5 files changed, 48 insertions, 38 deletions

diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index a850b4d8d14d..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 void __math_state_restore(struct task_struct *);
 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;
@@ -269,6 +270,16 @@ 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);
 }
 
@@ -279,19 +290,21 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
  */
 static inline int __thread_has_fpu(struct task_struct *tsk)
 {
-	return tsk->thread.has_fpu;
+	return tsk->thread.fpu.has_fpu;
 }
 
 /* Must be paired with an 'stts' after! */
 static inline void __thread_clear_has_fpu(struct task_struct *tsk)
 {
-	tsk->thread.has_fpu = 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.has_fpu = 1;
+	tsk->thread.fpu.has_fpu = 1;
+	percpu_write(fpu_owner_task, tsk);
 }
 
 /*
@@ -336,30 +349,36 @@ typedef struct { int preload; } fpu_switch_t;
  * 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 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)
+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))
-			fpu_lazy_state_intact(old);
-		__thread_clear_has_fpu(old);
-		old->fpu_counter++;
+		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) {
-			if (fpu_lazy_restore(new))
+			new->fpu_counter++;
+			if (fpu_lazy_restore(new, cpu))
 				fpu.preload = 0;
 			else
 				prefetch(new->thread.fpu.state);
@@ -377,8 +396,10 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
  */
 static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
 {
-	if (fpu.preload)
-		__math_state_restore(new);
+	if (fpu.preload) {
+		if (unlikely(restore_fpu_checking(new)))
+			__thread_fpu_end(new);
+	}
 }
 
 /*
@@ -451,8 +472,10 @@ static inline void kernel_fpu_begin(void)
 		__save_init_fpu(me);
 		__thread_clear_has_fpu(me);
 		/* We do 'stts()' in kernel_fpu_end() */
-	} else
+	} else {
+		percpu_write(fpu_owner_task, NULL);
 		clts();
+	}
 }
 
 static inline void kernel_fpu_end(void)
diff --git a/arch/x86/include/asm/irq_controller.h b/arch/x86/include/asm/irq_controller.h
deleted file mode 100644
index 423bbbddf36d..000000000000
--- a/arch/x86/include/asm/irq_controller.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __IRQ_CONTROLLER__
-#define __IRQ_CONTROLLER__
-
-struct irq_domain {
-	int (*xlate)(struct irq_domain *h, const u32 *intspec, u32 intsize,
-			u32 *out_hwirq, u32 *out_type);
-	void *priv;
-	struct device_node *controller;
-	struct list_head l;
-};
-
-#endif
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 096c975e099f..461ce432b1c2 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -242,4 +242,12 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
 static inline void perf_events_lapic_init(void)	{ }
 #endif
 
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
+ extern void amd_pmu_enable_virt(void);
+ extern void amd_pmu_disable_virt(void);
+#else
+ static inline void amd_pmu_enable_virt(void) { }
+ static inline void amd_pmu_disable_virt(void) { }
+#endif
+
 #endif /* _ASM_X86_PERF_EVENT_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index f7c89e231c6c..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;
 };
 
@@ -454,7 +456,6 @@ 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/prom.h b/arch/x86/include/asm/prom.h
index 644dd885f05a..60bef663609a 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -21,7 +21,6 @@
 #include <asm/irq.h>
 #include <linux/atomic.h>
 #include <asm/setup.h>
-#include <asm/irq_controller.h>
 
 #ifdef CONFIG_OF
 extern int of_ioapic;
@@ -43,15 +42,6 @@ extern char cmd_line[COMMAND_LINE_SIZE];
 #define pci_address_to_pio pci_address_to_pio
 unsigned long pci_address_to_pio(phys_addr_t addr);
 
-/**
- * irq_dispose_mapping - Unmap an interrupt
- * @virq: linux virq number of the interrupt to unmap
- *
- * FIXME: We really should implement proper virq handling like power,
- * but that's going to be major surgery.
- */
-static inline void irq_dispose_mapping(unsigned int virq) { }
-
 #define HAVE_ARCH_DEVTREE_FIXUPS
 
 #endif /* __ASSEMBLY__ */