- a/include/linux/platform_data/pn544.h +++ /dev/null @@ -1,43 +0,0 @@ -/* - * Driver include for the PN544 NFC chip. - * - * Copyright (C) Nokia Corporation - * - * Author: Jari Vanhala <ext-jari.vanhala@nokia.com> - * Contact: Matti Aaltoenn <matti.j.aaltonen@nokia.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef _PN544_H_ -#define _PN544_H_ - -#include <linux/i2c.h> - -enum { - NFC_GPIO_ENABLE, - NFC_GPIO_FW_RESET, - NFC_GPIO_IRQ -}; - -/* board config */ -struct pn544_nfc_platform_data { - int (*request_resources) (struct i2c_client *client); - void (*free_resources) (void); - void (*enable) (int fw); - int (*test) (void); - void (*disable) (void); - int (*get_gpio)(int type); -}; - -#endif /* _PN544_H_ */ diff --git a/include/linux/platform_data/rtc-m48t86.h b/include/linux/platform_data/rtc-m48t86.h deleted file mode 100644 index 915d6b4f0f89..000000000000 --- a/include/linux/platform_data/rtc-m48t86.h +++ /dev/null @@ -1,16 +0,0 @@ -/* - * ST M48T86 / Dallas DS12887 RTC driver - * Copyright (c) 2006 Tower Technologies - * - * Author: Alessandro Zummo <a.zummo@towertech.it> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. -*/ - -struct m48t86_ops -{ - void (*writebyte)(unsigned char value, unsigned long addr); - unsigned char (*readbyte)(unsigned long addr); -}; diff --git a/include/linux/platform_data/spi-ep93xx.h b/include/linux/platform_data/spi-ep93xx.h index 9bb63ac13f04..171a271c2cbd 100644 --- a/include/linux/platform_data/spi-ep93xx.h +++ b/include/linux/platform_data/spi-ep93xx.h @@ -5,25 +5,14 @@ struct spi_device; /** * struct ep93xx_spi_info - EP93xx specific SPI descriptor - * @num_chipselect: number of chip selects on this board, must be - * at least one + * @chipselect: array of gpio numbers to use as chip selects + * @num_chipselect: ARRAY_SIZE(chipselect) * @use_dma: use DMA for the transfers */ struct ep93xx_spi_info { + int *chipselect; int num_chipselect; bool use_dma; }; -/** - * struct ep93xx_spi_chip_ops - operation callbacks for SPI slave device - * @setup: setup the chip select mechanism - * @cleanup: cleanup the chip select mechanism - * @cs_control: control the device chip select - */ -struct ep93xx_spi_chip_ops { - int (*setup)(struct spi_device *spi); - void (*cleanup)(struct spi_device *spi); - void (*cs_control)(struct spi_device *spi, int value); -}; - #endif /* __ASM_MACH_EP93XX_SPI_H */ diff --git a/include/linux/platform_data/spi-mt65xx.h b/include/linux/platform_data/spi-mt65xx.h index 54b04483976c..ba4e4bb70262 100644 --- a/include/linux/platform_data/spi-mt65xx.h +++ b/include/linux/platform_data/spi-mt65xx.h @@ -16,5 +16,7 @@ struct mtk_chip_config { u32 tx_mlsb; u32 rx_mlsb; + u32 cs_pol; + u32 sample_sel; }; #endif diff --git a/include/linux/platform_data/st-nci.h b/include/linux/platform_data/st-nci.h deleted file mode 100644 index f6494b347c06..000000000000 --- a/include/linux/platform_data/st-nci.h +++ /dev/null @@ -1,31 +0,0 @@ -/* - * Driver include for ST NCI NFC chip family. - * - * Copyright (C) 2014-2015 STMicroelectronics SAS. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef _ST_NCI_H_ -#define _ST_NCI_H_ - -#define ST_NCI_DRIVER_NAME "st_nci" - -struct st_nci_nfc_platform_data { - unsigned int gpio_reset; - unsigned int irq_polarity; - bool is_ese_present; - bool is_uicc_present; -}; - -#endif /* _ST_NCI_H_ */ diff --git a/include/linux/platform_data/st21nfca.h b/include/linux/platform_data/st21nfca.h deleted file mode 100644 index cc2bdafb0c69..000000000000 --- a/include/linux/platform_data/st21nfca.h +++ /dev/null @@ -1,33 +0,0 @@ -/* - * Driver include for the ST21NFCA NFC chip. - * - * Copyright (C) 2014 STMicroelectronics SAS. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef _ST21NFCA_HCI_H_ -#define _ST21NFCA_HCI_H_ - -#include <linux/i2c.h> - -#define ST21NFCA_HCI_DRIVER_NAME "st21nfca_hci" - -struct st21nfca_nfc_platform_data { - unsigned int gpio_ena; - unsigned int irq_polarity; - bool is_ese_present; - bool is_uicc_present; -}; - -#endif /* _ST21NFCA_HCI_H_ */ diff --git a/include/linux/platform_data/ti-aemif.h b/include/linux/platform_data/ti-aemif.h new file mode 100644 index 000000000000..ac72e115093c --- /dev/null +++ b/include/linux/platform_data/ti-aemif.h @@ -0,0 +1,23 @@ +/* + * TI DaVinci AEMIF platform glue. + * + * Copyright (C) 2017 BayLibre SAS + * + * Author: + * Bartosz Golaszewski <bgolaszewski@baylibre.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __TI_DAVINCI_AEMIF_DATA_H__ +#define __TI_DAVINCI_AEMIF_DATA_H__ + +#include <linux/of_platform.h> + +struct aemif_platform_data { + struct of_dev_auxdata *dev_lookup; +}; + +#endif /* __TI_DAVINCI_AEMIF_DATA_H__ */ diff --git a/include/linux/i2c/tsc2007.h b/include/linux/platform_data/tsc2007.h index 4f35b6ad3889..c2d3aa1dadd4 100644 --- a/include/linux/i2c/tsc2007.h +++ b/include/linux/platform_data/tsc2007.h @@ -1,7 +1,7 @@ #ifndef __LINUX_I2C_TSC2007_H #define __LINUX_I2C_TSC2007_H -/* linux/i2c/tsc2007.h */ +/* linux/platform_data/tsc2007.h */ struct tsc2007_platform_data { u16 model; /* 2007. */ diff --git a/include/linux/platform_data/usb-ohci-s3c2410.h b/include/linux/platform_data/usb-ohci-s3c2410.h index 7fa1fbefc3f2..cc7554ae6e8b 100644 --- a/include/linux/platform_data/usb-ohci-s3c2410.h +++ b/include/linux/platform_data/usb-ohci-s3c2410.h @@ -31,7 +31,7 @@ struct s3c2410_hcd_info { void (*report_oc)(struct s3c2410_hcd_info *, int ports); }; -static void inline s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports) +static inline void s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports) { if (info->report_oc != NULL) { (info->report_oc)(info, ports); diff --git a/include/linux/platform_data/video-imxfb.h b/include/linux/platform_data/video-imxfb.h index 18e908324549..cf9348b376ac 100644 --- a/include/linux/platform_data/video-imxfb.h +++ b/include/linux/platform_data/video-imxfb.h @@ -47,13 +47,10 @@ #define LSCR1_GRAY2(x) (((x) & 0xf) << 4) #define LSCR1_GRAY1(x) (((x) & 0xf)) -#define DMACR_BURST (1 << 31) -#define DMACR_HM(x) (((x) & 0xf) << 16) -#define DMACR_TM(x) ((x) & 0xf) - struct imx_fb_videomode { struct fb_videomode mode; u32 pcr; + bool aus_mode; unsigned char bpp; }; diff --git a/include/linux/platform_data/x86/clk-pmc-atom.h b/include/linux/platform_data/x86/clk-pmc-atom.h new file mode 100644 index 000000000000..3ab892208343 --- /dev/null +++ b/include/linux/platform_data/x86/clk-pmc-atom.h @@ -0,0 +1,44 @@ +/* + * Intel Atom platform clocks for BayTrail and CherryTrail SoC. + * + * Copyright (C) 2016, Intel Corporation + * Author: Irina Tirdea <irina.tirdea@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef __PLATFORM_DATA_X86_CLK_PMC_ATOM_H +#define __PLATFORM_DATA_X86_CLK_PMC_ATOM_H + +/** + * struct pmc_clk - PMC platform clock configuration + * + * @name: identified, typically pmc_plt_clk_<x>, x=[0..5] + * @freq: in Hz, 19.2MHz and 25MHz (Baytrail only) supported + * @parent_name: one of 'xtal' or 'osc' + */ +struct pmc_clk { + const char *name; + unsigned long freq; + const char *parent_name; +}; + +/** + * struct pmc_clk_data - common PMC clock configuration + * + * @base: PMC clock register base offset + * @clks: pointer to set of registered clocks, typically 0..5 + */ +struct pmc_clk_data { + void __iomem *base; + const struct pmc_clk *clks; +}; + +#endif /* __PLATFORM_DATA_X86_CLK_PMC_ATOM_H */ diff --git a/include/linux/platform_data/x86/pmc_atom.h b/include/linux/platform_data/x86/pmc_atom.h new file mode 100644 index 000000000000..e4905fe69c38 --- /dev/null +++ b/include/linux/platform_data/x86/pmc_atom.h @@ -0,0 +1,158 @@ +/* + * Intel Atom SOC Power Management Controller Header File + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#ifndef PMC_ATOM_H +#define PMC_ATOM_H + +/* ValleyView Power Control Unit PCI Device ID */ +#define PCI_DEVICE_ID_VLV_PMC 0x0F1C +/* CherryTrail Power Control Unit PCI Device ID */ +#define PCI_DEVICE_ID_CHT_PMC 0x229C + +/* PMC Memory mapped IO registers */ +#define PMC_BASE_ADDR_OFFSET 0x44 +#define PMC_BASE_ADDR_MASK 0xFFFFFE00 +#define PMC_MMIO_REG_LEN 0x100 +#define PMC_REG_BIT_WIDTH 32 + +/* BIOS uses FUNC_DIS to disable specific function */ +#define PMC_FUNC_DIS 0x34 +#define PMC_FUNC_DIS_2 0x38 + +/* CHT specific bits in FUNC_DIS2 register */ +#define BIT_FD_GMM BIT(3) +#define BIT_FD_ISH BIT(4) + +/* S0ix wake event control */ +#define PMC_S0IX_WAKE_EN 0x3C + +#define BIT_LPC_CLOCK_RUN BIT(4) +#define BIT_SHARED_IRQ_GPSC BIT(5) +#define BIT_ORED_DEDICATED_IRQ_GPSS BIT(18) +#define BIT_ORED_DEDICATED_IRQ_GPSC BIT(19) +#define BIT_SHARED_IRQ_GPSS BIT(20) + +#define PMC_WAKE_EN_SETTING ~(BIT_LPC_CLOCK_RUN | \ + BIT_SHARED_IRQ_GPSC | \ + BIT_ORED_DEDICATED_IRQ_GPSS | \ + BIT_ORED_DEDICATED_IRQ_GPSC | \ + BIT_SHARED_IRQ_GPSS) + +/* The timers accumulate time spent in sleep state */ +#define PMC_S0IR_TMR 0x80 +#define PMC_S0I1_TMR 0x84 +#define PMC_S0I2_TMR 0x88 +#define PMC_S0I3_TMR 0x8C +#define PMC_S0_TMR 0x90 +/* Sleep state counter is in units of of 32us */ +#define PMC_TMR_SHIFT 5 + +/* Power status of power islands */ +#define PMC_PSS 0x98 + +#define PMC_PSS_BIT_GBE BIT(0) +#define PMC_PSS_BIT_SATA BIT(1) +#define PMC_PSS_BIT_HDA BIT(2) +#define PMC_PSS_BIT_SEC BIT(3) +#define PMC_PSS_BIT_PCIE BIT(4) +#define PMC_PSS_BIT_LPSS BIT(5) +#define PMC_PSS_BIT_LPE BIT(6) +#define PMC_PSS_BIT_DFX BIT(7) +#define PMC_PSS_BIT_USH_CTRL BIT(8) +#define PMC_PSS_BIT_USH_SUS BIT(9) +#define PMC_PSS_BIT_USH_VCCS BIT(10) +#define PMC_PSS_BIT_USH_VCCA BIT(11) +#define PMC_PSS_BIT_OTG_CTRL BIT(12) +#define PMC_PSS_BIT_OTG_VCCS BIT(13) +#define PMC_PSS_BIT_OTG_VCCA_CLK BIT(14) +#define PMC_PSS_BIT_OTG_VCCA BIT(15) +#define PMC_PSS_BIT_USB BIT(16) +#define PMC_PSS_BIT_USB_SUS BIT(17) + +/* CHT specific bits in PSS register */ +#define PMC_PSS_BIT_CHT_UFS BIT(7) +#define PMC_PSS_BIT_CHT_UXD BIT(11) +#define PMC_PSS_BIT_CHT_UXD_FD BIT(12) +#define PMC_PSS_BIT_CHT_UX_ENG BIT(15) +#define PMC_PSS_BIT_CHT_USB_SUS BIT(16) +#define PMC_PSS_BIT_CHT_GMM BIT(17) +#define PMC_PSS_BIT_CHT_ISH BIT(18) +#define PMC_PSS_BIT_CHT_DFX_MASTER BIT(26) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER1 BIT(27) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER2 BIT(28) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER3 BIT(29) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER4 BIT(30) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER5 BIT(31) + +/* These registers reflect D3 status of functions */ +#define PMC_D3_STS_0 0xA0 + +#define BIT_LPSS1_F0_DMA BIT(0) +#define BIT_LPSS1_F1_PWM1 BIT(1) +#define BIT_LPSS1_F2_PWM2 BIT(2) +#define BIT_LPSS1_F3_HSUART1 BIT(3) +#define BIT_LPSS1_F4_HSUART2 BIT(4) +#define BIT_LPSS1_F5_SPI BIT(5) +#define BIT_LPSS1_F6_XXX BIT(6) +#define BIT_LPSS1_F7_XXX BIT(7) +#define BIT_SCC_EMMC BIT(8) +#define BIT_SCC_SDIO BIT(9) +#define BIT_SCC_SDCARD BIT(10) +#define BIT_SCC_MIPI BIT(11) +#define BIT_HDA BIT(12) +#define BIT_LPE BIT(13) +#define BIT_OTG BIT(14) +#define BIT_USH BIT(15) +#define BIT_GBE BIT(16) +#define BIT_SATA BIT(17) +#define BIT_USB_EHCI BIT(18) +#define BIT_SEC BIT(19) +#define BIT_PCIE_PORT0 BIT(20) +#define BIT_PCIE_PORT1 BIT(21) +#define BIT_PCIE_PORT2 BIT(22) +#define BIT_PCIE_PORT3 BIT(23) +#define BIT_LPSS2_F0_DMA BIT(24) +#define BIT_LPSS2_F1_I2C1 BIT(25) +#define BIT_LPSS2_F2_I2C2 BIT(26) +#define BIT_LPSS2_F3_I2C3 BIT(27) +#define BIT_LPSS2_F4_I2C4 BIT(28) +#define BIT_LPSS2_F5_I2C5 BIT(29) +#define BIT_LPSS2_F6_I2C6 BIT(30) +#define BIT_LPSS2_F7_I2C7 BIT(31) + +#define PMC_D3_STS_1 0xA4 +#define BIT_SMB BIT(0) +#define BIT_OTG_SS_PHY BIT(1) +#define BIT_USH_SS_PHY BIT(2) +#define BIT_DFX BIT(3) + +/* CHT specific bits in PMC_D3_STS_1 register */ +#define BIT_STS_GMM BIT(1) +#define BIT_STS_ISH BIT(2) + +/* PMC I/O Registers */ +#define ACPI_BASE_ADDR_OFFSET 0x40 +#define ACPI_BASE_ADDR_MASK 0xFFFFFE00 +#define ACPI_MMIO_REG_LEN 0x100 + +#define PM1_CNT 0x4 +#define SLEEP_TYPE_MASK 0xFFFFECFF +#define SLEEP_TYPE_S5 0x1C00 +#define SLEEP_ENABLE 0x2000 + +extern int pmc_atom_read(int offset, u32 *value); +extern int pmc_atom_write(int offset, u32 value); + +#endif /* PMC_ATOM_H */ diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 98c2a7c7108e..49f634d96118 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -172,7 +172,7 @@ extern int platform_device_add_resources(struct platform_device *pdev, extern int platform_device_add_data(struct platform_device *pdev, const void *data, size_t size); extern int platform_device_add_properties(struct platform_device *pdev, - struct property_entry *properties); + const struct property_entry *properties); extern int platform_device_add(struct platform_device *pdev); extern void platform_device_del(struct platform_device *pdev); extern void platform_device_put(struct platform_device *pdev); diff --git a/include/linux/pm.h b/include/linux/pm.h index f926af41e122..b8b4df09fd8f 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -64,24 +64,7 @@ typedef struct pm_message { } pm_message_t; /** - * struct dev_pm_ops - device PM callbacks - * - * Several device power state transitions are externally visible, affecting - * the state of pending I/O queues and (for drivers that touch hardware) - * interrupts, wakeups, DMA, and other hardware state. There may also be - * internal transitions to various low-power modes which are transparent - * to the rest of the driver stack (such as a driver that's ON gating off - * clocks which are not in active use). - * - * The externally visible transitions are handled with the help of callbacks - * included in this structure in such a way that two levels of callbacks are - * involved. First, the PM core executes callbacks provided by PM domains, - * device types, classes and bus types. They are the subsystem-level callbacks - * supposed to execute callbacks provided by device drivers, although they may - * choose not to do that. If the driver callbacks are executed, they have to - * collaborate with the subsystem-level callbacks to achieve the goals - * appropriate for the given system transition, given transition phase and the - * subsystem the device belongs to. + * struct dev_pm_ops - device PM callbacks. * * @prepare: The principal role of this callback is to prevent new children of * the device from being registered after it has returned (the driver's @@ -240,34 +223,6 @@ typedef struct pm_message { * driver's interrupt handler, which is guaranteed not to run while * @restore_noirq() is being executed. Analogous to @resume_noirq(). * - * All of the above callbacks, except for @complete(), return error codes. - * However, the error codes returned by the resume operations, @resume(), - * @thaw(), @restore(), @resume_noirq(), @thaw_noirq(), and @restore_noirq(), do - * not cause the PM core to abort the resume transition during which they are - * returned. The error codes returned in those cases are only printed by the PM - * core to the system logs for debugging purposes. Still, it is recommended - * that drivers only return error codes from their resume methods in case of an - * unrecoverable failure (i.e. when the device being handled refuses to resume - * and becomes unusable) to allow us to modify the PM core in the future, so - * that it can avoid attempting to handle devices that failed to resume and - * their children. - * - * It is allowed to unregister devices while the above callbacks are being - * executed. However, a callback routine must NOT try to unregister the device - * it was called for, although it may unregister children of that device (for - * example, if it detects that a child was unplugged while the system was - * asleep). - * - * Refer to Documentation/power/admin-guide/devices.rst for more information about the role - * of the above callbacks in the system suspend process. - * - * There also are callbacks related to runtime power management of devices. - * Again, these callbacks are executed by the PM core only for subsystems - * (PM domains, device types, classes and bus types) and the subsystem-level - * callbacks are supposed to invoke the driver callbacks. Moreover, the exact - * actions to be performed by a device driver's callbacks generally depend on - * the platform and subsystem the device belongs to. - * * @runtime_suspend: Prepare the device for a condition in which it won't be * able to communicate with the CPU(s) and RAM due to power management. * This need not mean that the device should be put into a low-power state. @@ -287,11 +242,51 @@ typedef struct pm_message { * Check these conditions, and return 0 if it's appropriate to let the PM * core queue a suspend request for the device. * - * Refer to Documentation/power/runtime_pm.txt for more information about the - * role of the above callbacks in device runtime power management. + * Several device power state transitions are externally visible, affecting + * the state of pending I/O queues and (for drivers that touch hardware) + * interrupts, wakeups, DMA, and other hardware state. There may also be + * internal transitions to various low-power modes which are transparent + * to the rest of the driver stack (such as a driver that's ON gating off + * clocks which are not in active use). * + * The externally visible transitions are handled with the help of callbacks + * included in this structure in such a way that, typically, two levels of + * callbacks are involved. First, the PM core executes callbacks provided by PM + * domains, device types, classes and bus types. They are the subsystem-level + * callbacks expected to execute callbacks provided by device drivers, although + * they may choose not to do that. If the driver callbacks are executed, they + * have to collaborate with the subsystem-level callbacks to achieve the goals + * appropriate for the given system transition, given transition phase and the + * subsystem the device belongs to. + * + * All of the above callbacks, except for @complete(), return error codes. + * However, the error codes returned by @resume(), @thaw(), @restore(), + * @resume_noirq(), @thaw_noirq(), and @restore_noirq(), do not cause the PM + * core to abort the resume transition during which they are returned. The + * error codes returned in those cases are only printed to the system logs for + * debugging purposes. Still, it is recommended that drivers only return error + * codes from their resume methods in case of an unrecoverable failure (i.e. + * when the device being handled refuses to resume and becomes unusable) to + * allow the PM core to be modified in the future, so that it can avoid + * attempting to handle devices that failed to resume and their children. + * + * It is allowed to unregister devices while the above callbacks are being + * executed. However, a callback routine MUST NOT try to unregister the device + * it was called for, although it may unregister children of that device (for + * example, if it detects that a child was unplugged while the system was + * asleep). + * + * There also are callbacks related to runtime power management of devices. + * Again, as a rule these callbacks are executed by the PM core for subsystems + * (PM domains, device types, classes and bus types) and the subsystem-level + * callbacks are expected to invoke the driver callbacks. Moreover, the exact + * actions to be performed by a device driver's callbacks generally depend on + * the platform and subsystem the device belongs to. + * + * Refer to Documentation/power/runtime_pm.txt for more information about the + * role of the @runtime_suspend(), @runtime_resume() and @runtime_idle() + * callbacks in device runtime power management. */ - struct dev_pm_ops { int (*prepare)(struct device *dev); void (*complete)(struct device *dev); @@ -391,7 +386,7 @@ const struct dev_pm_ops name = { \ SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } -/** +/* * PM_EVENT_ messages * * The following PM_EVENT_ messages are defined for the internal use of the PM @@ -487,7 +482,7 @@ const struct dev_pm_ops name = { \ #define PMSG_IS_AUTO(msg) (((msg).event & PM_EVENT_AUTO) != 0) -/** +/* * Device run-time power management status. * * These status labels are used internally by the PM core to indicate the @@ -517,7 +512,7 @@ enum rpm_status { RPM_SUSPENDING, }; -/** +/* * Device run-time power management request types. * * RPM_REQ_NONE Do nothing. @@ -589,7 +584,6 @@ struct dev_pm_info { unsigned int idle_notification:1; unsigned int request_pending:1; unsigned int deferred_resume:1; - unsigned int run_wake:1; unsigned int runtime_auto:1; bool ignore_children:1; unsigned int no_callbacks:1; @@ -616,15 +610,18 @@ extern void update_pm_runtime_accounting(struct device *dev); extern int dev_pm_get_subsys_data(struct device *dev); extern void dev_pm_put_subsys_data(struct device *dev); -/* - * Power domains provide callbacks that are executed during system suspend, - * hibernation, system resume and during runtime PM transitions along with - * subsystem-level and driver-level callbacks. +/** + * struct dev_pm_domain - power management domain representation. * + * @ops: Power management operations associated with this domain. * @detach: Called when removing a device from the domain. * @activate: Called before executing probe routines for bus types and drivers. * @sync: Called after successful driver probe. * @dismiss: Called after unsuccessful driver probe and after driver removal. + * + * Power domains provide callbacks that are executed during system suspend, + * hibernation, system resume and during runtime PM transitions instead of + * subsystem-level and driver-level callbacks. */ struct dev_pm_domain { struct dev_pm_ops ops; diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 81ece61075df..41004d97cefa 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -20,6 +20,7 @@ /* Defines used for the flags field in the struct generic_pm_domain */ #define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ #define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ +#define GENPD_FLAG_ALWAYS_ON (1U << 2) /* PM domain is always powered on */ enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ @@ -117,6 +118,7 @@ struct generic_pm_domain_data { struct pm_domain_data base; struct gpd_timing_data td; struct notifier_block nb; + void *data; }; #ifdef CONFIG_PM_GENERIC_DOMAINS @@ -182,6 +184,9 @@ static inline int pm_genpd_remove(struct generic_pm_domain *genpd) { return -ENOTSUPP; } + +#define simple_qos_governor (*(struct dev_power_governor *)(NULL)) +#define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL)) #endif static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, @@ -201,9 +206,13 @@ static inline void pm_genpd_syscore_poweron(struct device *dev) {} /* OF PM domain providers */ struct of_device_id; +typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args, + void *data); + struct genpd_onecell_data { struct generic_pm_domain **domains; unsigned int num_domains; + genpd_xlate_t xlate; }; #ifdef CONFIG_PM_GENERIC_DOMAINS_OF diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 0edd88f93904..51ec727b4824 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -78,6 +78,9 @@ struct dev_pm_set_opp_data { #if defined(CONFIG_PM_OPP) +struct opp_table *dev_pm_opp_get_opp_table(struct device *dev); +void dev_pm_opp_put_opp_table(struct opp_table *opp_table); + unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp); @@ -88,7 +91,7 @@ int dev_pm_opp_get_opp_count(struct device *dev); unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev); unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev); unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev); -struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev); +unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, @@ -99,6 +102,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq); +void dev_pm_opp_put(struct dev_pm_opp *opp); int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt); @@ -108,22 +112,32 @@ int dev_pm_opp_enable(struct device *dev, unsigned long freq); int dev_pm_opp_disable(struct device *dev, unsigned long freq); -struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev); -int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, - unsigned int count); -void dev_pm_opp_put_supported_hw(struct device *dev); -int dev_pm_opp_set_prop_name(struct device *dev, const char *name); -void dev_pm_opp_put_prop_name(struct device *dev); +int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb); +int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb); + +struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, unsigned int count); +void dev_pm_opp_put_supported_hw(struct opp_table *opp_table); +struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name); +void dev_pm_opp_put_prop_name(struct opp_table *opp_table); struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); void dev_pm_opp_put_regulators(struct opp_table *opp_table); -int dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); -void dev_pm_opp_register_put_opp_helper(struct device *dev); +struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name); +void dev_pm_opp_put_clkname(struct opp_table *opp_table); +struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); +void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); void dev_pm_opp_remove_table(struct device *dev); void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask); #else +static inline struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) +{ + return ERR_PTR(-ENOTSUPP); +} + +static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {} + static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) { return 0; @@ -159,9 +173,9 @@ static inline unsigned long dev_pm_opp_get_max_transition_latency(struct device return 0; } -static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) +static inline unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev) { - return NULL; + return 0; } static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, @@ -182,6 +196,8 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, return ERR_PTR(-ENOTSUPP); } +static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} + static inline int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt) { @@ -202,35 +218,39 @@ static inline int dev_pm_opp_disable(struct device *dev, unsigned long freq) return 0; } -static inline struct srcu_notifier_head *dev_pm_opp_get_notifier( - struct device *dev) +static inline int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb) { - return ERR_PTR(-ENOTSUPP); + return -ENOTSUPP; } -static inline int dev_pm_opp_set_supported_hw(struct device *dev, - const u32 *versions, - unsigned int count) +static inline int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb) { return -ENOTSUPP; } -static inline void dev_pm_opp_put_supported_hw(struct device *dev) {} +static inline struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev, + const u32 *versions, + unsigned int count) +{ + return ERR_PTR(-ENOTSUPP); +} -static inline int dev_pm_opp_register_set_opp_helper(struct device *dev, +static inline void dev_pm_opp_put_supported_hw(struct opp_table *opp_table) {} + +static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)) { - return -ENOTSUPP; + return ERR_PTR(-ENOTSUPP); } -static inline void dev_pm_opp_register_put_opp_helper(struct device *dev) {} +static inline void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table) {} -static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) +static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) { - return -ENOTSUPP; + return ERR_PTR(-ENOTSUPP); } -static inline void dev_pm_opp_put_prop_name(struct device *dev) {} +static inline void dev_pm_opp_put_prop_name(struct opp_table *opp_table) {} static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count) { @@ -239,6 +259,13 @@ static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, co static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {} +static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name) +{ + return ERR_PTR(-ENOTSUPP); +} + +static inline void dev_pm_opp_put_clkname(struct opp_table *opp_table) {} + static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { return -ENOTSUPP; @@ -270,6 +297,7 @@ void dev_pm_opp_of_remove_table(struct device *dev); int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask); void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask); int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); +struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); #else static inline int dev_pm_opp_of_add_table(struct device *dev) { @@ -293,6 +321,11 @@ static inline int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct { return -ENOTSUPP; } + +static inline struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev) +{ + return NULL; +} #endif #endif /* __LINUX_OPP_H__ */ diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 0f65d36c2a75..032b55909145 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -6,7 +6,6 @@ */ #include <linux/plist.h> #include <linux/notifier.h> -#include <linux/miscdevice.h> #include <linux/device.h> #include <linux/workqueue.h> @@ -147,8 +146,6 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier); int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier); -int dev_pm_qos_add_global_notifier(struct notifier_block *notifier); -int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier); void dev_pm_qos_constraints_init(struct device *dev); void dev_pm_qos_constraints_destroy(struct device *dev); int dev_pm_qos_add_ancestor_request(struct device *dev, @@ -173,6 +170,12 @@ static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return dev->power.qos->flags_req->data.flr.flags; } + +static inline s32 dev_pm_qos_raw_read_value(struct device *dev) +{ + return IS_ERR_OR_NULL(dev->power.qos) ? + 0 : pm_qos_read_value(&dev->power.qos->resume_latency); +} #else static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask) @@ -200,12 +203,6 @@ static inline int dev_pm_qos_add_notifier(struct device *dev, static inline int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier) { return 0; } -static inline int dev_pm_qos_add_global_notifier( - struct notifier_block *notifier) - { return 0; } -static inline int dev_pm_qos_remove_global_notifier( - struct notifier_block *notifier) - { return 0; } static inline void dev_pm_qos_constraints_init(struct device *dev) { dev->power.power_state = PMSG_ON; @@ -237,6 +234,7 @@ static inline void dev_pm_qos_hide_latency_tolerance(struct device *dev) {} static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { return 0; } static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; } +static inline s32 dev_pm_qos_raw_read_value(struct device *dev) { return 0; } #endif #endif diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index ca4823e675e2..2efb08a60e63 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -76,16 +76,6 @@ static inline void pm_runtime_put_noidle(struct device *dev) atomic_add_unless(&dev->power.usage_count, -1, 0); } -static inline bool device_run_wake(struct device *dev) -{ - return dev->power.run_wake; -} - -static inline void device_set_run_wake(struct device *dev, bool enable) -{ - dev->power.run_wake = enable; -} - static inline bool pm_runtime_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED @@ -163,8 +153,6 @@ static inline void pm_runtime_forbid(struct device *dev) {} static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} -static inline bool device_run_wake(struct device *dev) { return false; } -static inline void device_set_run_wake(struct device *dev, bool enable) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } static inline bool pm_runtime_active(struct device *dev) { return true; } static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index a3447932df1f..4c2cba7ec1d4 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -106,8 +106,8 @@ extern void __pm_stay_awake(struct wakeup_source *ws); extern void pm_stay_awake(struct device *dev); extern void __pm_relax(struct wakeup_source *ws); extern void pm_relax(struct device *dev); -extern void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec); -extern void pm_wakeup_event(struct device *dev, unsigned int msec); +extern void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard); +extern void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard); #else /* !CONFIG_PM_SLEEP */ @@ -182,9 +182,11 @@ static inline void __pm_relax(struct wakeup_source *ws) {} static inline void pm_relax(struct device *dev) {} -static inline void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec) {} +static inline void pm_wakeup_ws_event(struct wakeup_source *ws, + unsigned int msec, bool hard) {} -static inline void pm_wakeup_event(struct device *dev, unsigned int msec) {} +static inline void pm_wakeup_dev_event(struct device *dev, unsigned int msec, + bool hard) {} #endif /* !CONFIG_PM_SLEEP */ @@ -201,4 +203,19 @@ static inline void wakeup_source_trash(struct wakeup_source *ws) wakeup_source_drop(ws); } +static inline void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec) +{ + return pm_wakeup_ws_event(ws, msec, false); +} + +static inline void pm_wakeup_event(struct device *dev, unsigned int msec) +{ + return pm_wakeup_dev_event(dev, msec, false); +} + +static inline void pm_wakeup_hard_event(struct device *dev) +{ + return pm_wakeup_dev_event(dev, 0, true); +} + #endif /* _LINUX_PM_WAKEUP_H */ diff --git a/include/linux/i2c/pmbus.h b/include/linux/pmbus.h index ee3c2aba2a8e..ee3c2aba2a8e 100644 --- a/include/linux/i2c/pmbus.h +++ b/include/linux/pmbus.h diff --git a/include/linux/pmem.h b/include/linux/pmem.h deleted file mode 100644 index e856c2cb0fe8..000000000000 --- a/include/linux/pmem.h +++ /dev/null @@ -1,165 +0,0 @@ -/* - * Copyright(c) 2015 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ -#ifndef __PMEM_H__ -#define __PMEM_H__ - -#include <linux/io.h> -#include <linux/uio.h> - -#ifdef CONFIG_ARCH_HAS_PMEM_API -#define ARCH_MEMREMAP_PMEM MEMREMAP_WB -#include <asm/pmem.h> -#else -#define ARCH_MEMREMAP_PMEM MEMREMAP_WT -/* - * These are simply here to enable compilation, all call sites gate - * calling these symbols with arch_has_pmem_api() and redirect to the - * implementation in asm/pmem.h. - */ -static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n) -{ - BUG(); -} - -static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n) -{ - BUG(); - return -EFAULT; -} - -static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes, - struct iov_iter *i) -{ - BUG(); - return 0; -} - -static inline void arch_clear_pmem(void *addr, size_t size) -{ - BUG(); -} - -static inline void arch_wb_cache_pmem(void *addr, size_t size) -{ - BUG(); -} - -static inline void arch_invalidate_pmem(void *addr, size_t size) -{ - BUG(); -} -#endif - -static inline bool arch_has_pmem_api(void) -{ - return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API); -} - -/* - * memcpy_from_pmem - read from persistent memory with error handling - * @dst: destination buffer - * @src: source buffer - * @size: transfer length - * - * Returns 0 on success negative error code on failure. - */ -static inline int memcpy_from_pmem(void *dst, void const *src, size_t size) -{ - if (arch_has_pmem_api()) - return arch_memcpy_from_pmem(dst, src, size); - else - memcpy(dst, src, size); - return 0; -} - -/** - * memcpy_to_pmem - copy data to persistent memory - * @dst: destination buffer for the copy - * @src: source buffer for the copy - * @n: length of the copy in bytes - * - * Perform a memory copy that results in the destination of the copy - * being effectively evicted from, or never written to, the processor - * cache hierarchy after the copy completes. After memcpy_to_pmem() - * data may still reside in cpu or platform buffers, so this operation - * must be followed by a blkdev_issue_flush() on the pmem block device. - */ -static inline void memcpy_to_pmem(void *dst, const void *src, size_t n) -{ - if (arch_has_pmem_api()) - arch_memcpy_to_pmem(dst, src, n); - else - memcpy(dst, src, n); -} - -/** - * copy_from_iter_pmem - copy data from an iterator to PMEM - * @addr: PMEM destination address - * @bytes: number of bytes to copy - * @i: iterator with source data - * - * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'. - * See blkdev_issue_flush() note for memcpy_to_pmem(). - */ -static inline size_t copy_from_iter_pmem(void *addr, size_t bytes, - struct iov_iter *i) -{ - if (arch_has_pmem_api()) - return arch_copy_from_iter_pmem(addr, bytes, i); - return copy_from_iter_nocache(addr, bytes, i); -} - -/** - * clear_pmem - zero a PMEM memory range - * @addr: virtual start address - * @size: number of bytes to zero - * - * Write zeros into the memory range starting at 'addr' for 'size' bytes. - * See blkdev_issue_flush() note for memcpy_to_pmem(). - */ -static inline void clear_pmem(void *addr, size_t size) -{ - if (arch_has_pmem_api()) - arch_clear_pmem(addr, size); - else - memset(addr, 0, size); -} - -/** - * invalidate_pmem - flush a pmem range from the cache hierarchy - * @addr: virtual start address - * @size: bytes to invalidate (internally aligned to cache line size) - * - * For platforms that support clearing poison this flushes any poisoned - * ranges out of the cache - */ -static inline void invalidate_pmem(void *addr, size_t size) -{ - if (arch_has_pmem_api()) - arch_invalidate_pmem(addr, size); -} - -/** - * wb_cache_pmem - write back processor cache for PMEM memory range - * @addr: virtual start address - * @size: number of bytes to write back - * - * Write back the processor cache range starting at 'addr' for 'size' bytes. - * See blkdev_issue_flush() note for memcpy_to_pmem(). - */ -static inline void wb_cache_pmem(void *addr, size_t size) -{ - if (arch_has_pmem_api()) - arch_wb_cache_pmem(addr, size); -} -#endif /* __PMEM_H__ */ diff --git a/include/linux/poison.h b/include/linux/poison.h index 51334edec506..a39540326417 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -80,6 +80,7 @@ /********** kernel/mutexes **********/ #define MUTEX_DEBUG_INIT 0x11 #define MUTEX_DEBUG_FREE 0x22 +#define MUTEX_POISON_WW_CTX ((void *) 0x500 + POISON_POINTER_DELTA) /********** lib/flex_array.c **********/ #define FLEX_ARRAY_FREE 0x6c /* for use-after-free poisoning */ diff --git a/include/linux/poll.h b/include/linux/poll.h index a46d6755035e..2889f09a1c60 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -75,7 +75,7 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) struct poll_table_entry { struct file *filp; unsigned long key; - wait_queue_t wait; + wait_queue_entry_t wait; wait_queue_head_t *wait_address; }; @@ -98,64 +98,8 @@ extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack); extern u64 select_estimate_accuracy(struct timespec64 *tv); - -static inline int poll_schedule(struct poll_wqueues *pwq, int state) -{ - return poll_schedule_timeout(pwq, state, NULL, 0); -} - -/* - * Scalable version of the fd_set. - */ - -typedef struct { - unsigned long *in, *out, *ex; - unsigned long *res_in, *res_out, *res_ex; -} fd_set_bits; - -/* - * How many longwords for "nr" bits? - */ -#define FDS_BITPERLONG (8*sizeof(long)) -#define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG) -#define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long)) - -/* - * We do a VERIFY_WRITE here even though we are only reading this time: - * we'll write to it eventually.. - * - * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned. - */ -static inline -int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) -{ - nr = FDS_BYTES(nr); - if (ufdset) - return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0; - - memset(fdset, 0, nr); - return 0; -} - -static inline unsigned long __must_check -set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) -{ - if (ufdset) - return __copy_to_user(ufdset, fdset, FDS_BYTES(nr)); - return 0; -} - -static inline -void zero_fd_set(unsigned long nr, unsigned long *fdset) -{ - memset(fdset, 0, FDS_BYTES(nr)); -} - #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1) -extern int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time); -extern int do_sys_poll(struct pollfd __user * ufds, unsigned int nfds, - struct timespec64 *end_time); extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time); diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index 34c4498b800f..38d8225510f1 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -42,12 +42,6 @@ struct posix_clock; * @clock_gettime: Read the current time * @clock_getres: Get the clock resolution * @clock_settime: Set the current time value - * @timer_create: Create a new timer - * @timer_delete: Remove a previously created timer - * @timer_gettime: Get remaining time and interval of a timer - * @timer_settime: Set a timer's initial expiration and interval - * @fasync: Optional character device fasync method - * @mmap: Optional character device mmap method * @open: Optional character device open method * @release: Optional character device release method * @ioctl: Optional character device ioctl method @@ -59,35 +53,19 @@ struct posix_clock_operations { int (*clock_adjtime)(struct posix_clock *pc, struct timex *tx); - int (*clock_gettime)(struct posix_clock *pc, struct timespec *ts); + int (*clock_gettime)(struct posix_clock *pc, struct timespec64 *ts); - int (*clock_getres) (struct posix_clock *pc, struct timespec *ts); + int (*clock_getres) (struct posix_clock *pc, struct timespec64 *ts); int (*clock_settime)(struct posix_clock *pc, - const struct timespec *ts); + const struct timespec64 *ts); - int (*timer_create) (struct posix_clock *pc, struct k_itimer *kit); - - int (*timer_delete) (struct posix_clock *pc, struct k_itimer *kit); - - void (*timer_gettime)(struct posix_clock *pc, - struct k_itimer *kit, struct itimerspec *tsp); - - int (*timer_settime)(struct posix_clock *pc, - struct k_itimer *kit, int flags, - struct itimerspec *tsp, struct itimerspec *old); /* * Optional character device methods: */ - int (*fasync) (struct posix_clock *pc, - int fd, struct file *file, int on); - long (*ioctl) (struct posix_clock *pc, unsigned int cmd, unsigned long arg); - int (*mmap) (struct posix_clock *pc, - struct vm_area_struct *vma); - int (*open) (struct posix_clock *pc, fmode_t f_mode); uint (*poll) (struct posix_clock *pc, diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 62d44c176071..62839fd04dce 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -7,20 +7,11 @@ #include <linux/timex.h> #include <linux/alarmtimer.h> - -static inline unsigned long long cputime_to_expires(cputime_t expires) -{ - return (__force unsigned long long)expires; -} - -static inline cputime_t expires_to_cputime(unsigned long long expires) -{ - return (__force cputime_t)expires; -} +struct siginfo; struct cpu_timer_list { struct list_head entry; - unsigned long long expires, incr; + u64 expires, incr; struct task_struct *task; int firing; }; @@ -58,81 +49,68 @@ struct cpu_timer_list { #define FD_TO_CLOCKID(fd) ((~(clockid_t) (fd) << 3) | CLOCKFD) #define CLOCKID_TO_FD(clk) ((unsigned int) ~((clk) >> 3)) -/* POSIX.1b interval timer structure. */ -struct k_itimer { - struct list_head list; /* free/ allocate list */ - struct hlist_node t_hash; - spinlock_t it_lock; - clockid_t it_clock; /* which timer type */ - timer_t it_id; /* timer id */ - int it_overrun; /* overrun on pending signal */ - int it_overrun_last; /* overrun on last delivered signal */ - int it_requeue_pending; /* waiting to requeue this timer */ #define REQUEUE_PENDING 1 - int it_sigev_notify; /* notify word of sigevent struct */ - struct signal_struct *it_signal; + +/** + * struct k_itimer - POSIX.1b interval timer structure. + * @list: List head for binding the timer to signals->posix_timers + * @t_hash: Entry in the posix timer hash table + * @it_lock: Lock protecting the timer + * @kclock: Pointer to the k_clock struct handling this timer + * @it_clock: The posix timer clock id + * @it_id: The posix timer id for identifying the timer + * @it_active: Marker that timer is active + * @it_overrun: The overrun counter for pending signals + * @it_overrun_last: The overrun at the time of the last delivered signal + * @it_requeue_pending: Indicator that timer waits for being requeued on + * signal delivery + * @it_sigev_notify: The notify word of sigevent struct for signal delivery + * @it_interval: The interval for periodic timers + * @it_signal: Pointer to the creators signal struct + * @it_pid: The pid of the process/task targeted by the signal + * @it_process: The task to wakeup on clock_nanosleep (CPU timers) + * @sigq: Pointer to preallocated sigqueue + * @it: Union representing the various posix timer type + * internals. Also used for rcu freeing the timer. + */ +struct k_itimer { + struct list_head list; + struct hlist_node t_hash; + spinlock_t it_lock; + const struct k_clock *kclock; + clockid_t it_clock; + timer_t it_id; + int it_active; + int it_overrun; + int it_overrun_last; + int it_requeue_pending; + int it_sigev_notify; + ktime_t it_interval; + struct signal_struct *it_signal; union { - struct pid *it_pid; /* pid of process to send signal to */ - struct task_struct *it_process; /* for clock_nanosleep */ + struct pid *it_pid; + struct task_struct *it_process; }; - struct sigqueue *sigq; /* signal queue entry. */ + struct sigqueue *sigq; union { struct { - struct hrtimer timer; - ktime_t interval; + struct hrtimer timer; } real; - struct cpu_timer_list cpu; - struct { - unsigned int clock; - unsigned int node; - unsigned long incr; - unsigned long expires; - } mmtimer; + struct cpu_timer_list cpu; struct { - struct alarm alarmtimer; - ktime_t interval; + struct alarm alarmtimer; } alarm; - struct rcu_head rcu; + struct rcu_head rcu; } it; }; -struct k_clock { - int (*clock_getres) (const clockid_t which_clock, struct timespec *tp); - int (*clock_set) (const clockid_t which_clock, - const struct timespec *tp); - int (*clock_get) (const clockid_t which_clock, struct timespec * tp); - int (*clock_adj) (const clockid_t which_clock, struct timex *tx); - int (*timer_create) (struct k_itimer *timer); - int (*nsleep) (const clockid_t which_clock, int flags, - struct timespec *, struct timespec __user *); - long (*nsleep_restart) (struct restart_block *restart_block); - int (*timer_set) (struct k_itimer * timr, int flags, - struct itimerspec * new_setting, - struct itimerspec * old_setting); - int (*timer_del) (struct k_itimer * timr); -#define TIMER_RETRY 1 - void (*timer_get) (struct k_itimer * timr, - struct itimerspec * cur_setting); -}; - -extern struct k_clock clock_posix_cpu; -extern struct k_clock clock_posix_dynamic; - -void posix_timers_register_clock(const clockid_t clock_id, struct k_clock *new_clock); - -/* function to call to trigger timer event */ -int posix_timer_event(struct k_itimer *timr, int si_private); - -void posix_cpu_timer_schedule(struct k_itimer *timer); - void run_posix_cpu_timers(struct task_struct *task); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, - cputime_t *newval, cputime_t *oldval); - -long clock_nanosleep_restart(struct restart_block *restart_block); + u64 *newval, u64 *oldval); void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); +void posixtimer_rearm(struct siginfo *info); #endif diff --git a/include/linux/power/bq24190_charger.h b/include/linux/power/bq24190_charger.h deleted file mode 100644 index 9f0283721cbc..000000000000 --- a/include/linux/power/bq24190_charger.h +++ /dev/null @@ -1,16 +0,0 @@ -/* - * Platform data for the TI bq24190 battery charger driver. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef _BQ24190_CHARGER_H_ -#define _BQ24190_CHARGER_H_ - -struct bq24190_platform_data { - unsigned int gpio_int; /* GPIO pin that's connected to INT# */ -}; - -#endif diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index bed9557b69e7..11e11685dd1d 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -4,8 +4,16 @@ enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ - BQ27500, /* bq27500 */ - BQ27510, /* bq27510, bq27520 */ + BQ2750X, /* bq27500 deprecated alias */ + BQ2751X, /* bq27510, bq27520 deprecated alias */ + BQ27500, /* bq27500/1 */ + BQ27510G1, /* bq27510G1 */ + BQ27510G2, /* bq27510G2 */ + BQ27510G3, /* bq27510G3 */ + BQ27520G1, /* bq27520G1 */ + BQ27520G2, /* bq27520G2 */ + BQ27520G3, /* bq27520G3 */ + BQ27520G4, /* bq27520G4 */ BQ27530, /* bq27530, bq27531 */ BQ27541, /* bq27541, bq27542, bq27546, bq27742 */ BQ27545, /* bq27545 */ @@ -32,6 +40,9 @@ struct bq27xxx_platform_data { struct bq27xxx_device_info; struct bq27xxx_access_methods { int (*read)(struct bq27xxx_device_info *di, u8 reg, bool single); + int (*write)(struct bq27xxx_device_info *di, u8 reg, int value, bool single); + int (*read_bulk)(struct bq27xxx_device_info *di, u8 reg, u8 *data, int len); + int (*write_bulk)(struct bq27xxx_device_info *di, u8 reg, u8 *data, int len); }; struct bq27xxx_reg_cache { @@ -52,7 +63,10 @@ struct bq27xxx_device_info { struct device *dev; int id; enum bq27xxx_chip chip; + bool ram_chip; const char *name; + struct bq27xxx_dm_reg *dm_regs; + u32 unseal_key; struct bq27xxx_access_methods bus; struct bq27xxx_reg_cache cache; int charge_design_full; diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h index 522757ac9cd4..a7ed29baf44a 100644 --- a/include/linux/power/max17042_battery.h +++ b/include/linux/power/max17042_battery.h @@ -24,8 +24,15 @@ #define __MAX17042_BATTERY_H_ #define MAX17042_STATUS_BattAbsent (1 << 3) -#define MAX17042_BATTERY_FULL (100) +#define MAX17042_BATTERY_FULL (95) /* Recommend. FullSOCThr value */ #define MAX17042_DEFAULT_SNS_RESISTOR (10000) +#define MAX17042_DEFAULT_VMIN (3000) +#define MAX17042_DEFAULT_VMAX (4500) /* LiHV cell max */ +#define MAX17042_DEFAULT_TEMP_MIN (0) /* For sys without temp sensor */ +#define MAX17042_DEFAULT_TEMP_MAX (700) /* 70 degrees Celcius */ + +/* Consider RepCap which is less then 10 units below FullCAP full */ +#define MAX17042_FULL_THRESHOLD 10 #define MAX17042_CHARACTERIZATION_DATA_SIZE 48 diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 3965503315ef..de89066b72b1 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -146,6 +146,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_TIME_TO_FULL_AVG, POWER_SUPPLY_PROP_TYPE, /* use power_supply.type instead */ POWER_SUPPLY_PROP_SCOPE, + POWER_SUPPLY_PROP_PRECHARGE_CURRENT, POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT, POWER_SUPPLY_PROP_CALIBRATE, /* Properties of type `const char *' */ @@ -159,13 +160,14 @@ enum power_supply_type { POWER_SUPPLY_TYPE_BATTERY, POWER_SUPPLY_TYPE_UPS, POWER_SUPPLY_TYPE_MAINS, - POWER_SUPPLY_TYPE_USB, /* Standard Downstream Port */ - POWER_SUPPLY_TYPE_USB_DCP, /* Dedicated Charging Port */ - POWER_SUPPLY_TYPE_USB_CDP, /* Charging Downstream Port */ - POWER_SUPPLY_TYPE_USB_ACA, /* Accessory Charger Adapters */ - POWER_SUPPLY_TYPE_USB_TYPE_C, /* Type C Port */ - POWER_SUPPLY_TYPE_USB_PD, /* Power Delivery Port */ - POWER_SUPPLY_TYPE_USB_PD_DRP, /* PD Dual Role Port */ + POWER_SUPPLY_TYPE_USB, /* Standard Downstream Port */ + POWER_SUPPLY_TYPE_USB_DCP, /* Dedicated Charging Port */ + POWER_SUPPLY_TYPE_USB_CDP, /* Charging Downstream Port */ + POWER_SUPPLY_TYPE_USB_ACA, /* Accessory Charger Adapters */ + POWER_SUPPLY_TYPE_USB_TYPE_C, /* Type C Port */ + POWER_SUPPLY_TYPE_USB_PD, /* Power Delivery Port */ + POWER_SUPPLY_TYPE_USB_PD_DRP, /* PD Dual Role Port */ + POWER_SUPPLY_TYPE_APPLE_BRICK_ID, /* Apple Charging Method */ }; enum power_supply_notifier_events { @@ -288,6 +290,25 @@ struct power_supply_info { int use_for_apm; }; +/* + * This is the recommended struct to manage static battery parameters, + * populated by power_supply_get_battery_info(). Most platform drivers should + * use these for consistency. + * Its field names must correspond to elements in enum power_supply_property. + * The default field value is -EINVAL. + * Power supply class itself doesn't use this. + */ + +struct power_supply_battery_info { + int energy_full_design_uwh; /* microWatt-hours */ + int charge_full_design_uah; /* microAmp-hours */ + int voltage_min_design_uv; /* microVolts */ + int precharge_current_ua; /* microAmps */ + int charge_term_current_ua; /* microAmps */ + int constant_charge_current_max_ua; /* microAmps */ + int constant_charge_voltage_max_uv; /* microVolts */ +}; + extern struct atomic_notifier_head power_supply_notifier; extern int power_supply_reg_notifier(struct notifier_block *nb); extern void power_supply_unreg_notifier(struct notifier_block *nb); @@ -306,6 +327,9 @@ static inline struct power_supply * devm_power_supply_get_by_phandle(struct device *dev, const char *property) { return NULL; } #endif /* CONFIG_OF */ + +extern int power_supply_get_battery_info(struct power_supply *psy, + struct power_supply_battery_info *info); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); extern int power_supply_set_battery_charged(struct power_supply *psy); @@ -359,6 +383,8 @@ static inline bool power_supply_is_amp_property(enum power_supply_property psp) case POWER_SUPPLY_PROP_CHARGE_NOW: case POWER_SUPPLY_PROP_CHARGE_AVG: case POWER_SUPPLY_PROP_CHARGE_COUNTER: + case POWER_SUPPLY_PROP_PRECHARGE_CURRENT: + case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT: case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: case POWER_SUPPLY_PROP_CURRENT_MAX: diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 7eeceac52dea..cae461224948 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -55,6 +55,27 @@ /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 +#define PREEMPT_DISABLED (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) + +/* + * Disable preemption until the scheduler is running -- use an unconditional + * value so that it also works on !PREEMPT_COUNT kernels. + * + * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count(). + */ +#define INIT_PREEMPT_COUNT PREEMPT_OFFSET + +/* + * Initial preempt_count value; reflects the preempt_count schedule invariant + * which states that during context switches: + * + * preempt_count() == 2*PREEMPT_DISABLE_OFFSET + * + * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels. + * Note: See finish_task_switch(). + */ +#define FORK_PREEMPT_COUNT (2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) + /* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */ #include <asm/preempt.h> diff --git a/include/linux/prime_numbers.h b/include/linux/prime_numbers.h new file mode 100644 index 000000000000..14ec4f567342 --- /dev/null +++ b/include/linux/prime_numbers.h @@ -0,0 +1,37 @@ +#ifndef __LINUX_PRIME_NUMBERS_H +#define __LINUX_PRIME_NUMBERS_H + +#include <linux/types.h> + +bool is_prime_number(unsigned long x); +unsigned long next_prime_number(unsigned long x); + +/** + * for_each_prime_number - iterate over each prime upto a value + * @prime: the current prime number in this iteration + * @max: the upper limit + * + * Starting from the first prime number 2 iterate over each prime number up to + * the @max value. On each iteration, @prime is set to the current prime number. + * @max should be less than ULONG_MAX to ensure termination. To begin with + * @prime set to 1 on the first iteration use for_each_prime_number_from() + * instead. + */ +#define for_each_prime_number(prime, max) \ + for_each_prime_number_from((prime), 2, (max)) + +/** + * for_each_prime_number_from - iterate over each prime upto a value + * @prime: the current prime number in this iteration + * @from: the initial value + * @max: the upper limit + * + * Starting from @from iterate over each successive prime number up to the + * @max value. On each iteration, @prime is set to the current prime number. + * @max should be less than ULONG_MAX, and @from less than @max, to ensure + * termination. + */ +#define for_each_prime_number_from(prime, from, max) \ + for (prime = (from); prime <= (max); prime = next_prime_number(prime)) + +#endif /* !__LINUX_PRIME_NUMBERS_H */ diff --git a/include/linux/printk.h b/include/linux/printk.h index 3472cc6b7a60..e10f27468322 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -147,17 +147,11 @@ void early_printk(const char *s, ...) { } #endif #ifdef CONFIG_PRINTK_NMI -extern void printk_nmi_init(void); extern void printk_nmi_enter(void); extern void printk_nmi_exit(void); -extern void printk_nmi_flush(void); -extern void printk_nmi_flush_on_panic(void); #else -static inline void printk_nmi_init(void) { } static inline void printk_nmi_enter(void) { } static inline void printk_nmi_exit(void) { } -static inline void printk_nmi_flush(void) { } -static inline void printk_nmi_flush_on_panic(void) { } #endif /* PRINTK_NMI */ #ifdef CONFIG_PRINTK @@ -204,11 +198,14 @@ extern void wake_up_klogd(void); char *log_buf_addr_get(void); u32 log_buf_len_get(void); -void log_buf_kexec_setup(void); +void log_buf_vmcoreinfo_setup(void); void __init setup_log_buf(int early); __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); +extern void printk_safe_init(void); +extern void printk_safe_flush(void); +extern void printk_safe_flush_on_panic(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -249,7 +246,7 @@ static inline u32 log_buf_len_get(void) return 0; } -static inline void log_buf_kexec_setup(void) +static inline void log_buf_vmcoreinfo_setup(void) { } @@ -268,6 +265,18 @@ static inline void dump_stack_print_info(const char *log_lvl) static inline void show_regs_print_info(const char *log_lvl) { } + +static inline void printk_safe_init(void) +{ +} + +static inline void printk_safe_flush(void) +{ +} + +static inline void printk_safe_flush_on_panic(void) +{ +} #endif extern asmlinkage void dump_stack(void) __cold; diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 12cb8bd81d2d..06844b54dfc1 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -14,18 +14,20 @@ struct inode; struct proc_ns_operations { const char *name; + const char *real_ns_name; int type; struct ns_common *(*get)(struct task_struct *task); void (*put)(struct ns_common *ns); int (*install)(struct nsproxy *nsproxy, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); struct ns_common *(*get_parent)(struct ns_common *ns); -}; +} __randomize_layout; extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; extern const struct proc_ns_operations ipcns_operations; extern const struct proc_ns_operations pidns_operations; +extern const struct proc_ns_operations pidns_for_children_operations; extern const struct proc_ns_operations userns_operations; extern const struct proc_ns_operations mntns_operations; extern const struct proc_ns_operations cgroupns_operations; diff --git a/include/linux/processor.h b/include/linux/processor.h new file mode 100644 index 000000000000..da0c5e56ca02 --- /dev/null +++ b/include/linux/processor.h @@ -0,0 +1,70 @@ +/* Misc low level processor primitives */ +#ifndef _LINUX_PROCESSOR_H +#define _LINUX_PROCESSOR_H + +#include <asm/processor.h> + +/* + * spin_begin is used before beginning a busy-wait loop, and must be paired + * with spin_end when the loop is exited. spin_cpu_relax must be called + * within the loop. + * + * The loop body should be as small and fast as possible, on the order of + * tens of instructions/cycles as a guide. It should and avoid calling + * cpu_relax, or any "spin" or sleep type of primitive including nested uses + * of these primitives. It should not lock or take any other resource. + * Violations of these guidelies will not cause a bug, but may cause sub + * optimal performance. + * + * These loops are optimized to be used where wait times are expected to be + * less than the cost of a context switch (and associated overhead). + * + * Detection of resource owner and decision to spin or sleep or guest-yield + * (e.g., spin lock holder vcpu preempted, or mutex owner not on CPU) can be + * tested within the loop body. + */ +#ifndef spin_begin +#define spin_begin() +#endif + +#ifndef spin_cpu_relax +#define spin_cpu_relax() cpu_relax() +#endif + +/* + * spin_cpu_yield may be called to yield (undirected) to the hypervisor if + * necessary. This should be used if the wait is expected to take longer + * than context switch overhead, but we can't sleep or do a directed yield. + */ +#ifndef spin_cpu_yield +#define spin_cpu_yield() cpu_relax_yield() +#endif + +#ifndef spin_end +#define spin_end() +#endif + +/* + * spin_until_cond can be used to wait for a condition to become true. It + * may be expected that the first iteration will true in the common case + * (no spinning), so that callers should not require a first "likely" test + * for the uncontended case before using this primitive. + * + * Usage and implementation guidelines are the same as for the spin_begin + * primitives, above. + */ +#ifndef spin_until_cond +#define spin_until_cond(cond) \ +do { \ + if (unlikely(!(cond))) { \ + spin_begin(); \ + do { \ + spin_cpu_relax(); \ + } while (!(cond)); \ + spin_end(); \ + } \ +} while (0) + +#endif + +#endif /* _LINUX_PROCESSOR_H */ diff --git a/include/linux/property.h b/include/linux/property.h index 856e50b2140c..7e77039e6b81 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -33,6 +33,8 @@ enum dev_dma_attr { DEV_DMA_COHERENT, }; +struct fwnode_handle *dev_fwnode(struct device *dev); + bool device_property_present(struct device *dev, const char *propname); int device_property_read_u8_array(struct device *dev, const char *propname, u8 *val, size_t nval); @@ -49,6 +51,7 @@ int device_property_read_string(struct device *dev, const char *propname, int device_property_match_string(struct device *dev, const char *propname, const char *string); +bool fwnode_device_is_available(struct fwnode_handle *fwnode); bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname); int fwnode_property_read_u8_array(struct fwnode_handle *fwnode, const char *propname, u8 *val, @@ -70,6 +73,15 @@ int fwnode_property_read_string(struct fwnode_handle *fwnode, int fwnode_property_match_string(struct fwnode_handle *fwnode, const char *propname, const char *string); +struct fwnode_handle *fwnode_get_parent(struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_next_child_node(struct fwnode_handle *fwnode, + struct fwnode_handle *child); + +#define fwnode_for_each_child_node(fwnode, child) \ + for (child = fwnode_get_next_child_node(fwnode, NULL); child; \ + child = fwnode_get_next_child_node(fwnode, child)) + struct fwnode_handle *device_get_next_child_node(struct device *dev, struct fwnode_handle *child); @@ -77,9 +89,12 @@ struct fwnode_handle *device_get_next_child_node(struct device *dev, for (child = device_get_next_child_node(dev, NULL); child; \ child = device_get_next_child_node(dev, child)) +struct fwnode_handle *fwnode_get_named_child_node(struct fwnode_handle *fwnode, + const char *childname); struct fwnode_handle *device_get_named_child_node(struct device *dev, const char *childname); +void fwnode_handle_get(struct fwnode_handle *fwnode); void fwnode_handle_put(struct fwnode_handle *fwnode); unsigned int device_get_child_node_count(struct device *dev); @@ -160,12 +175,12 @@ struct property_entry { bool is_string; union { union { - void *raw_data; - u8 *u8_data; - u16 *u16_data; - u32 *u32_data; - u64 *u64_data; - const char **str; + const void *raw_data; + const u8 *u8_data; + const u16 *u16_data; + const u32 *u32_data; + const u64 *u64_data; + const char * const *str; } pointer; union { unsigned long long raw_data; @@ -241,8 +256,13 @@ struct property_entry { .name = _name_, \ } +struct property_entry * +property_entries_dup(const struct property_entry *properties); + +void property_entries_free(const struct property_entry *properties); + int device_add_properties(struct device *dev, - struct property_entry *properties); + const struct property_entry *properties); void device_remove_properties(struct device *dev); bool device_dma_supported(struct device *dev); @@ -253,4 +273,20 @@ int device_get_phy_mode(struct device *dev); void *device_get_mac_address(struct device *dev, char *addr, int alen); +struct fwnode_handle *fwnode_graph_get_next_endpoint( + struct fwnode_handle *fwnode, struct fwnode_handle *prev); +struct fwnode_handle * +fwnode_graph_get_port_parent(struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_graph_get_remote_port_parent( + struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_graph_get_remote_port( + struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_graph_get_remote_endpoint( + struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_graph_get_remote_node(struct fwnode_handle *fwnode, + u32 port, u32 endpoint); + +int fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode, + struct fwnode_endpoint *endpoint); + #endif /* _LINUX_PROPERTY_H_ */ diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 0da29cae009b..61f806a7fe29 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -30,7 +30,9 @@ #include <linux/time.h> #include <linux/types.h> -/* types */ +struct module; + +/* pstore record types (see fs/pstore/inode.c for filename templates) */ enum pstore_type_id { PSTORE_TYPE_DMESG = 0, PSTORE_TYPE_MCE = 1, @@ -45,42 +47,149 @@ enum pstore_type_id { PSTORE_TYPE_UNKNOWN = 255 }; -struct module; +struct pstore_info; +/** + * struct pstore_record - details of a pstore record entry + * @psi: pstore backend driver information + * @type: pstore record type + * @id: per-type unique identifier for record + * @time: timestamp of the record + * @buf: pointer to record contents + * @size: size of @buf + * @ecc_notice_size: + * ECC information for @buf + * + * Valid for PSTORE_TYPE_DMESG @type: + * + * @count: Oops count since boot + * @reason: kdump reason for notification + * @part: position in a multipart record + * @compressed: whether the buffer is compressed + * + */ +struct pstore_record { + struct pstore_info *psi; + enum pstore_type_id type; + u64 id; + struct timespec time; + char *buf; + ssize_t size; + ssize_t ecc_notice_size; + int count; + enum kmsg_dump_reason reason; + unsigned int part; + bool compressed; +}; + +/** + * struct pstore_info - backend pstore driver structure + * + * @owner: module which is repsonsible for this backend driver + * @name: name of the backend driver + * + * @buf_lock: spinlock to serialize access to @buf + * @buf: preallocated crash dump buffer + * @bufsize: size of @buf available for crash dump writes + * + * @read_mutex: serializes @open, @read, @close, and @erase callbacks + * @flags: bitfield of frontends the backend can accept writes for + * @data: backend-private pointer passed back during callbacks + * + * Callbacks: + * + * @open: + * Notify backend that pstore is starting a full read of backend + * records. Followed by one or more @read calls, and a final @close. + * + * @psi: in: pointer to the struct pstore_info for the backend + * + * Returns 0 on success, and non-zero on error. + * + * @close: + * Notify backend that pstore has finished a full read of backend + * records. Always preceded by an @open call and one or more @read + * calls. + * + * @psi: in: pointer to the struct pstore_info for the backend + * + * Returns 0 on success, and non-zero on error. (Though pstore will + * ignore the error.) + * + * @read: + * Read next available backend record. Called after a successful + * @open. + * + * @record: + * pointer to record to populate. @buf should be allocated + * by the backend and filled. At least @type and @id should + * be populated, since these are used when creating pstorefs + * file names. + * + * Returns record size on success, zero when no more records are + * available, or negative on error. + * + * @write: + * A newly generated record needs to be written to backend storage. + * + * @record: + * pointer to record metadata. When @type is PSTORE_TYPE_DMESG, + * @buf will be pointing to the preallocated @psi.buf, since + * memory allocation may be broken during an Oops. Regardless, + * @buf must be proccesed or copied before returning. The + * backend is also expected to write @id with something that + * can help identify this record to a future @erase callback. + * The @time field will be prepopulated with the current time, + * when available. The @size field will have the size of data + * in @buf. + * + * Returns 0 on success, and non-zero on error. + * + * @write_user: + * Perform a frontend write to a backend record, using a specified + * buffer that is coming directly from userspace, instead of the + * @record @buf. + * + * @record: pointer to record metadata. + * @buf: pointer to userspace contents to write to backend + * + * Returns 0 on success, and non-zero on error. + * + * @erase: + * Delete a record from backend storage. Different backends + * identify records differently, so entire original record is + * passed back to assist in identification of what the backend + * should remove from storage. + * + * @record: pointer to record metadata. + * + * Returns 0 on success, and non-zero on error. + * + */ struct pstore_info { struct module *owner; char *name; - spinlock_t buf_lock; /* serialize access to 'buf' */ + + spinlock_t buf_lock; char *buf; size_t bufsize; - struct mutex read_mutex; /* serialize open/read/close */ + + struct mutex read_mutex; + int flags; + void *data; + int (*open)(struct pstore_info *psi); int (*close)(struct pstore_info *psi); - ssize_t (*read)(u64 *id, enum pstore_type_id *type, - int *count, struct timespec *time, char **buf, - bool *compressed, ssize_t *ecc_notice_size, - struct pstore_info *psi); - int (*write)(enum pstore_type_id type, - enum kmsg_dump_reason reason, u64 *id, - unsigned int part, int count, bool compressed, - size_t size, struct pstore_info *psi); - int (*write_buf)(enum pstore_type_id type, - enum kmsg_dump_reason reason, u64 *id, - unsigned int part, const char *buf, bool compressed, - size_t size, struct pstore_info *psi); - int (*write_buf_user)(enum pstore_type_id type, - enum kmsg_dump_reason reason, u64 *id, - unsigned int part, const char __user *buf, - bool compressed, size_t size, struct pstore_info *psi); - int (*erase)(enum pstore_type_id type, u64 id, - int count, struct timespec time, - struct pstore_info *psi); - void *data; + ssize_t (*read)(struct pstore_record *record); + int (*write)(struct pstore_record *record); + int (*write_user)(struct pstore_record *record, + const char __user *buf); + int (*erase)(struct pstore_record *record); }; +/* Supported frontends */ #define PSTORE_FLAGS_DMESG (1 << 0) -#define PSTORE_FLAGS_FRAGILE PSTORE_FLAGS_DMESG #define PSTORE_FLAGS_CONSOLE (1 << 1) #define PSTORE_FLAGS_FTRACE (1 << 2) #define PSTORE_FLAGS_PMSG (1 << 3) diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 2052011bf9fb..d8c97ec8a8e6 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -34,11 +34,13 @@ struct ptr_ring { int producer ____cacheline_aligned_in_smp; spinlock_t producer_lock; - int consumer ____cacheline_aligned_in_smp; + int consumer_head ____cacheline_aligned_in_smp; /* next valid entry */ + int consumer_tail; /* next entry to invalidate */ spinlock_t consumer_lock; /* Shared consumer/producer data */ /* Read-only by both the producer and the consumer */ int size ____cacheline_aligned_in_smp; /* max entries in queue */ + int batch; /* number of entries to consume in a batch */ void **queue; }; @@ -111,6 +113,11 @@ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) return 0; } +/* + * Note: resize (below) nests producer lock within consumer lock, so if you + * consume in interrupt or BH context, you must disable interrupts/BH when + * calling this. + */ static inline int ptr_ring_produce(struct ptr_ring *r, void *ptr) { int ret; @@ -165,7 +172,7 @@ static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr) static inline void *__ptr_ring_peek(struct ptr_ring *r) { if (likely(r->size)) - return r->queue[r->consumer]; + return r->queue[r->consumer_head]; return NULL; } @@ -226,9 +233,38 @@ static inline bool ptr_ring_empty_bh(struct ptr_ring *r) /* Must only be called after __ptr_ring_peek returned !NULL */ static inline void __ptr_ring_discard_one(struct ptr_ring *r) { - r->queue[r->consumer++] = NULL; - if (unlikely(r->consumer >= r->size)) - r->consumer = 0; + /* Fundamentally, what we want to do is update consumer + * index and zero out the entry so producer can reuse it. + * Doing it naively at each consume would be as simple as: + * r->queue[r->consumer++] = NULL; + * if (unlikely(r->consumer >= r->size)) + * r->consumer = 0; + * but that is suboptimal when the ring is full as producer is writing + * out new entries in the same cache line. Defer these updates until a + * batch of entries has been consumed. + */ + int head = r->consumer_head++; + + /* Once we have processed enough entries invalidate them in + * the ring all at once so producer can reuse their space in the ring. + * We also do this when we reach end of the ring - not mandatory + * but helps keep the implementation simple. + */ + if (unlikely(r->consumer_head - r->consumer_tail >= r->batch || + r->consumer_head >= r->size)) { + /* Zero out entries in the reverse order: this way we touch the + * cache line that producer might currently be reading the last; + * producer won't make progress and touch other cache lines + * besides the first one until we write out all entries. + */ + while (likely(head >= r->consumer_tail)) + r->queue[head--] = NULL; + r->consumer_tail = r->consumer_head; + } + if (unlikely(r->consumer_head >= r->size)) { + r->consumer_head = 0; + r->consumer_tail = 0; + } } static inline void *__ptr_ring_consume(struct ptr_ring *r) @@ -242,6 +278,27 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r) return ptr; } +static inline int __ptr_ring_consume_batched(struct ptr_ring *r, + void **array, int n) +{ + void *ptr; + int i; + + for (i = 0; i < n; i++) { + ptr = __ptr_ring_consume(r); + if (!ptr) + break; + array[i] = ptr; + } + + return i; +} + +/* + * Note: resize (below) nests producer lock within consumer lock, so if you + * call this in interrupt or BH context, you must disable interrupts/BH when + * producing. + */ static inline void *ptr_ring_consume(struct ptr_ring *r) { void *ptr; @@ -287,6 +344,55 @@ static inline void *ptr_ring_consume_bh(struct ptr_ring *r) return ptr; } +static inline int ptr_ring_consume_batched(struct ptr_ring *r, + void **array, int n) +{ + int ret; + + spin_lock(&r->consumer_lock); + ret = __ptr_ring_consume_batched(r, array, n); + spin_unlock(&r->consumer_lock); + + return ret; +} + +static inline int ptr_ring_consume_batched_irq(struct ptr_ring *r, + void **array, int n) +{ + int ret; + + spin_lock_irq(&r->consumer_lock); + ret = __ptr_ring_consume_batched(r, array, n); + spin_unlock_irq(&r->consumer_lock); + + return ret; +} + +static inline int ptr_ring_consume_batched_any(struct ptr_ring *r, + void **array, int n) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&r->consumer_lock, flags); + ret = __ptr_ring_consume_batched(r, array, n); + spin_unlock_irqrestore(&r->consumer_lock, flags); + + return ret; +} + +static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r, + void **array, int n) +{ + int ret; + + spin_lock_bh(&r->consumer_lock); + ret = __ptr_ring_consume_batched(r, array, n); + spin_unlock_bh(&r->consumer_lock); + + return ret; +} + /* Cast to structure type and call a function without discarding from FIFO. * Function must return a value. * Callers must take consumer_lock. @@ -335,20 +441,88 @@ static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp) return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp); } +static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) +{ + r->size = size; + r->batch = SMP_CACHE_BYTES * 2 / sizeof(*(r->queue)); + /* We need to set batch at least to 1 to make logic + * in __ptr_ring_discard_one work correctly. + * Batching too much (because ring is small) would cause a lot of + * burstiness. Needs tuning, for now disable batching. + */ + if (r->batch > r->size / 2 || !r->batch) + r->batch = 1; +} + static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) { r->queue = __ptr_ring_init_queue_alloc(size, gfp); if (!r->queue) return -ENOMEM; - r->size = size; - r->producer = r->consumer = 0; + __ptr_ring_set_size(r, size); + r->producer = r->consumer_head = r->consumer_tail = 0; spin_lock_init(&r->producer_lock); spin_lock_init(&r->consumer_lock); return 0; } +/* + * Return entries into ring. Destroy entries that don't fit. + * + * Note: this is expected to be a rare slow path operation. + * + * Note: producer lock is nested within consumer lock, so if you + * resize you must make sure all uses nest correctly. + * In particular if you consume ring in interrupt or BH context, you must + * disable interrupts/BH when doing so. + */ +static inline void ptr_ring_unconsume(struct ptr_ring *r, void **batch, int n, + void (*destroy)(void *)) +{ + unsigned long flags; + int head; + + spin_lock_irqsave(&r->consumer_lock, flags); + spin_lock(&r->producer_lock); + + if (!r->size) + goto done; + + /* + * Clean out buffered entries (for simplicity). This way following code + * can test entries for NULL and if not assume they are valid. + */ + head = r->consumer_head - 1; + while (likely(head >= r->consumer_tail)) + r->queue[head--] = NULL; + r->consumer_tail = r->consumer_head; + + /* + * Go over entries in batch, start moving head back and copy entries. + * Stop when we run into previously unconsumed entries. + */ + while (n) { + head = r->consumer_head - 1; + if (head < 0) + head = r->size - 1; + if (r->queue[head]) { + /* This batch entry will have to be destroyed. */ + goto done; + } + r->queue[head] = batch[--n]; + r->consumer_tail = r->consumer_head = head; + } + +done: + /* Destroy all entries left in the batch. */ + while (n) + destroy(batch[--n]); + spin_unlock(&r->producer_lock); + spin_unlock_irqrestore(&r->consumer_lock, flags); +} + static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue, int size, gfp_t gfp, void (*destroy)(void *)) @@ -357,21 +531,28 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue, void **old; void *ptr; - while ((ptr = ptr_ring_consume(r))) + while ((ptr = __ptr_ring_consume(r))) if (producer < size) queue[producer++] = ptr; else if (destroy) destroy(ptr); - r->size = size; + __ptr_ring_set_size(r, size); r->producer = producer; - r->consumer = 0; + r->consumer_head = 0; + r->consumer_tail = 0; old = r->queue; r->queue = queue; return old; } +/* + * Note: producer lock is nested within consumer lock, so if you + * resize you must make sure all uses nest correctly. + * In particular if you consume ring in interrupt or BH context, you must + * disable interrupts/BH when doing so. + */ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, void (*destroy)(void *)) { @@ -382,17 +563,25 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, if (!queue) return -ENOMEM; - spin_lock_irqsave(&(r)->producer_lock, flags); + spin_lock_irqsave(&(r)->consumer_lock, flags); + spin_lock(&(r)->producer_lock); old = __ptr_ring_swap_queue(r, queue, size, gfp, destroy); - spin_unlock_irqrestore(&(r)->producer_lock, flags); + spin_unlock(&(r)->producer_lock); + spin_unlock_irqrestore(&(r)->consumer_lock, flags); kfree(old); return 0; } +/* + * Note: producer lock is nested within consumer lock, so if you + * resize you must make sure all uses nest correctly. + * In particular if you consume ring in interrupt or BH context, you must + * disable interrupts/BH when doing so. + */ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings, int size, gfp_t gfp, void (*destroy)(void *)) @@ -412,10 +601,12 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings, } for (i = 0; i < nrings; ++i) { - spin_lock_irqsave(&(rings[i])->producer_lock, flags); + spin_lock_irqsave(&(rings[i])->consumer_lock, flags); + spin_lock(&(rings[i])->producer_lock); queues[i] = __ptr_ring_swap_queue(rings[i], queues[i], size, gfp, destroy); - spin_unlock_irqrestore(&(rings[i])->producer_lock, flags); + spin_unlock(&(rings[i])->producer_lock); + spin_unlock_irqrestore(&(rings[i])->consumer_lock, flags); } for (i = 0; i < nrings; ++i) diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index e0e539321ab9..0e5fcc11b1b8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -3,6 +3,7 @@ #include <linux/compiler.h> /* For unlikely. */ #include <linux/sched.h> /* For struct task_struct. */ +#include <linux/sched/signal.h> /* For send_sig(), same_thread_group(), etc. */ #include <linux/err.h> /* for IS_ERR_VALUE */ #include <linux/bug.h> /* For BUG_ON. */ #include <linux/pid_namespace.h> /* For task_active_pid_ns. */ @@ -53,7 +54,8 @@ extern int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, - struct task_struct *new_parent); + struct task_struct *new_parent, + const struct cred *ptracer_cred); extern void __ptrace_unlink(struct task_struct *child); extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 @@ -205,7 +207,7 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) if (unlikely(ptrace) && current->ptrace) { child->ptrace = current->ptrace; - __ptrace_link(child, current->parent); + __ptrace_link(child, current->parent, current->ptracer_cred); if (child->ptrace & PT_SEIZED) task_set_jobctl_pending(child, JOBCTL_TRAP_STOP); @@ -214,6 +216,8 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) set_tsk_thread_flag(child, TIF_SIGPENDING); } + else + child->ptracer_cred = NULL; } /** @@ -387,10 +391,6 @@ static inline void user_single_step_siginfo(struct task_struct *tsk, #define current_pt_regs() task_pt_regs(current) #endif -#ifndef ptrace_signal_deliver -#define ptrace_signal_deliver() ((void)0) -#endif - /* * unlike current_pt_regs(), this one is equal to task_pt_regs(current) * on *all* architectures; the only reason to have a per-arch definition diff --git a/include/linux/purgatory.h b/include/linux/purgatory.h new file mode 100644 index 000000000000..d60d4e278609 --- /dev/null +++ b/include/linux/purgatory.h @@ -0,0 +1,23 @@ +#ifndef _LINUX_PURGATORY_H +#define _LINUX_PURGATORY_H + +#include <linux/types.h> +#include <crypto/sha.h> +#include <uapi/linux/kexec.h> + +struct kexec_sha_region { + unsigned long start; + unsigned long len; +}; + +/* + * These forward declarations serve two purposes: + * + * 1) Make sparse happy when checking arch/purgatory + * 2) Document that these are required to be global so the symbol + * lookup in kexec works + */ +extern struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX]; +extern u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE]; + +#endif diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 2c6c5114c089..08fad7c6a471 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -287,8 +287,6 @@ struct pwm_ops { * @pwms: array of PWM devices allocated by the framework * @of_xlate: request a PWM device given a device tree PWM specifier * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier - * @can_sleep: must be true if the .config(), .enable() or .disable() - * operations may sleep */ struct pwm_chip { struct device *dev; @@ -302,7 +300,6 @@ struct pwm_chip { struct pwm_device * (*of_xlate)(struct pwm_chip *pc, const struct of_phandle_args *args); unsigned int of_pwm_n_cells; - bool can_sleep; }; /** @@ -451,8 +448,6 @@ struct pwm_device *devm_pwm_get(struct device *dev, const char *con_id); struct pwm_device *devm_of_pwm_get(struct device *dev, struct device_node *np, const char *con_id); void devm_pwm_put(struct device *dev, struct pwm_device *pwm); - -bool pwm_can_sleep(struct pwm_device *pwm); #else static inline struct pwm_device *pwm_request(int pwm_id, const char *label) { @@ -566,11 +561,6 @@ static inline struct pwm_device *devm_of_pwm_get(struct device *dev, static inline void devm_pwm_put(struct device *dev, struct pwm_device *pwm) { } - -static inline bool pwm_can_sleep(struct pwm_device *pwm) -{ - return false; -} #endif static inline void pwm_apply_args(struct pwm_device *pwm) @@ -613,18 +603,25 @@ struct pwm_lookup { const char *con_id; unsigned int period; enum pwm_polarity polarity; + const char *module; /* optional, may be NULL */ }; -#define PWM_LOOKUP(_provider, _index, _dev_id, _con_id, _period, _polarity) \ - { \ - .provider = _provider, \ - .index = _index, \ - .dev_id = _dev_id, \ - .con_id = _con_id, \ - .period = _period, \ - .polarity = _polarity \ +#define PWM_LOOKUP_WITH_MODULE(_provider, _index, _dev_id, _con_id, \ + _period, _polarity, _module) \ + { \ + .provider = _provider, \ + .index = _index, \ + .dev_id = _dev_id, \ + .con_id = _con_id, \ + .period = _period, \ + .polarity = _polarity, \ + .module = _module, \ } +#define PWM_LOOKUP(_provider, _index, _dev_id, _con_id, _period, _polarity) \ + PWM_LOOKUP_WITH_MODULE(_provider, _index, _dev_id, _con_id, _period, \ + _polarity, NULL) + #if IS_ENABLED(CONFIG_PWM) void pwm_add_table(struct pwm_lookup *table, size_t num); void pwm_remove_table(struct pwm_lookup *table, size_t num); diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 2d6f0c39ed68..8461b18e4608 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -90,9 +90,9 @@ #define SSSR_RFL_MASK (0xf << 12) /* Receive FIFO Level mask */ #define SSCR1_TFT (0x000003c0) /* Transmit FIFO Threshold (mask) */ -#define SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..16] */ +#define SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..16] */ #define SSCR1_RFT (0x00003c00) /* Receive FIFO Threshold (mask) */ -#define SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..16] */ +#define SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..16] */ #define RX_THRESH_CE4100_DFLT 2 #define TX_THRESH_CE4100_DFLT 2 @@ -106,9 +106,9 @@ #define CE4100_SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..4] */ /* QUARK_X1000 SSCR0 bit definition */ -#define QUARK_X1000_SSCR0_DSS (0x1F) /* Data Size Select (mask) */ -#define QUARK_X1000_SSCR0_DataSize(x) ((x) - 1) /* Data Size Select [4..32] */ -#define QUARK_X1000_SSCR0_FRF (0x3 << 5) /* FRame Format (mask) */ +#define QUARK_X1000_SSCR0_DSS (0x1F << 0) /* Data Size Select (mask) */ +#define QUARK_X1000_SSCR0_DataSize(x) ((x) - 1) /* Data Size Select [4..32] */ +#define QUARK_X1000_SSCR0_FRF (0x3 << 5) /* FRame Format (mask) */ #define QUARK_X1000_SSCR0_Motorola (0x0 << 5) /* Motorola's Serial Peripheral Interface (SPI) */ #define RX_THRESH_QUARK_X1000_DFLT 1 @@ -121,8 +121,8 @@ #define QUARK_X1000_SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..32] */ #define QUARK_X1000_SSCR1_RFT (0x1F << 11) /* Receive FIFO Threshold (mask) */ #define QUARK_X1000_SSCR1_RxTresh(x) (((x) - 1) << 11) /* level [1..32] */ -#define QUARK_X1000_SSCR1_STRF (1 << 17) /* Select FIFO or EFWR */ -#define QUARK_X1000_SSCR1_EFWR (1 << 16) /* Enable FIFO Write/Read */ +#define QUARK_X1000_SSCR1_STRF (1 << 17) /* Select FIFO or EFWR */ +#define QUARK_X1000_SSCR1_EFWR (1 << 16) /* Enable FIFO Write/Read */ /* extra bits in PXA255, PXA26x and PXA27x SSP ports */ #define SSCR0_TISSP (1 << 4) /* TI Sync Serial Protocol */ @@ -196,6 +196,7 @@ enum pxa_ssp_type { LPSS_BSW_SSP, LPSS_SPT_SSP, LPSS_BXT_SSP, + LPSS_CNL_SSP, }; struct ssp_device { diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index cc32ab852fbc..e5380471c2cd 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -13,9 +13,9 @@ #ifndef __QCOM_SCM_H #define __QCOM_SCM_H -extern int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus); -extern int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus); - +#define QCOM_SCM_VERSION(major, minor) (((major) << 16) | ((minor) & 0xFF)) +#define QCOM_SCM_CPU_PWR_DOWN_L2_ON 0x0 +#define QCOM_SCM_CPU_PWR_DOWN_L2_OFF 0x1 #define QCOM_SCM_HDCP_MAX_REQ_CNT 5 struct qcom_scm_hdcp_req { @@ -23,27 +23,55 @@ struct qcom_scm_hdcp_req { u32 val; }; +#if IS_ENABLED(CONFIG_QCOM_SCM) +extern int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus); +extern int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus); extern bool qcom_scm_is_available(void); - extern bool qcom_scm_hdcp_available(void); extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, - u32 *resp); - + u32 *resp); extern bool qcom_scm_pas_supported(u32 peripheral); extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, - size_t size); + size_t size); extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, - phys_addr_t size); + phys_addr_t size); extern int qcom_scm_pas_auth_and_reset(u32 peripheral); extern int qcom_scm_pas_shutdown(u32 peripheral); - -#define QCOM_SCM_CPU_PWR_DOWN_L2_ON 0x0 -#define QCOM_SCM_CPU_PWR_DOWN_L2_OFF 0x1 - extern void qcom_scm_cpu_power_down(u32 flags); - -#define QCOM_SCM_VERSION(major, minor) (((major) << 16) | ((minor) & 0xFF)) - extern u32 qcom_scm_get_version(void); - +extern int qcom_scm_set_remote_state(u32 state, u32 id); +extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); +extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); +extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); +#else +static inline +int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus) +{ + return -ENODEV; +} +static inline +int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus) +{ + return -ENODEV; +} +static inline bool qcom_scm_is_available(void) { return false; } +static inline bool qcom_scm_hdcp_available(void) { return false; } +static inline int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, + u32 *resp) { return -ENODEV; } +static inline bool qcom_scm_pas_supported(u32 peripheral) { return false; } +static inline int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, + size_t size) { return -ENODEV; } +static inline int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, + phys_addr_t size) { return -ENODEV; } +static inline int +qcom_scm_pas_auth_and_reset(u32 peripheral) { return -ENODEV; } +static inline int qcom_scm_pas_shutdown(u32 peripheral) { return -ENODEV; } +static inline void qcom_scm_cpu_power_down(u32 flags) {} +static inline u32 qcom_scm_get_version(void) { return 0; } +static inline u32 +qcom_scm_set_remote_state(u32 state,u32 id) { return -ENODEV; } +static inline int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) { return -ENODEV; } +static inline int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size) { return -ENODEV; } +static inline int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare) { return -ENODEV; } +#endif #endif diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 734deb094618..39e2a2ac2471 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -1,10 +1,35 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2015-2016 QLogic Corporation * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ + #ifndef _COMMON_HSI_H #define _COMMON_HSI_H #include <linux/types.h> @@ -13,6 +38,8 @@ #include <linux/slab.h> /* dma_addr_t manip */ +#define PTR_LO(x) ((u32)(((uintptr_t)(x)) & 0xffffffff)) +#define PTR_HI(x) ((u32)((((uintptr_t)(x)) >> 16) >> 16)) #define DMA_LO_LE(x) cpu_to_le32(lower_32_bits(x)) #define DMA_HI_LE(x) cpu_to_le32(upper_32_bits(x)) #define DMA_REGPAIR_LE(x, val) do { \ @@ -37,6 +64,7 @@ #define COMMON_QUEUE_ENTRY_MAX_BYTE_SIZE 64 #define ISCSI_CDU_TASK_SEG_TYPE 0 +#define FCOE_CDU_TASK_SEG_TYPE 0 #define RDMA_CDU_TASK_SEG_TYPE 1 #define FW_ASSERT_GENERAL_ATTN_IDX 32 @@ -70,12 +98,12 @@ #define CORE_SPQE_PAGE_SIZE_BYTES 4096 -#define MAX_NUM_LL2_RX_QUEUES 32 -#define MAX_NUM_LL2_TX_STATS_COUNTERS 32 +#define MAX_NUM_LL2_RX_QUEUES 48 +#define MAX_NUM_LL2_TX_STATS_COUNTERS 48 #define FW_MAJOR_VERSION 8 -#define FW_MINOR_VERSION 10 -#define FW_REVISION_VERSION 10 +#define FW_MINOR_VERSION 20 +#define FW_REVISION_VERSION 0 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -155,12 +183,23 @@ #define CDU_VF_FL_SEG_TYPE_OFFSET_REG_TYPE_SHIFT (12) #define CDU_VF_FL_SEG_TYPE_OFFSET_REG_OFFSET_MASK (0xfff) + +#define CDU_CONTEXT_VALIDATION_CFG_ENABLE_SHIFT (0) +#define CDU_CONTEXT_VALIDATION_CFG_VALIDATION_TYPE_SHIFT (1) +#define CDU_CONTEXT_VALIDATION_CFG_USE_TYPE (2) +#define CDU_CONTEXT_VALIDATION_CFG_USE_REGION (3) +#define CDU_CONTEXT_VALIDATION_CFG_USE_CID (4) +#define CDU_CONTEXT_VALIDATION_CFG_USE_ACTIVE (5) + /*****************/ /* DQ CONSTANTS */ /*****************/ /* DEMS */ #define DQ_DEMS_LEGACY 0 +#define DQ_DEMS_TOE_MORE_TO_SEND 3 +#define DQ_DEMS_TOE_LOCAL_ADV_WND 4 +#define DQ_DEMS_ROCE_CQ_CONS 7 /* XCM agg val selection */ #define DQ_XCM_AGG_VAL_SEL_WORD2 0 @@ -180,11 +219,17 @@ #define DQ_XCM_ETH_TX_BD_CONS_CMD DQ_XCM_AGG_VAL_SEL_WORD3 #define DQ_XCM_ETH_TX_BD_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 #define DQ_XCM_ETH_GO_TO_BD_CONS_CMD DQ_XCM_AGG_VAL_SEL_WORD5 +#define DQ_XCM_FCOE_SQ_CONS_CMD DQ_XCM_AGG_VAL_SEL_WORD3 +#define DQ_XCM_FCOE_SQ_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_FCOE_X_FERQ_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD5 #define DQ_XCM_ISCSI_SQ_CONS_CMD DQ_XCM_AGG_VAL_SEL_WORD3 #define DQ_XCM_ISCSI_SQ_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 #define DQ_XCM_ISCSI_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3 #define DQ_XCM_ISCSI_EXP_STAT_SN_CMD DQ_XCM_AGG_VAL_SEL_REG6 #define DQ_XCM_ROCE_SQ_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_TOE_TX_BD_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_TOE_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3 +#define DQ_XCM_TOE_LOCAL_ADV_WND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG4 /* UCM agg val selection (HW) */ #define DQ_UCM_AGG_VAL_SEL_WORD0 0 @@ -236,9 +281,12 @@ #define DQ_XCM_ETH_TERMINATE_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF19) #define DQ_XCM_ETH_SLOW_PATH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF22) #define DQ_XCM_ETH_TPH_EN_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF23) +#define DQ_XCM_FCOE_SLOW_PATH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF22) #define DQ_XCM_ISCSI_DQ_FLUSH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF19) #define DQ_XCM_ISCSI_SLOW_PATH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF22) #define DQ_XCM_ISCSI_PROC_ONLY_CLEANUP_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF23) +#define DQ_XCM_TOE_DQ_FLUSH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF19) +#define DQ_XCM_TOE_SLOW_PATH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF22) /* UCM agg counter flag selection (HW) */ #define DQ_UCM_AGG_FLG_SHIFT_CF0 0 @@ -255,6 +303,9 @@ #define DQ_UCM_ETH_PMD_RX_ARM_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5) #define DQ_UCM_ROCE_CQ_ARM_SE_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF4) #define DQ_UCM_ROCE_CQ_ARM_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5) +#define DQ_UCM_TOE_TIMER_STOP_ALL_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF3) +#define DQ_UCM_TOE_SLOW_PATH_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF4) +#define DQ_UCM_TOE_DQ_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5) /* TCM agg counter flag selection (HW) */ #define DQ_TCM_AGG_FLG_SHIFT_CF0 0 @@ -266,8 +317,14 @@ #define DQ_TCM_AGG_FLG_SHIFT_CF6 6 #define DQ_TCM_AGG_FLG_SHIFT_CF7 7 /* TCM agg counter flag selection (FW) */ +#define DQ_TCM_FCOE_FLUSH_Q0_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1) +#define DQ_TCM_FCOE_DUMMY_TIMER_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF2) +#define DQ_TCM_FCOE_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3) #define DQ_TCM_ISCSI_FLUSH_Q0_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1) #define DQ_TCM_ISCSI_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3) +#define DQ_TCM_TOE_FLUSH_Q0_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1) +#define DQ_TCM_TOE_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3) +#define DQ_TCM_IWARP_POST_RQ_CF_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1) /* PWM address mapping */ #define DQ_PWM_OFFSET_DPM_BASE 0x0 @@ -410,7 +467,6 @@ #define PXP_BAR_DQ 1 /* PTT and GTT */ -#define PXP_NUM_PF_WINDOWS 12 #define PXP_PER_PF_ENTRY_SIZE 8 #define PXP_NUM_GLOBAL_WINDOWS 243 #define PXP_GLOBAL_ENTRY_SIZE 4 @@ -435,6 +491,7 @@ #define PXP_PF_ME_OPAQUE_ADDR 0x1f8 #define PXP_PF_ME_CONCRETE_ADDR 0x1fc +#define PXP_NUM_PF_WINDOWS 12 #define PXP_EXTERNAL_BAR_PF_WINDOW_START 0x1000 #define PXP_EXTERNAL_BAR_PF_WINDOW_NUM PXP_NUM_PF_WINDOWS #define PXP_EXTERNAL_BAR_PF_WINDOW_SINGLE_SIZE 0x1000 @@ -571,16 +628,21 @@ /*****************/ /* PRM CONSTANTS */ /*****************/ -#define PRM_DMA_PAD_BYTES_NUM 2 -/******************/ -/* SDMs CONSTANTS */ -/******************/ -#define SDM_OP_GEN_TRIG_NONE 0 -#define SDM_OP_GEN_TRIG_WAKE_THREAD 1 -#define SDM_OP_GEN_TRIG_AGG_INT 2 -#define SDM_OP_GEN_TRIG_LOADER 4 -#define SDM_OP_GEN_TRIG_INDICATE_ERROR 6 -#define SDM_OP_GEN_TRIG_RELEASE_THREAD 7 +#define PRM_DMA_PAD_BYTES_NUM 2 +/*****************/ +/* SDMs CONSTANTS */ +/*****************/ + +#define SDM_OP_GEN_TRIG_NONE 0 +#define SDM_OP_GEN_TRIG_WAKE_THREAD 1 +#define SDM_OP_GEN_TRIG_AGG_INT 2 +#define SDM_OP_GEN_TRIG_LOADER 4 +#define SDM_OP_GEN_TRIG_INDICATE_ERROR 6 +#define SDM_OP_GEN_TRIG_INC_ORDER_CNT 9 + +/********************/ +/* Completion types */ +/********************/ #define SDM_COMP_TYPE_NONE 0 #define SDM_COMP_TYPE_WAKE_THREAD 1 @@ -591,10 +653,11 @@ #define SDM_COMP_TYPE_INDICATE_ERROR 6 #define SDM_COMP_TYPE_RELEASE_THREAD 7 #define SDM_COMP_TYPE_RAM 8 +#define SDM_COMP_TYPE_INC_ORDER_CNT 9 -/******************/ -/* PBF CONSTANTS */ -/******************/ +/*****************/ +/* PBF Constants */ +/*****************/ /* Number of PBF command queue lines. Each line is 32B. */ #define PBF_MAX_CMD_LINES 3328 @@ -656,6 +719,16 @@ struct iscsi_eqe_data { #define ISCSI_EQE_DATA_RESERVED0_SHIFT 7 }; +struct rdma_eqe_destroy_qp { + __le32 cid; + u8 reserved[4]; +}; + +union rdma_eqe_data { + struct regpair async_handle; + struct rdma_eqe_destroy_qp rdma_destroy_qp_data; +}; + struct malicious_vf_eqe_data { u8 vf_id; u8 err_id; @@ -672,9 +745,9 @@ union event_ring_data { u8 bytes[8]; struct vf_pf_channel_eqe_data vf_pf_channel; struct iscsi_eqe_data iscsi_info; + union rdma_eqe_data rdma_data; struct malicious_vf_eqe_data malicious_vf; struct initial_cleanup_eqe_data vf_init_cleanup; - struct regpair roce_handle; }; /* Event Ring Entry */ @@ -703,11 +776,11 @@ enum mf_mode { /* Per-protocol connection types */ enum protocol_type { PROTOCOLID_ISCSI, - PROTOCOLID_RESERVED2, + PROTOCOLID_FCOE, PROTOCOLID_ROCE, PROTOCOLID_CORE, PROTOCOLID_ETH, - PROTOCOLID_RESERVED4, + PROTOCOLID_IWARP, PROTOCOLID_RESERVED5, PROTOCOLID_PREROCE, PROTOCOLID_COMMON, @@ -804,7 +877,7 @@ enum db_dest { /* Enum of doorbell DPM types */ enum db_dpm_type { DPM_LEGACY, - DPM_ROCE, + DPM_RDMA, DPM_L2_INLINE, DPM_L2_BD, MAX_DB_DPM_TYPE @@ -827,8 +900,8 @@ struct db_l2_dpm_data { #define DB_L2_DPM_DATA_RESERVED0_SHIFT 27 #define DB_L2_DPM_DATA_SGE_NUM_MASK 0x7 #define DB_L2_DPM_DATA_SGE_NUM_SHIFT 28 -#define DB_L2_DPM_DATA_RESERVED1_MASK 0x1 -#define DB_L2_DPM_DATA_RESERVED1_SHIFT 31 +#define DB_L2_DPM_DATA_GFS_SRC_EN_MASK 0x1 +#define DB_L2_DPM_DATA_GFS_SRC_EN_SHIFT 31 }; /* Structure for SGE in a DPM doorbell of type DPM_L2_BD */ @@ -874,31 +947,33 @@ struct db_pwm_addr { }; /* Parameters to RoCE firmware, passed in EDPM doorbell */ -struct db_roce_dpm_params { +struct db_rdma_dpm_params { __le32 params; -#define DB_ROCE_DPM_PARAMS_SIZE_MASK 0x3F -#define DB_ROCE_DPM_PARAMS_SIZE_SHIFT 0 -#define DB_ROCE_DPM_PARAMS_DPM_TYPE_MASK 0x3 -#define DB_ROCE_DPM_PARAMS_DPM_TYPE_SHIFT 6 -#define DB_ROCE_DPM_PARAMS_OPCODE_MASK 0xFF -#define DB_ROCE_DPM_PARAMS_OPCODE_SHIFT 8 -#define DB_ROCE_DPM_PARAMS_WQE_SIZE_MASK 0x7FF -#define DB_ROCE_DPM_PARAMS_WQE_SIZE_SHIFT 16 -#define DB_ROCE_DPM_PARAMS_RESERVED0_MASK 0x1 -#define DB_ROCE_DPM_PARAMS_RESERVED0_SHIFT 27 -#define DB_ROCE_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 -#define DB_ROCE_DPM_PARAMS_COMPLETION_FLG_SHIFT 28 -#define DB_ROCE_DPM_PARAMS_S_FLG_MASK 0x1 -#define DB_ROCE_DPM_PARAMS_S_FLG_SHIFT 29 -#define DB_ROCE_DPM_PARAMS_RESERVED1_MASK 0x3 -#define DB_ROCE_DPM_PARAMS_RESERVED1_SHIFT 30 +#define DB_RDMA_DPM_PARAMS_SIZE_MASK 0x3F +#define DB_RDMA_DPM_PARAMS_SIZE_SHIFT 0 +#define DB_RDMA_DPM_PARAMS_DPM_TYPE_MASK 0x3 +#define DB_RDMA_DPM_PARAMS_DPM_TYPE_SHIFT 6 +#define DB_RDMA_DPM_PARAMS_OPCODE_MASK 0xFF +#define DB_RDMA_DPM_PARAMS_OPCODE_SHIFT 8 +#define DB_RDMA_DPM_PARAMS_WQE_SIZE_MASK 0x7FF +#define DB_RDMA_DPM_PARAMS_WQE_SIZE_SHIFT 16 +#define DB_RDMA_DPM_PARAMS_RESERVED0_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_RESERVED0_SHIFT 27 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 28 +#define DB_RDMA_DPM_PARAMS_S_FLG_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_S_FLG_SHIFT 29 +#define DB_RDMA_DPM_PARAMS_RESERVED1_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_RESERVED1_SHIFT 30 +#define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_SHIFT 31 }; /* Structure for doorbell data, in ROCE DPM mode, for 1st db in a DPM burst */ -struct db_roce_dpm_data { +struct db_rdma_dpm_data { __le16 icid; __le16 prod_val; - struct db_roce_dpm_params params; + struct db_rdma_dpm_params params; }; /* Igu interrupt command */ @@ -969,6 +1044,42 @@ struct parsing_and_err_flags { #define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMERROR_SHIFT 15 }; +struct parsing_err_flags { + __le16 flags; +#define PARSING_ERR_FLAGS_MAC_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_MAC_ERROR_SHIFT 0 +#define PARSING_ERR_FLAGS_TRUNC_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_TRUNC_ERROR_SHIFT 1 +#define PARSING_ERR_FLAGS_PKT_TOO_SMALL_MASK 0x1 +#define PARSING_ERR_FLAGS_PKT_TOO_SMALL_SHIFT 2 +#define PARSING_ERR_FLAGS_ANY_HDR_MISSING_TAG_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_MISSING_TAG_SHIFT 3 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_VER_MISMTCH_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_VER_MISMTCH_SHIFT 4 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_V4_HDR_LEN_TOO_SMALL_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_V4_HDR_LEN_TOO_SMALL_SHIFT 5 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_BAD_TOTAL_LEN_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_IP_BAD_TOTAL_LEN_SHIFT 6 +#define PARSING_ERR_FLAGS_IP_V4_CHKSM_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_IP_V4_CHKSM_ERROR_SHIFT 7 +#define PARSING_ERR_FLAGS_ANY_HDR_L4_IP_LEN_MISMTCH_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_L4_IP_LEN_MISMTCH_SHIFT 8 +#define PARSING_ERR_FLAGS_ZERO_UDP_IP_V6_CHKSM_MASK 0x1 +#define PARSING_ERR_FLAGS_ZERO_UDP_IP_V6_CHKSM_SHIFT 9 +#define PARSING_ERR_FLAGS_INNER_L4_CHKSM_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_INNER_L4_CHKSM_ERROR_SHIFT 10 +#define PARSING_ERR_FLAGS_ANY_HDR_ZERO_TTL_OR_HOP_LIM_MASK 0x1 +#define PARSING_ERR_FLAGS_ANY_HDR_ZERO_TTL_OR_HOP_LIM_SHIFT 11 +#define PARSING_ERR_FLAGS_NON_8021Q_TAG_EXISTS_IN_BOTH_HDRS_MASK 0x1 +#define PARSING_ERR_FLAGS_NON_8021Q_TAG_EXISTS_IN_BOTH_HDRS_SHIFT 12 +#define PARSING_ERR_FLAGS_GENEVE_OPTION_OVERSIZED_MASK 0x1 +#define PARSING_ERR_FLAGS_GENEVE_OPTION_OVERSIZED_SHIFT 13 +#define PARSING_ERR_FLAGS_TUNNEL_IP_V4_CHKSM_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_TUNNEL_IP_V4_CHKSM_ERROR_SHIFT 14 +#define PARSING_ERR_FLAGS_TUNNEL_L4_CHKSM_ERROR_MASK 0x1 +#define PARSING_ERR_FLAGS_TUNNEL_L4_CHKSM_ERROR_SHIFT 15 +}; + struct pb_context { __le32 crc[4]; }; @@ -1231,39 +1342,56 @@ struct tdif_task_context { struct timers_context { __le32 logical_client_0; -#define TIMERS_CONTEXT_EXPIRATIONTIMELC0_MASK 0xFFFFFFF -#define TIMERS_CONTEXT_EXPIRATIONTIMELC0_SHIFT 0 -#define TIMERS_CONTEXT_VALIDLC0_MASK 0x1 -#define TIMERS_CONTEXT_VALIDLC0_SHIFT 28 -#define TIMERS_CONTEXT_ACTIVELC0_MASK 0x1 -#define TIMERS_CONTEXT_ACTIVELC0_SHIFT 29 -#define TIMERS_CONTEXT_RESERVED0_MASK 0x3 -#define TIMERS_CONTEXT_RESERVED0_SHIFT 30 +#define TIMERS_CONTEXT_EXPIRATIONTIMELC0_MASK 0x7FFFFFF +#define TIMERS_CONTEXT_EXPIRATIONTIMELC0_SHIFT 0 +#define TIMERS_CONTEXT_RESERVED0_MASK 0x1 +#define