13 files changed, 346 insertions, 128 deletions

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index bc364f86100a..2a685b45b73b 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -27,6 +27,7 @@
 #include <linux/time.h>
 #include <linux/uaccess.h>
 #include <linux/list.h>
+#include <linux/blk-cgroup.h>
 
 #include "../../block/blk.h"
 
@@ -46,10 +47,16 @@ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock);
 
 /* Select an alternative, minimalistic output than the original one */
 #define TRACE_BLK_OPT_CLASSIC	0x1
+#define TRACE_BLK_OPT_CGROUP	0x2
+#define TRACE_BLK_OPT_CGNAME	0x4
 
 static struct tracer_opt blk_tracer_opts[] = {
 	/* Default disable the minimalistic output */
 	{ TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) },
+#ifdef CONFIG_BLK_CGROUP
+	{ TRACER_OPT(blk_cgroup, TRACE_BLK_OPT_CGROUP) },
+	{ TRACER_OPT(blk_cgname, TRACE_BLK_OPT_CGNAME) },
+#endif
 	{ }
 };
 
@@ -68,7 +75,8 @@ static void blk_unregister_tracepoints(void);
  * Send out a notify message.
  */
 static void trace_note(struct blk_trace *bt, pid_t pid, int action,
-		       const void *data, size_t len)
+		       const void *data, size_t len,
+		       union kernfs_node_id *cgid)
 {
 	struct blk_io_trace *t;
 	struct ring_buffer_event *event = NULL;
@@ -76,12 +84,13 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 	int pc = 0;
 	int cpu = smp_processor_id();
 	bool blk_tracer = blk_tracer_enabled;
+	ssize_t cgid_len = cgid ? sizeof(*cgid) : 0;
 
 	if (blk_tracer) {
 		buffer = blk_tr->trace_buffer.buffer;
 		pc = preempt_count();
 		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
-						  sizeof(*t) + len,
+						  sizeof(*t) + len + cgid_len,
 						  0, pc);
 		if (!event)
 			return;
@@ -92,17 +101,19 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 	if (!bt->rchan)
 		return;
 
-	t = relay_reserve(bt->rchan, sizeof(*t) + len);
+	t = relay_reserve(bt->rchan, sizeof(*t) + len + cgid_len);
 	if (t) {
 		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
 		t->time = ktime_to_ns(ktime_get());
 record_it:
 		t->device = bt->dev;
-		t->action = action;
+		t->action = action | (cgid ? __BLK_TN_CGROUP : 0);
 		t->pid = pid;
 		t->cpu = cpu;
-		t->pdu_len = len;
-		memcpy((void *) t + sizeof(*t), data, len);
+		t->pdu_len = len + cgid_len;
+		if (cgid)
+			memcpy((void *)t + sizeof(*t), cgid, cgid_len);
+		memcpy((void *) t + sizeof(*t) + cgid_len, data, len);
 
 		if (blk_tracer)
 			trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc);
@@ -122,7 +133,7 @@ static void trace_note_tsk(struct task_struct *tsk)
 	spin_lock_irqsave(&running_trace_lock, flags);
 	list_for_each_entry(bt, &running_trace_list, running_list) {
 		trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm,
-			   sizeof(tsk->comm));
+			   sizeof(tsk->comm), NULL);
 	}
 	spin_unlock_irqrestore(&running_trace_lock, flags);
 }
@@ -139,11 +150,12 @@ static void trace_note_time(struct blk_trace *bt)
 	words[1] = now.tv_nsec;
 
 	local_irq_save(flags);
-	trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words));
+	trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), NULL);
 	local_irq_restore(flags);
 }
 
-void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
+void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg,
+	const char *fmt, ...)
 {
 	int n;
 	va_list args;
@@ -167,7 +179,14 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
 	n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
 	va_end(args);
 
-	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n);
+	if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
+		blkcg = NULL;
+#ifdef CONFIG_BLK_CGROUP
+	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n,
+		blkcg ? cgroup_get_kernfs_id(blkcg->css.cgroup) : NULL);
+#else
+	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, NULL);
+#endif
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(__trace_note_message);
@@ -204,7 +223,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
  */
 static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		     int op, int op_flags, u32 what, int error, int pdu_len,
-		     void *pdu_data)
+		     void *pdu_data, union kernfs_node_id *cgid)
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
@@ -215,6 +234,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	pid_t pid;
 	int cpu, pc = 0;
 	bool blk_tracer = blk_tracer_enabled;
+	ssize_t cgid_len = cgid ? sizeof(*cgid) : 0;
 
