6 files changed, 48 insertions, 33 deletions

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index bfc8f43909c1..4823695c459f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2118,7 +2118,7 @@ static int x86_pmu_event_init(struct perf_event *event)
         }
 
         if (READ_ONCE(x86_pmu.attr_rdpmc) &&
-            !(event->hw.flags & PERF_X86_EVENT_FREERUNNING))
+            !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS))
                 event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED;
 
         return err;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 41c68d337e84..607bf565a90c 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2968,9 +2968,9 @@ static void intel_pebs_aliases_skl(struct perf_event *event)
         return intel_pebs_aliases_precdist(event);
 }
 
-static unsigned long intel_pmu_free_running_flags(struct perf_event *event)
+static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 {
-        unsigned long flags = x86_pmu.free_running_flags;
+        unsigned long flags = x86_pmu.large_pebs_flags;
 
         if (event->attr.use_clockid)
                 flags &= ~PERF_SAMPLE_TIME;
@@ -2992,8 +2992,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
                 if (!event->attr.freq) {
                         event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
                         if (!(event->attr.sample_type &
-                              ~intel_pmu_free_running_flags(event)))
-                                event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+                              ~intel_pmu_large_pebs_flags(event)))
+                                event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
                 }
                 if (x86_pmu.pebs_aliases)
                         x86_pmu.pebs_aliases(event);
@@ -3210,7 +3210,7 @@ static u64 bdw_limit_period(struct perf_event *event, u64 left)
                         X86_CONFIG(.event=0xc0, .umask=0x01)) {
                 if (left < 128)
                         left = 128;
-                left &= ~0x3fu;
+                left &= ~0x3fULL;
         }
         return left;
 }
@@ -3476,7 +3476,7 @@ static __initconst const struct x86_pmu core_pmu = {
         .event_map              = intel_pmu_event_map,
         .max_events             = ARRAY_SIZE(intel_perfmon_event_map),
         .apic                   = 1,
-        .free_running_flags     = PEBS_FREERUNNING_FLAGS,
+        .large_pebs_flags       = LARGE_PEBS_FLAGS,
 
         /*
          * Intel PMCs cannot be accessed sanely above 32-bit width,
@@ -3519,7 +3519,7 @@ static __initconst const struct x86_pmu intel_pmu = {
         .event_map              = intel_pmu_event_map,
         .max_events             = ARRAY_SIZE(intel_perfmon_event_map),
         .apic                   = 1,
-        .free_running_flags     = PEBS_FREERUNNING_FLAGS,
+        .large_pebs_flags       = LARGE_PEBS_FLAGS,
         /*
          * Intel PMCs cannot be accessed sanely above 32 bit width,
          * so we install an artificial 1<<31 period regardless of
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 73844025adaf..209bf7c16443 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -935,7 +935,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
         bool needed_cb = pebs_needs_sched_cb(cpuc);
 
         cpuc->n_pebs++;
-        if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+        if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
                 cpuc->n_large_pebs++;
 
         pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -975,7 +975,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
         bool needed_cb = pebs_needs_sched_cb(cpuc);
 
         cpuc->n_pebs--;
-        if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+        if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
                 cpuc->n_large_pebs--;
 
         pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -1623,7 +1623,7 @@ void __init intel_ds_init(void)
                         x86_pmu.pebs_record_size =
                                                 sizeof(struct pebs_record_skl);
                         x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
-                        x86_pmu.free_running_flags |= PERF_SAMPLE_TIME;
+                        x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
                         break;
 
                 default:
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 22ec65bc033a..c98b943e58b4 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3343,6 +3343,7 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = {
         SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4),
         SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8),
         SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8),
+        SNBEP_CBO_EVENT_EXTRA_REG(0x38, 0xff, 0x3),
         EVENT_EXTRA_END
 };
 
@@ -3562,24 +3563,27 @@ static struct intel_uncore_type *skx_msr_uncores[] = {
         NULL,
 };
 
