18 files changed, 414 insertions, 153 deletions

diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 6919e936345b..247904945d3f 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -29,10 +29,11 @@ extern unsigned int sig_xstate_size;
 extern void fpu_init(void);
 extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
-extern asmlinkage void math_state_restore(void);
-extern void __math_state_restore(void);
+extern void math_state_restore(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
+DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
+
 extern user_regset_active_fn fpregs_active, xfpregs_active;
 extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
                                 xstateregs_get;
@@ -212,19 +213,11 @@ static inline void fpu_fxsave(struct fpu *fpu)
 
 #endif  /* CONFIG_X86_64 */
 
-/* We need a safe address that is cheap to find and that is already
-   in L1 during context switch. The best choices are unfortunately
-   different for UP and SMP */
-#ifdef CONFIG_SMP
-#define safe_address (__per_cpu_offset[0])
-#else
-#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER])
-#endif
-
 /*
- * These must be called with preempt disabled
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact.
  */
-static inline void fpu_save_init(struct fpu *fpu)
+static inline int fpu_save_init(struct fpu *fpu)
 {
         if (use_xsave()) {
                 fpu_xsave(fpu);
@@ -233,33 +226,33 @@ static inline void fpu_save_init(struct fpu *fpu)
                  * xsave header may indicate the init state of the FP.
                  */
                 if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
-                        return;
+                        return 1;
         } else if (use_fxsr()) {
                 fpu_fxsave(fpu);
         } else {
                 asm volatile("fnsave %[fx]; fwait"
                              : [fx] "=m" (fpu->state->fsave));
-                return;
+                return 0;
         }
 
-        if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
+        /*
+         * If exceptions are pending, we need to clear them so
+         * that we don't randomly get exceptions later.
+         *
+         * FIXME! Is this perhaps only true for the old-style
+         * irq13 case? Maybe we could leave the x87 state
+         * intact otherwise?
+         */
+        if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
                 asm volatile("fnclex");
-
-        /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
-           is pending.  Clear the x87 state here by setting it to fixed
-           values. safe_address is a random variable that should be in L1 */
-        alternative_input(
-                ASM_NOP8 ASM_NOP2,
-                "emms\n\t"              /* clear stack tags */
-                "fildl %P[addr]",       /* set F?P to defined value */
-                X86_FEATURE_FXSAVE_LEAK,
-                [addr] "m" (safe_address));
+                return 0;
+        }
+        return 1;
 }
 
-static inline void __save_init_fpu(struct task_struct *tsk)
+static inline int __save_init_fpu(struct task_struct *tsk)
 {
-        fpu_save_init(&tsk->thread.fpu);
-        task_thread_info(tsk)->status &= ~TS_USEDFPU;
+        return fpu_save_init(&tsk->thread.fpu);
 }
 
 static inline int fpu_fxrstor_checking(struct fpu *fpu)
@@ -277,44 +270,212 @@ static inline int fpu_restore_checking(struct fpu *fpu)
 
 static inline int restore_fpu_checking(struct task_struct *tsk)
 {
+        /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+           is pending.  Clear the x87 state here by setting it to fixed
+           values. "m" is a random variable that should be in L1 */
+        alternative_input(
+                ASM_NOP8 ASM_NOP2,
+                "emms\n\t"              /* clear stack tags */
+                "fildl %P[addr]",       /* set F?P to defined value */
+                X86_FEATURE_FXSAVE_LEAK,
+                [addr] "m" (tsk->thread.fpu.has_fpu));
+
         return fpu_restore_checking(&tsk->thread.fpu);
 }
 
 /*
- * Signal frame handlers...
+ * Software FPU state helpers. Careful: these need to
+ * be preemption protection *and* they need to be
+ * properly paired with the CR0.TS changes!
  */
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
+static inline int __thread_has_fpu(struct task_struct *tsk)
+{
+        return tsk->thread.fpu.has_fpu;
+}
 
