Merge branch 'next' into for-linus

Prepare input updates for 5.11 merge window.

28 files changed, 3672 insertions, 2326 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 743647005f64..a4020c0b4508 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -10,11 +10,6 @@ config USER_STACKTRACE_SUPPORT
 config NOP_TRACER
 	bool
 
-config HAVE_FTRACE_NMI_ENTER
-	bool
-	help
-	  See Documentation/trace/ftrace-design.rst
-
 config HAVE_FUNCTION_TRACER
 	bool
 	help
@@ -72,11 +67,6 @@ config RING_BUFFER
 	select TRACE_CLOCK
 	select IRQ_WORK
 
-config FTRACE_NMI_ENTER
-       bool
-       depends on HAVE_FTRACE_NMI_ENTER
-       default y
-
 config EVENT_TRACING
 	select CONTEXT_SWITCH_TRACER
 	select GLOB
@@ -158,6 +148,7 @@ config FUNCTION_TRACER
 	select CONTEXT_SWITCH_TRACER
 	select GLOB
 	select TASKS_RCU if PREEMPTION
+	select TASKS_RUDE_RCU
 	help
 	  Enable the kernel to trace every kernel function. This is done
 	  by using a compiler feature to insert a small, 5-byte No-Operation
@@ -258,15 +249,6 @@ config TRACE_PREEMPT_TOGGLE
 	  Enables hooks which will be called when preemption is first disabled,
 	  and last enabled.
 
-config PREEMPTIRQ_EVENTS
-	bool "Enable trace events for preempt and irq disable/enable"
-	select TRACE_IRQFLAGS
-	select TRACE_PREEMPT_TOGGLE if PREEMPTION
-	select GENERIC_TRACER
-	default n
-	help
-	  Enable tracing of disable and enable events for preemption and irqs.
-
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
 	default n
@@ -623,12 +605,30 @@ config TRACING_MAP
 	  generally used outside of that context, and is normally
 	  selected by tracers that use it.
 
+config SYNTH_EVENTS
+	bool "Synthetic trace events"
+	select TRACING
+	select DYNAMIC_EVENTS
+	default n
+	help
+	  Synthetic events are user-defined trace events that can be
+	  used to combine data from other trace events or in fact any
+	  data source.  Synthetic events can be generated indirectly
+	  via the trace() action of histogram triggers or directly
+	  by way of an in-kernel API.
+
+	  See Documentation/trace/events.rst or
+	  Documentation/trace/histogram.rst for details and examples.
+
+	  If in doubt, say N.
+
 config HIST_TRIGGERS
 	bool "Histogram triggers"
 	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select TRACING_MAP
 	select TRACING
 	select DYNAMIC_EVENTS
+	select SYNTH_EVENTS
 	default n
 	help
 	  Hist triggers allow one or more arbitrary trace event fields
@@ -824,7 +824,7 @@ config PREEMPTIRQ_DELAY_TEST
 
 config SYNTH_EVENT_GEN_TEST
 	tristate "Test module for in-kernel synthetic event generation"
-	depends on HIST_TRIGGERS
+	depends on SYNTH_EVENTS
 	help
           This option creates a test module to check the base
           functionality of in-kernel synthetic event definition and
@@ -847,6 +847,29 @@ config KPROBE_EVENT_GEN_TEST
 
 	  If unsure, say N.
 
+config HIST_TRIGGERS_DEBUG
+	bool "Hist trigger debug support"
+	depends on HIST_TRIGGERS
+	help
+          Add "hist_debug" file for each event, which when read will
+          dump out a bunch of internal details about the hist triggers
+          defined on that event.
+
+          The hist_debug file serves a couple of purposes:
+
+            - Helps developers verify that nothing is broken.
+
+            - Provides educational information to support the details
+              of the hist trigger internals as described by
+              Documentation/trace/histogram-design.rst.
+
+          The hist_debug output only covers the data structures
+          related to the histogram definitions themselves and doesn't
+          display the internals of map buckets or variable values of
+          running histograms.
+
+          If unsure, say N.
+
 endif # FTRACE
 
 endif # TRACING_SUPPORT
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index f9dcd19165fa..e153be351548 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -2,9 +2,12 @@
 
 # Do not instrument the tracer itself:
 
+ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
+
 ifdef CONFIG_FUNCTION_TRACER
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))
+
+# Avoid recursion due to instrumentation.
+KCSAN_SANITIZE := n
 
 ifdef CONFIG_FTRACE_SELFTEST
 # selftest needs instrumentation
@@ -28,6 +31,8 @@ ifdef CONFIG_GCOV_PROFILE_FTRACE
 GCOV_PROFILE := y
 endif
 
+CFLAGS_bpf_trace.o := -I$(src)
+
 CFLAGS_trace_benchmark.o := -I$(src)
 CFLAGS_trace_events_filter.o := -I$(src)
 
@@ -72,6 +77,7 @@ endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
 obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o
+obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
 obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index ca39dc3230cb..4b3a42fc3b24 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -3,6 +3,9 @@
  * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
  *
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
 #include <linux/blktrace_api.h>
@@ -170,10 +173,10 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg,
 	if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
 		blkcg = NULL;
 #ifdef CONFIG_BLK_CGROUP
-	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n,
+	trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n,
 		   blkcg ? cgroup_id(blkcg->css.cgroup) : 1);
 #else
-	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, 0);
+	trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, 0);
 #endif
 	local_irq_restore(flags);
 }
@@ -344,7 +347,8 @@ static int __blk_trace_remove(struct request_queue *q)
 {
 	struct blk_trace *bt;
 
-	bt = xchg(&q->blk_trace, NULL);
+	bt = rcu_replace_pointer(q->blk_trace, NULL,
+				 lockdep_is_held(&q->debugfs_mutex));
 	if (!bt)
 		return -EINVAL;
 
@@ -358,9 +362,9 @@ int blk_trace_remove(struct request_queue *q)
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_remove(q);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -479,12 +483,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	struct dentry *dir = NULL;
 	int ret;
 
+	lockdep_assert_held(&q->debugfs_mutex);
+
 	if (!buts->buf_size || !buts->buf_nr)
 		return -EINVAL;
 
-	if (!blk_debugfs_root)
-		return -ENOENT;
-
 	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
 	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
 
@@ -494,6 +497,17 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 */
 	strreplace(buts->name, '/', '_');
 
+	/*
+	 * bdev can be NULL, as with scsi-generic, this is a helpful as
+	 * we can be.
+	 */
+	if (rcu_dereference_protected(q->blk_trace,
+				      lockdep_is_held(&q->debugfs_mutex))) {
+		pr_warn("Concurrent blktraces are not allowed on %s\n",
+			buts->name);
+		return -EBUSY;
+	}
+
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
 		return -ENOMEM;
@@ -507,12 +521,29 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->msg_data)
 		goto err;
 
-	ret = -ENOENT;
-
-	dir = debugfs_lookup(buts->name, blk_debugfs_root);
-	if (!dir)
+	/*
+	 * When tracing the whole disk reuse the existing debugfs directory
+	 * created by the block layer on init. For partitions block devices,
+	 * and scsi-generic block devices we create a temporary new debugfs
+	 * directory that will be removed once the trace ends.
+	 */
+	if (bdev && bdev == bdev->bd_contains)
+		dir = q->debugfs_dir;
+	else
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
 
+	/*
+	 * As blktrace relies on debugfs for its interface the debugfs directory
+	 * is required, contrary to the usual mantra of not checking for debugfs
+	 * files or directories.
+	 */
+	if (IS_ERR_OR_NULL(dir)) {
+		pr_warn("debugfs_dir not present for %s so skipping\n",
+			buts->name);
+		ret = -ENOENT;
+		goto err;
+	}
+
 	bt->dev = dev;
 	atomic_set(&bt->dropped, 0);
 	INIT_LIST_HEAD(&bt->running_list);
@@ -543,16 +574,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	bt->pid = buts->pid;
 	bt->trace_state = Blktrace_setup;
 
-	ret = -EBUSY;
-	if (cmpxchg(&q->blk_trace, NULL, bt))
-		goto err;
-
+	rcu_assign_pointer(q->blk_trace, bt);
 	get_probe_ref();
 
 	ret = 0;
 err:
-	if (dir && !bt->dir)
-		dput(dir);
 	if (ret)
 		blk_trace_free(bt);
 	return ret;
@@ -585,9 +611,9 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_setup(q, name, dev, bdev, arg);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -633,7 +659,7 @@ static int __blk_trace_startstop(struct request_queue *q, int start)
 	struct blk_trace *bt;
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -673,9 +699,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_startstop(q, start);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -704,7 +730,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	if (!q)
 		return -ENXIO;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	switch (cmd) {
 	case BLKTRACESETUP:
@@ -719,7 +745,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 #endif
 	case BLKTRACESTART:
 		start = 1;
-		/* fall through */
+		fallthrough;
 	case BLKTRACESTOP:
 		ret = __blk_trace_startstop(q, start);
 		break;
@@ -731,7 +757,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 		break;
 	}
 
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 	return ret;
 }
 
@@ -742,14 +768,14 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
  **/
 void blk_trace_shutdown(struct request_queue *q)
 {
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	if (rcu_dereference_protected(q->blk_trace,
-				      lockdep_is_held(&q->blk_trace_mutex))) {
+				      lockdep_is_held(&q->debugfs_mutex))) {
 		__blk_trace_startstop(q, 0);
 		__blk_trace_remove(q);
 	}
 
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 }
 
 #ifdef CONFIG_BLK_CGROUP
@@ -834,6 +860,13 @@ static void blk_add_trace_rq_issue(void *ignore,
 			 blk_trace_request_get_cgid(q, rq));
 }
 
+static void blk_add_trace_rq_merge(void *ignore,
+				   struct request_queue *q, struct request *rq)
+{
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE,
+			 blk_trace_request_get_cgid(q, rq));
+}
+
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
@@ -885,10 +918,10 @@ static void blk_add_trace_bio_bounce(void *ignore,
 }
 
 static void blk_add_trace_bio_complete(void *ignore,
-				       struct request_queue *q, struct bio *bio,
-				       int error)
+				       struct request_queue *q, struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
+	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE,
+			  blk_status_to_errno(bio->bi_status));
 }
 
 static void blk_add_trace_bio_backmerge(void *ignore,
@@ -995,8 +1028,10 @@ 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, blk_trace_bio_get_cgid(q, bio));
+				BLK_TA_SPLIT,
+				blk_status_to_errno(bio->bi_status),
+				sizeof(rpdu), &rpdu,
+				blk_trace_bio_get_cgid(q, bio));
 	}
 	rcu_read_unlock();
 }
@@ -1033,7 +1068,8 @@ static void blk_add_trace_bio_remap(void *ignore,
 	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,
+			bio_op(bio), bio->bi_opf, BLK_TA_REMAP,
+			blk_status_to_errno(bio->bi_status),
 			sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
 	rcu_read_unlock();
 }
@@ -1115,6 +1151,8 @@ static void blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
 	WARN_ON(ret);
+	ret = register_trace_block_rq_merge(blk_add_trace_rq_merge, NULL);
+	WARN_ON(ret);
 	ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
 	WARN_ON(ret);
 	ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
@@ -1161,6 +1199,7 @@ static void blk_unregister_tracepoints(void)
 	unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
 	unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
 	unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
+	unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL);
 	unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
 	unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
 
@@ -1253,21 +1292,10 @@ static inline __u16 t_error(const struct trace_entry *ent)
 
 static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg)
 {
-	const __u64 *val = pdu_start(ent, has_cg);
+	const __be64 *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, bool has_cg)
-{
-	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);
-	r->device_to   = be32_to_cpu(__r->device_to);
-	r->sector_from = be64_to_cpu(sector_from);
-}
-
 typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act,
 	bool has_cg);
 
@@ -1407,13 +1435,13 @@ static void blk_log_with_error(struct trace_seq *s,
 
 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, };
+	const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
 
-	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);
+			 MAJOR(be32_to_cpu(__r->device_from)),
+			 MINOR(be32_to_cpu(__r->device_from)),
+			 be64_to_cpu(__r->sector_from));
 }
 
 static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
@@ -1637,7 +1665,8 @@ static int blk_trace_remove_queue(struct request_queue *q)
 {
 	struct blk_trace *bt;
 
-	bt = xchg(&q->blk_trace, NULL);
+	bt = rcu_replace_pointer(q->blk_trace, NULL,
+				 lockdep_is_held(&q->debugfs_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -1669,10 +1698,7 @@ static int blk_trace_setup_queue(struct request_queue *q,
 
 	blk_trace_setup_lba(bt, bdev);
 
-	ret = -EBUSY;
-	if (cmpxchg(&q->blk_trace, NULL, bt))
-		goto free_bt;
-
+	rcu_assign_pointer(q->blk_trace, bt);
 	get_probe_ref();
 	return 0;
 
@@ -1815,10 +1841,10 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (attr == &dev_attr_enable) {
 		ret = sprintf(buf, "%u\n", !!bt);
 		goto out_unlock_bdev;
@@ -1836,7 +1862,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 		ret = sprintf(buf, "%llu\n", bt->end_lba);
 
 out_unlock_bdev:
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 out_bdput:
 	bdput(bdev);
 out:
@@ -1879,10 +1905,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (attr == &dev_attr_enable) {
 		if (!!value == !!bt) {
 			ret = 0;
@@ -1899,7 +1925,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (bt == NULL) {
 		ret = blk_trace_setup_queue(q, bdev);
 		bt = rcu_dereference_protected(q->blk_trace,
-				lockdep_is_held(&q->blk_trace_mutex));
+				lockdep_is_held(&q->debugfs_mutex));
 	}
 
 	if (ret == 0) {
@@ -1914,7 +1940,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	}
 
 out_unlock_bdev:
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 out_bdput:
 	bdput(bdev);
 out:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a010edc37ee0..a8d4f253ed77 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -11,14 +11,19 @@
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
 #include <linux/kprobes.h>
+#include <linux/spinlock.h>
 #include <linux/syscalls.h>
 #include <linux/error-injection.h>
+#include <linux/btf_ids.h>
 
 #include <asm/tlb.h>
 
 #include "trace_probe.h"
 #include "trace.h"
 
+#define CREATE_TRACE_POINTS
+#include "bpf_trace.h"
+
 #define bpf_event_rcu_dereference(p)					\
 	rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex))
 
@@ -136,18 +141,24 @@ static const struct bpf_func_proto bpf_override_return_proto = {
 };
 #endif
 
-BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size,
-	   const void __user *, unsafe_ptr)
+static __always_inline int
+bpf_probe_read_user_common(void *dst, u32 size, const void __user *unsafe_ptr)
 {
-	int ret = probe_user_read(dst, unsafe_ptr, size);
+	int ret;
 
+	ret = copy_from_user_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		memset(dst, 0, size);
-
 	return ret;
 }
 
-static const struct bpf_func_proto bpf_probe_read_user_proto = {
+BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size,
+	   const void __user *, unsafe_ptr)
+{
+	return bpf_probe_read_user_common(dst, size, unsafe_ptr);
+}
+
+const struct bpf_func_proto bpf_probe_read_user_proto = {
 	.func		= bpf_probe_read_user,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -156,18 +167,25 @@ static const struct bpf_func_proto bpf_probe_read_user_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size,
-	   const void __user *, unsafe_ptr)
+static __always_inline int
+bpf_probe_read_user_str_common(void *dst, u32 size,
+			       const void __user *unsafe_ptr)
 {
-	int ret = strncpy_from_unsafe_user(dst, unsafe_ptr, size);
+	int ret;
 
+	ret = strncpy_from_user_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		memset(dst, 0, size);
-
 	return ret;
 }
 
-static const struct bpf_func_proto bpf_probe_read_user_str_proto = {
+BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size,
+	   const void __user *, unsafe_ptr)
+{
+	return bpf_probe_read_user_str_common(dst, size, unsafe_ptr);
+}
+
+const struct bpf_func_proto bpf_probe_read_user_str_proto = {
 	.func		= bpf_probe_read_user_str,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -177,28 +195,28 @@ static const struct bpf_func_proto bpf_probe_read_user_str_proto = {
 };
 
 static __always_inline int
-bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr,
-			     const bool compat)
+bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
 {
 	int ret = security_locked_down(LOCKDOWN_BPF_READ);
 
 	if (unlikely(ret < 0))
-		goto out;
-	ret = compat ? probe_kernel_read(dst, unsafe_ptr, size) :
-	      probe_kernel_read_strict(dst, unsafe_ptr, size);
+		goto fail;
+	ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
-out:
-		memset(dst, 0, size);
+		goto fail;
+	return ret;
+fail:
+	memset(dst, 0, size);
 	return ret;
 }
 
 BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
 	   const void *, unsafe_ptr)
 {
-	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, false);
+	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr);
 }
 
-static const struct bpf_func_proto bpf_probe_read_kernel_proto = {
+const struct bpf_func_proto bpf_probe_read_kernel_proto = {
 	.func		= bpf_probe_read_kernel,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -207,53 +225,40 @@ static const struct bpf_func_proto bpf_probe_read_kernel_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size,
-	   const void *, unsafe_ptr)
-{
-	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, true);
-}
-
-static const struct bpf_func_proto bpf_probe_read_compat_proto = {
-	.func		= bpf_probe_read_compat,
-	.gpl_only	= true,
-	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
-	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
-	.arg3_type	= ARG_ANYTHING,
-};
-
 static __always_inline int
-bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr,
-				 const bool compat)
+bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr)
 {
 	int ret = security_locked_down(LOCKDOWN_BPF_READ);
 
 	if (unlikely(ret < 0))
-		goto out;
+		goto fail;
+
 	/*
-	 * The strncpy_from_unsafe_*() call will likely not fill the entire
-	 * buffer, but that's okay in this circumstance as we're probing
+	 * The strncpy_from_kernel_nofault() call will likely not fill the
+	 * entire buffer, but that's okay in this circumstance as we're probing
 	 * arbitrary memory anyway similar to bpf_probe_read_*() and might
 	 * as well probe the stack. Thus, memory is explicitly cleared
 	 * only in error case, so that improper users ignoring return
 	 * code altogether don't copy garbage; otherwise length of string
 	 * is returned that can be used for bpf_perf_event_output() et al.
 	 */
-	ret = compat ? strncpy_from_unsafe(dst, unsafe_ptr, size) :
-	      strncpy_from_unsafe_strict(dst, unsafe_ptr, size);
+	ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
-out:
-		memset(dst, 0, size);
+		goto fail;
+
+	return ret;
+fail:
+	memset(dst, 0, size);
 	return ret;
 }
 
 BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size,
 	   const void *, unsafe_ptr)
 {
-	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, false);
+	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr);
 }
 
-static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
+const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
 	.func		= bpf_probe_read_kernel_str,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -262,10 +267,34 @@ static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size,
+	   const void *, unsafe_ptr)
+{
+	if ((unsigned long)unsafe_ptr < TASK_SIZE) {
+		return bpf_probe_read_user_common(dst, size,
+				(__force void __user *)unsafe_ptr);
+	}
+	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr);
+}
+
+static const struct bpf_func_proto bpf_probe_read_compat_proto = {
+	.func		= bpf_probe_read_compat,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size,
 	   const void *, unsafe_ptr)
 {
-	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, true);
+	if ((unsigned long)unsafe_ptr < TASK_SIZE) {
+		return bpf_probe_read_user_str_common(dst, size,
+				(__force void __user *)unsafe_ptr);
+	}
+	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr);
 }
 
 static const struct bpf_func_proto bpf_probe_read_compat_str_proto = {
@@ -276,6 +305,7 @@ static const struct bpf_func_proto bpf_probe_read_compat_str_proto = {
 	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_ANYTHING,
 };
+#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */
 
 BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
 	   u32, size)
@@ -301,7 +331,7 @@ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
 
-	return probe_user_write(unsafe_ptr, src, size);
+	return copy_to_user_nofault(unsafe_ptr, src, size);
 }
 
 static const struct bpf_func_proto bpf_probe_write_user_proto = {
@@ -315,15 +345,67 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = {
 
 static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
 {
+	if (!capable(CAP_SYS_ADMIN))
+		return NULL;
+
 	pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!",
 			    current->comm, task_pid_nr(current));
 
 	return &bpf_probe_write_user_proto;
 }
 
+static void bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
+		size_t bufsz)
+{
+	void __user *user_ptr = (__force void __user *)unsafe_ptr;
+
+	buf[0] = 0;
+
+	switch (fmt_ptype) {
+	case 's':
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+		if ((unsigned long)unsafe_ptr < TASK_SIZE) {
+			strncpy_from_user_nofault(buf, user_ptr, bufsz);
+			break;
+		}
+		fallthrough;
+#endif
+	case 'k':
+		strncpy_from_kernel_nofault(buf, unsafe_ptr, bufsz);
+		break;
+	case 'u':
+		strncpy_from_user_nofault(buf, user_ptr, bufsz);
+		break;
+	}
+}
+
+static DEFINE_RAW_SPINLOCK(trace_printk_lock);
+
+#define BPF_TRACE_PRINTK_SIZE   1024
+
+static __printf(1, 0) int bpf_do_trace_printk(const char *fmt, ...)
+{
+	static char buf[BPF_TRACE_PRINTK_SIZE];
+	unsigned long flags;
+	va_list ap;
+	int ret;
+
+	raw_spin_lock_irqsave(&trace_printk_lock, flags);
+	va_start(ap, fmt);
+	ret = vsnprintf(buf, sizeof(buf), fmt, ap);
+	va_end(ap);
+	/* vsnprintf() will not append null for zero-length strings */
+	if (ret == 0)
+		buf[0] = '\0';
+	trace_bpf_trace_printk(buf);
+	raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+
+	return ret;
+}
+
 /*
  * Only limited trace_printk() conversion specifiers allowed:
- * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s
+ * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pB %pks %pus %s
  */
 BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 	   u64, arg2, u64, arg3)
@@ -367,6 +449,11 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 				goto fmt_str;
 			}
 
+			if (fmt[i + 1] == 'B') {
+				i++;
+				goto fmt_next;
+			}
+
 			/* disallow any further format extensions */
 			if (fmt[i + 1] != 0 &&
 			    !isspace(fmt[i + 1]) &&
@@ -403,24 +490,8 @@ fmt_str:
 				break;
 			}
 
-			buf[0] = 0;
-			switch (fmt_ptype) {
-			case 's':
-#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
-				strncpy_from_unsafe(buf, unsafe_ptr,
-						    sizeof(buf));
-				break;
-#endif
-			case 'k':
-				strncpy_from_unsafe_strict(buf, unsafe_ptr,
-							   sizeof(buf));
-				break;
-			case 'u':
-				strncpy_from_unsafe_user(buf,
-					(__force void __user *)unsafe_ptr,
-							 sizeof(buf));
-				break;
-			}
+			bpf_trace_copy_string(buf, unsafe_ptr, fmt_ptype,
+					sizeof(buf));
 			goto fmt_next;
 		}
 
@@ -441,8 +512,7 @@ fmt_next:
  */
 #define __BPF_TP_EMIT()	__BPF_ARG3_TP()
 #define __BPF_TP(...)							\
-	__trace_printk(0 /* Fake ip */,					\
-		       fmt, ##__VA_ARGS__)
+	bpf_do_trace_printk(fmt, ##__VA_ARGS__)
 
 #define __BPF_ARG1_TP(...)						\
 	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
@@ -479,14 +549,233 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 {
 	/*
-	 * this program might be calling bpf_trace_printk,
-	 * so allocate per-cpu printk buffers
+	 * This program might be calling bpf_trace_printk,
+	 * so enable the associated bpf_trace/bpf_trace_printk event.
+	 * Repeat this each time as it is possible a user has
+	 * disabled bpf_trace_printk events.  By loading a program
+	 * calling bpf_trace_printk() however the user has expressed
+	 * the intent to see such events.
 	 */
-	trace_printk_init_buffers();
+	if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1))
+		pr_warn_ratelimited("could not enable bpf_trace_printk events");
 
 	return &bpf_trace_printk_proto;
 }
 
+#define MAX_SEQ_PRINTF_VARARGS		12
+#define MAX_SEQ_PRINTF_MAX_MEMCPY	6
+#define MAX_SEQ_PRINTF_STR_LEN		128
+
+struct bpf_seq_printf_buf {
+	char buf[MAX_SEQ_PRINTF_MAX_MEMCPY][MAX_SEQ_PRINTF_STR_LEN];
+};
+static DEFINE_PER_CPU(struct bpf_seq_printf_buf, bpf_seq_printf_buf);
+static DEFINE_PER_CPU(int, bpf_seq_printf_buf_used);
+
+BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
+	   const void *, data, u32, data_len)
+{
+	int err = -EINVAL, fmt_cnt = 0, memcpy_cnt = 0;
+	int i, buf_used, copy_size, num_args;
+	u64 params[MAX_SEQ_PRINTF_VARARGS];
+	struct bpf_seq_printf_buf *bufs;
+	const u64 *args = data;
+
+	buf_used = this_cpu_inc_return(bpf_seq_printf_buf_used);
+	if (WARN_ON_ONCE(buf_used > 1)) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	bufs = this_cpu_ptr(&bpf_seq_printf_buf);
+
+	/*
+	 * bpf_check()->check_func_arg()->check_stack_boundary()
+	 * guarantees that fmt points to bpf program stack,
+	 * fmt_size bytes of it were initialized and fmt_size > 0
+	 */
+	if (fmt[--fmt_size] != 0)
+		goto out;
+
+	if (data_len & 7)
+		goto out;
+
+	for (i = 0; i < fmt_size; i++) {
+		if (fmt[i] == '%') {
+			if (fmt[i + 1] == '%')
+				i++;
+			else if (!data || !data_len)
+				goto out;
+		}
+	}
+
+	num_args = data_len / 8;
+
+	/* check format string for allowed specifiers */
+	for (i = 0; i < fmt_size; i++) {
+		/* only printable ascii for now. */
+		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		if (fmt[i] != '%')
+			continue;
+
+		if (fmt[i + 1] == '%') {
+			i++;
+			continue;
+		}
+
+		if (fmt_cnt >= MAX_SEQ_PRINTF_VARARGS) {
+			err = -E2BIG;
+			goto out;
+		}
+
+		if (fmt_cnt >= num_args) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		/* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
+		i++;
+
+		/* skip optional "[0 +-][num]" width formating field */
+		while (fmt[i] == '0' || fmt[i] == '+'  || fmt[i] == '-' ||
+		       fmt[i] == ' ')
+			i++;
+		if (fmt[i] >= '1' && fmt[i] <= '9') {
+			i++;
+			while (fmt[i] >= '0' && fmt[i] <= '9')
+				i++;
+		}
+
+		if (fmt[i] == 's') {
+			void *unsafe_ptr;
+
+			/* try our best to copy */
+			if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) {
+				err = -E2BIG;
+				goto out;
+			}
+
+			unsafe_ptr = (void *)(long)args[fmt_cnt];
+			err = strncpy_from_kernel_nofault(bufs->buf[memcpy_cnt],
+					unsafe_ptr, MAX_SEQ_PRINTF_STR_LEN);
+			if (err < 0)
+				bufs->buf[memcpy_cnt][0] = '\0';
+			params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt];
+
+			fmt_cnt++;
+			memcpy_cnt++;
+			continue;
+		}
+
+		if (fmt[i] == 'p') {
+			if (fmt[i + 1] == 0 ||
+			    fmt[i + 1] == 'K' ||
+			    fmt[i + 1] == 'x' ||
+			    fmt[i + 1] == 'B') {
+				/* just kernel pointers */
+				params[fmt_cnt] = args[fmt_cnt];
+				fmt_cnt++;
+				continue;
+			}
+
+			/* only support "%pI4", "%pi4", "%pI6" and "%pi6". */
+			if (fmt[i + 1] != 'i' && fmt[i + 1] != 'I') {
+				err = -EINVAL;
+				goto out;
+			}
+			if (fmt[i + 2] != '4' && fmt[i + 2] != '6') {
+				err = -EINVAL;
+				goto out;
+			}
+
+			if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) {
+				err = -E2BIG;
+				goto out;
+			}
+
+
+			copy_size = (fmt[i + 2] == '4') ? 4 : 16;
+
+			err = copy_from_kernel_nofault(bufs->buf[memcpy_cnt],
+						(void *) (long) args[fmt_cnt],
+						copy_size);
+			if (err < 0)
+				memset(bufs->buf[memcpy_cnt], 0, copy_size);
+			params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt];
+
+			i += 2;
+			fmt_cnt++;
+			memcpy_cnt++;
+			continue;
+		}
+
+		if (fmt[i] == 'l') {
+			i++;
+			if (fmt[i] == 'l')
+				i++;
+		}
+
+		if (fmt[i] != 'i' && fmt[i] != 'd' &&
+		    fmt[i] != 'u' && fmt[i] != 'x' &&
+		    fmt[i] != 'X') {
+			err = -EINVAL;
+			goto out;
+		}
+
+		params[fmt_cnt] = args[fmt_cnt];
+		fmt_cnt++;
+	}
+
+	/* Maximumly we can have MAX_SEQ_PRINTF_VARARGS parameter, just give
+	 * all of them to seq_printf().
+	 */
+	seq_printf(m, fmt, params[0], params[1], params[2], params[3],
+		   params[4], params[5], params[6], params[7], params[8],
+		   params[9], params[10], params[11]);
+
+	err = seq_has_overflowed(m) ? -EOVERFLOW : 0;
+out:
+	this_cpu_dec(bpf_seq_printf_buf_used);
+	return err;
+}
+
+BTF_ID_LIST(bpf_seq_printf_btf_ids)
+BTF_ID(struct, seq_file)
+
+static const struct bpf_func_proto bpf_seq_printf_proto = {
+	.func		= bpf_seq_printf,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
+	.btf_id		= bpf_seq_printf_btf_ids,
+};
+
+BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
+{
+	return seq_write(m, data, len) ? -EOVERFLOW : 0;
+}
+
+BTF_ID_LIST(bpf_seq_write_btf_ids)
+BTF_ID(struct, seq_file)
+
+static const struct bpf_func_proto bpf_seq_write_proto = {
+	.func		= bpf_seq_write,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.btf_id		= bpf_seq_write_btf_ids,
+};
+
 static __always_inline int
 get_map_perf_counter(struct bpf_map *map, u64 flags,
 		     u64 *value, u64 *enabled, u64 *running)
@@ -698,7 +987,7 @@ BPF_CALL_0(bpf_get_current_task)
 	return (long) current;
 }
 