+/*
+ * To determine the number of CHAs, it should read bits 27:0 in the CAPID6
+ * register which located at Device 30, Function 3, Offset 0x9C. PCI ID 0x2083.
+ */
+#define SKX_CAPID6              0x9c
+#define SKX_CHA_BIT_MASK        GENMASK(27, 0)
+
 static int skx_count_chabox(void)
 {
-        struct pci_dev *chabox_dev = NULL;
-        int bus, count = 0;
+        struct pci_dev *dev = NULL;
+        u32 val = 0;
 
-        while (1) {
-                chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev);
-                if (!chabox_dev)
-                        break;
-                if (count == 0)
-                        bus = chabox_dev->bus->number;
-                if (bus != chabox_dev->bus->number)
-                        break;
-                count++;
-        }
+        dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2083, dev);
+        if (!dev)
+                goto out;
 
-        pci_dev_put(chabox_dev);
-        return count;
+        pci_read_config_dword(dev, SKX_CAPID6, &val);
+        val &= SKX_CHA_BIT_MASK;
+out:
+        pci_dev_put(dev);
+        return hweight32(val);
 }
 
 void skx_uncore_cpu_init(void)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 91643472f385..9f3711470ec1 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -69,7 +69,7 @@ struct event_constraint {
 #define PERF_X86_EVENT_RDPMC_ALLOWED    0x0100 /* grant rdpmc permission */
 #define PERF_X86_EVENT_EXCL_ACCT        0x0200 /* accounted EXCL event */
 #define PERF_X86_EVENT_AUTO_RELOAD      0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_FREERUNNING      0x0800 /* use freerunning PEBS */
+#define PERF_X86_EVENT_LARGE_PEBS       0x0800 /* use large PEBS */
 
 
 struct amd_nb {
@@ -88,7 +88,7 @@ struct amd_nb {
  * REGS_USER can be handled for events limited to ring 3.
  *
  */
-#define PEBS_FREERUNNING_FLAGS \
+#define LARGE_PEBS_FLAGS \
         (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
         PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
         PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
@@ -609,7 +609,7 @@ struct x86_pmu {
         struct event_constraint *pebs_constraints;
         void            (*pebs_aliases)(struct perf_event *event);
         int             max_pebs_events;
-        unsigned long   free_running_flags;
+        unsigned long   large_pebs_flags;
 
         /*
          * Intel LBR
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 74a6e8f12a3c..7517b4fb3ef4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -724,9 +724,15 @@ static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
 
 static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
 {
-        struct perf_cgroup *cgrp_out = cpuctx->cgrp;
-        if (cgrp_out)
-                __update_cgrp_time(cgrp_out);
+        struct perf_cgroup *cgrp = cpuctx->cgrp;
+        struct cgroup_subsys_state *css;
+
+        if (cgrp) {
+                for (css = &cgrp->css; css; css = css->parent) {
+                        cgrp = container_of(css, struct perf_cgroup, css);
+                        __update_cgrp_time(cgrp);
+                }
+        }
 }
 
 static inline void update_cgrp_time_from_event(struct perf_event *event)
@@ -754,6 +760,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 {
         struct perf_cgroup *cgrp;
         struct perf_cgroup_info *info;
+        struct cgroup_subsys_state *css;
 
         /*
          * ctx->lock held by caller
@@ -764,8 +771,12 @@ perf_cgroup_set_timestamp(struct task_struct *task,
                 return;
 
         cgrp = perf_cgroup_from_task(task, ctx);
-        info = this_cpu_ptr(cgrp->info);
-        info->timestamp = ctx->timestamp;
+
+        for (css = &cgrp->css; css; css = css->parent) {
+                cgrp = container_of(css, struct perf_cgroup, css);
+                info = this_cpu_ptr(cgrp->info);
+                info->timestamp = ctx->timestamp;
+        }
 }
 
 static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);