-static inline void __unlazy_fpu(struct task_struct *tsk)
+/* Must be paired with an 'stts' after! */
+static inline void __thread_clear_has_fpu(struct task_struct *tsk)
 {
-        if (task_thread_info(tsk)->status & TS_USEDFPU) {
-                __save_init_fpu(tsk);
-                stts();
-        } else
-                tsk->fpu_counter = 0;
+        tsk->thread.fpu.has_fpu = 0;
+        percpu_write(fpu_owner_task, NULL);
+}
+
+/* Must be paired with a 'clts' before! */
+static inline void __thread_set_has_fpu(struct task_struct *tsk)
+{
+        tsk->thread.fpu.has_fpu = 1;
+        percpu_write(fpu_owner_task, tsk);
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void __thread_fpu_end(struct task_struct *tsk)
+{
+        __thread_clear_has_fpu(tsk);
+        stts();
+}
+
+static inline void __thread_fpu_begin(struct task_struct *tsk)
+{
+        clts();
+        __thread_set_has_fpu(tsk);
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ *  - switch_fpu_prepare() saves the old state and
+ *    sets the new state of the CR0.TS bit. This is
+ *    done within the context of the old process.
+ *
+ *  - switch_fpu_finish() restores the new state as
+ *    necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+/*
+ * FIXME! We could do a totally lazy restore, but we need to
+ * add a per-cpu "this was the task that last touched the FPU
+ * on this CPU" variable, and the task needs to have a "I last
+ * touched the FPU on this CPU" and check them.
+ *
+ * We don't do that yet, so "fpu_lazy_restore()" always returns
+ * false, but some day..
+ */
+static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
+{
+        return new == percpu_read_stable(fpu_owner_task) &&
+                cpu == new->thread.fpu.last_cpu;
+}
+
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
+{
+        fpu_switch_t fpu;
+
+        fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+        if (__thread_has_fpu(old)) {
+                if (!__save_init_fpu(old))
+                        cpu = ~0;
+                old->thread.fpu.last_cpu = cpu;
+                old->thread.fpu.has_fpu = 0;    /* But leave fpu_owner_task! */
+
+                /* Don't change CR0.TS if we just switch! */
+                if (fpu.preload) {
+                        new->fpu_counter++;
+                        __thread_set_has_fpu(new);
+                        prefetch(new->thread.fpu.state);
+                } else
+                        stts();
+        } else {
+                old->fpu_counter = 0;
+                old->thread.fpu.last_cpu = ~0;
+                if (fpu.preload) {
+                        new->fpu_counter++;
+                        if (fpu_lazy_restore(new, cpu))
+                                fpu.preload = 0;
+                        else
+                                prefetch(new->thread.fpu.state);
+                        __thread_fpu_begin(new);
+                }
+        }
+        return fpu;
+}
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
+{
+        if (fpu.preload) {
+                if (unlikely(restore_fpu_checking(new)))
+                        __thread_fpu_end(new);
+        }
 }
 
+/*
+ * Signal frame handlers...
+ */
+extern int save_i387_xstate(void __user *buf);
+extern int restore_i387_xstate(void __user *buf);
+
 static inline void __clear_fpu(struct task_struct *tsk)
 {
-        if (task_thread_info(tsk)->status & TS_USEDFPU) {
+        if (__thread_has_fpu(tsk)) {
                 /* Ignore delayed exceptions from user space */
                 asm volatile("1: fwait\n"
                              "2:\n"
                              _ASM_EXTABLE(1b, 2b));
-                task_thread_info(tsk)->status &= ~TS_USEDFPU;
-                stts();
+                __thread_fpu_end(tsk);
         }
 }
 
+/*
+ * Were we in an interrupt that interrupted kernel mode?
+ *
+ * We can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * pair does nothing at all: the thread must not have fpu (so
+ * that we don't try to save the FPU state), and TS must
+ * be set (so that the clts/stts pair does nothing that is
+ * visible in the interrupted kernel thread).
+ */
+static inline bool interrupted_kernel_fpu_idle(void)
+{
+        return !__thread_has_fpu(current) &&
+                (read_cr0() & X86_CR0_TS);
+}
+
+/*
+ * Were we in user mode (or vm86 mode) when we were
+ * interrupted?
+ *
+ * Doing kernel_fpu_begin/end() is ok if we are running
+ * in an interrupt context from user mode - we'll just
+ * save the FPU state as required.
+ */
+static inline bool interrupted_user_mode(void)
+{
+        struct pt_regs *regs = get_irq_regs();
+        return regs && user_mode_vm(regs);
+}
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ *
+ * It's always ok in process context (ie "not interrupt")
+ * but it is sometimes ok even from an irq.
+ */
+static inline bool irq_fpu_usable(void)
+{
+        return !in_interrupt() ||
+                interrupted_user_mode() ||
+                interrupted_kernel_fpu_idle();
+}
+
 static inline void kernel_fpu_begin(void)
 {
-        struct thread_info *me = current_thread_info();
+        struct task_struct *me = current;
+
+        WARN_ON_ONCE(!irq_fpu_usable());
         preempt_disable();
-        if (me->status & TS_USEDFPU)
-                __save_init_fpu(me->task);
-        else
+        if (__thread_has_fpu(me)) {
+                __save_init_fpu(me);
+                __thread_clear_has_fpu(me);
+                /* We do 'stts()' in kernel_fpu_end() */
+        } else {
+                percpu_write(fpu_owner_task, NULL);
                 clts();
+        }
 }
 
