7 files changed, 50 insertions, 38 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index f5f4b3fbbbc2..afb222b63cae 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -662,7 +662,13 @@ static int __init amd_core_pmu_init(void)
                 pr_cont("Fam15h ");
                 x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
                 break;
-
+        case 0x17:
+                pr_cont("Fam17h ");
+                /*
+                 * In family 17h, there are no event constraints in the PMC hardware.
+                 * We fallback to using default amd_get_event_constraints.
+                 */
+                break;
         default:
                 pr_err("core perfctr but no constraints; unknown hardware!\n");
                 return -ENODEV;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d31735f37ed7..9d4bf3ab049e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2352,7 +2352,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
                 frame.next_frame     = 0;
                 frame.return_address = 0;
 
-                if (!access_ok(VERIFY_READ, fp, 8))
+                if (!valid_user_frame(fp, sizeof(frame)))
                         break;
 
                 bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4);
@@ -2362,9 +2362,6 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
                 if (bytes != 0)
                         break;
 
-                if (!valid_user_frame(fp, sizeof(frame)))
-                        break;
-
                 perf_callchain_store(entry, cs_base + frame.return_address);
                 fp = compat_ptr(ss_base + frame.next_frame);
         }
@@ -2413,7 +2410,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
                 frame.next_frame             = NULL;
                 frame.return_address = 0;
 
-                if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
+                if (!valid_user_frame(fp, sizeof(frame)))
                         break;
 
                 bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
@@ -2423,9 +2420,6 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
                 if (bytes != 0)
                         break;
 
-                if (!valid_user_frame(fp, sizeof(frame)))
-                        break;
-
                 perf_callchain_store(entry, frame.return_address);
                 fp = (void __user *)frame.next_frame;
         }
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 0319311dbdbb..be202390bbd3 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1108,20 +1108,20 @@ static void setup_pebs_sample_data(struct perf_event *event,
         }
 
         /*
-         * We use the interrupt regs as a base because the PEBS record
-         * does not contain a full regs set, specifically it seems to
-         * lack segment descriptors, which get used by things like
-         * user_mode().
+         * We use the interrupt regs as a base because the PEBS record does not
+         * contain a full regs set, specifically it seems to lack segment
+         * descriptors, which get used by things like user_mode().
          *
-         * In the simple case fix up only the IP and BP,SP regs, for
-         * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
-         * A possible PERF_SAMPLE_REGS will have to transfer all regs.
+         * In the simple case fix up only the IP for PERF_SAMPLE_IP.
+         *
+         * We must however always use BP,SP from iregs for the unwinder to stay
+         * sane; the record BP,SP can point into thin air when the record is
+         * from a previous PMI context or an (I)RET happend between the record
+         * and PMI.
          */
         *regs = *iregs;
         regs->flags = pebs->flags;
         set_linear_ip(regs, pebs->ip);
-        regs->bp = pebs->bp;
-        regs->sp = pebs->sp;
 
         if (sample_type & PERF_SAMPLE_REGS_INTR) {
                 regs->ax = pebs->ax;
@@ -1130,10 +1130,21 @@ static void setup_pebs_sample_data(struct perf_event *event,
                 regs->dx = pebs->dx;
                 regs->si = pebs->si;
                 regs->di = pebs->di;
-                regs->bp = pebs->bp;
-                regs->sp = pebs->sp;
 
-                regs->flags = pebs->flags;
+                /*
+                 * Per the above; only set BP,SP if we don't need callchains.
+                 *
+                 * XXX: does this make sense?
+                 */
+                if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+                        regs->bp = pebs->bp;
+                        regs->sp = pebs->sp;
+                }
+
+                /*
+                 * Preserve PERF_EFLAGS_VM from set_linear_ip().
+                 */
+                regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM);
 #ifndef CONFIG_X86_32
                 regs->r8 = pebs->r8;
                 regs->r9 = pebs->r9;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index efca2685d876..dbaaf7dc8373 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -319,9 +319,9 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
  */
 static int uncore_pmu_event_init(struct perf_event *event);
 
-static bool is_uncore_event(struct perf_event *event)
+static bool is_box_event(struct intel_uncore_box *box, struct perf_event *event)
 {
-        return event->pmu->event_init == uncore_pmu_event_init;
+        return &box->pmu->pmu == event->pmu;
 }
 
 static int
@@ -340,7 +340,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
 
         n = box->n_events;
 
-        if (is_uncore_event(leader)) {
+        if (is_box_event(box, leader)) {
                 box->event_list[n] = leader;
                 n++;
         }
@@ -349,7 +349,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
                 return n;
 
         list_for_each_entry(event, &leader->sibling_list, group_entry) {
-                if (!is_uncore_event(event) ||
+                if (!is_box_event(box, event) ||
                     event->state <= PERF_EVENT_STATE_OFF)
                         continue;
 
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 81195cca7eae..a3dcc12bef4a 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -490,24 +490,12 @@ static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
 
         snb_uncore_imc_event_start(event, 0);
 
-        box->n_events++;
-
         return 0;
 }
 
 static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
 {
-        struct intel_uncore_box *box = uncore_event_to_box(event);
-        int i;
-
         snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
-
-        for (i = 0; i < box->n_events; i++) {
-                if (event == box->event_list[i]) {
-                        --box->n_events;
-                        break;
-                }
-        }
 }
 
 int snb_pci2phy_map_init(int devid)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 5874d8de1f8d..a77ee026643d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -113,7 +113,7 @@ struct debug_store {
  * Per register state.
  */
 struct er_account {
-        raw_spinlock_t          lock;   /* per-core: protect structure */
+        raw_spinlock_t      lock;       /* per-core: protect structure */
         u64                 config;     /* extra MSR config */
         u64                 reg;        /* extra MSR number */
         atomic_t            ref;        /* reference count */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0e292132efac..6ee1febdf6ff 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -902,6 +902,17 @@ list_update_cgroup_event(struct perf_event *event,
          * this will always be called from the right CPU.
          */
         cpuctx = __get_cpu_context(ctx);
+
+        /* Only set/clear cpuctx->cgrp if current task uses event->cgrp. */
+        if (perf_cgroup_from_task(current, ctx) != event->cgrp) {
+                /*
+                 * We are removing the last cpu event in this context.
+                 * If that event is not active in this cpu, cpuctx->cgrp
+                 * should've been cleared by perf_cgroup_switch.
+                 */
+                WARN_ON_ONCE(!add && cpuctx->cgrp);
+                return;
+        }
         cpuctx->cgrp = add ? event->cgrp : NULL;
 }
 
@@ -8018,6 +8029,7 @@ restart:
  * if <size> is not specified, the range is treated as a single address.
  */
 enum {
+        IF_ACT_NONE = -1,
         IF_ACT_FILTER,
         IF_ACT_START,
         IF_ACT_STOP,
@@ -8041,6 +8053,7 @@ static const match_table_t if_tokens = {
         { IF_SRC_KERNEL,        "%u/%u" },
         { IF_SRC_FILEADDR,      "%u@%s" },
         { IF_SRC_KERNELADDR,    "%u" },
+        { IF_ACT_NONE,          NULL },
 };
 
 /*