1 files changed, 129 insertions, 117 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 55d18791a72d..0aeca5f3c0ac 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -53,6 +53,7 @@
 #include <linux/min_heap.h>
 #include <linux/highmem.h>
 #include <linux/pgtable.h>
+#include <linux/buildid.h>
 
 #include "internal.h"
 
@@ -268,7 +269,7 @@ static void event_function_call(struct perf_event *event, event_f func, void *da
 	if (!event->parent) {
 		/*
 		 * If this is a !child event, we must hold ctx::mutex to
-		 * stabilize the the event->ctx relation. See
+		 * stabilize the event->ctx relation. See
 		 * perf_event_ctx_lock().
 		 */
 		lockdep_assert_held(&ctx->mutex);
@@ -397,6 +398,7 @@ static atomic_t nr_ksymbol_events __read_mostly;
 static atomic_t nr_bpf_events __read_mostly;
 static atomic_t nr_cgroup_events __read_mostly;
 static atomic_t nr_text_poke_events __read_mostly;
+static atomic_t nr_build_id_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -1301,7 +1303,7 @@ static void put_ctx(struct perf_event_context *ctx)
  * life-time rules separate them. That is an exiting task cannot fork, and a
  * spawning task cannot (yet) exit.
  *
- * But remember that that these are parent<->child context relations, and
+ * But remember that these are parent<->child context relations, and
  * migration does not affect children, therefore these two orderings should not
  * interact.
  *
@@ -1440,7 +1442,7 @@ static u64 primary_event_id(struct perf_event *event)
 /*
  * Get the perf_event_context for a task and lock it.
  *
- * This has to cope with with the fact that until it is locked,
+ * This has to cope with the fact that until it is locked,
  * the context could get moved to another task.
  */
 static struct perf_event_context *
@@ -1595,50 +1597,91 @@ static void perf_event_groups_init(struct perf_event_groups *groups)
 	groups->index = 0;
 }
 
+static inline struct cgroup *event_cgroup(const struct perf_event *event)
+{
+	struct cgroup *cgroup = NULL;
+
+#ifdef CONFIG_CGROUP_PERF
+	if (event->cgrp)
+		cgroup = event->cgrp->css.cgroup;
+#endif
+
+	return cgroup;
+}
+
 /*
  * Compare function for event groups;
  *
  * Implements complex key that first sorts by CPU and then by virtual index
  * which provides ordering when rotating groups for the same CPU.
  */
-static bool
-perf_event_groups_less(struct perf_event *left, struct perf_event *right)
+static __always_inline int
+perf_event_groups_cmp(const int left_cpu, const struct cgroup *left_cgroup,
+		      const u64 left_group_index, const struct perf_event *right)
 {
-	if (left->cpu < right->cpu)
-		return true;
-	if (left->cpu > right->cpu)
-		return false;
+	if (left_cpu < right->cpu)
+		return -1;
+	if (left_cpu > right->cpu)
+		return 1;
 
 #ifdef CONFIG_CGROUP_PERF
-	if (left->cgrp != right->cgrp) {
-		if (!left->cgrp || !left->cgrp->css.cgroup) {
-			/*
-			 * Left has no cgroup but right does, no cgroups come
-			 * first.
-			 */
-			return true;
-		}
-		if (!right->cgrp || !right->cgrp->css.cgroup) {
-			/*
-			 * Right has no cgroup but left does, no cgroups come
-			 * first.
-			 */
-			return false;
-		}
-		/* Two dissimilar cgroups, order by id. */
-		if (left->cgrp->css.cgroup->kn->id < right->cgrp->css.cgroup->kn->id)
-			return true;
+	{
+		const struct cgroup *right_cgroup = event_cgroup(right);
 
-		return false;
+		if (left_cgroup != right_cgroup) {
+			if (!left_cgroup) {
+				/*
+				 * Left has no cgroup but right does, no
+				 * cgroups come first.
+				 */
+				return -1;
+			}
+			if (!right_cgroup) {
+				/*
+				 * Right has no cgroup but left does, no
+				 * cgroups come first.
+				 */
+				return 1;
+			}
+			/* Two dissimilar cgroups, order by id. */
+			if (cgroup_id(left_cgroup) < cgroup_id(right_cgroup))
+				return -1;
+
+			return 1;
+		}
 	}
 #endif
 
-	if (left->group_index < right->group_index)
-		return true;
-	if (left->group_index > right->group_index)
-		return false;
+	if (left_group_index < right->group_index)
+		return -1;
+	if (left_group_index > right->group_index)
+		return 1;
 