 static inline void kernel_fpu_end(void)
@@ -323,14 +484,6 @@ static inline void kernel_fpu_end(void)
         preempt_enable();
 }
 
-static inline bool irq_fpu_usable(void)
-{
-        struct pt_regs *regs;
-
-        return !in_interrupt() || !(regs = get_irq_regs()) || \
-                user_mode(regs) || (read_cr0() & X86_CR0_TS);
-}
-
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
  * DNA fault but don't modify SSE registers. And these instructions
@@ -363,20 +516,64 @@ static inline void irq_ts_restore(int TS_state)
 }
 
 /*
+ * The question "does this thread have fpu access?"
+ * is slightly racy, since preemption could come in
+ * and revoke it immediately after the test.
+ *
+ * However, even in that very unlikely scenario,
+ * we can just assume we have FPU access - typically
+ * to save the FP state - we'll just take a #NM
+ * fault and get the FPU access back.
+ *
+ * The actual user_fpu_begin/end() functions
+ * need to be preemption-safe, though.
+ *
+ * NOTE! user_fpu_end() must be used only after you
+ * have saved the FP state, and user_fpu_begin() must
+ * be used only immediately before restoring it.
+ * These functions do not do any save/restore on
+ * their own.
+ */
+static inline int user_has_fpu(void)
+{
+        return __thread_has_fpu(current);
+}
+
+static inline void user_fpu_end(void)
+{
+        preempt_disable();
+        __thread_fpu_end(current);
+        preempt_enable();
+}
+
+static inline void user_fpu_begin(void)
+{
+        preempt_disable();
+        if (!user_has_fpu())
+                __thread_fpu_begin(current);
+        preempt_enable();
+}
+
+/*
  * These disable preemption on their own and are safe
  */
 static inline void save_init_fpu(struct task_struct *tsk)
 {
+        WARN_ON_ONCE(!__thread_has_fpu(tsk));
         preempt_disable();
         __save_init_fpu(tsk);
-        stts();
+        __thread_fpu_end(tsk);
         preempt_enable();
 }
 
 static inline void unlazy_fpu(struct task_struct *tsk)
 {
         preempt_disable();
-        __unlazy_fpu(tsk);
+        if (__thread_has_fpu(tsk)) {
+                __save_init_fpu(tsk);
+                __thread_fpu_end(tsk);
+        } else
+                tsk->fpu_counter = 0;
         preempt_enable();
 }
 
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index ab4092e3214e..7b9cfc4878af 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -190,6 +190,9 @@ struct x86_emulate_ops {
         int (*intercept)(struct x86_emulate_ctxt *ctxt,
                          struct x86_instruction_info *info,
                          enum x86_intercept_stage stage);
+
+        bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
+                         u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;
@@ -298,6 +301,19 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_PROT     (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
                                X86EMUL_MODE_PROT64)
 
