summaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/apic.h2
-rw-r--r--arch/x86/include/asm/arch_hweight.h13
-rw-r--r--arch/x86/include/asm/barrier.h11
-rw-r--r--arch/x86/include/asm/context_tracking.h10
-rw-r--r--arch/x86/include/asm/cpufeature.h1
-rw-r--r--arch/x86/include/asm/delay.h1
-rw-r--r--arch/x86/include/asm/desc.h15
-rw-r--r--arch/x86/include/asm/elf.h17
-rw-r--r--arch/x86/include/asm/ia32.h9
-rw-r--r--arch/x86/include/asm/irq_vectors.h10
-rw-r--r--arch/x86/include/asm/kasan.h3
-rw-r--r--arch/x86/include/asm/kvm_host.h43
-rw-r--r--arch/x86/include/asm/math_emu.h6
-rw-r--r--arch/x86/include/asm/mce.h8
-rw-r--r--arch/x86/include/asm/mmu.h5
-rw-r--r--arch/x86/include/asm/mmu_context.h68
-rw-r--r--arch/x86/include/asm/mshyperv.h5
-rw-r--r--arch/x86/include/asm/msr-index.h14
-rw-r--r--arch/x86/include/asm/msr.h70
-rw-r--r--arch/x86/include/asm/mwait.h45
-rw-r--r--arch/x86/include/asm/paravirt.h40
-rw-r--r--arch/x86/include/asm/paravirt_types.h2
-rw-r--r--arch/x86/include/asm/pci_x86.h2
-rw-r--r--arch/x86/include/asm/perf_event.h7
-rw-r--r--arch/x86/include/asm/preempt.h4
-rw-r--r--arch/x86/include/asm/processor.h21
-rw-r--r--arch/x86/include/asm/ptrace.h1
-rw-r--r--arch/x86/include/asm/pvclock.h10
-rw-r--r--arch/x86/include/asm/sigcontext.h6
-rw-r--r--arch/x86/include/asm/sigframe.h10
-rw-r--r--arch/x86/include/asm/signal.h2
-rw-r--r--arch/x86/include/asm/stackprotector.h2
-rw-r--r--arch/x86/include/asm/switch_to.h12
-rw-r--r--arch/x86/include/asm/syscalls.h1
-rw-r--r--arch/x86/include/asm/thread_info.h27
-rw-r--r--arch/x86/include/asm/traps.h4
-rw-r--r--arch/x86/include/asm/tsc.h19
-rw-r--r--arch/x86/include/asm/vm86.h57
-rw-r--r--arch/x86/include/asm/vmx.h47
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h2
-rw-r--r--arch/x86/include/uapi/asm/hyperv.h2
-rw-r--r--arch/x86/include/uapi/asm/kvm.h4
-rw-r--r--arch/x86/include/uapi/asm/mce.h3
-rw-r--r--arch/x86/include/uapi/asm/processor-flags.h2
-rw-r--r--arch/x86/include/uapi/asm/sigcontext.h21
-rw-r--r--arch/x86/include/uapi/asm/vmx.h2
46 files changed, 354 insertions, 312 deletions
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index c8393634ca0c..ebf6d5e5668c 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -313,7 +313,6 @@ struct apic {
/* wakeup_secondary_cpu */
int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
- bool wait_for_init_deassert;
void (*inquire_remote_apic)(int apicid);
/* apic ops */
@@ -378,7 +377,6 @@ extern struct apic *__apicdrivers[], *__apicdrivers_end[];
* APIC functionality to boot other CPUs - only used on SMP:
*/
#ifdef CONFIG_SMP
-extern atomic_t init_deasserted;
extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
#endif
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index 9686c3d9ff73..259a7c1ef709 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -21,7 +21,7 @@
* ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective
* compiler switches.
*/
-static inline unsigned int __arch_hweight32(unsigned int w)
+static __always_inline unsigned int __arch_hweight32(unsigned int w)
{
unsigned int res = 0;
@@ -42,20 +42,23 @@ static inline unsigned int __arch_hweight8(unsigned int w)
return __arch_hweight32(w & 0xff);
}
+#ifdef CONFIG_X86_32
static inline unsigned long __arch_hweight64(__u64 w)
{
- unsigned long res = 0;
-
-#ifdef CONFIG_X86_32
return __arch_hweight32((u32)w) +
__arch_hweight32((u32)(w >> 32));
+}
#else
+static __always_inline unsigned long __arch_hweight64(__u64 w)
+{
+ unsigned long res = 0;
+
asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT)
: "="REG_OUT (res)
: REG_IN (w));
-#endif /* CONFIG_X86_32 */
return res;
}
+#endif /* CONFIG_X86_32 */
#endif
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index e51a8f803f55..818cb8788225 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -91,15 +91,4 @@ do { \
#define smp_mb__before_atomic() barrier()
#define smp_mb__after_atomic() barrier()
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- */
-static __always_inline void rdtsc_barrier(void)
-{
- alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC,
- "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
#endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/context_tracking.h b/arch/x86/include/asm/context_tracking.h
deleted file mode 100644
index 1fe49704b146..000000000000
--- a/arch/x86/include/asm/context_tracking.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _ASM_X86_CONTEXT_TRACKING_H
-#define _ASM_X86_CONTEXT_TRACKING_H
-
-#ifdef CONFIG_CONTEXT_TRACKING
-# define SCHEDULE_USER call schedule_user
-#else
-# define SCHEDULE_USER call schedule
-#endif
-
-#endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 4b11974b4ea7..477fc28050e4 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -177,6 +177,7 @@
#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */
#define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */
#define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
/*
* Auxiliary flags: Linux defined - For features scattered in various
diff --git a/arch/x86/include/asm/delay.h b/arch/x86/include/asm/delay.h
index 9b3b4f2754c7..36a760bda462 100644
--- a/arch/x86/include/asm/delay.h
+++ b/arch/x86/include/asm/delay.h
@@ -4,5 +4,6 @@
#include <asm-generic/delay.h>
void use_tsc_delay(void);
+void use_mwaitx_delay(void);
#endif /* _ASM_X86_DELAY_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index a0bf89fd2647..4e10d73cf018 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/elf.h b/arch/x86/include/asm/elf.h
index f161c189c27b..141c561f4664 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -78,7 +78,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t;
#ifdef CONFIG_X86_64
extern unsigned int vdso64_enabled;
#endif
-#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
extern unsigned int vdso32_enabled;
#endif
@@ -187,8 +187,8 @@ static inline void elf_common_init(struct thread_struct *t,
#define COMPAT_ELF_PLAT_INIT(regs, load_addr) \
elf_common_init(&current->thread, regs, __USER_DS)
-void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp);
-#define compat_start_thread start_thread_ia32
+void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp);
+#define compat_start_thread compat_start_thread