-	return false;
+	return 0;
+}
+
+#define __node_2_pe(node) \
+	rb_entry((node), struct perf_event, group_node)
+
+static inline bool __group_less(struct rb_node *a, const struct rb_node *b)
+{
+	struct perf_event *e = __node_2_pe(a);
+	return perf_event_groups_cmp(e->cpu, event_cgroup(e), e->group_index,
+				     __node_2_pe(b)) < 0;
+}
+
+struct __group_key {
+	int cpu;
+	struct cgroup *cgroup;
+};
+
+static inline int __group_cmp(const void *key, const struct rb_node *node)
+{
+	const struct __group_key *a = key;
+	const struct perf_event *b = __node_2_pe(node);
+
+	/* partial/subtree match: @cpu, @cgroup; ignore: @group_index */
+	return perf_event_groups_cmp(a->cpu, a->cgroup, b->group_index, b);
 }
 
 /*
@@ -1650,27 +1693,9 @@ static void
 perf_event_groups_insert(struct perf_event_groups *groups,
 			 struct perf_event *event)
 {
-	struct perf_event *node_event;
-	struct rb_node *parent;
-	struct rb_node **node;
-
 	event->group_index = ++groups->index;
 
-	node = &groups->tree.rb_node;
-	parent = *node;
-
-	while (*node) {
-		parent = *node;
-		node_event = container_of(*node, struct perf_event, group_node);
-
-		if (perf_event_groups_less(event, node_event))
-			node = &parent->rb_left;
-		else
-			node = &parent->rb_right;
-	}
-
-	rb_link_node(&event->group_node, parent, node);
-	rb_insert_color(&event->group_node, &groups->tree);
+	rb_add(&event->group_node, &groups->tree, __group_less);
 }
 
 /*
@@ -1718,45 +1743,17 @@ static struct perf_event *
 perf_event_groups_first(struct perf_event_groups *groups, int cpu,
 			struct cgroup *cgrp)
 {
-	struct perf_event *node_event = NULL, *match = NULL;
-	struct rb_node *node = groups->tree.rb_node;
-#ifdef CONFIG_CGROUP_PERF
-	u64 node_cgrp_id, cgrp_id = 0;
-
-	if (cgrp)
-		cgrp_id = cgrp->kn->id;
-#endif
+	struct __group_key key = {
+		.cpu = cpu,
+		.cgroup = cgrp,
+	};
+	struct rb_node *node;
 
-	while (node) {
-		node_event = container_of(node, struct perf_event, group_node);
+	node = rb_find_first(&key, &groups->tree, __group_cmp);
+	if (node)
+		return __node_2_pe(node);
 
-		if (cpu < node_event->cpu) {
-			node = node->rb_left;
-			continue;
-		}
-		if (cpu > node_event->cpu) {
-			node = node->rb_right;
-			continue;
-		}
-#ifdef CONFIG_CGROUP_PERF
-		node_cgrp_id = 0;
-		if (node_event->cgrp && node_event->cgrp->css.cgroup)
-			node_cgrp_id = node_event->cgrp->css.cgroup->kn->id;
-
-		if (cgrp_id < node_cgrp_id) {
-			node = node->rb_left;
-			continue;
-		}
-		if (cgrp_id > node_cgrp_id) {
-			node = node->rb_right;
-			continue;
-		}
-#endif
-		match = node_event;
-		node = node->rb_left;
-	}
-
-	return match;
+	return NULL;
 }
 
 /*
@@ -1765,27 +1762,17 @@ perf_event_groups_first(struct perf_event_groups *groups, int cpu,
 static struct perf_event *
 perf_event_groups_next(struct perf_event *event)
 {
-	struct perf_event *next;
-#ifdef CONFIG_CGROUP_PERF
-	u64 curr_cgrp_id = 0;
-	u64 next_cgrp_id = 0;
-#endif
-
-	next = rb_entry_safe(rb_next(&event->group_node), typeof(*event), group_node);
-	if (next == NULL || next->cpu != event->cpu)
-		return NULL;
-
-#ifdef CONFIG_CGROUP_PERF
-	if (event->cgrp && event->cgrp->css.cgroup)
-		curr_cgrp_id = event->cgrp->css.cgroup->kn->id;
+	struct __group_key key = {
+		.cpu = event->cpu,
+		.cgroup = event_cgroup(event),
+	};
+	struct rb_node *next;
 
-	if (next->cgrp && next->cgrp->css.cgroup)
-		next_cgrp_id = next->cgrp->css.cgroup->kn->id;
+	next = rb_next_match(&key, &event->group_node, __group_cmp);
+	if (next)
+		return __node_2_pe(next);
 
-	if (curr_cgrp_id != next_cgrp_id)
-		return NULL;
-#endif
-	return next;
+	return NULL;
 }
 
 /*
@@ -1879,8 +1866,8 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_PERIOD)
 		size += sizeof(data->period);
 
-	if (sample_type & PERF_SAMPLE_WEIGHT)
-		size += sizeof(data->weight);
+	if (sample_type & PERF_SAMPLE_WEIGHT_TYPE)
+		size += sizeof(data->weight.full);
 
 	if (sample_type & PERF_SAMPLE_READ)
 		size += event->read_size;
@@ -2499,7 +2486,7 @@ static void perf_set_shadow_time(struct perf_event *event,
 	 * But this is a bit hairy.
 	 *
 	 * So instead, we have an explicit cgroup call to remain
-	 * within the time time source all along. We believe it
+	 * within the time source all along. We believe it
 	 * is cleaner and simpler to understand.
 	 */
 	if (is_cgroup_event(event))
@@ -4673,6 +4660,8 @@ static void unaccount_event(struct perf_event *event)
 		dec = true;
 	if (event->attr.mmap || event->attr.mmap_data)
 		atomic_dec(&nr_mmap_events);
+	if (event->attr.build_id)
+		atomic_dec(&nr_build_id_events);
 	if (event->attr.comm)
 		atomic_dec(&nr_comm_events);
 	if (event->attr.namespaces)
@@ -6907,8 +6896,8 @@ void perf_output_sample(struct perf_output_handle *handle,
 					  data->regs_user.regs);
 	}
 
-	if (sample_type & PERF_SAMPLE_WEIGHT)
-		perf_output_put(handle, data->weight);
+	if (sample_type & PERF_SAMPLE_WEIGHT_TYPE)
+		perf_output_put(handle, data->weight.full);
 
 	if (sample_type & PERF_SAMPLE_DATA_SRC)
 		perf_output_put(handle, data->data_src.val);
@@ -8046,6 +8035,8 @@ struct perf_mmap_event {
 	u64			ino;
 	u64			ino_generation;
 	u32			prot, flags;
+	u8			build_id[BUILD_ID_SIZE_MAX];
+	u32			build_id_size;
 
 	struct {
 		struct perf_event_header	header;
@@ -8077,6 +8068,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 	struct perf_sample_data sample;
 	int size = mmap_event->event_id.header.size;
 	u32 type = mmap_event->event_id.header.type;
+	bool use_build_id;
 	int ret;
 
 	if (!perf_event_mmap_match(event, data))
@@ -8101,13 +8093,25 @@ static void perf_event_mmap_output(struct perf_event *event,
 	mmap_event->event_id.pid = perf_event_pid(event, current);
 	mmap_event->event_id.tid = perf_event_tid(event, current);
 
+	use_build_id = event->attr.build_id && mmap_event->build_id_size;
+
+	if (event->attr.mmap2 && use_build_id)
+		mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_BUILD_ID;
+
 	perf_output_put(&handle, mmap_event->event_id);
 
 	if (event->attr.mmap2) {
-		perf_output_put(&handle, mmap_event->maj);
-		perf_output_put(&handle, mmap_event->min);
-		perf_output_put(&handle, mmap_event->ino);
-		perf_output_put(&handle, mmap_event->ino_generation);
+		if (use_build_id) {
+			u8 size[4] = { (u8) mmap_event->build_id_size, 0, 0, 0 };
+
+			__output_copy(&handle, size, 4);
+			__output_copy(&handle, mmap_event->build_id, BUILD_ID_SIZE_MAX);
+		} else {
+			perf_output_put(&handle, mmap_event->maj);
+			perf_output_put(&handle, mmap_event->min);
+			perf_output_put(&handle, mmap_event->ino);
+			perf_output_put(&handle, mmap_event->ino_generation);
+		}
 		perf_output_put(&handle, mmap_event->prot);
 		perf_output_put(&handle, mmap_event->flags);
 	}
@@ -8236,6 +8240,9 @@ got_name:
 
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
+	if (atomic_read(&nr_build_id_events))
+		build_id_parse(vma, mmap_event->build_id, &mmap_event->build_id_size);
+
 	perf_iterate_sb(perf_event_mmap_output,
 		       mmap_event,
 		       NULL);
@@ -11172,6 +11179,8 @@ static void account_event(struct perf_event *event)
 		inc = true;
 	if (event->attr.mmap || event->attr.mmap_data)
 		atomic_inc(&nr_mmap_events);
+	if (event->attr.build_id)
+		atomic_inc(&nr_build_id_events);
 	if (event->attr.comm)
 		atomic_inc(&nr_comm_events);
 	if (event->attr.namespaces)
@@ -11564,6 +11573,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (attr->sample_type & PERF_SAMPLE_CGROUP)
 		return -EINVAL;
 #endif
+	if ((attr->sample_type & PERF_SAMPLE_WEIGHT) &&
+	    (attr->sample_type & PERF_SAMPLE_WEIGHT_STRUCT))
+		return -EINVAL;
 
 out:
 	return ret;