Merge branch 'perf/hw-branch-sampling' into perf/core

Merge reason: The 'perf record -b' hardware branch sampling feature is ready for upstream.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 183 insertions, 0 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index e8b32ac75ce3..c61234b1a988 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -118,6 +118,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 		       PERF_FLAG_FD_OUTPUT  |\
 		       PERF_FLAG_PID_CGROUP)
 
+/*
+ * branch priv levels that need permission checks
+ */
+#define PERF_SAMPLE_BRANCH_PERM_PLM \
+	(PERF_SAMPLE_BRANCH_KERNEL |\
+	 PERF_SAMPLE_BRANCH_HV)
+
 enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
@@ -130,6 +137,7 @@ enum event_type_t {
  */
 struct static_key_deferred perf_sched_events __read_mostly;
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
@@ -881,6 +889,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (is_cgroup_event(event))
 		ctx->nr_cgroups++;
 
+	if (has_branch_stack(event))
+		ctx->nr_branch_stack++;
+
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	if (!ctx->nr_events)
 		perf_pmu_rotate_start(ctx->pmu);
@@ -1020,6 +1031,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 			cpuctx->cgrp = NULL;
 	}
 
+	if (has_branch_stack(event))
+		ctx->nr_branch_stack--;
+
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
@@ -2195,6 +2209,66 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 }
 
 /*
+ * When sampling the branck stack in system-wide, it may be necessary
+ * to flush the stack on context switch. This happens when the branch
+ * stack does not tag its entries with the pid of the current task.
+ * Otherwise it becomes impossible to associate a branch entry with a
+ * task. This ambiguity is more likely to appear when the branch stack
+ * supports priv level filtering and the user sets it to monitor only
+ * at the user level (which could be a useful measurement in system-wide
+ * mode). In that case, the risk is high of having a branch stack with
+ * branch from multiple tasks. Flushing may mean dropping the existing
+ * entries or stashing them somewhere in the PMU specific code layer.
+ *
+ * This function provides the context switch callback to the lower code
+ * layer. It is invoked ONLY when there is at least one system-wide context
+ * with at least one active event using taken branch sampling.
+ */
+static void perf_branch_stack_sched_in(struct task_struct *prev,
+				       struct task_struct *task)
+{
+	struct perf_cpu_context *cpuctx;
+	struct pmu *pmu;
+	unsigned long flags;
+
+	/* no need to flush branch stack if not changing task */
+	if (prev == task)
+		return;
+
+	local_irq_save(flags);
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+		/*
+		 * check if the context has at least one
+		 * event using PERF_SAMPLE_BRANCH_STACK
+		 */
+		if (cpuctx->ctx.nr_branch_stack > 0
+		    && pmu->flush_branch_stack) {
+
+			pmu = cpuctx->ctx.pmu;
+
+			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+			perf_pmu_disable(pmu);
+
+			pmu->flush_branch_stack();
+
+			perf_pmu_enable(pmu);
+
+			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+		}
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
+/*
  * Called from scheduler to add the events of the current task
  * with interrupts disabled.
  *
@@ -2225,6 +2299,10 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	 */
 	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
 		perf_cgroup_sched_in(prev, task);
+
+	/* check for system-wide branch_stack events */
+	if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
+		perf_branch_stack_sched_in(prev, task);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -2791,6 +2869,14 @@ static void free_event(struct perf_event *event)
 			atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
 			static_key_slow_dec_deferred(&perf_sched_events);
 		}
+
+		if (has_branch_stack(event)) {
+			static_key_slow_dec_deferred(&perf_sched_events);
+			/* is system-wide event */
+			if (!(event->attach_state & PERF_ATTACH_TASK))
+				atomic_dec(&per_cpu(perf_branch_stack_events,
+						    event->cpu));
+		}
 	}
 
