Merge branch 'perf/urgent' into perf/core, to pick up dependency

Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d0efb5c..18a1acf 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1201,6 +1201,9 @@
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be performed
 	 * at commit time (->commit_txn) as a whole.
+	 *
+	 * If commit fails, we'll call ->del() on all events
+	 * for which ->add() was called.
 	 */
 	if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
 		goto done_collect;
@@ -1223,6 +1226,14 @@
 	cpuc->n_added += n - n0;
 	cpuc->n_txn += n - n0;
 
+	if (x86_pmu.add) {
+		/*
+		 * This is before x86_pmu_enable() will call x86_pmu_start(),
+		 * so we enable LBRs before an event needs them etc..
+		 */
+		x86_pmu.add(event);
+	}
+
 	ret = 0;
 out:
 	return ret;
@@ -1346,7 +1357,7 @@
 	event->hw.flags &= ~PERF_X86_EVENT_COMMITTED;
 
 	/*
-	 * If we're called during a txn, we don't need to do anything.
+	 * If we're called during a txn, we only need to undo x86_pmu.add.
 	 * The events never got scheduled and ->cancel_txn will truncate
 	 * the event_list.
 	 *
@@ -1354,7 +1365,7 @@
 	 * an event added during that same TXN.
 	 */
 	if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
-		return;
+		goto do_del;
 
 	/*
 	 * Not a TXN, therefore cleanup properly.
@@ -1384,6 +1395,15 @@
 	--cpuc->n_events;
 
 	perf_event_update_userpage(event);
+
+do_del:
+	if (x86_pmu.del) {
+		/*
+		 * This is after x86_pmu_stop(); so we disable LBRs after any
+		 * event can need them etc..
+		 */
+		x86_pmu.del(event);
+	}
 }
 
 int x86_pmu_handle_irq(struct pt_regs *regs)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2cbde2f..88792f8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1907,13 +1907,6 @@
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
-	/*
-	 * must disable before any actual event
-	 * because any event may be combined with LBR
-	 */
-	if (needs_branch_stack(event))
-		intel_pmu_lbr_disable(event);
-
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
@@ -1925,6 +1918,14 @@
 		intel_pmu_pebs_disable(event);
 }
 
+static void intel_pmu_del_event(struct perf_event *event)
+{
+	if (needs_branch_stack(event))
+		intel_pmu_lbr_del(event);
+	if (event->attr.precise_ip)
+		intel_pmu_pebs_del(event);
+}
+
 static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 {
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
@@ -1968,12 +1969,6 @@
 		intel_pmu_enable_bts(hwc->config);
 		return;
 	}
-	/*
-	 * must enabled before any actual event
-	 * because any event may be combined with LBR
-	 */
-	if (needs_branch_stack(event))
-		intel_pmu_lbr_enable(event);
 
 	if (event->attr.exclude_host)
 		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
@@ -1994,6 +1989,14 @@
 	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
+static void intel_pmu_add_event(struct perf_event *event)
+{
+	if (event->attr.precise_ip)
+		intel_pmu_pebs_add(event);
+	if (needs_branch_stack(event))
+		intel_pmu_lbr_add(event);
+}
+
 /*
  * Save and restart an expired event. Called by NMI contexts,
  * so it has to be careful about preempting normal event ops:
@@ -3290,6 +3293,8 @@
 	.enable_all		= intel_pmu_enable_all,
 	.enable			= intel_pmu_enable_event,
 	.disable		= intel_pmu_disable_event,
+	.add			= intel_pmu_add_event,
+	.del			= intel_pmu_del_event,
 	.hw_config		= intel_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ce9f3f..248023f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -806,9 +806,55 @@
 	return &emptyconstraint;
 }
 
-static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
+/*
+ * We need the sched_task callback even for per-cpu events when we use
+ * the large interrupt threshold, such that we can provide PID and TID
+ * to PEBS samples.
+ */
+static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
 {
-	return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
+	return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
+}
+
+static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
+{
+	struct debug_store *ds = cpuc->ds;
+	u64 threshold;
+
+	if (cpuc->n_pebs == cpuc->n_large_pebs) {
+		threshold = ds->pebs_absolute_maximum -
+			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+	} else {
+		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+	}
+
+	ds->pebs_interrupt_threshold = threshold;
+}
+
+static void
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
+{
+	if (needed_cb != pebs_needs_sched_cb(cpuc)) {
+		if (!needed_cb)
+			perf_sched_cb_inc(pmu);
+		else
+			perf_sched_cb_dec(pmu);
+
+		pebs_update_threshold(cpuc);
+	}
+}
+
+void intel_pmu_pebs_add(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	bool needed_cb = pebs_needs_sched_cb(cpuc);
+
+	cpuc->n_pebs++;
+	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+		cpuc->n_large_pebs++;
+
+	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
 }
 
 void intel_pmu_pebs_enable(struct perf_event *event)
@@ -816,12 +862,9 @@
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	struct debug_store *ds = cpuc->ds;
-	bool first_pebs;
-	u64 threshold;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
-	first_pebs = !pebs_is_enabled(cpuc);
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
 
