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>

6 files changed, 87 insertions, 12 deletions

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/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 6b45e5e7a901..73d08ed98a64 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 786e76a86322..e4eeaaf58a47 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 3c44b712380c..f8bddb5b0600 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 513d617b93c4..82db83b5c3bc 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 0397b23be8e9..67250a52430b 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);