TIMERS_CONTEXT_RESERVED0_SHIFT 27 +#define TIMERS_CONTEXT_VALIDLC0_MASK 0x1 +#define TIMERS_CONTEXT_VALIDLC0_SHIFT 28 +#define TIMERS_CONTEXT_ACTIVELC0_MASK 0x1 +#define TIMERS_CONTEXT_ACTIVELC0_SHIFT 29 +#define TIMERS_CONTEXT_RESERVED1_MASK 0x3 +#define TIMERS_CONTEXT_RESERVED1_SHIFT 30 __le32 logical_client_1; -#define TIMERS_CONTEXT_EXPIRATIONTIMELC1_MASK 0xFFFFFFF -#define TIMERS_CONTEXT_EXPIRATIONTIMELC1_SHIFT 0 -#define TIMERS_CONTEXT_VALIDLC1_MASK 0x1 -#define TIMERS_CONTEXT_VALIDLC1_SHIFT 28 -#define TIMERS_CONTEXT_ACTIVELC1_MASK 0x1 -#define TIMERS_CONTEXT_ACTIVELC1_SHIFT 29 -#define TIMERS_CONTEXT_RESERVED1_MASK 0x3 -#define TIMERS_CONTEXT_RESERVED1_SHIFT 30 +#define TIMERS_CONTEXT_EXPIRATIONTIMELC1_MASK 0x7FFFFFF +#define TIMERS_CONTEXT_EXPIRATIONTIMELC1_SHIFT 0 +#define TIMERS_CONTEXT_RESERVED2_MASK 0x1 +#define TIMERS_CONTEXT_RESERVED2_SHIFT 27 +#define TIMERS_CONTEXT_VALIDLC1_MASK 0x1 +#define TIMERS_CONTEXT_VALIDLC1_SHIFT 28 +#define TIMERS_CONTEXT_ACTIVELC1_MASK 0x1 +#define TIMERS_CONTEXT_ACTIVELC1_SHIFT 29 +#define TIMERS_CONTEXT_RESERVED3_MASK 0x3 +#define TIMERS_CONTEXT_RESERVED3_SHIFT 30 __le32 logical_client_2; -#define TIMERS_CONTEXT_EXPIRATIONTIMELC2_MASK 0xFFFFFFF -#define TIMERS_CONTEXT_EXPIRATIONTIMELC2_SHIFT 0 -#define TIMERS_CONTEXT_VALIDLC2_MASK 0x1 -#define TIMERS_CONTEXT_VALIDLC2_SHIFT 28 -#define TIMERS_CONTEXT_ACTIVELC2_MASK 0x1 -#define TIMERS_CONTEXT_ACTIVELC2_SHIFT 29 -#define TIMERS_CONTEXT_RESERVED2_MASK 0x3 -#define TIMERS_CONTEXT_RESERVED2_SHIFT 30 +#define TIMERS_CONTEXT_EXPIRATIONTIMELC2_MASK 0x7FFFFFF +#define TIMERS_CONTEXT_EXPIRATIONTIMELC2_SHIFT 0 +#define TIMERS_CONTEXT_RESERVED4_MASK 0x1 +#define TIMERS_CONTEXT_RESERVED4_SHIFT 27 +#define TIMERS_CONTEXT_VALIDLC2_MASK 0x1 +#define TIMERS_CONTEXT_VALIDLC2_SHIFT 28 +#define TIMERS_CONTEXT_ACTIVELC2_MASK 0x1 +#define TIMERS_CONTEXT_ACTIVELC2_SHIFT 29 +#define TIMERS_CONTEXT_RESERVED5_MASK 0x3 +#define TIMERS_CONTEXT_RESERVED5_SHIFT 30 __le32 host_expiration_fields; -#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALUE_MASK 0xFFFFFFF -#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALUE_SHIFT 0 -#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALID_MASK 0x1 -#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALID_SHIFT 28 -#define TIMERS_CONTEXT_RESERVED3_MASK 0x7 -#define TIMERS_CONTEXT_RESERVED3_SHIFT 29 +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALUE_MASK 0x7FFFFFF +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALUE_SHIFT 0 +#define TIMERS_CONTEXT_RESERVED6_MASK 0x1 +#define TIMERS_CONTEXT_RESERVED6_SHIFT 27 +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALID_MASK 0x1 +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALID_SHIFT 28 +#define TIMERS_CONTEXT_RESERVED7_MASK 0x7 +#define TIMERS_CONTEXT_RESERVED7_SHIFT 29 }; + +enum tunnel_next_protocol { + e_unknown = 0, + e_l2 = 1, + e_ipv4 = 2, + e_ipv6 = 3, + MAX_TUNNEL_NEXT_PROTOCOL +}; + #endif /* __COMMON_HSI__ */ #endif diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index 1aa0727c4136..cb06e6e368e1 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -1,9 +1,33 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef __ETH_COMMON__ @@ -25,6 +49,9 @@ #define ETH_RX_CQE_PAGE_SIZE_BYTES 4096 #define ETH_RX_NUM_NEXT_PAGE_BDS 2 +#define ETH_MAX_TUNN_LSO_INNER_IPV4_OFFSET 253 +#define ETH_MAX_TUNN_LSO_INNER_IPV6_OFFSET 251 + #define ETH_TX_MIN_BDS_PER_NON_LSO_PKT 1 #define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET 18 #define ETH_TX_MAX_BDS_PER_LSO_PACKET 255 @@ -48,7 +75,8 @@ (ETH_NUM_STATISTIC_COUNTERS - 3 * MAX_NUM_VFS / 4) /* Maximum number of buffers, used for RX packet placement */ -#define ETH_RX_MAX_BUFF_PER_PKT 5 +#define ETH_RX_MAX_BUFF_PER_PKT 5 +#define ETH_RX_BD_THRESHOLD 12 /* num of MAC/VLAN filters */ #define ETH_NUM_MAC_FILTERS 512 diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h new file mode 100644 index 000000000000..12fc9e788eea --- /dev/null +++ b/include/linux/qed/fcoe_common.h @@ -0,0 +1,668 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef __FCOE_COMMON__ +#define __FCOE_COMMON__ +/*********************/ +/* FCOE FW CONSTANTS */ +/*********************/ + +#define FC_ABTS_REPLY_MAX_PAYLOAD_LEN 12 + +struct fcoe_abts_pkt { + __le32 abts_rsp_fc_payload_lo; + __le16 abts_rsp_rx_id; + u8 abts_rsp_rctl; + u8 reserved2; +}; + +/* FCoE additional WQE (Sq/XferQ) information */ +union fcoe_additional_info_union { + __le32 previous_tid; + __le32 parent_tid; + __le32 burst_length; + __le32 seq_rec_updated_offset; +}; + +struct fcoe_exp_ro { + __le32 data_offset; + __le32 reserved; +}; + +union fcoe_cleanup_addr_exp_ro_union { + struct regpair abts_rsp_fc_payload_hi; + struct fcoe_exp_ro exp_ro; +}; + +/* FCoE Ramrod Command IDs */ +enum fcoe_completion_status { + FCOE_COMPLETION_STATUS_SUCCESS, + FCOE_COMPLETION_STATUS_FCOE_VER_ERR, + FCOE_COMPLETION_STATUS_SRC_MAC_ADD_ARR_ERR, + MAX_FCOE_COMPLETION_STATUS +}; + +struct fc_addr_nw { + u8 addr_lo; + u8 addr_mid; + u8 addr_hi; +}; + +/* FCoE connection offload */ +struct fcoe_conn_offload_ramrod_data { + struct regpair sq_pbl_addr; + struct regpair sq_curr_page_addr; + struct regpair sq_next_page_addr; + struct regpair xferq_pbl_addr; + struct regpair xferq_curr_page_addr; + struct regpair xferq_next_page_addr; + struct regpair respq_pbl_addr; + struct regpair respq_curr_page_addr; + struct regpair respq_next_page_addr; + __le16 dst_mac_addr_lo; + __le16 dst_mac_addr_mid; + __le16 dst_mac_addr_hi; + __le16 src_mac_addr_lo; + __le16 src_mac_addr_mid; + __le16 src_mac_addr_hi; + __le16 tx_max_fc_pay_len; + __le16 e_d_tov_timer_val; + __le16 rx_max_fc_pay_len; + __le16 vlan_tag; +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_VLAN_ID_MASK 0xFFF +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_VLAN_ID_SHIFT 0 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_CFI_MASK 0x1 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_CFI_SHIFT 12 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_PRIORITY_MASK 0x7 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_PRIORITY_SHIFT 13 + __le16 physical_q0; + __le16 rec_rr_tov_timer_val; + struct fc_addr_nw s_id; + u8 max_conc_seqs_c3; + struct fc_addr_nw d_id; + u8 flags; +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_B_CONT_INCR_SEQ_CNT_MASK 0x1 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_B_CONT_INCR_SEQ_CNT_SHIFT 0 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_B_CONF_REQ_MASK 0x1 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_B_CONF_REQ_SHIFT 1 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_B_REC_VALID_MASK 0x1 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_B_REC_VALID_SHIFT 2 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_B_VLAN_FLAG_MASK 0x1 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_B_VLAN_FLAG_SHIFT 3 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_MODE_MASK 0x3 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_MODE_SHIFT 4 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_RESERVED0_MASK 0x3 +#define FCOE_CONN_OFFLOAD_RAMROD_DATA_RESERVED0_SHIFT 6 + __le16 conn_id; + u8 def_q_idx; + u8 reserved[5]; +}; + +/* FCoE terminate connection request */ +struct fcoe_conn_terminate_ramrod_data { + struct regpair terminate_params_addr; +}; + +struct fcoe_slow_sgl_ctx { + struct regpair base_sgl_addr; + __le16 curr_sge_off; + __le16 remainder_num_sges; + __le16 curr_sgl_index; + __le16 reserved; +}; + +union fcoe_dix_desc_ctx { + struct fcoe_slow_sgl_ctx dix_sgl; + struct scsi_sge cached_dix_sge; +}; + +struct fcoe_fast_sgl_ctx { + struct regpair sgl_start_addr; + __le32 sgl_byte_offset; + __le16 task_reuse_cnt; + __le16 init_offset_in_first_sge; +}; + +struct fcoe_fcp_cmd_payload { + __le32 opaque[8]; +}; + +struct fcoe_fcp_rsp_payload { + __le32 opaque[6]; +}; + +struct fcoe_fcp_xfer_payload { + __le32 opaque[3]; +}; + +/* FCoE firmware function init */ +struct fcoe_init_func_ramrod_data { + struct scsi_init_func_params func_params; + struct scsi_init_func_queues q_params; + __le16 mtu; + __le16 sq_num_pages_in_pbl; + __le32 reserved; +}; + +/* FCoE: Mode of the connection: Target or Initiator or both */ +enum fcoe_mode_type { + FCOE_INITIATOR_MODE = 0x0, + FCOE_TARGET_MODE = 0x1, + FCOE_BOTH_OR_NOT_CHOSEN = 0x3, + MAX_FCOE_MODE_TYPE +}; + +struct fcoe_rx_stat { + struct regpair fcoe_rx_byte_cnt; + struct regpair fcoe_rx_data_pkt_cnt; + struct regpair fcoe_rx_xfer_pkt_cnt; + struct regpair fcoe_rx_other_pkt_cnt; + __le32 fcoe_silent_drop_pkt_cmdq_full_cnt; + __le32 fcoe_silent_drop_pkt_rq_full_cnt; + __le32 fcoe_silent_drop_pkt_crc_error_cnt; + __le32 fcoe_silent_drop_pkt_task_invalid_cnt; + __le32 fcoe_silent_drop_total_pkt_cnt; + __le32 rsrv; +}; + +struct fcoe_stat_ramrod_data { + struct regpair stat_params_addr; +}; + +struct protection_info_ctx { + __le16 flags; +#define PROTECTION_INFO_CTX_HOST_INTERFACE_MASK 0x3 +#define PROTECTION_INFO_CTX_HOST_INTERFACE_SHIFT 0 +#define PROTECTION_INFO_CTX_DIF_TO_PEER_MASK 0x1 +#define PROTECTION_INFO_CTX_DIF_TO_PEER_SHIFT 2 +#define PROTECTION_INFO_CTX_VALIDATE_DIX_APP_TAG_MASK 0x1 +#define PROTECTION_INFO_CTX_VALIDATE_DIX_APP_TAG_SHIFT 3 +#define PROTECTION_INFO_CTX_INTERVAL_SIZE_LOG_MASK 0xF +#define PROTECTION_INFO_CTX_INTERVAL_SIZE_LOG_SHIFT 4 +#define PROTECTION_INFO_CTX_VALIDATE_DIX_REF_TAG_MASK 0x1 +#define PROTECTION_INFO_CTX_VALIDATE_DIX_REF_TAG_SHIFT 8 +#define PROTECTION_INFO_CTX_RESERVED0_MASK 0x7F +#define PROTECTION_INFO_CTX_RESERVED0_SHIFT 9 + u8 dix_block_size; + u8 dst_size; +}; + +union protection_info_union_ctx { + struct protection_info_ctx info; + __le32 value; +}; + +struct fcp_rsp_payload_padded { + struct fcoe_fcp_rsp_payload rsp_payload; + __le32 reserved[2]; +}; + +struct fcp_xfer_payload_padded { + struct fcoe_fcp_xfer_payload xfer_payload; + __le32 reserved[5]; +}; + +struct fcoe_tx_data_params { + __le32 data_offset; + __le32 offset_in_io; + u8 flags; +#define FCOE_TX_DATA_PARAMS_OFFSET_IN_IO_VALID_MASK 0x1 +#define FCOE_TX_DATA_PARAMS_OFFSET_IN_IO_VALID_SHIFT 0 +#define FCOE_TX_DATA_PARAMS_DROP_DATA_MASK 0x1 +#define FCOE_TX_DATA_PARAMS_DROP_DATA_SHIFT 1 +#define FCOE_TX_DATA_PARAMS_AFTER_SEQ_REC_MASK 0x1 +#define FCOE_TX_DATA_PARAMS_AFTER_SEQ_REC_SHIFT 2 +#define FCOE_TX_DATA_PARAMS_RESERVED0_MASK 0x1F +#define FCOE_TX_DATA_PARAMS_RESERVED0_SHIFT 3 + u8 dif_residual; + __le16 seq_cnt; + __le16 single_sge_saved_offset; + __le16 next_dif_offset; + __le16 seq_id; + __le16 reserved3; +}; + +struct fcoe_tx_mid_path_params { + __le32 parameter; + u8 r_ctl; + u8 type; + u8 cs_ctl; + u8 df_ctl; + __le16 rx_id; + __le16 ox_id; +}; + +struct fcoe_tx_params { + struct fcoe_tx_data_params data; + struct fcoe_tx_mid_path_params mid_path; +}; + +union fcoe_tx_info_union_ctx { + struct fcoe_fcp_cmd_payload fcp_cmd_payload; + struct fcp_rsp_payload_padded fcp_rsp_payload; + struct fcp_xfer_payload_padded fcp_xfer_payload; + struct fcoe_tx_params tx_params; +}; + +struct ystorm_fcoe_task_st_ctx { + u8 task_type; + u8 sgl_mode; +#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x1 +#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT 0 +#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK 0x7F +#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT 1 + u8 cached_dix_sge; + u8 expect_first_xfer; + __le32 num_pbf_zero_write; + union protection_info_union_ctx protection_info_union; + __le32 data_2_trns_rem; + struct scsi_sgl_params sgl_params; + u8 reserved1[12]; + union fcoe_tx_info_union_ctx tx_info_union; + union fcoe_dix_desc_ctx dix_desc; + struct scsi_cached_sges data_desc; + __le16 ox_id; + __le16 rx_id; + __le32 task_rety_identifier; + u8 reserved2[8]; +}; + +struct ystorm_fcoe_task_ag_ctx { + u8 byte0; + u8 byte1; + __le16 word0; + u8 flags0; +#define YSTORM_FCOE_TASK_AG_CTX_NIBBLE0_MASK 0xF +#define YSTORM_FCOE_TASK_AG_CTX_NIBBLE0_SHIFT 0 +#define YSTORM_FCOE_TASK_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_BIT0_SHIFT 4 +#define YSTORM_FCOE_TASK_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_BIT1_SHIFT 5 +#define YSTORM_FCOE_TASK_AG_CTX_BIT2_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_BIT2_SHIFT 6 +#define YSTORM_FCOE_TASK_AG_CTX_BIT3_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_BIT3_SHIFT 7 + u8 flags1; +#define YSTORM_FCOE_TASK_AG_CTX_CF0_MASK 0x3 +#define YSTORM_FCOE_TASK_AG_CTX_CF0_SHIFT 0 +#define YSTORM_FCOE_TASK_AG_CTX_CF1_MASK 0x3 +#define YSTORM_FCOE_TASK_AG_CTX_CF1_SHIFT 2 +#define YSTORM_FCOE_TASK_AG_CTX_CF2SPECIAL_MASK 0x3 +#define YSTORM_FCOE_TASK_AG_CTX_CF2SPECIAL_SHIFT 4 +#define YSTORM_FCOE_TASK_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_CF0EN_SHIFT 6 +#define YSTORM_FCOE_TASK_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_CF1EN_SHIFT 7 + u8 flags2; +#define YSTORM_FCOE_TASK_AG_CTX_BIT4_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_BIT4_SHIFT 0 +#define YSTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 2 +#define YSTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 3 +#define YSTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 4 +#define YSTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 5 +#define YSTORM_FCOE_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE5EN_SHIFT 6 +#define YSTORM_FCOE_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE6EN_SHIFT 7 + u8 byte2; + __le32 reg0; + u8 byte3; + u8 byte4; + __le16 rx_id; + __le16 word2; + __le16 word3; + __le16 word4; + __le16 word5; + __le32 reg1; + __le32 reg2; +}; + +struct tstorm_fcoe_task_ag_ctx { + u8 reserved; + u8 byte1; + __le16 icid; + u8 flags0; +#define TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define TSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define TSTORM_FCOE_TASK_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_BIT1_SHIFT 5 +#define TSTORM_FCOE_TASK_AG_CTX_WAIT_ABTS_RSP_F_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_WAIT_ABTS_RSP_F_SHIFT 6 +#define TSTORM_FCOE_TASK_AG_CTX_VALID_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_VALID_SHIFT 7 + u8 flags1; +#define TSTORM_FCOE_TASK_AG_CTX_FALSE_RR_TOV_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_FALSE_RR_TOV_SHIFT 0 +#define TSTORM_FCOE_TASK_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_BIT5_SHIFT 1 +#define TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_SHIFT 2 +#define TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_SHIFT 4 +#define TSTORM_FCOE_TASK_AG_CTX_CF2_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_CF2_SHIFT 6 + u8 flags2; +#define TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_SHIFT 0 +#define TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_SHIFT 2 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_SHIFT 4 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_SHIFT 6 + u8 flags3; +#define TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_SHIFT 0 +#define TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_EN_SHIFT 2 +#define TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_EN_SHIFT 3 +#define TSTORM_FCOE_TASK_AG_CTX_CF2EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_CF2EN_SHIFT 4 +#define TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 5 +#define TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_SHIFT 6 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_EN_SHIFT 7 + u8 flags4; +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_EN_SHIFT 0 +#define TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_EN_SHIFT 1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 2 +#define TSTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 3 +#define TSTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 4 +#define TSTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 5 +#define TSTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 6 +#define TSTORM_FCOE_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE5EN_SHIFT 7 + u8 cleanup_state; + __le16 last_sent_tid; + __le32 rec_rr_tov_exp_timeout; + u8 byte3; + u8 byte4; + __le16 word2; + __le16 word3; + __le16 word4; + __le32 data_offset_end_of_seq; + __le32 data_offset_next; +}; + +struct fcoe_tstorm_fcoe_task_st_ctx_read_write { + union fcoe_cleanup_addr_exp_ro_union cleanup_addr_exp_ro_union; + __le16 flags; +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK 0x1 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_SHIFT 0 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_MASK 0x1 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT 1 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_MASK 0x1 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT 2 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_MASK 0x1 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT 3 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_MASK 0x1 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 4 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_MASK 0x1 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT 5 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_MASK 0x3 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT 6 +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK 0xFF +#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT 8 + __le16 seq_cnt; + u8 seq_id; + u8 ooo_rx_seq_id; + __le16 rx_id; + struct fcoe_abts_pkt abts_data; + __le32 e_d_tov_exp_timeout_val; + __le16 ooo_rx_seq_cnt; + __le16 reserved1; +}; + +struct fcoe_tstorm_fcoe_task_st_ctx_read_only { + u8 task_type; + u8 dev_type; + u8 conf_supported; + u8 glbl_q_num; + __le32 cid; + __le32 fcp_cmd_trns_size; + __le32 rsrv; +}; + +struct tstorm_fcoe_task_st_ctx { + struct fcoe_tstorm_fcoe_task_st_ctx_read_write read_write; + struct fcoe_tstorm_fcoe_task_st_ctx_read_only read_only; +}; + +struct mstorm_fcoe_task_ag_ctx { + u8 byte0; + u8 byte1; + __le16 icid; + u8 flags0; +#define MSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define MSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define MSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define MSTORM_FCOE_TASK_AG_CTX_CQE_PLACED_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_CQE_PLACED_SHIFT 5 +#define MSTORM_FCOE_TASK_AG_CTX_BIT2_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_BIT2_SHIFT 6 +#define MSTORM_FCOE_TASK_AG_CTX_BIT3_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_BIT3_SHIFT 7 + u8 flags1; +#define MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_MASK 0x3 +#define MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_SHIFT 0 +#define MSTORM_FCOE_TASK_AG_CTX_CF1_MASK 0x3 +#define MSTORM_FCOE_TASK_AG_CTX_CF1_SHIFT 2 +#define MSTORM_FCOE_TASK_AG_CTX_CF2_MASK 0x3 +#define MSTORM_FCOE_TASK_AG_CTX_CF2_SHIFT 4 +#define MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_SHIFT 6 +#define MSTORM_FCOE_TASK_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_CF1EN_SHIFT 7 + u8 flags2; +#define MSTORM_FCOE_TASK_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_CF2EN_SHIFT 0 +#define MSTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 2 +#define MSTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 3 +#define MSTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 4 +#define MSTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 5 +#define MSTORM_FCOE_TASK_AG_CTX_XFER_PLACEMENT_EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_XFER_PLACEMENT_EN_SHIFT 6 +#define MSTORM_FCOE_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE6EN_SHIFT 7 + u8 cleanup_state; + __le32 received_bytes; + u8 byte3; + u8 glbl_q_num; + __le16 word1; + __le16 tid_to_xfer; + __le16 word3; + __le16 word4; + __le16 word5; + __le32 expected_bytes; + __le32 reg2; +}; + +struct mstorm_fcoe_task_st_ctx { + struct regpair rsp_buf_addr; + __le32 rsrv[2]; + struct scsi_sgl_params sgl_params; + __le32 data_2_trns_rem; + __le32 data_buffer_offset; + __le16 parent_id; + __le16 flags; +#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_MASK 0xF +#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_SHIFT 0 +#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_MASK 0x3 +#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_SHIFT 4 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_SHIFT 6 +#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_SHIFT 7 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_MASK 0x3 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_SHIFT 8 +#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_SHIFT 10 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_SHIFT 11 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_SHIFT 12 +#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x1 +#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT 13 +#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_MASK 0x3 +#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_SHIFT 14 + struct scsi_cached_sges data_desc; +}; + +struct ustorm_fcoe_task_ag_ctx { + u8 reserved; + u8 byte1; + __le16 icid; + u8 flags0; +#define USTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define USTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define USTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define USTORM_FCOE_TASK_AG_CTX_BIT1_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_BIT1_SHIFT 5 +#define USTORM_FCOE_TASK_AG_CTX_CF0_MASK 0x3 +#define USTORM_FCOE_TASK_AG_CTX_CF0_SHIFT 6 + u8 flags1; +#define USTORM_FCOE_TASK_AG_CTX_CF1_MASK 0x3 +#define USTORM_FCOE_TASK_AG_CTX_CF1_SHIFT 0 +#define USTORM_FCOE_TASK_AG_CTX_CF2_MASK 0x3 +#define USTORM_FCOE_TASK_AG_CTX_CF2_SHIFT 2 +#define USTORM_FCOE_TASK_AG_CTX_CF3_MASK 0x3 +#define USTORM_FCOE_TASK_AG_CTX_CF3_SHIFT 4 +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 + u8 flags2; +#define USTORM_FCOE_TASK_AG_CTX_CF0EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_CF0EN_SHIFT 0 +#define USTORM_FCOE_TASK_AG_CTX_CF1EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_FCOE_TASK_AG_CTX_CF2EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_FCOE_TASK_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 +#define USTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 5 +#define USTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 6 +#define USTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 7 + u8 flags3; +#define USTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 0 +#define USTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 1 +#define USTORM_FCOE_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE5EN_SHIFT 2 +#define USTORM_FCOE_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE6EN_SHIFT 3 +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 + __le32 dif_err_intervals; + __le32 dif_error_1st_interval; + __le32 global_cq_num; + __le32 reg3; + __le32 reg4; + __le32 reg5; +}; + +struct fcoe_task_context { + struct ystorm_fcoe_task_st_ctx ystorm_st_context; + struct regpair ystorm_st_padding[2]; + struct tdif_task_context tdif_context; + struct ystorm_fcoe_task_ag_ctx ystorm_ag_context; + struct tstorm_fcoe_task_ag_ctx tstorm_ag_context; + struct timers_context timer_context; + struct tstorm_fcoe_task_st_ctx tstorm_st_context; + struct regpair tstorm_st_padding[2]; + struct mstorm_fcoe_task_ag_ctx mstorm_ag_context; + struct mstorm_fcoe_task_st_ctx mstorm_st_context; + struct ustorm_fcoe_task_ag_ctx ustorm_ag_context; + struct rdif_task_context rdif_context; +}; + +struct fcoe_tx_stat { + struct regpair fcoe_tx_byte_cnt; + struct regpair fcoe_tx_data_pkt_cnt; + struct regpair fcoe_tx_xfer_pkt_cnt; + struct regpair fcoe_tx_other_pkt_cnt; +}; + +struct fcoe_wqe { + __le16 task_id; + __le16 flags; +#define FCOE_WQE_REQ_TYPE_MASK 0xF +#define FCOE_WQE_REQ_TYPE_SHIFT 0 +#define FCOE_WQE_SGL_MODE_MASK 0x1 +#define FCOE_WQE_SGL_MODE_SHIFT 4 +#define FCOE_WQE_CONTINUATION_MASK 0x1 +#define FCOE_WQE_CONTINUATION_SHIFT 5 +#define FCOE_WQE_SEND_AUTO_RSP_MASK 0x1 +#define FCOE_WQE_SEND_AUTO_RSP_SHIFT 6 +#define FCOE_WQE_RESERVED_MASK 0x1 +#define FCOE_WQE_RESERVED_SHIFT 7 +#define FCOE_WQE_NUM_SGES_MASK 0xF +#define FCOE_WQE_NUM_SGES_SHIFT 8 +#define FCOE_WQE_RESERVED1_MASK 0xF +#define FCOE_WQE_RESERVED1_SHIFT 12 + union fcoe_additional_info_union additional_info_union; +}; + +struct xfrqe_prot_flags { + u8 flags; +#define XFRQE_PROT_FLAGS_PROT_INTERVAL_SIZE_LOG_MASK 0xF +#define XFRQE_PROT_FLAGS_PROT_INTERVAL_SIZE_LOG_SHIFT 0 +#define XFRQE_PROT_FLAGS_DIF_TO_PEER_MASK 0x1 +#define XFRQE_PROT_FLAGS_DIF_TO_PEER_SHIFT 4 +#define XFRQE_PROT_FLAGS_HOST_INTERFACE_MASK 0x3 +#define XFRQE_PROT_FLAGS_HOST_INTERFACE_SHIFT 5 +#define XFRQE_PROT_FLAGS_RESERVED_MASK 0x1 +#define XFRQE_PROT_FLAGS_RESERVED_SHIFT 7 +}; + +struct fcoe_db_data { + u8 params; +#define FCOE_DB_DATA_DEST_MASK 0x3 +#define FCOE_DB_DATA_DEST_SHIFT 0 +#define FCOE_DB_DATA_AGG_CMD_MASK 0x3 +#define FCOE_DB_DATA_AGG_CMD_SHIFT 2 +#define FCOE_DB_DATA_BYPASS_EN_MASK 0x1 +#define FCOE_DB_DATA_BYPASS_EN_SHIFT 4 +#define FCOE_DB_DATA_RESERVED_MASK 0x1 +#define FCOE_DB_DATA_RESERVED_SHIFT 5 +#define FCOE_DB_DATA_AGG_VAL_SEL_MASK 0x3 +#define FCOE_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; + __le16 sq_prod; +}; +#endif /* __FCOE_COMMON__ */ diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 8f64b1223c2f..85e086cba639 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -1,9 +1,33 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef __ISCSI_COMMON__ @@ -15,17 +39,9 @@ /* iSCSI HSI constants */ #define ISCSI_DEFAULT_MTU (1500) -/* Current iSCSI HSI version number composed of two fields (16 bit) */ -#define ISCSI_HSI_MAJOR_VERSION (0) -#define ISCSI_HSI_MINOR_VERSION (0) - /* KWQ (kernel work queue) layer codes */ #define ISCSI_SLOW_PATH_LAYER_CODE (6) -/* CQE completion status */ -#define ISCSI_EQE_COMPLETION_SUCCESS (0x0) -#define ISCSI_EQE_RST_CONN_RCVD (0x1) - /* iSCSI parameter defaults */ #define ISCSI_DEFAULT_HEADER_DIGEST (0) #define ISCSI_DEFAULT_DATA_DIGEST (0) @@ -44,6 +60,10 @@ #define ISCSI_MIN_VAL_MAX_OUTSTANDING_R2T (1) #define ISCSI_MAX_VAL_MAX_OUTSTANDING_R2T (0xff) +#define ISCSI_AHS_CNTL_SIZE 4 + +#define ISCSI_WQE_NUM_SGES_SLOWIO (0xf) + /* iSCSI reserved params */ #define ISCSI_ITT_ALL_ONES (0xffffffff) #define ISCSI_TTT_ALL_ONES (0xffffffff) @@ -55,25 +75,13 @@ #define ISCSI_TARGET_MODE 1 /* iSCSI request op codes */ -#define ISCSI_OPCODE_NOP_OUT_NO_IMM (0) -#define ISCSI_OPCODE_NOP_OUT ( \ - ISCSI_OPCODE_NOP_OUT_NO_IMM | 0x40) -#define ISCSI_OPCODE_SCSI_CMD_NO_IMM (1) -#define ISCSI_OPCODE_SCSI_CMD ( \ - ISCSI_OPCODE_SCSI_CMD_NO_IMM | 0x40) -#define ISCSI_OPCODE_TMF_REQUEST_NO_IMM (2) -#define ISCSI_OPCODE_TMF_REQUEST ( \ - ISCSI_OPCODE_TMF_REQUEST_NO_IMM | 0x40) -#define ISCSI_OPCODE_LOGIN_REQUEST_NO_IMM (3) -#define ISCSI_OPCODE_LOGIN_REQUEST ( \ - ISCSI_OPCODE_LOGIN_REQUEST_NO_IMM | 0x40) -#define ISCSI_OPCODE_TEXT_REQUEST_NO_IMM (4) -#define ISCSI_OPCODE_TEXT_REQUEST ( \ - ISCSI_OPCODE_TEXT_REQUEST_NO_IMM | 0x40) -#define ISCSI_OPCODE_DATA_OUT (5) -#define ISCSI_OPCODE_LOGOUT_REQUEST_NO_IMM (6) -#define ISCSI_OPCODE_LOGOUT_REQUEST ( \ - ISCSI_OPCODE_LOGOUT_REQUEST_NO_IMM | 0x40) +#define ISCSI_OPCODE_NOP_OUT (0) +#define ISCSI_OPCODE_SCSI_CMD (1) +#define ISCSI_OPCODE_TMF_REQUEST (2) +#define ISCSI_OPCODE_LOGIN_REQUEST (3) +#define ISCSI_OPCODE_TEXT_REQUEST (4) +#define ISCSI_OPCODE_DATA_OUT (5) +#define ISCSI_OPCODE_LOGOUT_REQUEST (6) /* iSCSI response/messages op codes */ #define ISCSI_OPCODE_NOP_IN (0x20) @@ -149,33 +157,26 @@ struct iscsi_async_msg_hdr { __le32 reserved7; }; -struct iscsi_sge { - struct regpair sge_addr; - __le16 sge_len; - __le16 reserved0; - __le32 reserved1; -}; - -struct iscsi_cached_sge_ctx { - struct iscsi_sge sge; - struct regpair reserved; - __le32 dsgl_curr_offset[2]; -}; - struct iscsi_cmd_hdr { __le16 reserved1; u8 flags_attr; -#define ISCSI_CMD_HDR_ATTR_MASK 0x7 -#define ISCSI_CMD_HDR_ATTR_SHIFT 0 -#define ISCSI_CMD_HDR_RSRV_MASK 0x3 -#define ISCSI_CMD_HDR_RSRV_SHIFT 3 -#define ISCSI_CMD_HDR_WRITE_MASK 0x1 -#define ISCSI_CMD_HDR_WRITE_SHIFT 5 -#define ISCSI_CMD_HDR_READ_MASK 0x1 -#define ISCSI_CMD_HDR_READ_SHIFT 6 -#define ISCSI_CMD_HDR_FINAL_MASK 0x1 -#define ISCSI_CMD_HDR_FINAL_SHIFT 7 - u8 opcode; +#define ISCSI_CMD_HDR_ATTR_MASK 0x7 +#define ISCSI_CMD_HDR_ATTR_SHIFT 0 +#define ISCSI_CMD_HDR_RSRV_MASK 0x3 +#define ISCSI_CMD_HDR_RSRV_SHIFT 3 +#define ISCSI_CMD_HDR_WRITE_MASK 0x1 +#define ISCSI_CMD_HDR_WRITE_SHIFT 5 +#define ISCSI_CMD_HDR_READ_MASK 0x1 +#define ISCSI_CMD_HDR_READ_SHIFT 6 +#define ISCSI_CMD_HDR_FINAL_MASK 0x1 +#define ISCSI_CMD_HDR_FINAL_SHIFT 7 + u8 hdr_first_byte; +#define ISCSI_CMD_HDR_OPCODE_MASK 0x3F +#define ISCSI_CMD_HDR_OPCODE_SHIFT 0 +#define ISCSI_CMD_HDR_IMM_MASK 0x1 +#define ISCSI_CMD_HDR_IMM_SHIFT 6 +#define ISCSI_CMD_HDR_RSRV1_MASK 0x1 +#define ISCSI_CMD_HDR_RSRV1_SHIFT 7 __le32 hdr_second_dword; #define ISCSI_CMD_HDR_DATA_SEG_LEN_MASK 0xFFFFFF #define ISCSI_CMD_HDR_DATA_SEG_LEN_SHIFT 0 @@ -205,8 +206,13 @@ struct iscsi_common_hdr { #define ISCSI_COMMON_HDR_DATA_SEG_LEN_SHIFT 0 #define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_MASK 0xFF #define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_SHIFT 24 - __le32 lun_reserved[4]; - __le32 data[6]; + struct regpair lun_reserved; + __le32 itt; + __le32 ttt; + __le32 cmdstat_sn; + __le32 exp_statcmd_sn; + __le32 max_cmd_sn; + __le32 data[3]; }; struct iscsi_conn_offload_params { @@ -222,8 +228,10 @@ struct iscsi_conn_offload_params { #define ISCSI_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0 #define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK 0x1 #define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT 1 -#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0x3F -#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 2 +#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK 0x1 +#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT 2 +#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0x1F +#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 3 u8 pbl_page_size_log; u8 pbe_page_size_log; u8 default_cq; @@ -254,8 +262,12 @@ struct iscsi_conn_update_ramrod_params { #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T_SHIFT 2 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_MASK 0x1 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_SHIFT 3 -#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0xF -#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT 4 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_MASK 0x1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_SHIFT 4 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_MASK 0x1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_SHIFT 5 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0x3 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT 6 u8 reserved0[3]; __le32 max_seq_size; __le32 max_send_pdu_length; @@ -288,7 +300,7 @@ struct iscsi_ext_cdb_cmd_hdr { __le32 expected_transfer_length; __le32 cmd_sn; __le32 exp_stat_sn; - struct iscsi_sge cdb_sge; + struct scsi_sge cdb_sge; }; struct iscsi_login_req_hdr { @@ -495,8 +507,8 @@ struct iscsi_logout_response_hdr { __le32 exp_cmd_sn; __le32 max_cmd_sn; __le32 reserved4; - __le16 time2retain; - __le16 time2wait; + __le16 time_2_retain; + __le16 time_2_wait; __le32 reserved5[1]; }; @@ -578,7 +590,7 @@ struct iscsi_tmf_response_hdr { #define ISCSI_TMF_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24 struct regpair reserved0; __le32 itt; - __le32 rtt; + __le32 reserved1; __le32 stat_sn; __le32 exp_cmd_sn; __le32 max_cmd_sn; @@ -617,7 +629,7 @@ struct iscsi_reject_hdr { #define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_MASK 0xFF #define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_SHIFT 24 struct regpair reserved0; - __le32 reserved1; + __le32 all_ones; __le32 reserved2; __le32 stat_sn; __le32 exp_cmd_sn; @@ -664,7 +676,9 @@ struct iscsi_cqe_solicited { __le16 itid; u8 task_type; u8 fw_dbg_field; - __le32 reserved1[2]; + u8 caused_conn_err; + u8 reserved0[3]; + __le32 reserved1[1]; union iscsi_task_hdr iscsi_hdr; }; @@ -703,35 +717,6 @@ enum iscsi_cqe_unsolicited_type { MAX_ISCSI_CQE_UNSOLICITED_TYPE }; -struct iscsi_virt_sgl_ctx { - struct regpair sgl_base; - struct regpair dsgl_base; - __le32 sgl_initial_offset; - __le32 dsgl_initial_offset; - __le32 dsgl_curr_offset[2]; -}; - -struct iscsi_sgl_var_params { - u8 sgl_ptr; - u8 dsgl_ptr; - __le16 sge_offset; - __le16 dsge_offset; -}; - -struct iscsi_phys_sgl_ctx { - struct regpair sgl_base; - struct regpair dsgl_base; - u8 sgl_size; - u8 dsgl_size; - __le16 reserved; - struct iscsi_sgl_var_params var_params[2]; -}; - -union iscsi_data_desc_ctx { - struct iscsi_virt_sgl_ctx virt_sgl; - struct iscsi_phys_sgl_ctx phys_sgl; - struct iscsi_cached_sge_ctx cached_sge; -}; struct iscsi_debug_modes { u8 flags; @@ -747,8 +732,10 @@ struct iscsi_debug_modes { #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_REJECT_OR_ASYNC_SHIFT 4 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_MASK 0x1 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_SHIFT 5 -#define ISCSI_DEBUG_MODES_RESERVED0_MASK 0x3 -#define ISCSI_DEBUG_MODES_RESERVED0_SHIFT 6 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_SHIFT 6 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_SHIFT 7 }; struct iscsi_dif_flags { @@ -782,7 +769,6 @@ enum iscsi_eqe_opcode { ISCSI_EVENT_TYPE_ASYN_FIN_WAIT2, ISCSI_EVENT_TYPE_ISCSI_CONN_ERROR, ISCSI_EVENT_TYPE_TCP_CONN_ERROR, - ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES, MAX_ISCSI_EQE_OPCODE }; @@ -798,9 +784,9 @@ enum iscsi_error_types { ISCSI_CONN_ERROR_LOCAL_COMPLETION_ERROR, ISCSI_CONN_ERROR_DATA_OVERRUN, ISCSI_CONN_ERROR_OUT_OF_SGES_ERROR, - ISCSI_CONN_ERROR_TCP_SEG_PROC_URG_ERROR, - ISCSI_CONN_ERROR_TCP_SEG_PROC_IP_OPTIONS_ERROR, - ISCSI_CONN_ERROR_TCP_SEG_PROC_CONNECT_INVALID_WS_OPTION, + ISCSI_CONN_ERROR_IP_OPTIONS_ERROR, + ISCSI_CONN_ERROR_PRS_ERRORS, + ISCSI_CONN_ERROR_CONNECT_INVALID_TCP_OPTION, ISCSI_CONN_ERROR_TCP_IP_FRAGMENT_ERROR, ISCSI_CONN_ERROR_PROTOCOL_ERR_AHS_LEN, ISCSI_CONN_ERROR_PROTOCOL_ERR_AHS_TYPE, @@ -832,31 +818,11 @@ enum iscsi_error_types { ISCSI_CONN_ERROR_PROTOCOL_ERR_DIF_TX, ISCSI_CONN_ERROR_SENSE_DATA_LENGTH, ISCSI_CONN_ERROR_DATA_PLACEMENT_ERROR, + ISCSI_CONN_ERROR_INVALID_ITT, ISCSI_ERROR_UNKNOWN, MAX_ISCSI_ERROR_TYPES }; -struct iscsi_mflags { - u8 mflags; -#define ISCSI_MFLAGS_SLOW_IO_MASK 0x1 -#define ISCSI_MFLAGS_SLOW_IO_SHIFT 0 -#define ISCSI_MFLAGS_SINGLE_SGE_MASK 0x1 -#define ISCSI_MFLAGS_SINGLE_SGE_SHIFT 1 -#define ISCSI_MFLAGS_RESERVED_MASK 0x3F -#define ISCSI_MFLAGS_RESERVED_SHIFT 2 -}; - -struct iscsi_sgl { - struct regpair sgl_addr; - __le16 updated_sge_size; - __le16 updated_sge_offset; - __le32 byte_offset; -}; - -union iscsi_mstorm_sgl { - struct iscsi_sgl sgl_struct; - struct iscsi_sge single_sge; -}; enum iscsi_ramrod_cmd_id { ISCSI_RAMROD_CMD_ID_UNUSED = 0, @@ -872,10 +838,10 @@ enum iscsi_ramrod_cmd_id { struct iscsi_reg1 { __le32 reg1_map; -#define ISCSI_REG1_NUM_FAST_SGES_MASK 0x7 -#define ISCSI_REG1_NUM_FAST_SGES_SHIFT 0 -#define ISCSI_REG1_RESERVED1_MASK 0x1FFFFFFF -#define ISCSI_REG1_RESERVED1_SHIFT 3 +#define ISCSI_REG1_NUM_SGES_MASK 0xF +#define ISCSI_REG1_NUM_SGES_SHIFT 0 +#define ISCSI_REG1_RESERVED1_MASK 0xFFFFFFF +#define ISCSI_REG1_RESERVED1_SHIFT 4 }; union iscsi_seq_num { @@ -943,22 +909,33 @@ struct iscsi_spe_func_init { }; struct ystorm_iscsi_task_state { - union iscsi_data_desc_ctx sgl_ctx_union; - __le32 buffer_offset[2]; - __le16 bytes_nxt_dif; - __le16 rxmit_bytes_nxt_dif; - union iscsi_seq_num seq_num_union; - u8 dif_bytes_leftover; - u8 rxmit_dif_bytes_leftover; - __le16 reuse_count; - struct iscsi_dif_flags dif_flags; - u8 local_comp; + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; __le32 exp_r2t_sn; - __le32 sgl_offset[2]; + __le32 buffer_offset; + union iscsi_seq_num seq_num; + struct iscsi_dif_flags dif_flags; + u8 flags; +#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_MASK 0x1 +#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_SHIFT 0 +#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_MASK 0x1 +#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_SHIFT 1 +#define YSTORM_ISCSI_TASK_STATE_RESERVED0_MASK 0x3F +#define YSTORM_ISCSI_TASK_STATE_RESERVED0_SHIFT 2 +}; + +struct ystorm_iscsi_task_rxmit_opt { + __le32 fast_rxmit_sge_offset; + __le32 scan_start_buffer_offset; + __le32 fast_rxmit_buffer_offset; + u8 scan_start_sgl_index; + u8 fast_rxmit_sgl_index; + __le16 reserved; }; struct ystorm_iscsi_task_st_ctx { struct ystorm_iscsi_task_state state; + struct ystorm_iscsi_task_rxmit_opt rxmit_opt; union iscsi_task_hdr pdu_hdr; }; @@ -1128,25 +1105,16 @@ struct ustorm_iscsi_task_ag_ctx { }; struct mstorm_iscsi_task_st_ctx { - union iscsi_mstorm_sgl sgl_union; - struct iscsi_dif_flags dif_flags; - struct iscsi_mflags flags; - u8 sgl_size; - u8 host_sge_index; - __le16 dix_cur_sge_offset; - __le16 dix_cur_sge_size; - __le32 data_offset_rtid; - u8 dif_offset; - u8 dix_sgl_size; - u8 dix_sge_index; + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; + __le32 rem_task_size; + __le32 data_buffer_offset; u8 task_type; + struct iscsi_dif_flags dif_flags; + u8 reserved0[2]; struct regpair sense_db; - struct regpair dix_sgl_cur_sge; - __le32 rem_task_size; - __le16 reuse_count; - __le16 dif_data_residue; - u8 reserved0[4]; - __le32 reserved1[1]; + __le32 expected_itt; + __le32 reserved1; }; struct ustorm_iscsi_task_st_ctx { @@ -1160,7 +1128,7 @@ struct ustorm_iscsi_task_st_ctx { #define USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST_SHIFT 0 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_MASK 0x7F #define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_SHIFT 1 - u8 reserved2; + struct iscsi_dif_flags dif_flags; __le16 reserved3; __le32 reserved4; __le32 reserved5; @@ -1183,10 +1151,10 @@ struct ustorm_iscsi_task_st_ctx { #define USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP_SHIFT 2 #define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK 0x1 #define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT 3 -#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_MASK 0x1 -#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_SHIFT 4 -#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_MASK 0x1 -#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_SHIFT 5 +#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4 +#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT 5 #define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_MASK 0x1 #define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_SHIFT 6 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED0_MASK 0x1 @@ -1196,7 +1164,6 @@ struct ustorm_iscsi_task_st_ctx { struct iscsi_task_context { struct ystorm_iscsi_task_st_ctx ystorm_st_context; - struct regpair ystorm_st_padding[2]; struct ystorm_iscsi_task_ag_ctx ystorm_ag_context; struct regpair ystorm_ag_padding[2]; struct tdif_task_context tdif_context; @@ -1248,32 +1215,22 @@ struct iscsi_uhqe { #define ISCSI_UHQE_TASK_ID_LO_SHIFT 24 }; -struct iscsi_wqe_field { - __le32 contlen_cdbsize_field; -#define ISCSI_WQE_FIELD_CONT_LEN_MASK 0xFFFFFF -#define ISCSI_WQE_FIELD_CONT_LEN_SHIFT 0 -#define ISCSI_WQE_FIELD_CDB_SIZE_MASK 0xFF -#define ISCSI_WQE_FIELD_CDB_SIZE_SHIFT 24 -}; - -union iscsi_wqe_field_union { - struct iscsi_wqe_field cont_field; - __le32 prev_tid; -}; struct iscsi_wqe { __le16 task_id; u8 flags; #define ISCSI_WQE_WQE_TYPE_MASK 0x7 #define ISCSI_WQE_WQE_TYPE_SHIFT 0 -#define ISCSI_WQE_NUM_FAST_SGES_MASK 0x7 -#define ISCSI_WQE_NUM_FAST_SGES_SHIFT 3 -#define ISCSI_WQE_PTU_INVALIDATE_MASK 0x1 -#define ISCSI_WQE_PTU_INVALIDATE_SHIFT 6 +#define ISCSI_WQE_NUM_SGES_MASK 0xF +#define ISCSI_WQE_NUM_SGES_SHIFT 3 #define ISCSI_WQE_RESPONSE_MASK 0x1 #define ISCSI_WQE_RESPONSE_SHIFT 7 struct iscsi_dif_flags prot_flags; - union iscsi_wqe_field_union cont_prevtid_union; + __le32 contlen_cdbsize; +#define ISCSI_WQE_CONT_LEN_MASK 0xFFFFFF +#define ISCSI_WQE_CONT_LEN_SHIFT 0 +#define ISCSI_WQE_CDB_SIZE_MASK 0xFF +#define ISCSI_WQE_CDB_SIZE_SHIFT 24 }; enum iscsi_wqe_type { @@ -1294,17 +1251,15 @@ struct iscsi_xhqe { u8 total_ahs_length; u8 opcode; u8 flags; -#define ISCSI_XHQE_NUM_FAST_SGES_MASK 0x7 -#define ISCSI_XHQE_NUM_FAST_SGES_SHIFT 0 -#define ISCSI_XHQE_FINAL_MASK 0x1 -#define ISCSI_XHQE_FINAL_SHIFT 3 -#define ISCSI_XHQE_SUPER_IO_MASK 0x1 -#define ISCSI_XHQE_SUPER_IO_SHIFT 4 -#define ISCSI_XHQE_STATUS_BIT_MASK 0x1 -#define ISCSI_XHQE_STATUS_BIT_SHIFT 5 -#define ISCSI_XHQE_RESERVED_MASK 0x3 -#define ISCSI_XHQE_RESERVED_SHIFT 6 - union iscsi_seq_num seq_num_union; +#define ISCSI_XHQE_FINAL_MASK 0x1 +#define ISCSI_XHQE_FINAL_SHIFT 0 +#define ISCSI_XHQE_STATUS_BIT_MASK 0x1 +#define ISCSI_XHQE_STATUS_BIT_SHIFT 1 +#define ISCSI_XHQE_NUM_SGES_MASK 0xF +#define ISCSI_XHQE_NUM_SGES_SHIFT 2 +#define ISCSI_XHQE_RESERVED0_MASK 0x3 +#define ISCSI_XHQE_RESERVED0_SHIFT 6 + union iscsi_seq_num seq_num; __le16 reserved1; }; @@ -1343,22 +1298,6 @@ struct ystorm_iscsi_stats_drv { struct regpair iscsi_tx_total_pdu_cnt; }; -struct iscsi_db_data { - u8 params; -#define ISCSI_DB_DATA_DEST_MASK 0x3 -#define ISCSI_DB_DATA_DEST_SHIFT 0 -#define ISCSI_DB_DATA_AGG_CMD_MASK 0x3 -#define ISCSI_DB_DATA_AGG_CMD_SHIFT 2 -#define ISCSI_DB_DATA_BYPASS_EN_MASK 0x1 -#define ISCSI_DB_DATA_BYPASS_EN_SHIFT 4 -#define ISCSI_DB_DATA_RESERVED_MASK 0x1 -#define ISCSI_DB_DATA_RESERVED_SHIFT 5 -#define ISCSI_DB_DATA_AGG_VAL_SEL_MASK 0x3 -#define ISCSI_DB_DATA_AGG_VAL_SEL_SHIFT 6 - u8 agg_flags; - __le16 sq_prod; -}; - struct tstorm_iscsi_task_ag_ctx { u8 byte0; u8 byte1; @@ -1437,5 +1376,20 @@ struct tstorm_iscsi_task_ag_ctx { __le32 reg1; __le32 reg2; }; +struct iscsi_db_data { + u8 params; +#define ISCSI_DB_DATA_DEST_MASK 0x3 +#define ISCSI_DB_DATA_DEST_SHIFT 0 +#define ISCSI_DB_DATA_AGG_CMD_MASK 0x3 +#define ISCSI_DB_DATA_AGG_CMD_SHIFT 2 +#define ISCSI_DB_DATA_BYPASS_EN_MASK 0x1 +#define ISCSI_DB_DATA_BYPASS_EN_SHIFT 4 +#define ISCSI_DB_DATA_RESERVED_MASK 0x1 +#define ISCSI_DB_DATA_RESERVED_SHIFT 5 +#define ISCSI_DB_DATA_AGG_VAL_SEL_MASK 0x3 +#define ISCSI_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; + __le16 sq_prod; +}; #endif /* __ISCSI_COMMON__ */ diff --git a/include/linux/qed/iwarp_common.h b/include/linux/qed/iwarp_common.h new file mode 100644 index 000000000000..b8b3e1cfae90 --- /dev/null +++ b/include/linux/qed/iwarp_common.h @@ -0,0 +1,53 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015-2017 QLogic Corporation + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef __IWARP_COMMON__ +#define __IWARP_COMMON__ +#include <linux/qed/rdma_common.h> +/************************/ +/* IWARP FW CONSTANTS */ +/************************/ + +#define IWARP_ACTIVE_MODE 0 +#define IWARP_PASSIVE_MODE 1 + +#define IWARP_SHARED_QUEUE_PAGE_SIZE (0x8000) +#define IWARP_SHARED_QUEUE_PAGE_RQ_PBL_OFFSET (0x4000) +#define IWARP_SHARED_QUEUE_PAGE_RQ_PBL_MAX_SIZE (0x1000) +#define IWARP_SHARED_QUEUE_PAGE_SQ_PBL_OFFSET (0x5000) +#define IWARP_SHARED_QUEUE_PAGE_SQ_PBL_MAX_SIZE (0x3000) + +#define IWARP_REQ_MAX_INLINE_DATA_SIZE (128) +#define IWARP_REQ_MAX_SINGLE_SQ_WQE_SIZE (176) + +#define IWARP_MAX_QPS (64 * 1024) + +#endif /* __IWARP_COMMON__ */ diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 37dfba101c6c..59ddf9af909e 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -1,9 +1,33 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation - * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * Copyright (c) 2015-2017 QLogic Corporation + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef _QED_CHAIN_H @@ -56,6 +80,11 @@ struct qed_chain_pbl_u32 { u32 cons_page_idx; }; +struct qed_chain_ext_pbl { + dma_addr_t p_pbl_phys; + void *p_pbl_virt; +}; + struct qed_chain_u16 { /* Cyclic index of next element to produce/consme */ u16 prod_idx; @@ -131,6 +160,8 @@ struct qed_chain { u32 size; u8 intended_use; + + bool b_external_pbl; }; #define QED_CHAIN_PBL_ENTRY_SIZE (8) diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 7a52f7c58c37..0eef0a2b1901 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -1,9 +1,33 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef _QED_ETH_IF_H @@ -23,8 +47,7 @@ struct qed_queue_start_common_params { /* Relative, but relevant only for PFs */ u8 stats_id; - /* These are always absolute */ - u16 sb; + struct qed_sb_info *p_sb; u8 sb_idx; }; @@ -50,10 +73,13 @@ struct qed_dev_eth_info { /* Legacy VF - this affects the datapath, so qede has to know */ bool is_legacy; + + /* Might depend on available resources [in case of VF] */ + bool xdp_supported; }; struct qed_update_vport_rss_params { - u16 rss_ind_table[128]; + void *rss_ind_table[128]; u32 rss_key[10]; u8 rss_caps; }; @@ -72,6 +98,7 @@ struct qed_update_vport_params { struct qed_start_vport_params { bool remove_inner_vlan; + bool handle_ptp_pkts; bool gro_enable; bool drop_ttl0; u8 vport_id; @@ -133,6 +160,27 @@ struct qed_tunn_params { struct qed_eth_cb_ops { struct qed_common_cb_ops common; void (*force_mac) (void *dev, u8 *mac, bool forced); + void (*ports_update)(void *dev, u16 vxlan_port, u16 geneve_port); +}; + +#define QED_MAX_PHC_DRIFT_PPB 291666666 + +enum qed_ptp_filter_type { + QED_PTP_FILTER_NONE, + QED_PTP_FILTER_ALL, + QED_PTP_FILTER_V1_L4_EVENT, + QED_PTP_FILTER_V1_L4_GEN, + QED_PTP_FILTER_V2_L4_EVENT, + QED_PTP_FILTER_V2_L4_GEN, + QED_PTP_FILTER_V2_L2_EVENT, + QED_PTP_FILTER_V2_L2_GEN, + QED_PTP_FILTER_V2_EVENT, + QED_PTP_FILTER_V2_GEN +}; + +enum qed_ptp_hwtstamp_tx_type { + QED_PTP_HWTSTAMP_TX_OFF, + QED_PTP_HWTSTAMP_TX_ON, }; #ifdef CONFIG_DCB @@ -194,6 +242,17 @@ struct qed_eth_dcbnl_ops { }; #endif +struct qed_eth_ptp_ops { + int (*cfg_filters)(struct qed_dev *, enum qed_ptp_filter_type, + enum qed_ptp_hwtstamp_tx_type); + int (*read_rx_ts)(struct qed_dev *, u64 *); + int (*read_tx_ts)(struct qed_dev *, u64 *); + int (*read_cc)(struct qed_dev *, u64 *); + int (*disable)(struct qed_dev *); + int (*adjfreq)(struct qed_dev *, s32); + int (*enable)(struct qed_dev *); +}; + struct qed_eth_ops { const struct qed_common_ops *common; #ifdef CONFIG_QED_SRIOV @@ -202,6 +261,7 @@ struct qed_eth_ops { #ifdef CONFIG_DCB const struct qed_eth_dcbnl_ops *dcb; #endif + const struct qed_eth_ptp_ops *ptp; int (*fill_dev_info)(struct qed_dev *cdev, struct qed_dev_eth_info *info); @@ -255,6 +315,14 @@ struct qed_eth_ops { int (*tunn_config)(struct qed_dev *cdev, struct qed_tunn_params *params); + + int (*ntuple_filter_config)(struct qed_dev *cdev, void *cookie, + dma_addr_t mapping, u16 length, + u16 vport_id, u16 rx_queue_id, + bool add_filter); + + int (*configure_arfs_searcher)(struct qed_dev *cdev, + bool en_searcher); }; const struct qed_eth_ops *qed_get_eth_ops(void); diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h new file mode 100644 index 000000000000..1e015c50e6b8 --- /dev/null +++ b/include/linux/qed/qed_fcoe_if.h @@ -0,0 +1,150 @@ +#ifndef _QED_FCOE_IF_H +#define _QED_FCOE_IF_H +#include <linux/types.h> +#include <linux/qed/qed_if.h> +struct qed_fcoe_stats { + u64 fcoe_rx_byte_cnt; + u64 fcoe_rx_data_pkt_cnt; + u64 fcoe_rx_xfer_pkt_cnt; + u64 fcoe_rx_other_pkt_cnt; + u32 fcoe_silent_drop_pkt_cmdq_full_cnt; + u32 fcoe_silent_drop_pkt_rq_full_cnt; + u32 fcoe_silent_drop_pkt_crc_error_cnt; + u32 fcoe_silent_drop_pkt_task_invalid_cnt; + u32 fcoe_silent_drop_total_pkt_cnt; + + u64 fcoe_tx_byte_cnt; + u64 fcoe_tx_data_pkt_cnt; + u64 fcoe_tx_xfer_pkt_cnt; + u64 fcoe_tx_other_pkt_cnt; +}; + +struct qed_dev_fcoe_info { + struct qed_dev_info common; + + void __iomem *primary_dbq_rq_addr; + void __iomem *secondary_bdq_rq_addr; + + u64 wwpn; + u64 wwnn; + + u8 num_cqs; +}; + +struct qed_fcoe_params_offload { + dma_addr_t sq_pbl_addr; + dma_addr_t sq_curr_page_addr; + dma_addr_t sq_next_page_addr; + + u8 src_mac[ETH_ALEN]; + u8 dst_mac[ETH_ALEN]; + + u16 tx_max_fc_pay_len; + u16 e_d_tov_timer_val; + u16 rec_tov_timer_val; + u16 rx_max_fc_pay_len; + u16 vlan_tag; + + struct fc_addr_nw s_id; + u8 max_conc_seqs_c3; + struct fc_addr_nw d_id; + u8 flags; + u8 def_q_idx; +}; + +#define MAX_TID_BLOCKS_FCOE (512) +struct qed_fcoe_tid { + u32 size; /* In bytes per task */ + u32 num_tids_per_block; + u8 *blocks[MAX_TID_BLOCKS_FCOE]; +}; + +struct qed_fcoe_cb_ops { + struct qed_common_cb_ops common; + u32 (*get_login_failures)(void *cookie); +}; + +void qed_fcoe_set_pf_params(struct qed_dev *cdev, + struct qed_fcoe_pf_params *params); + +/** + * struct qed_fcoe_ops - qed FCoE operations. + * @common: common operations pointer + * @fill_dev_info: fills FCoE specific information + * @param cdev + * @param info + * @return 0 on sucesss, otherwise error value. + * @register_ops: register FCoE operations + * @param cdev + * @param ops - specified using qed_iscsi_cb_ops + * @param cookie - driver private + * @ll2: light L2 operations pointer + * @start: fcoe in FW + * @param cdev + * @param tasks - qed will fill information about tasks + * return 0 on success, otherwise error value. + * @stop: stops fcoe in FW + * @param cdev + * return 0 on success, otherwise error value. + * @acquire_conn: acquire a new fcoe connection + * @param cdev + * @param handle - qed will fill handle that should be + * used henceforth as identifier of the + * connection. + * @param p_doorbell - qed will fill the address of the + * doorbell. + * return 0 on sucesss, otherwise error value. + * @release_conn: release a previously acquired fcoe connection + * @param cdev + * @param handle - the connection handle. + * return 0 on success, otherwise error value. + * @offload_conn: configures an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * return 0 on success, otherwise error value. + * @destroy_conn: stops an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param terminate_params + * return 0 on success, otherwise error value. + * @get_stats: gets FCoE related statistics + * @param cdev + * @param stats - pointer to struck that would be filled + * we stats + * return 0 on success, error otherwise. + */ +struct qed_fcoe_ops { + const struct qed_common_ops *common; + + int (*fill_dev_info)(struct qed_dev *cdev, + struct qed_dev_fcoe_info *info); + + void (*register_ops)(struct qed_dev *cdev, + struct qed_fcoe_cb_ops *ops, void *cookie); + + const struct qed_ll2_ops *ll2; + + int (*start)(struct qed_dev *cdev, struct qed_fcoe_tid *tasks); + + int (*stop)(struct qed_dev *cdev); + + int (*acquire_conn)(struct qed_dev *cdev, + u32 *handle, + u32 *fw_cid, void __iomem **p_doorbell); + + int (*release_conn)(struct qed_dev *cdev, u32 handle); + + int (*offload_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_fcoe_params_offload *conn_info); + int (*destroy_conn)(struct qed_dev *cdev, + u32 handle, dma_addr_t terminate_params); + + int (*get_stats)(struct qed_dev *cdev, struct qed_fcoe_stats *stats); +}; + +const struct qed_fcoe_ops *qed_get_fcoe_ops(void); +void qed_put_fcoe_ops(void); +#endif diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 4b454f4f5b25..ef39c7f40ae6 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1,10 +1,33 @@ /* QLogic qed NIC Driver - * - * Copyright (c) 2015 QLogic Corporation - * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * Copyright (c) 2015-2017 QLogic Corporation + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef _QED_IF_H @@ -36,7 +59,6 @@ enum dcbx_protocol_type { #define QED_ROCE_PROTOCOL_INDEX (3) -#ifdef CONFIG_DCB #define QED_LLDP_CHASSIS_ID_STAT_LEN 4 #define QED_LLDP_PORT_ID_STAT_LEN 4 #define QED_DCBX_MAX_APP_PROTOCOL 32 @@ -122,6 +144,7 @@ struct qed_dcbx_operational_params { bool enabled; bool ieee; bool cee; + bool local; u32 err; }; @@ -132,7 +155,11 @@ struct qed_dcbx_get { struct qed_dcbx_remote_params remote; struct qed_dcbx_admin_params local; }; -#endif + +enum qed_nvm_images { + QED_NVM_IMAGE_ISCSI_CFG, + QED_NVM_IMAGE_FCOE_CFG, +}; enum qed_led_mode { QED_LED_MODE_OFF, @@ -157,6 +184,48 @@ struct qed_eth_pf_params { * to update_pf_params routine invoked before slowpath start */ u16 num_cons; + + /* per-VF number of CIDs */ + u8 num_vf_cons; +#define ETH_PF_PARAMS_VF_CONS_DEFAULT (32) + + /* To enable arfs, previous to HW-init a positive number needs to be + * set [as filters require allocated searcher ILT memory]. + * This will set the maximal number of configured steering-filters. + */ + u32 num_arfs_filters; +}; + +struct qed_fcoe_pf_params { + /* The following parameters are used during protocol-init */ + u64 glbl_q_params_addr; + u64 bdq_pbl_base_addr[2]; + + /* The following parameters are used during HW-init + * and these parameters need to be passed as arguments + * to update_pf_params routine invoked before slowpath start + */ + u16 num_cons; + u16 num_tasks; + + /* The following parameters are used during protocol-init */ + u16 sq_num_pbl_pages; + + u16 cq_num_entries; + u16 cmdq_num_entries; + u16 rq_buffer_log_size; + u16 mtu; + u16 dummy_icid; + u16 bdq_xoff_threshold[2]; + u16 bdq_xon_threshold[2]; + u16 rq_buffer_size; + u8 num_cqs; /* num of global CQs */ + u8 log_page_size; + u8 gl_rq_pi; + u8 gl_cmd_pi; + u8 debug_mode; + u8 is_target; + u8 bdq_pbl_num_entries[2]; }; /* Most of the the parameters below are described in the FW iSCSI / TCP HSI */ @@ -210,7 +279,6 @@ struct qed_rdma_pf_params { * the doorbell BAR). */ u32 min_dpis; /* number of requested DPIs */ - u32 num_mrs; /* number of requested memory regions */ u32 num_qps; /* number of requested Queue Pairs */ u32 num_srqs; /* number of requested SRQ */ u8 roce_edpm_mode; /* see QED_ROCE_EDPM_MODE_ENABLE */ @@ -222,6 +290,7 @@ struct qed_rdma_pf_params { struct qed_pf_params { struct qed_eth_pf_params eth_pf_params; + struct qed_fcoe_pf_params fcoe_pf_params; struct qed_iscsi_pf_params iscsi_pf_params; struct qed_rdma_pf_params rdma_pf_params; }; @@ -246,6 +315,11 @@ struct qed_sb_info { struct qed_dev *cdev; }; +enum qed_dev_type { + QED_DEV_TYPE_BB, + QED_DEV_TYPE_AH, +}; + struct qed_dev_info { unsigned long pci_mem_start; unsigned long pci_mem_end; @@ -263,6 +337,14 @@ struct qed_dev_info { /* MFW version */ u32 mfw_rev; +#define QED_MFW_VERSION_0_MASK 0x000000FF +#define QED_MFW_VERSION_0_OFFSET 0 +#define QED_MFW_VERSION_1_MASK 0x0000FF00 +#define QED_MFW_VERSION_1_OFFSET 8 +#define QED_MFW_VERSION_2_MASK 0x00FF0000 +#define QED_MFW_VERSION_2_OFFSET 16 +#define QED_MFW_VERSION_3_MASK 0xFF000000 +#define QED_MFW_VERSION_3_OFFSET 24 u32 flash_size; u8 mf_mode; @@ -271,6 +353,24 @@ struct qed_dev_info { u16 mtu; bool wol_support; + + /* MBI version */ + u32 mbi_version; +#define QED_MBI_VERSION_0_MASK 0x000000FF +#define QED_MBI_VERSION_0_OFFSET 0 +#define QED_MBI_VERSION_1_MASK 0x0000FF00 +#define QED_MBI_VERSION_1_OFFSET 8 +#define QED_MBI_VERSION_2_MASK 0x00FF0000 +#define QED_MBI_VERSION_2_OFFSET 16 + + enum qed_dev_type dev_type; + + /* Output parameters for qede */ + bool vxlan_enable; + bool gre_enable; + bool geneve_enable; + + u8 abs_pf_id; }; enum qed_sb_type { @@ -282,6 +382,7 @@ enum qed_sb_type { enum qed_protocol { QED_PROTOCOL_ETH, QED_PROTOCOL_ISCSI, + QED_PROTOCOL_FCOE, }; enum qed_link_mode_bits { @@ -366,8 +467,10 @@ struct qed_int_info { }; struct qed_common_cb_ops { + void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); + void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); }; struct qed_selftest_ops { @@ -428,9 +531,7 @@ struct qed_common_ops { int (*set_power_state)(struct qed_dev *cdev, pci_power_t state); - void (*set_id)(struct qed_dev *cdev, - char name[], - char ver_str[]); + void (*set_name) (struct qed_dev *cdev, char name[]); /* Client drivers need to make this call before slowpath_start. * PF params required for the call before slowpath_start is @@ -471,6 +572,10 @@ struct qed_common_ops { void (*simd_handler_clean)(struct qed_dev *cdev, int index); + int (*dbg_grc)(struct qed_dev *cdev, + void *buffer, u32 *num_dumped_bytes); + + int (*dbg_grc_size)(struct qed_dev *cdev); int (*dbg_all_data) (struct qed_dev *cdev, void *buffer); @@ -529,12 +634,26 @@ struct qed_common_ops { enum qed_chain_cnt_type cnt_type, u32 num_elems, size_t elem_size, - struct qed_chain *p_chain); + struct qed_chain *p_chain, + struct qed_chain_ext_pbl *ext_pbl); void (*chain_free)(struct qed_dev *cdev, struct qed_chain *p_chain); /** + * @brief nvm_get_image - reads an entire image from nvram + * + * @param cdev + * @param type - type of the request nvram image + * @param buf - preallocated buffer to fill with the image + * @param len - length of the allocated buffer + * + * @return 0 on success, error otherwise + */ + int (*nvm_get_image)(struct qed_dev *cdev, + enum qed_nvm_images type, u8 *buf, u16 len); + +/** * @brief get_coalesce - Get coalesce parameters in usec * * @param cdev @@ -556,7 +675,7 @@ struct qed_common_ops { * @return 0 on success, error otherwise. */ int (*set_coalesce)(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal, - u8 qid, u16 sb_id); + u16 qid, u16 sb_id); /** * @brief set_led - Configure LED mode @@ -621,11 +740,13 @@ struct qed_common_ops { (((value) >> (name ## _SHIFT)) & name ## _MASK) /* Debug print definitions */ -#define DP_ERR(cdev, fmt, ...) \ - pr_err("[%s:%d(%s)]" fmt, \ - __func__, __LINE__, \ - DP_NAME(cdev) ? DP_NAME(cdev) : "", \ - ## __VA_ARGS__) \ +#define DP_ERR(cdev, fmt, ...) \ + do { \ + pr_err("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + DP_NAME(cdev) ? DP_NAME(cdev) : "", \ + ## __VA_ARGS__); \ + } while (0) #define DP_NOTICE(cdev, fmt, ...) \ do { \ @@ -692,7 +813,7 @@ enum qed_mf_mode { QED_MF_NPAR, }; -struct qed_eth_stats { +struct qed_eth_stats_common { u64 no_buff_discards; u64 packet_too_big_discard; u64 ttl0_discard; @@ -724,11 +845,6 @@ struct qed_eth_stats { u64 rx_256_to_511_byte_packets; u64 rx_512_to_1023_byte_packets; u64 rx_1024_to_1518_byte_packets; - u64 rx_1519_to_1522_byte_packets; - u64 rx_1519_to_2047_byte_packets; - u64 rx_2048_to_4095_byte_packets; - u64 rx_4096_to_9216_byte_packets; - u64 rx_9217_to_16383_byte_packets; u64 rx_crc_errors; u64 rx_mac_crtl_frames; u64 rx_pause_frames; @@ -745,14 +861,8 @@ struct qed_eth_stats { u64 tx_256_to_511_byte_packets; u64 tx_512_to_1023_byte_packets; u64 tx_1024_to_1518_byte_packets; - u64 tx_1519_to_2047_byte_packets; - u64 tx_2048_to_4095_byte_packets; - u64 tx_4096_to_9216_byte_packets; - u64 tx_9217_to_16383_byte_packets; u64 tx_pause_frames; u64 tx_pfc_frames; - u64 tx_lpi_entry_count; - u64 tx_total_collisions; u64 brb_truncates; u64 brb_discards; u64 rx_mac_bytes; @@ -767,15 +877,49 @@ struct qed_eth_stats { u64 tx_mac_ctrl_frames; }; +struct qed_eth_stats_bb { + u64 rx_1519_to_1522_byte_packets; + u64 rx_1519_to_2047_byte_packets; + u64 rx_2048_to_4095_byte_packets; + u64 rx_4096_to_9216_byte_packets; + u64 rx_9217_to_16383_byte_packets; + u64 tx_1519_to_2047_byte_packets; + u64 tx_2048_to_4095_byte_packets; + u64 tx_4096_to_9216_byte_packets; + u64 tx_9217_to_16383_byte_packets; + u64 tx_lpi_entry_count; + u64 tx_total_collisions; +}; + +struct qed_eth_stats_ah { + u64 rx_1519_to_max_byte_packets; + u64 tx_1519_to_max_byte_packets; +}; + +struct qed_eth_stats { + struct qed_eth_stats_common common; + + union { + struct qed_eth_stats_bb bb; + struct qed_eth_stats_ah ah; + }; +}; + #define QED_SB_IDX 0x0002 #define RX_PI 0 #define TX_PI(tc) (RX_PI + 1 + tc) struct qed_sb_cnt_info { - int sb_cnt; - int sb_iov_cnt; - int sb_free_blk; + /* Original, current, and free SBs for PF */ + int orig; + int cnt; + int free_cnt; + + /* Original, current and free SBS for child VFs */ + int iov_orig; + int iov_cnt; + int free_cnt_iov; }; static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) diff --git a/include/linux/qed/qed_iov_if.h b/include/linux/qed/qed_iov_if.h index 5a4f8d0899e9..ac2e6a3199a3 100644 --- a/include/linux/qed/qed_iov_if.h +++ b/include/linux/qed/qed_iov_if.h @@ -1,9 +1,33 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef _QED_IOV_IF_H @@ -29,6 +53,8 @@ struct qed_iov_hv_ops { int (*set_rate) (struct qed_dev *cdev, int vfid, u32 min_rate, u32 max_rate); + + int (*set_trust) (struct qed_dev *cdev, int vfid, bool trust); }; #endif diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h index d27912480cb3..111e606a74c8 100644 --- a/include/linux/qed/qed_iscsi_if.h +++ b/include/linux/qed/qed_iscsi_if.h @@ -1,9 +1,33 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef _QED_ISCSI_IF_H @@ -43,6 +67,8 @@ struct qed_dev_iscsi_info { void __iomem *primary_dbq_rq_addr; void __iomem *secondary_bdq_rq_addr; + + u8 num_cqs; }; struct qed_iscsi_id_params { @@ -184,6 +210,11 @@ struct qed_iscsi_cb_ops { * @param stats - pointer to struck that would be filled * we stats * @return 0 on success, error otherwise. + * @change_mac Change MAC of interface + * @param cdev + * @param handle - the connection handle. + * @param mac - new MAC to configure. + * @return 0 on success, otherwise error value. */ struct qed_iscsi_ops { const struct qed_common_ops *common; @@ -222,6 +253,8 @@ struct qed_iscsi_ops { int (*get_stats)(struct qed_dev *cdev, struct qed_iscsi_stats *stats); + + int (*change_mac)(struct qed_dev *cdev, u32 handle, const u8 *mac); }; const struct qed_iscsi_ops *qed_get_iscsi_ops(void); diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index fd75c265dba3..dd7a3b86bb9e 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -1,10 +1,33 @@ /* QLogic qed NIC Driver + * Copyright (c) 2015-2017 QLogic Corporation * - * Copyright (c) 2015 QLogic Corporation + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef _QED_LL2_IF_H @@ -20,6 +43,36 @@ #include <linux/slab.h> #include <linux/qed/qed_if.h> +enum qed_ll2_conn_type { + QED_LL2_TYPE_FCOE, + QED_LL2_TYPE_ISCSI, + QED_LL2_TYPE_TEST, + QED_LL2_TYPE_OOO, + QED_LL2_TYPE_RESERVED2, + QED_LL2_TYPE_ROCE, + QED_LL2_TYPE_IWARP, + QED_LL2_TYPE_RESERVED3, + MAX_QED_LL2_RX_CONN_TYPE +}; + +enum qed_ll2_roce_flavor_type { + QED_LL2_ROCE, + QED_LL2_RROCE, + MAX_QED_LL2_ROCE_FLAVOR_TYPE +}; + +enum qed_ll2_tx_dest { + QED_LL2_TX_DEST_NW, /* Light L2 TX Destination to the Network */ + QED_LL2_TX_DEST_LB, /* Light L2 TX Destination to the Loopback */ + QED_LL2_TX_DEST_MAX +}; + +enum qed_ll2_error_handle { + QED_LL2_DROP_PACKET, + QED_LL2_DO_NOTHING, + QED_LL2_ASSERT, +}; + struct qed_ll2_stats { u64 gsi_invalid_hdr; u64 gsi_invalid_pkt_length; @@ -44,6 +97,105 @@ struct qed_ll2_stats { u64 sent_bcast_pkts; }; +struct qed_ll2_comp_rx_data { + void *cookie; + dma_addr_t rx_buf_addr; + u16 parse_flags; + u16 vlan; + bool b_last_packet; + u8 connection_handle; + + union { + u16 packet_length; + u16 data_length; + } length; + + u32 opaque_data_0; + u32 opaque_data_1; + + /* GSI only */ + u32 gid_dst[4]; + u16 qp_id; + + union { + u8 placement_offset; + u8 data_length_error; + } u; +}; + +typedef +void (*qed_ll2_complete_rx_packet_cb)(void *cxt, + struct qed_ll2_comp_rx_data *data); + +typedef +void (*qed_ll2_release_rx_packet_cb)(void *cxt, + u8 connection_handle, + void *cookie, + dma_addr_t rx_buf_addr, + bool b_last_packet); + +typedef +void (*qed_ll2_complete_tx_packet_cb)(void *cxt, + u8 connection_handle, + void *cookie, + dma_addr_t first_frag_addr, + bool b_last_fragment, + bool b_last_packet); + +typedef +void (*qed_ll2_release_tx_packet_cb)(void *cxt, + u8 connection_handle, + void *cookie, + dma_addr_t first_frag_addr, + bool b_last_fragment, bool b_last_packet); + +struct qed_ll2_cbs { + qed_ll2_complete_rx_packet_cb rx_comp_cb; + qed_ll2_release_rx_packet_cb rx_release_cb; + qed_ll2_complete_tx_packet_cb tx_comp_cb; + qed_ll2_release_tx_packet_cb tx_release_cb; + void *cookie; +}; + +struct qed_ll2_acquire_data_inputs { + enum qed_ll2_conn_type conn_type; + u16 mtu; + u16 rx_num_desc; + u16 rx_num_ooo_buffers; + u8 rx_drop_ttl0_flg; + u8 rx_vlan_removal_en; + u16 tx_num_desc; + u8 tx_max_bds_per_packet; + u8 tx_tc; + enum qed_ll2_tx_dest tx_dest; + enum qed_ll2_error_handle ai_err_packet_too_big; + enum qed_ll2_error_handle ai_err_no_buf; + u8 gsi_enable; +}; + +struct qed_ll2_acquire_data { + struct qed_ll2_acquire_data_inputs input; + const struct qed_ll2_cbs *cbs; + + /* Output container for LL2 connection's handle */ + u8 *p_connection_handle; +}; + +struct qed_ll2_tx_pkt_info { + void *cookie; + dma_addr_t first_frag; + enum qed_ll2_tx_dest tx_dest; + enum qed_ll2_roce_flavor_type qed_roce_flavor; + u16 vlan; + u16 l4_hdr_offset_w; /* from start of packet */ + u16 first_frag_len; + u8 num_of_bds; + u8 bd_flags; + bool enable_ip_cksum; + bool enable_l4_cksum; + bool calc_ip_len; +}; + #define QED_LL2_UNUSED_HANDLE (0xff) struct qed_ll2_cb_ops { diff --git a/include/linux/qed/qed_roce_if.h b/include/linux/qed/qed_rdma_if.h index 53047d3fa678..4dd72ba210f5 100644 --- a/include/linux/qed/qed_roce_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -1,5 +1,5 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015-2016 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -29,13 +29,11 @@ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ -#ifndef _QED_ROCE_IF_H -#define _QED_ROCE_IF_H +#ifndef _QED_RDMA_IF_H +#define _QED_RDMA_IF_H #include <linux/types.h> #include <linux/delay.h> #include <linux/list.h> -#include <linux/mutex.h> -#include <linux/pci.h> #include <linux/slab.h> #include <linux/qed/qed_if.h> #include <linux/qed/qed_ll2_if.h> @@ -240,6 +238,7 @@ struct qed_rdma_add_user_out_params { u64 dpi_addr; u64 dpi_phys_addr; u32 dpi_size; + u16 wid_count; }; enum roce_mode { @@ -471,6 +470,101 @@ struct qed_rdma_counters_out_params { #define QED_ROCE_TX_HEAD_FAILURE (1) #define QED_ROCE_TX_FRAG_FAILURE (2) +enum qed_iwarp_event_type { + QED_IWARP_EVENT_MPA_REQUEST, /* Passive side request received */ + QED_IWARP_EVENT_PASSIVE_COMPLETE, /* ack on mpa response */ + QED_IWARP_EVENT_ACTIVE_COMPLETE, /* Active side reply received */ + QED_IWARP_EVENT_DISCONNECT, + QED_IWARP_EVENT_CLOSE, + QED_IWARP_EVENT_IRQ_FULL, + QED_IWARP_EVENT_RQ_EMPTY, + QED_IWARP_EVENT_LLP_TIMEOUT, + QED_IWARP_EVENT_REMOTE_PROTECTION_ERROR, + QED_IWARP_EVENT_CQ_OVERFLOW, + QED_IWARP_EVENT_QP_CATASTROPHIC, + QED_IWARP_EVENT_ACTIVE_MPA_REPLY, + QED_IWARP_EVENT_LOCAL_ACCESS_ERROR, + QED_IWARP_EVENT_REMOTE_OPERATION_ERROR, + QED_IWARP_EVENT_TERMINATE_RECEIVED +}; + +enum qed_tcp_ip_version { + QED_TCP_IPV4, + QED_TCP_IPV6, +}; + +struct qed_iwarp_cm_info { + enum qed_tcp_ip_version ip_version; + u32 remote_ip[4]; + u32 local_ip[4]; + u16 remote_port; + u16 local_port; + u16 vlan; + u8 ord; + u8 ird; + u16 private_data_len; + const void *private_data; +}; + +struct qed_iwarp_cm_event_params { + enum qed_iwarp_event_type event; + const struct qed_iwarp_cm_info *cm_info; + void *ep_context; /* To be passed to accept call */ + int status; +}; + +typedef int (*iwarp_event_handler) (void *context, + struct qed_iwarp_cm_event_params *event); + +struct qed_iwarp_connect_in { + iwarp_event_handler event_cb; + void *cb_context; + struct qed_rdma_qp *qp; + struct qed_iwarp_cm_info cm_info; + u16 mss; + u8 remote_mac_addr[ETH_ALEN]; + u8 local_mac_addr[ETH_ALEN]; +}; + +struct qed_iwarp_connect_out { + void *ep_context; +}; + +struct qed_iwarp_listen_in { + iwarp_event_handler event_cb; + void *cb_context; /* passed to event_cb */ + u32 max_backlog; + enum qed_tcp_ip_version ip_version; + u32 ip_addr[4]; + u16 port; + u16 vlan; +}; + +struct qed_iwarp_listen_out { + void *handle; +}; + +struct qed_iwarp_accept_in { + void *ep_context; + void *cb_context; + struct qed_rdma_qp *qp; + const void *private_data; + u16 private_data_len; + u8 ord; + u8 ird; +}; + +struct qed_iwarp_reject_in { + void *ep_context; + void *cb_context; + const void *private_data; + u16 private_data_len; +}; + +struct qed_iwarp_send_rtr_in { + void *ep_context; +}; + struct qed_roce_ll2_header { void *vaddr; dma_addr_t baddr; @@ -490,49 +584,15 @@ struct qed_roce_ll2_packet { enum qed_roce_ll2_tx_dest tx_dest; }; -struct qed_roce_ll2_tx_params { - int reserved; -}; - -struct qed_roce_ll2_rx_params { - u16 vlan_id; - u8 smac[ETH_ALEN]; - int rc; -}; - -struct qed_roce_ll2_cbs { - void (*tx_cb)(void *pdev, struct qed_roce_ll2_packet *pkt); - - void (*rx_cb)(void *pdev, struct qed_roce_ll2_packet *pkt, - struct qed_roce_ll2_rx_params *params); -}; - -struct qed_roce_ll2_params { - u16 max_rx_buffers; - u16 max_tx_buffers; - u16 mtu; - u8 mac_address[ETH_ALEN]; - struct qed_roce_ll2_cbs cbs; - void *cb_cookie; -}; - -struct qed_roce_ll2_info { - u8 handle; - struct qed_roce_ll2_cbs cbs; - u8 mac_address[ETH_ALEN]; - void *cb_cookie; - - /* Lock to protect ll2 */ - struct mutex lock; -}; - enum qed_rdma_type { QED_RDMA_TYPE_ROCE, + QED_RDMA_TYPE_IWARP }; struct qed_dev_rdma_info { struct qed_dev_info common; enum qed_rdma_type rdma_type; + u8 user_dpm_enabled; }; struct qed_rdma_ops { @@ -577,26 +637,58 @@ struct qed_rdma_ops { int (*rdma_query_qp)(void *rdma_cxt, struct qed_rdma_qp *qp, struct qed_rdma_query_qp_out_params *oparams); int (*rdma_destroy_qp)(void *rdma_cxt, struct qed_rdma_qp *qp); + int (*rdma_register_tid)(void *rdma_cxt, struct qed_rdma_register_tid_in_params *iparams); + int (*rdma_deregister_tid)(void *rdma_cxt, u32 itid); int (*rdma_alloc_tid)(void *rdma_cxt, u32 *itid); void (*rdma_free_tid)(void *rdma_cxt, u32 itid); - int (*roce_ll2_start)(struct qed_dev *cdev, - struct qed_roce_ll2_params *params); - int (*roce_ll2_stop)(struct qed_dev *cdev); - int (*roce_ll2_tx)(struct qed_dev *cdev, - struct qed_roce_ll2_packet *packet, - struct qed_roce_ll2_tx_params *params); - int (*roce_ll2_post_rx_buffer)(struct qed_dev *cdev, - struct qed_roce_ll2_buffer *buf, - u64 cookie, u8 notify_fw); - int (*roce_ll2_set_mac_filter)(struct qed_dev *cdev, - u8 *old_mac_address, - u8 *new_mac_address); - int (*roce_ll2_stats)(struct qed_dev *cdev, - struct qed_ll2_stats *stats); + + int (*ll2_acquire_connection)(void *rdma_cxt, + struct qed_ll2_acquire_data *data); + + int (*ll2_establish_connection)(void *rdma_cxt, u8 connection_handle); + int (*ll2_terminate_connection)(void *rdma_cxt, u8 connection_handle); + void (*ll2_release_connection)(void *rdma_cxt, u8 connection_handle); + + int (*ll2_prepare_tx_packet)(void *rdma_cxt, + u8 connection_handle, + struct qed_ll2_tx_pkt_info *pkt, + bool notify_fw); + + int (*ll2_set_fragment_of_tx_packet)(void *rdma_cxt, + u8 connection_handle, + dma_addr_t addr, + u16 nbytes); + int (*ll2_post_rx_buffer)(void *rdma_cxt, u8 connection_handle, + dma_addr_t addr, u16 buf_len, void *cookie, + u8 notify_fw); + int (*ll2_get_stats)(void *rdma_cxt, + u8 connection_handle, + struct qed_ll2_stats *p_stats); + int (*ll2_set_mac_filter)(struct qed_dev *cdev, + u8 *old_mac_address, u8 *new_mac_address); + + int (*iwarp_connect)(void *rdma_cxt, + struct qed_iwarp_connect_in *iparams, + struct qed_iwarp_connect_out *oparams); + + int (*iwarp_create_listen)(void *rdma_cxt, + struct qed_iwarp_listen_in *iparams, + struct qed_iwarp_listen_out *oparams); + + int (*iwarp_accept)(void *rdma_cxt, + struct qed_iwarp_accept_in *iparams); + + int (*iwarp_reject)(void *rdma_cxt, + struct qed_iwarp_reject_in *iparams); + + int (*iwarp_destroy_listen)(void *rdma_cxt, void *handle); + + int (*iwarp_send_rtr)(void *rdma_cxt, + struct qed_iwarp_send_rtr_in *iparams); }; const struct qed_rdma_ops *qed_get_rdma_ops(void); diff --git a/include/linux/qed/qede_roce.h b/include/linux/qed/qede_rdma.h index f48d64b0e2fb..9904617a9730 100644 --- a/include/linux/qed/qede_roce.h +++ b/include/linux/qed/qede_rdma.h @@ -1,5 +1,5 @@ /* QLogic qedr NIC Driver - * Copyright (c) 2015-2016 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -32,22 +32,27 @@ #ifndef QEDE_ROCE_H #define QEDE_ROCE_H +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/types.h> +#include <linux/workqueue.h> + struct qedr_dev; struct qed_dev; struct qede_dev; -enum qede_roce_event { +enum qede_rdma_event { QEDE_UP, QEDE_DOWN, QEDE_CHANGE_ADDR, QEDE_CLOSE }; -struct qede_roce_event_work { +struct qede_rdma_event_work { struct list_head list; struct work_struct work; void *ptr; - enum qede_roce_event event; + enum qede_rdma_event event; }; struct qedr_driver { @@ -57,32 +62,33 @@ struct qedr_driver { struct net_device *); void (*remove)(struct qedr_dev *); - void (*notify)(struct qedr_dev *, enum qede_roce_event); + void (*notify)(struct qedr_dev *, enum qede_rdma_event); }; -/* APIs for RoCE driver to register callback handlers, +/* APIs for RDMA driver to register callback handlers, * which will be invoked when device is added, removed, ifup, ifdown */ -int qede_roce_register_driver(struct qedr_driver *drv); -void qede_roce_unregister_driver(struct qedr_driver *drv); +int qede_rdma_register_driver(struct qedr_driver *drv); +void qede_rdma_unregister_driver(struct qedr_driver *drv); -bool qede_roce_supported(struct qede_dev *dev); +bool qede_rdma_supported(struct qede_dev *dev); #if IS_ENABLED(CONFIG_QED_RDMA) -int qede_roce_dev_add(struct qede_dev *dev); -void qede_roce_dev_event_open(struct qede_dev *dev); -void qede_roce_dev_event_close(struct qede_dev *dev); -void qede_roce_dev_remove(struct qede_dev *dev); -void qede_roce_event_changeaddr(struct qede_dev *qedr); +int qede_rdma_dev_add(struct qede_dev *dev); +void qede_rdma_dev_event_open(struct qede_dev *dev); +void qede_rdma_dev_event_close(struct qede_dev *dev); +void qede_rdma_dev_remove(struct qede_dev *dev); +void qede_rdma_event_changeaddr(struct qede_dev *edr); + #else -static inline int qede_roce_dev_add(struct qede_dev *dev) +static inline int qede_rdma_dev_add(struct qede_dev *dev) { return 0; } -static inline void qede_roce_dev_event_open(struct qede_dev *dev) {} -static inline void qede_roce_dev_event_close(struct qede_dev *dev) {} -static inline void qede_roce_dev_remove(struct qede_dev *dev) {} -static inline void qede_roce_event_changeaddr(struct qede_dev *qedr) {} +static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {} +static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {} +static inline void qede_rdma_dev_remove(struct qede_dev *dev) {} +static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {} #endif #endif diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h index 7663725faa94..a9b3050f469c 100644 --- a/include/linux/qed/rdma_common.h +++ b/include/linux/qed/rdma_common.h @@ -1,9 +1,33 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef __RDMA_COMMON__ @@ -18,7 +42,7 @@ #define RDMA_MAX_SGE_PER_SQ_WQE (4) #define RDMA_MAX_SGE_PER_RQ_WQE (4) -#define RDMA_MAX_DATA_SIZE_IN_WQE (0x7FFFFFFF) +#define RDMA_MAX_DATA_SIZE_IN_WQE (0x80000000) #define RDMA_REQ_RD_ATOMIC_ELM_SIZE (0x50) #define RDMA_RESP_RD_ATOMIC_ELM_SIZE (0x20) @@ -28,7 +52,8 @@ #define RDMA_MAX_PDS (64 * 1024) #define RDMA_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS -#define RDMA_NUM_STATISTIC_COUNTERS_BB MAX_NUM_VPORTS_BB +#define RDMA_NUM_STATISTIC_COUNTERS_K2 MAX_NUM_VPORTS_K2 +#define RDMA_NUM_STATISTIC_COUNTERS_BB MAX_NUM_VPORTS_BB #define RDMA_TASK_TYPE (PROTOCOLID_ROCE) diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h index 2eeaf3dc6646..fe6a33e45977 100644 --- a/include/linux/qed/roce_common.h +++ b/include/linux/qed/roce_common.h @@ -1,9 +1,33 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef __ROCE_COMMON__ @@ -13,5 +37,24 @@ #define ROCE_REQ_MAX_SINGLE_SQ_WQE_SIZE (288) #define ROCE_MAX_QPS (32 * 1024) +#define ROCE_DCQCN_NP_MAX_QPS (64) +#define ROCE_DCQCN_RP_MAX_QPS (64) + +enum roce_async_events_type { + ROCE_ASYNC_EVENT_NONE = 0, + ROCE_ASYNC_EVENT_COMM_EST = 1, + ROCE_ASYNC_EVENT_SQ_DRAINED, + ROCE_ASYNC_EVENT_SRQ_LIMIT, + ROCE_ASYNC_EVENT_LAST_WQE_REACHED, + ROCE_ASYNC_EVENT_CQ_ERR, + ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR, + ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR, + ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR, + ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR, + ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR, + ROCE_ASYNC_EVENT_SRQ_EMPTY, + ROCE_ASYNC_EVENT_DESTROY_QP_DONE, + MAX_ROCE_ASYNC_EVENTS_TYPE +}; #endif /* __ROCE_COMMON__ */ diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h index 3b8e1efd9bc2..08df82a096b6 100644 --- a/include/linux/qed/storage_common.h +++ b/include/linux/qed/storage_common.h @@ -1,9 +1,33 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef __STORAGE_COMMON__ @@ -16,6 +40,8 @@ #define BDQ_ID_IMM_DATA (1) #define BDQ_NUM_IDS (2) +#define SCSI_NUM_SGES_SLOW_SGL_THR 8 + #define BDQ_MAX_EXTERNAL_RING_SIZE (1 << 15) struct scsi_bd { @@ -28,6 +54,16 @@ struct scsi_bdq_ram_drv_data { __le16 reserved0[3]; }; +struct scsi_sge { + struct regpair sge_addr; + __le32 sge_len; + __le32 reserved; +}; + +struct scsi_cached_sges { + struct scsi_sge sge[4]; +}; + struct scsi_drv_cmdq { __le16 cmdq_cons; __le16 reserved0; @@ -75,11 +111,19 @@ struct scsi_ram_per_bdq_resource_drv_data { struct scsi_bdq_ram_drv_data drv_data_per_bdq_id[BDQ_NUM_IDS]; }; -struct scsi_sge { - struct regpair sge_addr; - __le16 sge_len; - __le16 reserved0; - __le32 reserved1; +enum scsi_sgl_mode { + SCSI_TX_SLOW_SGL, + SCSI_FAST_SGL, + MAX_SCSI_SGL_MODE +}; + +struct scsi_sgl_params { + struct regpair sgl_addr; + __le32 sgl_total_length; + __le32 sge_offset; + __le16 sgl_num_sges; + u8 sgl_index; + u8 reserved; }; struct scsi_terminate_extra_params { diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h index dc3889d1bbe6..dbf7a43c3e1f 100644 --- a/include/linux/qed/tcp_common.h +++ b/include/linux/qed/tcp_common.h @@ -1,9 +1,33 @@ /* QLogic qed NIC Driver - * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2015-2017 QLogic Corporation * - * This software is available under the terms of the GNU General Public License - * (GPL) Version 2, available from the file COPYING in the main directory of - * this source tree. + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and /or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. */ #ifndef __TCP_COMMON__ @@ -87,7 +111,6 @@ struct tcp_offload_params { __le32 snd_wnd; __le32 rcv_wnd; __le32 snd_wl1; - __le32 ts_time; __le32 ts_recent; __le32 ts_recent_age; __le32 total_rt; @@ -98,7 +121,7 @@ struct tcp_offload_params { u8 ka_probe_cnt; u8 rt_cnt; __le16 rtt_var; - __le16 reserved2; + __le16 fw_internal; __le32 ka_timeout; __le32 ka_interval; __le32 max_rt_time; @@ -106,7 +129,7 @@ struct tcp_offload_params { u8 snd_wnd_scale; u8 ack_frequency; __le16 da_timeout_value; - __le32 ts_ticks_per_second; + __le32 reserved3[2]; }; struct tcp_offload_params_opt2 { @@ -149,6 +172,7 @@ enum tcp_seg_placement_event { TCP_EVENT_ADD_ISLE_RIGHT, TCP_EVENT_ADD_ISLE_LEFT, TCP_EVENT_JOIN, + TCP_EVENT_DELETE_ISLES, TCP_EVENT_NOP, MAX_TCP_SEG_PLACEMENT_EVENT }; diff --git a/include/linux/quota.h b/include/linux/quota.h index 3434eef2a5aa..bfd077ca6ac3 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -332,6 +332,8 @@ struct dquot_operations { * quota code only */ qsize_t *(*get_reserved_space) (struct inode *); int (*get_projid) (struct inode *, kprojid_t *);/* Get project ID */ + /* Get number of inodes that were charged for a given inode */ + int (*get_inode_usage) (struct inode *, qsize_t *); /* Get next ID with active quota structure */ int (*get_next_id) (struct super_block *sb, struct kqid *qid); }; diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 799a63d0e1a8..dda22f45fc1b 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -44,6 +44,7 @@ void inode_sub_rsv_space(struct inode *inode, qsize_t number); void inode_reclaim_rsv_space(struct inode *inode, qsize_t number); int dquot_initialize(struct inode *inode); +bool dquot_initialize_needed(struct inode *inode); void dquot_drop(struct inode *inode); struct dquot *dqget(struct super_block *sb, struct kqid qid); static inline struct dquot *dqgrab(struct dquot *dquot) @@ -162,7 +163,6 @@ static inline bool sb_has_quota_active(struct super_block *sb, int type) * Operations supported for diskquotas. */ extern const struct dquot_operations dquot_operations; -extern const struct quotactl_ops dquot_quotactl_ops; extern const struct quotactl_ops dquot_quotactl_sysfile_ops; #else @@ -208,6 +208,11 @@ static inline int dquot_initialize(struct inode *inode) return 0; } +static inline bool dquot_initialize_needed(struct inode *inode) +{ + return false; +} + static inline void dquot_drop(struct inode *inode) { } diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 52bda854593b..3e5735064b71 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -22,11 +22,13 @@ #define _LINUX_RADIX_TREE_H #include <linux/bitops.h> -#include <linux/preempt.h> -#include <linux/types.h> #include <linux/bug.h> #include <linux/kernel.h> +#include <linux/list.h> +#include <linux/preempt.h> #include <linux/rcupdate.h> +#include <linux/spinlock.h> +#include <linux/types.h> /* * The bottom two bits of the slot determine how the remaining bits in the @@ -94,7 +96,7 @@ struct radix_tree_node { unsigned char count; /* Total entry count */ unsigned char exceptional; /* Exceptional entry count */ struct radix_tree_node *parent; /* Used when ascending tree */ - void *private_data; /* For tree user */ + struct radix_tree_root *root; /* The tree we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ @@ -103,7 +105,10 @@ struct radix_tree_node { unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -/* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */ +/* The top bits of gfp_mask are used to store the root tags and the IDR flag */ +#define ROOT_IS_IDR ((__force gfp_t)(1 << __GFP_BITS_SHIFT)) +#define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT + 1) + struct radix_tree_root { gfp_t gfp_mask; struct radix_tree_node __rcu *rnode; @@ -123,7 +128,7 @@ do { \ (root)->rnode = NULL; \ } while (0) -static inline bool radix_tree_empty(struct radix_tree_root *root) +static inline bool radix_tree_empty(const struct radix_tree_root *root) { return root->rnode == NULL; } @@ -216,10 +221,8 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter) */ /** - * radix_tree_deref_slot - dereference a slot - * @pslot: pointer to slot, returned by radix_tree_lookup_slot - * Returns: item that was stored in that slot with any direct pointer flag - * removed. + * radix_tree_deref_slot - dereference a slot + * @slot: slot pointer, returned by radix_tree_lookup_slot * * For use with radix_tree_lookup_slot(). Caller must hold tree at least read * locked across slot lookup and dereference. Not required if write lock is @@ -227,26 +230,27 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter) * * radix_tree_deref_retry must be used to confirm validity of the pointer if * only the read lock is held. + * + * Return: entry stored in that slot. */ -static inline void *radix_tree_deref_slot(void **pslot) +static inline void *radix_tree_deref_slot(void __rcu **slot) { - return rcu_dereference(*pslot); + return rcu_dereference(*slot); } /** - * radix_tree_deref_slot_protected - dereference a slot without RCU lock but with tree lock held - * @pslot: pointer to slot, returned by radix_tree_lookup_slot - * Returns: item that was stored in that slot with any direct pointer flag - * removed. - * - * Similar to radix_tree_deref_slot but only used during migration when a pages - * mapping is being moved. The caller does not hold the RCU read lock but it - * must hold the tree lock to prevent parallel updates. + * radix_tree_deref_slot_protected - dereference a slot with tree lock held + * @slot: slot pointer, returned by radix_tree_lookup_slot + * + * Similar to radix_tree_deref_slot. The caller does not hold the RCU read + * lock but it must hold the tree lock to prevent parallel updates. + * + * Return: entry stored in that slot. */ -static inline void *radix_tree_deref_slot_protected(void **pslot, +static inline void *radix_tree_deref_slot_protected(void __rcu **slot, spinlock_t *treelock) { - return rcu_dereference_protected(*pslot, lockdep_is_held(treelock)); + return rcu_dereference_protected(*slot, lockdep_is_held(treelock)); } /** @@ -282,9 +286,9 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_create(struct radix_tree_root *root, unsigned long index, +int __radix_tree_create(struct radix_tree_root *, unsigned long index, unsigned order, struct radix_tree_node **nodep, - void ***slotp); + void __rcu ***slotp); int __radix_tree_insert(struct radix_tree_root *, unsigned long index, unsigned order, void *); static inline int radix_tree_insert(struct radix_tree_root *root, @@ -292,55 +296,56 @@ static inline int radix_tree_insert(struct radix_tree_root *root, { return __radix_tree_insert(root, index, 0, entry); } -void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, - struct radix_tree_node **nodep, void ***slotp); -void *radix_tree_lookup(struct radix_tree_root *, unsigned long); -void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); +void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, + struct radix_tree_node **nodep, void __rcu ***slotp); +void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); +void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, + unsigned long index); typedef void (*radix_tree_update_node_t)(struct radix_tree_node *, void *); -void __radix_tree_replace(struct radix_tree_root *root, - struct radix_tree_node *node, - void **slot, void *item, +void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, + void __rcu **slot, void *entry, radix_tree_update_node_t update_node, void *private); void radix_tree_iter_replace(struct radix_tree_root *, - const struct radix_tree_iter *, void **slot, void *item); -void radix_tree_replace_slot(struct radix_tree_root *root, - void **slot, void *item); -void __radix_tree_delete_node(struct radix_tree_root *root, - struct radix_tree_node *node, + const struct radix_tree_iter *, void __rcu **slot, void *entry); +void radix_tree_replace_slot(struct radix_tree_root *, + void __rcu **slot, void *entry); +void __radix_tree_delete_node(struct radix_tree_root *, + struct radix_tree_node *, radix_tree_update_node_t update_node, void *private); +void radix_tree_iter_delete(struct radix_tree_root *, + struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); -void radix_tree_clear_tags(struct radix_tree_root *root, - struct radix_tree_node *node, - void **slot); -unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, +void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *, + void __rcu **slot); +unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); -unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, - void ***results, unsigned long *indices, +unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *, + void __rcu ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); void radix_tree_init(void); -void *radix_tree_tag_set(struct radix_tree_root *root, +void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); -void *radix_tree_tag_clear(struct radix_tree_root *root, +void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); -int radix_tree_tag_get(struct radix_tree_root *root, +int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); -void radix_tree_iter_tag_set(struct radix_tree_root *root, +void radix_tree_iter_tag_set(struct radix_tree_root *, + const struct radix_tree_iter *iter, unsigned int tag); +void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); -unsigned int -radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, - unsigned long first_index, unsigned int max_items, - unsigned int tag); -unsigned int -radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, - unsigned long first_index, unsigned int max_items, - unsigned int tag); -int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); +unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, + void **results, unsigned long first_index, + unsigned int max_items, unsigned int tag); +unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *, + void __rcu ***results, unsigned long first_index, + unsigned int max_items, unsigned int tag); +int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { @@ -352,10 +357,14 @@ int radix_tree_split(struct radix_tree_root *, unsigned long index, unsigned new_order); int radix_tree_join(struct radix_tree_root *, unsigned long index, unsigned new_order, void *); +void __rcu **idr_get_free(struct radix_tree_root *, struct radix_tree_iter *, + gfp_t, int end); -#define RADIX_TREE_ITER_TAG_MASK 0x00FF /* tag index in lower byte */ -#define RADIX_TREE_ITER_TAGGED 0x0100 /* lookup tagged slots */ -#define RADIX_TREE_ITER_CONTIG 0x0200 /* stop at first hole */ +enum { + RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ + RADIX_TREE_ITER_TAGGED = 0x10, /* lookup tagged slots */ + RADIX_TREE_ITER_CONTIG = 0x20, /* stop at first hole */ +}; /** * radix_tree_iter_init - initialize radix tree iterator @@ -364,7 +373,7 @@ int radix_tree_join(struct radix_tree_root *, unsigned long index, * @start: iteration starting index * Returns: NULL */ -static __always_inline void ** +static __always_inline void __rcu ** radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) { /* @@ -393,10 +402,46 @@ radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) * Also it fills @iter with data about chunk: position in the tree (index), * its end (next_index), and constructs a bit mask for tagged iterating (tags). */ -void **radix_tree_next_chunk(struct radix_tree_root *root, +void __rcu **radix_tree_next_chunk(const struct radix_tree_root *, struct radix_tree_iter *iter, unsigned flags); /** + * radix_tree_iter_lookup - look up an index in the radix tree + * @root: radix tree root + * @iter: iterator state + * @index: key to look up + * + * If @index is present in the radix tree, this function returns the slot + * containing it and updates @iter to describe the entry. If @index is not + * present, it returns NULL. + */ +static inline void __rcu ** +radix_tree_iter_lookup(const struct radix_tree_root *root, + struct radix_tree_iter *iter, unsigned long index) +{ + radix_tree_iter_init(iter, index); + return radix_tree_next_chunk(root, iter, RADIX_TREE_ITER_CONTIG); +} + +/** + * radix_tree_iter_find - find a present entry + * @root: radix tree root + * @iter: iterator state + * @index: start location + * + * This function returns the slot containing the entry with the lowest index + * which is at least @index. If @index is larger than any present entry, this + * function returns NULL. The @iter is updated to describe the entry found. + */ +static inline void __rcu ** +radix_tree_iter_find(const struct radix_tree_root *root, + struct radix_tree_iter *iter, unsigned long index) +{ + radix_tree_iter_init(iter, index); + return radix_tree_next_chunk(root, iter, 0); +} + +/** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * @@ -406,7 +451,7 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, * and continue the iteration. */ static inline __must_check -void **radix_tree_iter_retry(struct radix_tree_iter *iter) +void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; iter->tags = 0; @@ -429,7 +474,7 @@ __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) * have been invalidated by an insertion or deletion. Call this function * before releasing the lock to continue the iteration from the next index. */ -void **__must_check radix_tree_iter_resume(void **slot, +void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter); /** @@ -445,11 +490,11 @@ radix_tree_chunk_size(struct radix_tree_iter *iter) } #ifdef CONFIG_RADIX_TREE_MULTIORDER -void ** __radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, - unsigned flags); +void __rcu **__radix_tree_next_slot(void __rcu **slot, + struct radix_tree_iter *iter, unsigned flags); #else /* Can't happen without sibling entries, but the compiler can't tell that */ -static inline void ** __radix_tree_next_slot(void **slot, +static inline void __rcu **__radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { return slot; @@ -475,8 +520,8 @@ static inline void ** __radix_tree_next_slot(void **slot, * b) we are doing non-tagged iteration, and iter->index and iter->next_index * have been set up so that radix_tree_chunk_size() returns 1 or 0. */ -static __always_inline void ** -radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) +static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, + struct radix_tree_iter *iter, unsigned flags) { if (flags & RADIX_TREE_ITER_TAGGED) { iter->tags >>= 1; @@ -514,7 +559,7 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) return NULL; found: - if (unlikely(radix_tree_is_internal_node(*slot))) + if (unlikely(radix_tree_is_internal_node(rcu_dereference_raw(*slot)))) return __radix_tree_next_slot(slot, iter, flags); return slot; } diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 4d57bbaaa1bf..30f945329818 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -142,6 +142,7 @@ int raid6_select_algo(void); extern const u8 raid6_gfmul[256][256] __attribute__((aligned(256))); extern const u8 raid6_vgfmul[256][32] __attribute__((aligned(256))); extern const u8 raid6_gfexp[256] __attribute__((aligned(256))); +extern const u8 raid6_gflog[256] __attribute__((aligned(256))); extern const u8 raid6_gfinv[256] __attribute__((aligned(256))); extern const u8 raid6_gfexi[256] __attribute__((aligned(256))); diff --git a/include/linux/random.h b/include/linux/random.h index 7bd2403e4fef..eafea6a09361 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,17 +34,76 @@ extern void add_input_randomness(unsigned int type, unsigned int code, extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; extern void get_random_bytes(void *buf, int nbytes); +extern int wait_for_random_bytes(void); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); extern void get_random_bytes_arch(void *buf, int nbytes); -extern int random_int_secret_init(void); #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; #endif -unsigned int get_random_int(void); -unsigned long get_random_long(void); +u32 get_random_u32(void); +u64 get_random_u64(void); +static inline unsigned int get_random_int(void) +{ + return get_random_u32(); +} +static inline unsigned long get_random_long(void) +{ +#if BITS_PER_LONG == 64 + return get_random_u64(); +#else + return get_random_u32(); +#endif +} + +/* + * On 64-bit architectures, protect against non-terminated C string overflows + * by zeroing out the first byte of the canary; this leaves 56 bits of entropy. + */ +#ifdef CONFIG_64BIT +# ifdef __LITTLE_ENDIAN +# define CANARY_MASK 0xffffffffffffff00UL +# else /* big endian, 64 bits: */ +# define CANARY_MASK 0x00ffffffffffffffUL +# endif +#else /* 32 bits: */ +# define CANARY_MASK 0xffffffffUL +#endif + +static inline unsigned long get_random_canary(void) +{ + unsigned long val = get_random_long(); + + return val & CANARY_MASK; +} + +/* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). + * Returns the result of the call to wait_for_random_bytes. */ +static inline int get_random_bytes_wait(void *buf, int nbytes) +{ + int ret = wait_for_random_bytes(); + if (unlikely(ret)) + return ret; + get_random_bytes(buf, nbytes); + return 0; +} + +#define declare_get_random_var_wait(var) \ + static inline int get_random_ ## var ## _wait(var *out) { \ + int ret = wait_for_random_bytes(); \ + if (unlikely(ret)) \ + return ret; \ + *out = get_random_ ## var(); \ + return 0; \ + } +declare_get_random_var_wait(u32) +declare_get_random_var_wait(u64) +declare_get_random_var_wait(int) +declare_get_random_var_wait(long) +#undef declare_get_random_var + unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); diff --git a/include/linux/ras.h b/include/linux/ras.h index 2aceeafd6fe5..be5338a35d57 100644 --- a/include/linux/ras.h +++ b/include/linux/ras.h @@ -1,14 +1,42 @@ #ifndef __RAS_H__ #define __RAS_H__ +#include <asm/errno.h> +#include <linux/uuid.h> +#include <linux/cper.h> + #ifdef CONFIG_DEBUG_FS int ras_userspace_consumers(void); void ras_debugfs_init(void); int ras_add_daemon_trace(void); #else static inline int ras_userspace_consumers(void) { return 0; } -static inline void ras_debugfs_init(void) { return; } +static inline void ras_debugfs_init(void) { } static inline int ras_add_daemon_trace(void) { return 0; } #endif +#ifdef CONFIG_RAS_CEC +void __init cec_init(void); +int __init parse_cec_param(char *str); +int cec_add_elem(u64 pfn); +#else +static inline void __init cec_init(void) { } +static inline int cec_add_elem(u64 pfn) { return -ENODEV; } +#endif + +#ifdef CONFIG_RAS +void log_non_standard_event(const guid_t *sec_type, + const guid_t *fru_id, const char *fru_text, + const u8 sev, const u8 *err, const u32 len); +void log_arm_hw_error(struct cper_sec_proc_arm *err); +#else +static inline void +log_non_standard_event(const guid_t *sec_type, + const guid_t *fru_id, const char *fru_text, + const u8 sev, const u8 *err, const u32 len) +{ return; } +static inline void +log_arm_hw_error(struct cper_sec_proc_arm *err) { return; } #endif + +#endif /* __RAS_H__ */ diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index d076183e49be..9702b6e183bc 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -90,7 +90,9 @@ rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ old->rbaugmented = rbcompute(old); \ } \ rbstatic const struct rb_augment_callbacks rbname = { \ - rbname ## _propagate, rbname ## _copy, rbname ## _rotate \ + .propagate = rbname ## _propagate, \ + .copy = rbname ## _copy, \ + .rotate = rbname ## _rotate \ }; diff --git a/include/linux/rcu_node_tree.h b/include/linux/rcu_node_tree.h new file mode 100644 index 000000000000..426cee67f0e2 --- /dev/null +++ b/include/linux/rcu_node_tree.h @@ -0,0 +1,103 @@ +/* + * RCU node combining tree definitions. These are used to compute + * global attributes while avoiding common-case global contention. A key + * property that these computations rely on is a tournament-style approach + * where only one of the tasks contending a lower level in the tree need + * advance to the next higher level. If properly configured, this allows + * unlimited scalability while maintaining a constant level of contention + * on the root node. + * + * This seemingly RCU-private file must be available to SRCU users + * because the size of the TREE SRCU srcu_struct structure depends + * on these definitions. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright IBM Corporation, 2017 + * + * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + */ + +#ifndef __LINUX_RCU_NODE_TREE_H +#define __LINUX_RCU_NODE_TREE_H + +/* + * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and + * CONFIG_RCU_FANOUT_LEAF. + * In theory, it should be possible to add more levels straightforwardly. + * In practice, this did work well going from three levels to four. + * Of course, your mileage may vary. + */ + +#ifdef CONFIG_RCU_FANOUT +#define RCU_FANOUT CONFIG_RCU_FANOUT +#else /* #ifdef CONFIG_RCU_FANOUT */ +# ifdef CONFIG_64BIT +# define RCU_FANOUT 64 +# else +# define RCU_FANOUT 32 +# endif +#endif /* #else #ifdef CONFIG_RCU_FANOUT */ + +#ifdef CONFIG_RCU_FANOUT_LEAF +#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF +#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */ +#define RCU_FANOUT_LEAF 16 +#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */ + +#define RCU_FANOUT_1 (RCU_FANOUT_LEAF) +#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT) +#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT) +#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT) + +#if NR_CPUS <= RCU_FANOUT_1 +# define RCU_NUM_LVLS 1 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_NODES NUM_RCU_LVL_0 +# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 } +# define RCU_NODE_NAME_INIT { "rcu_node_0" } +# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" } +#elif NR_CPUS <= RCU_FANOUT_2 +# define RCU_NUM_LVLS 2 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) +# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1) +# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 } +# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" } +# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" } +#elif NR_CPUS <= RCU_FANOUT_3 +# define RCU_NUM_LVLS 3 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) +# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) +# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2) +# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 } +# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" } +# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" } +#elif NR_CPUS <= RCU_FANOUT_4 +# define RCU_NUM_LVLS 4 +# define NUM_RCU_LVL_0 1 +# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3) +# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) +# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) +# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3) +# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 } +# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" } +# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" } +#else +# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" +#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */ + +#endif /* __LINUX_RCU_NODE_TREE_H */ diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h new file mode 100644 index 000000000000..c3ad00e63556 --- /dev/null +++ b/include/linux/rcu_segcblist.h @@ -0,0 +1,94 @@ +/* + * RCU segmented callback lists + * + * This seemingly RCU-private file must be available to SRCU users + * because the size of the TREE SRCU srcu_struct structure depends + * on these definitions. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright IBM Corporation, 2017 + * + * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + */ + +#ifndef __INCLUDE_LINUX_RCU_SEGCBLIST_H +#define __INCLUDE_LINUX_RCU_SEGCBLIST_H + +/* Simple unsegmented callback lists. */ +struct rcu_cblist { + struct rcu_head *head; + struct rcu_head **tail; + long len; + long len_lazy; +}; + +#define RCU_CBLIST_INITIALIZER(n) { .head = NULL, .tail = &n.head } + +/* Complicated segmented callback lists. ;-) */ + +/* + * Index values for segments in rcu_segcblist structure. + * + * The segments are as follows: + * + * [head, *tails[RCU_DONE_TAIL]): + * Callbacks whose grace period has elapsed, and thus can be invoked. + * [*tails[RCU_DONE_TAIL], *tails[RCU_WAIT_TAIL]): + * Callbacks waiting for the current GP from the current CPU's viewpoint. + * [*tails[RCU_WAIT_TAIL], *tails[RCU_NEXT_READY_TAIL]): + * Callbacks that arrived before the next GP started, again from + * the current CPU's viewpoint. These can be handled by the next GP. + * [*tails[RCU_NEXT_READY_TAIL], *tails[RCU_NEXT_TAIL]): + * Callbacks that might have arrived after the next GP started. + * There is some uncertainty as to when a given GP starts and + * ends, but a CPU knows the exact times if it is the one starting + * or ending the GP. Other CPUs know that the previous GP ends + * before the next one starts. + * + * Note that RCU_WAIT_TAIL cannot be empty unless RCU_NEXT_READY_TAIL is also + * empty. + * + * The ->gp_seq[] array contains the grace-period number at which the + * corresponding segment of callbacks will be ready to invoke. A given + * element of this array is meaningful only when the corresponding segment + * is non-empty, and it is never valid for RCU_DONE_TAIL (whose callbacks + * are already ready to invoke) or for RCU_NEXT_TAIL (whose callbacks have + * not yet been assigned a grace-period number). + */ +#define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */ +#define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */ +#define RCU_NEXT_READY_TAIL 2 /* Also RCU_NEXT head. */ +#define RCU_NEXT_TAIL 3 +#define RCU_CBLIST_NSEGS 4 + +struct rcu_segcblist { + struct rcu_head *head; + struct rcu_head **tails[RCU_CBLIST_NSEGS]; + unsigned long gp_seq[RCU_CBLIST_NSEGS]; + long len; + long len_lazy; +}; + +#define RCU_SEGCBLIST_INITIALIZER(n) \ +{ \ + .head = NULL, \ + .tails[RCU_DONE_TAIL] = &n.head, \ + .tails[RCU_WAIT_TAIL] = &n.head, \ + .tails[RCU_NEXT_READY_TAIL] = &n.head, \ + .tails[RCU_NEXT_TAIL] = &n.head, \ +} + +#endif /* __INCLUDE_LINUX_RCU_SEGCBLIST_H */ diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 4f7a9561b8c4..b1fd8bf85fdc 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -509,7 +509,8 @@ static inline void hlist_add_tail_rcu(struct hlist_node *n, { struct hlist_node *i, *last = NULL; - for (i = hlist_first_rcu(h); i; i = hlist_next_rcu(i)) + /* Note: write side code, so rcu accessors are not needed. */ + for (i = h->first; i; i = i->next) last = i; if (last) { diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 4ae95f7e8597..a23a33153180 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -156,5 +156,19 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos))) +/** + * hlist_nulls_for_each_entry_safe - + * iterate over list of given type safe against removal of list entry + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_nulls_node to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_nulls_node within the struct. + */ +#define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \ + for (({barrier();}), \ + pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ + (!is_a_nulls(pos)) && \ + ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \ + pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });) #endif #endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 01f71e1d2e94..f816fc72b51e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -34,100 +34,15 @@ #define __LINUX_RCUPDATE_H #include <linux/types.h> -#include <linux/cache.h> -#include <linux/spinlock.h> -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/seqlock.h> -#include <linux/lockdep.h> -#include <linux/completion.h> -#include <linux/debugobjects.h> -#include <linux/bug.h> #include <linux/compiler.h> -#include <linux/ktime.h> +#include <linux/atomic.h> #include <linux/irqflags.h> +#include <linux/preempt.h> +#include <linux/bottom_half.h> +#include <linux/lockdep.h> +#include <asm/processor.h> +#include <linux/cpumask.h> -#include <asm/barrier.h> - -#ifndef CONFIG_TINY_RCU -extern int rcu_expedited; /* for sysctl */ -extern int rcu_normal; /* also for sysctl */ -#endif /* #ifndef CONFIG_TINY_RCU */ - -#ifdef CONFIG_TINY_RCU -/* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ -static inline bool rcu_gp_is_normal(void) /* Internal RCU use. */ -{ - return true; -} -static inline bool rcu_gp_is_expedited(void) /* Internal RCU use. */ -{ - return false; -} - -static inline void rcu_expedite_gp(void) -{ -} - -static inline void rcu_unexpedite_gp(void) -{ -} -#else /* #ifdef CONFIG_TINY_RCU */ -bool rcu_gp_is_normal(void); /* Internal RCU use. */ -bool rcu_gp_is_expedited(void); /* Internal RCU use. */ -void rcu_expedite_gp(void); -void rcu_unexpedite_gp(void); -#endif /* #else #ifdef CONFIG_TINY_RCU */ - -enum rcutorture_type { - RCU_FLAVOR, - RCU_BH_FLAVOR, - RCU_SCHED_FLAVOR, - RCU_TASKS_FLAVOR, - SRCU_FLAVOR, - INVALID_RCU_FLAVOR -}; - -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) -void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gpnum, unsigned long *completed); -void rcutorture_record_test_transition(void); -void rcutorture_record_progress(unsigned long vernum); -void do_trace_rcu_torture_read(const char *rcutorturename, - struct rcu_head *rhp, - unsigned long secs, - unsigned long c_old, - unsigned long c); -#else -static inline void rcutorture_get_gp_data(enum rcutorture_type test_type, - int *flags, - unsigned long *gpnum, - unsigned long *completed) -{ - *flags = 0; - *gpnum = 0; - *completed = 0; -} -static inline void rcutorture_record_test_transition(void) -{ -} -static inline void rcutorture_record_progress(unsigned long vernum) -{ -} -#ifdef CONFIG_RCU_TRACE -void do_trace_rcu_torture_read(const char *rcutorturename, - struct rcu_head *rhp, - unsigned long secs, - unsigned long c_old, - unsigned long c); -#else -#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ - do { } while (0) -#endif -#endif - -#define UINT_CMP_GE(a, b) (UINT_MAX / 2 >= (a) - (b)) -#define UINT_CMP_LT(a, b) (UINT_MAX / 2 < (a) - (b)) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define ulong2long(a) (*(long *)(&(a))) @@ -135,154 +50,14 @@ void do_trace_rcu_torture_read(const char *rcutorturename, /* Exported common interfaces */ #ifdef CONFIG_PREEMPT_RCU - -/** - * call_rcu() - Queue an RCU callback for invocation after a grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all pre-existing RCU read-side - * critical sections have completed. However, the callback function - * might well execute concurrently with RCU read-side critical sections - * that started after call_rcu() was invoked. RCU read-side critical - * sections are delimited by rcu_read_lock() and rcu_read_unlock(), - * and may be nested. - * - * Note that all CPUs must agree that the grace period extended beyond - * all pre-existing RCU read-side critical section. On systems with more - * than one CPU, this means that when "func()" is invoked, each CPU is - * guaranteed to have executed a full memory barrier since the end of its - * last RCU read-side critical section whose beginning preceded the call - * to call_rcu(). It also means that each CPU executing an RCU read-side - * critical section that continues beyond the start of "func()" must have - * executed a memory barrier after the call_rcu() but before the beginning - * of that RCU read-side critical section. Note that these guarantees - * include CPUs that are offline, idle, or executing in user mode, as - * well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the - * resulting RCU callback function "func()", then both CPU A and CPU B are - * guaranteed to execute a full memory barrier during the time interval - * between the call to call_rcu() and the invocation of "func()" -- even - * if CPU A and CPU B are the same CPU (but again only if the system has - * more than one CPU). - */ -void call_rcu(struct rcu_head *head, - rcu_callback_t func); - +void call_rcu(struct rcu_head *head, rcu_callback_t func); #else /* #ifdef CONFIG_PREEMPT_RCU */ - -/* In classic RCU, call_rcu() is just call_rcu_sched(). */ #define call_rcu call_rcu_sched - #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ -/** - * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_bh() assumes - * that the read-side critical sections end on completion of a softirq - * handler. This means that read-side critical sections in process - * context must not be interrupted by softirqs. This interface is to be - * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. - * OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * These may be nested. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -void call_rcu_bh(struct rcu_head *head, - rcu_callback_t func); - -/** - * call_rcu_sched() - Queue an RCU for invocation after sched grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_sched() assumes - * that the read-side critical sections end on enabling of preemption - * or on voluntary preemption. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock_sched() and rcu_read_unlock_sched(), - * OR - * anything that disables preemption. - * These may be nested. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -void call_rcu_sched(struct rcu_head *head, - rcu_callback_t func); - +void call_rcu_bh(struct rcu_head *head, rcu_callback_t func); +void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); void synchronize_sched(void); - -/* - * Structure allowing asynchronous waiting on RCU. - */ -struct rcu_synchronize { - struct rcu_head head; - struct completion completion; -}; -void wakeme_after_rcu(struct rcu_head *head); - -void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, - struct rcu_synchronize *rs_array); - -#define _wait_rcu_gp(checktiny, ...) \ -do { \ - call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ - struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ - __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \ - __crcu_array, __rs_array); \ -} while (0) - -#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) - -/** - * synchronize_rcu_mult - Wait concurrently for multiple grace periods - * @...: List of call_rcu() functions for the flavors to wait on. - * - * This macro waits concurrently for multiple flavors of RCU grace periods. - * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait - * on concurrent RCU and RCU-bh grace periods. Waiting on a give SRCU - * domain requires you to write a wrapper function for that SRCU domain's - * call_srcu() function, supplying the corresponding srcu_struct. - * - * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU - * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called - * is automatically a grace period. - */ -#define synchronize_rcu_mult(...) \ - _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) - -/** - * call_rcu_tasks() - Queue an RCU for invocation task-based grace period - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_tasks() assumes - * that the read-side critical sections end at a voluntary context - * switch (not a preemption!), entry into idle, or transition to usermode - * execution. As such, there are no read-side primitives analogous to - * rcu_read_lock() and rcu_read_unlock() because this primitive is intended - * to determine that all tasks have passed through a safe state, not so - * much for data-strcuture synchronization. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void rcu_barrier_tasks(void); @@ -336,22 +111,12 @@ void rcu_check_callbacks(int user); void rcu_report_dead(unsigned int cpu); void rcu_cpu_starting(unsigned int cpu); -#ifndef CONFIG_TINY_RCU -void rcu_end_inkernel_boot(void); -#else /* #ifndef CONFIG_TINY_RCU */ -static inline void rcu_end_inkernel_boot(void) { } -#endif /* #ifndef CONFIG_TINY_RCU */ - #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ -static inline void rcu_sysrq_start(void) -{ -} -static inline void rcu_sysrq_end(void) -{ -} +static inline void rcu_sysrq_start(void) { } +static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #ifdef CONFIG_NO_HZ_FULL @@ -365,9 +130,7 @@ static inline void rcu_user_exit(void) { } #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ -static inline void rcu_init_nohz(void) -{ -} +static inline void rcu_init_nohz(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** @@ -403,15 +166,20 @@ static inline void rcu_init_nohz(void) #ifdef CONFIG_TASKS_RCU #define TASKS_RCU(x) x extern struct srcu_struct tasks_rcu_exit_srcu; -#define rcu_note_voluntary_context_switch(t) \ +#define rcu_note_voluntary_context_switch_lite(t) \ do { \ - rcu_all_qs(); \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) +#define rcu_note_voluntary_context_switch(t) \ + do { \ + rcu_all_qs(); \ + rcu_note_voluntary_context_switch_lite(t); \ + } while (0) #else /* #ifdef CONFIG_TASKS_RCU */ #define TASKS_RCU(x) do { } while (0) -#define rcu_note_voluntary_context_switch(t) rcu_all_qs() +#define rcu_note_voluntary_context_switch_lite(t) do { } while (0) +#define rcu_note_voluntary_context_switch(t) rcu_all_qs() #endif /* #else #ifdef CONFIG_TASKS_RCU */ /** @@ -427,10 +195,6 @@ do { \ rcu_note_voluntary_context_switch(current); \ } while (0) -#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) -bool __rcu_is_watching(void); -#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */ - /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. @@ -444,10 +208,6 @@ bool __rcu_is_watching(void); #error "Unknown RCU implementation specified to kernel configuration" #endif -#define RCU_SCHEDULER_INACTIVE 0 -#define RCU_SCHEDULER_INIT 1 -#define RCU_SCHEDULER_RUNNING 2 - /* * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic * initialization and destruction of rcu_head on the stack. rcu_head structures @@ -460,30 +220,16 @@ void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ -static inline void init_rcu_head(struct rcu_head *head) -{ -} - -static inline void destroy_rcu_head(struct rcu_head *head) -{ -} - -static inline void init_rcu_head_on_stack(struct rcu_head *head) -{ -} - -static inline void destroy_rcu_head_on_stack(struct rcu_head *head) -{ -} +static inline void init_rcu_head(struct rcu_head *head) { } +static inline void destroy_rcu_head(struct rcu_head *head) { } +static inline void init_rcu_head_on_stack(struct rcu_head *head) { } +static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ -static inline bool rcu_lockdep_current_cpu_online(void) -{ - return true; -} +static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -503,18 +249,8 @@ extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; int debug_lockdep_rcu_enabled(void); - int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); - -/** - * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? - * - * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an - * RCU-sched read-side critical section. In absence of - * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side - * critical section unless it can prove otherwise. - */ int rcu_read_lock_sched_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -561,9 +297,7 @@ static inline void rcu_preempt_sleep_check(void) "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ -static inline void rcu_preempt_sleep_check(void) -{ -} +static inline void rcu_preempt_sleep_check(void) { } #endif /* #else #ifdef CONFIG_PROVE_RCU */ #define rcu_sleep_check() \ @@ -1114,52 +848,18 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define kfree_rcu(ptr, rcu_head) \ __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) -#ifdef CONFIG_TINY_RCU -static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) -{ - *nextevt = KTIME_MAX; - return 0; -} -#endif /* #ifdef CONFIG_TINY_RCU */ - -#if defined(CONFIG_RCU_NOCB_CPU_ALL) -static inline bool rcu_is_nocb_cpu(int cpu) { return true; } -#elif defined(CONFIG_RCU_NOCB_CPU) -bool rcu_is_nocb_cpu(int cpu); -#else -static inline bool rcu_is_nocb_cpu(int cpu) { return false; } -#endif - - -/* Only for use by adaptive-ticks code. */ -#ifdef CONFIG_NO_HZ_FULL_SYSIDLE -bool rcu_sys_is_idle(void); -void rcu_sysidle_force_exit(void); -#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - -static inline bool rcu_sys_is_idle(void) -{ - return false; -} - -static inline void rcu_sysidle_force_exit(void) -{ -} - -#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - /* - * Dump the ftrace buffer, but only one time per callsite per boot. - */ -#define rcu_ftrace_dump(oops_dump_mode) \ -do { \ - static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \ - \ - if (!atomic_read(&___rfd_beenhere) && \ - !atomic_xchg(&___rfd_beenhere, 1)) \ - ftrace_dump(oops_dump_mode); \ -} while (0) + * Place this after a lock-acquisition primitive to guarantee that + * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies + * if the UNLOCK and LOCK are executed by the same CPU or if the + * UNLOCK and LOCK operate on the same lock variable. + */ +#ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE +#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ +#else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ +#define smp_mb__after_unlock_lock() do { } while (0) +#endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h new file mode 100644 index 000000000000..e774b4f5f220 --- /dev/null +++ b/include/linux/rcupdate_wait.h @@ -0,0 +1,50 @@ +#ifndef _LINUX_SCHED_RCUPDATE_WAIT_H +#define _LINUX_SCHED_RCUPDATE_WAIT_H + +/* + * RCU synchronization types and methods: + */ + +#include <linux/rcupdate.h> +#include <linux/completion.h> + +/* + * Structure allowing asynchronous waiting on RCU. + */ +struct rcu_synchronize { + struct rcu_head head; + struct completion completion; +}; +void wakeme_after_rcu(struct rcu_head *head); + +void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, + struct rcu_synchronize *rs_array); + +#define _wait_rcu_gp(checktiny, ...) \ +do { \ + call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ + struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ + __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \ + __crcu_array, __rs_array); \ +} while (0) + +#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) + +/** + * synchronize_rcu_mult - Wait concurrently for multiple grace periods + * @...: List of call_rcu() functions for the flavors to wait on. + * + * This macro waits concurrently for multiple flavors of RCU grace periods. + * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait + * on concurrent RCU and RCU-bh grace periods. Waiting on a give SRCU + * domain requires you to write a wrapper function for that SRCU domain's + * call_srcu() function, supplying the corresponding srcu_struct. + * + * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU + * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called + * is automatically a grace period. + */ +#define synchronize_rcu_mult(...) \ + _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) + +#endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index ac81e4063b40..5becbbccb998 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -25,7 +25,16 @@ #ifndef __LINUX_TINY_H #define __LINUX_TINY_H -#include <linux/cache.h> +#include <linux/ktime.h> + +struct rcu_dynticks; +static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) +{ + return 0; +} + +/* Never flag non-existent other CPUs! */ +static inline bool rcu_eqs_special_set(int cpu) { return false; } static inline unsigned long get_state_synchronize_rcu(void) { @@ -47,15 +56,8 @@ static inline void cond_synchronize_sched(unsigned long oldstate) might_sleep(); } -static inline void rcu_barrier_bh(void) -{ - wait_rcu_gp(call_rcu_bh); -} - -static inline void rcu_barrier_sched(void) -{ - wait_rcu_gp(call_rcu_sched); -} +extern void rcu_barrier_bh(void); +extern void rcu_barrier_sched(void); static inline void synchronize_rcu_expedited(void) { @@ -88,160 +90,44 @@ static inline void kfree_call_rcu(struct rcu_head *head, call_rcu(head, func); } -static inline void rcu_note_context_switch(void) -{ - rcu_sched_qs(); -} +#define rcu_note_context_switch(preempt) \ + do { \ + rcu_sched_qs(); \ + rcu_note_voluntary_context_switch_lite(current); \ + } while (0) -/* - * Take advantage of the fact that there is only one CPU, which - * allows us to ignore virtualization-based context switches. - */ -static inline void rcu_virt_note_context_switch(int cpu) -{ -} - -/* - * Return the number of grace periods started. - */ -static inline unsigned long rcu_batches_started(void) -{ - return 0; -} - -/* - * Return the number of bottom-half grace periods started. - */ -static inline unsigned long rcu_batches_started_bh(void) -{ - return 0; -} - -/* - * Return the number of sched grace periods started. - */ -static inline unsigned long rcu_batches_started_sched(void) -{ - return 0; -} - -/* - * Return the number of grace periods completed. - */ -static inline unsigned long rcu_batches_completed(void) -{ - return 0; -} - -/* - * Return the number of bottom-half grace periods completed. - */ -static inline unsigned long rcu_batches_completed_bh(void) -{ - return 0; -} - -/* - * Return the number of sched grace periods completed. - */ -static inline unsigned long rcu_batches_completed_sched(void) -{ - return 0; -} - -/* - * Return the number of expedited grace periods completed. - */ -static inline unsigned long rcu_exp_batches_completed(void) +static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) { + *nextevt = KTIME_MAX; return 0; } /* - * Return the number of expedited sched grace periods completed. + * Take advantage of the fact that there is only one CPU, which + * allows us to ignore virtualization-based context switches. */ -static inline unsigned long rcu_exp_batches_completed_sched(void) -{ - return 0; -} - -static inline void rcu_force_quiescent_state(void) -{ -} - -static inline void rcu_bh_force_quiescent_state(void) -{ -} - -static inline void rcu_sched_force_quiescent_state(void) -{ -} - -static inline void show_rcu_gp_kthreads(void) -{ -} - -static inline void rcu_cpu_stall_reset(void) -{ -} - -static inline void rcu_idle_enter(void) -{ -} - -static inline void rcu_idle_exit(void) -{ -} - -static inline void rcu_irq_enter(void) -{ -} - -static inline void rcu_irq_exit_irqson(void) -{ -} - -static inline void rcu_irq_enter_irqson(void) -{ -} - -static inline void rcu_irq_exit(void) -{ -} - -static inline void exit_rcu(void) -{ -} - -#ifdef CONFIG_DEBUG_LOCK_ALLOC +static inline void rcu_virt_note_context_switch(int cpu) { } +static inline void rcu_cpu_stall_reset(void) { } +static inline void rcu_idle_enter(void) { } +static inline void rcu_idle_exit(void) { } +static inline void rcu_irq_enter(void) { } +static inline bool rcu_irq_enter_disabled(void) { return false; } +static inline void rcu_irq_exit_irqson(void) { } +static inline void rcu_irq_enter_irqson(void) { } +static inline void rcu_irq_exit(void) { } +static inline void exit_rcu(void) { } + +#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) extern int rcu_scheduler_active __read_mostly; void rcu_scheduler_starting(void); -#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -static inline void rcu_scheduler_starting(void) -{ -} -#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ - -#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) - -static inline bool rcu_is_watching(void) -{ - return __rcu_is_watching(); -} - -#else /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ - -static inline bool rcu_is_watching(void) -{ - return true; -} - -#endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ - -static inline void rcu_all_qs(void) -{ - barrier(); /* Avoid RCU read-side critical sections leaking across. */ -} +#else /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */ +static inline void rcu_scheduler_starting(void) { } +#endif /* #else #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */ +static inline void rcu_end_inkernel_boot(void) { } +static inline bool rcu_is_watching(void) { return true; } + +/* Avoid RCU read-side critical sections leaking across. */ +static inline void rcu_all_qs(void) { barrier(); } /* RCUtree hotplug events */ #define rcutree_prepare_cpu NULL diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 63a4e4cf40a5..37d6fd3b7ff8 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -30,7 +30,7 @@ #ifndef __LINUX_RCUTREE_H #define __LINUX_RCUTREE_H -void rcu_note_context_switch(void); +void rcu_note_context_switch(bool preempt); int rcu_needs_cpu(u64 basem, u64 *nextevt); void rcu_cpu_stall_reset(void); @@ -41,7 +41,7 @@ void rcu_cpu_stall_reset(void); */ static inline void rcu_virt_note_context_switch(int cpu) { - rcu_note_context_switch(); + rcu_note_context_switch(false); } void synchronize_rcu_bh(void); @@ -79,36 +79,20 @@ void cond_synchronize_rcu(unsigned long oldstate); unsigned long get_state_synchronize_sched(void); void cond_synchronize_sched(unsigned long oldstate); -extern unsigned long rcutorture_testseq; -extern unsigned long rcutorture_vernum; -unsigned long rcu_batches_started(void); -unsigned long rcu_batches_started_bh(void); -unsigned long rcu_batches_started_sched(void); -unsigned long rcu_batches_completed(void); -unsigned long rcu_batches_completed_bh(void); -unsigned long rcu_batches_completed_sched(void); -unsigned long rcu_exp_batches_completed(void); -unsigned long rcu_exp_batches_completed_sched(void); -void show_rcu_gp_kthreads(void); - -void rcu_force_quiescent_state(void); -void rcu_bh_force_quiescent_state(void); -void rcu_sched_force_quiescent_state(void); - void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); void rcu_irq_enter_irqson(void); void rcu_irq_exit_irqson(void); +bool rcu_irq_enter_disabled(void); void exit_rcu(void); void rcu_scheduler_starting(void); extern int rcu_scheduler_active __read_mostly; - +void rcu_end_inkernel_boot(void); bool rcu_is_watching(void); - void rcu_all_qs(void); /* RCUtree hotplug events */ diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h new file mode 100644 index 000000000000..a4ede51b3e7c --- /dev/null +++ b/include/linux/rcuwait.h @@ -0,0 +1,63 @@ +#ifndef _LINUX_RCUWAIT_H_ +#define _LINUX_RCUWAIT_H_ + +#include <linux/rcupdate.h> + +/* + * rcuwait provides a way of blocking and waking up a single + * task in an rcu-safe manner; where it is forbidden to use + * after exit_notify(). task_struct is not properly rcu protected, + * unless dealing with rcu-aware lists, ie: find_task_by_*(). + * + * Alternatively we have task_rcu_dereference(), but the return + * semantics have different implications which would break the + * wakeup side. The only time @task is non-nil is when a user is + * blocked (or checking if it needs to) on a condition, and reset + * as soon as we know that the condition has succeeded and are + * awoken. + */ +struct rcuwait { + struct task_struct *task; +}; + +#define __RCUWAIT_INITIALIZER(name) \ + { .task = NULL, } + +static inline void rcuwait_init(struct rcuwait *w) +{ + w->task = NULL; +} + +extern void rcuwait_wake_up(struct rcuwait *w); + +/* + * The caller is responsible for locking around rcuwait_wait_event(), + * such that writes to @task are properly serialized. + */ +#define rcuwait_wait_event(w, condition) \ +({ \ + /* \ + * Complain if we are called after do_exit()/exit_notify(), \ + * as we cannot rely on the rcu critical region for the \ + * wakeup side. \ + */ \ + WARN_ON(current->exit_state); \ + \ + rcu_assign_pointer((w)->task, current); \ + for (;;) { \ + /* \ + * Implicit barrier (A) pairs with (B) in \ + * rcuwait_wake_up(). \ + */ \ + set_current_state(TASK_UNINTERRUPTIBLE); \ + if (condition) \ + break; \ + \ + schedule(); \ + } \ + \ + WRITE_ONCE((w)->task, NULL); \ + __set_current_state(TASK_RUNNING); \ +}) + +#endif /* _LINUX_RCUWAIT_H_ */ diff --git a/include/linux/reboot-mode.h b/include/linux/reboot-mode.h new file mode 100644 index 000000000000..75f7fe5c881f --- /dev/null +++ b/include/linux/reboot-mode.h @@ -0,0 +1,18 @@ +#ifndef __REBOOT_MODE_H__ +#define __REBOOT_MODE_H__ + +struct reboot_mode_driver { + struct device *dev; + struct list_head head; + int (*write)(struct reboot_mode_driver *reboot, unsigned int magic); + struct notifier_block reboot_notifier; +}; + +int reboot_mode_register(struct reboot_mode_driver *reboot); +int reboot_mode_unregister(struct reboot_mode_driver *reboot); +int devm_reboot_mode_register(struct device *dev, + struct reboot_mode_driver *reboot); +void devm_reboot_mode_unregister(struct device *dev, + struct reboot_mode_driver *reboot); + +#endif diff --git a/include/linux/refcount.h b/include/linux/refcount.h new file mode 100644 index 000000000000..591792c8e5b0 --- /dev/null +++ b/include/linux/refcount.h @@ -0,0 +1,97 @@ +#ifndef _LINUX_REFCOUNT_H +#define _LINUX_REFCOUNT_H + +#include <linux/atomic.h> +#include <linux/mutex.h> +#include <linux/spinlock.h> +#include <linux/kernel.h> + +/** + * refcount_t - variant of atomic_t specialized for reference counts + * @refs: atomic_t counter field + * + * The counter saturates at UINT_MAX and will not move once + * there. This avoids wrapping the counter and causing 'spurious' + * use-after-free bugs. + */ +typedef struct refcount_struct { + atomic_t refs; +} refcount_t; + +#define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } + +/** + * refcount_set - set a refcount's value + * @r: the refcount + * @n: value to which the refcount will be set + */ +static inline void refcount_set(refcount_t *r, unsigned int n) +{ + atomic_set(&r->refs, n); +} + +/** + * refcount_read - get a refcount's value + * @r: the refcount + * + * Return: the refcount's value + */ +static inline unsigned int refcount_read(const refcount_t *r) +{ + return atomic_read(&r->refs); +} + +#ifdef CONFIG_REFCOUNT_FULL +extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r); +extern void refcount_add(unsigned int i, refcount_t *r); + +extern __must_check bool refcount_inc_not_zero(refcount_t *r); +extern void refcount_inc(refcount_t *r); + +extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r); + +extern __must_check bool refcount_dec_and_test(refcount_t *r); +extern void refcount_dec(refcount_t *r); +#else +static inline __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r) +{ + return atomic_add_unless(&r->refs, i, 0); +} + +static inline void refcount_add(unsigned int i, refcount_t *r) +{ + atomic_add(i, &r->refs); +} + +static inline __must_check bool refcount_inc_not_zero(refcount_t *r) +{ + return atomic_add_unless(&r->refs, 1, 0); +} + +static inline void refcount_inc(refcount_t *r) +{ + atomic_inc(&r->refs); +} + +static inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) +{ + return atomic_sub_and_test(i, &r->refs); +} + +static inline __must_check bool refcount_dec_and_test(refcount_t *r) +{ + return atomic_dec_and_test(&r->refs); +} + +static inline void refcount_dec(refcount_t *r) +{ + atomic_dec(&r->refs); +} +#endif /* CONFIG_REFCOUNT_FULL */ + +extern __must_check bool refcount_dec_if_one(refcount_t *r); +extern __must_check bool refcount_dec_not_one(refcount_t *r); +extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); +extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); + +#endif /* _LINUX_REFCOUNT_H */ diff --git a/include/linux/regmap.h b/include/linux/regmap.h index f6673132431d..978abfbac617 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -40,12 +40,13 @@ enum regcache_type { }; /** - * Default value for a register. We use an array of structs rather - * than a simple array as many modern devices have very sparse - * register maps. + * struct reg_default - Default value for a register. * * @reg: Register address. * @def: Register default value. + * + * We use an array of structs rather than a simple array as many modern devices + * have very sparse register maps. */ struct reg_default { unsigned int reg; @@ -53,12 +54,14 @@ struct reg_default { }; /** - * Register/value pairs for sequences of writes with an optional delay in - * microseconds to be applied after each write. + * struct reg_sequence - An individual write from a sequence of writes. * * @reg: Register address. * @def: Register value. * @delay_us: Delay to be applied after the register write in microseconds + * + * Register/value pairs for sequences of writes with an optional delay in + * microseconds to be applied after each write. */ struct reg_sequence { unsigned int reg; @@ -98,6 +101,7 @@ struct reg_sequence { /** * regmap_read_poll_timeout - Poll until a condition is met or a timeout occurs + * * @map: Regmap to read from * @addr: Address to poll * @val: Unsigned integer variable to read the value into @@ -146,8 +150,8 @@ enum regmap_endian { }; /** - * A register range, used for access related checks - * (readable/writeable/volatile/precious checks) + * struct regmap_range - A register range, used for access related checks + * (readable/writeable/volatile/precious checks) * * @range_min: address of first register * @range_max: address of last register @@ -159,16 +163,18 @@ struct regmap_range { #define regmap_reg_range(low, high) { .range_min = low, .range_max = high, } -/* - * A table of ranges including some yes ranges and some no ranges. - * If a register belongs to a no_range, the corresponding check function - * will return false. If a register belongs to a yes range, the corresponding - * check function will return true. "no_ranges" are searched first. +/** + * struct regmap_access_table - A table of register ranges for access checks * * @yes_ranges : pointer to an array of regmap ranges used as "yes ranges" * @n_yes_ranges: size of the above array * @no_ranges: pointer to an array of regmap ranges used as "no ranges" * @n_no_ranges: size of the above array + * + * A table of ranges including some yes ranges and some no ranges. + * If a register belongs to a no_range, the corresponding check function + * will return false. If a register belongs to a yes range, the corresponding + * check function will return true. "no_ranges" are searched first. */ struct regmap_access_table { const struct regmap_range *yes_ranges; @@ -181,7 +187,7 @@ typedef void (*regmap_lock)(void *); typedef void (*regmap_unlock)(void *); /** - * Configuration for the register map of a device. + * struct regmap_config - Configuration for the register map of a device. * * @name: Optional name of the regmap. Useful when a device has multiple * register regions. @@ -314,22 +320,24 @@ struct regmap_config { }; /** - * Configuration for indirectly accessed or paged registers. - * Registers, mapped to this virtual range, are accessed in two steps: - * 1. page selector register update; - * 2. access through data window registers. + * struct regmap_range_cfg - Configuration for indirectly accessed or paged + * registers. * * @name: Descriptive name for diagnostics * * @range_min: Address of the lowest register address in virtual range. * @range_max: Address of the highest register in virtual range. * - * @page_sel_reg: Register with selector field. - * @page_sel_mask: Bit shift for selector value. - * @page_sel_shift: Bit mask for selector value. + * @selector_reg: Register with selector field. + * @selector_mask: Bit shift for selector value. + * @selector_shift: Bit mask for selector value. * * @window_start: Address of first (lowest) register in data window. * @window_len: Number of registers in data window. + * + * Registers, mapped to this virtual range, are accessed in two steps: + * 1. page selector register update; + * 2. access through data window registers. */ struct regmap_range_cfg { const char *name; @@ -372,7 +380,8 @@ typedef struct regmap_async *(*regmap_hw_async_alloc)(void); typedef void (*regmap_hw_free_context)(void *context); /** - * Description of a hardware bus for the register map infrastructure. + * struct regmap_bus - Description of a hardware bus for the register map + * infrastructure. * * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock @@ -385,6 +394,10 @@ typedef void (*regmap_hw_free_context)(void *context); * must serialise with respect to non-async I/O. * @reg_write: Write a single register value to the given register address. This * write operation has to complete when returning from the function. + * @reg_update_bits: Update bits operation to be used against volatile + * registers, intended for devices supporting some mechanism + * for setting clearing bits without having to + * read/modify/write. * @read: Read operation. Data is returned in the buffer used to transmit * data. * @reg_read: Read a single register value from a given register address. @@ -448,6 +461,10 @@ struct regmap *__regmap_init_spmi_ext(struct spmi_device *dev, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__regmap_init_w1(struct device *w1_dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__regmap_init_mmio_clk(struct device *dev, const char *clk_id, void __iomem *regs, const struct regmap_config *config, @@ -480,6 +497,10 @@ struct regmap *__devm_regmap_init_spmi_ext(struct spmi_device *dev, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__devm_regmap_init_w1(struct device *w1_dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__devm_regmap_init_mmio_clk(struct device *dev, const char *clk_id, void __iomem *regs, @@ -514,7 +535,7 @@ struct regmap *__devm_regmap_init_ac97(struct snd_ac97 *ac97, #endif /** - * regmap_init(): Initialise register map + * regmap_init() - Initialise register map * * @dev: Device that will be interacted with * @bus: Bus-specific callbacks to use with device @@ -532,7 +553,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, const struct regmap_config *config); /** - * regmap_init_i2c(): Initialise register map + * regmap_init_i2c() - Initialise register map * * @i2c: Device that will be interacted with * @config: Configuration for register map @@ -545,9 +566,9 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, i2c, config) /** - * regmap_init_spi(): Initialise register map + * regmap_init_spi() - Initialise register map * - * @spi: Device that will be interacted with + * @dev: Device that will be interacted with * @config: Configuration for register map * * The return value will be an ERR_PTR() on error or a valid pointer to @@ -558,8 +579,9 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, dev, config) /** - * regmap_init_spmi_base(): Create regmap for the Base register space - * @sdev: SPMI device that will be interacted with + * regmap_init_spmi_base() - Create regmap for the Base register space + * + * @dev: SPMI device that will be interacted with * @config: Configuration for register map * * The return value will be an ERR_PTR() on error or a valid pointer to @@ -570,8 +592,9 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, dev, config) /** - * regmap_init_spmi_ext(): Create regmap for Ext register space - * @sdev: Device that will be interacted with + * regmap_init_spmi_ext() - Create regmap for Ext register space + * + * @dev: Device that will be interacted with * @config: Configuration for register map * * The return value will be an ERR_PTR() on error or a valid pointer to @@ -582,7 +605,20 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, dev, config) /** - * regmap_init_mmio_clk(): Initialise register map with register clock + * regmap_init_w1() - Initialise register map + * + * @w1_dev: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_w1(w1_dev, config) \ + __regmap_lockdep_wrapper(__regmap_init_w1, #config, \ + w1_dev, config) + +/** + * regmap_init_mmio_clk() - Initialise register map with register clock * * @dev: Device that will be interacted with * @clk_id: register clock consumer ID @@ -597,7 +633,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, dev, clk_id, regs, config) /** - * regmap_init_mmio(): Initialise register map + * regmap_init_mmio() - Initialise register map * * @dev: Device that will be interacted with * @regs: Pointer to memory-mapped IO region @@ -610,7 +646,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, regmap_init_mmio_clk(dev, NULL, regs, config) /** - * regmap_init_ac97(): Initialise AC'97 register map + * regmap_init_ac97() - Initialise AC'97 register map * * @ac97: Device that will be interacted with * @config: Configuration for register map @@ -624,7 +660,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); /** - * devm_regmap_init(): Initialise managed register map + * devm_regmap_init() - Initialise managed register map * * @dev: Device that will be interacted with * @bus: Bus-specific callbacks to use with device @@ -641,7 +677,7 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); dev, bus, bus_context, config) /** - * devm_regmap_init_i2c(): Initialise managed register map + * devm_regmap_init_i2c() - Initialise managed register map * * @i2c: Device that will be interacted with * @config: Configuration for register map @@ -655,9 +691,9 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); i2c, config) /** - * devm_regmap_init_spi(): Initialise register map + * devm_regmap_init_spi() - Initialise register map * - * @spi: Device that will be interacted with + * @dev: Device that will be interacted with * @config: Configuration for register map * * The return value will be an ERR_PTR() on error or a valid pointer @@ -669,8 +705,9 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); dev, config) /** - * devm_regmap_init_spmi_base(): Create managed regmap for Base register space - * @sdev: SPMI device that will be interacted with + * devm_regmap_init_spmi_base() - Create managed regmap for Base register space + * + * @dev: SPMI device that will be interacted with * @config: Configuration for register map * * The return value will be an ERR_PTR() on error or a valid pointer @@ -682,8 +719,9 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); dev, config) /** - * devm_regmap_init_spmi_ext(): Create managed regmap for Ext register space - * @sdev: SPMI device that will be interacted with + * devm_regmap_init_spmi_ext() - Create managed regmap for Ext register space + * + * @dev: SPMI device that will be interacted with * @config: Configuration for register map * * The return value will be an ERR_PTR() on error or a valid pointer @@ -695,7 +733,20 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); dev, config) /** - * devm_regmap_init_mmio_clk(): Initialise managed register map with clock + * devm_regmap_init_w1() - Initialise managed register map + * + * @w1_dev: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_w1(w1_dev, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_w1, #config, \ + w1_dev, config) +/** + * devm_regmap_init_mmio_clk() - Initialise managed register map with clock * * @dev: Device that will be interacted with * @clk_id: register clock consumer ID @@ -711,7 +762,7 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); dev, clk_id, regs, config) /** - * devm_regmap_init_mmio(): Initialise managed register map + * devm_regmap_init_mmio() - Initialise managed register map * * @dev: Device that will be interacted with * @regs: Pointer to memory-mapped IO region @@ -725,7 +776,7 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); devm_regmap_init_mmio_clk(dev, NULL, regs, config) /** - * devm_regmap_init_ac97(): Initialise AC'97 register map + * devm_regmap_init_ac97() - Initialise AC'97 register map * * @ac97: Device that will be interacted with * @config: Configuration for register map @@ -800,7 +851,7 @@ bool regmap_reg_in_ranges(unsigned int reg, unsigned int nranges); /** - * Description of an register field + * struct reg_field - Description of an register field * * @reg: Offset of the register within the regmap bank * @lsb: lsb of the register field. @@ -841,7 +892,7 @@ int regmap_fields_update_bits_base(struct regmap_field *field, unsigned int id, bool *change, bool async, bool force); /** - * Description of an IRQ for the generic regmap irq_chip. + * struct regmap_irq - Description of an IRQ for the generic regmap irq_chip. * * @reg_offset: Offset of the status/mask register within the bank * @mask: Mask used to flag/control the register. @@ -861,14 +912,13 @@ struct regmap_irq { [_irq] = { .reg_offset = (_off), .mask = (_mask) } /** - * Description of a generic regmap irq_chip. This is not intended to - * handle every possible interrupt controller, but it should handle a - * substantial proportion of those that are found in the wild. + * struct regmap_irq_chip - Description of a generic regmap irq_chip. * * @name: Descriptive name for IRQ controller. * * @status_base: Base status register address. * @mask_base: Base mask register address. + * @mask_writeonly: Base mask register is write only. * @unmask_base: Base unmask register address. for chips who have * separate mask and unmask registers * @ack_base: Base ack address. If zero then the chip is clear on read. @@ -897,6 +947,10 @@ struct regmap_irq { * after handling the interrupts in regmap_irq_handler(). * @irq_drv_data: Driver specific IRQ data which is passed as parameter when * driver specific pre/post interrupt handler is called. + * + * This is not intended to handle every possible interrupt controller, but + * it should handle a substantial proportion of those that are found in the + * wild. */ struct regmap_irq_chip { const char *name; @@ -908,6 +962,7 @@ struct regmap_irq_chip { unsigned int wake_base; unsigned int type_base; unsigned int irq_reg_stride; + bool mask_writeonly:1; bool init_ack_masked:1; bool mask_invert:1; bool use_ack:1; diff --git a/include/linux/regulator/arizona-ldo1.h b/include/linux/regulator/arizona-ldo1.h new file mode 100644 index 000000000000..c685f1277c63 --- /dev/null +++ b/include/linux/regulator/arizona-ldo1.h @@ -0,0 +1,24 @@ +/* + * Platform data for Arizona LDO1 regulator + * + * Copyright 2017 Cirrus Logic + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef ARIZONA_LDO1_H +#define ARIZONA_LDO1_H + +struct regulator_init_data; + +struct arizona_ldo1_pdata { + /** GPIO controlling LDOENA, if any */ + int ldoena; + + /** Regulator configuration for LDO1 */ + const struct regulator_init_data *init_data; +}; + +#endif diff --git a/include/linux/regulator/arizona-micsupp.h b/include/linux/regulator/arizona-micsupp.h new file mode 100644 index 000000000000..616842619c00 --- /dev/null +++ b/include/linux/regulator/arizona-micsupp.h @@ -0,0 +1,21 @@ +/* + * Platform data for Arizona micsupp regulator + * + * Copyright 2017 Cirrus Logic + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef ARIZONA_MICSUPP_H +#define ARIZONA_MICSUPP_H + +struct regulator_init_data; + +struct arizona_micsupp_pdata { + /** Regulator configuration for micsupp */ + const struct regulator_init_data *init_data; +}; + +#endif diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index ea0fffa5faeb..df176d7c2b87 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -119,6 +119,7 @@ struct regmap; #define REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE 0x200 #define REGULATOR_EVENT_PRE_DISABLE 0x400 #define REGULATOR_EVENT_ABORT_DISABLE 0x800 +#define REGULATOR_EVENT_ENABLE 0x1000 /* * Regulator errors that can be queried using regulator_get_error_flags diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index dac8e7b16bc6..94417b4226bd 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -292,6 +292,14 @@ enum regulator_type { * set_active_discharge * @active_discharge_reg: Register for control when using regmap * set_active_discharge + * @soft_start_reg: Register for control when using regmap set_soft_start + * @soft_start_mask: Mask for control when using regmap set_soft_start + * @soft_start_val_on: Enabling value for control when using regmap + * set_soft_start + * @pull_down_reg: Register for control when using regmap set_pull_down + * @pull_down_mask: Mask for control when using regmap set_pull_down + * @pull_down_val_on: Enabling value for control when using regmap + * set_pull_down * * @enable_time: Time taken for initial enable of regulator (in uS). * @off_on_delay: guard time (in uS), before re-enabling a regulator @@ -345,6 +353,12 @@ struct regulator_desc { unsigned int active_discharge_off; unsigned int active_discharge_mask; unsigned int active_discharge_reg; + unsigned int soft_start_reg; + unsigned int soft_start_mask; + unsigned int soft_start_val_on; + unsigned int pull_down_reg; + unsigned int pull_down_mask; + unsigned int pull_down_val_on; unsigned int enable_time; @@ -429,6 +443,8 @@ struct regulator_dev { struct regulator_enable_gpio *ena_pin; unsigned int ena_gpio_state:1; + unsigned int is_switch:1; + /* time when this regulator was disabled last time */ unsigned long last_off_jiffy; }; @@ -476,6 +492,8 @@ int regulator_set_voltage_time_sel(struct regulator_dev *rdev, unsigned int new_selector); int regulator_set_bypass_regmap(struct regulator_dev *rdev, bool enable); int regulator_get_bypass_regmap(struct regulator_dev *rdev, bool *enable); +int regulator_set_soft_start_regmap(struct regulator_dev *rdev); +int regulator_set_pull_down_regmap(struct regulator_dev *rdev); int regulator_set_active_discharge_regmap(struct regulator_dev *rdev, bool enable); diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index ad3e5158e586..9cd4fef37203 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -65,7 +65,7 @@ struct regulator_state { int uV; /* suspend voltage */ unsigned int mode; /* suspend regulator operating mode */ int enabled; /* is regulator enabled in this suspend state */ - int disabled; /* is the regulator disbled in this suspend state */ + int disabled; /* is the regulator disabled in this suspend state */ }; /** @@ -108,6 +108,12 @@ struct regulator_state { * @initial_state: Suspend state to set by default. * @initial_mode: Mode to set at startup. * @ramp_delay: Time to settle down after voltage change (unit: uV/us) + * @settling_time: Time to settle down after voltage change when voltage + * change is non-linear (unit: microseconds). + * @settling_time_up: Time to settle down after voltage increase when voltage + * change is non-linear (unit: microseconds). + * @settling_time_down : Time to settle down after voltage decrease when + * voltage change is non-linear (unit: microseconds). * @active_discharge: Enable/disable active discharge. The enum * regulator_active_discharge values are used for * initialisation. @@ -149,6 +155,9 @@ struct regulation_constraints { unsigned int initial_mode; unsigned int ramp_delay; + unsigned int settling_time; + unsigned int settling_time_up; + unsigned int settling_time_down; unsigned int enable_time; unsigned int active_discharge; diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h index 70c6c66c5bcf..e0ccf46f66cf 100644 --- a/include/linux/regulator/pfuze100.h +++ b/include/linux/regulator/pfuze100.h @@ -48,6 +48,7 @@ #define PFUZE200_VGEN4 10 #define PFUZE200_VGEN5 11 #define PFUZE200_VGEN6 12 +#define PFUZE200_COIN 13 #define PFUZE3000_SW1A 0 #define PFUZE3000_SW1B 1 diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 8265d351c9f0..81da49564ff4 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -346,6 +346,7 @@ struct rproc_ops { * a message. * @RPROC_RUNNING: device is up and running * @RPROC_CRASHED: device has crashed; need to start recovery + * @RPROC_DELETED: device is deleted * @RPROC_LAST: just keep this one at the end * * Please note that the values of these states are used as indices @@ -359,7 +360,8 @@ enum rproc_state { RPROC_SUSPENDED = 1, RPROC_RUNNING = 2, RPROC_CRASHED = 3, - RPROC_LAST = 4, + RPROC_DELETED = 4, + RPROC_LAST = 5, }; /** @@ -397,7 +399,6 @@ enum rproc_crash_type { * @num_traces: number of trace buffers * @carveouts: list of physically contiguous memory allocations * @mappings: list of iommu mappings we initiated, needed on shutdown - * @firmware_loading_complete: marks e/o asynchronous firmware loading * @bootaddr: address of first instruction to boot rproc with (optional) * @rvdevs: list of remote virtio devices * @subdevs: list of subdevices, to following the running state @@ -429,7 +430,6 @@ struct rproc { int num_traces; struct list_head carveouts; struct list_head mappings; - struct completion firmware_loading_complete; u32 bootaddr; struct list_head rvdevs; struct list_head subdevs; diff --git a/include/linux/reservation.h b/include/linux/reservation.h index d9706a6f5ae2..156cfd330b66 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -145,6 +145,60 @@ reservation_object_get_list(struct reservation_object *obj) } /** + * reservation_object_lock - lock the reservation object + * @obj: the reservation object + * @ctx: the locking context + * + * Locks the reservation object for exclusive access and modification. Note, + * that the lock is only against other writers, readers will run concurrently + * with a writer under RCU. The seqlock is used to notify readers if they + * overlap with a writer. + * + * As the reservation object may be locked by multiple parties in an + * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle + * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation + * object may be locked by itself by passing NULL as @ctx. + */ +static inline int +reservation_object_lock(struct reservation_object *obj, + struct ww_acquire_ctx *ctx) +{ + return ww_mutex_lock(&obj->lock, ctx); +} + +/** + * reservation_object_trylock - trylock the reservation object + * @obj: the reservation object + * + * Tries to lock the reservation object for exclusive access and modification. + * Note, that the lock is only against other writers, readers will run + * concurrently with a writer under RCU. The seqlock is used to notify readers + * if they overlap with a writer. + * + * Also note that since no context is provided, no deadlock protection is + * possible. + * + * Returns true if the lock was acquired, false otherwise. + */ +static inline bool __must_check +reservation_object_trylock(struct reservation_object *obj) +{ + return ww_mutex_trylock(&obj->lock); +} + +/** + * reservation_object_unlock - unlock the reservation object + * @obj: the reservation object + * + * Unlocks the reservation object following exclusive access. + */ +static inline void +reservation_object_unlock(struct reservation_object *obj) +{ + ww_mutex_unlock(&obj->lock); +} + +/** * reservation_object_get_excl - get the reservation object's * exclusive fence, with update-side lock held * @obj: the reservation object diff --git a/include/linux/reset.h b/include/linux/reset.h index 5daff15722d3..13d8681210d5 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -13,10 +13,15 @@ int reset_control_deassert(struct reset_control *rstc); int reset_control_status(struct reset_control *rstc); struct reset_control *__of_reset_control_get(struct device_node *node, - const char *id, int index, int shared); + const char *id, int index, bool shared, + bool optional); +struct reset_control *__reset_control_get(struct device *dev, const char *id, + int index, bool shared, + bool optional); void reset_control_put(struct reset_control *rstc); struct reset_control *__devm_reset_control_get(struct device *dev, - const char *id, int index, int shared); + const char *id, int index, bool shared, + bool optional); int __must_check device_reset(struct device *dev); @@ -29,31 +34,26 @@ static inline int device_reset_optional(struct device *dev) static inline int reset_control_reset(struct reset_control *rstc) { - WARN_ON(1); return 0; } static inline int reset_control_assert(struct reset_control *rstc) { - WARN_ON(1); return 0; } static inline int reset_control_deassert(struct reset_control *rstc) { - WARN_ON(1); return 0; } static inline int reset_control_status(struct reset_control *rstc) { - WARN_ON(1); return 0; } static inline void reset_control_put(struct reset_control *rstc) { - WARN_ON(1); } static inline int __must_check device_reset(struct device *dev) @@ -69,16 +69,24 @@ static inline int device_reset_optional(struct device *dev) static inline struct reset_control *__of_reset_control_get( struct device_node *node, - const char *id, int index, int shared) + const char *id, int index, bool shared, + bool optional) +{ + return optional ? NULL : ERR_PTR(-ENOTSUPP); +} + +static inline struct reset_control *__reset_control_get( + struct device *dev, const char *id, + int index, bool shared, bool optional) { - return ERR_PTR(-ENOTSUPP); + return optional ? NULL : ERR_PTR(-ENOTSUPP); } static inline struct reset_control *__devm_reset_control_get( - struct device *dev, - const char *id, int index, int shared) + struct device *dev, const char *id, + int index, bool shared, bool optional) { - return ERR_PTR(-ENOTSUPP); + return optional ? NULL : ERR_PTR(-ENOTSUPP); } #endif /* CONFIG_RESET_CONTROLLER */ @@ -104,7 +112,7 @@ __must_check reset_control_get_exclusive(struct device *dev, const char *id) #ifndef CONFIG_RESET_CONTROLLER WARN_ON(1); #endif - return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 0); + return __reset_control_get(dev, id, 0, false, false); } /** @@ -132,19 +140,19 @@ __must_check reset_control_get_exclusive(struct device *dev, const char *id) static inline struct reset_control *reset_control_get_shared( struct device *dev, const char *id) { - return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 1); + return __reset_control_get(dev, id, 0, true, false); } static inline struct reset_control *reset_control_get_optional_exclusive( struct device *dev, const char *id) { - return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 0); + return __reset_control_get(dev, id, 0, false, true); } static inline struct reset_control *reset_control_get_optional_shared( struct device *dev, const char *id) { - return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, 1); + return __reset_control_get(dev, id, 0, true, true); } /** @@ -160,7 +168,7 @@ static inline struct reset_control *reset_control_get_optional_shared( static inline struct reset_control *of_reset_control_get_exclusive( struct device_node *node, const char *id) { - return __of_reset_control_get(node, id, 0, 0); + return __of_reset_control_get(node, id, 0, false, false); } /** @@ -185,7 +193,7 @@ static inline struct reset_control *of_reset_control_get_exclusive( static inline struct reset_control *of_reset_control_get_shared( struct device_node *node, const char *id) { - return __of_reset_control_get(node, id, 0, 1); + return __of_reset_control_get(node, id, 0, true, false); } /** @@ -202,7 +210,7 @@ static inline struct reset_control *of_reset_control_get_shared( static inline struct reset_control *of_reset_control_get_exclusive_by_index( struct device_node *node, int index) { - return __of_reset_control_get(node, NULL, index, 0); + return __of_reset_control_get(node, NULL, index, false, false); } /** @@ -230,7 +238,7 @@ static inline struct reset_control *of_reset_control_get_exclusive_by_index( static inline struct reset_control *of_reset_control_get_shared_by_index( struct device_node *node, int index) { - return __of_reset_control_get(node, NULL, index, 1); + return __of_reset_control_get(node, NULL, index, true, false); } /** @@ -252,7 +260,7 @@ __must_check devm_reset_control_get_exclusive(struct device *dev, #ifndef CONFIG_RESET_CONTROLLER WARN_ON(1); #endif - return __devm_reset_control_get(dev, id, 0, 0); + return __devm_reset_control_get(dev, id, 0, false, false); } /** @@ -267,19 +275,19 @@ __must_check devm_reset_control_get_exclusive(struct device *dev, static inline struct reset_control *devm_reset_control_get_shared( struct device *dev, const char *id) { - return __devm_reset_control_get(dev, id, 0, 1); + return __devm_reset_control_get(dev, id, 0, true, false); } static inline struct reset_control *devm_reset_control_get_optional_exclusive( struct device *dev, const char *id) { - return __devm_reset_control_get(dev, id, 0, 0); + return __devm_reset_control_get(dev, id, 0, false, true); } static inline struct reset_control *devm_reset_control_get_optional_shared( struct device *dev, const char *id) { - return __devm_reset_control_get(dev, id, 0, 1); + return __devm_reset_control_get(dev, id, 0, true, true); } /** @@ -297,7 +305,7 @@ static inline struct reset_control *devm_reset_control_get_optional_shared( static inline struct reset_control * devm_reset_control_get_exclusive_by_index(struct device *dev, int index) { - return __devm_reset_control_get(dev, NULL, index, 0); + return __devm_reset_control_get(dev, NULL, index, false, false); } /** @@ -313,7 +321,7 @@ devm_reset_control_get_exclusive_by_index(struct device *dev, int index) static inline struct reset_control * devm_reset_control_get_shared_by_index(struct device *dev, int index) { - return __devm_reset_control_get(dev, NULL, index, 1); + return __devm_reset_control_get(dev, NULL, index, true, false); } /* diff --git a/include/linux/resource.h b/include/linux/resource.h index 5bc3116e649c..277afdad6589 100644 --- a/include/linux/resource.h +++ b/include/linux/resource.h @@ -6,7 +6,7 @@ struct task_struct; -int getrusage(struct task_struct *p, int who, struct rusage __user *ru); +void getrusage(struct task_struct *p, int who, struct rusage *ru); int do_prlimit(struct task_struct *tsk, unsigned int resource, struct rlimit *new_rlim, struct rlimit *old_rlim); diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index 0d905d8ec553..19df8422606c 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -11,6 +11,14 @@ struct timespec; struct compat_timespec; struct pollfd; +enum timespec_type { + TT_NONE = 0, + TT_NATIVE = 1, +#ifdef CONFIG_COMPAT + TT_COMPAT = 2, +#endif +}; + /* * System call restart block. */ @@ -29,10 +37,13 @@ struct restart_block { /* For nanosleep */ struct { clockid_t clockid; - struct timespec __user *rmtp; + enum timespec_type type; + union { + struct timespec __user *rmtp; #ifdef CONFIG_COMPAT - struct compat_timespec __user *compat_rmtp; + struct compat_timespec __user *compat_rmtp; #endif + }; u64 expires; } nanosleep; /* For poll */ diff --git a/include/linux/rfkill-regulator.h b/include/linux/rfkill-regulator.h deleted file mode 100644 index aca36bc83315..000000000000 --- a/include/linux/rfkill-regulator.h +++ /dev/null @@ -1,48 +0,0 @@ -/* - * rfkill-regulator.c - Regulator consumer driver for rfkill - * - * Copyright (C) 2009 Guiming Zhuo <gmzhuo@gmail.com> - * Copyright (C) 2011 Antonio Ospite <ospite@studenti.unina.it> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#ifndef __LINUX_RFKILL_REGULATOR_H -#define __LINUX_RFKILL_REGULATOR_H - -/* - * Use "vrfkill" as supply id when declaring the regulator consumer: - * - * static struct regulator_consumer_supply pcap_regulator_V6_consumers [] = { - * { .dev_name = "rfkill-regulator.0", .supply = "vrfkill" }, - * }; - * - * If you have several regulator driven rfkill, you can append a numerical id to - * .dev_name as done above, and use the same id when declaring the platform - * device: - * - * static struct rfkill_regulator_platform_data ezx_rfkill_bt_data = { - * .name = "ezx-bluetooth", - * .type = RFKILL_TYPE_BLUETOOTH, - * }; - * - * static struct platform_device a910_rfkill = { - * .name = "rfkill-regulator", - * .id = 0, - * .dev = { - * .platform_data = &ezx_rfkill_bt_data, - * }, - * }; - */ - -#include <linux/rfkill.h> - -struct rfkill_regulator_platform_data { - char *name; /* the name for the rfkill switch */ - enum rfkill_type type; /* the type as specified in rfkill.h */ -}; - -#endif /* __LINUX_RFKILL_REGULATOR_H */ diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 5c132d3188be..7d56a7ea2b2e 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -25,7 +25,7 @@ #include <linux/list_nulls.h> #include <linux/workqueue.h> #include <linux/mutex.h> -#include <linux/rcupdate.h> +#include <linux/rculist.h> /* * The end of the chain is marked with a special nulls marks which has @@ -49,6 +49,21 @@ /* Base bits plus 1 bit for nulls marker */ #define RHT_HASH_RESERVED_SPACE (RHT_BASE_BITS + 1) +/* Maximum chain length before rehash + * + * The maximum (not average) chain length grows with the size of the hash + * table, at a rate of (log N)/(log log N). + * + * The value of 16 is selected so that even if the hash table grew to + * 2^32 you would not expect the maximum chain length to exceed it + * unless we are under attack (or extremely unlucky). + * + * As this limit is only to detect attacks, we don't need to set it to a + * lower value as you'd need the chain length to vastly exceed 16 to have + * any real effect on the system. + */ +#define RHT_ELASTICITY 16u + struct rhash_head { struct rhash_head __rcu *next; }; @@ -61,6 +76,7 @@ struct rhlist_head { /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets + * @nest: Number of bits of first-level nested table. * @rehash: Current bucket being rehashed * @hash_rnd: Random seed to fold into hash * @locks_mask: Mask to apply before accessing locks[] @@ -68,10 +84,12 @@ struct rhlist_head { * @walkers: List of active walkers * @rcu: RCU structure for freeing the table * @future_tbl: Table under construction during rehashing + * @ntbl: Nested table used when out of memory. * @buckets: size * hash buckets */ struct bucket_table { unsigned int size; + unsigned int nest; unsigned int rehash; u32 hash_rnd; unsigned int locks_mask; @@ -81,7 +99,7 @@ struct bucket_table { struct bucket_table __rcu *future_tbl; - struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; + struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; /** @@ -107,29 +125,25 @@ struct rhashtable; * @key_len: Length of key * @key_offset: Offset of key in struct to be hashed * @head_offset: Offset of rhash_head in struct to be hashed - * @insecure_max_entries: Maximum number of entries (may be exceeded) * @max_size: Maximum size while expanding * @min_size: Minimum size while shrinking - * @nulls_base: Base value to generate nulls marker - * @insecure_elasticity: Set to true to disable chain length checks - * @automatic_shrinking: Enable automatic shrinking of tables * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) + * @automatic_shrinking: Enable automatic shrinking of tables + * @nulls_base: Base value to generate nulls marker * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) * @obj_hashfn: Function to hash object * @obj_cmpfn: Function to compare key with object */ struct rhashtable_params { - size_t nelem_hint; - size_t key_len; - size_t key_offset; - size_t head_offset; - unsigned int insecure_max_entries; + u16 nelem_hint; + u16 key_len; + u16 key_offset; + u16 head_offset; unsigned int max_size; - unsigned int min_size; - u32 nulls_base; - bool insecure_elasticity; + u16 min_size; bool automatic_shrinking; - size_t locks_mul; + u8 locks_mul; + u32 nulls_base; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; rht_obj_cmpfn_t obj_cmpfn; @@ -140,8 +154,8 @@ struct rhashtable_params { * @tbl: Bucket table * @nelems: Number of elements in table * @key_len: Key length for hashfn - * @elasticity: Maximum chain length before rehash * @p: Configuration parameters + * @max_elems: Maximum number of elements in table * @rhlist: True if this is an rhltable * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping @@ -151,8 +165,8 @@ struct rhashtable { struct bucket_table __rcu *tbl; atomic_t nelems; unsigned int key_len; - unsigned int elasticity; struct rhashtable_params p; + unsigned int max_elems; bool rhlist; struct work_struct run_work; struct mutex mutex; @@ -315,8 +329,7 @@ static inline bool rht_grow_above_100(const struct rhashtable *ht, static inline bool rht_grow_above_max(const struct rhashtable *ht, const struct bucket_table *tbl) { - return ht->p.insecure_max_entries && - atomic_read(&ht->nelems) >= ht->p.insecure_max_entries; + return atomic_read(&ht->nelems) >= ht->max_elems; } /* The bucket lock is selected based on the hash and protects mutations @@ -374,6 +387,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, void *arg); void rhashtable_destroy(struct rhashtable *ht); +struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl, + unsigned int hash); +struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, + struct bucket_table *tbl, + unsigned int hash); + #define rht_dereference(p, ht) \ rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht)) @@ -389,6 +408,27 @@ void rhashtable_destroy(struct rhashtable *ht); #define rht_entry(tpos, pos, member) \ ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) +static inline struct rhash_head __rcu *const *rht_bucket( + const struct bucket_table *tbl, unsigned int hash) +{ + return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : + &tbl->buckets[hash]; +} + +static inline struct rhash_head __rcu **rht_bucket_var( + struct bucket_table *tbl, unsigned int hash) +{ + return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : + &tbl->buckets[hash]; +} + +static inline struct rhash_head __rcu **rht_bucket_insert( + struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) +{ + return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) : + &tbl->buckets[hash]; +} + /** * rht_for_each_continue - continue iterating over hash chain * @pos: the &struct rhash_head to use as a loop cursor. @@ -408,7 +448,7 @@ void rhashtable_destroy(struct rhashtable *ht); * @hash: the hash value / bucket index */ #define rht_for_each(pos, tbl, hash) \ - rht_for_each_continue(pos, (tbl)->buckets[hash], tbl, hash) + rht_for_each_continue(pos, *rht_bucket(tbl, hash), tbl, hash) /** * rht_for_each_entry_continue - continue iterating over hash chain @@ -433,7 +473,7 @@ void rhashtable_destroy(struct rhashtable *ht); * @member: name of the &struct rhash_head within the hashable struct. */ #define rht_for_each_entry(tpos, pos, tbl, hash, member) \ - rht_for_each_entry_continue(tpos, pos, (tbl)->buckets[hash], \ + rht_for_each_entry_continue(tpos, pos, *rht_bucket(tbl, hash), \ tbl, hash, member) /** @@ -448,13 +488,13 @@ void rhashtable_destroy(struct rhashtable *ht); * This hash chain list-traversal primitive allows for the looped code to * remove the loop cursor from the list. */ -#define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \ - for (pos = rht_dereference_bucket((tbl)->buckets[hash], tbl, hash), \ - next = !rht_is_a_nulls(pos) ? \ - rht_dereference_bucket(pos->next, tbl, hash) : NULL; \ - (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ - pos = next, \ - next = !rht_is_a_nulls(pos) ? \ +#define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \ + for (pos = rht_dereference_bucket(*rht_bucket(tbl, hash), tbl, hash), \ + next = !rht_is_a_nulls(pos) ? \ + rht_dereference_bucket(pos->next, tbl, hash) : NULL; \ + (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ + pos = next, \ + next = !rht_is_a_nulls(pos) ? \ rht_dereference_bucket(pos->next, tbl, hash) : NULL) /** @@ -485,7 +525,7 @@ void rhashtable_destroy(struct rhashtable *ht); * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_rcu(pos, tbl, hash) \ - rht_for_each_rcu_continue(pos, (tbl)->buckets[hash], tbl, hash) + rht_for_each_rcu_continue(pos, *rht_bucket(tbl, hash), tbl, hash) /** * rht_for_each_entry_rcu_continue - continue iterating over rcu hash chain @@ -518,8 +558,8 @@ void rhashtable_destroy(struct rhashtable *ht); * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ -#define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ - rht_for_each_entry_rcu_continue(tpos, pos, (tbl)->buckets[hash],\ +#define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ + rht_for_each_entry_rcu_continue(tpos, pos, *rht_bucket(tbl, hash), \ tbl, hash, member) /** @@ -565,7 +605,7 @@ static inline struct rhash_head *__rhashtable_lookup( .ht = ht, .key = key, }; - const struct bucket_table *tbl; + struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; @@ -696,9 +736,13 @@ slow_path: return rhashtable_insert_slow(ht, key, obj); } - elasticity = ht->elasticity; - pprev = &tbl->buckets[hash]; - rht_for_each(head, tbl, hash) { + elasticity = RHT_ELASTICITY; + pprev = rht_bucket_insert(ht, tbl, hash); + data = ERR_PTR(-ENOMEM); + if (!pprev) + goto out; + + rht_for_each_continue(head, *pprev, tbl, hash) { struct rhlist_head *plist; struct rhlist_head *list; @@ -736,7 +780,7 @@ slow_path: if (unlikely(rht_grow_above_100(ht, tbl))) goto slow_path; - head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); + head = rht_dereference_bucket(*pprev, tbl, hash); RCU_INIT_POINTER(obj->next, head); if (rhlist) { @@ -746,7 +790,7 @@ slow_path: RCU_INIT_POINTER(list->next, NULL); } - rcu_assign_pointer(tbl->buckets[hash], obj); + rcu_assign_pointer(*pprev, obj); atomic_inc(&ht->nelems); if (rht_grow_above_75(ht, tbl)) @@ -882,6 +926,28 @@ static inline int rhashtable_lookup_insert_fast( } /** + * rhashtable_lookup_get_insert_fast - lookup and insert object into hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Just like rhashtable_lookup_insert_fast(), but this function returns the + * object if it exists, NULL if it did not and the insertion was successful, + * and an ERR_PTR otherwise. + */ +static inline void *rhashtable_lookup_get_insert_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + const char *key = rht_obj(ht, obj); + + BUG_ON(ht->p.obj_hashfn); + + return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params, + false); +} + +/** * rhashtable_lookup_insert_key - search and insert object to hash table * with explicit key * @ht: hash table @@ -955,8 +1021,8 @@ static inline int __rhashtable_remove_fast_one( spin_lock_bh(lock); - pprev = &tbl->buckets[hash]; - rht_for_each(he, tbl, hash) { + pprev = rht_bucket_var(tbl, hash); + rht_for_each_continue(he, *pprev, tbl, hash) { struct rhlist_head *list; list = container_of(he, struct rhlist_head, rhead); @@ -1107,8 +1173,8 @@ static inline int __rhashtable_replace_fast( spin_lock_bh(lock); - pprev = &tbl->buckets[hash]; - rht_for_each(he, tbl, hash) { + pprev = rht_bucket_var(tbl, hash); + rht_for_each_continue(he, *pprev, tbl, hash) { if (he != obj_old) { pprev = &he->next; continue; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index b6d4568795a7..ee9b461af095 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -185,7 +185,7 @@ size_t ring_buffer_page_len(void *page); void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu); -void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data); +void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data); int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page, size_t len, int cpu, int full); diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 15321fb1df6b..43ef2c30cb0f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -9,6 +9,7 @@ #include <linux/mm.h> #include <linux/rwsem.h> #include <linux/memcontrol.h> +#include <linux/highmem.h> /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -82,19 +83,17 @@ struct anon_vma_chain { }; enum ttu_flags { - TTU_UNMAP = 1, /* unmap mode */ - TTU_MIGRATION = 2, /* migration mode */ - TTU_MUNLOCK = 4, /* munlock mode */ - TTU_LZFREE = 8, /* lazy free mode */ - TTU_SPLIT_HUGE_PMD = 16, /* split huge PMD if any */ - - TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */ - TTU_IGNORE_ACCESS = (1 << 9), /* don't age */ - TTU_IGNORE_HWPOISON = (1 << 10),/* corrupted page is recoverable */ - TTU_BATCH_FLUSH = (1 << 11), /* Batch TLB flushes where possible + TTU_MIGRATION = 0x1, /* migration mode */ + TTU_MUNLOCK = 0x2, /* munlock mode */ + + TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ + TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ + TTU_IGNORE_ACCESS = 0x10, /* don't age */ + TTU_IGNORE_HWPOISON = 0x20, /* corrupted page is recoverable */ + TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible * and caller guarantees they will * do a final flush if necessary */ - TTU_RMAP_LOCKED = (1 << 12) /* do not grab rmap lock: + TTU_RMAP_LOCKED = 0x80 /* do not grab rmap lock: * caller holds it */ }; @@ -192,45 +191,32 @@ static inline void page_dup_rmap(struct page *page, bool compound) int page_referenced(struct page *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); -#define TTU_ACTION(x) ((x) & TTU_ACTION_MASK) +bool try_to_unmap(struct page *, enum ttu_flags flags); -int try_to_unmap(struct page *, enum ttu_flags flags); +/* Avoid racy checks */ +#define PVMW_SYNC (1 << 0) +/* Look for migarion entries rather than present PTEs */ +#define PVMW_MIGRATION (1 << 1) -/* - * Used by uprobes to replace a userspace page safely - */ -pte_t *__page_check_address(struct page *, struct mm_struct *, - unsigned long, spinlock_t **, int); +struct page_vma_mapped_walk { + struct page *page; + struct vm_area_struct *vma; + unsigned long address; + pmd_t *pmd; + pte_t *pte; + spinlock_t *ptl; + unsigned int flags; +}; -static inline pte_t *page_check_address(struct page *page, struct mm_struct *mm, - unsigned long address, - spinlock_t **ptlp, int sync) +static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { - pte_t *ptep; - - __cond_lock(*ptlp, ptep = __page_check_address(page, mm, address, - ptlp, sync)); - return ptep; + if (pvmw->pte) + pte_unmap(pvmw->pte); + if (pvmw->ptl) + spin_unlock(pvmw->ptl); } -/* - * Used by idle page tracking to check if a page was referenced via page - * tables. - */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -bool page_check_address_transhuge(struct page *page, struct mm_struct *mm, - unsigned long address, pmd_t **pmdp, - pte_t **ptep, spinlock_t **ptlp); -#else -static inline bool page_check_address_transhuge(struct page *page, - struct mm_struct *mm, unsigned long address, - pmd_t **pmdp, pte_t **ptep, spinlock_t **ptlp) -{ - *ptep = page_check_address(page, mm, address, ptlp, 0); - *pmdp = NULL; - return !!*ptep; -} -#endif +bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); /* * Used by swapoff to help locate where page is expected in vma. @@ -249,7 +235,7 @@ int page_mkclean(struct page *); * called in munlock()/munmap() path to check for other vmas holding * the page mlocked. */ -int try_to_munlock(struct page *); +void try_to_munlock(struct page *); void remove_migration_ptes(struct page *old, struct page *new, bool locked); @@ -271,15 +257,19 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); */ struct rmap_walk_control { void *arg; - int (*rmap_one)(struct page *page, struct vm_area_struct *vma, + /* + * Return false if page table scanning in rmap_walk should be stopped. + * Otherwise, return true. + */ + bool (*rmap_one)(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct page *page); struct anon_vma *(*anon_lock)(struct page *page); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -int rmap_walk(struct page *page, struct rmap_walk_control *rwc); -int rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ @@ -295,7 +285,7 @@ static inline int page_referenced(struct page *page, int is_locked, return 0; } -#define try_to_unmap(page, refs) SWAP_FAIL +#define try_to_unmap(page, refs) false static inline int page_mkclean(struct page *page) { @@ -305,13 +295,4 @@ static inline int page_mkclean(struct page *page) #endif /* CONFIG_MMU */ -/* - * Return values of try_to_unmap - */ -#define SWAP_SUCCESS 0 -#define SWAP_AGAIN 1 -#define SWAP_FAIL 2 -#define SWAP_MLOCK 3 -#define SWAP_LZFREE 4 - #endif /* _LINUX_RMAP_H */ diff --git a/include/linux/rodata_test.h b/include/linux/rodata_test.h new file mode 100644 index 000000000000..84766bcdd01f --- /dev/null +++ b/include/linux/rodata_test.h @@ -0,0 +1,22 @@ +/* + * rodata_test.h: functional test for mark_rodata_ro function + * + * (C) Copyright 2008 Intel Corporation + * Author: Arjan van de Ven <arjan@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#ifndef _RODATA_TEST_H +#define _RODATA_TEST_H + +#ifdef CONFIG_DEBUG_RODATA_TEST +void rodata_test(void); +#else +static inline void rodata_test(void) {} +#endif + +#endif /* _RODATA_TEST_H */ diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index 18f9e1ae4b7e..10d6ae8bbb7d 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -41,6 +41,7 @@ #include <linux/mod_devicetable.h> #include <linux/kref.h> #include <linux/mutex.h> +#include <linux/poll.h> #define RPMSG_ADDR_ANY 0xFFFFFFFF @@ -156,6 +157,9 @@ int rpmsg_trysendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst); int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst, void *data, int len); +unsigned int rpmsg_poll(struct rpmsg_endpoint *ept, struct file *filp, + poll_table *wait); + #else static inline int register_rpmsg_device(struct rpmsg_device *dev) @@ -254,6 +258,15 @@ static inline int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, return -ENXIO; } +static inline unsigned int rpmsg_poll(struct rpmsg_endpoint *ept, + struct file *filp, poll_table *wait) +{ + /* This shouldn't be possible */ + WARN_ON(1); + + return 0; +} + #endif /* IS_ENABLED(CONFIG_RPMSG) */ /* use a macro to avoid include chaining to get THIS_MODULE */ diff --git a/include/linux/rpmsg/qcom_smd.h b/include/linux/rpmsg/qcom_smd.h index e674b2e3074b..f27917e0a101 100644 --- a/include/linux/rpmsg/qcom_smd.h +++ b/include/linux/rpmsg/qcom_smd.h @@ -6,7 +6,7 @@ struct qcom_smd_edge; -#if IS_ENABLED(CONFIG_RPMSG_QCOM_SMD) || IS_ENABLED(CONFIG_QCOM_SMD) +#if IS_ENABLED(CONFIG_RPMSG_QCOM_SMD) struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent, struct device_node *node); @@ -18,14 +18,12 @@ static inline struct qcom_smd_edge * qcom_smd_register_edge(struct device *parent, struct device_node *node) { - return ERR_PTR(-ENXIO); + return NULL; } static inline int qcom_smd_unregister_edge(struct qcom_smd_edge *edge) { - /* This shouldn't be possible */ - WARN_ON(1); - return -ENXIO; + return 0; } #endif diff --git a/include/linux/rtc.h b/include/linux/rtc.h index b693adac853b..0a0f0d14a5fb 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/interrupt.h> +#include <linux/nvmem-provider.h> #include <uapi/linux/rtc.h> extern int rtc_month_days(unsigned int month, unsigned int year); @@ -32,17 +33,11 @@ static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) return rtc_tm_to_time64(lhs) - rtc_tm_to_time64(rhs); } -/** - * Deprecated. Use rtc_time64_to_tm(). - */ static inline void rtc_time_to_tm(unsigned long time, struct rtc_time *tm) { rtc_time64_to_tm(time, tm); } -/** - * Deprecated. Use rtc_tm_to_time64(). - */ static inline int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time) { *time = rtc_tm_to_time64(tm); @@ -116,7 +111,6 @@ struct rtc_device { struct module *owner; int id; - char name[RTC_DEVICE_NAME_SIZE]; const struct rtc_class_ops *ops; struct mutex ops_lock; @@ -143,6 +137,14 @@ struct rtc_device { /* Some hardware can't support UIE mode */ int uie_unsupported; + bool registered; + + struct nvmem_config *nvmem_config; + struct nvmem_device *nvmem; + /* Old ABI support */ + bool nvram_old_abi; + struct bin_attribute *nvram; + #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL struct work_struct uie_task; struct timer_list uie_timer; @@ -164,6 +166,8 @@ extern struct rtc_device *devm_rtc_device_register(struct device *dev, const char *name, const struct rtc_class_ops *ops, struct module *owner); +struct rtc_device *devm_rtc_allocate_device(struct device *dev); +int __rtc_register_device(struct module *owner, struct rtc_device *rtc); extern void rtc_device_unregister(struct rtc_device *rtc); extern void devm_rtc_device_unregister(struct device *dev, struct rtc_device *rtc); @@ -219,6 +223,9 @@ static inline bool is_leap_year(unsigned int year) return (!(year % 4) && (year % 100)) || !(year % 400); } +#define rtc_register_device(device) \ + __rtc_register_device(THIS_MODULE, device) + #ifdef CONFIG_RTC_HCTOSYS_DEVICE extern int rtc_hctosys_ret; #else diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 1abba5ce2a2f..44fd002f7cd5 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -37,6 +37,9 @@ struct rt_mutex { int line; void *magic; #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif }; struct rt_mutex_waiter; @@ -58,19 +61,33 @@ struct hrtimer_sleeper; #ifdef CONFIG_DEBUG_RT_MUTEXES # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ , .name = #mutexname, .file = __FILE__, .line = __LINE__ -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, __func__) + +# define rt_mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + __rt_mutex_init(mutex, __func__, &__key); \ +} while (0) + extern void rt_mutex_debug_task_free(struct task_struct *tsk); #else # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL) +# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL, NULL) # define rt_mutex_debug_task_free(t) do { } while (0) #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \ + , .dep_map = { .name = #mutexname } +#else +#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) +#endif + #define __RT_MUTEX_INITIALIZER(mutexname) \ { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ , .waiters = RB_ROOT \ , .owner = NULL \ - __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} + __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ + __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)} #define DEFINE_RT_MUTEX(mutexname) \ struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) @@ -86,7 +103,7 @@ static inline int rt_mutex_is_locked(struct rt_mutex *lock) return lock->owner != NULL; } -extern void __rt_mutex_init(struct rt_mutex *lock, const char *name); +extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); extern void rt_mutex_destroy(struct rt_mutex *lock); extern void rt_mutex_lock(struct rt_mutex *lock); diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 57e54847b0b9..dea59c8eec54 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -18,7 +18,8 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags); struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, - unsigned change, gfp_t flags); + unsigned change, u32 event, + gfp_t flags); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags); diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h index c68307bc306f..7343f71783dc 100644 --- a/include/linux/rxrpc.h +++ b/include/linux/rxrpc.h @@ -37,6 +37,8 @@ struct sockaddr_rxrpc { #define RXRPC_SECURITY_KEYRING 2 /* [srvr] set ring of server security keys */ #define RXRPC_EXCLUSIVE_CONNECTION 3 /* Deprecated; use RXRPC_EXCLUSIVE_CALL instead */ #define RXRPC_MIN_SECURITY_LEVEL 4 /* minimum security level */ +#define RXRPC_UPGRADEABLE_SERVICE 5 /* Upgrade service[0] -> service[1] */ +#define RXRPC_SUPPORTED_CMSG 6 /* Get highest supported control message type */ /* * RxRPC control messages @@ -44,15 +46,20 @@ struct sockaddr_rxrpc { * - terminal messages mean that a user call ID tag can be recycled * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg() */ -#define RXRPC_USER_CALL_ID 1 /* sr: user call ID specifier */ -#define RXRPC_ABORT 2 /* sr: abort request / notification [terminal] */ -#define RXRPC_ACK 3 /* -r: [Service] RPC op final ACK received [terminal] */ -#define RXRPC_NET_ERROR 5 /* -r: network error received [terminal] */ -#define RXRPC_BUSY 6 /* -r: server busy received [terminal] */ -#define RXRPC_LOCAL_ERROR 7 /* -r: local error generated [terminal] */ -#define RXRPC_NEW_CALL 8 /* -r: [Service] new incoming call notification */ -#define RXRPC_ACCEPT 9 /* s-: [Service] accept request */ -#define RXRPC_EXCLUSIVE_CALL 10 /* s-: Call should be on exclusive connection */ +enum rxrpc_cmsg_type { + RXRPC_USER_CALL_ID = 1, /* sr: user call ID specifier */ + RXRPC_ABORT = 2, /* sr: abort request / notification [terminal] */ + RXRPC_ACK = 3, /* -r: [Service] RPC op final ACK received [terminal] */ + RXRPC_NET_ERROR = 5, /* -r: network error received [terminal] */ + RXRPC_BUSY = 6, /* -r: server busy received [terminal] */ + RXRPC_LOCAL_ERROR = 7, /* -r: local error generated [terminal] */ + RXRPC_NEW_CALL = 8, /* -r: [Service] new incoming call notification */ + RXRPC_ACCEPT = 9, /* s-: [Service] accept request */ + RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */ + RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */ + RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */ + RXRPC__SUPPORTED +}; /* * RxRPC security levels diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index f017fd6e69c4..a1904aadbc45 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -176,6 +176,25 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth); int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin); /** + * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap, + * limiting the depth used from each word. + * @sb: Bitmap to allocate from. + * @alloc_hint: Hint for where to start searching for a free bit. + * @shallow_depth: The maximum number of bits to allocate from a single word. + * + * This rather specific operation allows for having multiple users with + * different allocation limits. E.g., there can be a high-priority class that + * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow() + * with a @shallow_depth of (1 << (@sb->shift - 1)). Then, the low-priority + * class can only allocate half of the total bits in the bitmap, preventing it + * from starving out the high-priority class. + * + * Return: Non-negative allocated bit number if successful, -1 otherwise. + */ +int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, + unsigned long shallow_depth); + +/** * sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap. * @sb: Bitmap to check. * @@ -259,6 +278,26 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr) unsigned int sbitmap_weight(const struct sbitmap *sb); /** + * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file. + * @sb: Bitmap to show. + * @m: struct seq_file to write to. + * + * This is intended for debugging. The format may change at any time. + */ +void sbitmap_show(struct sbitmap *sb, struct seq_file *m); + +/** + * sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct + * seq_file. + * @sb: Bitmap to show. + * @m: struct seq_file to write to. + * + * This is intended for debugging. The output isn't guaranteed to be internally + * consistent. + */ +void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m); + +/** * sbitmap_queue_init_node() - Initialize a &struct sbitmap_queue on a specific * memory node. * @sbq: Bitmap queue to initialize. @@ -306,6 +345,19 @@ void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth); int __sbitmap_queue_get(struct sbitmap_queue *sbq); /** + * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct + * sbitmap_queue, limiting the depth used from each word, with preemption + * already disabled. + * @sbq: Bitmap queue to allocate from. + * @shallow_depth: The maximum number of bits to allocate from a single word. + * See sbitmap_get_shallow(). + * + * Return: Non-negative allocated bit number if successful, -1 otherwise. + */ +int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, + unsigned int shallow_depth); + +/** * sbitmap_queue_get() - Try to allocate a free bit from a &struct * sbitmap_queue. * @sbq: Bitmap queue to allocate from. @@ -326,6 +378,29 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq, } /** + * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct + * sbitmap_queue, limiting the depth used from each word. + * @sbq: Bitmap queue to allocate from. + * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to + * sbitmap_queue_clear()). + * @shallow_depth: The maximum number of bits to allocate from a single word. + * See sbitmap_get_shallow(). + * + * Return: Non-negative allocated bit number if successful, -1 otherwise. + */ +static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, + unsigned int *cpu, + unsigned int shallow_depth) +{ + int nr; + + *cpu = get_cpu(); + nr = __sbitmap_queue_get_shallow(sbq, shallow_depth); + put_cpu(); + return nr; +} + +/** * sbitmap_queue_clear() - Free an allocated bit and wake up waiters on a * &struct sbitmap_queue. * @sbq: Bitmap to free from. @@ -370,4 +445,14 @@ static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq, */ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq); +/** + * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct + * seq_file. + * @sbq: Bitmap queue to show. + * @m: struct seq_file to write to. + * + * This is intended for debugging. The format may change at any time. + */ +void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m); + #endif /* __LINUX_SCALE_BITMAP_H */ diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index cb3c8fe6acd7..4b3286ac60c8 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -278,6 +278,8 @@ size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents, const void *buf, size_t buflen, off_t skip); size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip); +size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents, + size_t buflen, off_t skip); /* * Maximum number of entries that will be allocated in one piece, if diff --git a/include/linux/sched.h b/include/linux/sched.h index ad3ec9ec61f7..8337e2db0bb2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1,198 +1,57 @@ #ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H -#include <uapi/linux/sched.h> - -#include <linux/sched/prio.h> - - -struct sched_param { - int sched_priority; -}; - -#include <asm/param.h> /* for HZ */ +/* + * Define 'struct task_struct' and provide the main scheduler + * APIs (schedule(), wakeup variants, etc.) + */ -#include <linux/capability.h> -#include <linux/threads.h> -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/timex.h> -#include <linux/jiffies.h> -#include <linux/plist.h> -#include <linux/rbtree.h> -#include <linux/thread_info.h> -#include <linux/cpumask.h> -#include <linux/errno.h> -#include <linux/nodemask.h> -#include <linux/mm_types.h> -#include <linux/preempt.h> +#include <uapi/linux/sched.h> -#include <asm/page.h> -#include <asm/ptrace.h> -#include <linux/cputime.h> +#include <asm/current.h> -#include <linux/smp.h> +#include <linux/pid.h> #include <linux/sem.h> #include <linux/shm.h> -#include <linux/signal.h> -#include <linux/compiler.h> -#include <linux/completion.h> -#include <linux/pid.h> -#include <linux/percpu.h> -#include <linux/topology.h> +#include <linux/kcov.h> +#include <linux/mutex.h> +#include <linux/plist.h> +#include <linux/hrtimer.h> #include <linux/seccomp.h> +#include <linux/nodemask.h> #include <linux/rcupdate.h> -#include <linux/rculist.h> -#include <linux/rtmutex.h> - -#include <linux/time.h> -#include <linux/param.h> #include <linux/resource.h> -#include <linux/timer.h> -#include <linux/hrtimer.h> -#include <linux/kcov.h> -#include <linux/task_io_accounting.h> #include <linux/latencytop.h> -#include <linux/cred.h> -#include <linux/llist.h> -#include <linux/uidgid.h> -#include <linux/gfp.h> -#include <linux/magic.h> -#include <linux/cgroup-defs.h> - -#include <asm/processor.h> - -#define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */ - -/* - * Extended scheduling parameters data structure. - * - * This is needed because the original struct sched_param can not be - * altered without introducing ABI issues with legacy applications - * (e.g., in sched_getparam()). - * - * However, the possibility of specifying more than just a priority for - * the tasks may be useful for a wide variety of application fields, e.g., - * multimedia, streaming, automation and control, and many others. - * - * This variant (sched_attr) is meant at describing a so-called - * sporadic time-constrained task. In such model a task is specified by: - * - the activation period or minimum instance inter-arrival time; - * - the maximum (or average, depending on the actual scheduling - * discipline) computation time of all instances, a.k.a. runtime; - * - the deadline (relative to the actual activation time) of each - * instance. - * Very briefly, a periodic (sporadic) task asks for the execution of - * some specific computation --which is typically called an instance-- - * (at most) every period. Moreover, each instance typically lasts no more - * than the runtime and must be completed by time instant t equal to - * the instance activation time + the deadline. - * - * This is reflected by the actual fields of the sched_attr structure: - * - * @size size of the structure, for fwd/bwd compat. - * - * @sched_policy task's scheduling policy - * @sched_flags for customizing the scheduler behaviour - * @sched_nice task's nice value (SCHED_NORMAL/BATCH) - * @sched_priority task's static priority (SCHED_FIFO/RR) - * @sched_deadline representative of the task's deadline - * @sched_runtime representative of the task's runtime - * @sched_period representative of the task's period - * - * Given this task model, there are a multiplicity of scheduling algorithms - * and policies, that can be used to ensure all the tasks will make their - * timing constraints. - * - * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the - * only user of this new interface. More information about the algorithm - * available in the scheduling class file or in Documentation/. - */ -struct sched_attr { - u32 size; - - u32 sched_policy; - u64 sched_flags; - - /* SCHED_NORMAL, SCHED_BATCH */ - s32 sched_nice; - - /* SCHED_FIFO, SCHED_RR */ - u32 sched_priority; - - /* SCHED_DEADLINE */ - u64 sched_runtime; - u64 sched_deadline; - u64 sched_period; -}; +#include <linux/sched/prio.h> +#include <linux/signal_types.h> +#include <linux/mm_types_task.h> +#include <linux/task_io_accounting.h> -struct futex_pi_state; -struct robust_list_head; +/* task_struct member predeclarations (sorted alphabetically): */ +struct audit_context; +struct backing_dev_info; struct bio_list; -struct fs_struct; -struct perf_event_context; struct blk_plug; -struct filename; +struct cfs_rq; +struct fs_struct; +struct futex_pi_state; +struct io_context; +struct mempolicy; struct nameidata; - -#define VMACACHE_BITS 2 -#define VMACACHE_SIZE (1U << VMACACHE_BITS) -#define VMACACHE_MASK (VMACACHE_SIZE - 1) - -/* - * These are the constant used to fake the fixed-point load-average - * counting. Some notes: - * - 11 bit fractions expand to 22 bits by the multiplies: this gives - * a load-average precision of 10 bits integer + 11 bits fractional - * - if you want to count load-averages more often, you need more - * precision, or rounding will get you. With 2-second counting freq, - * the EXP_n values would be 1981, 2034 and 2043 if still using only - * 11 bit fractions. - */ -extern unsigned long avenrun[]; /* Load averages */ -extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); - -#define FSHIFT 11 /* nr of bits of precision */ -#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */ -#define LOAD_FREQ (5*HZ+1) /* 5 sec intervals */ -#define EXP_1 1884 /* 1/exp(5sec/1min) as fixed-point */ -#define EXP_5 2014 /* 1/exp(5sec/5min) */ -#define EXP_15 2037 /* 1/exp(5sec/15min) */ - -#define CALC_LOAD(load,exp,n) \ - load *= exp; \ - load += n*(FIXED_1-exp); \ - load >>= FSHIFT; - -extern unsigned long total_forks; -extern int nr_threads; -DECLARE_PER_CPU(unsigned long, process_counts); -extern int nr_processes(void); -extern unsigned long nr_running(void); -extern bool single_task_running(void); -extern unsigned long nr_iowait(void); -extern unsigned long nr_iowait_cpu(int cpu); -extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); - -extern void calc_global_load(unsigned long ticks); - -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -extern void cpu_load_update_nohz_start(void); -extern void cpu_load_update_nohz_stop(void); -#else -static inline void cpu_load_update_nohz_start(void) { } -static inline void cpu_load_update_nohz_stop(void) { } -#endif - -extern void dump_cpu_task(int cpu); - +struct nsproxy; +struct perf_event_context; +struct pid_namespace; +struct pipe_inode_info; +struct rcu_node; +struct reclaim_state; +struct robust_list_head; +struct sched_attr; +struct sched_param; struct seq_file; -struct cfs_rq; +struct sighand_struct; +struct signal_struct; +struct task_delay_info; struct task_group; -#ifdef CONFIG_SCHED_DEBUG -extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); -extern void proc_sched_set_task(struct task_struct *p); -#endif /* * Task state bitmask. NOTE! These bits are also @@ -204,66 +63,55 @@ extern void proc_sched_set_task(struct task_struct *p); * modifying one set can't modify the other one by * mistake. */ -#define TASK_RUNNING 0 -#define TASK_INTERRUPTIBLE 1 -#define TASK_UNINTERRUPTIBLE 2 -#define __TASK_STOPPED 4 -#define __TASK_TRACED 8 -/* in tsk->exit_state */ -#define EXIT_DEAD 16 -#define EXIT_ZOMBIE 32 -#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) -/* in tsk->state again */ -#define TASK_DEAD 64 -#define TASK_WAKEKILL 128 -#define TASK_WAKING 256 -#define TASK_PARKED 512 -#define TASK_NOLOAD 1024 -#define TASK_NEW 2048 -#define TASK_STATE_MAX 4096 - -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" - -extern char ___assert_task_state[1 - 2*!!( - sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; - -/* Convenience macros for the sake of set_task_state */ -#define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) -#define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) -#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) - -#define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) - -/* Convenience macros for the sake of wake_up */ -#define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) -#define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED) - -/* get_task_state() */ -#define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ - TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ - __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) - -#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) -#define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) -#define task_is_stopped_or_traced(task) \ - ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) -#define task_contributes_to_load(task) \ - ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ - (task->flags & PF_FROZEN) == 0 && \ - (task->state & TASK_NOLOAD) == 0) -#ifdef CONFIG_DEBUG_ATOMIC_SLEEP +/* Used in tsk->state: */ +#define TASK_RUNNING 0 +#define TASK_INTERRUPTIBLE 1 +#define TASK_UNINTERRUPTIBLE 2 +#define __TASK_STOPPED 4 +#define __TASK_TRACED 8 +/* Used in tsk->exit_state: */ +#define EXIT_DEAD 16 +#define EXIT_ZOMBIE 32 +#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) +/* Used in tsk->state again: */ +#define TASK_DEAD 64 +#define TASK_WAKEKILL 128 +#define TASK_WAKING 256 +#define TASK_PARKED 512 +#define TASK_NOLOAD 1024 +#define TASK_NEW 2048 +#define TASK_STATE_MAX 4096 + +#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" + +/* Convenience macros for the sake of set_current_state: */ +#define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) +#define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) +#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) + +#define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) + +/* Convenience macros for the sake of wake_up(): */ +#define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) +#define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED) + +/* get_task_state(): */ +#define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ + TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ + __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) + +#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) + +#define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) + +#define task_is_stopped_or_traced(task) ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) + +#define task_contributes_to_load(task) ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ + (task->flags & PF_FROZEN) == 0 && \ + (task->state & TASK_NOLOAD) == 0) -#define __set_task_state(tsk, state_value) \ - do { \ - (tsk)->task_state_change = _THIS_IP_; \ - (tsk)->state = (state_value); \ - } while (0) -#define set_task_state(tsk, state_value) \ - do { \ - (tsk)->task_state_change = _THIS_IP_; \ - smp_store_mb((tsk)->state, (state_value)); \ - } while (0) +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP #define __set_current_state(state_value) \ do { \ @@ -277,20 +125,6 @@ extern char ___assert_task_state[1 - 2*!!( } while (0) #else - -/* - * @tsk had better be current, or you get to keep the pieces. - * - * The only reason is that computing current can be more expensive than - * using a pointer that's already available. - * - * Therefore, see set_current_state(). - */ -#define __set_task_state(tsk, state_value) \ - do { (tsk)->state = (state_value); } while (0) -#define set_task_state(tsk, state_value) \ - smp_store_mb((tsk)->state, (state_value)) - /* * set_current_state() includes a barrier so that the write of current->state * is correctly serialised wrt the caller's subsequent test of whether to @@ -325,259 +159,34 @@ extern char ___assert_task_state[1 - 2*!!