 	if (event->rb) {
@@ -3907,6 +3993,24 @@ void perf_output_sample(struct perf_output_handle *handle,
 			}
 		}
 	}
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		if (data->br_stack) {
+			size_t size;
+
+			size = data->br_stack->nr
+			     * sizeof(struct perf_branch_entry);
+
+			perf_output_put(handle, data->br_stack->nr);
+			perf_output_copy(handle, data->br_stack->entries, size);
+		} else {
+			/*
+			 * we always store at least the value of nr
+			 */
+			u64 nr = 0;
+			perf_output_put(handle, nr);
+		}
+	}
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
@@ -3949,6 +4053,15 @@ void perf_prepare_sample(struct perf_event_header *header,
 		WARN_ON_ONCE(size & (sizeof(u64)-1));
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		int size = sizeof(u64); /* nr */
+		if (data->br_stack) {
+			size += data->br_stack->nr
+			      * sizeof(struct perf_branch_entry);
+		}
+		header->size += size;
+	}
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -5010,6 +5123,12 @@ static int perf_swevent_init(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_SOFTWARE)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	switch (event_id) {
 	case PERF_COUNT_SW_CPU_CLOCK:
 	case PERF_COUNT_SW_TASK_CLOCK:
@@ -5120,6 +5239,12 @@ static int perf_tp_event_init(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for tracepoint events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	err = perf_trace_init(event);
 	if (err)
 		return err;
@@ -5345,6 +5470,12 @@ static int cpu_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	perf_swevent_init_hrtimer(event);
 
 	return 0;
@@ -5419,6 +5550,12 @@ static int task_clock_event_init(struct perf_event *event)
 	if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for software events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	perf_swevent_init_hrtimer(event);
 
 	return 0;
@@ -5866,6 +6003,12 @@ done:
 				return ERR_PTR(err);
 			}
 		}
+		if (has_branch_stack(event)) {
+			static_key_slow_inc(&perf_sched_events.key);
+			if (!(event->attach_state & PERF_ATTACH_TASK))
+				atomic_inc(&per_cpu(perf_branch_stack_events,
+						    event->cpu));
+		}
 	}
 
 	return event;
@@ -5935,6 +6078,40 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (attr->read_format & ~(PERF_FORMAT_MAX-1))
 		return -EINVAL;
 
+	if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		u64 mask = attr->branch_sample_type;
+
+		/* only using defined bits */
+		if (mask & ~(PERF_SAMPLE_BRANCH_MAX-1))
+			return -EINVAL;
+
+		/* at least one branch bit must be set */
+		if (!(mask & ~PERF_SAMPLE_BRANCH_PLM_ALL))
+			return -EINVAL;
+
+		/* kernel level capture: check permissions */
+		if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM)
+		    && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
+
+		/* propagate priv level, when not set for branch */
+		if (!(mask & PERF_SAMPLE_BRANCH_PLM_ALL)) {
+
+			/* exclude_kernel checked on syscall entry */
+			if (!attr->exclude_kernel)
+				mask |= PERF_SAMPLE_BRANCH_KERNEL;
+
+			if (!attr->exclude_user)
+				mask |= PERF_SAMPLE_BRANCH_USER;
+
+			if (!attr->exclude_hv)
+				mask |= PERF_SAMPLE_BRANCH_HV;
+			/*
+			 * adjust user setting (for HW filter setup)
+			 */
+			attr->branch_sample_type = mask;
+		}
+	}
 out:
 	return ret;
 
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 3330022a7ac1..bb38c4d3ee12 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -581,6 +581,12 @@ static int hw_breakpoint_event_init(struct perf_event *bp)
 	if (bp->attr.type != PERF_TYPE_BREAKPOINT)
 		return -ENOENT;
 
+	/*
+	 * no branch sampling for breakpoint events
+	 */
+	if (has_branch_stack(bp))
+		return -EOPNOTSUPP;
+
 	err = register_perf_hw_breakpoint(bp);
 	if (err)
 		return err;