Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Ingo writes:
  "perf fixes:
    - fix a CPU#0 hot unplug bug and a PCI enumeration bug in the x86 Intel uncore PMU driver
    - fix a CPU event enumeration bug in the x86 AMD PMU driver
    - fix a perf ring-buffer corruption bug when using tracepoints
    - fix a PMU unregister locking bug"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/amd/uncore: Set ThreadMask and SliceMask for L3 Cache perf events
  perf/x86/intel/uncore: Fix PCI BDF address of M3UPI on SKX
  perf/ring_buffer: Prevent concurent ring buffer access
  perf/x86/intel/uncore: Use boot_cpu_data.phys_proc_id instead of hardcorded physical package ID 0
  perf/core: Fix perf_pmu_unregister() locking

4 files changed, 29 insertions, 14 deletions

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 981ba5e8241b..8671de126eac 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -36,6 +36,7 @@
 
 static int num_counters_llc;
 static int num_counters_nb;
+static bool l3_mask;
 
 static HLIST_HEAD(uncore_unused_list);
 
@@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event)
 	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
 	hwc->idx = -1;
 
+	/*
+	 * SliceMask and ThreadMask need to be set for certain L3 events in
+	 * Family 17h. For other events, the two fields do not affect the count.
+	 */
+	if (l3_mask)
+		hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK);
+
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -525,6 +533,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l3";
 		format_attr_event_df.show = &event_show_df;
 		format_attr_event_l3.show = &event_show_l3;
+		l3_mask			  = true;
 	} else {
 		num_counters_nb		  = NUM_COUNTERS_NB;
 		num_counters_llc	  = NUM_COUNTERS_L2;
@@ -532,6 +541,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l2";
 		format_attr_event_df	  = format_attr_event;
 		format_attr_event_l3	  = format_attr_event;
+		l3_mask			  = false;
 	}
 
 	amd_nb_pmu.attr_groups	= amd_uncore_attr_groups_df;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 51d7c117e3c7..c07bee31abe8 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3061,7 +3061,7 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
 
 void bdx_uncore_cpu_init(void)
 {
-	int pkg = topology_phys_to_logical_pkg(0);
+	int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id);
 
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
@@ -3931,16 +3931,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = {
 		.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3),
 	},
 	{ /* M3UPI0 Link 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0),
 	},
 	{ /* M3UPI0 Link 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1),
 	},
 	{ /* M3UPI1 Link 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2),
 	},
 	{ /* end: all zeroes */ }
 };
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 12f54082f4c8..78241b736f2a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -46,6 +46,14 @@
 #define INTEL_ARCH_EVENT_MASK	\
 	(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
 
+#define AMD64_L3_SLICE_SHIFT				48
+#define AMD64_L3_SLICE_MASK				\
+	((0xFULL) << AMD64_L3_SLICE_SHIFT)
+
+#define AMD64_L3_THREAD_SHIFT				56
+#define AMD64_L3_THREAD_MASK				\
+	((0xFFULL) << AMD64_L3_THREAD_SHIFT)
+
 #define X86_RAW_EVENT_MASK		\
 	(ARCH_PERFMON_EVENTSEL_EVENT |	\
 	 ARCH_PERFMON_EVENTSEL_UMASK |	\
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dcb093e7b377..5a97f34bc14c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8314,6 +8314,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 			goto unlock;
 
 		list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+			if (event->cpu != smp_processor_id())
+				continue;
 			if (event->attr.type != PERF_TYPE_TRACEPOINT)
 				continue;
 			if (event->attr.config != entry->type)
@@ -9431,9 +9433,7 @@ static void free_pmu_context(struct pmu *pmu)
 	if (pmu->task_ctx_nr > perf_invalid_context)
 		return;
 
-	mutex_lock(&pmus_lock);
 	free_percpu(pmu->pmu_cpu_context);
-	mutex_unlock(&pmus_lock);
 }
 
 /*
@@ -9689,12 +9689,8 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
-	int remove_device;
-
 	mutex_lock(&pmus_lock);
-	remove_device = pmu_bus_running;
 	list_del_rcu(&pmu->entry);
-	mutex_unlock(&pmus_lock);
 
 	/*
 	 * We dereference the pmu list under both SRCU and regular RCU, so
@@ -9706,13 +9702,14 @@ void perf_pmu_unregister(struct pmu *pmu)
 	free_percpu(pmu->pmu_disable_count);
 	if (pmu->type >= PERF_TYPE_MAX)
 		idr_remove(&pmu_idr, pmu->type);
-	if (remove_device) {
+	if (pmu_bus_running) {
 		if (pmu->nr_addr_filters)
 			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
 		device_del(pmu->dev);
 		put_device(pmu->dev);
 	}
 	free_pmu_context(pmu);
+	mutex_unlock(&pmus_lock);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);