( * * Also see the comments of try_to_wake_up(). */ -#define __set_current_state(state_value) \ - do { current->state = (state_value); } while (0) -#define set_current_state(state_value) \ - smp_store_mb(current->state, (state_value)) - -#endif - -/* Task command name length */ -#define TASK_COMM_LEN 16 - -#include <linux/spinlock.h> - -/* - * This serializes "schedule()" and also protects - * the run-queue from deletions/modifications (but - * _adding_ to the beginning of the run-queue has - * a separate lock). - */ -extern rwlock_t tasklist_lock; -extern spinlock_t mmlist_lock; - -struct task_struct; - -#ifdef CONFIG_PROVE_RCU -extern int lockdep_tasklist_lock_is_held(void); -#endif /* #ifdef CONFIG_PROVE_RCU */ - -extern void sched_init(void); -extern void sched_init_smp(void); -extern asmlinkage void schedule_tail(struct task_struct *prev); -extern void init_idle(struct task_struct *idle, int cpu); -extern void init_idle_bootup_task(struct task_struct *idle); - -extern cpumask_var_t cpu_isolated_map; - -extern int runqueue_is_locked(int cpu); - -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -extern void nohz_balance_enter_idle(int cpu); -extern void set_cpu_sd_state_idle(void); -extern int get_nohz_timer_target(void); -#else -static inline void nohz_balance_enter_idle(int cpu) { } -static inline void set_cpu_sd_state_idle(void) { } +#define __set_current_state(state_value) do { current->state = (state_value); } while (0) +#define set_current_state(state_value) smp_store_mb(current->state, (state_value)) #endif -/* - * Only dump TASK_* tasks. (0 for all tasks) - */ -extern void show_state_filter(unsigned long state_filter); - -static inline void show_state(void) -{ - show_state_filter(0); -} - -extern void show_regs(struct pt_regs *); +/* Task command name length: */ +#define TASK_COMM_LEN 16 -/* - * TASK is a pointer to the task whose backtrace we want to see (or NULL for current - * task), SP is the stack pointer of the first frame that should be shown in the back - * trace (or NULL if the entire call-chain of the task should be shown). - */ -extern void show_stack(struct task_struct *task, unsigned long *sp); +extern cpumask_var_t cpu_isolated_map; -extern void cpu_init (void); -extern void trap_init(void); -extern void update_process_times(int user); extern void scheduler_tick(void); -extern int sched_cpu_starting(unsigned int cpu); -extern int sched_cpu_activate(unsigned int cpu); -extern int sched_cpu_deactivate(unsigned int cpu); - -#ifdef CONFIG_HOTPLUG_CPU -extern int sched_cpu_dying(unsigned int cpu); -#else -# define sched_cpu_dying NULL -#endif - -extern void sched_show_task(struct task_struct *p); - -#ifdef CONFIG_LOCKUP_DETECTOR -extern void touch_softlockup_watchdog_sched(void); -extern void touch_softlockup_watchdog(void); -extern void touch_softlockup_watchdog_sync(void); -extern void touch_all_softlockup_watchdogs(void); -extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); -extern unsigned int softlockup_panic; -extern unsigned int hardlockup_panic; -void lockup_detector_init(void); -#else -static inline void touch_softlockup_watchdog_sched(void) -{ -} -static inline void touch_softlockup_watchdog(void) -{ -} -static inline void touch_softlockup_watchdog_sync(void) -{ -} -static inline void touch_all_softlockup_watchdogs(void) -{ -} -static inline void lockup_detector_init(void) -{ -} -#endif - -#ifdef CONFIG_DETECT_HUNG_TASK -void reset_hung_task_detector(void); -#else -static inline void reset_hung_task_detector(void) -{ -} -#endif - -/* Attach to any functions which should be ignored in wchan output. */ -#define __sched __attribute__((__section__(".sched.text"))) -/* Linker adds these: start and end of __sched functions */ -extern char __sched_text_start[], __sched_text_end[]; +#define MAX_SCHEDULE_TIMEOUT LONG_MAX -/* Is this address in the __sched functions? */ -extern int in_sched_functions(unsigned long addr); - -#define MAX_SCHEDULE_TIMEOUT LONG_MAX -extern signed long schedule_timeout(signed long timeout); -extern signed long schedule_timeout_interruptible(signed long timeout); -extern signed long schedule_timeout_killable(signed long timeout); -extern signed long schedule_timeout_uninterruptible(signed long timeout); -extern signed long schedule_timeout_idle(signed long timeout); +extern long schedule_timeout(long timeout); +extern long schedule_timeout_interruptible(long timeout); +extern long schedule_timeout_killable(long timeout); +extern long schedule_timeout_uninterruptible(long timeout); +extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); +extern int __must_check io_schedule_prepare(void); +extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); - -static inline void io_schedule(void) -{ - io_schedule_timeout(MAX_SCHEDULE_TIMEOUT); -} - -void __noreturn do_task_dead(void); - -struct nsproxy; -struct user_namespace; - -#ifdef CONFIG_MMU -extern void arch_pick_mmap_layout(struct mm_struct *mm); -extern unsigned long -arch_get_unmapped_area(struct file *, unsigned long, unsigned long, - unsigned long, unsigned long); -extern unsigned long -arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags); -#else -static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} -#endif - -#define SUID_DUMP_DISABLE 0 /* No setuid dumping */ -#define SUID_DUMP_USER 1 /* Dump as user of process */ -#define SUID_DUMP_ROOT 2 /* Dump as root */ - -/* mm flags */ - -/* for SUID_DUMP_* above */ -#define MMF_DUMPABLE_BITS 2 -#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) - -extern void set_dumpable(struct mm_struct *mm, int value); -/* - * This returns the actual value of the suid_dumpable flag. For things - * that are using this for checking for privilege transitions, it must - * test against SUID_DUMP_USER rather than treating it as a boolean - * value. - */ -static inline int __get_dumpable(unsigned long mm_flags) -{ - return mm_flags & MMF_DUMPABLE_MASK; -} - -static inline int get_dumpable(struct mm_struct *mm) -{ - return __get_dumpable(mm->flags); -} - -/* coredump filter bits */ -#define MMF_DUMP_ANON_PRIVATE 2 -#define MMF_DUMP_ANON_SHARED 3 -#define MMF_DUMP_MAPPED_PRIVATE 4 -#define MMF_DUMP_MAPPED_SHARED 5 -#define MMF_DUMP_ELF_HEADERS 6 -#define MMF_DUMP_HUGETLB_PRIVATE 7 -#define MMF_DUMP_HUGETLB_SHARED 8 -#define MMF_DUMP_DAX_PRIVATE 9 -#define MMF_DUMP_DAX_SHARED 10 - -#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS -#define MMF_DUMP_FILTER_BITS 9 -#define MMF_DUMP_FILTER_MASK \ - (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) -#define MMF_DUMP_FILTER_DEFAULT \ - ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ - (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) - -#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS -# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) -#else -# define MMF_DUMP_MASK_DEFAULT_ELF 0 -#endif - /* leave room for more dump flags */ -#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ -#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ -/* - * This one-shot flag is dropped due to necessity of changing exe once again - * on NFS restore - */ -//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ - -#define MMF_HAS_UPROBES 19 /* has uprobes */ -#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ -#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ -#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ -#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ - -#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) - -struct sighand_struct { - atomic_t count; - struct k_sigaction action[_NSIG]; - spinlock_t siglock; - wait_queue_head_t signalfd_wqh; -}; - -struct pacct_struct { - int ac_flag; - long ac_exitcode; - unsigned long ac_mem; - cputime_t ac_utime, ac_stime; - unsigned long ac_minflt, ac_majflt; -}; - -struct cpu_itimer { - cputime_t expires; - cputime_t incr; - u32 error; - u32 incr_error; -}; +extern void io_schedule(void); /** - * struct prev_cputime - snaphsot of system and user cputime + * struct prev_cputime - snapshot of system and user cputime * @utime: time spent in user mode * @stime: time spent in system mode * @lock: protects the above two fields @@ -587,24 +196,16 @@ struct cpu_itimer { */ struct prev_cputime { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE - cputime_t utime; - cputime_t stime; - raw_spinlock_t lock; + u64 utime; + u64 stime; + raw_spinlock_t lock; #endif }; -static inline void prev_cputime_init(struct prev_cputime *prev) -{ -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE - prev->utime = prev->stime = 0; - raw_spin_lock_init(&prev->lock); -#endif -} - /** * struct task_cputime - collected CPU time counts - * @utime: time spent in user mode, in &cputime_t units - * @stime: time spent in kernel mode, in &cputime_t units + * @utime: time spent in user mode, in nanoseconds + * @stime: time spent in kernel mode, in nanoseconds * @sum_exec_runtime: total time spent on the CPU, in nanoseconds * * This structure groups together three kinds of CPU time that are tracked for @@ -612,382 +213,53 @@ static inline void prev_cputime_init(struct prev_cputime *prev) * these counts together and treat all three of them in parallel. */ struct task_cputime { - cputime_t utime; - cputime_t stime; - unsigned long long sum_exec_runtime; -}; - -/* Alternate field names when used to cache expirations. */ -#define virt_exp utime -#define prof_exp stime -#define sched_exp sum_exec_runtime - -#define INIT_CPUTIME \ - (struct task_cputime) { \ - .utime = 0, \ - .stime = 0, \ - .sum_exec_runtime = 0, \ - } - -/* - * This is the atomic variant of task_cputime, which can be used for - * storing and updating task_cputime statistics without locking. - */ -struct task_cputime_atomic { - atomic64_t utime; - atomic64_t stime; - atomic64_t sum_exec_runtime; -}; - -#define INIT_CPUTIME_ATOMIC \ - (struct task_cputime_atomic) { \ - .utime = ATOMIC64_INIT(0), \ - .stime = ATOMIC64_INIT(0), \ - .sum_exec_runtime = ATOMIC64_INIT(0), \ - } - -#define PREEMPT_DISABLED (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) - -/* - * Disable preemption until the scheduler is running -- use an unconditional - * value so that it also works on !PREEMPT_COUNT kernels. - * - * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count(). - */ -#define INIT_PREEMPT_COUNT PREEMPT_OFFSET - -/* - * Initial preempt_count value; reflects the preempt_count schedule invariant - * which states that during context switches: - * - * preempt_count() == 2*PREEMPT_DISABLE_OFFSET - * - * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels. - * Note: See finish_task_switch(). - */ -#define FORK_PREEMPT_COUNT (2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) - -/** - * struct thread_group_cputimer - thread group interval timer counts - * @cputime_atomic: atomic thread group interval timers. - * @running: true when there are timers running and - * @cputime_atomic receives updates. - * @checking_timer: true when a thread in the group is in the - * process of checking for thread group timers. - * - * This structure contains the version of task_cputime, above, that is - * used for thread group CPU timer calculations. - */ -struct thread_group_cputimer { - struct task_cputime_atomic cputime_atomic; - bool running; - bool checking_timer; + u64 utime; + u64 stime; + unsigned long long sum_exec_runtime; }; -#include <linux/rwsem.h> -struct autogroup; - -/* - * NOTE! "signal_struct" does not have its own - * locking, because a shared signal_struct always - * implies a shared sighand_struct, so locking - * sighand_struct is always a proper superset of - * the locking of signal_struct. - */ -struct signal_struct { - atomic_t sigcnt; - atomic_t live; - int nr_threads; - struct list_head thread_head; - - wait_queue_head_t wait_chldexit; /* for wait4() */ - - /* current thread group signal load-balancing target: */ - struct task_struct *curr_target; - - /* shared signal handling: */ - struct sigpending shared_pending; - - /* thread group exit support */ - int group_exit_code; - /* overloaded: - * - notify group_exit_task when ->count is equal to notify_count - * - everyone except group_exit_task is stopped during signal delivery - * of fatal signals, group_exit_task processes the signal. - */ - int notify_count; - struct task_struct *group_exit_task; - - /* thread group stop support, overloads group_exit_code too */ - int group_stop_count; - unsigned int flags; /* see SIGNAL_* flags below */ - - /* - * PR_SET_CHILD_SUBREAPER marks a process, like a service - * manager, to re-parent orphan (double-forking) child processes - * to this process instead of 'init'. The service manager is - * able to receive SIGCHLD signals and is able to investigate - * the process until it calls wait(). All children of this - * process will inherit a flag if they should look for a - * child_subreaper process at exit. - */ - unsigned int is_child_subreaper:1; - unsigned int has_child_subreaper:1; - - /* POSIX.1b Interval Timers */ - int posix_timer_id; - struct list_head posix_timers; - - /* ITIMER_REAL timer for the process */ - struct hrtimer real_timer; - struct pid *leader_pid; - ktime_t it_real_incr; - - /* - * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use - * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these - * values are defined to 0 and 1 respectively - */ - struct cpu_itimer it[2]; - - /* - * Thread group totals for process CPU timers. - * See thread_group_cputimer(), et al, for details. - */ - struct thread_group_cputimer cputimer; - - /* Earliest-expiration cache. */ - struct task_cputime cputime_expires; - -#ifdef CONFIG_NO_HZ_FULL - atomic_t tick_dep_mask; -#endif - - struct list_head cpu_timers[3]; - - struct pid *tty_old_pgrp; - - /* boolean value for session group leader */ - int leader; - - struct tty_struct *tty; /* NULL if no tty */ - -#ifdef CONFIG_SCHED_AUTOGROUP - struct autogroup *autogroup; -#endif - /* - * Cumulative resource counters for dead threads in the group, - * and for reaped dead child processes forked by this group. - * Live threads maintain their own counters and add to these - * in __exit_signal, except for the group leader. - */ - seqlock_t stats_lock; - cputime_t utime, stime, cutime, cstime; - cputime_t gtime; - cputime_t cgtime; - struct prev_cputime prev_cputime; - unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; - unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; - unsigned long inblock, oublock, cinblock, coublock; - unsigned long maxrss, cmaxrss; - struct task_io_accounting ioac; - - /* - * Cumulative ns of schedule CPU time fo dead threads in the - * group, not including a zombie group leader, (This only differs - * from jiffies_to_ns(utime + stime) if sched_clock uses something - * other than jiffies.) - */ - unsigned long long sum_sched_runtime; - - /* - * We don't bother to synchronize most readers of this at all, - * because there is no reader checking a limit that actually needs - * to get both rlim_cur and rlim_max atomically, and either one - * alone is a single word that can safely be read normally. - * getrlimit/setrlimit use task_lock(current->group_leader) to - * protect this instead of the siglock, because they really - * have no need to disable irqs. - */ - struct rlimit rlim[RLIM_NLIMITS]; - -#ifdef CONFIG_BSD_PROCESS_ACCT - struct pacct_struct pacct; /* per-process accounting information */ -#endif -#ifdef CONFIG_TASKSTATS - struct taskstats *stats; -#endif -#ifdef CONFIG_AUDIT - unsigned audit_tty; - struct tty_audit_buf *tty_audit_buf; -#endif - - /* - * Thread is the potential origin of an oom condition; kill first on - * oom - */ - bool oom_flag_origin; - short oom_score_adj; /* OOM kill score adjustment */ - short oom_score_adj_min; /* OOM kill score adjustment min value. - * Only settable by CAP_SYS_RESOURCE. */ - struct mm_struct *oom_mm; /* recorded mm when the thread group got - * killed by the oom killer */ - - struct mutex cred_guard_mutex; /* guard against foreign influences on - * credential calculations - * (notably. ptrace) */ +/* Alternate field names when used on cache expirations: */ +#define virt_exp utime +#define prof_exp stime +#define sched_exp sum_exec_runtime + +enum vtime_state { + /* Task is sleeping or running in a CPU with VTIME inactive: */ + VTIME_INACTIVE = 0, + /* Task runs in userspace in a CPU with VTIME active: */ + VTIME_USER, + /* Task runs in kernelspace in a CPU with VTIME active: */ + VTIME_SYS, }; -/* - * Bits in flags field of signal_struct. - */ -#define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ -#define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ -#define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ -#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ -/* - * Pending notifications to parent. - */ -#define SIGNAL_CLD_STOPPED 0x00000010 -#define SIGNAL_CLD_CONTINUED 0x00000020 -#define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED) - -#define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ - -#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ - SIGNAL_STOP_CONTINUED) - -static inline void signal_set_stop_flags(struct signal_struct *sig, - unsigned int flags) -{ - WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); - sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; -} - -/* If true, all threads except ->group_exit_task have pending SIGKILL */ -static inline int signal_group_exit(const struct signal_struct *sig) -{ - return (sig->flags & SIGNAL_GROUP_EXIT) || - (sig->group_exit_task != NULL); -} - -/* - * Some day this will be a full-fledged user tracking system.. - */ -struct user_struct { - atomic_t __count; /* reference count */ - atomic_t processes; /* How many processes does this user have? */ - atomic_t sigpending; /* How many pending signals does this user have? */ -#ifdef CONFIG_INOTIFY_USER - atomic_t inotify_watches; /* How many inotify watches does this user have? */ - atomic_t inotify_devs; /* How many inotify devs does this user have opened? */ -#endif -#ifdef CONFIG_FANOTIFY - atomic_t fanotify_listeners; -#endif -#ifdef CONFIG_EPOLL - atomic_long_t epoll_watches; /* The number of file descriptors currently watched */ -#endif -#ifdef CONFIG_POSIX_MQUEUE - /* protected by mq_lock */ - unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ -#endif - unsigned long locked_shm; /* How many pages of mlocked shm ? */ - unsigned long unix_inflight; /* How many files in flight in unix sockets */ - atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */ - -#ifdef CONFIG_KEYS - struct key *uid_keyring; /* UID specific keyring */ - struct key *session_keyring; /* UID's default session keyring */ -#endif - - /* Hash table maintenance information */ - struct hlist_node uidhash_node; - kuid_t uid; - -#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) - atomic_long_t locked_vm; -#endif +struct vtime { + seqcount_t seqcount; + unsigned long long starttime; + enum vtime_state state; + u64 utime; + u64 stime; + u64 gtime; }; -extern int uids_sysfs_init(void); - -extern struct user_struct *find_user(kuid_t); - -extern struct user_struct root_user; -#define INIT_USER (&root_user) - - -struct backing_dev_info; -struct reclaim_state; - -#ifdef CONFIG_SCHED_INFO struct sched_info { - /* cumulative counters */ - unsigned long pcount; /* # of times run on this cpu */ - unsigned long long run_delay; /* time spent waiting on a runqueue */ - - /* timestamps */ - unsigned long long last_arrival,/* when we last ran on a cpu */ - last_queued; /* when we were last queued to run */ -}; -#endif /* CONFIG_SCHED_INFO */ +#ifdef CONFIG_SCHED_INFO + /* Cumulative counters: */ -#ifdef CONFIG_TASK_DELAY_ACCT -struct task_delay_info { - spinlock_t lock; - unsigned int flags; /* Private per-task flags */ + /* # of times we have run on this CPU: */ + unsigned long pcount; - /* For each stat XXX, add following, aligned appropriately - * - * struct timespec XXX_start, XXX_end; - * u64 XXX_delay; - * u32 XXX_count; - * - * Atomicity of updates to XXX_delay, XXX_count protected by - * single lock above (split into XXX_lock if contention is an issue). - */ + /* Time spent waiting on a runqueue: */ + unsigned long long run_delay; - /* - * XXX_count is incremented on every XXX operation, the delay - * associated with the operation is added to XXX_delay. - * XXX_delay contains the accumulated delay time in nanoseconds. - */ - u64 blkio_start; /* Shared by blkio, swapin */ - u64 blkio_delay; /* wait for sync block io completion */ - u64 swapin_delay; /* wait for swapin block io completion */ - u32 blkio_count; /* total count of the number of sync block */ - /* io operations performed */ - u32 swapin_count; /* total count of the number of swapin block */ - /* io operations performed */ - - u64 freepages_start; - u64 freepages_delay; /* wait for memory reclaim */ - u32 freepages_count; /* total count of memory reclaim */ -}; -#endif /* CONFIG_TASK_DELAY_ACCT */ + /* Timestamps: */ -static inline int sched_info_on(void) -{ -#ifdef CONFIG_SCHEDSTATS - return 1; -#elif defined(CONFIG_TASK_DELAY_ACCT) - extern int delayacct_on; - return delayacct_on; -#else - return 0; -#endif -} + /* When did we last run on a CPU? */ + unsigned long long last_arrival; -#ifdef CONFIG_SCHEDSTATS -void force_schedstat_enabled(void); -#endif + /* When were we last queued to run? */ + unsigned long long last_queued; -enum cpu_idle_type { - CPU_IDLE, - CPU_NOT_IDLE, - CPU_NEWLY_IDLE, - CPU_MAX_IDLE_TYPES +#endif /* CONFIG_SCHED_INFO */ }; /* @@ -997,284 +269,12 @@ enum cpu_idle_type { * We define a basic fixed point arithmetic range, and then formalize * all these metrics based on that basic range. */ -# define SCHED_FIXEDPOINT_SHIFT 10 -# define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) - -/* - * Increase resolution of cpu_capacity calculations - */ -#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT -#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) - -/* - * Wake-queues are lists of tasks with a pending wakeup, whose - * callers have already marked the task as woken internally, - * and can thus carry on. A common use case is being able to - * do the wakeups once the corresponding user lock as been - * released. - * - * We hold reference to each task in the list across the wakeup, - * thus guaranteeing that the memory is still valid by the time - * the actual wakeups are performed in wake_up_q(). - * - * One per task suffices, because there's never a need for a task to be - * in two wake queues simultaneously; it is forbidden to abandon a task - * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is - * already in a wake queue, the wakeup will happen soon and the second - * waker can just skip it. - * - * The DEFINE_WAKE_Q macro declares and initializes the list head. - * wake_up_q() does NOT reinitialize the list; it's expected to be - * called near the end of a function, where the fact that the queue is - * not used again will be easy to see by inspection. - * - * Note that this can cause spurious wakeups. schedule() callers - * must ensure the call is done inside a loop, confirming that the - * wakeup condition has in fact occurred. - */ -struct wake_q_node { - struct wake_q_node *next; -}; - -struct wake_q_head { - struct wake_q_node *first; - struct wake_q_node **lastp; -}; - -#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) - -#define DEFINE_WAKE_Q(name) \ - struct wake_q_head name = { WAKE_Q_TAIL, &name.first } - -extern void wake_q_add(struct wake_q_head *head, - struct task_struct *task); -extern void wake_up_q(struct wake_q_head *head); - -/* - * sched-domains (multiprocessor balancing) declarations: - */ -#ifdef CONFIG_SMP -#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */ -#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */ -#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */ -#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */ -#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ -#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ -#define SD_ASYM_CPUCAPACITY 0x0040 /* Groups have different max cpu capacities */ -#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share cpu capacity */ -#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */ -#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ -#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ -#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ -#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ -#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ -#define SD_NUMA 0x4000 /* cross-node balancing */ - -#ifdef CONFIG_SCHED_SMT -static inline int cpu_smt_flags(void) -{ - return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; -} -#endif - -#ifdef CONFIG_SCHED_MC -static inline int cpu_core_flags(void) -{ - return SD_SHARE_PKG_RESOURCES; -} -#endif - -#ifdef CONFIG_NUMA -static inline int cpu_numa_flags(void) -{ - return SD_NUMA; -} -#endif - -extern int arch_asym_cpu_priority(int cpu); - -struct sched_domain_attr { - int relax_domain_level; -}; - -#define SD_ATTR_INIT (struct sched_domain_attr) { \ - .relax_domain_level = -1, \ -} - -extern int sched_domain_level_max; - -struct sched_group; - -struct sched_domain_shared { - atomic_t ref; - atomic_t nr_busy_cpus; - int has_idle_cores; -}; - -struct sched_domain { - /* These fields must be setup */ - struct sched_domain *parent; /* top domain must be null terminated */ - struct sched_domain *child; /* bottom domain must be null terminated */ - struct sched_group *groups; /* the balancing groups of the domain */ - unsigned long min_interval; /* Minimum balance interval ms */ - unsigned long max_interval; /* Maximum balance interval ms */ - unsigned int busy_factor; /* less balancing by factor if busy */ - unsigned int imbalance_pct; /* No balance until over watermark */ - unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ - unsigned int busy_idx; - unsigned int idle_idx; - unsigned int newidle_idx; - unsigned int wake_idx; - unsigned int forkexec_idx; - unsigned int smt_gain; - - int nohz_idle; /* NOHZ IDLE status */ - int flags; /* See SD_* */ - int level; - - /* Runtime fields. */ - unsigned long last_balance; /* init to jiffies. units in jiffies */ - unsigned int balance_interval; /* initialise to 1. units in ms. */ - unsigned int nr_balance_failed; /* initialise to 0 */ - - /* idle_balance() stats */ - u64 max_newidle_lb_cost; - unsigned long next_decay_max_lb_cost; - - u64 avg_scan_cost; /* select_idle_sibling */ - -#ifdef CONFIG_SCHEDSTATS - /* load_balance() stats */ - unsigned int lb_count[CPU_MAX_IDLE_TYPES]; - unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; - unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; - unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES]; - unsigned int lb_gained[CPU_MAX_IDLE_TYPES]; - unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES]; - unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES]; - unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES]; - - /* Active load balancing */ - unsigned int alb_count; - unsigned int alb_failed; - unsigned int alb_pushed; - - /* SD_BALANCE_EXEC stats */ - unsigned int sbe_count; - unsigned int sbe_balanced; - unsigned int sbe_pushed; - - /* SD_BALANCE_FORK stats */ - unsigned int sbf_count; - unsigned int sbf_balanced; - unsigned int sbf_pushed; - - /* try_to_wake_up() stats */ - unsigned int ttwu_wake_remote; - unsigned int ttwu_move_affine; - unsigned int ttwu_move_balance; -#endif -#ifdef CONFIG_SCHED_DEBUG - char *name; -#endif - union { - void *private; /* used during construction */ - struct rcu_head rcu; /* used during destruction */ - }; - struct sched_domain_shared *shared; - - unsigned int span_weight; - /* - * Span of all CPUs in this domain. - * - * NOTE: this field is variable length. (Allocated dynamically - * by attaching extra space to the end of the structure, - * depending on how many CPUs the kernel has booted up with) - */ - unsigned long span[0]; -}; - -static inline struct cpumask *sched_domain_span(struct sched_domain *sd) -{ - return to_cpumask(sd->span); -} - -extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new); - -/* Allocate an array of sched domains, for partition_sched_domains(). */ -cpumask_var_t *alloc_sched_domains(unsigned int ndoms); -void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); - -bool cpus_share_cache(int this_cpu, int that_cpu); - -typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); -typedef int (*sched_domain_flags_f)(void); - -#define SDTL_OVERLAP 0x01 - -struct sd_data { - struct sched_domain **__percpu sd; - struct sched_domain_shared **__percpu sds; - struct sched_group **__percpu sg; - struct sched_group_capacity **__percpu sgc; -}; - -struct sched_domain_topology_level { - sched_domain_mask_f mask; - sched_domain_flags_f sd_flags; - int flags; - int numa_level; - struct sd_data data; -#ifdef CONFIG_SCHED_DEBUG - char *name; -#endif -}; - -extern void set_sched_topology(struct sched_domain_topology_level *tl); -extern void wake_up_if_idle(int cpu); - -#ifdef CONFIG_SCHED_DEBUG -# define SD_INIT_NAME(type) .name = #type -#else -# define SD_INIT_NAME(type) -#endif - -#else /* CONFIG_SMP */ - -struct sched_domain_attr; - -static inline void -partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new) -{ -} - -static inline bool cpus_share_cache(int this_cpu, int that_cpu) -{ - return true; -} - -#endif /* !CONFIG_SMP */ - - -struct io_context; /* See blkdev.h */ - - -#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK -extern void prefetch_stack(struct task_struct *t); -#else -static inline void prefetch_stack(struct task_struct *t) { } -#endif - -struct audit_context; /* See audit.c */ -struct mempolicy; -struct pipe_inode_info; -struct uts_namespace; +# define SCHED_FIXEDPOINT_SHIFT 10 +# define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) struct load_weight { - unsigned long weight; - u32 inv_weight; + unsigned long weight; + u32 inv_weight; }; /* @@ -1330,71 +330,73 @@ struct load_weight { * issues. */ struct sched_avg { - u64 last_update_time, load_sum; - u32 util_sum, period_contrib; - unsigned long load_avg, util_avg; + u64 last_update_time; + u64 load_sum; + u32 util_sum; + u32 period_contrib; + unsigned long load_avg; + unsigned long util_avg; }; -#ifdef CONFIG_SCHEDSTATS struct sched_statistics { - u64 wait_start; - u64 wait_max; - u64 wait_count; - u64 wait_sum; - u64 iowait_count; - u64 iowait_sum; - - u64 sleep_start; - u64 sleep_max; - s64 sum_sleep_runtime; - - u64 block_start; - u64 block_max; - u64 exec_max; - u64 slice_max; - - u64 nr_migrations_cold; - u64 nr_failed_migrations_affine; - u64 nr_failed_migrations_running; - u64 nr_failed_migrations_hot; - u64 nr_forced_migrations; - - u64 nr_wakeups; - u64 nr_wakeups_sync; - u64 nr_wakeups_migrate; - u64 nr_wakeups_local; - u64 nr_wakeups_remote; - u64 nr_wakeups_affine; - u64 nr_wakeups_affine_attempts; - u64 nr_wakeups_passive; - u64 nr_wakeups_idle; -}; +#ifdef CONFIG_SCHEDSTATS + u64 wait_start; + u64 wait_max; + u64 wait_count; + u64 wait_sum; + u64 iowait_count; + u64 iowait_sum; + + u64 sleep_start; + u64 sleep_max; + s64 sum_sleep_runtime; + + u64 block_start; + u64 block_max; + u64 exec_max; + u64 slice_max; + + u64 nr_migrations_cold; + u64 nr_failed_migrations_affine; + u64 nr_failed_migrations_running; + u64 nr_failed_migrations_hot; + u64 nr_forced_migrations; + + u64 nr_wakeups; + u64 nr_wakeups_sync; + u64 nr_wakeups_migrate; + u64 nr_wakeups_local; + u64 nr_wakeups_remote; + u64 nr_wakeups_affine; + u64 nr_wakeups_affine_attempts; + u64 nr_wakeups_passive; + u64 nr_wakeups_idle; #endif +}; struct sched_entity { - struct load_weight load; /* for load-balancing */ - struct rb_node run_node; - struct list_head group_node; - unsigned int on_rq; + /* For load-balancing: */ + struct load_weight load; + struct rb_node run_node; + struct list_head group_node; + unsigned int on_rq; - u64 exec_start; - u64 sum_exec_runtime; - u64 vruntime; - u64 prev_sum_exec_runtime; + u64 exec_start; + u64 sum_exec_runtime; + u64 vruntime; + u64 prev_sum_exec_runtime; - u64 nr_migrations; + u64 nr_migrations; -#ifdef CONFIG_SCHEDSTATS - struct sched_statistics statistics; -#endif + struct sched_statistics statistics; #ifdef CONFIG_FAIR_GROUP_SCHED - int depth; - struct sched_entity *parent; + int depth; + struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ - struct cfs_rq *cfs_rq; + struct cfs_rq *cfs_rq; /* rq "owned" by this entity/group: */ - struct cfs_rq *my_q; + struct cfs_rq *my_q; #endif #ifdef CONFIG_SMP @@ -1404,49 +406,50 @@ struct sched_entity { * Put into separate cache line so it does not * collide with read-mostly values above. */ - struct sched_avg avg ____cacheline_aligned_in_smp; + struct sched_avg avg ____cacheline_aligned_in_smp; #endif }; struct sched_rt_entity { - struct list_head run_list; - unsigned long timeout; - unsigned long watchdog_stamp; - unsigned int time_slice; - unsigned short on_rq; - unsigned short on_list; - - struct sched_rt_entity *back; + struct list_head run_list; + unsigned long timeout; + unsigned long watchdog_stamp; + unsigned int time_slice; + unsigned short on_rq; + unsigned short on_list; + + struct sched_rt_entity *back; #ifdef CONFIG_RT_GROUP_SCHED - struct sched_rt_entity *parent; + struct sched_rt_entity *parent; /* rq on which this entity is (to be) queued: */ - struct rt_rq *rt_rq; + struct rt_rq *rt_rq; /* rq "owned" by this entity/group: */ - struct rt_rq *my_q; + struct rt_rq *my_q; #endif -}; +} __randomize_layout; struct sched_dl_entity { - struct rb_node rb_node; + struct rb_node rb_node; /* * Original scheduling parameters. Copied here from sched_attr * during sched_setattr(), they will remain the same until * the next sched_setattr(). */ - u64 dl_runtime; /* maximum runtime for each instance */ - u64 dl_deadline; /* relative deadline of each instance */ - u64 dl_period; /* separation of two instances (period) */ - u64 dl_bw; /* dl_runtime / dl_deadline */ + u64 dl_runtime; /* Maximum runtime for each instance */ + u64 dl_deadline; /* Relative deadline of each instance */ + u64 dl_period; /* Separation of two instances (period) */ + u64 dl_bw; /* dl_runtime / dl_period */ + u64 dl_density; /* dl_runtime / dl_deadline */ /* * Actual scheduling parameters. Initialized with the values above, * they are continously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ - s64 runtime; /* remaining runtime for this instance */ - u64 deadline; /* absolute deadline for this instance */ - unsigned int flags; /* specifying the scheduler behaviour */ + s64 runtime; /* Remaining runtime for this instance */ + u64 deadline; /* Absolute deadline for this instance */ + unsigned int flags; /* Specifying the scheduler behaviour */ /* * Some bool flags: @@ -1459,28 +462,48 @@ struct sched_dl_entity { * outside bandwidth enforcement mechanism (but only until we * exit the critical section); * - * @dl_yielded tells if task gave up the cpu before consuming + * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. + * + * @dl_non_contending tells if the task is inactive while still + * contributing to the active utilization. In other words, it + * indicates if the inactive timer has been armed and its handler + * has not been executed yet. This flag is useful to avoid race + * conditions between the inactive timer handler and the wakeup + * code. */ - int dl_throttled, dl_boosted, dl_yielded; + int dl_throttled; + int dl_boosted; + int dl_yielded; + int dl_non_contending; /* * Bandwidth enforcement timer. Each -deadline task has its * own bandwidth to be enforced, thus we need one timer per task. */ - struct hrtimer dl_timer; + struct hrtimer dl_timer; + + /* + * Inactive timer, responsible for decreasing the active utilization + * at the "0-lag time". When a -deadline task blocks, it contributes + * to GRUB's active utilization until the "0-lag time", hence a + * timer is needed to decrease the active utilization at the correct + * time. + */ + struct hrtimer inactive_timer; }; union rcu_special { struct { - u8 blocked; - u8 need_qs; - u8 exp_need_qs; - u8 pad; /* Otherwise the compiler can store garbage here. */ + u8 blocked; + u8 need_qs; + u8 exp_need_qs; + + /* Otherwise the compiler can store garbage here: */ + u8 pad; } b; /* Bits. */ u32 s; /* Set of bits. */ }; -struct rcu_node; enum perf_event_task_context { perf_invalid_context = -1, @@ -1489,23 +512,8 @@ enum perf_event_task_context { perf_nr_task_contexts, }; -/* Track pages that require TLB flushes */ -struct tlbflush_unmap_batch { - /* - * Each bit set is a CPU that potentially has a TLB entry for one of - * the PFNs being flushed. See set_tlb_ubc_flush_pending(). - */ - struct cpumask cpumask; - - /* True if any bit in cpumask is set */ - bool flush_required; - - /* - * If true then the PTE was dirty when unmapped. The entry must be - * flushed before IO is initiated or a stale TLB entry potentially - * allows an update without redirtying the page. - */ - bool writable; +struct wake_q_node { + struct wake_q_node *next; }; struct task_struct { @@ -1514,360 +522,421 @@ struct task_struct { * For reasons of header soup (see current_thread_info()), this * must be the first element of task_struct. */ - struct thread_info thread_info; + struct thread_info thread_info; #endif - volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ - void *stack; - atomic_t usage; - unsigned int flags; /* per process flags, defined below */ - unsigned int ptrace; + /* -1 unrunnable, 0 runnable, >0 stopped: */ + volatile long state; + + /* + * This begins the randomizable portion of task_struct. Only + * scheduling-critical items should be added above here. + */ + randomized_struct_fields_start + + void *stack; + atomic_t usage; + /* Per task flags (PF_*), defined further below: */ + unsigned int flags; + unsigned int ptrace; #ifdef CONFIG_SMP - struct llist_node wake_entry; - int on_cpu; + struct llist_node wake_entry; + int on_cpu; #ifdef CONFIG_THREAD_INFO_IN_TASK - unsigned int cpu; /* current CPU */ + /* Current CPU: */ + unsigned int cpu; #endif - unsigned int wakee_flips; - unsigned long wakee_flip_decay_ts; - struct task_struct *last_wakee; + unsigned int wakee_flips; + unsigned long wakee_flip_decay_ts; + struct task_struct *last_wakee; - int wake_cpu; + int wake_cpu; #endif - int on_rq; + int on_rq; + + int prio; + int static_prio; + int normal_prio; + unsigned int rt_priority; - int prio, static_prio, normal_prio; - unsigned int rt_priority; - const struct sched_class *sched_class; - struct sched_entity se; - struct sched_rt_entity rt; + const struct sched_class *sched_class; + struct sched_entity se; + struct sched_rt_entity rt; #ifdef CONFIG_CGROUP_SCHED - struct task_group *sched_task_group; + struct task_group *sched_task_group; #endif - struct sched_dl_entity dl; + struct sched_dl_entity dl; #ifdef CONFIG_PREEMPT_NOTIFIERS - /* list of struct preempt_notifier: */ - struct hlist_head preempt_notifiers; + /* List of struct preempt_notifier: */ + struct hlist_head preempt_notifiers; #endif #ifdef CONFIG_BLK_DEV_IO_TRACE - unsigned int btrace_seq; + unsigned int btrace_seq; #endif - unsigned int policy; - int nr_cpus_allowed; - cpumask_t cpus_allowed; + unsigned int policy; + int nr_cpus_allowed; + cpumask_t cpus_allowed; #ifdef CONFIG_PREEMPT_RCU - int rcu_read_lock_nesting; - union rcu_special rcu_read_unlock_special; - struct list_head rcu_node_entry; - struct rcu_node *rcu_blocked_node; + int rcu_read_lock_nesting; + union rcu_special rcu_read_unlock_special; + struct list_head rcu_node_entry; + struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_PREEMPT_RCU */ + #ifdef CONFIG_TASKS_RCU - unsigned long rcu_tasks_nvcsw; - bool rcu_tasks_holdout; - struct list_head rcu_tasks_holdout_list; - int rcu_tasks_idle_cpu; + unsigned long rcu_tasks_nvcsw; + bool rcu_tasks_holdout; + struct list_head rcu_tasks_holdout_list; + int rcu_tasks_idle_cpu; #endif /* #ifdef CONFIG_TASKS_RCU */ -#ifdef CONFIG_SCHED_INFO - struct sched_info sched_info; -#endif + struct sched_info sched_info; - struct list_head tasks; + struct list_head tasks; #ifdef CONFIG_SMP - struct plist_node pushable_tasks; - struct rb_node pushable_dl_tasks; -#endif - - struct mm_struct *mm, *active_mm; - /* per-thread vma caching */ - u32 vmacache_seqnum; - struct vm_area_struct *vmacache[VMACACHE_SIZE]; -#if defined(SPLIT_RSS_COUNTING) - struct task_rss_stat rss_stat; -#endif -/* task state */ - int exit_state; - int exit_code, exit_signal; - int pdeath_signal; /* The signal sent when the parent dies */ - unsigned long jobctl; /* JOBCTL_*, siglock protected */ - - /* Used for emulating ABI behavior of previous Linux versions */ - unsigned int personality; - - /* scheduler bits, serialized by scheduler locks */ - unsigned sched_reset_on_fork:1; - unsigned sched_contributes_to_load:1; - unsigned sched_migrated:1; - unsigned sched_remote_wakeup:1; - unsigned :0; /* force alignment to the next boundary */ - - /* unserialized, strictly 'current' */ - unsigned in_execve:1; /* bit to tell LSMs we're in execve */ - unsigned in_iowait:1; -#if !defined(TIF_RESTORE_SIGMASK) - unsigned restore_sigmask:1; + struct plist_node pushable_tasks; + struct rb_node pushable_dl_tasks; +#endif + + struct mm_struct *mm; + struct mm_struct *active_mm; + + /* Per-thread vma caching: */ + struct vmacache vmacache; + +#ifdef SPLIT_RSS_COUNTING + struct task_rss_stat rss_stat; +#endif + int exit_state; + int exit_code; + int exit_signal; + /* The signal sent when the parent dies: */ + int pdeath_signal; + /* JOBCTL_*, siglock protected: */ + unsigned long jobctl; + + /* Used for emulating ABI behavior of previous Linux versions: */ + unsigned int personality; + + /* Scheduler bits, serialized by scheduler locks: */ + unsigned sched_reset_on_fork:1; + unsigned sched_contributes_to_load:1; + unsigned sched_migrated:1; + unsigned sched_remote_wakeup:1; + /* Force alignment to the next boundary: */ + unsigned :0; + + /* Unserialized, strictly 'current' */ + + /* Bit to tell LSMs we're in execve(): */ + unsigned in_execve:1; + unsigned in_iowait:1; +#ifndef TIF_RESTORE_SIGMASK + unsigned restore_sigmask:1; #endif #ifdef CONFIG_MEMCG - unsigned memcg_may_oom:1; + unsigned memcg_may_oom:1; #ifndef CONFIG_SLOB - unsigned memcg_kmem_skip_account:1; + unsigned memcg_kmem_skip_account:1; #endif #endif #ifdef CONFIG_COMPAT_BRK - unsigned brk_randomized:1; + unsigned brk_randomized:1; +#endif +#ifdef CONFIG_CGROUPS + /* disallow userland-initiated cgroup migration */ + unsigned no_cgroup_migration:1; #endif - unsigned long atomic_flags; /* Flags needing atomic access. */ + unsigned long atomic_flags; /* Flags requiring atomic access. */ - struct restart_block restart_block; + struct restart_block restart_block; - pid_t pid; - pid_t tgid; + pid_t pid; + pid_t tgid; #ifdef CONFIG_CC_STACKPROTECTOR - /* Canary value for the -fstack-protector gcc feature */ - unsigned long stack_canary; + /* Canary value for the -fstack-protector GCC feature: */ + unsigned long stack_canary; #endif /* - * pointers to (original) parent process, youngest child, younger sibling, + * Pointers to the (original) parent process, youngest child, younger sibling, * older sibling, respectively. (p->father can be replaced with * p->real_parent->pid) */ - struct task_struct __rcu *real_parent; /* real parent process */ - struct task_struct __rcu *parent; /* recipient of SIGCHLD, wait4() reports */ + + /* Real parent process: */ + struct task_struct __rcu *real_parent; + + /* Recipient of SIGCHLD, wait4() reports: */ + struct task_struct __rcu *parent; + /* - * children/sibling forms the list of my natural children + * Children/sibling form the list of natural children: */ - struct list_head children; /* list of my children */ - struct list_head sibling; /* linkage in my parent's children list */ - struct task_struct *group_leader; /* threadgroup leader */ + struct list_head children; + struct list_head sibling; + struct task_struct *group_leader; /* - * ptraced is the list of tasks this task is using ptrace on. + * 'ptraced' is the list of tasks this task is using ptrace() on. + * * This includes both natural children and PTRACE_ATTACH targets. - * p->ptrace_entry is p's link on the p->parent->ptraced list. + * 'ptrace_entry' is this task's link on the p->parent->ptraced list. */ - struct list_head ptraced; - struct list_head ptrace_entry; + struct list_head ptraced; + struct list_head ptrace_entry; /* PID/PID hash table linkage. */ - struct pid_link pids[PIDTYPE_MAX]; - struct list_head thread_group; - struct list_head thread_node; + struct pid_link pids[PIDTYPE_MAX]; + struct list_head thread_group; + struct list_head thread_node; - struct completion *vfork_done; /* for vfork() */ - int __user *set_child_tid; /* CLONE_CHILD_SETTID */ - int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */ + struct completion *vfork_done; - cputime_t utime, stime; + /* CLONE_CHILD_SETTID: */ + int __user *set_child_tid; + + /* CLONE_CHILD_CLEARTID: */ + int __user *clear_child_tid; + + u64 utime; + u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME - cputime_t utimescaled, stimescaled; + u64 utimescaled; + u64 stimescaled; #endif - cputime_t gtime; - struct prev_cputime prev_cputime; + u64 gtime; + struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqcount_t vtime_seqcount; - unsigned long long vtime_snap; - enum { - /* Task is sleeping or running in a CPU with VTIME inactive */ - VTIME_INACTIVE = 0, - /* Task runs in userspace in a CPU with VTIME active */ - VTIME_USER, - /* Task runs in kernelspace in a CPU with VTIME active */ - VTIME_SYS, - } vtime_snap_whence; + struct vtime vtime; #endif #ifdef CONFIG_NO_HZ_FULL - atomic_t tick_dep_mask; -#endif - unsigned long nvcsw, nivcsw; /* context switch counts */ - u64 start_time; /* monotonic time in nsec */ - u64 real_start_time; /* boot based time in nsec */ -/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ - unsigned long min_flt, maj_flt; - - struct task_cputime cputime_expires; - struct list_head cpu_timers[3]; - -/* process credentials */ - const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */ - const struct cred __rcu *real_cred; /* objective and real subjective task - * credentials (COW) */ - const struct cred __rcu *cred; /* effective (overridable) subjective task - * credentials (COW) */ - char comm[TASK_COMM_LEN]; /* executable name excluding path - - access with [gs]et_task_comm (which lock - it with task_lock()) - - initialized normally by setup_new_exec */ -/* file system info */ - struct nameidata *nameidata; + atomic_t tick_dep_mask; +#endif + /* Context switch counts: */ + unsigned long nvcsw; + unsigned long nivcsw; + + /* Monotonic time in nsecs: */ + u64 start_time; + + /* Boot based time in nsecs: */ + u64 real_start_time; + + /* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */ + unsigned long min_flt; + unsigned long maj_flt; + +#ifdef CONFIG_POSIX_TIMERS + struct task_cputime cputime_expires; + struct list_head cpu_timers[3]; +#endif + + /* Process credentials: */ + + /* Tracer's credentials at attach: */ + const struct cred __rcu *ptracer_cred; + + /* Objective and real subjective task credentials (COW): */ + const struct cred __rcu *real_cred; + + /* Effective (overridable) subjective task credentials (COW): */ + const struct cred __rcu *cred; + + /* + * executable name, excluding path. + * + * - normally initialized setup_new_exec() + * - access it with [gs]et_task_comm() + * - lock it with task_lock() + */ + char comm[TASK_COMM_LEN]; + + struct nameidata *nameidata; + #ifdef CONFIG_SYSVIPC -/* ipc stuff */ - struct sysv_sem sysvsem; - struct sysv_shm sysvshm; + struct sysv_sem sysvsem; + struct sysv_shm sysvshm; #endif #ifdef CONFIG_DETECT_HUNG_TASK -/* hung task detection */ - unsigned long last_switch_count; -#endif -/* filesystem information */ - struct fs_struct *fs; -/* open file information */ - struct files_struct *files; -/* namespaces */ - struct nsproxy *nsproxy; -/* signal handlers */ - struct signal_struct *signal; - struct sighand_struct *sighand; - - sigset_t blocked, real_blocked; - sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */ - struct sigpending pending; - - unsigned long sas_ss_sp; - size_t sas_ss_size; - unsigned sas_ss_flags; - - struct callback_head *task_works; - - struct audit_context *audit_context; + unsigned long last_switch_count; +#endif + /* Filesystem information: */ + struct fs_struct *fs; + + /* Open file information: */ + struct files_struct *files; + + /* Namespaces: */ + struct nsproxy *nsproxy; + + /* Signal handlers: */ + struct signal_struct *signal; + struct sighand_struct *sighand; + sigset_t blocked; + sigset_t real_blocked; + /* Restored if set_restore_sigmask() was used: */ + sigset_t saved_sigmask; + struct sigpending pending; + unsigned long sas_ss_sp; + size_t sas_ss_size; + unsigned int sas_ss_flags; + + struct callback_head *task_works; + + struct audit_context *audit_context; #ifdef CONFIG_AUDITSYSCALL - kuid_t loginuid; - unsigned int sessionid; + kuid_t loginuid; + unsigned int sessionid; #endif - struct seccomp seccomp; + struct seccomp seccomp; -/* Thread group tracking */ - u32 parent_exec_id; - u32 self_exec_id; -/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, - * mempolicy */ - spinlock_t alloc_lock; + /* Thread group tracking: */ + u32 parent_exec_id; + u32 self_exec_id; + + /* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */ + spinlock_t alloc_lock; /* Protection of the PI data structures: */ - raw_spinlock_t pi_lock; + raw_spinlock_t pi_lock; - struct wake_q_node wake_q; + struct wake_q_node wake_q; #ifdef CONFIG_RT_MUTEXES - /* PI waiters blocked on a rt_mutex held by this task */ - struct rb_root pi_waiters; - struct rb_node *pi_waiters_leftmost; - /* Deadlock detection and priority inheritance handling */ - struct rt_mutex_waiter *pi_blocked_on; + /* PI waiters blocked on a rt_mutex held by this task: */ + struct rb_root pi_waiters; + struct rb_node *pi_waiters_leftmost; + /* Updated under owner's pi_lock and rq lock */ + struct task_struct *pi_top_task; + /* Deadlock detection and priority inheritance handling: */ + struct rt_mutex_waiter *pi_blocked_on; #endif #ifdef CONFIG_DEBUG_MUTEXES - /* mutex deadlock detection */ - struct mutex_waiter *blocked_on; + /* Mutex deadlock detection: */ + struct mutex_waiter *blocked_on; #endif + #ifdef CONFIG_TRACE_IRQFLAGS - unsigned int irq_events; - unsigned long hardirq_enable_ip; - unsigned long hardirq_disable_ip; - unsigned int hardirq_enable_event; - unsigned int hardirq_disable_event; - int hardirqs_enabled; - int hardirq_context; - unsigned long softirq_disable_ip; - unsigned long softirq_enable_ip; - unsigned int softirq_disable_event; - unsigned int softirq_enable_event; - int softirqs_enabled; - int softirq_context; + unsigned int irq_events; + unsigned long hardirq_enable_ip; + unsigned long hardirq_disable_ip; + unsigned int hardirq_enable_event; + unsigned int hardirq_disable_event; + int hardirqs_enabled; + int hardirq_context; + unsigned long softirq_disable_ip; + unsigned long softirq_enable_ip; + unsigned int softirq_disable_event; + unsigned int softirq_enable_event; + int softirqs_enabled; + int softirq_context; #endif + #ifdef CONFIG_LOCKDEP -# define MAX_LOCK_DEPTH 48UL - u64 curr_chain_key; - int lockdep_depth; - unsigned int lockdep_recursion; - struct held_lock held_locks[MAX_LOCK_DEPTH]; - gfp_t lockdep_reclaim_gfp; +# define MAX_LOCK_DEPTH 48UL + u64 curr_chain_key; + int lockdep_depth; + unsigned int lockdep_recursion; + struct held_lock held_locks[MAX_LOCK_DEPTH]; + gfp_t lockdep_reclaim_gfp; #endif + #ifdef CONFIG_UBSAN - unsigned int in_ubsan; + unsigned int in_ubsan; #endif -/* journalling filesystem info */ - void *journal_info; + /* Journalling filesystem info: */ + void *journal_info; -/* stacked block device info */ - struct bio_list *bio_list; + /* Stacked block device info: */ + struct bio_list *bio_list; #ifdef CONFIG_BLOCK -/* stack plugging */ - struct blk_plug *plug; + /* Stack plugging: */ + struct blk_plug *plug; #endif -/* VM state */ - struct reclaim_state *reclaim_state; + /* VM state: */ + struct reclaim_state *reclaim_state; - struct backing_dev_info *backing_dev_info; + struct backing_dev_info *backing_dev_info; - struct io_context *io_context; + struct io_context *io_context; - unsigned long ptrace_message; - siginfo_t *last_siginfo; /* For ptrace use. */ - struct task_io_accounting ioac; -#if defined(CONFIG_TASK_XACCT) - u64 acct_rss_mem1; /* accumulated rss usage */ - u64 acct_vm_mem1; /* accumulated virtual memory usage */ - cputime_t acct_timexpd; /* stime + utime since last update */ + /* Ptrace state: */ + unsigned long ptrace_message; + siginfo_t *last_siginfo; + + struct task_io_accounting ioac; +#ifdef CONFIG_TASK_XACCT + /* Accumulated RSS usage: */ + u64 acct_rss_mem1; + /* Accumulated virtual memory usage: */ + u64 acct_vm_mem1; + /* stime + utime since last update: */ + u64 acct_timexpd; #endif #ifdef CONFIG_CPUSETS - nodemask_t mems_allowed; /* Protected by alloc_lock */ - seqcount_t mems_allowed_seq; /* Seqence no to catch updates */ - int cpuset_mem_spread_rotor; - int cpuset_slab_spread_rotor; + /* Protected by ->alloc_lock: */ + nodemask_t mems_allowed; + /* Seqence number to catch updates: */ + seqcount_t mems_allowed_seq; + int cpuset_mem_spread_rotor; + int cpuset_slab_spread_rotor; #endif #ifdef CONFIG_CGROUPS - /* Control Group info protected by css_set_lock */ - struct css_set __rcu *cgroups; - /* cg_list protected by css_set_lock and tsk->alloc_lock */ - struct list_head cg_list; + /* Control Group info protected by css_set_lock: */ + struct css_set __rcu *cgroups; + /* cg_list protected by css_set_lock and tsk->alloc_lock: */ + struct list_head cg_list; #endif #ifdef CONFIG_INTEL_RDT_A - int closid; + int closid; #endif #ifdef CONFIG_FUTEX - struct robust_list_head __user *robust_list; + struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT struct compat_robust_list_head __user *compat_robust_list; #endif - struct list_head pi_state_list; - struct futex_pi_state *pi_state_cache; + struct list_head pi_state_list; + struct futex_pi_state *pi_state_cache; #endif #ifdef CONFIG_PERF_EVENTS - struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts]; - struct mutex perf_event_mutex; - struct list_head perf_event_list; + struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts]; + struct mutex perf_event_mutex; + struct list_head perf_event_list; #endif #ifdef CONFIG_DEBUG_PREEMPT - unsigned long preempt_disable_ip; + unsigned long preempt_disable_ip; #endif #ifdef CONFIG_NUMA - struct mempolicy *mempolicy; /* Protected by alloc_lock */ - short il_next; - short pref_node_fork; + /* Protected by alloc_lock: */ + struct mempolicy *mempolicy; + short il_prev; + short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING - int numa_scan_seq; - unsigned int numa_scan_period; - unsigned int numa_scan_period_max; - int numa_preferred_nid; - unsigned long numa_migrate_retry; - u64 node_stamp; /* migration stamp */ - u64 last_task_numa_placement; - u64 last_sum_exec_runtime; - struct callback_head numa_work; - - struct list_head numa_entry; - struct numa_group *numa_group; + int numa_scan_seq; + unsigned int numa_scan_period; + unsigned int numa_scan_period_max; + int numa_preferred_nid; + unsigned long numa_migrate_retry; + /* Migration stamp: */ + u64 node_stamp; + u64 last_task_numa_placement; + u64 last_sum_exec_runtime; + struct callback_head numa_work; + + struct list_head numa_entry; + struct numa_group *numa_group; /* * numa_faults is an array split into four regions: @@ -1883,8 +952,8 @@ struct task_struct { * during the current scan window. When the scan completes, the counts * in faults_memory and faults_cpu decay and these values are copied. */ - unsigned long *numa_faults; - unsigned long total_numa_faults; + unsigned long *numa_faults; + unsigned long total_numa_faults; /* * numa_faults_locality tracks if faults recorded during the last @@ -1892,208 +961,148 @@ struct task_struct { * period is adapted based on the locality of the faults with different * weights depending on whether they were shared or private faults */ - unsigned long numa_faults_locality[3]; + unsigned long numa_faults_locality[3]; - unsigned long numa_pages_migrated; + unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH - struct tlbflush_unmap_batch tlb_ubc; -#endif + struct tlbflush_unmap_batch tlb_ubc; - struct rcu_head rcu; + struct rcu_head rcu; - /* - * cache last used pipe for splice - */ - struct pipe_inode_info *splice_pipe; + /* Cache last used pipe for splice(): */ + struct pipe_inode_info *splice_pipe; - struct page_frag task_frag; + struct page_frag task_frag; -#ifdef CONFIG_TASK_DELAY_ACCT - struct task_delay_info *delays; +#ifdef CONFIG_TASK_DELAY_ACCT + struct task_delay_info *delays; #endif + #ifdef CONFIG_FAULT_INJECTION - int make_it_fail; + int make_it_fail; + unsigned int fail_nth; #endif /* - * when (nr_dirtied >= nr_dirtied_pause), it's time to call - * balance_dirty_pages() for some dirty throttling pause + * When (nr_dirtied >= nr_dirtied_pause), it's time to call + * balance_dirty_pages() for a dirty throttling pause: */ - int nr_dirtied; - int nr_dirtied_pause; - unsigned long dirty_paused_when; /* start of a write-and-pause period */ + int nr_dirtied; + int nr_dirtied_pause; + /* Start of a write-and-pause period: */ + unsigned long dirty_paused_when; #ifdef CONFIG_LATENCYTOP - int latency_record_count; - struct latency_record latency_record[LT_SAVECOUNT]; + int latency_record_count; + struct latency_record latency_record[LT_SAVECOUNT]; #endif /* - * time slack values; these are used to round up poll() and + * Time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ - u64 timer_slack_ns; - u64 default_timer_slack_ns; + u64 timer_slack_ns; + u64 default_timer_slack_ns; #ifdef CONFIG_KASAN - unsigned int kasan_depth; + unsigned int kasan_depth; #endif + #ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* Index of current stored address in ret_stack */ - int curr_ret_stack; - /* Stack of return addresses for return function tracing */ - struct ftrace_ret_stack *ret_stack; - /* time stamp for last schedule */ - unsigned long long ftrace_timestamp; + /* Index of current stored address in ret_stack: */ + int curr_ret_stack; + + /* Stack of return addresses for return function tracing: */ + struct ftrace_ret_stack *ret_stack; + + /* Timestamp for last schedule: */ + unsigned long long ftrace_timestamp; + /* * Number of functions that haven't been traced - * because of depth overrun. + * because of depth overrun: */ - atomic_t trace_overrun; - /* Pause for the tracing */ - atomic_t tracing_graph_pause; + atomic_t trace_overrun; + + /* Pause tracing: */ + atomic_t tracing_graph_pause; #endif + #ifdef CONFIG_TRACING - /* state flags for use by tracers */ - unsigned long trace; - /* bitmask and counter of trace recursion */ - unsigned long trace_recursion; + /* State flags for use by tracers: */ + unsigned long trace; + + /* Bitmask and counter of trace recursion: */ + unsigned long trace_recursion; #endif /* CONFIG_TRACING */ + #ifdef CONFIG_KCOV - /* Coverage collection mode enabled for this task (0 if disabled). */ - enum kcov_mode kcov_mode; - /* Size of the kcov_area. */ - unsigned kcov_size; - /* Buffer for coverage collection. */ - void *kcov_area; - /* kcov desciptor wired with this task or NULL. */ - struct kcov *kcov; + /* Coverage collection mode enabled for this task (0 if disabled): */ + enum kcov_mode kcov_mode; + + /* Size of the kcov_area: */ + unsigned int kcov_size; + + /* Buffer for coverage collection: */ + void *kcov_area; + + /* KCOV descriptor wired with this task or NULL: */ + struct kcov *kcov; #endif + #ifdef CONFIG_MEMCG - struct mem_cgroup *memcg_in_oom; - gfp_t memcg_oom_gfp_mask; - int memcg_oom_order; + struct mem_cgroup *memcg_in_oom; + gfp_t memcg_oom_gfp_mask; + int memcg_oom_order; - /* number of pages to reclaim on returning to userland */ - unsigned int memcg_nr_pages_over_high; + /* Number of pages to reclaim on returning to userland: */ + unsigned int memcg_nr_pages_over_high; #endif + #ifdef CONFIG_UPROBES - struct uprobe_task *utask; + struct uprobe_task *utask; #endif #if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) - unsigned int sequential_io; - unsigned int sequential_io_avg; + unsigned int sequential_io; + unsigned int sequential_io_avg; #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP - unsigned long task_state_change; + unsigned long task_state_change; #endif - int pagefault_disabled; + int pagefault_disabled; #ifdef CONFIG_MMU - struct task_struct *oom_reaper_list; + struct task_struct *oom_reaper_list; #endif #ifdef CONFIG_VMAP_STACK - struct vm_struct *stack_vm_area; + struct vm_struct *stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK - /* A live task holds one reference. */ - atomic_t stack_refcount; + /* A live task holds one reference: */ + atomic_t stack_refcount; #endif -/* CPU-specific state of this task */ - struct thread_struct thread; -/* - * WARNING: on x86, 'thread_struct' contains a variable-sized - * structure. It *MUST* be at the end of 'task_struct'. - * - * Do not put anything below here! - */ -}; - -#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT -extern int arch_task_struct_size __read_mostly; -#else -# define arch_task_struct_size (sizeof(struct task_struct)) +#ifdef CONFIG_LIVEPATCH + int patch_state; #endif - -#ifdef CONFIG_VMAP_STACK -static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) -{ - return t->stack_vm_area; -} -#else -static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) -{ - return NULL; -} +#ifdef CONFIG_SECURITY + /* Used by LSM modules for access restriction: */ + void *security; #endif -/* Future-safe accessor for struct task_struct's cpus_allowed. */ -#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) - -static inline int tsk_nr_cpus_allowed(struct task_struct *p) -{ - return p->nr_cpus_allowed; -} - -#define TNF_MIGRATED 0x01 -#define TNF_NO_GROUP 0x02 -#define TNF_SHARED 0x04 -#define TNF_FAULT_LOCAL 0x08 -#define TNF_MIGRATE_FAIL 0x10 + /* + * New fields for task_struct should be added above here, so that + * they are included in the randomized portion of task_struct. + */ + randomized_struct_fields_end -static inline bool in_vfork(struct task_struct *tsk) -{ - bool ret; + /* CPU-specific state of this task: */ + struct thread_struct thread; /* - * need RCU to access ->real_parent if CLONE_VM was used along with - * CLONE_PARENT. + * WARNING: on x86, 'thread_struct' contains a variable-sized + * structure. It *MUST* be at the end of 'task_struct'. * - * We check real_parent->mm == tsk->mm because CLONE_VFORK does not - * imply CLONE_VM - * - * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus - * ->real_parent is not necessarily the task doing vfork(), so in - * theory we can't rely on task_lock() if we want to dereference it. - * - * And in this case we can't trust the real_parent->mm == tsk->mm - * check, it can be false negative. But we do not care, if init or - * another oom-unkillable task does this it should blame itself. + * Do not put anything below here! */ - rcu_read_lock(); - ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm; - rcu_read_unlock(); - - return ret; -} - -#ifdef CONFIG_NUMA_BALANCING -extern void task_numa_fault(int last_node, int node, int pages, int flags); -extern pid_t task_numa_group_id(struct task_struct *p); -extern void set_numabalancing_state(bool enabled); -extern void task_numa_free(struct task_struct *p); -extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, - int src_nid, int dst_cpu); -#else -static inline void task_numa_fault(int last_node, int node, int pages, - int flags) -{ -} -static inline pid_t task_numa_group_id(struct task_struct *p) -{ - return 0; -} -static inline void set_numabalancing_state(bool enabled) -{ -} -static inline void task_numa_free(struct task_struct *p) -{ -} -static inline bool should_numa_migrate_memory(struct task_struct *p, - struct page *page, int src_nid, int dst_cpu) -{ - return true; -} -#endif +}; static inline struct pid *task_pid(struct task_struct *task) { @@ -2106,7 +1115,7 @@ static inline struct pid *task_tgid(struct task_struct *task) } /* - * Without tasklist or rcu lock it is not safe to dereference + * Without tasklist or RCU lock it is not safe to dereference * the result of task_pgrp/task_session even if task == current, * we can race with another thread doing sys_setsid/sys_setpgid. */ @@ -2120,8 +1129,6 @@ static inline struct pid *task_session(struct task_struct *task) return task->group_leader->pids[PIDTYPE_SID].pid; } -struct pid_namespace; - /* * the helpers to get the task's different pids as they are seen * from various namespaces @@ -2131,20 +1138,16 @@ struct pid_namespace; * current. * task_xid_nr_ns() : id seen from the ns specified; * - * set_task_vxid() : assigns a virtual id to a task; - * * see also pid_nr() etc in include/linux/pid.h */ -pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, - struct pid_namespace *ns); +pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); static inline pid_t task_pid_nr(struct task_struct *tsk) { return tsk->pid; } -static inline pid_t task_pid_nr_ns(struct task_struct *tsk, - struct pid_namespace *ns) +static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); } @@ -2160,15 +1163,28 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk) return tsk->tgid; } -pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); +extern pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); static inline pid_t task_tgid_vnr(struct task_struct *tsk) { return pid_vnr(task_tgid(tsk)); } +/** + * pid_alive - check that a task structure is not stale + * @p: Task structure to be checked. + * + * Test if a process is not yet dead (at most zombie state) + * If pid_alive fails, then pointers within the task structure + * can be stale and must not be dereferenced. + * + * Return: 1 if the process is alive. 0 otherwise. + */ +static inline int pid_alive(const struct task_struct *p) +{ + return p->pids[PIDTYPE_PID].pid != NULL; +} -static inline int pid_alive(const struct task_struct *p); static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) { pid_t pid = 0; @@ -2186,8 +1202,7 @@ static inline pid_t task_ppid_nr(const struct task_struct *tsk) return task_ppid_nr_ns(tsk, &init_pid_ns); } -static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, - struct pid_namespace *ns) +static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); } @@ -2198,8 +1213,7 @@ static inline pid_t task_pgrp_vnr(struct task_struct *tsk) } -static inline pid_t task_session_nr_ns(struct task_struct *tsk, - struct pid_namespace *ns) +static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); } @@ -2209,28 +1223,13 @@ static inline pid_t task_session_vnr(struct task_struct *tsk) return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } -/* obsolete, do not use */ +/* Obsolete, do not use: */ static inline pid_t task_pgrp_nr(struct task_struct *tsk) { return task_pgrp_nr_ns(tsk, &init_pid_ns); } /** - * pid_alive - check that a task structure is not stale - * @p: Task structure to be checked. - * - * Test if a process is not yet dead (at most zombie state) - * If pid_alive fails, then pointers within the task structure - * can be stale and must not be dereferenced. - * - * Return: 1 if the process is alive. 0 otherwise. - */ -static inline int pid_alive(const struct task_struct *p) -{ - return p->pids[PIDTYPE_PID].pid != NULL; -} - -/** * is_global_init - check if a task structure is init. Since init * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. @@ -2246,89 +1245,37 @@ static inline int is_global_init(struct task_struct *tsk) extern struct pid *cad_pid; -extern void free_task(struct task_struct *tsk); -#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) - -extern void __put_task_struct(struct task_struct *t); - -static inline void put_task_struct(struct task_struct *t) -{ - if (atomic_dec_and_test(&t->usage)) - __put_task_struct(t); -} - -struct task_struct *task_rcu_dereference(struct task_struct **ptask); -struct task_struct *try_get_task_struct(struct task_struct **ptask); - -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void task_cputime(struct task_struct *t, - cputime_t *utime, cputime_t *stime); -extern cputime_t task_gtime(struct task_struct *t); -#else -static inline void task_cputime(struct task_struct *t, - cputime_t *utime, cputime_t *stime) -{ - *utime = t->utime; - *stime = t->stime; -} - -static inline cputime_t task_gtime(struct task_struct *t) -{ - return t->gtime; -} -#endif - -#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME -static inline void task_cputime_scaled(struct task_struct *t, - cputime_t *utimescaled, - cputime_t *stimescaled) -{ - *utimescaled = t->utimescaled; - *stimescaled = t->stimescaled; -} -#else -static inline void task_cputime_scaled(struct task_struct *t, - cputime_t *utimescaled, - cputime_t *stimescaled) -{ - task_cputime(t, utimescaled, stimescaled); -} -#endif - -extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); -extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); - /* * Per process flags */ -#define PF_IDLE 0x00000002 /* I am an IDLE thread */ -#define PF_EXITING 0x00000004 /* getting shut down */ -#define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ -#define PF_VCPU 0x00000010 /* I'm a virtual CPU */ -#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ -#define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ -#define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */ -#define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ -#define PF_DUMPCORE 0x00000200 /* dumped core */ -#define PF_SIGNALED 0x00000400 /* killed by a signal */ -#define PF_MEMALLOC 0x00000800 /* Allocating memory */ -#define PF_NPROC_EXCEEDED 0x00001000 /* set_user noticed that RLIMIT_NPROC was exceeded */ -#define PF_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */ -#define PF_USED_ASYNC 0x00004000 /* used async_schedule*(), used by module init */ -#define PF_NOFREEZE 0x00008000 /* this thread should not be frozen */ -#define PF_FROZEN 0x00010000 /* frozen for system suspend */ -#define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ -#define PF_KSWAPD 0x00040000 /* I am kswapd */ -#define PF_MEMALLOC_NOIO 0x00080000 /* Allocating memory without IO involved */ -#define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ -#define PF_KTHREAD 0x00200000 /* I am a kernel thread */ -#define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ -#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ -#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ -#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ -#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ -#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ -#define PF_SUSPEND_TASK 0x80000000 /* this thread called freeze_processes and should not be frozen */ +#define PF_IDLE 0x00000002 /* I am an IDLE thread */ +#define PF_EXITING 0x00000004 /* Getting shut down */ +#define PF_EXITPIDONE 0x00000008 /* PI exit done on shut down */ +#define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ +#define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ +#define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */ +#define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */ +#define PF_DUMPCORE 0x00000200 /* Dumped core */ +#define PF_SIGNALED 0x00000400 /* Killed by a signal */ +#define PF_MEMALLOC 0x00000800 /* Allocating memory */ +#define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ +#define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ +#define PF_USED_ASYNC 0x00004000 /* Used async_schedule*(), used by module init */ +#define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ +#define PF_FROZEN 0x00010000 /* Frozen for system suspend */ +#define PF_KSWAPD 0x00020000 /* I am kswapd */ +#define PF_MEMALLOC_NOFS 0x00040000 /* All allocation requests will inherit GFP_NOFS */ +#define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */ +#define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ +#define PF_KTHREAD 0x00200000 /* I am a kernel thread */ +#define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ +#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ +#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ +#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ +#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ +#define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* * Only the _current_ task can read/write to tsk->flags, but other @@ -2341,55 +1288,47 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, * child is not running and in turn not changing child->flags * at the same time the parent does it. */ -#define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0) -#define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0) -#define clear_used_math() clear_stopped_child_used_math(current) -#define set_used_math() set_stopped_child_used_math(current) +#define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0) +#define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0) +#define clear_used_math() clear_stopped_child_used_math(current) +#define set_used_math() set_stopped_child_used_math(current) + #define conditional_stopped_child_used_math(condition, child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0) -#define conditional_used_math(condition) \ - conditional_stopped_child_used_math(condition, current) + +#define conditional_used_math(condition) conditional_stopped_child_used_math(condition, current) + #define copy_to_stopped_child_used_math(child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0) -/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */ -#define tsk_used_math(p) ((p)->flags & PF_USED_MATH) -#define used_math() tsk_used_math(current) - -/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags - * __GFP_FS is also cleared as it implies __GFP_IO. - */ -static inline gfp_t memalloc_noio_flags(gfp_t flags) -{ - if (unlikely(current->flags & PF_MEMALLOC_NOIO)) - flags &= ~(__GFP_IO | __GFP_FS); - return flags; -} -static inline unsigned int memalloc_noio_save(void) -{ - unsigned int flags = current->flags & PF_MEMALLOC_NOIO; - current->flags |= PF_MEMALLOC_NOIO; - return flags; -} +/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */ +#define tsk_used_math(p) ((p)->flags & PF_USED_MATH) +#define used_math() tsk_used_math(current) -static inline void memalloc_noio_restore(unsigned int flags) +static inline bool is_percpu_thread(void) { - current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; +#ifdef CONFIG_SMP + return (current->flags & PF_NO_SETAFFINITY) && + (current->nr_cpus_allowed == 1); +#else + return true; +#endif } /* Per-process atomic flags. */ -#define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ -#define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ -#define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ -#define PFA_LMK_WAITING 3 /* Lowmemorykiller is waiting */ +#define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ +#define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ +#define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ { return test_bit(PFA_##name, &p->atomic_flags); } + #define TASK_PFA_SET(name, func) \ static inline void task_set_##func(struct task_struct *p) \ { set_bit(PFA_##name, &p->atomic_flags); } + #define TASK_PFA_CLEAR(name, func) \ static inline void task_clear_##func(struct task_struct *p) \ { clear_bit(PFA_##name, &p->atomic_flags); } @@ -2405,78 +1344,23 @@ TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) -TASK_PFA_TEST(LMK_WAITING, lmk_waiting) -TASK_PFA_SET(LMK_WAITING, lmk_waiting) - -/* - * task->jobctl flags - */ -#define JOBCTL_STOP_SIGMASK 0xffff /* signr of the last group stop */ - -#define JOBCTL_STOP_DEQUEUED_BIT 16 /* stop signal dequeued */ -#define JOBCTL_STOP_PENDING_BIT 17 /* task should stop for group stop */ -#define JOBCTL_STOP_CONSUME_BIT 18 /* consume group stop count */ -#define JOBCTL_TRAP_STOP_BIT 19 /* trap for STOP */ -#define JOBCTL_TRAP_NOTIFY_BIT 20 /* trap for NOTIFY */ -#define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ -#define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ - -#define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) -#define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) -#define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT) -#define JOBCTL_TRAP_STOP (1UL << JOBCTL_TRAP_STOP_BIT) -#define JOBCTL_TRAP_NOTIFY (1UL << JOBCTL_TRAP_NOTIFY_BIT) -#define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) -#define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) - -#define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) -#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) - -extern bool task_set_jobctl_pending(struct task_struct *task, - unsigned long mask); -extern void task_clear_jobctl_trapping(struct task_struct *task); -extern void task_clear_jobctl_pending(struct task_struct *task, - unsigned long mask); - -static inline void rcu_copy_process(struct task_struct *p) -{ -#ifdef CONFIG_PREEMPT_RCU - p->rcu_read_lock_nesting = 0; - p->rcu_read_unlock_special.s = 0; - p->rcu_blocked_node = NULL; - INIT_LIST_HEAD(&p->rcu_node_entry); -#endif /* #ifdef CONFIG_PREEMPT_RCU */ -#ifdef CONFIG_TASKS_RCU - p->rcu_tasks_holdout = false; - INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); - p->rcu_tasks_idle_cpu = -1; -#endif /* #ifdef CONFIG_TASKS_RCU */ -} - -static inline void tsk_restore_flags(struct task_struct *task, - unsigned long orig_flags, unsigned long flags) +static inline void +current_restore_flags(unsigned long orig_flags, unsigned long flags) { - task->flags &= ~flags; - task->flags |= orig_flags & flags; + current->flags &= ~flags; + current->flags |= orig_flags & flags; } -extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, - const struct cpumask *trial); -extern int task_can_attach(struct task_struct *p, - const struct cpumask *cs_cpus_allowed); +extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); +extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed); #ifdef CONFIG_SMP -extern void do_set_cpus_allowed(struct task_struct *p, - const struct cpumask *new_mask); - -extern int set_cpus_allowed_ptr(struct task_struct *p, - const struct cpumask *new_mask); +extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); +extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); #else -static inline void do_set_cpus_allowed(struct task_struct *p, - const struct cpumask *new_mask) +static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { } -static inline int set_cpus_allowed_ptr(struct task_struct *p, - const struct cpumask *new_mask) +static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { if (!cpumask_test_cpu(0, new_mask)) return -EINVAL; @@ -2484,157 +1368,14 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, } #endif -#ifdef CONFIG_NO_HZ_COMMON -void calc_load_enter_idle(void); -void calc_load_exit_idle(void); -#else -static inline void calc_load_enter_idle(void) { } -static inline void calc_load_exit_idle(void) { } -#endif /* CONFIG_NO_HZ_COMMON */ - #ifndef cpu_relax_yield #define cpu_relax_yield() cpu_relax() #endif -/* - * Do not use outside of architecture code which knows its limitations. - * - * sched_clock() has no promise of monotonicity or bounded drift between - * CPUs, use (which you should not) requires disabling IRQs. - * - * Please use one of the three interfaces below. - */ -extern unsigned long long notrace sched_clock(void); -/* - * See the comment in kernel/sched/clock.c - */ -extern u64 running_clock(void); -extern u64 sched_clock_cpu(int cpu); - - -extern void sched_clock_init(void); - -#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -static inline void sched_clock_tick(void) -{ -} - -static inline void sched_clock_idle_sleep_event(void) -{ -} - -static inline void sched_clock_idle_wakeup_event(u64 delta_ns) -{ -} - -static inline u64 cpu_clock(int cpu) -{ - return sched_clock(); -} - -static inline u64 local_clock(void) -{ - return sched_clock(); -} -#else -/* - * Architectures can set this to 1 if they have specified - * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig, - * but then during bootup it turns out that sched_clock() - * is reliable after all: - */ -extern int sched_clock_stable(void); -extern void set_sched_clock_stable(void); -extern void clear_sched_clock_stable(void); - -extern void sched_clock_tick(void); -extern void sched_clock_idle_sleep_event(void); -extern void sched_clock_idle_wakeup_event(u64 delta_ns); - -/* - * As outlined in clock.c, provides a fast, high resolution, nanosecond - * time source that is monotonic per cpu argument and has bounded drift - * between cpus. - * - * ######################### BIG FAT WARNING ########################## - * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # - * # go backwards !! # - * #################################################################### - */ -static inline u64 cpu_clock(int cpu) -{ - return sched_clock_cpu(cpu); -} - -static inline u64 local_clock(void) -{ - return sched_clock_cpu(raw_smp_processor_id()); -} -#endif - -#ifdef CONFIG_IRQ_TIME_ACCOUNTING -/* - * An i/f to runtime opt-in for irq time accounting based off of sched_clock. - * The reason for this explicit opt-in is not to have perf penalty with - * slow sched_clocks. - */ -extern void enable_sched_clock_irqtime(void); -extern void disable_sched_clock_irqtime(void); -#else -static inline void enable_sched_clock_irqtime(void) {} -static inline void disable_sched_clock_irqtime(void) {} -#endif - -extern unsigned long long -task_sched_runtime(struct task_struct *task); - -/* sched_exec is called by processes performing an exec */ -#ifdef CONFIG_SMP -extern void sched_exec(void); -#else -#define sched_exec() {} -#endif - -extern void sched_clock_idle_sleep_event(void); -extern void sched_clock_idle_wakeup_event(u64 delta_ns); - -#ifdef CONFIG_HOTPLUG_CPU -extern void idle_task_exit(void); -#else -static inline void idle_task_exit(void) {} -#endif - -#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) -extern void wake_up_nohz_cpu(int cpu); -#else -static inline void wake_up_nohz_cpu(int cpu) { } -#endif - -#ifdef CONFIG_NO_HZ_FULL -extern u64 scheduler_tick_max_deferment(void); -#endif - -#ifdef CONFIG_SCHED_AUTOGROUP -extern void sched_autogroup_create_attach(struct task_struct *p); -extern void sched_autogroup_detach(struct task_struct *p); -extern void sched_autogroup_fork(struct signal_struct *sig); -extern void sched_autogroup_exit(struct signal_struct *sig); -extern void sched_autogroup_exit_task(struct task_struct *p); -#ifdef CONFIG_PROC_FS -extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); -extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice); -#endif -#else -static inline void sched_autogroup_create_attach(struct task_struct *p) { } -static inline void sched_autogroup_detach(struct task_struct *p) { } -static inline void sched_autogroup_fork(struct signal_struct *sig) { } -static inline void sched_autogroup_exit(struct signal_struct *sig) { } -static inline void sched_autogroup_exit_task(struct task_struct *p) { } -#endif - extern int yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); + /** * task_nice - return the nice value of a given task. * @p: the task in question. @@ -2645,16 +1386,15 @@ static inline int task_nice(const struct task_struct *p) { return PRIO_TO_NICE((p)->static_prio); } + extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); -extern int sched_setscheduler(struct task_struct *, int, - const struct sched_param *); -extern int sched_setscheduler_nocheck(struct task_struct *, int, - const struct sched_param *); -extern int sched_setattr(struct task_struct *, - const struct sched_attr *); +extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); +extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); +extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); + /** * is_idle_task - is the specified task an idle task? * @p: the task in question. @@ -2665,6 +1405,7 @@ static inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } + extern struct task_struct *curr_task(int cpu); extern void ia64_set_curr_task(int cpu, struct task_struct *p); @@ -2677,23 +1418,15 @@ union thread_union { unsigned long stack[THREAD_SIZE/sizeof(long)]; }; -#ifndef __HAVE_ARCH_KSTACK_END -static inline int kstack_end(void *addr) +#ifdef CONFIG_THREAD_INFO_IN_TASK +static inline struct thread_info *task_thread_info(struct task_struct *task) { - /* Reliable end of stack detection: - * Some APM bios versions misalign the stack - */ - return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*))); + return &task->thread_info; } +#elif !defined(__HAVE_THREAD_FUNCTIONS) +# define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif -extern union thread_union init_thread_union; -extern struct task_struct init_task; - -extern struct mm_struct init_mm; - -extern struct pid_namespace init_pid_ns; - /* * find a task by one of its numerical ids * @@ -2706,322 +1439,25 @@ extern struct pid_namespace init_pid_ns; */ extern struct task_struct *find_task_by_vpid(pid_t nr); -extern struct task_struct *find_task_by_pid_ns(pid_t nr, - struct pid_namespace *ns); - -/* per-UID process charging. */ -extern struct user_struct * alloc_uid(kuid_t); -static inline struct user_struct *get_uid(struct user_struct *u) -{ - atomic_inc(&u->__count); - return u; -} -extern void free_uid(struct user_struct *); - -#include <asm/current.h> - -extern void xtime_update(unsigned long ticks); +extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); -#ifdef CONFIG_SMP - extern void kick_process(struct task_struct *tsk); -#else - static inline void kick_process(struct task_struct *tsk) { } -#endif -extern int sched_fork(unsigned long clone_flags, struct task_struct *p); -extern void sched_dead(struct task_struct *p); - -extern void proc_caches_init(void); -extern void flush_signals(struct task_struct *); -extern void ignore_signals(struct task_struct *); -extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); - -static inline int kernel_dequeue_signal(siginfo_t *info) -{ - struct task_struct *tsk = current; - siginfo_t __info; - int ret; - - spin_lock_irq(&tsk->sighand->siglock); - ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info); - spin_unlock_irq(&tsk->sighand->siglock); - - return ret; -} - -static inline void kernel_signal_stop(void) -{ - spin_lock_irq(¤t->sighand->siglock); - if (current->jobctl & JOBCTL_STOP_DEQUEUED) - __set_current_state(TASK_STOPPED); - spin_unlock_irq(¤t->sighand->siglock); - - schedule(); -} - -extern void release_task(struct task_struct * p); -extern int send_sig_info(int, struct siginfo *, struct task_struct *); -extern int force_sigsegv(int, struct task_struct *); -extern int force_sig_info(int, struct siginfo *, struct task_struct *); -extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); -extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); -extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *, - const struct cred *, u32); -extern int kill_pgrp(struct pid *pid, int sig, int priv); -extern int kill_pid(struct pid *pid, int sig, int priv); -extern int kill_proc_info(int, struct siginfo *, pid_t); -extern __must_check bool do_notify_parent(struct task_struct *, int); -extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); -extern void force_sig(int, struct task_struct *); -extern int send_sig(int, struct task_struct *, int); -extern int zap_other_threads(struct task_struct *p); -extern struct sigqueue *sigqueue_alloc(void); -extern void sigqueue_free(struct sigqueue *); -extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group); -extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); - -#ifdef TIF_RESTORE_SIGMASK -/* - * Legacy restore_sigmask accessors. These are inefficient on - * SMP architectures because they require atomic operations. - */ - -/** - * set_restore_sigmask() - make sure saved_sigmask processing gets done - * - * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code - * will run before returning to user mode, to process the flag. For - * all callers, TIF_SIGPENDING is already set or it's no harm to set - * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the - * arch code will notice on return to user mode, in case those bits - * are scarce. We set TIF_SIGPENDING here to ensure that the arch - * signal code always gets run when TIF_RESTORE_SIGMASK is set. - */ -static inline void set_restore_sigmask(void) -{ - set_thread_flag(TIF_RESTORE_SIGMASK); - WARN_ON(!test_thread_flag(TIF_SIGPENDING)); -} -static inline void clear_restore_sigmask(void) -{ - clear_thread_flag(TIF_RESTORE_SIGMASK); -} -static inline bool test_restore_sigmask(void) -{ - return test_thread_flag(TIF_RESTORE_SIGMASK); -} -static inline bool test_and_clear_restore_sigmask(void) -{ - return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); -} - -#else /* TIF_RESTORE_SIGMASK */ - -/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ -static inline void set_restore_sigmask(void) -{ - current->restore_sigmask = true; - WARN_ON(!test_thread_flag(TIF_SIGPENDING)); -} -static inline void clear_restore_sigmask(void) -{ - current->restore_sigmask = false; -} -static inline bool test_restore_sigmask(void) -{ - return current->restore_sigmask; -} -static inline bool test_and_clear_restore_sigmask(void) -{ - if (!current->restore_sigmask) - return false; - current->restore_sigmask = false; - return true; -} -#endif - -static inline void restore_saved_sigmask(void) -{ - if (test_and_clear_restore_sigmask()) - __set_current_blocked(¤t->saved_sigmask); -} - -static inline sigset_t *sigmask_to_save(void) -{ - sigset_t *res = ¤t->blocked; - if (unlikely(test_restore_sigmask())) - res = ¤t->saved_sigmask; - return res; -} - -static inline int kill_cad_pid(int sig, int priv) -{ - return kill_pid(cad_pid, sig, priv); -} - -/* These can be the second arg to send_sig_info/send_group_sig_info. */ -#define SEND_SIG_NOINFO ((struct siginfo *) 0) -#define SEND_SIG_PRIV ((struct siginfo *) 1) -#define SEND_SIG_FORCED ((struct siginfo *) 2) - -/* - * True if we are on the alternate signal stack. - */ -static inline int on_sig_stack(unsigned long sp) -{ - /* - * If the signal stack is SS_AUTODISARM then, by construction, we - * can't be on the signal stack unless user code deliberately set - * SS_AUTODISARM when we were already on it. - * - * This improves reliability: if user state gets corrupted such that - * the stack pointer points very close to the end of the signal stack, - * then this check will enable the signal to be handled anyway. - */ - if (current->sas_ss_flags & SS_AUTODISARM) - return 0; - -#ifdef CONFIG_STACK_GROWSUP - return sp >= current->sas_ss_sp && - sp - current->sas_ss_sp < current->sas_ss_size; -#else - return sp > current->sas_ss_sp && - sp - current->sas_ss_sp <= current->sas_ss_size; -#endif -} - -static inline int sas_ss_flags(unsigned long sp) -{ - if (!current->sas_ss_size) - return SS_DISABLE; - - return on_sig_stack(sp) ? SS_ONSTACK : 0; -} - -static inline void sas_ss_reset(struct task_struct *p) -{ - p->sas_ss_sp = 0; - p->sas_ss_size = 0; - p->sas_ss_flags = SS_DISABLE; -} - -static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) -{ - if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) -#ifdef CONFIG_STACK_GROWSUP - return current->sas_ss_sp; -#else - return current->sas_ss_sp + current->sas_ss_size; -#endif - return sp; -} - -/* - * Routines for handling mm_structs - */ -extern struct mm_struct * mm_alloc(void); - -/* mmdrop drops the mm and the page tables */ -extern void __mmdrop(struct mm_struct *); -static inline void mmdrop(struct mm_struct *mm) -{ - if (unlikely(atomic_dec_and_test(&mm->mm_count))) - __mmdrop(mm); -} - -static inline void mmdrop_async_fn(struct work_struct *work) -{ - struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); - __mmdrop(mm); -} - -static inline void mmdrop_async(struct mm_struct *mm) -{ - if (unlikely(atomic_dec_and_test(&mm->mm_count))) { - INIT_WORK(&mm->async_put_work, mmdrop_async_fn); - schedule_work(&mm->async_put_work); - } -} - -static inline bool mmget_not_zero(struct mm_struct *mm) -{ - return atomic_inc_not_zero(&mm->mm_users); -} - -/* mmput gets rid of the mappings and all user-space */ -extern void mmput(struct mm_struct *); -#ifdef CONFIG_MMU -/* same as above but performs the slow path from the async context. Can - * be called from the atomic context as well - */ -extern void mmput_async(struct mm_struct *); -#endif - -/* Grab a reference to a task's mm, if it is not already going away */ -extern struct mm_struct *get_task_mm(struct task_struct *task); -/* - * Grab a reference to a task's mm, if it is not already going away - * and ptrace_may_access with the mode parameter passed to it - * succeeds. - */ -extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); -/* Remove the current tasks stale references to the old mm_struct */ -extern void mm_release(struct task_struct *, struct mm_struct *); - -#ifdef CONFIG_HAVE_COPY_THREAD_TLS -extern int copy_thread_tls(unsigned long, unsigned long, unsigned long, - struct task_struct *, unsigned long); -#else -extern int copy_thread(unsigned long, unsigned long, unsigned long, - struct task_struct *); - -/* Architectures that haven't opted into copy_thread_tls get the tls argument - * via pt_regs, so ignore the tls argument passed via C. */ -static inline int copy_thread_tls( - unsigned long clone_flags, unsigned long sp, unsigned long arg, - struct task_struct *p, unsigned long tls) -{ - return copy_thread(clone_flags, sp, arg, p); -} -#endif -extern void flush_thread(void); -#ifdef CONFIG_HAVE_EXIT_THREAD -extern void exit_thread(struct task_struct *tsk); +#ifdef CONFIG_SMP +extern void kick_process(struct task_struct *tsk); #else -static inline void exit_thread(struct task_struct *tsk) -{ -} +static inline void kick_process(struct task_struct *tsk) { } #endif -extern void exit_files(struct task_struct *); -extern void __cleanup_sighand(struct sighand_struct *); - -extern void exit_itimers(struct signal_struct *); -extern void flush_itimer_signals(void); - -extern void do_group_exit(int); - -extern int do_execve(struct filename *, - const char __user * const __user *, - const char __user * const __user *); -extern int do_execveat(int, struct filename *, - const char __user * const __user *, - const char __user * const __user *, - int); -extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long); -extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); -struct task_struct *fork_idle(int); -extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); - extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); + static inline void set_task_comm(struct task_struct *tsk, const char *from) { __set_task_comm(tsk, from, false); } + extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP @@ -3029,260 +1465,15 @@ void scheduler_ipi(void); extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else static inline void scheduler_ipi(void) { } -static inline unsigned long wait_task_inactive(struct task_struct *p, - long match_state) +static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state) { return 1; } #endif -#define tasklist_empty() \ - list_empty(&init_task.tasks) - -#define next_task(p) \ - list_entry_rcu((p)->tasks.next, struct task_struct, tasks) - -#define for_each_process(p) \ - for (p = &init_task ; (p = next_task(p)) != &init_task ; ) - -extern bool current_is_single_threaded(void); - -/* - * Careful: do_each_thread/while_each_thread is a double loop so - * 'break' will not work as expected - use goto instead. - */ -#define do_each_thread(g, t) \ - for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do - -#define while_each_thread(g, t) \ - while ((t = next_thread(t)) != g) - -#define __for_each_thread(signal, t) \ - list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node) - -#define for_each_thread(p, t) \ - __for_each_thread((p)->signal, t) - -/* Careful: this is a double loop, 'break' won't work as expected. */ -#define for_each_process_thread(p, t) \ - for_each_process(p) for_each_thread(p, t) - -static inline int get_nr_threads(struct task_struct *tsk) -{ - return tsk->signal->nr_threads; -} - -static inline bool thread_group_leader(struct task_struct *p) -{ - return p->exit_signal >= 0; -} - -/* Do to the insanities of de_thread it is possible for a process - * to have the pid of the thread group leader without actually being - * the thread group leader. For iteration through the pids in proc - * all we care about is that we have a task with the appropriate - * pid, we don't actually care if we have the right task. - */ -static inline bool has_group_leader_pid(struct task_struct *p) -{ - return task_pid(p) == p->signal->leader_pid; -} - -static inline -bool same_thread_group(struct task_struct *p1, struct task_struct *p2) -{ - return p1->signal == p2->signal; -} - -static inline struct task_struct *next_thread(const struct task_struct *p) -{ - return list_entry_rcu(p->thread_group.next, - struct task_struct, thread_group); -} - -static inline int thread_group_empty(struct task_struct *p) -{ - return list_empty(&p->thread_group); -} - -#define delay_group_leader(p) \ - (thread_group_leader(p) && !thread_group_empty(p)) - -/* - * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring - * subscriptions and synchronises with wait4(). Also used in procfs. Also - * pins the final release of task.io_context. Also protects ->cpuset and - * ->cgroup.subsys[]. And ->vfork_done. - * - * Nests both inside and outside of read_lock(&tasklist_lock). - * It must not be nested with write_lock_irq(&tasklist_lock), - * neither inside nor outside. - */ -static inline void task_lock(struct task_struct *p) -{ - spin_lock(&p->alloc_lock); -} - -static inline void task_unlock(struct task_struct *p) -{ - spin_unlock(&p->alloc_lock); -} - -extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, - unsigned long *flags); - -static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk, - unsigned long *flags) -{ - struct sighand_struct *ret; - - ret = __lock_task_sighand(tsk, flags); - (void)__cond_lock(&tsk->sighand->siglock, ret); - return ret; -} - -static inline void unlock_task_sighand(struct task_struct *tsk, - unsigned long *flags) -{ - spin_unlock_irqrestore(&tsk->sighand->siglock, *flags); -} - -/** - * threadgroup_change_begin - mark the beginning of changes to a threadgroup - * @tsk: task causing the changes - * - * All operations which modify a threadgroup - a new thread joining the - * group, death of a member thread (the assertion of PF_EXITING) and - * exec(2) dethreading the process and replacing the leader - are wrapped - * by threadgroup_change_{begin|end}(). This is to provide a place which - * subsystems needing threadgroup stability can hook into for - * synchronization. - */ -static inline void threadgroup_change_begin(struct task_struct *tsk) -{ - might_sleep(); - cgroup_threadgroup_change_begin(tsk); -} - -/** - * threadgroup_change_end - mark the end of changes to a threadgroup - * @tsk: task causing the changes - * - * See threadgroup_change_begin(). - */ -static inline void threadgroup_change_end(struct task_struct *tsk) -{ - cgroup_threadgroup_change_end(tsk); -} - -#ifdef CONFIG_THREAD_INFO_IN_TASK - -static inline struct thread_info *task_thread_info(struct task_struct *task) -{ - return &task->thread_info; -} - -/* - * When accessing the stack of a non-current task that might exit, use - * try_get_task_stack() instead. task_stack_page will return a pointer - * that could get freed out from under you. - */ -static inline void *task_stack_page(const struct task_struct *task) -{ - return task->stack; -} - -#define setup_thread_stack(new,old) do { } while(0) - -static inline unsigned long *end_of_stack(const struct task_struct *task) -{ - return task->stack; -} - -#elif !defined(__HAVE_THREAD_FUNCTIONS) - -#define task_thread_info(task) ((struct thread_info *)(task)->stack) -#define task_stack_page(task) ((void *)(task)->stack) - -static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) -{ - *task_thread_info(p) = *task_thread_info(org); - task_thread_info(p)->task = p; -} - /* - * Return the address of the last usable long on the stack. - * - * When the stack grows down, this is just above the thread - * info struct. Going any lower will corrupt the threadinfo. - * - * When the stack grows up, this is the highest address. - * Beyond that position, we corrupt data on the next page. - */ -static inline unsigned long *end_of_stack(struct task_struct *p) -{ -#ifdef CONFIG_STACK_GROWSUP - return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1; -#else - return (unsigned long *)(task_thread_info(p) + 1); -#endif -} - -#endif - -#ifdef CONFIG_THREAD_INFO_IN_TASK -static inline void *try_get_task_stack(struct task_struct *tsk) -{ - return atomic_inc_not_zero(&tsk->stack_refcount) ? - task_stack_page(tsk) : NULL; -} - -extern void put_task_stack(struct task_struct *tsk); -#else -static inline void *try_get_task_stack(struct task_struct *tsk) -{ - return task_stack_page(tsk); -} - -static inline void put_task_stack(struct task_struct *tsk) {} -#endif - -#define task_stack_end_corrupted(task) \ - (*(end_of_stack(task)) != STACK_END_MAGIC) - -static inline int object_is_on_stack(void *obj) -{ - void *stack = task_stack_page(current); - - return (obj >= stack) && (obj < (stack + THREAD_SIZE)); -} - -extern void thread_stack_cache_init(void); - -#ifdef CONFIG_DEBUG_STACK_USAGE -static inline unsigned long stack_not_used(struct task_struct *p) -{ - unsigned long *n = end_of_stack(p); - - do { /* Skip over canary */ -# ifdef CONFIG_STACK_GROWSUP - n--; -# else - n++; -# endif - } while (!