 	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
 		return;
@@ -229,6 +249,8 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		what |= BLK_TC_ACT(BLK_TC_DISCARD);
 	if (op == REQ_OP_FLUSH)
 		what |= BLK_TC_ACT(BLK_TC_FLUSH);
+	if (cgid)
+		what |= __BLK_TA_CGROUP;
 
 	pid = tsk->pid;
 	if (act_log_check(bt, what, sector, pid))
@@ -241,7 +263,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		buffer = blk_tr->trace_buffer.buffer;
 		pc = preempt_count();
 		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
-						  sizeof(*t) + pdu_len,
+						  sizeof(*t) + pdu_len + cgid_len,
 						  0, pc);
 		if (!event)
 			return;
@@ -258,7 +280,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	 * from coming in and stepping on our toes.
 	 */
 	local_irq_save(flags);
-	t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len);
+	t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len + cgid_len);
 	if (t) {
 		sequence = per_cpu_ptr(bt->sequence, cpu);
 
@@ -280,10 +302,12 @@ record_it:
 		t->action = what;
 		t->device = bt->dev;
 		t->error = error;
-		t->pdu_len = pdu_len;
+		t->pdu_len = pdu_len + cgid_len;
 
+		if (cgid_len)
+			memcpy((void *)t + sizeof(*t), cgid, cgid_len);
 		if (pdu_len)
-			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
+			memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len);
 
 		if (blk_tracer) {
 			trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc);
@@ -359,7 +383,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
 		return PTR_ERR(msg);
 
 	bt = filp->private_data;
-	__trace_note_message(bt, "%s", msg);
+	__trace_note_message(bt, NULL, "%s", msg);
 	kfree(msg);
 
 	return count;
@@ -684,6 +708,36 @@ void blk_trace_shutdown(struct request_queue *q)
 	}
 }
 
+#ifdef CONFIG_BLK_CGROUP
+static union kernfs_node_id *
+blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
+{
+	struct blk_trace *bt = q->blk_trace;
+
+	if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
+		return NULL;
+
+	if (!bio->bi_css)
+		return NULL;
+	return cgroup_get_kernfs_id(bio->bi_css->cgroup);
+}
+#else
+static union kernfs_node_id *
+blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
+{
+	return NULL;
+}
+#endif
+
+static union kernfs_node_id *
+blk_trace_request_get_cgid(struct request_queue *q, struct request *rq)
+{
+	if (!rq->bio)
+		return NULL;
+	/* Use the first bio */
+	return blk_trace_bio_get_cgid(q, rq->bio);
+}
+
 /*
  * blktrace probes
  */
@@ -694,13 +748,15 @@ void blk_trace_shutdown(struct request_queue *q)
  * @error:	return status to log
  * @nr_bytes:	number of completed bytes
  * @what:	the action
+ * @cgid:	the cgroup info
  *
  * Description:
  *     Records an action against a request. Will log the bio offset + size.
  *
  **/
 static void blk_add_trace_rq(struct request *rq, int error,
-			     unsigned int nr_bytes, u32 what)
+			     unsigned int nr_bytes, u32 what,
+			     union kernfs_node_id *cgid)
 {
 	struct blk_trace *bt = rq->q->blk_trace;
 
@@ -713,32 +769,36 @@ static void blk_add_trace_rq(struct request *rq, int error,
 		what |= BLK_TC_ACT(BLK_TC_FS);
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
-			rq->cmd_flags, what, error, 0, NULL);
+			rq->cmd_flags, what, error, 0, NULL, cgid);
 }
 
 static void blk_add_trace_rq_insert(void *ignore,
 				    struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT);
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT,
+			 blk_trace_request_get_cgid(q, rq));
 }
 
 static void blk_add_trace_rq_issue(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE);
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE,
+			 blk_trace_request_get_cgid(q, rq));
 }
 
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
 {
-	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE);
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE,
+			 blk_trace_request_get_cgid(q, rq));
 }
 
 static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
 			int error, unsigned int nr_bytes)
 {
-	blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE);
+	blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE,
+			 blk_trace_request_get_cgid(rq->q, rq));
 }
 
 /**
@@ -753,7 +813,7 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
  *
  **/
 static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
-			      u32 what, int error)
+			      u32 what, int error, union kernfs_node_id *cgid)
 {
 	struct blk_trace *bt = q->blk_trace;
 
@@ -761,20 +821,22 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
 		return;
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio_op(bio), bio->bi_opf, what, error, 0, NULL);
+			bio_op(bio), bio->bi_opf, what, error, 0, NULL, cgid);
 }
 
 static void blk_add_trace_bio_bounce(void *ignore,
 				     struct request_queue *q, struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
+	blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0,
+			  blk_trace_bio_get_cgid(q, bio));
 }
 
 static void blk_add_trace_bio_complete(void *ignore,
 				       struct request_queue *q, struct bio *bio,
 				       int error)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
+	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error,
+			  blk_trace_bio_get_cgid(q, bio));
 }
 
 static void blk_add_trace_bio_backmerge(void *ignore,
@@ -782,7 +844,8 @@ static void blk_add_trace_bio_backmerge(void *ignore,
 					struct request *rq,
 					struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0);
+	blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0,
+			 blk_trace_bio_get_cgid(q, bio));
 }
 
