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

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle on the kernel side were:

   - CPU PMU and uncore driver updates to Intel Snow Ridge, IceLake,
     KabyLake, AmberLake and WhiskeyLake CPUs.

   - Rework the MSR probing infrastructure to make it more robust, make
     it work better on virtualized systems and to better expose it on
     sysfs.

   - Rework PMU attributes group support based on the feedback from
     Greg. The core sysfs patch that adds sysfs_update_groups() was
     acked by Greg.

  There's a lot of perf tooling changes as well, all around the place:

   - vendor updates to Intel, cs-etm (ARM), ARM64, s390,

   - various enhancements to Intel PT tooling support:
      - Improve CBR (Core to Bus Ratio) packets support.
      - Export power and ptwrite events to sqlite and postgresql.
      - Add support for decoding PEBS via PT packets.
      - Add support for samples to contain IPC ratio, collecting cycles
        information from CYC packets, showing the IPC info periodically
      - Allow using time ranges

   - lots of updates to perf pmu, perf stat, perf trace, eBPF support,
     perf record, perf diff, etc. - please see the shortlog and Git log
     for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (252 commits)
  tools arch x86: Sync asm/cpufeatures.h with the with the kernel
  tools build: Check if gettid() is available before providing helper
  perf jvmti: Address gcc string overflow warning for strncpy()
  perf python: Remove -fstack-protector-strong if clang doesn't have it
  perf annotate TUI browser: Do not use member from variable within its own initialization
  perf tests: Fix record+probe_libc_inet_pton.sh for powerpc64
  perf evsel: Do not rely on errno values for precise_ip fallback
  perf thread: Allow references to thread objects after machine__exit()
  perf header: Assign proper ff->ph in perf_event__synthesize_features()
  tools arch kvm: Sync kvm headers with the kernel sources
  perf script: Allow specifying the files to process guest samples
  perf tools metric: Don't include duration_time in group
  perf list: Avoid extra : for --raw metrics
  perf vendor events intel: Metric fixes for SKX/CLX
  perf tools: Fix typos / broken sentences
  perf jevents: Add support for Hisi hip08 L3C PMU aliasing
  perf jevents: Add support for Hisi hip08 HHA PMU aliasing
  perf jevents: Add support for Hisi hip08 DDRC PMU aliasing
  perf pmu: Support more complex PMU event aliasing
  perf diff: Documentation -c cycles option
  ...

1 files changed, 30 insertions, 22 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 29e5f7880a4b..785d708f8553 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2952,6 +2952,12 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	if (!ctx->nr_active || !(is_active & EVENT_ALL))
 		return;
 
+	/*
+	 * If we had been multiplexing, no rotations are necessary, now no events
+	 * are active.
+	 */
+	ctx->rotate_necessary = 0;
+
 	perf_pmu_disable(ctx->pmu);
 	if (is_active & EVENT_PINNED) {
 		list_for_each_entry_safe(event, tmp, &ctx->pinned_active, active_list)
@@ -3319,10 +3325,13 @@ static int flexible_sched_in(struct perf_event *event, void *data)
 		return 0;
 
 	if (group_can_go_on(event, sid->cpuctx, sid->can_add_hw)) {
-		if (!group_sched_in(event, sid->cpuctx, sid->ctx))
-			list_add_tail(&event->active_list, &sid->ctx->flexible_active);
-		else
+		int ret = group_sched_in(event, sid->cpuctx, sid->ctx);
+		if (ret) {
 			sid->can_add_hw = 0;
+			sid->ctx->rotate_necessary = 1;
+			return 0;
+		}
+		list_add_tail(&event->active_list, &sid->ctx->flexible_active);
 	}
 
 	return 0;
@@ -3690,24 +3699,17 @@ ctx_first_active(struct perf_event_context *ctx)
 static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 {
 	struct perf_event *cpu_event = NULL, *task_event = NULL;
-	bool cpu_rotate = false, task_rotate = false;
-	struct perf_event_context *ctx = NULL;
+	struct perf_event_context *task_ctx = NULL;
+	int cpu_rotate, task_rotate;
 
 	/*
 	 * Since we run this from IRQ context, nobody can install new
 	 * events, thus the event count values are stable.
 	 */
 
-	if (cpuctx->ctx.nr_events) {
-		if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
-			cpu_rotate = true;
-	}
-
-	ctx = cpuctx->task_ctx;
-	if (ctx && ctx->nr_events) {
-		if (ctx->nr_events != ctx->nr_active)
-			task_rotate = true;
-	}
+	cpu_rotate = cpuctx->ctx.rotate_necessary;
+	task_ctx = cpuctx->task_ctx;
+	task_rotate = task_ctx ? task_ctx->rotate_necessary : 0;
 
 	if (!(cpu_rotate || task_rotate))
 		return false;
@@ -3716,7 +3718,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 	perf_pmu_disable(cpuctx->ctx.pmu);
 
 	if (task_rotate)
-		task_event = ctx_first_active(ctx);
+		task_event = ctx_first_active(task_ctx);
 	if (cpu_rotate)
 		cpu_event = ctx_first_active(&cpuctx->ctx);
 
@@ -3724,17 +3726,17 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 	 * As per the order given at ctx_resched() first 'pop' task flexible
 	 * and then, if needed CPU flexible.
 	 */
-	if (task_event || (ctx && cpu_event))
-		ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
+	if (task_event || (task_ctx && cpu_event))
+		ctx_sched_out(task_ctx, cpuctx, EVENT_FLEXIBLE);
 	if (cpu_event)
 		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 
 	if (task_event)
-		rotate_ctx(ctx, task_event);
+		rotate_ctx(task_ctx, task_event);
 	if (cpu_event)
 		rotate_ctx(&cpuctx->ctx, cpu_event);
 
-	perf_event_sched_in(cpuctx, ctx, current);
+	perf_event_sched_in(cpuctx, task_ctx, current);
 
 	perf_pmu_enable(cpuctx->ctx.pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
@@ -8535,9 +8537,9 @@ static int perf_tp_event_match(struct perf_event *event,
 	if (event->hw.state & PERF_HES_STOPPED)
 		return 0;
 	/*
-	 * All tracepoints are from kernel-space.
+	 * If exclude_kernel, only trace user-space tracepoints (uprobes)
 	 */
-	if (event->attr.exclude_kernel)
+	if (event->attr.exclude_kernel && !user_mode(regs))
 		return 0;
 
 	if (!perf_tp_filter_match(event, data))
@@ -9877,6 +9879,12 @@ static int pmu_dev_alloc(struct pmu *pmu)
 	if (ret)
 		goto del_dev;
 
+	if (pmu->attr_update)
+		ret = sysfs_update_groups(&pmu->dev->kobj, pmu->attr_update);
+
+	if (ret)
+		goto del_dev;
+
 out:
 	return ret;