*n); - -# ifdef CONFIG_STACK_GROWSUP - return (unsigned long)end_of_stack(p) - (unsigned long)n; -# else - return (unsigned long)n - (unsigned long)end_of_stack(p); -# endif -} -#endif -extern void set_task_stack_end_magic(struct task_struct *tsk); - -/* set thread flags in other task's structures - * - see asm/thread_info.h for TIF_xxxx flags available + * Set thread flags in other task's structures. + * See asm/thread_info.h for TIF_xxxx flags available: */ static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag) { @@ -3324,37 +1515,6 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } -static inline int restart_syscall(void) -{ - set_tsk_thread_flag(current, TIF_SIGPENDING); - return -ERESTARTNOINTR; -} - -static inline int signal_pending(struct task_struct *p) -{ - return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); -} - -static inline int __fatal_signal_pending(struct task_struct *p) -{ - return unlikely(sigismember(&p->pending.signal, SIGKILL)); -} - -static inline int fatal_signal_pending(struct task_struct *p) -{ - return signal_pending(p) && __fatal_signal_pending(p); -} - -static inline int signal_pending_state(long state, struct task_struct *p) -{ - if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) - return 0; - if (!signal_pending(p)) - return 0; - - return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); -} - /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return @@ -3396,15 +1556,6 @@ static inline void cond_resched_rcu(void) #endif } -static inline unsigned long get_preempt_disable_ip(struct task_struct *p) -{ -#ifdef CONFIG_DEBUG_PREEMPT - return p->preempt_disable_ip; -#else - return 0; -#endif -} - /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPT, @@ -3419,114 +1570,12 @@ static inline int spin_needbreak(spinlock_t *lock) #endif } -/* - * Idle thread specific functions to determine the need_resched - * polling state. - */ -#ifdef TIF_POLLING_NRFLAG -static inline int tsk_is_polling(struct task_struct *p) -{ - return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); -} - -static inline void __current_set_polling(void) -{ - set_thread_flag(TIF_POLLING_NRFLAG); -} - -static inline bool __must_check current_set_polling_and_test(void) -{ - __current_set_polling(); - - /* - * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_curr() - */ - smp_mb__after_atomic(); - - return unlikely(tif_need_resched()); -} - -static inline void __current_clr_polling(void) -{ - clear_thread_flag(TIF_POLLING_NRFLAG); -} - -static inline bool __must_check current_clr_polling_and_test(void) -{ - __current_clr_polling(); - - /* - * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_curr() - */ - smp_mb__after_atomic(); - - return unlikely(tif_need_resched()); -} - -#else -static inline int tsk_is_polling(struct task_struct *p) { return 0; } -static inline void __current_set_polling(void) { } -static inline void __current_clr_polling(void) { } - -static inline bool __must_check current_set_polling_and_test(void) -{ - return unlikely(tif_need_resched()); -} -static inline bool __must_check current_clr_polling_and_test(void) -{ - return unlikely(tif_need_resched()); -} -#endif - -static inline void current_clr_polling(void) -{ - __current_clr_polling(); - - /* - * Ensure we check TIF_NEED_RESCHED after we clear the polling bit. - * Once the bit is cleared, we'll get IPIs with every new - * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also - * fold. - */ - smp_mb(); /* paired with resched_curr() */ - - preempt_fold_need_resched(); -} - static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); } /* - * Thread group CPU time accounting. - */ -void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times); -void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times); - -/* - * Reevaluate whether the task has signals pending delivery. - * Wake the task if so. - * This is required every time the blocked sigset_t changes. - * callers must hold sighand->siglock. - */ -extern void recalc_sigpending_and_wake(struct task_struct *t); -extern void recalc_sigpending(void); - -extern void signal_wake_up_state(struct task_struct *t, unsigned int state); - -static inline void signal_wake_up(struct task_struct *t, bool resume) -{ - signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); -} -static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) -{ - signal_wake_up_state(t, resume ? __TASK_TRACED : 0); -} - -/* * Wrappers for p->thread_info->cpu access. No-op on UP. */ #ifdef CONFIG_SMP @@ -3540,11 +1589,6 @@ static inline unsigned int task_cpu(const struct task_struct *p) #endif } -static inline int task_node(const struct task_struct *p) -{ - return cpu_to_node(task_cpu(p)); -} - extern void set_task_cpu(struct task_struct *p, unsigned int cpu); #else @@ -3575,100 +1619,8 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); -#ifdef CONFIG_CGROUP_SCHED -extern struct task_group root_task_group; -#endif /* CONFIG_CGROUP_SCHED */ - -extern int task_can_switch_user(struct user_struct *up, - struct task_struct *tsk); - -#ifdef CONFIG_TASK_XACCT -static inline void add_rchar(struct task_struct *tsk, ssize_t amt) -{ - tsk->ioac.rchar += amt; -} - -static inline void add_wchar(struct task_struct *tsk, ssize_t amt) -{ - tsk->ioac.wchar += amt; -} - -static inline void inc_syscr(struct task_struct *tsk) -{ - tsk->ioac.syscr++; -} - -static inline void inc_syscw(struct task_struct *tsk) -{ - tsk->ioac.syscw++; -} -#else -static inline void add_rchar(struct task_struct *tsk, ssize_t amt) -{ -} - -static inline void add_wchar(struct task_struct *tsk, ssize_t amt) -{ -} - -static inline void inc_syscr(struct task_struct *tsk) -{ -} - -static inline void inc_syscw(struct task_struct *tsk) -{ -} -#endif - #ifndef TASK_SIZE_OF #define TASK_SIZE_OF(tsk) TASK_SIZE #endif -#ifdef CONFIG_MEMCG -extern void mm_update_next_owner(struct mm_struct *mm); -#else -static inline void mm_update_next_owner(struct mm_struct *mm) -{ -} -#endif /* CONFIG_MEMCG */ - -static inline unsigned long task_rlimit(const struct task_struct *tsk, - unsigned int limit) -{ - return READ_ONCE(tsk->signal->rlim[limit].rlim_cur); -} - -static inline unsigned long task_rlimit_max(const struct task_struct *tsk, - unsigned int limit) -{ - return READ_ONCE(tsk->signal->rlim[limit].rlim_max); -} - -static inline unsigned long rlimit(unsigned int limit) -{ - return task_rlimit(current, limit); -} - -static inline unsigned long rlimit_max(unsigned int limit) -{ - return task_rlimit_max(current, limit); -} - -#define SCHED_CPUFREQ_RT (1U << 0) -#define SCHED_CPUFREQ_DL (1U << 1) -#define SCHED_CPUFREQ_IOWAIT (1U << 2) - -#define SCHED_CPUFREQ_RT_DL (SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL) - -#ifdef CONFIG_CPU_FREQ -struct update_util_data { - void (*func)(struct update_util_data *data, u64 time, unsigned int flags); -}; - -void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, - void (*func)(struct update_util_data *data, u64 time, - unsigned int flags)); -void cpufreq_remove_update_util_hook(int cpu); -#endif /* CONFIG_CPU_FREQ */ - #endif diff --git a/include/linux/sched/autogroup.h b/include/linux/sched/autogroup.h new file mode 100644 index 000000000000..55cd496df884 --- /dev/null +++ b/include/linux/sched/autogroup.h @@ -0,0 +1,31 @@ +#ifndef _LINUX_SCHED_AUTOGROUP_H +#define _LINUX_SCHED_AUTOGROUP_H + +struct signal_struct; +struct task_struct; +struct task_group; +struct seq_file; + +#ifdef CONFIG_SCHED_AUTOGROUP +extern void sched_autogroup_create_attach(struct task_struct *p); +extern void sched_autogroup_detach(struct task_struct *p); +extern void sched_autogroup_fork(struct signal_struct *sig); +extern void sched_autogroup_exit(struct signal_struct *sig); +extern void sched_autogroup_exit_task(struct task_struct *p); +#ifdef CONFIG_PROC_FS +extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); +extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice); +#endif +#else +static inline void sched_autogroup_create_attach(struct task_struct *p) { } +static inline void sched_autogroup_detach(struct task_struct *p) { } +static inline void sched_autogroup_fork(struct signal_struct *sig) { } +static inline void sched_autogroup_exit(struct signal_struct *sig) { } +static inline void sched_autogroup_exit_task(struct task_struct *p) { } +#endif + +#ifdef CONFIG_CGROUP_SCHED +extern struct task_group root_task_group; +#endif /* CONFIG_CGROUP_SCHED */ + +#endif /* _LINUX_SCHED_AUTOGROUP_H */ diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h new file mode 100644 index 000000000000..a55600ffdf4b --- /dev/null +++ b/include/linux/sched/clock.h @@ -0,0 +1,100 @@ +#ifndef _LINUX_SCHED_CLOCK_H +#define _LINUX_SCHED_CLOCK_H + +#include <linux/smp.h> + +/* + * Do not use outside of architecture code which knows its limitations. + * + * sched_clock() has no promise of monotonicity or bounded drift between + * CPUs, use (which you should not) requires disabling IRQs. + * + * Please use one of the three interfaces below. + */ +extern unsigned long long notrace sched_clock(void); + +/* + * See the comment in kernel/sched/clock.c + */ +extern u64 running_clock(void); +extern u64 sched_clock_cpu(int cpu); + + +extern void sched_clock_init(void); + +#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK +static inline void sched_clock_tick(void) +{ +} + +static inline void clear_sched_clock_stable(void) +{ +} + +static inline void sched_clock_idle_sleep_event(void) +{ +} + +static inline void sched_clock_idle_wakeup_event(void) +{ +} + +static inline u64 cpu_clock(int cpu) +{ + return sched_clock(); +} + +static inline u64 local_clock(void) +{ + return sched_clock(); +} +#else +extern int sched_clock_stable(void); +extern void clear_sched_clock_stable(void); + +/* + * When sched_clock_stable(), __sched_clock_offset provides the offset + * between local_clock() and sched_clock(). + */ +extern u64 __sched_clock_offset; + +extern void sched_clock_tick(void); +extern void sched_clock_tick_stable(void); +extern void sched_clock_idle_sleep_event(void); +extern void sched_clock_idle_wakeup_event(void); + +/* + * As outlined in clock.c, provides a fast, high resolution, nanosecond + * time source that is monotonic per cpu argument and has bounded drift + * between cpus. + * + * ######################### BIG FAT WARNING ########################## + * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # + * # go backwards !! # + * #################################################################### + */ +static inline u64 cpu_clock(int cpu) +{ + return sched_clock_cpu(cpu); +} + +static inline u64 local_clock(void) +{ + return sched_clock_cpu(raw_smp_processor_id()); +} +#endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +/* + * An i/f to runtime opt-in for irq time accounting based off of sched_clock. + * The reason for this explicit opt-in is not to have perf penalty with + * slow sched_clocks. + */ +extern void enable_sched_clock_irqtime(void); +extern void disable_sched_clock_irqtime(void); +#else +static inline void enable_sched_clock_irqtime(void) {} +static inline void disable_sched_clock_irqtime(void) {} +#endif + +#endif /* _LINUX_SCHED_CLOCK_H */ diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h new file mode 100644 index 000000000000..98ae0d05aa32 --- /dev/null +++ b/include/linux/sched/coredump.h @@ -0,0 +1,77 @@ +#ifndef _LINUX_SCHED_COREDUMP_H +#define _LINUX_SCHED_COREDUMP_H + +#include <linux/mm_types.h> + +#define SUID_DUMP_DISABLE 0 /* No setuid dumping */ +#define SUID_DUMP_USER 1 /* Dump as user of process */ +#define SUID_DUMP_ROOT 2 /* Dump as root */ + +/* mm flags */ + +/* for SUID_DUMP_* above */ +#define MMF_DUMPABLE_BITS 2 +#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) + +extern void set_dumpable(struct mm_struct *mm, int value); +/* + * This returns the actual value of the suid_dumpable flag. For things + * that are using this for checking for privilege transitions, it must + * test against SUID_DUMP_USER rather than treating it as a boolean + * value. + */ +static inline int __get_dumpable(unsigned long mm_flags) +{ + return mm_flags & MMF_DUMPABLE_MASK; +} + +static inline int get_dumpable(struct mm_struct *mm) +{ + return __get_dumpable(mm->flags); +} + +/* coredump filter bits */ +#define MMF_DUMP_ANON_PRIVATE 2 +#define MMF_DUMP_ANON_SHARED 3 +#define MMF_DUMP_MAPPED_PRIVATE 4 +#define MMF_DUMP_MAPPED_SHARED 5 +#define MMF_DUMP_ELF_HEADERS 6 +#define MMF_DUMP_HUGETLB_PRIVATE 7 +#define MMF_DUMP_HUGETLB_SHARED 8 +#define MMF_DUMP_DAX_PRIVATE 9 +#define MMF_DUMP_DAX_SHARED 10 + +#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS +#define MMF_DUMP_FILTER_BITS 9 +#define MMF_DUMP_FILTER_MASK \ + (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) +#define MMF_DUMP_FILTER_DEFAULT \ + ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ + (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) + +#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS +# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) +#else +# define MMF_DUMP_MASK_DEFAULT_ELF 0 +#endif + /* leave room for more dump flags */ +#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ +#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ +/* + * This one-shot flag is dropped due to necessity of changing exe once again + * on NFS restore + */ +//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ + +#define MMF_HAS_UPROBES 19 /* has uprobes */ +#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ +#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ +#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ +#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ +#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ +#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) + +#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ + MMF_DISABLE_THP_MASK) + +#endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h new file mode 100644 index 000000000000..d2be2ccbb372 --- /dev/null +++ b/include/linux/sched/cpufreq.h @@ -0,0 +1,27 @@ +#ifndef _LINUX_SCHED_CPUFREQ_H +#define _LINUX_SCHED_CPUFREQ_H + +#include <linux/types.h> + +/* + * Interface between cpufreq drivers and the scheduler: + */ + +#define SCHED_CPUFREQ_RT (1U << 0) +#define SCHED_CPUFREQ_DL (1U << 1) +#define SCHED_CPUFREQ_IOWAIT (1U << 2) + +#define SCHED_CPUFREQ_RT_DL (SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL) + +#ifdef CONFIG_CPU_FREQ +struct update_util_data { + void (*func)(struct update_util_data *data, u64 time, unsigned int flags); +}; + +void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, + void (*func)(struct update_util_data *data, u64 time, + unsigned int flags)); +void cpufreq_remove_update_util_hook(int cpu); +#endif /* CONFIG_CPU_FREQ */ + +#endif /* _LINUX_SCHED_CPUFREQ_H */ diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h new file mode 100644 index 000000000000..4c5b9735c1ae --- /dev/null +++ b/include/linux/sched/cputime.h @@ -0,0 +1,187 @@ +#ifndef _LINUX_SCHED_CPUTIME_H +#define _LINUX_SCHED_CPUTIME_H + +#include <linux/sched/signal.h> + +/* + * cputime accounting APIs: + */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +#include <asm/cputime.h> + +#ifndef cputime_to_nsecs +# define cputime_to_nsecs(__ct) \ + (cputime_to_usecs(__ct) * NSEC_PER_USEC) +#endif +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern void task_cputime(struct task_struct *t, + u64 *utime, u64 *stime); +extern u64 task_gtime(struct task_struct *t); +#else +static inline void task_cputime(struct task_struct *t, + u64 *utime, u64 *stime) +{ + *utime = t->utime; + *stime = t->stime; +} + +static inline u64 task_gtime(struct task_struct *t) +{ + return t->gtime; +} +#endif + +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME +static inline void task_cputime_scaled(struct task_struct *t, + u64 *utimescaled, + u64 *stimescaled) +{ + *utimescaled = t->utimescaled; + *stimescaled = t->stimescaled; +} +#else +static inline void task_cputime_scaled(struct task_struct *t, + u64 *utimescaled, + u64 *stimescaled) +{ + task_cputime(t, utimescaled, stimescaled); +} +#endif + +extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st); +extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st); + + +/* + * Thread group CPU time accounting. + */ +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times); +void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times); + + +/* + * The following are functions that support scheduler-internal time accounting. + * These functions are generally called at the timer tick. None of this depends + * on CONFIG_SCHEDSTATS. + */ + +/** + * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running + * + * @tsk: Pointer to target task. + */ +#ifdef CONFIG_POSIX_TIMERS +static inline +struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + /* Check if cputimer isn't running. This is accessed without locking. */ + if (!READ_ONCE(cputimer->running)) + return NULL; + + /* + * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime + * in __exit_signal(), we won't account to the signal struct further + * cputime consumed by that task, even though the task can still be + * ticking after __exit_signal(). + * + * In order to keep a consistent behaviour between thread group cputime + * and thread group cputimer accounting, lets also ignore the cputime + * elapsing after __exit_signal() in any thread group timer running. + * + * This makes sure that POSIX CPU clocks and timers are synchronized, so + * that a POSIX CPU timer won't expire while the corresponding POSIX CPU + * clock delta is behind the expiring timer value. + */ + if (unlikely(!tsk->sighand)) + return NULL; + + return cputimer; +} +#else +static inline +struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) +{ + return NULL; +} +#endif + +/** + * account_group_user_time - Maintain utime for a thread group. + * + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the utime field of the + * thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void account_group_user_time(struct task_struct *tsk, + u64 cputime) +{ + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); + + if (!cputimer) + return; + + atomic64_add(cputime, &cputimer->cputime_atomic.utime); +} + +/** + * account_group_system_time - Maintain stime for a thread group. + * + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the stime field of the + * thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void account_group_system_time(struct task_struct *tsk, + u64 cputime) +{ + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); + + if (!cputimer) + return; + + atomic64_add(cputime, &cputimer->cputime_atomic.stime); +} + +/** + * account_group_exec_runtime - Maintain exec runtime for a thread group. + * + * @tsk: Pointer to task structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of the thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); + + if (!cputimer) + return; + + atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime); +} + +static inline void prev_cputime_init(struct prev_cputime *prev) +{ +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + prev->utime = prev->stime = 0; + raw_spin_lock_init(&prev->lock); +#endif +} + +extern unsigned long long +task_sched_runtime(struct task_struct *task); + +#endif /* _LINUX_SCHED_CPUTIME_H */ diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 9089a2ae913d..975be862e083 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -1,5 +1,7 @@ -#ifndef _SCHED_DEADLINE_H -#define _SCHED_DEADLINE_H +#ifndef _LINUX_SCHED_DEADLINE_H +#define _LINUX_SCHED_DEADLINE_H + +#include <linux/sched.h> /* * SCHED_DEADLINE tasks has negative priorities, reflecting @@ -26,4 +28,4 @@ static inline bool dl_time_before(u64 a, u64 b) return (s64)(a - b) < 0; } -#endif /* _SCHED_DEADLINE_H */ +#endif /* _LINUX_SCHED_DEADLINE_H */ diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h new file mode 100644 index 000000000000..e0eaee54c5a4 --- /dev/null +++ b/include/linux/sched/debug.h @@ -0,0 +1,50 @@ +#ifndef _LINUX_SCHED_DEBUG_H +#define _LINUX_SCHED_DEBUG_H + +/* + * Various scheduler/task debugging interfaces: + */ + +struct task_struct; + +extern void dump_cpu_task(int cpu); + +/* + * Only dump TASK_* tasks. (0 for all tasks) + */ +extern void show_state_filter(unsigned long state_filter); + +static inline void show_state(void) +{ + show_state_filter(0); +} + +struct pt_regs; + +extern void show_regs(struct pt_regs *); + +/* + * TASK is a pointer to the task whose backtrace we want to see (or NULL for current + * task), SP is the stack pointer of the first frame that should be shown in the back + * trace (or NULL if the entire call-chain of the task should be shown). + */ +extern void show_stack(struct task_struct *task, unsigned long *sp); + +extern void sched_show_task(struct task_struct *p); + +#ifdef CONFIG_SCHED_DEBUG +struct seq_file; +extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); +extern void proc_sched_set_task(struct task_struct *p); +#endif + +/* Attach to any functions which should be ignored in wchan output. */ +#define __sched __attribute__((__section__(".sched.text"))) + +/* Linker adds these: start and end of __sched functions */ +extern char __sched_text_start[], __sched_text_end[]; + +/* Is this address in the __sched functions? */ +extern int in_sched_functions(unsigned long addr); + +#endif /* _LINUX_SCHED_DEBUG_H */ diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h new file mode 100644 index 000000000000..752ac7e628d7 --- /dev/null +++ b/include/linux/sched/hotplug.h @@ -0,0 +1,24 @@ +#ifndef _LINUX_SCHED_HOTPLUG_H +#define _LINUX_SCHED_HOTPLUG_H + +/* + * Scheduler interfaces for hotplug CPU support: + */ + +extern int sched_cpu_starting(unsigned int cpu); +extern int sched_cpu_activate(unsigned int cpu); +extern int sched_cpu_deactivate(unsigned int cpu); + +#ifdef CONFIG_HOTPLUG_CPU +extern int sched_cpu_dying(unsigned int cpu); +#else +# define sched_cpu_dying NULL +#endif + +#ifdef CONFIG_HOTPLUG_CPU +extern void idle_task_exit(void); +#else +static inline void idle_task_exit(void) {} +#endif + +#endif /* _LINUX_SCHED_HOTPLUG_H */ diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h new file mode 100644 index 000000000000..5ca63ebad6b4 --- /dev/null +++ b/include/linux/sched/idle.h @@ -0,0 +1,86 @@ +#ifndef _LINUX_SCHED_IDLE_H +#define _LINUX_SCHED_IDLE_H + +#include <linux/sched.h> + +enum cpu_idle_type { + CPU_IDLE, + CPU_NOT_IDLE, + CPU_NEWLY_IDLE, + CPU_MAX_IDLE_TYPES +}; + +extern void wake_up_if_idle(int cpu); + +/* + * Idle thread specific functions to determine the need_resched + * polling state. + */ +#ifdef TIF_POLLING_NRFLAG + +static inline void __current_set_polling(void) +{ + set_thread_flag(TIF_POLLING_NRFLAG); +} + +static inline bool __must_check current_set_polling_and_test(void) +{ + __current_set_polling(); + + /* + * Polling state must be visible before we test NEED_RESCHED, + * paired by resched_curr() + */ + smp_mb__after_atomic(); + + return unlikely(tif_need_resched()); +} + +static inline void __current_clr_polling(void) +{ + clear_thread_flag(TIF_POLLING_NRFLAG); +} + +static inline bool __must_check current_clr_polling_and_test(void) +{ + __current_clr_polling(); + + /* + * Polling state must be visible before we test NEED_RESCHED, + * paired by resched_curr() + */ + smp_mb__after_atomic(); + + return unlikely(tif_need_resched()); +} + +#else +static inline void __current_set_polling(void) { } +static inline void __current_clr_polling(void) { } + +static inline bool __must_check current_set_polling_and_test(void) +{ + return unlikely(tif_need_resched()); +} +static inline bool __must_check current_clr_polling_and_test(void) +{ + return unlikely(tif_need_resched()); +} +#endif + +static inline void current_clr_polling(void) +{ + __current_clr_polling(); + + /* + * Ensure we check TIF_NEED_RESCHED after we clear the polling bit. + * Once the bit is cleared, we'll get IPIs with every new + * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also + * fold. + */ + smp_mb(); /* paired with resched_curr() */ + + preempt_fold_need_resched(); +} + +#endif /* _LINUX_SCHED_IDLE_H */ diff --git a/include/linux/sched/init.h b/include/linux/sched/init.h new file mode 100644 index 000000000000..127215045285 --- /dev/null +++ b/include/linux/sched/init.h @@ -0,0 +1,11 @@ +#ifndef _LINUX_SCHED_INIT_H +#define _LINUX_SCHED_INIT_H + +/* + * Scheduler init related prototypes: + */ + +extern void sched_init(void); +extern void sched_init_smp(void); + +#endif /* _LINUX_SCHED_INIT_H */ diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h new file mode 100644 index 000000000000..016afa0fb3bb --- /dev/null +++ b/include/linux/sched/jobctl.h @@ -0,0 +1,36 @@ +#ifndef _LINUX_SCHED_JOBCTL_H +#define _LINUX_SCHED_JOBCTL_H + +#include <linux/types.h> + +struct task_struct; + +/* + * task->jobctl flags + */ +#define JOBCTL_STOP_SIGMASK 0xffff /* signr of the last group stop */ + +#define JOBCTL_STOP_DEQUEUED_BIT 16 /* stop signal dequeued */ +#define JOBCTL_STOP_PENDING_BIT 17 /* task should stop for group stop */ +#define JOBCTL_STOP_CONSUME_BIT 18 /* consume group stop count */ +#define JOBCTL_TRAP_STOP_BIT 19 /* trap for STOP */ +#define JOBCTL_TRAP_NOTIFY_BIT 20 /* trap for NOTIFY */ +#define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ +#define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ + +#define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) +#define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) +#define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT) +#define JOBCTL_TRAP_STOP (1UL << JOBCTL_TRAP_STOP_BIT) +#define JOBCTL_TRAP_NOTIFY (1UL << JOBCTL_TRAP_NOTIFY_BIT) +#define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) +#define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) + +#define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) +#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) + +extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask); +extern void task_clear_jobctl_trapping(struct task_struct *task); +extern void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask); + +#endif /* _LINUX_SCHED_JOBCTL_H */ diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h new file mode 100644 index 000000000000..4264bc6b2c27 --- /dev/null +++ b/include/linux/sched/loadavg.h @@ -0,0 +1,31 @@ +#ifndef _LINUX_SCHED_LOADAVG_H +#define _LINUX_SCHED_LOADAVG_H + +/* + * These are the constant used to fake the fixed-point load-average + * counting. Some notes: + * - 11 bit fractions expand to 22 bits by the multiplies: this gives + * a load-average precision of 10 bits integer + 11 bits fractional + * - if you want to count load-averages more often, you need more + * precision, or rounding will get you. With 2-second counting freq, + * the EXP_n values would be 1981, 2034 and 2043 if still using only + * 11 bit fractions. + */ +extern unsigned long avenrun[]; /* Load averages */ +extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); + +#define FSHIFT 11 /* nr of bits of precision */ +#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */ +#define LOAD_FREQ (5*HZ+1) /* 5 sec intervals */ +#define EXP_1 1884 /* 1/exp(5sec/1min) as fixed-point */ +#define EXP_5 2014 /* 1/exp(5sec/5min) */ +#define EXP_15 2037 /* 1/exp(5sec/15min) */ + +#define CALC_LOAD(load,exp,n) \ + load *= exp; \ + load += n*(FIXED_1-exp); \ + load >>= FSHIFT; + +extern void calc_global_load(unsigned long ticks); + +#endif /* _LINUX_SCHED_LOADAVG_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h new file mode 100644 index 000000000000..2b24a6974847 --- /dev/null +++ b/include/linux/sched/mm.h @@ -0,0 +1,206 @@ +#ifndef _LINUX_SCHED_MM_H +#define _LINUX_SCHED_MM_H + +#include <linux/kernel.h> +#include <linux/atomic.h> +#include <linux/sched.h> +#include <linux/mm_types.h> +#include <linux/gfp.h> + +/* + * Routines for handling mm_structs + */ +extern struct mm_struct * mm_alloc(void); + +/** + * mmgrab() - Pin a &struct mm_struct. + * @mm: The &struct mm_struct to pin. + * + * Make sure that @mm will not get freed even after the owning task + * exits. This doesn't guarantee that the associated address space + * will still exist later on and mmget_not_zero() has to be used before + * accessing it. + * + * This is a preferred way to to pin @mm for a longer/unbounded amount + * of time. + * + * Use mmdrop() to release the reference acquired by mmgrab(). + * + * See also <Documentation/vm/active_mm.txt> for an in-depth explanation + * of &mm_struct.mm_count vs &mm_struct.mm_users. + */ +static inline void mmgrab(struct mm_struct *mm) +{ + atomic_inc(&mm->mm_count); +} + +/* mmdrop drops the mm and the page tables */ +extern void __mmdrop(struct mm_struct *); +static inline void mmdrop(struct mm_struct *mm) +{ + if (unlikely(atomic_dec_and_test(&mm->mm_count))) + __mmdrop(mm); +} + +static inline void mmdrop_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); + __mmdrop(mm); +} + +static inline void mmdrop_async(struct mm_struct *mm) +{ + if (unlikely(atomic_dec_and_test(&mm->mm_count))) { + INIT_WORK(&mm->async_put_work, mmdrop_async_fn); + schedule_work(&mm->async_put_work); + } +} + +/** + * mmget() - Pin the address space associated with a &struct mm_struct. + * @mm: The address space to pin. + * + * Make sure that the address space of the given &struct mm_struct doesn't + * go away. This does not protect against parts of the address space being + * modified or freed, however. + * + * Never use this function to pin this address space for an + * unbounded/indefinite amount of time. + * + * Use mmput() to release the reference acquired by mmget(). + * + * See also <Documentation/vm/active_mm.txt> for an in-depth explanation + * of &mm_struct.mm_count vs &mm_struct.mm_users. + */ +static inline void mmget(struct mm_struct *mm) +{ + atomic_inc(&mm->mm_users); +} + +static inline bool mmget_not_zero(struct mm_struct *mm) +{ + return atomic_inc_not_zero(&mm->mm_users); +} + +/* mmput gets rid of the mappings and all user-space */ +extern void mmput(struct mm_struct *); +#ifdef CONFIG_MMU +/* same as above but performs the slow path from the async context. Can + * be called from the atomic context as well + */ +extern void mmput_async(struct mm_struct *); +#endif + +/* Grab a reference to a task's mm, if it is not already going away */ +extern struct mm_struct *get_task_mm(struct task_struct *task); +/* + * Grab a reference to a task's mm, if it is not already going away + * and ptrace_may_access with the mode parameter passed to it + * succeeds. + */ +extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); +/* Remove the current tasks stale references to the old mm_struct */ +extern void mm_release(struct task_struct *, struct mm_struct *); + +#ifdef CONFIG_MEMCG +extern void mm_update_next_owner(struct mm_struct *mm); +#else +static inline void mm_update_next_owner(struct mm_struct *mm) +{ +} +#endif /* CONFIG_MEMCG */ + +#ifdef CONFIG_MMU +extern void arch_pick_mmap_layout(struct mm_struct *mm); +extern unsigned long +arch_get_unmapped_area(struct file *, unsigned long, unsigned long, + unsigned long, unsigned long); +extern unsigned long +arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); +#else +static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} +#endif + +static inline bool in_vfork(struct task_struct *tsk) +{ + bool ret; + + /* + * need RCU to access ->real_parent if CLONE_VM was used along with + * CLONE_PARENT. + * + * We check real_parent->mm == tsk->mm because CLONE_VFORK does not + * imply CLONE_VM + * + * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus + * ->real_parent is not necessarily the task doing vfork(), so in + * theory we can't rely on task_lock() if we want to dereference it. + * + * And in this case we can't trust the real_parent->mm == tsk->mm + * check, it can be false negative. But we do not care, if init or + * another oom-unkillable task does this it should blame itself. + */ + rcu_read_lock(); + ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm; + rcu_read_unlock(); + + return ret; +} + +/* + * Applies per-task gfp context to the given allocation flags. + * PF_MEMALLOC_NOIO implies GFP_NOIO + * PF_MEMALLOC_NOFS implies GFP_NOFS + */ +static inline gfp_t current_gfp_context(gfp_t flags) +{ + /* + * NOIO implies both NOIO and NOFS and it is a weaker context + * so always make sure it makes precendence + */ + if (unlikely(current->flags & PF_MEMALLOC_NOIO)) + flags &= ~(__GFP_IO | __GFP_FS); + else if (unlikely(current->flags & PF_MEMALLOC_NOFS)) + flags &= ~__GFP_FS; + return flags; +} + +static inline unsigned int memalloc_noio_save(void) +{ + unsigned int flags = current->flags & PF_MEMALLOC_NOIO; + current->flags |= PF_MEMALLOC_NOIO; + return flags; +} + +static inline void memalloc_noio_restore(unsigned int flags) +{ + current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; +} + +static inline unsigned int memalloc_nofs_save(void) +{ + unsigned int flags = current->flags & PF_MEMALLOC_NOFS; + current->flags |= PF_MEMALLOC_NOFS; + return flags; +} + +static inline void memalloc_nofs_restore(unsigned int flags) +{ + current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags; +} + +static inline unsigned int memalloc_noreclaim_save(void) +{ + unsigned int flags = current->flags & PF_MEMALLOC; + current->flags |= PF_MEMALLOC; + return flags; +} + +static inline void memalloc_noreclaim_restore(unsigned int flags) +{ + current->flags = (current->flags & ~PF_MEMALLOC) | flags; +} + +#endif /* _LINUX_SCHED_MM_H */ diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h new file mode 100644 index 000000000000..028d17b918a7 --- /dev/null +++ b/include/linux/sched/nohz.h @@ -0,0 +1,43 @@ +#ifndef _LINUX_SCHED_NOHZ_H +#define _LINUX_SCHED_NOHZ_H + +/* + * This is the interface between the scheduler and nohz/dynticks: + */ + +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern void cpu_load_update_nohz_start(void); +extern void cpu_load_update_nohz_stop(void); +#else +static inline void cpu_load_update_nohz_start(void) { } +static inline void cpu_load_update_nohz_stop(void) { } +#endif + +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern void nohz_balance_enter_idle(int cpu); +extern void set_cpu_sd_state_idle(void); +extern int get_nohz_timer_target(void); +#else +static inline void nohz_balance_enter_idle(int cpu) { } +static inline void set_cpu_sd_state_idle(void) { } +#endif + +#ifdef CONFIG_NO_HZ_COMMON +void calc_load_nohz_start(void); +void calc_load_nohz_stop(void); +#else +static inline void calc_load_nohz_start(void) { } +static inline void calc_load_nohz_stop(void) { } +#endif /* CONFIG_NO_HZ_COMMON */ + +#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) +extern void wake_up_nohz_cpu(int cpu); +#else +static inline void wake_up_nohz_cpu(int cpu) { } +#endif + +#ifdef CONFIG_NO_HZ_FULL +extern u64 scheduler_tick_max_deferment(void); +#endif + +#endif /* _LINUX_SCHED_NOHZ_H */ diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h new file mode 100644 index 000000000000..35d5fc77b4be --- /dev/null +++ b/include/linux/sched/numa_balancing.h @@ -0,0 +1,46 @@ +#ifndef _LINUX_SCHED_NUMA_BALANCING_H +#define _LINUX_SCHED_NUMA_BALANCING_H + +/* + * This is the interface between the scheduler and the MM that + * implements memory access pattern based NUMA-balancing: + */ + +#include <linux/sched.h> + +#define TNF_MIGRATED 0x01 +#define TNF_NO_GROUP 0x02 +#define TNF_SHARED 0x04 +#define TNF_FAULT_LOCAL 0x08 +#define TNF_MIGRATE_FAIL 0x10 + +#ifdef CONFIG_NUMA_BALANCING +extern void task_numa_fault(int last_node, int node, int pages, int flags); +extern pid_t task_numa_group_id(struct task_struct *p); +extern void set_numabalancing_state(bool enabled); +extern void task_numa_free(struct task_struct *p); +extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, + int src_nid, int dst_cpu); +#else +static inline void task_numa_fault(int last_node, int node, int pages, + int flags) +{ +} +static inline pid_t task_numa_group_id(struct task_struct *p) +{ + return 0; +} +static inline void set_numabalancing_state(bool enabled) +{ +} +static inline void task_numa_free(struct task_struct *p) +{ +} +static inline bool should_numa_migrate_memory(struct task_struct *p, + struct page *page, int src_nid, int dst_cpu) +{ + return true; +} +#endif + +#endif /* _LINUX_SCHED_NUMA_BALANCING_H */ diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h index d9cf5a5762d9..2cc450f6ec54 100644 --- a/include/linux/sched/prio.h +++ b/include/linux/sched/prio.h @@ -1,5 +1,5 @@ -#ifndef _SCHED_PRIO_H -#define _SCHED_PRIO_H +#ifndef _LINUX_SCHED_PRIO_H +#define _LINUX_SCHED_PRIO_H #define MAX_NICE 19 #define MIN_NICE -20 @@ -57,4 +57,4 @@ static inline long rlimit_to_nice(long prio) return (MAX_NICE - prio + 1); } -#endif /* _SCHED_PRIO_H */ +#endif /* _LINUX_SCHED_PRIO_H */ diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index a30b172df6e1..f93329aba31a 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -1,7 +1,9 @@ -#ifndef _SCHED_RT_H -#define _SCHED_RT_H +#ifndef _LINUX_SCHED_RT_H +#define _LINUX_SCHED_RT_H -#include <linux/sched/prio.h> +#include <linux/sched.h> + +struct task_struct; static inline int rt_prio(int prio) { @@ -16,27 +18,20 @@ static inline int rt_task(struct task_struct *p) } #ifdef CONFIG_RT_MUTEXES -extern int rt_mutex_getprio(struct task_struct *p); -extern void rt_mutex_setprio(struct task_struct *p, int prio); -extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio); -extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task); +/* + * Must hold either p->pi_lock or task_rq(p)->lock. + */ +static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p) +{ + return p->pi_top_task; +} +extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task); extern void rt_mutex_adjust_pi(struct task_struct *p); static inline bool tsk_is_pi_blocked(struct task_struct *tsk) { return tsk->pi_blocked_on != NULL; } #else -static inline int rt_mutex_getprio(struct task_struct *p) -{ - return p->normal_prio; -} - -static inline int rt_mutex_get_effective_prio(struct task_struct *task, - int newprio) -{ - return newprio; -} - static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) { return NULL; @@ -57,4 +52,4 @@ extern void normalize_rt_tasks(void); */ #define RR_TIMESLICE (100 * HZ / 1000) -#endif /* _SCHED_RT_H */ +#endif /* _LINUX_SCHED_RT_H */ diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h new file mode 100644 index 000000000000..2a0dd40b15db --- /dev/null +++ b/include/linux/sched/signal.h @@ -0,0 +1,612 @@ +#ifndef _LINUX_SCHED_SIGNAL_H +#define _LINUX_SCHED_SIGNAL_H + +#include <linux/rculist.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/sched/jobctl.h> +#include <linux/sched/task.h> +#include <linux/cred.h> + +/* + * Types defining task->signal and task->sighand and APIs using them: + */ + +struct sighand_struct { + atomic_t count; + struct k_sigaction action[_NSIG]; + spinlock_t siglock; + wait_queue_head_t signalfd_wqh; +}; + +/* + * Per-process accounting stats: + */ +struct pacct_struct { + int ac_flag; + long ac_exitcode; + unsigned long ac_mem; + u64 ac_utime, ac_stime; + unsigned long ac_minflt, ac_majflt; +}; + +struct cpu_itimer { + u64 expires; + u64 incr; +}; + +/* + * This is the atomic variant of task_cputime, which can be used for + * storing and updating task_cputime statistics without locking. + */ +struct task_cputime_atomic { + atomic64_t utime; + atomic64_t stime; + atomic64_t sum_exec_runtime; +}; + +#define INIT_CPUTIME_ATOMIC \ + (struct task_cputime_atomic) { \ + .utime = ATOMIC64_INIT(0), \ + .stime = ATOMIC64_INIT(0), \ + .sum_exec_runtime = ATOMIC64_INIT(0), \ + } +/** + * struct thread_group_cputimer - thread group interval timer counts + * @cputime_atomic: atomic thread group interval timers. + * @running: true when there are timers running and + * @cputime_atomic receives updates. + * @checking_timer: true when a thread in the group is in the + * process of checking for thread group timers. + * + * This structure contains the version of task_cputime, above, that is + * used for thread group CPU timer calculations. + */ +struct thread_group_cputimer { + struct task_cputime_atomic cputime_atomic; + bool running; + bool checking_timer; +}; + +/* + * NOTE! "signal_struct" does not have its own + * locking, because a shared signal_struct always + * implies a shared sighand_struct, so locking + * sighand_struct is always a proper superset of + * the locking of signal_struct. + */ +struct signal_struct { + atomic_t sigcnt; + atomic_t live; + int nr_threads; + struct list_head thread_head; + + wait_queue_head_t wait_chldexit; /* for wait4() */ + + /* current thread group signal load-balancing target: */ + struct task_struct *curr_target; + + /* shared signal handling: */ + struct sigpending shared_pending; + + /* thread group exit support */ + int group_exit_code; + /* overloaded: + * - notify group_exit_task when ->count is equal to notify_count + * - everyone except group_exit_task is stopped during signal delivery + * of fatal signals, group_exit_task processes the signal. + */ + int notify_count; + struct task_struct *group_exit_task; + + /* thread group stop support, overloads group_exit_code too */ + int group_stop_count; + unsigned int flags; /* see SIGNAL_* flags below */ + + /* + * PR_SET_CHILD_SUBREAPER marks a process, like a service + * manager, to re-parent orphan (double-forking) child processes + * to this process instead of 'init'. The service manager is + * able to receive SIGCHLD signals and is able to investigate + * the process until it calls wait(). All children of this + * process will inherit a flag if they should look for a + * child_subreaper process at exit. + */ + unsigned int is_child_subreaper:1; + unsigned int has_child_subreaper:1; + +#ifdef CONFIG_POSIX_TIMERS + + /* POSIX.1b Interval Timers */ + int posix_timer_id; + struct list_head posix_timers; + + /* ITIMER_REAL timer for the process */ + struct hrtimer real_timer; + ktime_t it_real_incr; + + /* + * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use + * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these + * values are defined to 0 and 1 respectively + */ + struct cpu_itimer it[2]; + + /* + * Thread group totals for process CPU timers. + * See thread_group_cputimer(), et al, for details. + */ + struct thread_group_cputimer cputimer; + + /* Earliest-expiration cache. */ + struct task_cputime cputime_expires; + + struct list_head cpu_timers[3]; + +#endif + + struct pid *leader_pid; + +#ifdef CONFIG_NO_HZ_FULL + atomic_t tick_dep_mask; +#endif + + struct pid *tty_old_pgrp; + + /* boolean value for session group leader */ + int leader; + + struct tty_struct *tty; /* NULL if no tty */ + +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif + /* + * Cumulative resource counters for dead threads in the group, + * and for reaped dead child processes forked by this group. + * Live threads maintain their own counters and add to these + * in __exit_signal, except for the group leader. + */ + seqlock_t stats_lock; + u64 utime, stime, cutime, cstime; + u64 gtime; + u64 cgtime; + struct prev_cputime prev_cputime; + unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; + unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; + unsigned long inblock, oublock, cinblock, coublock; + unsigned long maxrss, cmaxrss; + struct task_io_accounting ioac; + + /* + * Cumulative ns of schedule CPU time fo dead threads in the + * group, not including a zombie group leader, (This only differs + * from jiffies_to_ns(utime + stime) if sched_clock uses something + * other than jiffies.) + */ + unsigned long long sum_sched_runtime; + + /* + * We don't bother to synchronize most readers of this at all, + * because there is no reader checking a limit that actually needs + * to get both rlim_cur and rlim_max atomically, and either one + * alone is a single word that can safely be read normally. + * getrlimit/setrlimit use task_lock(current->group_leader) to + * protect this instead of the siglock, because they really + * have no need to disable irqs. + */ + struct rlimit rlim[RLIM_NLIMITS]; + +#ifdef CONFIG_BSD_PROCESS_ACCT + struct pacct_struct pacct; /* per-process accounting information */ +#endif +#ifdef CONFIG_TASKSTATS + struct taskstats *stats; +#endif +#ifdef CONFIG_AUDIT + unsigned audit_tty; + struct tty_audit_buf *tty_audit_buf; +#endif + + /* + * Thread is the potential origin of an oom condition; kill first on + * oom + */ + bool oom_flag_origin; + short oom_score_adj; /* OOM kill score adjustment */ + short oom_score_adj_min; /* OOM kill score adjustment min value. + * Only settable by CAP_SYS_RESOURCE. */ + struct mm_struct *oom_mm; /* recorded mm when the thread group got + * killed by the oom killer */ + + struct mutex cred_guard_mutex; /* guard against foreign influences on + * credential calculations + * (notably. ptrace) */ +} __randomize_layout; + +/* + * Bits in flags field of signal_struct. + */ +#define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ +#define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ +#define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ +#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ +/* + * Pending notifications to parent. + */ +#define SIGNAL_CLD_STOPPED 0x00000010 +#define SIGNAL_CLD_CONTINUED 0x00000020 +#define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED) + +#define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ + +#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ + SIGNAL_STOP_CONTINUED) + +static inline void signal_set_stop_flags(struct signal_struct *sig, + unsigned int flags) +{ + WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); + sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; +} + +/* If true, all threads except ->group_exit_task have pending SIGKILL */ +static inline int signal_group_exit(const struct signal_struct *sig) +{ + return (sig->flags & SIGNAL_GROUP_EXIT) || + (sig->group_exit_task != NULL); +} + +extern void flush_signals(struct task_struct *); +extern void ignore_signals(struct task_struct *); +extern void flush_signal_handlers(struct task_struct *, int force_default); +extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); + +static inline int kernel_dequeue_signal(siginfo_t *info) +{ + struct task_struct *tsk = current; + siginfo_t __info; + int ret; + + spin_lock_irq(&tsk->sighand->siglock); + ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info); + spin_unlock_irq(&tsk->sighand->siglock); + + return ret; +} + +static inline void kernel_signal_stop(void) +{ + spin_lock_irq(¤t->sighand->siglock); + if (current->jobctl & JOBCTL_STOP_DEQUEUED) + __set_current_state(TASK_STOPPED); + spin_unlock_irq(¤t->sighand->siglock); + + schedule(); +} +extern int send_sig_info(int, struct siginfo *, struct task_struct *); +extern int force_sigsegv(int, struct task_struct *); +extern int force_sig_info(int, struct siginfo *, struct task_struct *); +extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); +extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); +extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *, + const struct cred *, u32); +extern int kill_pgrp(struct pid *pid, int sig, int priv); +extern int kill_pid(struct pid *pid, int sig, int priv); +extern __must_check bool do_notify_parent(struct task_struct *, int); +extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); +extern void force_sig(int, struct task_struct *); +extern int send_sig(int, struct task_struct *, int); +extern int zap_other_threads(struct task_struct *p); +extern struct sigqueue *sigqueue_alloc(void); +extern void sigqueue_free(struct sigqueue *); +extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group); +extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); + +static inline int restart_syscall(void) +{ + set_tsk_thread_flag(current, TIF_SIGPENDING); + return -ERESTARTNOINTR; +} + +static inline int signal_pending(struct task_struct *p) +{ + return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); +} + +static inline int __fatal_signal_pending(struct task_struct *p) +{ + return unlikely(sigismember(&p->pending.signal, SIGKILL)); +} + +static inline int fatal_signal_pending(struct task_struct *p) +{ + return signal_pending(p) && __fatal_signal_pending(p); +} + +static inline int signal_pending_state(long state, struct task_struct *p) +{ + if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) + return 0; + if (!signal_pending(p)) + return 0; + + return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); +} + +/* + * Reevaluate whether the task has signals pending delivery. + * Wake the task if so. + * This is required every time the blocked sigset_t changes. + * callers must hold sighand->siglock. + */ +extern void recalc_sigpending_and_wake(struct task_struct *t); +extern void recalc_sigpending(void); + +extern void signal_wake_up_state(struct task_struct *t, unsigned int state); + +static inline void signal_wake_up(struct task_struct *t, bool resume) +{ + signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); +} +static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) +{ + signal_wake_up_state(t, resume ? __TASK_TRACED : 0); +} + +#ifdef TIF_RESTORE_SIGMASK +/* + * Legacy restore_sigmask accessors. These are inefficient on + * SMP architectures because they require atomic operations. + */ + +/** + * set_restore_sigmask() - make sure saved_sigmask processing gets done + * + * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code + * will run before returning to user mode, to process the flag. For + * all callers, TIF_SIGPENDING is already set or it's no harm to set + * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the + * arch code will notice on return to user mode, in case those bits + * are scarce. We set TIF_SIGPENDING here to ensure that the arch + * signal code always gets run when TIF_RESTORE_SIGMASK is set. + */ +static inline void set_restore_sigmask(void) +{ + set_thread_flag(TIF_RESTORE_SIGMASK); + WARN_ON(!test_thread_flag(TIF_SIGPENDING)); +} +static inline void clear_restore_sigmask(void) +{ + clear_thread_flag(TIF_RESTORE_SIGMASK); +} +static inline bool test_restore_sigmask(void) +{ + return test_thread_flag(TIF_RESTORE_SIGMASK); +} +static inline bool test_and_clear_restore_sigmask(void) +{ + return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); +} + +#else /* TIF_RESTORE_SIGMASK */ + +/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ +static inline void set_restore_sigmask(void) +{ + current->restore_sigmask = true; + WARN_ON(!test_thread_flag(TIF_SIGPENDING)); +} +static inline void clear_restore_sigmask(void) +{ + current->restore_sigmask = false; +} +static inline bool test_restore_sigmask(void) +{ + return current->restore_sigmask; +} +static inline bool test_and_clear_restore_sigmask(void) +{ + if (!current->restore_sigmask) + return false; + current->restore_sigmask = false; + return true; +} +#endif + +static inline void restore_saved_sigmask(void) +{ + if (test_and_clear_restore_sigmask()) + __set_current_blocked(¤t->saved_sigmask); +} + +static inline sigset_t *sigmask_to_save(void) +{ + sigset_t *res = ¤t->blocked; + if (unlikely(test_restore_sigmask())) + res = ¤t->saved_sigmask; + return res; +} + +static inline int kill_cad_pid(int sig, int priv) +{ + return kill_pid(cad_pid, sig, priv); +} + +/* These can be the second arg to send_sig_info/send_group_sig_info. */ +#define SEND_SIG_NOINFO ((struct siginfo *) 0) +#define SEND_SIG_PRIV ((struct siginfo *) 1) +#define SEND_SIG_FORCED ((struct siginfo *) 2) + +/* + * True if we are on the alternate signal stack. + */ +static inline int on_sig_stack(unsigned long sp) +{ + /* + * If the signal stack is SS_AUTODISARM then, by construction, we + * can't be on the signal stack unless user code deliberately set + * SS_AUTODISARM when we were already on it. + * + * This improves reliability: if user state gets corrupted such that + * the stack pointer points very close to the end of the signal stack, + * then this check will enable the signal to be handled anyway. + */ + if (current->sas_ss_flags & SS_AUTODISARM) + return 0; + +#ifdef CONFIG_STACK_GROWSUP + return sp >= current->sas_ss_sp && + sp - current->sas_ss_sp < current->sas_ss_size; +#else + return sp > current->sas_ss_sp && + sp - current->sas_ss_sp <= current->sas_ss_size; +#endif +} + +static inline int sas_ss_flags(unsigned long sp) +{ + if (!current->sas_ss_size) + return SS_DISABLE; + + return on_sig_stack(sp) ? SS_ONSTACK : 0; +} + +static inline void sas_ss_reset(struct task_struct *p) +{ + p->sas_ss_sp = 0; + p->sas_ss_size = 0; + p->sas_ss_flags = SS_DISABLE; +} + +static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) +{ + if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) +#ifdef CONFIG_STACK_GROWSUP + return current->sas_ss_sp; +#else + return current->sas_ss_sp + current->sas_ss_size; +#endif + return sp; +} + +extern void __cleanup_sighand(struct sighand_struct *); +extern void flush_itimer_signals(void); + +#define tasklist_empty() \ + list_empty(&init_task.tasks) + +#define next_task(p) \ + list_entry_rcu((p)->tasks.next, struct task_struct, tasks) + +#define for_each_process(p) \ + for (p = &init_task ; (p = next_task(p)) != &init_task ; ) + +extern bool current_is_single_threaded(void); + +/* + * Careful: do_each_thread/while_each_thread is a double loop so + * 'break' will not work as expected - use goto instead. + */ +#define do_each_thread(g, t) \ + for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do + +#define while_each_thread(g, t) \ + while ((t = next_thread(t)) != g) + +#define __for_each_thread(signal, t) \ + list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node) + +#define for_each_thread(p, t) \ + __for_each_thread((p)->signal, t) + +/* Careful: this is a double loop, 'break' won't work as expected. */ +#define for_each_process_thread(p, t) \ + for_each_process(p) for_each_thread(p, t) + +typedef int (*proc_visitor)(struct task_struct *p, void *data); +void walk_process_tree(struct task_struct *top, proc_visitor, void *); + +static inline int get_nr_threads(struct task_struct *tsk) +{ + return tsk->signal->nr_threads; +} + +static inline bool thread_group_leader(struct task_struct *p) +{ + return p->exit_signal >= 0; +} + +/* Do to the insanities of de_thread it is possible for a process + * to have the pid of the thread group leader without actually being + * the thread group leader. For iteration through the pids in proc + * all we care about is that we have a task with the appropriate + * pid, we don't actually care if we have the right task. + */ +static inline bool has_group_leader_pid(struct task_struct *p) +{ + return task_pid(p) == p->signal->leader_pid; +} + +static inline +bool same_thread_group(struct task_struct *p1, struct task_struct *p2) +{ + return p1->signal == p2->signal; +} + +static inline struct task_struct *next_thread(const struct task_struct *p) +{ + return list_entry_rcu(p->thread_group.next, + struct task_struct, thread_group); +} + +static inline int thread_group_empty(struct task_struct *p) +{ + return list_empty(&p->thread_group); +} + +#define delay_group_leader(p) \ + (thread_group_leader(p) && !thread_group_empty(p)) + +extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, + unsigned long *flags); + +static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk, + unsigned long *flags) +{ + struct sighand_struct *ret; + + ret = __lock_task_sighand(tsk, flags); + (void)__cond_lock(&tsk->sighand->siglock, ret); + return ret; +} + +static inline void unlock_task_sighand(struct task_struct *tsk, + unsigned long *flags) +{ + spin_unlock_irqrestore(&tsk->sighand->siglock, *flags); +} + +static inline unsigned long task_rlimit(const struct task_struct *tsk, + unsigned int limit) +{ + return READ_ONCE(tsk->signal->rlim[limit].rlim_cur); +} + +static inline unsigned long task_rlimit_max(const struct task_struct *tsk, + unsigned int limit) +{ + return READ_ONCE(tsk->signal->rlim[limit].rlim_max); +} + +static inline unsigned long rlimit(unsigned int limit) +{ + return task_rlimit(current, limit); +} + +static inline unsigned long rlimit_max(unsigned int limit) +{ + return task_rlimit_max(current, limit); +} + +#endif /* _LINUX_SCHED_SIGNAL_H */ diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h new file mode 100644 index 000000000000..141b74c53fad --- /dev/null +++ b/include/linux/sched/stat.h @@ -0,0 +1,40 @@ +#ifndef _LINUX_SCHED_STAT_H +#define _LINUX_SCHED_STAT_H + +#include <linux/percpu.h> + +/* + * Various counters maintained by the scheduler and fork(), + * exposed via /proc, sys.c or used by drivers via these APIs. + * + * ( Note that all these values are aquired without locking, + * so they can only be relied on in narrow circumstances. ) + */ + +extern unsigned long total_forks; +extern int nr_threads; +DECLARE_PER_CPU(unsigned long, process_counts); +extern int nr_processes(void); +extern unsigned long nr_running(void); +extern bool single_task_running(void); +extern unsigned long nr_iowait(void); +extern unsigned long nr_iowait_cpu(int cpu); +extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); + +static inline int sched_info_on(void) +{ +#ifdef CONFIG_SCHEDSTATS + return 1; +#elif defined(CONFIG_TASK_DELAY_ACCT) + extern int delayacct_on; + return delayacct_on; +#else + return 0; +#endif +} + +#ifdef CONFIG_SCHEDSTATS +void force_schedstat_enabled(void); +#endif + +#endif /* _LINUX_SCHED_STAT_H */ diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 441145351301..0f5ecd4d298e 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -1,5 +1,9 @@ -#ifndef _SCHED_SYSCTL_H -#define _SCHED_SYSCTL_H +#ifndef _LINUX_SCHED_SYSCTL_H +#define _LINUX_SCHED_SYSCTL_H + +#include <linux/types.h> + +struct ctl_table; #ifdef CONFIG_DETECT_HUNG_TASK extern int sysctl_hung_task_check_count; @@ -59,6 +63,7 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice; extern unsigned int sysctl_sched_autogroup_enabled; #endif +extern int sysctl_sched_rr_timeslice; extern int sched_rr_timeslice; extern int sched_rr_handler(struct ctl_table *table, int write, @@ -77,4 +82,4 @@ extern int sysctl_schedstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -#endif /* _SCHED_SYSCTL_H */ +#endif /* _LINUX_SCHED_SYSCTL_H */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h new file mode 100644 index 000000000000..c97e5f096927 --- /dev/null +++ b/include/linux/sched/task.h @@ -0,0 +1,139 @@ +#ifndef _LINUX_SCHED_TASK_H +#define _LINUX_SCHED_TASK_H + +/* + * Interface between the scheduler and various task lifetime (fork()/exit()) + * functionality: + */ + +#include <linux/sched.h> + +struct task_struct; +struct rusage; +union thread_union; + +/* + * This serializes "schedule()" and also protects + * the run-queue from deletions/modifications (but + * _adding_ to the beginning of the run-queue has + * a separate lock). + */ +extern rwlock_t tasklist_lock; +extern spinlock_t mmlist_lock; + +extern union thread_union init_thread_union; +extern struct task_struct init_task; + +#ifdef CONFIG_PROVE_RCU +extern int lockdep_tasklist_lock_is_held(void); +#endif /* #ifdef CONFIG_PROVE_RCU */ + +extern asmlinkage void schedule_tail(struct task_struct *prev); +extern void init_idle(struct task_struct *idle, int cpu); +extern void init_idle_bootup_task(struct task_struct *idle); + +extern int sched_fork(unsigned long clone_flags, struct task_struct *p); +extern void sched_dead(struct task_struct *p); + +void __noreturn do_task_dead(void); + +extern void proc_caches_init(void); + +extern void release_task(struct task_struct * p); + +#ifdef CONFIG_HAVE_COPY_THREAD_TLS +extern int copy_thread_tls(unsigned long, unsigned long, unsigned long, + struct task_struct *, unsigned long); +#else +extern int copy_thread(unsigned long, unsigned long, unsigned long, + struct task_struct *); + +/* Architectures that haven't opted into copy_thread_tls get the tls argument + * via pt_regs, so ignore the tls argument passed via C. */ +static inline int copy_thread_tls( + unsigned long clone_flags, unsigned long sp, unsigned long arg, + struct task_struct *p, unsigned long tls) +{ + return copy_thread(clone_flags, sp, arg, p); +} +#endif +extern void flush_thread(void); + +#ifdef CONFIG_HAVE_EXIT_THREAD +extern void exit_thread(struct task_struct *tsk); +#else +static inline void exit_thread(struct task_struct *tsk) +{ +} +#endif +extern void do_group_exit(int); + +extern void exit_files(struct task_struct *); +extern void exit_itimers(struct signal_struct *); + +extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long); +extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); +struct task_struct *fork_idle(int); +extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); +extern long kernel_wait4(pid_t, int *, int, struct rusage *); + +extern void free_task(struct task_struct *tsk); + +/* sched_exec is called by processes performing an exec */ +#ifdef CONFIG_SMP +extern void sched_exec(void); +#else +#define sched_exec() {} +#endif + +#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) + +extern void __put_task_struct(struct task_struct *t); + +static inline void put_task_struct(struct task_struct *t) +{ + if (atomic_dec_and_test(&t->usage)) + __put_task_struct(t); +} + +struct task_struct *task_rcu_dereference(struct task_struct **ptask); + +#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT +extern int arch_task_struct_size __read_mostly; +#else +# define arch_task_struct_size (sizeof(struct task_struct)) +#endif + +#ifdef CONFIG_VMAP_STACK +static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) +{ + return t->stack_vm_area; +} +#else +static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) +{ + return NULL; +} +#endif + +/* + * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring + * subscriptions and synchronises with wait4(). Also used in procfs. Also + * pins the final release of task.io_context. Also protects ->cpuset and + * ->cgroup.subsys[]. And ->vfork_done. + * + * Nests both inside and outside of read_lock(&tasklist_lock). + * It must not be nested with write_lock_irq(&tasklist_lock), + * neither inside nor outside. + */ +static inline void task_lock(struct task_struct *p) +{ + spin_lock(&p->alloc_lock); +} + +static inline void task_unlock(struct task_struct *p) +{ + spin_unlock(&p->alloc_lock); +} + +#endif /* _LINUX_SCHED_TASK_H */ diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h new file mode 100644 index 000000000000..df6ea6665b31 --- /dev/null +++ b/include/linux/sched/task_stack.h @@ -0,0 +1,121 @@ +#ifndef _LINUX_SCHED_TASK_STACK_H +#define _LINUX_SCHED_TASK_STACK_H + +/* + * task->stack (kernel stack) handling interfaces: + */ + +#include <linux/sched.h> +#include <linux/magic.h> + +#ifdef CONFIG_THREAD_INFO_IN_TASK + +/* + * When accessing the stack of a non-current task that might exit, use + * try_get_task_stack() instead. task_stack_page will return a pointer + * that could get freed out from under you. + */ +static inline void *task_stack_page(const struct task_struct *task) +{ + return task->stack; +} + +#define setup_thread_stack(new,old) do { } while(0) + +static inline unsigned long *end_of_stack(const struct task_struct *task) +{ + return task->stack; +} + +#elif !defined(__HAVE_THREAD_FUNCTIONS) + +#define task_stack_page(task) ((void *)(task)->stack) + +static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) +{ + *task_thread_info(p) = *task_thread_info(org); + task_thread_info(p)->task = p; +} + +/* + * Return the address of the last usable long on the stack. + * + * When the stack grows down, this is just above the thread + * info struct. Going any lower will corrupt the threadinfo. + * + * When the stack grows up, this is the highest address. + * Beyond that position, we corrupt data on the next page. + */ +static inline unsigned long *end_of_stack(struct task_struct *p) +{ +#ifdef CONFIG_STACK_GROWSUP + return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1; +#else + return (unsigned long *)(task_thread_info(p) + 1); +#endif +} + +#endif + +#ifdef CONFIG_THREAD_INFO_IN_TASK +static inline void *try_get_task_stack(struct task_struct *tsk) +{ + return atomic_inc_not_zero(&tsk->stack_refcount) ? + task_stack_page(tsk) : NULL; +} + +extern void put_task_stack(struct task_struct *tsk); +#else +static inline void *try_get_task_stack(struct task_struct *tsk) +{ + return task_stack_page(tsk); +} + +static inline void put_task_stack(struct task_struct *tsk) {} +#endif + +#define task_stack_end_corrupted(task) \ + (*(end_of_stack(task)) != STACK_END_MAGIC) + +static inline int object_is_on_stack(void *obj) +{ + void *stack = task_stack_page(current); + + return (obj >= stack) && (obj < (stack + THREAD_SIZE)); +} + +extern void thread_stack_cache_init(void); + +#ifdef CONFIG_DEBUG_STACK_USAGE +static inline unsigned long stack_not_used(struct task_struct *p) +{ + unsigned long *n = end_of_stack(p); + + do { /* Skip over canary */ +# ifdef CONFIG_STACK_GROWSUP + n--; +# else + n++; +# endif + } while (!*n); + +# ifdef CONFIG_STACK_GROWSUP + return (unsigned long)end_of_stack(p) - (unsigned long)n; +# else + return (unsigned long)n - (unsigned long)end_of_stack(p); +# endif +} +#endif +extern void set_task_stack_end_magic(struct task_struct *tsk); + +#ifndef __HAVE_ARCH_KSTACK_END +static inline int kstack_end(void *addr) +{ + /* Reliable end of stack detection: + * Some APM bios versions misalign the stack + */ + return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*))); +} +#endif + +#endif /* _LINUX_SCHED_TASK_STACK_H */ diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h new file mode 100644 index 000000000000..7d065abc7a47 --- /dev/null +++ b/include/linux/sched/topology.h @@ -0,0 +1,226 @@ +#ifndef _LINUX_SCHED_TOPOLOGY_H +#define _LINUX_SCHED_TOPOLOGY_H + +#include <linux/topology.h> + +#include <linux/sched/idle.h> + +/* + * sched-domains (multiprocessor balancing) declarations: + */ +#ifdef CONFIG_SMP + +#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */ +#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */ +#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */ +#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */ +#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ +#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ +#define SD_ASYM_CPUCAPACITY 0x0040 /* Groups have different max cpu capacities */ +#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share cpu capacity */ +#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */ +#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ +#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ +#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ +#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ +#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ +#define SD_NUMA 0x4000 /* cross-node balancing */ + +/* + * Increase resolution of cpu_capacity calculations + */ +#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT +#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) + +#ifdef CONFIG_SCHED_SMT +static inline int cpu_smt_flags(void) +{ + return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; +} +#endif + +#ifdef CONFIG_SCHED_MC +static inline int cpu_core_flags(void) +{ + return SD_SHARE_PKG_RESOURCES; +} +#endif + +#ifdef CONFIG_NUMA +static inline int cpu_numa_flags(void) +{ + return SD_NUMA; +} +#endif + +extern int arch_asym_cpu_priority(int cpu); + +struct sched_domain_attr { + int relax_domain_level; +}; + +#define SD_ATTR_INIT (struct sched_domain_attr) { \ + .relax_domain_level = -1, \ +} + +extern int sched_domain_level_max; + +struct sched_group; + +struct sched_domain_shared { + atomic_t ref; + atomic_t nr_busy_cpus; + int has_idle_cores; +}; + +struct sched_domain { + /* These fields must be setup */ + struct sched_domain *parent; /* top domain must be null terminated */ + struct sched_domain *child; /* bottom domain must be null terminated */ + struct sched_group *groups; /* the balancing groups of the domain */ + unsigned long min_interval; /* Minimum balance interval ms */ + unsigned long max_interval; /* Maximum balance interval ms */ + unsigned int busy_factor; /* less balancing by factor if busy */ + unsigned int imbalance_pct; /* No balance until over watermark */ + unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ + unsigned int busy_idx; + unsigned int idle_idx; + unsigned int newidle_idx; + unsigned int wake_idx; + unsigned int forkexec_idx; + unsigned int smt_gain; + + int nohz_idle; /* NOHZ IDLE status */ + int flags; /* See SD_* */ + int level; + + /* Runtime fields. */ + unsigned long last_balance; /* init to jiffies. units in jiffies */ + unsigned int balance_interval; /* initialise to 1. units in ms. */ + unsigned int nr_balance_failed; /* initialise to 0 */ + + /* idle_balance() stats */ + u64 max_newidle_lb_cost; + unsigned long next_decay_max_lb_cost; + + u64 avg_scan_cost; /* select_idle_sibling */ + +#ifdef CONFIG_SCHEDSTATS + /* load_balance() stats */ + unsigned int lb_count[CPU_MAX_IDLE_TYPES]; + unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; + unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES]; + unsigned int lb_gained[CPU_MAX_IDLE_TYPES]; + unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES]; + unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES]; + unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES]; + + /* Active load balancing */ + unsigned int alb_count; + unsigned int alb_failed; + unsigned int alb_pushed; + + /* SD_BALANCE_EXEC stats */ + unsigned int sbe_count; + unsigned int sbe_balanced; + unsigned int sbe_pushed; + + /* SD_BALANCE_FORK stats */ + unsigned int sbf_count; + unsigned int sbf_balanced; + unsigned int sbf_pushed; + + /* try_to_wake_up() stats */ + unsigned int ttwu_wake_remote; + unsigned int ttwu_move_affine; + unsigned int ttwu_move_balance; +#endif +#ifdef CONFIG_SCHED_DEBUG + char *name; +#endif + union { + void *private; /* used during construction */ + struct rcu_head rcu; /* used during destruction */ + }; + struct sched_domain_shared *shared; + + unsigned int span_weight; + /* + * Span of all CPUs in this domain. + * + * NOTE: this field is variable length. (Allocated dynamically + * by attaching extra space to the end of the structure, + * depending on how many CPUs the kernel has booted up with) + */ + unsigned long span[0]; +}; + +static inline struct cpumask *sched_domain_span(struct sched_domain *sd) +{ + return to_cpumask(sd->span); +} + +extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new); + +/* Allocate an array of sched domains, for partition_sched_domains(). */ +cpumask_var_t *alloc_sched_domains(unsigned int ndoms); +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); + +bool cpus_share_cache(int this_cpu, int that_cpu); + +typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); +typedef int (*sched_domain_flags_f)(void); + +#define SDTL_OVERLAP 0x01 + +struct sd_data { + struct sched_domain **__percpu sd; + struct sched_domain_shared **__percpu sds; + struct sched_group **__percpu sg; + struct sched_group_capacity **__percpu sgc; +}; + +struct sched_domain_topology_level { + sched_domain_mask_f mask; + sched_domain_flags_f sd_flags; + int flags; + int numa_level; + struct sd_data data; +#ifdef CONFIG_SCHED_DEBUG + char *name; +#endif +}; + +extern void set_sched_topology(struct sched_domain_topology_level *tl); + +#ifdef CONFIG_SCHED_DEBUG +# define SD_INIT_NAME(type) .name = #type +#else +# define SD_INIT_NAME(type) +#endif + +#else /* CONFIG_SMP */ + +struct sched_domain_attr; + +static inline void +partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ +} + +static inline bool cpus_share_cache(int this_cpu, int that_cpu) +{ + return true; +} + +#endif /* !CONFIG_SMP */ + +static inline int task_node(const struct task_struct *p) +{ + return cpu_to_node(task_cpu(p)); +} + +#endif /* _LINUX_SCHED_TOPOLOGY_H */ diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h new file mode 100644 index 000000000000..5d5415e129d4 --- /dev/null +++ b/include/linux/sched/user.h @@ -0,0 +1,61 @@ +#ifndef _LINUX_SCHED_USER_H +#define _LINUX_SCHED_USER_H + +#include <linux/uidgid.h> +#include <linux/atomic.h> + +struct key; + +/* + * Some day this will be a full-fledged user tracking system.. + */ +struct user_struct { + atomic_t __count; /* reference count */ + atomic_t processes; /* How many processes does this user have? */ + atomic_t sigpending; /* How many pending signals does this user have? */ +#ifdef CONFIG_FANOTIFY + atomic_t fanotify_listeners; +#endif +#ifdef CONFIG_EPOLL + atomic_long_t epoll_watches; /* The number of file descriptors currently watched */ +#endif +#ifdef CONFIG_POSIX_MQUEUE + /* protected by mq_lock */ + unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ +#endif + unsigned long locked_shm; /* How many pages of mlocked shm ? */ + unsigned long unix_inflight; /* How many files in flight in unix sockets */ + atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */ + +#ifdef CONFIG_KEYS + struct key *uid_keyring; /* UID specific keyring */ + struct key *session_keyring; /* UID's default session keyring */ +#endif + + /* Hash table maintenance information */ + struct hlist_node uidhash_node; + kuid_t uid; + +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) + atomic_long_t locked_vm; +#endif +}; + +extern int uids_sysfs_init(void); + +extern struct user_struct *find_user(kuid_t); + +extern struct user_struct root_user; +#define INIT_USER (&root_user) + + +/* per-UID process charging. */ +extern struct user_struct * alloc_uid(kuid_t); +static inline struct user_struct *get_uid(struct user_struct *u) +{ + atomic_inc(&u->__count); + return u; +} +extern void free_uid(struct user_struct *); + +#endif /* _LINUX_SCHED_USER_H */ diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h new file mode 100644 index 000000000000..d03d8a9047dc --- /dev/null +++ b/include/linux/sched/wake_q.h @@ -0,0 +1,53 @@ +#ifndef _LINUX_SCHED_WAKE_Q_H +#define _LINUX_SCHED_WAKE_Q_H + +/* + * Wake-queues are lists of tasks with a pending wakeup, whose + * callers have already marked the task as woken internally, + * and can thus carry on. A common use case is being able to + * do the wakeups once the corresponding user lock as been + * released. + * + * We hold reference to each task in the list across the wakeup, + * thus guaranteeing that the memory is still valid by the time + * the actual wakeups are performed in wake_up_q(). + * + * One per task suffices, because there's never a need for a task to be + * in two wake queues simultaneously; it is forbidden to abandon a task + * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is + * already in a wake queue, the wakeup will happen soon and the second + * waker can just skip it. + * + * The DEFINE_WAKE_Q macro declares and initializes the list head. + * wake_up_q() does NOT reinitialize the list; it's expected to be + * called near the end of a function. Otherwise, the list can be + * re-initialized for later re-use by wake_q_init(). + * + * Note that this can cause spurious wakeups. schedule() callers + * must ensure the call is done inside a loop, confirming that the + * wakeup condition has in fact occurred. + */ + +#include <linux/sched.h> + +struct wake_q_head { + struct wake_q_node *first; + struct wake_q_node **lastp; +}; + +#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) + +#define DEFINE_WAKE_Q(name) \ + struct wake_q_head name = { WAKE_Q_TAIL, &name.first } + +static inline void wake_q_init(struct wake_q_head *head) +{ + head->first = WAKE_Q_TAIL; + head->lastp = &head->first; +} + +extern void wake_q_add(struct wake_q_head *head, + struct task_struct *task); +extern void wake_up_q(struct wake_q_head *head); + +#endif /* _LINUX_SCHED_WAKE_Q_H */ diff --git a/include/linux/sched/xacct.h b/include/linux/sched/xacct.h new file mode 100644 index 000000000000..a28156a0d34a --- /dev/null +++ b/include/linux/sched/xacct.h @@ -0,0 +1,48 @@ +#ifndef _LINUX_SCHED_XACCT_H +#define _LINUX_SCHED_XACCT_H + +/* + * Extended task accounting methods: + */ + +#include <linux/sched.h> + +#ifdef CONFIG_TASK_XACCT +static inline void add_rchar(struct task_struct *tsk, ssize_t amt) +{ + tsk->ioac.rchar += amt; +} + +static inline void add_wchar(struct task_struct *tsk, ssize_t amt) +{ + tsk->ioac.wchar += amt; +} + +static inline void inc_syscr(struct task_struct *tsk) +{ + tsk->ioac.syscr++; +} + +static inline void inc_syscw(struct task_struct *tsk) +{ + tsk->ioac.syscw++; +} +#else +static inline void add_rchar(struct task_struct *tsk, ssize_t amt) +{ +} + +static inline void add_wchar(struct task_struct *tsk, ssize_t amt) +{ +} + +static inline void inc_syscr(struct task_struct *tsk) +{ +} + +static inline void inc_syscw(struct task_struct *tsk) +{ +} +#endif + +#endif /* _LINUX_SCHED_XACCT_H */ diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index dc5f989be226..327d65663dbf 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -67,6 +67,9 @@ struct scpi_ops { int (*dvfs_get_idx)(u8); int (*dvfs_set_idx)(u8, u8); struct scpi_dvfs_info *(*dvfs_get_info)(u8); + int (*device_domain_id)(struct device *); + int (*get_transition_latency)(struct device *); + int (*add_opps_to_device)(struct device *); int (*sensor_get_capability)(u16 *sensors); int (*sensor_get_info)(u16 sensor_id, struct scpi_sensor_info *); int (*sensor_get_value)(u16, u64 *); diff --git a/include/linux/sctp.h b/include/linux/sctp.h index fcb4c3646173..99e866487e2f 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -57,12 +57,12 @@ #include <uapi/linux/sctp.h> /* Section 3.1. SCTP Common Header Format */ -typedef struct sctphdr { +struct sctphdr { __be16 source; __be16 dest; __be32 vtag; __le32 checksum; -} __packed sctp_sctphdr_t; +}; static inline struct sctphdr *sctp_hdr(const struct sk_buff *skb) { @@ -70,11 +70,11 @@ static inline struct sctphdr *sctp_hdr(const struct sk_buff *skb) } /* Section 3.2. Chunk Field Descriptions. */ -typedef struct sctp_chunkhdr { +struct sctp_chunkhdr { __u8 type; __u8 flags; __be16 length; -} __packed sctp_chunkhdr_t; +}; /* Section 3.2. Chunk Type Values. @@ -82,7 +82,7 @@ typedef struct sctp_chunkhdr { * Value field. It takes a value from 0 to 254. The value of 255 is * reserved for future use as an extension field. */ -typedef enum { +enum sctp_cid { SCTP_CID_DATA = 0, SCTP_CID_INIT = 1, SCTP_CID_INIT_ACK = 2, @@ -108,7 +108,8 @@ typedef enum { /* Use hex, as defined in ADDIP sec. 3.1 */ SCTP_CID_ASCONF = 0xC1, SCTP_CID_ASCONF_ACK = 0x80, -} sctp_cid_t; /* enum */ + SCTP_CID_RECONF = 0x82, +}; /* enum */ /* Section 3.2 @@ -116,12 +117,12 @@ typedef enum { * the action that must be taken if the processing endpoint does not * recognize the Chunk Type. */ -typedef enum { +enum { SCTP_CID_ACTION_DISCARD = 0x00, SCTP_CID_ACTION_DISCARD_ERR = 0x40, SCTP_CID_ACTION_SKIP = 0x80, SCTP_CID_ACTION_SKIP_ERR = 0xc0, -} sctp_cid_action_t; +}; enum { SCTP_CID_ACTION_MASK = 0xc0, }; @@ -161,12 +162,12 @@ enum { SCTP_CHUNK_FLAG_T = 0x01 }; * Section 3.2.1 Optional/Variable-length Parmaeter Format. */ -typedef struct sctp_paramhdr { +struct sctp_paramhdr { __be16 type; __be16 length; -} __packed sctp_paramhdr_t; +}; -typedef enum { +enum sctp_param { /* RFC 2960 Section 3.3.5 */ SCTP_PARAM_HEARTBEAT_INFO = cpu_to_be16(1), @@ -199,7 +200,14 @@ typedef enum { SCTP_PARAM_SUCCESS_REPORT = cpu_to_be16(0xc005), SCTP_PARAM_ADAPTATION_LAYER_IND = cpu_to_be16(0xc006), -} sctp_param_t; /* enum */ + /* RE-CONFIG. Section 4 */ + SCTP_PARAM_RESET_OUT_REQUEST = cpu_to_be16(0x000d), + SCTP_PARAM_RESET_IN_REQUEST = cpu_to_be16(0x000e), + SCTP_PARAM_RESET_TSN_REQUEST = cpu_to_be16(0x000f), + SCTP_PARAM_RESET_RESPONSE = cpu_to_be16(0x0010), + SCTP_PARAM_RESET_ADD_OUT_STREAMS = cpu_to_be16(0x0011), + SCTP_PARAM_RESET_ADD_IN_STREAMS = cpu_to_be16(0x0012), +}; /* enum */ /* RFC 2960 Section 3.2.1 @@ -208,29 +216,29 @@ typedef enum { * not recognize the Parameter Type. * */ -typedef enum { +enum { SCTP_PARAM_ACTION_DISCARD = cpu_to_be16(0x0000), SCTP_PARAM_ACTION_DISCARD_ERR = cpu_to_be16(0x4000), SCTP_PARAM_ACTION_SKIP = cpu_to_be16(0x8000), SCTP_PARAM_ACTION_SKIP_ERR = cpu_to_be16(0xc000), -} sctp_param_action_t; +}; enum { SCTP_PARAM_ACTION_MASK = cpu_to_be16(0xc000), }; /* RFC 2960 Section 3.3.1 Payload Data (DATA) (0) */ -typedef struct sctp_datahdr { +struct sctp_datahdr { __be32 tsn; __be16 stream; __be16 ssn; __be32 ppid; __u8 payload[0]; -} __packed sctp_datahdr_t; +}; -typedef struct sctp_data_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_datahdr_t data_hdr; -} __packed sctp_data_chunk_t; +struct sctp_data_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_datahdr data_hdr; +}; /* DATA Chuck Specific Flags */ enum { @@ -249,103 +257,103 @@ enum { SCTP_DATA_FRAG_MASK = 0x03, }; * This chunk is used to initiate a SCTP association between two * endpoints. */ -typedef struct sctp_inithdr { +struct sctp_inithdr { __be32 init_tag; __be32 a_rwnd; __be16 num_outbound_streams; __be16 num_inbound_streams; __be32 initial_tsn; __u8 params[0]; -} __packed sctp_inithdr_t; +}; -typedef struct sctp_init_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_inithdr_t init_hdr; -} __packed sctp_init_chunk_t; +struct sctp_init_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_inithdr init_hdr; +}; /* Section 3.3.2.1. IPv4 Address Parameter (5) */ typedef struct sctp_ipv4addr_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; struct in_addr addr; -} __packed sctp_ipv4addr_param_t; +} sctp_ipv4addr_param_t; /* Section 3.3.2.1. IPv6 Address Parameter (6) */ typedef struct sctp_ipv6addr_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; struct in6_addr addr; -} __packed sctp_ipv6addr_param_t; +} sctp_ipv6addr_param_t; /* Section 3.3.2.1 Cookie Preservative (9) */ typedef struct sctp_cookie_preserve_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __be32 lifespan_increment; -} __packed sctp_cookie_preserve_param_t; +} sctp_cookie_preserve_param_t; /* Section 3.3.2.1 Host Name Address (11) */ typedef struct sctp_hostname_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; uint8_t hostname[0]; -} __packed sctp_hostname_param_t; +} sctp_hostname_param_t; /* Section 3.3.2.1 Supported Address Types (12) */ typedef struct sctp_supported_addrs_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __be16 types[0]; -} __packed sctp_supported_addrs_param_t; +} sctp_supported_addrs_param_t; /* Appendix A. ECN Capable (32768) */ typedef struct sctp_ecn_capable_param { - sctp_paramhdr_t param_hdr; -} __packed sctp_ecn_capable_param_t; + struct sctp_paramhdr param_hdr; +} sctp_ecn_capable_param_t; /* ADDIP Section 3.2.6 Adaptation Layer Indication */ typedef struct sctp_adaptation_ind_param { struct sctp_paramhdr param_hdr; __be32 adaptation_ind; -} __packed sctp_adaptation_ind_param_t; +} sctp_adaptation_ind_param_t; /* ADDIP Section 4.2.7 Supported Extensions Parameter */ typedef struct sctp_supported_ext_param { struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} __packed sctp_supported_ext_param_t; +} sctp_supported_ext_param_t; /* AUTH Section 3.1 Random */ typedef struct sctp_random_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u8 random_val[0]; -} __packed sctp_random_param_t; +} sctp_random_param_t; /* AUTH Section 3.2 Chunk List */ typedef struct sctp_chunks_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} __packed sctp_chunks_param_t; +} sctp_chunks_param_t; /* AUTH Section 3.3 HMAC Algorithm */ typedef struct sctp_hmac_algo_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __be16 hmac_ids[0]; -} __packed sctp_hmac_algo_param_t; +} sctp_hmac_algo_param_t; /* RFC 2960. Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2): * The INIT ACK chunk is used to acknowledge the initiation of an SCTP * association. */ -typedef sctp_init_chunk_t sctp_initack_chunk_t; +typedef struct sctp_init_chunk sctp_initack_chunk_t; /* Section 3.3.3.1 State Cookie (7) */ typedef struct sctp_cookie_param { - sctp_paramhdr_t p; + struct sctp_paramhdr p; __u8 body[0]; -} __packed sctp_cookie_param_t; +} sctp_cookie_param_t; /* Section 3.3.3.1 Unrecognized Parameters (8) */ typedef struct sctp_unrecognized_param { - sctp_paramhdr_t param_hdr; - sctp_paramhdr_t unrecognized; -} __packed sctp_unrecognized_param_t; + struct sctp_paramhdr param_hdr; + struct sctp_paramhdr unrecognized; +} sctp_unrecognized_param_t; @@ -360,7 +368,7 @@ typedef struct sctp_unrecognized_param { typedef struct sctp_gap_ack_block { __be16 start; __be16 end; -} __packed sctp_gap_ack_block_t; +} sctp_gap_ack_block_t; typedef __be32 sctp_dup_tsn_t; @@ -375,12 +383,12 @@ typedef struct sctp_sackhdr { __be16 num_gap_ack_blocks; __be16 num_dup_tsns; sctp_sack_variable_t variable[0]; -} __packed sctp_sackhdr_t; +} sctp_sackhdr_t; typedef struct sctp_sack_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_sackhdr_t sack_hdr; -} __packed sctp_sack_chunk_t; +} sctp_sack_chunk_t; /* RFC 2960. Section 3.3.5 Heartbeat Request (HEARTBEAT) (4): @@ -391,13 +399,13 @@ typedef struct sctp_sack_chunk { */ typedef struct sctp_heartbeathdr { - sctp_paramhdr_t info; -} __packed sctp_heartbeathdr_t; + struct sctp_paramhdr info; +} sctp_heartbeathdr_t; typedef struct sctp_heartbeat_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_heartbeathdr_t hb_hdr; -} __packed sctp_heartbeat_chunk_t; +} sctp_heartbeat_chunk_t; /* For the abort and shutdown ACK we must carry the init tag in the @@ -405,8 +413,8 @@ typedef struct sctp_heartbeat_chunk { * chunk descriptor. */ typedef struct sctp_abort_chunk { - sctp_chunkhdr_t uh; -} __packed sctp_abort_chunk_t; + struct sctp_chunkhdr uh; +} sctp_abort_chunk_t; /* For the graceful shutdown we must carry the tag (in common header) @@ -414,12 +422,12 @@ typedef struct sctp_abort_chunk { */ typedef struct sctp_shutdownhdr { __be32 cum_tsn_ack; -} __packed sctp_shutdownhdr_t; +} sctp_shutdownhdr_t; struct sctp_shutdown_chunk_t { - sctp_chunkhdr_t chunk_hdr; - sctp_shutdownhdr_t shutdown_hdr; -} __packed; + struct sctp_chunkhdr chunk_hdr; + sctp_shutdownhdr_t shutdown_hdr; +}; /* RFC 2960. Section 3.3.10 Operation Error (ERROR) (9) */ @@ -427,12 +435,12 @@ typedef struct sctp_errhdr { __be16 cause; __be16 length; __u8 variable[0]; -} __packed sctp_errhdr_t; +} sctp_errhdr_t; typedef struct sctp_operr_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_errhdr_t err_hdr; -} __packed sctp_operr_chunk_t; + struct sctp_chunkhdr chunk_hdr; + sctp_errhdr_t err_hdr; +} sctp_operr_chunk_t; /* RFC 2960 3.3.10 - Operation Error * @@ -520,9 +528,9 @@ typedef struct sctp_ecnehdr { } sctp_ecnehdr_t; typedef struct sctp_ecne_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_ecnehdr_t ence_hdr; -} __packed sctp_ecne_chunk_t; +} sctp_ecne_chunk_t; /* RFC 2960. Appendix A. Explicit Congestion Notification. * Congestion Window Reduced (CWR) (13) @@ -532,9 +540,9 @@ typedef struct sctp_cwrhdr { } sctp_cwrhdr_t; typedef struct sctp_cwr_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_cwrhdr_t cwr_hdr; -} __packed sctp_cwr_chunk_t; +} sctp_cwr_chunk_t; /* PR-SCTP * 3.2 Forward Cumulative TSN Chunk Definition (FORWARD TSN) @@ -585,17 +593,17 @@ typedef struct sctp_cwr_chunk { struct sctp_fwdtsn_skip { __be16 stream; __be16 ssn; -} __packed; +}; struct sctp_fwdtsn_hdr { __be32 new_cum_tsn; struct sctp_fwdtsn_skip skip[0]; -} __packed; +}; struct sctp_fwdtsn_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_fwdtsn_hdr fwdtsn_hdr; -} __packed; +}; /* ADDIP @@ -631,19 +639,19 @@ struct sctp_fwdtsn_chunk { * report status of ASCONF processing. */ typedef struct sctp_addip_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __be32 crr_id; -} __packed sctp_addip_param_t; +} sctp_addip_param_t; typedef struct sctp_addiphdr { __be32 serial; __u8 params[0]; -} __packed sctp_addiphdr_t; +} sctp_addiphdr_t; typedef struct sctp_addip_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_addiphdr_t addip_hdr; -} __packed sctp_addip_chunk_t; +} sctp_addip_chunk_t; /* AUTH * Section 4.1 Authentication Chunk (AUTH) @@ -698,16 +706,71 @@ typedef struct sctp_authhdr { __be16 shkey_id; __be16 hmac_id; __u8 hmac[0]; -} __packed sctp_authhdr_t; +} sctp_authhdr_t; typedef struct sctp_auth_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_authhdr_t auth_hdr; -} __packed sctp_auth_chunk_t; +} sctp_auth_chunk_t; struct sctp_infox { struct sctp_info *sctpinfo; struct sctp_association *asoc; }; +struct sctp_reconf_chunk { + struct sctp_chunkhdr chunk_hdr; + __u8 params[0]; +}; + +struct sctp_strreset_outreq { + struct sctp_paramhdr param_hdr; + __u32 request_seq; + __u32 response_seq; + __u32 send_reset_at_tsn; + __u16 list_of_streams[0]; +}; + +struct sctp_strreset_inreq { + struct sctp_paramhdr param_hdr; + __u32 request_seq; + __u16 list_of_streams[0]; +}; + +struct sctp_strreset_tsnreq { + struct sctp_paramhdr param_hdr; + __u32 request_seq; +}; + +struct sctp_strreset_addstrm { + struct sctp_paramhdr param_hdr; + __u32 request_seq; + __u16 number_of_streams; + __u16 reserved; +}; + +enum { + SCTP_STRRESET_NOTHING_TO_DO = 0x00, + SCTP_STRRESET_PERFORMED = 0x01, + SCTP_STRRESET_DENIED = 0x02, + SCTP_STRRESET_ERR_WRONG_SSN = 0x03, + SCTP_STRRESET_ERR_IN_PROGRESS = 0x04, + SCTP_STRRESET_ERR_BAD_SEQNO = 0x05, + SCTP_STRRESET_IN_PROGRESS = 0x06, +}; + +struct sctp_strreset_resp { + struct sctp_paramhdr param_hdr; + __u32 response_seq; + __u32 result; +}; + +struct sctp_strreset_resptsn { + struct sctp_paramhdr param_hdr; + __u32 response_seq; + __u32 result; + __u32 senders_next_tsn; + __u32 receivers_next_tsn; +}; + #endif /* __LINUX_SCTP_H__ */ diff --git a/include/linux/security.h b/include/linux/security.h index c2125e9093e8..b6ea1dc9cc9d 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -6,6 +6,7 @@ * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2001 James Morris <jmorris@intercode.com.au> * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) + * Copyright (C) 2016 Mellanox Techonologies * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -68,6 +69,10 @@ struct audit_krule; struct user_namespace; struct timezone; +enum lsm_event { + LSM_POLICY_CHANGE, +}; + /* These functions are in security/commoncap.c */ extern int cap_capable(const struct cred *cred, struct user_namespace *ns, int cap, int audit); @@ -133,6 +138,10 @@ extern unsigned long dac_mmap_min_addr; /* setfsuid or setfsgid, id0 == fsuid or fsgid */ #define LSM_SETID_FS 8 +/* Flags for security_task_prlimit(). */ +#define LSM_PRLIMIT_READ 1 +#define LSM_PRLIMIT_WRITE 2 + /* forward declares to avoid warnings */ struct sched_param; struct request_sock; @@ -140,8 +149,7 @@ struct request_sock; /* bprm->unsafe reasons */ #define LSM_UNSAFE_SHARE 1 #define LSM_UNSAFE_PTRACE 2 -#define LSM_UNSAFE_PTRACE_CAP 4 -#define LSM_UNSAFE_NO_NEW_PRIVS 8 +#define LSM_UNSAFE_NO_NEW_PRIVS 4 #ifdef CONFIG_MMU extern int mmap_min_addr_handler(struct ctl_table *table, int write, @@ -160,6 +168,10 @@ struct security_mnt_opts { int num_mnt_opts; }; +int call_lsm_notifier(enum lsm_event event, void *data); +int register_lsm_notifier(struct notifier_block *nb); +int unregister_lsm_notifier(struct notifier_block *nb); + static inline void security_init_mnt_opts(struct security_mnt_opts *opts) { opts->mnt_opts = NULL; @@ -237,7 +249,9 @@ int security_sb_set_mnt_opts(struct super_block *sb, unsigned long kern_flags, unsigned long *set_kern_flags); int security_sb_clone_mnt_opts(const struct super_block *oldsb, - struct super_block *newsb); + struct super_block *newsb, + unsigned long kern_flags, + unsigned long *set_kern_flags); int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts); int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, void **ctx, @@ -305,6 +319,7 @@ int security_file_send_sigiotask(struct task_struct *tsk, int security_file_receive(struct file *file); int security_file_open(struct file *file, const struct cred *cred); int security_task_create(unsigned long clone_flags); +int security_task_alloc(struct task_struct *task, unsigned long clone_flags); void security_task_free(struct task_struct *task); int security_cred_alloc_blank(struct cred *cred, gfp_t gfp); void security_cred_free(struct cred *cred); @@ -325,6 +340,8 @@ void security_task_getsecid(struct task_struct *p, u32 *secid); int security_task_setnice(struct task_struct *p, int nice); int security_task_setioprio(struct task_struct *p, int ioprio); int security_task_getioprio(struct task_struct *p); +int security_task_prlimit(const struct cred *cred, const struct cred *tcred, + unsigned int flags); int security_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim); int security_task_setscheduler(struct task_struct *p); @@ -332,7 +349,6 @@ int security_task_getscheduler(struct task_struct *p); int security_task_movememory(struct task_struct *p); int security_task_kill(struct task_struct *p, struct siginfo *info, int sig, u32 secid); -int security_task_wait(struct task_struct *p); int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); void security_task_to_inode(struct task_struct *p, struct inode *inode); @@ -361,7 +377,7 @@ int security_sem_semop(struct sem_array *sma, struct sembuf *sops, unsigned nsops, int alter); void security_d_instantiate(struct dentry *dentry, struct inode *inode); int security_getprocattr(struct task_struct *p, char *name, char **value); -int security_setprocattr(struct task_struct *p, char *name, void *value, size_t size); +int security_setprocattr(const char *name, void *value, size_t size); int security_netlink_send(struct sock *sk, struct sk_buff *skb); int security_ismaclabel(const char *name); int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); @@ -376,6 +392,21 @@ int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen); struct security_mnt_opts { }; +static inline int call_lsm_notifier(enum lsm_event event, void *data) +{ + return 0; +} + +static inline int register_lsm_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int unregister_lsm_notifier(struct notifier_block *nb) +{ + return 0; +} + static inline void security_init_mnt_opts(struct security_mnt_opts *opts) { } @@ -576,7 +607,9 @@ static inline int security_sb_set_mnt_opts(struct super_block *sb, } static inline int security_sb_clone_mnt_opts(const struct super_block *oldsb, - struct super_block *newsb) + struct super_block *newsb, + unsigned long kern_flags, + unsigned long *set_kern_flags) { return 0; } @@ -857,6 +890,12 @@ static inline int security_task_create(unsigned long clone_flags) return 0; } +static inline int security_task_alloc(struct task_struct *task, + unsigned long clone_flags) +{ + return 0; +} + static inline void security_task_free(struct task_struct *task) { } @@ -951,6 +990,13 @@ static inline int security_task_getioprio(struct task_struct *p) return 0; } +static inline int security_task_prlimit(const struct cred *cred, + const struct cred *tcred, + unsigned int flags) +{ + return 0; +} + static inline int security_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) @@ -980,11 +1026,6 @@ static inline int security_task_kill(struct task_struct *p, return 0; } -static inline int security_task_wait(struct task_struct *p) -{ - return 0; -} - static inline int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, @@ -1106,7 +1147,7 @@ static inline int security_getprocattr(struct task_struct *p, char *name, char * return -EINVAL; } -static inline int security_setprocattr(struct task_struct *p, char *name, void *value, size_t size) +static inline int security_setprocattr(char *name, void *value, size_t size) { return -EINVAL; } @@ -1393,6 +1434,32 @@ static inline int security_tun_dev_open(void *security) } #endif /* CONFIG_SECURITY_NETWORK */ +#ifdef CONFIG_SECURITY_INFINIBAND +int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey); +int security_ib_endport_manage_subnet(void *sec, const char *name, u8 port_num); +int security_ib_alloc_security(void **sec); +void security_ib_free_security(void *sec); +#else /* CONFIG_SECURITY_INFINIBAND */ +static inline int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey) +{ + return 0; +} + +static inline int security_ib_endport_manage_subnet(void *sec, const char *dev_name, u8 port_num) +{ + return 0; +} + +static inline int security_ib_alloc_security(void **sec) +{ + return 0; +} + +static inline void security_ib_free_security(void *sec) +{ +} +#endif /* CONFIG_SECURITY_INFINIBAND */ + #ifdef CONFIG_SECURITY_NETWORK_XFRM int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, @@ -1638,6 +1705,10 @@ extern struct dentry *securityfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); extern struct dentry *securityfs_create_dir(const char *name, struct dentry *parent); +struct dentry *securityfs_create_symlink(const char *name, + struct dentry *parent, + const char *target, + const struct inode_operations *iops); extern void securityfs_remove(struct dentry *dentry); #else /* CONFIG_SECURITYFS */ @@ -1657,6 +1728,14 @@ static inline struct dentry *securityfs_create_file(const char *name, return ERR_PTR(-ENODEV); } +static inline struct dentry *securityfs_create_symlink(const char *name, + struct dentry *parent, + const char *target, + const struct inode_operations *iops) +{ + return ERR_PTR(-ENODEV); +} + static inline void securityfs_remove(struct dentry *dentry) {} diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h new file mode 100644 index 000000000000..04b124fca51e --- /dev/null +++ b/include/linux/sed-opal.h @@ -0,0 +1,75 @@ +/* + * Copyright © 2016 Intel Corporation + * + * Authors: + * Rafael Antognolli <rafael.antognolli@intel.com> + * Scott Bauer <scott.bauer@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef LINUX_OPAL_H +#define LINUX_OPAL_H + +#include <uapi/linux/sed-opal.h> +#include <linux/kernel.h> + +struct opal_dev; + +typedef int (sec_send_recv)(void *data, u16 spsp, u8 secp, void *buffer, + size_t len, bool send); + +#ifdef CONFIG_BLK_SED_OPAL +void free_opal_dev(struct opal_dev *dev); +bool opal_unlock_from_suspend(struct opal_dev *dev); +struct opal_dev *init_opal_dev(void *data, sec_send_recv *send_recv); +int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *ioctl_ptr); + +static inline bool is_sed_ioctl(unsigned int cmd) +{ + switch (cmd) { + case IOC_OPAL_SAVE: + case IOC_OPAL_LOCK_UNLOCK: + case IOC_OPAL_TAKE_OWNERSHIP: + case IOC_OPAL_ACTIVATE_LSP: + case IOC_OPAL_SET_PW: + case IOC_OPAL_ACTIVATE_USR: + case IOC_OPAL_REVERT_TPR: + case IOC_OPAL_LR_SETUP: + case IOC_OPAL_ADD_USR_TO_LR: + case IOC_OPAL_ENABLE_DISABLE_MBR: + case IOC_OPAL_ERASE_LR: + case IOC_OPAL_SECURE_ERASE_LR: + return true; + } + return false; +} +#else +static inline void free_opal_dev(struct opal_dev *dev) +{ +} + +static inline bool is_sed_ioctl(unsigned int cmd) +{ + return false; +} + +static inline int sed_ioctl(struct opal_dev *dev, unsigned int cmd, + void __user *ioctl_ptr) +{ + return 0; +} +static inline bool opal_unlock_from_suspend(struct opal_dev *dev) +{ + return false; +} +#define init_opal_dev(data, send_recv) NULL +#endif /* CONFIG_BLK_SED_OPAL */ +#endif /* LINUX_OPAL_H */ diff --git a/include/linux/sem.h b/include/linux/sem.h index d0efd6e6c20a..de2deb8676bd 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -8,12 +8,29 @@ struct task_struct; +/* One semaphore structure for each semaphore in the system. */ +struct sem { + int semval; /* current value */ + /* + * PID of the process that last modified the semaphore. For + * Linux, specifically these are: + * - semop + * - semctl, via SETVAL and SETALL. + * - at task exit when performing undo adjustments (see exit_sem). + */ + int sempid; + spinlock_t lock; /* spinlock for fine-grained semtimedop */ + struct list_head pending_alter; /* pending single-sop operations */ + /* that alter the semaphore */ + struct list_head pending_const; /* pending single-sop operations */ + /* that do not alter the semaphore*/ + time_t sem_otime; /* candidate for sem_otime */ +} ____cacheline_aligned_in_smp; + /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { - struct kern_ipc_perm ____cacheline_aligned_in_smp - sem_perm; /* permissions .. see ipc.h */ - time_t sem_ctime; /* last change time */ - struct sem *sem_base; /* ptr to first semaphore in array */ + struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ + time_t sem_ctime; /* create/last semctl() time */ struct list_head pending_alter; /* pending operations */ /* that alter the array */ struct list_head pending_const; /* pending complex operations */ @@ -21,8 +38,10 @@ struct sem_array { struct list_head list_id; /* undo requests on this array */ int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ - bool complex_mode; /* no parallel simple ops */ -}; + unsigned int use_global_lock;/* >0: global lock required */ + + struct sem sems[]; +} __randomize_layout; #ifdef CONFIG_SYSVIPC diff --git a/include/linux/serdev.h b/include/linux/serdev.h new file mode 100644 index 000000000000..e69402d4a8ae --- /dev/null +++ b/include/linux/serdev.h @@ -0,0 +1,325 @@ +/* + * Copyright (C) 2016-2017 Linaro Ltd., Rob Herring <robh@kernel.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#ifndef _LINUX_SERDEV_H +#define _LINUX_SERDEV_H + +#include <linux/types.h> +#include <linux/device.h> +#include <linux/termios.h> +#include <linux/delay.h> + +struct serdev_controller; +struct serdev_device; + +/* + * serdev device structures + */ + +/** + * struct serdev_device_ops - Callback operations for a serdev device + * @receive_buf: Function called with data received from device. + * @write_wakeup: Function called when ready to transmit more data. + */ +struct serdev_device_ops { + int (*receive_buf)(struct serdev_device *, const unsigned char *, size_t); + void (*write_wakeup)(struct serdev_device *); +}; + +/** + * struct serdev_device - Basic representation of an serdev device + * @dev: Driver model representation of the device. + * @nr: Device number on serdev bus. + * @ctrl: serdev controller managing this device. + * @ops: Device operations. + * @write_comp Completion used by serdev_device_write() internally + * @write_lock Lock to serialize access when writing data + */ +struct serdev_device { + struct device dev; + int nr; + struct serdev_controller *ctrl; + const struct serdev_device_ops *ops; + struct completion write_comp; + struct mutex write_lock; +}; + +static inline struct serdev_device *to_serdev_device(struct device *d) +{ + return container_of(d, struct serdev_device, dev); +} + +/** + * struct serdev_device_driver - serdev slave device driver + * @driver: serdev device drivers should initialize name field of this + * structure. + * @probe: binds this driver to a serdev device. + * @remove: unbinds this driver from the serdev device. + */ +struct serdev_device_driver { + struct device_driver driver; + int (*probe)(struct serdev_device *); + void (*remove)(struct serdev_device *); +}; + +static inline struct serdev_device_driver *to_serdev_device_driver(struct device_driver *d) +{ + return container_of(d, struct serdev_device_driver, driver); +} + +/* + * serdev controller structures + */ +struct serdev_controller_ops { + int (*write_buf)(struct serdev_controller *, const unsigned char *, size_t); + void (*write_flush)(struct serdev_controller *); + int (*write_room)(struct serdev_controller *); + int (*open)(struct serdev_controller *); + void (*close)(struct serdev_controller *); + void (*set_flow_control)(struct serdev_controller *, bool); + unsigned int (*set_baudrate)(struct serdev_controller *, unsigned int); + void (*wait_until_sent)(struct serdev_controller *, long); + int (*get_tiocm)(struct serdev_controller *); + int (*set_tiocm)(struct serdev_controller *, unsigned int, unsigned int); +}; + +/** + * struct serdev_controller - interface to the serdev controller + * @dev: Driver model representation of the device. + * @nr: number identifier for this controller/bus. + * @serdev: Pointer to slave device for this controller. + * @ops: Controller operations. + */ +struct serdev_controller { + struct device dev; + unsigned int nr; + struct serdev_device *serdev; + const struct serdev_controller_ops *ops; +}; + +static inline struct serdev_controller *to_serdev_controller(struct device *d) +{ + return container_of(d, struct serdev_controller, dev); +} + +static inline void *serdev_device_get_drvdata(const struct serdev_device *serdev) +{ + return dev_get_drvdata(&serdev->dev); +} + +static inline void serdev_device_set_drvdata(struct serdev_device *serdev, void *data) +{ + dev_set_drvdata(&serdev->dev, data); +} + +/** + * serdev_device_put() - decrement serdev device refcount + * @serdev serdev device. + */ +static inline void serdev_device_put(struct serdev_device *serdev) +{ + if (serdev) + put_device(&serdev->dev); +} + +static inline void serdev_device_set_client_ops(struct serdev_device *serdev, + const struct serdev_device_ops *ops) +{ + serdev->ops = ops; +} + +static inline +void *serdev_controller_get_drvdata(const struct serdev_controller *ctrl) +{ + return ctrl ? dev_get_drvdata(&ctrl->dev) : NULL; +} + +static inline void serdev_controller_set_drvdata(struct serdev_controller *ctrl, + void *data) +{ + dev_set_drvdata(&ctrl->dev, data); +} + +/** + * serdev_controller_put() - decrement controller refcount + * @ctrl serdev controller. + */ +static inline void serdev_controller_put(struct serdev_controller *ctrl) +{ + if (ctrl) + put_device(&ctrl->dev); +} + +struct serdev_device *serdev_device_alloc(struct serdev_controller *); +int serdev_device_add(struct serdev_device *); +void serdev_device_remove(struct serdev_device *); + +struct serdev_controller *serdev_controller_alloc(struct device *, size_t); +int serdev_controller_add(struct serdev_controller *); +void serdev_controller_remove(struct serdev_controller *); + +static inline void serdev_controller_write_wakeup(struct serdev_controller *ctrl) +{ + struct serdev_device *serdev = ctrl->serdev; + + if (!serdev || !serdev->ops->write_wakeup) + return; + + serdev->ops->write_wakeup(serdev); +} + +static inline int serdev_controller_receive_buf(struct serdev_controller *ctrl, + const unsigned char *data, + size_t count) +{ + struct serdev_device *serdev = ctrl->serdev; + + if (!serdev || !serdev->ops->receive_buf) + return -EINVAL; + + return serdev->ops->receive_buf(serdev, data, count); +} + +#if IS_ENABLED(CONFIG_SERIAL_DEV_BUS) + +int serdev_device_open(struct serdev_device *); +void serdev_device_close(struct serdev_device *); +unsigned int serdev_device_set_baudrate(struct serdev_device *, unsigned int); +void serdev_device_set_flow_control(struct serdev_device *, bool); +int serdev_device_write_buf(struct serdev_device *, const unsigned char *, size_t); +void serdev_device_wait_until_sent(struct serdev_device *, long); +int serdev_device_get_tiocm(struct serdev_device *); +int serdev_device_set_tiocm(struct serdev_device *, int, int); +void serdev_device_write_wakeup(struct serdev_device *); +int serdev_device_write(struct serdev_device *, const unsigned char *, size_t, unsigned long); +void serdev_device_write_flush(struct serdev_device *); +int serdev_device_write_room(struct serdev_device *); + +/* + * serdev device driver functions + */ +int __serdev_device_driver_register(struct serdev_device_driver *, struct module *); +#define serdev_device_driver_register(sdrv) \ + __serdev_device_driver_register(sdrv, THIS_MODULE) + +/** + * serdev_device_driver_unregister() - unregister an serdev client driver + * @sdrv: the driver to unregister + */ +static inline void serdev_device_driver_unregister(struct serdev_device_driver *sdrv) +{ + if (sdrv) + driver_unregister(&sdrv->driver); +} + +#define module_serdev_device_driver(__serdev_device_driver) \ + module_driver(__serdev_device_driver, serdev_device_driver_register, \ + serdev_device_driver_unregister) + +#else + +static inline int serdev_device_open(struct serdev_device *sdev) +{ + return -ENODEV; +} +static inline void serdev_device_close(struct serdev_device *sdev) {} +static inline unsigned int serdev_device_set_baudrate(struct serdev_device *sdev, unsigned int baudrate) +{ + return 0; +} +static inline void serdev_device_set_flow_control(struct serdev_device *sdev, bool enable) {} +static inline int serdev_device_write_buf(struct serdev_device *serdev, + const unsigned char *buf, + size_t count) +{ + return -ENODEV; +} +static inline void serdev_device_wait_until_sent(struct serdev_device *sdev, long timeout) {} +static inline int serdev_device_get_tiocm(struct serdev_device *serdev) +{ + return -ENOTSUPP; +} +static inline int serdev_device_set_tiocm(struct serdev_device *serdev, int set, int clear) +{ + return -ENOTSUPP; +} +static inline int serdev_device_write(struct serdev_device *sdev, const unsigned char *buf, + size_t count, unsigned long timeout) +{ + return -ENODEV; +} +static inline void serdev_device_write_flush(struct serdev_device *sdev) {} +static inline int serdev_device_write_room(struct serdev_device *sdev) +{ + return 0; +} + +#define serdev_device_driver_register(x) +#define serdev_device_driver_unregister(x) + +#endif /* CONFIG_SERIAL_DEV_BUS */ + +static inline bool serdev_device_get_cts(struct serdev_device *serdev) +{ + int status = serdev_device_get_tiocm(serdev); + return !!