 static void blk_add_trace_bio_frontmerge(void *ignore,
@@ -790,13 +853,15 @@ static void blk_add_trace_bio_frontmerge(void *ignore,
 					 struct request *rq,
 					 struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0);
+	blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0,
+			  blk_trace_bio_get_cgid(q, bio));
 }
 
 static void blk_add_trace_bio_queue(void *ignore,
 				    struct request_queue *q, struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0);
+	blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0,
+			  blk_trace_bio_get_cgid(q, bio));
 }
 
 static void blk_add_trace_getrq(void *ignore,
@@ -804,13 +869,14 @@ static void blk_add_trace_getrq(void *ignore,
 				struct bio *bio, int rw)
 {
 	if (bio)
-		blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0);
+		blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0,
+				  blk_trace_bio_get_cgid(q, bio));
 	else {
 		struct blk_trace *bt = q->blk_trace;
 
 		if (bt)
 			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0,
-					NULL);
+					NULL, NULL);
 	}
 }
 
@@ -820,13 +886,14 @@ static void blk_add_trace_sleeprq(void *ignore,
 				  struct bio *bio, int rw)
 {
 	if (bio)
-		blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0);
+		blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0,
+				  blk_trace_bio_get_cgid(q, bio));
 	else {
 		struct blk_trace *bt = q->blk_trace;
 
 		if (bt)
 			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ,
-					0, 0, NULL);
+					0, 0, NULL, NULL);
 	}
 }
 
@@ -835,7 +902,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q)
 	struct blk_trace *bt = q->blk_trace;
 
 	if (bt)
-		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
+		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL);
 }
 
 static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
@@ -852,7 +919,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 		else
 			what = BLK_TA_UNPLUG_TIMER;
 
-		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu);
+		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL);
 	}
 }
 
@@ -868,7 +935,7 @@ static void blk_add_trace_split(void *ignore,
 		__blk_add_trace(bt, bio->bi_iter.bi_sector,
 				bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
 				BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu),
-				&rpdu);
+				&rpdu, blk_trace_bio_get_cgid(q, bio));
 	}
 }
 
@@ -896,12 +963,12 @@ static void blk_add_trace_bio_remap(void *ignore,
 		return;
 
 	r.device_from = cpu_to_be32(dev);
-	r.device_to   = cpu_to_be32(bio->bi_bdev->bd_dev);
+	r.device_to   = cpu_to_be32(bio_dev(bio));
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
 			bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status,
-			sizeof(r), &r);
+			sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
 }
 
 /**
@@ -934,7 +1001,7 @@ static void blk_add_trace_rq_remap(void *ignore,
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
 			rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
-			sizeof(r), &r);
+			sizeof(r), &r, blk_trace_request_get_cgid(q, rq));
 }
 
 /**
@@ -958,7 +1025,8 @@ void blk_add_driver_data(struct request_queue *q,
 		return;
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
-				BLK_TA_DRV_DATA, 0, len, data);
+				BLK_TA_DRV_DATA, 0, len, data,
+				blk_trace_request_get_cgid(q, rq));
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
 
@@ -1031,7 +1099,7 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
 	int i = 0;
 	int tc = t->action >> BLK_TC_SHIFT;
 
-	if (t->action == BLK_TN_MESSAGE) {
+	if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) {
 		rwbs[i++] = 'N';
 		goto out;
 	}
@@ -1066,9 +1134,21 @@ const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent)
 	return (const struct blk_io_trace *)ent;
 }
 
-static inline const void *pdu_start(const struct trace_entry *ent)
+static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg)
+{
+	return (void *)(te_blk_io_trace(ent) + 1) +
+		(has_cg ? sizeof(union kernfs_node_id) : 0);
+}
+
+static inline const void *cgid_start(const struct trace_entry *ent)
+{
+	return (void *)(te_blk_io_trace(ent) + 1);
+}
+
+static inline int pdu_real_len(const struct trace_entry *ent, bool has_cg)
 {
-	return te_blk_io_trace(ent) + 1;
+	return te_blk_io_trace(ent)->pdu_len -
+			(has_cg ? sizeof(union kernfs_node_id) : 0);
 }
 
 static inline u32 t_action(const struct trace_entry *ent)
@@ -1096,16 +1176,16 @@ static inline __u16 t_error(const struct trace_entry *ent)
 	return te_blk_io_trace(ent)->error;
 }
 