 	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
@@ -830,46 +873,34 @@
 		cpuc->pebs_enabled |= 1ULL << 63;
 
 	/*
-	 * When the event is constrained enough we can use a larger
-	 * threshold and run the event with less frequent PMI.
+	 * Use auto-reload if possible to save a MSR write in the PMI.
+	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
 	 */
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
-		threshold = ds->pebs_absolute_maximum -
-			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
-
-		if (first_pebs)
-			perf_sched_cb_inc(event->ctx->pmu);
-	} else {
-		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
-
-		/*
-		 * If not all events can use larger buffer,
-		 * roll back to threshold = 1
-		 */
-		if (!first_pebs &&
-		    (ds->pebs_interrupt_threshold > threshold))
-			perf_sched_cb_dec(event->ctx->pmu);
-	}
-
-	/* Use auto-reload if possible to save a MSR write in the PMI */
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
 		ds->pebs_event_reset[hwc->idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
 	}
+}
 
-	if (first_pebs || ds->pebs_interrupt_threshold > threshold)
-		ds->pebs_interrupt_threshold = threshold;
+void intel_pmu_pebs_del(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	bool needed_cb = pebs_needs_sched_cb(cpuc);
+
+	cpuc->n_pebs--;
+	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+		cpuc->n_large_pebs--;
+
+	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	struct debug_store *ds = cpuc->ds;
-	bool large_pebs = ds->pebs_interrupt_threshold >
-		ds->pebs_buffer_base + x86_pmu.pebs_record_size;
 
-	if (large_pebs)
+	if (cpuc->n_pebs == cpuc->n_large_pebs)
 		intel_pmu_drain_pebs_buffer();
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
@@ -879,9 +910,6 @@
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
-	if (large_pebs && !pebs_is_enabled(cpuc))
-		perf_sched_cb_dec(event->ctx->pmu);
-
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 707d358..fc6cf21 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -380,7 +380,6 @@
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
 
 	/*
@@ -390,31 +389,21 @@
 	 */
 	task_ctx = ctx ? ctx->task_ctx_data : NULL;
 	if (task_ctx) {
-		if (sched_in) {
+		if (sched_in)
 			__intel_pmu_lbr_restore(task_ctx);
-			cpuc->lbr_context = ctx;
-		} else {
+		else
 			__intel_pmu_lbr_save(task_ctx);
-		}
 		return;
 	}
 
 	/*
-	 * 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.
- 	 */
-	if (sched_in) {
+	 * Since a context switch can flip the address space and LBR entries
+	 * are not tagged with an identifier, we need to wipe the LBR, even for
+	 * per-cpu events. You simply cannot resolve the branches from the old
+	 * address space.
+	 */
+	if (sched_in)
 		intel_pmu_lbr_reset();
-		cpuc->lbr_context = ctx;
-	}
 }
 
 static inline bool branch_user_callstack(unsigned br_sel)
@@ -422,7 +411,7 @@
 	return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK);
 }
 
-void intel_pmu_lbr_enable(struct perf_event *event)
+void intel_pmu_lbr_add(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
@@ -430,27 +419,38 @@
 	if (!x86_pmu.lbr_nr)
 		return;
 
-	/*
-	 * Reset the LBR stack if we changed task context to
-	 * avoid data leaks.
-	 */
-	if (event->ctx->task && cpuc->lbr_context != event->ctx) {
-		intel_pmu_lbr_reset();
-		cpuc->lbr_context = event->ctx;
-	}
 	cpuc->br_sel = event->hw.branch_reg.reg;
 
-	if (branch_user_callstack(cpuc->br_sel) && event->ctx &&
-					event->ctx->task_ctx_data) {
+	if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) {
 		task_ctx = event->ctx->task_ctx_data;
 		task_ctx->lbr_callstack_users++;
 	}
 
-	cpuc->lbr_users++;
+	/*
+	 * Request pmu::sched_task() callback, which will fire inside the
+	 * regular perf event scheduling, so that call will:
+	 *
+	 *  - restore or wipe; when LBR-callstack,
+	 *  - wipe; otherwise,
+	 *
+	 * when this is from __perf_event_task_sched_in().
+	 *
+	 * However, if this is from perf_install_in_context(), no such callback
+	 * will follow and we'll need to reset the LBR here if this is the
+	 * first LBR event.
+	 *
+	 * The problem is, we cannot tell these cases apart... but we can
+	 * exclude the biggest chunk of cases by looking at
+	 * event->total_time_running. An event that has accrued runtime cannot
+	 * be 'new'. Conversely, a new event can get installed through the
+	 * context switch path for the first time.
+	 */
 	perf_sched_cb_inc(event->ctx->pmu);
+	if (!cpuc->lbr_users++ && !event->total_time_running)
+		intel_pmu_lbr_reset();
 }
 
