summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig.cpu4
-rw-r--r--arch/x86/boot/compressed/aslr.c9
-rw-r--r--arch/x86/include/asm/barrier.h8
-rw-r--r--arch/x86/include/asm/efi.h3
-rw-r--r--arch/x86/include/asm/io.h2
-rw-r--r--arch/x86/include/asm/spinlock.h5
-rw-r--r--arch/x86/include/asm/topology.h3
-rw-r--r--arch/x86/include/asm/tsc.h2
-rw-r--r--arch/x86/kernel/aperture_64.c20
-rw-r--r--arch/x86/kernel/cpu/centaur.c272
-rw-r--r--arch/x86/kernel/cpu/common.c7
-rw-r--r--arch/x86/kernel/cpu/perf_event.c11
-rw-r--r--arch/x86/kernel/cpu/perf_event.h1
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c11
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c13
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c48
-rw-r--r--arch/x86/kernel/ftrace.c83
-rw-r--r--arch/x86/kernel/head_32.S7
-rw-r--r--arch/x86/kernel/head_64.S6
-rw-r--r--arch/x86/kernel/i387.c15
-rw-r--r--arch/x86/kernel/machine_kexec_64.c2
-rw-r--r--arch/x86/kernel/pci-dma.c4
-rw-r--r--arch/x86/kernel/quirks.c2
-rw-r--r--arch/x86/kernel/setup.c10
-rw-r--r--arch/x86/kernel/tsc.c11
-rw-r--r--arch/x86/kernel/tsc_msr.c30
-rw-r--r--arch/x86/kvm/mmu.c1
-rw-r--r--arch/x86/kvm/svm.c6
-rw-r--r--arch/x86/kvm/vmx.c2
-rw-r--r--arch/x86/kvm/x86.c2
-rw-r--r--arch/x86/mm/fault.c61
-rw-r--r--arch/x86/net/bpf_jit.S2
-rw-r--r--arch/x86/platform/efi/efi-bgrt.c2
-rw-r--r--arch/x86/platform/efi/efi.c25
-rw-r--r--arch/x86/platform/efi/efi_32.c6
-rw-r--r--arch/x86/platform/efi/efi_64.c9
-rw-r--r--arch/x86/um/asm/barrier.h4
37 files changed, 264 insertions, 445 deletions
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index c026cca5602c..f3aaf231b4e5 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -341,10 +341,6 @@ config X86_USE_3DNOW
def_bool y
depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
-config X86_OOSTORE
- def_bool y
- depends on (MWINCHIP3D || MWINCHIPC6) && MTRR
-
#
# P6_NOPs are a relatively minor optimization that require a family >=
# 6 processor, except that it is broken on certain VIA chips.
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 90a21f430117..4dbf967da50d 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -111,7 +111,7 @@ struct mem_vector {
};
#define MEM_AVOID_MAX 5
-struct mem_vector mem_avoid[MEM_AVOID_MAX];
+static struct mem_vector mem_avoid[MEM_AVOID_MAX];
static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
{
@@ -180,7 +180,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
}
/* Does this memory vector overlap a known avoided area? */
-bool mem_avoid_overlap(struct mem_vector *img)
+static bool mem_avoid_overlap(struct mem_vector *img)
{
int i;
@@ -192,8 +192,9 @@ bool mem_avoid_overlap(struct mem_vector *img)
return false;
}
-unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN];
-unsigned long slot_max = 0;
+static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+ CONFIG_PHYSICAL_ALIGN];
+static unsigned long slot_max;
static void slots_append(unsigned long addr)
{
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 04a48903b2eb..69bbb4845020 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -85,11 +85,7 @@
#else
# define smp_rmb() barrier()
#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() wmb()
-#else
-# define smp_wmb() barrier()
-#endif
+#define smp_wmb() barrier()
#define smp_read_barrier_depends() read_barrier_depends()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else /* !SMP */
@@ -100,7 +96,7 @@
#define set_mb(var, value) do { var = value; barrier(); } while (0)
#endif /* SMP */
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
/*
* For either of these options x86 doesn't have a strong TSO memory
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3b978c472d08..acd86c850414 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -132,6 +132,9 @@ extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
extern void efi_sync_low_kernel_mappings(void);
extern void efi_setup_page_tables(void);
extern void __init old_map_region(efi_memory_desc_t *md);
+extern void __init runtime_code_page_mkexec(void);
+extern void __init efi_runtime_mkexec(void);
+extern void __init efi_apply_memmap_quirks(void);
struct efi_setup_data {
u64 fw_vendor;
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 34f69cb9350a..91d9c69a629e 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -237,7 +237,7 @@ memcpy_toio(volatile void __iomem *dst, const void *src, size_t count)
static inline void flush_write_buffers(void)
