summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/boot/Makefile3
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl2
-rw-r--r--arch/x86/include/asm/mtrr.h6
-rw-r--r--arch/x86/include/asm/pat.h2
-rw-r--r--arch/x86/include/asm/pvclock.h2
-rw-r--r--arch/x86/include/asm/tlbflush.h7
-rw-r--r--arch/x86/kernel/amd_nb.c4
-rw-r--r--arch/x86/kernel/apic/apic.c3
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c12
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c24
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c13
-rw-r--r--arch/x86/kernel/cpu/mtrr/mtrr.h1
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c2
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_cqm.c56
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c9
-rw-r--r--arch/x86/kernel/early-quirks.c105
-rw-r--r--arch/x86/kernel/kprobes/core.c12
-rw-r--r--arch/x86/kernel/pvclock.c4
-rw-r--r--arch/x86/kernel/uprobes.c22
-rw-r--r--arch/x86/kvm/mtrr.c1
-rw-r--r--arch/x86/kvm/vmx.c43
-rw-r--r--arch/x86/mm/mmap.c14
-rw-r--r--arch/x86/mm/pat.c109
-rw-r--r--arch/x86/pci/intel_mid_pci.c12
-rw-r--r--arch/x86/xen/enlighten.c9
25 files changed, 341 insertions, 136 deletions
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 2ee62dba0373..c0cc2a6be0bf 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -162,6 +162,9 @@ isoimage: $(obj)/bzImage
for i in lib lib64 share end ; do \
if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \
cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \
+ if [ -f /usr/$$i/syslinux/ldlinux.c32 ]; then \
+ cp /usr/$$i/syslinux/ldlinux.c32 $(obj)/isoimage ; \
+ fi ; \
break ; \
fi ; \
if [ $$i = end ] ; then exit 1 ; fi ; \
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index f17705e1332c..e62f4401e792 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -294,7 +294,7 @@
# 285 sys_setaltroot
286 i386 add_key sys_add_key
287 i386 request_key sys_request_key
-288 i386 keyctl sys_keyctl
+288 i386 keyctl sys_keyctl compat_sys_keyctl
289 i386 ioprio_set sys_ioprio_set
290 i386 ioprio_get sys_ioprio_get
291 i386 inotify_init sys_inotify_init
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index b94f6f64e23d..dbff1456d215 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -24,6 +24,7 @@
#define _ASM_X86_MTRR_H
#include <uapi/asm/mtrr.h>
+#include <asm/pat.h>
/*
@@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
{
}
+static inline void mtrr_bp_init(void)
+{
+ pat_disable("MTRRs disabled, skipping PAT initialization too.");
+}
#define mtrr_ap_init() do {} while (0)
-#define mtrr_bp_init() do {} while (0)
#define set_mtrr_aps_delayed_init() do {} while (0)
#define mtrr_aps_init() do {} while (0)
#define mtrr_bp_restore() do {} while (0)
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index ca6c228d5e62..0b1ff4c1c14e 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -5,8 +5,8 @@
#include <asm/pgtable_types.h>
bool pat_enabled(void);
+void pat_disable(const char *reason);
extern void pat_init(void);
-void pat_init_cache_modes(u64);
extern int reserve_memtype(u64 start, u64 end,
enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 7a6bed5c08bc..baad72e4c100 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -76,6 +76,8 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
u8 ret_flags;
version = src->version;
+ /* Make the latest version visible */
+ smp_rmb();
offset = pvclock_get_nsec_offset(src);
ret = src->system_time + offset;
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6df2029405a3..3142218e546f 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -86,7 +86,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
static inline void __native_flush_tlb(void)
{
+ /*
+ * If current->mm == NULL then we borrow a mm which may change during a
+ * task switch and therefore we must not be preempted while we write CR3
+ * back:
+ */
+ preempt_disable();
native_write_cr3(native_read_cr3());
+ preempt_enable();
}
static inline void __native_flush_tlb_global_irq_disabled(void)
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 29fa475ec518..c986d0b3bc35 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -71,8 +71,8 @@ int amd_cache_northbridges(void)
while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
i++;
- if (i == 0)
- return 0;
+ if (!i)
+ return -ENODEV;
nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
if (!nb)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2f69e3b184f6..a3e1f8497f8c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1587,6 +1587,9 @@ void __init enable_IR_x2apic(void)
unsigned long flags;
int ret, ir_stat;
+ if (skip_ioapic_setup)
+ return;
+
ir_stat = irq_remapping_prepare();
if (ir_stat < 0 && !x2apic_supported())
return;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 20e242ea1bc4..cfc4a966e2b9 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -152,6 +152,11 @@ static struct clocksource hyperv_cs = {
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
+static unsigned char hv_get_nmi_reason(void)
+{
+ return 0;
+}
+
static void __init ms_hyperv_init_platform(void)
{
/*
@@ -191,6 +196,13 @@ static void __init ms_hyperv_init_platform(void)
machine_ops.crash_shutdown = hv_machine_crash_shutdown;
#endif
mark_tsc_unstable("running on Hyper-V");
+
+ /*
+ * Generation 2 instances don't support reading the NMI status from
+ * 0x61 port.