-void intel_pmu_lbr_disable(struct perf_event *event)
+void intel_pmu_lbr_del(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
@@ -467,12 +467,6 @@
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
 	perf_sched_cb_dec(event->ctx->pmu);
-
-	if (cpuc->enabled && !cpuc->lbr_users) {
-		__intel_pmu_lbr_disable();
-		/* avoid stale pointer */
-		cpuc->lbr_context = NULL;
-	}
 }
 
 void intel_pmu_lbr_enable_all(bool pmi)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8c4a477..5874d8d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -194,12 +194,13 @@
 	 */
 	struct debug_store	*ds;
 	u64			pebs_enabled;
+	int			n_pebs;
+	int			n_large_pebs;
 
 	/*
 	 * Intel LBR bits
 	 */
 	int				lbr_users;
-	void				*lbr_context;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
@@ -508,6 +509,8 @@
 	void		(*enable_all)(int added);
 	void		(*enable)(struct perf_event *);
 	void		(*disable)(struct perf_event *);
+	void		(*add)(struct perf_event *);
+	void		(*del)(struct perf_event *);
 	int		(*hw_config)(struct perf_event *event);
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
@@ -888,6 +891,10 @@
 
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
+void intel_pmu_pebs_add(struct perf_event *event);
+
+void intel_pmu_pebs_del(struct perf_event *event);
+
 void intel_pmu_pebs_enable(struct perf_event *event);
 
 void intel_pmu_pebs_disable(struct perf_event *event);
@@ -906,9 +913,9 @@
 
 void intel_pmu_lbr_reset(void);
 
-void intel_pmu_lbr_enable(struct perf_event *event);
+void intel_pmu_lbr_add(struct perf_event *event);
 
-void intel_pmu_lbr_disable(struct perf_event *event);
+void intel_pmu_lbr_del(struct perf_event *event);
 
 void intel_pmu_lbr_enable_all(bool pmi);
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2b6b43c..529c41f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -774,6 +774,9 @@
 #ifdef CONFIG_CGROUP_PERF
 	struct perf_cgroup		*cgrp;
 #endif
+
+	struct list_head		sched_cb_entry;
+	int				sched_cb_usage;
 };
 
 struct perf_output_handle {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1903b8f..803481c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1796,6 +1796,8 @@
 	struct perf_event *event;
 	int state = group_event->state;
 
+	perf_pmu_disable(ctx->pmu);
+
 	event_sched_out(group_event, cpuctx, ctx);
 
 	/*
@@ -1804,6 +1806,8 @@
 	list_for_each_entry(event, &group_event->sibling_list, group_entry)
 		event_sched_out(event, cpuctx, ctx);
 
+	perf_pmu_enable(ctx->pmu);
+
 	if (state == PERF_EVENT_STATE_ACTIVE && group_event->attr.exclusive)
 		cpuctx->exclusive = 0;
 }
@@ -2801,19 +2805,36 @@
 	}
 }
 
+static DEFINE_PER_CPU(struct list_head, sched_cb_list);
+
 void perf_sched_cb_dec(struct pmu *pmu)
 {
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
 	this_cpu_dec(perf_sched_cb_usages);
+
+	if (!--cpuctx->sched_cb_usage)
+		list_del(&cpuctx->sched_cb_entry);
 }
 
+
 void perf_sched_cb_inc(struct pmu *pmu)
 {
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+	if (!cpuctx->sched_cb_usage++)
+		list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
+
 	this_cpu_inc(perf_sched_cb_usages);
 }
 
 /*
  * This function provides the context switch callback to the lower code
  * layer. It is invoked ONLY when the context switch callback is enabled.
+ *
+ * This callback is relevant even to per-cpu events; for example multi event
+ * PEBS requires this to provide PID/TID information. This requires we flush
+ * all queued PEBS records before we context switch to a new task.
  */
 static void perf_pmu_sched_task(struct task_struct *prev,
 				struct task_struct *next,
@@ -2821,34 +2842,24 @@
 {
 	struct perf_cpu_context *cpuctx;
 	struct pmu *pmu;
-	unsigned long flags;
 
 	if (prev == next)
 		return;
 
-	local_irq_save(flags);
+	list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
+		pmu = cpuctx->unique_pmu; /* software PMUs will not have sched_task */
 
-	rcu_read_lock();
+		if (WARN_ON_ONCE(!pmu->sched_task))
+			continue;
 
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		if (pmu->sched_task) {
-			cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+		perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+		perf_pmu_disable(pmu);
 
-			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+		pmu->sched_task(cpuctx->task_ctx, sched_in);
 
-			perf_pmu_disable(pmu);
-
-			pmu->sched_task(cpuctx->task_ctx, sched_in);
-
-			perf_pmu_enable(pmu);
-
-			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
-		}
+		perf_pmu_enable(pmu);
+		perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 	}
-
-	rcu_read_unlock();
-
-	local_irq_restore(flags);
 }
 
 static void perf_event_switch(struct task_struct *task,
@@ -10385,6 +10396,8 @@
 
 		INIT_LIST_HEAD(&per_cpu(pmu_sb_events.list, cpu));
 		raw_spin_lock_init(&per_cpu(pmu_sb_events.lock, cpu));
+
+		INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
 	}
 }