-static __u64 get_pdu_int(const struct trace_entry *ent)
+static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg)
 {
-	const __u64 *val = pdu_start(ent);
+	const __u64 *val = pdu_start(ent, has_cg);
 	return be64_to_cpu(*val);
 }
 
 static void get_pdu_remap(const struct trace_entry *ent,
-			  struct blk_io_trace_remap *r)
+			  struct blk_io_trace_remap *r, bool has_cg)
 {
-	const struct blk_io_trace_remap *__r = pdu_start(ent);
+	const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
 	__u64 sector_from = __r->sector_from;
 
 	r->device_from = be32_to_cpu(__r->device_from);
@@ -1113,9 +1193,11 @@ static void get_pdu_remap(const struct trace_entry *ent,
 	r->sector_from = be64_to_cpu(sector_from);
 }
 
-typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act);
+typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act,
+	bool has_cg);
 
-static void blk_log_action_classic(struct trace_iterator *iter, const char *act)
+static void blk_log_action_classic(struct trace_iterator *iter, const char *act,
+	bool has_cg)
 {
 	char rwbs[RWBS_LEN];
 	unsigned long long ts  = iter->ts;
@@ -1131,24 +1213,43 @@ static void blk_log_action_classic(struct trace_iterator *iter, const char *act)
 			 secs, nsec_rem, iter->ent->pid, act, rwbs);
 }
 
-static void blk_log_action(struct trace_iterator *iter, const char *act)
+static void blk_log_action(struct trace_iterator *iter, const char *act,
+	bool has_cg)
 {
 	char rwbs[RWBS_LEN];
 	const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
 
 	fill_rwbs(rwbs, t);
-	trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ",
-			 MAJOR(t->device), MINOR(t->device), act, rwbs);
-}
-
-static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent)
+	if (has_cg) {
+		const union kernfs_node_id *id = cgid_start(iter->ent);
+
+		if (blk_tracer_flags.val & TRACE_BLK_OPT_CGNAME) {
+			char blkcg_name_buf[NAME_MAX + 1] = "<...>";
+
+			cgroup_path_from_kernfs_id(id, blkcg_name_buf,
+				sizeof(blkcg_name_buf));
+			trace_seq_printf(&iter->seq, "%3d,%-3d %s %2s %3s ",
+				 MAJOR(t->device), MINOR(t->device),
+				 blkcg_name_buf, act, rwbs);
+		} else
+			trace_seq_printf(&iter->seq,
+				 "%3d,%-3d %x,%-x %2s %3s ",
+				 MAJOR(t->device), MINOR(t->device),
+				 id->ino, id->generation, act, rwbs);
+	} else
+		trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ",
+				 MAJOR(t->device), MINOR(t->device), act, rwbs);
+}
+
+static void blk_log_dump_pdu(struct trace_seq *s,
+	const struct trace_entry *ent, bool has_cg)
 {
 	const unsigned char *pdu_buf;
 	int pdu_len;
 	int i, end;
 
-	pdu_buf = pdu_start(ent);
-	pdu_len = te_blk_io_trace(ent)->pdu_len;
+	pdu_buf = pdu_start(ent, has_cg);
+	pdu_len = pdu_real_len(ent, has_cg);
 
 	if (!pdu_len)
 		return;
@@ -1179,7 +1280,7 @@ static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent)
 	trace_seq_puts(s, ") ");
 }
 
-static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
 {
 	char cmd[TASK_COMM_LEN];
 
@@ -1187,7 +1288,7 @@ static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
 
 	if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
 		trace_seq_printf(s, "%u ", t_bytes(ent));
-		blk_log_dump_pdu(s, ent);
+		blk_log_dump_pdu(s, ent, has_cg);
 		trace_seq_printf(s, "[%s]\n", cmd);
 	} else {
 		if (t_sec(ent))
@@ -1199,10 +1300,10 @@ static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
 }
 
 static void blk_log_with_error(struct trace_seq *s,
-			      const struct trace_entry *ent)
+			      const struct trace_entry *ent, bool has_cg)
 {
 	if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
-		blk_log_dump_pdu(s, ent);
+		blk_log_dump_pdu(s, ent, has_cg);
 		trace_seq_printf(s, "[%d]\n", t_error(ent));
 	} else {
 		if (t_sec(ent))
@@ -1215,18 +1316,18 @@ static void blk_log_with_error(struct trace_seq *s,
 	}
 }
 
-static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
 {
 	struct blk_io_trace_remap r = { .device_from = 0, };
 
-	get_pdu_remap(ent, &r);
+	get_pdu_remap(ent, &r, has_cg);
 	trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
 			 t_sector(ent), t_sec(ent),
 			 MAJOR(r.device_from), MINOR(r.device_from),
 			 (unsigned long long)r.sector_from);
 }
 
-static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
 {
 	char cmd[TASK_COMM_LEN];
 
@@ -1235,30 +1336,31 @@ static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
 	trace_seq_printf(s, "[%s]\n", cmd);
 }
 
-static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
 {
 	char cmd[TASK_COMM_LEN];
 
 	trace_find_cmdline(ent->pid, cmd);
 
-	trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent));
+	trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent, has_cg));
 }
 
-static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
 {
 	char cmd[TASK_COMM_LEN];
 
 	trace_find_cmdline(ent->pid, cmd);
 
 	trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent),
-			 get_pdu_int(ent), cmd);
+			 get_pdu_int(ent, has_cg), cmd);
 }
 
-static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent)
+static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent,
+			bool has_cg)
 {
-	const struct blk_io_trace *t = te_blk_io_trace(ent);
 
-	trace_seq_putmem(s, t + 1, t->pdu_len);
+	trace_seq_putmem(s, pdu_start(ent, has_cg),
+		pdu_real_len(ent, has_cg));
 	trace_seq_putc(s, '\n');
 }
 
@@ -1298,7 +1400,8 @@ static void blk_tracer_reset(struct trace_array *tr)
 
 static const struct {
 	const char *act[2];
-	void	   (*print)(struct trace_seq *s, const struct trace_entry *ent);
+	void	   (*print)(struct trace_seq *s, const struct trace_entry *ent,
+			    bool has_cg);
 } what2act[] = {
 	[__BLK_TA_QUEUE]	= {{  "Q", "queue" },	   blk_log_generic },
 	[__BLK_TA_BACKMERGE]	= {{  "M", "backmerge" },  blk_log_generic },
@@ -1326,23 +1429,25 @@ static enum print_line_t print_one_line(struct trace_iterator *iter,
 	u16 what;
 	bool long_act;
 	blk_log_action_t *log_action;
+	bool has_cg;
 
 	t	   = te_blk_io_trace(iter->ent);
-	what	   = t->action & ((1 << BLK_TC_SHIFT) - 1);
+	what	   = (t->action & ((1 << BLK_TC_SHIFT) - 1)) & ~__BLK_TA_CGROUP;
 	long_act   = !!(tr->trace_flags & TRACE_ITER_VERBOSE);
 	log_action = classic ? &blk_log_action_classic : &blk_log_action;
+	has_cg	   = t->action & __BLK_TA_CGROUP;
 
-	if (t->action == BLK_TN_MESSAGE) {
-		log_action(iter, long_act ? "message" : "m");
-		blk_log_msg(s, iter->ent);
+	if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) {
+		log_action(iter, long_act ? "message" : "m", has_cg);
+		blk_log_msg(s, iter->ent, has_cg);
 		return trace_handle_return(s);
 	}
 
 	if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
 		trace_seq_printf(s, "Unknown action %x\n", what);
 	else {
-		log_action(iter, what2act[what].act[long_act]);
-		what2act[what].print(s, iter->ent);
+		log_action(iter, what2act[what].act[long_act], has_cg);
+		what2act[what].print(s, iter->ent, has_cg);
 	}
 
 	return trace_handle_return(s);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 37385193a608..dc498b605d5d 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -204,10 +204,36 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		fmt_cnt++;
 	}
 
-	return __trace_printk(1/* fake ip will not be printed */, fmt,
-			      mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1,
-			      mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2,
-			      mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3);
+/* Horrid workaround for getting va_list handling working with different
+ * argument type combinations generically for 32 and 64 bit archs.
+ */
+#define __BPF_TP_EMIT()	__BPF_ARG3_TP()
+#define __BPF_TP(...)							\
+	__trace_printk(1 /* Fake ip will not be printed. */,		\
+		       fmt, ##__VA_ARGS__)
+
+#define __BPF_ARG1_TP(...)						\
+	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_TP(arg1, ##__VA_ARGS__)				\
+	  : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_TP((long)arg1, ##__VA_ARGS__)			\
+	      : __BPF_TP((u32)arg1, ##__VA_ARGS__)))
+
+#define __BPF_ARG2_TP(...)						\
+	((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__)				\
+	  : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__)		\
+	      : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))
+
+#define __BPF_ARG3_TP(...)						\
+	((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__)				\
+	  : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__)		\
+	      : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))
+
+	return __BPF_TP_EMIT();
 }
 
 static const struct bpf_func_proto bpf_trace_printk_proto = {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 53f6b6401cf0..96cea88fa00f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -113,7 +113,7 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_MUTEX(ftrace_lock);
 
-static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
+static struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
 
@@ -169,8 +169,11 @@ int ftrace_nr_registered_ops(void)
 
 	mutex_lock(&ftrace_lock);
 
-	for (ops = ftrace_ops_list;
-	     ops != &ftrace_list_end; ops = ops->next)
+	for (ops = rcu_dereference_protected(ftrace_ops_list,
+					     lockdep_is_held(&ftrace_lock));
+	     ops != &ftrace_list_end;
+	     ops = rcu_dereference_protected(ops->next,
+					     lockdep_is_held(&ftrace_lock)))
 		cnt++;
 
 	mutex_unlock(&ftrace_lock);
@@ -275,10 +278,11 @@ static void update_ftrace_function(void)
 	 * If there's only one ftrace_ops registered, the ftrace_ops_list
 	 * will point to the ops we want.
 	 */
-	set_function_trace_op = ftrace_ops_list;
+	set_function_trace_op = rcu_dereference_protected(ftrace_ops_list,
+						lockdep_is_held(&ftrace_lock));
 
 	/* If there's no ftrace_ops registered, just call the stub function */
-	if (ftrace_ops_list == &ftrace_list_end) {
+	if (set_function_trace_op == &ftrace_list_end) {
 		func = ftrace_stub;
 
 	/*
@@ -286,7 +290,8 @@ static void update_ftrace_function(void)
 	 * recursion safe and not dynamic and the arch supports passing ops,
 	 * then have the mcount trampoline call the function directly.
 	 */
-	} else if (ftrace_ops_list->next == &ftrace_list_end) {
+	} else if (rcu_dereference_protected(ftrace_ops_list->next,
+			lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) {
 		func = ftrace_ops_get_list_func(ftrace_ops_list);
 
 	} else {
@@ -348,9 +353,11 @@ int using_ftrace_ops_list_func(void)
 	return ftrace_trace_function == ftrace_ops_list_func;
 }
 
-static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
+static void add_ftrace_ops(struct ftrace_ops __rcu **list,
+			   struct ftrace_ops *ops)
 {
-	ops->next = *list;
+	rcu_assign_pointer(ops->next, *list);
+
 	/*
 	 * We are entering ops into the list but another
 	 * CPU might be walking that list. We need to make sure
@@ -360,7 +367,8 @@ static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
 	rcu_assign_pointer(*list, ops);
 }
 
-static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
+static int remove_ftrace_ops(struct ftrace_ops __rcu **list,
+			     struct ftrace_ops *ops)
 {
 	struct ftrace_ops **p;
 
@@ -368,7 +376,10 @@ static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
 	 * If we are removing the last function, then simply point
 	 * to the ftrace_stub.
 	 */
-	if (*list == ops && ops->next == &ftrace_list_end) {
+	if (rcu_dereference_protected(*list,
+			lockdep_is_held(&ftrace_lock)) == ops &&
+	    rcu_dereference_protected(ops->next,
+			lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) {
 		*list = &ftrace_list_end;
 		return 0;
 	}
@@ -878,6 +889,10 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace)
 
 	function_profile_call(trace->func, 0, NULL, NULL);
 
+	/* If function graph is shutting down, ret_stack can be NULL */
+	if (!current->ret_stack)
+		return 0;
+
 	if (index >= 0 && index < FTRACE_RETFUNC_DEPTH)
 		current->ret_stack[index].subtime = 0;
 
@@ -1569,8 +1584,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 		return 0;
 #endif
 
-	hash.filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash);
-	hash.notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash);
+	rcu_assign_pointer(hash.filter_hash, ops->func_hash->filter_hash);
+	rcu_assign_pointer(hash.notrace_hash, ops->func_hash->notrace_hash);
 
 	if (hash_contains_ip(ip, &hash))
 		ret = 1;
@@ -2840,7 +2855,8 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 * If there's no more ops registered with ftrace, run a
 	 * sanity check to make sure all rec flags are cleared.
 	 */
-	if (ftrace_ops_list == &ftrace_list_end) {
+	if (rcu_dereference_protected(ftrace_ops_list,
+			lockdep_is_held(&ftrace_lock)) == &ftrace_list_end) {
 		struct ftrace_page *pg;
 		struct dyn_ftrace *rec;
 
@@ -6453,7 +6469,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 	if (ftrace_enabled) {
 
 		/* we are starting ftrace again */
-		if (ftrace_ops_list != &ftrace_list_end)
+		if (rcu_dereference_protected(ftrace_ops_list,
+			lockdep_is_held(&ftrace_lock)) != &ftrace_list_end)
 			update_ftrace_function();
 
 		ftrace_startup_sysctl();
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 4ae268e687fe..81279c6602ff 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1136,12 +1136,12 @@ static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu)
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page;
 		/*
-		 * __GFP_NORETRY flag makes sure that the allocation fails
-		 * gracefully without invoking oom-killer and the system is
-		 * not destabilized.
+		 * __GFP_RETRY_MAYFAIL flag makes sure that the allocation fails
+		 * gracefully without invoking oom-killer and the system is not
+		 * destabilized.
 		 */
 		bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
-				    GFP_KERNEL | __GFP_NORETRY,
+				    GFP_KERNEL | __GFP_RETRY_MAYFAIL,
 				    cpu_to_node(cpu));
 		if (!bpage)
 			goto free_pages;
@@ -1149,7 +1149,7 @@ static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu)
 		list_add(&bpage->list, pages);
 
 		page = alloc_pages_node(cpu_to_node(cpu),
-					GFP_KERNEL | __GFP_NORETRY, 0);
+					GFP_KERNEL | __GFP_RETRY_MAYFAIL, 0);
 		if (!page)
 			goto free_pages;
 		bpage->page = page_address(page);
@@ -4386,15 +4386,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
  * the page that was allocated, with the read page of the buffer.
  *
  * Returns:
- *  The page allocated, or NULL on error.
+ *  The page allocated, or ERR_PTR
  */
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
 {
-	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	struct ring_buffer_per_cpu *cpu_buffer;
 	struct buffer_data_page *bpage = NULL;
 	unsigned long flags;
 	struct page *page;
 
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return ERR_PTR(-ENODEV);
+
+	cpu_buffer = buffer->buffers[cpu];
 	local_irq_save(flags);
 	arch_spin_lock(&cpu_buffer->lock);
 
@@ -4412,7 +4416,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
 	page = alloc_pages_node(cpu_to_node(cpu),
 				GFP_KERNEL | __GFP_NORETRY, 0);
 	if (!page)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	bpage = page_address(page);
 
@@ -4467,8 +4471,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *
  * for example:
  *	rpage = ring_buffer_alloc_read_page(buffer, cpu);
- *	if (!rpage)
- *		return error;
+ *	if (IS_ERR(rpage))
+ *		return PTR_ERR(rpage);
  *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
  *	if (ret >= 0)
  *		process_page(rpage, ret);
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 9fbcaf567886..68ee79afe31c 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -113,7 +113,7 @@ static enum event_status read_page(int cpu)
 	int i;
 
 	bpage = ring_buffer_alloc_read_page(buffer, cpu);
-	if (!bpage)
+	if (IS_ERR(bpage))
 		return EVENT_DROPPED;
 
 	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2d0ffcc49dba..44004d8aa3b3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6598,7 +6598,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 {
 	struct ftrace_buffer_info *info = filp->private_data;
 	struct trace_iterator *iter = &info->iter;
-	ssize_t ret;
+	ssize_t ret = 0;
 	ssize_t size;
 
 	if (!count)
@@ -6612,10 +6612,15 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (!info->spare) {
 		info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer,
 							  iter->cpu_file);
-		info->spare_cpu = iter->cpu_file;
+		if (IS_ERR(info->spare)) {
+			ret = PTR_ERR(info->spare);
+			info->spare = NULL;
+		} else {
+			info->spare_cpu = iter->cpu_file;
+		}
 	}
 	if (!info->spare)
-		return -ENOMEM;
+		return ret;
 
 	/* Do we have previous read data to read? */
 	if (info->read < PAGE_SIZE)
@@ -6790,8 +6795,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		ref->ref = 1;
 		ref->buffer = iter->trace_buffer->buffer;
 		ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
-		if (!ref->page) {
-			ret = -ENOMEM;
+		if (IS_ERR(ref->page)) {
+			ret = PTR_ERR(ref->page);
+			ref->page = NULL;
 			kfree(ref);
 			break;
 		}
@@ -7774,6 +7780,7 @@ static int instance_rmdir(const char *name)
 	}
 	kfree(tr->topts);
 
+	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
 
@@ -8292,6 +8299,7 @@ __init static int tracer_alloc_buffers(void)
 	if (ret < 0)
 		goto out_free_cpumask;
 	/* Used for event triggers */
+	ret = -ENOMEM;
 	temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE);
 	if (!temp_buffer)
 		goto out_rm_hp_state;
@@ -8406,4 +8414,4 @@ __init static int clear_boot_tracer(void)
 }
 
 fs_initcall(tracer_init_tracefs);
-late_initcall(clear_boot_tracer);
+late_initcall_sync(clear_boot_tracer);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6ade1c55cc3a..490ba229931d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1210,9 +1210,9 @@ struct ftrace_event_field {
 struct event_filter {
 	int			n_preds;	/* Number assigned */
 	int			a_preds;	/* allocated */
-	struct filter_pred	*preds;
-	struct filter_pred	*root;
-	char			*filter_string;
+	struct filter_pred __rcu	*preds;
+	struct filter_pred __rcu	*root;
+	char				*filter_string;
 };
 
 struct event_subsystem {
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 562fa69df5d3..13ba2d3f6a91 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -306,6 +306,7 @@ static void
 perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 			  struct ftrace_ops *ops, struct pt_regs *pt_regs)
 {
+	struct perf_event *event;
 	struct ftrace_entry *entry;
 	struct hlist_head *head;
 	struct pt_regs regs;
@@ -329,8 +330,9 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 
 	entry->ip = ip;
 	entry->parent_ip = parent_ip;
+	event = container_of(ops, struct perf_event, ftrace_ops);
 	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN,
-			      1, &regs, head, NULL);
+			      1, &regs, head, NULL, event);
 
 #undef ENTRY_SIZE
 }
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 59a411ff60c7..181e139a8057 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1959,6 +1959,10 @@ static int create_filter(struct trace_event_call *call,
 		if (err && set_str)
 			append_filter_err(ps, filter);
 	}
+	if (err && !set_str) {
+		free_event_filter(filter);
+		filter = NULL;
+	}
 	create_filter_finish(ps);
 
 	*filterp = filter;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c9b5aa10fbf9..8a907e12b6b9 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1200,7 +1200,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	memset(&entry[1], 0, dsize);
 	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
-			      head, NULL);
+			      head, NULL, NULL);
 }
 NOKPROBE_SYMBOL(kprobe_perf_func);
 
@@ -1236,7 +1236,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	entry->ret_ip = (unsigned long)ri->ret_addr;
 	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
-			      head, NULL);
+			      head, NULL, NULL);
 }
 NOKPROBE_SYMBOL(kretprobe_perf_func);
 #endif	/* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5e10395da88e..9c4eef20301c 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -559,11 +559,29 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
 static int sys_perf_refcount_enter;
 static int sys_perf_refcount_exit;
 
+static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
+			      struct syscall_metadata *sys_data,
+			      struct syscall_trace_enter *rec) {
+	struct syscall_tp_t {
+		unsigned long long regs;
+		unsigned long syscall_nr;
+		unsigned long args[sys_data->nb_args];
+	} param;
+	int i;
+
+	*(struct pt_regs **)&param = regs;
+	param.syscall_nr = rec->nr;
+	for (i = 0; i < sys_data->nb_args; i++)
+		param.args[i] = rec->args[i];
+	return trace_call_bpf(prog, &param);
+}
+
 static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
 	struct hlist_head *head;
+	struct bpf_prog *prog;
 	int syscall_nr;
 	int rctx;
 	int size;
@@ -578,8 +596,9 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	if (!sys_data)
 		return;
 
+	prog = READ_ONCE(sys_data->enter_event->prog);
 	head = this_cpu_ptr(sys_data->enter_event->perf_events);
-	if (hlist_empty(head))
+	if (!prog && hlist_empty(head))
 		return;
 
 	/* get the size after alignment with the u32 buffer size field */
@@ -594,9 +613,16 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	rec->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
+
+	if ((prog && !perf_call_bpf_enter(prog, regs, sys_data, rec)) ||
+	    hlist_empty(head)) {
+		perf_swevent_put_recursion_context(rctx);
+		return;
+	}
+
 	perf_trace_buf_submit(rec, size, rctx,
 			      sys_data->enter_event->event.type, 1, regs,
-			      head, NULL);
+			      head, NULL, NULL);
 }
 
 static int perf_sysenter_enable(struct trace_event_call *call)
@@ -633,11 +659,26 @@ static void perf_sysenter_disable(struct trace_event_call *call)
 	mutex_unlock(&syscall_trace_lock);
 }
 
+static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs,
+			      struct syscall_trace_exit *rec) {
+	struct syscall_tp_t {
+		unsigned long long regs;
+		unsigned long syscall_nr;
+		unsigned long ret;
+	} param;
+
+	*(struct pt_regs **)&param = regs;
+	param.syscall_nr = rec->nr;
+	param.ret = rec->ret;
+	return trace_call_bpf(prog, &param);
+}
+
 static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_exit *rec;
 	struct hlist_head *head;
+	struct bpf_prog *prog;
 	int syscall_nr;
 	int rctx;
 	int size;
@@ -652,8 +693,9 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
+	prog = READ_ONCE(sys_data->exit_event->prog);
 	head = this_cpu_ptr(sys_data->exit_event->perf_events);
-	if (hlist_empty(head))
+	if (!prog && hlist_empty(head))
 		return;
 
 	/* We can probably do that at build time */
@@ -666,8 +708,15 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
+
+	if ((prog && !perf_call_bpf_exit(prog, regs, rec)) ||
+	    hlist_empty(head)) {
+		perf_swevent_put_recursion_context(rctx);
+		return;
+	}
+
 	perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
-			      1, regs, head, NULL);
+			      1, regs, head, NULL, NULL);
 }
 
 static int perf_sysexit_enable(struct trace_event_call *call)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index a7581fec9681..4525e0271a53 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1156,7 +1156,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 	}
 
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
-			      head, NULL);
+			      head, NULL, NULL);
  out:
 	preempt_enable();
 }
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 0a689bbb78ef..305039b122fa 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -221,16 +221,19 @@ void tracing_map_array_free(struct tracing_map_array *a)
 	if (!a)
 		return;
 
-	if (!a->pages) {
-		kfree(a);
-		return;
-	}
+	if (!a->pages)
+		goto free;
 
 	for (i = 0; i < a->n_pages; i++) {
 		if (!a->pages[i])
 			break;
 		free_page((unsigned long)a->pages[i]);
 	}
+
+	kfree(a->pages);
+
+ free:
+	kfree(a);
 }
 
 struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,