+/* CPUID vendors */
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
+
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx 0x69444d41
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273
+
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69
+
 enum x86_intercept_stage {
         X86_ICTP_NONE = 0,   /* Allow zero-init to not match anything */
         X86_ICPT_PRE_EXCEPT,
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index aa9088c26931..58545c97d071 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -374,6 +374,8 @@ union thread_xstate {
 };
 
 struct fpu {
+        unsigned int last_cpu;
+        unsigned int has_fpu;
         union thread_xstate *state;
 };
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index bc817cd8b443..cfd8144d5527 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -247,8 +247,6 @@ static inline struct thread_info *current_thread_info(void)
  * ever touches our thread-synchronous status, so we don't
  * have to worry about atomic accesses.
  */
-#define TS_USEDFPU              0x0001  /* FPU was used by this task
-                                           this quantum (SMP) */
 #define TS_COMPAT               0x0002  /* 32bit syscall active (64BIT)*/
 #define TS_POLLING              0x0004  /* idle task polling need_resched,
                                            skip sending interrupt */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d43cad74f166..c0f7d68d318f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1044,6 +1044,9 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) =
 
 DEFINE_PER_CPU(unsigned int, irq_count) = -1;
 
+DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
+EXPORT_PER_CPU_SYMBOL(fpu_owner_task);
+
 /*
  * Special IST stacks which the CPU switches to when it calls
  * an IST-marked descriptor entry. Up to 7 stacks (hardware
@@ -1111,6 +1114,8 @@ void debug_stack_reset(void)
 
 DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
+DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
+EXPORT_PER_CPU_SYMBOL(fpu_owner_task);
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 73da6b64f5b7..d6bd49faa40c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -439,7 +439,6 @@ void intel_pmu_pebs_enable(struct perf_event *event)
         hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
         cpuc->pebs_enabled |= 1ULL << hwc->idx;
-        WARN_ON_ONCE(cpuc->enabled);
 
         if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
                 intel_pmu_lbr_enable(event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 3fab3de3ce96..47a7e63bfe54 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -72,8 +72,6 @@ void intel_pmu_lbr_enable(struct perf_event *event)
         if (!x86_pmu.lbr_nr)
                 return;
 
-        WARN_ON_ONCE(cpuc->enabled);
-
         /*
          * Reset the LBR stack if we changed task context to
          * avoid data leaks.
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 485204f58cda..c08d1ff12b7c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -214,6 +214,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
         task_user_gs(p) = get_user_gs(regs);
 
+        p->fpu_counter = 0;
         p->thread.io_bitmap_ptr = NULL;
         tsk = current;
         err = -ENOMEM;
@@ -299,22 +300,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                                  *next = &next_p->thread;
         int cpu = smp_processor_id();
         struct tss_struct *tss = &per_cpu(init_tss, cpu);
-        bool preload_fpu;
+        fpu_switch_t fpu;
 
         /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-        /*
-         * If the task has used fpu the last 5 timeslices, just do a full
-         * restore of the math state immediately to avoid the trap; the
-         * chances of needing FPU soon are obviously high now
-         */
-        preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
-        __unlazy_fpu(prev_p);
-
-        /* we're going to use this soon, after a few expensive things */
-        if (preload_fpu)
-                prefetch(next->fpu.state);
+        fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
         /*
          * Reload esp0.
@@ -354,11 +344,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                      task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
                 __switch_to_xtra(prev_p, next_p, tss);
 
-        /* If we're going to preload the fpu context, make sure clts
-           is run while we're batching the cpu state updates. */
-        if (preload_fpu)
-                clts();
-
         /*
          * Leave lazy mode, flushing any hypercalls made here.
          * This must be done before restoring TLS segments so
@@ -368,15 +353,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
          */
         arch_end_context_switch(next_p);
 
-        if (preload_fpu)
-                __math_state_restore();
-
         /*
          * Restore %gs if needed (which is common)
          */
         if (prev->gs | next->gs)
                 lazy_load_gs(next->gs);
 
+        switch_fpu_finish(next_p, fpu);
+
         percpu_write(current_task, next_p);
 
         return prev_p;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9b9fe4a85c87..cfa5c90c01db 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -286,6 +286,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
         set_tsk_thread_flag(p, TIF_FORK);
 
+        p->fpu_counter = 0;
         p->thread.io_bitmap_ptr = NULL;
 
         savesegment(gs, p->thread.gsindex);
@@ -386,18 +387,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         int cpu = smp_processor_id();
         struct tss_struct *tss = &per_cpu(init_tss, cpu);
         unsigned fsindex, gsindex;
-        bool preload_fpu;
+        fpu_switch_t fpu;
 
-        /*
-         * If the task has used fpu the last 5 timeslices, just do a full
-         * restore of the math state immediately to avoid the trap; the
-         * chances of needing FPU soon are obviously high now
-         */
-        preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
-        /* we're going to use this soon, after a few expensive things */
-        if (preload_fpu)
-                prefetch(next->fpu.state);
+        fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
         /*
          * Reload esp0, LDT and the page table pointer:
@@ -427,13 +419,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
         load_TLS(next, cpu);
 
-        /* Must be after DS reload */
-        __unlazy_fpu(prev_p);
-
-        /* Make sure cpu is ready for new context */
-        if (preload_fpu)
-                clts();
-
         /*
          * Leave lazy mode, flushing any hypercalls made here.
          * This must be done before restoring TLS segments so
@@ -474,6 +459,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                 wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
         prev->gsindex = gsindex;
 
+        switch_fpu_finish(next_p, fpu);
+
         /*
          * Switch the PDA and FPU contexts.
          */
@@ -492,13 +479,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                      task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
                 __switch_to_xtra(prev_p, next_p, tss);
 
-        /*
-         * Preload the FPU context, now that we've determined that the
-         * task is likely to be using it. 
-         */
-        if (preload_fpu)
-                __math_state_restore();
-
         return prev_p;
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 482ec3af2067..4bbe04d96744 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -571,41 +571,18 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
 }
 
 /*
- * __math_state_restore assumes that cr0.TS is already clear and the
- * fpu state is all ready for use.  Used during context switch.
- */
-void __math_state_restore(void)
-{
-        struct thread_info *thread = current_thread_info();
-        struct task_struct *tsk = thread->task;
-
-        /*
-         * Paranoid restore. send a SIGSEGV if we fail to restore the state.
-         */
-        if (unlikely(restore_fpu_checking(tsk))) {
-                stts();
-                force_sig(SIGSEGV, tsk);
-                return;
-        }
-
-        thread->status |= TS_USEDFPU;   /* So we fnsave on switch_to() */
-        tsk->fpu_counter++;
-}
-
-/*
  * 'math_state_restore()' saves the current math information in the
  * old math state array, and gets the new ones from the current task
  *
  * Careful.. There are problems with IBM-designed IRQ13 behaviour.
  * Don't touch unless you *really* know how it works.
  *
- * Must be called with kernel preemption disabled (in this case,
- * local interrupts are disabled at the call-site in entry.S).
+ * Must be called with kernel preemption disabled (eg with local
+ * local interrupts as in the case of do_device_not_available).
  */
-asmlinkage void math_state_restore(void)
+void math_state_restore(void)
 {
-        struct thread_info *thread = current_thread_info();
-        struct task_struct *tsk = thread->task;
+        struct task_struct *tsk = current;
 
         if (!tsk_used_math(tsk)) {
                 local_irq_enable();
@@ -622,9 +599,17 @@ asmlinkage void math_state_restore(void)
                 local_irq_disable();
         }
 
-        clts();                         /* Allow maths ops (or we recurse) */
+        __thread_fpu_begin(tsk);
+        /*
+         * Paranoid restore. send a SIGSEGV if we fail to restore the state.
+         */
+        if (unlikely(restore_fpu_checking(tsk))) {
+                __thread_fpu_end(tsk);
+                force_sig(SIGSEGV, tsk);
+                return;
+        }
 
-        __math_state_restore();
+        tsk->fpu_counter++;
 }
 EXPORT_SYMBOL_GPL(math_state_restore);
 
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index a3911343976b..711091114119 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -47,7 +47,7 @@ void __sanitize_i387_state(struct task_struct *tsk)
         if (!fx)
                 return;
 
-        BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU);
+        BUG_ON(__thread_has_fpu(tsk));
 
         xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
 
@@ -168,7 +168,7 @@ int save_i387_xstate(void __user *buf)
         if (!used_math())
                 return 0;
 
-        if (task_thread_info(tsk)->status & TS_USEDFPU) {
+        if (user_has_fpu()) {
                 if (use_xsave())
                         err = xsave_user(buf);
                 else
@@ -176,8 +176,7 @@ int save_i387_xstate(void __user *buf)
 
                 if (err)
                         return err;
-                task_thread_info(tsk)->status &= ~TS_USEDFPU;
-                stts();
+                user_fpu_end();
         } else {
                 sanitize_i387_state(tsk);
                 if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
@@ -292,10 +291,7 @@ int restore_i387_xstate(void __user *buf)
                         return err;
         }
 
