7 files changed, 252 insertions, 62 deletions

diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 0c9fa2745f13..b3b733262909 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -145,13 +145,13 @@ extern void __add_wrong_size(void)
 
 #ifdef __HAVE_ARCH_CMPXCHG
 #define cmpxchg(ptr, old, new)                                          \
-        __cmpxchg((ptr), (old), (new), sizeof(*ptr))
+        __cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
 #define sync_cmpxchg(ptr, old, new)                                     \
-        __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
+        __sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
 #define cmpxchg_local(ptr, old, new)                                    \
-        __cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
+        __cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
 #endif
 
 /*
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 17c5d4bdee5e..8d67d428b0f9 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -159,6 +159,7 @@
 #define X86_FEATURE_WDT         (6*32+13) /* Watchdog timer */
 #define X86_FEATURE_LWP         (6*32+15) /* Light Weight Profiling */
 #define X86_FEATURE_FMA4        (6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE         (6*32+17) /* translation cache extension */
 #define X86_FEATURE_NODEID_MSR  (6*32+19) /* NodeId MSR */
 #define X86_FEATURE_TBM         (6*32+21) /* trailing bit manipulations */
 #define X86_FEATURE_TOPOEXT     (6*32+22) /* topology extensions CPUID leafs */
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 6919e936345b..a850b4d8d14d 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -29,8 +29,8 @@ 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(struct task_struct *);
+extern void math_state_restore(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
 extern user_regset_active_fn fpregs_active, xfpregs_active;
@@ -212,19 +212,11 @@ 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 +225,33 @@ 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)
@@ -281,39 +273,185 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
 }
 
 /*
- * 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.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.has_fpu = 0;
+}
+
+/* Must be paired with a 'clts' before! */
+static inline void __thread_set_has_fpu(struct task_struct *tsk)
+{
+        tsk->thread.has_fpu = 1;
 }
 
+/*
+ * 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..
+ */
+#define fpu_lazy_restore(tsk) (0)
+#define fpu_lazy_state_intact(tsk) do { } while (0)
+
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new)
+{
+        fpu_switch_t fpu;
+
+        fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+        if (__thread_has_fpu(old)) {
+                if (__save_init_fpu(old))
+                        fpu_lazy_state_intact(old);
+                __thread_clear_has_fpu(old);
+                old->fpu_counter++;
+
+                /* Don't change CR0.TS if we just switch! */
+                if (fpu.preload) {
+                        __thread_set_has_fpu(new);
+                        prefetch(new->thread.fpu.state);
+                } else
+                        stts();
+        } else {
+                old->fpu_counter = 0;
+                if (fpu.preload) {
+                        if (fpu_lazy_restore(new))
+                                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)
+                __math_state_restore(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
                 clts();
 }
 
@@ -323,14 +461,6 @@ 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 +493,64 @@ 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..f7c89e231c6c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -454,6 +454,7 @@ struct thread_struct {
         unsigned long           trap_no;
         unsigned long           error_code;
         /* floating point and extended processor state */
+        unsigned long           has_fpu;
         struct fpu              fpu;
 #ifdef CONFIG_X86_32
         /* Virtual 86 mode info */
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/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 54a13aaebc40..21f7385badb8 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -318,13 +318,13 @@ uv_gpa_in_mmr_space(unsigned long gpa)
 /* UV global physical address --> socket phys RAM */
 static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
 {
-        unsigned long paddr = gpa & uv_hub_info->gpa_mask;
+        unsigned long paddr;
         unsigned long remap_base = uv_hub_info->lowmem_remap_base;
         unsigned long remap_top =  uv_hub_info->lowmem_remap_top;
 
         gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
                 ((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val);
-        gpa = gpa & uv_hub_info->gpa_mask;
+        paddr = gpa & uv_hub_info->gpa_mask;
         if (paddr >= remap_base && paddr < remap_base + remap_top)
                 paddr -= remap_base;
         return paddr;