{
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
asm volatile("lock; addl $0,0(%%esp)": : :"memory");
#endif
}
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index bf156ded74b5..0f62f5482d91 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -26,10 +26,9 @@
# define LOCK_PTR_REG "D"
#endif
-#if defined(CONFIG_X86_32) && \
- (defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
+#if defined(CONFIG_X86_32) && (defined(CONFIG_X86_PPRO_FENCE))
/*
- * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
+ * On PPro SMP, we use a locked operation to unlock
* (PPro errata 66, 92)
*/
# define UNLOCK_LOCK_PREFIX LOCK_PREFIX
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index d35f24e231cd..1306d117967d 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -119,9 +119,10 @@ static inline void setup_node_to_cpumask_map(void) { }
extern const struct cpumask *cpu_coregroup_mask(int cpu);
-#ifdef ENABLE_TOPO_DEFINES
#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
+
+#ifdef ENABLE_TOPO_DEFINES
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
#endif
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 57ae63cd6ee2..94605c0e9cee 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -66,6 +66,6 @@ extern void tsc_save_sched_clock_state(void);
extern void tsc_restore_sched_clock_state(void);
/* MSR based TSC calibration for Intel Atom SoC platforms */
-int try_msr_calibrate_tsc(unsigned long *fast_calibrate);
+unsigned long try_msr_calibrate_tsc(void);
#endif /* _ASM_X86_TSC_H */
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index fd972a3e4cbb..9fa8aa051f54 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -18,7 +18,6 @@
#include <linux/pci_ids.h>
#include <linux/pci.h>
#include <linux/bitops.h>
-#include <linux/ioport.h>
#include <linux/suspend.h>
#include <asm/e820.h>
#include <asm/io.h>
@@ -54,18 +53,6 @@ int fallback_aper_force __initdata;
int fix_aperture __initdata = 1;
-static struct resource gart_resource = {
- .name = "GART",
- .flags = IORESOURCE_MEM,
-};
-
-static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
-{
- gart_resource.start = aper_base;
- gart_resource.end = aper_base + aper_size - 1;
- insert_resource(&iomem_resource, &gart_resource);
-}
-
/* This code runs before the PCI subsystem is initialized, so just
access the northbridge directly. */
@@ -96,7 +83,6 @@ static u32 __init allocate_aperture(void)
memblock_reserve(addr, aper_size);
printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
aper_size >> 10, addr);
- insert_aperture_resource((u32)addr, aper_size);
register_nosave_region(addr >> PAGE_SHIFT,
(addr+aper_size) >> PAGE_SHIFT);
@@ -444,12 +430,8 @@ int __init gart_iommu_hole_init(void)
out:
if (!fix && !fallback_aper_force) {
- if (last_aper_base) {
- unsigned long n = (32 * 1024 * 1024) << last_aper_order;
-
- insert_aperture_resource((u32)last_aper_base, n);
+ if (last_aper_base)
return 1;
- }
return 0;
}
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 8779edab684e..d8fba5c15fbd 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -8,236 +8,6 @@
#include "cpu.h"
-#ifdef CONFIG_X86_OOSTORE
-
-static u32 power2(u32 x)
-{
- u32 s = 1;
-
- while (s <= x)
- s <<= 1;
-
- return s >>= 1;
-}
-
-
-/*
- * Set up an actual MCR
- */
-static void centaur_mcr_insert(int reg, u32 base, u32 size, int key)
-{
- u32 lo, hi;
-
- hi = base & ~0xFFF;
- lo = ~(size-1); /* Size is a power of 2 so this makes a mask */
- lo &= ~0xFFF; /* Remove the ctrl value bits */
- lo |= key; /* Attribute we wish to set */
- wrmsr(reg+MSR_IDT_MCR0, lo, hi);
- mtrr_centaur_report_mcr(reg, lo, hi); /* Tell the mtrr driver */
-}
-
-/*
- * Figure what we can cover with MCR's
- *
- * Shortcut: We know you can't put 4Gig of RAM on a winchip
- */
-static u32 ramtop(void)
-{
- u32 clip = 0xFFFFFFFFUL;
- u32 top = 0;
- int i;
-
- for (i = 0; i < e820.nr_map; i++) {
- unsigned long start, end;
-
- if (e820.map[i].addr > 0xFFFFFFFFUL)
- continue;
- /*
- * Don't MCR over reserved space. Ignore the ISA hole
- * we frob around that catastrophe already
- */
- if (e820.map[i].type == E820_RESERVED) {
- if (e820.map[i].addr >= 0x100000UL &&
- e820.map[i].addr < clip)
- clip = e820.map[i].addr;
- continue;
- }
- start = e820.map[i].addr;
- end = e820.map[i].addr + e820.map[i].size;
- if (start >= end)
- continue;
- if (end > top)
- top = end;
- }
- /*
- * Everything below 'top' should be RAM except for the ISA hole.
- * Because of the limited MCR's we want to map NV/ACPI into our
- * MCR range for gunk in RAM
- *
- * Clip might cause us to MCR insufficient RAM but that is an
- * acceptable failure mode and should only bite obscure boxes with
- * a VESA hole at 15Mb
- *
- * The second case Clip sometimes kicks in is when the EBDA is marked
- * as reserved. Again we fail safe with reasonable results
- */
- if (top > clip)
- top = clip;
-
- return top;
-}
-
-/*
- * Compute a set of MCR's to give maximum coverage
- */
-static int centaur_mcr_compute(int nr, int key)
-{
- u32 mem = ramtop();
- u32 root = power2(mem);
- u32 base = root;
- u32 top = root;
- u32 floor = 0;
- int ct = 0;
-
- while (ct < nr) {
- u32 fspace = 0;
- u32 high;
- u32 low;
-
- /*
- * Find the largest block we will fill going upwards
- */
- high = power2(mem-top);
-
- /*
- * Find the largest block we will fill going downwards
- */
- low = base/2;
-
- /*
- * Don't fill below 1Mb going downwards as there
- * is an ISA hole in the way.
- */
- if (base <= 1024*1024)
- low = 0;
-
- /*
- * See how much space we could cover by filling below
- * the ISA hole
- */
-
- if (floor == 0)
- fspace = 512*1024;
- else if (floor == 512*1024)
- fspace = 128*1024;
-
- /* And forget ROM space */
-
- /*
- * Now install the largest coverage we get
- */
- if (fspace > high && fspace > low) {
- centaur_mcr_insert(ct, floor, fspace, key);
- floor += fspace;
- } else if (high > low) {
- centaur_mcr_insert(ct, top, high, key);
- top += high;
- } else if (low > 0) {
- base -= low;
- centaur_mcr_insert(ct, base, low, key);
- } else
- break;
- ct++;
- }
- /*
- * We loaded ct values. We now need to set the mask. The caller
- * must do this bit.
- */
- return ct;
-}
-
-static void centaur_create_optimal_mcr(void)
-{
- int used;
- int i;
-
- /*
- * Allocate up to 6 mcrs to mark as much of ram as possible
- * as write combining and weak write ordered.
- *
- * To experiment with: Linux never uses stack operations for
- * mmio spaces so we could globally enable stack operation wc
- *
- * Load the registers with type 31 - full write combining, all
- * writes weakly ordered.
- */
- used = centaur_mcr_compute(6, 31);
-
- /*
- * Wipe unused MCRs
- */
- for (i = used; i < 8; i++)
- wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-static void winchip2_create_optimal_mcr(void)
-{
- u32 lo, hi;
- int used;
- int i;
-
- /*
- * Allocate up to 6 mcrs to mark as much of ram as possible
- * as write combining, weak store ordered.
- *
- * Load the registers with type 25
- * 8 - weak write ordering
- * 16 - weak read ordering
- * 1 - write combining
- */
- used = centaur_mcr_compute(6, 25);
-
- /*
- * Mark the registers we are using.
- */
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- for (i = 0; i < used; i++)
- lo |= 1<<(9+i);
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-
- /*
- * Wipe unused MCRs
- */
-
- for (i = used; i < 8; i++)
- wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-/*
- * Handle the MCR key on the Winchip 2.
- */
-static void winchip2_unprotect_mcr(void)
-{
- u32 lo, hi;
- u32 key;
-
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- lo &= ~0x1C0; /* blank bits 8-6 */
- key = (lo>>17) & 7;
- lo |= key<<6; /* replace with unlock key */
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-
-static void winchip2_protect_mcr(void)
-{
- u32 lo, hi;
-
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- lo &= ~0x1C0; /* blank bits 8-6 */
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-#endif /* CONFIG_X86_OOSTORE */
-
#define ACE_PRESENT (1 << 6)
#define ACE_ENABLED (1 << 7)
#define ACE_FCR (1 << 28) /* MSR_VIA_FCR */
@@ -362,20 +132,6 @@ static void init_centaur(struct cpuinfo_x86 *c)
fcr_clr = DPDC;
printk(KERN_NOTICE "Disabling bugged TSC.\n");
clear_cpu_cap(c, X86_FEATURE_TSC);
-#ifdef CONFIG_X86_OOSTORE
- centaur_create_optimal_mcr();
- /*
- * Enable:
- * write combining on non-stack, non-string
- * write combining on string, all types
- * weak write ordering
- *
- * The C6 original lacks weak read order
- *
- * Note 0x120 is write only on Winchip 1
- */
- wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0);
-#endif
break;
case 8:
switch (c->x86_mask) {
@@ -392,40 +148,12 @@ static void init_centaur(struct cpuinfo_x86 *c)
fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
E2MMX|EAMD3D;
fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
- winchip2_unprotect_mcr();
- winchip2_create_optimal_mcr();
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- /*
- * Enable:
- * write combining on non-stack, non-string
- * write combining on string, all types
- * weak write ordering
- */
- lo |= 31;
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
- winchip2_protect_mcr();
-#endif
break;
case 9:
name = "3";
fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
E2MMX|EAMD3D;
fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
- winchip2_unprotect_mcr();
- winchip2_create_optimal_mcr();
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- /*
- * Enable:
- * write combining on non-stack, non-string
- * write combining on string, all types
- * weak write ordering
- */
- lo |= 31;
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
- winchip2_protect_mcr();
-#endif
break;
default:
name = "??";
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 24b6fd10625a..8e28bf2fc3ef 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -284,8 +284,13 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
raw_local_save_flags(eflags);
BUG_ON(eflags & X86_EFLAGS_AC);
- if (cpu_has(c, X86_FEATURE_SMAP))
+ if (cpu_has(c, X86_FEATURE_SMAP)) {
+#ifdef CONFIG_X86_SMAP
set_in_cr4(X86_CR4_SMAP);
+#else
+ clear_in_cr4(X86_CR4_SMAP);
+#endif
+ }
}
/*
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b88645191fe5..79f9f848bee4 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1192,6 +1192,9 @@ static void x86_pmu_del(struct perf_event *event, int flags)
for (i = 0; i < cpuc->n_events; i++) {
if (event == cpuc->event_list[i]) {
+ if (i >= cpuc->n_events - cpuc->n_added)
+ --cpuc->n_added;
+
if (x86_pmu.put_event_constraints)
x86_pmu.put_event_constraints(cpuc, event);
@@ -1521,6 +1524,8 @@ static int __init init_hw_perf_events(void)
pr_cont("%s PMU driver.\n", x86_pmu.name);
+ x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+
for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
quirk->func();
@@ -1534,7 +1539,6 @@ static int __init init_hw_perf_events(void)
__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
0, x86_pmu.num_counters, 0, 0);
- x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
if (x86_pmu.event_attrs)
@@ -1820,9 +1824,12 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
if (ret)
return ret;
+ if (x86_pmu.attr_rdpmc_broken)
+ return -ENOTSUPP;
+
if (!!val != !!x86_pmu.attr_rdpmc) {
x86_pmu.attr_rdpmc = !!val;
- smp_call_function(change_rdpmc, (void *)val, 1);
+ on_each_cpu(change_rdpmc, (void *)val, 1);
}
return count;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index c1a861829d81..4972c244d0bc 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -409,6 +409,7 @@ struct x86_pmu {
/*
* sysfs attrs
*/
+ int attr_rdpmc_broken;
int attr_rdpmc;
struct attribute **format_attrs;
struct attribute **event_attrs;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 0fa4f242f050..aa333d966886 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1361,10 +1361,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
intel_pmu_disable_all();
handled = intel_pmu_drain_bts_buffer();
status = intel_pmu_get_status();
- if (!status) {
- intel_pmu_enable_all(0);
- return handled;
- }
+ if (!status)
+ goto done;
loops = 0;
again:
@@ -2310,10 +2308,7 @@ __init int intel_pmu_init(void)
if (version > 1)
x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
- /*
- * v2 and above have a perf capabilities MSR
- */
- if (version > 1) {
+ if (boot_cpu_has(X86_FEATURE_PDCM)) {
u64 capabilities;
rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 29c248799ced..047f540cf3f7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -501,8 +501,11 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6),
SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6),
SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6),
SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
@@ -1178,10 +1181,15 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc),
SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc),
SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc),
SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
@@ -3326,6 +3334,8 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
if (!pmus)
return -ENOMEM;
+ type->pmus = pmus;
+
type->unconstrainted = (struct event_constraint)
__EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
0, type->num_counters, 0, 0);
@@ -3361,7 +3371,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
}
type->pmu_group = &uncore_pmu_attr_group;
- type->pmus = pmus;
return 0;
fail:
uncore_type_exit(type);
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index b1e2fe115323..7c1a0c07b607 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -231,31 +231,49 @@ static __initconst const struct x86_pmu p6_pmu = {
};
+static __init void p6_pmu_rdpmc_quirk(void)
+{
+ if (boot_cpu_data.x86_mask < 9) {
+ /*
+ * PPro erratum 26; fixed in stepping 9 and above.
+ */
+ pr_warn("Userspace RDPMC support disabled due to a CPU erratum\n");
+ x86_pmu.attr_rdpmc_broken = 1;
+ x86_pmu.attr_rdpmc = 0;
+ }
+}
+
__init int p6_pmu_init(void)
{
+ x86_pmu = p6_pmu;
+
switch (boot_cpu_data.x86_model) {
- case 1:
- case 3: /* Pentium Pro */
- case 5:
- case 6: /* Pentium II */
- case 7:
- case 8:
- case 11: /* Pentium III */
- case 9:
- case 13:
- /* Pentium M */
+ case 1: /* Pentium Pro */
+ x86_add_quirk(p6_pmu_rdpmc_quirk);
+ break;
+
+ case 3: /* Pentium II - Klamath */
+ case 5: /* Pentium II - Deschutes */
+ case 6: /* Pentium II - Mendocino */
break;
+
+ case 7: /* Pentium III - Katmai */
+ case 8: /* Pentium III - Coppermine */
+ case 10: /* Pentium III Xeon */
+ case 11: /* Pentium III - Tualatin */
+ break;
+
+ case 9: /* Pentium M - Banias */
+ case 13: /* Pentium M - Dothan */
+ break;
+
default:
- pr_cont("unsupported p6 CPU model %d ",
- boot_cpu_data.x86_model);
+ pr_cont("unsupported p6 CPU model %d ", boot_cpu_data.x86_model);
return -ENODEV;
}
- x86_pmu = p6_pmu;
-
memcpy(hw_cache_event_ids, p6_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
-
return 0;
}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index d4bdd253fea7..e6253195a301 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -77,8 +77,7 @@ within(unsigned long addr, unsigned long start, unsigned long end)
return addr >= start && addr < end;
}
-static int
-do_ftrace_mod_code(unsigned long ip, const void *new_code)
+static unsigned long text_ip_addr(unsigned long ip)
{
/*
* On x86_64, kernel text mappings are mapped read-only with
@@ -91,7 +90,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code)
if (within(ip, (unsigned long)_text, (unsigned long)_etext))
ip = (unsigned long)__va(__pa_symbol(ip));
- return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
+ return ip;
}
static const unsigned char *ftrace_nop_replace(void)
@@ -123,8 +122,10 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
return -EINVAL;
+ ip = text_ip_addr(ip);
+
/* replace the text with the new text */
- if (do_ftrace_mod_code(ip, new_code))
+ if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
return -EPERM;
sync_core();
@@ -221,37 +222,51 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
return -EINVAL;
}
-int ftrace_update_ftrace_func(ftrace_func_t func)
+static unsigned long ftrace_update_func;
+
+static int update_ftrace_func(unsigned long ip, void *new)
{
- unsigned long ip = (unsigned long)(&ftrace_call);
- unsigned char old[MCOUNT_INSN_SIZE], *new;
+ unsigned char old[MCOUNT_INSN_SIZE];
int ret;
- memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
- new = ftrace_call_replace(ip, (unsigned long)func);
+ memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);
+
+ ftrace_update_func = ip;
+ /* Make sure the breakpoints see the ftrace_update_func update */
+ smp_wmb();
/* See comment above by declaration of modifying_ftrace_code */
atomic_inc(&modifying_ftrace_code);
ret = ftrace_modify_code(ip, old, new);
+ atomic_dec(&modifying_ftrace_code);
+
+ return ret;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+ unsigned long ip = (unsigned long)(&ftrace_call);
+ unsigned char *new;
+ int ret;
+
+ new = ftrace_call_replace(ip, (unsigned long)func);
+ ret = update_ftrace_func(ip, new);
+
/* Also update the regs callback function */
if (!ret) {
ip = (unsigned long)(&ftrace_regs_call);
- memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
new = ftrace_call_replace(ip, (unsigned long)func);
- ret = ftrace_modify_code(ip, old, new);
+ ret = update_ftrace_func(ip, new);
}
- atomic_dec(&modifying_ftrace_code);
-
return ret;
}
static int is_ftrace_caller(unsigned long ip)
{
- if (ip == (unsigned long)(&ftrace_call) ||
- ip == (unsigned long)(&ftrace_regs_call))
+ if (ip == ftrace_update_func)
return 1;
return 0;
@@ -677,45 +692,41 @@ int __init ftrace_dyn_arch_init(void *data)
#ifdef CONFIG_DYNAMIC_FTRACE
extern void ftrace_graph_call(void);
-static int ftrace_mod_jmp(unsigned long ip,
- int old_offset, int new_offset)
+static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
{
- unsigned char code[MCOUNT_INSN_SIZE];
+ static union ftrace_code_union calc;
- if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
- return -EFAULT;
+ /* Jmp not a call (ignore the .e8) */
+ calc.e8 = 0xe9;
+ calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
- if (code[0] != 0xe9 || old_offset != *(int *)(&code[1]))
- return -EINVAL;
+ /*
+ * ftrace external locks synchronize the access to the static variable.
+ */
+ return calc.code;
+}
- *(int *)(&code[1]) = new_offset;
+static int ftrace_mod_jmp(unsigned long ip, void *func)
+{
+ unsigned char *new;
- if (do_ftrace_mod_code(ip, &code))
- return -EPERM;
+ new = ftrace_jmp_replace(ip, (unsigned long)func);
- return 0;
+ return update_ftrace_func(ip, new);
}
int ftrace_enable_ftrace_graph_caller(void)
{
unsigned long ip = (unsigned long)(&ftrace_graph_call);
- int old_offset, new_offset;
- old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
- new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-
- return ftrace_mod_jmp(ip, old_offset, new_offset);
+ return ftrace_mod_jmp(ip, &ftrace_graph_caller);
}
int ftrace_disable_ftrace_graph_caller(void)
{
unsigned long ip = (unsigned long)(&ftrace_graph_call);
- int old_offset, new_offset;
-
- old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
- new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
- return ftrace_mod_jmp(ip, old_offset, new_offset);
+ return ftrace_mod_jmp(ip, &ftrace_stub);
}
#endif /* !CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 81ba27679f18..f36bd42d6f0c 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -544,6 +544,10 @@ ENDPROC(early_idt_handlers)
/* This is global to keep gas from relaxing the jumps */
ENTRY(early_idt_handler)
cld
+
+ cmpl $2,(%esp) # X86_TRAP_NMI
+ je is_nmi # Ignore NMI
+
cmpl $2,%ss:early_recursion_flag
je hlt_loop
incl %ss:early_recursion_flag
@@ -594,8 +598,9 @@ ex_entry:
pop %edx
pop %ecx
pop %eax
- addl $8,%esp /* drop vector number and error code */
decl %ss:early_recursion_flag
+is_nmi:
+ addl $8,%esp /* drop vector number and error code */
iret
ENDPROC(early_idt_handler)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e1aabdb314c8..a468c0a65c42 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -343,6 +343,9 @@ early_idt_handlers:
ENTRY(early_idt_handler)
cld
+ cmpl $2,(%rsp) # X86_TRAP_NMI
+ je is_nmi # Ignore NMI
+
cmpl $2,early_recursion_flag(%rip)
jz 1f
incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@ ENTRY(early_idt_handler)
popq %rdx
popq %rcx
popq %rax
- addq $16,%rsp # drop vector number and error code
decl early_recursion_flag(%rip)
+is_nmi:
+ addq $16,%rsp # drop vector number and error code
INTERRUPT_RETURN
ENDPROC(early_idt_handler)
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e8368c6dd2a2..d5dd80814419 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin);
void __kernel_fpu_end(void)
{
- if (use_eager_fpu())
- math_state_restore();
- else
+ if (use_eager_fpu()) {
+ /*
+ * For eager fpu, most the time, tsk_used_math() is true.
+ * Restore the user math as we are done with the kernel usage.
+ * At few instances during thread exit, signal handling etc,
+ * tsk_used_math() is false. Those few places will take proper
+ * actions, so we don't need to restore the math here.
+ */
+ if (likely(tsk_used_math(current)))
+ math_state_restore();
+ } else {
stts();
+ }
}
EXPORT_SYMBOL(__kernel_fpu_end);
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4eabc160696f..679cef0791cd 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -279,5 +279,7 @@ void arch_crash_save_vmcoreinfo(void)
VMCOREINFO_SYMBOL(node_data);
VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
#endif
+ vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
+ (unsigned long)&_text - __START_KERNEL);
}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 872079a67e4d..f7d0672481fd 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -100,8 +100,10 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
flag |= __GFP_ZERO;
again:
page = NULL;
- if (!(flag & GFP_ATOMIC))
+ /* CMA can be used only in the context which permits sleeping */
+ if (flag & __GFP_WAIT)
page = dma_alloc_from_contiguous(dev, count, get_order(size));
+ /* fallback */
if (!page)
page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
if (!page)
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 7c6acd4b8995..ff898bbf579d 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -529,7 +529,7 @@ static void quirk_amd_nb_node(struct pci_dev *dev)
return;
pci_read_config_dword(nb_ht, 0x60, &val);
- node = val & 7;
+ node = pcibus_to_node(dev->bus) | (val & 7);
/*
* Some hardware may return an invalid node ID,
* so check it first:
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 06853e670354..ce72964b2f46 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1239,14 +1239,8 @@ void __init setup_arch(char **cmdline_p)
register_refined_jiffies(CLOCK_TICK_RATE);
#ifdef CONFIG_EFI
- /* Once setup is done above, unmap the EFI memory map on
- * mismatched firmware/kernel archtectures since there is no
- * support for runtime services.
- */
- if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
- pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
- efi_unmap_memmap();
- }
+ if (efi_enabled(EFI_BOOT))
+ efi_apply_memmap_quirks();
#endif
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 19e5adb49a27..cfbe99f88830 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -209,7 +209,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
* dance when its actually needed.
*/
- preempt_disable();
+ preempt_disable_notrace();
data = this_cpu_read(cyc2ns.head);
tail = this_cpu_read(cyc2ns.tail);
@@ -229,7 +229,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
if (!--data->__count)
this_cpu_write(cyc2ns.tail, data);
}
- preempt_enable();
+ preempt_enable_notrace();
return ns;
}
@@ -653,13 +653,10 @@ unsigned long native_calibrate_tsc(void)
/* Calibrate TSC using MSR for Intel Atom SoCs */
local_irq_save(flags);
- i = try_msr_calibrate_tsc(&fast_calibrate);
+ fast_calibrate = try_msr_calibrate_tsc();
local_irq_restore(flags);
- if (i >= 0) {
- if (i == 0)
- pr_warn("Fast TSC calibration using MSR failed\n");
+ if (fast_calibrate)
return fast_calibrate;
- }
local_irq_save(flags);
fast_calibrate = quick_pit_calibrate();
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 8b5434f4389f..92ae6acac8a7 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -53,7 +53,7 @@ static struct freq_desc freq_desc_tables[] = {
/* TNG */
{ 6, 0x4a, 1, { 0, FREQ_100, FREQ_133, 0, 0, 0, 0, 0 } },
/* VLV2 */
- { 6, 0x37, 1, { 0, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } },
+ { 6, 0x37, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } },
/* ANN */
{ 6, 0x5a, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_100, 0, 0, 0, 0 } },
};
@@ -77,21 +77,18 @@ static int match_cpu(u8 family, u8 model)
/*
* Do MSR calibration only for known/supported CPUs.
- * Return values:
- * -1: CPU is unknown/unsupported for MSR based calibration
- * 0: CPU is known/supported, but calibration failed
- * 1: CPU is known/supported, and calibration succeeded
+ *
+ * Returns the calibration value or 0 if MSR calibration failed.
*/
-int try_msr_calibrate_tsc(unsigned long *fast_calibrate)
+unsigned long try_msr_calibrate_tsc(void)
{
- int cpu_index;
u32 lo, hi, ratio, freq_id, freq;
+ unsigned long res;
+ int cpu_index;
cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model);
if (cpu_index < 0)
- return -1;
-
- *fast_calibrate = 0;
+ return 0;
if (freq_desc_tables[cpu_index].msr_plat) {
rdmsr(MSR_PLATFORM_INFO, lo, hi);
@@ -103,7 +100,7 @@ int try_msr_calibrate_tsc(unsigned long *fast_calibrate)
pr_info("Maximum core-clock to bus-clock ratio: 0x%x\n", ratio);
if (!ratio)
- return 0;
+ goto fail;
/* Get FSB FREQ ID */
rdmsr(MSR_FSB_FREQ, lo, hi);
@@ -112,16 +109,19 @@ int try_msr_calibrate_tsc(unsigned long *fast_calibrate)
pr_info("Resolved frequency ID: %u, frequency: %u KHz\n",
freq_id, freq);
if (!freq)
- return 0;
+ goto fail;
/* TSC frequency = maximum resolved freq * maximum resolved bus ratio */
- *fast_calibrate = freq * ratio;
- pr_info("TSC runs at %lu KHz\n", *fast_calibrate);
+ res = freq * ratio;
+ pr_info("TSC runs at %lu KHz\n", res);
#ifdef CONFIG_X86_LOCAL_APIC
lapic_timer_frequency = (freq * 1000) / HZ;
pr_info("lapic_timer_frequency = %d\n", lapic_timer_frequency);
#endif
+ return res;
- return 1;
+fail:
+ pr_warn("Fast TSC calibration using MSR failed\n");
+ return 0;
}
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e50425d0f5f7..9b531351a587 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2672,6 +2672,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
break;
}
+ drop_large_spte(vcpu, iterator.sptep);
if (!is_shadow_present_pte(*iterator.sptep)) {
u64 base_addr = iterator.addr;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e81df8fce027..2de1bc09a8d4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3002,10 +3002,8 @@ static int cr8_write_interception(struct vcpu_svm *svm)
u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
/* instruction emulation calls kvm_set_cr8() */
r = cr_interception(svm);
- if (irqchip_in_kernel(svm->vcpu.kvm)) {
- clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+ if (irqchip_in_kernel(svm->vcpu.kvm))
return r;
- }
if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
return r;
kvm_run->exit_reason = KVM_EXIT_SET_TPR;
@@ -3567,6 +3565,8 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
return;
+ clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+
if (irr == -1)
return;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a06f101ef64b..392752834751 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6688,7 +6688,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
else if (is_page_fault(intr_info))
return enable_ept;
else if (is_no_device(intr_info) &&
- !(nested_read_cr0(vmcs12) & X86_CR0_TS))
+ !(vmcs12->guest_cr0 & X86_CR0_TS))
return 0;
return vmcs12->exception_bitmap &
(1u << (intr_info & INTR_INFO_VECTOR_MASK));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 39c28f09dfd5..2b8578432d5b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6186,7 +6186,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
frag->len -= len;
}
- if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+ if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
vcpu->mmio_needed = 0;
/* FIXME: return into emulator if single-stepping. */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9d591c895803..a10c8c792161 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1001,6 +1001,12 @@ static int fault_in_kernel_space(unsigned long address)
static inline bool smap_violation(int error_code, struct pt_regs *regs)
{
+ if (!IS_ENABLED(CONFIG_X86_SMAP))
+ return false;
+
+ if (!static_cpu_has(X86_FEATURE_SMAP))
+ return false;
+
if (error_code & PF_USER)
return false;
@@ -1014,13 +1020,17 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs)
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
+ *
+ * This function must have noinline because both callers
+ * {,trace_}do_page_fault() have notrace on. Having this an actual function
+ * guarantees there's a function trace entry.
*/
-static void __kprobes
-__do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes noinline
+__do_page_fault(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
- unsigned long address;
struct mm_struct *mm;
int fault;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -1028,9 +1038,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
tsk = current;
mm = tsk->mm;
- /* Get the faulting address: */
- address = read_cr2();
-
/*
* Detect and handle instructions that would cause a page fault for
* both a tracked kernel page and a userspace page.
@@ -1087,11 +1094,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
- if (static_cpu_has(X86_FEATURE_SMAP)) {
- if (unlikely(smap_violation(error_code, regs))) {
- bad_area_nosemaphore(regs, error_code, address);
- return;
- }
+ if (unlikely(smap_violation(error_code, regs))) {
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
}
/*
@@ -1244,32 +1249,50 @@ good_area:
up_read(&mm->mmap_sem);
}
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
+ unsigned long address = read_cr2(); /* Get the faulting address */
enum ctx_state prev_state;
+ /*
+ * We must have this function tagged with __kprobes, notrace and call
+ * read_cr2() before calling anything else. To avoid calling any kind
+ * of tracing machinery before we've observed the CR2 value.
+ *
+ * exception_{enter,exit}() contain all sorts of tracepoints.
+ */
+
prev_state = exception_enter();
- __do_page_fault(regs, error_code);
+ __do_page_fault(regs, error_code, address);
exception_exit(prev_state);
}
-static void trace_page_fault_entries(struct pt_regs *regs,
+#ifdef CONFIG_TRACING
+static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
unsigned long error_code)
{
if (user_mode(regs))
- trace_page_fault_user(read_cr2(), regs, error_code);
+ trace_page_fault_user(address, regs, error_code);
else
- trace_page_fault_kernel(read_cr2(), regs, error_code);
+ trace_page_fault_kernel(address, regs, error_code);
}
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
+ /*
+ * The exception_enter and tracepoint processing could
+ * trigger another page faults (user space callchain
+ * reading) and destroy the original cr2 value, so read
+ * the faulting address now.
+ */
+ unsigned long address = read_cr2();
enum ctx_state prev_state;
prev_state = exception_enter();
- trace_page_fault_entries(regs, error_code);
- __do_page_fault(regs, error_code);
+ trace_page_fault_entries(address, regs, error_code);
+ __do_page_fault(regs, error_code, address);
exception_exit(prev_state);
}
+#endif /* CONFIG_TRACING */
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 877b9a1b2152..01495755701b 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -140,7 +140,7 @@ bpf_slow_path_byte_msh:
push %r9; \
push SKBDATA; \
/* rsi already has offset */ \
- mov $SIZE,%ecx; /* size */ \
+ mov $SIZE,%edx; /* size */ \
call bpf_internal_load_pointer_neg_helper; \
test %rax,%rax; \
pop SKBDATA; \
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index 4df9591eadad..f15103dff4b4 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -42,7 +42,7 @@ void __init efi_bgrt_init(void)
if (bgrt_tab->header.length < sizeof(*bgrt_tab))
return;
- if (bgrt_tab->version != 1)
+ if (bgrt_tab->version != 1 || bgrt_tab->status != 1)
return;
if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address)
return;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index d62ec87a2b26..b97acecf3fd9 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -52,6 +52,7 @@
#include <asm/tlbflush.h>
#include <asm/x86_init.h>
#include <asm/rtc.h>
+#include <asm/uv/uv.h>
#define EFI_DEBUG
@@ -792,7 +793,7 @@ void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
set_memory_nx(addr, npages);
}
-static void __init runtime_code_page_mkexec(void)
+void __init runtime_code_page_mkexec(void)
{
efi_memory_desc_t *md;
void *p;
@@ -1069,8 +1070,7 @@ void __init efi_enter_virtual_mode(void)
efi.update_capsule = virt_efi_update_capsule;
efi.query_capsule_caps = virt_efi_query_capsule_caps;
- if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
- runtime_code_page_mkexec();
+ efi_runtime_mkexec();
kfree(new_memmap);
@@ -1211,3 +1211,22 @@ static int __init parse_efi_cmdline(char *str)
return 0;
}
early_param("efi", parse_efi_cmdline);
+
+void __init efi_apply_memmap_quirks(void)
+{
+ /*
+ * Once setup is done earlier, unmap the EFI memory map on mismatched
+ * firmware/kernel architectures since there is no support for runtime
+ * services.
+ */
+ if (!efi_is_native()) {
+ pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+ efi_unmap_memmap();
+ }
+
+ /*
+ * UV doesn't support the new EFI pagetable mapping yet.
+ */
+ if (is_uv_system())
+ set_bit(EFI_OLD_MEMMAP, &x86_efi_facility);
+}
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 249b183cf417..0b74cdf7f816 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -77,3 +77,9 @@ void efi_call_phys_epilog(void)
local_irq_restore(efi_rt_eflags);
}
+
+void __init efi_runtime_mkexec(void)
+{
+ if (__supported_pte_mask & _PAGE_NX)
+ runtime_code_page_mkexec();
+}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6284f158a47d..0c2a234fef1e 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -233,3 +233,12 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len)
{
efi_setup = phys_addr + sizeof(struct setup_data);
}
+
+void __init efi_runtime_mkexec(void)
+{
+ if (!efi_enabled(EFI_OLD_MEMMAP))
+ return;
+
+ if (__supported_pte_mask & _PAGE_NX)
+ runtime_code_page_mkexec();
+}
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 7d01b8c56c00..cc04e67bfd05 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -40,11 +40,7 @@
#define smp_rmb() barrier()
#endif /* CONFIG_X86_PPRO_FENCE */
-#ifdef CONFIG_X86_OOSTORE
-#define smp_wmb() wmb()
-#else /* CONFIG_X86_OOSTORE */
#define smp_wmb() barrier()
-#endif /* CONFIG_X86_OOSTORE */
#define smp_read_barrier_depends() read_barrier_depends()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)