Merge branch 'perf/urgent' into perf/core, to pick up dependent patches and fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 60 insertions, 18 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 45ad0f608349..6ccf363d73cc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4993,7 +4993,7 @@ static struct perf_event_pmu_context *
 find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 		     struct perf_event *event)
 {
-	struct perf_event_pmu_context *new = NULL, *epc;
+	struct perf_event_pmu_context *new = NULL, *pos = NULL, *epc;
 	void *task_ctx_data = NULL;
 
 	if (!ctx->task) {
@@ -5050,12 +5050,19 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 			atomic_inc(&epc->refcount);
 			goto found_epc;
 		}
+		/* Make sure the pmu_ctx_list is sorted by PMU type: */
+		if (!pos && epc->pmu->type > pmu->type)
+			pos = epc;
 	}
 
 	epc = new;
 	new = NULL;
 
-	list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
+	if (!pos)
+		list_add_tail(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
+	else
+		list_add(&epc->pmu_ctx_entry, pos->pmu_ctx_entry.prev);
+
 	epc->ctx = ctx;
 
 found_epc:
@@ -6005,14 +6012,15 @@ static int _perf_event_period(struct perf_event *event, u64 value)
 	if (!value)
 		return -EINVAL;
 
-	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
-		return -EINVAL;
-
-	if (perf_event_check_period(event, value))
-		return -EINVAL;
-
-	if (!event->attr.freq && (value & (1ULL << 63)))
-		return -EINVAL;
+	if (event->attr.freq) {
+		if (value > sysctl_perf_event_sample_rate)
+			return -EINVAL;
+	} else {
+		if (perf_event_check_period(event, value))
+			return -EINVAL;
+		if (value & (1ULL << 63))
+			return -EINVAL;
+	}
 
 	event_function_call(event, __perf_event_period, &value);
 
@@ -8365,7 +8373,8 @@ void perf_event_exec(void)
 
 	perf_event_enable_on_exec(ctx);
 	perf_event_remove_on_exec(ctx);
-	perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true);
+	scoped_guard(rcu)
+		perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true);
 
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
@@ -11865,6 +11874,21 @@ free_dev:
 static struct lock_class_key cpuctx_mutex;
 static struct lock_class_key cpuctx_lock;
 
+static bool idr_cmpxchg(struct idr *idr, unsigned long id, void *old, void *new)
+{
+	void *tmp, *val = idr_find(idr, id);
+
+	if (val != old)
+		return false;
+
+	tmp = idr_replace(idr, new, id);
+	if (IS_ERR(tmp))
+		return false;
+
+	WARN_ON_ONCE(tmp != val);
+	return true;
+}
+
 int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 {
 	int cpu, ret, max = PERF_TYPE_MAX;
@@ -11891,7 +11915,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 	if (type >= 0)
 		max = type;
 
-	ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL);
+	ret = idr_alloc(&pmu_idr, NULL, max, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto free_pdc;
 
@@ -11899,6 +11923,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 
 	type = ret;
 	pmu->type = type;
+	atomic_set(&pmu->exclusive_cnt, 0);
 
 	if (pmu_bus_running && !pmu->dev) {
 		ret = pmu_dev_alloc(pmu);
@@ -11947,14 +11972,22 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;
 
+	/*
+	 * Now that the PMU is complete, make it visible to perf_try_init_event().
+	 */
+	if (!idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu))
+		goto free_context;
 	list_add_rcu(&pmu->entry, &pmus);
-	atomic_set(&pmu->exclusive_cnt, 0);
+
 	ret = 0;
 unlock:
 	mutex_unlock(&pmus_lock);
 
 	return ret;
 
+free_context:
+	free_percpu(pmu->cpu_pmu_context);
+
 free_dev:
 	if (pmu->dev && pmu->dev != PMU_NULL_DEV) {
 		device_del(pmu->dev);
@@ -11974,6 +12007,8 @@ void perf_pmu_unregister(struct pmu *pmu)
 {
 	mutex_lock(&pmus_lock);
 	list_del_rcu(&pmu->entry);
+	idr_remove(&pmu_idr, pmu->type);
+	mutex_unlock(&pmus_lock);
 
 	/*
 	 * We dereference the pmu list under both SRCU and regular RCU, so
@@ -11983,7 +12018,6 @@ void perf_pmu_unregister(struct pmu *pmu)
 	synchronize_rcu();
 
 	free_percpu(pmu->pmu_disable_count);
-	idr_remove(&pmu_idr, pmu->type);
 	if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) {
 		if (pmu->nr_addr_filters)
 			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
@@ -11991,7 +12025,6 @@ void perf_pmu_unregister(struct pmu *pmu)
 		put_device(pmu->dev);
 	}
 	free_pmu_context(pmu);
-	mutex_unlock(&pmus_lock);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index e783da1d1762..921ad9162136 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -495,6 +495,11 @@ retry:
 	if (ret <= 0)
 		goto put_old;
 
+	if (is_zero_page(old_page)) {
+		ret = -EINVAL;
+		goto put_old;
+	}
+
 	if (WARN(!is_register && PageCompound(old_page),
 		 "uprobe unregister should never work on compound page\n")) {
 		ret = -EINVAL;
@@ -762,10 +767,14 @@ static struct uprobe *hprobe_expire(struct hprobe *hprobe, bool get)
 	enum hprobe_state hstate;
 
 	/*
-	 * return_instance's hprobe is protected by RCU.
-	 * Underlying uprobe is itself protected from reuse by SRCU.
+	 * Caller should guarantee that return_instance is not going to be
+	 * freed from under us. This can be achieved either through holding
+	 * rcu_read_lock() or by owning return_instance in the first place.
+	 *
+	 * Underlying uprobe is itself protected from reuse by SRCU, so ensure
+	 * SRCU lock is held properly.
 	 */
-	lockdep_assert(rcu_read_lock_held() && srcu_read_lock_held(&uretprobes_srcu));
+	lockdep_assert(srcu_read_lock_held(&uretprobes_srcu));
 
 	hstate = READ_ONCE(hprobe->state);
 	switch (hstate) {