void set_personality_ia32(bool);
#define COMPAT_SET_PERSONALITY(ex) \
@@ -344,14 +344,9 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
*/
static inline int mmap_is_ia32(void)
{
-#ifdef CONFIG_X86_32
- return 1;
-#endif
-#ifdef CONFIG_IA32_EMULATION
- if (test_thread_flag(TIF_ADDR32))
- return 1;
-#endif
- return 0;
+ return config_enabled(CONFIG_X86_32) ||
+ (config_enabled(CONFIG_COMPAT) &&
+ test_thread_flag(TIF_ADDR32));
}
/* Do not change the values. See get_align_mask() */
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index d0e8e0141041..28019765442e 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -22,15 +22,6 @@ struct ucontext_ia32 {
compat_sigset_t uc_sigmask; /* mask last for extensibility */
};
-struct ucontext_x32 {
- unsigned int uc_flags;
- unsigned int uc_link;
- compat_stack_t uc_stack;
- unsigned int uc__pad0; /* needed for alignment */
- struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */
- compat_sigset_t uc_sigmask; /* mask last for extensibility */
-};
-
/* This matches struct stat64 in glibc2.2, hence the absolutely
* insane amounts of padding around dev_t's.
*/
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 4c2d2eb2060a..6ca9fd6234e1 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -117,16 +117,6 @@
#define FPU_IRQ 13
-#define FIRST_VM86_IRQ 3
-#define LAST_VM86_IRQ 15
-
-#ifndef __ASSEMBLY__
-static inline int invalid_vm86_irq(int irq)
-{
- return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ;
-}
-#endif
-
/*
* Size the maximum number of interrupts.
*
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index 74a2a8dc9908..1410b567ecde 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -1,6 +1,9 @@
#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
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 49ec9038ec14..c12e845f59e6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -252,6 +252,11 @@ struct kvm_pio_request {
int size;
};
+struct rsvd_bits_validate {
+ u64 rsvd_bits_mask[2][4];
+ u64 bad_mt_xwr;
+};
+
/*
* x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
* 32-bit). The kvm_mmu structure abstracts the details of the current mmu
@@ -289,8 +294,15 @@ struct kvm_mmu {
u64 *pae_root;
u64 *lm_root;
- u64 rsvd_bits_mask[2][4];
- u64 bad_mt_xwr;
+
+ /*
+ * check zero bits on shadow page table entries, these
+ * bits include not only hardware reserved bits but also
+ * the bits spte never used.
+ */
+ struct rsvd_bits_validate shadow_zero_check;
+
+ struct rsvd_bits_validate guest_rsvd_check;
/*
* Bitmap: bit set = last pte in walk
@@ -358,6 +370,11 @@ struct kvm_mtrr {
struct list_head head;
};
+/* Hyper-V per vcpu emulation context */
+struct kvm_vcpu_hv {
+ u64 hv_vapic;
+};
+
struct kvm_vcpu_arch {
/*
* rip and regs accesses must go through
@@ -514,8 +531,7 @@ struct kvm_vcpu_arch {
/* used for guest single stepping over the given code position */
unsigned long singlestep_rip;
- /* fields used by HYPER-V emulation */
- u64 hv_vapic;
+ struct kvm_vcpu_hv hyperv;
cpumask_var_t wbinvd_dirty_mask;
@@ -586,6 +602,17 @@ struct kvm_apic_map {
struct kvm_lapic *logical_map[16][16];
};
+/* Hyper-V emulation context */
+struct kvm_hv {
+ u64 hv_guest_os_id;
+ u64 hv_hypercall;
+ u64 hv_tsc_page;
+
+ /* Hyper-v based guest crash (NT kernel bugcheck) parameters */
+ u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
+ u64 hv_crash_ctl;
+};
+
struct kvm_arch {
unsigned int n_used_mmu_pages;
unsigned int n_requested_mmu_pages;
@@ -645,16 +672,14 @@ struct kvm_arch {
/* reads protected by irq_srcu, writes by irq_lock */
struct hlist_head mask_notifier_list;
- /* fields used by HYPER-V emulation */
- u64 hv_guest_os_id;
- u64 hv_hypercall;
- u64 hv_tsc_page;
+ struct kvm_hv hyperv;
#ifdef CONFIG_KVM_MMU_AUDIT
int audit_point;
#endif
bool boot_vcpu_runs_old_kvmclock;
+ u32 bsp_vcpu_id;
u64 disabled_quirks;
};
@@ -1203,5 +1228,7 @@ int __x86_set_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem);
int x86_set_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem);
+bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
+bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h
index 031f6266f425..0d9b14f60d2c 100644
--- a/arch/x86/include/asm/math_emu.h
+++ b/arch/x86/include/asm/math_emu.h
@@ -2,7 +2,6 @@
#define _ASM_X86_MATH_EMU_H
#include <asm/ptrace.h>
-#include <asm/vm86.h>
/* This structure matches the layout of the data saved to the stack
following a device-not-present interrupt, part of it saved
@@ -10,9 +9,6 @@
*/
struct math_emu_info {
long ___orig_eip;
- union {
- struct pt_regs *regs;
- struct kernel_vm86_regs *vm86;
- };
+ struct pt_regs *regs;
};
#endif /* _ASM_X86_MATH_EMU_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 982dfc3679ad..2dbc0bf2b9f3 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -151,10 +151,12 @@ extern int mce_p5_enabled;
#ifdef CONFIG_X86_MCE
int mcheck_init(void);
void mcheck_cpu_init(struct cpuinfo_x86 *c);
+void mcheck_cpu_clear(struct cpuinfo_x86 *c);
void mcheck_vendor_init_severity(void);
#else
static inline int mcheck_init(void) { return 0; }
static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {}
+static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {}
static inline void mcheck_vendor_init_severity(void) {}
#endif
@@ -181,20 +183,18 @@ DECLARE_PER_CPU(struct device *, mce_device);
#ifdef CONFIG_X86_MCE_INTEL
void mce_intel_feature_init(struct cpuinfo_x86 *c);
+void mce_intel_feature_clear(struct cpuinfo_x86 *c);
void cmci_clear(void);
void cmci_reenable(void);
void cmci_rediscover(void);
void cmci_recheck(void);
-void lmce_clear(void);
-void lmce_enable(void);
#else
static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
+static inline void mce_intel_feature_clear(struct cpuinfo_x86 *c) { }
static inline void cmci_clear(void) {}
static inline void cmci_reenable(void) {}
static inline void cmci_rediscover(void) {}
static inline void cmci_recheck(void) {}
-static inline void lmce_clear(void) {}
-static inline void lmce_enable(void) {}
#endif
#ifdef CONFIG_X86_MCE_AMD
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 09b9620a73b4..55234d5e7160 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,8 +9,9 @@
* we put the segment information here.
*/
typedef struct {
- void *ldt;
- int size;
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ struct ldt_struct *ldt;
+#endif
#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 804a3a6030ca..379cd3658799 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -33,12 +33,68 @@ static inline void load_mm_cr4(struct mm_struct *mm)
static inline void load_mm_cr4(struct mm_struct *mm) {}
#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+/*
+ * 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;
+};
+
/*
* Used for LDT copy/destruction.
*/
int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
void destroy_context(struct mm_struct *mm);
+#else /* CONFIG_MODIFY_LDT_SYSCALL */
+static inline int init_new_context(struct task_struct *tsk,
+ struct mm_struct *mm)
+{
+ return 0;
+}
+static inline void destroy_context(struct mm_struct *mm) {}
+#endif
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ 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();
+#else
+ clear_LDT();
+#endif
+
+ DEBUG_LOCKS_WARN_ON(preemptible());
+}
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
@@ -70,6 +126,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
/* Load per-mm CR4 state */
load_mm_cr4(next);
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
/*
* Load the LDT, if the LDT is different.
*
@@ -78,12 +135,13 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
* was called and then modify_ldt changed
* prev->context.ldt but suppressed an IPI to this CPU.
* In this case, prev->context.ldt != NULL, because we
- * never free an LDT while the mm still exists. That
- * means that next->context.ldt != prev->context.ldt,
- * because mms never share an LDT.
+ * never set context.ldt to NULL while the mm still
+ * exists. That means that next->context.ldt !=
+ * prev->context.ldt, because mms never share an LDT.
*/
if (unlikely(prev->context.ldt != next->context.ldt))
- load_LDT_nolock(&next->context);
+ load_mm_ldt(next);
+#endif
}
#ifdef CONFIG_SMP
else {
@@ -106,7 +164,7 @@ 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_mm_cr4(next);
- load_LDT_nolock(&next->context);
+ load_mm_ldt(next);
}
}
#endif
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index c163215abb9a..aaf59b7da98a 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -7,6 +7,7 @@
struct ms_hyperv_info {
u32 features;
+ u32 misc_features;
u32 hints;
};
@@ -20,4 +21,8 @@ void hyperv_vector_handler(struct pt_regs *regs);
void hv_setup_vmbus_irq(void (*handler)(void));
void hv_remove_vmbus_irq(void);
+void hv_setup_kexec_handler(void (*handler)(void));
+void hv_remove_kexec_handler(void);
+void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
+void hv_remove_crash_handler(void);
#endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 9ebc3d009373..fcd17c1fc0c6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -73,6 +73,12 @@
#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
@@ -80,13 +86,21 @@
#define MSR_IA32_RTIT_CTL 0x00000570
#define RTIT_CTL_TRACEEN BIT(0)
+#define RTIT_CTL_CYCLEACC BIT(1)
#define RTIT_CTL_OS BIT(2)
#define RTIT_CTL_USR BIT(3)
#define RTIT_CTL_CR3EN BIT(7)
#define RTIT_CTL_TOPA BIT(8)
+#define RTIT_CTL_MTC_EN BIT(9)
#define RTIT_CTL_TSC_EN BIT(10)
#define RTIT_CTL_DISRETC BIT(11)
#define RTIT_CTL_BRANCH_EN BIT(13)
+#define RTIT_CTL_MTC_RANGE_OFFSET 14
+#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
+#define RTIT_CTL_CYC_THRESH_OFFSET 19
+#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET)
+#define RTIT_CTL_PSB_FREQ_OFFSET 24
+#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET)
#define MSR_IA32_RTIT_STATUS 0x00000571
#define RTIT_STATUS_CONTEXTEN BIT(1)
#define RTIT_STATUS_TRIGGEREN BIT(2)
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index e6a707eb5081..77d8b284e4a7 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -47,14 +47,13 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
* it means rax *or* rdx.
*/
#ifdef CONFIG_X86_64
-#define DECLARE_ARGS(val, low, high) unsigned low, high
-#define EAX_EDX_VAL(val, low, high) ((low) | ((u64)(high) << 32))
-#define EAX_EDX_ARGS(val, low, high) "a" (low), "d" (high)
+/* Using 64-bit values saves one instruction clearing the high half of low */
+#define DECLARE_ARGS(val, low, high) unsigned long low, high
+#define EAX_EDX_VAL(val, low, high) ((low) | (high) << 32)
#define EAX_EDX_RET(val, low, high) "=a" (low), "=d" (high)
#else
#define DECLARE_ARGS(val, low, high) unsigned long long val
#define EAX_EDX_VAL(val, low, high) (val)
-#define EAX_EDX_ARGS(val, low, high) "A" (val)
#define EAX_EDX_RET(val, low, high) "=A" (val)
#endif
@@ -106,12 +105,19 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
return err;
}
-extern unsigned long long native_read_tsc(void);
-
extern int rdmsr_safe_regs(u32 regs[8]);
extern int wrmsr_safe_regs(u32 regs[8]);
-static __always_inline unsigned long long __native_read_tsc(void)
+/**
+ * rdtsc() - returns the current TSC without ordering constraints
+ *
+ * rdtsc() returns the result of RDTSC as a 64-bit integer. The
+ * only ordering constraint it supplies is the ordering implied by
+ * "asm volatile": it will put the RDTSC in the place you expect. The
+ * CPU can and will speculatively execute that RDTSC, though, so the
+ * results can be non-monotonic if compared on different CPUs.
+ */
+static __always_inline unsigned long long rdtsc(void)
{
DECLARE_ARGS(val, low, high);
@@ -120,6 +126,35 @@ static __always_inline unsigned long long __native_read_tsc(void)
return EAX_EDX_VAL(val, low, high);
}
+/**
+ * rdtsc_ordered() - read the current TSC in program order
+ *
+ * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer.
+ * It is ordered like a load to a global in-memory counter. It should
+ * be impossible to observe non-monotonic rdtsc_unordered() behavior
+ * across multiple CPUs as long as the TSC is synced.
+ */
+static __always_inline unsigned long long rdtsc_ordered(void)
+{
+ /*
+ * The RDTSC instruction is not ordered relative to memory
+ * access. The Intel SDM and the AMD APM are both vague on this
+ * point, but empirically an RDTSC instruction can be
+ * speculatively executed before prior loads. An RDTSC
+ * immediately after an appropriate barrier appears to be
+ * ordered as a normal load, that is, it provides the same
+ * ordering guarantees as reading from a global memory location
+ * that some other imaginary CPU is updating continuously with a
+ * time stamp.
+ */
+ alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC,
+ "lfence", X86_FEATURE_LFENCE_RDTSC);
+ return rdtsc();
+}
+
+/* Deprecated, keep it for a cycle for easier merging: */
+#define rdtscll(now) do { (now) = rdtsc_ordered(); } while (0)
+
static inline unsigned long long native_read_pmc(int counter)
{
DECLARE_ARGS(val, low, high);
@@ -153,8 +188,10 @@ static inline void wrmsr(unsigned msr, unsigned low, unsigned high)
#define rdmsrl(msr, val) \
((val) = native_read_msr((msr)))
-#define wrmsrl(msr, val) \
- native_write_msr((msr), (u32)((u64)(val)), (u32)((u64)(val) >> 32))
+static inline void wrmsrl(unsigned msr, u64 val)
+{
+ native_write_msr(msr, (u32)val, (u32)(val >> 32));
+}
/* wrmsr with exception handling */
static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high)
@@ -180,12 +217,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
return err;
}
-#define rdtscl(low) \
- ((low) = (u32)__native_read_tsc())
-
-#define rdtscll(val) \
- ((val) = __native_read_tsc())
-
#define rdpmc(counter, low, high) \
do { \
u64 _l = native_read_pmc((counter)); \
@@ -195,15 +226,6 @@ do { \
#define rdpmcl(counter, val) ((val) = native_read_pmc(counter))
-#define rdtscp(low, high, aux) \
-do { \
- unsigned long long _val = native_read_tscp(&(aux)); \
- (low) = (u32)_val; \
- (high) = (u32)(_val >> 32); \
-} while (0)
-
-#define rdtscpll(val, aux) (val) = native_read_tscp(&(aux))
-
#endif /* !CONFIG_PARAVIRT */
/*
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 653dfa7662e1..c70689b5e5aa 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -14,6 +14,9 @@
#define CPUID5_ECX_INTERRUPT_BREAK 0x2
#define MWAIT_ECX_INTERRUPT_BREAK 0x1
+#define MWAITX_ECX_TIMER_ENABLE BIT(1)
+#define MWAITX_MAX_LOOPS ((u32)-1)
+#define MWAITX_DISABLE_CSTATES 0xf
static inline void __monitor(const void *eax, unsigned long ecx,
unsigned long edx)
@@ -23,6 +26,14 @@ static inline void __monitor(const void *eax, unsigned long ecx,
:: "a" (eax), "c" (ecx), "d"(edx));
}
+static inline void __monitorx(const void *eax, unsigned long ecx,
+ unsigned long edx)
+{
+ /* "monitorx %eax, %ecx, %edx;" */
+ asm volatile(".byte 0x0f, 0x01, 0xfa;"
+ :: "a" (eax), "c" (ecx), "d"(edx));
+}
+
static inline void __mwait(unsigned long eax, unsigned long ecx)
{
/* "mwait %eax, %ecx;" */
@@ -30,6 +41,40 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
:: "a" (eax), "c" (ecx));
}
+/*
+ * MWAITX allows for a timer expiration to get the core out a wait state in
+ * addition to the default MWAIT exit condition of a store appearing at a
+ * monitored virtual address.
+ *
+ * Registers:
+ *
+ * MWAITX ECX[1]: enable timer if set
+ * MWAITX EBX[31:0]: max wait time expressed in SW P0 clocks. The software P0
+ * frequency is the same as the TSC frequency.
+ *
+ * Below is a comparison between MWAIT and MWAITX on AMD processors:
+ *
+ * MWAIT MWAITX
+ * opcode 0f 01 c9 | 0f 01 fb
+ * ECX[0] value of RFLAGS.IF seen by instruction
+ * ECX[1] unused/#GP if set | enable timer if set
+ * ECX[31:2] unused/#GP if set
+ * EAX unused (reserve for hint)
+ * EBX[31:0] unused | max wait time (P0 clocks)
+ *
+ * MONITOR MONITORX
+ * opcode 0f 01 c8 | 0f 01 fa
+ * EAX (logical) address to monitor
+ * ECX #GP if not zero
+ */
+static inline void __mwaitx(unsigned long eax, unsigned long ebx,
+ unsigned long ecx)
+{
+ /* "mwaitx %eax, %ebx, %ecx;" */
+ asm volatile(".byte 0x0f, 0x01, 0xfb;"
+ :: "a" (eax), "b" (ebx), "c" (ecx));
+}
+
static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
{
trace_hardirqs_on();
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index d143bfad45d7..10d0596433f8 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -153,7 +153,11 @@ do { \
val = paravirt_read_msr(msr, &_err); \
} while (0)
-#define wrmsrl(msr, val) wrmsr(msr, (u32)((u64)(val)), ((u64)(val))>>32)
+static inline void wrmsrl(unsigned msr, u64 val)
+{
+ wrmsr(msr, (u32)val, (u32)(val>>32));
+}
+
#define wrmsr_safe(msr, a, b) paravirt_write_msr(msr, a, b)
/* rdmsr with exception handling */
@@ -174,19 +178,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
return err;
}
-static inline u64 paravirt_read_tsc(void)
-{
- return PVOP_CALL0(u64, pv_cpu_ops.read_tsc);
-}
-
-#define rdtscl(low) \
-do { \
- u64 _l = paravirt_read_tsc(); \
- low = (int)_l; \
-} while (0)
-
-#define rdtscll(val) (val = paravirt_read_tsc())
-
static inline unsigned long long paravirt_sched_clock(void)
{
return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
@@ -215,27 +206,6 @@ do { \
#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
-static inline unsigned long long paravirt_rdtscp(unsigned int *aux)
-{
- return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux);
-}
-
-#define rdtscp(low, high, aux) \
-do { \
- int __aux; \
- unsigned long __val = paravirt_rdtscp(&__aux); \
- (low) = (u32)__val; \
- (high) = (u32)(__val >> 32); \
- (aux) = __aux; \
-} while (0)
-
-#define rdtscpll(val, aux) \
-do { \
- unsigned long __aux; \
- val = paravirt_rdtscp(&__aux); \
- (aux) = __aux; \
-} while (0)
-
static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
{
PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index a6b8f9fadb06..ce029e4fa7c6 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -156,9 +156,7 @@ struct pv_cpu_ops {
u64 (*read_msr)(unsigned int msr, int *err);
int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
- u64 (*read_tsc)(void);
u64 (*read_pmc)(int counter);
- unsigned long long (*read_tscp)(unsigned int *aux);
#ifdef CONFIG_X86_32
/*
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 164e3f8d3c3d..fa1195dae425 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,8 +93,6 @@ extern raw_spinlock_t pci_config_lock;
extern int (*pcibios_enable_irq)(struct pci_dev *dev);
extern void (*pcibios_disable_irq)(struct pci_dev *dev);
-extern bool mp_should_keep_irq(struct device *dev);
-
struct pci_raw_ops {
int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
int reg, int len, u32 *val);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index dc0f6ed35b08..7bcb861a04e5 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -159,6 +159,13 @@ 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)
+
/*
* IBS cpuid feature detection
*/
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index dca71714f860..b12f81022a6b 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -90,9 +90,9 @@ static __always_inline bool __preempt_count_dec_and_test(void)
/*
* Returns true when we need to resched and can (barring IRQ state).
*/
-static __always_inline bool should_resched(void)
+static __always_inline bool should_resched(int preempt_offset)
{
- return unlikely(!raw_cpu_read_4(__preempt_count));
+ return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
}
#ifdef CONFIG_PREEMPT
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 944f1785ed0d..19577dd325fa 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -6,8 +6,8 @@
/* Forward declaration, a strange C thing */
struct task_struct;
struct mm_struct;
+struct vm86;
-#include <asm/vm86.h>
#include <asm/math_emu.h>
#include <asm/segment.h>
#include <asm/types.h>
@@ -400,15 +400,9 @@ struct thread_struct {
unsigned long cr2;
unsigned long trap_nr;
unsigned long error_code;
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_VM86
/* Virtual 86 mode info */
- struct vm86_struct __user *vm86_info;
- unsigned long screen_bitmap;
- unsigned long v86flags;
- unsigned long v86mask;
- unsigned long saved_sp0;
- unsigned int saved_fs;
- unsigned int saved_gs;
+ struct vm86 *vm86;
#endif
/* IO permissions: */
unsigned long *io_bitmap_ptr;
@@ -651,14 +645,6 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
extern void set_task_blockstep(struct task_struct *task, bool on);
-/*
- * from system description table in BIOS. Mostly for MCA use, but
- * others may find it useful:
- */
-extern unsigned int machine_id;
-extern unsigned int machine_submodel_id;
-extern unsigned int BIOS_revision;
-
/* Boot loader type from the setup header: */
extern int bootloader_type;
extern int bootloader_version;
@@ -720,7 +706,6 @@ static inline void spin_lock_prefetch(const void *x)
#define INIT_THREAD { \
.sp0 = TOP_OF_INIT_STACK, \
- .vm86_info = NULL, \
.sysenter_cs = __KERNEL_CS, \
.io_bitmap_ptr = NULL, \
}
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 5fabf1362942..6271281f947d 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -88,7 +88,6 @@ extern long syscall_trace_enter_phase2(struct pt_regs *, u32 arch,
unsigned long phase1_result);
extern long syscall_trace_enter(struct pt_regs *);
-extern void syscall_trace_leave(struct pt_regs *);
static inline unsigned long regs_return_value(struct pt_regs *regs)
{
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 628954ceede1..7a6bed5c08bc 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -62,7 +62,7 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
static __always_inline
u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src)
{
- u64 delta = __native_read_tsc() - src->tsc_timestamp;
+ u64 delta = rdtsc_ordered() - src->tsc_timestamp;
return pvclock_scale_delta(delta, src->tsc_to_system_mul,
src->tsc_shift);
}
@@ -76,13 +76,7 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
u8 ret_flags;
version = src->version;
- /* Note: emulated platforms which do not advertise SSE2 support
- * result in kvmclock not using the necessary RDTSC barriers.
- * Without barriers, it is possible that RDTSC instruction reads from
- * the time stamp counter outside rdtsc_barrier protected section
- * below, resulting in violation of monotonicity.
- */
- rdtsc_barrier();
+
offset = pvclock_get_nsec_offset(src);
ret = src->system_time + offset;
ret_flags = src->flags;
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 6fe6b182c998..9dfce4e0417d 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -57,9 +57,9 @@ struct sigcontext {
unsigned long ip;
unsigned long flags;
unsigned short cs;
- unsigned short __pad2; /* Was called gs, but was always zero. */
- unsigned short __pad1; /* Was called fs, but was always zero. */
- unsigned short ss;
+ unsigned short gs;
+ unsigned short fs;
+ unsigned short __pad0;
unsigned long err;
unsigned long trapno;
unsigned long oldmask;
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
index 7c7c27c97daa..1f3175bb994e 100644
--- a/arch/x86/include/asm/sigframe.h
+++ b/arch/x86/include/asm/sigframe.h
@@ -4,6 +4,7 @@
#include <asm/sigcontext.h>
#include <asm/siginfo.h>
#include <asm/ucontext.h>
+#include <linux/compat.h>
#ifdef CONFIG_X86_32
#define sigframe_ia32 sigframe
@@ -69,6 +70,15 @@ struct rt_sigframe {
#ifdef CONFIG_X86_X32_ABI
+struct ucontext_x32 {
+ unsigned int uc_flags;
+ unsigned int uc_link;
+ compat_stack_t uc_stack;
+ unsigned int uc__pad0; /* needed for alignment */
+ struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */
+ compat_sigset_t uc_sigmask; /* mask last for extensibility */
+};
+
struct rt_sigframe_x32 {
u64 pretcode;
struct ucontext_x32 uc;
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 31eab867e6d3..c481be78fcf1 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -30,7 +30,7 @@ typedef sigset_t compat_sigset_t;
#endif /* __ASSEMBLY__ */
#include <uapi/asm/signal.h>
#ifndef __ASSEMBLY__
-extern void do_notify_resume(struct pt_regs *, void *, __u32);
+extern void do_signal(struct pt_regs *regs);
#define __ARCH_HAS_SA_RESTORER
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index c2e00bb2a136..58505f01962f 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -72,7 +72,7 @@ static __always_inline void boot_init_stack_canary(void)
* on during the bootup the random pool has true entropy too.
*/
get_random_bytes(&canary, sizeof(canary));
- tsc = __native_read_tsc();
+ tsc = rdtsc();
canary += tsc + (tsc << 32UL);
current->stack_canary = canary;
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 751bf4b7bf11..d7f3b3b78ac3 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -79,12 +79,12 @@ do { \
#else /* CONFIG_X86_32 */
/* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t"
+#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
#define __EXTRA_CLOBBER \
, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
- "r12", "r13", "r14", "r15", "flags"
+ "r12", "r13", "r14", "r15"
#ifdef CONFIG_CC_STACKPROTECTOR
#define __switch_canary \
@@ -100,11 +100,7 @@ do { \
#define __switch_canary_iparam
#endif /* CC_STACKPROTECTOR */
-/*
- * There is no need to save or restore flags, because flags are always
- * clean in kernel mode, with the possible exception of IOPL. Kernel IOPL
- * has no effect.
- */
+/* Save restore flags to clear handle leaking NT */
#define switch_to(prev, next, last) \
asm volatile(SAVE_CONTEXT \
"movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 592a6a672e07..91dfcafe27a6 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -37,6 +37,7 @@ asmlinkage long sys_get_thread_area(struct user_desc __user *);
asmlinkage unsigned long sys_sigreturn(void);
/* kernel/vm86_32.c */
+struct vm86_struct;
asmlinkage long sys_vm86old(struct vm86_struct __user *);
asmlinkage long sys_vm86(unsigned long, unsigned long);
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 225ee545e1a0..8afdc3e44247 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -27,14 +27,17 @@
* 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.
+ * In vm86 mode, the hardware frame is much longer still, so add 16
+ * bytes to make room for the real-mode segments.
*
* x86_64 has a fixed-length stack frame.
*/
#ifdef CONFIG_X86_32
-# define TOP_OF_KERNEL_STACK_PADDING 8
+# ifdef CONFIG_VM86
+# define TOP_OF_KERNEL_STACK_PADDING 16
+# else
+# define TOP_OF_KERNEL_STACK_PADDING 8
+# endif
#else
# define TOP_OF_KERNEL_STACK_PADDING 0
#endif
@@ -140,27 +143,11 @@ struct thread_info {
_TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \
_TIF_NOHZ)
-/* work to do in syscall_trace_leave() */
-#define _TIF_WORK_SYSCALL_EXIT \
- (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \
- _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ)
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK \
- (0x0000FFFF & \
- ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT| \
- _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
-
/* work to do on any return to user space */
#define _TIF_ALLWORK_MASK \
((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT | \
_TIF_NOHZ)
-/* Only used for 64 bit */
-#define _TIF_DO_NOTIFY_MASK \
- (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \
- _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE)
-
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW \
(_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index c5380bea2a36..c3496619740a 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -112,8 +112,8 @@ asmlinkage void smp_threshold_interrupt(void);
asmlinkage void smp_deferred_error_interrupt(void);
#endif
-extern enum ctx_state ist_enter(struct pt_regs *regs);
-extern void ist_exit(struct pt_regs *regs, enum ctx_state prev_state);
+extern void ist_enter(struct pt_regs *regs);
+extern void ist_exit(struct pt_regs *regs);
extern void ist_begin_non_atomic(struct pt_regs *regs);
extern void ist_end_non_atomic(void);
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 94605c0e9cee..6d7c5479bcea 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -21,28 +21,12 @@ extern void disable_TSC(void);
static inline cycles_t get_cycles(void)
{
- unsigned long long ret = 0;
-
#ifndef CONFIG_X86_TSC
if (!cpu_has_tsc)
return 0;
#endif
- rdtscll(ret);
-
- return ret;
-}
-static __always_inline cycles_t vget_cycles(void)
-{
- /*
- * We only do VDSOs on TSC capable CPUs, so this shouldn't
- * access boot_cpu_data (which is not VDSO-safe):
- */
-#ifndef CONFIG_X86_TSC
- if (!cpu_has_tsc)
- return 0;
-#endif
- return (cycles_t)__native_read_tsc();
+ return rdtsc();
}
extern void tsc_init(void);
@@ -51,6 +35,7 @@ extern int unsynchronized_tsc(void);
extern int check_tsc_unstable(void);
extern int check_tsc_disabled(void);
extern unsigned long native_calibrate_tsc(void);
+extern unsigned long long native_sched_clock_from_tsc(u64 tsc);
extern int tsc_clocksource_reliable;
diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h
index 1d8de3f3feca..1e491f3af317 100644
--- a/arch/x86/include/asm/vm86.h
+++ b/arch/x86/include/asm/vm86.h
@@ -1,7 +1,6 @@
#ifndef _ASM_X86_VM86_H
#define _ASM_X86_VM86_H
-
#include <asm/ptrace.h>
#include <uapi/asm/vm86.h>
@@ -28,43 +27,49 @@ struct kernel_vm86_regs {
unsigned short gs, __gsh;
};
-struct kernel_vm86_struct {
- struct kernel_vm86_regs regs;
-/*
- * the below part remains on the kernel stack while we are in VM86 mode.
- * 'tss.esp0' then contains the address of VM86_TSS_ESP0 below, and when we
- * get forced back from VM86, the CPU and "SAVE_ALL" will restore the above
- * 'struct kernel_vm86_regs' with the then actual values.
- * Therefore, pt_regs in fact points to a complete 'kernel_vm86_struct'
- * in kernelspace, hence we need not reget the data from userspace.
- */
-#define VM86_TSS_ESP0 flags
+struct vm86 {
+ struct vm86plus_struct __user *user_vm86;
+ struct pt_regs regs32;
+ unsigned long veflags;
+ unsigned long veflags_mask;
+ unsigned long saved_sp0;
+
unsigned long flags;
unsigned long screen_bitmap;
unsigned long cpu_type;
struct revectored_struct int_revectored;
struct revectored_struct int21_revectored;
struct vm86plus_info_struct vm86plus;
- struct pt_regs *regs32; /* here we save the pointer to the old regs */
-/*
- * The below is not part of the structure, but the stack layout continues
- * this way. In front of 'return-eip' may be some data, depending on
- * compilation, so we don't rely on this and save the pointer to 'oldregs'
- * in 'regs32' above.
- * However, with GCC-2.7.2 and the current CFLAGS you see exactly this:
-
- long return-eip; from call to vm86()
- struct pt_regs oldregs; user space registers as saved by syscall
- */
};
#ifdef CONFIG_VM86
void handle_vm86_fault(struct kernel_vm86_regs *, long);
int handle_vm86_trap(struct kernel_vm86_regs *, long, int);
-struct pt_regs *save_v86_state(struct kernel_vm86_regs *);
+void save_v86_state(struct kernel_vm86_regs *, int);
struct task_struct;
+
+#define free_vm86(t) do { \
+ struct thread_struct *__t = (t); \
+ if (__t->vm86 != NULL) { \
+ kfree(__t->vm86); \
+ __t->vm86 = NULL; \
+ } \
+} while (0)
+
+/*
+ * Support for VM86 programs to request interrupts for
+ * real mode hardware drivers:
+ */
+#define FIRST_VM86_IRQ 3
+#define LAST_VM86_IRQ 15
+
+static inline int invalid_vm86_irq(int irq)
+{
+ return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ;
+}
+
void release_vm86_irqs(struct task_struct *);
#else
@@ -77,6 +82,10 @@ static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c)
return 0;
}
+static inline void save_v86_state(struct kernel_vm86_regs *a, int b) { }
+
+#define free_vm86(t) do { } while(0)
+
#endif /* CONFIG_VM86 */
#endif /* _ASM_X86_VM86_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index da772edd19ab..448b7ca61aee 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -47,6 +47,7 @@
#define CPU_BASED_MOV_DR_EXITING 0x00800000
#define CPU_BASED_UNCOND_IO_EXITING 0x01000000
#define CPU_BASED_USE_IO_BITMAPS 0x02000000
+#define CPU_BASED_MONITOR_TRAP_FLAG 0x08000000
#define CPU_BASED_USE_MSR_BITMAPS 0x10000000
#define CPU_BASED_MONITOR_EXITING 0x20000000
#define CPU_BASED_PAUSE_EXITING 0x40000000
@@ -367,29 +368,29 @@ enum vmcs_field {
#define TYPE_PHYSICAL_APIC_EVENT (10 << 12)
#define TYPE_PHYSICAL_APIC_INST (15 << 12)
-/* segment AR */
-#define SEGMENT_AR_L_MASK (1 << 13)
-
-#define AR_TYPE_ACCESSES_MASK 1
-#define AR_TYPE_READABLE_MASK (1 << 1)
-#define AR_TYPE_WRITEABLE_MASK (1 << 2)
-#define AR_TYPE_CODE_MASK (1 << 3)
-#define AR_TYPE_MASK 0x0f
-#define AR_TYPE_BUSY_64_TSS 11
-#define AR_TYPE_BUSY_32_TSS 11
-#define AR_TYPE_BUSY_16_TSS 3
-#define AR_TYPE_LDT 2
-
-#define AR_UNUSABLE_MASK (1 << 16)
-#define AR_S_MASK (1 << 4)
-#define AR_P_MASK (1 << 7)
-#define AR_L_MASK (1 << 13)
-#define AR_DB_MASK (1 << 14)
-#define AR_G_MASK (1 << 15)
-#define AR_DPL_SHIFT 5
-#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3)
-
-#define AR_RESERVD_MASK 0xfffe0f00
+/* segment AR in VMCS -- these are different from what LAR reports */
+#define VMX_SEGMENT_AR_L_MASK (1 << 13)
+
+#define VMX_AR_TYPE_ACCESSES_MASK 1
+#define VMX_AR_TYPE_READABLE_MASK (1 << 1)
+#define VMX_AR_TYPE_WRITEABLE_MASK (1 << 2)
+#define VMX_AR_TYPE_CODE_MASK (1 << 3)
+#define VMX_AR_TYPE_MASK 0x0f
+#define VMX_AR_TYPE_BUSY_64_TSS 11
+#define VMX_AR_TYPE_BUSY_32_TSS 11
+#define VMX_AR_TYPE_BUSY_16_TSS 3
+#define VMX_AR_TYPE_LDT 2
+
+#define VMX_AR_UNUSABLE_MASK (1 << 16)
+#define VMX_AR_S_MASK (1 << 4)
+#define VMX_AR_P_MASK (1 << 7)
+#define VMX_AR_L_MASK (1 << 13)
+#define VMX_AR_DB_MASK (1 << 14)
+#define VMX_AR_G_MASK (1 << 15)
+#define VMX_AR_DPL_SHIFT 5
+#define VMX_AR_DPL(ar) (((ar) >> VMX_AR_DPL_SHIFT) & 3)
+
+#define VMX_AR_RESERVD_MASK 0xfffe0f00
#define TSS_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 0)
#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 1)
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index ab456dc233b5..329254373479 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -120,7 +120,7 @@ struct boot_params {
__u8 _pad3[16]; /* 0x070 */
__u8 hd0_info[16]; /* obsolete! */ /* 0x080 */
__u8 hd1_info[16]; /* obsolete! */ /* 0x090 */
- struct sys_desc_table sys_desc_table; /* 0x0a0 */
+ struct sys_desc_table sys_desc_table; /* obsolete! */ /* 0x0a0 */
struct olpc_ofw_header olpc_ofw_header; /* 0x0b0 */
__u32 ext_ramdisk_image; /* 0x0c0 */
__u32 ext_ramdisk_size; /* 0x0c4 */
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index f36d56bd7632..f0412c50c47b 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -27,6 +27,8 @@
#define HV_X64_MSR_VP_RUNTIME_AVAILABLE (1 << 0)
/* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
#define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1)
+/* Partition reference TSC MSR is available */
+#define HV_X64_MSR_REFERENCE_TSC_AVAILABLE (1 << 9)
/* A partition's reference time stamp counter (TSC) page */
#define HV_X64_MSR_REFERENCE_TSC 0x40000021
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index a4ae82eb82aa..cd54147cb365 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -354,7 +354,7 @@ struct kvm_xcrs {
struct kvm_sync_regs {
};
-#define KVM_QUIRK_LINT0_REENABLED (1 << 0)
-#define KVM_QUIRK_CD_NW_CLEARED (1 << 1)
+#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index a0eab85ce7b8..76880ede9a35 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -15,7 +15,8 @@ struct mce {
__u64 time; /* wall time_t when error was detected */
__u8 cpuvendor; /* cpu vendor as encoded in system.h */
__u8 inject_flags; /* software inject flags */
- __u16 pad;
+ __u8 severity;
+ __u8 usable_addr;
__u32 cpuid; /* CPUID 1 EAX */
__u8 cs; /* code segment */
__u8 bank; /* machine check bank */
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 180a0c3c224d..79887abcb5e1 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -37,8 +37,6 @@
#define X86_EFLAGS_VM _BITUL(X86_EFLAGS_VM_BIT)
#define X86_EFLAGS_AC_BIT 18 /* Alignment Check/Access Control */
#define X86_EFLAGS_AC _BITUL(X86_EFLAGS_AC_BIT)
-#define X86_EFLAGS_AC_BIT 18 /* Alignment Check/Access Control */
-#define X86_EFLAGS_AC _BITUL(X86_EFLAGS_AC_BIT)
#define X86_EFLAGS_VIF_BIT 19 /* Virtual Interrupt Flag */
#define X86_EFLAGS_VIF _BITUL(X86_EFLAGS_VIF_BIT)
#define X86_EFLAGS_VIP_BIT 20 /* Virtual Interrupt Pending */
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index 0e8a973de9ee..40836a9a7250 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -177,24 +177,9 @@ struct sigcontext {
__u64 rip;
__u64 eflags; /* RFLAGS */
__u16 cs;
-
- /*
- * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"),
- * Linux saved and restored fs and gs in these slots. This
- * was counterproductive, as fsbase and gsbase were never
- * saved, so arch_prctl was presumably unreliable.
- *
- * If these slots are ever needed for any other purpose, there
- * is some risk that very old 64-bit binaries could get
- * confused. I doubt that many such binaries still work,
- * though, since the same patch in 2.5.64 also removed the
- * 64-bit set_thread_area syscall, so it appears that there is
- * no TLS API that works in both pre- and post-2.5.64 kernels.
- */
- __u16 __pad2; /* Was gs. */
- __u16 __pad1; /* Was fs. */
-
- __u16 ss;
+ __u16 gs;
+ __u16 fs;
+ __u16 __pad0;
__u64 err;
__u64 trapno;
__u64 oldmask;
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 1fe92181ee9e..37fee272618f 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -58,6 +58,7 @@
#define EXIT_REASON_INVALID_STATE 33
#define EXIT_REASON_MSR_LOAD_FAIL 34
#define EXIT_REASON_MWAIT_INSTRUCTION 36
+#define EXIT_REASON_MONITOR_TRAP_FLAG 37
#define EXIT_REASON_MONITOR_INSTRUCTION 39
#define EXIT_REASON_PAUSE_INSTRUCTION 40
#define EXIT_REASON_MCE_DURING_VMENTRY 41
@@ -106,6 +107,7 @@
{ EXIT_REASON_MSR_READ, "MSR_READ" }, \
{ EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \
{ EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \
+ { EXIT_REASON_MONITOR_TRAP_FLAG, "MONITOR_TRAP_FLAG" }, \
{ EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \
{ EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \
{ EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \