Merge branch 'perf/urgent' into perf/core

Conflicts:
	tools/perf/builtin-record.c
	tools/perf/builtin-top.c
	tools/perf/perf.h
	tools/perf/util/top.h

Merge reason: resolve these cherry-picking conflicts.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

12 files changed, 123 insertions, 97 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d43cad74f16..c0f7d68d318 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/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 6b45e5e7a90..73d08ed98a6 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -326,8 +326,7 @@ static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb)
 	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
-static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
-					int index)
+static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index)
 {
 	int node;
 
@@ -725,14 +724,16 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info);
 #define CPUID4_INFO_IDX(x, y)	(&((per_cpu(ici_cpuid4_info, x))[y]))
 
 #ifdef CONFIG_SMP
-static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+
+static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index)
 {
-	struct _cpuid4_info	*this_leaf, *sibling_leaf;
-	unsigned long num_threads_sharing;
-	int index_msb, i, sibling;
+	struct _cpuid4_info *this_leaf;
+	int ret, i, sibling;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
+	ret = 0;
+	if (index == 3) {
+		ret = 1;
 		for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
 			if (!per_cpu(ici_cpuid4_info, i))
 				continue;
@@ -743,8 +744,35 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 				set_bit(sibling, this_leaf->shared_cpu_map);
 			}
 		}
-		return;
+	} else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) {
+		ret = 1;
+		for_each_cpu(i, cpu_sibling_mask(cpu)) {
+			if (!per_cpu(ici_cpuid4_info, i))
+				continue;
+			this_leaf = CPUID4_INFO_IDX(i, index);
+			for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+				if (!cpu_online(sibling))
+					continue;
+				set_bit(sibling, this_leaf->shared_cpu_map);
+			}
+		}
 	}
+
+	return ret;
+}
+
+static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+{
+	struct _cpuid4_info *this_leaf, *sibling_leaf;
+	unsigned long num_threads_sharing;
+	int index_msb, i;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		if (cache_shared_amd_cpu_map_setup(cpu, index))
+			return;
+	}
+
 	this_leaf = CPUID4_INFO_IDX(cpu, index);
 	num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing;
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 786e76a8632..e4eeaaf58a4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -528,6 +528,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 	sprintf(name, "threshold_bank%i", bank);
 
+#ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
 		i = cpumask_first(cpu_llc_shared_mask(cpu));
 
@@ -553,6 +554,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 		goto out;
 	}
+#endif
 
 	b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL);
 	if (!b) {
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3c44b712380..f8bddb5b060 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -988,6 +988,9 @@ static void x86_pmu_start(struct perf_event *event, int flags)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx = event->hw.idx;
 
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
 	if (WARN_ON_ONCE(idx == -1))
 		return;
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 513d617b93c..82db83b5c3b 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -147,7 +147,9 @@ struct cpu_hw_events {
 	/*
 	 * AMD specific bits
 	 */
-	struct amd_nb		*amd_nb;
+	struct amd_nb			*amd_nb;
+	/* Inverted mask of bits to clear in the perf_ctr ctrl registers */
+	u64				perf_ctr_virt_mask;
 
 	void				*kfree_on_online;
 };
@@ -425,9 +427,11 @@ void x86_pmu_disable_all(void);
 static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 					  u64 enable_mask)
 {
+	u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
+
 	if (hwc->extra_reg.reg)
 		wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
-	wrmsrl(hwc->config_base, hwc->config | enable_mask);
+	wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
 }
 
 void x86_pmu_enable_all(int added);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 0397b23be8e..67250a52430 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -1,4 +1,5 @@
 #include <linux/perf_event.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -357,7 +358,9 @@ static void amd_pmu_cpu_starting(int cpu)
 	struct amd_nb *nb;
 	int i, nb_id;
 
-	if (boot_cpu_data.x86_max_cores < 2)
+	cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+
+	if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15)
 		return;
 
 	nb_id = amd_get_nb_id(cpu);
@@ -587,9 +590,9 @@ static __initconst const struct x86_pmu amd_pmu_f15h = {
 	.put_event_constraints	= amd_put_event_constraints,
 
 	.cpu_prepare		= amd_pmu_cpu_prepare,
-	.cpu_starting		= amd_pmu_cpu_starting,
 	.cpu_dead		= amd_pmu_cpu_dead,
 #endif
+	.cpu_starting		= amd_pmu_cpu_starting,
 };
 
 __init int amd_pmu_init(void)
@@ -621,3 +624,33 @@ __init int amd_pmu_init(void)
 
 	return 0;
 }
+
+void amd_pmu_enable_virt(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	cpuc->perf_ctr_virt_mask = 0;
+
+	/* Reload all events */
+	x86_pmu_disable_all();
+	x86_pmu_enable_all(0);
+}
+EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
+
+void amd_pmu_disable_virt(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	/*
+	 * We only mask out the Host-only bit so that host-only counting works
+	 * when SVM is disabled. If someone sets up a guest-only counter when
+	 * SVM is disabled the Guest-only bits still gets set and the counter
+	 * will not count anything.
+	 */
+	cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+
+	/* Reload all events */
+	x86_pmu_disable_all();
+	x86_pmu_enable_all(0);
+}
+EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 3fe8239fd8f..1333d985177 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1532,10 +1532,17 @@ ENTRY(nmi)
 	pushq_cfi %rdx
 
 	/*
+	 * If %cs was not the kernel segment, then the NMI triggered in user
+	 * space, which means it is definitely not nested.
+	 */
+	cmpl $__KERNEL_CS, 16(%rsp)
+	jne first_nmi
+
+	/*
 	 * Check the special variable on the stack to see if NMIs are
 	 * executing.
 	 */
-	cmp $1, -8(%rsp)
+	cmpl $1, -8(%rsp)
 	je nested_nmi
 
 	/*
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index ac0417be913..73465aab28f 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -360,7 +360,6 @@ out:
 static enum ucode_state
 request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
-	pr_info("AMD microcode update via /dev/cpu/microcode not supported\n");
 	return UCODE_ERROR;
 }
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 485204f58cd..c08d1ff12b7 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 9b9fe4a85c8..cfa5c90c01d 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 482ec3af206..4bbe04d9674 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 a3911343976..71109111411 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