+ */
+ if (efi_enabled(EFI_BOOT))
+ x86_platform.get_nmi_reason = hv_get_nmi_reason;
}
const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 3b533cf37c74..b5624fafa44a 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -444,11 +444,24 @@ static void __init print_mtrr_state(void)
pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20);
}
+/* PAT setup for BP. We need to go through sync steps here */
+void __init mtrr_bp_pat_init(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ prepare_set();
+
+ pat_init();
+
+ post_set();
+ local_irq_restore(flags);
+}
+
/* Grab all of the MTRR state for this CPU into *state */
bool __init get_mtrr_state(void)
{
struct mtrr_var_range *vrs;
- unsigned long flags;
unsigned lo, dummy;
unsigned int i;
@@ -481,15 +494,6 @@ bool __init get_mtrr_state(void)
mtrr_state_set = 1;
- /* PAT setup for BP. We need to go through sync steps here */
- local_irq_save(flags);
- prepare_set();
-
- pat_init();
-
- post_set();
- local_irq_restore(flags);
-
return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
}
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index f891b4750f04..fa77ac8291f0 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -752,6 +752,9 @@ void __init mtrr_bp_init(void)
/* BIOS may override */
__mtrr_enabled = get_mtrr_state();
+ if (mtrr_enabled())
+ mtrr_bp_pat_init();
+
if (mtrr_cleanup(phys_addr)) {
changed_by_mtrr_cleanup = 1;
mtrr_if->set_all();
@@ -759,8 +762,16 @@ void __init mtrr_bp_init(void)
}
}
- if (!mtrr_enabled())
+ if (!mtrr_enabled()) {
pr_info("MTRR: Disabled\n");
+
+ /*
+ * PAT initialization relies on MTRR's rendezvous handler.
+ * Skip PAT init until the handler can initialize both
+ * features independently.
+ */
+ pat_disable("MTRRs disabled, skipping PAT initialization too.");
+ }
}
void mtrr_ap_init(void)
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 951884dcc433..6c7ced07d16d 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
void fill_mtrr_var_range(unsigned int index,
u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
bool get_mtrr_state(void);
+void mtrr_bp_pat_init(void);
extern void set_mtrr_ops(const struct mtrr_ops *ops);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 078de2e86b7a..5f82cd59f0e5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -3601,7 +3601,7 @@ __init int intel_pmu_init(void)
c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
}
c->idxmsk64 &=
- ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+ ~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
c->weight = hweight64(c->idxmsk64);
}
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index a316ca96f1b6..fc704ed587e8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -211,6 +211,20 @@ static void __put_rmid(u32 rmid)
list_add_tail(&entry->list, &cqm_rmid_limbo_lru);
}
+static void cqm_cleanup(void)
+{
+ int i;
+
+ if (!cqm_rmid_ptrs)
+ return;
+
+ for (i = 0; i < cqm_max_rmid; i++)
+ kfree(cqm_rmid_ptrs[i]);
+
+ kfree(cqm_rmid_ptrs);
+ cqm_rmid_ptrs = NULL;
+}
+
static int intel_cqm_setup_rmid_cache(void)
{
struct cqm_rmid_entry *entry;
@@ -218,7 +232,7 @@ static int intel_cqm_setup_rmid_cache(void)
int r = 0;
nr_rmids = cqm_max_rmid + 1;
- cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) *
+ cqm_rmid_ptrs = kzalloc(sizeof(struct cqm_rmid_entry *) *
nr_rmids, GFP_KERNEL);
if (!cqm_rmid_ptrs)
return -ENOMEM;
@@ -249,11 +263,9 @@ static int intel_cqm_setup_rmid_cache(void)
mutex_unlock(&cache_mutex);
return 0;
-fail:
- while (r--)
- kfree(cqm_rmid_ptrs[r]);
- kfree(cqm_rmid_ptrs);
+fail:
+ cqm_cleanup();
return -ENOMEM;
}
@@ -281,9 +293,13 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
/*
* Events that target same task are placed into the same cache group.
+ * Mark it as a multi event group, so that we update ->count
+ * for every event rather than just the group leader later.
*/
- if (a->hw.target == b->hw.target)
+ if (a->hw.target == b->hw.target) {
+ b->hw.is_group_event = true;
return true;
+ }
/*
* Are we an inherited event?
@@ -849,6 +865,7 @@ static void intel_cqm_setup_event(struct perf_event *event,
bool conflict = false;
u32 rmid;
+ event->hw.is_group_event = false;
list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
rmid = iter->hw.cqm_rmid;
@@ -940,7 +957,9 @@ static u64 intel_cqm_event_count(struct perf_event *event)
return __perf_event_count(event);
/*
- * Only the group leader gets to report values. This stops us
+ * Only the group leader gets to report values except in case of
+ * multiple events in the same group, we still need to read the
+ * other events.This stops us
* reporting duplicate values to userspace, and gives us a clear
* rule for which task gets to report the values.
*
@@ -948,7 +967,7 @@ static u64 intel_cqm_event_count(struct perf_event *event)
* specific packages - we forfeit that ability when we create
* task events.
*/
- if (!cqm_group_leader(event))
+ if (!cqm_group_leader(event) && !event->hw.is_group_event)
return 0;
/*
@@ -1315,7 +1334,7 @@ static const struct x86_cpu_id intel_cqm_match[] = {
static int __init intel_cqm_init(void)
{
- char *str, scale[20];
+ char *str = NULL, scale[20];
int i, cpu, ret;
if (!x86_match_cpu(intel_cqm_match))
@@ -1375,16 +1394,25 @@ static int __init intel_cqm_init(void)
cqm_pick_event_reader(i);
}
- __perf_cpu_notifier(intel_cqm_cpu_notifier);
-
ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1);
- if (ret)
+ if (ret) {
pr_err("Intel CQM perf registration failed: %d\n", ret);
- else
- pr_info("Intel CQM monitoring enabled\n");
+ goto out;
+ }
+
+ pr_info("Intel CQM monitoring enabled\n");
+ /*
+ * Register the hot cpu notifier once we are sure cqm
+ * is enabled to avoid notifier leak.
+ */
+ __perf_cpu_notifier(intel_cqm_cpu_notifier);
out:
cpu_notifier_register_done();
+ if (ret) {
+ kfree(str);
+ cqm_cleanup();
+ }
return ret;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 7abb2b88572e..1e7de3cefc9c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -1110,6 +1110,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
void *at;
u64 pebs_status;
+ /*
+ * fmt0 does not have a status bitfield (does not use
+ * perf_record_nhm format)
+ */
+ if (x86_pmu.intel_cap.pebs_format < 1)
+ return base;
+
if (base == NULL)
return NULL;
@@ -1195,7 +1202,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
if (!event->attr.precise_ip)
return;
- n = (top - at) / x86_pmu.pebs_record_size;
+ n = top - at;
if (n <= 0)
return;
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index db9a675e751b..9fdf1d330727 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -11,7 +11,11 @@
#include <linux/pci.h>
#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/dmi.h>
#include <linux/pci_ids.h>
+#include <linux/bcma/bcma.h>
+#include <linux/bcma/bcma_regs.h>
#include <drm/i915_drm.h>
#include <asm/pci-direct.h>
#include <asm/dma.h>
@@ -21,6 +25,9 @@
#include <asm/iommu.h>
#include <asm/gart.h>
#include <asm/irq_remapping.h>
+#include <asm/early_ioremap.h>
+
+#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg)
static void __init fix_hypertransport_config(int num, int slot, int func)
{
@@ -76,6 +83,13 @@ static void __init nvidia_bugs(int num, int slot, int func)
#ifdef CONFIG_ACPI
#ifdef CONFIG_X86_IO_APIC
/*
+ * Only applies to Nvidia root ports (bus 0) and not to
+ * Nvidia graphics cards with PCI ports on secondary buses.
+ */
+ if (num)
+ return;
+
+ /*
* All timer overrides on Nvidia are
* wrong unless HPET is enabled.
* Unfortunately that's not true on many Asus boards.
@@ -589,6 +603,61 @@ static void __init force_disable_hpet(int num, int slot, int func)
#endif
}
+#define BCM4331_MMIO_SIZE 16384
+#define BCM4331_PM_CAP 0x40
+#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg)
+#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg)
+
+static void __init apple_airport_reset(int bus, int slot, int func)
+{
+ void __iomem *mmio;
+ u16 pmcsr;
+ u64 addr;
+ int i;
+
+ if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc."))
+ return;
+
+ /* Card may have been put into PCI_D3hot by grub quirk */
+ pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
+
+ if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
+ pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
+ write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr);
+ mdelay(10);
+
+ pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
+ if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
+ dev_err("Cannot power up Apple AirPort card\n");
+ return;
+ }
+ }
+
+ addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0);
+ addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32;
+ addr &= PCI_BASE_ADDRESS_MEM_MASK;
+
+ mmio = early_ioremap(addr, BCM4331_MMIO_SIZE);
+ if (!mmio) {
+ dev_err("Cannot iomap Apple AirPort card\n");
+ return;
+ }
+
+ pr_info("Resetting Apple AirPort card (left enabled by EFI)\n");
+
+ for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++)
+ udelay(10);
+
+ bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET);
+ bcma_aread32(BCMA_RESET_CTL);
+ udelay(1);
+
+ bcma_awrite32(BCMA_RESET_CTL, 0);
+ bcma_aread32(BCMA_RESET_CTL);
+ udelay(10);
+
+ early_iounmap(mmio, BCM4331_MMIO_SIZE);
+}
#define QFLAG_APPLY_ONCE 0x1
#define QFLAG_APPLIED 0x2
@@ -602,12 +671,6 @@ struct chipset {
void (*f)(int num, int slot, int func);
};
-/*
- * Only works for devices on the root bus. If you add any devices
- * not on bus 0 readd another loop level in early_quirks(). But
- * be careful because at least the Nvidia quirk here relies on
- * only matching on bus 0.
- */
static struct chipset early_qrk[] __initdata = {
{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
@@ -637,9 +700,13 @@ static struct chipset early_qrk[] __initdata = {
*/
{ PCI_VENDOR_ID_INTEL, 0x0f00,
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
+ { PCI_VENDOR_ID_BROADCOM, 0x4331,
+ PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
{}
};
+static void __init early_pci_scan_bus(int bus);
+
/**
* check_dev_quirk - apply early quirks to a given PCI device
* @num: bus number
@@ -648,7 +715,7 @@ static struct chipset early_qrk[] __initdata = {
*
* Check the vendor & device ID against the early quirks table.
*
- * If the device is single function, let early_quirks() know so we don't
+ * If the device is single function, let early_pci_scan_bus() know so we don't
* poke at this device again.
*/
static int __init check_dev_quirk(int num, int slot, int func)
@@ -657,6 +724,7 @@ static int __init check_dev_quirk(int num, int slot, int func)
u16 vendor;
u16 device;
u8 type;
+ u8 sec;
int i;
class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE);
@@ -684,25 +752,36 @@ static int __init check_dev_quirk(int num, int slot, int func)
type = read_pci_config_byte(num, slot, func,
PCI_HEADER_TYPE);
+
+ if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) {
+ sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS);
+ if (sec > num)
+ early_pci_scan_bus(sec);
+ }
+
if (!(type & 0x80))
return -1;
return 0;
}
-void __init early_quirks(void)
+static void __init early_pci_scan_bus(int bus)
{
int slot, func;
- if (!early_pci_allowed())
- return;
-
/* Poor man's PCI discovery */
- /* Only scan the root bus */
for (slot = 0; slot < 32; slot++)
for (func = 0; func < 8; func++) {
/* Only probe function 0 on single fn devices */
- if (check_dev_quirk(0, slot, func))
+ if (check_dev_quirk(bus, slot, func))
break;
}
}
+
+void __init early_quirks(void)
+{
+ if (!early_pci_allowed())
+ return;
+
+ early_pci_scan_bus(0);
+}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 1deffe6cc873..023c442c33bb 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -959,7 +959,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
* normal page fault.
*/
regs->ip = (unsigned long)cur->addr;
+ /*
+ * Trap flag (TF) has been set here because this fault
+ * happened where the single stepping will be done.
+ * So clear it by resetting the current kprobe:
+ */
+ regs->flags &= ~X86_EFLAGS_TF;
+
+ /*
+ * If the TF flag was set before the kprobe hit,
+ * don't touch it:
+ */
regs->flags |= kcb->kprobe_old_flags;
+
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
else
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 2f355d229a58..bf0ce75735b0 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -66,6 +66,8 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
do {
version = __pvclock_read_cycles(src, &ret, &flags);
+ /* Make sure that the version double-check is last. */
+ smp_rmb();
} while ((src->version & 1) || version != src->version);
return flags & valid_flags;
@@ -80,6 +82,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
do {
version = __pvclock_read_cycles(src, &ret, &flags);
+ /* Make sure that the version double-check is last. */
+ smp_rmb();
} while ((src->version & 1) || version != src->version);
if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index bf4db6eaec8f..c6aace2bbe08 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -357,20 +357,22 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
*cursor &= 0xfe;
}
/*
- * Similar treatment for VEX3 prefix.
- * TODO: add XOP/EVEX treatment when insn decoder supports them
+ * Similar treatment for VEX3/EVEX prefix.
+ * TODO: add XOP treatment when insn decoder supports them
*/
- if (insn->vex_prefix.nbytes == 3) {
+ if (insn->vex_prefix.nbytes >= 3) {
/*
* vex2: c5 rvvvvLpp (has no b bit)
* vex3/xop: c4/8f rxbmmmmm wvvvvLpp
* evex: 62 rxbR00mm wvvvv1pp zllBVaaa
- * (evex will need setting of both b and x since
- * in non-sib encoding evex.x is 4th bit of MODRM.rm)
- * Setting VEX3.b (setting because it has inverted meaning):
+ * Setting VEX3.b (setting because it has inverted meaning).
+ * Setting EVEX.x since (in non-SIB encoding) EVEX.x
+ * is the 4th bit of MODRM.rm, and needs the same treatment.
+ * For VEX3-encoded insns, VEX3.x value has no effect in
+ * non-SIB encoding, the change is superfluous but harmless.
*/
cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1;
- *cursor |= 0x20;
+ *cursor |= 0x60;
}
/*
@@ -415,12 +417,10 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
reg = MODRM_REG(insn); /* Fetch modrm.reg */
reg2 = 0xff; /* Fetch vex.vvvv */
- if (insn->vex_prefix.nbytes == 2)
- reg2 = insn->vex_prefix.bytes[1];
- else if (insn->vex_prefix.nbytes == 3)
+ if (insn->vex_prefix.nbytes)
reg2 = insn->vex_prefix.bytes[2];
/*
- * TODO: add XOP, EXEV vvvv reading.
+ * TODO: add XOP vvvv reading.
*
* vex.vvvv field is in bits 6-3, bits are inverted.
* But in 32-bit mode, high-order bit may be ignored.
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index c146f3c262c3..0149ac59c273 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -539,6 +539,7 @@ static void mtrr_lookup_var_start(struct mtrr_iter *iter)
iter->fixed = false;
iter->start_max = iter->start;
+ iter->range = NULL;
iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node);
__mtrr_lookup_var_next(iter);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f314e9b9660b..4589b6feeb7b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6579,7 +6579,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
/* Checks for #GP/#SS exceptions. */
exn = false;
- if (is_protmode(vcpu)) {
+ if (is_long_mode(vcpu)) {
+ /* Long mode: #GP(0)/#SS(0) if the memory address is in a
+ * non-canonical form. This is the only check on the memory
+ * destination for long mode!
+ */
+ exn = is_noncanonical_address(*ret);
+ } else if (is_protmode(vcpu)) {
/* Protected mode: apply checks for segment validity in the
* following order:
* - segment type check (#GP(0) may be thrown)
@@ -6596,17 +6602,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
* execute-only code segment
*/
exn = ((s.type & 0xa) == 8);
- }
- if (exn) {
- kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
- return 1;
- }
- if (is_long_mode(vcpu)) {
- /* Long mode: #GP(0)/#SS(0) if the memory address is in a
- * non-canonical form. This is an only check for long mode.
- */
- exn = is_noncanonical_address(*ret);
- } else if (is_protmode(vcpu)) {
+ if (exn) {
+ kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+ return 1;
+ }
/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
*/
exn = (s.unusable != 0);
@@ -8125,6 +8124,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
exit_reason != EXIT_REASON_EPT_VIOLATION &&
+ exit_reason != EXIT_REASON_PML_FULL &&
exit_reason != EXIT_REASON_TASK_SWITCH)) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -8737,6 +8737,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
put_cpu();
}
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int r;
+
+ r = vcpu_load(vcpu);
+ BUG_ON(r);
+ vmx_load_vmcs01(vcpu);
+ free_nested(vmx);
+ vcpu_put(vcpu);
+}
+
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8745,8 +8761,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
vmx_destroy_pml_buffer(vmx);
free_vpid(vmx->vpid);
leave_guest_mode(vcpu);
- vmx_load_vmcs01(vcpu);
- free_nested(vmx);
+ vmx_free_vcpu_nested(vcpu);
free_loaded_vmcs(vmx->loaded_vmcs);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 844b06d67df4..307f60ecfc6d 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -94,18 +94,6 @@ static unsigned long mmap_base(unsigned long rnd)
}
/*
- * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64
- * does, but not when emulating X86_32
- */
-static unsigned long mmap_legacy_base(unsigned long rnd)
-{
- if (mmap_is_ia32())
- return TASK_UNMAPPED_BASE;
- else
- return TASK_UNMAPPED_BASE + rnd;
-}
-
-/*
* This function, called very early during the creation of a new
* process VM image, sets up which VM layout function to use:
*/
@@ -116,7 +104,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
if (current->flags & PF_RANDOMIZE)
random_factor = arch_mmap_rnd();
- mm->mmap_legacy_base = mmap_legacy_base(random_factor);
+ mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor;
if (mmap_is_legacy()) {
mm->mmap_base = mm->mmap_legacy_base;
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 188e3e07eeeb..6ad687d104ca 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -39,11 +39,22 @@
static bool boot_cpu_done;
static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
+static void init_cache_modes(void);
-static inline void pat_disable(const char *reason)
+void pat_disable(const char *reason)
{
+ if (!__pat_enabled)
+ return;
+
+ if (boot_cpu_done) {
+ WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n");
+ return;
+ }
+
__pat_enabled = 0;
pr_info("x86/PAT: %s\n", reason);
+
+ init_cache_modes();
}
static int __init nopat(char *str)
@@ -180,7 +191,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
* configuration.
* Using lower indices is preferred, so we start with highest index.
*/
-void pat_init_cache_modes(u64 pat)
+static void __init_cache_modes(u64 pat)
{
enum page_cache_mode cache;
char pat_msg[33];
@@ -201,14 +212,11 @@ static void pat_bsp_init(u64 pat)
{
u64 tmp_pat;
- if (!cpu_has_pat) {
+ if (!boot_cpu_has(X86_FEATURE_PAT)) {
pat_disable("PAT not supported by CPU.");
return;
}
- if (!pat_enabled())
- goto done;
-
rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
if (!tmp_pat) {
pat_disable("PAT MSR is 0, disabled.");
@@ -217,16 +225,12 @@ static void pat_bsp_init(u64 pat)
wrmsrl(MSR_IA32_CR_PAT, pat);
-done:
- pat_init_cache_modes(pat);
+ __init_cache_modes(pat);
}
static void pat_ap_init(u64 pat)
{
- if (!pat_enabled())
- return;
-
- if (!cpu_has_pat) {
+ if (!boot_cpu_has(X86_FEATURE_PAT)) {
/*
* If this happens we are on a secondary CPU, but switched to
* PAT on the boot CPU. We have no way to undo PAT.
@@ -237,18 +241,32 @@ static void pat_ap_init(u64 pat)
wrmsrl(MSR_IA32_CR_PAT, pat);
}
-void pat_init(void)
+static void init_cache_modes(void)
{
- u64 pat;
- struct cpuinfo_x86 *c = &boot_cpu_data;
+ u64 pat = 0;
+ static int init_cm_done;
- if (!pat_enabled()) {
+ if (init_cm_done)
+ return;
+
+ if (boot_cpu_has(X86_FEATURE_PAT)) {
+ /*
+ * CPU supports PAT. Set PAT table to be consistent with
+ * PAT MSR. This case supports "nopat" boot option, and
+ * virtual machine environments which support PAT without
+ * MTRRs. In specific, Xen has unique setup to PAT MSR.
+ *
+ * If PAT MSR returns 0, it is considered invalid and emulates
+ * as No PAT.
+ */
+ rdmsrl(MSR_IA32_CR_PAT, pat);
+ }
+
+ if (!pat) {
/*
* No PAT. Emulate the PAT table that corresponds to the two
- * cache bits, PWT (Write Through) and PCD (Cache Disable). This
- * setup is the same as the BIOS default setup when the system
- * has PAT but the "nopat" boot option has been specified. This
- * emulated PAT table is used when MSR_IA32_CR_PAT returns 0.
+ * cache bits, PWT (Write Through) and PCD (Cache Disable).
+ * This setup is also the same as the BIOS default setup.
*
* PTE encoding:
*
@@ -265,10 +283,36 @@ void pat_init(void)
*/
pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
+ }
+
+ __init_cache_modes(pat);
+
+ init_cm_done = 1;
+}
+
+/**
+ * pat_init - Initialize PAT MSR and PAT table
+ *
+ * This function initializes PAT MSR and PAT table with an OS-defined value
+ * to enable additional cache attributes, WC and WT.
+ *
+ * This function must be called on all CPUs using the specific sequence of
+ * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this
+ * procedure for PAT.
+ */
+void pat_init(void)
+{
+ u64 pat;
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ if (!pat_enabled()) {
+ init_cache_modes();
+ return;
+ }
- } else if ((c->x86_vendor == X86_VENDOR_INTEL) &&
- (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
- ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+ if ((c->x86_vendor == X86_VENDOR_INTEL) &&
+ (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
+ ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
/*
* PAT support with the lower four entries. Intel Pentium 2,
* 3, M, and 4 are affected by PAT errata, which makes the
@@ -733,25 +777,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
if (file->f_flags & O_DSYNC)
pcm = _PAGE_CACHE_MODE_UC_MINUS;
-#ifdef CONFIG_X86_32
- /*
- * On the PPro and successors, the MTRRs are used to set
- * memory types for physical addresses outside main memory,
- * so blindly setting UC or PWT on those pages is wrong.
- * For Pentiums and earlier, the surround logic should disable
- * caching for the high addresses through the KEN pin, but
- * we maintain the tradition of paranoia in this code.
- */
- if (!pat_enabled() &&
- !(boot_cpu_has(X86_FEATURE_MTRR) ||
- boot_cpu_has(X86_FEATURE_K6_MTRR) ||
- boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
- boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
- (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
- pcm = _PAGE_CACHE_MODE_UC;
- }
-#endif
-
*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
cachemode2protval(pcm));
return 1;
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 8b93e634af84..ae97f24a4371 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -37,6 +37,7 @@
/* Quirks for the listed devices */
#define PCI_DEVICE_ID_INTEL_MRFL_MMC 0x1190
+#define PCI_DEVICE_ID_INTEL_MRFL_HSU 0x1191
/* Fixed BAR fields */
#define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00 /* Fixed BAR (TBD) */
@@ -225,13 +226,20 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
/* Special treatment for IRQ0 */
if (dev->irq == 0) {
/*
+ * Skip HS UART common registers device since it has
+ * IRQ0 assigned and not used by the kernel.
+ */
+ if (dev->device == PCI_DEVICE_ID_INTEL_MRFL_HSU)
+ return -EBUSY;
+ /*
* TNG has IRQ0 assigned to eMMC controller. But there
* are also other devices with bogus PCI configuration
* that have IRQ0 assigned. This check ensures that
- * eMMC gets it.
+ * eMMC gets it. The rest of devices still could be
+ * enabled without interrupt line being allocated.
*/
if (dev->device != PCI_DEVICE_ID_INTEL_MRFL_MMC)
- return -EBUSY;
+ return 0;
}
break;
default:
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index beab8c706ac9..ffa41591bff9 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -74,7 +74,6 @@
#include <asm/mach_traps.h>
#include <asm/mwait.h>
#include <asm/pci_x86.h>
-#include <asm/pat.h>
#include <asm/cpu.h>
#ifdef CONFIG_ACPI
@@ -1519,7 +1518,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
{
struct physdev_set_iopl set_iopl;
unsigned long initrd_start = 0;
- u64 pat;
int rc;
if (!xen_start_info)
@@ -1627,13 +1625,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
xen_start_info->nr_pages);
xen_reserve_special_pages();
- /*
- * Modify the cache mode translation tables to match Xen's PAT
- * configuration.
- */
- rdmsrl(MSR_IA32_CR_PAT, pat);
- pat_init_cache_modes(pat);
-
/* keep using Xen gdt for now; no urgent need to change it */
#ifdef CONFIG_X86_32