(status & TIOCM_CTS); +} + +static inline int serdev_device_wait_for_cts(struct serdev_device *serdev, bool state, int timeout_ms) +{ + unsigned long timeout; + bool signal; + + timeout = jiffies + msecs_to_jiffies(timeout_ms); + while (time_is_after_jiffies(timeout)) { + signal = serdev_device_get_cts(serdev); + if (signal == state) + return 0; + usleep_range(1000, 2000); + } + + return -ETIMEDOUT; +} + +static inline int serdev_device_set_rts(struct serdev_device *serdev, bool enable) +{ + if (enable) + return serdev_device_set_tiocm(serdev, TIOCM_RTS, 0); + else + return serdev_device_set_tiocm(serdev, 0, TIOCM_RTS); +} + +/* + * serdev hooks into TTY core + */ +struct tty_port; +struct tty_driver; + +#ifdef CONFIG_SERIAL_DEV_CTRL_TTYPORT +struct device *serdev_tty_port_register(struct tty_port *port, + struct device *parent, + struct tty_driver *drv, int idx); +int serdev_tty_port_unregister(struct tty_port *port); +#else +static inline struct device *serdev_tty_port_register(struct tty_port *port, + struct device *parent, + struct tty_driver *drv, int idx) +{ + return ERR_PTR(-ENODEV); +} +static inline int serdev_tty_port_unregister(struct tty_port *port) +{ + return -ENODEV; +} +#endif /* CONFIG_SERIAL_DEV_CTRL_TTYPORT */ + +#endif /*_LINUX_SERDEV_H */ diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 5def8e830fb0..1775500294bb 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -195,6 +195,7 @@ struct uart_port { #define UPF_NO_TXEN_TEST ((__force upf_t) (1 << 15)) #define UPF_MAGIC_MULTIPLIER ((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ ) +#define UPF_NO_THRE_TEST ((__force upf_t) (1 << 19)) /* Port has hardware-assisted h/w flow control */ #define UPF_AUTO_CTS ((__force upf_t) (1 << 20)) #define UPF_AUTO_RTS ((__force upf_t) (1 << 21)) @@ -247,6 +248,7 @@ struct uart_port { unsigned char suspended; unsigned char irq_wake; unsigned char unused[2]; + const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; @@ -450,7 +452,7 @@ extern void uart_handle_cts_change(struct uart_port *uport, extern void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, unsigned int ch, unsigned int flag); -#ifdef SUPPORT_SYSRQ +#if defined(SUPPORT_SYSRQ) && defined(CONFIG_MAGIC_SYSRQ_SERIAL) static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) { diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 9f2bfd055742..e598eaef3962 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -9,8 +9,6 @@ * Generic header for SuperH (H)SCI(F) (used by sh/sh64 and related parts) */ -#define SCIx_NOT_SUPPORTED (-1) - /* Serial Control Register (@ = not supported by all parts) */ #define SCSCR_TIE BIT(7) /* Transmit Interrupt Enable */ #define SCSCR_RIE BIT(6) /* Receive Interrupt Enable */ @@ -41,24 +39,16 @@ enum { SCIx_NR_REGTYPES, }; -struct device; - struct plat_sci_port_ops { void (*init_pins)(struct uart_port *, unsigned int cflag); }; /* - * Port-specific capabilities - */ -#define SCIx_HAVE_RTSCTS BIT(0) - -/* * Platform device specific platform_data struct */ struct plat_sci_port { unsigned int type; /* SCI / SCIF / IRDA / HSCIF */ upf_t flags; /* UPF_* flags */ - unsigned long capabilities; /* Port features/capabilities */ unsigned int sampling_rate; unsigned int scscr; /* SCSCR initialization */ @@ -66,14 +56,9 @@ struct plat_sci_port { /* * Platform overrides if necessary, defaults otherwise. */ - int port_reg; - unsigned char regshift; unsigned char regtype; struct plat_sci_port_ops *ops; - - unsigned int dma_slave_tx; - unsigned int dma_slave_rx; }; #endif /* __LINUX_SERIAL_SCI_H */ diff --git a/include/linux/serio.h b/include/linux/serio.h index c733cff44e18..138a5efe863a 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -77,6 +77,7 @@ struct serio_driver { irqreturn_t (*interrupt)(struct serio *, unsigned char, unsigned int); int (*connect)(struct serio *, struct serio_driver *drv); int (*reconnect)(struct serio *); + int (*fast_reconnect)(struct serio *); void (*disconnect)(struct serio *); void (*cleanup)(struct serio *); diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h new file mode 100644 index 000000000000..e5140648f638 --- /dev/null +++ b/include/linux/set_memory.h @@ -0,0 +1,20 @@ +/* + * Copyright 2017, Michael Ellerman, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation; + */ +#ifndef _LINUX_SET_MEMORY_H_ +#define _LINUX_SET_MEMORY_H_ + +#ifdef CONFIG_ARCH_HAS_SET_MEMORY +#include <asm/set_memory.h> +#else +static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; } +static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; } +static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } +static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } +#endif + +#endif /* _LINUX_SET_MEMORY_H_ */ diff --git a/include/linux/shm.h b/include/linux/shm.h index 04e881829625..0fb7061ec54c 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -22,7 +22,7 @@ struct shmid_kernel /* private to the kernel */ /* The task created the shm object. NULL if the task is dead. */ struct task_struct *shm_creator; struct list_head shm_clist; /* list by creator */ -}; +} __randomize_layout; /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index ff078e7043b6..a7d6bd2a918f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -57,7 +57,14 @@ extern int shmem_zero_setup(struct vm_area_struct *); extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +#ifdef CONFIG_SHMEM extern bool shmem_mapping(struct address_space *mapping); +#else +static inline bool shmem_mapping(struct address_space *mapping) +{ + return false; +} +#endif /* CONFIG_SHMEM */ extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); @@ -124,4 +131,15 @@ static inline bool shmem_huge_enabled(struct vm_area_struct *vma) } #endif +#ifdef CONFIG_SHMEM +extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep); +#else +#define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ + src_addr, pagep) ({ BUG(); 0; }) +#endif + #endif diff --git a/include/linux/signal.h b/include/linux/signal.h index 5308304993be..e2678b5dbb21 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -1,36 +1,14 @@ #ifndef _LINUX_SIGNAL_H #define _LINUX_SIGNAL_H -#include <linux/list.h> #include <linux/bug.h> -#include <uapi/linux/signal.h> +#include <linux/signal_types.h> +#include <linux/string.h> struct task_struct; /* for sysctl */ extern int print_fatal_signals; -/* - * Real Time signals may be queued. - */ - -struct sigqueue { - struct list_head list; - int flags; - siginfo_t info; - struct user_struct *user; -}; - -/* flags values. */ -#define SIGQUEUE_PREALLOC 1 - -struct sigpending { - struct list_head list; - sigset_t signal; -}; - -#ifndef HAVE_ARCH_COPY_SIGINFO - -#include <linux/string.h> static inline void copy_siginfo(struct siginfo *to, struct siginfo *from) { @@ -41,7 +19,7 @@ static inline void copy_siginfo(struct siginfo *to, struct siginfo *from) memcpy(to, from, __ARCH_SI_PREAMBLE_SIZE + sizeof(from->_sifields._sigchld)); } -#endif +int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from); /* * Define some primitives to manipulate sigset_t. @@ -265,49 +243,11 @@ extern int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, bool group); extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p); extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); -extern int do_sigtimedwait(const sigset_t *, siginfo_t *, - const struct timespec *); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; -struct sigaction { -#ifndef __ARCH_HAS_IRIX_SIGACTION - __sighandler_t sa_handler; - unsigned long sa_flags; -#else - unsigned int sa_flags; - __sighandler_t sa_handler; -#endif -#ifdef __ARCH_HAS_SA_RESTORER - __sigrestore_t sa_restorer; -#endif - sigset_t sa_mask; /* mask last for extensibility */ -}; - -struct k_sigaction { - struct sigaction sa; -#ifdef __ARCH_HAS_KA_RESTORER - __sigrestore_t ka_restorer; -#endif -}; - -#ifdef CONFIG_OLD_SIGACTION -struct old_sigaction { - __sighandler_t sa_handler; - old_sigset_t sa_mask; - unsigned long sa_flags; - __sigrestore_t sa_restorer; -}; -#endif - -struct ksignal { - struct k_sigaction ka; - siginfo_t info; - int sig; -}; - extern int get_signal(struct ksignal *ksig); extern void signal_setup_done(int failed, struct ksignal *ksig, int stepping); extern void exit_signals(struct task_struct *tsk); @@ -445,10 +385,6 @@ int unhandled_signal(struct task_struct *tsk, int sig); #define sig_kernel_ignore(sig) siginmask(sig, SIG_KERNEL_IGNORE_MASK) #define sig_kernel_stop(sig) siginmask(sig, SIG_KERNEL_STOP_MASK) -#define sig_user_defined(t, signr) \ - (((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_DFL) && \ - ((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_IGN)) - #define sig_fatal(t, signr) \ (!siginmask(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \ (t)->sighand->action[(signr)-1].sa.sa_handler == SIG_DFL) diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h new file mode 100644 index 000000000000..16d862a3d8f3 --- /dev/null +++ b/include/linux/signal_types.h @@ -0,0 +1,66 @@ +#ifndef _LINUX_SIGNAL_TYPES_H +#define _LINUX_SIGNAL_TYPES_H + +/* + * Basic signal handling related data type definitions: + */ + +#include <linux/list.h> +#include <uapi/linux/signal.h> + +/* + * Real Time signals may be queued. + */ + +struct sigqueue { + struct list_head list; + int flags; + siginfo_t info; + struct user_struct *user; +}; + +/* flags values. */ +#define SIGQUEUE_PREALLOC 1 + +struct sigpending { + struct list_head list; + sigset_t signal; +}; + +struct sigaction { +#ifndef __ARCH_HAS_IRIX_SIGACTION + __sighandler_t sa_handler; + unsigned long sa_flags; +#else + unsigned int sa_flags; + __sighandler_t sa_handler; +#endif +#ifdef __ARCH_HAS_SA_RESTORER + __sigrestore_t sa_restorer; +#endif + sigset_t sa_mask; /* mask last for extensibility */ +}; + +struct k_sigaction { + struct sigaction sa; +#ifdef __ARCH_HAS_KA_RESTORER + __sigrestore_t ka_restorer; +#endif +}; + +#ifdef CONFIG_OLD_SIGACTION +struct old_sigaction { + __sighandler_t sa_handler; + old_sigset_t sa_mask; + unsigned long sa_flags; + __sigrestore_t sa_restorer; +}; +#endif + +struct ksignal { + struct k_sigaction ka; + siginfo_t info; + int sig; +}; + +#endif /* _LINUX_SIGNAL_TYPES_H */ diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h index eadbe227c256..4985048640a7 100644 --- a/include/linux/signalfd.h +++ b/include/linux/signalfd.h @@ -8,7 +8,7 @@ #define _LINUX_SIGNALFD_H #include <uapi/linux/signalfd.h> - +#include <linux/sched/signal.h> #ifdef CONFIG_SIGNALFD diff --git a/include/linux/siphash.h b/include/linux/siphash.h new file mode 100644 index 000000000000..fa7a6b9cedbf --- /dev/null +++ b/include/linux/siphash.h @@ -0,0 +1,140 @@ +/* Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + * + * This file is provided under a dual BSD/GPLv2 license. + * + * SipHash: a fast short-input PRF + * https://131002.net/siphash/ + * + * This implementation is specifically for SipHash2-4 for a secure PRF + * and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for + * hashtables. + */ + +#ifndef _LINUX_SIPHASH_H +#define _LINUX_SIPHASH_H + +#include <linux/types.h> +#include <linux/kernel.h> + +#define SIPHASH_ALIGNMENT __alignof__(u64) +typedef struct { + u64 key[2]; +} siphash_key_t; + +u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key); +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS +u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key); +#endif + +u64 siphash_1u64(const u64 a, const siphash_key_t *key); +u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key); +u64 siphash_3u64(const u64 a, const u64 b, const u64 c, + const siphash_key_t *key); +u64 siphash_4u64(const u64 a, const u64 b, const u64 c, const u64 d, + const siphash_key_t *key); +u64 siphash_1u32(const u32 a, const siphash_key_t *key); +u64 siphash_3u32(const u32 a, const u32 b, const u32 c, + const siphash_key_t *key); + +static inline u64 siphash_2u32(const u32 a, const u32 b, + const siphash_key_t *key) +{ + return siphash_1u64((u64)b << 32 | a, key); +} +static inline u64 siphash_4u32(const u32 a, const u32 b, const u32 c, + const u32 d, const siphash_key_t *key) +{ + return siphash_2u64((u64)b << 32 | a, (u64)d << 32 | c, key); +} + + +static inline u64 ___siphash_aligned(const __le64 *data, size_t len, + const siphash_key_t *key) +{ + if (__builtin_constant_p(len) && len == 4) + return siphash_1u32(le32_to_cpup((const __le32 *)data), key); + if (__builtin_constant_p(len) && len == 8) + return siphash_1u64(le64_to_cpu(data[0]), key); + if (__builtin_constant_p(len) && len == 16) + return siphash_2u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]), + key); + if (__builtin_constant_p(len) && len == 24) + return siphash_3u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]), + le64_to_cpu(data[2]), key); + if (__builtin_constant_p(len) && len == 32) + return siphash_4u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]), + le64_to_cpu(data[2]), le64_to_cpu(data[3]), + key); + return __siphash_aligned(data, len, key); +} + +/** + * siphash - compute 64-bit siphash PRF value + * @data: buffer to hash + * @size: size of @data + * @key: the siphash key + */ +static inline u64 siphash(const void *data, size_t len, + const siphash_key_t *key) +{ +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT)) + return __siphash_unaligned(data, len, key); +#endif + return ___siphash_aligned(data, len, key); +} + +#define HSIPHASH_ALIGNMENT __alignof__(unsigned long) +typedef struct { + unsigned long key[2]; +} hsiphash_key_t; + +u32 __hsiphash_aligned(const void *data, size_t len, + const hsiphash_key_t *key); +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS +u32 __hsiphash_unaligned(const void *data, size_t len, + const hsiphash_key_t *key); +#endif + +u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key); +u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key); +u32 hsiphash_3u32(const u32 a, const u32 b, const u32 c, + const hsiphash_key_t *key); +u32 hsiphash_4u32(const u32 a, const u32 b, const u32 c, const u32 d, + const hsiphash_key_t *key); + +static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len, + const hsiphash_key_t *key) +{ + if (__builtin_constant_p(len) && len == 4) + return hsiphash_1u32(le32_to_cpu(data[0]), key); + if (__builtin_constant_p(len) && len == 8) + return hsiphash_2u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]), + key); + if (__builtin_constant_p(len) && len == 12) + return hsiphash_3u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]), + le32_to_cpu(data[2]), key); + if (__builtin_constant_p(len) && len == 16) + return hsiphash_4u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]), + le32_to_cpu(data[2]), le32_to_cpu(data[3]), + key); + return __hsiphash_aligned(data, len, key); +} + +/** + * hsiphash - compute 32-bit hsiphash PRF value + * @data: buffer to hash + * @size: size of @data + * @key: the hsiphash key + */ +static inline u32 hsiphash(const void *data, size_t len, + const hsiphash_key_t *key) +{ +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT)) + return __hsiphash_unaligned(data, len, key); +#endif + return ___hsiphash_aligned(data, len, key); +} + +#endif /* _LINUX_SIPHASH_H */ diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index f4dfade428f0..35226cd4efb0 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -97,21 +97,46 @@ static inline struct sk_buff *skb_array_consume(struct skb_array *a) return ptr_ring_consume(&a->ring); } +static inline int skb_array_consume_batched(struct skb_array *a, + struct sk_buff **array, int n) +{ + return ptr_ring_consume_batched(&a->ring, (void **)array, n); +} + static inline struct sk_buff *skb_array_consume_irq(struct skb_array *a) { return ptr_ring_consume_irq(&a->ring); } +static inline int skb_array_consume_batched_irq(struct skb_array *a, + struct sk_buff **array, int n) +{ + return ptr_ring_consume_batched_irq(&a->ring, (void **)array, n); +} + static inline struct sk_buff *skb_array_consume_any(struct skb_array *a) { return ptr_ring_consume_any(&a->ring); } +static inline int skb_array_consume_batched_any(struct skb_array *a, + struct sk_buff **array, int n) +{ + return ptr_ring_consume_batched_any(&a->ring, (void **)array, n); +} + + static inline struct sk_buff *skb_array_consume_bh(struct skb_array *a) { return ptr_ring_consume_bh(&a->ring); } +static inline int skb_array_consume_batched_bh(struct skb_array *a, + struct sk_buff **array, int n) +{ + return ptr_ring_consume_batched_bh(&a->ring, (void **)array, n); +} + static inline int __skb_array_len_with_tag(struct sk_buff *skb) { if (likely(skb)) { @@ -156,6 +181,12 @@ static void __skb_array_destroy_skb(void *ptr) kfree_skb(ptr); } +static inline void skb_array_unconsume(struct skb_array *a, + struct sk_buff **skbs, int n) +{ + ptr_ring_unconsume(&a->ring, (void **)skbs, n, __skb_array_destroy_skb); +} + static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) { return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a410715bbef8..dbe29b6c9bd6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -34,6 +34,7 @@ #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <linux/sched.h> +#include <linux/sched/clock.h> #include <net/flow_dissector.h> #include <linux/splice.h> #include <linux/in6.h> @@ -108,6 +109,7 @@ * may perform further validation in this case. * GRE: only if the checksum is present in the header. * SCTP: indicates the CRC in SCTP header has been validated. + * FCOE: indicates the CRC in FC frame has been validated. * * skb->csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as CHECKSUM_UNNECESSARY. @@ -125,8 +127,10 @@ * packet as seen by netif_rx() and fills out in skb->csum. Meaning, the * hardware doesn't need to parse L3/L4 headers to implement this. * - * Note: Even if device supports only some protocols, but is able to produce - * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. + * Notes: + * - Even if device supports only some protocols, but is able to produce + * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. + * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * CHECKSUM_PARTIAL: * @@ -161,14 +165,11 @@ * * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate - * checksum offload capability. If a device has limited checksum capabilities - * (for instance can only perform NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM as - * described above) a helper function can be called to resolve - * CHECKSUM_PARTIAL. The helper functions are skb_csum_off_chk*. The helper - * function takes a spec argument that describes the protocol layer that is - * supported for checksum offload and can be called for each packet. If a - * packet does not match the specification for offload, skb_checksum_help - * is called to resolve the checksum. + * checksum offload capability. + * skb_csum_hwoffload_help() can be called to resolve CHECKSUM_PARTIAL based + * on network device checksumming capabilities: if a packet does not match + * them, skb_checksum_help or skb_crc32c_help (depending on the value of + * csum_not_inet, see item D.) is called to resolve the checksum. * * CHECKSUM_NONE: * @@ -188,11 +189,13 @@ * * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of * offloading the SCTP CRC in a packet. To perform this offload the stack - * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset - * accordingly. Note the there is no indication in the skbuff that the - * CHECKSUM_PARTIAL refers to an SCTP checksum, a driver that supports - * both IP checksum offload and SCTP CRC offload must verify which offload - * is configured for a packet presumably by inspecting packet headers. + * will set set csum_start and csum_offset accordingly, set ip_summed to + * CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication in + * the skbuff that the CHECKSUM_PARTIAL refers to CRC32c. + * A driver that supports both IP checksum offload and SCTP CRC32c offload + * must verify which offload is configured for a packet by testing the + * value of skb->csum_not_inet; skb_crc32c_csum_help is provided to resolve + * CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of * offloading the FCOE CRC in a packet. To perform this offload the stack @@ -249,7 +252,7 @@ struct nf_conntrack { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { - atomic_t use; + refcount_t use; enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, @@ -412,14 +415,15 @@ struct ubuf_info { * the end of the header data, ie. at skb->end. */ struct skb_shared_info { + unsigned short _unused; unsigned char nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; - unsigned short gso_type; struct sk_buff *frag_list; struct skb_shared_hwtstamps hwtstamps; + unsigned int gso_type; u32 tskey; __be32 ip6_frag_id; @@ -490,6 +494,8 @@ enum { SKB_GSO_TUNNEL_REMCSUM = 1 << 14, SKB_GSO_SCTP = 1 << 15, + + SKB_GSO_ESP = 1 << 16, }; #if BITS_PER_LONG > 32 @@ -502,66 +508,6 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif -/** - * struct skb_mstamp - multi resolution time stamps - * @stamp_us: timestamp in us resolution - * @stamp_jiffies: timestamp in jiffies - */ -struct skb_mstamp { - union { - u64 v64; - struct { - u32 stamp_us; - u32 stamp_jiffies; - }; - }; -}; - -/** - * skb_mstamp_get - get current timestamp - * @cl: place to store timestamps - */ -static inline void skb_mstamp_get(struct skb_mstamp *cl) -{ - u64 val = local_clock(); - - do_div(val, NSEC_PER_USEC); - cl->stamp_us = (u32)val; - cl->stamp_jiffies = (u32)jiffies; -} - -/** - * skb_mstamp_delta - compute the difference in usec between two skb_mstamp - * @t1: pointer to newest sample - * @t0: pointer to oldest sample - */ -static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, - const struct skb_mstamp *t0) -{ - s32 delta_us = t1->stamp_us - t0->stamp_us; - u32 delta_jiffies = t1->stamp_jiffies - t0->stamp_jiffies; - - /* If delta_us is negative, this might be because interval is too big, - * or local_clock() drift is too big : fallback using jiffies. - */ - if (delta_us <= 0 || - delta_jiffies >= (INT_MAX / (USEC_PER_SEC / HZ))) - - delta_us = jiffies_to_usecs(delta_jiffies); - - return delta_us; -} - -static inline bool skb_mstamp_after(const struct skb_mstamp *t1, - const struct skb_mstamp *t0) -{ - s32 diff = t1->stamp_jiffies - t0->stamp_jiffies; - - if (!diff) - diff = t1->stamp_us - t0->stamp_us; - return diff > 0; -} - /** * struct sk_buff - socket buffer * @next: Next buffer in list @@ -585,20 +531,22 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header - * @nfctinfo: Relationship of this skb to the connection * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs + * @tc_skip_classify: do not classify packet. set by IFB device + * @tc_at_ingress: used within tc_classify to distinguish in/egress + * @tc_redirected: packet was redirected by a tc action + * @tc_from_ingress: if tc_redirected, tc_at_ingress at time of redirect * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function - * @nfct: Associated connection, if any + * @_nfct: Associated connection, if any (with nfctinfo bits) * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index - * @tc_verd: traffic control verdict * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @xmit_more: More SKBs are pending for this queue @@ -610,6 +558,8 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS + * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL + * @dst_pending_confirm: need to confirm neighbour * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking * @mark: Generic packet mark @@ -639,7 +589,7 @@ struct sk_buff { union { ktime_t tstamp; - struct skb_mstamp skb_mstamp; + u64 skb_mstamp; }; }; struct rb_node rbnode; /* used in netem & tcp stack */ @@ -668,7 +618,7 @@ struct sk_buff { struct sec_path *sp; #endif #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - struct nf_conntrack *nfct; + unsigned long _nfct; #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info *nf_bridge; @@ -721,7 +671,6 @@ struct sk_buff { __u8 pkt_type:3; __u8 pfmemalloc:1; __u8 ignore_df:1; - __u8 nfctinfo:3; __u8 nf_trace:1; __u8 ip_summed:2; @@ -738,8 +687,9 @@ struct sk_buff { __u8 csum_valid:1; __u8 csum_complete_sw:1; __u8 csum_level:2; - __u8 csum_bad:1; + __u8 csum_not_inet:1; + __u8 dst_pending_confirm:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif @@ -749,13 +699,15 @@ struct sk_buff { #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; #endif - /* 2, 4 or 5 bit hole */ +#ifdef CONFIG_NET_CLS_ACT + __u8 tc_skip_classify:1; + __u8 tc_at_ingress:1; + __u8 tc_redirected:1; + __u8 tc_from_ingress:1; +#endif #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ -#ifdef CONFIG_NET_CLS_ACT - __u16 tc_verd; /* traffic control verdict */ -#endif #endif union { @@ -809,7 +761,7 @@ struct sk_buff { unsigned char *head, *data; unsigned int truesize; - atomic_t users; + refcount_t users; }; #ifdef __KERNEL__ @@ -836,6 +788,7 @@ static inline bool skb_pfmemalloc(const struct sk_buff *skb) #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) +#define SKB_NFCT_PTRMASK ~(7UL) /** * skb_dst - returns skb dst_entry * @skb: buffer @@ -905,10 +858,34 @@ static inline bool skb_pkt_type_ok(u32 ptype) return ptype <= PACKET_OTHERHOST; } +static inline unsigned int skb_napi_id(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + return skb->napi_id; +#else + return 0; +#endif +} + +/* decrement the reference count and return true if we can free the skb */ +static inline bool skb_unref(struct sk_buff *skb) +{ + if (unlikely(!skb)) + return false; + if (likely(refcount_read(&skb->users) == 1)) + smp_rmb(); + else if (likely(!refcount_dec_and_test(&skb->users))) + return false; + + return true; +} + +void skb_release_head_state(struct sk_buff *skb); void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_tx_error(struct sk_buff *skb); void consume_skb(struct sk_buff *skb); +void consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); extern struct kmem_cache *skbuff_head_cache; @@ -938,7 +915,7 @@ struct sk_buff_fclones { struct sk_buff skb2; - atomic_t fclone_ref; + refcount_t fclone_ref; }; /** @@ -958,7 +935,7 @@ static inline bool skb_fclone_busy(const struct sock *sk, fclones = container_of(skb, struct sk_buff_fclones, skb1); return skb->fclone == SKB_FCLONE_ORIG && - atomic_read(&fclones->fclone_ref) > 1 && + refcount_read(&fclones->fclone_ref) > 1 && fclones->skb2.sk == sk; } @@ -991,10 +968,10 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); -int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, - int offset, int len); -int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, - int len); +int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len); +int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); int skb_pad(struct sk_buff *skb, int pad); #define dev_kfree_skb(a) consume_skb(a) @@ -1306,7 +1283,7 @@ static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { - atomic_inc(&skb->users); + refcount_inc(&skb->users); return skb; } @@ -1407,7 +1384,7 @@ static inline void __skb_header_release(struct sk_buff *skb) */ static inline int skb_shared(const struct sk_buff *skb) { - return atomic_read(&skb->users) != 1; + return refcount_read(&skb->users) != 1; } /** @@ -1916,41 +1893,87 @@ static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) /* * Add data to an sk_buff */ -unsigned char *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); -unsigned char *skb_put(struct sk_buff *skb, unsigned int len); -static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len) +void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); +void *skb_put(struct sk_buff *skb, unsigned int len); +static inline void *__skb_put(struct sk_buff *skb, unsigned int len) { - unsigned char *tmp = skb_tail_pointer(skb); + void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; return tmp; } -unsigned char *skb_push(struct sk_buff *skb, unsigned int len); -static inline unsigned char *__skb_push(struct sk_buff *skb, unsigned int len) +static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len) +{ + void *tmp = __skb_put(skb, len); + + memset(tmp, 0, len); + return tmp; +} + +static inline void *__skb_put_data(struct sk_buff *skb, const void *data, + unsigned int len) +{ + void *tmp = __skb_put(skb, len); + + memcpy(tmp, data, len); + return tmp; +} + +static inline void __skb_put_u8(struct sk_buff *skb, u8 val) +{ + *(u8 *)__skb_put(skb, 1) = val; +} + +static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len) +{ + void *tmp = skb_put(skb, len); + + memset(tmp, 0, len); + + return tmp; +} + +static inline void *skb_put_data(struct sk_buff *skb, const void *data, + unsigned int len) +{ + void *tmp = skb_put(skb, len); + + memcpy(tmp, data, len); + + return tmp; +} + +static inline void skb_put_u8(struct sk_buff *skb, u8 val) +{ + *(u8 *)skb_put(skb, 1) = val; +} + +void *skb_push(struct sk_buff *skb, unsigned int len); +static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { skb->data -= len; skb->len += len; return skb->data; } -unsigned char *skb_pull(struct sk_buff *skb, unsigned int len); -static inline unsigned char *__skb_pull(struct sk_buff *skb, unsigned int len) +void *skb_pull(struct sk_buff *skb, unsigned int len); +static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { skb->len -= len; BUG_ON(skb->len < skb->data_len); return skb->data += len; } -static inline unsigned char *skb_pull_inline(struct sk_buff *skb, unsigned int len) +static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } -unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta); +void *__pskb_pull_tail(struct sk_buff *skb, int delta); -static inline unsigned char *__pskb_pull(struct sk_buff *skb, unsigned int len) +static inline void *__pskb_pull(struct sk_buff *skb, unsigned int len) { if (len > skb_headlen(skb) && !__pskb_pull_tail(skb, len - skb_headlen(skb))) @@ -1959,7 +1982,7 @@ static inline unsigned char *__pskb_pull(struct sk_buff *skb, unsigned int len) return skb->data += len; } -static inline unsigned char *pskb_pull(struct sk_buff *skb, unsigned int len) +static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len); } @@ -2178,6 +2201,16 @@ static inline unsigned char *skb_mac_header(const struct sk_buff *skb) return skb->head + skb->mac_header; } +static inline int skb_mac_offset(const struct sk_buff *skb) +{ + return skb_mac_header(skb) - skb->data; +} + +static inline u32 skb_mac_header_len(const struct sk_buff *skb) +{ + return skb->network_header - skb->mac_header; +} + static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != (typeof(skb->mac_header))~0U; @@ -2676,7 +2709,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); * @offset: the offset within the fragment (starting at the * fragment's own offset) * @size: the number of bytes to map - * @dir: the direction of the mapping (%PCI_DMA_*) + * @dir: the direction of the mapping (``PCI_DMA_*``) * * Maps the page associated with @frag to @device. */ @@ -2937,7 +2970,7 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb, __skb_postpush_rcsum(skb, start, len, 0); } -unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); +void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); /** * skb_push_rcsum - push skb and update receive checksum @@ -2950,8 +2983,7 @@ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ -static inline unsigned char *skb_push_rcsum(struct sk_buff *skb, - unsigned int len) +static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) { skb_push(skb, len); skb_postpush_rcsum(skb, skb->data, len); @@ -3041,6 +3073,13 @@ static inline void skb_frag_list_init(struct sk_buff *skb) int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, const struct sk_buff *skb); +struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, + struct sk_buff_head *queue, + unsigned int flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb), + int *peeked, int *off, int *err, + struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), @@ -3101,7 +3140,7 @@ struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { - return copy_from_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; + return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) @@ -3114,6 +3153,8 @@ struct skb_checksum_ops { __wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len); }; +extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly; + __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, @@ -3283,13 +3324,6 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps); -static inline void sw_tx_timestamp(struct sk_buff *skb) -{ - if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP && - !(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) - skb_tstamp_tx(skb, NULL); -} - /** * skb_tx_timestamp() - Driver hook for transmit timestamping * @@ -3305,7 +3339,8 @@ static inline void sw_tx_timestamp(struct sk_buff *skb) static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); - sw_tx_timestamp(skb); + if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP) + skb_tstamp_tx(skb, NULL); } /** @@ -3371,21 +3406,6 @@ static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) } } -static inline void __skb_mark_checksum_bad(struct sk_buff *skb) -{ - /* Mark current checksum as bad (typically called from GRO - * path). In the case that ip_summed is CHECKSUM_NONE - * this must be the first checksum encountered in the packet. - * When ip_summed is CHECKSUM_UNNECESSARY, this is the first - * checksum after the last one validated. For UDP, a zero - * checksum can not be marked as bad. - */ - - if (skb->ip_summed == CHECKSUM_NONE || - skb->ip_summed == CHECKSUM_UNNECESSARY) - skb->csum_bad = 1; -} - /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise @@ -3439,9 +3459,6 @@ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, skb->csum_valid = 1; return 0; } - } else if (skb->csum_bad) { - /* ip_summed == CHECKSUM_NONE in this case */ - return (__force __sum16)1; } skb->csum = psum; @@ -3501,8 +3518,7 @@ static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) static inline bool __skb_checksum_convert_check(struct sk_buff *skb) { - return (skb->ip_summed == CHECKSUM_NONE && - skb->csum_valid && !skb->csum_bad); + return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } static inline void __skb_checksum_convert(struct sk_buff *skb, @@ -3553,6 +3569,15 @@ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, skb->csum = csum_add(skb->csum, delta); } +static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + return (void *)(skb->_nfct & SKB_NFCT_PTRMASK); +#else + return NULL; +#endif +} + #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) void nf_conntrack_destroy(struct nf_conntrack *nfct); static inline void nf_conntrack_put(struct nf_conntrack *nfct) @@ -3569,20 +3594,20 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct) #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge) { - if (nf_bridge && atomic_dec_and_test(&nf_bridge->use)) + if (nf_bridge && refcount_dec_and_test(&nf_bridge->use)) kfree(nf_bridge); } static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge) { if (nf_bridge) - atomic_inc(&nf_bridge->use); + refcount_inc(&nf_bridge->use); } #endif /* CONFIG_BRIDGE_NETFILTER */ static inline void nf_reset(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - nf_conntrack_put(skb->nfct); - skb->nfct = NULL; + nf_conntrack_put(skb_nfct(skb)); + skb->_nfct = 0; #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nf_bridge_put(skb->nf_bridge); @@ -3602,10 +3627,8 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - dst->nfct = src->nfct; - nf_conntrack_get(src->nfct); - if (copy) - dst->nfctinfo = src->nfctinfo; + dst->_nfct = src->_nfct; + nf_conntrack_get(skb_nfct(src)); #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) dst->nf_bridge = src->nf_bridge; @@ -3620,7 +3643,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - nf_conntrack_put(dst->nfct); + nf_conntrack_put(skb_nfct(dst)); #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nf_bridge_put(dst->nf_bridge); @@ -3652,9 +3675,7 @@ static inline bool skb_irq_freeable(const struct sk_buff *skb) #if IS_ENABLED(CONFIG_XFRM) !skb->sp && #endif -#if IS_ENABLED(CONFIG_NF_CONNTRACK) - !skb->nfct && -#endif + !skb_nfct(skb) && !skb->_skb_refdst && !skb_has_frag_list(skb); } @@ -3689,6 +3710,16 @@ static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) return skb->queue_mapping != 0; } +static inline void skb_set_dst_pending_confirm(struct sk_buff *skb, u32 val) +{ + skb->dst_pending_confirm = val; +} + +static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb) +{ + return skb->dst_pending_confirm != 0; +} + static inline struct sec_path *skb_sec_path(struct sk_buff *skb) { #ifdef CONFIG_XFRM diff --git a/include/linux/slab.h b/include/linux/slab.h index 4c5363566815..41473df6dfb0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -28,7 +28,7 @@ #define SLAB_STORE_USER 0x00010000UL /* DEBUG: Store the last owner for bug hunting */ #define SLAB_PANIC 0x00040000UL /* Panic if kmem_cache_create() fails */ /* - * SLAB_DESTROY_BY_RCU - **WARNING** READ THIS! + * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() @@ -61,8 +61,10 @@ * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. + * + * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ -#define SLAB_DESTROY_BY_RCU 0x00080000UL /* Defer freeing slabs to RCU */ +#define SLAB_TYPESAFE_BY_RCU 0x00080000UL /* Defer freeing slabs to RCU */ #define SLAB_MEM_SPREAD 0x00100000UL /* Spread some memory over cpuset */ #define SLAB_TRACE 0x00200000UL /* Trace allocations and frees */ @@ -469,7 +471,8 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * * %__GFP_NOWARN - If allocation fails, don't issue any warnings. * - * %__GFP_REPEAT - If allocation fails initially, try once more before failing. + * %__GFP_RETRY_MAYFAIL - Try really hard to succeed the allocation but fail + * eventually. * * There are other flags available as well, but these are not intended * for general use, and so are not documented here. For a full list of @@ -545,22 +548,49 @@ struct memcg_cache_array { * array to be accessed without taking any locks, on relocation we free the old * version only after a grace period. * - * Child caches will hold extra metadata needed for its operation. Fields are: + * Root and child caches hold different metadata. + * + * @root_cache: Common to root and child caches. NULL for root, pointer to + * the root cache for children. + * + * The following fields are specific to root caches. + * + * @memcg_caches: kmemcg ID indexed table of child caches. This table is + * used to index child cachces during allocation and cleared + * early during shutdown. + * + * @root_caches_node: List node for slab_root_caches list. * - * @memcg: pointer to the memcg this cache belongs to - * @root_cache: pointer to the global, root cache, this cache was derived from + * @children: List of all child caches. While the child caches are also + * reachable through @memcg_caches, a child cache remains on + * this list until it is actually destroyed. * - * Both root and child caches of the same kind are linked into a list chained - * through @list. + * The following fields are specific to child caches. + * + * @memcg: Pointer to the memcg this cache belongs to. + * + * @children_node: List node for @root_cache->children list. + * + * @kmem_caches_node: List node for @memcg->kmem_caches list. */ struct memcg_cache_params { - bool is_root_cache; - struct list_head list; + struct kmem_cache *root_cache; union { - struct memcg_cache_array __rcu *memcg_caches; + struct { + struct memcg_cache_array __rcu *memcg_caches; + struct list_head __root_caches_node; + struct list_head children; + }; struct { struct mem_cgroup *memcg; - struct kmem_cache *root_cache; + struct list_head children_node; + struct list_head kmem_caches_node; + + void (*deact_fn)(struct kmem_cache *); + union { + struct rcu_head deact_rcu_head; + struct work_struct deact_work; + }; }; }; }; diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 75f56c2ef2d4..cc0faf3a90be 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -41,12 +41,31 @@ struct kmem_cache_cpu { void **freelist; /* Pointer to next available object */ unsigned long tid; /* Globally unique transaction id */ struct page *page; /* The slab from which we are allocating */ +#ifdef CONFIG_SLUB_CPU_PARTIAL struct page *partial; /* Partially allocated frozen slabs */ +#endif #ifdef CONFIG_SLUB_STATS unsigned stat[NR_SLUB_STAT_ITEMS]; #endif }; +#ifdef CONFIG_SLUB_CPU_PARTIAL +#define slub_percpu_partial(c) ((c)->partial) + +#define slub_set_percpu_partial(c, p) \ +({ \ + slub_percpu_partial(c) = (p)->next; \ +}) + +#define slub_percpu_partial_read_once(c) READ_ONCE(slub_percpu_partial(c)) +#else +#define slub_percpu_partial(c) NULL + +#define slub_set_percpu_partial(c, p) + +#define slub_percpu_partial_read_once(c) NULL +#endif // CONFIG_SLUB_CPU_PARTIAL + /* * Word size structure that can be atomically updated or read and that * contains both the order and the number of objects that a slab of the @@ -67,7 +86,9 @@ struct kmem_cache { int size; /* The size of an object including meta data */ int object_size; /* The size of an object without meta data */ int offset; /* Free pointer offset. */ +#ifdef CONFIG_SLUB_CPU_PARTIAL int cpu_partial; /* Number of per cpu partial objects to keep around */ +#endif struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ @@ -79,11 +100,12 @@ struct kmem_cache { int inuse; /* Offset to metadata */ int align; /* Alignment */ int reserved; /* Reserved bytes at the end of slabs */ + int red_left_pad; /* Left redzone padding size */ const char *name; /* Name (only for display!) */ struct list_head list; /* List of slab caches */ - int red_left_pad; /* Left redzone padding size */ #ifdef CONFIG_SYSFS struct kobject kobj; /* For sysfs */ + struct work_struct kobj_remove_work; #endif #ifdef CONFIG_MEMCG struct memcg_cache_params memcg_params; @@ -111,11 +133,22 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; +#ifdef CONFIG_SLUB_CPU_PARTIAL +#define slub_cpu_partial(s) ((s)->cpu_partial) +#define slub_set_cpu_partial(s, n) \ +({ \ + slub_cpu_partial(s) = (n); \ +}) +#else +#define slub_cpu_partial(s) (0) +#define slub_set_cpu_partial(s, n) +#endif // CONFIG_SLUB_CPU_PARTIAL + #ifdef CONFIG_SYSFS #define SLAB_SUPPORTS_SYSFS -void sysfs_slab_remove(struct kmem_cache *); +void sysfs_slab_release(struct kmem_cache *); #else -static inline void sysfs_slab_remove(struct kmem_cache *s) +static inline void sysfs_slab_release(struct kmem_cache *s) { } #endif diff --git a/include/linux/smp.h b/include/linux/smp.h index 8e0cb7a0f836..68123c1fe549 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -120,6 +120,13 @@ extern unsigned int setup_max_cpus; extern void __init setup_nr_cpu_ids(void); extern void __init smp_init(void); +extern int __boot_cpu_id; + +static inline int get_boot_cpu_id(void) +{ + return __boot_cpu_id; +} + #else /* !SMP */ static inline void smp_send_stop(void) { } @@ -158,6 +165,11 @@ static inline void smp_init(void) { up_late_init(); } static inline void smp_init(void) { } #endif +static inline int get_boot_cpu_id(void) +{ + return 0; +} + #endif /* !SMP */ /* diff --git a/include/linux/soc/actions/owl-sps.h b/include/linux/soc/actions/owl-sps.h new file mode 100644 index 000000000000..33d0dbeceb55 --- /dev/null +++ b/include/linux/soc/actions/owl-sps.h @@ -0,0 +1,11 @@ +/* + * Copyright (c) 2017 Andreas Färber + * + * SPDX-License-Identifier: GPL-2.0+ + */ +#ifndef SOC_ACTIONS_OWL_SPS_H +#define SOC_ACTIONS_OWL_SPS_H + +int owl_sps_set_pg(void __iomem *base, u32 pwr_mask, u32 ack_mask, bool enable); + +#endif diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h new file mode 100644 index 000000000000..f423001db3a9 --- /dev/null +++ b/include/linux/soc/qcom/mdt_loader.h @@ -0,0 +1,18 @@ +#ifndef __QCOM_MDT_LOADER_H__ +#define __QCOM_MDT_LOADER_H__ + +#include <linux/types.h> + +#define QCOM_MDT_TYPE_MASK (7 << 24) +#define QCOM_MDT_TYPE_HASH (2 << 24) +#define QCOM_MDT_RELOCATABLE BIT(27) + +struct device; +struct firmware; + +ssize_t qcom_mdt_get_size(const struct firmware *fw); +int qcom_mdt_load(struct device *dev, const struct firmware *fw, + const char *fw_name, int pas_id, void *mem_region, + phys_addr_t mem_phys, size_t mem_size); + +#endif diff --git a/include/linux/soc/qcom/smd.h b/include/linux/soc/qcom/smd.h deleted file mode 100644 index f148e0ffbec7..000000000000 --- a/include/linux/soc/qcom/smd.h +++ /dev/null @@ -1,139 +0,0 @@ -#ifndef __QCOM_SMD_H__ -#define __QCOM_SMD_H__ - -#include <linux/device.h> -#include <linux/mod_devicetable.h> - -struct qcom_smd; -struct qcom_smd_channel; -struct qcom_smd_lookup; - -/** - * struct qcom_smd_id - struct used for matching a smd device - * @name: name of the channel - */ -struct qcom_smd_id { - char name[20]; -}; - -/** - * struct qcom_smd_device - smd device struct - * @dev: the device struct - * @channel: handle to the smd channel for this device - */ -struct qcom_smd_device { - struct device dev; - struct qcom_smd_channel *channel; -}; - -typedef int (*qcom_smd_cb_t)(struct qcom_smd_channel *, const void *, size_t); - -/** - * struct qcom_smd_driver - smd driver struct - * @driver: underlying device driver - * @smd_match_table: static channel match table - * @probe: invoked when the smd channel is found - * @remove: invoked when the smd channel is closed - * @callback: invoked when an inbound message is received on the channel, - * should return 0 on success or -EBUSY if the data cannot be - * consumed at this time - */ -struct qcom_smd_driver { - struct device_driver driver; - const struct qcom_smd_id *smd_match_table; - - int (*probe)(struct qcom_smd_device *dev); - void (*remove)(struct qcom_smd_device *dev); - qcom_smd_cb_t callback; -}; - -#if IS_ENABLED(CONFIG_QCOM_SMD) - -int qcom_smd_driver_register(struct qcom_smd_driver *drv); -void qcom_smd_driver_unregister(struct qcom_smd_driver *drv); - -struct qcom_smd_channel *qcom_smd_open_channel(struct qcom_smd_channel *channel, - const char *name, - qcom_smd_cb_t cb); -void qcom_smd_close_channel(struct qcom_smd_channel *channel); -void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel); -void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data); -int qcom_smd_send(struct qcom_smd_channel *channel, const void *data, int len); - - -struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent, - struct device_node *node); -int qcom_smd_unregister_edge(struct qcom_smd_edge *edge); - -#else - -static inline int qcom_smd_driver_register(struct qcom_smd_driver *drv) -{ - return -ENXIO; -} - -static inline void qcom_smd_driver_unregister(struct qcom_smd_driver *drv) -{ - /* This shouldn't be possible */ - WARN_ON(1); -} - -static inline struct qcom_smd_channel * -qcom_smd_open_channel(struct qcom_smd_channel *channel, - const char *name, - qcom_smd_cb_t cb) -{ - /* This shouldn't be possible */ - WARN_ON(1); - return NULL; -} - -static inline void qcom_smd_close_channel(struct qcom_smd_channel *channel) -{ - /* This shouldn't be possible */ - WARN_ON(1); -} - -static inline void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel) -{ - /* This shouldn't be possible */ - WARN_ON(1); - return NULL; -} - -static inline void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data) -{ - /* This shouldn't be possible */ - WARN_ON(1); -} - -static inline int qcom_smd_send(struct qcom_smd_channel *channel, - const void *data, int len) -{ - /* This shouldn't be possible */ - WARN_ON(1); - return -ENXIO; -} - -static inline struct qcom_smd_edge * -qcom_smd_register_edge(struct device *parent, - struct device_node *node) -{ - return ERR_PTR(-ENXIO); -} - -static inline int qcom_smd_unregister_edge(struct qcom_smd_edge *edge) -{ - /* This shouldn't be possible */ - WARN_ON(1); - return -ENXIO; -} - -#endif - -#define module_qcom_smd_driver(__smd_driver) \ - module_driver(__smd_driver, qcom_smd_driver_register, \ - qcom_smd_driver_unregister) - - -#endif diff --git a/include/linux/soc/qcom/smem_state.h b/include/linux/soc/qcom/smem_state.h index 7b88697929e9..b8478ee7a71f 100644 --- a/include/linux/soc/qcom/smem_state.h +++ b/include/linux/soc/qcom/smem_state.h @@ -1,7 +1,7 @@ #ifndef __QCOM_SMEM_STATE__ #define __QCOM_SMEM_STATE__ -#include <linux/errno.h> +#include <linux/err.h> struct device_node; struct qcom_smem_state; diff --git a/include/linux/soc/qcom/wcnss_ctrl.h b/include/linux/soc/qcom/wcnss_ctrl.h index eab64976a73b..a4dd4d7c711d 100644 --- a/include/linux/soc/qcom/wcnss_ctrl.h +++ b/include/linux/soc/qcom/wcnss_ctrl.h @@ -1,16 +1,19 @@ #ifndef __WCNSS_CTRL_H__ #define __WCNSS_CTRL_H__ -#include <linux/soc/qcom/smd.h> +#include <linux/rpmsg.h> #if IS_ENABLED(CONFIG_QCOM_WCNSS_CTRL) -struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb); +struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss, const char *name, + rpmsg_rx_cb_t cb, void *priv); #else -static inline struct qcom_smd_channel* -qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb) +static struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss, + const char *name, + rpmsg_rx_cb_t cb, + void *priv) { WARN_ON(1); return ERR_PTR(-ENXIO); diff --git a/include/linux/soc/renesas/rcar-rst.h b/include/linux/soc/renesas/rcar-rst.h index a18e0783946b..2c231f2280a6 100644 --- a/include/linux/soc/renesas/rcar-rst.h +++ b/include/linux/soc/renesas/rcar-rst.h @@ -1,6 +1,10 @@ #ifndef __LINUX_SOC_RENESAS_RCAR_RST_H__ #define __LINUX_SOC_RENESAS_RCAR_RST_H__ +#ifdef CONFIG_RST_RCAR int rcar_rst_read_mode_pins(u32 *mode); +#else +static inline int rcar_rst_read_mode_pins(u32 *mode) { return -ENODEV; } +#endif #endif /* __LINUX_SOC_RENESAS_RCAR_RST_H__ */ diff --git a/include/linux/soc/samsung/exynos-pmu.h b/include/linux/soc/samsung/exynos-pmu.h index e2e9de1acc5b..e57eb4b6cc5a 100644 --- a/include/linux/soc/samsung/exynos-pmu.h +++ b/include/linux/soc/samsung/exynos-pmu.h @@ -12,6 +12,8 @@ #ifndef __LINUX_SOC_EXYNOS_PMU_H #define __LINUX_SOC_EXYNOS_PMU_H +struct regmap; + enum sys_powerdown { SYS_AFTR, SYS_LPA, @@ -20,5 +22,13 @@ enum sys_powerdown { }; extern void exynos_sys_powerdown_conf(enum sys_powerdown mode); +#ifdef CONFIG_EXYNOS_PMU +extern struct regmap *exynos_get_pmu_regmap(void); +#else +static inline struct regmap *exynos_get_pmu_regmap(void) +{ + return ERR_PTR(-ENODEV); +} +#endif #endif /* __LINUX_SOC_EXYNOS_PMU_H */ diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index d30186e2b609..bebdde5dccd6 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2010-2012 Samsung Electronics Co., Ltd. + * Copyright (c) 2010-2015 Samsung Electronics Co., Ltd. * http://www.samsung.com * * EXYNOS - Power management unit definition @@ -7,7 +7,13 @@ * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. -*/ + * + * + * Notice: + * This is not a list of all Exynos Power Management Unit SFRs. + * There are too many of them, not mentioning subtle differences + * between SoCs. For now, put here only the used registers. + */ #ifndef __LINUX_SOC_EXYNOS_REGS_PMU_H #define __LINUX_SOC_EXYNOS_REGS_PMU_H __FILE__ @@ -38,13 +44,20 @@ #define EXYNOS_CORE_PO_RESET(n) ((1 << 4) << n) #define EXYNOS_WAKEUP_FROM_LOWPWR (1 << 28) #define EXYNOS_SWRESET 0x0400 -#define EXYNOS5440_SWRESET 0x00C4 #define S5P_WAKEUP_STAT 0x0600 #define S5P_EINT_WAKEUP_MASK 0x0604 #define S5P_WAKEUP_MASK 0x0608 #define S5P_WAKEUP_MASK2 0x0614 +/* MIPI_PHYn_CONTROL, valid for Exynos3250, Exynos4, Exynos5250 and Exynos5433 */ +#define EXYNOS4_MIPI_PHY_CONTROL(n) (0x0710 + (n) * 4) +/* Phy enable bit, common for all phy registers, not only MIPI */ +#define EXYNOS4_PHY_ENABLE (1 << 0) +#define EXYNOS4_MIPI_PHY_SRESETN (1 << 1) +#define EXYNOS4_MIPI_PHY_MRESETN (1 << 2) +#define EXYNOS4_MIPI_PHY_RESET_MASK (3 << 1) + #define S5P_INFORM0 0x0800 #define S5P_INFORM1 0x0804 #define S5P_INFORM5 0x0814 @@ -136,12 +149,6 @@ #define EXYNOS_COMMON_OPTION(_nr) \ (EXYNOS_COMMON_CONFIGURATION(_nr) + 0x8) -#define EXYNOS_CORE_LOCAL_PWR_EN 0x3 - -#define EXYNOS_ARM_COMMON_STATUS 0x2504 -#define EXYNOS_COMMON_OPTION(_nr) \ - (EXYNOS_COMMON_CONFIGURATION(_nr) + 0x8) - #define EXYNOS_ARM_L2_CONFIGURATION 0x2600 #define EXYNOS_L2_CONFIGURATION(_nr) \ (EXYNOS_ARM_L2_CONFIGURATION + ((_nr) * 0x80)) @@ -149,17 +156,8 @@ (EXYNOS_L2_CONFIGURATION(_nr) + 0x4) #define EXYNOS_L2_OPTION(_nr) \ (EXYNOS_L2_CONFIGURATION(_nr) + 0x8) -#define EXYNOS_L2_COMMON_PWR_EN 0x3 -#define EXYNOS_ARM_CORE_X_STATUS_OFFSET 0x4 - -#define EXYNOS5_APLL_SYSCLK_CONFIGURATION 0x2A00 -#define EXYNOS5_APLL_SYSCLK_STATUS 0x2A04 - -#define EXYNOS5_ARM_L2_OPTION 0x2608 -#define EXYNOS5_USE_RETENTION BIT(4) - -#define EXYNOS5_L2RSTDISABLE_VALUE BIT(3) +#define EXYNOS_L2_USE_RETENTION BIT(4) #define S5P_PAD_RET_MAUDIO_OPTION 0x3028 #define S5P_PAD_RET_MMC2_OPTION 0x30c8 @@ -352,6 +350,8 @@ #define EXYNOS5_AUTO_WDTRESET_DISABLE 0x0408 #define EXYNOS5_MASK_WDTRESET_REQUEST 0x040C +#define EXYNOS5_USBDRD_PHY_CONTROL 0x0704 +#define EXYNOS5_DPTX_PHY_CONTROL 0x0720 #define EXYNOS5_USE_RETENTION BIT(4) #define EXYNOS5_SYS_WDTRESET (1 << 20) @@ -411,7 +411,6 @@ #define EXYNOS5_SATA_MEM_SYS_PWR_REG 0x11FC #define EXYNOS5_PAD_RETENTION_DRAM_SYS_PWR_REG 0x1200 #define EXYNOS5_PAD_RETENTION_MAU_SYS_PWR_REG 0x1204 -#define EXYNOS5_PAD_RETENTION_EFNAND_SYS_PWR_REG 0x1208 #define EXYNOS5_PAD_RETENTION_GPIO_SYS_PWR_REG 0x1220 #define EXYNOS5_PAD_RETENTION_UART_SYS_PWR_REG 0x1224 #define EXYNOS5_PAD_RETENTION_MMCA_SYS_PWR_REG 0x1228 @@ -485,7 +484,6 @@ #define EXYNOS5420_SWRESET_KFC_SEL 0x3 /* Only for EXYNOS5420 */ -#define EXYNOS5420_ISP_ARM_OPTION 0x2488 #define EXYNOS5420_L2RSTDISABLE_VALUE BIT(3) #define EXYNOS5420_LPI_MASK 0x0004 @@ -494,9 +492,6 @@ #define EXYNOS5420_ATB_KFC BIT(13) #define EXYNOS5420_ATB_ISP_ARM BIT(19) #define EXYNOS5420_EMULATION BIT(31) -#define ATB_ISP_ARM BIT(12) -#define ATB_KFC BIT(13) -#define ATB_NOC BIT(14) #define EXYNOS5420_ARM_INTR_SPREAD_ENABLE 0x0100 #define EXYNOS5420_ARM_INTR_SPREAD_USE_STANDBYWFI 0x0104 @@ -510,11 +505,9 @@ #define EXYNOS5420_KFC_CORE_RESET(_nr) \ ((EXYNOS5420_KFC_CORE_RESET0 | EXYNOS5420_KFC_ETM_RESET0) << (_nr)) -#define EXYNOS5420_BB_CON1 0x0784 -#define EXYNOS5420_BB_SEL_EN BIT(31) -#define EXYNOS5420_BB_PMOS_EN BIT(7) -#define EXYNOS5420_BB_1300X 0XF - +#define EXYNOS5420_USBDRD1_PHY_CONTROL 0x0708 +#define EXYNOS5420_MIPI_PHY_CONTROL(n) (0x0714 + (n) * 4) +#define EXYNOS5420_DPTX_PHY_CONTROL 0x0728 #define EXYNOS5420_ARM_CORE2_SYS_PWR_REG 0x1020 #define EXYNOS5420_DIS_IRQ_ARM_CORE2_LOCAL_SYS_PWR_REG 0x1024 #define EXYNOS5420_DIS_IRQ_ARM_CORE2_CENTRAL_SYS_PWR_REG 0x1028 @@ -546,15 +539,6 @@ #define EXYNOS5420_SPLL_SYSCLK_SYS_PWR_REG 0x1178 #define EXYNOS5420_INTRAM_MEM_SYS_PWR_REG 0x11B8 #define EXYNOS5420_INTROM_MEM_SYS_PWR_REG 0x11BC -#define EXYNOS5420_ONENANDXL_MEM_SYS_PWR 0x11C0 -#define EXYNOS5420_USBDEV_MEM_SYS_PWR 0x11CC -#define EXYNOS5420_USBDEV1_MEM_SYS_PWR 0x11D0 -#define EXYNOS5420_SDMMC_MEM_SYS_PWR 0x11D4 -#define EXYNOS5420_CSSYS_MEM_SYS_PWR 0x11D8 -#define EXYNOS5420_SECSS_MEM_SYS_PWR 0x11DC -#define EXYNOS5420_ROTATOR_MEM_SYS_PWR 0x11E0 -#define EXYNOS5420_INTRAM_MEM_SYS_PWR 0x11E4 -#define EXYNOS5420_INTROM_MEM_SYS_PWR 0x11E8 #define EXYNOS5420_PAD_RETENTION_JTAG_SYS_PWR_REG 0x1208 #define EXYNOS5420_PAD_RETENTION_DRAM_SYS_PWR_REG 0x1210 #define EXYNOS5420_PAD_RETENTION_UART_SYS_PWR_REG 0x1214 @@ -605,13 +589,7 @@ #define EXYNOS5420_CMU_RESET_MSC_SYS_PWR_REG 0x159C #define EXYNOS5420_CMU_RESET_FSYS_SYS_PWR_REG 0x15A0 #define EXYNOS5420_SFR_AXI_CGDIS1 0x15E4 -#define EXYNOS_ARM_CORE2_CONFIGURATION 0x2100 -#define EXYNOS5420_ARM_CORE2_OPTION 0x2108 -#define EXYNOS_ARM_CORE3_CONFIGURATION 0x2180 -#define EXYNOS5420_ARM_CORE3_OPTION 0x2188 -#define EXYNOS5420_ARM_COMMON_STATUS 0x2504 #define EXYNOS5420_ARM_COMMON_OPTION 0x2508 -#define EXYNOS5420_KFC_COMMON_STATUS 0x2584 #define EXYNOS5420_KFC_COMMON_OPTION 0x2588 #define EXYNOS5420_LOGIC_RESET_DURATION3 0x2D1C @@ -626,33 +604,9 @@ #define EXYNOS_PAD_RET_DRAM_OPTION 0x3008 #define EXYNOS_PAD_RET_MAUDIO_OPTION 0x3028 #define EXYNOS_PAD_RET_JTAG_OPTION 0x3048 -#define EXYNOS_PAD_RET_GPIO_OPTION 0x3108 -#define EXYNOS_PAD_RET_UART_OPTION 0x3128 -#define EXYNOS_PAD_RET_MMCA_OPTION 0x3148 -#define EXYNOS_PAD_RET_MMCB_OPTION 0x3168 #define EXYNOS_PAD_RET_EBIA_OPTION 0x3188 #define EXYNOS_PAD_RET_EBIB_OPTION 0x31A8 -#define EXYNOS_PS_HOLD_CONTROL 0x330C - -/* For SYS_PWR_REG */ -#define EXYNOS_SYS_PWR_CFG BIT(0) - -#define EXYNOS5420_MFC_CONFIGURATION 0x4060 -#define EXYNOS5420_MFC_STATUS 0x4064 -#define EXYNOS5420_MFC_OPTION 0x4068 -#define EXYNOS5420_G3D_CONFIGURATION 0x4080 -#define EXYNOS5420_G3D_STATUS 0x4084 -#define EXYNOS5420_G3D_OPTION 0x4088 -#define EXYNOS5420_DISP0_CONFIGURATION 0x40A0 -#define EXYNOS5420_DISP0_STATUS 0x40A4 -#define EXYNOS5420_DISP0_OPTION 0x40A8 -#define EXYNOS5420_DISP1_CONFIGURATION 0x40C0 -#define EXYNOS5420_DISP1_STATUS 0x40C4 -#define EXYNOS5420_DISP1_OPTION 0x40C8 -#define EXYNOS5420_MAU_CONFIGURATION 0x40E0 -#define EXYNOS5420_MAU_STATUS 0x40E4 -#define EXYNOS5420_MAU_OPTION 0x40E8 #define EXYNOS5420_FSYS2_OPTION 0x4168 #define EXYNOS5420_PSGEN_OPTION 0x4188 @@ -690,4 +644,21 @@ | EXYNOS5420_KFC_USE_STANDBY_WFI2 \ | EXYNOS5420_KFC_USE_STANDBY_WFI3) +/* For EXYNOS5433 */ +#define EXYNOS5433_USBHOST30_PHY_CONTROL (0x0728) +#define EXYNOS5433_PAD_RETENTION_AUD_OPTION (0x3028) +#define EXYNOS5433_PAD_RETENTION_MMC2_OPTION (0x30C8) +#define EXYNOS5433_PAD_RETENTION_TOP_OPTION (0x3108) +#define EXYNOS5433_PAD_RETENTION_UART_OPTION (0x3128) +#define EXYNOS5433_PAD_RETENTION_MMC0_OPTION (0x3148) +#define EXYNOS5433_PAD_RETENTION_MMC1_OPTION (0x3168) +#define EXYNOS5433_PAD_RETENTION_EBIA_OPTION (0x3188) +#define EXYNOS5433_PAD_RETENTION_EBIB_OPTION (0x31A8) +#define EXYNOS5433_PAD_RETENTION_SPI_OPTION (0x31C8) +#define EXYNOS5433_PAD_RETENTION_MIF_OPTION (0x31E8) +#define EXYNOS5433_PAD_RETENTION_USBXTI_OPTION (0x3228) +#define EXYNOS5433_PAD_RETENTION_BOOTLDO_OPTION (0x3248) +#define EXYNOS5433_PAD_RETENTION_UFS_OPTION (0x3268) +#define EXYNOS5433_PAD_RETENTION_FSYSGENIO_OPTION (0x32A8) + #endif /* __LINUX_SOC_EXYNOS_REGS_PMU_H */ diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h index 35cb9264e0d5..2b7882666ef6 100644 --- a/include/linux/soc/ti/knav_dma.h +++ b/include/linux/soc/ti/knav_dma.h @@ -41,6 +41,8 @@ #define KNAV_DMA_DESC_RETQ_SHIFT 0 #define KNAV_DMA_DESC_RETQ_MASK MASK(14) #define KNAV_DMA_DESC_BUF_LEN_MASK MASK(22) +#define KNAV_DMA_DESC_EFLAGS_MASK MASK(4) +#define KNAV_DMA_DESC_EFLAGS_SHIFT 20 #define KNAV_DMA_NUM_EPIB_WORDS 4 #define KNAV_DMA_NUM_PS_WORDS 16 diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index a0596ca0e80a..a2f8109bb215 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -24,6 +24,7 @@ void sock_diag_unregister(const struct sock_diag_handler *h); void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); +u64 sock_gen_cookie(struct sock *sk); int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie); diff --git a/include/linux/socket.h b/include/linux/socket.h index b5cc5a6d7011..8b13db5163cc 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -92,9 +92,9 @@ struct cmsghdr { #define CMSG_ALIGN(len) ( ((len)+sizeof(long)-1) & ~(sizeof(long)-1) ) -#define CMSG_DATA(cmsg) ((void *)((char *)(cmsg) + CMSG_ALIGN(sizeof(struct cmsghdr)))) -#define CMSG_SPACE(len) (CMSG_ALIGN(sizeof(struct cmsghdr)) + CMSG_ALIGN(len)) -#define CMSG_LEN(len) (CMSG_ALIGN(sizeof(struct cmsghdr)) + (len)) +#define CMSG_DATA(cmsg) ((void *)((char *)(cmsg) + sizeof(struct cmsghdr))) +#define CMSG_SPACE(len) (sizeof(struct cmsghdr) + CMSG_ALIGN(len)) +#define CMSG_LEN(len) (sizeof(struct cmsghdr) + (len)) #define __CMSG_FIRSTHDR(ctl,len) ((len) >= sizeof(struct cmsghdr) ? \ (struct cmsghdr *)(ctl) : \ @@ -202,8 +202,12 @@ struct ucred { #define AF_VSOCK 40 /* vSockets */ #define AF_KCM 41 /* Kernel Connection Multiplexor*/ #define AF_QIPCRTR 42 /* Qualcomm IPC Router */ +#define AF_SMC 43 /* smc sockets: reserve number for + * PF_SMC protocol family that + * reuses AF_INET address family + */ -#define AF_MAX 43 /* For now.. */ +#define AF_MAX 44 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -251,6 +255,7 @@ struct ucred { #define PF_VSOCK AF_VSOCK #define PF_KCM AF_KCM #define PF_QIPCRTR AF_QIPCRTR +#define PF_SMC AF_SMC #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -329,6 +334,7 @@ struct ucred { #define SOL_ALG 279 #define SOL_NFC 280 #define SOL_KCM 281 +#define SOL_TLS 282 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/spi/flash.h b/include/linux/spi/flash.h index 3f22932e67a4..f4199e758f97 100644 --- a/include/linux/spi/flash.h +++ b/include/linux/spi/flash.h @@ -7,7 +7,7 @@ struct mtd_partition; * struct flash_platform_data: board-specific flash data * @name: optional flash device name (eg, as used with mtdparts=) * @parts: optional array of mtd_partitions for static partitioning - * @nr_parts: number of mtd_partitions for static partitoning + * @nr_parts: number of mtd_partitions for static partitioning * @type: optional flash device type (e.g. m25p80 vs m25p64), for use * with chips that can't be queried for JEDEC or other IDs * diff --git a/include/linux/spi/mcp23s08.h b/include/linux/spi/mcp23s08.h index aa07d7b32568..82d96a346e6f 100644 --- a/include/linux/spi/mcp23s08.h +++ b/include/linux/spi/mcp23s08.h @@ -1,11 +1,3 @@ - -/* FIXME driver should be able to handle IRQs... */ - -struct mcp23s08_chip_info { - bool is_present; /* true if populated */ - unsigned pullups; /* BIT(x) means enable pullup x */ -}; - struct mcp23s08_platform_data { /* For mcp23s08, up to 4 slaves (numbered 0..3) can share one SPI * chipselect, each providing 1 gpio_chip instance with 8 gpios. @@ -13,31 +5,13 @@ struct mcp23s08_platform_data { * chipselect, each providing 1 gpio_chip (port A + port B) with * 16 gpios. */ - struct mcp23s08_chip_info chip[8]; + u32 spi_present_mask; - /* "base" is the number of the first GPIO. Dynamic assignment is - * not currently supported, and even if there are gaps in chip - * addressing the GPIO numbers are sequential .. so for example - * if only slaves 0 and 3 are present, their GPIOs range from - * base to base+15 (or base+31 for s17 variant). + /* "base" is the number of the first GPIO or -1 for dynamic + * assignment. If there are gaps in chip addressing the GPIO + * numbers are sequential .. so for example if only slaves 0 + * and 3 are present, their GPIOs range from base to base+15 + * (or base+31 for s17 variant). */ unsigned base; - /* Marks the device as a interrupt controller. - * NOTE: The interrupt functionality is only supported for i2c - * versions of the chips. The spi chips can also do the interrupts, - * but this is not supported by the linux driver yet. - */ - bool irq_controller; - - /* Sets the mirror flag in the IOCON register. Devices - * with two interrupt outputs (these are the devices ending with 17 and - * those that have 16 IOs) have two IO banks: IO 0-7 form bank 1 and - * IO 8-15 are bank 2. These chips have two different interrupt outputs: - * One for bank 1 and another for bank 2. If irq-mirror is set, both - * interrupts are generated regardless of the bank that an input change - * occurred on. If it is not set, the interrupt are only generated for - * the bank they belong to. - * On devices with only one interrupt output this property is useless. - */ - bool mirror; }; diff --git a/include/linux/spi/sh_msiof.h b/include/linux/spi/sh_msiof.h index b087a85f5f72..f74b581f242f 100644 --- a/include/linux/spi/sh_msiof.h +++ b/include/linux/spi/sh_msiof.h @@ -1,10 +1,16 @@ #ifndef __SPI_SH_MSIOF_H__ #define __SPI_SH_MSIOF_H__ +enum { + MSIOF_SPI_MASTER, + MSIOF_SPI_SLAVE, +}; + struct sh_msiof_spi_info { int tx_fifo_override; int rx_fifo_override; u16 num_chipselect; + int mode; unsigned int dma_tx_id; unsigned int dma_rx_id; u32 dtdl; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 75c6bd0ac605..7b2170bfd6e7 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -23,13 +23,14 @@ #include <linux/scatterlist.h> struct dma_chan; -struct spi_master; +struct property_entry; +struct spi_controller; struct spi_transfer; struct spi_flash_read_message; /* - * INTERFACES between SPI master-side drivers and SPI infrastructure. - * (There's no SPI slave support for Linux yet...) + * INTERFACES between SPI master-side drivers and SPI slave protocol handlers, + * and SPI infrastructure. */ extern struct bus_type spi_bus_type; @@ -83,7 +84,7 @@ struct spi_statistics { void spi_statistics_add_transfer_stats(struct spi_statistics *stats, struct spi_transfer *xfer, - struct spi_master *master); + struct spi_controller *ctlr); #define SPI_STATISTICS_ADD_TO_FIELD(stats, field, count) \ do { \ @@ -97,13 +98,14 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, SPI_STATISTICS_ADD_TO_FIELD(stats, field, 1) /** - * struct spi_device - Master side proxy for an SPI slave device + * struct spi_device - Controller side proxy for an SPI slave device * @dev: Driver model representation of the device. - * @master: SPI controller used with the device. + * @controller: SPI controller used with the device. + * @master: Copy of controller, for backwards compatibility. * @max_speed_hz: Maximum clock rate to be used with this chip * (on this board); may be changed by the device's driver. * The spi_transfer.speed_hz can override this for each transfer. - * @chip_select: Chipselect, distinguishing chips handled by @master. + * @chip_select: Chipselect, distinguishing chips handled by @controller. * @mode: The spi mode defines how data is clocked out and in. * This may be changed by the device's driver. * The "active low" default for chipselect mode can be overridden @@ -139,7 +141,8 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, */ struct spi_device { struct device dev; - struct spi_master *master; + struct spi_controller *controller; + struct spi_controller *master; /* compatibility layer */ u32 max_speed_hz; u8 chip_select; u8 bits_per_word; @@ -197,7 +200,7 @@ static inline void spi_dev_put(struct spi_device *spi) put_device(&spi->dev); } -/* ctldata is for the bus_master driver's runtime state */ +/* ctldata is for the bus_controller driver's runtime state */ static inline void *spi_get_ctldata(struct spi_device *spi) { return spi->controller_state; @@ -291,9 +294,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) spi_unregister_driver) /** - * struct spi_master - interface to SPI master controller + * struct spi_controller - interface to SPI master or slave controller * @dev: device interface to this driver - * @list: link with the global spi_master list + * @list: link with the global spi_controller list * @bus_num: board-specific (and often SOC-specific) identifier for a * given SPI controller. * @num_chipselect: chipselects are used to distinguish individual @@ -310,6 +313,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @min_speed_hz: Lowest supported transfer speed * @max_speed_hz: Highest supported transfer speed * @flags: other constraints relevant to this driver + * @slave: indicates that this is an SPI slave controller * @max_transfer_size: function that returns the max transfer size for * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. * @max_message_size: function that returns the max message size for @@ -325,8 +329,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * the device whose settings are being modified. * @transfer: adds a message to the controller's transfer queue. * @cleanup: frees controller-specific state - * @can_dma: determine whether this master supports DMA - * @queued: whether this master is providing an internal message queue + * @can_dma: determine whether this controller supports DMA + * @queued: whether this controller is providing an internal message queue * @kworker: thread struct for message pump * @kworker_task: pointer to task for message pump kworker thread * @pump_messages: work struct for scheduling work to the message pump @@ -373,13 +377,16 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @handle_err: the subsystem calls the driver to handle an error that occurs * in the generic implementation of transfer_one_message(). * @unprepare_message: undo any work done by prepare_message(). + * @slave_abort: abort the ongoing transfer request on an SPI slave controller * @spi_flash_read: to support spi-controller hardwares that provide * accelerated interface to read from flash devices. + * @spi_flash_can_dma: analogous to can_dma() interface, but for + * controllers implementing spi_flash_read. * @flash_read_supported: spi device supports flash read * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS * number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). - * @statistics: statistics for the spi_master + * @statistics: statistics for the spi_controller * @dma_tx: DMA transmit channel * @dma_rx: DMA receive channel * @dummy_rx: dummy receive buffer for full-duplex devices @@ -388,7 +395,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * what Linux expects, this optional hook can be used to translate * between the two. * - * Each SPI master controller can communicate with one or more @spi_device + * Each SPI controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals * but not chip select signals. Each device may be configured to use a * different clock rate, since those shared signals are ignored unless @@ -399,7 +406,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * an SPI slave device. For each such message it queues, it calls the * message's completion function when the transaction completes. */ -struct spi_master { +struct spi_controller { struct device dev; struct list_head list; @@ -437,12 +444,16 @@ struct spi_master { /* other constraints relevant to this driver */ u16 flags; -#define SPI_MASTER_HALF_DUPLEX BIT(0) /* can't do full duplex */ -#define SPI_MASTER_NO_RX BIT(1) /* can't do buffer read */ -#define SPI_MASTER_NO_TX BIT(2) /* can't do buffer write */ -#define SPI_MASTER_MUST_RX BIT(3) /* requires rx */ -#define SPI_MASTER_MUST_TX BIT(4) /* requires tx */ -#define SPI_MASTER_GPIO_SS BIT(5) /* GPIO CS must select slave */ +#define SPI_CONTROLLER_HALF_DUPLEX BIT(0) /* can't do full duplex */ +#define SPI_CONTROLLER_NO_RX BIT(1) /* can't do buffer read */ +#define SPI_CONTROLLER_NO_TX BIT(2) /* can't do buffer write */ +#define SPI_CONTROLLER_MUST_RX BIT(3) /* requires rx */ +#define SPI_CONTROLLER_MUST_TX BIT(4) /* requires tx */ + +#define SPI_MASTER_GPIO_SS BIT(5) /* GPIO CS must select slave */ + + /* flag indicating this is an SPI slave controller */ + bool slave; /* * on some hardware transfer / message size may be constrained @@ -477,8 +488,8 @@ struct spi_master { * any other request management * + To a given spi_device, message queueing is pure fifo * - * + The master's main job is to process its message queue, - * selecting a chip then transferring data + * + The controller's main job is to process its message queue, + * selecting a chip (for masters), then transferring data * + If there are multiple spi_device children, the i/o queue * arbitration algorithm is unspecified (round robin, fifo, * priority, reservations, preemption, etc) @@ -491,7 +502,7 @@ struct spi_master { int (*transfer)(struct spi_device *spi, struct spi_message *mesg); - /* called on release() to free memory provided by spi_master */ + /* called on release() to free memory provided by spi_controller */ void (*cleanup)(struct spi_device *spi); /* @@ -501,13 +512,13 @@ struct spi_master { * not modify or store xfer and dma_tx and dma_rx must be set * while the device is prepared. */ - bool (*can_dma)(struct spi_master *master, + bool (*can_dma)(struct spi_controller *ctlr, struct spi_device *spi, struct spi_transfer *xfer); /* * These hooks are for drivers that want to use the generic - * master transfer queueing mechanism. If these are used, the + * controller transfer queueing mechanism. If these are used, the * transfer() function above must NOT be specified by the driver. * Over time we expect SPI drivers to be phased over to this API. */ @@ -528,16 +539,19 @@ struct spi_master { struct completion xfer_completion; size_t max_dma_len; - int (*prepare_transfer_hardware)(struct spi_master *master); - int (*transfer_one_message)(struct spi_master *master, + int (*prepare_transfer_hardware)(struct spi_controller *ctlr); + int (*transfer_one_message)(struct spi_controller *ctlr, struct spi_message *mesg); - int (*unprepare_transfer_hardware)(struct spi_master *master); - int (*prepare_message)(struct spi_master *master, + int (*unprepare_transfer_hardware)(struct spi_controller *ctlr); + int (*prepare_message)(struct spi_controller *ctlr, struct spi_message *message); - int (*unprepare_message)(struct spi_master *master, + int (*unprepare_message)(struct spi_controller *ctlr, struct spi_message *message); + int (*slave_abort)(struct spi_controller *ctlr); int (*spi_flash_read)(struct spi_device *spi, struct spi_flash_read_message *msg); + bool (*spi_flash_can_dma)(struct spi_device *spi, + struct spi_flash_read_message *msg); bool (*flash_read_supported)(struct spi_device *spi); /* @@ -545,9 +559,9 @@ struct spi_master { * of transfer_one_message() provied by the core. */ void (*set_cs)(struct spi_device *spi, bool enable); - int (*transfer_one)(struct spi_master *master, struct spi_device *spi, + int (*transfer_one)(struct spi_controller *ctlr, struct spi_device *spi, struct spi_transfer *transfer); - void (*handle_err)(struct spi_master *master, + void (*handle_err)(struct spi_controller *ctlr, struct spi_message *message); /* gpio chip select */ @@ -564,57 +578,78 @@ struct spi_master { void *dummy_rx; void *dummy_tx; - int (*fw_translate_cs)(struct spi_master *master, unsigned cs); + int (*fw_translate_cs)(struct spi_controller *ctlr, unsigned cs); }; -static inline void *spi_master_get_devdata(struct spi_master *master) +static inline void *spi_controller_get_devdata(struct spi_controller *ctlr) { - return dev_get_drvdata(&master->dev); + return dev_get_drvdata(&ctlr->dev); } -static inline void spi_master_set_devdata(struct spi_master *master, void *data) +static inline void spi_controller_set_devdata(struct spi_controller *ctlr, + void *data) { - dev_set_drvdata(&master->dev, data); + dev_set_drvdata(&ctlr->dev, data); } -static inline struct spi_master *spi_master_get(struct spi_master *master) +static inline struct spi_controller *spi_controller_get(struct spi_controller *ctlr) { - if (!master || !get_device(&master->dev)) + if (!ctlr || !get_device(&ctlr->dev)) return NULL; - return master; + return ctlr; +} + +static inline void spi_controller_put(struct spi_controller *ctlr) +{ + if (ctlr) + put_device(&ctlr->dev); } -static inline void spi_master_put(struct spi_master *master) +static inline bool spi_controller_is_slave(struct spi_controller *ctlr) { - if (master) - put_device(&master->dev); + return IS_ENABLED(CONFIG_SPI_SLAVE) && ctlr->slave; } /* PM calls that need to be issued by the driver */ -extern int spi_master_suspend(struct spi_master *master); -extern int spi_master_resume(struct spi_master *master); +extern int spi_controller_suspend(struct spi_controller *ctlr); +extern int spi_controller_resume(struct spi_controller *ctlr); /* Calls the driver make to interact with the message queue */ -extern struct spi_message *spi_get_next_queued_message(struct spi_master *master); -extern void spi_finalize_current_message(struct spi_master *master); -extern void spi_finalize_current_transfer(struct spi_master *master); +extern struct spi_message *spi_get_next_queued_message(struct spi_controller *ctlr); +extern void spi_finalize_current_message(struct spi_controller *ctlr); +extern void spi_finalize_current_transfer(struct spi_controller *ctlr); -/* the spi driver core manages memory for the spi_master classdev */ -extern struct spi_master * -spi_alloc_master(struct device *host, unsigned size); +/* the spi driver core manages memory for the spi_controller classdev */ +extern struct spi_controller *__spi_alloc_controller(struct device *host, + unsigned int size, bool slave); -extern int spi_register_master(struct spi_master *master); -extern int devm_spi_register_master(struct device *dev, - struct spi_master *master); -extern void spi_unregister_master(struct spi_master *master); +static inline struct spi_controller *spi_alloc_master(struct device *host, + unsigned int size) +{ + return __spi_alloc_controller(host, size, false); +} -extern struct spi_master *spi_busnum_to_master(u16 busnum); +static inline struct spi_controller *spi_alloc_slave(struct device *host, + unsigned int size) +{ + if (!IS_ENABLED(CONFIG_SPI_SLAVE)) + return NULL; + + return __spi_alloc_controller(host, size, true); +} + +extern int spi_register_controller(struct spi_controller *ctlr); +extern int devm_spi_register_controller(struct device *dev, + struct spi_controller *ctlr); +extern void spi_unregister_controller(struct spi_controller *ctlr); + +extern struct spi_controller *spi_busnum_to_master(u16 busnum); /* * SPI resource management while processing a SPI message */ -typedef void (*spi_res_release_t)(struct spi_master *master, +typedef void (*spi_res_release_t)(struct spi_controller *ctlr, struct spi_message *msg, void *res); @@ -639,7 +674,7 @@ extern void *spi_res_alloc(struct spi_device *spi, extern void spi_res_add(struct spi_message *message, void *res); extern void spi_res_free(void *res); -extern void spi_res_release(struct spi_master *master, +extern void spi_res_release(struct spi_controller *ctlr, struct spi_message *message); /*---------------------------------------------------------------------------*/ @@ -823,7 +858,7 @@ struct spi_message { /* for optional use by whatever driver currently owns the * spi_message ... between calls to spi_async and then later - * complete(), that's the spi_master controller driver. + * complete(), that's the spi_controller controller driver. */ struct list_head queue; void *state; @@ -891,7 +926,7 @@ static inline struct spi_message *spi_message_alloc(unsigned ntrans, gfp_t flags unsigned i; struct spi_transfer *t = (struct spi_transfer *)(m + 1); - INIT_LIST_HEAD(&m->transfers); + spi_message_init_no_memset(m); for (i = 0; i < ntrans; i++, t++) spi_message_add_tail(t, m); } @@ -907,25 +942,27 @@ extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); extern int spi_async_locked(struct spi_device *spi, struct spi_message *message); +extern int spi_slave_abort(struct spi_device *spi); static inline size_t spi_max_message_size(struct spi_device *spi) { - struct spi_master *master = spi->master; - if (!master->max_message_size) + struct spi_controller *ctlr = spi->controller; + + if (!ctlr->max_message_size) return SIZE_MAX; - return master->max_message_size(spi); + return ctlr->max_message_size(spi); } static inline size_t spi_max_transfer_size(struct spi_device *spi) { - struct spi_master *master = spi->master; + struct spi_controller *ctlr = spi->controller; size_t tr_max = SIZE_MAX; size_t msg_max = spi_max_message_size(spi); - if (master->max_transfer_size) - tr_max = master->max_transfer_size(spi); + if (ctlr->max_transfer_size) + tr_max = ctlr->max_transfer_size(spi); /* transfer size limit must not be greater than messsage size limit */ return min(tr_max, msg_max); @@ -936,7 +973,7 @@ spi_max_transfer_size(struct spi_device *spi) /* SPI transfer replacement methods which make use of spi_res */ struct spi_replaced_transfers; -typedef void (*spi_replaced_release_t)(struct spi_master *master, +typedef void (*spi_replaced_release_t)(struct spi_controller *ctlr, struct spi_message *msg, struct spi_replaced_transfers *res); /** @@ -980,7 +1017,7 @@ extern struct spi_replaced_transfers *spi_replace_transfers( /* SPI transfer transformation methods */ -extern int spi_split_transfers_maxsize(struct spi_master *master, +extern int spi_split_transfers_maxsize(struct spi_controller *ctlr, struct spi_message *msg, size_t maxsize, gfp_t gfp); @@ -994,8 +1031,8 @@ extern int spi_split_transfers_maxsize(struct spi_master *master, extern int spi_sync(struct spi_device *spi, struct spi_message *message); extern int spi_sync_locked(struct spi_device *spi, struct spi_message *message); -extern int spi_bus_lock(struct spi_master *master); -extern int spi_bus_unlock(struct spi_master *master); +extern int spi_bus_lock(struct spi_controller *ctlr); +extern int spi_bus_unlock(struct spi_controller *ctlr); /** * spi_sync_transfer - synchronous SPI data transfer @@ -1180,9 +1217,9 @@ struct spi_flash_read_message { /* SPI core interface for flash read support */ static inline bool spi_flash_read_supported(struct spi_device *spi) { - return spi->master->spi_flash_read && - (!spi->master->flash_read_supported || - spi->master->flash_read_supported(spi)); + return spi->controller->spi_flash_read && + (!spi->controller->flash_read_supported || + spi->controller->flash_read_supported(spi)); } int spi_flash_read(struct spi_device *spi, @@ -1209,12 +1246,13 @@ int spi_flash_read(struct spi_device *spi, * @modalias: Initializes spi_device.modalias; identifies the driver. * @platform_data: Initializes spi_device.platform_data; the particular * data stored there is driver-specific. + * @properties: Additional device properties for the device. * @controller_data: Initializes spi_device.controller_data; some * controllers need hints about hardware setup, e.g. for DMA. * @irq: Initializes spi_device.irq; depends on how the board is wired. * @max_speed_hz: Initializes spi_device.max_speed_hz; based on limits * from the chip datasheet and board-specific signal quality issues. - * @bus_num: Identifies which spi_master parents the spi_device; unused + * @bus_num: Identifies which spi_controller parents the spi_device; unused * by spi_new_device(), and otherwise depends on board wiring. * @chip_select: Initializes spi_device.chip_select; depends on how * the board is wired. @@ -1241,10 +1279,12 @@ struct spi_board_info { * * platform_data goes to spi_device.dev.platform_data, * controller_data goes to spi_device.controller_data, + * device properties are copied and attached to spi_device, * irq is copied too */ char modalias[SPI_NAME_SIZE]; const void *platform_data; + const struct property_entry *properties; void *controller_data; int irq; @@ -1253,7 +1293,7 @@ struct spi_board_info { /* bus_num is board specific and matches the bus_num of some - * spi_master that will probably be registered later. + * spi_controller that will probably be registered later. * * chip_select reflects how this chip is wired to that master; * it's less than num_chipselect. @@ -1287,7 +1327,7 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) /* If you're hotplugging an adapter with devices (parport, usb, etc) * use spi_new_device() to describe each device. You can also call * spi_unregister_device() to start making that device vanish, but - * normally that would be handled by spi_unregister_master(). + * normally that would be handled by spi_unregister_controller(). * * You can also use spi_alloc_device() and spi_add_device() to use a two * stage registration sequence for each spi_device. This gives the caller @@ -1296,13 +1336,13 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) * be defined using the board info. */ extern struct spi_device * -spi_alloc_device(struct spi_master *master); +spi_alloc_device(struct spi_controller *ctlr); extern int spi_add_device(struct spi_device *spi); extern struct spi_device * -spi_new_device(struct spi_master *, struct spi_board_info *); +spi_new_device(struct spi_controller *, struct spi_board_info *); extern void spi_unregister_device(struct spi_device *spi); @@ -1310,9 +1350,32 @@ extern const struct spi_device_id * spi_get_device_id(const struct spi_device *sdev); static inline bool -spi_transfer_is_last(struct spi_master *master, struct spi_transfer *xfer) +spi_transfer_is_last(struct spi_controller *ctlr, struct spi_transfer *xfer) { - return list_is_last(&xfer->transfer_list, &master->cur_msg->transfers); + return list_is_last(&xfer->transfer_list, &ctlr->cur_msg->transfers); } + +/* Compatibility layer */ +#define spi_master spi_controller + +#define SPI_MASTER_HALF_DUPLEX SPI_CONTROLLER_HALF_DUPLEX +#define SPI_MASTER_NO_RX SPI_CONTROLLER_NO_RX +#define SPI_MASTER_NO_TX SPI_CONTROLLER_NO_TX +#define SPI_MASTER_MUST_RX SPI_CONTROLLER_MUST_RX +#define SPI_MASTER_MUST_TX SPI_CONTROLLER_MUST_TX + +#define spi_master_get_devdata(_ctlr) spi_controller_get_devdata(_ctlr) +#define spi_master_set_devdata(_ctlr, _data) \ + spi_controller_set_devdata(_ctlr, _data) +#define spi_master_get(_ctlr) spi_controller_get(_ctlr) +#define spi_master_put(_ctlr) spi_controller_put(_ctlr) +#define spi_master_suspend(_ctlr) spi_controller_suspend(_ctlr) +#define spi_master_resume(_ctlr) spi_controller_resume(_ctlr) + +#define spi_register_master(_ctlr) spi_register_controller(_ctlr) +#define devm_spi_register_master(_dev, _ctlr) \ + devm_spi_register_controller(_dev, _ctlr) +#define spi_unregister_master(_ctlr) spi_unregister_controller(_ctlr) + #endif /* __LINUX_SPI_H */ diff --git a/include/linux/spi/tsc2005.h b/include/linux/spi/tsc2005.h deleted file mode 100644 index 563b3b1799a8..000000000000 --- a/include/linux/spi/tsc2005.h +++ /dev/null @@ -1,34 +0,0 @@ -/* - * This file is part of TSC2005 touchscreen driver - * - * Copyright (C) 2009-2010 Nokia Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef _LINUX_SPI_TSC2005_H -#define _LINUX_SPI_TSC2005_H - -#include <linux/types.h> - -struct tsc2005_platform_data { - int ts_pressure_max; - int ts_pressure_fudge; - int ts_x_max; - int ts_x_fudge; - int ts_y_max; - int ts_y_fudge; - int ts_x_plate_ohm; - unsigned int esd_timeout_ms; - void (*set_reset)(bool enable); -}; - -#endif diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 47dd0cebd204..d9510e8522d4 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -180,8 +180,6 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock_nested(lock, subclass) -# define raw_spin_lock_bh_nested(lock, subclass) \ - _raw_spin_lock_bh_nested(lock, subclass) # define raw_spin_lock_nest_lock(lock, nest_lock) \ do { \ @@ -197,7 +195,6 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock(((void)(subclass), (lock))) # define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock) -# define raw_spin_lock_bh_nested(lock, subclass) _raw_spin_lock_bh(lock) #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) @@ -317,11 +314,6 @@ do { \ raw_spin_lock_nested(spinlock_check(lock), subclass); \ } while (0) -#define spin_lock_bh_nested(lock, subclass) \ -do { \ - raw_spin_lock_bh_nested(spinlock_check(lock), subclass);\ -} while (0) - #define spin_lock_nest_lock(lock, nest_lock) \ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ @@ -377,6 +369,26 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock) raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) +/** + * spin_unlock_wait - Interpose between successive critical sections + * @lock: the spinlock whose critical sections are to be interposed. + * + * Semantically this is equivalent to a spin_lock() immediately + * followed by a spin_unlock(). However, most architectures have + * more efficient implementations in which the spin_unlock_wait() + * cannot block concurrent lock acquisition, and in some cases + * where spin_unlock_wait() does not write to the lock variable. + * Nevertheless, spin_unlock_wait() can have high overhead, so if + * you feel the need to use it, please check to see if there is + * a better way to get your job done. + * + * The ordering guarantees provided by spin_unlock_wait() are: + * + * 1. All accesses preceding the spin_unlock_wait() happen before + * any accesses in later critical sections for this same lock. + * 2. All accesses following the spin_unlock_wait() happen after + * any accesses in earlier critical sections for this same lock. + */ static __always_inline void spin_unlock_wait(spinlock_t *lock) { raw_spin_unlock_wait(&lock->rlock); diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 5344268e6e62..42dfab89e740 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -22,8 +22,6 @@ int in_lock_functions(unsigned long addr); void __lockfunc _raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) __acquires(lock); -void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass) - __acquires(lock); void __lockfunc _raw_spin_lock_nest_lock(raw_spinlock_t *lock, struct lockdep_map *map) __acquires(lock); diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h index d3afef9d8dbe..d0d188861ad6 100644 --- a/include/linux/spinlock_api_up.h +++ b/include/linux/spinlock_api_up.h @@ -57,7 +57,6 @@ #define _raw_spin_lock(lock) __LOCK(lock) #define _raw_spin_lock_nested(lock, subclass) __LOCK(lock) -#define _raw_spin_lock_bh_nested(lock, subclass) __LOCK(lock) #define _raw_read_lock(lock) __LOCK(lock) #define _raw_write_lock(lock) __LOCK(lock) #define _raw_spin_lock_bh(lock) __LOCK_BH(lock) diff --git a/include/linux/splice.h b/include/linux/splice.h index 00a21166e268..db42746bdfea 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -20,6 +20,8 @@ #define SPLICE_F_MORE (0x04) /* expect more data */ #define SPLICE_F_GIFT (0x08) /* pages passed in are a gift */ +#define SPLICE_F_ALL (SPLICE_F_MOVE|SPLICE_F_NONBLOCK|SPLICE_F_MORE|SPLICE_F_GIFT) + /* * Passed to the actors */ @@ -55,7 +57,6 @@ struct splice_pipe_desc { struct partial_page *partial; /* pages[] may not be contig */ int nr_pages; /* number of populated pages in map */ unsigned int nr_pages_max; /* pages[] & partial[] arrays size */ - unsigned int flags; /* splice flags */ const struct pipe_buf_operations *ops;/* ops associated with output pipe */ void (*spd_release)(struct splice_pipe_desc *, unsigned int); }; @@ -82,7 +83,6 @@ extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, */ extern int splice_grow_spd(const struct pipe_inode_info *, struct splice_pipe_desc *); extern void splice_shrink_spd(struct splice_pipe_desc *); -extern void spd_release_page(struct splice_pipe_desc *, unsigned int); extern const struct pipe_buf_operations page_cache_pipe_buf_ops; extern const struct pipe_buf_operations default_pipe_buf_ops; diff --git a/include/linux/sram.h b/include/linux/sram.h new file mode 100644 index 000000000000..4fb405fb0480 --- /dev/null +++ b/include/linux/sram.h @@ -0,0 +1,27 @@ +/* + * Generic SRAM Driver Interface + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#ifndef __LINUX_SRAM_H__ +#define __LINUX_SRAM_H__ + +struct gen_pool; + +#ifdef CONFIG_SRAM_EXEC +void *sram_exec_copy(struct gen_pool *pool, void *dst, void *src, size_t size); +#else +static inline void *sram_exec_copy(struct gen_pool *pool, void *dst, void *src, + size_t size) +{ + return NULL; +} +#endif /* CONFIG_SRAM_EXEC */ +#endif /* __LINUX_SRAM_H__ */ diff --git a/include/linux/srcu.h b/include/linux/srcu.h index dc8eb63c6568..39af9bc0f653 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -22,7 +22,7 @@ * Lai Jiangshan <laijs@cn.fujitsu.com> * * For detailed explanation of Read-Copy Update mechanism see - - * Documentation/RCU/ *.txt + * Documentation/RCU/ *.txt * */ @@ -32,35 +32,9 @@ #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> +#include <linux/rcu_segcblist.h> -struct srcu_struct_array { - unsigned long c[2]; - unsigned long seq[2]; -}; - -struct rcu_batch { - struct rcu_head *head, **tail; -}; - -#define RCU_BATCH_INIT(name) { NULL, &(name.head) } - -struct srcu_struct { - unsigned long completed; - struct srcu_struct_array __percpu *per_cpu_ref; - spinlock_t queue_lock; /* protect ->batch_queue, ->running */ - bool running; - /* callbacks just queued */ - struct rcu_batch batch_queue; - /* callbacks try to do the first check_zero */ - struct rcu_batch batch_check0; - /* callbacks done with the first check_zero and the flip */ - struct rcu_batch batch_check1; - struct rcu_batch batch_done; - struct delayed_work work; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -}; +struct srcu_struct; #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -82,74 +56,23 @@ int init_srcu_struct(struct srcu_struct *sp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -void process_srcu(struct work_struct *work); - -#define __SRCU_STRUCT_INIT(name) \ - { \ - .completed = -300, \ - .per_cpu_ref = &name##_srcu_array, \ - .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \ - .running = false, \ - .batch_queue = RCU_BATCH_INIT(name.batch_queue), \ - .batch_check0 = RCU_BATCH_INIT(name.batch_check0), \ - .batch_check1 = RCU_BATCH_INIT(name.batch_check1), \ - .batch_done = RCU_BATCH_INIT(name.batch_done), \ - .work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\ - __SRCU_DEP_MAP_INIT(name) \ - } - -/* - * Define and initialize a srcu struct at build time. - * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it. - * - * Note that although DEFINE_STATIC_SRCU() hides the name from other - * files, the per-CPU variable rules nevertheless require that the - * chosen name be globally unique. These rules also prohibit use of - * DEFINE_STATIC_SRCU() within a function. If these rules are too - * restrictive, declare the srcu_struct manually. For example, in - * each file: - * - * static struct srcu_struct my_srcu; - * - * Then, before the first use of each my_srcu, manually initialize it: - * - * init_srcu_struct(&my_srcu); - * - * See include/linux/percpu-defs.h for the rules on per-CPU variables. - */ -#define __DEFINE_SRCU(name, is_static) \ - static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) -#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) -#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) +#ifdef CONFIG_TINY_SRCU +#include <linux/srcutiny.h> +#elif defined(CONFIG_TREE_SRCU) +#include <linux/srcutree.h> +#elif defined(CONFIG_SRCU) +#error "Unknown SRCU implementation specified to kernel configuration" +#else +/* Dummy definition for things like notifiers. Actual use gets link error. */ +struct srcu_struct { }; +#endif -/** - * call_srcu() - Queue a callback for invocation after an SRCU grace period - * @sp: srcu_struct in queue the callback - * @head: structure to be used for queueing the SRCU callback. - * @func: function to be invoked after the SRCU grace period - * - * The callback function will be invoked some time after a full SRCU - * grace period elapses, in other words after all pre-existing SRCU - * read-side critical sections have completed. However, the callback - * function might well execute concurrently with other SRCU read-side - * critical sections that started after call_srcu() was invoked. SRCU - * read-side critical sections are delimited by srcu_read_lock() and - * srcu_read_unlock(), and may be nested. - * - * The callback will be invoked from process context, but must nevertheless - * be fast and must not block. - */ void call_srcu(struct srcu_struct *sp, struct rcu_head *head, void (*func)(struct rcu_head *head)); - void cleanup_srcu_struct(struct srcu_struct *sp); int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp); void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); void synchronize_srcu(struct srcu_struct *sp); -void synchronize_srcu_expedited(struct srcu_struct *sp); -unsigned long srcu_batches_completed(struct srcu_struct *sp); -void srcu_barrier(struct srcu_struct *sp); #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -232,9 +155,7 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) { int retval; - preempt_disable(); retval = __srcu_read_lock(sp); - preempt_enable(); rcu_lock_acquire(&(sp)->dep_map); return retval; } diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h new file mode 100644 index 000000000000..cfbfc540cafc --- /dev/null +++ b/include/linux/srcutiny.h @@ -0,0 +1,90 @@ +/* + * Sleepable Read-Copy Update mechanism for mutual exclusion, + * tiny variant. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (C) IBM Corporation, 2017 + * + * Author: Paul McKenney <paulmck@us.ibm.com> + */ + +#ifndef _LINUX_SRCU_TINY_H +#define _LINUX_SRCU_TINY_H + +#include <linux/swait.h> + +struct srcu_struct { + short srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */ + short srcu_idx; /* Current reader array element. */ + u8 srcu_gp_running; /* GP workqueue running? */ + u8 srcu_gp_waiting; /* GP waiting for readers? */ + struct swait_queue_head srcu_wq; + /* Last srcu_read_unlock() wakes GP. */ + struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ + struct rcu_head **srcu_cb_tail; /* Pending callbacks: Tail. */ + struct work_struct srcu_work; /* For driving grace periods. */ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +}; + +void srcu_drive_gp(struct work_struct *wp); + +#define __SRCU_STRUCT_INIT(name) \ +{ \ + .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ + .srcu_cb_tail = &name.srcu_cb_head, \ + .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \ + __SRCU_DEP_MAP_INIT(name) \ +} + +/* + * This odd _STATIC_ arrangement is needed for API compatibility with + * Tree SRCU, which needs some per-CPU data. + */ +#define DEFINE_SRCU(name) \ + struct srcu_struct name = __SRCU_STRUCT_INIT(name) +#define DEFINE_STATIC_SRCU(name) \ + static struct srcu_struct name = __SRCU_STRUCT_INIT(name) + +void synchronize_srcu(struct srcu_struct *sp); + +/* + * Counts the new reader in the appropriate per-CPU element of the + * srcu_struct. Can be invoked from irq/bh handlers, but the matching + * __srcu_read_unlock() must be in the same handler instance. Returns an + * index that must be passed to the matching srcu_read_unlock(). + */ +static inline int __srcu_read_lock(struct srcu_struct *sp) +{ + int idx; + + idx = READ_ONCE(sp->srcu_idx); + WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1); + return idx; +} + +static inline void synchronize_srcu_expedited(struct srcu_struct *sp) +{ + synchronize_srcu(sp); +} + +static inline void srcu_barrier(struct srcu_struct *sp) +{ + synchronize_srcu(sp); +} + +#endif diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h new file mode 100644 index 000000000000..42973f787e7e --- /dev/null +++ b/include/linux/srcutree.h @@ -0,0 +1,145 @@ +/* + * Sleepable Read-Copy Update mechanism for mutual exclusion, + * tree variant. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (C) IBM Corporation, 2017 + * + * Author: Paul McKenney <paulmck@us.ibm.com> + */ + +#ifndef _LINUX_SRCU_TREE_H +#define _LINUX_SRCU_TREE_H + +#include <linux/rcu_node_tree.h> +#include <linux/completion.h> + +struct srcu_node; +struct srcu_struct; + +/* + * Per-CPU structure feeding into leaf srcu_node, similar in function + * to rcu_node. + */ +struct srcu_data { + /* Read-side state. */ + unsigned long srcu_lock_count[2]; /* Locks per CPU. */ + unsigned long srcu_unlock_count[2]; /* Unlocks per CPU. */ + + /* Update-side state. */ + raw_spinlock_t __private lock ____cacheline_internodealigned_in_smp; + struct rcu_segcblist srcu_cblist; /* List of callbacks.*/ + unsigned long srcu_gp_seq_needed; /* Furthest future GP needed. */ + unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + bool srcu_cblist_invoking; /* Invoking these CBs? */ + struct delayed_work work; /* Context for CB invoking. */ + struct rcu_head srcu_barrier_head; /* For srcu_barrier() use. */ + struct srcu_node *mynode; /* Leaf srcu_node. */ + unsigned long grpmask; /* Mask for leaf srcu_node */ + /* ->srcu_data_have_cbs[]. */ + int cpu; + struct srcu_struct *sp; +}; + +/* + * Node in SRCU combining tree, similar in function to rcu_data. + */ +struct srcu_node { + raw_spinlock_t __private lock; + unsigned long srcu_have_cbs[4]; /* GP seq for children */ + /* having CBs, but only */ + /* is > ->srcu_gq_seq. */ + unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs */ + /* have CBs for given GP? */ + unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + struct srcu_node *srcu_parent; /* Next up in tree. */ + int grplo; /* Least CPU for node. */ + int grphi; /* Biggest CPU for node. */ +}; + +/* + * Per-SRCU-domain structure, similar in function to rcu_state. + */ +struct srcu_struct { + struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ + struct srcu_node *level[RCU_NUM_LVLS + 1]; + /* First node at each level. */ + struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ + raw_spinlock_t __private lock; /* Protect counters */ + struct mutex srcu_gp_mutex; /* Serialize GP work. */ + unsigned int srcu_idx; /* Current rdr array element. */ + unsigned long srcu_gp_seq; /* Grace-period seq #. */ + unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ + unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ + struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ + unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ + struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ + struct completion srcu_barrier_completion; + /* Awaken barrier rq at end. */ + atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ + /* callback for the barrier */ + /* operation. */ + struct delayed_work work; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +}; + +/* Values for state variable (bottom bits of ->srcu_gp_seq). */ +#define SRCU_STATE_IDLE 0 +#define SRCU_STATE_SCAN1 1 +#define SRCU_STATE_SCAN2 2 + +void process_srcu(struct work_struct *work); + +#define __SRCU_STRUCT_INIT(name) \ + { \ + .sda = &name##_srcu_data, \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ + .srcu_gp_seq_needed = 0 - 1, \ + __SRCU_DEP_MAP_INIT(name) \ + } + +/* + * Define and initialize a srcu struct at build time. + * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it. + * + * Note that although DEFINE_STATIC_SRCU() hides the name from other + * files, the per-CPU variable rules nevertheless require that the + * chosen name be globally unique. These rules also prohibit use of + * DEFINE_STATIC_SRCU() within a function. If these rules are too + * restrictive, declare the srcu_struct manually. For example, in + * each file: + * + * static struct srcu_struct my_srcu; + * + * Then, before the first use of each my_srcu, manually initialize it: + * + * init_srcu_struct(&my_srcu); + * + * See include/linux/percpu-defs.h for the rules on per-CPU variables. + */ +#define __DEFINE_SRCU(name, is_static) \ + static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data);\ + is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) +#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) +#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) + +void synchronize_srcu_expedited(struct srcu_struct *sp); +void srcu_barrier(struct srcu_struct *sp); + +#endif diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 0a34489a46b6..4205f71a5f0e 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -18,6 +18,8 @@ extern void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace); extern void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace); +extern int save_stack_trace_tsk_reliable(struct task_struct *tsk, + struct stack_trace *trace); extern void print_stack_trace(struct stack_trace *trace, int spaces); extern int snprint_stack_trace(char *buf, size_t size, @@ -29,12 +31,13 @@ extern void save_stack_trace_user(struct stack_trace *trace); # define save_stack_trace_user(trace) do { } while (0) #endif -#else +#else /* !CONFIG_STACKTRACE */ # define save_stack_trace(trace) do { } while (0) # define save_stack_trace_tsk(tsk, trace) do { } while (0) # define save_stack_trace_user(trace) do { } while (0) # define print_stack_trace(trace, spaces) do { } while (0) # define snprint_stack_trace(buf, size, trace, spaces) do { } while (0) -#endif +# define save_stack_trace_tsk_reliable(tsk, trace) ({ -ENOSYS; }) +#endif /* CONFIG_STACKTRACE */ -#endif +#endif /* __LINUX_STACKTRACE_H */ diff --git a/include/linux/stat.h b/include/linux/stat.h index 075cb0c7eb2a..64b6b3aece21 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -18,20 +18,33 @@ #include <linux/time.h> #include <linux/uidgid.h> +#define KSTAT_QUERY_FLAGS (AT_STATX_SYNC_TYPE) + struct kstat { - u64 ino; - dev_t dev; + u32 result_mask; /* What fields the user got */ umode_t mode; unsigned int nlink; + uint32_t blksize; /* Preferred I/O size */ + u64 attributes; + u64 attributes_mask; +#define KSTAT_ATTR_FS_IOC_FLAGS \ + (STATX_ATTR_COMPRESSED | \ + STATX_ATTR_IMMUTABLE | \ + STATX_ATTR_APPEND | \ + STATX_ATTR_NODUMP | \ + STATX_ATTR_ENCRYPTED \ + )/* Attrs corresponding to FS_*_FL flags */ + u64 ino; + dev_t dev; + dev_t rdev; kuid_t uid; kgid_t gid; - dev_t rdev; loff_t size; - struct timespec atime; + struct timespec atime; struct timespec mtime; struct timespec ctime; - unsigned long blksize; - unsigned long long blocks; + struct timespec btime; /* File creation time */ + u64 blocks; }; #endif diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 266dab9ad782..108739ff9223 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -28,6 +28,9 @@ #include <linux/platform_device.h> +#define MTL_MAX_RX_QUEUES 8 +#define MTL_MAX_TX_QUEUES 8 + #define STMMAC_RX_COE_NONE 0 #define STMMAC_RX_COE_TYPE1 1 #define STMMAC_RX_COE_TYPE2 2 @@ -44,6 +47,18 @@ #define STMMAC_CSR_150_250M 0x4 /* MDC = clk_scr_i/102 */ #define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/122 */ +/* MTL algorithms identifiers */ +#define MTL_TX_ALGORITHM_WRR 0x0 +#define MTL_TX_ALGORITHM_WFQ 0x1 +#define MTL_TX_ALGORITHM_DWRR 0x2 +#define MTL_TX_ALGORITHM_SP 0x3 +#define MTL_RX_ALGORITHM_SP 0x4 +#define MTL_RX_ALGORITHM_WSP 0x5 + +/* RX/TX Queue Mode */ +#define MTL_QUEUE_AVB 0x0 +#define MTL_QUEUE_DCB 0x1 + /* The MDC clock could be set higher than the IEEE 802.3 * specified frequency limit 0f 2.5 MHz, by programming a clock divider * of value different than the above defined values. The resultant MDIO @@ -103,13 +118,32 @@ struct stmmac_axi { u32 axi_wr_osr_lmt; u32 axi_rd_osr_lmt; bool axi_kbbe; - bool axi_axi_all; u32 axi_blen[AXI_BLEN]; bool axi_fb; bool axi_mb; bool axi_rb; }; +struct stmmac_rxq_cfg { + u8 mode_to_use; + u8 chan; + u8 pkt_route; + bool use_prio; + u32 prio; +}; + +struct stmmac_txq_cfg { + u8 weight; + u8 mode_to_use; + /* Credit Base Shaper parameters */ + u32 send_slope; + u32 idle_slope; + u32 high_credit; + u32 low_credit; + bool use_prio; + u32 prio; +}; + struct plat_stmmacenet_data { int bus_id; int phy_addr; @@ -134,14 +168,27 @@ struct plat_stmmacenet_data { int unicast_filter_entries; int tx_fifo_size; int rx_fifo_size; + u8 rx_queues_to_use; + u8 tx_queues_to_use; + u8 rx_sched_algorithm; + u8 tx_sched_algorithm; + struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; + struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; void (*fix_mac_speed)(void *priv, unsigned int speed); - void (*bus_setup)(void __iomem *ioaddr); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); + struct mac_device_info *(*setup)(void *priv); void *bsp_priv; + struct clk *stmmac_clk; + struct clk *pclk; + struct clk *clk_ptp_ref; + unsigned int clk_ptp_rate; + struct reset_control *stmmac_rst; struct stmmac_axi *axi; int has_gmac4; + bool has_sun8i; bool tso_en; int mac_port_sel_speed; + bool en_tx_lpi_clockgating; }; #endif diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 3cc9632dcc2a..3d60275e3ba9 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -116,15 +116,29 @@ static inline int try_stop_cpus(const struct cpumask *cpumask, * @fn() runs. * * This can be thought of as a very heavy write lock, equivalent to - * grabbing every spinlock in the kernel. */ + * grabbing every spinlock in the kernel. + * + * Protects against CPU hotplug. + */ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); +/** + * stop_machine_cpuslocked: freeze the machine on all CPUs and run this function + * @fn: the function to run + * @data: the data ptr for the @fn() + * @cpus: the cpus to run the @fn() on (NULL = any online cpu) + * + * Same as above. Must be called from with in a cpus_read_lock() protected + * region. Avoids nested calls to cpus_read_lock(). + */ +int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); + int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); #else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ -static inline int stop_machine(cpu_stop_fn_t fn, void *data, - const struct cpumask *cpus) +static inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, + const struct cpumask *cpus) { unsigned long flags; int ret; @@ -134,6 +148,12 @@ static inline int stop_machine(cpu_stop_fn_t fn, void *data, return ret; } +static inline int stop_machine(cpu_stop_fn_t fn, void *data, + const struct cpumask *cpus) +{ + return stop_machine_cpuslocked(fn, data, cpus); +} + static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { diff --git a/include/linux/string.h b/include/linux/string.h index 26b6f6a66f83..a467e617eeb0 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -114,6 +114,20 @@ extern int memcmp(const void *,const void *,__kernel_size_t); #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif +#ifndef __HAVE_ARCH_MEMCPY_MCSAFE +static inline __must_check int memcpy_mcsafe(void *dst, const void *src, + size_t cnt) +{ + memcpy(dst, src, cnt); + return 0; +} +#endif +#ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE +static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) +{ + memcpy(dst, src, cnt); +} +#endif void *memchr_inv(const void *s, int c, size_t n); char *strreplace(char *s, char old, char new); @@ -123,6 +137,7 @@ extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); +extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); @@ -135,6 +150,16 @@ static inline int strtobool(const char *s, bool *res) } int match_string(const char * const *array, size_t n, const char *string); +int __sysfs_match_string(const char * const *array, size_t n, const char *s); + +/** + * sysfs_match_string - matches given string in an array + * @_a: array of strings + * @_s: string to match with + * + * Helper for __sysfs_match_string(). Calculates the size of @a automatically. + */ +#define sysfs_match_string(_a, _s) __sysfs_match_string(_a, ARRAY_SIZE(_a), _s) #ifdef CONFIG_BINARY_PRINTF int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); @@ -169,4 +194,205 @@ static inline const char *kbasename(const char *path) return tail ? tail + 1 : path; } +#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) +#define __RENAME(x) __asm__(#x) + +void fortify_panic(const char *name) __noreturn __cold; +void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); +void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); +void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); + +#if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) +__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_strncpy(p, q, size); +} + +__FORTIFY_INLINE char *strcat(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + if (p_size == (size_t)-1) + return __builtin_strcat(p, q); + if (strlcat(p, q, p_size) >= p_size) + fortify_panic(__func__); + return p; +} + +__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +{ + __kernel_size_t ret; + size_t p_size = __builtin_object_size(p, 0); + if (p_size == (size_t)-1) + return __builtin_strlen(p); + ret = strnlen(p, p_size); + if (p_size <= ret) + fortify_panic(__func__); + return ret; +} + +extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); +__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +{ + size_t p_size = __builtin_object_size(p, 0); + __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); + if (p_size <= ret && maxlen != ret) + fortify_panic(__func__); + return ret; +} + +/* defined after fortified strlen to reuse it */ +extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); +__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +{ + size_t ret; + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __real_strlcpy(p, q, size); + ret = strlen(q); + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + if (__builtin_constant_p(len) && len >= p_size) + __write_overflow(); + if (len >= p_size) + fortify_panic(__func__); + __builtin_memcpy(p, q, len); + p[len] = '\0'; + } + return ret; +} + +/* defined after fortified strlen and strnlen to reuse them */ +__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +{ + size_t p_len, copy_len; + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strncat(p, q, count); + p_len = strlen(p); + copy_len = strnlen(q, count); + if (p_size < p_len + copy_len + 1) + fortify_panic(__func__); + __builtin_memcpy(p + p_len, q, copy_len); + p[p_len + copy_len] = '\0'; + return p; +} + +__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_memset(p, c, size); +} + +__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memcpy(p, q, size); +} + +__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memmove(p, q, size); +} + +extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); +__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memscan(p, c, size); +} + +__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __read_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memcmp(p, q, size); +} + +__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_memchr(p, c, size); +} + +void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); +__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memchr_inv(p, c, size); +} + +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); +__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_kmemdup(p, size, gfp); +} + +/* defined after fortified strlen and memcpy to reuse them */ +__FORTIFY_INLINE char *strcpy(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strcpy(p, q); + memcpy(p, q, strlen(q) + 1); + return p; +} + +#endif + #endif /* _LINUX_STRING_H_ */ diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index b1bc62ba20a2..8fd3504946ad 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -32,6 +32,7 @@ */ #define UNX_MAXNODENAME __NEW_UTS_LEN #define UNX_CALLSLACK (21 + XDR_QUADLEN(UNX_MAXNODENAME)) +#define UNX_NGROUPS 16 struct rpcsec_gss_info; @@ -63,9 +64,6 @@ struct rpc_cred { struct rcu_head cr_rcu; struct rpc_auth * cr_auth; const struct rpc_credops *cr_ops; -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - unsigned long cr_magic; /* 0x0f4aa4f0 */ -#endif unsigned long cr_expire; /* when to gc */ unsigned long cr_flags; /* various flags */ atomic_t cr_count; /* ref count */ @@ -79,8 +77,6 @@ struct rpc_cred { #define RPCAUTH_CRED_HASHED 2 #define RPCAUTH_CRED_NEGATIVE 3 -#define RPCAUTH_CRED_MAGIC 0x0f4aa4f0 - /* rpc_auth au_flags */ #define RPCAUTH_AUTH_NO_CRKEY_TIMEOUT 0x0001 /* underlying cred has no key timeout */ diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h index 36eebc451b41..cebdf8745901 100644 --- a/include/linux/sunrpc/auth_gss.h +++ b/include/linux/sunrpc/auth_gss.h @@ -13,6 +13,7 @@ #define _LINUX_SUNRPC_AUTH_GSS_H #ifdef __KERNEL__ +#include <linux/refcount.h> #include <linux/sunrpc/auth.h> #include <linux/sunrpc/svc.h> #include <linux/sunrpc/gss_api.h> @@ -65,7 +66,7 @@ struct rpc_gss_init_res { * the wire when communicating with a server. */ struct gss_cl_ctx { - atomic_t count; + refcount_t count; enum rpc_gss_proc gc_proc; u32 gc_seq; spinlock_t gc_seq_lock; diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 62a60eeacb0a..270bad0e1bed 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -63,15 +63,6 @@ struct cache_head { #define CACHE_NEW_EXPIRY 120 /* keep new things pending confirmation for 120 seconds */ -struct cache_detail_procfs { - struct proc_dir_entry *proc_ent; - struct proc_dir_entry *flush_ent, *channel_ent, *content_ent; -}; - -struct cache_detail_pipefs { - struct dentry *dir; -}; - struct cache_detail { struct module * owner; int hash_size; @@ -123,9 +114,9 @@ struct cache_detail { time_t last_warn; /* when we last warned about no readers */ union { - struct cache_detail_procfs procfs; - struct cache_detail_pipefs pipefs; - } u; + struct proc_dir_entry *procfs; + struct dentry *pipefs; + }; struct net *net; }; @@ -198,14 +189,17 @@ static inline struct cache_head *cache_get(struct cache_head *h) static inline void cache_put(struct cache_head *h, struct cache_detail *cd) { - if (atomic_read(&h->ref.refcount) <= 2 && + if (kref_read(&h->ref) <= 2 && h->expiry_time < cd->nextcheck) cd->nextcheck = h->expiry_time; kref_put(&h->ref, cd->cache_put); } -static inline int cache_is_expired(struct cache_detail *detail, struct cache_head *h) +static inline bool cache_is_expired(struct cache_detail *detail, struct cache_head *h) { + if (!test_bit(CACHE_VALID, &h->flags)) + return false; + return (h->expiry_time < seconds_since_boot()) || (detail->flush_time >= h->last_refresh); } @@ -227,6 +221,7 @@ extern void sunrpc_destroy_cache_detail(struct cache_detail *cd); extern int sunrpc_cache_register_pipefs(struct dentry *parent, const char *, umode_t, struct cache_detail *); extern void sunrpc_cache_unregister_pipefs(struct cache_detail *); +extern void sunrpc_cache_unhash(struct cache_detail *, struct cache_head *); /* Must store cache_detail in seq_file->private if using next three functions */ extern void *cache_seq_start(struct seq_file *file, loff_t *pos); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 333ad11b3dd9..55ef67bea06b 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -39,7 +39,7 @@ struct rpc_clnt { struct list_head cl_tasks; /* List of tasks */ spinlock_t cl_lock; /* spinlock */ struct rpc_xprt __rcu * cl_xprt; /* transport */ - struct rpc_procinfo * cl_procinfo; /* procedure info */ + const struct rpc_procinfo *cl_procinfo; /* procedure info */ u32 cl_prog, /* RPC program number */ cl_vers, /* RPC version number */ cl_maxproc; /* max procedure number */ @@ -87,7 +87,8 @@ struct rpc_program { struct rpc_version { u32 number; /* version number */ unsigned int nrprocs; /* number of procs */ - struct rpc_procinfo * procs; /* procedure array */ + const struct rpc_procinfo *procs; /* procedure array */ + unsigned int *counts; /* call counts */ }; /* @@ -99,7 +100,6 @@ struct rpc_procinfo { kxdrdproc_t p_decode; /* XDR decode function */ unsigned int p_arglen; /* argument hdr length (u32) */ unsigned int p_replen; /* reply hdr length (u32) */ - unsigned int p_count; /* call count */ unsigned int p_timer; /* Which RTT timer to use */ u32 p_statidx; /* Which procedure to account */ const char * p_name; /* name of procedure */ @@ -182,7 +182,6 @@ int rpc_protocol(struct rpc_clnt *); struct net * rpc_net_ns(struct rpc_clnt *); size_t rpc_max_payload(struct rpc_clnt *); size_t rpc_max_bc_payload(struct rpc_clnt *); -unsigned long rpc_get_timeout(struct rpc_clnt *clnt); void rpc_force_rebind(struct rpc_clnt *); size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t); const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); @@ -202,8 +201,9 @@ int rpc_clnt_add_xprt(struct rpc_clnt *, struct xprt_create *, struct rpc_xprt *, void *), void *data); -void rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, - unsigned long timeo); +void rpc_set_connect_timeout(struct rpc_clnt *clnt, + unsigned long connect_timeout, + unsigned long reconnect_timeout); int rpc_clnt_setup_test_and_add_xprt(struct rpc_clnt *, struct rpc_xprt_switch *, diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h index 59a7889e15db..8da0f37f3bdc 100644 --- a/include/linux/sunrpc/debug.h +++ b/include/linux/sunrpc/debug.h @@ -20,33 +20,55 @@ extern unsigned int nfsd_debug; extern unsigned int nlm_debug; #endif -#define dprintk(args...) dfprintk(FACILITY, ## args) -#define dprintk_rcu(args...) dfprintk_rcu(FACILITY, ## args) +#define dprintk(fmt, ...) \ + dfprintk(FACILITY, fmt, ##__VA_ARGS__) +#define dprintk_cont(fmt, ...) \ + dfprintk_cont(FACILITY, fmt, ##__VA_ARGS__) +#define dprintk_rcu(fmt, ...) \ + dfprintk_rcu(FACILITY, fmt, ##__VA_ARGS__) +#define dprintk_rcu_cont(fmt, ...) \ + dfprintk_rcu_cont(FACILITY, fmt, ##__VA_ARGS__) #undef ifdebug #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define ifdebug(fac) if (unlikely(rpc_debug & RPCDBG_##fac)) -# define dfprintk(fac, args...) \ - do { \ - ifdebug(fac) \ - printk(KERN_DEFAULT args); \ - } while (0) - -# define dfprintk_rcu(fac, args...) \ - do { \ - ifdebug(fac) { \ - rcu_read_lock(); \ - printk(KERN_DEFAULT args); \ - rcu_read_unlock(); \ - } \ - } while (0) +# define dfprintk(fac, fmt, ...) \ +do { \ + ifdebug(fac) \ + printk(KERN_DEFAULT fmt, ##__VA_ARGS__); \ +} while (0) + +# define dfprintk_cont(fac, fmt, ...) \ +do { \ + ifdebug(fac) \ + printk(KERN_CONT fmt, ##__VA_ARGS__); \ +} while (0) + +# define dfprintk_rcu(fac, fmt, ...) \ +do { \ + ifdebug(fac) { \ + rcu_read_lock(); \ + printk(KERN_DEFAULT fmt, ##__VA_ARGS__); \ + rcu_read_unlock(); \ + } \ +} while (0) + +# define dfprintk_rcu_cont(fac, fmt, ...) \ +do { \ + ifdebug(fac) { \ + rcu_read_lock(); \ + printk(KERN_CONT fmt, ##__VA_ARGS__); \ + rcu_read_unlock(); \ + } \ +} while (0) # define RPC_IFDEBUG(x) x #else # define ifdebug(fac) if (0) -# define dfprintk(fac, args...) do {} while (0) -# define dfprintk_rcu(fac, args...) do {} while (0) +# define dfprintk(fac, fmt, ...) do {} while (0) +# define dfprintk_cont(fac, fmt, ...) do {} while (0) +# define dfprintk_rcu(fac, fmt, ...) do {} while (0) # define RPC_IFDEBUG(x) #endif diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index cfda6adcf33c..b7e85b341a54 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -110,6 +110,15 @@ struct rpcrdma_msg { }; /* + * XDR sizes, in quads + */ +enum { + rpcrdma_fixed_maxsz = 4, + rpcrdma_segment_maxsz = 4, + rpcrdma_readchunk_maxsz = 2 + rpcrdma_segment_maxsz, +}; + +/* * Smallest RPC/RDMA header: rm_xid through rm_type, then rm_nochunks */ #define RPCRDMA_HDRLEN_MIN (sizeof(__be32) * 7) @@ -134,6 +143,9 @@ enum rpcrdma_proc { #define rdma_done cpu_to_be32(RDMA_DONE) #define rdma_error cpu_to_be32(RDMA_ERROR) +#define err_vers cpu_to_be32(ERR_VERS) +#define err_chunk cpu_to_be32(ERR_CHUNK) + /* * Private extension to RPC-over-RDMA Version One. * Message passed during RDMA-CM connection set-up. diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 7ba040c797ec..50a99a117da7 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -13,7 +13,7 @@ #include <linux/ktime.h> #include <linux/sunrpc/types.h> #include <linux/spinlock.h> -#include <linux/wait.h> +#include <linux/wait_bit.h> #include <linux/workqueue.h> #include <linux/sunrpc/xdr.h> @@ -22,7 +22,7 @@ */ struct rpc_procinfo; struct rpc_message { - struct rpc_procinfo * rpc_proc; /* Procedure information */ + const struct rpc_procinfo *rpc_proc; /* Procedure information */ void * rpc_argp; /* Arguments */ void * rpc_resp; /* Result */ struct rpc_cred * rpc_cred; /* Credentials */ diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 7321ae933867..a3f8af9bd543 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -237,7 +237,7 @@ struct svc_rqst { struct svc_serv * rq_server; /* RPC service definition */ struct svc_pool * rq_pool; /* thread pool */ - struct svc_procedure * rq_procinfo; /* procedure info */ + const struct svc_procedure *rq_procinfo;/* procedure info */ struct auth_ops * rq_authop; /* authentication flavour */ struct svc_cred rq_cred; /* auth info */ void * rq_xprt_ctxt; /* transport specific context ptr */ @@ -246,7 +246,7 @@ struct svc_rqst { size_t rq_xprt_hlen; /* xprt header len */ struct xdr_buf rq_arg; struct xdr_buf rq_res; - struct page * rq_pages[RPCSVC_MAXPAGES]; + struct page *rq_pages[RPCSVC_MAXPAGES + 1]; struct page * *rq_respages; /* points into rq_pages */ struct page * *rq_next_page; /* next reply page to use */ struct page * *rq_page_end; /* one past the last page */ @@ -384,7 +384,7 @@ struct svc_program { unsigned int pg_lovers; /* lowest version */ unsigned int pg_hivers; /* highest version */ unsigned int pg_nvers; /* number of versions */ - struct svc_version ** pg_vers; /* version array */ + const struct svc_version **pg_vers; /* version array */ char * pg_name; /* service name */ char * pg_class; /* class name: services sharing authentication */ struct svc_stat * pg_stats; /* rpc statistics */ @@ -397,13 +397,18 @@ struct svc_program { struct svc_version { u32 vs_vers; /* version number */ u32 vs_nproc; /* number of procedures */ - struct svc_procedure * vs_proc; /* per-procedure info */ + const struct svc_procedure *vs_proc; /* per-procedure info */ + unsigned int *vs_count; /* call counts */ u32 vs_xdrsize; /* xdrsize needed for this version */ - unsigned int vs_hidden : 1, /* Don't register with portmapper. - * Only used for nfsacl so far. */ - vs_rpcb_optnl:1;/* Don't care the result of register. - * Only used for nfsv4. */ + /* Don't register with rpcbind */ + bool vs_hidden; + + /* Don't care if the rpcbind registration fails */ + bool vs_rpcb_optnl; + + /* Need xprt with congestion control */ + bool vs_need_cong_ctrl; /* Override dispatch function (e.g. when caching replies). * A return value of 0 means drop the request. @@ -415,15 +420,17 @@ struct svc_version { /* * RPC procedure info */ -typedef __be32 (*svc_procfunc)(struct svc_rqst *, void *argp, void *resp); struct svc_procedure { - svc_procfunc pc_func; /* process the request */ - kxdrproc_t pc_decode; /* XDR decode args */ - kxdrproc_t pc_encode; /* XDR encode result */ - kxdrproc_t pc_release; /* XDR free result */ + /* process the request: */ + __be32 (*pc_func)(struct svc_rqst *); + /* XDR decode args: */ + int (*pc_decode)(struct svc_rqst *, __be32 *data); + /* XDR encode result: */ + int (*pc_encode)(struct svc_rqst *, __be32 *data); + /* XDR free result: */ + void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ unsigned int pc_ressize; /* result struct size */ - unsigned int pc_count; /* call count */ unsigned int pc_cachetype; /* cache info (NFS) */ unsigned int pc_xdrressize; /* maximum size of XDR reply */ }; @@ -470,6 +477,7 @@ void svc_pool_map_put(void); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, struct svc_serv_ops *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); +int svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); void svc_destroy(struct svc_serv *); void svc_shutdown_net(struct svc_serv *, struct net *); diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 757fb963696c..995c6fe9ee90 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -48,6 +48,12 @@ #include <rdma/rdma_cm.h> #define SVCRDMA_DEBUG +/* Default and maximum inline threshold sizes */ +enum { + RPCRDMA_DEF_INLINE_THRESH = 4096, + RPCRDMA_MAX_INLINE_THRESH = 65536 +}; + /* RPC/RDMA parameters and stats */ extern unsigned int svcrdma_ord; extern unsigned int svcrdma_max_requests; @@ -70,108 +76,55 @@ extern atomic_t rdma_stat_sq_prod; * completes. */ struct svc_rdma_op_ctxt { - struct list_head free; - struct svc_rdma_op_ctxt *read_hdr; - struct svc_rdma_fastreg_mr *frmr; - int hdr_count; + struct list_head list; struct xdr_buf arg; struct ib_cqe cqe; - struct ib_cqe reg_cqe; - struct ib_cqe inv_cqe; - struct list_head dto_q; u32 byte_len; - u32 position; struct svcxprt_rdma *xprt; - unsigned long flags; enum dma_data_direction direction; int count; unsigned int mapped_sges; - struct ib_sge sge[RPCSVC_MAXPAGES]; + int hdr_count; + struct ib_send_wr send_wr; + struct ib_sge sge[1 + RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE]; struct page *pages[RPCSVC_MAXPAGES]; }; -/* - * NFS_ requests are mapped on the client side by the chunk lists in - * the RPCRDMA header. During the fetching of the RPC from the client - * and the writing of the reply to the client, the memory in the - * client and the memory in the server must be mapped as contiguous - * vaddr/len for access by the hardware. These data strucures keep - * these mappings. - * - * For an RDMA_WRITE, the 'sge' maps the RPC REPLY. For RDMA_READ, the - * 'sge' in the svc_rdma_req_map maps the server side RPC reply and the - * 'ch' field maps the read-list of the RPCRDMA header to the 'sge' - * mapping of the reply. - */ -struct svc_rdma_chunk_sge { - int start; /* sge no for this chunk */ - int count; /* sge count for this chunk */ -}; -struct svc_rdma_fastreg_mr { - struct ib_mr *mr; - struct scatterlist *sg; - int sg_nents; - unsigned long access_flags; - enum dma_data_direction direction; - struct list_head frmr_list; -}; -struct svc_rdma_req_map { - struct list_head free; - unsigned long count; - union { - struct kvec sge[RPCSVC_MAXPAGES]; - struct svc_rdma_chunk_sge ch[RPCSVC_MAXPAGES]; - unsigned long lkey[RPCSVC_MAXPAGES]; - }; -}; -#define RDMACTXT_F_LAST_CTXT 2 - -#define SVCRDMA_DEVCAP_FAST_REG 1 /* fast mr registration */ -#define SVCRDMA_DEVCAP_READ_W_INV 2 /* read w/ invalidate */ - struct svcxprt_rdma { struct svc_xprt sc_xprt; /* SVC transport structure */ struct rdma_cm_id *sc_cm_id; /* RDMA connection id */ struct list_head sc_accept_q; /* Conn. waiting accept */ int sc_ord; /* RDMA read limit */ int sc_max_sge; - int sc_max_sge_rd; /* max sge for read target */ bool sc_snd_w_inv; /* OK to use Send With Invalidate */ atomic_t sc_sq_avail; /* SQEs ready to be consumed */ unsigned int sc_sq_depth; /* Depth of SQ */ unsigned int sc_rq_depth; /* Depth of RQ */ - u32 sc_max_requests; /* Forward credits */ + __be32 sc_fc_credits; /* Forward credits */ + u32 sc_max_requests; /* Max requests */ u32 sc_max_bc_requests;/* Backward credits */ int sc_max_req_size; /* Size of each RQ WR buf */ + u8 sc_port_num; struct ib_pd *sc_pd; spinlock_t sc_ctxt_lock; struct list_head sc_ctxts; int sc_ctxt_used; - spinlock_t sc_map_lock; - struct list_head sc_maps; + spinlock_t sc_rw_ctxt_lock; + struct list_head sc_rw_ctxts; struct list_head sc_rq_dto_q; spinlock_t sc_rq_dto_lock; struct ib_qp *sc_qp; struct ib_cq *sc_rq_cq; struct ib_cq *sc_sq_cq; - int (*sc_reader)(struct svcxprt_rdma *, - struct svc_rqst *, - struct svc_rdma_op_ctxt *, - int *, u32 *, u32, u32, u64, bool); - u32 sc_dev_caps; /* distilled device caps */ - unsigned int sc_frmr_pg_list_len; - struct list_head sc_frmr_q; - spinlock_t sc_frmr_q_lock; spinlock_t sc_lock; /* transport lock */ wait_queue_head_t sc_send_wait; /* SQ exhaustion waitlist */ unsigned long sc_flags; - struct list_head sc_dto_q; /* DTO tasklet I/O pending Q */ struct list_head sc_read_complete_q; struct work_struct sc_work; }; @@ -182,9 +135,7 @@ struct svcxprt_rdma { /* The default ORD value is based on two outstanding full-size writes with a * page size of 4k, or 32k * 2 ops / 4k = 16 outstanding RDMA_READ. */ #define RPCRDMA_ORD (64/4) -#define RPCRDMA_SQ_DEPTH_MULT 8 #define RPCRDMA_MAX_REQUESTS 32 -#define RPCRDMA_MAX_REQ_SIZE 4096 /* Typical ULP usage of BC requests is NFSv4.1 backchannel. Our * current NFSv4.1 implementation supports one backchannel slot. @@ -202,43 +153,34 @@ static inline void svc_rdma_count_mappings(struct svcxprt_rdma *rdma, /* svc_rdma_backchannel.c */ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, - struct rpcrdma_msg *rmsgp, + __be32 *rdma_resp, struct xdr_buf *rcvbuf); -/* svc_rdma_marshal.c */ -extern int svc_rdma_xdr_decode_req(struct xdr_buf *); -extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *, - struct rpcrdma_msg *, - enum rpcrdma_errcode, __be32 *); -extern void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *, int); -extern void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *, int); -extern void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *, int, - __be32, __be64, u32); -extern void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *, - struct rpcrdma_msg *, - struct rpcrdma_msg *, - enum rpcrdma_proc); -extern int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *); - /* svc_rdma_recvfrom.c */ extern int svc_rdma_recvfrom(struct svc_rqst *); -extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *, - struct svc_rdma_op_ctxt *, int *, u32 *, - u32, u32, u64, bool); -extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *, - struct svc_rdma_op_ctxt *, int *, u32 *, - u32, u32, u64, bool); + +/* svc_rdma_rw.c */ +extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma); +extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, + struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *head, __be32 *p); +extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, + __be32 *wr_ch, struct xdr_buf *xdr); +extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, + __be32 *rp_ch, bool writelist, + struct xdr_buf *xdr); /* svc_rdma_sendto.c */ -extern int svc_rdma_map_xdr(struct svcxprt_rdma *, struct xdr_buf *, - struct svc_rdma_req_map *, bool); +extern int svc_rdma_map_reply_hdr(struct svcxprt_rdma *rdma, + struct svc_rdma_op_ctxt *ctxt, + __be32 *rdma_resp, unsigned int len); +extern int svc_rdma_post_send_wr(struct svcxprt_rdma *rdma, + struct svc_rdma_op_ctxt *ctxt, + int num_sge, u32 inv_rkey); extern int svc_rdma_sendto(struct svc_rqst *); -extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *, - int); /* svc_rdma_transport.c */ extern void svc_rdma_wc_send(struct ib_cq *, struct ib_wc *); -extern void svc_rdma_wc_write(struct ib_cq *, struct ib_wc *); extern void svc_rdma_wc_reg(struct ib_cq *, struct ib_wc *); extern void svc_rdma_wc_read(struct ib_cq *, struct ib_wc *); extern void svc_rdma_wc_inv(struct ib_cq *, struct ib_wc *); @@ -249,12 +191,6 @@ extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int); extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt); -extern struct svc_rdma_req_map *svc_rdma_get_req_map(struct svcxprt_rdma *); -extern void svc_rdma_put_req_map(struct svcxprt_rdma *, - struct svc_rdma_req_map *); -extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *); -extern void svc_rdma_put_frmr(struct svcxprt_rdma *, - struct svc_rdma_fastreg_mr *); extern void svc_sq_reap(struct svcxprt_rdma *); extern void svc_rq_reap(struct svcxprt_rdma *); extern void svc_rdma_prep_reply_hdr(struct svc_rqst *); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 7440290f64ac..ddb7f94a9d06 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -67,6 +67,7 @@ struct svc_xprt { #define XPT_CACHE_AUTH 11 /* cache auth info */ #define XPT_LOCAL 12 /* connection from loopback interface */ #define XPT_KILL_TEMP 13 /* call xpo_kill_temp_xprt before closing */ +#define XPT_CONG_CTRL 14 /* has congestion control */ struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ diff --git a/include/linux/sunrpc/types.h b/include/linux/sunrpc/types.h index d222f47550af..11a7536c0fd2 100644 --- a/include/linux/sunrpc/types.h +++ b/include/linux/sunrpc/types.h @@ -10,6 +10,7 @@ #define _LINUX_SUNRPC_TYPES_H_ #include <linux/timer.h> +#include <linux/sched/signal.h> #include <linux/workqueue.h> #include <linux/sunrpc/debug.h> #include <linux/list.h> diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 56c48c884a24..261b48a2701d 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -17,6 +17,8 @@ #include <asm/unaligned.h> #include <linux/scatterlist.h> +struct rpc_rqst; + /* * Buffer adjustment */ @@ -33,13 +35,6 @@ struct xdr_netobj { }; /* - * This is the legacy generic XDR function. rqstp is either a rpc_rqst - * (client side) or svc_rqst pointer (server side). - * Encode functions always assume there's enough room in the buffer. - */ -typedef int (*kxdrproc_t)(void *rqstp, __be32 *data, void *obj); - -/* * Basic structure for transmission/reception of a client XDR message. * Features a header (for a linear buffer containing RPC headers * and the data payload for short messages), and then an array of @@ -222,8 +217,10 @@ struct xdr_stream { /* * These are the xdr_stream style generic XDR encode and decode functions. */ -typedef void (*kxdreproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); -typedef int (*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); +typedef void (*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + const void *obj); +typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *obj); extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); @@ -242,6 +239,185 @@ extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data); +ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, + size_t maxlen, gfp_t gfp_flags); +/** + * xdr_align_size - Calculate padded size of an object + * @n: Size of an object being XDR encoded (in bytes) + * + * Return value: + * Size (in bytes) of the object including xdr padding + */ +static inline size_t +xdr_align_size(size_t n) +{ + const size_t mask = sizeof(__u32) - 1; + + return (n + mask) & ~mask; +} + +/** + * xdr_stream_encode_u32 - Encode a 32-bit integer + * @xdr: pointer to xdr_stream + * @n: integer to encode + * + * Return values: + * On success, returns length in bytes of XDR buffer consumed + * %-EMSGSIZE on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_encode_u32(struct xdr_stream *xdr, __u32 n) +{ + const size_t len = sizeof(n); + __be32 *p = xdr_reserve_space(xdr, len); + + if (unlikely(!p)) + return -EMSGSIZE; + *p = cpu_to_be32(n); + return len; +} + +/** + * xdr_stream_encode_u64 - Encode a 64-bit integer + * @xdr: pointer to xdr_stream + * @n: 64-bit integer to encode + * + * Return values: + * On success, returns length in bytes of XDR buffer consumed + * %-EMSGSIZE on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_encode_u64(struct xdr_stream *xdr, __u64 n) +{ + const size_t len = sizeof(n); + __be32 *p = xdr_reserve_space(xdr, len); + + if (unlikely(!p)) + return -EMSGSIZE; + xdr_encode_hyper(p, n); + return len; +} + +/** + * xdr_stream_encode_opaque_fixed - Encode fixed length opaque xdr data + * @xdr: pointer to xdr_stream + * @ptr: pointer to opaque data object + * @len: size of object pointed to by @ptr + * + * Return values: + * On success, returns length in bytes of XDR buffer consumed + * %-EMSGSIZE on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_encode_opaque_fixed(struct xdr_stream *xdr, const void *ptr, size_t len) +{ + __be32 *p = xdr_reserve_space(xdr, len); + + if (unlikely(!p)) + return -EMSGSIZE; + xdr_encode_opaque_fixed(p, ptr, len); + return xdr_align_size(len); +} + +/** + * xdr_stream_encode_opaque - Encode variable length opaque xdr data + * @xdr: pointer to xdr_stream + * @ptr: pointer to opaque data object + * @len: size of object pointed to by @ptr + * + * Return values: + * On success, returns length in bytes of XDR buffer consumed + * %-EMSGSIZE on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_encode_opaque(struct xdr_stream *xdr, const void *ptr, size_t len) +{ + size_t count = sizeof(__u32) + xdr_align_size(len); + __be32 *p = xdr_reserve_space(xdr, count); + + if (unlikely(!p)) + return -EMSGSIZE; + xdr_encode_opaque(p, ptr, len); + return count; +} + +/** + * xdr_stream_decode_u32 - Decode a 32-bit integer + * @xdr: pointer to xdr_stream + * @ptr: location to store integer + * + * Return values: + * %0 on success + * %-EBADMSG on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_decode_u32(struct xdr_stream *xdr, __u32 *ptr) +{ + const size_t count = sizeof(*ptr); + __be32 *p = xdr_inline_decode(xdr, count); + + if (unlikely(!p)) + return -EBADMSG; + *ptr = be32_to_cpup(p); + return 0; +} + +/** + * xdr_stream_decode_opaque_fixed - Decode fixed length opaque xdr data + * @xdr: pointer to xdr_stream + * @ptr: location to store data + * @len: size of buffer pointed to by @ptr + * + * Return values: + * On success, returns size of object stored in @ptr + * %-EBADMSG on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_decode_opaque_fixed(struct xdr_stream *xdr, void *ptr, size_t len) +{ + __be32 *p = xdr_inline_decode(xdr, len); + + if (unlikely(!p)) + return -EBADMSG; + xdr_decode_opaque_fixed(p, ptr, len); + return len; +} + +/** + * xdr_stream_decode_opaque_inline - Decode variable length opaque xdr data + * @xdr: pointer to xdr_stream + * @ptr: location to store pointer to opaque data + * @maxlen: maximum acceptable object size + * + * Note: the pointer stored in @ptr cannot be assumed valid after the XDR + * buffer has been destroyed, or even after calling xdr_inline_decode() + * on @xdr. It is therefore expected that the object it points to should + * be processed immediately. + * + * Return values: + * On success, returns size of object stored in *@ptr + * %-EBADMSG on XDR buffer overflow + * %-EMSGSIZE if the size of the object would exceed @maxlen + */ +static inline ssize_t +xdr_stream_decode_opaque_inline(struct xdr_stream *xdr, void **ptr, size_t maxlen) +{ + __be32 *p; + __u32 len; + + *ptr = NULL; + if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) + return -EBADMSG; + if (len != 0) { + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return -EBADMSG; + if (unlikely(len > maxlen)) + return -EMSGSIZE; + *ptr = p; + } + return len; +} #endif /* __KERNEL__ */ #endif /* _SUNRPC_XDR_H_ */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index a5da60b24d83..eab1c749e192 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -137,6 +137,9 @@ struct rpc_xprt_ops { void (*release_request)(struct rpc_task *task); void (*close)(struct rpc_xprt *xprt); void (*destroy)(struct rpc_xprt *xprt); + void (*set_connect_timeout)(struct rpc_xprt *xprt, + unsigned long connect_timeout, + unsigned long reconnect_timeout); void (*print_stats)(struct rpc_xprt *xprt, struct seq_file *seq); int (*enable_swap)(struct rpc_xprt *xprt); void (*disable_swap)(struct rpc_xprt *xprt); @@ -221,6 +224,7 @@ struct rpc_xprt { struct timer_list timer; unsigned long last_used, idle_timeout, + connect_timeout, max_reconnect_timeout; /* diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index bef3fb0abb8f..c9959d7e3579 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -55,6 +55,8 @@ struct sock_xprt { size_t rcvsize, sndsize; + struct rpc_timeout tcp_timeout; + /* * Saved socket callback addresses */ @@ -81,6 +83,7 @@ struct sock_xprt { #define XPRT_SOCK_CONNECTING 1U #define XPRT_SOCK_DATA_READY (2) +#define XPRT_SOCK_UPD_TIMEOUT (3) #endif /* __KERNEL__ */ diff --git a/include/linux/superhyway.h b/include/linux/superhyway.h index 17ea468fa362..8d3376775813 100644 --- a/include/linux/superhyway.h +++ b/include/linux/superhyway.h @@ -101,7 +101,7 @@ int superhyway_add_device(unsigned long base, struct superhyway_device *, struct int superhyway_add_devices(struct superhyway_bus *bus, struct superhyway_device **devices, int nr_devices); /* drivers/sh/superhyway/superhyway-sysfs.c */ -extern struct device_attribute superhyway_dev_attrs[]; +extern const struct attribute_group *superhyway_dev_groups[]; #endif /* __LINUX_SUPERHYWAY_H */ diff --git a/include/linux/suspend.h b/include/linux/suspend.h index d9718378a8be..0b1cf32edfd7 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -189,6 +189,8 @@ struct platform_suspend_ops { struct platform_freeze_ops { int (*begin)(void); int (*prepare)(void); + void (*wake)(void); + void (*sync)(void); void (*restore)(void); void (*end)(void); }; @@ -428,7 +430,8 @@ extern unsigned int pm_wakeup_irq; extern bool pm_wakeup_pending(void); extern void pm_system_wakeup(void); -extern void pm_wakeup_clear(void); +extern void pm_system_cancel_wakeup(void); +extern void pm_wakeup_clear(bool reset); extern void pm_system_irq_wakeup(unsigned int irq_number); extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); @@ -478,7 +481,7 @@ static inline int unregister_pm_notifier(struct notifier_block *nb) static inline bool pm_wakeup_pending(void) { return false; } static inline void pm_system_wakeup(void) {} -static inline void pm_wakeup_clear(void) {} +static inline void pm_wakeup_clear(bool reset) {} static inline void pm_system_irq_wakeup(unsigned int irq_number) {} static inline void lock_system_sleep(void) {} diff --git a/include/linux/swap.h b/include/linux/swap.h index 7f47b7098b1b..d83d28e53e62 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -27,6 +27,7 @@ struct bio; #define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \ SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \ SWAP_FLAG_DISCARD_PAGES) +#define SWAP_BATCH 64 static inline int current_is_kswapd(void) { @@ -176,6 +177,12 @@ enum { * protected by swap_info_struct.lock. */ struct swap_cluster_info { + spinlock_t lock; /* + * Protect swap_cluster_info fields + * and swap_info_struct->swap_map + * elements correspond to the swap + * cluster + */ unsigned int data:24; unsigned int flags:8; }; @@ -270,9 +277,10 @@ extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); +extern void lru_add_drain_all_cpuslocked(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); -extern void deactivate_page(struct page *page); +extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); extern void add_page_to_unevictable_list(struct page *page); @@ -324,7 +332,7 @@ extern void kswapd_stop(int nid); #include <linux/blk_types.h> /* for bio_end_io_t */ /* linux/mm/page_io.c */ -extern int swap_readpage(struct page *); +extern int swap_readpage(struct page *page, bool do_poll); extern int swap_writepage(struct page *page, struct writeback_control *wbc); extern void end_swap_bio_write(struct bio *bio); extern int __swap_writepage(struct page *page, struct writeback_control *wbc, @@ -337,11 +345,16 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); /* linux/mm/swap_state.c */ -extern struct address_space swapper_spaces[]; -#define swap_address_space(entry) (&swapper_spaces[swp_type(entry)]) +/* One swap address space for each 64M swap space */ +#define SWAP_ADDRESS_SPACE_SHIFT 14 +#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) +extern struct address_space *swapper_spaces[]; +#define swap_address_space(entry) \ + (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ + >> SWAP_ADDRESS_SPACE_SHIFT]) extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); -extern int add_to_swap(struct page *, struct list_head *list); +extern int add_to_swap(struct page *page); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); extern int __add_to_swap_cache(struct page *page, swp_entry_t entry); extern void __delete_from_swap_cache(struct page *); @@ -350,7 +363,8 @@ extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr); + struct vm_area_struct *vma, unsigned long addr, + bool do_poll); extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool *new_page_allocated); @@ -360,6 +374,7 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t, /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; +extern bool has_usable_swap(void); /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) @@ -373,25 +388,30 @@ static inline long get_nr_swap_pages(void) } extern void si_swapinfo(struct sysinfo *); -extern swp_entry_t get_swap_page(void); +extern swp_entry_t get_swap_page(struct page *page); +extern void put_swap_page(struct page *page, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); +extern int get_swap_pages(int n, bool cluster, swp_entry_t swp_entries[]); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); -extern void swapcache_free(swp_entry_t); +extern void swapcache_free_entries(swp_entry_t *entries, int n); extern int free_swap_and_cache(swp_entry_t); extern int swap_type_of(dev_t, sector_t, struct block_device **); extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); extern int page_swapcount(struct page *); +extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern bool reuse_swap_page(struct page *, int *); extern int try_to_free_swap(struct page *); struct backing_dev_info; +extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); +extern void exit_swap_address_space(unsigned int type); #else /* CONFIG_SWAP */ @@ -435,7 +455,7 @@ static inline void swap_free(swp_entry_t swp) { } -static inline void swapcache_free(swp_entry_t swp) +static inline void put_swap_page(struct page *page, swp_entry_t swp) { } @@ -455,7 +475,7 @@ static inline struct page *lookup_swap_cache(swp_entry_t swp) return NULL; } -static inline int add_to_swap(struct page *page, struct list_head *list) +static inline int add_to_swap(struct page *page) { return 0; } @@ -479,6 +499,11 @@ static inline int page_swapcount(struct page *page) return 0; } +static inline int __swp_swapcount(swp_entry_t entry) +{ + return 0; +} + static inline int swp_swapcount(swp_entry_t entry) { return 0; @@ -492,7 +517,7 @@ static inline int try_to_free_swap(struct page *page) return 0; } -static inline swp_entry_t get_swap_page(void) +static inline swp_entry_t get_swap_page(struct page *page) { swp_entry_t entry; entry.val = 0; @@ -525,7 +550,7 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) #ifdef CONFIG_MEMCG_SWAP extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); -extern void mem_cgroup_uncharge_swap(swp_entry_t entry); +extern void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct page *page); #else @@ -539,7 +564,8 @@ static inline int mem_cgroup_try_charge_swap(struct page *page, return 0; } -static inline void mem_cgroup_uncharge_swap(swp_entry_t entry) +static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, + unsigned int nr_pages) { } diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h index 145306bdc92f..b2b8ec7bda3f 100644 --- a/include/linux/swap_cgroup.h +++ b/include/linux/swap_cgroup.h @@ -7,7 +7,8 @@ extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, unsigned short old, unsigned short new); -extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id); +extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, + unsigned int nr_ents); extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent); extern int swap_cgroup_swapon(int type, unsigned long max_pages); extern void swap_cgroup_swapoff(int type); @@ -15,7 +16,8 @@ extern void swap_cgroup_swapoff(int type); #else static inline -unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) +unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, + unsigned int nr_ents) { return 0; } diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h new file mode 100644 index 000000000000..6ef92d17633d --- /dev/null +++ b/include/linux/swap_slots.h @@ -0,0 +1,30 @@ +#ifndef _LINUX_SWAP_SLOTS_H +#define _LINUX_SWAP_SLOTS_H + +#include <linux/swap.h> +#include <linux/spinlock.h> +#include <linux/mutex.h> + +#define SWAP_SLOTS_CACHE_SIZE SWAP_BATCH +#define THRESHOLD_ACTIVATE_SWAP_SLOTS_CACHE (5*SWAP_SLOTS_CACHE_SIZE) +#define THRESHOLD_DEACTIVATE_SWAP_SLOTS_CACHE (2*SWAP_SLOTS_CACHE_SIZE) + +struct swap_slots_cache { + bool lock_initialized; + struct mutex alloc_lock; /* protects slots, nr, cur */ + swp_entry_t *slots; + int nr; + int cur; + spinlock_t free_lock; /* protects slots_ret, n_ret */ + swp_entry_t *slots_ret; + int n_ret; +}; + +void disable_swap_slots_cache_lock(void); +void reenable_swap_slots_cache_unlock(void); +int enable_swap_slots_cache(void); +int free_swap_slot(swp_entry_t entry); + +extern bool swap_slot_cache_enabled; + +#endif /* _LINUX_SWAP_SLOTS_H */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5c3a5f3e7eec..c5ff7b217ee6 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -196,15 +196,6 @@ static inline void num_poisoned_pages_dec(void) atomic_long_dec(&num_poisoned_pages); } -static inline void num_poisoned_pages_add(long num) -{ - atomic_long_add(num, &num_poisoned_pages); -} - -static inline void num_poisoned_pages_sub(long num) -{ - atomic_long_sub(num, &num_poisoned_pages); -} #else static inline swp_entry_t make_hwpoison_entry(struct page *page) diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h index 3e3ab84fc4cd..5726107963b2 100644 --- a/include/linux/sync_file.h +++ b/include/linux/sync_file.h @@ -14,7 +14,6 @@ #define _LINUX_SYNC_FILE_H #include <linux/types.h> -#include <linux/kref.h> #include <linux/ktime.h> #include <linux/list.h> #include <linux/spinlock.h> @@ -24,8 +23,6 @@ /** * struct sync_file - sync file to export to the userspace * @file: file representing this fence - * @kref: reference count on fence. - * @name: name of sync_file. Useful for debugging * @sync_file_list: membership in global file list * @wq: wait queue for fence signaling * @fence: fence with the fences in the sync_file @@ -33,8 +30,14 @@ */ struct sync_file { struct file *file; - struct kref kref; - char name[32]; + /** + * @user_name: + * + * Name of the sync file provided by userspace, for merged fences. + * Otherwise generated through driver callbacks (in which case the + * entire array is 0). + */ + char user_name[32]; #ifdef CONFIG_DEBUG_FS struct list_head sync_file_list; #endif @@ -49,5 +52,6 @@ struct sync_file { struct sync_file *sync_file_create(struct dma_fence *fence); struct dma_fence *sync_file_get_fence(int fd); +char *sync_file_get_name(struct sync_file *sync_file, char *buf, int len); #endif /* _LINUX_SYNC_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 91a740f6b884..3cb15ea48aee 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -48,6 +48,7 @@ struct stat; struct stat64; struct statfs; struct statfs64; +struct statx; struct __sysctl_args; struct sysinfo; struct timespec; @@ -649,7 +650,7 @@ asmlinkage long sys_olduname(struct oldold_utsname __user *); asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim); -#if defined(COMPAT_RLIM_OLD_INFINITY) || !(defined(CONFIG_IA64)) +#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim); #endif asmlinkage long sys_setrlimit(unsigned int resource, @@ -902,5 +903,7 @@ asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len, unsigned long prot, int pkey); asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val); asmlinkage long sys_pkey_free(int pkey); +asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, + unsigned mask, struct statx __user *buffer); #endif diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index adf4e51cf597..1d4dba490fb6 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -47,6 +47,9 @@ extern int proc_douintvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, @@ -117,7 +120,7 @@ struct ctl_table struct ctl_table_poll *poll; void *extra1; void *extra2; -}; +} __randomize_layout; struct ctl_node { struct rb_node node; @@ -143,6 +146,7 @@ struct ctl_table_header struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; + struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */ }; struct ctl_dir { @@ -179,7 +183,6 @@ extern void setup_sysctl_set(struct ctl_table_set *p, int (*is_seen)(struct ctl_table_set *)); extern void retire_sysctl_set(struct ctl_table_set *set); -void register_sysctl_root(struct ctl_table_root *root); struct ctl_table_header *__register_sysctl_table( struct ctl_table_set *set, const char *path, struct ctl_table *table); diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index c6f0f0d0e17e..aa02c328dff5 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -512,7 +512,7 @@ static inline void sysfs_notify_dirent(struct kernfs_node *kn) } static inline struct kernfs_node *sysfs_get_dirent(struct kernfs_node *parent, - const unsigned char *name) + const char *name) { return kernfs_find_and_get(parent, name); } diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index 9fba9dd33544..635a3c5706bd 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -33,10 +33,12 @@ struct t10_pi_tuple { __be32 ref_tag; /* Target LBA or indirect LBA */ }; +#define T10_PI_APP_ESCAPE cpu_to_be16(0xffff) +#define T10_PI_REF_ESCAPE cpu_to_be32(0xffffffff) -extern struct blk_integrity_profile t10_pi_type1_crc; -extern struct blk_integrity_profile t10_pi_type1_ip; -extern struct blk_integrity_profile t10_pi_type3_crc; -extern struct blk_integrity_profile t10_pi_type3_ip; +extern const struct blk_integrity_profile t10_pi_type1_crc; +extern const struct blk_integrity_profile t10_pi_type1_ip; +extern const struct blk_integrity_profile t10_pi_type3_crc; +extern const struct blk_integrity_profile t10_pi_type3_ip; #endif diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index 58de6edf751f..e2a5daf8d14f 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -8,7 +8,7 @@ #define _LINUX_TASKSTATS_KERN_H #include <linux/taskstats.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> #include <linux/slab.h> #ifdef CONFIG_TASKSTATS diff --git a/include/linux/tcp.h b/include/linux/tcp.h index c93f4b3a59cb..542ca1ae02c4 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -123,7 +123,7 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; - struct skb_mstamp snt_synack; /* first SYNACK sent time */ + u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; u32 txhash; u32 rcv_isn; @@ -211,7 +211,9 @@ struct tcp_sock { /* Information of the most recently (s)acked skb */ struct tcp_rack { - struct skb_mstamp mstamp; /* (Re)sent time of the skb */ + u64 mstamp; /* (Re)sent time of the skb */ + u32 rtt_us; /* Associated RTT */ + u32 end_seq; /* Ending TCP sequence of the skb */ u8 advanced; /* mstamp advanced since last lost marking */ u8 reord; /* reordering detected */ } rack; @@ -220,23 +222,25 @@ struct tcp_sock { u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ - unused:5; + fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ + unused:4; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ - thin_dupack : 1,/* Fast retransmit on first dupack */ + unused1 : 1, repair : 1, frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; - u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ - syn_data:1, /* SYN includes data */ + u8 syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ + syn_fastopen_ch:1, /* Active TFO re-enabling probe */ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ save_syn:1, /* Save headers of SYN packet */ is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ /* RTT measurement */ + u64 tcp_mstamp; /* most recent packet received/sent */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ @@ -276,8 +280,8 @@ struct tcp_sock { u32 delivered; /* Total data packets delivered incl. rexmits */ u32 lost; /* Total data packets lost incl. rexmits */ u32 app_limited; /* limited until "delivered" reaches this val */ - struct skb_mstamp first_tx_mstamp; /* start of window send phase */ - struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */ + u64 first_tx_mstamp; /* start of window send phase */ + u64 delivered_mstamp; /* time we reached "delivered" */ u32 rate_delivered; /* saved rate sample: packets delivered */ u32 rate_interval_us; /* saved rate sample: time elapsed */ @@ -289,6 +293,8 @@ struct tcp_sock { u32 sacked_out; /* SACK'd packets */ u32 fackets_out; /* FACK'd packets */ + struct hrtimer pacing_timer; + /* from STCP, retrans queue hinting */ struct sk_buff* lost_skb_hint; struct sk_buff *retransmit_skb_hint; @@ -310,7 +316,6 @@ struct tcp_sock { */ int lost_cnt_hint; - u32 retransmit_high; /* L-bits may be on up to this seqno */ u32 prior_ssthresh; /* ssthresh saved at recovery start */ u32 high_seq; /* snd_nxt at onset of congestion */ @@ -330,16 +335,16 @@ struct tcp_sock { /* Receiver side RTT estimation */ struct { - u32 rtt; + u32 rtt_us; u32 seq; - u32 time; + u64 time; } rcv_rtt_est; /* Receiver queue space */ struct { int space; u32 seq; - u32 time; + u64 time; } rcvq_space; /* TCP-specific MTU probe information. */ @@ -444,4 +449,13 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk); +static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) +{ + /* We use READ_ONCE() here because socket might not be locked. + * This happens for listeners. + */ + u16 user_mss = READ_ONCE(tp->rx_opt.user_mss); + + return (user_mss && user_mss < mss) ? user_mss : mss; +} #endif /* _LINUX_TCP_H */ diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h new file mode 100644 index 000000000000..0f175b8f6456 --- /dev/null +++ b/include/linux/tee_drv.h @@ -0,0 +1,277 @@ +/* + * Copyright (c) 2015-2016, Linaro Limited + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef __TEE_DRV_H +#define __TEE_DRV_H + +#include <linux/types.h> +#include <linux/idr.h> +#include <linux/list.h> +#include <linux/tee.h> + +/* + * The file describes the API provided by the generic TEE driver to the + * specific TEE driver. + */ + +#define TEE_SHM_MAPPED 0x1 /* Memory mapped by the kernel */ +#define TEE_SHM_DMA_BUF 0x2 /* Memory with dma-buf handle */ + +struct tee_device; +struct tee_shm; +struct tee_shm_pool; + +/** + * struct tee_context - driver specific context on file pointer data + * @teedev: pointer to this drivers struct tee_device + * @list_shm: List of shared memory object owned by this context + * @data: driver specific context data, managed by the driver + */ +struct tee_context { + struct tee_device *teedev; + struct list_head list_shm; + void *data; +}; + +struct tee_param_memref { + size_t shm_offs; + size_t size; + struct tee_shm *shm; +}; + +struct tee_param_value { + u64 a; + u64 b; + u64 c; +}; + +struct tee_param { + u64 attr; + union { + struct tee_param_memref memref; + struct tee_param_value value; + } u; +}; + +/** + * struct tee_driver_ops - driver operations vtable + * @get_version: returns version of driver + * @open: called when the device file is opened + * @release: release this open file + * @open_session: open a new session + * @close_session: close a session + * @invoke_func: invoke a trusted function + * @cancel_req: request cancel of an ongoing invoke or open + * @supp_revc: called for supplicant to get a command + * @supp_send: called for supplicant to send a response + */ +struct tee_driver_ops { + void (*get_version)(struct tee_device *teedev, + struct tee_ioctl_version_data *vers); + int (*open)(struct tee_context *ctx); + void (*release)(struct tee_context *ctx); + int (*open_session)(struct tee_context *ctx, + struct tee_ioctl_open_session_arg *arg, + struct tee_param *param); + int (*close_session)(struct tee_context *ctx, u32 session); + int (*invoke_func)(struct tee_context *ctx, + struct tee_ioctl_invoke_arg *arg, + struct tee_param *param); + int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session); + int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params, + struct tee_param *param); + int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params, + struct tee_param *param); +}; + +/** + * struct tee_desc - Describes the TEE driver to the subsystem + * @name: name of driver + * @ops: driver operations vtable + * @owner: module providing the driver + * @flags: Extra properties of driver, defined by TEE_DESC_* below + */ +#define TEE_DESC_PRIVILEGED 0x1 +struct tee_desc { + const char *name; + const struct tee_driver_ops *ops; + struct module *owner; + u32 flags; +}; + +/** + * tee_device_alloc() - Allocate a new struct tee_device instance + * @teedesc: Descriptor for this driver + * @dev: Parent device for this device + * @pool: Shared memory pool, NULL if not used + * @driver_data: Private driver data for this device + * + * Allocates a new struct tee_device instance. The device is + * removed by tee_device_unregister(). + * + * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure + */ +struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, + struct device *dev, + struct tee_shm_pool *pool, + void *driver_data); + +/** + * tee_device_register() - Registers a TEE device + * @teedev: Device to register + * + * tee_device_unregister() need to be called to remove the @teedev if + * this function fails. + * + * @returns < 0 on failure + */ +int tee_device_register(struct tee_device *teedev); + +/** + * tee_device_unregister() - Removes a TEE device + * @teedev: Device to unregister + * + * This function should be called to remove the @teedev even if + * tee_device_register() hasn't been called yet. Does nothing if + * @teedev is NULL. + */ +void tee_device_unregister(struct tee_device *teedev); + +/** + * struct tee_shm_pool_mem_info - holds information needed to create a shared + * memory pool + * @vaddr: Virtual address of start of pool + * @paddr: Physical address of start of pool + * @size: Size in bytes of the pool + */ +struct tee_shm_pool_mem_info { + unsigned long vaddr; + phys_addr_t paddr; + size_t size; +}; + +/** + * tee_shm_pool_alloc_res_mem() - Create a shared memory pool from reserved + * memory range + * @priv_info: Information for driver private shared memory pool + * @dmabuf_info: Information for dma-buf shared memory pool + * + * Start and end of pools will must be page aligned. + * + * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied + * in @dmabuf, others will use the range provided by @priv. + * + * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. + */ +struct tee_shm_pool * +tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info, + struct tee_shm_pool_mem_info *dmabuf_info); + +/** + * tee_shm_pool_free() - Free a shared memory pool + * @pool: The shared memory pool to free + * + * The must be no remaining shared memory allocated from this pool when + * this function is called. + */ +void tee_shm_pool_free(struct tee_shm_pool *pool); + +/** + * tee_get_drvdata() - Return driver_data pointer + * @returns the driver_data pointer supplied to tee_register(). + */ +void *tee_get_drvdata(struct tee_device *teedev); + +/** + * tee_shm_alloc() - Allocate shared memory + * @ctx: Context that allocates the shared memory + * @size: Requested size of shared memory + * @flags: Flags setting properties for the requested shared memory. + * + * Memory allocated as global shared memory is automatically freed when the + * TEE file pointer is closed. The @flags field uses the bits defined by + * TEE_SHM_* above. TEE_SHM_MAPPED must currently always be set. If + * TEE_SHM_DMA_BUF global shared memory will be allocated and associated + * with a dma-buf handle, else driver private memory. + * + * @returns a pointer to 'struct tee_shm' + */ +struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags); + +/** + * tee_shm_free() - Free shared memory + * @shm: Handle to shared memory to free + */ +void tee_shm_free(struct tee_shm *shm); + +/** + * tee_shm_put() - Decrease reference count on a shared memory handle + * @shm: Shared memory handle + */ +void tee_shm_put(struct tee_shm *shm); + +/** + * tee_shm_va2pa() - Get physical address of a virtual address + * @shm: Shared memory handle + * @va: Virtual address to tranlsate + * @pa: Returned physical address + * @returns 0 on success and < 0 on failure + */ +int tee_shm_va2pa(struct tee_shm *shm, void *va, phys_addr_t *pa); + +/** + * tee_shm_pa2va() - Get virtual address of a physical address + * @shm: Shared memory handle + * @pa: Physical address to tranlsate + * @va: Returned virtual address + * @returns 0 on success and < 0 on failure + */ +int tee_shm_pa2va(struct tee_shm *shm, phys_addr_t pa, void **va); + +/** + * tee_shm_get_va() - Get virtual address of a shared memory plus an offset + * @shm: Shared memory handle + * @offs: Offset from start of this shared memory + * @returns virtual address of the shared memory + offs if offs is within + * the bounds of this shared memory, else an ERR_PTR + */ +void *tee_shm_get_va(struct tee_shm *shm, size_t offs); + +/** + * tee_shm_get_pa() - Get physical address of a shared memory plus an offset + * @shm: Shared memory handle + * @offs: Offset from start of this shared memory + * @pa: Physical address to return + * @returns 0 if offs is within the bounds of this shared memory, else an + * error code. + */ +int tee_shm_get_pa(struct tee_shm *shm, size_t offs, phys_addr_t *pa); + +/** + * tee_shm_get_id() - Get id of a shared memory object + * @shm: Shared memory handle + * @returns id + */ +int tee_shm_get_id(struct tee_shm *shm); + +/** + * tee_shm_get_from_id() - Find shared memory object and increase reference + * count + * @ctx: Context owning the shared memory + * @id: Id of shared memory object + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure + */ +struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); + +#endif /*__TEE_DRV_H*/ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index e275e98bdceb..dab11f97e1c6 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -194,7 +194,7 @@ struct thermal_attr { * @governor: pointer to the governor for this thermal zone * @governor_data: private pointer for governor data * @thermal_instances: list of &struct thermal_instance of this thermal zone - * @idr: &struct idr to generate unique id for this zone's cooling + * @ida: &struct ida to generate unique id for this zone's cooling * devices * @lock: lock to protect thermal_instances list * @node: node in thermal_tz_list (in thermal_core.c) @@ -227,7 +227,7 @@ struct thermal_zone_device { struct thermal_governor *governor; void *governor_data; struct list_head thermal_instances; - struct idr idr; + struct ida ida; struct mutex lock; struct list_head node; struct delayed_work poll_queue; diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 58373875e8ee..250a27614328 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -22,6 +22,18 @@ #endif #include <linux/bitops.h> + +/* + * For per-arch arch_within_stack_frames() implementations, defined in + * asm/thread_info.h. + */ +enum { + BAD_STACK = -1, + NOT_STACK = 0, + GOOD_FRAME, + GOOD_STACK, +}; + #include <asm/thread_info.h> #ifdef __KERNEL__ @@ -101,6 +113,37 @@ static inline void check_object_size(const void *ptr, unsigned long n, { } #endif /* CONFIG_HARDENED_USERCOPY */ +extern void __compiletime_error("copy source size is too small") +__bad_copy_from(void); +extern void __compiletime_error("copy destination size is too small") +__bad_copy_to(void); + +static inline void copy_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} + +static __always_inline bool +check_copy_size(const void *addr, size_t bytes, bool is_source) +{ + int sz = __compiletime_object_size(addr); + if (unlikely(sz >= 0 && sz < bytes)) { + if (!__builtin_constant_p(bytes)) + copy_overflow(sz, bytes); + else if (is_source) + __bad_copy_from(); + else + __bad_copy_to(); + return false; + } + check_object_size(addr, bytes, is_source); + return true; +} + +#ifndef arch_setup_new_exec +static inline void arch_setup_new_exec(void) { } +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ diff --git a/include/linux/tick.h b/include/linux/tick.h index a04fea19676f..fe01e68bf520 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -117,6 +117,7 @@ extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); extern ktime_t tick_nohz_get_sleep_length(void); +extern unsigned long tick_nohz_get_idle_calls(void); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); #else /* !CONFIG_NO_HZ_COMMON */ diff --git a/include/linux/time.h b/include/linux/time.h index 23f0f5ce3090..4abb32d4c6b8 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -8,6 +8,15 @@ extern struct timezone sys_tz; +int get_timespec64(struct timespec64 *ts, + const struct timespec __user *uts); +int put_timespec64(const struct timespec64 *ts, + struct timespec __user *uts); +int get_itimerspec64(struct itimerspec64 *it, + const struct itimerspec __user *uit); +int put_itimerspec64(const struct itimerspec64 *it, + struct itimerspec __user *uit); + #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) static inline int timespec_equal(const struct timespec *a, @@ -151,9 +160,6 @@ static inline bool timespec_inject_offset_valid(const struct timespec *ts) return true; } -#define CURRENT_TIME (current_kernel_time()) -#define CURRENT_TIME_SEC ((struct timespec) { get_seconds(), 0 }) - /* Some architectures do not supply their own clocksource. * This is mainly the case in architectures that get their * inter-tick times by reading the counter on their interval @@ -174,9 +180,6 @@ extern int do_getitimer(int which, struct itimerval *value); extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags); -struct tms; -extern void do_sys_times(struct tms *); - /* * Similar to the struct tm in userspace <time.h>, but it needs to be here so * that the kernel source is self contained. @@ -273,4 +276,13 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) a->tv_nsec = ns; } +static inline bool itimerspec64_valid(const struct itimerspec64 *its) +{ + if (!timespec64_valid(&(its->it_interval)) || + !timespec64_valid(&(its->it_value))) + return false; + + return true; +} + #endif diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 110f4532188c..0a0a53daf2a2 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -29,7 +29,6 @@ */ struct tk_read_base { struct clocksource *clock; - u64 (*read)(struct clocksource *cs); u64 mask; u64 cycle_last; u32 mult; @@ -52,13 +51,13 @@ struct tk_read_base { * @clock_was_set_seq: The sequence number of clock was set events * @cs_was_changed_seq: The sequence number of clocksource change events * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second - * @raw_time: Monotonic raw base time in timespec64 format + * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds * @cycle_interval: Number of clock cycles in one NTP interval * @xtime_interval: Number of clock shifted nano seconds in one NTP * interval. * @xtime_remainder: Shifted nano seconds left over when rounding * @cycle_interval - * @raw_interval: Raw nano seconds accumulated per NTP interval. + * @raw_interval: Shifted raw nano seconds accumulated per NTP interval. * @ntp_error: Difference between accumulated time and NTP time in ntp * shifted nano seconds. * @ntp_error_shift: Shift conversion between clock shifted nano seconds and @@ -94,13 +93,13 @@ struct timekeeper { unsigned int clock_was_set_seq; u8 cs_was_changed_seq; ktime_t next_leap_ktime; - struct timespec64 raw_time; + u64 raw_sec; /* The following members are for timekeeping internal use */ u64 cycle_interval; u64 xtime_interval; s64 xtime_remainder; - u32 raw_interval; + u64 raw_interval; /* The ntp_tick_length() value currently being used. * This cached copy ensures we consistently apply the tick * length for an entire tick, as ntp_tick_length may change diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index d2e804e15c3e..ddc229ff6d1e 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -8,6 +8,10 @@ void timekeeping_init(void); extern int timekeeping_suspended; +/* Architecture timer tick functions: */ +extern void update_process_times(int user); +extern void xtime_update(unsigned long ticks); + /* * Get and set timeofday */ @@ -15,21 +19,6 @@ extern void do_gettimeofday(struct timeval *tv); extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); -static inline int do_sys_settimeofday(const struct timespec *tv, - const struct timezone *tz) -{ - struct timespec64 ts64; - - if (!tv) - return do_sys_settimeofday64(NULL, tz); - - if (!timespec_valid(tv)) - return -EINVAL; - - ts64 = timespec_to_timespec64(*tv); - return do_sys_settimeofday64(&ts64, tz); -} - /* * Kernel time accessors */ @@ -269,6 +258,11 @@ static inline void timekeeping_clocktai(struct timespec *ts) *ts = ktime_to_timespec(ktime_get_clocktai()); } +static inline void timekeeping_clocktai64(struct timespec64 *ts) +{ + *ts = ktime_to_timespec64(ktime_get_clocktai()); +} + /* * RTC specific */ diff --git a/include/linux/timer.h b/include/linux/timer.h index 51d601f192d4..e6789b8757d5 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -20,11 +20,6 @@ struct timer_list { unsigned long data; u32 flags; -#ifdef CONFIG_TIMER_STATS - int start_pid; - void *start_site; - char start_comm[16]; -#endif #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif @@ -66,6 +61,8 @@ struct timer_list { #define TIMER_ARRAYSHIFT 22 #define TIMER_ARRAYMASK 0xFFC00000 +#define TIMER_TRACE_FLAGMASK (TIMER_MIGRATING | TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE) + #define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \ .entry = { .next = TIMER_ENTRY_STATIC }, \ .function = (_function), \ @@ -197,46 +194,6 @@ extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); */ #define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1) -/* - * Timer-statistics info: - */ -#ifdef CONFIG_TIMER_STATS - -extern int timer_stats_active; - -extern void init_timer_stats(void); - -extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf, - void *timerf, char *comm, u32 flags); - -extern void __timer_stats_timer_set_start_info(struct timer_list *timer, - void *addr); - -static inline void timer_stats_timer_set_start_info(struct timer_list *timer) -{ - if (likely(!timer_stats_active)) - return; - __timer_stats_timer_set_start_info(timer, __builtin_return_address(0)); -} - -static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) -{ - timer->start_site = NULL; -} -#else -static inline void init_timer_stats(void) -{ -} - -static inline void timer_stats_timer_set_start_info(struct timer_list *timer) -{ -} - -static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) -{ -} -#endif - extern void add_timer(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); @@ -255,7 +212,7 @@ struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -#include <linux/sysctl.h> +struct ctl_table; extern unsigned int sysctl_timer_migration; int timer_migration_handler(struct ctl_table *table, int write, diff --git a/include/linux/timeriomem-rng.h b/include/linux/timeriomem-rng.h index 46eb27ddbfab..3e00122bcf88 100644 --- a/include/linux/timeriomem-rng.h +++ b/include/linux/timeriomem-rng.h @@ -13,4 +13,7 @@ struct timeriomem_rng_data { /* measures in usecs */ unsigned int period; + + /* bits of entropy per 1024 bits read */ + unsigned int quality; }; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index da158f06e0b2..5a090f5ab335 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -48,7 +48,8 @@ struct tpm_class_ops { u8 (*status) (struct tpm_chip *chip); bool (*update_timeouts)(struct tpm_chip *chip, unsigned long *timeout_cap); - + int (*request_locality)(struct tpm_chip *chip, int loc); + void (*relinquish_locality)(struct tpm_chip *chip, int loc); }; #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index be007610ceb0..536c80ff7ad9 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -23,6 +23,10 @@ const char *trace_print_symbols_seq(struct trace_seq *p, unsigned long val, const struct trace_print_flags *symbol_array); #if BITS_PER_LONG == 32 +const char *trace_print_flags_seq_u64(struct trace_seq *p, const char *delim, + unsigned long long flags, + const struct trace_print_flags_u64 *flag_array); + const char *trace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val, const struct trace_print_flags_u64 @@ -33,7 +37,8 @@ const char *trace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr, unsigned int bitmask_size); const char *trace_print_hex_seq(struct trace_seq *p, - const unsigned char *buf, int len); + const unsigned char *buf, int len, + bool concatenate); const char *trace_print_array_seq(struct trace_seq *p, const void *buf, int count, @@ -133,16 +138,7 @@ enum print_line_t { TRACE_TYPE_NO_CONSUME = 3 /* Handled but ask to not consume */ }; -/* - * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq - * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function - * simplifies those functions and keeps them in sync. - */ -static inline enum print_line_t trace_handle_return(struct trace_seq *s) -{ - return trace_seq_has_overflowed(s) ? - TRACE_TYPE_PARTIAL_LINE : TRACE_TYPE_HANDLED; -} +enum print_line_t trace_handle_return(struct trace_seq *s); void tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, @@ -155,7 +151,15 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer, int type, unsigned long len, unsigned long flags, int pc); -void tracing_record_cmdline(struct task_struct *tsk); +#define TRACE_RECORD_CMDLINE BIT(0) +#define TRACE_RECORD_TGID BIT(1) + +void tracing_record_taskinfo(struct task_struct *task, int flags); +void tracing_record_taskinfo_sched_switch(struct task_struct *prev, + struct task_struct *next, int flags); + +void tracing_record_cmdline(struct task_struct *task); +void tracing_record_tgid(struct task_struct *task); int trace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...); @@ -294,6 +298,7 @@ struct trace_subsystem_dir; enum { EVENT_FILE_FL_ENABLED_BIT, EVENT_FILE_FL_RECORDED_CMD_BIT, + EVENT_FILE_FL_RECORDED_TGID_BIT, EVENT_FILE_FL_FILTERED_BIT, EVENT_FILE_FL_NO_SET_FILTER_BIT, EVENT_FILE_FL_SOFT_MODE_BIT, @@ -307,6 +312,7 @@ enum { * Event file flags: * ENABLED - The event is enabled * RECORDED_CMD - The comms should be recorded at sched_switch + * RECORDED_TGID - The tgids should be recorded at sched_switch * FILTERED - The event has a filter attached * NO_SET_FILTER - Set when filter has error and is to be ignored * SOFT_MODE - The event is enabled/disabled by SOFT_DISABLED @@ -319,6 +325,7 @@ enum { enum { EVENT_FILE_FL_ENABLED = (1 << EVENT_FILE_FL_ENABLED_BIT), EVENT_FILE_FL_RECORDED_CMD = (1 << EVENT_FILE_FL_RECORDED_CMD_BIT), + EVENT_FILE_FL_RECORDED_TGID = (1 << EVENT_FILE_FL_RECORDED_TGID_BIT), EVENT_FILE_FL_FILTERED = (1 << EVENT_FILE_FL_FILTERED_BIT), EVENT_FILE_FL_NO_SET_FILTER = (1 << EVENT_FILE_FL_NO_SET_FILTER_BIT), EVENT_FILE_FL_SOFT_MODE = (1 << EVENT_FILE_FL_SOFT_MODE_BIT), @@ -331,7 +338,7 @@ enum { struct trace_event_file { struct list_head list; struct trace_event_call *event_call; - struct event_filter *filter; + struct event_filter __rcu *filter; struct dentry *dir; struct trace_array *tr; struct trace_subsystem_dir *system; diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index f72fcfe0e66a..a26ffbe09e71 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -25,10 +25,10 @@ struct module; struct tracepoint; struct notifier_block; -struct trace_enum_map { +struct trace_eval_map { const char *system; - const char *enum_string; - unsigned long enum_value; + const char *eval_string; + unsigned long eval_value; }; #define TRACEPOINT_DEFAULT_PRIO 10 @@ -88,6 +88,7 @@ extern void syscall_unregfunc(void); #define PARAMS(args...) args #define TRACE_DEFINE_ENUM(x) +#define TRACE_DEFINE_SIZEOF(x) #endif /* _LINUX_TRACEPOINT_H */ @@ -128,7 +129,7 @@ extern void syscall_unregfunc(void); * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto". */ -#define __DO_TRACE(tp, proto, args, cond, prercu, postrcu) \ +#define __DO_TRACE(tp, proto, args, cond, rcucheck) \ do { \ struct tracepoint_func *it_func_ptr; \ void *it_func; \ @@ -136,7 +137,11 @@ extern void syscall_unregfunc(void); \ if (!(cond)) \ return; \ - prercu; \ + if (rcucheck) { \ + if (WARN_ON_ONCE(rcu_irq_enter_disabled())) \ + return; \ + rcu_irq_enter_irqson(); \ + } \ rcu_read_lock_sched_notrace(); \ it_func_ptr = rcu_dereference_sched((tp)->funcs); \ if (it_func_ptr) { \ @@ -147,20 +152,19 @@ extern void syscall_unregfunc(void); } while ((++it_func_ptr)->func); \ } \ rcu_read_unlock_sched_notrace(); \ - postrcu; \ + if (rcucheck) \ + rcu_irq_exit_irqson(); \ } while (0) #ifndef MODULE -#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) \ +#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) \ static inline void trace_##name##_rcuidle(proto) \ { \ if (static_key_false(&__tracepoint_##name.key)) \ __DO_TRACE(&__tracepoint_##name, \ TP_PROTO(data_proto), \ TP_ARGS(data_args), \ - TP_CONDITION(cond), \ - rcu_irq_enter_irqson(), \ - rcu_irq_exit_irqson()); \ + TP_CONDITION(cond), 1); \ } #else #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) @@ -186,7 +190,7 @@ extern void syscall_unregfunc(void); __DO_TRACE(&__tracepoint_##name, \ TP_PROTO(data_proto), \ TP_ARGS(data_args), \ - TP_CONDITION(cond),,); \ + TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ rcu_read_lock_sched_notrace(); \ rcu_dereference_sched(__tracepoint_##name.funcs);\ diff --git a/include/linux/tty.h b/include/linux/tty.h index 40144f382516..79c30daf46a9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -217,12 +217,18 @@ struct tty_port_operations { /* Called on the final put of a port */ void (*destruct)(struct tty_port *port); }; - + +struct tty_port_client_operations { + int (*receive_buf)(struct tty_port *port, const unsigned char *, const unsigned char *, size_t); + void (*write_wakeup)(struct tty_port *port); +}; + struct tty_port { struct tty_bufhead buf; /* Locked internally */ struct tty_struct *tty; /* Back pointer */ struct tty_struct *itty; /* internal back ptr */ const struct tty_port_operations *ops; /* Port operations */ + const struct tty_port_client_operations *client_ops; /* Port client operations */ spinlock_t lock; /* Lock protecting tty field */ int blocked_open; /* Waiting to open */ int count; /* Usage count */ @@ -241,6 +247,7 @@ struct tty_port { based drain is needed else set to size of fifo */ struct kref kref; /* Ref counter */ + void *client_data; }; /* tty_port::iflags bits -- use atomic bit ops */ @@ -309,7 +316,6 @@ struct tty_struct { struct tty_struct *link; struct fasync_struct *fasync; - int alt_speed; /* For magic substitution of 38400 bps */ wait_queue_head_t write_wait; wait_queue_head_t read_wait; struct work_struct hangup_work; @@ -326,7 +332,7 @@ struct tty_struct { /* If the tty has a pending do_SAK, queue it here - akpm */ struct work_struct SAK_work; struct tty_port *port; -}; +} __randomize_layout; /* Each of a tty's open files has private_data pointing to tty_file_private */ struct tty_file_private { @@ -383,7 +389,6 @@ static inline bool tty_throttled(struct tty_struct *tty) } #ifdef CONFIG_TTY -extern void console_init(void); extern void tty_kref_put(struct tty_struct *tty); extern struct pid *tty_get_pgrp(struct tty_struct *tty); extern void tty_vhangup_self(void); @@ -394,9 +399,10 @@ extern struct tty_struct *get_current_tty(void); /* tty_io.c */ extern int __init tty_init(void); extern const char *tty_name(const struct tty_struct *tty); +extern struct tty_struct *tty_open_by_driver(dev_t device, struct inode *inode, + struct file *filp); +extern int tty_dev_name_to_number(const char *name, dev_t *number); #else -static inline void console_init(void) -{ } static inline void tty_kref_put(struct tty_struct *tty) { } static inline struct pid *tty_get_pgrp(struct tty_struct *tty) @@ -416,6 +422,11 @@ static inline int __init tty_init(void) { return 0; } static inline const char *tty_name(const struct tty_struct *tty) { return "(none)"; } +static inline struct tty_struct *tty_open_by_driver(dev_t device, + struct inode *inode, struct file *filp) +{ return NULL; } +static inline int tty_dev_name_to_number(const char *name, dev_t *number) +{ return -ENOTSUPP; } #endif extern struct ktermios tty_std_termios; @@ -471,9 +482,13 @@ extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws); extern int is_current_pgrp_orphaned(void); extern void tty_hangup(struct tty_struct *tty); extern void tty_vhangup(struct tty_struct *tty); +extern void tty_vhangup_session(struct tty_struct *tty); extern int tty_hung_up_p(struct file *filp); extern void do_SAK(struct tty_struct *tty); extern void __do_SAK(struct tty_struct *tty); +extern void tty_open_proc_set_tty(struct file *filp, struct tty_struct *tty); +extern int tty_signal_session_leader(struct tty_struct *tty, int exit_session); +extern void session_clear_tty(struct pid *session); extern void no_tty(void); extern void tty_buffer_free_all(struct tty_port *port); extern void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld); @@ -521,6 +536,8 @@ extern void tty_ldisc_flush(struct tty_struct *tty); extern long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg); extern int tty_mode_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); +extern long tty_jobctrl_ioctl(struct tty_struct *tty, struct tty_struct *real_tty, + struct file *file, unsigned int cmd, unsigned long arg); extern int tty_perform_flush(struct tty_struct *tty, unsigned long arg); extern void tty_default_fops(struct file_operations *fops); extern struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx); @@ -528,6 +545,7 @@ extern int tty_alloc_file(struct file *file); extern void tty_add_file(struct tty_struct *tty, struct file *file); extern void tty_free_file(struct file *file); extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); +extern void tty_release_struct(struct tty_struct *tty, int idx); extern int tty_release(struct inode *inode, struct file *filp); extern void tty_init_termios(struct tty_struct *tty); extern int tty_standard_install(struct tty_driver *driver, @@ -547,6 +565,15 @@ extern struct device *tty_port_register_device_attr(struct tty_port *port, struct tty_driver *driver, unsigned index, struct device *device, void *drvdata, const struct attribute_group **attr_grp); +extern struct device *tty_port_register_device_serdev(struct tty_port *port, + struct tty_driver *driver, unsigned index, + struct device *device); +extern struct device *tty_port_register_device_attr_serdev(struct tty_port *port, + struct tty_driver *driver, unsigned index, + struct device *device, void *drvdata, + const struct attribute_group **attr_grp); +extern void tty_port_unregister_device(struct tty_port *port, + struct tty_driver *driver, unsigned index); extern int tty_port_alloc_xmit_buf(struct tty_port *port); extern void tty_port_free_xmit_buf(struct tty_port *port); extern void tty_port_destroy(struct tty_port *port); @@ -656,12 +683,16 @@ extern int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty); extern void tty_ldisc_release(struct tty_struct *tty); extern void tty_ldisc_init(struct tty_struct *tty); extern void tty_ldisc_deinit(struct tty_struct *tty); -extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p, +extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, char *f, int count); /* n_tty.c */ extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops); +#ifdef CONFIG_TTY extern void __init n_tty_init(void); +#else +static inline void n_tty_init(void) { } +#endif /* tty_audit.c */ #ifdef CONFIG_AUDIT diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index b742b5e47cc2..00b2213f6a35 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -291,7 +291,7 @@ struct tty_operations { void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif const struct file_operations *proc_fops; -}; +} __randomize_layout; struct tty_driver { int magic; /* magic number for this structure */ @@ -325,7 +325,7 @@ struct tty_driver { const struct tty_operations *ops; struct list_head tty_drivers; -}; +} __randomize_layout; extern struct list_head tty_drivers; diff --git a/include/linux/types.h b/include/linux/types.h index 1e7bd24848fc..258099a4ed82 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -209,7 +209,7 @@ struct ustat { * naturally due ABI requirements, but some architectures (like CRIS) have * weird ABI and we need to ask it explicitly. * - * The alignment is required to guarantee that bits 0 and 1 of @next will be + * The alignment is required to guarantee that bit 0 of @next will be * clear under normal conditions -- as long as we use call_rcu(), * call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback. * diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index f30c187ed785..acdd6f915a8d 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -2,8 +2,169 @@ #define __LINUX_UACCESS_H__ #include <linux/sched.h> +#include <linux/thread_info.h> +#include <linux/kasan-checks.h> + +#define VERIFY_READ 0 +#define VERIFY_WRITE 1 + +#define uaccess_kernel() segment_eq(get_fs(), KERNEL_DS) + #include <asm/uaccess.h> +/* + * Architectures should provide two primitives (raw_copy_{to,from}_user()) + * and get rid of their private instances of copy_{to,from}_user() and + * __copy_{to,from}_user{,_inatomic}(). + * + * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and + * return the amount left to copy. They should assume that access_ok() has + * already been checked (and succeeded); they should *not* zero-pad anything. + * No KASAN or object size checks either - those belong here. + * + * Both of these functions should attempt to copy size bytes starting at from + * into the area starting at to. They must not fetch or store anything + * outside of those areas. Return value must be between 0 (everything + * copied successfully) and size (nothing copied). + * + * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting + * at to must become equal to the bytes fetched from the corresponding area + * starting at from. All data past to + size - N must be left unmodified. + * + * If copying succeeds, the return value must be 0. If some data cannot be + * fetched, it is permitted to copy less than had been fetched; the only + * hard requirement is that not storing anything at all (i.e. returning size) + * should happen only when nothing could be copied. In other words, you don't + * have to squeeze as much as possible - it is allowed, but not necessary. + * + * For raw_copy_from_user() to always points to kernel memory and no faults + * on store should happen. Interpretation of from is affected by set_fs(). + * For raw_copy_to_user() it's the other way round. + * + * Both can be inlined - it's up to architectures whether it wants to bother + * with that. They should not be used directly; they are used to implement + * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) + * that are used instead. Out of those, __... ones are inlined. Plain + * copy_{to,from}_user() might or might not be inlined. If you want them + * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. + * + * NOTE: only copy_from_user() zero-pads the destination in case of short copy. + * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything + * at all; their callers absolutely must check the return value. + * + * Biarch ones should also provide raw_copy_in_user() - similar to the above, + * but both source and destination are __user pointers (affected by set_fs() + * as usual) and both source and destination can trigger faults. + */ + +static __always_inline unsigned long +__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) +{ + kasan_check_write(to, n); + check_object_size(to, n, false); + return raw_copy_from_user(to, from, n); +} + +static __always_inline unsigned long +__copy_from_user(void *to, const void __user *from, unsigned long n) +{ + might_fault(); + kasan_check_write(to, n); + check_object_size(to, n, false); + return raw_copy_from_user(to, from, n); +} + +/** + * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. + * @to: Destination address, in user space. + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * + * Context: User context only. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. + * The caller should also make sure he pins the user space address + * so that we don't result in page fault and sleep. + */ +static __always_inline unsigned long +__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) +{ + kasan_check_read(from, n); + check_object_size(from, n, true); + return raw_copy_to_user(to, from, n); +} + +static __always_inline unsigned long +__copy_to_user(void __user *to, const void *from, unsigned long n) +{ + might_fault(); + kasan_check_read(from, n); + check_object_size(from, n, true); + return raw_copy_to_user(to, from, n); +} + +#ifdef INLINE_COPY_FROM_USER +static inline unsigned long +_copy_from_user(void *to, const void __user *from, unsigned long n) +{ + unsigned long res = n; + might_fault(); + if (likely(access_ok(VERIFY_READ, from, n))) { + kasan_check_write(to, n); + res = raw_copy_from_user(to, from, n); + } + if (unlikely(res)) + memset(to + (n - res), 0, res); + return res; +} +#else +extern unsigned long +_copy_from_user(void *, const void __user *, unsigned long); +#endif + +#ifdef INLINE_COPY_TO_USER +static inline unsigned long +_copy_to_user(void __user *to, const void *from, unsigned long n) +{ + might_fault(); + if (access_ok(VERIFY_WRITE, to, n)) { + kasan_check_read(from, n); + n = raw_copy_to_user(to, from, n); + } + return n; +} +#else +extern unsigned long +_copy_to_user(void __user *, const void *, unsigned long); +#endif + +static __always_inline unsigned long __must_check +copy_from_user(void *to, const void __user *from, unsigned long n) +{ + if (likely(check_copy_size(to, n, false))) + n = _copy_from_user(to, from, n); + return n; +} + +static __always_inline unsigned long __must_check +copy_to_user(void __user *to, const void *from, unsigned long n) +{ + if (likely(check_copy_size(from, n, true))) + n = _copy_to_user(to, from, n); + return n; +} +#ifdef CONFIG_COMPAT +static __always_inline unsigned long __must_check +copy_in_user(void __user *to, const void *from, unsigned long n) +{ + might_fault(); + if (access_ok(VERIFY_WRITE, to, n) && access_ok(VERIFY_READ, from, n)) + n = raw_copy_in_user(to, from, n); + return n; +} +#endif + static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; @@ -12,7 +173,6 @@ static __always_inline void pagefault_disabled_inc(void) static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; - WARN_ON(current->pagefault_disabled < 0); } /* @@ -67,12 +227,6 @@ static inline unsigned long __copy_from_user_inatomic_nocache(void *to, return __copy_from_user_inatomic(to, from, n); } -static inline unsigned long __copy_from_user_nocache(void *to, - const void __user *from, unsigned long n) -{ - return __copy_from_user(to, from, n); -} - #endif /* ARCH_HAS_NOCACHE_UACCESS */ /* diff --git a/include/linux/udp.h b/include/linux/udp.h index c0f530809d1f..eaea63bc79bb 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -80,6 +80,9 @@ struct udp_sock { struct sk_buff *skb, int nhoff); + /* udp_recvmsg try to use this before splicing sk_receive_queue */ + struct sk_buff_head reader_queue ____cacheline_aligned_in_smp; + /* This field is dirtied by udp_recvmsg() */ int forward_deficit; }; @@ -115,6 +118,6 @@ static inline bool udp_get_no_check6_rx(struct sock *sk) #define udp_portaddr_for_each_entry_rcu(__sk, list) \ hlist_for_each_entry_rcu(__sk, list, __sk_common.skc_portaddr_node) -#define IS_UDPLITE(__sk) (udp_sk(__sk)->pcflag) +#define IS_UDPLITE(__sk) (__sk->sk_protocol == IPPROTO_UDPLITE) #endif /* _LINUX_UDP_H */ diff --git a/include/linux/uio.h b/include/linux/uio.h index 804e34c6f981..8a642cda641c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -10,6 +10,7 @@ #define __LINUX_UIO_H #include <linux/kernel.h> +#include <linux/thread_info.h> #include <uapi/linux/uio.h> struct page; @@ -39,7 +40,10 @@ struct iov_iter { }; union { unsigned long nr_segs; - int idx; + struct { + int idx; + int start_idx; + }; }; }; @@ -81,17 +85,86 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to); size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); +void iov_iter_revert(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); -size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); -size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); -bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i); -size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); -bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i); + +size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); +size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); +bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i); +size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); +bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i); + +static __always_inline __must_check +size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, true))) + return 0; + else + return _copy_to_iter(addr, bytes, i); +} + +static __always_inline __must_check +size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return 0; + else + return _copy_from_iter(addr, bytes, i); +} + +static __always_inline __must_check +bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return false; + else + return _copy_from_iter_full(addr, bytes, i); +} + +static __always_inline __must_check +size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return 0; + else + return _copy_from_iter_nocache(addr, bytes, i); +} + +static __always_inline __must_check +bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return false; + else + return _copy_from_iter_full_nocache(addr, bytes, i); +} + +#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +/* + * Note, users like pmem that depend on the stricter semantics of + * copy_from_iter_flushcache() than copy_from_iter_nocache() must check for + * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the + * destination is flushed from the cache on return. + */ +size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); +#else +#define _copy_from_iter_flushcache _copy_from_iter_nocache +#endif + +static __always_inline __must_check +size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) +{ + if (unlikely(!check_copy_size(addr, bytes, false))) + return 0; + else + return _copy_from_iter_flushcache(addr, bytes, i); +} + size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 32c0e83d6239..3c85c81b0027 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -23,11 +23,13 @@ struct uio_map; /** * struct uio_mem - description of a UIO memory region * @name: name of the memory region for identification - * @addr: address of the device's memory (phys_addr is used since - * addr can be logical, virtual, or physical & phys_addr_t - * should always be large enough to handle any of the - * address types) - * @size: size of IO + * @addr: address of the device's memory rounded to page + * size (phys_addr is used since addr can be + * logical, virtual, or physical & phys_addr_t + * should always be large enough to handle any of + * the address types) + * @offs: offset of device memory within the page + * @size: size of IO (multiple of page size) * @memtype: type of memory addr points to * @internal_addr: ioremap-ped version of addr, for driver internal use * @map: for use by the UIO core only. @@ -35,6 +37,7 @@ struct uio_map; struct uio_mem { const char *name; phys_addr_t addr; + unsigned long offs; resource_size_t size; int memtype; void __iomem *internal_addr; diff --git a/include/linux/usb.h b/include/linux/usb.h index 7e68259360de..cb9fbd54386e 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -99,6 +99,76 @@ enum usb_interface_condition { USB_INTERFACE_UNBINDING, }; +int __must_check +usb_find_common_endpoints(struct usb_host_interface *alt, + struct usb_endpoint_descriptor **bulk_in, + struct usb_endpoint_descriptor **bulk_out, + struct usb_endpoint_descriptor **int_in, + struct usb_endpoint_descriptor **int_out); + +int __must_check +usb_find_common_endpoints_reverse(struct usb_host_interface *alt, + struct usb_endpoint_descriptor **bulk_in, + struct usb_endpoint_descriptor **bulk_out, + struct usb_endpoint_descriptor **int_in, + struct usb_endpoint_descriptor **int_out); + +static inline int __must_check +usb_find_bulk_in_endpoint(struct usb_host_interface *alt, + struct usb_endpoint_descriptor **bulk_in) +{ + return usb_find_common_endpoints(alt, bulk_in, NULL, NULL, NULL); +} + +static inline int __must_check +usb_find_bulk_out_endpoint(struct usb_host_interface *alt, + struct usb_endpoint_descriptor **bulk_out) +{ + return usb_find_common_endpoints(alt, NULL, bulk_out, NULL, NULL); +} + +static inline int __must_check +usb_find_int_in_endpoint(struct usb_host_interface *alt, + struct usb_endpoint_descriptor **int_in) +{ + return usb_find_common_endpoints(alt, NULL, NULL, int_in, NULL); +} + +static inline int __must_check +usb_find_int_out_endpoint(struct usb_host_interface *alt, + struct usb_endpoint_descriptor **int_out) +{ + return usb_find_common_endpoints(alt, NULL, NULL, NULL, int_out); +} + +static inline int __must_check +usb_find_last_bulk_in_endpoint(struct usb_host_interface *alt, + struct usb_endpoint_descriptor **bulk_in) +{ + return usb_find_common_endpoints_reverse(alt, bulk_in, NULL, NULL, NULL); +} + +static inline int __must_check +usb_find_last_bulk_out_endpoint(struct usb_host_interface *alt, + struct usb_endpoint_descriptor **bulk_out) +{ + return usb_find_common_endpoints_reverse(alt, NULL, bulk_out, NULL, NULL); +} + +static inline int __must_check +usb_find_last_int_in_endpoint(struct usb_host_interface *alt, + struct usb_endpoint_descriptor **int_in) +{ + return usb_find_common_endpoints_reverse(alt, NULL, NULL, int_in, NULL); +} + +static inline int __must_check +usb_find_last_int_out_endpoint(struct usb_host_interface *alt, + struct usb_endpoint_descriptor **int_out) +{ + return usb_find_common_endpoints_reverse(alt, NULL, NULL, NULL, int_out); +} + /** * struct usb_interface - what usb device drivers talk to * @altsetting: array of interface structures, one for each alternate @@ -248,7 +318,7 @@ void usb_put_intf(struct usb_interface *intf); * struct usb_interface (which persists only as long as its configuration * is installed). The altsetting arrays can be accessed through these * structures at any time, permitting comparison of configurations and - * providing support for the /proc/bus/usb/devices pseudo-file. + * providing support for the /sys/kernel/debug/usb/devices pseudo-file. */ struct usb_interface_cache { unsigned num_altsetting; /* number of alternate settings */ @@ -354,6 +424,7 @@ struct usb_devmap { */ struct usb_bus { struct device *controller; /* host/master side hardware */ + struct device *sysdev; /* as seen from firmware or bus */ int busnum; /* Bus number (in order of reg) */ const char *bus_name; /* stable id (PCI slot_name etc) */ u8 uses_dma; /* Does the host controller use DMA? */ diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index c5f2158ab00e..fd73bc0e9027 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -115,13 +115,13 @@ struct uac2_input_terminal_descriptor { __u8 bDescriptorType; __u8 bDescriptorSubtype; __u8 bTerminalID; - __u16 wTerminalType; + __le16 wTerminalType; __u8 bAssocTerminal; __u8 bCSourceID; __u8 bNrChannels; - __u32 bmChannelConfig; + __le32 bmChannelConfig; __u8 iChannelNames; - __u16 bmControls; + __le16 bmControls; __u8 iTerminal; } __attribute__((packed)); @@ -132,11 +132,11 @@ struct uac2_output_terminal_descriptor { __u8 bDescriptorType; __u8 bDescriptorSubtype; __u8 bTerminalID; - __u16 wTerminalType; + __le16 wTerminalType; __u8 bAssocTerminal; __u8 bSourceID; __u8 bCSourceID; - __u16 bmControls; + __le16 bmControls; __u8 iTerminal; } __attribute__((packed)); @@ -164,9 +164,9 @@ struct uac2_as_header_descriptor { __u8 bTerminalLink; __u8 bmControls; __u8 bFormatType; - __u32 bmFormats; + __le32 bmFormats; __u8 bNrChannels; - __u32 bmChannelConfig; + __le32 bmChannelConfig; __u8 iChannelNames; } __attribute__((packed)); diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 00d232406f18..1a59699cf82a 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -83,6 +83,7 @@ /* Driver flags */ #define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ #define CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE 0x04 /* Avoid altsetting toggle during init */ +#define CDC_NCM_FLAG_RESET_NTB16 0x08 /* set NDP16 one more time after altsetting switch */ #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) @@ -117,6 +118,9 @@ struct cdc_ncm_ctx { u32 tx_curr_frame_num; u32 rx_max; u32 tx_max; + u32 tx_curr_size; + u32 tx_low_mem_max_cnt; + u32 tx_low_mem_val; u32 max_datagram_size; u16 tx_max_datagrams; u16 tx_remainder; diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 5dd75fa47dd8..c5fdfcf99828 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -12,16 +12,18 @@ struct ci_hdrc; /** * struct ci_hdrc_cable - structure for external connector cable state tracking - * @state: current state of the line + * @connected: true if cable is connected, false otherwise * @changed: set to true when extcon event happen + * @enabled: set to true if we've enabled the vbus or id interrupt * @edev: device which generate events * @ci: driver state of the chipidea device * @nb: hold event notification callback * @conn: used for notification registration */ struct ci_hdrc_cable { - bool state; + bool connected; bool changed; + bool enabled; struct extcon_dev *edev; struct ci_hdrc *ci; struct notifier_block nb; @@ -55,10 +57,11 @@ struct ci_hdrc_platform_data { #define CI_HDRC_OVERRIDE_AHB_BURST BIT(9) #define CI_HDRC_OVERRIDE_TX_BURST BIT(10) #define CI_HDRC_OVERRIDE_RX_BURST BIT(11) +#define CI_HDRC_OVERRIDE_PHY_CONTROL BIT(12) /* Glue layer manages phy */ enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 - void (*notify_event) (struct ci_hdrc *ci, unsigned event); + int (*notify_event) (struct ci_hdrc *ci, unsigned event); struct regulator *reg_vbus; struct usb_otg_caps ci_otg_caps; bool tpl_support; diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 4616a49a1c2e..f665d2ceac20 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -451,6 +451,7 @@ static inline struct usb_composite_driver *to_cdriver( * sure doing that won't hurt too much. * * One notion for how to handle Wireless USB devices involves: + * * (a) a second gadget here, discovery mechanism TBD, but likely * needing separate "register/unregister WUSB gadget" calls; * (b) updates to usb_gadget to include flags "is it wireless", @@ -503,8 +504,9 @@ struct usb_composite_dev { /* protects deactivations and delayed_status counts*/ spinlock_t lock; - unsigned setup_pending:1; - unsigned os_desc_pending:1; + /* public: */ + unsigned int setup_pending:1; + unsigned int os_desc_pending:1; }; extern int usb_string_id(struct usb_composite_dev *c); diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index e4516e9ded0f..1a4a4bacfae6 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -188,7 +188,7 @@ struct usb_ep_caps { * @caps:The structure describing types and directions supported by endoint. * @maxpacket:The maximum packet size used on this endpoint. The initial * value can sometimes be reduced (hardware allowing), according to - * the endpoint descriptor used to configure the endpoint. + * the endpoint descriptor used to configure the endpoint. * @maxpacket_limit:The maximum packet size value which can be handled by this * endpoint. It's set once by UDC driver when endpoint is initialized, and * should not be changed. Should not be confused with maxpacket. @@ -304,6 +304,7 @@ struct usb_gadget_ops { int (*udc_start)(struct usb_gadget *, struct usb_gadget_driver *); int (*udc_stop)(struct usb_gadget *); + void (*udc_set_speed)(struct usb_gadget *, enum usb_device_speed); struct usb_ep *(*match_ep)(struct usb_gadget *, struct usb_endpoint_descriptor *, struct usb_ss_ep_comp_descriptor *); @@ -352,6 +353,8 @@ struct usb_gadget_ops { * @deactivated: True if gadget is deactivated - in deactivated state it cannot * be connected. * @connected: True if gadget is connected. + * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag + * indicates that it supports LPM as per the LPM ECN & errata. * * Gadgets have a mostly-portable "gadget driver" implementing device * functions, handling all usb configurations and interfaces. Gadget @@ -404,6 +407,7 @@ struct usb_gadget { unsigned is_selfpowered:1; unsigned deactivated:1; unsigned connected:1; + unsigned lpm_capable:1; }; #define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 40edf6a8533e..a1f03ebfde47 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -148,6 +148,7 @@ struct usb_hcd { unsigned rh_registered:1;/* is root hub registered? */ unsigned rh_pollable:1; /* may we poll the root hub? */ unsigned msix_enabled:1; /* driver has MSI-X enabled? */ + unsigned msi_enabled:1; /* driver has MSI enabled? */ unsigned remove_phy:1; /* auto-remove USB phy */ /* The next flag is a stopgap, to be removed when all the HCDs @@ -437,6 +438,9 @@ extern int usb_hcd_alloc_bandwidth(struct usb_device *udev, struct usb_host_interface *new_alt); extern int usb_hcd_get_frame_number(struct usb_device *udev); +struct usb_hcd *__usb_create_hcd(const struct hc_driver *driver, + struct device *sysdev, struct device *dev, const char *bus_name, + struct usb_hcd *primary_hcd); extern struct usb_hcd *usb_create_hcd(const struct hc_driver *driver, struct device *dev, const char *bus_name); extern struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver, @@ -453,7 +457,7 @@ extern int usb_hcd_find_raw_port_number(struct usb_hcd *hcd, int port1); struct platform_device; extern void usb_hcd_platform_shutdown(struct platform_device *dev); -#ifdef CONFIG_PCI +#ifdef CONFIG_USB_PCI struct pci_dev; struct pci_device_id; extern int usb_hcd_pci_probe(struct pci_dev *dev, @@ -466,7 +470,7 @@ extern int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *dev); #ifdef CONFIG_PM extern const struct dev_pm_ops usb_hcd_pci_pm_ops; #endif -#endif /* CONFIG_PCI */ +#endif /* CONFIG_USB_PCI */ /* pci-ish (pdev null is ok) buffer alloc/mapping support */ void usb_init_pool_max(void); @@ -561,9 +565,9 @@ extern void usb_ep0_reinit(struct usb_device *); ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) #define EndpointRequest \ - ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) + ((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8) #define EndpointOutRequest \ - ((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8) + ((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8) /* class requests from the USB 2.0 hub spec, table 11-15 */ #define HUB_CLASS_REQ(dir, type, request) ((((dir) | (type)) << 8) | (request)) diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index 5ff9032ee1b4..4031f47629ec 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -18,6 +18,7 @@ int of_usb_update_otg_caps(struct device_node *np, struct usb_otg_caps *otg_caps); struct device_node *usb_of_get_child_node(struct device_node *parent, int portnum); +struct device *usb_of_get_companion_dev(struct device *dev); #else static inline enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *np, int arg0) @@ -38,6 +39,10 @@ static inline struct device_node *usb_of_get_child_node { return NULL; } +static inline struct device *usb_of_get_companion_dev(struct device *dev) +{ + return NULL; +} #endif #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_SUPPORT) diff --git a/include/linux/usb/otg-fsm.h b/include/linux/usb/otg-fsm.h index 7a0350535cb1..a0a8f878503c 100644 --- a/include/linux/usb/otg-fsm.h +++ b/include/linux/usb/otg-fsm.h @@ -21,21 +21,6 @@ #include <linux/mutex.h> #include <linux/errno.h> -#undef VERBOSE - -#ifdef VERBOSE -#define VDBG(fmt, args...) pr_debug("[%s] " fmt , \ - __func__, ## args) -#else -#define VDBG(stuff...) do {} while (0) -#endif - -#ifdef VERBOSE -#define MPC_LOC printk("Current Location [%s]:[%d]\n", __FILE__, __LINE__) -#else -#define MPC_LOC do {} while (0) -#endif - #define PROTO_UNDEF (0) #define PROTO_HOST (1) #define PROTO_GADGET (2) diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index 31a8068c42a5..299245105610 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -9,6 +9,7 @@ #ifndef __LINUX_USB_PHY_H #define __LINUX_USB_PHY_H +#include <linux/extcon.h> #include <linux/notifier.h> #include <linux/usb.h> @@ -85,6 +86,12 @@ struct usb_phy { struct usb_phy_io_ops *io_ops; void __iomem *io_priv; + /* to support extcon device */ + struct extcon_dev *edev; + struct extcon_dev *id_edev; + struct notifier_block vbus_nb; + struct notifier_block id_nb; + /* for notification of usb_phy_events */ struct atomic_notifier_head notifier; diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 1d0043dc34e4..de2a722fe3cf 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -50,4 +50,10 @@ /* device can't handle Link Power Management */ #define USB_QUIRK_NO_LPM BIT(10) +/* + * Device reports its bInterval as linear frames instead of the + * USB 2.0 calculation. + */ +#define USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL BIT(11) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 704a1ab8240c..e2f0ab07eea5 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -20,7 +20,7 @@ #include <linux/kfifo.h> /* The maximum number of ports one device can grab at once */ -#define MAX_NUM_PORTS 8 +#define MAX_NUM_PORTS 16 /* parity check flag */ #define RELEVANT_IFLAG(iflag) (iflag & (IGNBRK|BRKINT|IGNPAR|PARMRK|INPCK)) @@ -159,10 +159,10 @@ struct usb_serial { unsigned char minors_reserved:1; unsigned char num_ports; unsigned char num_port_pointers; - char num_interrupt_in; - char num_interrupt_out; - char num_bulk_in; - char num_bulk_out; + unsigned char num_interrupt_in; + unsigned char num_interrupt_out; + unsigned char num_bulk_in; + unsigned char num_bulk_out; struct usb_serial_port *port[MAX_NUM_PORTS]; struct kref kref; struct mutex disc_mutex; @@ -181,6 +181,17 @@ static inline void usb_set_serial_data(struct usb_serial *serial, void *data) serial->private = data; } +struct usb_serial_endpoints { + unsigned char num_bulk_in; + unsigned char num_bulk_out; + unsigned char num_interrupt_in; + unsigned char num_interrupt_out; + struct usb_endpoint_descriptor *bulk_in[MAX_NUM_PORTS]; + struct usb_endpoint_descriptor *bulk_out[MAX_NUM_PORTS]; + struct usb_endpoint_descriptor *interrupt_in[MAX_NUM_PORTS]; + struct usb_endpoint_descriptor *interrupt_out[MAX_NUM_PORTS]; +}; + /** * usb_serial_driver - describes a usb serial driver * @description: pointer to a string that describes this driver. This string @@ -188,12 +199,17 @@ static inline void usb_set_serial_data(struct usb_serial *serial, void *data) * @id_table: pointer to a list of usb_device_id structures that define all * of the devices this structure can support. * @num_ports: the number of different ports this device will have. + * @num_bulk_in: minimum number of bulk-in endpoints + * @num_bulk_out: minimum number of bulk-out endpoints + * @num_interrupt_in: minimum number of interrupt-in endpoints + * @num_interrupt_out: minimum number of interrupt-out endpoints * @bulk_in_size: minimum number of bytes to allocate for bulk-in buffer * (0 = end-point size) * @bulk_out_size: bytes to allocate for bulk-out buffer (0 = end-point size) * @calc_num_ports: pointer to a function to determine how many ports this - * device has dynamically. It will be called after the probe() - * callback is called, but before attach() + * device has dynamically. It can also be used to verify the number of + * endpoints or to modify the port-endpoint mapping. It will be called + * after the probe() callback is called, but before attach(). * @probe: pointer to the driver's probe function. * This will be called when the device is inserted into the system, * but before the device has been fully initialized by the usb_serial @@ -227,19 +243,26 @@ static inline void usb_set_serial_data(struct usb_serial *serial, void *data) struct usb_serial_driver { const char *description; const struct usb_device_id *id_table; - char num_ports; struct list_head driver_list; struct device_driver driver; struct usb_driver *usb_driver; struct usb_dynids dynids; + unsigned char num_ports; + + unsigned char num_bulk_in; + unsigned char num_bulk_out; + unsigned char num_interrupt_in; + unsigned char num_interrupt_out; + size_t bulk_in_size; size_t bulk_out_size; int (*probe)(struct usb_serial *serial, const struct usb_device_id *id); int (*attach)(struct usb_serial *serial); - int (*calc_num_ports) (struct usb_serial *serial); + int (*calc_num_ports)(struct usb_serial *serial, + struct usb_serial_endpoints *epds); void (*disconnect)(struct usb_serial *serial); void (*release)(struct usb_serial *serial); @@ -356,7 +379,6 @@ extern void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, extern int usb_serial_bus_register(struct usb_serial_driver *device); extern void usb_serial_bus_deregister(struct usb_serial_driver *device); -extern struct usb_serial_driver usb_serial_generic_device; extern struct bus_type usb_serial_bus_type; extern struct tty_driver *usb_serial_tty_driver; diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h new file mode 100644 index 000000000000..ffe7487886ca --- /dev/null +++ b/include/linux/usb/typec.h @@ -0,0 +1,247 @@ + +#ifndef __LINUX_USB_TYPEC_H +#define __LINUX_USB_TYPEC_H + +#include <linux/types.h> + +/* XXX: Once we have a header for USB Power Delivery, this belongs there */ +#define ALTMODE_MAX_MODES 6 + +/* USB Type-C Specification releases */ +#define USB_TYPEC_REV_1_0 0x100 /* 1.0 */ +#define USB_TYPEC_REV_1_1 0x110 /* 1.1 */ +#define USB_TYPEC_REV_1_2 0x120 /* 1.2 */ + +struct typec_altmode; +struct typec_partner; +struct typec_cable; +struct typec_plug; +struct typec_port; + +struct fwnode_handle; + +enum typec_port_type { + TYPEC_PORT_DFP, + TYPEC_PORT_UFP, + TYPEC_PORT_DRP, +}; + +enum typec_plug_type { + USB_PLUG_NONE, + USB_PLUG_TYPE_A, + USB_PLUG_TYPE_B, + USB_PLUG_TYPE_C, + USB_PLUG_CAPTIVE, +}; + +enum typec_data_role { + TYPEC_DEVICE, + TYPEC_HOST, +}; + +enum typec_role { + TYPEC_SINK, + TYPEC_SOURCE, +}; + +enum typec_pwr_opmode { + TYPEC_PWR_MODE_USB, + TYPEC_PWR_MODE_1_5A, + TYPEC_PWR_MODE_3_0A, + TYPEC_PWR_MODE_PD, +}; + +enum typec_accessory { + TYPEC_ACCESSORY_NONE, + TYPEC_ACCESSORY_AUDIO, + TYPEC_ACCESSORY_DEBUG, +}; + +#define TYPEC_MAX_ACCESSORY 3 + +/* + * struct usb_pd_identity - USB Power Delivery identity data + * @id_header: ID Header VDO + * @cert_stat: Cert Stat VDO + * @product: Product VDO + * + * USB power delivery Discover Identity command response data. + * + * REVISIT: This is USB Power Delivery specific information, so this structure + * probable belongs to USB Power Delivery header file once we have them. + */ +struct usb_pd_identity { + u32 id_header; + u32 cert_stat; + u32 product; +}; + +int typec_partner_set_identity(struct typec_partner *partner); +int typec_cable_set_identity(struct typec_cable *cable); + +/* + * struct typec_mode_desc - Individual Mode of an Alternate Mode + * @index: Index of the Mode within the SVID + * @vdo: VDO returned by Discover Modes USB PD command + * @desc: Optional human readable description of the mode + * @roles: Only for ports. DRP if the mode is available in both roles + * + * Description of a mode of an Alternate Mode which a connector, cable plug or + * partner supports. Every mode will have it's own sysfs group. The details are + * the VDO returned by discover modes command, description for the mode and + * active flag telling has the mode being entered or not. + */ +struct typec_mode_desc { + int index; + u32 vdo; + char *desc; + /* Only used with ports */ + enum typec_port_type roles; +}; + +/* + * struct typec_altmode_desc - USB Type-C Alternate Mode Descriptor + * @svid: Standard or Vendor ID + * @n_modes: Number of modes + * @modes: Array of modes supported by the Alternate Mode + * + * Representation of an Alternate Mode that has SVID assigned by USB-IF. The + * array of modes will list the modes of a particular SVID that are supported by + * a connector, partner of a cable plug. + */ +struct typec_altmode_desc { + u16 svid; + int n_modes; + struct typec_mode_desc modes[ALTMODE_MAX_MODES]; +}; + +struct typec_altmode +*typec_partner_register_altmode(struct typec_partner *partner, + const struct typec_altmode_desc *desc); +struct typec_altmode +*typec_plug_register_altmode(struct typec_plug *plug, + const struct typec_altmode_desc *desc); +struct typec_altmode +*typec_port_register_altmode(struct typec_port *port, + const struct typec_altmode_desc *desc); +void typec_unregister_altmode(struct typec_altmode *altmode); + +struct typec_port *typec_altmode2port(struct typec_altmode *alt); + +void typec_altmode_update_active(struct typec_altmode *alt, int mode, + bool active); + +enum typec_plug_index { + TYPEC_PLUG_SOP_P, + TYPEC_PLUG_SOP_PP, +}; + +/* + * struct typec_plug_desc - USB Type-C Cable Plug Descriptor + * @index: SOP Prime for the plug connected to DFP and SOP Double Prime for the + * plug connected to UFP + * + * Represents USB Type-C Cable Plug. + */ +struct typec_plug_desc { + enum typec_plug_index index; +}; + +/* + * struct typec_cable_desc - USB Type-C Cable Descriptor + * @type: The plug type from USB PD Cable VDO + * @active: Is the cable active or passive + * @identity: Result of Discover Identity command + * + * Represents USB Type-C Cable attached to USB Type-C port. + */ +struct typec_cable_desc { + enum typec_plug_type type; + unsigned int active:1; + struct usb_pd_identity *identity; +}; + +/* + * struct typec_partner_desc - USB Type-C Partner Descriptor + * @usb_pd: USB Power Delivery support + * @accessory: Audio, Debug or none. + * @identity: Discover Identity command data + * + * Details about a partner that is attached to USB Type-C port. If @identity + * member exists when partner is registered, a directory named "identity" is + * created to sysfs for the partner device. + */ +struct typec_partner_desc { + unsigned int usb_pd:1; + enum typec_accessory accessory; + struct usb_pd_identity *identity; +}; + +/* + * struct typec_capability - USB Type-C Port Capabilities + * @role: DFP (Host-only), UFP (Device-only) or DRP (Dual Role) + * @revision: USB Type-C Specification release. Binary coded decimal + * @pd_revision: USB Power Delivery Specification revision if supported + * @prefer_role: Initial role preference + * @accessory: Supported Accessory Modes + * @fwnode: Optional fwnode of the port + * @try_role: Set data role preference for DRP port + * @dr_set: Set Data Role + * @pr_set: Set Power Role + * @vconn_set: Set VCONN Role + * @activate_mode: Enter/exit given Alternate Mode + * @port_type_set: Set port type + * + * Static capabilities of a single USB Type-C port. + */ +struct typec_capability { + enum typec_port_type type; + u16 revision; /* 0120H = "1.2" */ + u16 pd_revision; /* 0300H = "3.0" */ + int prefer_role; + enum typec_accessory accessory[TYPEC_MAX_ACCESSORY]; + + struct fwnode_handle *fwnode; + + int (*try_role)(const struct typec_capability *, + int role); + + int (*dr_set)(const struct typec_capability *, + enum typec_data_role); + int (*pr_set)(const struct typec_capability *, + enum typec_role); + int (*vconn_set)(const struct typec_capability *, + enum typec_role); + + int (*activate_mode)(const struct typec_capability *, + int mode, int activate); + int (*port_type_set)(const struct typec_capability *, + enum typec_port_type); + +}; + +/* Specific to try_role(). Indicates the user want's to clear the preference. */ +#define TYPEC_NO_PREFERRED_ROLE (-1) + +struct typec_port *typec_register_port(struct device *parent, + const struct typec_capability *cap); +void typec_unregister_port(struct typec_port *port); + +struct typec_partner *typec_register_partner(struct typec_port *port, + struct typec_partner_desc *desc); +void typec_unregister_partner(struct typec_partner *partner); + +struct typec_cable *typec_register_cable(struct typec_port *port, + struct typec_cable_desc *desc); +void typec_unregister_cable(struct typec_cable *cable); + +struct typec_plug *typec_register_plug(struct typec_cable *cable, + struct typec_plug_desc *desc); +void typec_unregister_plug(struct typec_plug *plug); + +void typec_set_data_role(struct typec_port *port, enum typec_data_role role); +void typec_set_pwr_role(struct typec_port *port, enum typec_role role); +void typec_set_vconn_role(struct typec_port *port, enum typec_role role); +void typec_set_pwr_opmode(struct typec_port *port, enum typec_pwr_opmode mode); + +#endif /* __LINUX_USB_TYPEC_H */ diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 6e0ce8c7b8cb..97116379db5f 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -64,6 +64,8 @@ struct usbnet { struct usb_anchor deferred; struct tasklet_struct bh; + struct pcpu_sw_netstats __percpu *stats64; + struct work_struct kevent; unsigned long flags; # define EVENT_TX_HALT 0 @@ -204,6 +206,7 @@ struct cdc_state { }; extern int usbnet_generic_cdc_bind(struct usbnet *, struct usb_interface *); +extern int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf); extern int usbnet_cdc_bind(struct usbnet *, struct usb_interface *); extern void usbnet_cdc_unbind(struct usbnet *, struct usb_interface *); extern void usbnet_cdc_status(struct usbnet *, struct urb *); @@ -261,10 +264,10 @@ extern void usbnet_pause_rx(struct usbnet *); extern void usbnet_resume_rx(struct usbnet *); extern void usbnet_purge_paused_rxq(struct usbnet *); -extern int usbnet_get_settings(struct net_device *net, - struct ethtool_cmd *cmd); -extern int usbnet_set_settings(struct net_device *net, - struct ethtool_cmd *cmd); +extern int usbnet_get_link_ksettings(struct net_device *net, + struct ethtool_link_ksettings *cmd); +extern int usbnet_set_link_ksettings(struct net_device *net, + const struct ethtool_link_ksettings *cmd); extern u32 usbnet_get_link(struct net_device *net); extern u32 usbnet_get_msglevel(struct net_device *); extern void usbnet_set_msglevel(struct net_device *, u32); @@ -278,5 +281,7 @@ extern int usbnet_status_start(struct usbnet *dev, gfp_t mem_flags); extern void usbnet_status_stop(struct usbnet *dev); extern void usbnet_update_max_qlen(struct usbnet *dev); +extern void usbnet_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats); #endif /* __LINUX_USB_USBNET_H */ diff --git a/include/linux/usb/xhci-dbgp.h b/include/linux/usb/xhci-dbgp.h new file mode 100644 index 000000000000..80c1cca1f529 --- /dev/null +++ b/include/linux/usb/xhci-dbgp.h @@ -0,0 +1,29 @@ +/* + * Standalone xHCI debug capability driver + * + * Copyright (C) 2016 Intel Corporation + * + * Author: Lu Baolu <baolu.lu@linux.intel.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_XHCI_DBGP_H +#define __LINUX_XHCI_DBGP_H + +#ifdef CONFIG_EARLY_PRINTK_USB_XDBC +int __init early_xdbc_parse_parameter(char *s); +int __init early_xdbc_setup_hardware(void); +void __init early_xdbc_register_console(void); +#else +static inline int __init early_xdbc_setup_hardware(void) +{ + return -ENODEV; +} +static inline void __init early_xdbc_register_console(void) +{ +} +#endif /* CONFIG_EARLY_PRINTK_USB_XDBC */ +#endif /* __LINUX_XHCI_DBGP_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index eb209d4523f5..b3575ce29148 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -5,6 +5,9 @@ #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/sched.h> +#include <linux/workqueue.h> +#include <linux/rwsem.h> +#include <linux/sysctl.h> #include <linux/err.h> #define UID_GID_MAP_MAX_EXTENTS 5 @@ -32,6 +35,10 @@ enum ucount_type { UCOUNT_NET_NAMESPACES, UCOUNT_MNT_NAMESPACES, UCOUNT_CGROUP_NAMESPACES, +#ifdef CONFIG_INOTIFY_USER + UCOUNT_INOTIFY_INSTANCES, + UCOUNT_INOTIFY_WATCHES, +#endif UCOUNT_COUNTS, }; @@ -59,13 +66,13 @@ struct user_namespace { #endif struct ucounts *ucounts; int ucount_max[UCOUNT_COUNTS]; -}; +} __randomize_layout; struct ucounts { struct hlist_node node; struct user_namespace *ns; kuid_t uid; - atomic_t count; + int count; atomic_t ucount[UCOUNT_COUNTS]; }; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 11b92b047a1e..48a3483dccb1 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -52,6 +52,25 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP); } +extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); +extern void dup_userfaultfd_complete(struct list_head *); + +extern void mremap_userfaultfd_prep(struct vm_area_struct *, + struct vm_userfaultfd_ctx *); +extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *, + unsigned long from, unsigned long to, + unsigned long len); + +extern bool userfaultfd_remove(struct vm_area_struct *vma, + unsigned long start, + unsigned long end); + +extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct list_head *uf); +extern void userfaultfd_unmap_complete(struct mm_struct *mm, + struct list_head *uf); + #else /* CONFIG_USERFAULTFD */ /* mm helpers */ @@ -76,6 +95,47 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) return false; } +static inline int dup_userfaultfd(struct vm_area_struct *vma, + struct list_head *l) +{ + return 0; +} + +static inline void dup_userfaultfd_complete(struct list_head *l) +{ +} + +static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, + struct vm_userfaultfd_ctx *ctx) +{ +} + +static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx, + unsigned long from, + unsigned long to, + unsigned long len) +{ +} + +static inline bool userfaultfd_remove(struct vm_area_struct *vma, + unsigned long start, + unsigned long end) +{ + return true; +} + +static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct list_head *uf) +{ + return 0; +} + +static inline void userfaultfd_unmap_complete(struct mm_struct *mm, + struct list_head *uf) +{ +} + #endif /* CONFIG_USERFAULTFD */ #endif /* _LINUX_USERFAULTFD_K_H */ diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 60f0bb83b313..da826ed059cf 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -26,7 +26,7 @@ struct uts_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct uts_namespace init_uts_ns; #ifdef CONFIG_UTS_NS diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 2d095fc60204..2251e1925ea4 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -18,33 +18,92 @@ #include <uapi/linux/uuid.h> +#define UUID_SIZE 16 + +typedef struct { + __u8 b[UUID_SIZE]; +} uuid_t; + +#define UUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((uuid_t) \ +{{ ((a) >> 24) & 0xff, ((a) >> 16) & 0xff, ((a) >> 8) & 0xff, (a) & 0xff, \ + ((b) >> 8) & 0xff, (b) & 0xff, \ + ((c) >> 8) & 0xff, (c) & 0xff, \ + (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) + /* * The length of a UUID string ("aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee") * not including trailing NUL. */ #define UUID_STRING_LEN 36 -static inline int uuid_le_cmp(const uuid_le u1, const uuid_le u2) +extern const guid_t guid_null; +extern const uuid_t uuid_null; + +static inline bool guid_equal(const guid_t *u1, const guid_t *u2) +{ + return memcmp(u1, u2, sizeof(guid_t)) == 0; +} + +static inline void guid_copy(guid_t *dst, const guid_t *src) +{ + memcpy(dst, src, sizeof(guid_t)); +} + +static inline bool guid_is_null(const guid_t *guid) +{ + return guid_equal(guid, &guid_null); +} + +static inline bool uuid_equal(const uuid_t *u1, const uuid_t *u2) +{ + return memcmp(u1, u2, sizeof(uuid_t)) == 0; +} + +static inline void uuid_copy(uuid_t *dst, const uuid_t *src) { - return memcmp(&u1, &u2, sizeof(uuid_le)); + memcpy(dst, src, sizeof(uuid_t)); } -static inline int uuid_be_cmp(const uuid_be u1, const uuid_be u2) +static inline bool uuid_is_null(const uuid_t *uuid) { - return memcmp(&u1, &u2, sizeof(uuid_be)); + return uuid_equal(uuid, &uuid_null); } void generate_random_uuid(unsigned char uuid[16]); -extern void uuid_le_gen(uuid_le *u); -extern void uuid_be_gen(uuid_be *u); +extern void guid_gen(guid_t *u); +extern void uuid_gen(uuid_t *u); bool __must_check uuid_is_valid(const char *uuid); -extern const u8 uuid_le_index[16]; -extern const u8 uuid_be_index[16]; +extern const u8 guid_index[16]; +extern const u8 uuid_index[16]; + +int guid_parse(const char *uuid, guid_t *u); +int uuid_parse(const char *uuid, uuid_t *u); + +/* backwards compatibility, don't use in new code */ +typedef uuid_t uuid_be; +#define UUID_BE(a, _b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ + UUID_INIT(a, _b, c, d0, d1, d2, d3, d4, d5, d6, d7) +#define NULL_UUID_BE \ + UUID_BE(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00) -int uuid_le_to_bin(const char *uuid, uuid_le *u); -int uuid_be_to_bin(const char *uuid, uuid_be *u); +#define uuid_le_gen(u) guid_gen(u) +#define uuid_be_gen(u) uuid_gen(u) +#define uuid_le_to_bin(guid, u) guid_parse(guid, u) +#define uuid_be_to_bin(uuid, u) uuid_parse(uuid, u) + +static inline int uuid_le_cmp(const guid_t u1, const guid_t u2) +{ + return memcmp(&u1, &u2, sizeof(guid_t)); +} + +static inline int uuid_be_cmp(const uuid_t u1, const uuid_t u2) +{ + return memcmp(&u1, &u2, sizeof(uuid_t)); +} #endif diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 6f8fbcf10dfb..af6c03f7f986 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -24,10 +24,17 @@ #ifndef MODULE_ARCH_VERMAGIC #define MODULE_ARCH_VERMAGIC "" #endif +#ifdef RANDSTRUCT_PLUGIN +#include <generated/randomize_layout_hash.h> +#define MODULE_RANDSTRUCT_PLUGIN "RANDSTRUCT_PLUGIN_" RANDSTRUCT_HASHED_SEED +#else +#define MODULE_RANDSTRUCT_PLUGIN +#endif #define VERMAGIC_STRING \ UTS_RELEASE " " \ MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \ MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \ - MODULE_ARCH_VERMAGIC + MODULE_ARCH_VERMAGIC \ + MODULE_RANDSTRUCT_PLUGIN diff --git a/include/linux/vfio.h b/include/linux/vfio.h index edf9b2cad277..586809abb273 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -97,6 +97,8 @@ extern void vfio_unregister_iommu_driver( */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); +extern bool vfio_external_group_match_file(struct vfio_group *group, + struct file *filep); extern int vfio_external_user_iommu_id(struct vfio_group *group); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); @@ -183,7 +185,7 @@ struct virqfd { void (*thread)(void *, void *); void *data; struct work_struct inject; - wait_queue_t wait; + wait_queue_entry_t wait; poll_table pt; struct work_struct shutdown; struct virqfd **pvirqfd; diff --git a/include/linux/virtio.h b/include/linux/virtio.h index d5eb5479a425..28b0e965360f 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -44,6 +44,12 @@ int virtqueue_add_inbuf(struct virtqueue *vq, void *data, gfp_t gfp); +int virtqueue_add_inbuf_ctx(struct virtqueue *vq, + struct scatterlist sg[], unsigned int num, + void *data, + void *ctx, + gfp_t gfp); + int virtqueue_add_sgs(struct virtqueue *vq, struct scatterlist *sgs[], unsigned int out_sgs, @@ -59,6 +65,9 @@ bool virtqueue_notify(struct virtqueue *vq); void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len); +void *virtqueue_get_buf_ctx(struct virtqueue *vq, unsigned int *len, + void **ctx); + void virtqueue_disable_cb(struct virtqueue *vq); bool virtqueue_enable_cb(struct virtqueue *vq); @@ -132,12 +141,16 @@ static inline struct virtio_device *dev_to_virtio(struct device *_dev) return container_of(_dev, struct virtio_device, dev); } +void virtio_add_status(struct virtio_device *dev, unsigned int status); int register_virtio_device(struct virtio_device *dev); void unregister_virtio_device(struct virtio_device *dev); void virtio_break_device(struct virtio_device *dev); void virtio_config_changed(struct virtio_device *dev); +void virtio_config_disable(struct virtio_device *dev); +void virtio_config_enable(struct virtio_device *dev); +int virtio_finalize_features(struct virtio_device *dev); #ifdef CONFIG_PM_SLEEP int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); @@ -152,9 +165,13 @@ int virtio_device_restore(struct virtio_device *dev); * @feature_table_legacy: same as feature_table but when working in legacy mode. * @feature_table_size_legacy: number of entries in feature table legacy array. * @probe: the function to call when a device is found. Returns 0 or -errno. + * @scan: optional function to call after successful probe; intended + * for virtio-scsi to invoke a scan. * @remove: the function to call when a device is removed. * @config_changed: optional function to call when the device configuration * changes; may be called in interrupt context. + * @freeze: optional function to call during suspend/hibernation. + * @restore: optional function to call on resume. */ struct virtio_driver { struct device_driver driver; @@ -163,6 +180,7 @@ struct virtio_driver { unsigned int feature_table_size; const unsigned int *feature_table_legacy; unsigned int feature_table_size_legacy; + int (*validate)(struct virtio_device *dev); int (*probe)(struct virtio_device *dev); void (*scan)(struct virtio_device *dev); void (*remove)(struct virtio_device *dev); diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 26c155bb639b..0133d8a12ccd 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -7,6 +7,8 @@ #include <linux/virtio_byteorder.h> #include <uapi/linux/virtio_config.h> +struct irq_affinity; + /** * virtio_config_ops - operations for configuring a virtio device * @get: read the value of a configuration field @@ -56,6 +58,7 @@ * This returns a pointer to the bus name a la pci_name from which * the caller can then copy. * @set_vq_affinity: set the affinity for a virtqueue. + * @get_vq_affinity: get the affinity for a virtqueue (optional). */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { @@ -68,14 +71,16 @@ struct virtio_config_ops { void (*set_status)(struct virtio_device *vdev, u8 status); void (*reset)(struct virtio_device *vdev); int (*find_vqs)(struct virtio_device *, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[]); + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], const bool *ctx, + struct irq_affinity *desc); void (*del_vqs)(struct virtio_device *); u64 (*get_features)(struct virtio_device *vdev); int (*finalize_features)(struct virtio_device *vdev); const char *(*bus_name)(struct virtio_device *vdev); int (*set_vq_affinity)(struct virtqueue *vq, int cpu); + const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev, + int index); }; /* If driver didn't advertise the feature, it will never appear. */ @@ -169,12 +174,32 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev, vq_callback_t *callbacks[] = { c }; const char *names[] = { n }; struct virtqueue *vq; - int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names); + int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL, + NULL); if (err < 0) return ERR_PTR(err); return vq; } +static inline +int virtio_find_vqs(struct virtio_device *vdev, unsigned nvqs, + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], + struct irq_affinity *desc) +{ + return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, desc); +} + +static inline +int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], const bool *ctx, + struct irq_affinity *desc) +{ + return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, + desc); +} + /** * virtio_device_ready - enable vq use in probe function * @vdev: the device diff --git a/include/linux/virtio_mmio.h b/include/linux/virtio_mmio.h deleted file mode 100644 index c4b09689ab64..000000000000 --- a/include/linux/virtio_mmio.h +++ /dev/null @@ -1,141 +0,0 @@ -/* - * Virtio platform device driver - * - * Copyright 2011, ARM Ltd. - * - * Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007 - * - * This header is BSD licensed so anyone can use the definitions to implement - * compatible drivers/servers. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of IBM nor the names of its contributors - * may be used to endorse or promote products derived from this software - * without specific prior written permission. - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND - * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL - * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS - * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT - * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY - * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF - * SUCH DAMAGE. - */ - -#ifndef _LINUX_VIRTIO_MMIO_H -#define _LINUX_VIRTIO_MMIO_H - -/* - * Control registers - */ - -/* Magic value ("virt" string) - Read Only */ -#define VIRTIO_MMIO_MAGIC_VALUE 0x000 - -/* Virtio device version - Read Only */ -#define VIRTIO_MMIO_VERSION 0x004 - -/* Virtio device ID - Read Only */ -#define VIRTIO_MMIO_DEVICE_ID 0x008 - -/* Virtio vendor ID - Read Only */ -#define VIRTIO_MMIO_VENDOR_ID 0x00c - -/* Bitmask of the features supported by the device (host) - * (32 bits per set) - Read Only */ -#define VIRTIO_MMIO_DEVICE_FEATURES 0x010 - -/* Device (host) features set selector - Write Only */ -#define VIRTIO_MMIO_DEVICE_FEATURES_SEL 0x014 - -/* Bitmask of features activated by the driver (guest) - * (32 bits per set) - Write Only */ -#define VIRTIO_MMIO_DRIVER_FEATURES 0x020 - -/* Activated features set selector - Write Only */ -#define VIRTIO_MMIO_DRIVER_FEATURES_SEL 0x024 - - -#ifndef VIRTIO_MMIO_NO_LEGACY /* LEGACY DEVICES ONLY! */ - -/* Guest's memory page size in bytes - Write Only */ -#define VIRTIO_MMIO_GUEST_PAGE_SIZE 0x028 - -#endif - - -/* Queue selector - Write Only */ -#define VIRTIO_MMIO_QUEUE_SEL 0x030 - -/* Maximum size of the currently selected queue - Read Only */ -#define VIRTIO_MMIO_QUEUE_NUM_MAX 0x034 - -/* Queue size for the currently selected queue - Write Only */ -#define VIRTIO_MMIO_QUEUE_NUM 0x038 - - -#ifndef VIRTIO_MMIO_NO_LEGACY /* LEGACY DEVICES ONLY! */ - -/* Used Ring alignment for the currently selected queue - Write Only */ -#define VIRTIO_MMIO_QUEUE_ALIGN 0x03c - -/* Guest's PFN for the currently selected queue - Read Write */ -#define VIRTIO_MMIO_QUEUE_PFN 0x040 - -#endif - - -/* Ready bit for the currently selected queue - Read Write */ -#define VIRTIO_MMIO_QUEUE_READY 0x044 - -/* Queue notifier - Write Only */ -#define VIRTIO_MMIO_QUEUE_NOTIFY 0x050 - -/* Interrupt status - Read Only */ -#define VIRTIO_MMIO_INTERRUPT_STATUS 0x060 - -/* Interrupt acknowledge - Write Only */ -#define VIRTIO_MMIO_INTERRUPT_ACK 0x064 - -/* Device status register - Read Write */ -#define VIRTIO_MMIO_STATUS 0x070 - -/* Selected queue's Descriptor Table address, 64 bits in two halves */ -#define VIRTIO_MMIO_QUEUE_DESC_LOW 0x080 -#define VIRTIO_MMIO_QUEUE_DESC_HIGH 0x084 - -/* Selected queue's Available Ring address, 64 bits in two halves */ -#define VIRTIO_MMIO_QUEUE_AVAIL_LOW 0x090 -#define VIRTIO_MMIO_QUEUE_AVAIL_HIGH 0x094 - -/* Selected queue's Used Ring address, 64 bits in two halves */ -#define VIRTIO_MMIO_QUEUE_USED_LOW 0x0a0 -#define VIRTIO_MMIO_QUEUE_USED_HIGH 0x0a4 - -/* Configuration atomicity value */ -#define VIRTIO_MMIO_CONFIG_GENERATION 0x0fc - -/* The config space is defined by each driver as - * the per-driver configuration space - Read Write */ -#define VIRTIO_MMIO_CONFIG 0x100 - - - -/* - * Interrupt flags (re: interrupt status & acknowledge registers) - */ - -#define VIRTIO_MMIO_INT_VRING (1 << 0) -#define VIRTIO_MMIO_INT_CONFIG (1 << 1) - -#endif diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index e8d36938f09a..270cfa81830e 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -71,6 +71,7 @@ struct virtqueue *vring_create_virtqueue(unsigned int index, struct virtio_device *vdev, bool weak_barriers, bool may_reduce_num, + bool ctx, bool (*notify)(struct virtqueue *vq), void (*callback)(struct virtqueue *vq), const char *name); @@ -80,6 +81,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, struct vring vring, struct virtio_device *vdev, bool weak_barriers, + bool ctx, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name); @@ -93,6 +95,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int index, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, + bool ctx, void *pages, bool (*notify)(struct virtqueue *vq), void (*callback)(struct virtqueue *vq), diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 9638bfeb0d1f..ab13f0743da8 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -48,6 +48,8 @@ struct virtio_vsock_pkt { struct virtio_vsock_hdr hdr; struct work_struct work; struct list_head list; + /* socket refcnt not held, only use for cancellation */ + struct vsock_sock *vsk; void *buf; u32 len; u32 off; @@ -56,6 +58,7 @@ struct virtio_vsock_pkt { struct virtio_vsock_pkt_info { u32 remote_cid, remote_port; + struct vsock_sock *vsk; struct msghdr *msg; u32 pkt_len; u16 type; @@ -150,5 +153,6 @@ void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt); void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt); u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit); +void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt); #endif /* _LINUX_VIRTIO_VSOCK_H */ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 4d6ec58a8d45..37e8d31a4632 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -25,7 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, FOR_ALL_ZONES(PGALLOC), FOR_ALL_ZONES(ALLOCSTALL), FOR_ALL_ZONES(PGSCAN_SKIP), - PGFREE, PGACTIVATE, PGDEACTIVATE, + PGFREE, PGACTIVATE, PGDEACTIVATE, PGLAZYFREE, PGFAULT, PGMAJFAULT, PGLAZYFREED, PGREFILL, @@ -41,6 +41,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, PAGEOUTRUN, PGROTATED, DROP_PAGECACHE, DROP_SLAB, + OOM_KILL, #ifdef CONFIG_NUMA_BALANCING NUMA_PTE_UPDATES, NUMA_HUGE_PTE_UPDATES, @@ -56,6 +57,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, COMPACTISOLATED, COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS, KCOMPACTD_WAKE, + KCOMPACTD_MIGRATE_SCANNED, KCOMPACTD_FREE_SCANNED, #endif #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, @@ -78,6 +80,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_SPLIT_PAGE_FAILED, THP_DEFERRED_SPLIT_PAGE, THP_SPLIT_PMD, +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + THP_SPLIT_PUD, +#endif THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif @@ -89,10 +94,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif #endif #ifdef CONFIG_DEBUG_TLBFLUSH -#ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ -#endif /* CONFIG_SMP */ NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, #endif /* CONFIG_DEBUG_TLBFLUSH */ diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h index c3fa0fd43949..1081db987391 100644 --- a/include/linux/vmacache.h +++ b/include/linux/vmacache.h @@ -12,7 +12,7 @@ static inline void vmacache_flush(struct task_struct *tsk) { - memset(tsk->vmacache, 0, sizeof(tsk->vmacache)); + memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); } extern void vmacache_flush_all(struct mm_struct *mm); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index d68edffbf142..2d92dd002abd 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -80,6 +80,17 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller); +#ifndef CONFIG_MMU +extern void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags); +static inline void *__vmalloc_node_flags_caller(unsigned long size, int node, + gfp_t flags, void *caller) +{ + return __vmalloc_node_flags(size, node, flags); +} +#else +extern void *__vmalloc_node_flags_caller(unsigned long size, + int node, gfp_t flags, void *caller); +#endif extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); diff --git a/include/linux/vme.h b/include/linux/vme.h index 8c589176c2f8..25874da3f2e1 100644 --- a/include/linux/vme.h +++ b/include/linux/vme.h @@ -92,7 +92,7 @@ extern struct bus_type vme_bus_type; #define VME_SLOT_ALL -2 /** - * Structure representing a VME device + * struct vme_dev - Structure representing a VME device * @num: The device number * @bridge: Pointer to the bridge device this device is on * @dev: Internal device structure @@ -107,8 +107,17 @@ struct vme_dev { struct list_head bridge_list; }; +/** + * struct vme_driver - Structure representing a VME driver + * @name: Driver name, should be unique among VME drivers and usually the same + * as the module name. + * @match: Callback used to determine whether probe should be run. + * @probe: Callback for device binding, called when new device is detected. + * @remove: Callback, called on device removal. + * @driver: Underlying generic device driver structure. + * @devices: List of VME devices (struct vme_dev) associated with this driver. + */ struct vme_driver { - struct list_head node; const char *name; int (*match)(struct vme_dev *); int (*probe)(struct vme_dev *); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 613771909b6e..b3d85f30d424 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -3,7 +3,6 @@ #include <linux/types.h> #include <linux/percpu.h> -#include <linux/mm.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index 1bd31a38c51e..b724ef7005de 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -54,13 +54,6 @@ #define VMCI_IMR_DATAGRAM 0x1 #define VMCI_IMR_NOTIFICATION 0x2 -/* Interrupt type. */ -enum { - VMCI_INTR_TYPE_INTX = 0, - VMCI_INTR_TYPE_MSI = 1, - VMCI_INTR_TYPE_MSIX = 2, -}; - /* Maximum MSI/MSI-X interrupt vectors in the device. */ #define VMCI_MAX_INTRS 2 diff --git a/include/linux/vtime.h b/include/linux/vtime.h index aa9bfea8804a..18b405e3cd93 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -58,23 +58,17 @@ static inline void vtime_task_switch(struct task_struct *prev) extern void vtime_account_system(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); -extern void vtime_account_user(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ static inline void vtime_task_switch(struct task_struct *prev) { } static inline void vtime_account_system(struct task_struct *tsk) { } -static inline void vtime_account_user(struct task_struct *tsk) { } #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void arch_vtime_task_switch(struct task_struct *tsk); extern void vtime_user_enter(struct task_struct *tsk); - -static inline void vtime_user_exit(struct task_struct *tsk) -{ - vtime_account_user(tsk); -} +extern void vtime_user_exit(struct task_struct *tsk); extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); extern void vtime_init_idle(struct task_struct *tsk, int cpu); @@ -93,9 +87,11 @@ static inline void vtime_account_irq_exit(struct task_struct *tsk) /* On hard|softirq exit we always account to hard|softirq cputime */ vtime_account_system(tsk); } +extern void vtime_flush(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static inline void vtime_account_irq_enter(struct task_struct *tsk) { } static inline void vtime_account_irq_exit(struct task_struct *tsk) { } +static inline void vtime_flush(struct task_struct *tsk) { } #endif diff --git a/include/linux/w1.h b/include/linux/w1.h new file mode 100644 index 000000000000..90cbe7e65059 --- /dev/null +++ b/include/linux/w1.h @@ -0,0 +1,320 @@ +/* + * Copyright (c) 2004 Evgeniy Polyakov <zbr@ioremap.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_W1_H +#define __LINUX_W1_H + +#include <linux/device.h> + +/** + * struct w1_reg_num - broken out slave device id + * + * @family: identifies the type of device + * @id: along with family is the unique device id + * @crc: checksum of the other bytes + */ +struct w1_reg_num { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u64 family:8, + id:48, + crc:8; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u64 crc:8, + id:48, + family:8; +#else +#error "Please fix <asm/byteorder.h>" +#endif +}; + +#ifdef __KERNEL__ + +#define W1_MAXNAMELEN 32 + +#define W1_SEARCH 0xF0 +#define W1_ALARM_SEARCH 0xEC +#define W1_CONVERT_TEMP 0x44 +#define W1_SKIP_ROM 0xCC +#define W1_COPY_SCRATCHPAD 0x48 +#define W1_WRITE_SCRATCHPAD 0x4E +#define W1_READ_SCRATCHPAD 0xBE +#define W1_READ_ROM 0x33 +#define W1_READ_PSUPPLY 0xB4 +#define W1_MATCH_ROM 0x55 +#define W1_RESUME_CMD 0xA5 + +/** + * struct w1_slave - holds a single slave device on the bus + * + * @owner: Points to the one wire "wire" kernel module. + * @name: Device id is ascii. + * @w1_slave_entry: data for the linked list + * @reg_num: the slave id in binary + * @refcnt: reference count, delete when 0 + * @flags: bit flags for W1_SLAVE_ACTIVE W1_SLAVE_DETACH + * @ttl: decrement per search this slave isn't found, deatch at 0 + * @master: bus which this slave is on + * @family: module for device family type + * @family_data: pointer for use by the family module + * @dev: kernel device identifier + * + */ +struct w1_slave { + struct module *owner; + unsigned char name[W1_MAXNAMELEN]; + struct list_head w1_slave_entry; + struct w1_reg_num reg_num; + atomic_t refcnt; + int ttl; + unsigned long flags; + + struct w1_master *master; + struct w1_family *family; + void *family_data; + struct device dev; +}; + +typedef void (*w1_slave_found_callback)(struct w1_master *, u64); + +/** + * struct w1_bus_master - operations available on a bus master + * + * @data: the first parameter in all the functions below + * + * @read_bit: Sample the line level @return the level read (0 or 1) + * + * @write_bit: Sets the line level + * + * @touch_bit: the lowest-level function for devices that really support the + * 1-wire protocol. + * touch_bit(0) = write-0 cycle + * touch_bit(1) = write-1 / read cycle + * @return the bit read (0 or 1) + * + * @read_byte: Reads a bytes. Same as 8 touch_bit(1) calls. + * @return the byte read + * + * @write_byte: Writes a byte. Same as 8 touch_bit(x) calls. + * + * @read_block: Same as a series of read_byte() calls + * @return the number of bytes read + * + * @write_block: Same as a series of write_byte() calls + * + * @triplet: Combines two reads and a smart write for ROM searches + * @return bit0=Id bit1=comp_id bit2=dir_taken + * + * @reset_bus: long write-0 with a read for the presence pulse detection + * @return -1=Error, 0=Device present, 1=No device present + * + * @set_pullup: Put out a strong pull-up pulse of the specified duration. + * @return -1=Error, 0=completed + * + * @search: Really nice hardware can handles the different types of ROM search + * w1_master* is passed to the slave found callback. + * u8 is search_type, W1_SEARCH or W1_ALARM_SEARCH + * + * Note: read_bit and write_bit are very low level functions and should only + * be used with hardware that doesn't really support 1-wire operations, + * like a parallel/serial port. + * Either define read_bit and write_bit OR define, at minimum, touch_bit and + * reset_bus. + * + */ +struct w1_bus_master { + void *data; + + u8 (*read_bit)(void *); + + void (*write_bit)(void *, u8); + + u8 (*touch_bit)(void *, u8); + + u8 (*read_byte)(void *); + + void (*write_byte)(void *, u8); + + u8 (*read_block)(void *, u8 *, int); + + void (*write_block)(void *, const u8 *, int); + + u8 (*triplet)(void *, u8); + + u8 (*reset_bus)(void *); + + u8 (*set_pullup)(void *, int); + + void (*search)(void *, struct w1_master *, + u8, w1_slave_found_callback); +}; + +/** + * enum w1_master_flags - bitfields used in w1_master.flags + * @W1_ABORT_SEARCH: abort searching early on shutdown + * @W1_WARN_MAX_COUNT: limit warning when the maximum count is reached + */ +enum w1_master_flags { + W1_ABORT_SEARCH = 0, + W1_WARN_MAX_COUNT = 1, +}; + +/** + * struct w1_master - one per bus master + * @w1_master_entry: master linked list + * @owner: module owner + * @name: dynamically allocate bus name + * @list_mutex: protect slist and async_list + * @slist: linked list of slaves + * @async_list: linked list of netlink commands to execute + * @max_slave_count: maximum number of slaves to search for at a time + * @slave_count: current number of slaves known + * @attempts: number of searches ran + * @slave_ttl: number of searches before a slave is timed out + * @initialized: prevent init/removal race conditions + * @id: w1 bus number + * @search_count: number of automatic searches to run, -1 unlimited + * @search_id: allows continuing a search + * @refcnt: reference count + * @priv: private data storage + * @enable_pullup: allows a strong pullup + * @pullup_duration: time for the next strong pullup + * @flags: one of w1_master_flags + * @thread: thread for bus search and netlink commands + * @mutex: protect most of w1_master + * @bus_mutex: pretect concurrent bus access + * @driver: sysfs driver + * @dev: sysfs device + * @bus_master: io operations available + * @seq: sequence number used for netlink broadcasts + */ +struct w1_master { + struct list_head w1_master_entry; + struct module *owner; + unsigned char name[W1_MAXNAMELEN]; + /* list_mutex protects just slist and async_list so slaves can be + * searched for and async commands added while the master has + * w1_master.mutex locked and is operating on the bus. + * lock order w1_mlock, w1_master.mutex, w1_master.list_mutex + */ + struct mutex list_mutex; + struct list_head slist; + struct list_head async_list; + int max_slave_count, slave_count; + unsigned long attempts; + int slave_ttl; + int initialized; + u32 id; + int search_count; + /* id to start searching on, to continue a search or 0 to restart */ + u64 search_id; + + atomic_t refcnt; + + void *priv; + + /** 5V strong pullup enabled flag, 1 enabled, zero disabled. */ + int enable_pullup; + /** 5V strong pullup duration in milliseconds, zero disabled. */ + int pullup_duration; + + long flags; + + struct task_struct *thread; + struct mutex mutex; + struct mutex bus_mutex; + + struct device_driver *driver; + struct device dev; + + struct w1_bus_master *bus_master; + + u32 seq; +}; + +int w1_add_master_device(struct w1_bus_master *master); +void w1_remove_master_device(struct w1_bus_master *master); + +/** + * struct w1_family_ops - operations for a family type + * @add_slave: add_slave + * @remove_slave: remove_slave + * @groups: sysfs group + */ +struct w1_family_ops { + int (*add_slave)(struct w1_slave *sl); + void (*remove_slave)(struct w1_slave *sl); + const struct attribute_group **groups; +}; + +/** + * struct w1_family - reference counted family structure. + * @family_entry: family linked list + * @fid: 8 bit family identifier + * @fops: operations for this family + * @refcnt: reference counter + */ +struct w1_family { + struct list_head family_entry; + u8 fid; + + struct w1_family_ops *fops; + + atomic_t refcnt; +}; + +int w1_register_family(struct w1_family *family); +void w1_unregister_family(struct w1_family *family); + +/** + * module_w1_driver() - Helper macro for registering a 1-Wire families + * @__w1_family: w1_family struct + * + * Helper macro for 1-Wire families which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only + * use this macro once, and calling it replaces module_init() and module_exit() + */ +#define module_w1_family(__w1_family) \ + module_driver(__w1_family, w1_register_family, \ + w1_unregister_family) + +u8 w1_triplet(struct w1_master *dev, int bdir); +void w1_write_8(struct w1_master *, u8); +u8 w1_read_8(struct w1_master *); +int w1_reset_bus(struct w1_master *); +u8 w1_calc_crc8(u8 *, int); +void w1_write_block(struct w1_master *, const u8 *, int); +void w1_touch_block(struct w1_master *, u8 *, int); +u8 w1_read_block(struct w1_master *, u8 *, int); +int w1_reset_select_slave(struct w1_slave *sl); +int w1_reset_resume_command(struct w1_master *); +void w1_next_pullup(struct w1_master *, int); + +static inline struct w1_slave* dev_to_w1_slave(struct device *dev) +{ + return container_of(dev, struct w1_slave, dev); +} + +static inline struct w1_slave* kobj_to_w1_slave(struct kobject *kobj) +{ + return dev_to_w1_slave(container_of(kobj, struct device, kobj)); +} + +static inline struct w1_master* dev_to_w1_master(struct device *dev) +{ + return container_of(dev, struct w1_master, dev); +} + +#endif /* __KERNEL__ */ + +#endif /* __LINUX_W1_H */ diff --git a/include/linux/wait.h b/include/linux/wait.h index 1421132e9086..b289c96151ee 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -6,41 +6,34 @@ #include <linux/list.h> #include <linux/stddef.h> #include <linux/spinlock.h> + #include <asm/current.h> #include <uapi/linux/wait.h> -typedef struct __wait_queue wait_queue_t; -typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key); -int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key); +typedef struct wait_queue_entry wait_queue_entry_t; + +typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); +int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); -/* __wait_queue::flags */ +/* wait_queue_entry::flags */ #define WQ_FLAG_EXCLUSIVE 0x01 #define WQ_FLAG_WOKEN 0x02 -struct __wait_queue { +/* + * A single wait-queue entry structure: + */ +struct wait_queue_entry { unsigned int flags; void *private; wait_queue_func_t func; - struct list_head task_list; -}; - -struct wait_bit_key { - void *flags; - int bit_nr; -#define WAIT_ATOMIC_T_BIT_NR -1 - unsigned long timeout; -}; - -struct wait_bit_queue { - struct wait_bit_key key; - wait_queue_t wait; + struct list_head entry; }; -struct __wait_queue_head { +struct wait_queue_head { spinlock_t lock; - struct list_head task_list; + struct list_head head; }; -typedef struct __wait_queue_head wait_queue_head_t; +typedef struct wait_queue_head wait_queue_head_t; struct task_struct; @@ -48,82 +41,76 @@ struct task_struct; * Macros for declaration and initialisaton of the datatypes */ -#define __WAITQUEUE_INITIALIZER(name, tsk) { \ - .private = tsk, \ - .func = default_wake_function, \ - .task_list = { NULL, NULL } } +#define __WAITQUEUE_INITIALIZER(name, tsk) { \ + .private = tsk, \ + .func = default_wake_function, \ + .entry = { NULL, NULL } } -#define DECLARE_WAITQUEUE(name, tsk) \ - wait_queue_t name = __WAITQUEUE_INITIALIZER(name, tsk) +#define DECLARE_WAITQUEUE(name, tsk) \ + struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk) -#define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .task_list = { &(name).task_list, &(name).task_list } } +#define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .head = { &(name).head, &(name).head } } #define DECLARE_WAIT_QUEUE_HEAD(name) \ - wait_queue_head_t name = __WAIT_QUEUE_HEAD_INITIALIZER(name) - -#define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ - { .flags = word, .bit_nr = bit, } - -#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p) \ - { .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, } + struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name) -extern void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *); +extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *); -#define init_waitqueue_head(q) \ - do { \ - static struct lock_class_key __key; \ - \ - __init_waitqueue_head((q), #q, &__key); \ +#define init_waitqueue_head(wq_head) \ + do { \ + static struct lock_class_key __key; \ + \ + __init_waitqueue_head((wq_head), #wq_head, &__key); \ } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ ({ init_waitqueue_head(&name); name; }) # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \ - wait_queue_head_t name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) + struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) #else # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name) #endif -static inline void init_waitqueue_entry(wait_queue_t *q, struct task_struct *p) +static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p) { - q->flags = 0; - q->private = p; - q->func = default_wake_function; + wq_entry->flags = 0; + wq_entry->private = p; + wq_entry->func = default_wake_function; } static inline void -init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func) +init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func) { - q->flags = 0; - q->private = NULL; - q->func = func; + wq_entry->flags = 0; + wq_entry->private = NULL; + wq_entry->func = func; } /** * waitqueue_active -- locklessly test for waiters on the queue - * @q: the waitqueue to test for waiters + * @wq_head: the waitqueue to test for waiters * * returns true if the wait list is not empty * * NOTE: this function is lockless and requires care, incorrect usage _will_ * lead to sporadic and non-obvious failure. * - * Use either while holding wait_queue_head_t::lock or when used for wakeups + * Use either while holding wait_queue_head::lock or when used for wakeups * with an extra smp_mb() like: * * CPU0 - waker CPU1 - waiter * * for (;;) { - * @cond = true; prepare_to_wait(&wq, &wait, state); + * @cond = true; prepare_to_wait(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() - * if (waitqueue_active(wq)) if (@cond) - * wake_up(wq); break; + * if (waitqueue_active(wq_head)) if (@cond) + * wake_up(wq_head); break; * schedule(); * } - * finish_wait(&wq, &wait); + * finish_wait(&wq_head, &wait); * * Because without the explicit smp_mb() it's possible for the * waitqueue_active() load to get hoisted over the @cond store such that we'll @@ -132,20 +119,20 @@ init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func) * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), * which (when the lock is uncontended) are of roughly equal cost. */ -static inline int waitqueue_active(wait_queue_head_t *q) +static inline int waitqueue_active(struct wait_queue_head *wq_head) { - return !list_empty(&q->task_list); + return !list_empty(&wq_head->head); } /** * wq_has_sleeper - check if there are any waiting processes - * @wq: wait queue head + * @wq_head: wait queue head * - * Returns true if wq has waiting processes + * Returns true if wq_head has waiting processes * * Please refer to the comment for waitqueue_active. */ -static inline bool wq_has_sleeper(wait_queue_head_t *wq) +static inline bool wq_has_sleeper(struct wait_queue_head *wq_head) { /* * We need to be sure we are in sync with the @@ -155,63 +142,51 @@ static inline bool wq_has_sleeper(wait_queue_head_t *wq) * waiting side. */ smp_mb(); - return waitqueue_active(wq); + return waitqueue_active(wq_head); } -extern void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait); -extern void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait); -extern void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait); +extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); -static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new) +static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - list_add(&new->task_list, &head->task_list); + list_add(&wq_entry->entry, &wq_head->head); } /* * Used for wake-one threads: */ static inline void -__add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +__add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - wait->flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue(q, wait); + wq_entry->flags |= WQ_FLAG_EXCLUSIVE; + __add_wait_queue(wq_head, wq_entry); } -static inline void __add_wait_queue_tail(wait_queue_head_t *head, - wait_queue_t *new) +static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - list_add_tail(&new->task_list, &head->task_list); + list_add_tail(&wq_entry->entry, &wq_head->head); } static inline void -__add_wait_queue_tail_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +__add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - wait->flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue_tail(q, wait); + wq_entry->flags |= WQ_FLAG_EXCLUSIVE; + __add_wait_queue_entry_tail(wq_head, wq_entry); } static inline void -__remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) +__remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { - list_del(&old->task_list); + list_del(&wq_entry->entry); } -typedef int wait_bit_action_f(struct wait_bit_key *, int mode); -void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); -void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); -void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); -void __wake_up_bit(wait_queue_head_t *, void *, int); -int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); -int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); -void wake_up_bit(void *, int); -void wake_up_atomic_t(atomic_t *); -int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned); -int out_of_line_wait_on_bit_timeout(void *, int, wait_bit_action_f *, unsigned, unsigned long); -int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned); -int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned); -wait_queue_head_t *bit_waitqueue(void *, int); +void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); +void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); +void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); +void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); +void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) @@ -227,28 +202,28 @@ wait_queue_head_t *bit_waitqueue(void *, int); /* * Wakeup macros to be used to report events to the targets. */ -#define wake_up_poll(x, m) \ +#define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, (void *) (m)) -#define wake_up_locked_poll(x, m) \ +#define wake_up_locked_poll(x, m) \ __wake_up_locked_key((x), TASK_NORMAL, (void *) (m)) -#define wake_up_interruptible_poll(x, m) \ +#define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m)) -#define wake_up_interruptible_sync_poll(x, m) \ +#define wake_up_interruptible_sync_poll(x, m) \ __wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, (void *) (m)) -#define ___wait_cond_timeout(condition) \ -({ \ - bool __cond = (condition); \ - if (__cond && !__ret) \ - __ret = 1; \ - __cond || !__ret; \ +#define ___wait_cond_timeout(condition) \ +({ \ + bool __cond = (condition); \ + if (__cond && !__ret) \ + __ret = 1; \ + __cond || !__ret; \ }) -#define ___wait_is_interruptible(state) \ - (!__builtin_constant_p(state) || \ - state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ +#define ___wait_is_interruptible(state) \ + (!__builtin_constant_p(state) || \ + state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ -extern void init_wait_entry(wait_queue_t *__wait, int flags); +extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); /* * The below macro ___wait_event() has an explicit shadow of the __ret @@ -262,108 +237,108 @@ extern void init_wait_entry(wait_queue_t *__wait, int flags); * otherwise. */ -#define ___wait_event(wq, condition, state, exclusive, ret, cmd) \ -({ \ - __label__ __out; \ - wait_queue_t __wait; \ - long __ret = ret; /* explicit shadow */ \ - \ - init_wait_entry(&__wait, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ - for (;;) { \ - long __int = prepare_to_wait_event(&wq, &__wait, state);\ - \ - if (condition) \ - break; \ - \ - if (___wait_is_interruptible(state) && __int) { \ - __ret = __int; \ - goto __out; \ - } \ - \ - cmd; \ - } \ - finish_wait(&wq, &__wait); \ -__out: __ret; \ +#define ___wait_event(wq_head, condition, state, exclusive, ret, cmd) \ +({ \ + __label__ __out; \ + struct wait_queue_entry __wq_entry; \ + long __ret = ret; /* explicit shadow */ \ + \ + init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ + for (;;) { \ + long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\ + \ + if (condition) \ + break; \ + \ + if (___wait_is_interruptible(state) && __int) { \ + __ret = __int; \ + goto __out; \ + } \ + \ + cmd; \ + } \ + finish_wait(&wq_head, &__wq_entry); \ +__out: __ret; \ }) -#define __wait_event(wq, condition) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ +#define __wait_event(wq_head, condition) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event - sleep until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ -#define wait_event(wq, condition) \ -do { \ - might_sleep(); \ - if (condition) \ - break; \ - __wait_event(wq, condition); \ +#define wait_event(wq_head, condition) \ +do { \ + might_sleep(); \ + if (condition) \ + break; \ + __wait_event(wq_head, condition); \ } while (0) -#define __io_wait_event(wq, condition) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ +#define __io_wait_event(wq_head, condition) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ io_schedule()) /* * io_wait_event() -- like wait_event() but with io_schedule() */ -#define io_wait_event(wq, condition) \ -do { \ - might_sleep(); \ - if (condition) \ - break; \ - __io_wait_event(wq, condition); \ +#define io_wait_event(wq_head, condition) \ +do { \ + might_sleep(); \ + if (condition) \ + break; \ + __io_wait_event(wq_head, condition); \ } while (0) -#define __wait_event_freezable(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ +#define __wait_event_freezable(wq_head, condition) \ + ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule(); try_to_freeze()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute * to system load) until the @condition evaluates to true. The - * @condition is checked each time the waitqueue @wq is woken up. + * @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ -#define wait_event_freezable(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_freezable(wq, condition); \ - __ret; \ +#define wait_event_freezable(wq_head, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_freezable(wq_head, condition); \ + __ret; \ }) -#define __wait_event_timeout(wq, condition, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_UNINTERRUPTIBLE, 0, timeout, \ +#define __wait_event_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_timeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -374,83 +349,83 @@ do { \ * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ -#define wait_event_timeout(wq, condition, timeout) \ -({ \ - long __ret = timeout; \ - might_sleep(); \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_timeout(wq, condition, timeout); \ - __ret; \ +#define wait_event_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_timeout(wq_head, condition, timeout); \ + __ret; \ }) -#define __wait_event_freezable_timeout(wq, condition, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ +#define __wait_event_freezable_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret); try_to_freeze()) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid * increasing load and is freezable. */ -#define wait_event_freezable_timeout(wq, condition, timeout) \ -({ \ - long __ret = timeout; \ - might_sleep(); \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_freezable_timeout(wq, condition, timeout); \ - __ret; \ +#define wait_event_freezable_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \ + __ret; \ }) -#define __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ +#define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ cmd1; schedule(); cmd2) /* * Just like wait_event_cmd(), except it sets exclusive flag */ -#define wait_event_exclusive_cmd(wq, condition, cmd1, cmd2) \ -do { \ - if (condition) \ - break; \ - __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2); \ +#define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ +do { \ + if (condition) \ + break; \ + __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) -#define __wait_event_cmd(wq, condition, cmd1, cmd2) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ +#define __wait_event_cmd(wq_head, condition, cmd1, cmd2) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ cmd1; schedule(); cmd2) /** * wait_event_cmd - sleep until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @cmd1: the command will be executed before sleep * @cmd2: the command will be executed after sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ -#define wait_event_cmd(wq, condition, cmd1, cmd2) \ -do { \ - if (condition) \ - break; \ - __wait_event_cmd(wq, condition, cmd1, cmd2); \ +#define wait_event_cmd(wq_head, condition, cmd1, cmd2) \ +do { \ + if (condition) \ + break; \ + __wait_event_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) -#define __wait_event_interruptible(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ +#define __wait_event_interruptible(wq_head, condition) \ + ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event_interruptible - sleep until a condition gets true - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -458,29 +433,29 @@ do { \ * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_interruptible(wq, condition); \ - __ret; \ +#define wait_event_interruptible(wq_head, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_interruptible(wq_head, condition); \ + __ret; \ }) -#define __wait_event_interruptible_timeout(wq, condition, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ +#define __wait_event_interruptible_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -492,50 +467,49 @@ do { \ * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a signal. */ -#define wait_event_interruptible_timeout(wq, condition, timeout) \ -({ \ - long __ret = timeout; \ - might_sleep(); \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_interruptible_timeout(wq, \ - condition, timeout); \ - __ret; \ +#define wait_event_interruptible_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_interruptible_timeout(wq_head, \ + condition, timeout); \ + __ret; \ }) -#define __wait_event_hrtimeout(wq, condition, timeout, state) \ -({ \ - int __ret = 0; \ - struct hrtimer_sleeper __t; \ - \ - hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, \ - HRTIMER_MODE_REL); \ - hrtimer_init_sleeper(&__t, current); \ - if ((timeout) != KTIME_MAX) \ - hrtimer_start_range_ns(&__t.timer, timeout, \ - current->timer_slack_ns, \ - HRTIMER_MODE_REL); \ - \ - __ret = ___wait_event(wq, condition, state, 0, 0, \ - if (!__t.task) { \ - __ret = -ETIME; \ - break; \ - } \ - schedule()); \ - \ - hrtimer_cancel(&__t.timer); \ - destroy_hrtimer_on_stack(&__t.timer); \ - __ret; \ +#define __wait_event_hrtimeout(wq_head, condition, timeout, state) \ +({ \ + int __ret = 0; \ + struct hrtimer_sleeper __t; \ + \ + hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); \ + hrtimer_init_sleeper(&__t, current); \ + if ((timeout) != KTIME_MAX) \ + hrtimer_start_range_ns(&__t.timer, timeout, \ + current->timer_slack_ns, \ + HRTIMER_MODE_REL); \ + \ + __ret = ___wait_event(wq_head, condition, state, 0, 0, \ + if (!__t.task) { \ + __ret = -ETIME; \ + break; \ + } \ + schedule()); \ + \ + hrtimer_cancel(&__t.timer); \ + destroy_hrtimer_on_stack(&__t.timer); \ + __ret; \ }) /** * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -543,25 +517,25 @@ do { \ * The function returns 0 if @condition became true, or -ETIME if the timeout * elapsed. */ -#define wait_event_hrtimeout(wq, condition, timeout) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_hrtimeout(wq, condition, timeout, \ - TASK_UNINTERRUPTIBLE); \ - __ret; \ +#define wait_event_hrtimeout(wq_head, condition, timeout) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq_head, condition, timeout, \ + TASK_UNINTERRUPTIBLE); \ + __ret; \ }) /** * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. - * The @condition is checked each time the waitqueue @wq is woken up. + * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -569,84 +543,73 @@ do { \ * The function returns 0 if @condition became true, -ERESTARTSYS if it was * interrupted by a signal, or -ETIME if the timeout elapsed. */ -#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ -({ \ - long __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_hrtimeout(wq, condition, timeout, \ - TASK_INTERRUPTIBLE); \ - __ret; \ +#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ +({ \ + long __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_INTERRUPTIBLE); \ + __ret; \ }) -#define __wait_event_interruptible_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ +#define __wait_event_interruptible_exclusive(wq, condition) \ + ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule()) -#define wait_event_interruptible_exclusive(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_interruptible_exclusive(wq, condition);\ - __ret; \ +#define wait_event_interruptible_exclusive(wq, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_interruptible_exclusive(wq, condition); \ + __ret; \ }) -#define __wait_event_killable_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ +#define __wait_event_killable_exclusive(wq, condition) \ + ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ schedule()) -#define wait_event_killable_exclusive(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_killable_exclusive(wq, condition); \ - __ret; \ +#define wait_event_killable_exclusive(wq, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_killable_exclusive(wq, condition); \ + __ret; \ }) -#define __wait_event_freezable_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ +#define __wait_event_freezable_exclusive(wq, condition) \ + ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule(); try_to_freeze()) -#define wait_event_freezable_exclusive(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_freezable_exclusive(wq, condition);\ - __ret; \ +#define wait_event_freezable_exclusive(wq, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_freezable_exclusive(wq, condition); \ + __ret; \ }) - -#define __wait_event_interruptible_locked(wq, condition, exclusive, irq) \ -({ \ - int __ret = 0; \ - DEFINE_WAIT(__wait); \ - if (exclusive) \ - __wait.flags |= WQ_FLAG_EXCLUSIVE; \ - do { \ - if (likely(list_empty(&__wait.task_list))) \ - __add_wait_queue_tail(&(wq), &__wait); \ - set_current_state(TASK_INTERRUPTIBLE); \ - if (signal_pending(current)) { \ - __ret = -ERESTARTSYS; \ - break; \ - } \ - if (irq) \ - spin_unlock_irq(&(wq).lock); \ - else \ - spin_unlock(&(wq).lock); \ - schedule(); \ - if (irq) \ - spin_lock_irq(&(wq).lock); \ - else \ - spin_lock(&(wq).lock); \ - } while (!(condition)); \ - __remove_wait_queue(&(wq), &__wait); \ - __set_current_state(TASK_RUNNING); \ - __ret; \ +extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *); +extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); + +#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ +({ \ + int __ret; \ + DEFINE_WAIT(__wait); \ + if (exclusive) \ + __wait.flags |= WQ_FLAG_EXCLUSIVE; \ + do { \ + __ret = fn(&(wq), &__wait); \ + if (__ret) \ + break; \ + } while (!(condition)); \ + __remove_wait_queue(&(wq), &__wait); \ + __set_current_state(TASK_RUNNING); \ + __ret; \ }) @@ -673,9 +636,9 @@ do { \ * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_locked(wq, condition) \ - ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 0)) +#define wait_event_interruptible_locked(wq, condition) \ + ((condition) \ + ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr)) /** * wait_event_interruptible_locked_irq - sleep until a condition gets true @@ -700,9 +663,9 @@ do { \ * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_locked_irq(wq, condition) \ - ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 1)) +#define wait_event_interruptible_locked_irq(wq, condition) \ + ((condition) \ + ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq)) /** * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true @@ -731,9 +694,9 @@ do { \ * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_exclusive_locked(wq, condition) \ - ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 0)) +#define wait_event_interruptible_exclusive_locked(wq, condition) \ + ((condition) \ + ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr)) /** * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true @@ -762,12 +725,12 @@ do { \ * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ - ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 1)) +#define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ + ((condition) \ + ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq)) -#define __wait_event_killable(wq, condition) \ +#define __wait_event_killable(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule()) /** @@ -785,21 +748,21 @@ do { \ * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ -#define wait_event_killable(wq, condition) \ -({ \ - int __ret = 0; \ - might_sleep(); \ - if (!(condition)) \ - __ret = __wait_event_killable(wq, condition); \ - __ret; \ +#define wait_event_killable(wq_head, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_killable(wq_head, condition); \ + __ret; \ }) -#define __wait_event_lock_irq(wq, condition, lock, cmd) \ - (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ - spin_unlock_irq(&lock); \ - cmd; \ - schedule(); \ +#define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ + (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ + spin_unlock_irq(&lock); \ + cmd; \ + schedule(); \ spin_lock_irq(&lock)) /** @@ -807,7 +770,7 @@ do { \ * condition is checked under the lock. This * is expected to be called with the lock * taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd * and schedule() and reacquired afterwards. @@ -816,7 +779,7 @@ do { \ * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -825,11 +788,11 @@ do { \ * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. */ -#define wait_event_lock_irq_cmd(wq, condition, lock, cmd) \ -do { \ - if (condition) \ - break; \ - __wait_event_lock_irq(wq, condition, lock, cmd); \ +#define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd) \ +do { \ + if (condition) \ + break; \ + __wait_event_lock_irq(wq_head, condition, lock, cmd); \ } while (0) /** @@ -837,14 +800,14 @@ do { \ * condition is checked under the lock. This * is expected to be called with the lock * taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time - * the waitqueue @wq is woken up. + * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -852,26 +815,26 @@ do { \ * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. */ -#define wait_event_lock_irq(wq, condition, lock) \ -do { \ - if (condition) \ - break; \ - __wait_event_lock_irq(wq, condition, lock, ); \ +#define wait_event_lock_irq(wq_head, condition, lock) \ +do { \ + if (condition) \ + break; \ + __wait_event_lock_irq(wq_head, condition, lock, ); \ } while (0) -#define __wait_event_interruptible_lock_irq(wq, condition, lock, cmd) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ - spin_unlock_irq(&lock); \ - cmd; \ - schedule(); \ +#define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd) \ + ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ + spin_unlock_irq(&lock); \ + cmd; \ + schedule(); \ spin_lock_irq(&lock)) /** * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true. * The condition is checked under the lock. This is expected to * be called with the lock taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd and * schedule() and reacquired afterwards. @@ -880,7 +843,7 @@ do { \ * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. The @condition is - * checked each time the waitqueue @wq is woken up. + * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -892,27 +855,27 @@ do { \ * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_lock_irq_cmd(wq, condition, lock, cmd) \ -({ \ - int __ret = 0; \ - if (!(condition)) \ - __ret = __wait_event_interruptible_lock_irq(wq, \ - condition, lock, cmd); \ - __ret; \ +#define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_interruptible_lock_irq(wq_head, \ + condition, lock, cmd); \ + __ret; \ }) /** * wait_event_interruptible_lock_irq - sleep until a condition gets true. * The condition is checked under the lock. This is expected * to be called with the lock taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is - * checked each time the waitqueue @wq is woken up. + * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -923,28 +886,28 @@ do { \ * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ -#define wait_event_interruptible_lock_irq(wq, condition, lock) \ -({ \ - int __ret = 0; \ - if (!(condition)) \ - __ret = __wait_event_interruptible_lock_irq(wq, \ - condition, lock,); \ - __ret; \ +#define wait_event_interruptible_lock_irq(wq_head, condition, lock) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_interruptible_lock_irq(wq_head, \ + condition, lock,); \ + __ret; \ }) -#define __wait_event_interruptible_lock_irq_timeout(wq, condition, \ - lock, timeout) \ - ___wait_event(wq, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ - spin_unlock_irq(&lock); \ - __ret = schedule_timeout(__ret); \ +#define __wait_event_interruptible_lock_irq_timeout(wq_head, condition, \ + lock, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, 0, timeout, \ + spin_unlock_irq(&lock); \ + __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); /** * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets * true or a timeout elapses. The condition is checked under * the lock. This is expected to be called with the lock taken. - * @wq: the waitqueue to wait on + * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. @@ -952,7 +915,7 @@ do { \ * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is - * checked each time the waitqueue @wq is woken up. + * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. @@ -964,263 +927,42 @@ do { \ * was interrupted by a signal, and the remaining jiffies otherwise * if the condition evaluated to true before the timeout elapsed. */ -#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock, \ - timeout) \ -({ \ - long __ret = timeout; \ - if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_interruptible_lock_irq_timeout( \ - wq, condition, lock, timeout); \ - __ret; \ +#define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock, \ + timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_interruptible_lock_irq_timeout( \ + wq_head, condition, lock, timeout); \ + __ret; \ }) /* * Waitqueues which are removed from the waitqueue_head at wakeup time */ -void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state); -void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state); -long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state); -void finish_wait(wait_queue_head_t *q, wait_queue_t *wait); -long wait_woken(wait_queue_t *wait, unsigned mode, long timeout); -int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); -int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); -int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); - -#define DEFINE_WAIT_FUNC(name, function) \ - wait_queue_t name = { \ - .private = current, \ - .func = function, \ - .task_list = LIST_HEAD_INIT((name).task_list), \ +void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +void prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); +int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); +int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); + +#define DEFINE_WAIT_FUNC(name, function) \ + struct wait_queue_entry name = { \ + .private = current, \ + .func = function, \ + .entry = LIST_HEAD_INIT((name).entry), \ } #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) -#define DEFINE_WAIT_BIT(name, word, bit) \ - struct wait_bit_queue name = { \ - .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ - .wait = { \ - .private = current, \ - .func = wake_bit_function, \ - .task_list = \ - LIST_HEAD_INIT((name).wait.task_list), \ - }, \ - } - -#define init_wait(wait) \ - do { \ - (wait)->private = current; \ - (wait)->func = autoremove_wake_function; \ - INIT_LIST_HEAD(&(wait)->task_list); \ - (wait)->flags = 0; \ +#define init_wait(wait) \ + do { \ + (wait)->private = current; \ + (wait)->func = autoremove_wake_function; \ + INIT_LIST_HEAD(&(wait)->entry); \ + (wait)->flags = 0; \ } while (0) - -extern int bit_wait(struct wait_bit_key *, int); -extern int bit_wait_io(struct wait_bit_key *, int); -extern int bit_wait_timeout(struct wait_bit_key *, int); -extern int bit_wait_io_timeout(struct wait_bit_key *, int); - -/** - * wait_on_bit - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that waits on a bit. - * For instance, if one were to have waiters on a bitflag, one would - * call wait_on_bit() in threads waiting for the bit to clear. - * One uses wait_on_bit() where one is waiting for the bit to clear, - * but has no intention of setting it. - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. - */ -static inline int -wait_on_bit(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit(word, bit, - bit_wait, - mode); -} - -/** - * wait_on_bit_io - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared. This is similar to wait_on_bit(), but calls - * io_schedule() instead of schedule() for the actual waiting. - * - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. - */ -static inline int -wait_on_bit_io(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit(word, bit, - bit_wait_io, - mode); -} - -/** - * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * @timeout: timeout, in jiffies - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared. This is similar to wait_on_bit(), except also takes a - * timeout parameter. - * - * Returned value will be zero if the bit was cleared before the - * @timeout elapsed, or non-zero if the @timeout elapsed or process - * received a signal and the mode permitted wakeup on that signal. - */ -static inline int -wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, - unsigned long timeout) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_timeout(word, bit, - bit_wait_timeout, - mode, timeout); -} - -/** - * wait_on_bit_action - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared, and allow the waiting action to be specified. - * This is like wait_on_bit() but allows fine control of how the waiting - * is done. - * - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. - */ -static inline int -wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, - unsigned mode) -{ - might_sleep(); - if (!test_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit(word, bit, action, mode); -} - -/** - * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that waits on a bit - * when one intends to set it, for instance, trying to lock bitflags. - * For instance, if one were to have waiters trying to set bitflag - * and waiting for it to clear before setting it, one would call - * wait_on_bit() in threads waiting to be able to set the bit. - * One uses wait_on_bit_lock() where one is waiting for the bit to - * clear with the intention of setting it, and when done, clearing it. - * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. - */ -static inline int -wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_and_set_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); -} - -/** - * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared and then to atomically set it. This is similar - * to wait_on_bit(), but calls io_schedule() instead of schedule() - * for the actual waiting. - * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. - */ -static inline int -wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) -{ - might_sleep(); - if (!test_and_set_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); -} - -/** - * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions - * @mode: the task state to sleep in - * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared and then to set it, and allow the waiting action - * to be specified. - * This is like wait_on_bit() but allows fine control of how the waiting - * is done. - * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. - */ -static inline int -wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, - unsigned mode) -{ - might_sleep(); - if (!test_and_set_bit(bit, word)) - return 0; - return out_of_line_wait_on_bit_lock(word, bit, action, mode); -} - -/** - * wait_on_atomic_t - Wait for an atomic_t to become 0 - * @val: The atomic value being waited on, a kernel virtual address - * @action: the function used to sleep, which may take special actions - * @mode: the task state to sleep in - * - * Wait for an atomic_t to become 0. We abuse the bit-wait waitqueue table for - * the purpose of getting a waitqueue, but we set the key to a bit number - * outside of the target 'word'. - */ -static inline -int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode) -{ - might_sleep(); - if (atomic_read(val) == 0) - return 0; - return out_of_line_wait_on_atomic_t(val, action, mode); -} - #endif /* _LINUX_WAIT_H */ diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h new file mode 100644 index 000000000000..12b26660d7e9 --- /dev/null +++ b/include/linux/wait_bit.h @@ -0,0 +1,261 @@ +#ifndef _LINUX_WAIT_BIT_H +#define _LINUX_WAIT_BIT_H + +/* + * Linux wait-bit related types and methods: + */ +#include <linux/wait.h> + +struct wait_bit_key { + void *flags; + int bit_nr; +#define WAIT_ATOMIC_T_BIT_NR -1 + unsigned long timeout; +}; + +struct wait_bit_queue_entry { + struct wait_bit_key key; + struct wait_queue_entry wq_entry; +}; + +#define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ + { .flags = word, .bit_nr = bit, } + +#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p) \ + { .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, } + +typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); +void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); +int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); +int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); +void wake_up_bit(void *word, int bit); +void wake_up_atomic_t(atomic_t *p); +int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); +int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); +int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); +int out_of_line_wait_on_atomic_t(atomic_t *p, int (*)(atomic_t *), unsigned int mode); +struct wait_queue_head *bit_waitqueue(void *word, int bit); +extern void __init wait_bit_init(void); + +int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); + +#define DEFINE_WAIT_BIT(name, word, bit) \ + struct wait_bit_queue_entry name = { \ + .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ + .wq_entry = { \ + .private = current, \ + .func = wake_bit_function, \ + .entry = \ + LIST_HEAD_INIT((name).wq_entry.entry), \ + }, \ + } + +extern int bit_wait(struct wait_bit_key *key, int bit); +extern int bit_wait_io(struct wait_bit_key *key, int bit); +extern int bit_wait_timeout(struct wait_bit_key *key, int bit); +extern int bit_wait_io_timeout(struct wait_bit_key *key, int bit); + +/** + * wait_on_bit - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that waits on a bit. + * For instance, if one were to have waiters on a bitflag, one would + * call wait_on_bit() in threads waiting for the bit to clear. + * One uses wait_on_bit() where one is waiting for the bit to clear, + * but has no intention of setting it. + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait, + mode); +} + +/** + * wait_on_bit_io - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), but calls + * io_schedule() instead of schedule() for the actual waiting. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit_io(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait_io, + mode); +} + +/** + * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * @timeout: timeout, in jiffies + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), except also takes a + * timeout parameter. + * + * Returned value will be zero if the bit was cleared before the + * @timeout elapsed, or non-zero if the @timeout elapsed or process + * received a signal and the mode permitted wakeup on that signal. + */ +static inline int +wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, + unsigned long timeout) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_timeout(word, bit, + bit_wait_timeout, + mode, timeout); +} + +/** + * wait_on_bit_action - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared, and allow the waiting action to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, + unsigned mode) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, action, mode); +} + +/** + * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that waits on a bit + * when one intends to set it, for instance, trying to lock bitflags. + * For instance, if one were to have waiters trying to set bitflag + * and waiting for it to clear before setting it, one would call + * wait_on_bit() in threads waiting to be able to set the bit. + * One uses wait_on_bit_lock() where one is waiting for the bit to + * clear with the intention of setting it, and when done, clearing it. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); +} + +/** + * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to atomically set it. This is similar + * to wait_on_bit(), but calls io_schedule() instead of schedule() + * for the actual waiting. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) +{ + might_sleep(); + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); +} + +/** + * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to set it, and allow the waiting action + * to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, + unsigned mode) +{ + might_sleep(); + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, action, mode); +} + +/** + * wait_on_atomic_t - Wait for an atomic_t to become 0 + * @val: The atomic value being waited on, a kernel virtual address + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Wait for an atomic_t to become 0. We abuse the bit-wait waitqueue table for + * the purpose of getting a waitqueue, but we set the key to a bit number + * outside of the target 'word'. + */ +static inline +int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode) +{ + might_sleep(); + if (atomic_read(val) == 0) + return 0; + return out_of_line_wait_on_atomic_t(val, action, mode); +} + +#endif /* _LINUX_WAIT_BIT_H */ diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 35a4d8185b51..a786e5e8973b 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -117,6 +117,7 @@ struct watchdog_device { #define WDOG_NO_WAY_OUT 1 /* Is 'nowayout' feature set ? */ #define WDOG_STOP_ON_REBOOT 2 /* Should be stopped on reboot */ #define WDOG_HW_RUNNING 3 /* True if HW watchdog running */ +#define WDOG_STOP_ON_UNREGISTER 4 /* Should be stopped on unregister */ struct list_head deferred; }; @@ -151,6 +152,12 @@ static inline void watchdog_stop_on_reboot(struct watchdog_device *wdd) set_bit(WDOG_STOP_ON_REBOOT, &wdd->status); } +/* Use the following function to stop the watchdog when unregistering it */ +static inline void watchdog_stop_on_unregister(struct watchdog_device *wdd) +{ + set_bit(WDOG_STOP_ON_UNREGISTER, &wdd->status); +} + /* Use the following function to check if a timeout value is invalid */ static inline bool watchdog_timeout_invalid(struct watchdog_device *wdd, unsigned int t) { diff --git a/include/linux/wmi.h b/include/linux/wmi.h new file mode 100644 index 000000000000..cd0d7734dc49 --- /dev/null +++ b/include/linux/wmi.h @@ -0,0 +1,59 @@ +/* + * wmi.h - ACPI WMI interface + * + * Copyright (c) 2015 Andrew Lutomirski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _LINUX_WMI_H +#define _LINUX_WMI_H + +#include <linux/device.h> +#include <linux/acpi.h> + +struct wmi_device { + struct device dev; + + /* True for data blocks implementing the Set Control Method */ + bool setable; +}; + +/* Caller must kfree the result. */ +extern union acpi_object *wmidev_block_query(struct wmi_device *wdev, + u8 instance); + +/* Gets another device on the same bus. Caller must put_device the result. */ +extern struct wmi_device *wmidev_get_other_guid(struct wmi_device *wdev, + const char *guid_string); + +struct wmi_device_id { + const char *guid_string; +}; + +struct wmi_driver { + struct device_driver driver; + const struct wmi_device_id *id_table; + + int (*probe)(struct wmi_device *wdev); + int (*remove)(struct wmi_device *wdev); + void (*notify)(struct wmi_device *device, union acpi_object *data); +}; + +extern int __must_check __wmi_driver_register(struct wmi_driver *driver, + struct module *owner); +extern void wmi_driver_unregister(struct wmi_driver *driver); +#define wmi_driver_register(driver) __wmi_driver_register((driver), THIS_MODULE) + +#define module_wmi_driver(__wmi_driver) \ + module_driver(__wmi_driver, wmi_driver_register, \ + wmi_driver_unregister) + +#endif diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index a26cc437293c..c102ef65cb64 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -106,9 +106,9 @@ struct work_struct { #endif }; -#define WORK_DATA_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL) +#define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ - ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC) + ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) struct delayed_work { struct work_struct work; @@ -608,8 +608,13 @@ static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } +static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) +{ + return fn(arg); +} #else long work_on_cpu(int cpu, long (*fn)(void *), void *arg); +long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 5527d910ba3d..d5815794416c 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -46,7 +46,7 @@ enum writeback_sync_modes { */ enum wb_reason { WB_REASON_BACKGROUND, - WB_REASON_TRY_TO_FREE_PAGES, + WB_REASON_VMSCAN, WB_REASON_SYNC, WB_REASON_PERIODIC, WB_REASON_LAPTOP_TIMER, @@ -237,6 +237,7 @@ static inline void inode_attach_wb(struct inode *inode, struct page *page) static inline void inode_detach_wb(struct inode *inode) { if (inode->i_wb) { + WARN_ON_ONCE(!(inode->i_state & I_CLEAR)); wb_put(inode->i_wb); inode->i_wb = NULL; } diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 7b0066814fa0..5dd9a7682227 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -51,10 +51,10 @@ struct ww_mutex { }; #ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class) \ - , .ww_class = &ww_class +# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) \ + , .ww_class = class #else -# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class) +# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) #endif #define __WW_CLASS_INITIALIZER(ww_class) \ @@ -63,7 +63,7 @@ struct ww_mutex { , .mutex_name = #ww_class "_mutex" } #define __WW_MUTEX_INITIALIZER(lockname, class) \ - { .base = { \__MUTEX_INITIALIZER(lockname) } \ + { .base = __MUTEX_INITIALIZER(lockname.base) \ __WW_CLASS_MUTEX_INITIALIZER(lockname, class) } #define DEFINE_WW_CLASS(classname) \ @@ -186,11 +186,6 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) #endif } -extern int __must_check __ww_mutex_lock(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx); -extern int __must_check __ww_mutex_lock_interruptible(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx); - /** * ww_mutex_lock - acquire the w/w mutex * @lock: the mutex to be acquired @@ -220,14 +215,7 @@ extern int __must_check __ww_mutex_lock_interruptible(struct ww_mutex *lock, * * A mutex acquired with this function must be released with ww_mutex_unlock. */ -static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) -{ - if (ctx) - return __ww_mutex_lock(lock, ctx); - - mutex_lock(&lock->base); - return 0; -} +extern int /* __must_check */ ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx); /** * ww_mutex_lock_interruptible - acquire the w/w mutex, interruptible @@ -259,14 +247,8 @@ static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ct * * A mutex acquired with this function must be released with ww_mutex_unlock. */ -static inline int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock, - struct ww_acquire_ctx *ctx) -{ - if (ctx) - return __ww_mutex_lock_interruptible(lock, ctx); - else - return mutex_lock_interruptible(&lock->base); -} +extern int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx); /** * ww_mutex_lock_slow - slowpath acquiring of the w/w mutex |