-        if (!(task_thread_info(current)->status & TS_USEDFPU)) {
-                clts();
-                task_thread_info(current)->status |= TS_USEDFPU;
-        }
+        user_fpu_begin();
         if (use_xsave())
                 err = restore_user_xstate(buf);
         else
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 05a562b85025..0982507b962a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1891,6 +1891,51 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
         ss->p = 1;
 }
 
+static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
+{
+        struct x86_emulate_ops *ops = ctxt->ops;
+        u32 eax, ebx, ecx, edx;
+
+        /*
+         * syscall should always be enabled in longmode - so only become
+         * vendor specific (cpuid) if other modes are active...
+         */
+        if (ctxt->mode == X86EMUL_MODE_PROT64)
+                return true;
+
+        eax = 0x00000000;
+        ecx = 0x00000000;
+        if (ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx)) {
+                /*
+                 * Intel ("GenuineIntel")
+                 * remark: Intel CPUs only support "syscall" in 64bit
+                 * longmode. Also an 64bit guest with a
+                 * 32bit compat-app running will #UD !! While this
+                 * behaviour can be fixed (by emulating) into AMD
+                 * response - CPUs of AMD can't behave like Intel.
+                 */
+                if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx &&
+                    ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx &&
+                    edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx)
+                        return false;
+
+                /* AMD ("AuthenticAMD") */
+                if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx &&
+                    ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx &&
+                    edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+                        return true;
+
+                /* AMD ("AMDisbetter!") */
+                if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx &&
+                    ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx &&
+                    edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx)
+                        return true;
+        }
+
+        /* default: (not Intel, not AMD), apply Intel's stricter rules... */
+        return false;
+}
+
 static int em_syscall(struct x86_emulate_ctxt *ctxt)
 {
         struct x86_emulate_ops *ops = ctxt->ops;
@@ -1904,9 +1949,15 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
             ctxt->mode == X86EMUL_MODE_VM86)
                 return emulate_ud(ctxt);
 
+        if (!(em_syscall_is_enabled(ctxt)))
+                return emulate_ud(ctxt);
+
         ops->get_msr(ctxt, MSR_EFER, &efer);
         setup_syscalls_segments(ctxt, &cs, &ss);
 
+        if (!(efer & EFER_SCE))
+                return emulate_ud(ctxt);
+
         ops->get_msr(ctxt, MSR_STAR, &msr_data);
         msr_data >>= 32;
         cs_sel = (u16)(msr_data & 0xfffc);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d29216c462b3..3b4c8d8ad906 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1457,7 +1457,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 #ifdef CONFIG_X86_64
         wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
-        if (current_thread_info()->status & TS_USEDFPU)
+        if (__thread_has_fpu(current))
                 clts();
         load_gdt(&__get_cpu_var(host_gdt));
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 14d6cadc4ba6..9cbfc0698118 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1495,6 +1495,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
+        bool pr = false;
+
         switch (msr) {
         case MSR_EFER:
                 return set_efer(vcpu, data);
@@ -1635,6 +1637,18 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
                 pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
                         "0x%x data 0x%llx\n", msr, data);
                 break;
+        case MSR_P6_PERFCTR0:
+        case MSR_P6_PERFCTR1:
+                pr = true;
+        case MSR_P6_EVNTSEL0:
+        case MSR_P6_EVNTSEL1:
+                if (kvm_pmu_msr(vcpu, msr))
+                        return kvm_pmu_set_msr(vcpu, msr, data);
+
+                if (pr || data != 0)
+                        pr_unimpl(vcpu, "disabled perfctr wrmsr: "
+                                "0x%x data 0x%llx\n", msr, data);
+                break;
         case MSR_K7_CLK_CTL:
                 /*
                  * Ignore all writes to this no longer documented MSR.
@@ -1835,6 +1849,14 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
         case MSR_FAM10H_MMIO_CONF_BASE:
                 data = 0;
                 break;
+        case MSR_P6_PERFCTR0:
+        case MSR_P6_PERFCTR1:
+        case MSR_P6_EVNTSEL0:
+        case MSR_P6_EVNTSEL1:
+                if (kvm_pmu_msr(vcpu, msr))
+                        return kvm_pmu_get_msr(vcpu, msr, pdata);
+                data = 0;
+                break;
         case MSR_IA32_UCODE_REV:
                 data = 0x100000000ULL;
                 break;
@@ -4180,6 +4202,28 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
         return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage);
 }
 
