aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/acpi.h1
-rw-r--r--arch/x86/include/asm/apic.h2
-rw-r--r--arch/x86/include/asm/desc.h15
-rw-r--r--arch/x86/include/asm/hugetlb.h1
-rw-r--r--arch/x86/include/asm/iommu_table.h11
-rw-r--r--arch/x86/include/asm/kasan.h34
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/include/asm/mmu.h3
-rw-r--r--arch/x86/include/asm/mmu_context.h48
-rw-r--r--arch/x86/include/asm/page_64_types.h12
-rw-r--r--arch/x86/include/asm/paravirt.h6
-rw-r--r--arch/x86/include/asm/perf_event.h8
-rw-r--r--arch/x86/include/asm/pgtable.h5
-rw-r--r--arch/x86/include/asm/processor.h36
-rw-r--r--arch/x86/include/asm/segment.h15
-rw-r--r--arch/x86/include/asm/special_insns.h6
-rw-r--r--arch/x86/include/asm/string_64.h18
-rw-r--r--arch/x86/include/asm/thread_info.h27
-rw-r--r--arch/x86/include/asm/tlbflush.h77
-rw-r--r--arch/x86/include/asm/virtext.h5
-rw-r--r--arch/x86/include/asm/x86_init.h3
-rw-r--r--arch/x86/include/asm/xen/hypervisor.h2
-rw-r--r--arch/x86/include/uapi/asm/msr-index.h6
-rw-r--r--arch/x86/include/uapi/asm/svm.h1
24 files changed, 260 insertions, 84 deletions
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 0ab4f9fd2687..3a45668f6dc3 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -50,6 +50,7 @@ void acpi_pic_sci_set_trigger(unsigned int, u16);
extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
int trigger, int polarity);
+extern void (*__acpi_unregister_gsi)(u32 gsi);
static inline void disable_acpi(void)
{
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 465b309af254..dbaf844ddcb1 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -651,8 +651,8 @@ static inline void entering_irq(void)
static inline void entering_ack_irq(void)
{
- ack_APIC_irq();
entering_irq();
+ ack_APIC_irq();
}
static inline void exiting_irq(void)
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index a94b82e8f156..69126184c609 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -280,21 +280,6 @@ static inline void clear_LDT(void)
set_ldt(NULL, 0);
}
-/*
- * load one particular LDT into the current CPU
- */
-static inline void load_LDT_nolock(mm_context_t *pc)
-{
- set_ldt(pc->ldt, pc->size);
-}
-
-static inline void load_LDT(mm_context_t *pc)
-{
- preempt_disable();
- load_LDT_nolock(pc);
- preempt_enable();
-}
-
static inline unsigned long get_desc_base(const struct desc_struct *desc)
{
return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 68c05398bba9..7aadd3cea843 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -4,6 +4,7 @@
#include <asm/page.h>
#include <asm-generic/hugetlb.h>
+#define hugepages_supported() cpu_has_pse
static inline int is_hugepage_only_range(struct mm_struct *mm,
unsigned long addr,
diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h
index f42a04735a0a..e37d6b3ad983 100644
--- a/arch/x86/include/asm/iommu_table.h
+++ b/arch/x86/include/asm/iommu_table.h
@@ -79,11 +79,12 @@ struct iommu_table_entry {
* d). Similar to the 'init', except that this gets called from pci_iommu_init
* where we do have a memory allocator.
*
- * The standard vs the _FINISH differs in that the _FINISH variant will
- * continue detecting other IOMMUs in the call list after the
- * the detection routine returns a positive number. The _FINISH will
- * stop the execution chain. Both will still call the 'init' and
- * 'late_init' functions if they are set.
+ * The standard IOMMU_INIT differs from the IOMMU_INIT_FINISH variant
+ * in that the former will continue detecting other IOMMUs in the call
+ * list after the detection routine returns a positive number, while the
+ * latter will stop the execution chain upon first successful detection.
+ * Both variants will still call the 'init' and 'late_init' functions if
+ * they are set.
*/
#define IOMMU_INIT_FINISH(_detect, _depend, _init, _late_init) \
__IOMMU_INIT(_detect, _depend, _init, _late_init, 1)
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
new file mode 100644
index 000000000000..491e4fd7754e
--- /dev/null
+++ b/arch/x86/include/asm/kasan.h
@@ -0,0 +1,34 @@
+#ifndef _ASM_X86_KASAN_H
+#define _ASM_X86_KASAN_H
+
+#include <linux/const.h>
+#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+
+/*
+ * Compiler uses shadow offset assuming that addresses start
+ * from 0. Kernel addresses don't start from 0, so shadow
+ * for kernel really starts from compiler's shadow offset +
+ * 'kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT
+ */
+#define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \
+ (0xffff800000000000ULL >> 3))
+/* 47 bits for kernel address -> (47 - 3) bits for shadow */
+#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1ULL << (47 - 3)))
+
+#ifndef __ASSEMBLY__
+
+extern pte_t kasan_zero_pte[];
+extern pte_t kasan_zero_pmd[];
+extern pte_t kasan_zero_pud[];
+
+#ifdef CONFIG_KASAN
+void __init kasan_map_early_shadow(pgd_t *pgd);
+void __init kasan_init(void);
+#else
+static inline void kasan_map_early_shadow(pgd_t *pgd) { }
+static inline void kasan_init(void) { }
+#endif
+
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6c0709ff2f38..306d152336cd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -571,7 +571,7 @@ struct kvm_arch {
struct kvm_pic *vpic;
struct kvm_ioapic *vioapic;
struct kvm_pit *vpit;
- int vapics_in_nmi_mode;
+ atomic_t vapics_in_nmi_mode;
struct mutex apic_map_lock;
struct kvm_apic_map *apic_map;
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 876e74e8eec7..b6b7bc3f5d26 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,8 +9,7 @@
* we put the segment information here.
*/
typedef struct {
- void *ldt;
- int size;
+ struct ldt_struct *ldt;
#ifdef CONFIG_X86_64
/* True if mm supports a task running in 32 bit compatibility mode. */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 166af2a8e865..23e0625a6183 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -20,6 +20,50 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
#endif /* !CONFIG_PARAVIRT */
/*
+ * ldt_structs can be allocated, used, and freed, but they are never
+ * modified while live.
+ */
+struct ldt_struct {
+ /*
+ * Xen requires page-aligned LDTs with special permissions. This is
+ * needed to prevent us from installing evil descriptors such as
+ * call gates. On native, we could merge the ldt_struct and LDT
+ * allocations, but it's not worth trying to optimize.
+ */
+ struct desc_struct *entries;
+ int size;
+};
+
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
+ struct ldt_struct *ldt;
+
+ /* lockless_dereference synchronizes with smp_store_release */
+ ldt = lockless_dereference(mm->context.ldt);
+
+ /*
+ * Any change to mm->context.ldt is followed by an IPI to all
+ * CPUs with the mm active. The LDT will not be freed until
+ * after the IPI is handled by all such CPUs. This means that,
+ * if the ldt_struct changes before we return, the values we see
+ * will be safe, and the new values will be loaded before we run
+ * any user code.
+ *
+ * NB: don't try to convert this to use RCU without extreme care.
+ * We would still need IRQs off, because we don't want to change
+ * the local LDT after an IPI loaded a newer value than the one
+ * that we can see.
+ */
+
+ if (unlikely(ldt))
+ set_ldt(ldt->entries, ldt->size);
+ else
+ clear_LDT();
+
+ DEBUG_LOCKS_WARN_ON(preemptible());
+}
+
+/*
* Used for LDT copy/destruction.
*/
int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
@@ -55,7 +99,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
/* Load the LDT, if the LDT is different: */
if (unlikely(prev->context.ldt != next->context.ldt))
- load_LDT_nolock(&next->context);
+ load_mm_ldt(next);
}
#ifdef CONFIG_SMP
else {
@@ -77,7 +121,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
*/
load_cr3(next->pgd);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
- load_LDT_nolock(&next->context);
+ load_mm_ldt(next);
}
}
#endif
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 75450b2c7be4..4edd53b79a81 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -1,17 +1,23 @@
#ifndef _ASM_X86_PAGE_64_DEFS_H
#define _ASM_X86_PAGE_64_DEFS_H
-#define THREAD_SIZE_ORDER 2
+#ifdef CONFIG_KASAN
+#define KASAN_STACK_ORDER 1
+#else
+#define KASAN_STACK_ORDER 0
+#endif
+
+#define THREAD_SIZE_ORDER (2 + KASAN_STACK_ORDER)
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
#define CURRENT_MASK (~(THREAD_SIZE - 1))
-#define EXCEPTION_STACK_ORDER 0
+#define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER)
#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
-#define IRQ_STACK_ORDER 2
+#define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER)
#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
#define DOUBLEFAULT_STACK 1
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cd6e1610e29e..a9d76e02301b 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -80,16 +80,16 @@ static inline void write_cr3(unsigned long x)
PVOP_VCALL1(pv_mmu_ops.write_cr3, x);
}
-static inline unsigned long read_cr4(void)
+static inline unsigned long __read_cr4(void)
{
return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4);
}
-static inline unsigned long read_cr4_safe(void)
+static inline unsigned long __read_cr4_safe(void)
{
return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe);
}
-static inline void write_cr4(unsigned long x)
+static inline void __write_cr4(unsigned long x)
{
PVOP_VCALL1(pv_cpu_ops.write_cr4, x);
}
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8dfc9fd094a3..024fa1a20f15 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -159,6 +159,14 @@ struct x86_pmu_capability {
*/
#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16)
+#define GLOBAL_STATUS_COND_CHG BIT_ULL(63)
+#define GLOBAL_STATUS_BUFFER_OVF BIT_ULL(62)
+#define GLOBAL_STATUS_UNC_OVF BIT_ULL(61)
+#define GLOBAL_STATUS_ASIF BIT_ULL(60)
+#define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59)
+#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58)
+#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55)
+
/*
* IBS cpuid feature detection
*/
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index aa97a070f09f..081d6f45e006 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -99,6 +99,11 @@ static inline int pte_young(pte_t pte)
return pte_flags(pte) & _PAGE_ACCESSED;
}
+static inline int pmd_dirty(pmd_t pmd)
+{
+ return pmd_flags(pmd) & _PAGE_DIRTY;
+}
+
static inline int pmd_young(pmd_t pmd)
{
return pmd_flags(pmd) & _PAGE_ACCESSED;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index eb71ec794732..26d5e05a7def 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -578,39 +578,6 @@ static inline void load_sp0(struct tss_struct *tss,
#define set_iopl_mask native_set_iopl_mask
#endif /* CONFIG_PARAVIRT */
-/*
- * Save the cr4 feature set we're using (ie
- * Pentium 4MB enable and PPro Global page
- * enable), so that any CPU's that boot up
- * after us can get the correct flags.
- */
-extern unsigned long mmu_cr4_features;
-extern u32 *trampoline_cr4_features;
-
-static inline void set_in_cr4(unsigned long mask)
-{
- unsigned long cr4;
-
- mmu_cr4_features |= mask;
- if (trampoline_cr4_features)
- *trampoline_cr4_features = mmu_cr4_features;
- cr4 = read_cr4();
- cr4 |= mask;
- write_cr4(cr4);
-}
-
-static inline void clear_in_cr4(unsigned long mask)
-{
- unsigned long cr4;
-
- mmu_cr4_features &= ~mask;
- if (trampoline_cr4_features)
- *trampoline_cr4_features = mmu_cr4_features;
- cr4 = read_cr4();
- cr4 &= ~mask;
- write_cr4(cr4);
-}
-
typedef struct {
unsigned long seg;
} mm_segment_t;
@@ -885,7 +852,8 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
#define task_pt_regs(task) \
({ \
struct pt_regs *__regs__; \
- __regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task))-8); \
+ __regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task)) - \
+ TOP_OF_KERNEL_STACK_PADDING); \
__regs__ - 1; \
})
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 6f1c3a8a33ab..bcc9a2f46c62 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -212,10 +212,21 @@
#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8)
#ifdef __KERNEL__
+
+/*
+ * early_idt_handler_array is an array of entry points referenced in the
+ * early IDT. For simplicity, it's a real array with one entry point
+ * every nine bytes. That leaves room for an optional 'push $0' if the
+ * vector has no error code (two bytes), a 'push $vector_number' (two
+ * bytes), and a jump to the common entry code (up to five bytes).
+ */
+#define EARLY_IDT_HANDLER_SIZE 9
+
#ifndef __ASSEMBLY__
-extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5];
+
+extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
#ifdef CONFIG_TRACING
-#define trace_early_idt_handlers early_idt_handlers
+# define trace_early_idt_handler_array early_idt_handler_array
#endif
/*
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index e820c080a4e9..6a4b00fafb00 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -137,17 +137,17 @@ static inline void write_cr3(unsigned long x)
native_write_cr3(x);
}
-static inline unsigned long read_cr4(void)
+static inline unsigned long __read_cr4(void)
{
return native_read_cr4();
}
-static inline unsigned long read_cr4_safe(void)
+static inline unsigned long __read_cr4_safe(void)
{
return native_read_cr4_safe();
}
-static inline void write_cr4(unsigned long x)
+static inline void __write_cr4(unsigned long x)
{
native_write_cr4(x);
}
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 19e2c468fc2c..e4661196994e 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -27,11 +27,12 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t
function. */
#define __HAVE_ARCH_MEMCPY 1
+extern void *__memcpy(void *to, const void *from, size_t len);
+
#ifndef CONFIG_KMEMCHECK
#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
extern void *memcpy(void *to, const void *from, size_t len);
#else
-extern void *__memcpy(void *to, const void *from, size_t len);
#define memcpy(dst, src, len) \
({ \
size_t __len = (len); \
@@ -53,9 +54,11 @@ extern void *__memcpy(void *to, const void *from, size_t len);
#define __HAVE_ARCH_MEMSET
void *memset(void *s, int c, size_t n);
+void *__memset(void *s, int c, size_t n);
#define __HAVE_ARCH_MEMMOVE
void *memmove(void *dest, const void *src, size_t count);
+void *__memmove(void *dest, const void *src, size_t count);
int memcmp(const void *cs, const void *ct, size_t count);
size_t strlen(const char *s);
@@ -63,6 +66,19 @@ char *strcpy(char *dest, const char *src);
char *strcat(char *dest, const char *src);
int strcmp(const char *cs, const char *ct);
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+
+/*
+ * For files that not instrumented (e.g. mm/slub.c) we
+ * should use not instrumented version of mem* functions.
+ */
+
+#undef memcpy
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+#endif
+
#endif /* __KERNEL__ */
#endif /* _ASM_X86_STRING_64_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 223b9f0d463f..766fa5cc15b4 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -13,6 +13,33 @@
#include <asm/types.h>
/*
+ * TOP_OF_KERNEL_STACK_PADDING is a number of unused bytes that we
+ * reserve at the top of the kernel stack. We do it because of a nasty
+ * 32-bit corner case. On x86_32, the hardware stack frame is
+ * variable-length. Except for vm86 mode, struct pt_regs assumes a
+ * maximum-length frame. If we enter from CPL 0, the top 8 bytes of
+ * pt_regs don't actually exist. Ordinarily this doesn't matter, but it
+ * does in at least one case:
+ *
+ * If we take an NMI early enough in SYSENTER, then we can end up with
+ * pt_regs that extends above sp0. On the way out, in the espfix code,
+ * we can read the saved SS value, but that value will be above sp0.
+ * Without this offset, that can result in a page fault. (We are
+ * careful that, in this case, the value we read doesn't matter.)
+ *
+ * In vm86 mode, the hardware frame is much longer still, but we neither
+ * access the extra members from NMI context, nor do we write such a
+ * frame at sp0 at all.
+ *
+ * x86_64 has a fixed-length stack frame.
+ */
+#ifdef CONFIG_X86_32
+# define TOP_OF_KERNEL_STACK_PADDING 8
+#else
+# define TOP_OF_KERNEL_STACK_PADDING 0
+#endif
+
+/*
* low level task data that entry.S needs immediate access to
* - this struct should fit entirely inside of one cache line
* - this struct shares the supervisor stack pages
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 04905bfc508b..cd791948b286 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -15,6 +15,75 @@
#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
#endif
+struct tlb_state {
+#ifdef CONFIG_SMP
+ struct mm_struct *active_mm;
+ int state;
+#endif
+
+ /*
+ * Access to this CR4 shadow and to H/W CR4 is protected by
+ * disabling interrupts when modifying either one.
+ */
+ unsigned long cr4;
+};
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
+
+/* Initialize cr4 shadow for this CPU. */
+static inline void cr4_init_shadow(void)
+{
+ this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
+}
+
+/* Set in this cpu's CR4. */
+static inline void cr4_set_bits(unsigned long mask)
+{
+ unsigned long cr4;
+
+ cr4 = this_cpu_read(cpu_tlbstate.cr4);
+ if ((cr4 | mask) != cr4) {
+ cr4 |= mask;
+ this_cpu_write(cpu_tlbstate.cr4, cr4);
+ __write_cr4(cr4);
+ }
+}
+
+/* Clear in this cpu's CR4. */
+static inline void cr4_clear_bits(unsigned long mask)
+{
+ unsigned long cr4;
+
+ cr4 = this_cpu_read(cpu_tlbstate.cr4);
+ if ((cr4 & ~mask) != cr4) {
+ cr4 &= ~mask;
+ this_cpu_write(cpu_tlbstate.cr4, cr4);
+ __write_cr4(cr4);
+ }
+}
+
+/* Read the CR4 shadow. */
+static inline unsigned long cr4_read_shadow(void)
+{
+ return this_cpu_read(cpu_tlbstate.cr4);
+}
+
+/*
+ * Save some of cr4 feature set we're using (e.g. Pentium 4MB
+ * enable and PPro Global page enable), so that any CPU's that boot
+ * up after us can get the correct flags. This should only be used
+ * during boot on the boot cpu.
+ */
+extern unsigned long mmu_cr4_features;
+extern u32 *trampoline_cr4_features;
+
+static inline void cr4_set_bits_and_update_boot(unsigned long mask)
+{
+ mmu_cr4_features |= mask;
+ if (trampoline_cr4_features)
+ *trampoline_cr4_features = mmu_cr4_features;
+ cr4_set_bits(mask);
+}
+
static inline void __native_flush_tlb(void)
{
native_write_cr3(native_read_cr3());
@@ -24,7 +93,7 @@ static inline void __native_flush_tlb_global_irq_disabled(void)
{
unsigned long cr4;
- cr4 = native_read_cr4();
+ cr4 = this_cpu_read(cpu_tlbstate.cr4);
/* clear PGE */
native_write_cr4(cr4 & ~X86_CR4_PGE);
/* write old PGE again and flush TLBs */
@@ -184,12 +253,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
#define TLBSTATE_OK 1
#define TLBSTATE_LAZY 2
-struct tlb_state {
- struct mm_struct *active_mm;
- int state;
-};
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
-
static inline void reset_lazy_tlbstate(void)
{
this_cpu_write(cpu_tlbstate.state, 0);
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 5da71c27cc59..cce9ee68e335 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -19,6 +19,7 @@
#include <asm/vmx.h>
#include <asm/svm.h>
+#include <asm/tlbflush.h>
/*
* VMX functions:
@@ -40,12 +41,12 @@ static inline int cpu_has_vmx(void)
static inline void cpu_vmxoff(void)
{
asm volatile (ASM_VMX_VMXOFF : : : "cc");
- write_cr4(read_cr4() & ~X86_CR4_VMXE);
+ cr4_clear_bits(X86_CR4_VMXE);
}
static inline int cpu_vmx_enabled(void)
{
- return read_cr4() & X86_CR4_VMXE;
+ return __read_cr4() & X86_CR4_VMXE;
}
/** Disable VMX if it is enabled on the current CPU
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index e45e4da96bf1..f58a9c7a3c86 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -172,7 +172,6 @@ struct x86_platform_ops {
struct pci_dev;
struct msi_msg;
-struct msi_desc;
struct x86_msi_ops {
int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
@@ -183,8 +182,6 @@ struct x86_msi_ops {
void (*teardown_msi_irqs)(struct pci_dev *dev);
void (*restore_msi_irqs)(struct pci_dev *dev);
int (*setup_hpet_msi)(unsigned int irq, unsigned int id);
- u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag);
- u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag);
};
struct IO_APIC_route_entry;
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index d866959e5685..d2ad00a42234 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -57,4 +57,6 @@ static inline bool xen_x2apic_para_available(void)
}
#endif
+extern void xen_set_iopl_mask(unsigned mask);
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index e21331ce368f..177889cd0505 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -69,6 +69,12 @@
#define MSR_LBR_CORE_FROM 0x00000040
#define MSR_LBR_CORE_TO 0x00000060
+#define MSR_LBR_INFO_0 0x00000dc0 /* ... 0xddf for _31 */
+#define LBR_INFO_MISPRED BIT_ULL(63)
+#define LBR_INFO_IN_TX BIT_ULL(62)
+#define LBR_INFO_ABORT BIT_ULL(61)
+#define LBR_INFO_CYCLES 0xffff
+
#define MSR_IA32_PEBS_ENABLE 0x000003f1
#define MSR_IA32_DS_AREA 0x00000600
#define MSR_IA32_PERF_CAPABILITIES 0x00000345
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index b5d7640abc5d..8a4add8e4639 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -100,6 +100,7 @@
{ SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \
{ SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \
{ SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \
+ { SVM_EXIT_EXCP_BASE + AC_VECTOR, "AC excp" }, \
{ SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \
{ SVM_EXIT_INTR, "interrupt" }, \
{ SVM_EXIT_NMI, "nmi" }, \