-static const struct bpf_func_proto bpf_get_current_task_proto = {
+const struct bpf_func_proto bpf_get_current_task_proto = {
 	.func		= bpf_get_current_task,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -827,6 +1116,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_map_peek_elem_proto;
 	case BPF_FUNC_ktime_get_ns:
 		return &bpf_ktime_get_ns_proto;
+	case BPF_FUNC_ktime_get_boot_ns:
+		return &bpf_ktime_get_boot_ns_proto;
 	case BPF_FUNC_tail_call:
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_get_current_pid_tgid:
@@ -877,6 +1168,20 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_perf_event_read_value_proto;
 	case BPF_FUNC_get_ns_current_pid_tgid:
 		return &bpf_get_ns_current_pid_tgid_proto;
+	case BPF_FUNC_ringbuf_output:
+		return &bpf_ringbuf_output_proto;
+	case BPF_FUNC_ringbuf_reserve:
+		return &bpf_ringbuf_reserve_proto;
+	case BPF_FUNC_ringbuf_submit:
+		return &bpf_ringbuf_submit_proto;
+	case BPF_FUNC_ringbuf_discard:
+		return &bpf_ringbuf_discard_proto;
+	case BPF_FUNC_ringbuf_query:
+		return &bpf_ringbuf_query_proto;
+	case BPF_FUNC_jiffies64:
+		return &bpf_jiffies64_proto;
+	case BPF_FUNC_get_task_stack:
+		return &bpf_get_task_stack_proto;
 	default:
 		return NULL;
 	}
@@ -1106,9 +1411,9 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_perf_event_output_proto_tp;
 	case BPF_FUNC_get_stackid:
-		return &bpf_get_stackid_proto_tp;
+		return &bpf_get_stackid_proto_pe;
 	case BPF_FUNC_get_stack:
-		return &bpf_get_stack_proto_tp;
+		return &bpf_get_stack_proto_pe;
 	case BPF_FUNC_perf_prog_read_value:
 		return &bpf_perf_prog_read_value_proto;
 	case BPF_FUNC_read_branch_records:
@@ -1246,7 +1551,7 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	}
 }
 
-static const struct bpf_func_proto *
+const struct bpf_func_proto *
 tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
@@ -1255,7 +1560,25 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skb_output_proto;
 	case BPF_FUNC_xdp_output:
 		return &bpf_xdp_output_proto;
+	case BPF_FUNC_skc_to_tcp6_sock:
+		return &bpf_skc_to_tcp6_sock_proto;
+	case BPF_FUNC_skc_to_tcp_sock:
+		return &bpf_skc_to_tcp_sock_proto;
+	case BPF_FUNC_skc_to_tcp_timewait_sock:
+		return &bpf_skc_to_tcp_timewait_sock_proto;
+	case BPF_FUNC_skc_to_tcp_request_sock:
+		return &bpf_skc_to_tcp_request_sock_proto;
+	case BPF_FUNC_skc_to_udp6_sock:
+		return &bpf_skc_to_udp6_sock_proto;
 #endif
+	case BPF_FUNC_seq_printf:
+		return prog->expected_attach_type == BPF_TRACE_ITER ?
+		       &bpf_seq_printf_proto :
+		       NULL;
+	case BPF_FUNC_seq_write:
+		return prog->expected_attach_type == BPF_TRACE_ITER ?
+		       &bpf_seq_write_proto :
+		       NULL;
 	default:
 		return raw_tp_prog_func_proto(func_id, prog);
 	}
@@ -1500,7 +1823,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 	u32 *ids, prog_cnt, ids_len;
 	int ret;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EPERM;
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return -EINVAL;
diff --git a/kernel/trace/bpf_trace.h b/kernel/trace/bpf_trace.h
new file mode 100644
index 000000000000..9acbc11ac7bb
--- /dev/null
+++ b/kernel/trace/bpf_trace.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM bpf_trace
+
+#if !defined(_TRACE_BPF_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+
+#define _TRACE_BPF_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(bpf_trace_printk,
+
+	TP_PROTO(const char *bpf_string),
+
+	TP_ARGS(bpf_string),
+
+	TP_STRUCT__entry(
+		__string(bpf_string, bpf_string)
+	),
+
+	TP_fast_assign(
+		__assign_str(bpf_string, bpf_string);
+	),
+
+	TP_printk("%s", __get_str(bpf_string))
+);
+
+#endif /* _TRACE_BPF_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE bpf_trace
+
+#include <trace/define_trace.h>
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index bd030b1b9514..541453927c82 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -139,9 +139,6 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops)
 #endif
 }
 
-#define FTRACE_PID_IGNORE	-1
-#define FTRACE_PID_TRACE	-2
-
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 			    struct ftrace_ops *op, struct pt_regs *regs)
 {
@@ -160,17 +157,6 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 	op->saved_func(ip, parent_ip, op, regs);
 }
 
-static void ftrace_sync(struct work_struct *work)
-{
-	/*
-	 * This function is just a stub to implement a hard force
-	 * of synchronize_rcu(). This requires synchronizing
-	 * tasks even in userspace and idle.
-	 *
-	 * Yes, function tracing is rude.
-	 */
-}
-
 static void ftrace_sync_ipi(void *data)
 {
 	/* Probably not needed, but do it anyway */
@@ -256,7 +242,7 @@ static void update_ftrace_function(void)
 	 * Make sure all CPUs see this. Yes this is slow, but static
 	 * tracing is slow and nasty to have enabled.
 	 */
-	schedule_on_each_cpu(ftrace_sync);
+	synchronize_rcu_tasks_rude();
 	/* Now all cpus are using the list ops. */
 	function_trace_op = set_function_trace_op;
 	/* Make sure the function_trace_op is visible on all CPUs */
@@ -2027,16 +2013,16 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
 {
 	unsigned long ip = rec ? rec->ip : 0;
 
+	pr_info("------------[ ftrace bug ]------------\n");
+
 	switch (failed) {
 	case -EFAULT:
-		FTRACE_WARN_ON_ONCE(1);
 		pr_info("ftrace faulted on modifying ");
-		print_ip_sym(ip);
+		print_ip_sym(KERN_INFO, ip);
 		break;
 	case -EINVAL:
-		FTRACE_WARN_ON_ONCE(1);
 		pr_info("ftrace failed to modify ");
-		print_ip_sym(ip);
+		print_ip_sym(KERN_INFO, ip);
 		print_ip_ins(" actual:   ", (unsigned char *)ip);
 		pr_cont("\n");
 		if (ftrace_expected) {
@@ -2045,14 +2031,12 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
 		}
 		break;
 	case -EPERM:
-		FTRACE_WARN_ON_ONCE(1);
 		pr_info("ftrace faulted on writing ");
-		print_ip_sym(ip);
+		print_ip_sym(KERN_INFO, ip);
 		break;
 	default:
-		FTRACE_WARN_ON_ONCE(1);
 		pr_info("ftrace faulted on unknown error ");
-		print_ip_sym(ip);
+		print_ip_sym(KERN_INFO, ip);
 	}
 	print_bug_type();
 	if (rec) {
@@ -2077,6 +2061,8 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
 		ip = ftrace_get_addr_curr(rec);
 		pr_cont("\n expected tramp: %lx\n", ip);
 	}
+
+	FTRACE_WARN_ON_ONCE(1);
 }
 
 static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
@@ -2271,7 +2257,7 @@ ftrace_find_tramp_ops_next(struct dyn_ftrace *rec,
 
 		if (hash_contains_ip(ip, op->func_hash))
 			return op;
-	} 
+	}
 
 	return NULL;
 }
@@ -2399,6 +2385,14 @@ struct ftrace_ops direct_ops = {
 	.flags		= FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_RECURSION_SAFE
 			  | FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS
 			  | FTRACE_OPS_FL_PERMANENT,
+	/*
+	 * By declaring the main trampoline as this trampoline
+	 * it will never have one allocated for it. Allocated
+	 * trampolines should not call direct functions.
+	 * The direct_ops should only be called by the builtin
+	 * ftrace_regs_caller trampoline.
+	 */
+	.trampoline	= FTRACE_REGS_ADDR,
 };
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
@@ -2775,6 +2769,51 @@ void __weak arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 }
 
+/* List of trace_ops that have allocated trampolines */
+static LIST_HEAD(ftrace_ops_trampoline_list);
+
+static void ftrace_add_trampoline_to_kallsyms(struct ftrace_ops *ops)
+{
+	lockdep_assert_held(&ftrace_lock);
+	list_add_rcu(&ops->list, &ftrace_ops_trampoline_list);
+}
+
+static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
+{
+	lockdep_assert_held(&ftrace_lock);
+	list_del_rcu(&ops->list);
+	synchronize_rcu();
+}
+
+/*
+ * "__builtin__ftrace" is used as a module name in /proc/kallsyms for symbols
+ * for pages allocated for ftrace purposes, even though "__builtin__ftrace" is
+ * not a module.
+ */
+#define FTRACE_TRAMPOLINE_MOD "__builtin__ftrace"
+#define FTRACE_TRAMPOLINE_SYM "ftrace_trampoline"
+
+static void ftrace_trampoline_free(struct ftrace_ops *ops)
+{
+	if (ops && (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP) &&
+	    ops->trampoline) {
+		/*
+		 * Record the text poke event before the ksymbol unregister
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size, NULL, 0);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size,
+				   true, FTRACE_TRAMPOLINE_SYM);
+		/* Remove from kallsyms after the perf events */
+		ftrace_remove_trampoline_from_kallsyms(ops);
+	}
+
+	arch_ftrace_trampoline_free(ops);
+}
+
 static void ftrace_startup_enable(int command)
 {
 	if (saved_ftrace_func != ftrace_trace_function) {
@@ -2824,6 +2863,8 @@ int ftrace_startup(struct ftrace_ops *ops, int command)
 		__unregister_ftrace_function(ops);
 		ftrace_start_up--;
 		ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+		if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
+			ftrace_trampoline_free(ops);
 		return ret;
 	}
 
@@ -2932,7 +2973,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		 * infrastructure to do the synchronization, thus we must do it
 		 * ourselves.
 		 */
-		schedule_on_each_cpu(ftrace_sync);
+		synchronize_rcu_tasks_rude();
 
 		/*
 		 * When the kernel is preeptive, tasks can be preempted
@@ -2945,7 +2986,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 			synchronize_rcu_tasks();
 
  free_ops:
-		arch_ftrace_trampoline_free(ops);
+		ftrace_trampoline_free(ops);
 	}
 
 	return 0;
@@ -3610,7 +3651,7 @@ static int t_show(struct seq_file *m, void *v)
 			if (direct)
 				seq_printf(m, "\n\tdirect-->%pS", (void *)direct);
 		}
-	}	
+	}
 
 	seq_putc(m, '\n');
 
@@ -5888,7 +5929,7 @@ ftrace_graph_release(struct inode *inode, struct file *file)
 		 * infrastructure to do the synchronization, thus we must do it
 		 * ourselves.
 		 */
-		schedule_on_each_cpu(ftrace_sync);
+		synchronize_rcu_tasks_rude();
 
 		free_ftrace_hash(old_hash);
 	}
@@ -6189,6 +6230,27 @@ struct ftrace_mod_map {
 	unsigned int		num_funcs;
 };
 
+static int ftrace_get_trampoline_kallsym(unsigned int symnum,
+					 unsigned long *value, char *type,
+					 char *name, char *module_name,
+					 int *exported)
+{
+	struct ftrace_ops *op;
+
+	list_for_each_entry_rcu(op, &ftrace_ops_trampoline_list, list) {
+		if (!op->trampoline || symnum--)
+			continue;
+		*value = op->trampoline;
+		*type = 't';
+		strlcpy(name, FTRACE_TRAMPOLINE_SYM, KSYM_NAME_LEN);
+		strlcpy(module_name, FTRACE_TRAMPOLINE_MOD, MODULE_NAME_LEN);
+		*exported = 0;
+		return 0;
+	}
+
+	return -ERANGE;
+}
+
 #ifdef CONFIG_MODULES
 
 #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
@@ -6201,8 +6263,19 @@ static int referenced_filters(struct dyn_ftrace *rec)
 	int cnt = 0;
 
 	for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
-		if (ops_references_rec(ops, rec))
-		    cnt++;
+		if (ops_references_rec(ops, rec)) {
+			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_DIRECT))
+				continue;
+			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_IPMODIFY))
+				continue;
+			cnt++;
+			if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+				rec->flags |= FTRACE_FL_REGS;
+			if (cnt == 1 && ops->trampoline)
+				rec->flags |= FTRACE_FL_TRAMP;
+			else
+				rec->flags &= ~FTRACE_FL_TRAMP;
+		}
 	}
 
 	return cnt;
@@ -6381,8 +6454,8 @@ void ftrace_module_enable(struct module *mod)
 		if (ftrace_start_up)
 			cnt += referenced_filters(rec);
 
-		/* This clears FTRACE_FL_DISABLED */
-		rec->flags = cnt;
+		rec->flags &= ~FTRACE_FL_DISABLED;
+		rec->flags += cnt;
 
 		if (ftrace_start_up && cnt) {
 			int failed = __ftrace_replace_code(rec, 1);
@@ -6525,6 +6598,7 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 {
 	struct ftrace_mod_map *mod_map;
 	struct ftrace_mod_func *mod_func;
+	int ret;
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) {
@@ -6551,8 +6625,10 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 		WARN_ON(1);
 		break;
 	}
+	ret = ftrace_get_trampoline_kallsym(symnum, value, type, name,
+					    module_name, exported);
 	preempt_enable();
-	return -ERANGE;
+	return ret;
 }
 
 #else
@@ -6564,6 +6640,18 @@ allocate_ftrace_mod_map(struct module *mod,
 {
 	return NULL;
 }
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name, char *module_name,
+			   int *exported)
+{
+	int ret;
+
+	preempt_disable();
+	ret = ftrace_get_trampoline_kallsym(symnum, value, type, name,
+					    module_name, exported);
+	preempt_enable();
+	return ret;
+}
 #endif /* CONFIG_MODULES */
 
 struct ftrace_init_func {
@@ -6744,7 +6832,24 @@ void __weak arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 
 static void ftrace_update_trampoline(struct ftrace_ops *ops)
 {
+	unsigned long trampoline = ops->trampoline;
+
 	arch_ftrace_update_trampoline(ops);
+	if (ops->trampoline && ops->trampoline != trampoline &&
+	    (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) {
+		/* Add to kallsyms before the perf events */
+		ftrace_add_trampoline_to_kallsyms(ops);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size, false,
+				   FTRACE_TRAMPOLINE_SYM);
+		/*
+		 * Record the perf text poke event after the ksymbol register
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline, NULL, 0,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size);
+	}
 }
 
 void ftrace_init_trace_array(struct trace_array *tr)
@@ -6888,16 +6993,14 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 {
 	int bit;
 
-	if ((op->flags & FTRACE_OPS_FL_RCU) && !rcu_is_watching())
-		return;
-
 	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
 	if (bit < 0)
 		return;
 
 	preempt_disable_notrace();
 
-	op->func(ip, parent_ip, op, regs);
+	if (!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching())
+		op->func(ip, parent_ip, op, regs);
 
 	preempt_enable_notrace();
 	trace_clear_recursion(bit);
@@ -6980,12 +7083,12 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						  tr);
-		register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		register_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						  tr);
 	} else {
 		unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		unregister_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						    tr);
 	}
 }
@@ -7162,6 +7265,10 @@ static int pid_open(struct inode *inode, struct file *file, int type)
 	case TRACE_NO_PIDS:
 		seq_ops = &ftrace_no_pid_sops;
 		break;
+	default:
+		trace_array_put(tr);
+		WARN_ON_ONCE(1);
+		return -EINVAL;
 	}
 
 	ret = seq_open(file, seq_ops);
@@ -7240,6 +7347,10 @@ pid_write(struct file *filp, const char __user *ubuf,
 		other_pids = rcu_dereference_protected(tr->function_pids,
 					     lockdep_is_held(&ftrace_lock));
 		break;
+	default:
+		ret = -EINVAL;
+		WARN_ON_ONCE(1);
+		goto out;
 	}
 
 	ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
@@ -7421,8 +7532,7 @@ static bool is_permanent_ops_registered(void)
 
 int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-		     void __user *buffer, size_t *lenp,
-		     loff_t *ppos)
+		     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = -ENODEV;
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b8e1ca48be50..93ef0ab6ea20 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -270,6 +270,9 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 #define for_each_buffer_cpu(buffer, cpu)		\
 	for_each_cpu(cpu, buffer->cpumask)
 
+#define for_each_online_buffer_cpu(buffer, cpu)		\
+	for_each_cpu_and(cpu, buffer->cpumask, cpu_online_mask)
+
 #define TS_SHIFT	27
 #define TS_MASK		((1ULL << TS_SHIFT) - 1)
 #define TS_DELTA_TEST	(~TS_MASK)
@@ -413,12 +416,27 @@ struct rb_irq_work {
 struct rb_event_info {
 	u64			ts;
 	u64			delta;
+	u64			before;
+	u64			after;
 	unsigned long		length;
 	struct buffer_page	*tail_page;
 	int			add_timestamp;
 };
 
 /*
+ * Used for the add_timestamp
+ *  NONE
+ *  EXTEND - wants a time extend
+ *  ABSOLUTE - the buffer requests all events to have absolute time stamps
+ *  FORCE - force a full time stamp.
+ */
+enum {
+	RB_ADD_STAMP_NONE		= 0,
+	RB_ADD_STAMP_EXTEND		= BIT(1),
+	RB_ADD_STAMP_ABSOLUTE		= BIT(2),
+	RB_ADD_STAMP_FORCE		= BIT(3)
+};
+/*
  * Used for which event context the event is in.
  *  NMI     = 0
  *  IRQ     = 1
@@ -435,6 +453,28 @@ enum {
 	RB_CTX_MAX
 };
 
+#if BITS_PER_LONG == 32
+#define RB_TIME_32
+#endif
+
+/* To test on 64 bit machines */
+//#define RB_TIME_32
+
+#ifdef RB_TIME_32
+
+struct rb_time_struct {
+	local_t		cnt;
+	local_t		top;
+	local_t		bottom;
+};
+#else
+#include <asm/local64.h>
+struct rb_time_struct {
+	local64_t	time;
+};
+#endif
+typedef struct rb_time_struct rb_time_t;
+
 /*
  * head_page == tail_page && head == tail then buffer is empty.
  */
@@ -470,7 +510,8 @@ struct ring_buffer_per_cpu {
 	size_t				shortest_full;
 	unsigned long			read;
 	unsigned long			read_bytes;
-	u64				write_stamp;
+	rb_time_t			write_stamp;
+	rb_time_t			before_stamp;
 	u64				read_stamp;
 	/* ring buffer pages to update, > 0 to add, < 0 to remove */
 	long				nr_pages_to_update;
@@ -513,6 +554,189 @@ struct ring_buffer_iter {
 	int				missed_events;
 };
 
+#ifdef RB_TIME_32
+
+/*
+ * On 32 bit machines, local64_t is very expensive. As the ring
+ * buffer doesn't need all the features of a true 64 bit atomic,
+ * on 32 bit, it uses these functions (64 still uses local64_t).
+ *
+ * For the ring buffer, 64 bit required operations for the time is
+ * the following:
+ *
+ *  - Only need 59 bits (uses 60 to make it even).
+ *  - Reads may fail if it interrupted a modification of the time stamp.
+ *      It will succeed if it did not interrupt another write even if
+ *      the read itself is interrupted by a write.
+ *      It returns whether it was successful or not.
+ *
+ *  - Writes always succeed and will overwrite other writes and writes
+ *      that were done by events interrupting the current write.
+ *
+ *  - A write followed by a read of the same time stamp will always succeed,
+ *      but may not contain the same value.
+ *
+ *  - A cmpxchg will fail if it interrupted another write or cmpxchg.
+ *      Other than that, it acts like a normal cmpxchg.
+ *
+ * The 60 bit time stamp is broken up by 30 bits in a top and bottom half
+ *  (bottom being the least significant 30 bits of the 60 bit time stamp).
+ *
+ * The two most significant bits of each half holds a 2 bit counter (0-3).
+ * Each update will increment this counter by one.
+ * When reading the top and bottom, if the two counter bits match then the
+ *  top and bottom together make a valid 60 bit number.
+ */
+#define RB_TIME_SHIFT	30
+#define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1)
+
+static inline int rb_time_cnt(unsigned long val)
+{
+	return (val >> RB_TIME_SHIFT) & 3;
+}
+
+static inline u64 rb_time_val(unsigned long top, unsigned long bottom)
+{
+	u64 val;
+
+	val = top & RB_TIME_VAL_MASK;
+	val <<= RB_TIME_SHIFT;
+	val |= bottom & RB_TIME_VAL_MASK;
+
+	return val;
+}
+
+static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
+{
+	unsigned long top, bottom;
+	unsigned long c;
+
+	/*
+	 * If the read is interrupted by a write, then the cnt will
+	 * be different. Loop until both top and bottom have been read
+	 * without interruption.
+	 */
+	do {
+		c = local_read(&t->cnt);
+		top = local_read(&t->top);
+		bottom = local_read(&t->bottom);
+	} while (c != local_read(&t->cnt));
+
+	*cnt = rb_time_cnt(top);
+
+	/* If top and bottom counts don't match, this interrupted a write */
+	if (*cnt != rb_time_cnt(bottom))
+		return false;
+
+	*ret = rb_time_val(top, bottom);
+	return true;
+}
+
+static bool rb_time_read(rb_time_t *t, u64 *ret)
+{
+	unsigned long cnt;
+
+	return __rb_time_read(t, ret, &cnt);
+}
+
+static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt)
+{
+	return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT);
+}
+
+static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom)
+{
+	*top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK);
+	*bottom = (unsigned long)(val & RB_TIME_VAL_MASK);
+}
+
+static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt)
+{
+	val = rb_time_val_cnt(val, cnt);
+	local_set(t, val);
+}
+
+static void rb_time_set(rb_time_t *t, u64 val)
+{
+	unsigned long cnt, top, bottom;
+
+	rb_time_split(val, &top, &bottom);
+
+	/* Writes always succeed with a valid number even if it gets interrupted. */
+	do {
+		cnt = local_inc_return(&t->cnt);
+		rb_time_val_set(&t->top, top, cnt);
+		rb_time_val_set(&t->bottom, bottom, cnt);
+	} while (cnt != local_read(&t->cnt));
+}
+
+static inline bool
+rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
+{
+	unsigned long ret;
+
+	ret = local_cmpxchg(l, expect, set);
+	return ret == expect;
+}
+
+static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
+{
+	unsigned long cnt, top, bottom;
+	unsigned long cnt2, top2, bottom2;
+	u64 val;
+
+	/* The cmpxchg always fails if it interrupted an update */
+	 if (!__rb_time_read(t, &val, &cnt2))
+		 return false;
+
+	 if (val != expect)
+		 return false;
+
+	 cnt = local_read(&t->cnt);
+	 if ((cnt & 3) != cnt2)
+		 return false;
+
+	 cnt2 = cnt + 1;
+
+	 rb_time_split(val, &top, &bottom);
+	 top = rb_time_val_cnt(top, cnt);
+	 bottom = rb_time_val_cnt(bottom, cnt);
+
+	 rb_time_split(set, &top2, &bottom2);
+	 top2 = rb_time_val_cnt(top2, cnt2);
+	 bottom2 = rb_time_val_cnt(bottom2, cnt2);
+
+	if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2))
+		return false;
+	if (!rb_time_read_cmpxchg(&t->top, top, top2))
+		return false;
+	if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2))
+		return false;
+	return true;
+}
+
+#else /* 64 bits */
+
+/* local64_t always succeeds */
+
+static inline bool rb_time_read(rb_time_t *t, u64 *ret)
+{
+	*ret = local64_read(&t->time);
+	return true;
+}
+static void rb_time_set(rb_time_t *t, u64 val)
+{
+	local64_set(&t->time, val);
+}
+
+static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
+{
+	u64 val;
+	val = local64_cmpxchg(&t->time, expect, set);
+	return val == expect;
+}
+#endif
+
 /**
  * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer
  * @buffer: The ring_buffer to get the number of pages from
@@ -577,7 +801,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
  */
 int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 {
-	struct ring_buffer_per_cpu *uninitialized_var(cpu_buffer);
+	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
 	struct rb_irq_work *work;
 	int ret = 0;
@@ -746,8 +970,16 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 
 static inline u64 rb_time_stamp(struct trace_buffer *buffer)
 {
+	u64 ts;
+
+	/* Skip retpolines :-( */
+	if (IS_ENABLED(CONFIG_RETPOLINE) && likely(buffer->clock == trace_clock_local))
+		ts = trace_clock_local();
+	else
+		ts = buffer->clock();
+
 	/* shift to debug/test normalization and TIME_EXTENTS */
-	return buffer->clock() << DEBUG_SHIFT;
+	return ts << DEBUG_SHIFT;
 }
 
 u64 ring_buffer_time_stamp(struct trace_buffer *buffer, int cpu)
@@ -2372,8 +2604,8 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	return NULL;
 }
 
-/* Slow path, do not inline */
-static noinline struct ring_buffer_event *
+/* Slow path */
+static struct ring_buffer_event *
 rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
 {
 	if (abs)
@@ -2397,6 +2629,66 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
 static inline bool rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 				     struct ring_buffer_event *event);
 
+#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static inline bool sched_clock_stable(void)
+{
+	return true;
+}
+#endif
+
+static void
+rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
+		   struct rb_event_info *info)
+{
+	u64 write_stamp;
+
+	WARN_ONCE(1, "Delta way too big! %llu ts=%llu before=%llu after=%llu write stamp=%llu\n%s",
+		  (unsigned long long)info->delta,
+		  (unsigned long long)info->ts,
+		  (unsigned long long)info->before,
+		  (unsigned long long)info->after,
+		  (unsigned long long)(rb_time_read(&cpu_buffer->write_stamp, &write_stamp) ? write_stamp : 0),
+		  sched_clock_stable() ? "" :
+		  "If you just came from a suspend/resume,\n"
+		  "please switch to the trace global clock:\n"
+		  "  echo global > /sys/kernel/debug/tracing/trace_clock\n"
+		  "or add trace_clock=global to the kernel command line\n");
+}
+
+static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
+				      struct ring_buffer_event **event,
+				      struct rb_event_info *info,
+				      u64 *delta,
+				      unsigned int *length)
+{
+	bool abs = info->add_timestamp &
+		(RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE);
+
+	if (unlikely(info->delta > (1ULL << 59))) {
+		/* did the clock go backwards */
+		if (info->before == info->after && info->before > info->ts) {
+			/* not interrupted */
+			static int once;
+
+			/*
+			 * This is possible with a recalibrating of the TSC.
+			 * Do not produce a call stack, but just report it.
+			 */
+			if (!once) {
+				once++;
+				pr_warn("Ring buffer clock went backwards: %llu -> %llu\n",
+					info->before, info->ts);
+			}
+		} else
+			rb_check_timestamp(cpu_buffer, info);
+		if (!abs)
+			info->delta = 0;
+	}
+	*event = rb_add_time_stamp(*event, info->delta, abs);
+	*length -= RB_LEN_TIME_EXTEND;
+	*delta = 0;
+}
+
 /**
  * rb_update_event - update event type and data
  * @cpu_buffer: The per cpu buffer of the @event
@@ -2416,21 +2708,12 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,
 	unsigned length = info->length;
 	u64 delta = info->delta;
 
-	/* Only a commit updates the timestamp */
-	if (unlikely(!rb_event_is_commit(cpu_buffer, event)))
-		delta = 0;
-
 	/*
 	 * If we need to add a timestamp, then we
 	 * add it to the start of the reserved space.
 	 */
-	if (unlikely(info->add_timestamp)) {
-		bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer);
-
-		event = rb_add_time_stamp(event, info->delta, abs);
-		length -= RB_LEN_TIME_EXTEND;
-		delta = 0;
-	}
+	if (unlikely(info->add_timestamp))
+		rb_add_timestamp(cpu_buffer, &event, info, &delta, &length);
 
 	event->time_delta = delta;
 	length -= RB_EVNT_HDR_SIZE;
@@ -2473,12 +2756,38 @@ static unsigned rb_calculate_event_length(unsigned length)
 	return length;
 }
 
-#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static inline bool sched_clock_stable(void)
+static __always_inline bool
+rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
+		   struct ring_buffer_event *event)
 {
-	return true;
+	unsigned long addr = (unsigned long)event;
+	unsigned long index;
+
+	index = rb_event_index(event);
+	addr &= PAGE_MASK;
+
+	return cpu_buffer->commit_page->page == (void *)addr &&
+		rb_commit_index(cpu_buffer) == index;
+}
+
+static u64 rb_time_delta(struct ring_buffer_event *event)
+{
+	switch (event->type_len) {
+	case RINGBUF_TYPE_PADDING:
+		return 0;
+
+	case RINGBUF_TYPE_TIME_EXTEND:
+		return ring_buffer_event_time_stamp(event);
+
+	case RINGBUF_TYPE_TIME_STAMP:
+		return 0;
+
+	case RINGBUF_TYPE_DATA:
+		return event->time_delta;
+	default:
+		return 0;
+	}
 }
-#endif
 
 static inline int
 rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
@@ -2488,6 +2797,8 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	struct buffer_page *bpage;
 	unsigned long index;
 	unsigned long addr;
+	u64 write_stamp;
+	u64 delta;
 
 	new_index = rb_event_index(event);
 	old_index = new_index + rb_event_ts_length(event);
@@ -2496,10 +2807,32 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 
 	bpage = READ_ONCE(cpu_buffer->tail_page);
 
+	delta = rb_time_delta(event);
+
+	if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp))
+		return 0;
+
+	/* Make sure the write stamp is read before testing the location */
+	barrier();
+
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
 		unsigned long write_mask =
 			local_read(&bpage->write) & ~RB_WRITE_MASK;
 		unsigned long event_length = rb_event_length(event);
+
+		/* Something came in, can't discard */
+		if (!rb_time_cmpxchg(&cpu_buffer->write_stamp,
+				       write_stamp, write_stamp - delta))
+			return 0;
+
+		/*
+		 * If an event were to come in now, it would see that the
+		 * write_stamp and the before_stamp are different, and assume
+		 * that this event just added itself before updating
+		 * the write stamp. The interrupting event will fix the
+		 * write stamp for us, and use the before stamp as its delta.
+		 */
+
 		/*
 		 * This is on the tail page. It is possible that
 		 * a write could come in and move the tail page
@@ -2551,10 +2884,6 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 		local_set(&cpu_buffer->commit_page->page->commit,
 			  rb_page_write(cpu_buffer->commit_page));
 		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
-		/* Only update the write stamp if the page has an event */
-		if (rb_page_write(cpu_buffer->commit_page))
-			cpu_buffer->write_stamp =
-				cpu_buffer->commit_page->page->time_stamp;
 		/* add barrier to keep gcc from optimizing too much */
 		barrier();
 	}
@@ -2626,54 +2955,10 @@ static inline void rb_event_discard(struct ring_buffer_event *event)
 		event->time_delta = 1;
 }
 
-static __always_inline bool
-rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
-		   struct ring_buffer_event *event)
-{
-	unsigned long addr = (unsigned long)event;
-	unsigned long index;
-
-	index = rb_event_index(event);
-	addr &= PAGE_MASK;
-
-	return cpu_buffer->commit_page->page == (void *)addr &&
-		rb_commit_index(cpu_buffer) == index;
-}
-
-static __always_inline void
-rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer,
-		      struct ring_buffer_event *event)
-{
-	u64 delta;
-
-	/*
-	 * The event first in the commit queue updates the
-	 * time stamp.
-	 */
-	if (rb_event_is_commit(cpu_buffer, event)) {
-		/*
-		 * A commit event that is first on a page
-		 * updates the write timestamp with the page stamp
-		 */
-		if (!rb_event_index(event))
-			cpu_buffer->write_stamp =
-				cpu_buffer->commit_page->page->time_stamp;
-		else if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
-			delta = ring_buffer_event_time_stamp(event);
-			cpu_buffer->write_stamp += delta;
-		} else if (event->type_len == RINGBUF_TYPE_TIME_STAMP) {
-			delta = ring_buffer_event_time_stamp(event);
-			cpu_buffer->write_stamp = delta;
-		} else
-			cpu_buffer->write_stamp += event->time_delta;
-	}
-}
-
 static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 		      struct ring_buffer_event *event)
 {
 	local_inc(&cpu_buffer->entries);
-	rb_update_write_stamp(cpu_buffer, event);
 	rb_end_commit(cpu_buffer);
 }
 
@@ -2864,58 +3149,138 @@ int ring_buffer_unlock_commit(struct trace_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
 
-static noinline void
-rb_handle_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
-		    struct rb_event_info *info)
-{
-	WARN_ONCE(info->delta > (1ULL << 59),
-		  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
-		  (unsigned long long)info->delta,
-		  (unsigned long long)info->ts,
-		  (unsigned long long)cpu_buffer->write_stamp,
-		  sched_clock_stable() ? "" :
-		  "If you just came from a suspend/resume,\n"
-		  "please switch to the trace global clock:\n"
-		  "  echo global > /sys/kernel/debug/tracing/trace_clock\n"
-		  "or add trace_clock=global to the kernel command line\n");
-	info->add_timestamp = 1;
-}
-
 static struct ring_buffer_event *
 __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		  struct rb_event_info *info)
 {
 	struct ring_buffer_event *event;
 	struct buffer_page *tail_page;
-	unsigned long tail, write;
-
-	/*
-	 * If the time delta since the last event is too big to
-	 * hold in the time field of the event, then we append a
-	 * TIME EXTEND event ahead of the data event.
-	 */
-	if (unlikely(info->add_timestamp))
-		info->length += RB_LEN_TIME_EXTEND;
+	unsigned long tail, write, w;
+	bool a_ok;
+	bool b_ok;
 
 	/* Don't let the compiler play games with cpu_buffer->tail_page */
 	tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page);
-	write = local_add_return(info->length, &tail_page->write);
+
+ /*A*/	w = local_read(&tail_page->write) & RB_WRITE_MASK;
+	barrier();
+	b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
+	a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+	barrier();
+	info->ts = rb_time_stamp(cpu_buffer->buffer);
+
+	if ((info->add_timestamp & RB_ADD_STAMP_ABSOLUTE)) {
+		info->delta = info->ts;
+	} else {
+		/*
+		 * If interrupting an event time update, we may need an
+		 * absolute timestamp.
+		 * Don't bother if this is the start of a new page (w == 0).
+		 */
+		if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) {
+			info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND;
+			info->length += RB_LEN_TIME_EXTEND;
+		} else {
+			info->delta = info->ts - info->after;
+			if (unlikely(test_time_stamp(info->delta))) {
+				info->add_timestamp |= RB_ADD_STAMP_EXTEND;
+				info->length += RB_LEN_TIME_EXTEND;
+			}
+		}
+	}
+
+ /*B*/	rb_time_set(&cpu_buffer->before_stamp, info->ts);
+
+ /*C*/	write = local_add_return(info->length, &tail_page->write);
 
 	/* set write to only the index of the write */
 	write &= RB_WRITE_MASK;
+
 	tail = write - info->length;
 
+	/* See if we shot pass the end of this buffer page */
+	if (unlikely(write > BUF_PAGE_SIZE)) {
+		if (tail != w) {
+			/* before and after may now different, fix it up*/
+			b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
+			a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+			if (a_ok && b_ok && info->before != info->after)
+				(void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
+						      info->before, info->after);
+		}
+		return rb_move_tail(cpu_buffer, tail, info);
+	}
+
+	if (likely(tail == w)) {
+		u64 save_before;
+		bool s_ok;
+
+		/* Nothing interrupted us between A and C */
+ /*D*/		rb_time_set(&cpu_buffer->write_stamp, info->ts);
+		barrier();
+ /*E*/		s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before);
+		RB_WARN_ON(cpu_buffer, !s_ok);
+		if (likely(!(info->add_timestamp &
+			     (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE))))
+			/* This did not interrupt any time update */
+			info->delta = info->ts - info->after;
+		else
+			/* Just use full timestamp for inerrupting event */
+			info->delta = info->ts;
+		barrier();
+		if (unlikely(info->ts != save_before)) {
+			/* SLOW PATH - Interrupted between C and E */
+
+			a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+			RB_WARN_ON(cpu_buffer, !a_ok);
+
+			/* Write stamp must only go forward */
+			if (save_before > info->after) {
+				/*
+				 * We do not care about the result, only that
+				 * it gets updated atomically.
+				 */
+				(void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
+						      info->after, save_before);
+			}
+		}
+	} else {
+		u64 ts;
+		/* SLOW PATH - Interrupted between A and C */
+		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+		/* Was interrupted before here, write_stamp must be valid */
+		RB_WARN_ON(cpu_buffer, !a_ok);
+		ts = rb_time_stamp(cpu_buffer->buffer);
+		barrier();
+ /*E*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
+		    info->after < ts) {
+			/* Nothing came after this event between C and E */
+			info->delta = ts - info->after;
+			(void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
+					      info->after, info->ts);
+			info->ts = ts;
+		} else {
+			/*
+			 * Interrupted beween C and E:
+			 * Lost the previous events time stamp. Just set the
+			 * delta to zero, and this will be the same time as
+			 * the event this event interrupted. And the events that
+			 * came after this will still be correct (as they would
+			 * have built their delta on the previous event.
+			 */
+			info->delta = 0;
+		}
+		info->add_timestamp &= ~RB_ADD_STAMP_FORCE;
+	}
+
 	/*
 	 * If this is the first commit on the page, then it has the same
 	 * timestamp as the page itself.
 	 */
-	if (!tail && !ring_buffer_time_stamp_abs(cpu_buffer->buffer))
+	if (unlikely(!tail && !(info->add_timestamp &
+				(RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE))))
 		info->delta = 0;
 
-	/* See if we shot pass the end of this buffer page */
-	if (unlikely(write > BUF_PAGE_SIZE))
-		return rb_move_tail(cpu_buffer, tail, info);
-
 	/* We reserved something on the buffer */
 
 	event = __rb_page_index(tail_page, tail);
@@ -2927,7 +3292,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	 * If this is the first commit on the page, then update
 	 * its timestamp.
 	 */
-	if (!tail)
+	if (unlikely(!tail))
 		tail_page->page->time_stamp = info->ts;
 
 	/* account for these added bytes */
@@ -2944,9 +3309,10 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	struct ring_buffer_event *event;
 	struct rb_event_info info;
 	int nr_loops = 0;
-	u64 diff;
+	int add_ts_default;
 
 	rb_start_commit(cpu_buffer);
+	/* The commit page can not change after this */
 
 #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
 	/*
@@ -2964,8 +3330,16 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 #endif
 
 	info.length = rb_calculate_event_length(length);
+
+	if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
+		add_ts_default = RB_ADD_STAMP_ABSOLUTE;
+		info.length += RB_LEN_TIME_EXTEND;
+	} else {
+		add_ts_default = RB_ADD_STAMP_NONE;
+	}
+
  again:
-	info.add_timestamp = 0;
+	info.add_timestamp = add_ts_default;
 	info.delta = 0;
 
 	/*
@@ -2980,35 +3354,16 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
 		goto out_fail;
 
-	info.ts = rb_time_stamp(cpu_buffer->buffer);
-	diff = info.ts - cpu_buffer->write_stamp;
-
-	/* make sure this diff is calculated here */
-	barrier();
-
-	if (ring_buffer_time_stamp_abs(buffer)) {
-		info.delta = info.ts;
-		rb_handle_timestamp(cpu_buffer, &info);
-	} else /* Did the write stamp get updated already? */
-		if (likely(info.ts >= cpu_buffer->write_stamp)) {
-		info.delta = diff;
-		if (unlikely(test_time_stamp(info.delta)))
-			rb_handle_timestamp(cpu_buffer, &info);
-	}
-
 	event = __rb_reserve_next(cpu_buffer, &info);
 
 	if (unlikely(PTR_ERR(event) == -EAGAIN)) {
-		if (info.add_timestamp)
+		if (info.add_timestamp & (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND))
 			info.length -= RB_LEN_TIME_EXTEND;
 		goto again;
 	}
 
-	if (!event)
-		goto out_fail;
-
-	return event;
-
+	if (likely(event))
+		return event;
  out_fail:
 	rb_end_commit(cpu_buffer);
 	return NULL;
@@ -3154,11 +3509,6 @@ void ring_buffer_discard_commit(struct trace_buffer *buffer,
 	if (rb_try_to_discard(cpu_buffer, event))
 		goto out;
 
-	/*
-	 * The commit is still visible by the reader, so we
-	 * must still update the timestamp.
-	 */
-	rb_update_write_stamp(cpu_buffer, event);
  out:
 	rb_end_commit(cpu_buffer);
 
@@ -4475,8 +4825,8 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->read = 0;
 	cpu_buffer->read_bytes = 0;
 
-	cpu_buffer->write_stamp = 0;
-	cpu_buffer->read_stamp = 0;
+	rb_time_set(&cpu_buffer->write_stamp, 0);
+	rb_time_set(&cpu_buffer->before_stamp, 0);
 
 	cpu_buffer->lost_events = 0;
 	cpu_buffer->last_overrun = 0;
@@ -4484,6 +4834,26 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	rb_head_page_activate(cpu_buffer);
 }
 
+/* Must have disabled the cpu buffer then done a synchronize_rcu */
+static void reset_disabled_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
+		goto out;
+
+	arch_spin_lock(&cpu_buffer->lock);
+
+	rb_reset_cpu(cpu_buffer);
+
+	arch_spin_unlock(&cpu_buffer->lock);
+
+ out:
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+}
+
 /**
  * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
  * @buffer: The ring buffer to reset a per cpu buffer of
@@ -4492,7 +4862,6 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
-	unsigned long flags;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
@@ -4503,24 +4872,42 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
 	/* Make sure all commits have finished */
 	synchronize_rcu();
 
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	reset_disabled_cpu_buffer(cpu_buffer);
 
-	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
-		goto out;
+	atomic_dec(&cpu_buffer->record_disabled);
+	atomic_dec(&cpu_buffer->resize_disabled);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
-	arch_spin_lock(&cpu_buffer->lock);
+/**
+ * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
+ * @buffer: The ring buffer to reset a per cpu buffer of
+ * @cpu: The CPU buffer to be reset
+ */
+void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	int cpu;
 
-	rb_reset_cpu(cpu_buffer);
+	for_each_online_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
 
-	arch_spin_unlock(&cpu_buffer->lock);
+		atomic_inc(&cpu_buffer->resize_disabled);
+		atomic_inc(&cpu_buffer->record_disabled);
+	}
 
- out:
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	/* Make sure all commits have finished */
+	synchronize_rcu();
 
-	atomic_dec(&cpu_buffer->record_disabled);
-	atomic_dec(&cpu_buffer->resize_disabled);
+	for_each_online_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		reset_disabled_cpu_buffer(cpu_buffer);
+
+		atomic_dec(&cpu_buffer->record_disabled);
+		atomic_dec(&cpu_buffer->resize_disabled);
+	}
 }
-EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
 /**
  * ring_buffer_reset - reset a ring buffer
@@ -4528,10 +4915,27 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
  */
 void ring_buffer_reset(struct trace_buffer *buffer)
 {
+	struct ring_buffer_per_cpu *cpu_buffer;
 	int cpu;
 
-	for_each_buffer_cpu(buffer, cpu)
-		ring_buffer_reset_cpu(buffer, cpu);
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		atomic_inc(&cpu_buffer->resize_disabled);
+		atomic_inc(&cpu_buffer->record_disabled);
+	}
+
+	/* Make sure all commits have finished */
+	synchronize_rcu();
+
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		reset_disabled_cpu_buffer(cpu_buffer);
+
+		atomic_dec(&cpu_buffer->record_disabled);
+		atomic_dec(&cpu_buffer->resize_disabled);
+	}
 }
 EXPORT_SYMBOL_GPL(ring_buffer_reset);
 
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 8df0aa810950..78e576575b79 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -45,8 +45,8 @@ MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
 static int producer_nice = MAX_NICE;
 static int consumer_nice = MAX_NICE;
 
-static int producer_fifo = -1;
-static int consumer_fifo = -1;
+static int producer_fifo;
+static int consumer_fifo;
 
 module_param(producer_nice, int, 0644);
 MODULE_PARM_DESC(producer_nice, "nice prio for producer");
@@ -55,10 +55,10 @@ module_param(consumer_nice, int, 0644);
 MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
 
 module_param(producer_fifo, int, 0644);
-MODULE_PARM_DESC(producer_fifo, "fifo prio for producer");
+MODULE_PARM_DESC(producer_fifo, "use fifo for producer: 0 - disabled, 1 - low prio, 2 - fifo");
 
 module_param(consumer_fifo, int, 0644);
-MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
+MODULE_PARM_DESC(consumer_fifo, "use fifo for consumer: 0 - disabled, 1 - low prio, 2 - fifo");
 
 static int read_events;
 
@@ -303,22 +303,22 @@ static void ring_buffer_producer(void)
 		trace_printk("ERROR!\n");
 
 	if (!disable_reader) {
-		if (consumer_fifo < 0)
+		if (consumer_fifo)
+			trace_printk("Running Consumer at SCHED_FIFO %s\n",
+				     consumer_fifo == 1 ? "low" : "high");
+		else
 			trace_printk("Running Consumer at nice: %d\n",
 				     consumer_nice);
-		else
-			trace_printk("Running Consumer at SCHED_FIFO %d\n",
-				     consumer_fifo);
 	}
-	if (producer_fifo < 0)
+	if (producer_fifo)
+		trace_printk("Running Producer at SCHED_FIFO %s\n",
+			     producer_fifo == 1 ? "low" : "high");
+	else
 		trace_printk("Running Producer at nice: %d\n",
 			     producer_nice);
-	else
-		trace_printk("Running Producer at SCHED_FIFO %d\n",
-			     producer_fifo);
 
 	/* Let the user know that the test is running at low priority */
-	if (producer_fifo < 0 && consumer_fifo < 0 &&
+	if (!producer_fifo && !consumer_fifo &&
 	    producer_nice == MAX_NICE && consumer_nice == MAX_NICE)
 		trace_printk("WARNING!!! This test is running at lowest priority.\n");
 
@@ -455,21 +455,19 @@ static int __init ring_buffer_benchmark_init(void)
 	 * Run them as low-prio background tasks by default:
 	 */
 	if (!disable_reader) {
-		if (consumer_fifo >= 0) {
-			struct sched_param param = {
-				.sched_priority = consumer_fifo
-			};
-			sched_setscheduler(consumer, SCHED_FIFO, &param);
-		} else
+		if (consumer_fifo >= 2)
+			sched_set_fifo(consumer);
+		else if (consumer_fifo == 1)
+			sched_set_fifo_low(consumer);
+		else
 			set_user_nice(consumer, consumer_nice);
 	}
 
-	if (producer_fifo >= 0) {
-		struct sched_param param = {
-			.sched_priority = producer_fifo
-		};
-		sched_setscheduler(producer, SCHED_FIFO, &param);
-	} else
+	if (producer_fifo >= 2)
+		sched_set_fifo(producer);
+	else if (producer_fifo == 1)
+		sched_set_fifo_low(producer);
+	else
 		set_user_nice(producer, producer_nice);
 
 	return 0;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 29615f15a820..d3e5de717df2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1299,8 +1299,11 @@ EXPORT_SYMBOL_GPL(tracing_off);
 
 void disable_trace_on_warning(void)
 {
-	if (__disable_trace_on_warning)
+	if (__disable_trace_on_warning) {
+		trace_array_printk_buf(global_trace.array_buffer.buffer, _THIS_IP_,
+			"Disabling tracing due to warning\n");
 		tracing_off();
+	}
 }
 
 /**
@@ -1540,8 +1543,7 @@ static void latency_fsnotify_workfn(struct work_struct *work)
 {
 	struct trace_array *tr = container_of(work, struct trace_array,
 					      fsnotify_work);
-	fsnotify(tr->d_max_latency->d_inode, FS_MODIFY,
-		 tr->d_max_latency->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	fsnotify_inode(tr->d_max_latency->d_inode, FS_MODIFY);
 }
 
 static void latency_fsnotify_workfn_irq(struct irq_work *iwork)
@@ -2000,7 +2002,6 @@ static void tracing_reset_cpu(struct array_buffer *buf, int cpu)
 void tracing_reset_online_cpus(struct array_buffer *buf)
 {
 	struct trace_buffer *buffer = buf->buffer;
-	int cpu;
 
 	if (!buffer)
 		return;
@@ -2012,8 +2013,7 @@ void tracing_reset_online_cpus(struct array_buffer *buf)
 
 	buf->time_start = buffer_ftrace_now(buf, buf->cpu);
 
-	for_each_online_cpu(cpu)
-		ring_buffer_reset_cpu(buffer, cpu);
+	ring_buffer_reset_online_cpus(buffer);
 
 	ring_buffer_record_enable(buffer);
 }
@@ -2662,7 +2662,7 @@ static void output_printk(struct trace_event_buffer *fbuffer)
 }
 
 int tracepoint_printk_sysctl(struct ctl_table *table, int write,
-			     void __user *buffer, size_t *lenp,
+			     void *buffer, size_t *lenp,
 			     loff_t *ppos)
 {
 	int save_tracepoint_printk;
@@ -2929,12 +2929,6 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 		skip++;
 #endif
 
-	/*
-	 * Since events can happen in NMIs there's no safe way to
-	 * use the per cpu ftrace_stacks. We reserve it and if an interrupt
-	 * or NMI comes in, it will just have to use the default
-	 * FTRACE_STACK_SIZE.
-	 */
 	preempt_disable_notrace();
 
 	stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;
@@ -3134,6 +3128,9 @@ static int alloc_percpu_trace_buffer(void)
 {
 	struct trace_buffer_struct *buffers;
 
+	if (trace_percpu_buffer)
+		return 0;
+
 	buffers = alloc_percpu(struct trace_buffer_struct);
 	if (MEM_FAIL(!buffers, "Could not allocate percpu trace_printk buffer"))
 		return -ENOMEM;
@@ -3336,6 +3333,26 @@ int trace_array_vprintk(struct trace_array *tr,
 	return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args);
 }
 
+/**
+ * trace_array_printk - Print a message to a specific instance
+ * @tr: The instance trace_array descriptor
+ * @ip: The instruction pointer that this is called from.
+ * @fmt: The format to print (printf format)
+ *
+ * If a subsystem sets up its own instance, they have the right to
+ * printk strings into their tracing instance buffer using this
+ * function. Note, this function will not write into the top level
+ * buffer (use trace_printk() for that), as writing into the top level
+ * buffer should only have events that can be individually disabled.
+ * trace_printk() is only used for debugging a kernel, and should not
+ * be ever encorporated in normal use.
+ *
+ * trace_array_printk() can be used, as it will not add noise to the
+ * top level tracing buffer.
+ *
+ * Note, trace_array_init_printk() must be called on @tr before this
+ * can be used.
+ */
 __printf(3, 0)
 int trace_array_printk(struct trace_array *tr,
 		       unsigned long ip, const char *fmt, ...)
@@ -3343,12 +3360,16 @@ int trace_array_printk(struct trace_array *tr,
 	int ret;
 	va_list ap;
 
-	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
-		return 0;
-
 	if (!tr)
 		return -ENOENT;
 
+	/* This is only allowed for created instances */
+	if (tr == &global_trace)
+		return 0;
+
+	if (!(tr->trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
 	va_start(ap, fmt);
 	ret = trace_array_vprintk(tr, ip, fmt, ap);
 	va_end(ap);
@@ -3356,6 +3377,27 @@ int trace_array_printk(struct trace_array *tr,
 }
 EXPORT_SYMBOL_GPL(trace_array_printk);
 
+/**
+ * trace_array_init_printk - Initialize buffers for trace_array_printk()
+ * @tr: The trace array to initialize the buffers for
+ *
+ * As trace_array_printk() only writes into instances, they are OK to
+ * have in the kernel (unlike trace_printk()). This needs to be called
+ * before trace_array_printk() can be used on a trace_array.
+ */
+int trace_array_init_printk(struct trace_array *tr)
+{
+	if (!tr)
+		return -ENOENT;
+
+	/* This is only allowed for created instances */
+	if (tr == &global_trace)
+		return -EINVAL;
+
+	return alloc_percpu_trace_buffer();
+}
+EXPORT_SYMBOL_GPL(trace_array_init_printk);
+
 __printf(3, 4)
 int trace_array_printk_buf(struct trace_buffer *buffer,
 			   unsigned long ip, const char *fmt, ...)
@@ -3504,13 +3546,15 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 	if (iter->ent && iter->ent != iter->temp) {
 		if ((!iter->temp || iter->temp_size < iter->ent_size) &&
 		    !WARN_ON_ONCE(iter->temp == static_temp_buf)) {
-			kfree(iter->temp);
-			iter->temp = kmalloc(iter->ent_size, GFP_KERNEL);
-			if (!iter->temp)
+			void *temp;
+			temp = kmalloc(iter->ent_size, GFP_KERNEL);
+			if (!temp)
 				return NULL;
+			kfree(iter->temp);
+			iter->temp = temp;
+			iter->temp_size = iter->ent_size;
 		}
 		memcpy(iter->temp, iter->ent, iter->ent_size);
-		iter->temp_size = iter->ent_size;
 		iter->ent = iter->temp;
 	}
 	entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts);
@@ -3567,7 +3611,6 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 {
-	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter;
 	unsigned long entries = 0;
 	u64 ts;
@@ -3585,7 +3628,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 	 * that a reset never took place on a cpu. This is evident
 	 * by the timestamp being before the start of the buffer.
 	 */
-	while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
+	while (ring_buffer_iter_peek(buf_iter, &ts)) {
 		if (ts >= iter->array_buffer->time_start)
 			break;
 		entries++;
@@ -3741,14 +3784,14 @@ unsigned long trace_total_entries(struct trace_array *tr)
 
 static void print_lat_help_header(struct seq_file *m)
 {
-	seq_puts(m, "#                  _------=> CPU#            \n"
-		    "#                 / _-----=> irqs-off        \n"
-		    "#                | / _----=> need-resched    \n"
-		    "#                || / _---=> hardirq/softirq \n"
-		    "#                ||| / _--=> preempt-depth   \n"
-		    "#                |||| /     delay            \n"
-		    "#  cmd     pid   ||||| time  |   caller      \n"
-		    "#     \\   /      |||||  \\    |   /         \n");
+	seq_puts(m, "#                    _------=> CPU#            \n"
+		    "#                   / _-----=> irqs-off        \n"
+		    "#                  | / _----=> need-resched    \n"
+		    "#                  || / _---=> hardirq/softirq \n"
+		    "#                  ||| / _--=> preempt-depth   \n"
+		    "#                  |||| /     delay            \n"
+		    "#  cmd     pid     ||||| time  |   caller      \n"
+		    "#     \\   /        |||||  \\    |   /         \n");
 }
 
 static void print_event_info(struct array_buffer *buf, struct seq_file *m)
@@ -3769,26 +3812,26 @@ static void print_func_help_header(struct array_buffer *buf, struct seq_file *m,
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#           TASK-PID   %s  CPU#   TIMESTAMP  FUNCTION\n", tgid ? "TGID     " : "");
-	seq_printf(m, "#              | |     %s    |       |         |\n",	 tgid ? "  |      " : "");
+	seq_printf(m, "#           TASK-PID    %s CPU#     TIMESTAMP  FUNCTION\n", tgid ? "   TGID   " : "");
+	seq_printf(m, "#              | |      %s   |         |         |\n",      tgid ? "     |    " : "");
 }
 
 static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m,
 				       unsigned int flags)
 {
 	bool tgid = flags & TRACE_ITER_RECORD_TGID;
-	const char *space = "          ";
-	int prec = tgid ? 10 : 2;
+	const char *space = "            ";
+	int prec = tgid ? 12 : 2;
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#                          %.*s  _-----=> irqs-off\n", prec, space);
-	seq_printf(m, "#                          %.*s / _----=> need-resched\n", prec, space);
-	seq_printf(m, "#                          %.*s| / _---=> hardirq/softirq\n", prec, space);
-	seq_printf(m, "#                          %.*s|| / _--=> preempt-depth\n", prec, space);
-	seq_printf(m, "#                          %.*s||| /     delay\n", prec, space);
-	seq_printf(m, "#           TASK-PID %.*sCPU#  ||||    TIMESTAMP  FUNCTION\n", prec, "   TGID   ");
-	seq_printf(m, "#              | |   %.*s  |   ||||       |         |\n", prec, "     |    ");
+	seq_printf(m, "#                            %.*s  _-----=> irqs-off\n", prec, space);
+	seq_printf(m, "#                            %.*s / _----=> need-resched\n", prec, space);
+	seq_printf(m, "#                            %.*s| / _---=> hardirq/softirq\n", prec, space);
+	seq_printf(m, "#                            %.*s|| / _--=> preempt-depth\n", prec, space);
+	seq_printf(m, "#                            %.*s||| /     delay\n", prec, space);
+	seq_printf(m, "#           TASK-PID  %.*s CPU#  ||||   TIMESTAMP  FUNCTION\n", prec, "     TGID   ");
+	seq_printf(m, "#              | |    %.*s   |   ||||      |         |\n", prec, "       |    ");
 }
 
 void
@@ -5885,7 +5928,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 	}
 
 	/* If trace pipe files are being read, we can't change the tracer */
-	if (tr->current_trace->ref) {
+	if (tr->trace_ref) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -6101,7 +6144,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 
 	nonseekable_open(inode, filp);
 
-	tr->current_trace->ref++;
+	tr->trace_ref++;
 out:
 	mutex_unlock(&trace_types_lock);
 	return ret;
@@ -6120,7 +6163,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
-	tr->current_trace->ref--;
+	tr->trace_ref--;
 
 	if (iter->trace->pipe_close)
 		iter->trace->pipe_close(iter);
@@ -6305,13 +6348,6 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
 	__free_page(spd->pages[idx]);
 }
 
-static const struct pipe_buf_operations tracing_pipe_buf_ops = {
-	.confirm		= generic_pipe_buf_confirm,
-	.release		= generic_pipe_buf_release,
-	.steal			= generic_pipe_buf_steal,
-	.get			= generic_pipe_buf_get,
-};
-
 static size_t
 tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
 {
@@ -6373,7 +6409,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		.partial	= partial_def,
 		.nr_pages	= 0, /* This gets updated below. */
 		.nr_pages_max	= PIPE_DEF_BUFFERS,
-		.ops		= &tracing_pipe_buf_ops,
+		.ops		= &default_pipe_buf_ops,
 		.spd_release	= tracing_spd_release_pipe,
 	};
 	ssize_t ret;
@@ -7411,7 +7447,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 	if (ret)
 		return ret;
 
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	info = kvzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info) {
 		trace_array_put(tr);
 		return -ENOMEM;
@@ -7429,7 +7465,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 
 	filp->private_data = info;
 
-	tr->current_trace->ref++;
+	tr->trace_ref++;
 
 	mutex_unlock(&trace_types_lock);
 
@@ -7530,14 +7566,14 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
-	iter->tr->current_trace->ref--;
+	iter->tr->trace_ref--;
 
 	__trace_array_put(iter->tr);
 
 	if (info->spare)
 		ring_buffer_free_read_page(iter->array_buffer->buffer,
 					   info->spare_cpu, info->spare);
-	kfree(info);
+	kvfree(info);
 
 	mutex_unlock(&trace_types_lock);
 
@@ -7582,9 +7618,7 @@ static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 
 /* Pipe buffer operations for a buffer. */
 static const struct pipe_buf_operations buffer_pipe_buf_ops = {
-	.confirm		= generic_pipe_buf_confirm,
 	.release		= buffer_pipe_buf_release,
-	.steal			= generic_pipe_buf_nosteal,
 	.get			= buffer_pipe_buf_get,
 };
 
@@ -8527,18 +8561,6 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	allocate_snapshot = false;
 #endif
 
-	/*
-	 * Because of some magic with the way alloc_percpu() works on
-	 * x86_64, we need to synchronize the pgd of all the tables,
-	 * otherwise the trace events that happen in x86_64 page fault
-	 * handlers can't cope with accessing the chance that a
-	 * alloc_percpu()'d memory might be touched in the page fault trace
-	 * event. Oh, and we need to audit all other alloc_percpu() and vmalloc()
-	 * calls in tracing, because something might get triggered within a
-	 * page fault trace event!
-	 */
-	vmalloc_sync_mappings();
-
 	return 0;
 }
 
@@ -8752,7 +8774,7 @@ static int __remove_instance(struct trace_array *tr)
 	int i;
 
 	/* Reference counter for a newly created trace array = 1. */
-	if (tr->ref > 1 || (tr->current_trace && tr->current_trace->ref))
+	if (tr->ref > 1 || (tr->current_trace && tr->trace_ref))
 		return -EBUSY;
 
 	list_del(&tr->list);
@@ -8964,9 +8986,7 @@ struct dentry *tracing_init_dentry(void)
 	if (tr->dir)
 		return NULL;
 
-	if (WARN_ON(!tracefs_initialized()) ||
-		(IS_ENABLED(CONFIG_DEBUG_FS) &&
-		 WARN_ON(!debugfs_initialized())))
+	if (WARN_ON(!tracefs_initialized()))
 		return ERR_PTR(-ENODEV);
 
 	/*
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 4eb1d004d5f2..610d21355526 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -61,6 +61,9 @@ enum trace_type {
 #undef __field_desc
 #define __field_desc(type, container, item)
 
+#undef __field_packed
+#define __field_packed(type, container, item)
+
 #undef __array
 #define __array(type, item, size)	type	item[size];
 
@@ -353,6 +356,7 @@ struct trace_array {
 	struct trace_event_file *trace_marker_file;
 	cpumask_var_t		tracing_cpumask; /* only trace on set CPUs */
 	int			ref;
+	int			trace_ref;
 #ifdef CONFIG_FUNCTION_TRACER
 	struct ftrace_ops	*ops;
 	struct trace_pid_list	__rcu *function_pids;
@@ -544,7 +548,6 @@ struct tracer {
 	struct tracer		*next;
 	struct tracer_flags	*flags;
 	int			enabled;
-	int			ref;
 	bool			print_max;
 	bool			allow_instances;
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -1100,6 +1103,10 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 extern struct list_head ftrace_pids;
 
 #ifdef CONFIG_FUNCTION_TRACER
+
+#define FTRACE_PID_IGNORE	-1
+#define FTRACE_PID_TRACE	-2
+
 struct ftrace_func_command {
 	struct list_head	list;
 	char			*name;
@@ -1111,7 +1118,8 @@ struct ftrace_func_command {
 extern bool ftrace_filter_param __initdata;
 static inline int ftrace_trace_task(struct trace_array *tr)
 {
-	return !this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid);
+	return this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid) !=
+		FTRACE_PID_IGNORE;
 }
 extern int ftrace_is_dead(void);
 int ftrace_create_function_files(struct trace_array *tr,
@@ -1661,6 +1669,7 @@ extern struct list_head ftrace_events;
 
 extern const struct file_operations event_trigger_fops;
 extern const struct file_operations event_hist_fops;
+extern const struct file_operations event_hist_debug_fops;
 extern const struct file_operations event_inject_fops;
 
 #ifdef CONFIG_HIST_TRIGGERS
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 9de29bb45a27..fa0fc08c6ef8 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -101,12 +101,16 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)
 		kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
 
 		ret = kprobe_event_gen_cmd_start(&cmd, event, val);
-		if (ret)
+		if (ret) {
+			pr_err("Failed to generate probe: %s\n", buf);
 			break;
+		}
 
 		ret = kprobe_event_gen_cmd_end(&cmd);
-		if (ret)
+		if (ret) {
 			pr_err("Failed to add probe: %s\n", buf);
+			break;
+		}
 	}
 
 	return ret;
@@ -120,7 +124,7 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)
 }
 #endif
 
-#ifdef CONFIG_HIST_TRIGGERS
+#ifdef CONFIG_SYNTH_EVENTS
 static int __init
 trace_boot_add_synth_event(struct xbc_node *node, const char *event)
 {
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index a523da0dae0a..18c4a58aff79 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -78,8 +78,8 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
 
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ent,	graph_ent	)
-		__field_desc(	unsigned long,	graph_ent,	func		)
-		__field_desc(	int,		graph_ent,	depth		)
+		__field_packed(	unsigned long,	graph_ent,	func		)
+		__field_packed(	int,		graph_ent,	depth		)
 	),
 
 	F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth)
@@ -92,11 +92,11 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ret,	ret	)
-		__field_desc(	unsigned long,	ret,		func	)
-		__field_desc(	unsigned long,	ret,		overrun	)
-		__field_desc(	unsigned long long, ret,	calltime)
-		__field_desc(	unsigned long long, ret,	rettime	)
-		__field_desc(	int,		ret,		depth	)
+		__field_packed(	unsigned long,	ret,		func	)
+		__field_packed(	unsigned long,	ret,		overrun	)
+		__field_packed(	unsigned long long, ret,	calltime)
+		__field_packed(	unsigned long long, ret,	rettime	)
+		__field_packed(	int,		ret,		depth	)
 	),
 
 	F_printk("<-- %ps (%d) (start: %llx  end: %llx) over: %d",
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 242f59e7f17d..a85effb2373b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -538,12 +538,12 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork,
 						       tr, INT_MIN);
-		register_trace_prio_sched_process_exit(event_filter_pid_sched_process_exit,
+		register_trace_prio_sched_process_free(event_filter_pid_sched_process_exit,
 						       tr, INT_MAX);
 	} else {
 		unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(event_filter_pid_sched_process_exit,
+		unregister_trace_sched_process_free(event_filter_pid_sched_process_exit,
 						    tr);
 	}
 }
@@ -2209,6 +2209,10 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	trace_create_file("hist", 0444, file->dir, file,
 			  &event_hist_fops);
 #endif
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+	trace_create_file("hist_debug", 0444, file->dir, file,
+			  &event_hist_debug_fops);
+#endif
 	trace_create_file("format", 0444, file->dir, call,
 			  &ftrace_event_format_fops);
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index bf44f6bbd0c3..78a678eeb140 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -499,7 +499,7 @@ predicate_parse(const char *str, int nr_parens, int nr_preds,
 					ptr++;
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			default:
 				parse_error(pe, FILT_ERR_TOO_MANY_PREDS,
 					    next - str);
@@ -1273,7 +1273,7 @@ static int parse_pred(const char *str, void *data,
 		switch (op) {
 		case OP_NE:
 			pred->not = 1;
-			/* Fall through */
+			fallthrough;
 		case OP_GLOB:
 		case OP_EQ:
 			break;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index fcab11cc6833..1b2ef6490229 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -19,13 +19,7 @@
 #include <trace/events/mmflags.h>
 
 #include "tracing_map.h"
-#include "trace.h"
-#include "trace_dynevent.h"
-
-#define SYNTH_SYSTEM		"synthetic"
-#define SYNTH_FIELDS_MAX	32
-
-#define STR_VAR_LEN_MAX		32 /* must be multiple of sizeof(u64) */
+#include "trace_synth.h"
 
 #define ERRORS								\
 	C(NONE,			"No error"),				\
@@ -380,69 +374,6 @@ struct hist_trigger_data {
 	unsigned int			n_save_var_str;
 };
 
-static int create_synth_event(int argc, const char **argv);
-static int synth_event_show(struct seq_file *m, struct dyn_event *ev);
-static int synth_event_release(struct dyn_event *ev);
-static bool synth_event_is_busy(struct dyn_event *ev);
-static bool synth_event_match(const char *system, const char *event,
-			int argc, const char **argv, struct dyn_event *ev);
-
-static struct dyn_event_operations synth_event_ops = {
-	.create = create_synth_event,
-	.show = synth_event_show,
-	.is_busy = synth_event_is_busy,
-	.free = synth_event_release,
-	.match = synth_event_match,
-};
-
-struct synth_field {
-	char *type;
-	char *name;
-	size_t size;
-	unsigned int offset;
-	bool is_signed;
-	bool is_string;
-};
-
-struct synth_event {
-	struct dyn_event			devent;
-	int					ref;
-	char					*name;
-	struct synth_field			**fields;
-	unsigned int				n_fields;
-	unsigned int				n_u64;
-	struct trace_event_class		class;
-	struct trace_event_call			call;
-	struct tracepoint			*tp;
-	struct module				*mod;
-};
-
-static bool is_synth_event(struct dyn_event *ev)
-{
-	return ev->ops == &synth_event_ops;
-}
-
-static struct synth_event *to_synth_event(struct dyn_event *ev)
-{
-	return container_of(ev, struct synth_event, devent);
-}
-
-static bool synth_event_is_busy(struct dyn_event *ev)
-{
-	struct synth_event *event = to_synth_event(ev);
-
-	return event->ref != 0;
-}
-
-static bool synth_event_match(const char *system, const char *event,
-			int argc, const char **argv, struct dyn_event *ev)
-{
-	struct synth_event *sev = to_synth_event(ev);
-
-	return strcmp(sev->name, event) == 0 &&
-		(!system || strcmp(system, SYNTH_SYSTEM) == 0);
-}
-
 struct action_data;
 
 typedef void (*action_fn_t) (struct hist_trigger_data *hist_data,
@@ -589,6 +520,7 @@ static struct track_data *track_data_alloc(unsigned int key_len,
 		track_data_free(data);
 		return ERR_PTR(-ENOMEM);
 	}
+
 	data->elt.private_data = elt_data;
 
 	elt_data->comm = kzalloc(TASK_COMM_LEN, GFP_KERNEL);
@@ -621,7 +553,6 @@ static void last_cmd_set(struct trace_event_file *file, char *str)
 
 	if (file) {
 		call = file->event_call;
-
 		system = call->class->system;
 		if (system) {
 			name = trace_event_name(call);
@@ -646,510 +577,6 @@ static void hist_err_clear(void)
 	last_cmd_loc[0] = '\0';
 }
 
-struct synth_trace_event {
-	struct trace_entry	ent;
-	u64			fields[];
-};
-
-static int synth_event_define_fields(struct trace_event_call *call)
-{
-	struct synth_trace_event trace;
-	int offset = offsetof(typeof(trace), fields);
-	struct synth_event *event = call->data;
-	unsigned int i, size, n_u64;
-	char *name, *type;
-	bool is_signed;
-	int ret = 0;
-
-	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
-		size = event->fields[i]->size;
-		is_signed = event->fields[i]->is_signed;
-		type = event->fields[i]->type;
-		name = event->fields[i]->name;
-		ret = trace_define_field(call, type, name, offset, size,
-					 is_signed, FILTER_OTHER);
-		if (ret)
-			break;
-
-		event->fields[i]->offset = n_u64;
-
-		if (event->fields[i]->is_string) {
-			offset += STR_VAR_LEN_MAX;
-			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
-		} else {
-			offset += sizeof(u64);
-			n_u64++;
-		}
-	}
-
-	event->n_u64 = n_u64;
-
-	return ret;
-}
-
-static bool synth_field_signed(char *type)
-{
-	if (str_has_prefix(type, "u"))
-		return false;
-	if (strcmp(type, "gfp_t") == 0)
-		return false;
-
-	return true;
-}
-
-static int synth_field_is_string(char *type)
-{
-	if (strstr(type, "char[") != NULL)
-		return true;
-
-	return false;
-}
-
-static int synth_field_string_size(char *type)
-{
-	char buf[4], *end, *start;
-	unsigned int len;
-	int size, err;
-
-	start = strstr(type, "char[");
-	if (start == NULL)
-		return -EINVAL;
-	start += sizeof("char[") - 1;
-
-	end = strchr(type, ']');
-	if (!end || end < start)
-		return -EINVAL;
-
-	len = end - start;
-	if (len > 3)
-		return -EINVAL;
-
-	strncpy(buf, start, len);
-	buf[len] = '\0';
-
-	err = kstrtouint(buf, 0, &size);
-	if (err)
-		return err;
-
-	if (size > STR_VAR_LEN_MAX)
-		return -EINVAL;
-
-	return size;
-}
-
-static int synth_field_size(char *type)
-{
-	int size = 0;
-
-	if (strcmp(type, "s64") == 0)
-		size = sizeof(s64);
-	else if (strcmp(type, "u64") == 0)
-		size = sizeof(u64);
-	else if (strcmp(type, "s32") == 0)
-		size = sizeof(s32);
-	else if (strcmp(type, "u32") == 0)
-		size = sizeof(u32);
-	else if (strcmp(type, "s16") == 0)
-		size = sizeof(s16);
-	else if (strcmp(type, "u16") == 0)
-		size = sizeof(u16);
-	else if (strcmp(type, "s8") == 0)
-		size = sizeof(s8);
-	else if (strcmp(type, "u8") == 0)
-		size = sizeof(u8);
-	else if (strcmp(type, "char") == 0)
-		size = sizeof(char);
-	else if (strcmp(type, "unsigned char") == 0)
-		size = sizeof(unsigned char);
-	else if (strcmp(type, "int") == 0)
-		size = sizeof(int);
-	else if (strcmp(type, "unsigned int") == 0)
-		size = sizeof(unsigned int);
-	else if (strcmp(type, "long") == 0)
-		size = sizeof(long);
-	else if (strcmp(type, "unsigned long") == 0)
-		size = sizeof(unsigned long);
-	else if (strcmp(type, "pid_t") == 0)
-		size = sizeof(pid_t);
-	else if (strcmp(type, "gfp_t") == 0)
-		size = sizeof(gfp_t);
-	else if (synth_field_is_string(type))
-		size = synth_field_string_size(type);
-
-	return size;
-}
-
-static const char *synth_field_fmt(char *type)
-{
-	const char *fmt = "%llu";
-
-	if (strcmp(type, "s64") == 0)
-		fmt = "%lld";
-	else if (strcmp(type, "u64") == 0)
-		fmt = "%llu";
-	else if (strcmp(type, "s32") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "u32") == 0)
-		fmt = "%u";
-	else if (strcmp(type, "s16") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "u16") == 0)
-		fmt = "%u";
-	else if (strcmp(type, "s8") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "u8") == 0)
-		fmt = "%u";
-	else if (strcmp(type, "char") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "unsigned char") == 0)
-		fmt = "%u";
-	else if (strcmp(type, "int") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "unsigned int") == 0)
-		fmt = "%u";
-	else if (strcmp(type, "long") == 0)
-		fmt = "%ld";
-	else if (strcmp(type, "unsigned long") == 0)
-		fmt = "%lu";
-	else if (strcmp(type, "pid_t") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "gfp_t") == 0)
-		fmt = "%x";
-	else if (synth_field_is_string(type))
-		fmt = "%s";
-
-	return fmt;
-}
-
-static void print_synth_event_num_val(struct trace_seq *s,
-				      char *print_fmt, char *name,
-				      int size, u64 val, char *space)
-{
-	switch (size) {
-	case 1:
-		trace_seq_printf(s, print_fmt, name, (u8)val, space);
-		break;
-
-	case 2:
-		trace_seq_printf(s, print_fmt, name, (u16)val, space);
-		break;
-
-	case 4:
-		trace_seq_printf(s, print_fmt, name, (u32)val, space);
-		break;
-
-	default:
-		trace_seq_printf(s, print_fmt, name, val, space);
-		break;
-	}
-}
-
-static enum print_line_t print_synth_event(struct trace_iterator *iter,
-					   int flags,
-					   struct trace_event *event)
-{
-	struct trace_array *tr = iter->tr;
-	struct trace_seq *s = &iter->seq;
-	struct synth_trace_event *entry;
-	struct synth_event *se;
-	unsigned int i, n_u64;
-	char print_fmt[32];
-	const char *fmt;
-
-	entry = (struct synth_trace_event *)iter->ent;
-	se = container_of(event, struct synth_event, call.event);
-
-	trace_seq_printf(s, "%s: ", se->name);
-
-	for (i = 0, n_u64 = 0; i < se->n_fields; i++) {
-		if (trace_seq_has_overflowed(s))
-			goto end;
-
-		fmt = synth_field_fmt(se->fields[i]->type);
-
-		/* parameter types */
-		if (tr && tr->trace_flags & TRACE_ITER_VERBOSE)
-			trace_seq_printf(s, "%s ", fmt);
-
-		snprintf(print_fmt, sizeof(print_fmt), "%%s=%s%%s", fmt);
-
-		/* parameter values */
-		if (se->fields[i]->is_string) {
-			trace_seq_printf(s, print_fmt, se->fields[i]->name,
-					 (char *)&entry->fields[n_u64],
-					 i == se->n_fields - 1 ? "" : " ");
-			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
-		} else {
-			struct trace_print_flags __flags[] = {
-			    __def_gfpflag_names, {-1, NULL} };
-			char *space = (i == se->n_fields - 1 ? "" : " ");
-
-			print_synth_event_num_val(s, print_fmt,
-						  se->fields[i]->name,
-						  se->fields[i]->size,
-						  entry->fields[n_u64],
-						  space);
-
-			if (strcmp(se->fields[i]->type, "gfp_t") == 0) {
-				trace_seq_puts(s, " (");
-				trace_print_flags_seq(s, "|",
-						      entry->fields[n_u64],
-						      __flags);
-				trace_seq_putc(s, ')');
-			}
-			n_u64++;
-		}
-	}
-end:
-	trace_seq_putc(s, '\n');
-
-	return trace_handle_return(s);
-}
-
-static struct trace_event_functions synth_event_funcs = {
-	.trace		= print_synth_event
-};
-
-static notrace void trace_event_raw_event_synth(void *__data,
-						u64 *var_ref_vals,
-						unsigned int *var_ref_idx)
-{
-	struct trace_event_file *trace_file = __data;
-	struct synth_trace_event *entry;
-	struct trace_event_buffer fbuffer;
-	struct trace_buffer *buffer;
-	struct synth_event *event;
-	unsigned int i, n_u64, val_idx;
-	int fields_size = 0;
-
-	event = trace_file->event_call->data;
-
-	if (trace_trigger_soft_disabled(trace_file))
-		return;
-
-	fields_size = event->n_u64 * sizeof(u64);
-
-	/*
-	 * Avoid ring buffer recursion detection, as this event
-	 * is being performed within another event.
-	 */
-	buffer = trace_file->tr->array_buffer.buffer;
-	ring_buffer_nest_start(buffer);
-
-	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
-					   sizeof(*entry) + fields_size);
-	if (!entry)
-		goto out;
-
-	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
-		val_idx = var_ref_idx[i];
-		if (event->fields[i]->is_string) {
-			char *str_val = (char *)(long)var_ref_vals[val_idx];
-			char *str_field = (char *)&entry->fields[n_u64];
-
-			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
-			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
-		} else {
-			struct synth_field *field = event->fields[i];
-			u64 val = var_ref_vals[val_idx];
-
-			switch (field->size) {
-			case 1:
-				*(u8 *)&entry->fields[n_u64] = (u8)val;
-				break;
-
-			case 2:
-				*(u16 *)&entry->fields[n_u64] = (u16)val;
-				break;
-
-			case 4:
-				*(u32 *)&entry->fields[n_u64] = (u32)val;
-				break;
-
-			default:
-				entry->fields[n_u64] = val;
-				break;
-			}
-			n_u64++;
-		}
-	}
-
-	trace_event_buffer_commit(&fbuffer);
-out:
-	ring_buffer_nest_end(buffer);
-}
-
-static void free_synth_event_print_fmt(struct trace_event_call *call)
-{
-	if (call) {
-		kfree(call->print_fmt);
-		call->print_fmt = NULL;
-	}
-}
-
-static int __set_synth_event_print_fmt(struct synth_event *event,
-				       char *buf, int len)
-{
-	const char *fmt;
-	int pos = 0;
-	int i;
-
-	/* When len=0, we just calculate the needed length */
-#define LEN_OR_ZERO (len ? len - pos : 0)
-
-	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
-	for (i = 0; i < event->n_fields; i++) {
-		fmt = synth_field_fmt(event->fields[i]->type);
-		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s=%s%s",
-				event->fields[i]->name, fmt,
-				i == event->n_fields - 1 ? "" : ", ");
-	}
-	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
-
-	for (i = 0; i < event->n_fields; i++) {
-		pos += snprintf(buf + pos, LEN_OR_ZERO,
-				", REC->%s", event->fields[i]->name);
-	}
-
-#undef LEN_OR_ZERO
-
-	/* return the length of print_fmt */
-	return pos;
-}
-
-static int set_synth_event_print_fmt(struct trace_event_call *call)
-{
-	struct synth_event *event = call->data;
-	char *print_fmt;
-	int len;
-
-	/* First: called with 0 length to calculate the needed length */
-	len = __set_synth_event_print_fmt(event, NULL, 0);
-
-	print_fmt = kmalloc(len + 1, GFP_KERNEL);
-	if (!print_fmt)
-		return -ENOMEM;
-
-	/* Second: actually write the @print_fmt */
-	__set_synth_event_print_fmt(event, print_fmt, len + 1);
-	call->print_fmt = print_fmt;
-
-	return 0;
-}
-
-static void free_synth_field(struct synth_field *field)
-{
-	kfree(field->type);
-	kfree(field->name);
-	kfree(field);
-}
-
-static struct synth_field *parse_synth_field(int argc, const char **argv,
-					     int *consumed)
-{
-	struct synth_field *field;
-	const char *prefix = NULL, *field_type = argv[0], *field_name, *array;
-	int len, ret = 0;
-
-	if (field_type[0] == ';')
-		field_type++;
-
-	if (!strcmp(field_type, "unsigned")) {
-		if (argc < 3)
-			return ERR_PTR(-EINVAL);
-		prefix = "unsigned ";
-		field_type = argv[1];
-		field_name = argv[2];
-		*consumed = 3;
-	} else {
-		field_name = argv[1];
-		*consumed = 2;
-	}
-
-	field = kzalloc(sizeof(*field), GFP_KERNEL);
-	if (!field)
-		return ERR_PTR(-ENOMEM);
-
-	len = strlen(field_name);
-	array = strchr(field_name, '[');
-	if (array)
-		len -= strlen(array);
-	else if (field_name[len - 1] == ';')
-		len--;
-
-	field->name = kmemdup_nul(field_name, len, GFP_KERNEL);
-	if (!field->name) {
-		ret = -ENOMEM;
-		goto free;
-	}
-
-	if (field_type[0] == ';')
-		field_type++;
-	len = strlen(field_type) + 1;
-	if (array)
-		len += strlen(array);
-	if (prefix)
-		len += strlen(prefix);
-
-	field->type = kzalloc(len, GFP_KERNEL);
-	if (!field->type) {
-		ret = -ENOMEM;
-		goto free;
-	}
-	if (prefix)
-		strcat(field->type, prefix);
-	strcat(field->type, field_type);
-	if (array) {
-		strcat(field->type, array);
-		if (field->type[len - 1] == ';')
-			field->type[len - 1] = '\0';
-	}
-
-	field->size = synth_field_size(field->type);
-	if (!field->size) {
-		ret = -EINVAL;
-		goto free;
-	}
-
-	if (synth_field_is_string(field->type))
-		field->is_string = true;
-
-	field->is_signed = synth_field_signed(field->type);
-
- out:
-	return field;
- free:
-	free_synth_field(field);
-	field = ERR_PTR(ret);
-	goto out;
-}
-
-static void free_synth_tracepoint(struct tracepoint *tp)
-{
-	if (!tp)
-		return;
-
-	kfree(tp->name);
-	kfree(tp);
-}
-
-static struct tracepoint *alloc_synth_tracepoint(char *name)
-{
-	struct tracepoint *tp;
-
-	tp = kzalloc(sizeof(*tp), GFP_KERNEL);
-	if (!tp)
-		return ERR_PTR(-ENOMEM);
-
-	tp->name = kstrdup(name, GFP_KERNEL);
-	if (!tp->name) {
-		kfree(tp);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	return tp;
-}
-
 typedef void (*synth_probe_func_t) (void *__data, u64 *var_ref_vals,
 				    unsigned int *var_ref_idx);
 
@@ -1177,145 +604,6 @@ static inline void trace_synth(struct synth_event *event, u64 *var_ref_vals,
 	}
 }
 
-static struct synth_event *find_synth_event(const char *name)
-{
-	struct dyn_event *pos;
-	struct synth_event *event;
-
-	for_each_dyn_event(pos) {
-		if (!is_synth_event(pos))
-			continue;
-		event = to_synth_event(pos);
-		if (strcmp(event->name, name) == 0)
-			return event;
-	}
-
-	return NULL;
-}
-
-static struct trace_event_fields synth_event_fields_array[] = {
-	{ .type = TRACE_FUNCTION_TYPE,
-	  .define_fields = synth_event_define_fields },
-	{}
-};
-
-static int register_synth_event(struct synth_event *event)
-{
-	struct trace_event_call *call = &event->call;
-	int ret = 0;
-
-	event->call.class = &event->class;
-	event->class.system = kstrdup(SYNTH_SYSTEM, GFP_KERNEL);
-	if (!event->class.system) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	event->tp = alloc_synth_tracepoint(event->name);
-	if (IS_ERR(event->tp)) {
-		ret = PTR_ERR(event->tp);
-		event->tp = NULL;
-		goto out;
-	}
-
-	INIT_LIST_HEAD(&call->class->fields);
-	call->event.funcs = &synth_event_funcs;
-	call->class->fields_array = synth_event_fields_array;
-
-	ret = register_trace_event(&call->event);
-	if (!ret) {
-		ret = -ENODEV;
-		goto out;
-	}
-	call->flags = TRACE_EVENT_FL_TRACEPOINT;
-	call->class->reg = trace_event_reg;
-	call->class->probe = trace_event_raw_event_synth;
-	call->data = event;
-	call->tp = event->tp;
-
-	ret = trace_add_event_call(call);
-	if (ret) {
-		pr_warn("Failed to register synthetic event: %s\n",
-			trace_event_name(call));
-		goto err;
-	}
-
-	ret = set_synth_event_print_fmt(call);
-	if (ret < 0) {
-		trace_remove_event_call(call);
-		goto err;
-	}
- out:
-	return ret;
- err:
-	unregister_trace_event(&call->event);
-	goto out;
-}
-
-static int unregister_synth_event(struct synth_event *event)
-{
-	struct trace_event_call *call = &event->call;
-	int ret;
-
-	ret = trace_remove_event_call(call);
-
-	return ret;
-}
-
-static void free_synth_event(struct synth_event *event)
-{
-	unsigned int i;
-
-	if (!event)
-		return;
-
-	for (i = 0; i < event->n_fields; i++)
-		free_synth_field(event->fields[i]);
-
-	kfree(event->fields);
-	kfree(event->name);
-	kfree(event->class.system);
-	free_synth_tracepoint(event->tp);
-	free_synth_event_print_fmt(&event->call);
-	kfree(event);
-}
-
-static struct synth_event *alloc_synth_event(const char *name, int n_fields,
-					     struct synth_field **fields)
-{
-	struct synth_event *event;
-	unsigned int i;
-
-	event = kzalloc(sizeof(*event), GFP_KERNEL);
-	if (!event) {
-		event = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	event->name = kstrdup(name, GFP_KERNEL);
-	if (!event->name) {
-		kfree(event);
-		event = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	event->fields = kcalloc(n_fields, sizeof(*event->fields), GFP_KERNEL);
-	if (!event->fields) {
-		free_synth_event(event);
-		event = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	dyn_event_init(&event->devent, &synth_event_ops);
-
-	for (i = 0; i < n_fields; i++)
-		event->fields[i] = fields[i];
-
-	event->n_fields = n_fields;
- out:
-	return event;
-}
-
 static void action_trace(struct hist_trigger_data *hist_data,
 			 struct tracing_map_elt *elt, void *rec,
 			 struct ring_buffer_event *rbe, void *key,
@@ -1331,1056 +619,6 @@ struct hist_var_data {
 	struct hist_trigger_data *hist_data;
 };
 
-static int synth_event_check_arg_fn(void *data)
-{
-	struct dynevent_arg_pair *arg_pair = data;
-	int size;
-
-	size = synth_field_size((char *)arg_pair->lhs);
-
-	return size ? 0 : -EINVAL;
-}
-
-/**
- * synth_event_add_field - Add a new field to a synthetic event cmd
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @type: The type of the new field to add
- * @name: The name of the new field to add
- *
- * Add a new field to a synthetic event cmd object.  Field ordering is in
- * the same order the fields are added.
- *
- * See synth_field_size() for available types. If field_name contains
- * [n] the field is considered to be an array.
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_add_field(struct dynevent_cmd *cmd, const char *type,
-			  const char *name)
-{
-	struct dynevent_arg_pair arg_pair;
-	int ret;
-
-	if (cmd->type != DYNEVENT_TYPE_SYNTH)
-		return -EINVAL;
-
-	if (!type || !name)
-		return -EINVAL;
-
-	dynevent_arg_pair_init(&arg_pair, 0, ';');
-
-	arg_pair.lhs = type;
-	arg_pair.rhs = name;
-
-	ret = dynevent_arg_pair_add(cmd, &arg_pair, synth_event_check_arg_fn);
-	if (ret)
-		return ret;
-
-	if (++cmd->n_fields > SYNTH_FIELDS_MAX)
-		ret = -EINVAL;
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_add_field);
-
-/**
- * synth_event_add_field_str - Add a new field to a synthetic event cmd
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @type_name: The type and name of the new field to add, as a single string
- *
- * Add a new field to a synthetic event cmd object, as a single
- * string.  The @type_name string is expected to be of the form 'type
- * name', which will be appended by ';'.  No sanity checking is done -
- * what's passed in is assumed to already be well-formed.  Field
- * ordering is in the same order the fields are added.
- *
- * See synth_field_size() for available types. If field_name contains
- * [n] the field is considered to be an array.
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_add_field_str(struct dynevent_cmd *cmd, const char *type_name)
-{
-	struct dynevent_arg arg;
-	int ret;
-
-	if (cmd->type != DYNEVENT_TYPE_SYNTH)
-		return -EINVAL;
-
-	if (!type_name)
-		return -EINVAL;
-
-	dynevent_arg_init(&arg, ';');
-
-	arg.str = type_name;
-
-	ret = dynevent_arg_add(cmd, &arg, NULL);
-	if (ret)
-		return ret;
-
-	if (++cmd->n_fields > SYNTH_FIELDS_MAX)
-		ret = -EINVAL;
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_add_field_str);
-
-/**
- * synth_event_add_fields - Add multiple fields to a synthetic event cmd
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @fields: An array of type/name field descriptions
- * @n_fields: The number of field descriptions contained in the fields array
- *
- * Add a new set of fields to a synthetic event cmd object.  The event
- * fields that will be defined for the event should be passed in as an
- * array of struct synth_field_desc, and the number of elements in the
- * array passed in as n_fields.  Field ordering will retain the
- * ordering given in the fields array.
- *
- * See synth_field_size() for available types. If field_name contains
- * [n] the field is considered to be an array.
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_add_fields(struct dynevent_cmd *cmd,
-			   struct synth_field_desc *fields,
-			   unsigned int n_fields)
-{
-	unsigned int i;
-	int ret = 0;
-
-	for (i = 0; i < n_fields; i++) {
-		if (fields[i].type == NULL || fields[i].name == NULL) {
-			ret = -EINVAL;
-			break;
-		}
-
-		ret = synth_event_add_field(cmd, fields[i].type, fields[i].name);
-		if (ret)
-			break;
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_add_fields);
-
-/**
- * __synth_event_gen_cmd_start - Start a synthetic event command from arg list
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @name: The name of the synthetic event
- * @mod: The module creating the event, NULL if not created from a module
- * @args: Variable number of arg (pairs), one pair for each field
- *
- * NOTE: Users normally won't want to call this function directly, but
- * rather use the synth_event_gen_cmd_start() wrapper, which
- * automatically adds a NULL to the end of the arg list.  If this
- * function is used directly, make sure the last arg in the variable
- * arg list is NULL.
- *
- * Generate a synthetic event command to be executed by
- * synth_event_gen_cmd_end().  This function can be used to generate
- * the complete command or only the first part of it; in the latter
- * case, synth_event_add_field(), synth_event_add_field_str(), or
- * synth_event_add_fields() can be used to add more fields following
- * this.
- *
- * There should be an even number variable args, each pair consisting
- * of a type followed by a field name.
- *
- * See synth_field_size() for available types. If field_name contains
- * [n] the field is considered to be an array.
- *
- * Return: 0 if successful, error otherwise.
- */
-int __synth_event_gen_cmd_start(struct dynevent_cmd *cmd, const char *name,
-				struct module *mod, ...)
-{
-	struct dynevent_arg arg;
-	va_list args;
-	int ret;
-
-	cmd->event_name = name;
-	cmd->private_data = mod;
-
-	if (cmd->type != DYNEVENT_TYPE_SYNTH)
-		return -EINVAL;
-
-	dynevent_arg_init(&arg, 0);
-	arg.str = name;
-	ret = dynevent_arg_add(cmd, &arg, NULL);
-	if (ret)
-		return ret;
-
-	va_start(args, mod);
-	for (;;) {
-		const char *type, *name;
-
-		type = va_arg(args, const char *);
-		if (!type)
-			break;
-		name = va_arg(args, const char *);
-		if (!name)
-			break;
-
-		if (++cmd->n_fields > SYNTH_FIELDS_MAX) {
-			ret = -EINVAL;
-			break;
-		}
-
-		ret = synth_event_add_field(cmd, type, name);
-		if (ret)
-			break;
-	}
-	va_end(args);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(__synth_event_gen_cmd_start);
-
-/**
- * synth_event_gen_cmd_array_start - Start synthetic event command from an array
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @name: The name of the synthetic event
- * @fields: An array of type/name field descriptions
- * @n_fields: The number of field descriptions contained in the fields array
- *
- * Generate a synthetic event command to be executed by
- * synth_event_gen_cmd_end().  This function can be used to generate
- * the complete command or only the first part of it; in the latter
- * case, synth_event_add_field(), synth_event_add_field_str(), or
- * synth_event_add_fields() can be used to add more fields following
- * this.
- *
- * The event fields that will be defined for the event should be
- * passed in as an array of struct synth_field_desc, and the number of
- * elements in the array passed in as n_fields.  Field ordering will
- * retain the ordering given in the fields array.
- *
- * See synth_field_size() for available types. If field_name contains
- * [n] the field is considered to be an array.
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_gen_cmd_array_start(struct dynevent_cmd *cmd, const char *name,
-				    struct module *mod,
-				    struct synth_field_desc *fields,
-				    unsigned int n_fields)
-{
-	struct dynevent_arg arg;
-	unsigned int i;
-	int ret = 0;
-
-	cmd->event_name = name;
-	cmd->private_data = mod;
-
-	if (cmd->type != DYNEVENT_TYPE_SYNTH)
-		return -EINVAL;
-
-	if (n_fields > SYNTH_FIELDS_MAX)
-		return -EINVAL;
-
-	dynevent_arg_init(&arg, 0);
-	arg.str = name;
-	ret = dynevent_arg_add(cmd, &arg, NULL);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < n_fields; i++) {
-		if (fields[i].type == NULL || fields[i].name == NULL)
-			return -EINVAL;
-
-		ret = synth_event_add_field(cmd, fields[i].type, fields[i].name);
-		if (ret)
-			break;
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_gen_cmd_array_start);
-
-static int __create_synth_event(int argc, const char *name, const char **argv)
-{
-	struct synth_field *field, *fields[SYNTH_FIELDS_MAX];
-	struct synth_event *event = NULL;
-	int i, consumed = 0, n_fields = 0, ret = 0;
-
-	/*
-	 * Argument syntax:
-	 *  - Add synthetic event: <event_name> field[;field] ...
-	 *  - Remove synthetic event: !<event_name> field[;field] ...
-	 *      where 'field' = type field_name
-	 */
-
-	if (name[0] == '\0' || argc < 1)
-		return -EINVAL;
-
-	mutex_lock(&event_mutex);
-
-	event = find_synth_event(name);
-	if (event) {
-		ret = -EEXIST;
-		goto out;
-	}
-
-	for (i = 0; i < argc - 1; i++) {
-		if (strcmp(argv[i], ";") == 0)
-			continue;
-		if (n_fields == SYNTH_FIELDS_MAX) {
-			ret = -EINVAL;
-			goto err;
-		}
-
-		field = parse_synth_field(argc - i, &argv[i], &consumed);
-		if (IS_ERR(field)) {
-			ret = PTR_ERR(field);
-			goto err;
-		}
-		fields[n_fields++] = field;
-		i += consumed - 1;
-	}
-
-	if (i < argc && strcmp(argv[i], ";") != 0) {
-		ret = -EINVAL;
-		goto err;
-	}
-
-	event = alloc_synth_event(name, n_fields, fields);
-	if (IS_ERR(event)) {
-		ret = PTR_ERR(event);
-		event = NULL;
-		goto err;
-	}
-	ret = register_synth_event(event);
-	if (!ret)
-		dyn_event_add(&event->devent);
-	else
-		free_synth_event(event);
- out:
-	mutex_unlock(&event_mutex);
-
-	return ret;
- err:
-	for (i = 0; i < n_fields; i++)
-		free_synth_field(fields[i]);
-
-	goto out;
-}
-
-/**
- * synth_event_create - Create a new synthetic event
- * @name: The name of the new sythetic event
- * @fields: An array of type/name field descriptions
- * @n_fields: The number of field descriptions contained in the fields array
- * @mod: The module creating the event, NULL if not created from a module
- *
- * Create a new synthetic event with the given name under the
- * trace/events/synthetic/ directory.  The event fields that will be
- * defined for the event should be passed in as an array of struct
- * synth_field_desc, and the number elements in the array passed in as
- * n_fields. Field ordering will retain the ordering given in the
- * fields array.
- *
- * If the new synthetic event is being created from a module, the mod
- * param must be non-NULL.  This will ensure that the trace buffer
- * won't contain unreadable events.
- *
- * The new synth event should be deleted using synth_event_delete()
- * function.  The new synthetic event can be generated from modules or
- * other kernel code using trace_synth_event() and related functions.
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_create(const char *name, struct synth_field_desc *fields,
-		       unsigned int n_fields, struct module *mod)
-{
-	struct dynevent_cmd cmd;
-	char *buf;
-	int ret;
-
-	buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	synth_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN);
-
-	ret = synth_event_gen_cmd_array_start(&cmd, name, mod,
-					      fields, n_fields);
-	if (ret)
-		goto out;
-
-	ret = synth_event_gen_cmd_end(&cmd);
- out:
-	kfree(buf);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_create);
-
-static int destroy_synth_event(struct synth_event *se)
-{
-	int ret;
-
-	if (se->ref)
-		ret = -EBUSY;
-	else {
-		ret = unregister_synth_event(se);
-		if (!ret) {
-			dyn_event_remove(&se->devent);
-			free_synth_event(se);
-		}
-	}
-
-	return ret;
-}
-
-/**
- * synth_event_delete - Delete a synthetic event
- * @event_name: The name of the new sythetic event
- *
- * Delete a synthetic event that was created with synth_event_create().
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_delete(const char *event_name)
-{
-	struct synth_event *se = NULL;
-	struct module *mod = NULL;
-	int ret = -ENOENT;
-
-	mutex_lock(&event_mutex);
-	se = find_synth_event(event_name);
-	if (se) {
-		mod = se->mod;
-		ret = destroy_synth_event(se);
-	}
-	mutex_unlock(&event_mutex);
-
-	if (mod) {
-		mutex_lock(&trace_types_lock);
-		/*
-		 * It is safest to reset the ring buffer if the module
-		 * being unloaded registered any events that were
-		 * used. The only worry is if a new module gets
-		 * loaded, and takes on the same id as the events of
-		 * this module. When printing out the buffer, traced
-		 * events left over from this module may be passed to
-		 * the new module events and unexpected results may
-		 * occur.
-		 */
-		tracing_reset_all_online_cpus();
-		mutex_unlock(&trace_types_lock);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_delete);
-
-static int create_or_delete_synth_event(int argc, char **argv)
-{
-	const char *name = argv[0];
-	int ret;
-
-	/* trace_run_command() ensures argc != 0 */
-	if (name[0] == '!') {
-		ret = synth_event_delete(name + 1);
-		return ret;
-	}
-
-	ret = __create_synth_event(argc - 1, name, (const char **)argv + 1);
-	return ret == -ECANCELED ? -EINVAL : ret;
-}
-
-static int synth_event_run_command(struct dynevent_cmd *cmd)
-{
-	struct synth_event *se;
-	int ret;
-
-	ret = trace_run_command(cmd->seq.buffer, create_or_delete_synth_event);
-	if (ret)
-		return ret;
-
-	se = find_synth_event(cmd->event_name);
-	if (WARN_ON(!se))
-		return -ENOENT;
-
-	se->mod = cmd->private_data;
-
-	return ret;
-}
-
-/**
- * synth_event_cmd_init - Initialize a synthetic event command object
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @buf: A pointer to the buffer used to build the command
- * @maxlen: The length of the buffer passed in @buf
- *
- * Initialize a synthetic event command object.  Use this before
- * calling any of the other dyenvent_cmd functions.
- */
-void synth_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen)
-{
-	dynevent_cmd_init(cmd, buf, maxlen, DYNEVENT_TYPE_SYNTH,
-			  synth_event_run_command);
-}
-EXPORT_SYMBOL_GPL(synth_event_cmd_init);
-
-static inline int
-__synth_event_trace_start(struct trace_event_file *file,
-			  struct synth_event_trace_state *trace_state)
-{
-	int entry_size, fields_size = 0;
-	int ret = 0;
-
-	memset(trace_state, '\0', sizeof(*trace_state));
-
-	/*
-	 * Normal event tracing doesn't get called at all unless the
-	 * ENABLED bit is set (which attaches the probe thus allowing
-	 * this code to be called, etc).  Because this is called
-	 * directly by the user, we don't have that but we still need
-	 * to honor not logging when disabled.  For the the iterated
-	 * trace case, we save the enabed state upon start and just
-	 * ignore the following data calls.
-	 */
-	if (!(file->flags & EVENT_FILE_FL_ENABLED) ||
-	    trace_trigger_soft_disabled(file)) {
-		trace_state->disabled = true;
-		ret = -ENOENT;
-		goto out;
-	}
-
-	trace_state->event = file->event_call->data;
-
-	fields_size = trace_state->event->n_u64 * sizeof(u64);
-
-	/*
-	 * Avoid ring buffer recursion detection, as this event
-	 * is being performed within another event.
-	 */
-	trace_state->buffer = file->tr->array_buffer.buffer;
-	ring_buffer_nest_start(trace_state->buffer);
-
-	entry_size = sizeof(*trace_state->entry) + fields_size;
-	trace_state->entry = trace_event_buffer_reserve(&trace_state->fbuffer,
-							file,
-							entry_size);
-	if (!trace_state->entry) {
-		ring_buffer_nest_end(trace_state->buffer);
-		ret = -EINVAL;
-	}
-out:
-	return ret;
-}
-
-static inline void
-__synth_event_trace_end(struct synth_event_trace_state *trace_state)
-{
-	trace_event_buffer_commit(&trace_state->fbuffer);
-
-	ring_buffer_nest_end(trace_state->buffer);
-}
-
-/**
- * synth_event_trace - Trace a synthetic event
- * @file: The trace_event_file representing the synthetic event
- * @n_vals: The number of values in vals
- * @args: Variable number of args containing the event values
- *
- * Trace a synthetic event using the values passed in the variable
- * argument list.
- *
- * The argument list should be a list 'n_vals' u64 values.  The number
- * of vals must match the number of field in the synthetic event, and
- * must be in the same order as the synthetic event fields.
- *
- * All vals should be cast to u64, and string vals are just pointers
- * to strings, cast to u64.  Strings will be copied into space
- * reserved in the event for the string, using these pointers.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...)
-{
-	struct synth_event_trace_state state;
-	unsigned int i, n_u64;
-	va_list args;
-	int ret;
-
-	ret = __synth_event_trace_start(file, &state);
-	if (ret) {
-		if (ret == -ENOENT)
-			ret = 0; /* just disabled, not really an error */
-		return ret;
-	}
-
-	if (n_vals != state.event->n_fields) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	va_start(args, n_vals);
-	for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
-		u64 val;
-
-		val = va_arg(args, u64);
-
-		if (state.event->fields[i]->is_string) {
-			char *str_val = (char *)(long)val;
-			char *str_field = (char *)&state.entry->fields[n_u64];
-
-			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
-			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
-		} else {
-			struct synth_field *field = state.event->fields[i];
-
-			switch (field->size) {
-			case 1:
-				*(u8 *)&state.entry->fields[n_u64] = (u8)val;
-				break;
-
-			case 2:
-				*(u16 *)&state.entry->fields[n_u64] = (u16)val;
-				break;
-
-			case 4:
-				*(u32 *)&state.entry->fields[n_u64] = (u32)val;
-				break;
-
-			default:
-				state.entry->fields[n_u64] = val;
-				break;
-			}
-			n_u64++;
-		}
-	}
-	va_end(args);
-out:
-	__synth_event_trace_end(&state);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_trace);
-
-/**
- * synth_event_trace_array - Trace a synthetic event from an array
- * @file: The trace_event_file representing the synthetic event
- * @vals: Array of values
- * @n_vals: The number of values in vals
- *
- * Trace a synthetic event using the values passed in as 'vals'.
- *
- * The 'vals' array is just an array of 'n_vals' u64.  The number of
- * vals must match the number of field in the synthetic event, and
- * must be in the same order as the synthetic event fields.
- *
- * All vals should be cast to u64, and string vals are just pointers
- * to strings, cast to u64.  Strings will be copied into space
- * reserved in the event for the string, using these pointers.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_trace_array(struct trace_event_file *file, u64 *vals,
-			    unsigned int n_vals)
-{
-	struct synth_event_trace_state state;
-	unsigned int i, n_u64;
-	int ret;
-
-	ret = __synth_event_trace_start(file, &state);
-	if (ret) {
-		if (ret == -ENOENT)
-			ret = 0; /* just disabled, not really an error */
-		return ret;
-	}
-
-	if (n_vals != state.event->n_fields) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
-		if (state.event->fields[i]->is_string) {
-			char *str_val = (char *)(long)vals[i];
-			char *str_field = (char *)&state.entry->fields[n_u64];
-
-			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
-			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
-		} else {
-			struct synth_field *field = state.event->fields[i];
-			u64 val = vals[i];
-
-			switch (field->size) {
-			case 1:
-				*(u8 *)&state.entry->fields[n_u64] = (u8)val;
-				break;
-
-			case 2:
-				*(u16 *)&state.entry->fields[n_u64] = (u16)val;
-				break;
-
-			case 4:
-				*(u32 *)&state.entry->fields[n_u64] = (u32)val;
-				break;
-
-			default:
-				state.entry->fields[n_u64] = val;
-				break;
-			}
-			n_u64++;
-		}
-	}
-out:
-	__synth_event_trace_end(&state);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_trace_array);
-
-/**
- * synth_event_trace_start - Start piecewise synthetic event trace
- * @file: The trace_event_file representing the synthetic event
- * @trace_state: A pointer to object tracking the piecewise trace state
- *
- * Start the trace of a synthetic event field-by-field rather than all
- * at once.
- *
- * This function 'opens' an event trace, which means space is reserved
- * for the event in the trace buffer, after which the event's
- * individual field values can be set through either
- * synth_event_add_next_val() or synth_event_add_val().
- *
- * A pointer to a trace_state object is passed in, which will keep
- * track of the current event trace state until the event trace is
- * closed (and the event finally traced) using
- * synth_event_trace_end().
- *
- * Note that synth_event_trace_end() must be called after all values
- * have been added for each event trace, regardless of whether adding
- * all field values succeeded or not.
- *
- * Note also that for a given event trace, all fields must be added
- * using either synth_event_add_next_val() or synth_event_add_val()
- * but not both together or interleaved.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_trace_start(struct trace_event_file *file,
-			    struct synth_event_trace_state *trace_state)
-{
-	int ret;
-
-	if (!trace_state)
-		return -EINVAL;
-
-	ret = __synth_event_trace_start(file, trace_state);
-	if (ret == -ENOENT)
-		ret = 0; /* just disabled, not really an error */
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_trace_start);
-
-static int __synth_event_add_val(const char *field_name, u64 val,
-				 struct synth_event_trace_state *trace_state)
-{
-	struct synth_field *field = NULL;
-	struct synth_trace_event *entry;
-	struct synth_event *event;
-	int i, ret = 0;
-
-	if (!trace_state) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* can't mix add_next_synth_val() with add_synth_val() */
-	if (field_name) {
-		if (trace_state->add_next) {
-			ret = -EINVAL;
-			goto out;
-		}
-		trace_state->add_name = true;
-	} else {
-		if (trace_state->add_name) {
-			ret = -EINVAL;
-			goto out;
-		}
-		trace_state->add_next = true;
-	}
-
-	if (trace_state->disabled)
-		goto out;
-
-	event = trace_state->event;
-	if (trace_state->add_name) {
-		for (i = 0; i < event->n_fields; i++) {
-			field = event->fields[i];
-			if (strcmp(field->name, field_name) == 0)
-				break;
-		}
-		if (!field) {
-			ret = -EINVAL;
-			goto out;
-		}
-	} else {
-		if (trace_state->cur_field >= event->n_fields) {
-			ret = -EINVAL;
-			goto out;
-		}
-		field = event->fields[trace_state->cur_field++];
-	}
-
-	entry = trace_state->entry;
-	if (field->is_string) {
-		char *str_val = (char *)(long)val;
-		char *str_field;
-
-		if (!str_val) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		str_field = (char *)&entry->fields[field->offset];
-		strscpy(str_field, str_val, STR_VAR_LEN_MAX);
-	} else {
-		switch (field->size) {
-		case 1:
-			*(u8 *)&trace_state->entry->fields[field->offset] = (u8)val;
-			break;
-
-		case 2:
-			*(u16 *)&trace_state->entry->fields[field->offset] = (u16)val;
-			break;
-
-		case 4:
-			*(u32 *)&trace_state->entry->fields[field->offset] = (u32)val;
-			break;
-
-		default:
-			trace_state->entry->fields[field->offset] = val;
-			break;
-		}
-	}
- out:
-	return ret;
-}
-
-/**
- * synth_event_add_next_val - Add the next field's value to an open synth trace
- * @val: The value to set the next field to
- * @trace_state: A pointer to object tracking the piecewise trace state
- *
- * Set the value of the next field in an event that's been opened by
- * synth_event_trace_start().
- *
- * The val param should be the value cast to u64.  If the value points
- * to a string, the val param should be a char * cast to u64.
- *
- * This function assumes all the fields in an event are to be set one
- * after another - successive calls to this function are made, one for
- * each field, in the order of the fields in the event, until all
- * fields have been set.  If you'd rather set each field individually
- * without regard to ordering, synth_event_add_val() can be used
- * instead.
- *
- * Note however that synth_event_add_next_val() and
- * synth_event_add_val() can't be intermixed for a given event trace -
- * one or the other but not both can be used at the same time.
- *
- * Note also that synth_event_trace_end() must be called after all
- * values have been added for each event trace, regardless of whether
- * adding all field values succeeded or not.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_add_next_val(u64 val,
-			     struct synth_event_trace_state *trace_state)
-{
-	return __synth_event_add_val(NULL, val, trace_state);
-}
-EXPORT_SYMBOL_GPL(synth_event_add_next_val);
-
-/**
- * synth_event_add_val - Add a named field's value to an open synth trace
- * @field_name: The name of the synthetic event field value to set
- * @val: The value to set the next field to
- * @trace_state: A pointer to object tracking the piecewise trace state
- *
- * Set the value of the named field in an event that's been opened by
- * synth_event_trace_start().
- *
- * The val param should be the value cast to u64.  If the value points
- * to a string, the val param should be a char * cast to u64.
- *
- * This function looks up the field name, and if found, sets the field
- * to the specified value.  This lookup makes this function more
- * expensive than synth_event_add_next_val(), so use that or the
- * none-piecewise synth_event_trace() instead if efficiency is more
- * important.
- *
- * Note however that synth_event_add_next_val() and
- * synth_event_add_val() can't be intermixed for a given event trace -
- * one or the other but not both can be used at the same time.
- *
- * Note also that synth_event_trace_end() must be called after all
- * values have been added for each event trace, regardless of whether
- * adding all field values succeeded or not.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_add_val(const char *field_name, u64 val,
-			struct synth_event_trace_state *trace_state)
-{
-	return __synth_event_add_val(field_name, val, trace_state);
-}
-EXPORT_SYMBOL_GPL(synth_event_add_val);
-
-/**
- * synth_event_trace_end - End piecewise synthetic event trace
- * @trace_state: A pointer to object tracking the piecewise trace state
- *
- * End the trace of a synthetic event opened by
- * synth_event_trace__start().
- *
- * This function 'closes' an event trace, which basically means that
- * it commits the reserved event and cleans up other loose ends.
- *
- * A pointer to a trace_state object is passed in, which will keep
- * track of the current event trace state opened with
- * synth_event_trace_start().
- *
- * Note that this function must be called after all values have been
- * added for each event trace, regardless of whether adding all field
- * values succeeded or not.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_trace_end(struct synth_event_trace_state *trace_state)
-{
-	if (!trace_state)
-		return -EINVAL;
-
-	__synth_event_trace_end(trace_state);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(synth_event_trace_end);
-
-static int create_synth_event(int argc, const char **argv)
-{
-	const char *name = argv[0];
-	int len;
-
-	if (name[0] != 's' || name[1] != ':')
-		return -ECANCELED;
-	name += 2;
-
-	/* This interface accepts group name prefix */
-	if (strchr(name, '/')) {
-		len = str_has_prefix(name, SYNTH_SYSTEM "/");
-		if (len == 0)
-			return -EINVAL;
-		name += len;
-	}
-	return __create_synth_event(argc - 1, name, argv + 1);
-}
-
-static int synth_event_release(struct dyn_event *ev)
-{
-	struct synth_event *event = to_synth_event(ev);
-	int ret;
-
-	if (event->ref)
-		return -EBUSY;
-
-	ret = unregister_synth_event(event);
-	if (ret)
-		return ret;
-
-	dyn_event_remove(ev);
-	free_synth_event(event);
-	return 0;
-}
-
-static int __synth_event_show(struct seq_file *m, struct synth_event *event)
-{
-	struct synth_field *field;
-	unsigned int i;
-
-	seq_printf(m, "%s\t", event->name);
-
-	for (i = 0; i < event->n_fields; i++) {
-		field = event->fields[i];
-
-		/* parameter values */
-		seq_printf(m, "%s %s%s", field->type, field->name,
-			   i == event->n_fields - 1 ? "" : "; ");
-	}
-
-	seq_putc(m, '\n');
-
-	return 0;
-}
-
-static int synth_event_show(struct seq_file *m, struct dyn_event *ev)
-{
-	struct synth_event *event = to_synth_event(ev);
-
-	seq_printf(m, "s:%s/", event->class.system);
-
-	return __synth_event_show(m, event);
-}
-
-static int synth_events_seq_show(struct seq_file *m, void *v)
-{
-	struct dyn_event *ev = v;
-
-	if (!is_synth_event(ev))
-		return 0;
-
-	return __synth_event_show(m, to_synth_event(ev));
-}
-
-static const struct seq_operations synth_events_seq_op = {
-	.start	= dyn_event_seq_start,
-	.next	= dyn_event_seq_next,
-	.stop	= dyn_event_seq_stop,
-	.show	= synth_events_seq_show,
-};
-
-static int synth_events_open(struct inode *inode, struct file *file)
-{
-	int ret;
-
-	ret = security_locked_down(LOCKDOWN_TRACEFS);
-	if (ret)
-		return ret;
-
-	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
-		ret = dyn_events_release_all(&synth_event_ops);
-		if (ret < 0)
-			return ret;
-	}
-
-	return seq_open(file, &synth_events_seq_op);
-}
-
-static ssize_t synth_events_write(struct file *file,
-				  const char __user *buffer,
-				  size_t count, loff_t *ppos)
-{
-	return trace_parse_run_command(file, buffer, count, ppos,
-				       create_or_delete_synth_event);
-}
-
-static const struct file_operations synth_events_fops = {
-	.open           = synth_events_open,
-	.write		= synth_events_write,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = seq_release,
-};
-
 static u64 hist_field_timestamp(struct hist_field *hist_field,
 				struct tracing_map_elt *elt,
 				struct ring_buffer_event *rbe,
@@ -5627,7 +3865,6 @@ static int parse_var_defs(struct hist_trigger_data *hist_data)
 
 			s = kstrdup(field_str, GFP_KERNEL);
 			if (!s) {
-				kfree(hist_data->attrs->var_defs.name[n_vars]);
 				ret = -ENOMEM;
 				goto free;
 			}
@@ -6491,6 +4728,279 @@ const struct file_operations event_hist_fops = {
 	.release = single_release,
 };
 
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+static void hist_field_debug_show_flags(struct seq_file *m,
+					unsigned long flags)
+{
+	seq_puts(m, "      flags:\n");
+
+	if (flags & HIST_FIELD_FL_KEY)
+		seq_puts(m, "        HIST_FIELD_FL_KEY\n");
+	else if (flags & HIST_FIELD_FL_HITCOUNT)
+		seq_puts(m, "        VAL: HIST_FIELD_FL_HITCOUNT\n");
+	else if (flags & HIST_FIELD_FL_VAR)
+		seq_puts(m, "        HIST_FIELD_FL_VAR\n");
+	else if (flags & HIST_FIELD_FL_VAR_REF)
+		seq_puts(m, "        HIST_FIELD_FL_VAR_REF\n");
+	else
+		seq_puts(m, "        VAL: normal u64 value\n");
+
+	if (flags & HIST_FIELD_FL_ALIAS)
+		seq_puts(m, "        HIST_FIELD_FL_ALIAS\n");
+}
+
+static int hist_field_debug_show(struct seq_file *m,
+				 struct hist_field *field, unsigned long flags)
+{
+	if ((field->flags & flags) != flags) {
+		seq_printf(m, "ERROR: bad flags - %lx\n", flags);
+		return -EINVAL;
+	}
+
+	hist_field_debug_show_flags(m, field->flags);
+	if (field->field)
+		seq_printf(m, "      ftrace_event_field name: %s\n",
+			   field->field->name);
+
+	if (field->flags & HIST_FIELD_FL_VAR) {
+		seq_printf(m, "      var.name: %s\n", field->var.name);
+		seq_printf(m, "      var.idx (into tracing_map_elt.vars[]): %u\n",
+			   field->var.idx);
+	}
+
+	if (field->flags & HIST_FIELD_FL_ALIAS)
+		seq_printf(m, "      var_ref_idx (into hist_data->var_refs[]): %u\n",
+			   field->var_ref_idx);
+
+	if (field->flags & HIST_FIELD_FL_VAR_REF) {
+		seq_printf(m, "      name: %s\n", field->name);
+		seq_printf(m, "      var.idx (into tracing_map_elt.vars[]): %u\n",
+			   field->var.idx);
+		seq_printf(m, "      var.hist_data: %p\n", field->var.hist_data);
+		seq_printf(m, "      var_ref_idx (into hist_data->var_refs[]): %u\n",
+			   field->var_ref_idx);
+		if (field->system)
+			seq_printf(m, "      system: %s\n", field->system);
+		if (field->event_name)
+			seq_printf(m, "      event_name: %s\n", field->event_name);
+	}
+
+	seq_printf(m, "      type: %s\n", field->type);
+	seq_printf(m, "      size: %u\n", field->size);
+	seq_printf(m, "      is_signed: %u\n", field->is_signed);
+
+	return 0;
+}
+
+static int field_var_debug_show(struct seq_file *m,
+				struct field_var *field_var, unsigned int i,
+				bool save_vars)
+{
+	const char *vars_name = save_vars ? "save_vars" : "field_vars";
+	struct hist_field *field;
+	int ret = 0;
+
+	seq_printf(m, "\n    hist_data->%s[%d]:\n", vars_name, i);
+
+	field = field_var->var;
+
+	seq_printf(m, "\n      %s[%d].var:\n", vars_name, i);
+
+	hist_field_debug_show_flags(m, field->flags);
+	seq_printf(m, "      var.name: %s\n", field->var.name);
+	seq_printf(m, "      var.idx (into tracing_map_elt.vars[]): %u\n",
+		   field->var.idx);
+
+	field = field_var->val;
+
+	seq_printf(m, "\n      %s[%d].val:\n", vars_name, i);
+	if (field->field)
+		seq_printf(m, "      ftrace_event_field name: %s\n",
+			   field->field->name);
+	else {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	seq_printf(m, "      type: %s\n", field->type);
+	seq_printf(m, "      size: %u\n", field->size);
+	seq_printf(m, "      is_signed: %u\n", field->is_signed);
+out:
+	return ret;
+}
+
+static int hist_action_debug_show(struct seq_file *m,
+				  struct action_data *data, int i)
+{
+	int ret = 0;
+
+	if (data->handler == HANDLER_ONMAX ||
+	    data->handler == HANDLER_ONCHANGE) {
+		seq_printf(m, "\n    hist_data->actions[%d].track_data.var_ref:\n", i);
+		ret = hist_field_debug_show(m, data->track_data.var_ref,
+					    HIST_FIELD_FL_VAR_REF);
+		if (ret)
+			goto out;
+
+		seq_printf(m, "\n    hist_data->actions[%d].track_data.track_var:\n", i);
+		ret = hist_field_debug_show(m, data->track_data.track_var,
+					    HIST_FIELD_FL_VAR);
+		if (ret)
+			goto out;
+	}
+
+	if (data->handler == HANDLER_ONMATCH) {
+		seq_printf(m, "\n    hist_data->actions[%d].match_data.event_system: %s\n",
+			   i, data->match_data.event_system);
+		seq_printf(m, "    hist_data->actions[%d].match_data.event: %s\n",
+			   i, data->match_data.event);
+	}
+out:
+	return ret;
+}
+
+static int hist_actions_debug_show(struct seq_file *m,
+				   struct hist_trigger_data *hist_data)
+{
+	int i, ret = 0;
+
+	if (hist_data->n_actions)
+		seq_puts(m, "\n  action tracking variables (for onmax()/onchange()/onmatch()):\n");
+
+	for (i = 0; i < hist_data->n_actions; i++) {
+		struct action_data *action = hist_data->actions[i];
+
+		ret = hist_action_debug_show(m, action, i);
+		if (ret)
+			goto out;
+	}
+
+	if (hist_data->n_save_vars)
+		seq_puts(m, "\n  save action variables (save() params):\n");
+
+	for (i = 0; i < hist_data->n_save_vars; i++) {
+		ret = field_var_debug_show(m, hist_data->save_vars[i], i, true);
+		if (ret)
+			goto out;
+	}
+out:
+	return ret;
+}
+
+static void hist_trigger_debug_show(struct seq_file *m,
+				    struct event_trigger_data *data, int n)
+{
+	struct hist_trigger_data *hist_data;
+	int i, ret;
+
+	if (n > 0)
+		seq_puts(m, "\n\n");
+
+	seq_puts(m, "# event histogram\n#\n# trigger info: ");
+	data->ops->print(m, data->ops, data);
+	seq_puts(m, "#\n\n");
+
+	hist_data = data->private_data;
+
+	seq_printf(m, "hist_data: %p\n\n", hist_data);
+	seq_printf(m, "  n_vals: %u\n", hist_data->n_vals);
+	seq_printf(m, "  n_keys: %u\n", hist_data->n_keys);
+	seq_printf(m, "  n_fields: %u\n", hist_data->n_fields);
+
+	seq_puts(m, "\n  val fields:\n\n");
+
+	seq_puts(m, "    hist_data->fields[0]:\n");
+	ret = hist_field_debug_show(m, hist_data->fields[0],
+				    HIST_FIELD_FL_HITCOUNT);
+	if (ret)
+		return;
+
+	for (i = 1; i < hist_data->n_vals; i++) {
+		seq_printf(m, "\n    hist_data->fields[%d]:\n", i);
+		ret = hist_field_debug_show(m, hist_data->fields[i], 0);
+		if (ret)
+			return;
+	}
+
+	seq_puts(m, "\n  key fields:\n");
+
+	for (i = hist_data->n_vals; i < hist_data->n_fields; i++) {
+		seq_printf(m, "\n    hist_data->fields[%d]:\n", i);
+		ret = hist_field_debug_show(m, hist_data->fields[i],
+					    HIST_FIELD_FL_KEY);
+		if (ret)
+			return;
+	}
+
+	if (hist_data->n_var_refs)
+		seq_puts(m, "\n  variable reference fields:\n");
+
+	for (i = 0; i < hist_data->n_var_refs; i++) {
+		seq_printf(m, "\n    hist_data->var_refs[%d]:\n", i);
+		ret = hist_field_debug_show(m, hist_data->var_refs[i],
+					    HIST_FIELD_FL_VAR_REF);
+		if (ret)
+			return;
+	}
+
+	if (hist_data->n_field_vars)
+		seq_puts(m, "\n  field variables:\n");
+
+	for (i = 0; i < hist_data->n_field_vars; i++) {
+		ret = field_var_debug_show(m, hist_data->field_vars[i], i, false);
+		if (ret)
+			return;
+	}
+
+	ret = hist_actions_debug_show(m, hist_data);
+	if (ret)
+		return;
+}
+
+static int hist_debug_show(struct seq_file *m, void *v)
+{
+	struct event_trigger_data *data;
+	struct trace_event_file *event_file;
+	int n = 0, ret = 0;
+
+	mutex_lock(&event_mutex);
+
+	event_file = event_file_data(m->private);
+	if (unlikely(!event_file)) {
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	list_for_each_entry(data, &event_file->triggers, list) {
+		if (data->cmd_ops->trigger_type == ETT_EVENT_HIST)
+			hist_trigger_debug_show(m, data, n++);
+	}
+
+ out_unlock:
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+static int event_hist_debug_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
+	return single_open(file, hist_debug_show, file);
+}
+
+const struct file_operations event_hist_debug_fops = {
+	.open = event_hist_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+#endif
+
 static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
 {
 	const char *field_name = hist_field_name(hist_field, 0);
@@ -7393,37 +5903,3 @@ __init int register_trigger_hist_enable_disable_cmds(void)
 
 	return ret;
 }
-
-static __init int trace_events_hist_init(void)
-{
-	struct dentry *entry = NULL;
-	struct dentry *d_tracer;
-	int err = 0;
-
-	err = dyn_event_register(&synth_event_ops);
-	if (err) {
-		pr_warn("Could not register synth_event_ops\n");
-		return err;
-	}
-
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer)) {
-		err = PTR_ERR(d_tracer);
-		goto err;
-	}
-
-	entry = tracefs_create_file("synthetic_events", 0644, d_tracer,
-				    NULL, &synth_events_fops);
-	if (!entry) {
-		err = -ENODEV;
-		goto err;
-	}
-
-	return err;
- err:
-	pr_warn("Could not create tracefs 'synthetic_events' entry\n");
-
-	return err;
-}
-
-fs_initcall(trace_events_hist_init);
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
new file mode 100644
index 000000000000..c6cca0d1d584
--- /dev/null
+++ b/kernel/trace/trace_events_synth.c
@@ -0,0 +1,1789 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace_events_synth - synthetic trace events
+ *
+ * Copyright (C) 2015, 2020 Tom Zanussi <tom.zanussi@linux.intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/security.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/stacktrace.h>
+#include <linux/rculist.h>
+#include <linux/tracefs.h>
+
+/* for gfp flag names */
+#include <linux/trace_events.h>
+#include <trace/events/mmflags.h>
+
+#include "trace_synth.h"
+
+static int create_synth_event(int argc, const char **argv);
+static int synth_event_show(struct seq_file *m, struct dyn_event *ev);
+static int synth_event_release(struct dyn_event *ev);
+static bool synth_event_is_busy(struct dyn_event *ev);
+static bool synth_event_match(const char *system, const char *event,
+			int argc, const char **argv, struct dyn_event *ev);
+
+static struct dyn_event_operations synth_event_ops = {
+	.create = create_synth_event,
+	.show = synth_event_show,
+	.is_busy = synth_event_is_busy,
+	.free = synth_event_release,
+	.match = synth_event_match,
+};
+
+static bool is_synth_event(struct dyn_event *ev)
+{
+	return ev->ops == &synth_event_ops;
+}
+
+static struct synth_event *to_synth_event(struct dyn_event *ev)
+{
+	return container_of(ev, struct synth_event, devent);
+}
+
+static bool synth_event_is_busy(struct dyn_event *ev)
+{
+	struct synth_event *event = to_synth_event(ev);
+
+	return event->ref != 0;
+}
+
+static bool synth_event_match(const char *system, const char *event,
+			int argc, const char **argv, struct dyn_event *ev)
+{
+	struct synth_event *sev = to_synth_event(ev);
+
+	return strcmp(sev->name, event) == 0 &&
+		(!system || strcmp(system, SYNTH_SYSTEM) == 0);
+}
+
+struct synth_trace_event {
+	struct trace_entry	ent;
+	u64			fields[];
+};
+
+static int synth_event_define_fields(struct trace_event_call *call)
+{
+	struct synth_trace_event trace;
+	int offset = offsetof(typeof(trace), fields);
+	struct synth_event *event = call->data;
+	unsigned int i, size, n_u64;
+	char *name, *type;
+	bool is_signed;
+	int ret = 0;
+
+	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
+		size = event->fields[i]->size;
+		is_signed = event->fields[i]->is_signed;
+		type = event->fields[i]->type;
+		name = event->fields[i]->name;
+		ret = trace_define_field(call, type, name, offset, size,
+					 is_signed, FILTER_OTHER);
+		if (ret)
+			break;
+
+		event->fields[i]->offset = n_u64;
+
+		if (event->fields[i]->is_string) {
+			offset += STR_VAR_LEN_MAX;
+			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+		} else {
+			offset += sizeof(u64);
+			n_u64++;
+		}
+	}
+
+	event->n_u64 = n_u64;
+
+	return ret;
+}
+
+static bool synth_field_signed(char *type)
+{
+	if (str_has_prefix(type, "u"))
+		return false;
+	if (strcmp(type, "gfp_t") == 0)
+		return false;
+
+	return true;
+}
+
+static int synth_field_is_string(char *type)
+{
+	if (strstr(type, "char[") != NULL)
+		return true;
+
+	return false;
+}
+
+static int synth_field_string_size(char *type)
+{
+	char buf[4], *end, *start;
+	unsigned int len;
+	int size, err;
+
+	start = strstr(type, "char[");
+	if (start == NULL)
+		return -EINVAL;
+	start += sizeof("char[") - 1;
+
+	end = strchr(type, ']');
+	if (!end || end < start)
+		return -EINVAL;
+
+	len = end - start;
+	if (len > 3)
+		return -EINVAL;
+
+	strncpy(buf, start, len);
+	buf[len] = '\0';
+
+	err = kstrtouint(buf, 0, &size);
+	if (err)
+		return err;
+
+	if (size > STR_VAR_LEN_MAX)
+		return -EINVAL;
+
+	return size;
+}
+
+static int synth_field_size(char *type)
+{
+	int size = 0;
+
+	if (strcmp(type, "s64") == 0)
+		size = sizeof(s64);
+	else if (strcmp(type, "u64") == 0)
+		size = sizeof(u64);
+	else if (strcmp(type, "s32") == 0)
+		size = sizeof(s32);
+	else if (strcmp(type, "u32") == 0)
+		size = sizeof(u32);
+	else if (strcmp(type, "s16") == 0)
+		size = sizeof(s16);
+	else if (strcmp(type, "u16") == 0)
+		size = sizeof(u16);
+	else if (strcmp(type, "s8") == 0)
+		size = sizeof(s8);
+	else if (strcmp(type, "u8") == 0)
+		size = sizeof(u8);
+	else if (strcmp(type, "char") == 0)
+		size = sizeof(char);
+	else if (strcmp(type, "unsigned char") == 0)
+		size = sizeof(unsigned char);
+	else if (strcmp(type, "int") == 0)
+		size = sizeof(int);
+	else if (strcmp(type, "unsigned int") == 0)
+		size = sizeof(unsigned int);
+	else if (strcmp(type, "long") == 0)
+		size = sizeof(long);
+	else if (strcmp(type, "unsigned long") == 0)
+		size = sizeof(unsigned long);
+	else if (strcmp(type, "pid_t") == 0)
+		size = sizeof(pid_t);
+	else if (strcmp(type, "gfp_t") == 0)
+		size = sizeof(gfp_t);
+	else if (synth_field_is_string(type))
+		size = synth_field_string_size(type);
+
+	return size;
+}
+
+static const char *synth_field_fmt(char *type)
+{
+	const char *fmt = "%llu";
+
+	if (strcmp(type, "s64") == 0)
+		fmt = "%lld";
+	else if (strcmp(type, "u64") == 0)
+		fmt = "%llu";
+	else if (strcmp(type, "s32") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "u32") == 0)
+		fmt = "%u";
+	else if (strcmp(type, "s16") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "u16") == 0)
+		fmt = "%u";
+	else if (strcmp(type, "s8") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "u8") == 0)
+		fmt = "%u";
+	else if (strcmp(type, "char") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "unsigned char") == 0)
+		fmt = "%u";
+	else if (strcmp(type, "int") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "unsigned int") == 0)
+		fmt = "%u";
+	else if (strcmp(type, "long") == 0)
+		fmt = "%ld";
+	else if (strcmp(type, "unsigned long") == 0)
+		fmt = "%lu";
+	else if (strcmp(type, "pid_t") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "gfp_t") == 0)
+		fmt = "%x";
+	else if (synth_field_is_string(type))
+		fmt = "%s";
+
+	return fmt;
+}
+
+static void print_synth_event_num_val(struct trace_seq *s,
+				      char *print_fmt, char *name,
+				      int size, u64 val, char *space)
+{
+	switch (size) {
+	case 1:
+		trace_seq_printf(s, print_fmt, name, (u8)val, space);
+		break;
+
+	case 2:
+		trace_seq_printf(s, print_fmt, name, (u16)val, space);
+		break;
+
+	case 4:
+		trace_seq_printf(s, print_fmt, name, (u32)val, space);
+		break;
+
+	default:
+		trace_seq_printf(s, print_fmt, name, val, space);
+		break;
+	}
+}
+
+static enum print_line_t print_synth_event(struct trace_iterator *iter,
+					   int flags,
+					   struct trace_event *event)
+{
+	struct trace_array *tr = iter->tr;
+	struct trace_seq *s = &iter->seq;
+	struct synth_trace_event *entry;
+	struct synth_event *se;
+	unsigned int i, n_u64;
+	char print_fmt[32];
+	const char *fmt;
+
+	entry = (struct synth_trace_event *)iter->ent;
+	se = container_of(event, struct synth_event, call.event);
+
+	trace_seq_printf(s, "%s: ", se->name);
+
+	for (i = 0, n_u64 = 0; i < se->n_fields; i++) {
+		if (trace_seq_has_overflowed(s))
+			goto end;
+
+		fmt = synth_field_fmt(se->fields[i]->type);
+
+		/* parameter types */
+		if (tr && tr->trace_flags & TRACE_ITER_VERBOSE)
+			trace_seq_printf(s, "%s ", fmt);
+
+		snprintf(print_fmt, sizeof(print_fmt), "%%s=%s%%s", fmt);
+
+		/* parameter values */
+		if (se->fields[i]->is_string) {
+			trace_seq_printf(s, print_fmt, se->fields[i]->name,
+					 (char *)&entry->fields[n_u64],
+					 i == se->n_fields - 1 ? "" : " ");
+			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+		} else {
+			struct trace_print_flags __flags[] = {
+			    __def_gfpflag_names, {-1, NULL} };
+			char *space = (i == se->n_fields - 1 ? "" : " ");
+
+			print_synth_event_num_val(s, print_fmt,
+						  se->fields[i]->name,
+						  se->fields[i]->size,
+						  entry->fields[n_u64],
+						  space);
+
+			if (strcmp(se->fields[i]->type, "gfp_t") == 0) {
+				trace_seq_puts(s, " (");
+				trace_print_flags_seq(s, "|",
+						      entry->fields[n_u64],
+						      __flags);
+				trace_seq_putc(s, ')');
+			}
+			n_u64++;
+		}
+	}
+end:
+	trace_seq_putc(s, '\n');
+
+	return trace_handle_return(s);
+}
+
+static struct trace_event_functions synth_event_funcs = {
+	.trace		= print_synth_event
+};
+
+static notrace void trace_event_raw_event_synth(void *__data,
+						u64 *var_ref_vals,
+						unsigned int *var_ref_idx)
+{
+	struct trace_event_file *trace_file = __data;
+	struct synth_trace_event *entry;
+	struct trace_event_buffer fbuffer;
+	struct trace_buffer *buffer;
+	struct synth_event *event;
+	unsigned int i, n_u64, val_idx;
+	int fields_size = 0;
+
+	event = trace_file->event_call->data;
+
+	if (trace_trigger_soft_disabled(trace_file))
+		return;
+
+	fields_size = event->n_u64 * sizeof(u64);
+
+	/*
+	 * Avoid ring buffer recursion detection, as this event
+	 * is being performed within another event.
+	 */
+	buffer = trace_file->tr->array_buffer.buffer;
+	ring_buffer_nest_start(buffer);
+
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
+					   sizeof(*entry) + fields_size);
+	if (!entry)
+		goto out;
+
+	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
+		val_idx = var_ref_idx[i];
+		if (event->fields[i]->is_string) {
+			char *str_val = (char *)(long)var_ref_vals[val_idx];
+			char *str_field = (char *)&entry->fields[n_u64];
+
+			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+		} else {
+			struct synth_field *field = event->fields[i];
+			u64 val = var_ref_vals[val_idx];
+
+			switch (field->size) {
+			case 1:
+				*(u8 *)&entry->fields[n_u64] = (u8)val;
+				break;
+
+			case 2:
+				*(u16 *)&entry->fields[n_u64] = (u16)val;
+				break;
+
+			case 4:
+				*(u32 *)&entry->fields[n_u64] = (u32)val;
+				break;
+
+			default:
+				entry->fields[n_u64] = val;
+				break;
+			}
+			n_u64++;
+		}
+	}
+
+	trace_event_buffer_commit(&fbuffer);
+out:
+	ring_buffer_nest_end(buffer);
+}
+
+static void free_synth_event_print_fmt(struct trace_event_call *call)
+{
+	if (call) {
+		kfree(call->print_fmt);
+		call->print_fmt = NULL;
+	}
+}
+
+static int __set_synth_event_print_fmt(struct synth_event *event,
+				       char *buf, int len)
+{
+	const char *fmt;
+	int pos = 0;
+	int i;
+
+	/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+	for (i = 0; i < event->n_fields; i++) {
+		fmt = synth_field_fmt(event->fields[i]->type);
+		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s=%s%s",
+				event->fields[i]->name, fmt,
+				i == event->n_fields - 1 ? "" : ", ");
+	}
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+
+	for (i = 0; i < event->n_fields; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO,
+				", REC->%s", event->fields[i]->name);
+	}
+
+#undef LEN_OR_ZERO
+
+	/* return the length of print_fmt */
+	return pos;
+}
+
+static int set_synth_event_print_fmt(struct trace_event_call *call)
+{
+	struct synth_event *event = call->data;
+	char *print_fmt;
+	int len;
+
+	/* First: called with 0 length to calculate the needed length */
+	len = __set_synth_event_print_fmt(event, NULL, 0);
+
+	print_fmt = kmalloc(len + 1, GFP_KERNEL);
+	if (!print_fmt)
+		return -ENOMEM;
+
+	/* Second: actually write the @print_fmt */
+	__set_synth_event_print_fmt(event, print_fmt, len + 1);
+	call->print_fmt = print_fmt;
+
+	return 0;
+}
+
+static void free_synth_field(struct synth_field *field)
+{
+	kfree(field->type);
+	kfree(field->name);
+	kfree(field);
+}
+
+static struct synth_field *parse_synth_field(int argc, const char **argv,
+					     int *consumed)
+{
+	struct synth_field *field;
+	const char *prefix = NULL, *field_type = argv[0], *field_name, *array;
+	int len, ret = 0;
+
+	if (field_type[0] == ';')
+		field_type++;
+
+	if (!strcmp(field_type, "unsigned")) {
+		if (argc < 3)
+			return ERR_PTR(-EINVAL);
+		prefix = "unsigned ";
+		field_type = argv[1];
+		field_name = argv[2];
+		*consumed = 3;
+	} else {
+		field_name = argv[1];
+		*consumed = 2;
+	}
+
+	field = kzalloc(sizeof(*field), GFP_KERNEL);
+	if (!field)
+		return ERR_PTR(-ENOMEM);
+
+	len = strlen(field_name);
+	array = strchr(field_name, '[');
+	if (array)
+		len -= strlen(array);
+	else if (field_name[len - 1] == ';')
+		len--;
+
+	field->name = kmemdup_nul(field_name, len, GFP_KERNEL);
+	if (!field->name) {
+		ret = -ENOMEM;
+		goto free;
+	}
+
+	if (field_type[0] == ';')
+		field_type++;
+	len = strlen(field_type) + 1;
+	if (array)
+		len += strlen(array);
+	if (prefix)
+		len += strlen(prefix);
+
+	field->type = kzalloc(len, GFP_KERNEL);
+	if (!field->type) {
+		ret = -ENOMEM;
+		goto free;
+	}
+	if (prefix)
+		strcat(field->type, prefix);
+	strcat(field->type, field_type);
+	if (array) {
+		strcat(field->type, array);
+		if (field->type[len - 1] == ';')
+			field->type[len - 1] = '\0';
+	}
+
+	field->size = synth_field_size(field->type);
+	if (!field->size) {
+		ret = -EINVAL;
+		goto free;
+	}
+
+	if (synth_field_is_string(field->type))
+		field->is_string = true;
+
+	field->is_signed = synth_field_signed(field->type);
+
+ out:
+	return field;
+ free:
+	free_synth_field(field);
+	field = ERR_PTR(ret);
+	goto out;
+}
+
+static void free_synth_tracepoint(struct tracepoint *tp)
+{
+	if (!tp)
+		return;
+
+	kfree(tp->name);
+	kfree(tp);
+}
+
+static struct tracepoint *alloc_synth_tracepoint(char *name)
+{
+	struct tracepoint *tp;
+
+	tp = kzalloc(sizeof(*tp), GFP_KERNEL);
+	if (!tp)
+		return ERR_PTR(-ENOMEM);
+
+	tp->name = kstrdup(name, GFP_KERNEL);
+	if (!tp->name) {
+		kfree(tp);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return tp;
+}
+
+struct synth_event *find_synth_event(const char *name)
+{
+	struct dyn_event *pos;
+	struct synth_event *event;
+
+	for_each_dyn_event(pos) {
+		if (!is_synth_event(pos))
+			continue;
+		event = to_synth_event(pos);
+		if (strcmp(event->name, name) == 0)
+			return event;
+	}
+
+	return NULL;
+}
+
+static struct trace_event_fields synth_event_fields_array[] = {
+	{ .type = TRACE_FUNCTION_TYPE,
+	  .define_fields = synth_event_define_fields },
+	{}
+};
+
+static int register_synth_event(struct synth_event *event)
+{
+	struct trace_event_call *call = &event->call;
+	int ret = 0;
+
+	event->call.class = &event->class;
+	event->class.system = kstrdup(SYNTH_SYSTEM, GFP_KERNEL);
+	if (!event->class.system) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	event->tp = alloc_synth_tracepoint(event->name);
+	if (IS_ERR(event->tp)) {
+		ret = PTR_ERR(event->tp);
+		event->tp = NULL;
+		goto out;
+	}
+
+	INIT_LIST_HEAD(&call->class->fields);
+	call->event.funcs = &synth_event_funcs;
+	call->class->fields_array = synth_event_fields_array;
+
+	ret = register_trace_event(&call->event);
+	if (!ret) {
+		ret = -ENODEV;
+		goto out;
+	}
+	call->flags = TRACE_EVENT_FL_TRACEPOINT;
+	call->class->reg = trace_event_reg;
+	call->class->probe = trace_event_raw_event_synth;
+	call->data = event;
+	call->tp = event->tp;
+
+	ret = trace_add_event_call(call);
+	if (ret) {
+		pr_warn("Failed to register synthetic event: %s\n",
+			trace_event_name(call));
+		goto err;
+	}
+
+	ret = set_synth_event_print_fmt(call);
+	if (ret < 0) {
+		trace_remove_event_call(call);
+		goto err;
+	}
+ out:
+	return ret;
+ err:
+	unregister_trace_event(&call->event);
+	goto out;
+}
+
+static int unregister_synth_event(struct synth_event *event)
+{
+	struct trace_event_call *call = &event->call;
+	int ret;
+
+	ret = trace_remove_event_call(call);
+
+	return ret;
+}
+
+static void free_synth_event(struct synth_event *event)
+{
+	unsigned int i;
+
+	if (!event)
+		return;
+
+	for (i = 0; i < event->n_fields; i++)
+		free_synth_field(event->fields[i]);
+
+	kfree(event->fields);
+	kfree(event->name);
+	kfree(event->class.system);
+	free_synth_tracepoint(event->tp);
+	free_synth_event_print_fmt(&event->call);
+	kfree(event);
+}
+
+static struct synth_event *alloc_synth_event(const char *name, int n_fields,
+					     struct synth_field **fields)
+{
+	struct synth_event *event;
+	unsigned int i;
+
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event) {
+		event = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	event->name = kstrdup(name, GFP_KERNEL);
+	if (!event->name) {
+		kfree(event);
+		event = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	event->fields = kcalloc(n_fields, sizeof(*event->fields), GFP_KERNEL);
+	if (!event->fields) {
+		free_synth_event(event);
+		event = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	dyn_event_init(&event->devent, &synth_event_ops);
+
+	for (i = 0; i < n_fields; i++)
+		event->fields[i] = fields[i];
+
+	event->n_fields = n_fields;
+ out:
+	return event;
+}
+
+static int synth_event_check_arg_fn(void *data)
+{
+	struct dynevent_arg_pair *arg_pair = data;
+	int size;
+
+	size = synth_field_size((char *)arg_pair->lhs);
+
+	return size ? 0 : -EINVAL;
+}
+
+/**
+ * synth_event_add_field - Add a new field to a synthetic event cmd
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @type: The type of the new field to add
+ * @name: The name of the new field to add
+ *
+ * Add a new field to a synthetic event cmd object.  Field ordering is in
+ * the same order the fields are added.
+ *
+ * See synth_field_size() for available types. If field_name contains
+ * [n] the field is considered to be an array.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_add_field(struct dynevent_cmd *cmd, const char *type,
+			  const char *name)
+{
+	struct dynevent_arg_pair arg_pair;
+	int ret;
+
+	if (cmd->type != DYNEVENT_TYPE_SYNTH)
+		return -EINVAL;
+
+	if (!type || !name)
+		return -EINVAL;
+
+	dynevent_arg_pair_init(&arg_pair, 0, ';');
+
+	arg_pair.lhs = type;
+	arg_pair.rhs = name;
+
+	ret = dynevent_arg_pair_add(cmd, &arg_pair, synth_event_check_arg_fn);
+	if (ret)
+		return ret;
+
+	if (++cmd->n_fields > SYNTH_FIELDS_MAX)
+		ret = -EINVAL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_add_field);
+
+/**
+ * synth_event_add_field_str - Add a new field to a synthetic event cmd
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @type_name: The type and name of the new field to add, as a single string
+ *
+ * Add a new field to a synthetic event cmd object, as a single
+ * string.  The @type_name string is expected to be of the form 'type
+ * name', which will be appended by ';'.  No sanity checking is done -
+ * what's passed in is assumed to already be well-formed.  Field
+ * ordering is in the same order the fields are added.
+ *
+ * See synth_field_size() for available types. If field_name contains
+ * [n] the field is considered to be an array.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_add_field_str(struct dynevent_cmd *cmd, const char *type_name)
+{
+	struct dynevent_arg arg;
+	int ret;
+
+	if (cmd->type != DYNEVENT_TYPE_SYNTH)
+		return -EINVAL;
+
+	if (!type_name)
+		return -EINVAL;
+
+	dynevent_arg_init(&arg, ';');
+
+	arg.str = type_name;
+
+	ret = dynevent_arg_add(cmd, &arg, NULL);
+	if (ret)
+		return ret;
+
+	if (++cmd->n_fields > SYNTH_FIELDS_MAX)
+		ret = -EINVAL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_add_field_str);
+
+/**
+ * synth_event_add_fields - Add multiple fields to a synthetic event cmd
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @fields: An array of type/name field descriptions
+ * @n_fields: The number of field descriptions contained in the fields array
+ *
+ * Add a new set of fields to a synthetic event cmd object.  The event
+ * fields that will be defined for the event should be passed in as an
+ * array of struct synth_field_desc, and the number of elements in the
+ * array passed in as n_fields.  Field ordering will retain the
+ * ordering given in the fields array.
+ *
+ * See synth_field_size() for available types. If field_name contains
+ * [n] the field is considered to be an array.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_add_fields(struct dynevent_cmd *cmd,
+			   struct synth_field_desc *fields,
+			   unsigned int n_fields)
+{
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0; i < n_fields; i++) {
+		if (fields[i].type == NULL || fields[i].name == NULL) {
+			ret = -EINVAL;
+			break;
+		}
+
+		ret = synth_event_add_field(cmd, fields[i].type, fields[i].name);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_add_fields);
+
+/**
+ * __synth_event_gen_cmd_start - Start a synthetic event command from arg list
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @name: The name of the synthetic event
+ * @mod: The module creating the event, NULL if not created from a module
+ * @args: Variable number of arg (pairs), one pair for each field
+ *
+ * NOTE: Users normally won't want to call this function directly, but
+ * rather use the synth_event_gen_cmd_start() wrapper, which
+ * automatically adds a NULL to the end of the arg list.  If this
+ * function is used directly, make sure the last arg in the variable
+ * arg list is NULL.
+ *
+ * Generate a synthetic event command to be executed by
+ * synth_event_gen_cmd_end().  This function can be used to generate
+ * the complete command or only the first part of it; in the latter
+ * case, synth_event_add_field(), synth_event_add_field_str(), or
+ * synth_event_add_fields() can be used to add more fields following
+ * this.
+ *
+ * There should be an even number variable args, each pair consisting
+ * of a type followed by a field name.
+ *
+ * See synth_field_size() for available types. If field_name contains
+ * [n] the field is considered to be an array.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int __synth_event_gen_cmd_start(struct dynevent_cmd *cmd, const char *name,
+				struct module *mod, ...)
+{
+	struct dynevent_arg arg;
+	va_list args;
+	int ret;
+
+	cmd->event_name = name;
+	cmd->private_data = mod;
+
+	if (cmd->type != DYNEVENT_TYPE_SYNTH)
+		return -EINVAL;
+
+	dynevent_arg_init(&arg, 0);
+	arg.str = name;
+	ret = dynevent_arg_add(cmd, &arg, NULL);
+	if (ret)
+		return ret;
+
+	va_start(args, mod);
+	for (;;) {
+		const char *type, *name;
+
+		type = va_arg(args, const char *);
+		if (!type)
+			break;
+		name = va_arg(args, const char *);
+		if (!name)
+			break;
+
+		if (++cmd->n_fields > SYNTH_FIELDS_MAX) {
+			ret = -EINVAL;
+			break;
+		}
+
+		ret = synth_event_add_field(cmd, type, name);
+		if (ret)
+			break;
+	}
+	va_end(args);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__synth_event_gen_cmd_start);
+
+/**
+ * synth_event_gen_cmd_array_start - Start synthetic event command from an array
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @name: The name of the synthetic event
+ * @fields: An array of type/name field descriptions
+ * @n_fields: The number of field descriptions contained in the fields array
+ *
+ * Generate a synthetic event command to be executed by
+ * synth_event_gen_cmd_end().  This function can be used to generate
+ * the complete command or only the first part of it; in the latter
+ * case, synth_event_add_field(), synth_event_add_field_str(), or
+ * synth_event_add_fields() can be used to add more fields following
+ * this.
+ *
+ * The event fields that will be defined for the event should be
+ * passed in as an array of struct synth_field_desc, and the number of
+ * elements in the array passed in as n_fields.  Field ordering will
+ * retain the ordering given in the fields array.
+ *
+ * See synth_field_size() for available types. If field_name contains
+ * [n] the field is considered to be an array.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_gen_cmd_array_start(struct dynevent_cmd *cmd, const char *name,
+				    struct module *mod,
+				    struct synth_field_desc *fields,
+				    unsigned int n_fields)
+{
+	struct dynevent_arg arg;
+	unsigned int i;
+	int ret = 0;
+
+	cmd->event_name = name;
+	cmd->private_data = mod;
+
+	if (cmd->type != DYNEVENT_TYPE_SYNTH)
+		return -EINVAL;
+
+	if (n_fields > SYNTH_FIELDS_MAX)
+		return -EINVAL;
+
+	dynevent_arg_init(&arg, 0);
+	arg.str = name;
+	ret = dynevent_arg_add(cmd, &arg, NULL);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < n_fields; i++) {
+		if (fields[i].type == NULL || fields[i].name == NULL)
+			return -EINVAL;
+
+		ret = synth_event_add_field(cmd, fields[i].type, fields[i].name);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_gen_cmd_array_start);
+
+static int __create_synth_event(int argc, const char *name, const char **argv)
+{
+	struct synth_field *field, *fields[SYNTH_FIELDS_MAX];
+	struct synth_event *event = NULL;
+	int i, consumed = 0, n_fields = 0, ret = 0;
+
+	/*
+	 * Argument syntax:
+	 *  - Add synthetic event: <event_name> field[;field] ...
+	 *  - Remove synthetic event: !<event_name> field[;field] ...
+	 *      where 'field' = type field_name
+	 */
+
+	if (name[0] == '\0' || argc < 1)
+		return -EINVAL;
+
+	mutex_lock(&event_mutex);
+
+	event = find_synth_event(name);
+	if (event) {
+		ret = -EEXIST;
+		goto out;
+	}
+
+	for (i = 0; i < argc - 1; i++) {
+		if (strcmp(argv[i], ";") == 0)
+			continue;
+		if (n_fields == SYNTH_FIELDS_MAX) {
+			ret = -EINVAL;
+			goto err;
+		}
+
+		field = parse_synth_field(argc - i, &argv[i], &consumed);
+		if (IS_ERR(field)) {
+			ret = PTR_ERR(field);
+			goto err;
+		}
+		fields[n_fields++] = field;
+		i += consumed - 1;
+	}
+
+	if (i < argc && strcmp(argv[i], ";") != 0) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	event = alloc_synth_event(name, n_fields, fields);
+	if (IS_ERR(event)) {
+		ret = PTR_ERR(event);
+		event = NULL;
+		goto err;
+	}
+	ret = register_synth_event(event);
+	if (!ret)
+		dyn_event_add(&event->devent);
+	else
+		free_synth_event(event);
+ out:
+	mutex_unlock(&event_mutex);
+
+	return ret;
+ err:
+	for (i = 0; i < n_fields; i++)
+		free_synth_field(fields[i]);
+
+	goto out;
+}
+
+/**
+ * synth_event_create - Create a new synthetic event
+ * @name: The name of the new sythetic event
+ * @fields: An array of type/name field descriptions
+ * @n_fields: The number of field descriptions contained in the fields array
+ * @mod: The module creating the event, NULL if not created from a module
+ *
+ * Create a new synthetic event with the given name under the
+ * trace/events/synthetic/ directory.  The event fields that will be
+ * defined for the event should be passed in as an array of struct
+ * synth_field_desc, and the number elements in the array passed in as
+ * n_fields. Field ordering will retain the ordering given in the
+ * fields array.
+ *
+ * If the new synthetic event is being created from a module, the mod
+ * param must be non-NULL.  This will ensure that the trace buffer
+ * won't contain unreadable events.
+ *
+ * The new synth event should be deleted using synth_event_delete()
+ * function.  The new synthetic event can be generated from modules or
+ * other kernel code using trace_synth_event() and related functions.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_create(const char *name, struct synth_field_desc *fields,
+		       unsigned int n_fields, struct module *mod)
+{
+	struct dynevent_cmd cmd;
+	char *buf;
+	int ret;
+
+	buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	synth_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN);
+
+	ret = synth_event_gen_cmd_array_start(&cmd, name, mod,
+					      fields, n_fields);
+	if (ret)
+		goto out;
+
+	ret = synth_event_gen_cmd_end(&cmd);
+ out:
+	kfree(buf);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_create);
+
+static int destroy_synth_event(struct synth_event *se)
+{
+	int ret;
+
+	if (se->ref)
+		ret = -EBUSY;
+	else {
+		ret = unregister_synth_event(se);
+		if (!ret) {
+			dyn_event_remove(&se->devent);
+			free_synth_event(se);
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * synth_event_delete - Delete a synthetic event
+ * @event_name: The name of the new sythetic event
+ *
+ * Delete a synthetic event that was created with synth_event_create().
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_delete(const char *event_name)
+{
+	struct synth_event *se = NULL;
+	struct module *mod = NULL;
+	int ret = -ENOENT;
+
+	mutex_lock(&event_mutex);
+	se = find_synth_event(event_name);
+	if (se) {
+		mod = se->mod;
+		ret = destroy_synth_event(se);
+	}
+	mutex_unlock(&event_mutex);
+
+	if (mod) {
+		mutex_lock(&trace_types_lock);
+		/*
+		 * It is safest to reset the ring buffer if the module
+		 * being unloaded registered any events that were
+		 * used. The only worry is if a new module gets
+		 * loaded, and takes on the same id as the events of
+		 * this module. When printing out the buffer, traced
+		 * events left over from this module may be passed to
+		 * the new module events and unexpected results may
+		 * occur.
+		 */
+		tracing_reset_all_online_cpus();
+		mutex_unlock(&trace_types_lock);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_delete);
+
+static int create_or_delete_synth_event(int argc, char **argv)
+{
+	const char *name = argv[0];
+	int ret;
+
+	/* trace_run_command() ensures argc != 0 */
+	if (name[0] == '!') {
+		ret = synth_event_delete(name + 1);
+		return ret;
+	}
+
+	ret = __create_synth_event(argc - 1, name, (const char **)argv + 1);
+	return ret == -ECANCELED ? -EINVAL : ret;
+}
+
+static int synth_event_run_command(struct dynevent_cmd *cmd)
+{
+	struct synth_event *se;
+	int ret;
+
+	ret = trace_run_command(cmd->seq.buffer, create_or_delete_synth_event);
+	if (ret)
+		return ret;
+
+	se = find_synth_event(cmd->event_name);
+	if (WARN_ON(!se))
+		return -ENOENT;
+
+	se->mod = cmd->private_data;
+
+	return ret;
+}
+
+/**
+ * synth_event_cmd_init - Initialize a synthetic event command object
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @buf: A pointer to the buffer used to build the command
+ * @maxlen: The length of the buffer passed in @buf
+ *
+ * Initialize a synthetic event command object.  Use this before
+ * calling any of the other dyenvent_cmd functions.
+ */
+void synth_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen)
+{
+	dynevent_cmd_init(cmd, buf, maxlen, DYNEVENT_TYPE_SYNTH,
+			  synth_event_run_command);
+}
+EXPORT_SYMBOL_GPL(synth_event_cmd_init);
+
+static inline int
+__synth_event_trace_start(struct trace_event_file *file,
+			  struct synth_event_trace_state *trace_state)
+{
+	int entry_size, fields_size = 0;
+	int ret = 0;
+
+	memset(trace_state, '\0', sizeof(*trace_state));
+
+	/*
+	 * Normal event tracing doesn't get called at all unless the
+	 * ENABLED bit is set (which attaches the probe thus allowing
+	 * this code to be called, etc).  Because this is called
+	 * directly by the user, we don't have that but we still need
+	 * to honor not logging when disabled.  For the the iterated
+	 * trace case, we save the enabed state upon start and just
+	 * ignore the following data calls.
+	 */
+	if (!(file->flags & EVENT_FILE_FL_ENABLED) ||
+	    trace_trigger_soft_disabled(file)) {
+		trace_state->disabled = true;
+		ret = -ENOENT;
+		goto out;
+	}
+
+	trace_state->event = file->event_call->data;
+
+	fields_size = trace_state->event->n_u64 * sizeof(u64);
+
+	/*
+	 * Avoid ring buffer recursion detection, as this event
+	 * is being performed within another event.
+	 */
+	trace_state->buffer = file->tr->array_buffer.buffer;
+	ring_buffer_nest_start(trace_state->buffer);
+
+	entry_size = sizeof(*trace_state->entry) + fields_size;
+	trace_state->entry = trace_event_buffer_reserve(&trace_state->fbuffer,
+							file,
+							entry_size);
+	if (!trace_state->entry) {
+		ring_buffer_nest_end(trace_state->buffer);
+		ret = -EINVAL;
+	}
+out:
+	return ret;
+}
+
+static inline void
+__synth_event_trace_end(struct synth_event_trace_state *trace_state)
+{
+	trace_event_buffer_commit(&trace_state->fbuffer);
+
+	ring_buffer_nest_end(trace_state->buffer);
+}
+
+/**
+ * synth_event_trace - Trace a synthetic event
+ * @file: The trace_event_file representing the synthetic event
+ * @n_vals: The number of values in vals
+ * @args: Variable number of args containing the event values
+ *
+ * Trace a synthetic event using the values passed in the variable
+ * argument list.
+ *
+ * The argument list should be a list 'n_vals' u64 values.  The number
+ * of vals must match the number of field in the synthetic event, and
+ * must be in the same order as the synthetic event fields.
+ *
+ * All vals should be cast to u64, and string vals are just pointers
+ * to strings, cast to u64.  Strings will be copied into space
+ * reserved in the event for the string, using these pointers.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...)
+{
+	struct synth_event_trace_state state;
+	unsigned int i, n_u64;
+	va_list args;
+	int ret;
+
+	ret = __synth_event_trace_start(file, &state);
+	if (ret) {
+		if (ret == -ENOENT)
+			ret = 0; /* just disabled, not really an error */
+		return ret;
+	}
+
+	if (n_vals != state.event->n_fields) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	va_start(args, n_vals);
+	for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
+		u64 val;
+
+		val = va_arg(args, u64);
+
+		if (state.event->fields[i]->is_string) {
+			char *str_val = (char *)(long)val;
+			char *str_field = (char *)&state.entry->fields[n_u64];
+
+			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+		} else {
+			struct synth_field *field = state.event->fields[i];
+
+			switch (field->size) {
+			case 1:
+				*(u8 *)&state.entry->fields[n_u64] = (u8)val;
+				break;
+
+			case 2:
+				*(u16 *)&state.entry->fields[n_u64] = (u16)val;
+				break;
+
+			case 4:
+				*(u32 *)&state.entry->fields[n_u64] = (u32)val;
+				break;
+
+			default:
+				state.entry->fields[n_u64] = val;
+				break;
+			}
+			n_u64++;
+		}
+	}
+	va_end(args);
+out:
+	__synth_event_trace_end(&state);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_trace);
+
+/**
+ * synth_event_trace_array - Trace a synthetic event from an array
+ * @file: The trace_event_file representing the synthetic event
+ * @vals: Array of values
+ * @n_vals: The number of values in vals
+ *
+ * Trace a synthetic event using the values passed in as 'vals'.
+ *
+ * The 'vals' array is just an array of 'n_vals' u64.  The number of
+ * vals must match the number of field in the synthetic event, and
+ * must be in the same order as the synthetic event fields.
+ *
+ * All vals should be cast to u64, and string vals are just pointers
+ * to strings, cast to u64.  Strings will be copied into space
+ * reserved in the event for the string, using these pointers.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_trace_array(struct trace_event_file *file, u64 *vals,
+			    unsigned int n_vals)
+{
+	struct synth_event_trace_state state;
+	unsigned int i, n_u64;
+	int ret;
+
+	ret = __synth_event_trace_start(file, &state);
+	if (ret) {
+		if (ret == -ENOENT)
+			ret = 0; /* just disabled, not really an error */
+		return ret;
+	}
+
+	if (n_vals != state.event->n_fields) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
+		if (state.event->fields[i]->is_string) {
+			char *str_val = (char *)(long)vals[i];
+			char *str_field = (char *)&state.entry->fields[n_u64];
+
+			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+		} else {
+			struct synth_field *field = state.event->fields[i];
+			u64 val = vals[i];
+
+			switch (field->size) {
+			case 1:
+				*(u8 *)&state.entry->fields[n_u64] = (u8)val;
+				break;
+
+			case 2:
+				*(u16 *)&state.entry->fields[n_u64] = (u16)val;
+				break;
+
+			case 4:
+				*(u32 *)&state.entry->fields[n_u64] = (u32)val;
+				break;
+
+			default:
+				state.entry->fields[n_u64] = val;
+				break;
+			}
+			n_u64++;
+		}
+	}
+out:
+	__synth_event_trace_end(&state);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_trace_array);
+
+/**
+ * synth_event_trace_start - Start piecewise synthetic event trace
+ * @file: The trace_event_file representing the synthetic event
+ * @trace_state: A pointer to object tracking the piecewise trace state
+ *
+ * Start the trace of a synthetic event field-by-field rather than all
+ * at once.
+ *
+ * This function 'opens' an event trace, which means space is reserved
+ * for the event in the trace buffer, after which the event's
+ * individual field values can be set through either
+ * synth_event_add_next_val() or synth_event_add_val().
+ *
+ * A pointer to a trace_state object is passed in, which will keep
+ * track of the current event trace state until the event trace is
+ * closed (and the event finally traced) using
+ * synth_event_trace_end().
+ *
+ * Note that synth_event_trace_end() must be called after all values
+ * have been added for each event trace, regardless of whether adding
+ * all field values succeeded or not.
+ *
+ * Note also that for a given event trace, all fields must be added
+ * using either synth_event_add_next_val() or synth_event_add_val()
+ * but not both together or interleaved.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_trace_start(struct trace_event_file *file,
+			    struct synth_event_trace_state *trace_state)
+{
+	int ret;
+
+	if (!trace_state)
+		return -EINVAL;
+
+	ret = __synth_event_trace_start(file, trace_state);
+	if (ret == -ENOENT)
+		ret = 0; /* just disabled, not really an error */
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_trace_start);
+
+static int __synth_event_add_val(const char *field_name, u64 val,
+				 struct synth_event_trace_state *trace_state)
+{
+	struct synth_field *field = NULL;
+	struct synth_trace_event *entry;
+	struct synth_event *event;
+	int i, ret = 0;
+
+	if (!trace_state) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* can't mix add_next_synth_val() with add_synth_val() */
+	if (field_name) {
+		if (trace_state->add_next) {
+			ret = -EINVAL;
+			goto out;
+		}
+		trace_state->add_name = true;
+	} else {
+		if (trace_state->add_name) {
+			ret = -EINVAL;
+			goto out;
+		}
+		trace_state->add_next = true;
+	}
+
+	if (trace_state->disabled)
+		goto out;
+
+	event = trace_state->event;
+	if (trace_state->add_name) {
+		for (i = 0; i < event->n_fields; i++) {
+			field = event->fields[i];
+			if (strcmp(field->name, field_name) == 0)
+				break;
+		}
+		if (!field) {
+			ret = -EINVAL;
+			goto out;
+		}
+	} else {
+		if (trace_state->cur_field >= event->n_fields) {
+			ret = -EINVAL;
+			goto out;
+		}
+		field = event->fields[trace_state->cur_field++];
+	}
+
+	entry = trace_state->entry;
+	if (field->is_string) {
+		char *str_val = (char *)(long)val;
+		char *str_field;
+
+		if (!str_val) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		str_field = (char *)&entry->fields[field->offset];
+		strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+	} else {
+		switch (field->size) {
+		case 1:
+			*(u8 *)&trace_state->entry->fields[field->offset] = (u8)val;
+			break;
+
+		case 2:
+			*(u16 *)&trace_state->entry->fields[field->offset] = (u16)val;
+			break;
+
+		case 4:
+			*(u32 *)&trace_state->entry->fields[field->offset] = (u32)val;
+			break;
+
+		default:
+			trace_state->entry->fields[field->offset] = val;
+			break;
+		}
+	}
+ out:
+	return ret;
+}
+
+/**
+ * synth_event_add_next_val - Add the next field's value to an open synth trace
+ * @val: The value to set the next field to
+ * @trace_state: A pointer to object tracking the piecewise trace state
+ *
+ * Set the value of the next field in an event that's been opened by
+ * synth_event_trace_start().
+ *
+ * The val param should be the value cast to u64.  If the value points
+ * to a string, the val param should be a char * cast to u64.
+ *
+ * This function assumes all the fields in an event are to be set one
+ * after another - successive calls to this function are made, one for
+ * each field, in the order of the fields in the event, until all
+ * fields have been set.  If you'd rather set each field individually
+ * without regard to ordering, synth_event_add_val() can be used
+ * instead.
+ *
+ * Note however that synth_event_add_next_val() and
+ * synth_event_add_val() can't be intermixed for a given event trace -
+ * one or the other but not both can be used at the same time.
+ *
+ * Note also that synth_event_trace_end() must be called after all
+ * values have been added for each event trace, regardless of whether
+ * adding all field values succeeded or not.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_add_next_val(u64 val,
+			     struct synth_event_trace_state *trace_state)
+{
+	return __synth_event_add_val(NULL, val, trace_state);
+}
+EXPORT_SYMBOL_GPL(synth_event_add_next_val);
+
+/**
+ * synth_event_add_val - Add a named field's value to an open synth trace
+ * @field_name: The name of the synthetic event field value to set
+ * @val: The value to set the next field to
+ * @trace_state: A pointer to object tracking the piecewise trace state
+ *
+ * Set the value of the named field in an event that's been opened by
+ * synth_event_trace_start().
+ *
+ * The val param should be the value cast to u64.  If the value points
+ * to a string, the val param should be a char * cast to u64.
+ *
+ * This function looks up the field name, and if found, sets the field
+ * to the specified value.  This lookup makes this function more
+ * expensive than synth_event_add_next_val(), so use that or the
+ * none-piecewise synth_event_trace() instead if efficiency is more
+ * important.
+ *
+ * Note however that synth_event_add_next_val() and
+ * synth_event_add_val() can't be intermixed for a given event trace -
+ * one or the other but not both can be used at the same time.
+ *
+ * Note also that synth_event_trace_end() must be called after all
+ * values have been added for each event trace, regardless of whether
+ * adding all field values succeeded or not.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_add_val(const char *field_name, u64 val,
+			struct synth_event_trace_state *trace_state)
+{
+	return __synth_event_add_val(field_name, val, trace_state);
+}
+EXPORT_SYMBOL_GPL(synth_event_add_val);
+
+/**
+ * synth_event_trace_end - End piecewise synthetic event trace
+ * @trace_state: A pointer to object tracking the piecewise trace state
+ *
+ * End the trace of a synthetic event opened by
+ * synth_event_trace__start().
+ *
+ * This function 'closes' an event trace, which basically means that
+ * it commits the reserved event and cleans up other loose ends.
+ *
+ * A pointer to a trace_state object is passed in, which will keep
+ * track of the current event trace state opened with
+ * synth_event_trace_start().
+ *
+ * Note that this function must be called after all values have been
+ * added for each event trace, regardless of whether adding all field
+ * values succeeded or not.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_trace_end(struct synth_event_trace_state *trace_state)
+{
+	if (!trace_state)
+		return -EINVAL;
+
+	__synth_event_trace_end(trace_state);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(synth_event_trace_end);
+
+static int create_synth_event(int argc, const char **argv)
+{
+	const char *name = argv[0];
+	int len;
+
+	if (name[0] != 's' || name[1] != ':')
+		return -ECANCELED;
+	name += 2;
+
+	/* This interface accepts group name prefix */
+	if (strchr(name, '/')) {
+		len = str_has_prefix(name, SYNTH_SYSTEM "/");
+		if (len == 0)
+			return -EINVAL;
+		name += len;
+	}
+	return __create_synth_event(argc - 1, name, argv + 1);
+}
+
+static int synth_event_release(struct dyn_event *ev)
+{
+	struct synth_event *event = to_synth_event(ev);
+	int ret;
+
+	if (event->ref)
+		return -EBUSY;
+
+	ret = unregister_synth_event(event);
+	if (ret)
+		return ret;
+
+	dyn_event_remove(ev);
+	free_synth_event(event);
+	return 0;
+}
+
+static int __synth_event_show(struct seq_file *m, struct synth_event *event)
+{
+	struct synth_field *field;
+	unsigned int i;
+
+	seq_printf(m, "%s\t", event->name);
+
+	for (i = 0; i < event->n_fields; i++) {
+		field = event->fields[i];
+
+		/* parameter values */
+		seq_printf(m, "%s %s%s", field->type, field->name,
+			   i == event->n_fields - 1 ? "" : "; ");
+	}
+
+	seq_putc(m, '\n');
+
+	return 0;
+}
+
+static int synth_event_show(struct seq_file *m, struct dyn_event *ev)
+{
+	struct synth_event *event = to_synth_event(ev);
+
+	seq_printf(m, "s:%s/", event->class.system);
+
+	return __synth_event_show(m, event);
+}
+
+static int synth_events_seq_show(struct seq_file *m, void *v)
+{
+	struct dyn_event *ev = v;
+
+	if (!is_synth_event(ev))
+		return 0;
+
+	return __synth_event_show(m, to_synth_event(ev));
+}
+
+static const struct seq_operations synth_events_seq_op = {
+	.start	= dyn_event_seq_start,
+	.next	= dyn_event_seq_next,
+	.stop	= dyn_event_seq_stop,
+	.show	= synth_events_seq_show,
+};
+
+static int synth_events_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+		ret = dyn_events_release_all(&synth_event_ops);
+		if (ret < 0)
+			return ret;
+	}
+
+	return seq_open(file, &synth_events_seq_op);
+}
+
+static ssize_t synth_events_write(struct file *file,
+				  const char __user *buffer,
+				  size_t count, loff_t *ppos)
+{
+	return trace_parse_run_command(file, buffer, count, ppos,
+				       create_or_delete_synth_event);
+}
+
+static const struct file_operations synth_events_fops = {
+	.open           = synth_events_open,
+	.write		= synth_events_write,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = seq_release,
+};
+
+static __init int trace_events_synth_init(void)
+{
+	struct dentry *entry = NULL;
+	struct dentry *d_tracer;
+	int err = 0;
+
+	err = dyn_event_register(&synth_event_ops);
+	if (err) {
+		pr_warn("Could not register synth_event_ops\n");
+		return err;
+	}
+
+	d_tracer = tracing_init_dentry();
+	if (IS_ERR(d_tracer)) {
+		err = PTR_ERR(d_tracer);
+		goto err;
+	}
+
+	entry = tracefs_create_file("synthetic_events", 0644, d_tracer,
+				    NULL, &synth_events_fops);
+	if (!entry) {
+		err = -ENODEV;
+		goto err;
+	}
+
+	return err;
+ err:
+	pr_warn("Could not create tracefs 'synthetic_events' entry\n");
+
+	return err;
+}
+
+fs_initcall(trace_events_synth_init);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 3a74736da363..f725802160c0 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -216,11 +216,17 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
 
 int trigger_process_regex(struct trace_event_file *file, char *buff)
 {
-	char *command, *next = buff;
+	char *command, *next;
 	struct event_command *p;
 	int ret = -EINVAL;
 
+	next = buff = skip_spaces(buff);
 	command = strsep(&next, ": \t");
+	if (next) {
+		next = skip_spaces(next);
+		if (!*next)
+			next = NULL;
+	}
 	command = (command[0] != '!') ? command : command + 1;
 
 	mutex_lock(&trigger_cmd_mutex);
@@ -630,8 +636,14 @@ event_trigger_callback(struct event_command *cmd_ops,
 	int ret;
 
 	/* separate the trigger from the filter (t:n [if filter]) */
-	if (param && isdigit(param[0]))
+	if (param && isdigit(param[0])) {
 		trigger = strsep(&param, " \t");
+		if (param) {
+			param = skip_spaces(param);
+			if (!*param)
+				param = NULL;
+		}
+	}
 
 	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
 
@@ -1368,6 +1380,11 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 	trigger = strsep(&param, " \t");
 	if (!trigger)
 		return -EINVAL;
+	if (param) {
+		param = skip_spaces(param);
+		if (!*param)
+			param = NULL;
+	}
 
 	system = strsep(&trigger, ":");
 	if (!trigger)
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 77ce5a3b6773..70d3d0a09053 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -45,6 +45,9 @@ static int ftrace_event_register(struct trace_event_call *call,
 #undef __field_desc
 #define __field_desc(type, container, item)		type item;
 
+#undef __field_packed
+#define __field_packed(type, container, item)		type item;
+
 #undef __array
 #define __array(type, item, size)			type item[size];
 
@@ -85,6 +88,13 @@ static void __always_unused ____ftrace_check_##name(void)		\
 	.size = sizeof(_type), .align = __alignof__(_type),		\
 	is_signed_type(_type), .filter_type = _filter_type },
 
+
+#undef __field_ext_packed
+#define __field_ext_packed(_type, _item, _filter_type) {	\
+	.type = #_type, .name = #_item,				\
+	.size = sizeof(_type), .align = 1,			\
+	is_signed_type(_type), .filter_type = _filter_type },
+
 #undef __field
 #define __field(_type, _item) __field_ext(_type, _item, FILTER_OTHER)
 
@@ -94,6 +104,9 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #undef __field_desc
 #define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER)
 
+#undef __field_packed
+#define __field_packed(_type, _container, _item) __field_ext_packed(_type, _item, FILTER_OTHER)
+
 #undef __array
 #define __array(_type, _item, _len) {					\
 	.type = #_type"["__stringify(_len)"]", .name = #_item,		\
@@ -129,6 +142,9 @@ static struct trace_event_fields ftrace_event_fields_##name[] = {	\
 #undef __field_desc
 #define __field_desc(type, container, item)
 
+#undef __field_packed
+#define __field_packed(type, container, item)
+
 #undef __array
 #define __array(type, item, len)
 
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 8a4c8d5c2c98..dd4dff71d89a 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -42,7 +42,7 @@ static int allocate_ftrace_ops(struct trace_array *tr)
 	if (!ops)
 		return -ENOMEM;
 
-	/* Currently only the non stack verision is supported */
+	/* Currently only the non stack version is supported */
 	ops->func = function_trace_call;
 	ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID;
 
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index e2be7bb7ef7e..17873e5d0353 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -283,6 +283,7 @@ static bool disable_migrate;
 static void move_to_next_cpu(void)
 {
 	struct cpumask *current_mask = &save_cpumask;
+	struct trace_array *tr = hwlat_trace;
 	int next_cpu;
 
 	if (disable_migrate)
@@ -296,7 +297,7 @@ static void move_to_next_cpu(void)
 		goto disable;
 
 	get_online_cpus();
-	cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	next_cpu = cpumask_next(smp_processor_id(), current_mask);
 	put_online_cpus();
 
@@ -371,9 +372,8 @@ static int start_kthread(struct trace_array *tr)
 		return 0;
 
 	/* Just pick the first CPU on first iteration */
-	current_mask = &save_cpumask;
 	get_online_cpus();
-	cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	put_online_cpus();
 	next_cpu = cpumask_first(current_mask);
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 35989383ae11..aefb6065b508 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1202,35 +1202,41 @@ static const struct file_operations kprobe_profile_ops = {
 
 /* Return the length of string -- including null terminal byte */
 static nokprobe_inline int
+fetch_store_strlen_user(unsigned long addr)
+{
+	const void __user *uaddr =  (__force const void __user *)addr;
+
+	return strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
+}
+
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
 fetch_store_strlen(unsigned long addr)
 {
 	int ret, len = 0;
 	u8 c;
 
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	if (addr < TASK_SIZE)
+		return fetch_store_strlen_user(addr);
+#endif
+
 	do {
-		ret = probe_kernel_read(&c, (u8 *)addr + len, 1);
+		ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
 		len++;
 	} while (c && ret == 0 && len < MAX_STRING_SIZE);
 
 	return (ret < 0) ? ret : len;
 }
 
-/* Return the length of string -- including null terminal byte */
-static nokprobe_inline int
-fetch_store_strlen_user(unsigned long addr)
-{
-	const void __user *uaddr =  (__force const void __user *)addr;
-
-	return strnlen_unsafe_user(uaddr, MAX_STRING_SIZE);
-}
-
 /*
- * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max
- * length and relative data location.
+ * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf
+ * with max length and relative data location.
  */
 static nokprobe_inline int
-fetch_store_string(unsigned long addr, void *dest, void *base)
+fetch_store_string_user(unsigned long addr, void *dest, void *base)
 {
+	const void __user *uaddr =  (__force const void __user *)addr;
 	int maxlen = get_loc_len(*(u32 *)dest);
 	void *__dest;
 	long ret;
@@ -1240,11 +1246,7 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 
 	__dest = get_loc_data(dest, base);
 
-	/*
-	 * Try to get string again, since the string can be changed while
-	 * probing.
-	 */
-	ret = strncpy_from_unsafe(__dest, (void *)addr, maxlen);
+	ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
 	if (ret >= 0)
 		*(u32 *)dest = make_data_loc(ret, __dest - base);
 
@@ -1252,23 +1254,31 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 }
 
 /*
- * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf
- * with max length and relative data location.
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max
+ * length and relative data location.
  */
 static nokprobe_inline int
-fetch_store_string_user(unsigned long addr, void *dest, void *base)
+fetch_store_string(unsigned long addr, void *dest, void *base)
 {
-	const void __user *uaddr =  (__force const void __user *)addr;
 	int maxlen = get_loc_len(*(u32 *)dest);
 	void *__dest;
 	long ret;
 
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	if ((unsigned long)addr < TASK_SIZE)
+		return fetch_store_string_user(addr, dest, base);
+#endif
+
 	if (unlikely(!maxlen))
 		return -ENOMEM;
 
 	__dest = get_loc_data(dest, base);
 
-	ret = strncpy_from_unsafe_user(__dest, uaddr, maxlen);
+	/*
+	 * Try to get string again, since the string can be changed while
+	 * probing.
+	 */
+	ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
 	if (ret >= 0)
 		*(u32 *)dest = make_data_loc(ret, __dest - base);
 
@@ -1276,17 +1286,21 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base)
 }
 
 static nokprobe_inline int
-probe_mem_read(void *dest, void *src, size_t size)
+probe_mem_read_user(void *dest, void *src, size_t size)
 {
-	return probe_kernel_read(dest, src, size);
+	const void __user *uaddr =  (__force const void __user *)src;
+
+	return copy_from_user_nofault(dest, uaddr, size);
 }
 
 static nokprobe_inline int
-probe_mem_read_user(void *dest, void *src, size_t size)
+probe_mem_read(void *dest, void *src, size_t size)
 {
-	const void __user *uaddr =  (__force const void __user *)src;
-
-	return probe_user_read(dest, uaddr, size);
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	if ((unsigned long)src < TASK_SIZE)
+		return probe_mem_read_user(dest, src, size);
+#endif
+	return copy_from_kernel_nofault(dest, src, size);
 }
 
 /* Note that we don't verify it, since the code does not come from user space */
@@ -1629,7 +1643,7 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
 	if (perf_type_tracepoint)
 		tk = find_trace_kprobe(pevent, group);
 	else
-		tk = event->tp_event->data;
+		tk = trace_kprobe_primary_from_call(event->tp_event);
 	if (!tk)
 		return -EINVAL;
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 9a121e147102..000e9dc224c6 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -20,7 +20,7 @@ DECLARE_RWSEM(trace_event_sem);
 
 static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
-static int next_event_type = __TRACE_LAST_TYPE + 1;
+static int next_event_type = __TRACE_LAST_TYPE;
 
 enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter)
 {
@@ -393,7 +393,7 @@ static int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
 	if (mm) {
 		const struct vm_area_struct *vma;
 
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 		vma = find_vma(mm, ip);
 		if (vma) {
 			file = vma->vm_file;
@@ -405,7 +405,7 @@ static int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
 				trace_seq_printf(s, "[+0x%lx]",
 						 ip - vmstart);
 		}
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 	}
 	if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file))
 		trace_seq_printf(s, " <" IP_FMT ">", ip);
@@ -497,7 +497,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	trace_seq_printf(s, "%8.8s-%-5d %3d",
+	trace_seq_printf(s, "%8.8s-%-7d %3d",
 			 comm, entry->pid, cpu);
 
 	return trace_print_lat_fmt(s, entry);
@@ -588,15 +588,15 @@ int trace_print_context(struct trace_iterator *iter)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+	trace_seq_printf(s, "%16s-%-7d ", comm, entry->pid);
 
 	if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
 		unsigned int tgid = trace_find_tgid(entry->pid);
 
 		if (!tgid)
-			trace_seq_printf(s, "(-----) ");
+			trace_seq_printf(s, "(-------) ");
 		else
-			trace_seq_printf(s, "(%5d) ", tgid);
+			trace_seq_printf(s, "(%7d) ", tgid);
 	}
 
 	trace_seq_printf(s, "[%03d] ", iter->cpu);
@@ -636,7 +636,7 @@ int trace_print_lat_context(struct trace_iterator *iter)
 		trace_find_cmdline(entry->pid, comm);
 
 		trace_seq_printf(
-			s, "%16s %5d %3d %d %08x %08lx ",
+			s, "%16s %7d %3d %d %08x %08lx ",
 			comm, entry->pid, iter->cpu, entry->flags,
 			entry->preempt_count, iter->idx);
 	} else {
@@ -675,11 +675,11 @@ static LIST_HEAD(ftrace_event_list);
 static int trace_search_list(struct list_head **list)
 {
 	struct trace_event *e;
-	int last = __TRACE_LAST_TYPE;
+	int next = __TRACE_LAST_TYPE;
 
 	if (list_empty(&ftrace_event_list)) {
 		*list = &ftrace_event_list;
-		return last + 1;
+		return next;
 	}
 
 	/*
@@ -687,17 +687,17 @@ static int trace_search_list(struct list_head **list)
 	 * lets see if somebody freed one.
 	 */
 	list_for_each_entry(e, &ftrace_event_list, list) {
-		if (e->type != last + 1)
+		if (e->type != next)
 			break;
-		last++;
+		next++;
 	}
 
 	/* Did we used up all 65 thousand events??? */
-	if ((last + 1) > TRACE_EVENT_TYPE_MAX)
+	if (next > TRACE_EVENT_TYPE_MAX)
 		return 0;
 
 	*list = &e->list;
-	return last + 1;
+	return next;
 }
 
 void trace_event_read_lock(void)
@@ -917,7 +917,7 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
 	S = task_index_to_char(field->prev_state);
 	trace_find_cmdline(field->next_pid, comm);
 	trace_seq_printf(&iter->seq,
-			 " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
+			 " %7d:%3d:%c %s [%03d] %7d:%3d:%c %s\n",
 			 field->prev_pid,
 			 field->prev_prio,
 			 S, delim,
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index 4d8e99fdbbbe..f4938040c228 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -19,6 +19,24 @@
 /* Per-cpu variable to prevent redundant calls when IRQs already off */
 static DEFINE_PER_CPU(int, tracing_irq_cpu);
 
+/*
+ * Like trace_hardirqs_on() but without the lockdep invocation. This is
+ * used in the low level entry code where the ordering vs. RCU is important
+ * and lockdep uses a staged approach which splits the lockdep hardirq
+ * tracking into a RCU on and a RCU off section.
+ */
+void trace_hardirqs_on_prepare(void)
+{
+	if (this_cpu_read(tracing_irq_cpu)) {
+		if (!in_nmi())
+			trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1);
+		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
+		this_cpu_write(tracing_irq_cpu, 0);
+	}
+}
+EXPORT_SYMBOL(trace_hardirqs_on_prepare);
+NOKPROBE_SYMBOL(trace_hardirqs_on_prepare);
+
 void trace_hardirqs_on(void)
 {
 	if (this_cpu_read(tracing_irq_cpu)) {
@@ -28,21 +46,41 @@ void trace_hardirqs_on(void)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on);
 NOKPROBE_SYMBOL(trace_hardirqs_on);
 
-void trace_hardirqs_off(void)
+/*
+ * Like trace_hardirqs_off() but without the lockdep invocation. This is
+ * used in the low level entry code where the ordering vs. RCU is important
+ * and lockdep uses a staged approach which splits the lockdep hardirq
+ * tracking into a RCU on and a RCU off section.
+ */
+void trace_hardirqs_off_finish(void)
 {
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
 		if (!in_nmi())
-			trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+			trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1);
 	}
 
+}
+EXPORT_SYMBOL(trace_hardirqs_off_finish);
+NOKPROBE_SYMBOL(trace_hardirqs_off_finish);
+
+void trace_hardirqs_off(void)
+{
 	lockdep_hardirqs_off(CALLER_ADDR0);
+
+	if (!this_cpu_read(tracing_irq_cpu)) {
+		this_cpu_write(tracing_irq_cpu, 1);
+		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
+		if (!in_nmi())
+			trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+	}
 }
 EXPORT_SYMBOL(trace_hardirqs_off);
 NOKPROBE_SYMBOL(trace_hardirqs_off);
@@ -56,6 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
@@ -63,14 +102,14 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
 
 __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, caller_addr);
 		if (!in_nmi())
 			trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
 	}
-
-	lockdep_hardirqs_off(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_off_caller);
 NOKPROBE_SYMBOL(trace_hardirqs_off_caller);
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index ab8b6436d53f..d2867ccc6aca 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -639,8 +639,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 			ret = -EINVAL;
 			goto fail;
 		}
-		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) ||
-		     parg->count) {
+		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM ||
+		     code->op == FETCH_OP_DATA) || parg->count) {
 			/*
 			 * IMM, DATA and COMM is pointing actual address, those
 			 * must be kept, and if parg->count != 0, this is an
@@ -1006,7 +1006,7 @@ int trace_probe_init(struct trace_probe *tp, const char *event,
 	INIT_LIST_HEAD(&tp->event->class.fields);
 	INIT_LIST_HEAD(&tp->event->probes);
 	INIT_LIST_HEAD(&tp->list);
-	list_add(&tp->event->probes, &tp->list);
+	list_add(&tp->list, &tp->event->probes);
 
 	call = trace_probe_event_call(tp);
 	call->class = &tp->event->class;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index a0ff9e200ef6..a22b62813f8c 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -236,7 +236,7 @@ struct trace_probe_event {
 	struct trace_event_call		call;
 	struct list_head 		files;
 	struct list_head		probes;
-	struct trace_uprobe_filter	filter[0];
+	struct trace_uprobe_filter	filter[];
 };
 
 struct trace_probe {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index c557f42a9397..98bba4764c52 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -515,9 +515,8 @@ static const struct file_operations stack_trace_filter_fops = {
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 int
-stack_trace_sysctl(struct ctl_table *table, int write,
-		   void __user *buffer, size_t *lenp,
-		   loff_t *ppos)
+stack_trace_sysctl(struct ctl_table *table, int write, void *buffer,
+		   size_t *lenp, loff_t *ppos)
 {
 	int was_enabled;
 	int ret;
diff --git a/kernel/trace/trace_synth.h b/kernel/trace/trace_synth.h
new file mode 100644
index 000000000000..ac35c45207c4
--- /dev/null
+++ b/kernel/trace/trace_synth.h
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __TRACE_SYNTH_H
+#define __TRACE_SYNTH_H
+
+#include "trace_dynevent.h"
+
+#define SYNTH_SYSTEM		"synthetic"
+#define SYNTH_FIELDS_MAX	32
+
+#define STR_VAR_LEN_MAX		32 /* must be multiple of sizeof(u64) */
+
+struct synth_field {
+	char *type;
+	char *name;
+	size_t size;
+	unsigned int offset;
+	bool is_signed;
+	bool is_string;
+};
+
+struct synth_event {
+	struct dyn_event			devent;
+	int					ref;
+	char					*name;
+	struct synth_field			**fields;
+	unsigned int				n_fields;
+	unsigned int				n_u64;
+	struct trace_event_class		class;
+	struct trace_event_call			call;
+	struct tracepoint			*tp;
+	struct module				*mod;
+};
+
+extern struct synth_event *find_synth_event(const char *name);
+
+#endif /* __TRACE_SYNTH_H */
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 2a8e8e9c1c75..f4286c9bdeb4 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1412,7 +1412,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
 	if (perf_type_tracepoint)
 		tu = find_probe_event(pevent, group);
 	else
-		tu = event->tp_event->data;
+		tu = trace_uprobe_primary_from_call(event->tp_event);
 	if (!tu)
 		return -EINVAL;
 
@@ -1456,7 +1456,6 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type,
 	default:
 		return 0;
 	}
-	return 0;
 }
 
 static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)