+static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
+                               u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
+{
+        struct kvm_cpuid_entry2 *cpuid = NULL;
+
+        if (eax && ecx)
+                cpuid = kvm_find_cpuid_entry(emul_to_vcpu(ctxt),
+                                            *eax, *ecx);
+
+        if (cpuid) {
+                *eax = cpuid->eax;
+                *ecx = cpuid->ecx;
+                if (ebx)
+                        *ebx = cpuid->ebx;
+                if (edx)
+                        *edx = cpuid->edx;
+                return true;
+        }
+
+        return false;
+}
+
 static struct x86_emulate_ops emulate_ops = {
         .read_std            = kvm_read_guest_virt_system,
         .write_std           = kvm_write_guest_virt_system,
@@ -4211,6 +4255,7 @@ static struct x86_emulate_ops emulate_ops = {
         .get_fpu             = emulator_get_fpu,
         .put_fpu             = emulator_put_fpu,
         .intercept           = emulator_intercept,
+        .get_cpuid           = emulator_get_cpuid,
 };
 
 static void cache_all_regs(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 492ade8c978e..d99346ea8fdb 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -374,7 +374,7 @@ int __init pci_xen_init(void)
 
 int __init pci_xen_hvm_init(void)
 {
-        if (!xen_feature(XENFEAT_hvm_pirqs))
+        if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
                 return 0;
 
 #ifdef CONFIG_ACPI
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 12eb07bfb267..4172af8ceeb3 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1141,7 +1141,9 @@ asmlinkage void __init xen_start_kernel(void)
 
         /* Prevent unwanted bits from being set in PTEs. */
         __supported_pte_mask &= ~_PAGE_GLOBAL;
+#if 0
         if (!xen_initial_domain())
+#endif
                 __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
 
         __supported_pte_mask |= _PAGE_IOMAP;
@@ -1204,10 +1206,6 @@ asmlinkage void __init xen_start_kernel(void)
 
         pgd = (pgd_t *)xen_start_info->pt_base;
 
-        if (!xen_initial_domain())
-                __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
-
-        __supported_pte_mask |= _PAGE_IOMAP;
         /* Don't do the full vcpu_info placement stuff until we have a
            possible map and a non-dummy shared_info. */
         per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 58a0e46c404d..95c1cf60c669 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -415,13 +415,13 @@ static pteval_t iomap_pte(pteval_t val)
 static pteval_t xen_pte_val(pte_t pte)
 {
         pteval_t pteval = pte.pte;
-
+#if 0
         /* If this is a WC pte, convert back from Xen WC to Linux WC */
         if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) {
                 WARN_ON(!pat_enabled);
                 pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
         }
-
+#endif
         if (xen_initial_domain() && (pteval & _PAGE_IOMAP))
                 return pteval;
 
@@ -463,7 +463,7 @@ void xen_set_pat(u64 pat)
 static pte_t xen_make_pte(pteval_t pte)
 {
         phys_addr_t addr = (pte & PTE_PFN_MASK);
-
+#if 0
         /* If Linux is trying to set a WC pte, then map to the Xen WC.
          * If _PAGE_PAT is set, then it probably means it is really
          * _PAGE_PSE, so avoid fiddling with the PAT mapping and hope
@@ -476,7 +476,7 @@ static pte_t xen_make_pte(pteval_t pte)
                 if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT)
                         pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
         }
-
+#endif
         /*
          * Unprivileged domains are allowed to do IOMAPpings for
          * PCI passthrough, but not map ISA space.  The ISA
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 041d4fe9dfe4..501d4e0244ba 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -409,6 +409,13 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */
         play_dead_common();
         HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
         cpu_bringup();
+        /*
+         * Balance out the preempt calls - as we are running in cpu_idle
+         * loop which has been called at bootup from cpu_bringup_and_idle.
+         * The cpucpu_bringup_and_idle called cpu_bringup which made a
+         * preempt_disable() So this preempt_enable will balance it out.
+         */
+        preempt_enable();
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */