Merge branch 'main' into zstd-linus

51 files changed, 7896 insertions, 1382 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a5eb5e7fd624..e9e95c790b8e 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -10,6 +10,17 @@ config USER_STACKTRACE_SUPPORT
 config NOP_TRACER
 	bool
 
+config HAVE_RETHOOK
+	bool
+
+config RETHOOK
+	bool
+	depends on HAVE_RETHOOK
+	help
+	  Enable generic return hooking feature. This is an internal
+	  API, which will be used by other function-entry hooking
+	  features like fprobe and kprobes.
+
 config HAVE_FUNCTION_TRACER
 	bool
 	help
@@ -40,6 +51,12 @@ config HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	 This allows for use of regs_get_kernel_argument() and
 	 kernel_stack_pointer().
 
+config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
+	bool
+	help
+	  If the architecture generates __patchable_function_entries sections
+	  but does not want them included in the ftrace locations.
+
 config HAVE_FTRACE_MCOUNT_RECORD
 	bool
 	help
@@ -133,6 +150,7 @@ config TRACING
 	select BINARY_PRINTF
 	select EVENT_TRACING
 	select TRACE_CLOCK
+	select TASKS_RCU if PREEMPTION
 
 config GENERIC_TRACER
 	bool
@@ -182,7 +200,8 @@ config FUNCTION_TRACER
 	  sequence is then dynamically patched into a tracer call when
 	  tracing is enabled by the administrator. If it's runtime disabled
 	  (the bootup default), then the overhead of the instructions is very
-	  small and not measurable even in micro-benchmarks.
+	  small and not measurable even in micro-benchmarks (at least on
+	  x86, but may have impact on other architectures).
 
 config FUNCTION_GRAPH_TRACER
 	bool "Kernel Function Graph Tracer"
@@ -236,6 +255,21 @@ config DYNAMIC_FTRACE_WITH_ARGS
 	depends on DYNAMIC_FTRACE
 	depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
+config FPROBE
+	bool "Kernel Function Probe (fprobe)"
+	depends on FUNCTION_TRACER
+	depends on DYNAMIC_FTRACE_WITH_REGS
+	depends on HAVE_RETHOOK
+	select RETHOOK
+	default n
+	help
+	  This option enables kernel function probe (fprobe) based on ftrace.
+	  The fprobe is similar to kprobes, but probes only for kernel function
+	  entries and exits. This also can probe multiple functions by one
+	  fprobe.
+
+	  If unsure, say N.
+
 config FUNCTION_PROFILER
 	bool "Kernel function profiler"
 	depends on FUNCTION_TRACER
@@ -702,6 +736,7 @@ config FTRACE_MCOUNT_USE_OBJTOOL
 	depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
 	depends on !FTRACE_MCOUNT_USE_CC
 	depends on FTRACE_MCOUNT_RECORD
+	select OBJTOOL
 
 config FTRACE_MCOUNT_USE_RECORDMCOUNT
 	def_bool y
@@ -737,6 +772,21 @@ config SYNTH_EVENTS
 
 	  If in doubt, say N.
 
+config USER_EVENTS
+	bool "User trace events"
+	select TRACING
+	select DYNAMIC_EVENTS
+	depends on BROKEN || COMPILE_TEST # API needs to be straighten out
+	help
+	  User trace events are user-defined trace events that
+	  can be used like an existing kernel trace event.  User trace
+	  events are generated by writing to a tracefs file.  User
+	  processes can determine if their tracing events should be
+	  generated by memory mapping a tracefs file and checking for
+	  an associated byte being non-zero.
+
+	  If in doubt, say N.
+
 config HIST_TRIGGERS
 	bool "Histogram triggers"
 	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
@@ -1062,4 +1112,6 @@ config HIST_TRIGGERS_DEBUG
 
           If unsure, say N.
 
+source "kernel/trace/rv/Kconfig"
+
 endif # FTRACE
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index bedc5caceec7..c6651e16b557 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -31,6 +31,10 @@ ifdef CONFIG_GCOV_PROFILE_FTRACE
 GCOV_PROFILE := y
 endif
 
+# Functions in this file could be invoked from early interrupt
+# code and produce random code coverage.
+KCOV_INSTRUMENT_trace_preemptirq.o := n
+
 CFLAGS_bpf_trace.o := -I$(src)
 
 CFLAGS_trace_benchmark.o := -I$(src)
@@ -82,6 +86,7 @@ obj-$(CONFIG_PROBE_EVENTS) += trace_eprobe.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_USER_EVENTS) += trace_events_user.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
 obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o
@@ -97,7 +102,10 @@ obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
 obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
 obj-$(CONFIG_BOOTTIME_TRACING) += trace_boot.o
 obj-$(CONFIG_FTRACE_RECORD_RECURSION) += trace_recursion_record.o
+obj-$(CONFIG_FPROBE) += fprobe.o
+obj-$(CONFIG_RETHOOK) += rethook.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
+obj-$(CONFIG_RV) += rv/
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index af68a67179b4..a995ea1ef849 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -145,13 +145,14 @@ static void trace_note_time(struct blk_trace *bt)
 	local_irq_restore(flags);
 }
 
-void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg,
-	const char *fmt, ...)
+void __blk_trace_note_message(struct blk_trace *bt,
+		struct cgroup_subsys_state *css, const char *fmt, ...)
 {
 	int n;
 	va_list args;
 	unsigned long flags;
 	char *buf;
+	u64 cgid = 0;
 
 	if (unlikely(bt->trace_state != Blktrace_running &&
 		     !blk_tracer_enabled))
@@ -170,17 +171,16 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg,
 	n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
 	va_end(args);
 
-	if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
-		blkcg = NULL;
 #ifdef CONFIG_BLK_CGROUP
-	trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n,
-		   blkcg ? cgroup_id(blkcg->css.cgroup) : 1);
-#else
-	trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, 0);
+	if (css && (blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
+		cgid = cgroup_id(css->cgroup);
+	else
+		cgid = 1;
 #endif
+	trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, cgid);
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(__trace_note_message);
+EXPORT_SYMBOL_GPL(__blk_trace_note_message);
 
 static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
 			 pid_t pid)
@@ -205,7 +205,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
 #define BLK_TC_PREFLUSH		BLK_TC_FLUSH
 
 /* The ilog2() calls fall out because they're constant */
-#define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \
+#define MASK_TC_BIT(rw, __name) ((__force u32)(rw & REQ_ ## __name) <<	\
 	  (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name))
 
 /*
@@ -213,8 +213,8 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
  * blk_io_trace structure and places it in a per-cpu subbuffer.
  */
 static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
-		     int op, int op_flags, u32 what, int error, int pdu_len,
-		     void *pdu_data, u64 cgid)
+			    const blk_opf_t opf, u32 what, int error,
+			    int pdu_len, void *pdu_data, u64 cgid)
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
@@ -227,16 +227,17 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	int cpu;
 	bool blk_tracer = blk_tracer_enabled;
 	ssize_t cgid_len = cgid ? sizeof(cgid) : 0;
+	const enum req_op op = opf & REQ_OP_MASK;
 
 	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
 		return;
 
 	what |= ddir_act[op_is_write(op) ? WRITE : READ];
-	what |= MASK_TC_BIT(op_flags, SYNC);
-	what |= MASK_TC_BIT(op_flags, RAHEAD);
-	what |= MASK_TC_BIT(op_flags, META);
-	what |= MASK_TC_BIT(op_flags, PREFLUSH);
-	what |= MASK_TC_BIT(op_flags, FUA);
+	what |= MASK_TC_BIT(opf, SYNC);
+	what |= MASK_TC_BIT(opf, RAHEAD);
+	what |= MASK_TC_BIT(opf, META);
+	what |= MASK_TC_BIT(opf, PREFLUSH);
+	what |= MASK_TC_BIT(opf, FUA);
 	if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
 		what |= BLK_TC_ACT(BLK_TC_DISCARD);
 	if (op == REQ_OP_FLUSH)
@@ -310,10 +311,20 @@ record_it:
 	local_irq_restore(flags);
 }
 
-static void blk_trace_free(struct blk_trace *bt)
+static void blk_trace_free(struct request_queue *q, struct blk_trace *bt)
 {
 	relay_close(bt->rchan);
-	debugfs_remove(bt->dir);
+
+	/*
+	 * If 'bt->dir' is not set, then both 'dropped' and 'msg' are created
+	 * under 'q->debugfs_dir', thus lookup and remove them.
+	 */
+	if (!bt->dir) {
+		debugfs_remove(debugfs_lookup("dropped", q->debugfs_dir));
+		debugfs_remove(debugfs_lookup("msg", q->debugfs_dir));
+	} else {
+		debugfs_remove(bt->dir);
+	}
 	free_percpu(bt->sequence);
 	free_percpu(bt->msg_data);
 	kfree(bt);
@@ -335,10 +346,42 @@ static void put_probe_ref(void)
 	mutex_unlock(&blk_probe_mutex);
 }
 
-static void blk_trace_cleanup(struct blk_trace *bt)
+static int blk_trace_start(struct blk_trace *bt)
+{
+	if (bt->trace_state != Blktrace_setup &&
+	    bt->trace_state != Blktrace_stopped)
+		return -EINVAL;
+
+	blktrace_seq++;
+	smp_mb();
+	bt->trace_state = Blktrace_running;
+	raw_spin_lock_irq(&running_trace_lock);
+	list_add(&bt->running_list, &running_trace_list);
+	raw_spin_unlock_irq(&running_trace_lock);
+	trace_note_time(bt);
+
+	return 0;
+}
+
+static int blk_trace_stop(struct blk_trace *bt)
+{
+	if (bt->trace_state != Blktrace_running)
+		return -EINVAL;
+
+	bt->trace_state = Blktrace_stopped;
+	raw_spin_lock_irq(&running_trace_lock);
+	list_del_init(&bt->running_list);
+	raw_spin_unlock_irq(&running_trace_lock);
+	relay_flush(bt->rchan);
+
+	return 0;
+}
+
+static void blk_trace_cleanup(struct request_queue *q, struct blk_trace *bt)
 {
+	blk_trace_stop(bt);
 	synchronize_rcu();
-	blk_trace_free(bt);
+	blk_trace_free(q, bt);
 	put_probe_ref();
 }
 
@@ -351,8 +394,7 @@ static int __blk_trace_remove(struct request_queue *q)
 	if (!bt)
 		return -EINVAL;
 
-	if (bt->trace_state != Blktrace_running)
-		blk_trace_cleanup(bt);
+	blk_trace_cleanup(q, bt);
 
 	return 0;
 }
@@ -401,7 +443,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
 		return PTR_ERR(msg);
 
 	bt = filp->private_data;
-	__trace_note_message(bt, NULL, "%s", msg);
+	__blk_trace_note_message(bt, NULL, "%s", msg);
 	kfree(msg);
 
 	return count;
@@ -572,7 +614,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	ret = 0;
 err:
 	if (ret)
-		blk_trace_free(bt);
+		blk_trace_free(q, bt);
 	return ret;
 }
 
@@ -647,7 +689,6 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
 
 static int __blk_trace_startstop(struct request_queue *q, int start)
 {
-	int ret;
 	struct blk_trace *bt;
 
 	bt = rcu_dereference_protected(q->blk_trace,
@@ -655,36 +696,10 @@ static int __blk_trace_startstop(struct request_queue *q, int start)
 	if (bt == NULL)
 		return -EINVAL;
 
-	/*
-	 * For starting a trace, we can transition from a setup or stopped
-	 * trace. For stopping a trace, the state must be running
-	 */
-	ret = -EINVAL;
-	if (start) {
-		if (bt->trace_state == Blktrace_setup ||
-		    bt->trace_state == Blktrace_stopped) {
-			blktrace_seq++;
-			smp_mb();
-			bt->trace_state = Blktrace_running;
-			raw_spin_lock_irq(&running_trace_lock);
-			list_add(&bt->running_list, &running_trace_list);
-			raw_spin_unlock_irq(&running_trace_lock);
-
-			trace_note_time(bt);
-			ret = 0;
-		}
-	} else {
-		if (bt->trace_state == Blktrace_running) {
-			bt->trace_state = Blktrace_stopped;
-			raw_spin_lock_irq(&running_trace_lock);
-			list_del_init(&bt->running_list);
-			raw_spin_unlock_irq(&running_trace_lock);
-			relay_flush(bt->rchan);
-			ret = 0;
-		}
-	}
-
-	return ret;
+	if (start)
+		return blk_trace_start(bt);
+	else
+		return blk_trace_stop(bt);
 }
 
 int blk_trace_startstop(struct request_queue *q, int start)
@@ -726,12 +741,12 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 
 	switch (cmd) {
 	case BLKTRACESETUP:
-		bdevname(bdev, b);
+		snprintf(b, sizeof(b), "%pg", bdev);
 		ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
 #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
 	case BLKTRACESETUP32:
-		bdevname(bdev, b);
+		snprintf(b, sizeof(b), "%pg", bdev);
 		ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
 #endif
@@ -760,19 +775,15 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
  **/
 void blk_trace_shutdown(struct request_queue *q)
 {
-	mutex_lock(&q->debugfs_mutex);
 	if (rcu_dereference_protected(q->blk_trace,
-				      lockdep_is_held(&q->debugfs_mutex))) {
-		__blk_trace_startstop(q, 0);
+				      lockdep_is_held(&q->debugfs_mutex)))
 		__blk_trace_remove(q);
-	}
-
-	mutex_unlock(&q->debugfs_mutex);
 }
 
 #ifdef CONFIG_BLK_CGROUP
 static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 {
+	struct cgroup_subsys_state *blkcg_css;
 	struct blk_trace *bt;
 
 	/* We don't use the 'bt' value here except as an optimization... */
@@ -780,9 +791,10 @@ static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 	if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
 		return 0;
 
-	if (!bio->bi_blkg)
+	blkcg_css = bio_blkcg_css(bio);
+	if (!blkcg_css)
 		return 0;
-	return cgroup_id(bio_blkcg(bio)->css.cgroup);
+	return cgroup_id(blkcg_css->cgroup);
 }
 #else
 static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
@@ -833,9 +845,8 @@ static void blk_add_trace_rq(struct request *rq, blk_status_t error,
 	else
 		what |= BLK_TC_ACT(BLK_TC_FS);
 
-	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
-			rq->cmd_flags, what, blk_status_to_errno(error), 0,
-			NULL, cgid);
+	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, rq->cmd_flags,
+			what, blk_status_to_errno(error), 0, NULL, cgid);
 	rcu_read_unlock();
 }
 
@@ -894,7 +905,7 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
 	}
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio_op(bio), bio->bi_opf, what, error, 0, NULL,
+			bio->bi_opf, what, error, 0, NULL,
 			blk_trace_bio_get_cgid(q, bio));
 	rcu_read_unlock();
 }
@@ -940,7 +951,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q)
 	rcu_read_lock();
 	bt = rcu_dereference(q->blk_trace);
 	if (bt)
-		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
+		__blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
 	rcu_read_unlock();
 }
 
@@ -960,7 +971,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 		else
 			what = BLK_TA_UNPLUG_TIMER;
 
-		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
+		__blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
 	}
 	rcu_read_unlock();
 }
@@ -976,8 +987,7 @@ static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu)
 		__be64 rpdu = cpu_to_be64(pdu);
 
 		__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_iter.bi_size, bio->bi_opf, BLK_TA_SPLIT,
 				blk_status_to_errno(bio->bi_status),
 				sizeof(rpdu), &rpdu,
 				blk_trace_bio_get_cgid(q, bio));
@@ -1013,7 +1023,7 @@ static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev,
 	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_opf, BLK_TA_REMAP,
 			blk_status_to_errno(bio->bi_status),
 			sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
 	rcu_read_unlock();
@@ -1049,7 +1059,7 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
-			rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
+			rq->cmd_flags, BLK_TA_REMAP, 0,
 			sizeof(r), &r, blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
 }
@@ -1075,7 +1085,7 @@ void blk_add_driver_data(struct request *rq, void *data, size_t len)
 		return;
 	}
 
-	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
+	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0,
 				BLK_TA_DRV_DATA, 0, len, data,
 				blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
@@ -1606,17 +1616,11 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (bt == NULL)
 		return -EINVAL;
 
-	if (bt->trace_state == Blktrace_running) {
-		bt->trace_state = Blktrace_stopped;
-		raw_spin_lock_irq(&running_trace_lock);
-		list_del_init(&bt->running_list);
-		raw_spin_unlock_irq(&running_trace_lock);
-		relay_flush(bt->rchan);
-	}
+	blk_trace_stop(bt);
 
 	put_probe_ref();
 	synchronize_rcu();
-	blk_trace_free(bt);
+	blk_trace_free(q, bt);
 	return 0;
 }
 
@@ -1647,7 +1651,7 @@ static int blk_trace_setup_queue(struct request_queue *q,
 	return 0;
 
 free_bt:
-	blk_trace_free(bt);
+	blk_trace_free(q, bt);
 	return ret;
 }
 
@@ -1858,17 +1862,6 @@ out_unlock_bdev:
 out:
 	return ret ? ret : count;
 }
-
-int blk_trace_init_sysfs(struct device *dev)
-{
-	return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
-}
-
-void blk_trace_remove_sysfs(struct device *dev)
-{
-	sysfs_remove_group(&dev->kobj, &blk_trace_attr_group);
-}
-
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #ifdef CONFIG_EVENT_TRACING
@@ -1876,23 +1869,22 @@ void blk_trace_remove_sysfs(struct device *dev)
 /**
  * blk_fill_rwbs - Fill the buffer rwbs by mapping op to character string.
  * @rwbs:	buffer to be filled
- * @op:		REQ_OP_XXX for the tracepoint
+ * @opf:	request operation type (REQ_OP_XXX) and flags for the tracepoint
  *
  * Description:
- *     Maps the REQ_OP_XXX to character and fills the buffer provided by the
- *     caller with resulting string.
+ *     Maps each request operation and flag to a single character and fills the
+ *     buffer provided by the caller with resulting string.
  *
  **/
-void blk_fill_rwbs(char *rwbs, unsigned int op)
+void blk_fill_rwbs(char *rwbs, blk_opf_t opf)
 {
 	int i = 0;
 
-	if (op & REQ_PREFLUSH)
+	if (opf & REQ_PREFLUSH)
 		rwbs[i++] = 'F';
 
-	switch (op & REQ_OP_MASK) {
+	switch (opf & REQ_OP_MASK) {
 	case REQ_OP_WRITE:
-	case REQ_OP_WRITE_SAME:
 		rwbs[i++] = 'W';
 		break;
 	case REQ_OP_DISCARD:
@@ -1912,13 +1904,13 @@ void blk_fill_rwbs(char *rwbs, unsigned int op)
 		rwbs[i++] = 'N';
 	}
 
-	if (op & REQ_FUA)
+	if (opf & REQ_FUA)
 		rwbs[i++] = 'F';
-	if (op & REQ_RAHEAD)
+	if (opf & REQ_RAHEAD)
 		rwbs[i++] = 'A';
-	if (op & REQ_SYNC)
+	if (opf & REQ_SYNC)
 		rwbs[i++] = 'S';
-	if (op & REQ_META)
+	if (opf & REQ_META)
 		rwbs[i++] = 'M';
 
 	rwbs[i] = '\0';
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 21aa30644219..1ed08967fb97 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -17,6 +17,11 @@
 #include <linux/error-injection.h>
 #include <linux/btf_ids.h>
 #include <linux/bpf_lsm.h>
+#include <linux/fprobe.h>
+#include <linux/bsearch.h>
+#include <linux/sort.h>
+#include <linux/key.h>
+#include <linux/verification.h>
 
 #include <net/bpf_sk_storage.h>
 
@@ -77,6 +82,8 @@ u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
 				  u64 flags, const struct btf **btf,
 				  s32 *btf_id);
+static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx);
+static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx);
 
 /**
  * trace_call_bpf - invoke BPF program
@@ -124,7 +131,10 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 	 * out of events when it was updated in between this and the
 	 * rcu_dereference() which is accepted risk.
 	 */
-	ret = BPF_PROG_RUN_ARRAY(call->prog_array, ctx, bpf_prog_run);
+	rcu_read_lock();
+	ret = bpf_prog_run_array(rcu_dereference(call->prog_array),
+				 ctx, bpf_prog_run);
+	rcu_read_unlock();
 
  out:
 	__this_cpu_dec(bpf_prog_active);
@@ -332,8 +342,6 @@ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
 	if (unlikely(in_interrupt() ||
 		     current->flags & (PF_KTHREAD | PF_EXITING)))
 		return -EPERM;
-	if (unlikely(uaccess_kernel()))
-		return -EPERM;
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
 
@@ -679,6 +687,7 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 
 	perf_sample_data_init(sd, 0, 0);
 	sd->raw = &raw;
+	sd->sample_flags |= PERF_SAMPLE_RAW;
 
 	err = __bpf_perf_event_output(regs, map, flags, sd);
 
@@ -737,6 +746,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 	perf_fetch_caller_regs(regs);
 	perf_sample_data_init(sd, 0, 0);
 	sd->raw = &raw;
+	sd->sample_flags |= PERF_SAMPLE_RAW;
 
 	ret = __bpf_perf_event_output(regs, map, flags, sd);
 out:
@@ -835,8 +845,6 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
 	 */
 	if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING)))
 		return -EPERM;
-	if (unlikely(uaccess_kernel()))
-		return -EPERM;
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
 
@@ -1022,11 +1030,30 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+#ifdef CONFIG_X86_KERNEL_IBT
+static unsigned long get_entry_ip(unsigned long fentry_ip)
+{
+	u32 instr;
+
+	/* Being extra safe in here in case entry ip is on the page-edge. */
+	if (get_kernel_nofault(instr, (u32 *) fentry_ip - 1))
+		return fentry_ip;
+	if (is_endbr(instr))
+		fentry_ip -= ENDBR_INSN_SIZE;
+	return fentry_ip;
+}
+#else
+#define get_entry_ip(fentry_ip) fentry_ip
+#endif
+
 BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs)
 {
 	struct kprobe *kp = kprobe_running();
 
-	return kp ? (uintptr_t)kp->addr : 0;
+	if (!kp || !(kp->flags & KPROBE_FLAG_ON_FUNC_ENTRY))
+		return 0;
+
+	return get_entry_ip((uintptr_t)kp->addr);
 }
 
 static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe = {
@@ -1036,6 +1063,30 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_1(bpf_get_func_ip_kprobe_multi, struct pt_regs *, regs)
+{
+	return bpf_kprobe_multi_entry_ip(current->bpf_ctx);
+}
+
+static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe_multi = {
+	.func		= bpf_get_func_ip_kprobe_multi,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_attach_cookie_kprobe_multi, struct pt_regs *, regs)
+{
+	return bpf_kprobe_multi_cookie(current->bpf_ctx);
+}
+
+static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = {
+	.func		= bpf_get_attach_cookie_kprobe_multi,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx)
 {
 	struct bpf_trace_run_ctx *run_ctx;
@@ -1063,6 +1114,21 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_1(bpf_get_attach_cookie_tracing, void *, ctx)
+{
+	struct bpf_trace_run_ctx *run_ctx;
+
+	run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx);
+	return run_ctx->bpf_cookie;
+}
+
+static const struct bpf_func_proto bpf_get_attach_cookie_proto_tracing = {
+	.func		= bpf_get_attach_cookie_tracing,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags)
 {
 #ifndef CONFIG_X86
@@ -1138,6 +1204,184 @@ static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+#ifdef CONFIG_KEYS
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "kfuncs which will be used in BPF programs");
+
+/**
+ * bpf_lookup_user_key - lookup a key by its serial
+ * @serial: key handle serial number
+ * @flags: lookup-specific flags
+ *
+ * Search a key with a given *serial* and the provided *flags*.
+ * If found, increment the reference count of the key by one, and
+ * return it in the bpf_key structure.
+ *
+ * The bpf_key structure must be passed to bpf_key_put() when done
+ * with it, so that the key reference count is decremented and the
+ * bpf_key structure is freed.
+ *
+ * Permission checks are deferred to the time the key is used by
+ * one of the available key-specific kfuncs.
+ *
+ * Set *flags* with KEY_LOOKUP_CREATE, to attempt creating a requested
+ * special keyring (e.g. session keyring), if it doesn't yet exist.
+ * Set *flags* with KEY_LOOKUP_PARTIAL, to lookup a key without waiting
+ * for the key construction, and to retrieve uninstantiated keys (keys
+ * without data attached to them).
+ *
+ * Return: a bpf_key pointer with a valid key pointer if the key is found, a
+ *         NULL pointer otherwise.
+ */
+struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags)
+{
+	key_ref_t key_ref;
+	struct bpf_key *bkey;
+
+	if (flags & ~KEY_LOOKUP_ALL)
+		return NULL;
+
+	/*
+	 * Permission check is deferred until the key is used, as the
+	 * intent of the caller is unknown here.
+	 */
+	key_ref = lookup_user_key(serial, flags, KEY_DEFER_PERM_CHECK);
+	if (IS_ERR(key_ref))
+		return NULL;
+
+	bkey = kmalloc(sizeof(*bkey), GFP_KERNEL);
+	if (!bkey) {
+		key_put(key_ref_to_ptr(key_ref));
+		return NULL;
+	}
+
+	bkey->key = key_ref_to_ptr(key_ref);
+	bkey->has_ref = true;
+
+	return bkey;
+}
+
+/**
+ * bpf_lookup_system_key - lookup a key by a system-defined ID
+ * @id: key ID
+ *
+ * Obtain a bpf_key structure with a key pointer set to the passed key ID.
+ * The key pointer is marked as invalid, to prevent bpf_key_put() from
+ * attempting to decrement the key reference count on that pointer. The key
+ * pointer set in such way is currently understood only by
+ * verify_pkcs7_signature().
+ *
+ * Set *id* to one of the values defined in include/linux/verification.h:
+ * 0 for the primary keyring (immutable keyring of system keys);
+ * VERIFY_USE_SECONDARY_KEYRING for both the primary and secondary keyring
+ * (where keys can be added only if they are vouched for by existing keys
+ * in those keyrings); VERIFY_USE_PLATFORM_KEYRING for the platform
+ * keyring (primarily used by the integrity subsystem to verify a kexec'ed
+ * kerned image and, possibly, the initramfs signature).
+ *
+ * Return: a bpf_key pointer with an invalid key pointer set from the
+ *         pre-determined ID on success, a NULL pointer otherwise
+ */
+struct bpf_key *bpf_lookup_system_key(u64 id)
+{
+	struct bpf_key *bkey;
+
+	if (system_keyring_id_check(id) < 0)
+		return NULL;
+
+	bkey = kmalloc(sizeof(*bkey), GFP_ATOMIC);
+	if (!bkey)
+		return NULL;
+
+	bkey->key = (struct key *)(unsigned long)id;
+	bkey->has_ref = false;
+
+	return bkey;
+}
+
+/**
+ * bpf_key_put - decrement key reference count if key is valid and free bpf_key
+ * @bkey: bpf_key structure
+ *
+ * Decrement the reference count of the key inside *bkey*, if the pointer
+ * is valid, and free *bkey*.
+ */
+void bpf_key_put(struct bpf_key *bkey)
+{
+	if (bkey->has_ref)
+		key_put(bkey->key);
+
+	kfree(bkey);
+}
+
+#ifdef CONFIG_SYSTEM_DATA_VERIFICATION
+/**
+ * bpf_verify_pkcs7_signature - verify a PKCS#7 signature
+ * @data_ptr: data to verify
+ * @sig_ptr: signature of the data
+ * @trusted_keyring: keyring with keys trusted for signature verification
+ *
+ * Verify the PKCS#7 signature *sig_ptr* against the supplied *data_ptr*
+ * with keys in a keyring referenced by *trusted_keyring*.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
+			       struct bpf_dynptr_kern *sig_ptr,
+			       struct bpf_key *trusted_keyring)
+{
+	int ret;
+
+	if (trusted_keyring->has_ref) {
+		/*
+		 * Do the permission check deferred in bpf_lookup_user_key().
+		 * See bpf_lookup_user_key() for more details.
+		 *
+		 * A call to key_task_permission() here would be redundant, as
+		 * it is already done by keyring_search() called by
+		 * find_asymmetric_key().
+		 */
+		ret = key_validate(trusted_keyring->key);
+		if (ret < 0)
+			return ret;
+	}
+
+	return verify_pkcs7_signature(data_ptr->data,
+				      bpf_dynptr_get_size(data_ptr),
+				      sig_ptr->data,
+				      bpf_dynptr_get_size(sig_ptr),
+				      trusted_keyring->key,
+				      VERIFYING_UNSPECIFIED_SIGNATURE, NULL,
+				      NULL);
+}
+#endif /* CONFIG_SYSTEM_DATA_VERIFICATION */
+
+__diag_pop();
+
+BTF_SET8_START(key_sig_kfunc_set)
+BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_lookup_system_key, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_key_put, KF_RELEASE)
+#ifdef CONFIG_SYSTEM_DATA_VERIFICATION
+BTF_ID_FLAGS(func, bpf_verify_pkcs7_signature, KF_SLEEPABLE)
+#endif
+BTF_SET8_END(key_sig_kfunc_set)
+
+static const struct btf_kfunc_id_set bpf_key_sig_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set = &key_sig_kfunc_set,
+};
+
+static int __init bpf_key_sig_kfuncs_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
+					 &bpf_key_sig_kfunc_set);
+}
+
+late_initcall(bpf_key_sig_kfuncs_init);
+#endif /* CONFIG_KEYS */
+
 static const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1154,6 +1398,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_map_pop_elem_proto;
 	case BPF_FUNC_map_peek_elem:
 		return &bpf_map_peek_elem_proto;
+	case BPF_FUNC_map_lookup_percpu_elem:
+		return &bpf_map_lookup_percpu_elem_proto;
 	case BPF_FUNC_ktime_get_ns:
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
@@ -1235,6 +1481,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_task_stack_proto;
 	case BPF_FUNC_copy_from_user:
 		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
+	case BPF_FUNC_copy_from_user_task:
+		return prog->aux->sleepable ? &bpf_copy_from_user_task_proto : NULL;
 	case BPF_FUNC_snprintf_btf:
 		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_per_cpu_ptr:
@@ -1277,9 +1525,13 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_override_return_proto;
 #endif
 	case BPF_FUNC_get_func_ip:
-		return &bpf_get_func_ip_proto_kprobe;
+		return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
+			&bpf_get_func_ip_proto_kprobe_multi :
+			&bpf_get_func_ip_proto_kprobe;
 	case BPF_FUNC_get_attach_cookie:
-		return &bpf_get_attach_cookie_proto_trace;
+		return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
+			&bpf_get_attach_cookie_proto_kmulti :
+			&bpf_get_attach_cookie_proto_trace;
 	default:
 		return bpf_tracing_func_proto(func_id, prog);
 	}
@@ -1456,6 +1708,9 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
 	if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE))
 		return -EINVAL;
 
+	if (unlikely(!(ctx->data->sample_flags & PERF_SAMPLE_BRANCH_STACK)))
+		return -ENOENT;
+
 	if (unlikely(!br_stack))
 		return -ENOENT;
 
@@ -1562,6 +1817,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 
 extern const struct bpf_func_proto bpf_skb_output_proto;
 extern const struct bpf_func_proto bpf_xdp_output_proto;
+extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto;
 
 BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags)
@@ -1653,6 +1909,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_to_udp6_sock_proto;
 	case BPF_FUNC_skc_to_unix_sock:
 		return &bpf_skc_to_unix_sock_proto;
+	case BPF_FUNC_skc_to_mptcp_sock:
+		return &bpf_skc_to_mptcp_sock_proto;
 	case BPF_FUNC_sk_storage_get:
 		return &bpf_sk_storage_get_tracing_proto;
 	case BPF_FUNC_sk_storage_delete:
@@ -1661,6 +1919,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sock_from_file_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_ptr_cookie_proto;
+	case BPF_FUNC_xdp_get_buff_len:
+		return &bpf_xdp_get_buff_len_trace_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
@@ -1682,6 +1942,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL;
 	case BPF_FUNC_get_func_arg_cnt:
 		return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL;
+	case BPF_FUNC_get_attach_cookie:
+		return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto_tracing : NULL;
 	default:
 		fn = raw_tp_prog_func_proto(func_id, prog);
 		if (!fn && prog->expected_attach_type == BPF_TRACE_ITER)
@@ -1878,7 +2140,7 @@ int perf_event_attach_bpf_prog(struct perf_event *event,
 	event->prog = prog;
 	event->bpf_cookie = bpf_cookie;
 	rcu_assign_pointer(event->tp_event->prog_array, new_array);
-	bpf_prog_array_free(old_array);
+	bpf_prog_array_free_sleepable(old_array);
 
 unlock:
 	mutex_unlock(&bpf_event_mutex);
@@ -1904,7 +2166,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
 		bpf_prog_array_delete_safe(old_array, event->prog);
 	} else {
 		rcu_assign_pointer(event->tp_event->prog_array, new_array);
-		bpf_prog_array_free(old_array);
+		bpf_prog_array_free_sleepable(old_array);
 	}
 
 	bpf_prog_put(event->prog);
@@ -1984,9 +2246,15 @@ static __always_inline
 void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
 {
 	cant_sleep();
+	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
+		bpf_prog_inc_misses_counter(prog);
+		goto out;
+	}
 	rcu_read_lock();
 	(void) bpf_prog_run(prog, args);
 	rcu_read_unlock();
+out:
+	this_cpu_dec(*(prog->active));
 }
 
 #define UNPACK(...)			__VA_ARGS__
@@ -2176,3 +2444,362 @@ static int __init bpf_event_init(void)
 
 fs_initcall(bpf_event_init);
 #endif /* CONFIG_MODULES */
+
+#ifdef CONFIG_FPROBE
+struct bpf_kprobe_multi_link {
+	struct bpf_link link;
+	struct fprobe fp;
+	unsigned long *addrs;
+	u64 *cookies;
+	u32 cnt;
+};
+
+struct bpf_kprobe_multi_run_ctx {
+	struct bpf_run_ctx run_ctx;
+	struct bpf_kprobe_multi_link *link;
+	unsigned long entry_ip;
+};
+
+struct user_syms {
+	const char **syms;
+	char *buf;
+};
+
+static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt)
+{
+	unsigned long __user usymbol;
+	const char **syms = NULL;
+	char *buf = NULL, *p;
+	int err = -ENOMEM;
+	unsigned int i;
+
+	syms = kvmalloc_array(cnt, sizeof(*syms), GFP_KERNEL);
+	if (!syms)
+		goto error;
+
+	buf = kvmalloc_array(cnt, KSYM_NAME_LEN, GFP_KERNEL);
+	if (!buf)
+		goto error;
+
+	for (p = buf, i = 0; i < cnt; i++) {
+		if (__get_user(usymbol, usyms + i)) {
+			err = -EFAULT;
+			goto error;
+		}
+		err = strncpy_from_user(p, (const char __user *) usymbol, KSYM_NAME_LEN);
+		if (err == KSYM_NAME_LEN)
+			err = -E2BIG;
+		if (err < 0)
+			goto error;
+		syms[i] = p;
+		p += err + 1;
+	}
+
+	us->syms = syms;
+	us->buf = buf;
+	return 0;
+
+error:
+	if (err) {
+		kvfree(syms);
+		kvfree(buf);
+	}
+	return err;
+}
+
+static void free_user_syms(struct user_syms *us)
+{
+	kvfree(us->syms);
+	kvfree(us->buf);
+}
+
+static void bpf_kprobe_multi_link_release(struct bpf_link *link)
+{
+	struct bpf_kprobe_multi_link *kmulti_link;
+
+	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	unregister_fprobe(&kmulti_link->fp);
+}
+
+static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_kprobe_multi_link *kmulti_link;
+
+	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	kvfree(kmulti_link->addrs);
+	kvfree(kmulti_link->cookies);
+	kfree(kmulti_link);
+}
+
+static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
+	.release = bpf_kprobe_multi_link_release,
+	.dealloc = bpf_kprobe_multi_link_dealloc,
+};
+
+static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv)
+{
+	const struct bpf_kprobe_multi_link *link = priv;
+	unsigned long *addr_a = a, *addr_b = b;
+	u64 *cookie_a, *cookie_b;
+
+	cookie_a = link->cookies + (addr_a - link->addrs);
+	cookie_b = link->cookies + (addr_b - link->addrs);
+
+	/* swap addr_a/addr_b and cookie_a/cookie_b values */
+	swap(*addr_a, *addr_b);
+	swap(*cookie_a, *cookie_b);
+}
+
+static int __bpf_kprobe_multi_cookie_cmp(const void *a, const void *b)
+{
+	const unsigned long *addr_a = a, *addr_b = b;
+
+	if (*addr_a == *addr_b)
+		return 0;
+	return *addr_a < *addr_b ? -1 : 1;
+}
+
+static int bpf_kprobe_multi_cookie_cmp(const void *a, const void *b, const void *priv)
+{
+	return __bpf_kprobe_multi_cookie_cmp(a, b);
+}
+
+static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx)
+{
+	struct bpf_kprobe_multi_run_ctx *run_ctx;
+	struct bpf_kprobe_multi_link *link;
+	u64 *cookie, entry_ip;
+	unsigned long *addr;
+
+	if (WARN_ON_ONCE(!ctx))
+		return 0;
+	run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx);
+	link = run_ctx->link;
+	if (!link->cookies)
+		return 0;
+	entry_ip = run_ctx->entry_ip;
+	addr = bsearch(&entry_ip, link->addrs, link->cnt, sizeof(entry_ip),
+		       __bpf_kprobe_multi_cookie_cmp);
+	if (!addr)
+		return 0;
+	cookie = link->cookies + (addr - link->addrs);
+	return *cookie;
+}
+
+static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
+{
+	struct bpf_kprobe_multi_run_ctx *run_ctx;
+
+	run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx);
+	return run_ctx->entry_ip;
+}
+
+static int
+kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
+			   unsigned long entry_ip, struct pt_regs *regs)
+{
+	struct bpf_kprobe_multi_run_ctx run_ctx = {
+		.link = link,
+		.entry_ip = entry_ip,
+	};
+	struct bpf_run_ctx *old_run_ctx;
+	int err;
+
+	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
+		err = 0;
+		goto out;
+	}
+
+	migrate_disable();
+	rcu_read_lock();
+	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+	err = bpf_prog_run(link->link.prog, regs);
+	bpf_reset_run_ctx(old_run_ctx);
+	rcu_read_unlock();
+	migrate_enable();
+
+ out:
+	__this_cpu_dec(bpf_prog_active);
+	return err;
+}
+
+static void
+kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip,
+			  struct pt_regs *regs)
+{
+	struct bpf_kprobe_multi_link *link;
+
+	link = container_of(fp, struct bpf_kprobe_multi_link, fp);
+	kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs);
+}
+
+static int symbols_cmp_r(const void *a, const void *b, const void *priv)
+{
+	const char **str_a = (const char **) a;
+	const char **str_b = (const char **) b;
+
+	return strcmp(*str_a, *str_b);
+}
+
+struct multi_symbols_sort {
+	const char **funcs;
+	u64 *cookies;
+};
+
+static void symbols_swap_r(void *a, void *b, int size, const void *priv)
+{
+	const struct multi_symbols_sort *data = priv;
+	const char **name_a = a, **name_b = b;
+
+	swap(*name_a, *name_b);
+
+	/* If defined, swap also related cookies. */
+	if (data->cookies) {
+		u64 *cookie_a, *cookie_b;
+
+		cookie_a = data->cookies + (name_a - data->funcs);
+		cookie_b = data->cookies + (name_b - data->funcs);
+		swap(*cookie_a, *cookie_b);
+	}
+}
+
+int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_kprobe_multi_link *link = NULL;
+	struct bpf_link_primer link_primer;
+	void __user *ucookies;
+	unsigned long *addrs;
+	u32 flags, cnt, size;
+	void __user *uaddrs;
+	u64 *cookies = NULL;
+	void __user *usyms;
+	int err;
+
+	/* no support for 32bit archs yet */
+	if (sizeof(u64) != sizeof(void *))
+		return -EOPNOTSUPP;
+
+	if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI)
+		return -EINVAL;
+
+	flags = attr->link_create.kprobe_multi.flags;
+	if (flags & ~BPF_F_KPROBE_MULTI_RETURN)
+		return -EINVAL;
+
+	uaddrs = u64_to_user_ptr(attr->link_create.kprobe_multi.addrs);
+	usyms = u64_to_user_ptr(attr->link_create.kprobe_multi.syms);
+	if (!!uaddrs == !!usyms)
+		return -EINVAL;
+
+	cnt = attr->link_create.kprobe_multi.cnt;
+	if (!cnt)
+		return -EINVAL;
+
+	size = cnt * sizeof(*addrs);
+	addrs = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
+	if (!addrs)
+		return -ENOMEM;
+
+	ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies);
+	if (ucookies) {
+		cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
+		if (!cookies) {
+			err = -ENOMEM;
+			goto error;
+		}
+		if (copy_from_user(cookies, ucookies, size)) {
+			err = -EFAULT;
+			goto error;
+		}
+	}
+
+	if (uaddrs) {
+		if (copy_from_user(addrs, uaddrs, size)) {
+			err = -EFAULT;
+			goto error;
+		}
+	} else {
+		struct multi_symbols_sort data = {
+			.cookies = cookies,
+		};
+		struct user_syms us;
+
+		err = copy_user_syms(&us, usyms, cnt);
+		if (err)
+			goto error;
+
+		if (cookies)
+			data.funcs = us.syms;
+
+		sort_r(us.syms, cnt, sizeof(*us.syms), symbols_cmp_r,
+		       symbols_swap_r, &data);
+
+		err = ftrace_lookup_symbols(us.syms, cnt, addrs);
+		free_user_syms(&us);
+		if (err)
+			goto error;
+	}
+
+	link = kzalloc(sizeof(*link), GFP_KERNEL);
+	if (!link) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_KPROBE_MULTI,
+		      &bpf_kprobe_multi_link_lops, prog);
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err)
+		goto error;
+
+	if (flags & BPF_F_KPROBE_MULTI_RETURN)
+		link->fp.exit_handler = kprobe_multi_link_handler;
+	else
+		link->fp.entry_handler = kprobe_multi_link_handler;
+
+	link->addrs = addrs;
+	link->cookies = cookies;
+	link->cnt = cnt;
+
+	if (cookies) {
+		/*
+		 * Sorting addresses will trigger sorting cookies as well
+		 * (check bpf_kprobe_multi_cookie_swap). This way we can
+		 * find cookie based on the address in bpf_get_attach_cookie
+		 * helper.
+		 */
+		sort_r(addrs, cnt, sizeof(*addrs),
+		       bpf_kprobe_multi_cookie_cmp,
+		       bpf_kprobe_multi_cookie_swap,
+		       link);
+	}
+
+	err = register_fprobe_ips(&link->fp, addrs, cnt);
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		return err;
+	}
+
+	return bpf_link_settle(&link_primer);
+
+error:
+	kfree(link);
+	kvfree(addrs);
+	kvfree(cookies);
+	return err;
+}
+#else /* !CONFIG_FPROBE */
+int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
+static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx)
+{
+	return 0;
+}
+static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
+{
+	return 0;
+}
+#endif
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 22061d38fc00..218cd95bf8e4 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -7,6 +7,7 @@
  *
  * Highly modified by Steven Rostedt (VMware).
  */
+#include <linux/jump_label.h>
 #include <linux/suspend.h>
 #include <linux/ftrace.h>
 #include <linux/slab.h>
@@ -23,23 +24,31 @@
 #define ASSIGN_OPS_HASH(opsname, val)
 #endif
 
-static bool kill_ftrace_graph;
+DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph);
 int ftrace_graph_active;
 
 /* Both enabled by default (can be cleared by function_graph tracer flags */
 static bool fgraph_sleep_time = true;
 
-/**
- * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called
- *
- * ftrace_graph_stop() is called when a severe error is detected in
- * the function graph tracing. This function is called by the critical
- * paths of function graph to keep those paths from doing any more harm.
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * archs can override this function if they must do something
+ * to enable hook for graph tracer.
+ */
+int __weak ftrace_enable_ftrace_graph_caller(void)
+{
+	return 0;
+}
+
+/*
+ * archs can override this function if they must do something
+ * to disable hook for graph tracer.
  */
-bool ftrace_graph_is_dead(void)
+int __weak ftrace_disable_ftrace_graph_caller(void)
 {
-	return kill_ftrace_graph;
+	return 0;
 }
+#endif
 
 /**
  * ftrace_graph_stop - set to permanently disable function graph tracing
@@ -51,7 +60,7 @@ bool ftrace_graph_is_dead(void)
  */
 void ftrace_graph_stop(void)
 {
-	kill_ftrace_graph = true;
+	static_branch_enable(&kill_ftrace_graph);
 }
 
 /* Add a function return address to the trace stack on thread info.*/
@@ -415,7 +424,9 @@ free:
 
 static void
 ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
-			struct task_struct *prev, struct task_struct *next)
+				struct task_struct *prev,
+				struct task_struct *next,
+				unsigned int prev_state)
 {
 	unsigned long long timestamp;
 	int index;
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
new file mode 100644
index 000000000000..e8143e368074
--- /dev/null
+++ b/kernel/trace/fprobe.c
@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fprobe - Simple ftrace probe wrapper for function entry.
+ */
+#define pr_fmt(fmt) "fprobe: " fmt
+
+#include <linux/err.h>
+#include <linux/fprobe.h>
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/rethook.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+
+#include "trace.h"
+
+struct fprobe_rethook_node {
+	struct rethook_node node;
+	unsigned long entry_ip;
+};
+
+static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
+			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
+{
+	struct fprobe_rethook_node *fpr;
+	struct rethook_node *rh;
+	struct fprobe *fp;
+	int bit;
+
+	fp = container_of(ops, struct fprobe, ops);
+	if (fprobe_disabled(fp))
+		return;
+
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
+	if (bit < 0) {
+		fp->nmissed++;
+		return;
+	}
+
+	if (fp->entry_handler)
+		fp->entry_handler(fp, ip, ftrace_get_regs(fregs));
+
+	if (fp->exit_handler) {
+		rh = rethook_try_get(fp->rethook);
+		if (!rh) {
+			fp->nmissed++;
+			goto out;
+		}
+		fpr = container_of(rh, struct fprobe_rethook_node, node);
+		fpr->entry_ip = ip;
+		rethook_hook(rh, ftrace_get_regs(fregs), true);
+	}
+
+out:
+	ftrace_test_recursion_unlock(bit);
+}
+NOKPROBE_SYMBOL(fprobe_handler);
+
+static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
+				  struct ftrace_ops *ops, struct ftrace_regs *fregs)
+{
+	struct fprobe *fp = container_of(ops, struct fprobe, ops);
+
+	if (unlikely(kprobe_running())) {
+		fp->nmissed++;
+		return;
+	}
+	kprobe_busy_begin();
+	fprobe_handler(ip, parent_ip, ops, fregs);
+	kprobe_busy_end();
+}
+
+static void fprobe_exit_handler(struct rethook_node *rh, void *data,
+				struct pt_regs *regs)
+{
+	struct fprobe *fp = (struct fprobe *)data;
+	struct fprobe_rethook_node *fpr;
+
+	if (!fp || fprobe_disabled(fp))
+		return;
+
+	fpr = container_of(rh, struct fprobe_rethook_node, node);
+
+	fp->exit_handler(fp, fpr->entry_ip, regs);
+}
+NOKPROBE_SYMBOL(fprobe_exit_handler);
+
+static int symbols_cmp(const void *a, const void *b)
+{
+	const char **str_a = (const char **) a;
+	const char **str_b = (const char **) b;
+
+	return strcmp(*str_a, *str_b);
+}
+
+/* Convert ftrace location address from symbols */
+static unsigned long *get_ftrace_locations(const char **syms, int num)
+{
+	unsigned long *addrs;
+
+	/* Convert symbols to symbol address */
+	addrs = kcalloc(num, sizeof(*addrs), GFP_KERNEL);
+	if (!addrs)
+		return ERR_PTR(-ENOMEM);
+
+	/* ftrace_lookup_symbols expects sorted symbols */
+	sort(syms, num, sizeof(*syms), symbols_cmp, NULL);
+
+	if (!ftrace_lookup_symbols(syms, num, addrs))
+		return addrs;
+
+	kfree(addrs);
+	return ERR_PTR(-ENOENT);
+}
+
+static void fprobe_init(struct fprobe *fp)
+{
+	fp->nmissed = 0;
+	if (fprobe_shared_with_kprobes(fp))
+		fp->ops.func = fprobe_kprobe_handler;
+	else
+		fp->ops.func = fprobe_handler;
+	fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS;
+}
+
+static int fprobe_init_rethook(struct fprobe *fp, int num)
+{
+	int i, size;
+
+	if (num < 0)
+		return -EINVAL;
+
+	if (!fp->exit_handler) {
+		fp->rethook = NULL;
+		return 0;
+	}
+
+	/* Initialize rethook if needed */
+	size = num * num_possible_cpus() * 2;
+	if (size < 0)
+		return -E2BIG;
+
+	fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler);
+	if (!fp->rethook)
+		return -ENOMEM;
+	for (i = 0; i < size; i++) {
+		struct fprobe_rethook_node *node;
+
+		node = kzalloc(sizeof(*node), GFP_KERNEL);
+		if (!node) {
+			rethook_free(fp->rethook);
+			fp->rethook = NULL;
+			return -ENOMEM;
+		}
+		rethook_add_node(fp->rethook, &node->node);
+	}
+	return 0;
+}
+
+static void fprobe_fail_cleanup(struct fprobe *fp)
+{
+	if (fp->rethook) {
+		/* Don't need to cleanup rethook->handler because this is not used. */
+		rethook_free(fp->rethook);
+		fp->rethook = NULL;
+	}
+	ftrace_free_filter(&fp->ops);
+}
+
+/**
+ * register_fprobe() - Register fprobe to ftrace by pattern.
+ * @fp: A fprobe data structure to be registered.
+ * @filter: A wildcard pattern of probed symbols.
+ * @notfilter: A wildcard pattern of NOT probed symbols.
+ *
+ * Register @fp to ftrace for enabling the probe on the symbols matched to @filter.
+ * If @notfilter is not NULL, the symbols matched the @notfilter are not probed.
+ *
+ * Return 0 if @fp is registered successfully, -errno if not.
+ */
+int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter)
+{
+	struct ftrace_hash *hash;
+	unsigned char *str;
+	int ret, len;
+
+	if (!fp || !filter)
+		return -EINVAL;
+
+	fprobe_init(fp);
+
+	len = strlen(filter);
+	str = kstrdup(filter, GFP_KERNEL);
+	ret = ftrace_set_filter(&fp->ops, str, len, 0);
+	kfree(str);
+	if (ret)
+		return ret;
+
+	if (notfilter) {
+		len = strlen(notfilter);
+		str = kstrdup(notfilter, GFP_KERNEL);
+		ret = ftrace_set_notrace(&fp->ops, str, len, 0);
+		kfree(str);
+		if (ret)
+			goto out;
+	}
+
+	/* TODO:
+	 * correctly calculate the total number of filtered symbols
+	 * from both filter and notfilter.
+	 */
+	hash = rcu_access_pointer(fp->ops.local_hash.filter_hash);
+	if (WARN_ON_ONCE(!hash))
+		goto out;
+
+	ret = fprobe_init_rethook(fp, (int)hash->count);
+	if (!ret)
+		ret = register_ftrace_function(&fp->ops);
+
+out:
+	if (ret)
+		fprobe_fail_cleanup(fp);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_fprobe);
+
+/**
+ * register_fprobe_ips() - Register fprobe to ftrace by address.
+ * @fp: A fprobe data structure to be registered.
+ * @addrs: An array of target ftrace location addresses.
+ * @num: The number of entries of @addrs.
+ *
+ * Register @fp to ftrace for enabling the probe on the address given by @addrs.
+ * The @addrs must be the addresses of ftrace location address, which may be
+ * the symbol address + arch-dependent offset.
+ * If you unsure what this mean, please use other registration functions.
+ *
+ * Return 0 if @fp is registered successfully, -errno if not.
+ */
+int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num)
+{
+	int ret;
+
+	if (!fp || !addrs || num <= 0)
+		return -EINVAL;
+
+	fprobe_init(fp);
+
+	ret = ftrace_set_filter_ips(&fp->ops, addrs, num, 0, 0);
+	if (ret)
+		return ret;
+
+	ret = fprobe_init_rethook(fp, num);
+	if (!ret)
+		ret = register_ftrace_function(&fp->ops);
+
+	if (ret)
+		fprobe_fail_cleanup(fp);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_fprobe_ips);
+
+/**
+ * register_fprobe_syms() - Register fprobe to ftrace by symbols.
+ * @fp: A fprobe data structure to be registered.
+ * @syms: An array of target symbols.
+ * @num: The number of entries of @syms.
+ *
+ * Register @fp to the symbols given by @syms array. This will be useful if
+ * you are sure the symbols exist in the kernel.
+ *
+ * Return 0 if @fp is registered successfully, -errno if not.
+ */
+int register_fprobe_syms(struct fprobe *fp, const char **syms, int num)
+{
+	unsigned long *addrs;
+	int ret;
+
+	if (!fp || !syms || num <= 0)
+		return -EINVAL;
+
+	addrs = get_ftrace_locations(syms, num);
+	if (IS_ERR(addrs))
+		return PTR_ERR(addrs);
+
+	ret = register_fprobe_ips(fp, addrs, num);
+
+	kfree(addrs);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_fprobe_syms);
+
+/**
+ * unregister_fprobe() - Unregister fprobe from ftrace
+ * @fp: A fprobe data structure to be unregistered.
+ *
+ * Unregister fprobe (and remove ftrace hooks from the function entries).
+ *
+ * Return 0 if @fp is unregistered successfully, -errno if not.
+ */
+int unregister_fprobe(struct fprobe *fp)
+{
+	int ret;
+
+	if (!fp || (fp->ops.saved_func != fprobe_handler &&
+		    fp->ops.saved_func != fprobe_kprobe_handler))
+		return -EINVAL;
+
+	/*
+	 * rethook_free() starts disabling the rethook, but the rethook handlers
+	 * may be running on other processors at this point. To make sure that all
+	 * current running handlers are finished, call unregister_ftrace_function()
+	 * after this.
+	 */
+	if (fp->rethook)
+		rethook_free(fp->rethook);
+
+	ret = unregister_ftrace_function(&fp->ops);
+	if (ret < 0)
+		return ret;
+
+	ftrace_free_filter(&fp->ops);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(unregister_fprobe);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f9feb197b2da..33236241f236 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -45,6 +45,8 @@
 #include "trace_output.h"
 #include "trace_stat.h"
 
+#define FTRACE_INVALID_FUNCTION		"__ftrace_invalid_address__"
+
 #define FTRACE_WARN_ON(cond)			\
 	({					\
 		int ___r = cond;		\
@@ -86,7 +88,7 @@ struct ftrace_ops ftrace_list_end __read_mostly = {
 
 /* ftrace_enabled is a method to turn ftrace on or off */
 int ftrace_enabled __read_mostly;
-static int last_ftrace_enabled;
+static int __maybe_unused last_ftrace_enabled;
 
 /* Current function tracing op */
 struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
@@ -119,7 +121,7 @@ struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 struct ftrace_ops global_ops;
 
-/* Defined by vmlinux.lds.h see the commment above arch_ftrace_ops_list_func for details */
+/* Defined by vmlinux.lds.h see the comment above arch_ftrace_ops_list_func for details */
 void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 			  struct ftrace_ops *op, struct ftrace_regs *fregs);
 
@@ -952,7 +954,6 @@ static struct tracer_stat function_stats __initdata = {
 static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
 {
 	struct ftrace_profile_stat *stat;
-	struct dentry *entry;
 	char *name;
 	int ret;
 	int cpu;
@@ -983,11 +984,9 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
 		}
 	}
 
-	entry = tracefs_create_file("function_profile_enabled",
-				    TRACE_MODE_WRITE, d_tracer, NULL,
-				    &ftrace_profile_fops);
-	if (!entry)
-		pr_warn("Could not create tracefs 'function_profile_enabled' entry\n");
+	trace_create_file("function_profile_enabled",
+			  TRACE_MODE_WRITE, d_tracer, NULL,
+			  &ftrace_profile_fops);
 }
 
 #else /* CONFIG_FUNCTION_PROFILER */
@@ -1290,6 +1289,7 @@ static int ftrace_add_mod(struct trace_array *tr,
 	if (!ftrace_mod)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&ftrace_mod->list);
 	ftrace_mod->func = kstrdup(func, GFP_KERNEL);
 	ftrace_mod->module = kstrdup(module, GFP_KERNEL);
 	ftrace_mod->enable = enable;
@@ -1568,17 +1568,34 @@ unsigned long ftrace_location_range(unsigned long start, unsigned long end)
 }
 
 /**
- * ftrace_location - return true if the ip giving is a traced location
+ * ftrace_location - return the ftrace location
  * @ip: the instruction pointer to check
  *
- * Returns rec->ip if @ip given is a pointer to a ftrace location.
- * That is, the instruction that is either a NOP or call to
- * the function tracer. It checks the ftrace internal tables to
- * determine if the address belongs or not.
+ * If @ip matches the ftrace location, return @ip.
+ * If @ip matches sym+0, return sym's ftrace location.
+ * Otherwise, return 0.
  */
 unsigned long ftrace_location(unsigned long ip)
 {
-	return ftrace_location_range(ip, ip);
+	struct dyn_ftrace *rec;
+	unsigned long offset;
+	unsigned long size;
+
+	rec = lookup_rec(ip, ip);
+	if (!rec) {
+		if (!kallsyms_lookup_size_offset(ip, &size, &offset))
+			goto out;
+
+		/* map sym+0 to __fentry__ */
+		if (!offset)
+			rec = lookup_rec(ip, ip + size - 1);
+	}
+
+	if (rec)
+		return rec->ip;
+
+out:
+	return 0;
 }
 
 /**
@@ -1628,6 +1645,18 @@ ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_ex
 static struct ftrace_ops *
 ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops);
 
+static bool skip_record(struct dyn_ftrace *rec)
+{
+	/*
+	 * At boot up, weak functions are set to disable. Function tracing
+	 * can be enabled before they are, and they still need to be disabled now.
+	 * If the record is disabled, still continue if it is marked as already
+	 * enabled (this is needed to keep the accounting working).
+	 */
+	return rec->flags & FTRACE_FL_DISABLED &&
+		!(rec->flags & FTRACE_FL_ENABLED);
+}
+
 static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				     int filter_hash,
 				     bool inc)
@@ -1677,7 +1706,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 		int in_hash = 0;
 		int match = 0;
 
-		if (rec->flags & FTRACE_FL_DISABLED)
+		if (skip_record(rec))
 			continue;
 
 		if (all) {
@@ -1853,6 +1882,13 @@ static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops,
  *  - If the hash is NULL, it hits all recs (if IPMODIFY is set, this is rejected)
  *  - If the hash is EMPTY_HASH, it hits nothing
  *  - Anything else hits the recs which match the hash entries.
+ *
+ * DIRECT ops does not have IPMODIFY flag, but we still need to check it
+ * against functions with FTRACE_FL_IPMODIFY. If there is any overlap, call
+ * ops_func(SHARE_IPMODIFY_SELF) to make sure current ops can share with
+ * IPMODIFY. If ops_func(SHARE_IPMODIFY_SELF) returns non-zero, propagate
+ * the return value to the caller and eventually to the owner of the DIRECT
+ * ops.
  */
 static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops,
 					 struct ftrace_hash *old_hash,
@@ -1861,17 +1897,26 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops,
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec, *end = NULL;
 	int in_old, in_new;
+	bool is_ipmodify, is_direct;
 
 	/* Only update if the ops has been registered */
 	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
 		return 0;
 
-	if (!(ops->flags & FTRACE_OPS_FL_IPMODIFY))
+	is_ipmodify = ops->flags & FTRACE_OPS_FL_IPMODIFY;
+	is_direct = ops->flags & FTRACE_OPS_FL_DIRECT;
+
+	/* neither IPMODIFY nor DIRECT, skip */
+	if (!is_ipmodify && !is_direct)
+		return 0;
+
+	if (WARN_ON_ONCE(is_ipmodify && is_direct))
 		return 0;
 
 	/*
-	 * Since the IPMODIFY is a very address sensitive action, we do not
-	 * allow ftrace_ops to set all functions to new hash.
+	 * Since the IPMODIFY and DIRECT are very address sensitive
+	 * actions, we do not allow ftrace_ops to set all functions to new
+	 * hash.
 	 */
 	if (!new_hash || !old_hash)
 		return -EINVAL;
@@ -1889,12 +1934,32 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops,
 			continue;
 
 		if (in_new) {
-			/* New entries must ensure no others are using it */
-			if (rec->flags & FTRACE_FL_IPMODIFY)
-				goto rollback;
-			rec->flags |= FTRACE_FL_IPMODIFY;
-		} else /* Removed entry */
+			if (rec->flags & FTRACE_FL_IPMODIFY) {
+				int ret;
+
+				/* Cannot have two ipmodify on same rec */
+				if (is_ipmodify)
+					goto rollback;
+
+				FTRACE_WARN_ON(rec->flags & FTRACE_FL_DIRECT);
+
+				/*
+				 * Another ops with IPMODIFY is already
+				 * attached. We are now attaching a direct
+				 * ops. Run SHARE_IPMODIFY_SELF, to check
+				 * whether sharing is supported.
+				 */
+				if (!ops->ops_func)
+					return -EBUSY;
+				ret = ops->ops_func(ops, FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_SELF);
+				if (ret)
+					return ret;
+			} else if (is_ipmodify) {
+				rec->flags |= FTRACE_FL_IPMODIFY;
+			}
+		} else if (is_ipmodify) {
 			rec->flags &= ~FTRACE_FL_IPMODIFY;
+		}
 	} while_for_each_ftrace_rec();
 
 	return 0;
@@ -1964,7 +2029,6 @@ static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops,
 static void print_ip_ins(const char *fmt, const unsigned char *p)
 {
 	char ins[MCOUNT_INSN_SIZE];
-	int i;
 
 	if (copy_from_kernel_nofault(ins, p, MCOUNT_INSN_SIZE)) {
 		printk(KERN_CONT "%s[FAULT] %px\n", fmt, p);
@@ -1972,9 +2036,7 @@ static void print_ip_ins(const char *fmt, const unsigned char *p)
 	}
 
 	printk(KERN_CONT "%s", fmt);
-
-	for (i = 0; i < MCOUNT_INSN_SIZE; i++)
-		printk(KERN_CONT "%s%02x", i ? ":" : "", ins[i]);
+	pr_cont("%*phC", MCOUNT_INSN_SIZE, ins);
 }
 
 enum ftrace_bug_type ftrace_bug_type;
@@ -2074,7 +2136,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
 
 	ftrace_bug_type = FTRACE_BUG_UNKNOWN;
 
-	if (rec->flags & FTRACE_FL_DISABLED)
+	if (skip_record(rec))
 		return FTRACE_UPDATE_IGNORE;
 
 	/*
@@ -2189,7 +2251,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
 	if (update) {
 		/* If there's no more users, clear all flags */
 		if (!ftrace_rec_count(rec))
-			rec->flags = 0;
+			rec->flags &= FTRACE_FL_DISABLED;
 		else
 			/*
 			 * Just disable the record, but keep the ops TRAMP
@@ -2438,8 +2500,7 @@ static void call_direct_funcs(unsigned long ip, unsigned long pip,
 
 struct ftrace_ops direct_ops = {
 	.func		= call_direct_funcs,
-	.flags		= FTRACE_OPS_FL_IPMODIFY
-			  | FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS
+	.flags		= FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS
 			  | FTRACE_OPS_FL_PERMANENT,
 	/*
 	 * By declaring the main trampoline as this trampoline
@@ -2583,7 +2644,7 @@ void __weak ftrace_replace_code(int mod_flags)
 
 	do_for_each_ftrace_rec(pg, rec) {
 
-		if (rec->flags & FTRACE_FL_DISABLED)
+		if (skip_record(rec))
 			continue;
 
 		failed = __ftrace_replace_code(rec, enable);
@@ -2690,18 +2751,16 @@ ftrace_nop_initialize(struct module *mod, struct dyn_ftrace *rec)
  * archs can override this function if they must do something
  * before the modifying code is performed.
  */
-int __weak ftrace_arch_code_modify_prepare(void)
+void __weak ftrace_arch_code_modify_prepare(void)
 {
-	return 0;
 }
 
 /*
  * archs can override this function if they must do something
  * after the modifying code is performed.
  */
-int __weak ftrace_arch_code_modify_post_process(void)
+void __weak ftrace_arch_code_modify_post_process(void)
 {
-	return 0;
 }
 
 void ftrace_modify_all_code(int command)
@@ -2787,12 +2846,7 @@ void __weak arch_ftrace_update_code(int command)
 
 static void ftrace_run_update_code(int command)
 {
-	int ret;
-
-	ret = ftrace_arch_code_modify_prepare();
-	FTRACE_WARN_ON(ret);
-	if (ret)
-		return;
+	ftrace_arch_code_modify_prepare();
 
 	/*
 	 * By default we use stop_machine() to modify the code.
@@ -2802,8 +2856,7 @@ static void ftrace_run_update_code(int command)
 	 */
 	arch_ftrace_update_code(command);
 
-	ret = ftrace_arch_code_modify_post_process();
-	FTRACE_WARN_ON(ret);
+	ftrace_arch_code_modify_post_process();
 }
 
 static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
@@ -2929,6 +2982,16 @@ int ftrace_startup(struct ftrace_ops *ops, int command)
 
 	ftrace_startup_enable(command);
 
+	/*
+	 * If ftrace is in an undefined state, we just remove ops from list
+	 * to prevent the NULL pointer, instead of totally rolling it back and
+	 * free trampoline, because those actions could cause further damage.
+	 */
+	if (unlikely(ftrace_disabled)) {
+		__unregister_ftrace_function(ops);
+		return -ENODEV;
+	}
+
 	ops->flags &= ~FTRACE_OPS_FL_ADDING;
 
 	return 0;
@@ -2966,18 +3029,8 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		command |= FTRACE_UPDATE_TRACE_FUNC;
 	}
 
-	if (!command || !ftrace_enabled) {
-		/*
-		 * If these are dynamic or per_cpu ops, they still
-		 * need their data freed. Since, function tracing is
-		 * not currently active, we can just free them
-		 * without synchronizing all CPUs.
-		 */
-		if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
-			goto free_ops;
-
-		return 0;
-	}
+	if (!command || !ftrace_enabled)
+		goto out;
 
 	/*
 	 * If the ops uses a trampoline, then it needs to be
@@ -3014,6 +3067,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	removed_ops = NULL;
 	ops->flags &= ~FTRACE_OPS_FL_REMOVING;
 
+out:
 	/*
 	 * Dynamic ops may be freed, we must make sure that all
 	 * callers are done before leaving this function.
@@ -3041,47 +3095,12 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		if (IS_ENABLED(CONFIG_PREEMPTION))
 			synchronize_rcu_tasks();
 
- free_ops:
 		ftrace_trampoline_free(ops);
 	}
 
 	return 0;
 }
 
-static void ftrace_startup_sysctl(void)
-{
-	int command;
-
-	if (unlikely(ftrace_disabled))
-		return;
-
-	/* Force update next time */
-	saved_ftrace_func = NULL;
-	/* ftrace_start_up is true if we want ftrace running */
-	if (ftrace_start_up) {
-		command = FTRACE_UPDATE_CALLS;
-		if (ftrace_graph_active)
-			command |= FTRACE_START_FUNC_RET;
-		ftrace_startup_enable(command);
-	}
-}
-
-static void ftrace_shutdown_sysctl(void)
-{
-	int command;
-
-	if (unlikely(ftrace_disabled))
-		return;
-
-	/* ftrace_start_up is true if ftrace is running */
-	if (ftrace_start_up) {
-		command = FTRACE_DISABLE_CALLS;
-		if (ftrace_graph_active)
-			command |= FTRACE_STOP_FUNC_RET;
-		ftrace_run_update_code(command);
-	}
-}
-
 static u64		ftrace_update_time;
 unsigned long		ftrace_update_tot_cnt;
 unsigned long		ftrace_number_of_pages;
@@ -3097,36 +3116,6 @@ static inline int ops_traces_mod(struct ftrace_ops *ops)
 		ftrace_hash_empty(ops->func_hash->notrace_hash);
 }
 
-/*
- * Check if the current ops references the record.
- *
- * If the ops traces all functions, then it was already accounted for.
- * If the ops does not trace the current record function, skip it.
- * If the ops ignores the function via notrace filter, skip it.
- */
-static inline bool
-ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
-{
-	/* If ops isn't enabled, ignore it */
-	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
-		return false;
-
-	/* If ops traces all then it includes this function */
-	if (ops_traces_mod(ops))
-		return true;
-
-	/* The function must be in the filter */
-	if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
-	    !__ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))
-		return false;
-
-	/* If in notrace hash, we ignore it too */
-	if (ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip))
-		return false;
-
-	return true;
-}
-
 static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 {
 	bool init_nop = ftrace_need_init_nop();
@@ -3202,7 +3191,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count)
 		/* if we can't allocate this size, try something smaller */
 		if (!order)
 			return -ENOMEM;
-		order >>= 1;
+		order--;
 		goto again;
 	}
 
@@ -3648,6 +3637,105 @@ static void add_trampoline_func(struct seq_file *m, struct ftrace_ops *ops,
 		seq_printf(m, " ->%pS", ptr);
 }
 
+#ifdef FTRACE_MCOUNT_MAX_OFFSET
+/*
+ * Weak functions can still have an mcount/fentry that is saved in
+ * the __mcount_loc section. These can be detected by having a
+ * symbol offset of greater than FTRACE_MCOUNT_MAX_OFFSET, as the
+ * symbol found by kallsyms is not the function that the mcount/fentry
+ * is part of. The offset is much greater in these cases.
+ *
+ * Test the record to make sure that the ip points to a valid kallsyms
+ * and if not, mark it disabled.
+ */
+static int test_for_valid_rec(struct dyn_ftrace *rec)
+{
+	char str[KSYM_SYMBOL_LEN];
+	unsigned long offset;
+	const char *ret;
+
+	ret = kallsyms_lookup(rec->ip, NULL, &offset, NULL, str);
+
+	/* Weak functions can cause invalid addresses */
+	if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) {
+		rec->flags |= FTRACE_FL_DISABLED;
+		return 0;
+	}
+	return 1;
+}
+
+static struct workqueue_struct *ftrace_check_wq __initdata;
+static struct work_struct ftrace_check_work __initdata;
+
+/*
+ * Scan all the mcount/fentry entries to make sure they are valid.
+ */
+static __init void ftrace_check_work_func(struct work_struct *work)
+{
+	struct ftrace_page *pg;
+	struct dyn_ftrace *rec;
+
+	mutex_lock(&ftrace_lock);
+	do_for_each_ftrace_rec(pg, rec) {
+		test_for_valid_rec(rec);
+	} while_for_each_ftrace_rec();
+	mutex_unlock(&ftrace_lock);
+}
+
+static int __init ftrace_check_for_weak_functions(void)
+{
+	INIT_WORK(&ftrace_check_work, ftrace_check_work_func);
+
+	ftrace_check_wq = alloc_workqueue("ftrace_check_wq", WQ_UNBOUND, 0);
+
+	queue_work(ftrace_check_wq, &ftrace_check_work);
+	return 0;
+}
+
+static int __init ftrace_check_sync(void)
+{
+	/* Make sure the ftrace_check updates are finished */
+	if (ftrace_check_wq)
+		destroy_workqueue(ftrace_check_wq);
+	return 0;
+}
+
+late_initcall_sync(ftrace_check_sync);
+subsys_initcall(ftrace_check_for_weak_functions);
+
+static int print_rec(struct seq_file *m, unsigned long ip)
+{
+	unsigned long offset;
+	char str[KSYM_SYMBOL_LEN];
+	char *modname;
+	const char *ret;
+
+	ret = kallsyms_lookup(ip, NULL, &offset, &modname, str);
+	/* Weak functions can cause invalid addresses */
+	if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) {
+		snprintf(str, KSYM_SYMBOL_LEN, "%s_%ld",
+			 FTRACE_INVALID_FUNCTION, offset);
+		ret = NULL;
+	}
+
+	seq_puts(m, str);
+	if (modname)
+		seq_printf(m, " [%s]", modname);
+	return ret == NULL ? -1 : 0;
+}
+#else
+static inline int test_for_valid_rec(struct dyn_ftrace *rec)
+{
+	return 1;
+}
+
+static inline int print_rec(struct seq_file *m, unsigned long ip)
+{
+	seq_printf(m, "%ps", (void *)ip);
+	return 0;
+}
+#endif
+
 static int t_show(struct seq_file *m, void *v)
 {
 	struct ftrace_iterator *iter = m->private;
@@ -3672,7 +3760,13 @@ static int t_show(struct seq_file *m, void *v)
 	if (!rec)
 		return 0;
 
-	seq_printf(m, "%ps", (void *)rec->ip);
+	if (print_rec(m, rec->ip)) {
+		/* This should only happen when a rec is disabled */
+		WARN_ON_ONCE(!(rec->flags & FTRACE_FL_DISABLED));
+		seq_putc(m, '\n');
+		return 0;
+	}
+
 	if (iter->flags & FTRACE_ITER_ENABLED) {
 		struct ftrace_ops *ops;
 
@@ -3990,6 +4084,24 @@ add_rec_by_index(struct ftrace_hash *hash, struct ftrace_glob *func_g,
 	return 0;
 }
 
+#ifdef FTRACE_MCOUNT_MAX_OFFSET
+static int lookup_ip(unsigned long ip, char **modname, char *str)
+{
+	unsigned long offset;
+
+	kallsyms_lookup(ip, NULL, &offset, modname, str);
+	if (offset > FTRACE_MCOUNT_MAX_OFFSET)
+		return -1;
+	return 0;
+}
+#else
+static int lookup_ip(unsigned long ip, char **modname, char *str)
+{
+	kallsyms_lookup(ip, NULL, NULL, modname, str);
+	return 0;
+}
+#endif
+
 static int
 ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g,
 		struct ftrace_glob *mod_g, int exclude_mod)
@@ -3997,7 +4109,12 @@ ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g,
 	char str[KSYM_SYMBOL_LEN];
 	char *modname;
 
-	kallsyms_lookup(rec->ip, NULL, NULL, &modname, str);
+	if (lookup_ip(rec->ip, &modname, str)) {
+		/* This should only happen when a rec is disabled */
+		WARN_ON_ONCE(system_state == SYSTEM_RUNNING &&
+			     !(rec->flags & FTRACE_FL_DISABLED));
+		return 0;
+	}
 
 	if (mod_g) {
 		int mod_matches = (modname) ? ftrace_match(modname, mod_g) : 0;
@@ -4448,7 +4565,7 @@ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
  * @ip: The instruction pointer address to remove the data from
  *
  * Returns the data if it is found, otherwise NULL.
- * Note, if the data pointer is used as the data itself, (see 
+ * Note, if the data pointer is used as the data itself, (see
  * ftrace_func_mapper_find_ip(), then the return value may be meaningless,
  * if the data pointer was set to zero.
  */
@@ -4543,8 +4660,8 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr,
 			       struct ftrace_probe_ops *probe_ops,
 			       void *data)
 {
+	struct ftrace_func_probe *probe = NULL, *iter;
 	struct ftrace_func_entry *entry;
-	struct ftrace_func_probe *probe;
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *old_hash;
 	struct ftrace_hash *hash;
@@ -4563,11 +4680,13 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr,
 
 	mutex_lock(&ftrace_lock);
 	/* Check if the probe_ops is already registered */
-	list_for_each_entry(probe, &tr->func_probes, list) {
-		if (probe->probe_ops == probe_ops)
+	list_for_each_entry(iter, &tr->func_probes, list) {
+		if (iter->probe_ops == probe_ops) {
+			probe = iter;
 			break;
+		}
 	}
-	if (&probe->list == &tr->func_probes) {
+	if (!probe) {
 		probe = kzalloc(sizeof(*probe), GFP_KERNEL);
 		if (!probe) {
 			mutex_unlock(&ftrace_lock);
@@ -4685,9 +4804,9 @@ int
 unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
 				      struct ftrace_probe_ops *probe_ops)
 {
+	struct ftrace_func_probe *probe = NULL, *iter;
 	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_func_entry *entry;
-	struct ftrace_func_probe *probe;
 	struct ftrace_glob func_g;
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *old_hash;
@@ -4715,11 +4834,13 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
 
 	mutex_lock(&ftrace_lock);
 	/* Check if the probe_ops is already registered */
-	list_for_each_entry(probe, &tr->func_probes, list) {
-		if (probe->probe_ops == probe_ops)
+	list_for_each_entry(iter, &tr->func_probes, list) {
+		if (iter->probe_ops == probe_ops) {
+			probe = iter;
 			break;
+		}
 	}
-	if (&probe->list == &tr->func_probes)
+	if (!probe)
 		goto err_unlock_ftrace;
 
 	ret = -EINVAL;
@@ -4958,11 +5079,12 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf,
 }
 
 static int
-ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
+__ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 {
 	struct ftrace_func_entry *entry;
 
-	if (!ftrace_location(ip))
+	ip = ftrace_location(ip);
+	if (!ip)
 		return -EINVAL;
 
 	if (remove) {
@@ -4977,8 +5099,29 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 }
 
 static int
+ftrace_match_addr(struct ftrace_hash *hash, unsigned long *ips,
+		  unsigned int cnt, int remove)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < cnt; i++) {
+		err = __ftrace_match_addr(hash, ips[i], remove);
+		if (err) {
+			/*
+			 * This expects the @hash is a temporary hash and if this
+			 * fails the caller must free the @hash.
+			 */
+			return err;
+		}
+	}
+	return 0;
+}
+
+static int
 ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
-		unsigned long ip, int remove, int reset, int enable)
+		unsigned long *ips, unsigned int cnt,
+		int remove, int reset, int enable)
 {
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *hash;
@@ -5008,8 +5151,8 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 		ret = -EINVAL;
 		goto out_regex_unlock;
 	}
-	if (ip) {
-		ret = ftrace_match_addr(hash, ip, remove);
+	if (ips) {
+		ret = ftrace_match_addr(hash, ips, cnt, remove);
 		if (ret < 0)
 			goto out_regex_unlock;
 	}
@@ -5026,10 +5169,10 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 }
 
 static int
-ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove,
-		int reset, int enable)
+ftrace_set_addr(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt,
+		int remove, int reset, int enable)
 {
-	return ftrace_set_hash(ops, NULL, 0, ip, remove, reset, enable);
+	return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable);
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
@@ -5087,6 +5230,8 @@ static struct ftrace_direct_func *ftrace_alloc_direct_func(unsigned long addr)
 	return direct;
 }
 
+static int register_ftrace_function_nolock(struct ftrace_ops *ops);
+
 /**
  * register_ftrace_direct - Call a custom trampoline directly
  * @ip: The address of the nop at the beginning of a function
@@ -5110,11 +5255,16 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 	struct ftrace_func_entry *entry;
 	struct ftrace_hash *free_hash = NULL;
 	struct dyn_ftrace *rec;
-	int ret = -EBUSY;
+	int ret = -ENODEV;
 
 	mutex_lock(&direct_mutex);
 
+	ip = ftrace_location(ip);
+	if (!ip)
+		goto out_unlock;
+
 	/* See if there's a direct function at @ip already */
+	ret = -EBUSY;
 	if (ftrace_find_rec_direct(ip))
 		goto out_unlock;
 
@@ -5151,16 +5301,15 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 		goto out_unlock;
 
 	ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0);
-	if (ret)
-		remove_hash_entry(direct_functions, entry);
 
 	if (!ret && !(direct_ops.flags & FTRACE_OPS_FL_ENABLED)) {
-		ret = register_ftrace_function(&direct_ops);
+		ret = register_ftrace_function_nolock(&direct_ops);
 		if (ret)
 			ftrace_set_filter_ip(&direct_ops, ip, 1, 0);
 	}
 
 	if (ret) {
+		remove_hash_entry(direct_functions, entry);
 		kfree(entry);
 		if (!direct->count) {
 			list_del_rcu(&direct->next);
@@ -5222,6 +5371,10 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 
 	mutex_lock(&direct_mutex);
 
+	ip = ftrace_location(ip);
+	if (!ip)
+		goto out_unlock;
+
 	entry = find_direct_entry(&ip, NULL);
 	if (!entry)
 		goto out_unlock;
@@ -5274,6 +5427,8 @@ static struct ftrace_ops stub_ops = {
  * it is safe to modify the ftrace record, where it should be
  * currently calling @old_addr directly, to call @new_addr.
  *
+ * This is called with direct_mutex locked.
+ *
  * Safety checks should be made to make sure that the code at
  * @rec->ip is currently calling @old_addr. And this must
  * also update entry->direct to @new_addr.
@@ -5286,6 +5441,8 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 	unsigned long ip = rec->ip;
 	int ret;
 
+	lockdep_assert_held(&direct_mutex);
+
 	/*
 	 * The ftrace_lock was used to determine if the record
 	 * had more than one registered user to it. If it did,
@@ -5308,7 +5465,7 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 	if (ret)
 		goto out_lock;
 
-	ret = register_ftrace_function(&stub_ops);
+	ret = register_ftrace_function_nolock(&stub_ops);
 	if (ret) {
 		ftrace_set_filter_ip(&stub_ops, ip, 1, 0);
 		goto out_lock;
@@ -5354,6 +5511,11 @@ int modify_ftrace_direct(unsigned long ip,
 	mutex_lock(&direct_mutex);
 
 	mutex_lock(&ftrace_lock);
+
+	ip = ftrace_location(ip);
+	if (!ip)
+		goto out_unlock;
+
 	entry = find_direct_entry(&ip, &rec);
 	if (!entry)
 		goto out_unlock;
@@ -5404,8 +5566,7 @@ int modify_ftrace_direct(unsigned long ip,
 }
 EXPORT_SYMBOL_GPL(modify_ftrace_direct);
 
-#define MULTI_FLAGS (FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_DIRECT | \
-		     FTRACE_OPS_FL_SAVE_REGS)
+#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS)
 
 static int check_direct_multi(struct ftrace_ops *ops)
 {
@@ -5498,7 +5659,7 @@ int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 	ops->flags = MULTI_FLAGS;
 	ops->trampoline = FTRACE_REGS_ADDR;
 
-	err = register_ftrace_function(ops);
+	err = register_ftrace_function_nolock(ops);
 
  out_remove:
 	if (err)
@@ -5550,22 +5711,8 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 }
 EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
 
-/**
- * modify_ftrace_direct_multi - Modify an existing direct 'multi' call
- * to call something else
- * @ops: The address of the struct ftrace_ops object
- * @addr: The address of the new trampoline to call at @ops functions
- *
- * This is used to unregister currently registered direct caller and
- * register new one @addr on functions registered in @ops object.
- *
- * Note there's window between ftrace_shutdown and ftrace_startup calls
- * where there will be no callbacks called.
- *
- * Returns: zero on success. Non zero on error, which includes:
- *  -EINVAL - The @ops object was not properly registered.
- */
-int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+static int
+__modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 {
 	struct ftrace_hash *hash;
 	struct ftrace_func_entry *entry, *iter;
@@ -5576,20 +5723,15 @@ int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 	int i, size;
 	int err;
 
-	if (check_direct_multi(ops))
-		return -EINVAL;
-	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
-		return -EINVAL;
-
-	mutex_lock(&direct_mutex);
+	lockdep_assert_held_once(&direct_mutex);
 
 	/* Enable the tmp_ops to have the same functions as the direct ops */
 	ftrace_ops_init(&tmp_ops);
 	tmp_ops.func_hash = ops->func_hash;
 
-	err = register_ftrace_function(&tmp_ops);
+	err = register_ftrace_function_nolock(&tmp_ops);
 	if (err)
-		goto out_direct;
+		return err;
 
 	/*
 	 * Now the ftrace_ops_list_func() is called to do the direct callers.
@@ -5613,7 +5755,64 @@ int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 	/* Removing the tmp_ops will add the updated direct callers to the functions */
 	unregister_ftrace_function(&tmp_ops);
 
- out_direct:
+	return err;
+}
+
+/**
+ * modify_ftrace_direct_multi_nolock - Modify an existing direct 'multi' call
+ * to call something else
+ * @ops: The address of the struct ftrace_ops object
+ * @addr: The address of the new trampoline to call at @ops functions
+ *
+ * This is used to unregister currently registered direct caller and
+ * register new one @addr on functions registered in @ops object.
+ *
+ * Note there's window between ftrace_shutdown and ftrace_startup calls
+ * where there will be no callbacks called.
+ *
+ * Caller should already have direct_mutex locked, so we don't lock
+ * direct_mutex here.
+ *
+ * Returns: zero on success. Non zero on error, which includes:
+ *  -EINVAL - The @ops object was not properly registered.
+ */
+int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr)
+{
+	if (check_direct_multi(ops))
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return -EINVAL;
+
+	return __modify_ftrace_direct_multi(ops, addr);
+}
+EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi_nolock);
+
+/**
+ * modify_ftrace_direct_multi - Modify an existing direct 'multi' call
+ * to call something else
+ * @ops: The address of the struct ftrace_ops object
+ * @addr: The address of the new trampoline to call at @ops functions
+ *
+ * This is used to unregister currently registered direct caller and
+ * register new one @addr on functions registered in @ops object.
+ *
+ * Note there's window between ftrace_shutdown and ftrace_startup calls
+ * where there will be no callbacks called.
+ *
+ * Returns: zero on success. Non zero on error, which includes:
+ *  -EINVAL - The @ops object was not properly registered.
+ */
+int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	int err;
+
+	if (check_direct_multi(ops))
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return -EINVAL;
+
+	mutex_lock(&direct_mutex);
+	err = __modify_ftrace_direct_multi(ops, addr);
 	mutex_unlock(&direct_mutex);
 	return err;
 }
@@ -5634,11 +5833,30 @@ int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
 			 int remove, int reset)
 {
 	ftrace_ops_init(ops);
-	return ftrace_set_addr(ops, ip, remove, reset, 1);
+	return ftrace_set_addr(ops, &ip, 1, remove, reset, 1);
 }
 EXPORT_SYMBOL_GPL(ftrace_set_filter_ip);
 
 /**
+ * ftrace_set_filter_ips - set functions to filter on in ftrace by addresses
+ * @ops - the ops to set the filter with
+ * @ips - the array of addresses to add to or remove from the filter.
+ * @cnt - the number of addresses in @ips
+ * @remove - non zero to remove ips from the filter
+ * @reset - non zero to reset all filters before applying this filter.
+ *
+ * Filters denote which functions should be enabled when tracing is enabled
+ * If @ips array or any ip specified within is NULL , it fails to update filter.
+ */
+int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips,
+			  unsigned int cnt, int remove, int reset)
+{
+	ftrace_ops_init(ops);
+	return ftrace_set_addr(ops, ips, cnt, remove, reset, 1);
+}
+EXPORT_SYMBOL_GPL(ftrace_set_filter_ips);
+
+/**
  * ftrace_ops_set_global_filter - setup ops to use global filters
  * @ops - the ops which will use the global filters
  *
@@ -5659,7 +5877,7 @@ static int
 ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 		 int reset, int enable)
 {
-	return ftrace_set_hash(ops, buf, len, 0, 0, reset, enable);
+	return ftrace_set_hash(ops, buf, len, NULL, 0, 0, reset, enable);
 }
 
 /**
@@ -5867,8 +6085,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 
 		if (filter_hash) {
 			orig_hash = &iter->ops->func_hash->filter_hash;
-			if (iter->tr && !list_empty(&iter->tr->mod_trace))
-				iter->hash->flags |= FTRACE_HASH_FL_MOD;
+			if (iter->tr) {
+				if (list_empty(&iter->tr->mod_trace))
+					iter->hash->flags &= ~FTRACE_HASH_FL_MOD;
+				else
+					iter->hash->flags |= FTRACE_HASH_FL_MOD;
+			}
 		} else
 			orig_hash = &iter->ops->func_hash->notrace_hash;
 
@@ -6563,6 +6785,38 @@ static int ftrace_get_trampoline_kallsym(unsigned int symnum,
 	return -ERANGE;
 }
 
+#if defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) || defined(CONFIG_MODULES)
+/*
+ * Check if the current ops references the given ip.
+ *
+ * If the ops traces all functions, then it was already accounted for.
+ * If the ops does not trace the current record function, skip it.
+ * If the ops ignores the function via notrace filter, skip it.
+ */
+static bool
+ops_references_ip(struct ftrace_ops *ops, unsigned long ip)
+{
+	/* If ops isn't enabled, ignore it */
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return false;
+
+	/* If ops traces all then it includes this function */
+	if (ops_traces_mod(ops))
+		return true;
+
+	/* The function must be in the filter */
+	if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
+	    !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip))
+		return false;
+
+	/* If in notrace hash, we ignore it too */
+	if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip))
+		return false;
+
+	return true;
+}
+#endif
+
 #ifdef CONFIG_MODULES
 
 #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
@@ -6575,7 +6829,7 @@ 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)) {
+		if (ops_references_ip(ops, rec->ip)) {
 			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_DIRECT))
 				continue;
 			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_IPMODIFY))
@@ -6755,6 +7009,13 @@ void ftrace_module_enable(struct module *mod)
 		    !within_module_init(rec->ip, mod))
 			break;
 
+		/* Weak functions should still be ignored */
+		if (!test_for_valid_rec(rec)) {
+			/* Clear all other flags. Should not be enabled anyway */
+			rec->flags = FTRACE_FL_DISABLED;
+			continue;
+		}
+
 		cnt = 0;
 
 		/*
@@ -6791,11 +7052,16 @@ void ftrace_module_enable(struct module *mod)
 
 void ftrace_module_init(struct module *mod)
 {
+	int ret;
+
 	if (ftrace_disabled || !mod->num_ftrace_callsites)
 		return;
 
-	ftrace_process_locs(mod, mod->ftrace_callsites,
-			    mod->ftrace_callsites + mod->num_ftrace_callsites);
+	ret = ftrace_process_locs(mod, mod->ftrace_callsites,
+				  mod->ftrace_callsites + mod->num_ftrace_callsites);
+	if (ret)
+		pr_warn("ftrace: failed to allocate entries for module '%s' functions\n",
+			mod->name);
 }
 
 static void save_ftrace_mod_rec(struct ftrace_mod_map *mod_map,
@@ -7096,6 +7362,8 @@ void __init ftrace_free_init_mem(void)
 	void *start = (void *)(&__init_begin);
 	void *end = (void *)(&__init_end);
 
+	ftrace_boot_snapshot();
+
 	ftrace_free_mem(NULL, start, end);
 }
 
@@ -7124,17 +7392,21 @@ void __init ftrace_init(void)
 	}
 
 	pr_info("ftrace: allocating %ld entries in %ld pages\n",
-		count, count / ENTRIES_PER_PAGE + 1);
-
-	last_ftrace_enabled = ftrace_enabled = 1;
+		count, DIV_ROUND_UP(count, ENTRIES_PER_PAGE));
 
 	ret = ftrace_process_locs(NULL,
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
+	if (ret) {
+		pr_warn("ftrace: failed to allocate entries for functions\n");
+		goto failed;
+	}
 
 	pr_info("ftrace: allocated %ld pages with %ld groups\n",
 		ftrace_number_of_pages, ftrace_number_of_groups);
 
+	last_ftrace_enabled = ftrace_enabled = 1;
+
 	set_ftrace_early_filters();
 
 	return;
@@ -7191,12 +7463,8 @@ static int __init ftrace_nodyn_init(void)
 core_initcall(ftrace_nodyn_init);
 
 static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; }
-static inline void ftrace_startup_enable(int command) { }
 static inline void ftrace_startup_all(int command) { }
 
-# define ftrace_startup_sysctl()	do { } while (0)
-# define ftrace_shutdown_sysctl()	do { } while (0)
-
 static void ftrace_update_trampoline(struct ftrace_ops *ops)
 {
 }
@@ -7347,7 +7615,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
 
 static void
 ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
-		    struct task_struct *prev, struct task_struct *next)
+				     struct task_struct *prev,
+				     struct task_struct *next,
+				     unsigned int prev_state)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *pid_list;
@@ -7789,9 +8059,146 @@ int ftrace_is_dead(void)
 	return ftrace_disabled;
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+/*
+ * When registering ftrace_ops with IPMODIFY, it is necessary to make sure
+ * it doesn't conflict with any direct ftrace_ops. If there is existing
+ * direct ftrace_ops on a kernel function being patched, call
+ * FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_PEER on it to enable sharing.
+ *
+ * @ops:     ftrace_ops being registered.
+ *
+ * Returns:
+ *         0 on success;
+ *         Negative on failure.
+ */
+static int prepare_direct_functions_for_ipmodify(struct ftrace_ops *ops)
+{
+	struct ftrace_func_entry *entry;
+	struct ftrace_hash *hash;
+	struct ftrace_ops *op;
+	int size, i, ret;
+
+	lockdep_assert_held_once(&direct_mutex);
+
+	if (!(ops->flags & FTRACE_OPS_FL_IPMODIFY))
+		return 0;
+
+	hash = ops->func_hash->filter_hash;
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			unsigned long ip = entry->ip;
+			bool found_op = false;
+
+			mutex_lock(&ftrace_lock);
+			do_for_each_ftrace_op(op, ftrace_ops_list) {
+				if (!(op->flags & FTRACE_OPS_FL_DIRECT))
+					continue;
+				if (ops_references_ip(op, ip)) {
+					found_op = true;
+					break;
+				}
+			} while_for_each_ftrace_op(op);
+			mutex_unlock(&ftrace_lock);
+
+			if (found_op) {
+				if (!op->ops_func)
+					return -EBUSY;
+
+				ret = op->ops_func(op, FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_PEER);
+				if (ret)
+					return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Similar to prepare_direct_functions_for_ipmodify, clean up after ops
+ * with IPMODIFY is unregistered. The cleanup is optional for most DIRECT
+ * ops.
+ */
+static void cleanup_direct_functions_after_ipmodify(struct ftrace_ops *ops)
+{
+	struct ftrace_func_entry *entry;
+	struct ftrace_hash *hash;
+	struct ftrace_ops *op;
+	int size, i;
+
+	if (!(ops->flags & FTRACE_OPS_FL_IPMODIFY))
+		return;
+
+	mutex_lock(&direct_mutex);
+
+	hash = ops->func_hash->filter_hash;
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			unsigned long ip = entry->ip;
+			bool found_op = false;
+
+			mutex_lock(&ftrace_lock);
+			do_for_each_ftrace_op(op, ftrace_ops_list) {
+				if (!(op->flags & FTRACE_OPS_FL_DIRECT))
+					continue;
+				if (ops_references_ip(op, ip)) {
+					found_op = true;
+					break;
+				}
+			} while_for_each_ftrace_op(op);
+			mutex_unlock(&ftrace_lock);
+
+			/* The cleanup is optional, ignore any errors */
+			if (found_op && op->ops_func)
+				op->ops_func(op, FTRACE_OPS_CMD_DISABLE_SHARE_IPMODIFY_PEER);
+		}
+	}
+	mutex_unlock(&direct_mutex);
+}
+
+#define lock_direct_mutex()	mutex_lock(&direct_mutex)
+#define unlock_direct_mutex()	mutex_unlock(&direct_mutex)
+
+#else  /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
+
+static int prepare_direct_functions_for_ipmodify(struct ftrace_ops *ops)
+{
+	return 0;
+}
+
+static void cleanup_direct_functions_after_ipmodify(struct ftrace_ops *ops)
+{
+}
+
+#define lock_direct_mutex()	do { } while (0)
+#define unlock_direct_mutex()	do { } while (0)
+
+#endif  /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
+
+/*
+ * Similar to register_ftrace_function, except we don't lock direct_mutex.
+ */
+static int register_ftrace_function_nolock(struct ftrace_ops *ops)
+{
+	int ret;
+
+	ftrace_ops_init(ops);
+
+	mutex_lock(&ftrace_lock);
+
+	ret = ftrace_startup(ops, 0);
+
+	mutex_unlock(&ftrace_lock);
+
+	return ret;
+}
+
 /**
  * register_ftrace_function - register a function for profiling
- * @ops - ops structure that holds the function for profiling.
+ * @ops:	ops structure that holds the function for profiling.
  *
  * Register a function to be called by all functions in the
  * kernel.
@@ -7804,21 +8211,22 @@ int register_ftrace_function(struct ftrace_ops *ops)
 {
 	int ret;
 
-	ftrace_ops_init(ops);
-
-	mutex_lock(&ftrace_lock);
-
-	ret = ftrace_startup(ops, 0);
+	lock_direct_mutex();
+	ret = prepare_direct_functions_for_ipmodify(ops);
+	if (ret < 0)
+		goto out_unlock;
 
-	mutex_unlock(&ftrace_lock);
+	ret = register_ftrace_function_nolock(ops);
 
+out_unlock:
+	unlock_direct_mutex();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(register_ftrace_function);
 
 /**
  * unregister_ftrace_function - unregister a function for profiling.
- * @ops - ops structure that holds the function to unregister
+ * @ops:	ops structure that holds the function to unregister
  *
  * Unregister a function that was added to be called by ftrace profiling.
  */
@@ -7830,10 +8238,122 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 	ret = ftrace_shutdown(ops, 0);
 	mutex_unlock(&ftrace_lock);
 
+	cleanup_direct_functions_after_ipmodify(ops);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(unregister_ftrace_function);
 
+static int symbols_cmp(const void *a, const void *b)
+{
+	const char **str_a = (const char **) a;
+	const char **str_b = (const char **) b;
+
+	return strcmp(*str_a, *str_b);
+}
+
+struct kallsyms_data {
+	unsigned long *addrs;
+	const char **syms;
+	size_t cnt;
+	size_t found;
+};
+
+static int kallsyms_callback(void *data, const char *name,
+			     struct module *mod, unsigned long addr)
+{
+	struct kallsyms_data *args = data;
+	const char **sym;
+	int idx;
+
+	sym = bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp);
+	if (!sym)
+		return 0;
+
+	idx = sym - args->syms;
+	if (args->addrs[idx])
+		return 0;
+
+	if (!ftrace_location(addr))
+		return 0;
+
+	args->addrs[idx] = addr;
+	args->found++;
+	return args->found == args->cnt ? 1 : 0;
+}
+
+/**
+ * ftrace_lookup_symbols - Lookup addresses for array of symbols
+ *
+ * @sorted_syms: array of symbols pointers symbols to resolve,
+ * must be alphabetically sorted
+ * @cnt: number of symbols/addresses in @syms/@addrs arrays
+ * @addrs: array for storing resulting addresses
+ *
+ * This function looks up addresses for array of symbols provided in
+ * @syms array (must be alphabetically sorted) and stores them in
+ * @addrs array, which needs to be big enough to store at least @cnt
+ * addresses.
+ *
+ * This function returns 0 if all provided symbols are found,
+ * -ESRCH otherwise.
+ */
+int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs)
+{
+	struct kallsyms_data args;
+	int err;
+
+	memset(addrs, 0, sizeof(*addrs) * cnt);
+	args.addrs = addrs;
+	args.syms = sorted_syms;
+	args.cnt = cnt;
+	args.found = 0;
+	err = kallsyms_on_each_symbol(kallsyms_callback, &args);
+	if (err < 0)
+		return err;
+	return args.found == args.cnt ? 0 : -ESRCH;
+}
+
+#ifdef CONFIG_SYSCTL
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+static void ftrace_startup_sysctl(void)
+{
+	int command;
+
+	if (unlikely(ftrace_disabled))
+		return;
+
+	/* Force update next time */
+	saved_ftrace_func = NULL;
+	/* ftrace_start_up is true if we want ftrace running */
+	if (ftrace_start_up) {
+		command = FTRACE_UPDATE_CALLS;
+		if (ftrace_graph_active)
+			command |= FTRACE_START_FUNC_RET;
+		ftrace_startup_enable(command);
+	}
+}
+
+static void ftrace_shutdown_sysctl(void)
+{
+	int command;
+
+	if (unlikely(ftrace_disabled))
+		return;
+
+	/* ftrace_start_up is true if ftrace is running */
+	if (ftrace_start_up) {
+		command = FTRACE_DISABLE_CALLS;
+		if (ftrace_graph_active)
+			command |= FTRACE_STOP_FUNC_RET;
+		ftrace_run_update_code(command);
+	}
+}
+#else
+# define ftrace_startup_sysctl()       do { } while (0)
+# define ftrace_shutdown_sysctl()      do { } while (0)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
 static bool is_permanent_ops_registered(void)
 {
 	struct ftrace_ops *op;
@@ -7846,7 +8366,7 @@ static bool is_permanent_ops_registered(void)
 	return false;
 }
 
-int
+static int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
 		     void *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -7889,3 +8409,22 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 	mutex_unlock(&ftrace_lock);
 	return ret;
 }
+
+static struct ctl_table ftrace_sysctls[] = {
+	{
+		.procname       = "ftrace_enabled",
+		.data           = &ftrace_enabled,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = ftrace_enable_sysctl,
+	},
+	{}
+};
+
+static int __init ftrace_sysctl_init(void)
+{
+	register_sysctl_init("kernel", ftrace_sysctls);
+	return 0;
+}
+late_initcall(ftrace_sysctl_init);
+#endif
diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c
index 18b0f1cbb947..c736487fc0e4 100644
--- a/kernel/trace/kprobe_event_gen_test.c
+++ b/kernel/trace/kprobe_event_gen_test.c
@@ -35,6 +35,49 @@
 static struct trace_event_file *gen_kprobe_test;
 static struct trace_event_file *gen_kretprobe_test;
 
+#define KPROBE_GEN_TEST_FUNC	"do_sys_open"
+
+/* X86 */
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_32)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%ax"
+#define KPROBE_GEN_TEST_ARG1	"filename=%dx"
+#define KPROBE_GEN_TEST_ARG2	"flags=%cx"
+#define KPROBE_GEN_TEST_ARG3	"mode=+4($stack)"
+
+/* ARM64 */
+#elif defined(CONFIG_ARM64)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%x0"
+#define KPROBE_GEN_TEST_ARG1	"filename=%x1"
+#define KPROBE_GEN_TEST_ARG2	"flags=%x2"
+#define KPROBE_GEN_TEST_ARG3	"mode=%x3"
+
+/* ARM */
+#elif defined(CONFIG_ARM)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%r0"
+#define KPROBE_GEN_TEST_ARG1	"filename=%r1"
+#define KPROBE_GEN_TEST_ARG2	"flags=%r2"
+#define KPROBE_GEN_TEST_ARG3	"mode=%r3"
+
+/* RISCV */
+#elif defined(CONFIG_RISCV)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%a0"
+#define KPROBE_GEN_TEST_ARG1	"filename=%a1"
+#define KPROBE_GEN_TEST_ARG2	"flags=%a2"
+#define KPROBE_GEN_TEST_ARG3	"mode=%a3"
+
+/* others */
+#else
+#define KPROBE_GEN_TEST_ARG0	NULL
+#define KPROBE_GEN_TEST_ARG1	NULL
+#define KPROBE_GEN_TEST_ARG2	NULL
+#define KPROBE_GEN_TEST_ARG3	NULL
+#endif
+
+static bool trace_event_file_is_valid(struct trace_event_file *input)
+{
+	return input && !IS_ERR(input);
+}
+
 /*
  * Test to make sure we can create a kprobe event, then add more
  * fields.
@@ -58,23 +101,23 @@ static int __init test_gen_kprobe_cmd(void)
 	 * fields.
 	 */
 	ret = kprobe_event_gen_cmd_start(&cmd, "gen_kprobe_test",
-					 "do_sys_open",
-					 "dfd=%ax", "filename=%dx");
+					 KPROBE_GEN_TEST_FUNC,
+					 KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1);
 	if (ret)
-		goto free;
+		goto out;
 
 	/* Use kprobe_event_add_fields to add the rest of the fields */
 
-	ret = kprobe_event_add_fields(&cmd, "flags=%cx", "mode=+4($stack)");
+	ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3);
 	if (ret)
-		goto free;
+		goto out;
 
 	/*
 	 * This actually creates the event.
 	 */
 	ret = kprobe_event_gen_cmd_end(&cmd);
 	if (ret)
-		goto free;
+		goto out;
 
 	/*
 	 * Now get the gen_kprobe_test event file.  We need to prevent
@@ -97,13 +140,13 @@ static int __init test_gen_kprobe_cmd(void)
 		goto delete;
 	}
  out:
+	kfree(buf);
 	return ret;
  delete:
+	if (trace_event_file_is_valid(gen_kprobe_test))
+		gen_kprobe_test = NULL;
 	/* We got an error after creating the event, delete it */
 	ret = kprobe_event_delete("gen_kprobe_test");
- free:
-	kfree(buf);
-
 	goto out;
 }
 
@@ -128,17 +171,17 @@ static int __init test_gen_kretprobe_cmd(void)
 	 * Define the kretprobe event.
 	 */
 	ret = kretprobe_event_gen_cmd_start(&cmd, "gen_kretprobe_test",
-					    "do_sys_open",
+					    KPROBE_GEN_TEST_FUNC,
 					    "$retval");
 	if (ret)
-		goto free;
+		goto out;
 
 	/*
 	 * This actually creates the event.
 	 */
 	ret = kretprobe_event_gen_cmd_end(&cmd);
 	if (ret)
-		goto free;
+		goto out;
 
 	/*
 	 * Now get the gen_kretprobe_test event file.  We need to
@@ -162,13 +205,13 @@ static int __init test_gen_kretprobe_cmd(void)
 		goto delete;
 	}
  out:
+	kfree(buf);
 	return ret;
  delete:
+	if (trace_event_file_is_valid(gen_kretprobe_test))
+		gen_kretprobe_test = NULL;
 	/* We got an error after creating the event, delete it */
 	ret = kprobe_event_delete("gen_kretprobe_test");
- free:
-	kfree(buf);
-
 	goto out;
 }
 
@@ -182,10 +225,12 @@ static int __init kprobe_event_gen_test_init(void)
 
 	ret = test_gen_kretprobe_cmd();
 	if (ret) {
-		WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
-						  "kprobes",
-						  "gen_kretprobe_test", false));
-		trace_put_event_file(gen_kretprobe_test);
+		if (trace_event_file_is_valid(gen_kretprobe_test)) {
+			WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
+							  "kprobes",
+							  "gen_kretprobe_test", false));
+			trace_put_event_file(gen_kretprobe_test);
+		}
 		WARN_ON(kprobe_event_delete("gen_kretprobe_test"));
 	}
 
@@ -194,24 +239,30 @@ static int __init kprobe_event_gen_test_init(void)
 
 static void __exit kprobe_event_gen_test_exit(void)
 {
-	/* Disable the event or you can't remove it */
-	WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr,
-					  "kprobes",
-					  "gen_kprobe_test", false));
+	if (trace_event_file_is_valid(gen_kprobe_test)) {
+		/* Disable the event or you can't remove it */
+		WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr,
+						  "kprobes",
+						  "gen_kprobe_test", false));
+
+		/* Now give the file and instance back */
+		trace_put_event_file(gen_kprobe_test);
+	}
 
-	/* Now give the file and instance back */
-	trace_put_event_file(gen_kprobe_test);
 
 	/* Now unregister and free the event */
 	WARN_ON(kprobe_event_delete("gen_kprobe_test"));
 
-	/* Disable the event or you can't remove it */
-	WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr,
-					  "kprobes",
-					  "gen_kretprobe_test", false));
+	if (trace_event_file_is_valid(gen_kretprobe_test)) {
+		/* Disable the event or you can't remove it */
+		WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
+						  "kprobes",
+						  "gen_kretprobe_test", false));
+
+		/* Now give the file and instance back */
+		trace_put_event_file(gen_kretprobe_test);
+	}
 
-	/* Now give the file and instance back */
-	trace_put_event_file(gen_kretprobe_test);
 
 	/* Now unregister and free the event */
 	WARN_ON(kprobe_event_delete("gen_kretprobe_test"));
diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c
index a2ef1d18126a..95106d02b32d 100644
--- a/kernel/trace/pid_list.c
+++ b/kernel/trace/pid_list.c
@@ -118,9 +118,9 @@ static inline unsigned int pid_join(unsigned int upper1,
 /**
  * trace_pid_list_is_set - test if the pid is set in the list
  * @pid_list: The pid list to test
- * @pid: The pid to to see if set in the list.
+ * @pid: The pid to see if set in the list.
  *
- * Tests if @pid is is set in the @pid_list. This is usually called
+ * Tests if @pid is set in the @pid_list. This is usually called
  * from the scheduler when a task is scheduled. Its pid is checked
  * if it should be traced or not.
  *
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
new file mode 100644
index 000000000000..32c3dfdb4d6a
--- /dev/null
+++ b/kernel/trace/rethook.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define pr_fmt(fmt) "rethook: " fmt
+
+#include <linux/bug.h>
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/preempt.h>
+#include <linux/rethook.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+
+/* Return hook list (shadow stack by list) */
+
+/*
+ * This function is called from delayed_put_task_struct() when a task is
+ * dead and cleaned up to recycle any kretprobe instances associated with
+ * this task. These left over instances represent probed functions that
+ * have been called but will never return.
+ */
+void rethook_flush_task(struct task_struct *tk)
+{
+	struct rethook_node *rhn;
+	struct llist_node *node;
+
+	node = __llist_del_all(&tk->rethooks);
+	while (node) {
+		rhn = container_of(node, struct rethook_node, llist);
+		node = node->next;
+		preempt_disable();
+		rethook_recycle(rhn);
+		preempt_enable();
+	}
+}
+
+static void rethook_free_rcu(struct rcu_head *head)
+{
+	struct rethook *rh = container_of(head, struct rethook, rcu);
+	struct rethook_node *rhn;
+	struct freelist_node *node;
+	int count = 1;
+
+	node = rh->pool.head;
+	while (node) {
+		rhn = container_of(node, struct rethook_node, freelist);
+		node = node->next;
+		kfree(rhn);
+		count++;
+	}
+
+	/* The rh->ref is the number of pooled node + 1 */
+	if (refcount_sub_and_test(count, &rh->ref))
+		kfree(rh);
+}
+
+/**
+ * rethook_free() - Free struct rethook.
+ * @rh: the struct rethook to be freed.
+ *
+ * Free the rethook. Before calling this function, user must ensure the
+ * @rh::data is cleaned if needed (or, the handler can access it after
+ * calling this function.) This function will set the @rh to be freed
+ * after all rethook_node are freed (not soon). And the caller must
+ * not touch @rh after calling this.
+ */
+void rethook_free(struct rethook *rh)
+{
+	WRITE_ONCE(rh->handler, NULL);
+
+	call_rcu(&rh->rcu, rethook_free_rcu);
+}
+
+/**
+ * rethook_alloc() - Allocate struct rethook.
+ * @data: a data to pass the @handler when hooking the return.
+ * @handler: the return hook callback function.
+ *
+ * Allocate and initialize a new rethook with @data and @handler.
+ * Return NULL if memory allocation fails or @handler is NULL.
+ * Note that @handler == NULL means this rethook is going to be freed.
+ */
+struct rethook *rethook_alloc(void *data, rethook_handler_t handler)
+{
+	struct rethook *rh = kzalloc(sizeof(struct rethook), GFP_KERNEL);
+
+	if (!rh || !handler) {
+		kfree(rh);
+		return NULL;
+	}
+
+	rh->data = data;
+	rh->handler = handler;
+	rh->pool.head = NULL;
+	refcount_set(&rh->ref, 1);
+
+	return rh;
+}
+
+/**
+ * rethook_add_node() - Add a new node to the rethook.
+ * @rh: the struct rethook.
+ * @node: the struct rethook_node to be added.
+ *
+ * Add @node to @rh. User must allocate @node (as a part of user's
+ * data structure.) The @node fields are initialized in this function.
+ */
+void rethook_add_node(struct rethook *rh, struct rethook_node *node)
+{
+	node->rethook = rh;
+	freelist_add(&node->freelist, &rh->pool);
+	refcount_inc(&rh->ref);
+}
+
+static void free_rethook_node_rcu(struct rcu_head *head)
+{
+	struct rethook_node *node = container_of(head, struct rethook_node, rcu);
+
+	if (refcount_dec_and_test(&node->rethook->ref))
+		kfree(node->rethook);
+	kfree(node);
+}
+
+/**
+ * rethook_recycle() - return the node to rethook.
+ * @node: The struct rethook_node to be returned.
+ *
+ * Return back the @node to @node::rethook. If the @node::rethook is already
+ * marked as freed, this will free the @node.
+ */
+void rethook_recycle(struct rethook_node *node)
+{
+	lockdep_assert_preemption_disabled();
+
+	if (likely(READ_ONCE(node->rethook->handler)))
+		freelist_add(&node->freelist, &node->rethook->pool);
+	else
+		call_rcu(&node->rcu, free_rethook_node_rcu);
+}
+NOKPROBE_SYMBOL(rethook_recycle);
+
+/**
+ * rethook_try_get() - get an unused rethook node.
+ * @rh: The struct rethook which pools the nodes.
+ *
+ * Get an unused rethook node from @rh. If the node pool is empty, this
+ * will return NULL. Caller must disable preemption.
+ */
+struct rethook_node *rethook_try_get(struct rethook *rh)
+{
+	rethook_handler_t handler = READ_ONCE(rh->handler);
+	struct freelist_node *fn;
+
+	lockdep_assert_preemption_disabled();
+
+	/* Check whether @rh is going to be freed. */
+	if (unlikely(!handler))
+		return NULL;
+
+	/*
+	 * This expects the caller will set up a rethook on a function entry.
+	 * When the function returns, the rethook will eventually be reclaimed
+	 * or released in the rethook_recycle() with call_rcu().
+	 * This means the caller must be run in the RCU-availabe context.
+	 */
+	if (unlikely(!rcu_is_watching()))
+		return NULL;
+
+	fn = freelist_try_get(&rh->pool);
+	if (!fn)
+		return NULL;
+
+	return container_of(fn, struct rethook_node, freelist);
+}
+NOKPROBE_SYMBOL(rethook_try_get);
+
+/**
+ * rethook_hook() - Hook the current function return.
+ * @node: The struct rethook node to hook the function return.
+ * @regs: The struct pt_regs for the function entry.
+ * @mcount: True if this is called from mcount(ftrace) context.
+ *
+ * Hook the current running function return. This must be called when the
+ * function entry (or at least @regs must be the registers of the function
+ * entry.) @mcount is used for identifying the context. If this is called
+ * from ftrace (mcount) callback, @mcount must be set true. If this is called
+ * from the real function entry (e.g. kprobes) @mcount must be set false.
+ * This is because the way to hook the function return depends on the context.
+ */
+void rethook_hook(struct rethook_node *node, struct pt_regs *regs, bool mcount)
+{
+	arch_rethook_prepare(node, regs, mcount);
+	__llist_add(&node->llist, &current->rethooks);
+}
+NOKPROBE_SYMBOL(rethook_hook);
+
+/* This assumes the 'tsk' is the current task or is not running. */
+static unsigned long __rethook_find_ret_addr(struct task_struct *tsk,
+					     struct llist_node **cur)
+{
+	struct rethook_node *rh = NULL;
+	struct llist_node *node = *cur;
+
+	if (!node)
+		node = tsk->rethooks.first;
+	else
+		node = node->next;
+
+	while (node) {
+		rh = container_of(node, struct rethook_node, llist);
+		if (rh->ret_addr != (unsigned long)arch_rethook_trampoline) {
+			*cur = node;
+			return rh->ret_addr;
+		}
+		node = node->next;
+	}
+	return 0;
+}
+NOKPROBE_SYMBOL(__rethook_find_ret_addr);
+
+/**
+ * rethook_find_ret_addr -- Find correct return address modified by rethook
+ * @tsk: Target task
+ * @frame: A frame pointer
+ * @cur: a storage of the loop cursor llist_node pointer for next call
+ *
+ * Find the correct return address modified by a rethook on @tsk in unsigned
+ * long type.
+ * The @tsk must be 'current' or a task which is not running. @frame is a hint
+ * to get the currect return address - which is compared with the
+ * rethook::frame field. The @cur is a loop cursor for searching the
+ * kretprobe return addresses on the @tsk. The '*@cur' should be NULL at the
+ * first call, but '@cur' itself must NOT NULL.
+ *
+ * Returns found address value or zero if not found.
+ */
+unsigned long rethook_find_ret_addr(struct task_struct *tsk, unsigned long frame,
+				    struct llist_node **cur)
+{
+	struct rethook_node *rhn = NULL;
+	unsigned long ret;
+
+	if (WARN_ON_ONCE(!cur))
+		return 0;
+
+	if (WARN_ON_ONCE(tsk != current && task_is_running(tsk)))
+		return 0;
+
+	do {
+		ret = __rethook_find_ret_addr(tsk, cur);
+		if (!ret)
+			break;
+		rhn = container_of(*cur, struct rethook_node, llist);
+	} while (rhn->frame != frame);
+
+	return ret;
+}
+NOKPROBE_SYMBOL(rethook_find_ret_addr);
+
+void __weak arch_rethook_fixup_return(struct pt_regs *regs,
+				      unsigned long correct_ret_addr)
+{
+	/*
+	 * Do nothing by default. If the architecture which uses a
+	 * frame pointer to record real return address on the stack,
+	 * it should fill this function to fixup the return address
+	 * so that stacktrace works from the rethook handler.
+	 */
+}
+
+/* This function will be called from each arch-defined trampoline. */
+unsigned long rethook_trampoline_handler(struct pt_regs *regs,
+					 unsigned long frame)
+{
+	struct llist_node *first, *node = NULL;
+	unsigned long correct_ret_addr;
+	rethook_handler_t handler;
+	struct rethook_node *rhn;
+
+	correct_ret_addr = __rethook_find_ret_addr(current, &node);
+	if (!correct_ret_addr) {
+		pr_err("rethook: Return address not found! Maybe there is a bug in the kernel\n");
+		BUG_ON(1);
+	}
+
+	instruction_pointer_set(regs, correct_ret_addr);
+
+	/*
+	 * These loops must be protected from rethook_free_rcu() because those
+	 * are accessing 'rhn->rethook'.
+	 */
+	preempt_disable();
+
+	/*
+	 * Run the handler on the shadow stack. Do not unlink the list here because
+	 * stackdump inside the handlers needs to decode it.
+	 */
+	first = current->rethooks.first;
+	while (first) {
+		rhn = container_of(first, struct rethook_node, llist);
+		if (WARN_ON_ONCE(rhn->frame != frame))
+			break;
+		handler = READ_ONCE(rhn->rethook->handler);
+		if (handler)
+			handler(rhn, rhn->rethook->data, regs);
+
+		if (first == node)
+			break;
+		first = first->next;
+	}
+
+	/* Fixup registers for returning to correct address. */
+	arch_rethook_fixup_return(regs, correct_ret_addr);
+
+	/* Unlink used shadow stack */
+	first = current->rethooks.first;
+	current->rethooks.first = node->next;
+	node->next = NULL;
+
+	while (first) {
+		rhn = container_of(first, struct rethook_node, llist);
+		first = first->next;
+		rethook_recycle(rhn);
+	}
+	preempt_enable();
+
+	return correct_ret_addr;
+}
+NOKPROBE_SYMBOL(rethook_trampoline_handler);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 05dfc7a12d3d..b21bf14bae9b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -29,6 +29,14 @@
 
 #include <asm/local.h>
 
+/*
+ * The "absolute" timestamp in the buffer is only 59 bits.
+ * If a clock has the 5 MSBs set, it needs to be saved and
+ * reinserted.
+ */
+#define TS_MSB		(0xf8ULL << 56)
+#define ABS_TS_MASK	(~TS_MSB)
+
 static void update_pages_handler(struct work_struct *work);
 
 /*
@@ -405,6 +413,7 @@ struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
 	wait_queue_head_t		full_waiters;
+	long				wait_index;
 	bool				waiters_pending;
 	bool				full_waiters_pending;
 	bool				wakeup_full;
@@ -468,6 +477,7 @@ struct rb_time_struct {
 	local_t		cnt;
 	local_t		top;
 	local_t		bottom;
+	local_t		msb;
 };
 #else
 #include <asm/local64.h>
@@ -509,6 +519,7 @@ struct ring_buffer_per_cpu {
 	local_t				committing;
 	local_t				commits;
 	local_t				pages_touched;
+	local_t				pages_lost;
 	local_t				pages_read;
 	long				last_pages_touch;
 	size_t				shortest_full;
@@ -569,7 +580,6 @@ struct ring_buffer_iter {
  * 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.
@@ -594,6 +604,7 @@ struct ring_buffer_iter {
  */
 #define RB_TIME_SHIFT	30
 #define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1)
+#define RB_TIME_MSB_SHIFT	 60
 
 static inline int rb_time_cnt(unsigned long val)
 {
@@ -613,7 +624,7 @@ static inline u64 rb_time_val(unsigned long top, unsigned long bottom)
 
 static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
 {
-	unsigned long top, bottom;
+	unsigned long top, bottom, msb;
 	unsigned long c;
 
 	/*
@@ -625,6 +636,7 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
 		c = local_read(&t->cnt);
 		top = local_read(&t->top);
 		bottom = local_read(&t->bottom);
+		msb = local_read(&t->msb);
 	} while (c != local_read(&t->cnt));
 
 	*cnt = rb_time_cnt(top);
@@ -633,7 +645,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
 	if (*cnt != rb_time_cnt(bottom))
 		return false;
 
-	*ret = rb_time_val(top, bottom);
+	/* The shift to msb will lose its cnt bits */
+	*ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT);
 	return true;
 }
 
@@ -649,10 +662,12 @@ 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)
+static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom,
+				 unsigned long *msb)
 {
 	*top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK);
 	*bottom = (unsigned long)(val & RB_TIME_VAL_MASK);
+	*msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT);
 }
 
 static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt)
@@ -663,15 +678,16 @@ static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long
 
 static void rb_time_set(rb_time_t *t, u64 val)
 {
-	unsigned long cnt, top, bottom;
+	unsigned long cnt, top, bottom, msb;
 
-	rb_time_split(val, &top, &bottom);
+	rb_time_split(val, &top, &bottom, &msb);
 
 	/* 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);
+		rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt);
 	} while (cnt != local_read(&t->cnt));
 }
 
@@ -686,8 +702,8 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
 
 static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
 {
-	unsigned long cnt, top, bottom;
-	unsigned long cnt2, top2, bottom2;
+	unsigned long cnt, top, bottom, msb;
+	unsigned long cnt2, top2, bottom2, msb2;
 	u64 val;
 
 	/* The cmpxchg always fails if it interrupted an update */
@@ -703,16 +719,18 @@ static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
 
 	 cnt2 = cnt + 1;
 
-	 rb_time_split(val, &top, &bottom);
+	 rb_time_split(val, &top, &bottom, &msb);
 	 top = rb_time_val_cnt(top, cnt);
 	 bottom = rb_time_val_cnt(bottom, cnt);
 
-	 rb_time_split(set, &top2, &bottom2);
+	 rb_time_split(set, &top2, &bottom2, &msb2);
 	 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->msb, msb, msb2))
+		return false;
 	if (!rb_time_read_cmpxchg(&t->top, top, top2))
 		return false;
 	if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2))
@@ -783,6 +801,24 @@ static inline void verify_event(struct ring_buffer_per_cpu *cpu_buffer,
 }
 #endif
 
+/*
+ * The absolute time stamp drops the 5 MSBs and some clocks may
+ * require them. The rb_fix_abs_ts() will take a previous full
+ * time stamp, and add the 5 MSB of that time stamp on to the
+ * saved absolute time stamp. Then they are compared in case of
+ * the unlikely event that the latest time stamp incremented
+ * the 5 MSB.
+ */
+static inline u64 rb_fix_abs_ts(u64 abs, u64 save_ts)
+{
+	if (save_ts & TS_MSB) {
+		abs |= save_ts & TS_MSB;
+		/* Check for overflow */
+		if (unlikely(abs < save_ts))
+			abs += 1ULL << 59;
+	}
+	return abs;
+}
 
 static inline u64 rb_time_stamp(struct trace_buffer *buffer);
 
@@ -811,8 +847,10 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer,
 	u64 ts;
 
 	/* If the event includes an absolute time, then just use that */
-	if (event->type_len == RINGBUF_TYPE_TIME_STAMP)
-		return rb_event_time_stamp(event);
+	if (event->type_len == RINGBUF_TYPE_TIME_STAMP) {
+		ts = rb_event_time_stamp(event);
+		return rb_fix_abs_ts(ts, cpu_buffer->tail_page->page->time_stamp);
+	}
 
 	nest = local_read(&cpu_buffer->committing);
 	verify_event(cpu_buffer, event);
@@ -848,7 +886,7 @@ size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu)
 }
 
 /**
- * ring_buffer_nr_pages_dirty - get the number of used pages in the ring buffer
+ * ring_buffer_nr_dirty_pages - get the number of used pages in the ring buffer
  * @buffer: The ring_buffer to get the number of pages from
  * @cpu: The cpu of the ring_buffer to get the number of pages from
  *
@@ -857,10 +895,18 @@ size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu)
 size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu)
 {
 	size_t read;
+	size_t lost;
 	size_t cnt;
 
 	read = local_read(&buffer->buffers[cpu]->pages_read);
+	lost = local_read(&buffer->buffers[cpu]->pages_lost);
 	cnt = local_read(&buffer->buffers[cpu]->pages_touched);
+
+	if (WARN_ON_ONCE(cnt < lost))
+		return 0;
+
+	cnt -= lost;
+
 	/* The reader can read an empty page, but not more than that */
 	if (cnt < read) {
 		WARN_ON_ONCE(read > cnt + 1);
@@ -870,6 +916,21 @@ size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu)
 	return cnt - read;
 }
 
+static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int full)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	size_t nr_pages;
+	size_t dirty;
+
+	nr_pages = cpu_buffer->nr_pages;
+	if (!nr_pages || !full)
+		return true;
+
+	dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+
+	return (dirty * 100) > (full * nr_pages);
+}
+
 /*
  * rb_wake_up_waiters - wake up tasks waiting for ring buffer input
  *
@@ -881,13 +942,56 @@ static void rb_wake_up_waiters(struct irq_work *work)
 	struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
 
 	wake_up_all(&rbwork->waiters);
-	if (rbwork->wakeup_full) {
+	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
 		rbwork->wakeup_full = false;
+		rbwork->full_waiters_pending = false;
 		wake_up_all(&rbwork->full_waiters);
 	}
 }
 
 /**
+ * ring_buffer_wake_waiters - wake up any waiters on this ring buffer
+ * @buffer: The ring buffer to wake waiters on
+ *
+ * In the case of a file that represents a ring buffer is closing,
+ * it is prudent to wake up any waiters that are on this.
+ */
+void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct rb_irq_work *rbwork;
+
+	if (!buffer)
+		return;
+
+	if (cpu == RING_BUFFER_ALL_CPUS) {
+
+		/* Wake up individual ones too. One level recursion */
+		for_each_buffer_cpu(buffer, cpu)
+			ring_buffer_wake_waiters(buffer, cpu);
+
+		rbwork = &buffer->irq_work;
+	} else {
+		if (WARN_ON_ONCE(!buffer->buffers))
+			return;
+		if (WARN_ON_ONCE(cpu >= nr_cpu_ids))
+			return;
+
+		cpu_buffer = buffer->buffers[cpu];
+		/* The CPU buffer may not have been initialized yet */
+		if (!cpu_buffer)
+			return;
+		rbwork = &cpu_buffer->irq_work;
+	}
+
+	rbwork->wait_index++;
+	/* make sure the waiters see the new index */
+	smp_wmb();
+
+	rb_wake_up_waiters(&rbwork->work);
+}
+
+/**
  * ring_buffer_wait - wait for input to the ring buffer
  * @buffer: buffer to wait on
  * @cpu: the cpu buffer to wait on
@@ -902,6 +1006,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
 	struct rb_irq_work *work;
+	long wait_index;
 	int ret = 0;
 
 	/*
@@ -920,6 +1025,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 		work = &cpu_buffer->irq_work;
 	}
 
+	wait_index = READ_ONCE(work->wait_index);
 
 	while (true) {
 		if (full)
@@ -964,26 +1070,29 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 		    !ring_buffer_empty_cpu(buffer, cpu)) {
 			unsigned long flags;
 			bool pagebusy;
-			size_t nr_pages;
-			size_t dirty;
+			bool done;
 
 			if (!full)
 				break;
 
 			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
-			nr_pages = cpu_buffer->nr_pages;
-			dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+			done = !pagebusy && full_hit(buffer, cpu, full);
+
 			if (!cpu_buffer->shortest_full ||
-			    cpu_buffer->shortest_full < full)
+			    cpu_buffer->shortest_full > full)
 				cpu_buffer->shortest_full = full;
 			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-			if (!pagebusy &&
-			    (!nr_pages || (dirty * 100) > full * nr_pages))
+			if (done)
 				break;
 		}
 
 		schedule();
+
+		/* Make sure to see the new wait index */
+		smp_rmb();
+		if (wait_index != work->wait_index)
+			break;
 	}
 
 	if (full)
@@ -1000,6 +1109,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
  * @cpu: the cpu buffer to wait on
  * @filp: the file descriptor
  * @poll_table: The poll descriptor
+ * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS
  *
  * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
  * as data is added to any of the @buffer's cpu buffers. Otherwise
@@ -1009,14 +1119,15 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
  * zero otherwise.
  */
 __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
-			  struct file *filp, poll_table *poll_table)
+			  struct file *filp, poll_table *poll_table, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct rb_irq_work *work;
 
-	if (cpu == RING_BUFFER_ALL_CPUS)
+	if (cpu == RING_BUFFER_ALL_CPUS) {
 		work = &buffer->irq_work;
-	else {
+		full = 0;
+	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			return -EINVAL;
 
@@ -1024,8 +1135,14 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 		work = &cpu_buffer->irq_work;
 	}
 
-	poll_wait(filp, &work->waiters, poll_table);
-	work->waiters_pending = true;
+	if (full) {
+		poll_wait(filp, &work->full_waiters, poll_table);
+		work->full_waiters_pending = true;
+	} else {
+		poll_wait(filp, &work->waiters, poll_table);
+		work->waiters_pending = true;
+	}
+
 	/*
 	 * There's a tight race between setting the waiters_pending and
 	 * checking if the ring buffer is empty.  Once the waiters_pending bit
@@ -1041,6 +1158,9 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 	 */
 	smp_mb();
 
+	if (full)
+		return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0;
+
 	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
 	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
 		return EPOLLIN | EPOLLRDNORM;
@@ -1682,9 +1802,9 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 
 	free_buffer_page(cpu_buffer->reader_page);
 
-	rb_head_page_deactivate(cpu_buffer);
-
 	if (head) {
+		rb_head_page_deactivate(cpu_buffer);
+
 		list_for_each_entry_safe(bpage, tmp, head, list) {
 			list_del_init(&bpage->list);
 			free_buffer_page(bpage);
@@ -1920,6 +2040,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 			 */
 			local_add(page_entries, &cpu_buffer->overrun);
 			local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+			local_inc(&cpu_buffer->pages_lost);
 		}
 
 		/*
@@ -2404,6 +2525,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
 		 */
 		local_add(entries, &cpu_buffer->overrun);
 		local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+		local_inc(&cpu_buffer->pages_lost);
 
 		/*
 		 * The entries will be zeroed out when we move the
@@ -2572,6 +2694,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 		/* Mark the rest of the page with padding */
 		rb_event_set_padding(event);
 
+		/* Make sure the padding is visible before the write update */
+		smp_wmb();
+
 		/* Set the write back to the previous setting */
 		local_sub(length, &tail_page->write);
 		return;
@@ -2583,6 +2708,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	/* time delta must be non zero */
 	event->time_delta = 1;
 
+	/* Make sure the padding is visible before the tail_page->write update */
+	smp_wmb();
+
 	/* Set write to end of buffer */
 	length = (tail + length) - BUF_PAGE_SIZE;
 	local_sub(length, &tail_page->write);
@@ -2754,8 +2882,15 @@ static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
 		(RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE);
 
 	if (unlikely(info->delta > (1ULL << 59))) {
+		/*
+		 * Some timers can use more than 59 bits, and when a timestamp
+		 * is added to the buffer, it will lose those bits.
+		 */
+		if (abs && (info->ts & TS_MSB)) {
+			info->delta &= ABS_TS_MASK;
+
 		/* did the clock go backwards */
-		if (info->before == info->after && info->before > info->ts) {
+		} else if (info->before == info->after && info->before > info->ts) {
 			/* not interrupted */
 			static int once;
 
@@ -3055,10 +3190,6 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 static __always_inline void
 rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
 {
-	size_t nr_pages;
-	size_t dirty;
-	size_t full;
-
 	if (buffer->irq_work.waiters_pending) {
 		buffer->irq_work.waiters_pending = false;
 		/* irq_work_queue() supplies it's own memory barriers */
@@ -3082,10 +3213,7 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
 
 	cpu_buffer->last_pages_touch = local_read(&cpu_buffer->pages_touched);
 
-	full = cpu_buffer->shortest_full;
-	nr_pages = cpu_buffer->nr_pages;
-	dirty = ring_buffer_nr_dirty_pages(buffer, cpu_buffer->cpu);
-	if (full && nr_pages && (dirty * 100) <= full * nr_pages)
+	if (!full_hit(buffer, cpu_buffer->cpu, cpu_buffer->shortest_full))
 		return;
 
 	cpu_buffer->irq_work.wakeup_full = true;
@@ -3304,7 +3432,7 @@ static void dump_buffer_page(struct buffer_data_page *bpage,
 
 		case RINGBUF_TYPE_TIME_STAMP:
 			delta = rb_event_time_stamp(event);
-			ts = delta;
+			ts = rb_fix_abs_ts(delta, ts);
 			pr_warn("  [%lld] absolute:%lld TIME STAMP\n", ts, delta);
 			break;
 
@@ -3380,7 +3508,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 
 		case RINGBUF_TYPE_TIME_STAMP:
 			delta = rb_event_time_stamp(event);
-			ts = delta;
+			ts = rb_fix_abs_ts(delta, ts);
 			break;
 
 		case RINGBUF_TYPE_PADDING:
@@ -4367,6 +4495,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 
 	case RINGBUF_TYPE_TIME_STAMP:
 		delta = rb_event_time_stamp(event);
+		delta = rb_fix_abs_ts(delta, cpu_buffer->read_stamp);
 		cpu_buffer->read_stamp = delta;
 		return;
 
@@ -4397,6 +4526,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
 
 	case RINGBUF_TYPE_TIME_STAMP:
 		delta = rb_event_time_stamp(event);
+		delta = rb_fix_abs_ts(delta, iter->read_stamp);
 		iter->read_stamp = delta;
 		return;
 
@@ -4542,6 +4672,33 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
+	/*
+	 * The writer has preempt disable, wait for it. But not forever
+	 * Although, 1 second is pretty much "forever"
+	 */
+#define USECS_WAIT	1000000
+        for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) {
+		/* If the write is past the end of page, a writer is still updating it */
+		if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE))
+			break;
+
+		udelay(1);
+
+		/* Get the latest version of the reader write value */
+		smp_rmb();
+	}
+
+	/* The writer is not moving forward? Something is wrong */
+	if (RB_WARN_ON(cpu_buffer, nr_loops == USECS_WAIT))
+		reader = NULL;
+
+	/*
+	 * Make sure we see any padding after the write update
+	 * (see rb_reset_tail())
+	 */
+	smp_rmb();
+
+
 	return reader;
 }
 
@@ -4650,6 +4807,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
 	case RINGBUF_TYPE_TIME_STAMP:
 		if (ts) {
 			*ts = rb_event_time_stamp(event);
+			*ts = rb_fix_abs_ts(*ts, reader->page->time_stamp);
 			ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
 							 cpu_buffer->cpu, ts);
 		}
@@ -4741,6 +4899,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	case RINGBUF_TYPE_TIME_STAMP:
 		if (ts) {
 			*ts = rb_event_time_stamp(event);
+			*ts = rb_fix_abs_ts(*ts, iter->head_page->page->time_stamp);
 			ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
 							 cpu_buffer->cpu, ts);
 		}
@@ -5117,6 +5276,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->committing, 0);
 	local_set(&cpu_buffer->commits, 0);
 	local_set(&cpu_buffer->pages_touched, 0);
+	local_set(&cpu_buffer->pages_lost, 0);
 	local_set(&cpu_buffer->pages_read, 0);
 	cpu_buffer->last_pages_touch = 0;
 	cpu_buffer->shortest_full = 0;
@@ -5185,7 +5345,7 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
 EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
 /**
- * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
+ * ring_buffer_reset_online_cpus - 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
  */
@@ -5255,7 +5415,7 @@ void ring_buffer_reset(struct trace_buffer *buffer)
 EXPORT_SYMBOL_GPL(ring_buffer_reset);
 
 /**
- * rind_buffer_empty - is the ring buffer empty?
+ * ring_buffer_empty - is the ring buffer empty?
  * @buffer: The ring buffer to test
  */
 bool ring_buffer_empty(struct trace_buffer *buffer)
@@ -5569,7 +5729,15 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		unsigned int pos = 0;
 		unsigned int size;
 
-		if (full)
+		/*
+		 * If a full page is expected, this can still be returned
+		 * if there's been a previous partial read and the
+		 * rest of the page can be read and the commit page is off
+		 * the reader page.
+		 */
+		if (full &&
+		    (!read || (len < (commit - read)) ||
+		     cpu_buffer->reader_page == cpu_buffer->commit_page))
 			goto out_unlock;
 
 		if (len > (commit - read))
@@ -6011,10 +6179,10 @@ static __init int test_ringbuffer(void)
 		pr_info("        total events:   %ld\n", total_lost + total_read);
 		pr_info("  recorded len bytes:   %ld\n", total_len);
 		pr_info(" recorded size bytes:   %ld\n", total_size);
-		if (total_lost)
+		if (total_lost) {
 			pr_info(" With dropped events, record len and size may not match\n"
 				" alloced and written from above\n");
-		if (!total_lost) {
+		} else {
 			if (RB_WARN_ON(buffer, total_len != total_alloc ||
 				       total_size != total_written))
 				break;
diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig
new file mode 100644
index 000000000000..831779607e84
--- /dev/null
+++ b/kernel/trace/rv/Kconfig
@@ -0,0 +1,78 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config DA_MON_EVENTS
+	bool
+
+config DA_MON_EVENTS_IMPLICIT
+	select DA_MON_EVENTS
+	bool
+
+config DA_MON_EVENTS_ID
+	select DA_MON_EVENTS
+	bool
+
+menuconfig RV
+	bool "Runtime Verification"
+	depends on TRACING
+	help
+	  Enable the kernel runtime verification infrastructure. RV is a
+	  lightweight (yet rigorous) method that complements classical
+	  exhaustive verification techniques (such as model checking and
+	  theorem proving). RV works by analyzing the trace of the system's
+	  actual execution, comparing it against a formal specification of
+	  the system behavior.
+
+	  For further information, see:
+	    Documentation/trace/rv/runtime-verification.rst
+
+config RV_MON_WIP
+	depends on RV
+	depends on PREEMPT_TRACER
+	select DA_MON_EVENTS_IMPLICIT
+	bool "wip monitor"
+	help
+	  Enable wip (wakeup in preemptive) sample monitor that illustrates
+	  the usage of per-cpu monitors, and one limitation of the
+	  preempt_disable/enable events.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_wip.rst
+
+config RV_MON_WWNR
+	depends on RV
+	select DA_MON_EVENTS_ID
+	bool "wwnr monitor"
+	help
+	  Enable wwnr (wakeup while not running) sample monitor, this is a
+	  sample monitor that illustrates the usage of per-task monitor.
+	  The model is borken on purpose: it serves to test reactors.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_wwnr.rst
+
+config RV_REACTORS
+	bool "Runtime verification reactors"
+	default y
+	depends on RV
+	help
+	  Enables the online runtime verification reactors. A runtime
+	  monitor can cause a reaction to the detection of an exception
+	  on the model's execution. By default, the monitors have
+	  tracing reactions, printing the monitor output via tracepoints,
+	  but other reactions can be added (on-demand) via this interface.
+
+config RV_REACT_PRINTK
+	bool "Printk reactor"
+	depends on RV_REACTORS
+	default y
+	help
+	  Enables the printk reactor. The printk reactor emits a printk()
+	  message if an exception is found.
+
+config RV_REACT_PANIC
+	bool "Panic reactor"
+	depends on RV_REACTORS
+	default y
+	help
+	  Enables the panic reactor. The panic reactor emits a printk()
+	  message if an exception is found and panic()s the system.
diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile
new file mode 100644
index 000000000000..963d14875b45
--- /dev/null
+++ b/kernel/trace/rv/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_RV) += rv.o
+obj-$(CONFIG_RV_MON_WIP) += monitors/wip/wip.o
+obj-$(CONFIG_RV_MON_WWNR) += monitors/wwnr/wwnr.o
+obj-$(CONFIG_RV_REACTORS) += rv_reactors.o
+obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o
+obj-$(CONFIG_RV_REACT_PANIC) += reactor_panic.o
diff --git a/kernel/trace/rv/monitors/wip/wip.c b/kernel/trace/rv/monitors/wip/wip.c
new file mode 100644
index 000000000000..b2b49a27e886
--- /dev/null
+++ b/kernel/trace/rv/monitors/wip/wip.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+#include <rv/da_monitor.h>
+
+#define MODULE_NAME "wip"
+
+#include <trace/events/rv.h>
+#include <trace/events/sched.h>
+#include <trace/events/preemptirq.h>
+
+#include "wip.h"
+
+static struct rv_monitor rv_wip;
+DECLARE_DA_MON_PER_CPU(wip, unsigned char);
+
+static void handle_preempt_disable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_event_wip(preempt_disable_wip);
+}
+
+static void handle_preempt_enable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_start_event_wip(preempt_enable_wip);
+}
+
+static void handle_sched_waking(void *data, struct task_struct *task)
+{
+	da_handle_event_wip(sched_waking_wip);
+}
+
+static int enable_wip(void)
+{
+	int retval;
+
+	retval = da_monitor_init_wip();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("wip", preempt_enable, handle_preempt_enable);
+	rv_attach_trace_probe("wip", sched_waking, handle_sched_waking);
+	rv_attach_trace_probe("wip", preempt_disable, handle_preempt_disable);
+
+	return 0;
+}
+
+static void disable_wip(void)
+{
+	rv_wip.enabled = 0;
+
+	rv_detach_trace_probe("wip", preempt_disable, handle_preempt_disable);
+	rv_detach_trace_probe("wip", preempt_enable, handle_preempt_enable);
+	rv_detach_trace_probe("wip", sched_waking, handle_sched_waking);
+
+	da_monitor_destroy_wip();
+}
+
+static struct rv_monitor rv_wip = {
+	.name = "wip",
+	.description = "wakeup in preemptive per-cpu testing monitor.",
+	.enable = enable_wip,
+	.disable = disable_wip,
+	.reset = da_monitor_reset_all_wip,
+	.enabled = 0,
+};
+
+static int __init register_wip(void)
+{
+	rv_register_monitor(&rv_wip);
+	return 0;
+}
+
+static void __exit unregister_wip(void)
+{
+	rv_unregister_monitor(&rv_wip);
+}
+
+module_init(register_wip);
+module_exit(unregister_wip);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Bristot de Oliveira <bristot@kernel.org>");
+MODULE_DESCRIPTION("wip: wakeup in preemptive - per-cpu sample monitor.");
diff --git a/kernel/trace/rv/monitors/wip/wip.h b/kernel/trace/rv/monitors/wip/wip.h
new file mode 100644
index 000000000000..dacc37b62a2c
--- /dev/null
+++ b/kernel/trace/rv/monitors/wip/wip.h
@@ -0,0 +1,46 @@
+/*
+ * Automatically generated C representation of wip automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+enum states_wip {
+	preemptive_wip = 0,
+	non_preemptive_wip,
+	state_max_wip
+};
+
+#define INVALID_STATE state_max_wip
+
+enum events_wip {
+	preempt_disable_wip = 0,
+	preempt_enable_wip,
+	sched_waking_wip,
+	event_max_wip
+};
+
+struct automaton_wip {
+	char *state_names[state_max_wip];
+	char *event_names[event_max_wip];
+	unsigned char function[state_max_wip][event_max_wip];
+	unsigned char initial_state;
+	bool final_states[state_max_wip];
+};
+
+static struct automaton_wip automaton_wip = {
+	.state_names = {
+		"preemptive",
+		"non_preemptive"
+	},
+	.event_names = {
+		"preempt_disable",
+		"preempt_enable",
+		"sched_waking"
+	},
+	.function = {
+		{ non_preemptive_wip,      INVALID_STATE,      INVALID_STATE },
+		{      INVALID_STATE,     preemptive_wip, non_preemptive_wip },
+	},
+	.initial_state = preemptive_wip,
+	.final_states = { 1, 0 },
+};
diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.c b/kernel/trace/rv/monitors/wwnr/wwnr.c
new file mode 100644
index 000000000000..0e43dd2db685
--- /dev/null
+++ b/kernel/trace/rv/monitors/wwnr/wwnr.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+#include <rv/da_monitor.h>
+
+#define MODULE_NAME "wwnr"
+
+#include <trace/events/rv.h>
+#include <trace/events/sched.h>
+
+#include "wwnr.h"
+
+static struct rv_monitor rv_wwnr;
+DECLARE_DA_MON_PER_TASK(wwnr, unsigned char);
+
+static void handle_switch(void *data, bool preempt, struct task_struct *p,
+			  struct task_struct *n, unsigned int prev_state)
+{
+	/* start monitoring only after the first suspension */
+	if (prev_state == TASK_INTERRUPTIBLE)
+		da_handle_start_event_wwnr(p, switch_out_wwnr);
+	else
+		da_handle_event_wwnr(p, switch_out_wwnr);
+
+	da_handle_event_wwnr(n, switch_in_wwnr);
+}
+
+static void handle_wakeup(void *data, struct task_struct *p)
+{
+	da_handle_event_wwnr(p, wakeup_wwnr);
+}
+
+static int enable_wwnr(void)
+{
+	int retval;
+
+	retval = da_monitor_init_wwnr();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("wwnr", sched_switch, handle_switch);
+	rv_attach_trace_probe("wwnr", sched_wakeup, handle_wakeup);
+
+	return 0;
+}
+
+static void disable_wwnr(void)
+{
+	rv_wwnr.enabled = 0;
+
+	rv_detach_trace_probe("wwnr", sched_switch, handle_switch);
+	rv_detach_trace_probe("wwnr", sched_wakeup, handle_wakeup);
+
+	da_monitor_destroy_wwnr();
+}
+
+static struct rv_monitor rv_wwnr = {
+	.name = "wwnr",
+	.description = "wakeup while not running per-task testing model.",
+	.enable = enable_wwnr,
+	.disable = disable_wwnr,
+	.reset = da_monitor_reset_all_wwnr,
+	.enabled = 0,
+};
+
+static int __init register_wwnr(void)
+{
+	rv_register_monitor(&rv_wwnr);
+	return 0;
+}
+
+static void __exit unregister_wwnr(void)
+{
+	rv_unregister_monitor(&rv_wwnr);
+}
+
+module_init(register_wwnr);
+module_exit(unregister_wwnr);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Bristot de Oliveira <bristot@kernel.org>");
+MODULE_DESCRIPTION("wwnr: wakeup while not running monitor");
diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.h b/kernel/trace/rv/monitors/wwnr/wwnr.h
new file mode 100644
index 000000000000..118e576b91b4
--- /dev/null
+++ b/kernel/trace/rv/monitors/wwnr/wwnr.h
@@ -0,0 +1,46 @@
+/*
+ * Automatically generated C representation of wwnr automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+enum states_wwnr {
+	not_running_wwnr = 0,
+	running_wwnr,
+	state_max_wwnr
+};
+
+#define INVALID_STATE state_max_wwnr
+
+enum events_wwnr {
+	switch_in_wwnr = 0,
+	switch_out_wwnr,
+	wakeup_wwnr,
+	event_max_wwnr
+};
+
+struct automaton_wwnr {
+	char *state_names[state_max_wwnr];
+	char *event_names[event_max_wwnr];
+	unsigned char function[state_max_wwnr][event_max_wwnr];
+	unsigned char initial_state;
+	bool final_states[state_max_wwnr];
+};
+
+static struct automaton_wwnr automaton_wwnr = {
+	.state_names = {
+		"not_running",
+		"running"
+	},
+	.event_names = {
+		"switch_in",
+		"switch_out",
+		"wakeup"
+	},
+	.function = {
+		{       running_wwnr,      INVALID_STATE,   not_running_wwnr },
+		{      INVALID_STATE,   not_running_wwnr,      INVALID_STATE },
+	},
+	.initial_state = not_running_wwnr,
+	.final_states = { 1, 0 },
+};
diff --git a/kernel/trace/rv/reactor_panic.c b/kernel/trace/rv/reactor_panic.c
new file mode 100644
index 000000000000..d65f6c25a87c
--- /dev/null
+++ b/kernel/trace/rv/reactor_panic.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019-2022 Red Hat, Inc. Daniel Bristot de Oliveira <bristot@kernel.org>
+ *
+ * Panic RV reactor:
+ *   Prints the exception msg to the kernel message log and panic().
+ */
+
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+
+static void rv_panic_reaction(char *msg)
+{
+	panic(msg);
+}
+
+static struct rv_reactor rv_panic = {
+	.name = "panic",
+	.description = "panic the system if an exception is found.",
+	.react = rv_panic_reaction
+};
+
+static int __init register_react_panic(void)
+{
+	rv_register_reactor(&rv_panic);
+	return 0;
+}
+
+static void __exit unregister_react_panic(void)
+{
+	rv_unregister_reactor(&rv_panic);
+}
+
+module_init(register_react_panic);
+module_exit(unregister_react_panic);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Bristot de Oliveira");
+MODULE_DESCRIPTION("panic rv reactor: panic if an exception is found.");
diff --git a/kernel/trace/rv/reactor_printk.c b/kernel/trace/rv/reactor_printk.c
new file mode 100644
index 000000000000..4b6b7106a477
--- /dev/null
+++ b/kernel/trace/rv/reactor_printk.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019-2022 Red Hat, Inc. Daniel Bristot de Oliveira <bristot@kernel.org>
+ *
+ * Printk RV reactor:
+ *   Prints the exception msg to the kernel message log.
+ */
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+
+static void rv_printk_reaction(char *msg)
+{
+	printk_deferred(msg);
+}
+
+static struct rv_reactor rv_printk = {
+	.name = "printk",
+	.description = "prints the exception msg to the kernel message log.",
+	.react = rv_printk_reaction
+};
+
+static int __init register_react_printk(void)
+{
+	rv_register_reactor(&rv_printk);
+	return 0;
+}
+
+static void __exit unregister_react_printk(void)
+{
+	rv_unregister_reactor(&rv_printk);
+}
+
+module_init(register_react_printk);
+module_exit(unregister_react_printk);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Bristot de Oliveira");
+MODULE_DESCRIPTION("printk rv reactor: printk if an exception is hit.");
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
new file mode 100644
index 000000000000..6c97cc2d754a
--- /dev/null
+++ b/kernel/trace/rv/rv.c
@@ -0,0 +1,799 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019-2022 Red Hat, Inc. Daniel Bristot de Oliveira <bristot@kernel.org>
+ *
+ * This is the online Runtime Verification (RV) interface.
+ *
+ * RV is a lightweight (yet rigorous) method that complements classical
+ * exhaustive verification techniques (such as model checking and
+ * theorem proving) with a more practical approach to complex systems.
+ *
+ * RV works by analyzing the trace of the system's actual execution,
+ * comparing it against a formal specification of the system behavior.
+ * RV can give precise information on the runtime behavior of the
+ * monitored system while enabling the reaction for unexpected
+ * events, avoiding, for example, the propagation of a failure on
+ * safety-critical systems.
+ *
+ * The development of this interface roots in the development of the
+ * paper:
+ *
+ * De Oliveira, Daniel Bristot; Cucinotta, Tommaso; De Oliveira, Romulo
+ * Silva. Efficient formal verification for the Linux kernel. In:
+ * International Conference on Software Engineering and Formal Methods.
+ * Springer, Cham, 2019. p. 315-332.
+ *
+ * And:
+ *
+ * De Oliveira, Daniel Bristot, et al. Automata-based formal analysis
+ * and verification of the real-time Linux kernel. PhD Thesis, 2020.
+ *
+ * == Runtime monitor interface ==
+ *
+ * A monitor is the central part of the runtime verification of a system.
+ *
+ * The monitor stands in between the formal specification of the desired
+ * (or undesired) behavior, and the trace of the actual system.
+ *
+ * In Linux terms, the runtime verification monitors are encapsulated
+ * inside the "RV monitor" abstraction. A RV monitor includes a reference
+ * model of the system, a set of instances of the monitor (per-cpu monitor,
+ * per-task monitor, and so on), and the helper functions that glue the
+ * monitor to the system via trace. Generally, a monitor includes some form
+ * of trace output as a reaction for event parsing and exceptions,
+ * as depicted bellow:
+ *
+ * Linux  +----- RV Monitor ----------------------------------+ Formal
+ *  Realm |                                                   |  Realm
+ *  +-------------------+     +----------------+     +-----------------+
+ *  |   Linux kernel    |     |     Monitor    |     |     Reference   |
+ *  |     Tracing       |  -> |   Instance(s)  | <-  |       Model     |
+ *  | (instrumentation) |     | (verification) |     | (specification) |
+ *  +-------------------+     +----------------+     +-----------------+
+ *         |                          |                       |
+ *         |                          V                       |
+ *         |                     +----------+                 |
+ *         |                     | Reaction |                 |
+ *         |                     +--+--+--+-+                 |
+ *         |                        |  |  |                   |
+ *         |                        |  |  +-> trace output ?  |
+ *         +------------------------|--|----------------------+
+ *                                  |  +----> panic ?
+ *                                  +-------> <user-specified>
+ *
+ * This file implements the interface for loading RV monitors, and
+ * to control the verification session.
+ *
+ * == Registering monitors ==
+ *
+ * The struct rv_monitor defines a set of callback functions to control
+ * a verification session. For instance, when a given monitor is enabled,
+ * the "enable" callback function is called to hook the instrumentation
+ * functions to the kernel trace events. The "disable" function is called
+ * when disabling the verification session.
+ *
+ * A RV monitor is registered via:
+ *   int rv_register_monitor(struct rv_monitor *monitor);
+ * And unregistered via:
+ *   int rv_unregister_monitor(struct rv_monitor *monitor);
+ *
+ * == User interface ==
+ *
+ * The user interface resembles kernel tracing interface. It presents
+ * these files:
+ *
+ *  "available_monitors"
+ *    - List the available monitors, one per line.
+ *
+ *    For example:
+ *      # cat available_monitors
+ *      wip
+ *      wwnr
+ *
+ *  "enabled_monitors"
+ *    - Lists the enabled monitors, one per line;
+ *    - Writing to it enables a given monitor;
+ *    - Writing a monitor name with a '!' prefix disables it;
+ *    - Truncating the file disables all enabled monitors.
+ *
+ *    For example:
+ *      # cat enabled_monitors
+ *      # echo wip > enabled_monitors
+ *      # echo wwnr >> enabled_monitors
+ *      # cat enabled_monitors
+ *      wip
+ *      wwnr
+ *      # echo '!wip' >> enabled_monitors
+ *      # cat enabled_monitors
+ *      wwnr
+ *      # echo > enabled_monitors
+ *      # cat enabled_monitors
+ *      #
+ *
+ *    Note that more than one monitor can be enabled concurrently.
+ *
+ *  "monitoring_on"
+ *    - It is an on/off general switcher for monitoring. Note
+ *    that it does not disable enabled monitors or detach events,
+ *    but stops the per-entity monitors from monitoring the events
+ *    received from the instrumentation. It resembles the "tracing_on"
+ *    switcher.
+ *
+ *  "monitors/"
+ *    Each monitor will have its own directory inside "monitors/". There
+ *    the monitor specific files will be presented.
+ *    The "monitors/" directory resembles the "events" directory on
+ *    tracefs.
+ *
+ *    For example:
+ *      # cd monitors/wip/
+ *      # ls
+ *      desc  enable
+ *      # cat desc
+ *      auto-generated wakeup in preemptive monitor.
+ *      # cat enable
+ *      0
+ *
+ *  For further information, see:
+ *   Documentation/trace/rv/runtime-verification.rst
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+
+#ifdef CONFIG_DA_MON_EVENTS
+#define CREATE_TRACE_POINTS
+#include <trace/events/rv.h>
+#endif
+
+#include "rv.h"
+
+DEFINE_MUTEX(rv_interface_lock);
+
+static struct rv_interface rv_root;
+
+struct dentry *get_monitors_root(void)
+{
+	return rv_root.monitors_dir;
+}
+
+/*
+ * Interface for the monitor register.
+ */
+static LIST_HEAD(rv_monitors_list);
+
+static int task_monitor_count;
+static bool task_monitor_slots[RV_PER_TASK_MONITORS];
+
+int rv_get_task_monitor_slot(void)
+{
+	int i;
+
+	lockdep_assert_held(&rv_interface_lock);
+
+	if (task_monitor_count == RV_PER_TASK_MONITORS)
+		return -EBUSY;
+
+	task_monitor_count++;
+
+	for (i = 0; i < RV_PER_TASK_MONITORS; i++) {
+		if (task_monitor_slots[i] == false) {
+			task_monitor_slots[i] = true;
+			return i;
+		}
+	}
+
+	WARN_ONCE(1, "RV task_monitor_count and slots are out of sync\n");
+
+	return -EINVAL;
+}
+
+void rv_put_task_monitor_slot(int slot)
+{
+	lockdep_assert_held(&rv_interface_lock);
+
+	if (slot < 0 || slot >= RV_PER_TASK_MONITORS) {
+		WARN_ONCE(1, "RV releasing an invalid slot!: %d\n", slot);
+		return;
+	}
+
+	WARN_ONCE(!task_monitor_slots[slot], "RV releasing unused task_monitor_slots: %d\n",
+		  slot);
+
+	task_monitor_count--;
+	task_monitor_slots[slot] = false;
+}
+
+/*
+ * This section collects the monitor/ files and folders.
+ */
+static ssize_t monitor_enable_read_data(struct file *filp, char __user *user_buf, size_t count,
+					loff_t *ppos)
+{
+	struct rv_monitor_def *mdef = filp->private_data;
+	const char *buff;
+
+	buff = mdef->monitor->enabled ? "1\n" : "0\n";
+
+	return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff)+1);
+}
+
+/*
+ * __rv_disable_monitor - disabled an enabled monitor
+ */
+static int __rv_disable_monitor(struct rv_monitor_def *mdef, bool sync)
+{
+	lockdep_assert_held(&rv_interface_lock);
+
+	if (mdef->monitor->enabled) {
+		mdef->monitor->enabled = 0;
+		mdef->monitor->disable();
+
+		/*
+		 * Wait for the execution of all events to finish.
+		 * Otherwise, the data used by the monitor could
+		 * be inconsistent. i.e., if the monitor is re-enabled.
+		 */
+		if (sync)
+			tracepoint_synchronize_unregister();
+		return 1;
+	}
+	return 0;
+}
+
+/**
+ * rv_disable_monitor - disable a given runtime monitor
+ *
+ * Returns 0 on success.
+ */
+int rv_disable_monitor(struct rv_monitor_def *mdef)
+{
+	__rv_disable_monitor(mdef, true);
+	return 0;
+}
+
+/**
+ * rv_enable_monitor - enable a given runtime monitor
+ *
+ * Returns 0 on success, error otherwise.
+ */
+int rv_enable_monitor(struct rv_monitor_def *mdef)
+{
+	int retval;
+
+	lockdep_assert_held(&rv_interface_lock);
+
+	if (mdef->monitor->enabled)
+		return 0;
+
+	retval = mdef->monitor->enable();
+
+	if (!retval)
+		mdef->monitor->enabled = 1;
+
+	return retval;
+}
+
+/*
+ * interface for enabling/disabling a monitor.
+ */
+static ssize_t monitor_enable_write_data(struct file *filp, const char __user *user_buf,
+					 size_t count, loff_t *ppos)
+{
+	struct rv_monitor_def *mdef = filp->private_data;
+	int retval;
+	bool val;
+
+	retval = kstrtobool_from_user(user_buf, count, &val);
+	if (retval)
+		return retval;
+
+	retval = count;
+
+	mutex_lock(&rv_interface_lock);
+
+	if (val)
+		retval = rv_enable_monitor(mdef);
+	else
+		retval = rv_disable_monitor(mdef);
+
+	mutex_unlock(&rv_interface_lock);
+
+	return retval ? : count;
+}
+
+static const struct file_operations interface_enable_fops = {
+	.open   = simple_open,
+	.llseek = no_llseek,
+	.write  = monitor_enable_write_data,
+	.read   = monitor_enable_read_data,
+};
+
+/*
+ * Interface to read monitors description.
+ */
+static ssize_t monitor_desc_read_data(struct file *filp, char __user *user_buf, size_t count,
+				      loff_t *ppos)
+{
+	struct rv_monitor_def *mdef = filp->private_data;
+	char buff[256];
+
+	memset(buff, 0, sizeof(buff));
+
+	snprintf(buff, sizeof(buff), "%s\n", mdef->monitor->description);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff) + 1);
+}
+
+static const struct file_operations interface_desc_fops = {
+	.open   = simple_open,
+	.llseek	= no_llseek,
+	.read	= monitor_desc_read_data,
+};
+
+/*
+ * During the registration of a monitor, this function creates
+ * the monitor dir, where the specific options of the monitor
+ * are exposed.
+ */
+static int create_monitor_dir(struct rv_monitor_def *mdef)
+{
+	struct dentry *root = get_monitors_root();
+	const char *name = mdef->monitor->name;
+	struct dentry *tmp;
+	int retval;
+
+	mdef->root_d = rv_create_dir(name, root);
+	if (!mdef->root_d)
+		return -ENOMEM;
+
+	tmp = rv_create_file("enable", RV_MODE_WRITE, mdef->root_d, mdef, &interface_enable_fops);
+	if (!tmp) {
+		retval = -ENOMEM;
+		goto out_remove_root;
+	}
+
+	tmp = rv_create_file("desc", RV_MODE_READ, mdef->root_d, mdef, &interface_desc_fops);
+	if (!tmp) {
+		retval = -ENOMEM;
+		goto out_remove_root;
+	}
+
+	retval = reactor_populate_monitor(mdef);
+	if (retval)
+		goto out_remove_root;
+
+	return 0;
+
+out_remove_root:
+	rv_remove(mdef->root_d);
+	return retval;
+}
+
+/*
+ * Available/Enable monitor shared seq functions.
+ */
+static int monitors_show(struct seq_file *m, void *p)
+{
+	struct rv_monitor_def *mon_def = p;
+
+	seq_printf(m, "%s\n", mon_def->monitor->name);
+	return 0;
+}
+
+/*
+ * Used by the seq file operations at the end of a read
+ * operation.
+ */
+static void monitors_stop(struct seq_file *m, void *p)
+{
+	mutex_unlock(&rv_interface_lock);
+}
+
+/*
+ * Available monitor seq functions.
+ */
+static void *available_monitors_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&rv_interface_lock);
+	return seq_list_start(&rv_monitors_list, *pos);
+}
+
+static void *available_monitors_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next(p, &rv_monitors_list, pos);
+}
+
+/*
+ * Enable monitor seq functions.
+ */
+static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct rv_monitor_def *m_def = p;
+
+	(*pos)++;
+
+	list_for_each_entry_continue(m_def, &rv_monitors_list, list) {
+		if (m_def->monitor->enabled)
+			return m_def;
+	}
+
+	return NULL;
+}
+
+static void *enabled_monitors_start(struct seq_file *m, loff_t *pos)
+{
+	struct rv_monitor_def *m_def;
+	loff_t l;
+
+	mutex_lock(&rv_interface_lock);
+
+	if (list_empty(&rv_monitors_list))
+		return NULL;
+
+	m_def = list_entry(&rv_monitors_list, struct rv_monitor_def, list);
+
+	for (l = 0; l <= *pos; ) {
+		m_def = enabled_monitors_next(m, m_def, &l);
+		if (!m_def)
+			break;
+	}
+
+	return m_def;
+}
+
+/*
+ * available/enabled monitors seq definition.
+ */
+static const struct seq_operations available_monitors_seq_ops = {
+	.start	= available_monitors_start,
+	.next	= available_monitors_next,
+	.stop	= monitors_stop,
+	.show	= monitors_show
+};
+
+static const struct seq_operations enabled_monitors_seq_ops = {
+	.start  = enabled_monitors_start,
+	.next   = enabled_monitors_next,
+	.stop   = monitors_stop,
+	.show   = monitors_show
+};
+
+/*
+ * available_monitors interface.
+ */
+static int available_monitors_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &available_monitors_seq_ops);
+};
+
+static const struct file_operations available_monitors_ops = {
+	.open    = available_monitors_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+/*
+ * enabled_monitors interface.
+ */
+static void disable_all_monitors(void)
+{
+	struct rv_monitor_def *mdef;
+	int enabled = 0;
+
+	mutex_lock(&rv_interface_lock);
+
+	list_for_each_entry(mdef, &rv_monitors_list, list)
+		enabled += __rv_disable_monitor(mdef, false);
+
+	if (enabled) {
+		/*
+		 * Wait for the execution of all events to finish.
+		 * Otherwise, the data used by the monitor could
+		 * be inconsistent. i.e., if the monitor is re-enabled.
+		 */
+		tracepoint_synchronize_unregister();
+	}
+
+	mutex_unlock(&rv_interface_lock);
+}
+
+static int enabled_monitors_open(struct inode *inode, struct file *file)
+{
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC))
+		disable_all_monitors();
+
+	return seq_open(file, &enabled_monitors_seq_ops);
+};
+
+static ssize_t enabled_monitors_write(struct file *filp, const char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	char buff[MAX_RV_MONITOR_NAME_SIZE + 2];
+	struct rv_monitor_def *mdef;
+	int retval = -EINVAL;
+	bool enable = true;
+	char *ptr = buff;
+	int len;
+
+	if (count < 1 || count > MAX_RV_MONITOR_NAME_SIZE + 1)
+		return -EINVAL;
+
+	memset(buff, 0, sizeof(buff));
+
+	retval = simple_write_to_buffer(buff, sizeof(buff) - 1, ppos, user_buf, count);
+	if (retval < 0)
+		return -EFAULT;
+
+	ptr = strim(buff);
+
+	if (ptr[0] == '!') {
+		enable = false;
+		ptr++;
+	}
+
+	len = strlen(ptr);
+	if (!len)
+		return count;
+
+	mutex_lock(&rv_interface_lock);
+
+	retval = -EINVAL;
+
+	list_for_each_entry(mdef, &rv_monitors_list, list) {
+		if (strcmp(ptr, mdef->monitor->name) != 0)
+			continue;
+
+		/*
+		 * Monitor found!
+		 */
+		if (enable)
+			retval = rv_enable_monitor(mdef);
+		else
+			retval = rv_disable_monitor(mdef);
+
+		if (!retval)
+			retval = count;
+
+		break;
+	}
+
+	mutex_unlock(&rv_interface_lock);
+	return retval;
+}
+
+static const struct file_operations enabled_monitors_ops = {
+	.open		= enabled_monitors_open,
+	.read		= seq_read,
+	.write		= enabled_monitors_write,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+/*
+ * Monitoring on global switcher!
+ */
+static bool __read_mostly monitoring_on;
+
+/**
+ * rv_monitoring_on - checks if monitoring is on
+ *
+ * Returns 1 if on, 0 otherwise.
+ */
+bool rv_monitoring_on(void)
+{
+	/* Ensures that concurrent monitors read consistent monitoring_on */
+	smp_rmb();
+	return READ_ONCE(monitoring_on);
+}
+
+/*
+ * monitoring_on general switcher.
+ */
+static ssize_t monitoring_on_read_data(struct file *filp, char __user *user_buf,
+				       size_t count, loff_t *ppos)
+{
+	const char *buff;
+
+	buff = rv_monitoring_on() ? "1\n" : "0\n";
+
+	return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff) + 1);
+}
+
+static void turn_monitoring_off(void)
+{
+	WRITE_ONCE(monitoring_on, false);
+	/* Ensures that concurrent monitors read consistent monitoring_on */
+	smp_wmb();
+}
+
+static void reset_all_monitors(void)
+{
+	struct rv_monitor_def *mdef;
+
+	list_for_each_entry(mdef, &rv_monitors_list, list) {
+		if (mdef->monitor->enabled)
+			mdef->monitor->reset();
+	}
+}
+
+static void turn_monitoring_on(void)
+{
+	WRITE_ONCE(monitoring_on, true);
+	/* Ensures that concurrent monitors read consistent monitoring_on */
+	smp_wmb();
+}
+
+static void turn_monitoring_on_with_reset(void)
+{
+	lockdep_assert_held(&rv_interface_lock);
+
+	if (rv_monitoring_on())
+		return;
+
+	/*
+	 * Monitors might be out of sync with the system if events were not
+	 * processed because of !rv_monitoring_on().
+	 *
+	 * Reset all monitors, forcing a re-sync.
+	 */
+	reset_all_monitors();
+	turn_monitoring_on();
+}
+
+static ssize_t monitoring_on_write_data(struct file *filp, const char __user *user_buf,
+					size_t count, loff_t *ppos)
+{
+	int retval;
+	bool val;
+
+	retval = kstrtobool_from_user(user_buf, count, &val);
+	if (retval)
+		return retval;
+
+	mutex_lock(&rv_interface_lock);
+
+	if (val)
+		turn_monitoring_on_with_reset();
+	else
+		turn_monitoring_off();
+
+	/*
+	 * Wait for the execution of all events to finish
+	 * before returning to user-space.
+	 */
+	tracepoint_synchronize_unregister();
+
+	mutex_unlock(&rv_interface_lock);
+
+	return count;
+}
+
+static const struct file_operations monitoring_on_fops = {
+	.open   = simple_open,
+	.llseek = no_llseek,
+	.write  = monitoring_on_write_data,
+	.read   = monitoring_on_read_data,
+};
+
+static void destroy_monitor_dir(struct rv_monitor_def *mdef)
+{
+	reactor_cleanup_monitor(mdef);
+	rv_remove(mdef->root_d);
+}
+
+/**
+ * rv_register_monitor - register a rv monitor.
+ * @monitor:    The rv_monitor to be registered.
+ *
+ * Returns 0 if successful, error otherwise.
+ */
+int rv_register_monitor(struct rv_monitor *monitor)
+{
+	struct rv_monitor_def *r;
+	int retval = 0;
+
+	if (strlen(monitor->name) >= MAX_RV_MONITOR_NAME_SIZE) {
+		pr_info("Monitor %s has a name longer than %d\n", monitor->name,
+			MAX_RV_MONITOR_NAME_SIZE);
+		return -1;
+	}
+
+	mutex_lock(&rv_interface_lock);
+
+	list_for_each_entry(r, &rv_monitors_list, list) {
+		if (strcmp(monitor->name, r->monitor->name) == 0) {
+			pr_info("Monitor %s is already registered\n", monitor->name);
+			retval = -1;
+			goto out_unlock;
+		}
+	}
+
+	r = kzalloc(sizeof(struct rv_monitor_def), GFP_KERNEL);
+	if (!r) {
+		retval = -ENOMEM;
+		goto out_unlock;
+	}
+
+	r->monitor = monitor;
+
+	retval = create_monitor_dir(r);
+	if (retval) {
+		kfree(r);
+		goto out_unlock;
+	}
+
+	list_add_tail(&r->list, &rv_monitors_list);
+
+out_unlock:
+	mutex_unlock(&rv_interface_lock);
+	return retval;
+}
+
+/**
+ * rv_unregister_monitor - unregister a rv monitor.
+ * @monitor:    The rv_monitor to be unregistered.
+ *
+ * Returns 0 if successful, error otherwise.
+ */
+int rv_unregister_monitor(struct rv_monitor *monitor)
+{
+	struct rv_monitor_def *ptr, *next;
+
+	mutex_lock(&rv_interface_lock);
+
+	list_for_each_entry_safe(ptr, next, &rv_monitors_list, list) {
+		if (strcmp(monitor->name, ptr->monitor->name) == 0) {
+			rv_disable_monitor(ptr);
+			list_del(&ptr->list);
+			destroy_monitor_dir(ptr);
+		}
+	}
+
+	mutex_unlock(&rv_interface_lock);
+	return 0;
+}
+
+int __init rv_init_interface(void)
+{
+	struct dentry *tmp;
+	int retval;
+
+	rv_root.root_dir = rv_create_dir("rv", NULL);
+	if (!rv_root.root_dir)
+		goto out_err;
+
+	rv_root.monitors_dir = rv_create_dir("monitors", rv_root.root_dir);
+	if (!rv_root.monitors_dir)
+		goto out_err;
+
+	tmp = rv_create_file("available_monitors", RV_MODE_READ, rv_root.root_dir, NULL,
+			     &available_monitors_ops);
+	if (!tmp)
+		goto out_err;
+
+	tmp = rv_create_file("enabled_monitors", RV_MODE_WRITE, rv_root.root_dir, NULL,
+			     &enabled_monitors_ops);
+	if (!tmp)
+		goto out_err;
+
+	tmp = rv_create_file("monitoring_on", RV_MODE_WRITE, rv_root.root_dir, NULL,
+			     &monitoring_on_fops);
+	if (!tmp)
+		goto out_err;
+	retval = init_rv_reactors(rv_root.root_dir);
+	if (retval)
+		goto out_err;
+
+	turn_monitoring_on();
+
+	return 0;
+
+out_err:
+	rv_remove(rv_root.root_dir);
+	printk(KERN_ERR "RV: Error while creating the RV interface\n");
+	return 1;
+}
diff --git a/kernel/trace/rv/rv.h b/kernel/trace/rv/rv.h
new file mode 100644
index 000000000000..db6cb0913dbd
--- /dev/null
+++ b/kernel/trace/rv/rv.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/mutex.h>
+
+struct rv_interface {
+	struct dentry		*root_dir;
+	struct dentry		*monitors_dir;
+};
+
+#include "../trace.h"
+#include <linux/tracefs.h>
+#include <linux/rv.h>
+
+#define RV_MODE_WRITE			TRACE_MODE_WRITE
+#define RV_MODE_READ			TRACE_MODE_READ
+
+#define rv_create_dir			tracefs_create_dir
+#define rv_create_file			tracefs_create_file
+#define rv_remove			tracefs_remove
+
+#define MAX_RV_MONITOR_NAME_SIZE	32
+#define MAX_RV_REACTOR_NAME_SIZE	32
+
+extern struct mutex rv_interface_lock;
+
+#ifdef CONFIG_RV_REACTORS
+struct rv_reactor_def {
+	struct list_head	list;
+	struct rv_reactor	*reactor;
+	/* protected by the monitor interface lock */
+	int			counter;
+};
+#endif
+
+struct rv_monitor_def {
+	struct list_head	list;
+	struct rv_monitor	*monitor;
+	struct dentry		*root_d;
+#ifdef CONFIG_RV_REACTORS
+	struct rv_reactor_def	*rdef;
+	bool			reacting;
+#endif
+	bool			task_monitor;
+};
+
+struct dentry *get_monitors_root(void);
+int rv_disable_monitor(struct rv_monitor_def *mdef);
+int rv_enable_monitor(struct rv_monitor_def *mdef);
+
+#ifdef CONFIG_RV_REACTORS
+int reactor_populate_monitor(struct rv_monitor_def *mdef);
+void reactor_cleanup_monitor(struct rv_monitor_def *mdef);
+int init_rv_reactors(struct dentry *root_dir);
+#else
+static inline int reactor_populate_monitor(struct rv_monitor_def *mdef)
+{
+	return 0;
+}
+
+static inline void reactor_cleanup_monitor(struct rv_monitor_def *mdef)
+{
+	return;
+}
+
+static inline int init_rv_reactors(struct dentry *root_dir)
+{
+	return 0;
+}
+#endif
diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c
new file mode 100644
index 000000000000..6aae106695b6
--- /dev/null
+++ b/kernel/trace/rv/rv_reactors.c
@@ -0,0 +1,510 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019-2022 Red Hat, Inc. Daniel Bristot de Oliveira <bristot@kernel.org>
+ *
+ * Runtime reactor interface.
+ *
+ * A runtime monitor can cause a reaction to the detection of an
+ * exception on the model's execution. By default, the monitors have
+ * tracing reactions, printing the monitor output via tracepoints.
+ * But other reactions can be added (on-demand) via this interface.
+ *
+ * == Registering reactors ==
+ *
+ * The struct rv_reactor defines a callback function to be executed
+ * in case of a model exception happens. The callback function
+ * receives a message to be (optionally) printed before executing
+ * the reaction.
+ *
+ * A RV reactor is registered via:
+ *   int rv_register_reactor(struct rv_reactor *reactor)
+ * And unregistered via:
+ *   int rv_unregister_reactor(struct rv_reactor *reactor)
+ *
+ * These functions are exported to modules, enabling reactors to be
+ * dynamically loaded.
+ *
+ * == User interface ==
+ *
+ * The user interface resembles the kernel tracing interface and
+ * presents these files:
+ *
+ *  "available_reactors"
+ *    - List the available reactors, one per line.
+ *
+ *    For example:
+ *      # cat available_reactors
+ *      nop
+ *      panic
+ *      printk
+ *
+ *  "reacting_on"
+ *    - It is an on/off general switch for reactors, disabling
+ *    all reactions.
+ *
+ *  "monitors/MONITOR/reactors"
+ *    - List available reactors, with the select reaction for the given
+ *    MONITOR inside []. The default one is the nop (no operation)
+ *    reactor.
+ *    - Writing the name of an reactor enables it to the given
+ *    MONITOR.
+ *
+ *    For example:
+ *      # cat monitors/wip/reactors
+ *      [nop]
+ *      panic
+ *      printk
+ *      # echo panic > monitors/wip/reactors
+ *      # cat monitors/wip/reactors
+ *      nop
+ *      [panic]
+ *      printk
+ */
+
+#include <linux/slab.h>
+
+#include "rv.h"
+
+/*
+ * Interface for the reactor register.
+ */
+static LIST_HEAD(rv_reactors_list);
+
+static struct rv_reactor_def *get_reactor_rdef_by_name(char *name)
+{
+	struct rv_reactor_def *r;
+
+	list_for_each_entry(r, &rv_reactors_list, list) {
+		if (strcmp(name, r->reactor->name) == 0)
+			return r;
+	}
+	return NULL;
+}
+
+/*
+ * Available reactors seq functions.
+ */
+static int reactors_show(struct seq_file *m, void *p)
+{
+	struct rv_reactor_def *rea_def = p;
+
+	seq_printf(m, "%s\n", rea_def->reactor->name);
+	return 0;
+}
+
+static void reactors_stop(struct seq_file *m, void *p)
+{
+	mutex_unlock(&rv_interface_lock);
+}
+
+static void *reactors_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&rv_interface_lock);
+	return seq_list_start(&rv_reactors_list, *pos);
+}
+
+static void *reactors_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next(p, &rv_reactors_list, pos);
+}
+
+/*
+ * available_reactors seq definition.
+ */
+static const struct seq_operations available_reactors_seq_ops = {
+	.start	= reactors_start,
+	.next	= reactors_next,
+	.stop	= reactors_stop,
+	.show	= reactors_show
+};
+
+/*
+ * available_reactors interface.
+ */
+static int available_reactors_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &available_reactors_seq_ops);
+};
+
+static const struct file_operations available_reactors_ops = {
+	.open    = available_reactors_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release
+};
+
+/*
+ * Monitor's reactor file.
+ */
+static int monitor_reactor_show(struct seq_file *m, void *p)
+{
+	struct rv_monitor_def *mdef = m->private;
+	struct rv_reactor_def *rdef = p;
+
+	if (mdef->rdef == rdef)
+		seq_printf(m, "[%s]\n", rdef->reactor->name);
+	else
+		seq_printf(m, "%s\n", rdef->reactor->name);
+	return 0;
+}
+
+/*
+ * available_reactors seq definition.
+ */
+static const struct seq_operations monitor_reactors_seq_ops = {
+	.start	= reactors_start,
+	.next	= reactors_next,
+	.stop	= reactors_stop,
+	.show	= monitor_reactor_show
+};
+
+static void monitor_swap_reactors(struct rv_monitor_def *mdef, struct rv_reactor_def *rdef,
+				    bool reacting)
+{
+	bool monitor_enabled;
+
+	/* nothing to do */
+	if (mdef->rdef == rdef)
+		return;
+
+	monitor_enabled = mdef->monitor->enabled;
+	if (monitor_enabled)
+		rv_disable_monitor(mdef);
+
+	/* swap reactor's usage */
+	mdef->rdef->counter--;
+	rdef->counter++;
+
+	mdef->rdef = rdef;
+	mdef->reacting = reacting;
+	mdef->monitor->react = rdef->reactor->react;
+
+	if (monitor_enabled)
+		rv_enable_monitor(mdef);
+}
+
+static ssize_t
+monitor_reactors_write(struct file *file, const char __user *user_buf,
+		      size_t count, loff_t *ppos)
+{
+	char buff[MAX_RV_REACTOR_NAME_SIZE + 2];
+	struct rv_monitor_def *mdef;
+	struct rv_reactor_def *rdef;
+	struct seq_file *seq_f;
+	int retval = -EINVAL;
+	bool enable;
+	char *ptr;
+	int len;
+
+	if (count < 1 || count > MAX_RV_REACTOR_NAME_SIZE + 1)
+		return -EINVAL;
+
+	memset(buff, 0, sizeof(buff));
+
+	retval = simple_write_to_buffer(buff, sizeof(buff) - 1, ppos, user_buf, count);
+	if (retval < 0)
+		return -EFAULT;
+
+	ptr = strim(buff);
+
+	len = strlen(ptr);
+	if (!len)
+		return count;
+
+	/*
+	 * See monitor_reactors_open()
+	 */
+	seq_f = file->private_data;
+	mdef = seq_f->private;
+
+	mutex_lock(&rv_interface_lock);
+
+	retval = -EINVAL;
+
+	list_for_each_entry(rdef, &rv_reactors_list, list) {
+		if (strcmp(ptr, rdef->reactor->name) != 0)
+			continue;
+
+		if (rdef == get_reactor_rdef_by_name("nop"))
+			enable = false;
+		else
+			enable = true;
+
+		monitor_swap_reactors(mdef, rdef, enable);
+
+		retval = count;
+		break;
+	}
+
+	mutex_unlock(&rv_interface_lock);
+
+	return retval;
+}
+
+/*
+ * available_reactors interface.
+ */
+static int monitor_reactors_open(struct inode *inode, struct file *file)
+{
+	struct rv_monitor_def *mdef = inode->i_private;
+	struct seq_file *seq_f;
+	int ret;
+
+	ret = seq_open(file, &monitor_reactors_seq_ops);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * seq_open stores the seq_file on the file->private data.
+	 */
+	seq_f = file->private_data;
+
+	/*
+	 * Copy the create file "private" data to the seq_file private data.
+	 */
+	seq_f->private = mdef;
+
+	return 0;
+};
+
+static const struct file_operations monitor_reactors_ops = {
+	.open    = monitor_reactors_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+	.write = monitor_reactors_write
+};
+
+static int __rv_register_reactor(struct rv_reactor *reactor)
+{
+	struct rv_reactor_def *r;
+
+	list_for_each_entry(r, &rv_reactors_list, list) {
+		if (strcmp(reactor->name, r->reactor->name) == 0) {
+			pr_info("Reactor %s is already registered\n", reactor->name);
+			return -EINVAL;
+		}
+	}
+
+	r = kzalloc(sizeof(struct rv_reactor_def), GFP_KERNEL);
+	if (!r)
+		return -ENOMEM;
+
+	r->reactor = reactor;
+	r->counter = 0;
+
+	list_add_tail(&r->list, &rv_reactors_list);
+
+	return 0;
+}
+
+/**
+ * rv_register_reactor - register a rv reactor.
+ * @reactor:	The rv_reactor to be registered.
+ *
+ * Returns 0 if successful, error otherwise.
+ */
+int rv_register_reactor(struct rv_reactor *reactor)
+{
+	int retval = 0;
+
+	if (strlen(reactor->name) >= MAX_RV_REACTOR_NAME_SIZE) {
+		pr_info("Reactor %s has a name longer than %d\n",
+			reactor->name, MAX_RV_MONITOR_NAME_SIZE);
+		return -EINVAL;
+	}
+
+	mutex_lock(&rv_interface_lock);
+	retval = __rv_register_reactor(reactor);
+	mutex_unlock(&rv_interface_lock);
+	return retval;
+}
+
+/**
+ * rv_unregister_reactor - unregister a rv reactor.
+ * @reactor:	The rv_reactor to be unregistered.
+ *
+ * Returns 0 if successful, error otherwise.
+ */
+int rv_unregister_reactor(struct rv_reactor *reactor)
+{
+	struct rv_reactor_def *ptr, *next;
+	int ret = 0;
+
+	mutex_lock(&rv_interface_lock);
+
+	list_for_each_entry_safe(ptr, next, &rv_reactors_list, list) {
+		if (strcmp(reactor->name, ptr->reactor->name) == 0) {
+
+			if (!ptr->counter) {
+				list_del(&ptr->list);
+			} else {
+				printk(KERN_WARNING
+				       "rv: the rv_reactor %s is in use by %d monitor(s)\n",
+				       ptr->reactor->name, ptr->counter);
+				printk(KERN_WARNING "rv: the rv_reactor %s cannot be removed\n",
+				       ptr->reactor->name);
+				ret = -EBUSY;
+				break;
+			}
+		}
+	}
+
+	mutex_unlock(&rv_interface_lock);
+	return ret;
+}
+
+/*
+ * reacting_on interface.
+ */
+static bool __read_mostly reacting_on;
+
+/**
+ * rv_reacting_on - checks if reacting is on
+ *
+ * Returns 1 if on, 0 otherwise.
+ */
+bool rv_reacting_on(void)
+{
+	/* Ensures that concurrent monitors read consistent reacting_on */
+	smp_rmb();
+	return READ_ONCE(reacting_on);
+}
+
+static ssize_t reacting_on_read_data(struct file *filp,
+				     char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	char *buff;
+
+	buff = rv_reacting_on() ? "1\n" : "0\n";
+
+	return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff)+1);
+}
+
+static void turn_reacting_off(void)
+{
+	WRITE_ONCE(reacting_on, false);
+	/* Ensures that concurrent monitors read consistent reacting_on */
+	smp_wmb();
+}
+
+static void turn_reacting_on(void)
+{
+	WRITE_ONCE(reacting_on, true);
+	/* Ensures that concurrent monitors read consistent reacting_on */
+	smp_wmb();
+}
+
+static ssize_t reacting_on_write_data(struct file *filp, const char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	int retval;
+	bool val;
+
+	retval = kstrtobool_from_user(user_buf, count, &val);
+	if (retval)
+		return retval;
+
+	mutex_lock(&rv_interface_lock);
+
+	if (val)
+		turn_reacting_on();
+	else
+		turn_reacting_off();
+
+	/*
+	 * Wait for the execution of all events to finish
+	 * before returning to user-space.
+	 */
+	tracepoint_synchronize_unregister();
+
+	mutex_unlock(&rv_interface_lock);
+
+	return count;
+}
+
+static const struct file_operations reacting_on_fops = {
+	.open   = simple_open,
+	.llseek = no_llseek,
+	.write  = reacting_on_write_data,
+	.read   = reacting_on_read_data,
+};
+
+/**
+ * reactor_populate_monitor - creates per monitor reactors file
+ * @mdef:	monitor's definition.
+ *
+ * Returns 0 if successful, error otherwise.
+ */
+int reactor_populate_monitor(struct rv_monitor_def *mdef)
+{
+	struct dentry *tmp;
+
+	tmp = rv_create_file("reactors", RV_MODE_WRITE, mdef->root_d, mdef, &monitor_reactors_ops);
+	if (!tmp)
+		return -ENOMEM;
+
+	/*
+	 * Configure as the rv_nop reactor.
+	 */
+	mdef->rdef = get_reactor_rdef_by_name("nop");
+	mdef->rdef->counter++;
+	mdef->reacting = false;
+
+	return 0;
+}
+
+/**
+ * reactor_cleanup_monitor - cleanup a monitor reference
+ * @mdef:       monitor's definition.
+ */
+void reactor_cleanup_monitor(struct rv_monitor_def *mdef)
+{
+	lockdep_assert_held(&rv_interface_lock);
+	mdef->rdef->counter--;
+	WARN_ON_ONCE(mdef->rdef->counter < 0);
+}
+
+/*
+ * Nop reactor register
+ */
+static void rv_nop_reaction(char *msg)
+{
+}
+
+static struct rv_reactor rv_nop = {
+	.name = "nop",
+	.description = "no-operation reactor: do nothing.",
+	.react = rv_nop_reaction
+};
+
+int init_rv_reactors(struct dentry *root_dir)
+{
+	struct dentry *available, *reacting;
+	int retval;
+
+	available = rv_create_file("available_reactors", RV_MODE_READ, root_dir, NULL,
+				   &available_reactors_ops);
+	if (!available)
+		goto out_err;
+
+	reacting = rv_create_file("reacting_on", RV_MODE_WRITE, root_dir, NULL, &reacting_on_fops);
+	if (!reacting)
+		goto rm_available;
+
+	retval = __rv_register_reactor(&rv_nop);
+	if (retval)
+		goto rm_reacting;
+
+	turn_reacting_on();
+
+	return 0;
+
+rm_reacting:
+	rv_remove(reacting);
+rm_available:
+	rv_remove(available);
+out_err:
+	return -ENOMEM;
+}
diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c
index 0b15e975d2c2..8d77526892f4 100644
--- a/kernel/trace/synth_event_gen_test.c
+++ b/kernel/trace/synth_event_gen_test.c
@@ -120,15 +120,13 @@ static int __init test_gen_synth_cmd(void)
 
 	/* Now generate a gen_synth_test event */
 	ret = synth_event_trace_array(gen_synth_test, vals, ARRAY_SIZE(vals));
- out:
+ free:
+	kfree(buf);
 	return ret;
  delete:
 	/* We got an error after creating the event, delete it */
 	synth_event_delete("gen_synth_test");
- free:
-	kfree(buf);
-
-	goto out;
+	goto free;
 }
 
 /*
@@ -227,15 +225,13 @@ static int __init test_empty_synth_event(void)
 
 	/* Now trace an empty_synth_test event */
 	ret = synth_event_trace_array(empty_synth_test, vals, ARRAY_SIZE(vals));
- out:
+ free:
+	kfree(buf);
 	return ret;
  delete:
 	/* We got an error after creating the event, delete it */
 	synth_event_delete("empty_synth_test");
- free:
-	kfree(buf);
-
-	goto out;
+	goto free;
 }
 
 static struct synth_field_desc create_synth_test_fields[] = {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c860f582b078..5cfc95a52bc3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -185,6 +185,7 @@ static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
 static char *default_bootup_tracer;
 
 static bool allocate_snapshot;
+static bool snapshot_at_boot;
 
 static int __init set_cmdline_ftrace(char *str)
 {
@@ -230,12 +231,21 @@ static int __init boot_alloc_snapshot(char *str)
 __setup("alloc_snapshot", boot_alloc_snapshot);
 
 
+static int __init boot_snapshot(char *str)
+{
+	snapshot_at_boot = true;
+	boot_alloc_snapshot(str);
+	return 1;
+}
+__setup("ftrace_boot_snapshot", boot_snapshot);
+
+
 static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
 
 static int __init set_trace_boot_options(char *str)
 {
 	strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
-	return 0;
+	return 1;
 }
 __setup("trace_options=", set_trace_boot_options);
 
@@ -246,12 +256,16 @@ static int __init set_trace_boot_clock(char *str)
 {
 	strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE);
 	trace_boot_clock = trace_boot_clock_buf;
-	return 0;
+	return 1;
 }
 __setup("trace_clock=", set_trace_boot_clock);
 
 static int __init set_tracepoint_printk(char *str)
 {
+	/* Ignore the "tp_printk_stop_on_boot" param */
+	if (*str == '_')
+		return 0;
+
 	if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0))
 		tracepoint_printk = 1;
 	return 1;
@@ -707,13 +721,16 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 		pos = 0;
 
 		ret = trace_get_user(&parser, ubuf, cnt, &pos);
-		if (ret < 0 || !trace_parser_loaded(&parser))
+		if (ret < 0)
 			break;
 
 		read += ret;
 		ubuf += ret;
 		cnt -= ret;
 
+		if (!trace_parser_loaded(&parser))
+			break;
+
 		ret = -EINVAL;
 		if (kstrtoul(parser.buffer, 0, &val))
 			break;
@@ -739,7 +756,6 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	if (!nr_pids) {
 		/* Cleared the list of pids */
 		trace_pid_list_free(pid_list);
-		read = ret;
 		pid_list = NULL;
 	}
 
@@ -1160,7 +1176,7 @@ void tracing_snapshot_cond(struct trace_array *tr, void *cond_data)
 EXPORT_SYMBOL_GPL(tracing_snapshot_cond);
 
 /**
- * tracing_snapshot_cond_data - get the user data associated with a snapshot
+ * tracing_cond_snapshot_data - get the user data associated with a snapshot
  * @tr:		The tracing instance
  *
  * When the user enables a conditional snapshot using
@@ -1177,12 +1193,14 @@ void *tracing_cond_snapshot_data(struct trace_array *tr)
 {
 	void *cond_data = NULL;
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 
 	if (tr->cond_snapshot)
 		cond_data = tr->cond_snapshot->cond_data;
 
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 
 	return cond_data;
 }
@@ -1318,9 +1336,11 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data,
 		goto fail_unlock;
 	}
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 	tr->cond_snapshot = cond_snapshot;
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 
 	mutex_unlock(&trace_types_lock);
 
@@ -1347,6 +1367,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr)
 {
 	int ret = 0;
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 
 	if (!tr->cond_snapshot)
@@ -1357,6 +1378,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr)
 	}
 
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 
 	return ret;
 }
@@ -1470,10 +1492,12 @@ static int __init set_buf_size(char *str)
 	if (!str)
 		return 0;
 	buf_size = memparse(str, &str);
-	/* nr_entries can not be zero */
-	if (buf_size == 0)
-		return 0;
-	trace_buf_size = buf_size;
+	/*
+	 * nr_entries can not be zero and the startup
+	 * tests require some buffer space. Therefore
+	 * ensure we have at least 4096 bytes of buffer.
+	 */
+	trace_buf_size = max(4096UL, buf_size);
 	return 1;
 }
 __setup("trace_buf_size=", set_buf_size);
@@ -1526,6 +1550,7 @@ static struct {
 	{ ktime_get_mono_fast_ns,	"mono",		1 },
 	{ ktime_get_raw_fast_ns,	"mono_raw",	1 },
 	{ ktime_get_boot_fast_ns,	"boot",		1 },
+	{ ktime_get_tai_fast_ns,	"tai",		1 },
 	ARCH_TRACE_CLOCKS
 };
 
@@ -2155,10 +2180,12 @@ void tracing_reset_online_cpus(struct array_buffer *buf)
 }
 
 /* Must have trace_types_lock held */
-void tracing_reset_all_online_cpus(void)
+void tracing_reset_all_online_cpus_unlocked(void)
 {
 	struct trace_array *tr;
 
+	lockdep_assert_held(&trace_types_lock);
+
 	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
 		if (!tr->clear_trace)
 			continue;
@@ -2170,6 +2197,13 @@ void tracing_reset_all_online_cpus(void)
 	}
 }
 
+void tracing_reset_all_online_cpus(void)
+{
+	mutex_lock(&trace_types_lock);
+	tracing_reset_all_online_cpus_unlocked();
+	mutex_unlock(&trace_types_lock);
+}
+
 /*
  * The tgid_map array maps from pid to tgid; i.e. the value stored at index i
  * is the tgid last observed corresponding to pid=i.
@@ -2181,6 +2215,11 @@ static size_t tgid_map_max;
 
 #define SAVED_CMDLINES_DEFAULT 128
 #define NO_CMDLINE_MAP UINT_MAX
+/*
+ * Preemption must be disabled before acquiring trace_cmdline_lock.
+ * The various trace_arrays' max_lock must be acquired in a context
+ * where interrupt is disabled.
+ */
 static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 struct saved_cmdlines_buffer {
 	unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
@@ -2393,7 +2432,11 @@ static int trace_save_cmdline(struct task_struct *tsk)
 	 * the lock, but we also don't want to spin
 	 * nor do we want to disable interrupts,
 	 * so if we miss here, then better luck next time.
+	 *
+	 * This is called within the scheduler and wake up, so interrupts
+	 * had better been disabled and run queue lock been held.
 	 */
+	lockdep_assert_preemption_disabled();
 	if (!arch_spin_trylock(&trace_cmdline_lock))
 		return 0;
 
@@ -2819,7 +2862,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
 }
 EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
 
-static DEFINE_SPINLOCK(tracepoint_iter_lock);
+static DEFINE_RAW_SPINLOCK(tracepoint_iter_lock);
 static DEFINE_MUTEX(tracepoint_printk_mutex);
 
 static void output_printk(struct trace_event_buffer *fbuffer)
@@ -2847,14 +2890,14 @@ static void output_printk(struct trace_event_buffer *fbuffer)
 
 	event = &fbuffer->trace_file->event_call->event;
 
-	spin_lock_irqsave(&tracepoint_iter_lock, flags);
+	raw_spin_lock_irqsave(&tracepoint_iter_lock, flags);
 	trace_seq_init(&iter->seq);
 	iter->ent = fbuffer->entry;
 	event_call->event.funcs->trace(iter, 0, event);
 	trace_seq_putc(&iter->seq, 0);
 	printk("%s", iter->seq.buffer);
 
-	spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
+	raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
 }
 
 int tracepoint_printk_sysctl(struct ctl_table *table, int write,
@@ -3086,17 +3129,17 @@ void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
 	}
 
 	/*
-	 * When an NMI triggers, RCU is enabled via rcu_nmi_enter(),
+	 * When an NMI triggers, RCU is enabled via ct_nmi_enter(),
 	 * but if the above rcu_is_watching() failed, then the NMI
-	 * triggered someplace critical, and rcu_irq_enter() should
+	 * triggered someplace critical, and ct_irq_enter() should
 	 * not be called from NMI.
 	 */
 	if (unlikely(in_nmi()))
 		return;
 
-	rcu_irq_enter_irqson();
+	ct_irq_enter_irqson();
 	__ftrace_trace_stack(buffer, trace_ctx, skip, NULL);
-	rcu_irq_exit_irqson();
+	ct_irq_exit_irqson();
 }
 
 /**
@@ -3657,12 +3700,17 @@ static char *trace_iter_expand_format(struct trace_iterator *iter)
 }
 
 /* Returns true if the string is safe to dereference from an event */
-static bool trace_safe_str(struct trace_iterator *iter, const char *str)
+static bool trace_safe_str(struct trace_iterator *iter, const char *str,
+			   bool star, int len)
 {
 	unsigned long addr = (unsigned long)str;
 	struct trace_event *trace_event;
 	struct trace_event_call *event;
 
+	/* Ignore strings with no length */
+	if (star && !len)
+		return true;
+
 	/* OK if part of the event data */
 	if ((addr >= (unsigned long)iter->ent) &&
 	    (addr < (unsigned long)iter->ent + iter->ent_size))
@@ -3848,7 +3896,7 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 		 * instead. See samples/trace_events/trace-events-sample.h
 		 * for reference.
 		 */
-		if (WARN_ONCE(!trace_safe_str(iter, str),
+		if (WARN_ONCE(!trace_safe_str(iter, str, star, len),
 			      "fmt: '%s' current_buffer: '%s'",
 			      fmt, show_buffer(&iter->seq))) {
 			int ret;
@@ -4228,7 +4276,7 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file
 				       unsigned int flags)
 {
 	bool tgid = flags & TRACE_ITER_RECORD_TGID;
-	const char *space = "            ";
+	static const char space[] = "            ";
 	int prec = tgid ? 12 : 2;
 
 	print_event_info(buf, m);
@@ -4252,9 +4300,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 	struct tracer *type = iter->trace;
 	unsigned long entries;
 	unsigned long total;
-	const char *name = "preemption";
-
-	name = type->name;
+	const char *name = type->name;
 
 	get_total_entries(buf, &total, &entries);
 
@@ -4268,17 +4314,11 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 		   entries,
 		   total,
 		   buf->cpu,
-#if defined(CONFIG_PREEMPT_NONE)
-		   "server",
-#elif defined(CONFIG_PREEMPT_VOLUNTARY)
-		   "desktop",
-#elif defined(CONFIG_PREEMPT)
-		   "preempt",
-#elif defined(CONFIG_PREEMPT_RT)
-		   "preempt_rt",
-#else
+		   preempt_model_none()      ? "server" :
+		   preempt_model_voluntary() ? "desktop" :
+		   preempt_model_full()      ? "preempt" :
+		   preempt_model_rt()        ? "preempt_rt" :
 		   "unknown",
-#endif
 		   /* These are reserved for later use */
 		   0, 0, 0, 0);
 #ifdef CONFIG_SMP
@@ -5454,7 +5494,7 @@ static const char readme_msg[] =
 	"  error_log\t- error log for failed commands (that support it)\n"
 	"  buffer_size_kb\t- view and modify size of per cpu buffer\n"
 	"  buffer_total_size_kb  - view total size of all cpu buffers\n\n"
-	"  trace_clock\t\t-change the clock used to order events\n"
+	"  trace_clock\t\t- change the clock used to order events\n"
 	"       local:   Per cpu clock but may not be synced across CPUs\n"
 	"      global:   Synced across CPUs but slows tracing down.\n"
 	"     counter:   Not a clock, but just an increment\n"
@@ -5463,7 +5503,7 @@ static const char readme_msg[] =
 #ifdef CONFIG_X86_64
 	"     x86-tsc:   TSC cycle counter\n"
 #endif
-	"\n  timestamp_mode\t-view the mode used to timestamp events\n"
+	"\n  timestamp_mode\t- view the mode used to timestamp events\n"
 	"       delta:   Delta difference against a buffer-wide timestamp\n"
 	"    absolute:   Absolute (standalone) timestamp\n"
 	"\n  trace_marker\t\t- Writes into this file writes into the kernel buffer\n"
@@ -5553,13 +5593,13 @@ static const char readme_msg[] =
 #endif
 #if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
 	"\t  accepts: event-definitions (one definition per line)\n"
-	"\t   Format: p[:[<group>/]<event>] <place> [<args>]\n"
-	"\t           r[maxactive][:[<group>/]<event>] <place> [<args>]\n"
+	"\t   Format: p[:[<group>/][<event>]] <place> [<args>]\n"
+	"\t           r[maxactive][:[<group>/][<event>]] <place> [<args>]\n"
 #ifdef CONFIG_HIST_TRIGGERS
 	"\t           s:[synthetic/]<event> <field> [<field>]\n"
 #endif
-	"\t           e[:[<group>/]<event>] <attached-group>.<attached-event> [<args>]\n"
-	"\t           -:[<group>/]<event>\n"
+	"\t           e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]\n"
+	"\t           -:[<group>/][<event>]\n"
 #ifdef CONFIG_KPROBE_EVENTS
 	"\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
   "place (kretprobe): [<module>:]<symbol>[+<offset>]%return|<memaddr>\n"
@@ -5874,9 +5914,11 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
 	char buf[64];
 	int r;
 
+	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 	r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
 	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
@@ -5901,10 +5943,12 @@ static int tracing_resize_saved_cmdlines(unsigned int val)
 		return -ENOMEM;
 	}
 
+	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 	savedcmd_temp = savedcmd;
 	savedcmd = s;
 	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
 	free_saved_cmdlines_buffer(savedcmd_temp);
 
 	return 0;
@@ -6311,12 +6355,18 @@ static void tracing_set_nop(struct trace_array *tr)
 	tr->current_trace = &nop_trace;
 }
 
+static bool tracer_options_updated;
+
 static void add_tracer_options(struct trace_array *tr, struct tracer *t)
 {
 	/* Only enable if the directory has been created already. */
 	if (!tr->dir)
 		return;
 
+	/* Only create trace option files after update_tracer_options finish */
+	if (!tracer_options_updated)
+		return;
+
 	create_trace_option_files(tr, t);
 }
 
@@ -6351,10 +6401,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 
 #ifdef CONFIG_TRACER_SNAPSHOT
 	if (t->use_max_tr) {
+		local_irq_disable();
 		arch_spin_lock(&tr->max_lock);
 		if (tr->cond_snapshot)
 			ret = -EBUSY;
 		arch_spin_unlock(&tr->max_lock);
+		local_irq_enable();
 		if (ret)
 			goto out;
 	}
@@ -6385,12 +6437,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 	if (tr->current_trace->reset)
 		tr->current_trace->reset(tr);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+	had_max_tr = tr->current_trace->use_max_tr;
+
 	/* Current trace needs to be nop_trace before synchronize_rcu */
 	tr->current_trace = &nop_trace;
 
-#ifdef CONFIG_TRACER_MAX_TRACE
-	had_max_tr = tr->allocated_snapshot;
-
 	if (had_max_tr && !t->use_max_tr) {
 		/*
 		 * We need to make sure that the update_max_tr sees that
@@ -6402,14 +6454,14 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 		synchronize_rcu();
 		free_snapshot(tr);
 	}
-#endif
 
-#ifdef CONFIG_TRACER_MAX_TRACE
-	if (t->use_max_tr && !had_max_tr) {
+	if (t->use_max_tr && !tr->allocated_snapshot) {
 		ret = tracing_alloc_snapshot_instance(tr);
 		if (ret < 0)
 			goto out;
 	}
+#else
+	tr->current_trace = &nop_trace;
 #endif
 
 	if (t->init) {
@@ -6433,7 +6485,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 {
 	struct trace_array *tr = filp->private_data;
 	char buf[MAX_TRACER_SIZE+1];
-	int i;
+	char *name;
 	size_t ret;
 	int err;
 
@@ -6447,11 +6499,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 
 	buf[cnt] = 0;
 
-	/* strip ending whitespace. */
-	for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
-		buf[i] = 0;
+	name = strim(buf);
 
-	err = tracing_set_tracer(tr, buf);
+	err = tracing_set_tracer(tr, name);
 	if (err)
 		return err;
 
@@ -6616,6 +6666,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 	mutex_unlock(&trace_types_lock);
 
 	free_cpumask_var(iter->started);
+	kfree(iter->fmt);
 	mutex_destroy(&iter->mutex);
 	kfree(iter);
 
@@ -6640,7 +6691,7 @@ trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_tabl
 		return EPOLLIN | EPOLLRDNORM;
 	else
 		return ring_buffer_poll_wait(iter->array_buffer->buffer, iter->cpu_file,
-					     filp, poll_table);
+					     filp, poll_table, iter->tr->buffer_percent);
 }
 
 static __poll_t
@@ -7418,10 +7469,12 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		goto out;
 	}
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 	if (tr->cond_snapshot)
 		ret = -EBUSY;
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 	if (ret)
 		goto out;
 
@@ -7719,7 +7772,7 @@ const struct file_operations trace_min_max_fops = {
 struct err_info {
 	const char	**errs;	/* ptr to loc-specific array of err strings */
 	u8		type;	/* index into errs -> specific err string */
-	u8		pos;	/* MAX_FILTER_STR_VAL = 256 */
+	u16		pos;	/* caret position */
 	u64		ts;
 };
 
@@ -7727,26 +7780,53 @@ struct tracing_log_err {
 	struct list_head	list;
 	struct err_info		info;
 	char			loc[TRACING_LOG_LOC_MAX]; /* err location */
-	char			cmd[MAX_FILTER_STR_VAL]; /* what caused err */
+	char			*cmd;                     /* what caused err */
 };
 
 static DEFINE_MUTEX(tracing_err_log_lock);
 
-static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr)
+static struct tracing_log_err *alloc_tracing_log_err(int len)
 {
 	struct tracing_log_err *err;
 
+	err = kzalloc(sizeof(*err), GFP_KERNEL);
+	if (!err)
+		return ERR_PTR(-ENOMEM);
+
+	err->cmd = kzalloc(len, GFP_KERNEL);
+	if (!err->cmd) {
+		kfree(err);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return err;
+}
+
+static void free_tracing_log_err(struct tracing_log_err *err)
+{
+	kfree(err->cmd);
+	kfree(err);
+}
+
+static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr,
+						   int len)
+{
+	struct tracing_log_err *err;
+	char *cmd;
+
 	if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) {
-		err = kzalloc(sizeof(*err), GFP_KERNEL);
-		if (!err)
-			err = ERR_PTR(-ENOMEM);
-		else
+		err = alloc_tracing_log_err(len);
+		if (PTR_ERR(err) != -ENOMEM)
 			tr->n_err_log_entries++;
 
 		return err;
 	}
-
+	cmd = kzalloc(len, GFP_KERNEL);
+	if (!cmd)
+		return ERR_PTR(-ENOMEM);
 	err = list_first_entry(&tr->err_log, struct tracing_log_err, list);
+	kfree(err->cmd);
+	err->cmd = cmd;
 	list_del(&err->list);
 
 	return err;
@@ -7807,22 +7887,25 @@ unsigned int err_pos(char *cmd, const char *str)
  */
 void tracing_log_err(struct trace_array *tr,
 		     const char *loc, const char *cmd,
-		     const char **errs, u8 type, u8 pos)
+		     const char **errs, u8 type, u16 pos)
 {
 	struct tracing_log_err *err;
+	int len = 0;
 
 	if (!tr)
 		tr = &global_trace;
 
+	len += sizeof(CMD_PREFIX) + 2 * sizeof("\n") + strlen(cmd) + 1;
+
 	mutex_lock(&tracing_err_log_lock);
-	err = get_tracing_log_err(tr);
+	err = get_tracing_log_err(tr, len);
 	if (PTR_ERR(err) == -ENOMEM) {
 		mutex_unlock(&tracing_err_log_lock);
 		return;
 	}
 
 	snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc);
-	snprintf(err->cmd, MAX_FILTER_STR_VAL,"\n" CMD_PREFIX "%s\n", cmd);
+	snprintf(err->cmd, len, "\n" CMD_PREFIX "%s\n", cmd);
 
 	err->info.errs = errs;
 	err->info.type = type;
@@ -7840,7 +7923,7 @@ static void clear_tracing_err_log(struct trace_array *tr)
 	mutex_lock(&tracing_err_log_lock);
 	list_for_each_entry_safe(err, next, &tr->err_log, list) {
 		list_del(&err->list);
-		kfree(err);
+		free_tracing_log_err(err);
 	}
 
 	tr->n_err_log_entries = 0;
@@ -7868,9 +7951,9 @@ static void tracing_err_log_seq_stop(struct seq_file *m, void *v)
 	mutex_unlock(&tracing_err_log_lock);
 }
 
-static void tracing_err_log_show_pos(struct seq_file *m, u8 pos)
+static void tracing_err_log_show_pos(struct seq_file *m, u16 pos)
 {
-	u8 i;
+	u16 i;
 
 	for (i = 0; i < sizeof(CMD_PREFIX) - 1; i++)
 		seq_putc(m, ' ');
@@ -8090,6 +8173,12 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 
 	__trace_array_put(iter->tr);
 
+	iter->wait_index++;
+	/* Make sure the waiters see the new wait_index */
+	smp_wmb();
+
+	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
 	if (info->spare)
 		ring_buffer_free_read_page(iter->array_buffer->buffer,
 					   info->spare_cpu, info->spare);
@@ -8243,6 +8332,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 
 	/* did we read anything? */
 	if (!spd.nr_pages) {
+		long wait_index;
+
 		if (ret)
 			goto out;
 
@@ -8250,10 +8341,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
 			goto out;
 
+		wait_index = READ_ONCE(iter->wait_index);
+
 		ret = wait_on_pipe(iter, iter->tr->buffer_percent);
 		if (ret)
 			goto out;
 
+		/* No need to wait after waking up when tracing is off */
+		if (!tracer_tracing_is_on(iter->tr))
+			goto out;
+
+		/* Make sure we see the new wait_index */
+		smp_rmb();
+		if (wait_index != iter->wait_index)
+			goto out;
+
 		goto again;
 	}
 
@@ -8264,12 +8366,34 @@ out:
 	return ret;
 }
 
+/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */
+static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct ftrace_buffer_info *info = file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	if (cmd)
+		return -ENOIOCTLCMD;
+
+	mutex_lock(&trace_types_lock);
+
+	iter->wait_index++;
+	/* Make sure the waiters see the new wait_index */
+	smp_wmb();
+
+	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
+	mutex_unlock(&trace_types_lock);
+	return 0;
+}
+
 static const struct file_operations tracing_buffers_fops = {
 	.open		= tracing_buffers_open,
 	.read		= tracing_buffers_read,
 	.poll		= tracing_buffers_poll,
 	.release	= tracing_buffers_release,
 	.splice_read	= tracing_buffers_splice_read,
+	.unlocked_ioctl = tracing_buffers_ioctl,
 	.llseek		= no_llseek,
 };
 
@@ -8958,6 +9082,8 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 			tracer_tracing_off(tr);
 			if (tr->current_trace->stop)
 				tr->current_trace->stop(tr);
+			/* Wake up any waiters */
+			ring_buffer_wake_waiters(buffer, RING_BUFFER_ALL_CPUS);
 		}
 		mutex_unlock(&trace_types_lock);
 	}
@@ -9054,6 +9180,16 @@ allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size
 	return 0;
 }
 
+static void free_trace_buffer(struct array_buffer *buf)
+{
+	if (buf->buffer) {
+		ring_buffer_free(buf->buffer);
+		buf->buffer = NULL;
+		free_percpu(buf->data);
+		buf->data = NULL;
+	}
+}
+
 static int allocate_trace_buffers(struct trace_array *tr, int size)
 {
 	int ret;
@@ -9066,10 +9202,7 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	ret = allocate_trace_buffer(tr, &tr->max_buffer,
 				    allocate_snapshot ? size : 1);
 	if (MEM_FAIL(ret, "Failed to allocate trace buffer\n")) {
-		ring_buffer_free(tr->array_buffer.buffer);
-		tr->array_buffer.buffer = NULL;
-		free_percpu(tr->array_buffer.data);
-		tr->array_buffer.data = NULL;
+		free_trace_buffer(&tr->array_buffer);
 		return -ENOMEM;
 	}
 	tr->allocated_snapshot = allocate_snapshot;
@@ -9084,16 +9217,6 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	return 0;
 }
 
-static void free_trace_buffer(struct array_buffer *buf)
-{
-	if (buf->buffer) {
-		ring_buffer_free(buf->buffer);
-		buf->buffer = NULL;
-		free_percpu(buf->data);
-		buf->data = NULL;
-	}
-}
-
 static void free_trace_buffers(struct trace_array *tr)
 {
 	if (!tr)
@@ -9126,6 +9249,7 @@ static void __update_tracer_options(struct trace_array *tr)
 static void update_tracer_options(struct trace_array *tr)
 {
 	mutex_lock(&trace_types_lock);
+	tracer_options_updated = true;
 	__update_tracer_options(tr);
 	mutex_unlock(&trace_types_lock);
 }
@@ -9558,6 +9682,7 @@ extern struct trace_eval_map *__stop_ftrace_eval_maps[];
 
 static struct workqueue_struct *eval_map_wq __initdata;
 static struct work_struct eval_map_work __initdata;
+static struct work_struct tracerfs_init_work __initdata;
 
 static void __init eval_map_work_func(struct work_struct *work)
 {
@@ -9583,6 +9708,8 @@ static int __init trace_eval_init(void)
 	return 0;
 }
 
+subsys_initcall(trace_eval_init);
+
 static int __init trace_eval_sync(void)
 {
 	/* Make sure the eval map updates are finished */
@@ -9665,15 +9792,8 @@ static struct notifier_block trace_module_nb = {
 };
 #endif /* CONFIG_MODULES */
 
-static __init int tracer_init_tracefs(void)
+static __init void tracer_init_tracefs_work_func(struct work_struct *work)
 {
-	int ret;
-
-	trace_access_lock_init();
-
-	ret = tracing_init_dentry();
-	if (ret)
-		return 0;
 
 	event_trace_init();
 
@@ -9695,8 +9815,6 @@ static __init int tracer_init_tracefs(void)
 	trace_create_file("saved_tgids", TRACE_MODE_READ, NULL,
 			NULL, &tracing_saved_tgids_fops);
 
-	trace_eval_init();
-
 	trace_create_eval_file(NULL);
 
 #ifdef CONFIG_MODULES
@@ -9711,6 +9829,26 @@ static __init int tracer_init_tracefs(void)
 	create_trace_instances(NULL);
 
 	update_tracer_options(&global_trace);
+}
+
+static __init int tracer_init_tracefs(void)
+{
+	int ret;
+
+	trace_access_lock_init();
+
+	ret = tracing_init_dentry();
+	if (ret)
+		return 0;
+
+	if (eval_map_wq) {
+		INIT_WORK(&tracerfs_init_work, tracer_init_tracefs_work_func);
+		queue_work(eval_map_wq, &tracerfs_init_work);
+	} else {
+		tracer_init_tracefs_work_func(NULL);
+	}
+
+	rv_init_interface();
 
 	return 0;
 }
@@ -9804,6 +9942,12 @@ void trace_init_global_iter(struct trace_iterator *iter)
 	/* Output in nanoseconds only if we are using a clock in nanoseconds. */
 	if (trace_clocks[iter->tr->clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
+	/* Can not use kmalloc for iter.temp and iter.fmt */
+	iter->temp = static_temp_buf;
+	iter->temp_size = STATIC_TEMP_BUF_SIZE;
+	iter->fmt = static_fmt_buf;
+	iter->fmt_size = STATIC_FMT_BUF_SIZE;
 }
 
 void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
@@ -9836,11 +9980,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 
 	/* Simulate the iterator */
 	trace_init_global_iter(&iter);
-	/* Can not use kmalloc for iter.temp and iter.fmt */
-	iter.temp = static_temp_buf;
-	iter.temp_size = STATIC_TEMP_BUF_SIZE;
-	iter.fmt = static_fmt_buf;
-	iter.fmt_size = STATIC_FMT_BUF_SIZE;
 
 	for_each_tracing_cpu(cpu) {
 		atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
@@ -10031,7 +10170,7 @@ __init static int tracer_alloc_buffers(void)
 	 * buffer. The memory will be removed once the "instance" is removed.
 	 */
 	ret = cpuhp_setup_state_multi(CPUHP_TRACE_RB_PREPARE,
-				      "trace/RB:preapre", trace_rb_cpu_prepare,
+				      "trace/RB:prepare", trace_rb_cpu_prepare,
 				      NULL);
 	if (ret < 0)
 		goto out_free_cpumask;
@@ -10116,6 +10255,14 @@ out:
 	return ret;
 }
 
+void __init ftrace_boot_snapshot(void)
+{
+	if (snapshot_at_boot) {
+		tracing_snapshot();
+		internal_trace_puts("** Boot snapshot taken **\n");
+	}
+}
+
 void __init early_trace_init(void)
 {
 	if (tracepoint_printk) {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d038ddbf1bea..d42e24507152 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -136,7 +136,6 @@ struct kprobe_trace_entry_head {
 
 struct eprobe_trace_entry_head {
 	struct trace_entry	ent;
-	unsigned int		type;
 };
 
 struct kretprobe_trace_entry_head {
@@ -581,6 +580,7 @@ int tracing_is_enabled(void);
 void tracing_reset_online_cpus(struct array_buffer *buf);
 void tracing_reset_current(int cpu);
 void tracing_reset_all_online_cpus(void);
+void tracing_reset_all_online_cpus_unlocked(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 int tracing_open_generic_tr(struct inode *inode, struct file *filp);
 bool tracing_is_disabled(void);
@@ -1436,8 +1436,6 @@ event_trigger_unlock_commit(struct trace_event_file *file,
 struct filter_pred;
 struct regex;
 
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
-
 typedef int (*regex_match_func)(char *str, struct regex *r, int len);
 
 enum regex_type {
@@ -1456,17 +1454,6 @@ struct regex {
 	regex_match_func	match;
 };
 
-struct filter_pred {
-	filter_pred_fn_t 	fn;
-	u64 			val;
-	struct regex		regex;
-	unsigned short		*ops;
-	struct ftrace_event_field *field;
-	int 			offset;
-	int			not;
-	int 			op;
-};
-
 static inline bool is_string_field(struct ftrace_event_field *field)
 {
 	return field->filter_type == FILTER_DYN_STRING ||
@@ -1574,13 +1561,12 @@ struct enable_trigger_data {
 };
 
 extern int event_enable_trigger_print(struct seq_file *m,
-				      struct event_trigger_ops *ops,
-				      struct event_trigger_data *data);
-extern void event_enable_trigger_free(struct event_trigger_ops *ops,
 				      struct event_trigger_data *data);
+extern void event_enable_trigger_free(struct event_trigger_data *data);
 extern int event_enable_trigger_parse(struct event_command *cmd_ops,
 				      struct trace_event_file *file,
-				      char *glob, char *cmd, char *param);
+				      char *glob, char *cmd,
+				      char *param_and_filter);
 extern int event_enable_register_trigger(char *glob,
 					 struct event_trigger_data *data,
 					 struct trace_event_file *file);
@@ -1588,8 +1574,7 @@ extern void event_enable_unregister_trigger(char *glob,
 					    struct event_trigger_data *test,
 					    struct trace_event_file *file);
 extern void trigger_data_free(struct event_trigger_data *data);
-extern int event_trigger_init(struct event_trigger_ops *ops,
-			      struct event_trigger_data *data);
+extern int event_trigger_init(struct event_trigger_data *data);
 extern int trace_event_trigger_enable_disable(struct trace_event_file *file,
 					      int trigger_enable);
 extern void update_cond_flag(struct trace_event_file *file);
@@ -1630,10 +1615,11 @@ extern void event_trigger_reset_filter(struct event_command *cmd_ops,
 extern int event_trigger_register(struct event_command *cmd_ops,
 				  struct trace_event_file *file,
 				  char *glob,
-				  char *cmd,
-				  char *trigger,
-				  struct event_trigger_data *trigger_data,
-				  int *n_registered);
+				  struct event_trigger_data *trigger_data);
+extern void event_trigger_unregister(struct event_command *cmd_ops,
+				     struct trace_event_file *file,
+				     char *glob,
+				     struct event_trigger_data *trigger_data);
 
 /**
  * struct event_trigger_ops - callbacks for trace event triggers
@@ -1687,12 +1673,9 @@ struct event_trigger_ops {
 					   struct trace_buffer *buffer,
 					   void *rec,
 					   struct ring_buffer_event *rbe);
-	int			(*init)(struct event_trigger_ops *ops,
-					struct event_trigger_data *data);
-	void			(*free)(struct event_trigger_ops *ops,
-					struct event_trigger_data *data);
+	int			(*init)(struct event_trigger_data *data);
+	void			(*free)(struct event_trigger_data *data);
 	int			(*print)(struct seq_file *m,
-					 struct event_trigger_ops *ops,
 					 struct event_trigger_data *data);
 };
 
@@ -1878,7 +1861,7 @@ extern ssize_t trace_parse_run_command(struct file *file,
 extern unsigned int err_pos(char *cmd, const char *str);
 extern void tracing_log_err(struct trace_array *tr,
 			    const char *loc, const char *cmd,
-			    const char **errs, u8 type, u8 pos);
+			    const char **errs, u8 type, u16 pos);
 
 /*
  * Normal trace_printk() and friends allocates special buffers
@@ -2010,4 +1993,13 @@ struct trace_min_max_param {
 
 extern const struct file_operations trace_min_max_fops;
 
+#ifdef CONFIG_RV
+extern int rv_init_interface(void);
+#else
+static inline int rv_init_interface(void)
+{
+	return 0;
+}
+#endif
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index 801c2a7f7605..54d5fa35c90a 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -51,7 +51,7 @@ static void trace_do_benchmark(void)
 
 	local_irq_disable();
 	start = trace_clock_local();
-	trace_benchmark_event(bm_str);
+	trace_benchmark_event(bm_str, bm_last);
 	stop = trace_clock_local();
 	local_irq_enable();
 
diff --git a/kernel/trace/trace_benchmark.h b/kernel/trace/trace_benchmark.h
index 79e6fbe5b365..c3e91060dc94 100644
--- a/kernel/trace/trace_benchmark.h
+++ b/kernel/trace/trace_benchmark.h
@@ -14,19 +14,21 @@ extern void trace_benchmark_unreg(void);
 
 TRACE_EVENT_FN(benchmark_event,
 
-	TP_PROTO(const char *str),
+	TP_PROTO(const char *str, u64 delta),
 
-	TP_ARGS(str),
+	TP_ARGS(str, delta),
 
 	TP_STRUCT__entry(
 		__array(	char,	str,	BENCHMARK_EVENT_STRLEN	)
+		__field(	u64,	delta)
 	),
 
 	TP_fast_assign(
 		memcpy(__entry->str, str, BENCHMARK_EVENT_STRLEN);
+		__entry->delta = delta;
 	),
 
-	TP_printk("%s", __entry->str),
+	TP_printk("%s delta=%llu", __entry->str, __entry->delta),
 
 	trace_benchmark_reg, trace_benchmark_unreg
 );
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 0580287d7a0d..778200dd8ede 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -300,7 +300,7 @@ trace_boot_hist_add_handlers(struct xbc_node *hnode, char **bufp,
 {
 	struct xbc_node *node;
 	const char *p, *handler;
-	int ret;
+	int ret = 0;
 
 	handler = xbc_node_get_data(hnode);
 
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index e34e8182ee4b..4376887e0d8a 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -101,7 +101,7 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type
 		event = p + 1;
 		*p = '\0';
 	}
-	if (event[0] == '\0') {
+	if (!system && event[0] == '\0') {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -118,6 +118,7 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type
 		if (ret)
 			break;
 	}
+	tracing_reset_all_online_cpus();
 	mutex_unlock(&event_mutex);
 out:
 	argv_free(argv);
@@ -214,6 +215,7 @@ int dyn_events_release_all(struct dyn_event_operations *type)
 			break;
 	}
 out:
+	tracing_reset_all_online_cpus();
 	mutex_unlock(&event_mutex);
 
 	return ret;
@@ -255,19 +257,14 @@ static const struct file_operations dynamic_events_ops = {
 /* Make a tracefs interface for controlling dynamic events */
 static __init int init_dynamic_event(void)
 {
-	struct dentry *entry;
 	int ret;
 
 	ret = tracing_init_dentry();
 	if (ret)
 		return 0;
 
-	entry = tracefs_create_file("dynamic_events", TRACE_MODE_WRITE, NULL,
-				    NULL, &dynamic_events_ops);
-
-	/* Event list interface */
-	if (!entry)
-		pr_warn("Could not create tracefs 'dynamic_events' entry\n");
+	trace_create_file("dynamic_events", TRACE_MODE_WRITE, NULL,
+			  NULL, &dynamic_events_ops);
 
 	return 0;
 }
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 191db32dec46..352b65e2b910 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -16,6 +16,7 @@
 #include "trace_dynevent.h"
 #include "trace_probe.h"
 #include "trace_probe_tmpl.h"
+#include "trace_probe_kernel.h"
 
 #define EPROBE_EVENT_SYSTEM "eprobes"
 
@@ -26,6 +27,9 @@ struct trace_eprobe {
 	/* tracepoint event */
 	const char *event_name;
 
+	/* filter string for the tracepoint */
+	char *filter_str;
+
 	struct trace_event_call *event;
 
 	struct dyn_event	devent;
@@ -48,6 +52,7 @@ static void trace_event_probe_cleanup(struct trace_eprobe *ep)
 	kfree(ep->event_system);
 	if (ep->event)
 		trace_event_put_ref(ep->event);
+	kfree(ep->filter_str);
 	kfree(ep);
 }
 
@@ -125,6 +130,7 @@ static bool eprobe_dyn_event_match(const char *system, const char *event,
 	 * We match the following:
 	 *  event only			- match all eprobes with event name
 	 *  system and event only	- match all system/event probes
+	 *  system only			- match all system probes
 	 *
 	 * The below has the above satisfied with more arguments:
 	 *
@@ -143,7 +149,7 @@ static bool eprobe_dyn_event_match(const char *system, const char *event,
 		return false;
 
 	/* Must match the event name */
-	if (strcmp(trace_probe_name(&ep->tp), event) != 0)
+	if (event[0] != '\0' && strcmp(trace_probe_name(&ep->tp), event) != 0)
 		return false;
 
 	/* No arguments match all */
@@ -226,6 +232,7 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
 	struct probe_arg *parg = &ep->tp.args[i];
 	struct ftrace_event_field *field;
 	struct list_head *head;
+	int ret = -ENOENT;
 
 	head = trace_get_fields(ep->event);
 	list_for_each_entry(field, head, link) {
@@ -235,14 +242,24 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
 			return 0;
 		}
 	}
+
+	/*
+	 * Argument not found on event. But allow for comm and COMM
+	 * to be used to get the current->comm.
+	 */
+	if (strcmp(parg->code->data, "COMM") == 0 ||
+	    strcmp(parg->code->data, "comm") == 0) {
+		parg->code->op = FETCH_OP_COMM;
+		ret = 0;
+	}
+
 	kfree(parg->code->data);
 	parg->code->data = NULL;
-	return -ENOENT;
+	return ret;
 }
 
 static int eprobe_event_define_fields(struct trace_event_call *event_call)
 {
-	int ret;
 	struct eprobe_trace_entry_head field;
 	struct trace_probe *tp;
 
@@ -250,8 +267,6 @@ static int eprobe_event_define_fields(struct trace_event_call *event_call)
 	if (WARN_ON_ONCE(!tp))
 		return -ENOENT;
 
-	DEFINE_FIELD(unsigned int, type, FIELD_STRING_TYPE, 0);
-
 	return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
 }
 
@@ -270,7 +285,9 @@ print_eprobe_event(struct trace_iterator *iter, int flags,
 	struct trace_event_call *pevent;
 	struct trace_event *probed_event;
 	struct trace_seq *s = &iter->seq;
+	struct trace_eprobe *ep;
 	struct trace_probe *tp;
+	unsigned int type;
 
 	field = (struct eprobe_trace_entry_head *)iter->ent;
 	tp = trace_probe_primary_from_call(
@@ -278,15 +295,18 @@ print_eprobe_event(struct trace_iterator *iter, int flags,
 	if (WARN_ON_ONCE(!tp))
 		goto out;
 
+	ep = container_of(tp, struct trace_eprobe, tp);
+	type = ep->event->event.type;
+
 	trace_seq_printf(s, "%s: (", trace_probe_name(tp));
 
-	probed_event = ftrace_find_event(field->type);
+	probed_event = ftrace_find_event(type);
 	if (probed_event) {
 		pevent = container_of(probed_event, struct trace_event_call, event);
 		trace_seq_printf(s, "%s.%s", pevent->class->system,
 				 trace_event_name(pevent));
 	} else {
-		trace_seq_printf(s, "%u", field->type);
+		trace_seq_printf(s, "%u", type);
 	}
 
 	trace_seq_putc(s, ')');
@@ -308,6 +328,27 @@ static unsigned long get_event_field(struct fetch_insn *code, void *rec)
 
 	addr = rec + field->offset;
 
+	if (is_string_field(field)) {
+		switch (field->filter_type) {
+		case FILTER_DYN_STRING:
+			val = (unsigned long)(rec + (*(unsigned int *)addr & 0xffff));
+			break;
+		case FILTER_RDYN_STRING:
+			val = (unsigned long)(addr + (*(unsigned int *)addr & 0xffff));
+			break;
+		case FILTER_STATIC_STRING:
+			val = (unsigned long)addr;
+			break;
+		case FILTER_PTR_STRING:
+			val = (unsigned long)(*(char *)addr);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			return 0;
+		}
+		return val;
+	}
+
 	switch (field->size) {
 	case 1:
 		if (field->is_signed)
@@ -339,16 +380,38 @@ static unsigned long get_event_field(struct fetch_insn *code, void *rec)
 
 static int get_eprobe_size(struct trace_probe *tp, void *rec)
 {
+	struct fetch_insn *code;
 	struct probe_arg *arg;
 	int i, len, ret = 0;
 
 	for (i = 0; i < tp->nr_args; i++) {
 		arg = tp->args + i;
-		if (unlikely(arg->dynamic)) {
+		if (arg->dynamic) {
 			unsigned long val;
 
-			val = get_event_field(arg->code, rec);
-			len = process_fetch_insn_bottom(arg->code + 1, val, NULL, NULL);
+			code = arg->code;
+ retry:
+			switch (code->op) {
+			case FETCH_OP_TP_ARG:
+				val = get_event_field(code, rec);
+				break;
+			case FETCH_OP_IMM:
+				val = code->immediate;
+				break;
+			case FETCH_OP_COMM:
+				val = (unsigned long)current->comm;
+				break;
+			case FETCH_OP_DATA:
+				val = (unsigned long)code->data;
+				break;
+			case FETCH_NOP_SYMBOL:	/* Ignore a place holder */
+				code++;
+				goto retry;
+			default:
+				continue;
+			}
+			code++;
+			len = process_fetch_insn_bottom(code, val, NULL, NULL);
 			if (len > 0)
 				ret += len;
 		}
@@ -366,8 +429,28 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
 {
 	unsigned long val;
 
-	val = get_event_field(code, rec);
-	return process_fetch_insn_bottom(code + 1, val, dest, base);
+ retry:
+	switch (code->op) {
+	case FETCH_OP_TP_ARG:
+		val = get_event_field(code, rec);
+		break;
+	case FETCH_OP_IMM:
+		val = code->immediate;
+		break;
+	case FETCH_OP_COMM:
+		val = (unsigned long)current->comm;
+		break;
+	case FETCH_OP_DATA:
+		val = (unsigned long)code->data;
+		break;
+	case FETCH_NOP_SYMBOL:	/* Ignore a place holder */
+		code++;
+		goto retry;
+	default:
+		return -EILSEQ;
+	}
+	code++;
+	return process_fetch_insn_bottom(code, val, dest, base);
 }
 NOKPROBE_SYMBOL(process_fetch_insn)
 
@@ -375,29 +458,14 @@ NOKPROBE_SYMBOL(process_fetch_insn)
 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 kern_fetch_store_strlen_user(addr);
 }
 
 /* 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 = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
-		len++;
-	} while (c && ret == 0 && len < MAX_STRING_SIZE);
-
-	return (ret < 0) ? ret : len;
+	return kern_fetch_store_strlen(addr);
 }
 
 /*
@@ -407,21 +475,7 @@ fetch_store_strlen(unsigned long addr)
 static nokprobe_inline int
 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;
-
-	if (unlikely(!maxlen))
-		return -ENOMEM;
-
-	__dest = get_loc_data(dest, base);
-
-	ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
-	if (ret >= 0)
-		*(u32 *)dest = make_data_loc(ret, __dest - base);
-
-	return ret;
+	return kern_fetch_store_string_user(addr, dest, base);
 }
 
 /*
@@ -431,29 +485,7 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base)
 static nokprobe_inline int
 fetch_store_string(unsigned long addr, void *dest, void *base)
 {
-	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);
-
-	/*
-	 * 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);
-
-	return ret;
+	return kern_fetch_store_string(addr, dest, base);
 }
 
 static nokprobe_inline int
@@ -498,10 +530,6 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec)
 		return;
 
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
-	if (edata->ep->event)
-		entry->type = edata->ep->event->event.type;
-	else
-		entry->type = 0;
 	store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
@@ -513,20 +541,17 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec)
  * functions are just stubs to fulfill what is needed to use the trigger
  * infrastructure.
  */
-static int eprobe_trigger_init(struct event_trigger_ops *ops,
-			       struct event_trigger_data *data)
+static int eprobe_trigger_init(struct event_trigger_data *data)
 {
 	return 0;
 }
 
-static void eprobe_trigger_free(struct event_trigger_ops *ops,
-				struct event_trigger_data *data)
+static void eprobe_trigger_free(struct event_trigger_data *data)
 {
 
 }
 
 static int eprobe_trigger_print(struct seq_file *m,
-				struct event_trigger_ops *ops,
 				struct event_trigger_data *data)
 {
 	/* Do not print eprobe event triggers */
@@ -539,6 +564,9 @@ static void eprobe_trigger_func(struct event_trigger_data *data,
 {
 	struct eprobe_data *edata = data->private_data;
 
+	if (unlikely(!rec))
+		return;
+
 	__eprobe_trace_func(edata, rec);
 }
 
@@ -551,7 +579,8 @@ static struct event_trigger_ops eprobe_trigger_ops = {
 
 static int eprobe_trigger_cmd_parse(struct event_command *cmd_ops,
 				    struct trace_event_file *file,
-				    char *glob, char *cmd, char *param)
+				    char *glob, char *cmd,
+				    char *param_and_filter)
 {
 	return -1;
 }
@@ -592,14 +621,15 @@ static struct event_trigger_data *
 new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file)
 {
 	struct event_trigger_data *trigger;
+	struct event_filter *filter = NULL;
 	struct eprobe_data *edata;
+	int ret;
 
 	edata = kzalloc(sizeof(*edata), GFP_KERNEL);
 	trigger = kzalloc(sizeof(*trigger), GFP_KERNEL);
 	if (!trigger || !edata) {
-		kfree(edata);
-		kfree(trigger);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto error;
 	}
 
 	trigger->flags = EVENT_TRIGGER_FL_PROBE;
@@ -614,13 +644,25 @@ new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file)
 	trigger->cmd_ops = &event_trigger_cmd;
 
 	INIT_LIST_HEAD(&trigger->list);
-	RCU_INIT_POINTER(trigger->filter, NULL);
+
+	if (ep->filter_str) {
+		ret = create_event_filter(file->tr, ep->event,
+					ep->filter_str, false, &filter);
+		if (ret)
+			goto error;
+	}
+	RCU_INIT_POINTER(trigger->filter, filter);
 
 	edata->file = file;
 	edata->ep = ep;
 	trigger->private_data = edata;
 
 	return trigger;
+error:
+	free_event_filter(filter);
+	kfree(edata);
+	kfree(trigger);
+	return ERR_PTR(ret);
 }
 
 static int enable_eprobe(struct trace_eprobe *ep,
@@ -652,22 +694,25 @@ static struct trace_event_functions eprobe_funcs = {
 static int disable_eprobe(struct trace_eprobe *ep,
 			  struct trace_array *tr)
 {
-	struct event_trigger_data *trigger;
+	struct event_trigger_data *trigger = NULL, *iter;
 	struct trace_event_file *file;
+	struct event_filter *filter;
 	struct eprobe_data *edata;
 
 	file = find_event_file(tr, ep->event_system, ep->event_name);
 	if (!file)
 		return -ENOENT;
 
-	list_for_each_entry(trigger, &file->triggers, list) {
-		if (!(trigger->flags & EVENT_TRIGGER_FL_PROBE))
+	list_for_each_entry(iter, &file->triggers, list) {
+		if (!(iter->flags & EVENT_TRIGGER_FL_PROBE))
 			continue;
-		edata = trigger->private_data;
-		if (edata->ep == ep)
+		edata = iter->private_data;
+		if (edata->ep == ep) {
+			trigger = iter;
 			break;
+		}
 	}
-	if (list_entry_is_head(trigger, &file->triggers, list))
+	if (!trigger)
 		return -ENODEV;
 
 	list_del_rcu(&trigger->list);
@@ -678,6 +723,10 @@ static int disable_eprobe(struct trace_eprobe *ep,
 	/* Make sure nothing is using the edata or trigger */
 	tracepoint_synchronize_unregister();
 
+	filter = rcu_access_pointer(trigger->filter);
+
+	if (filter)
+		free_event_filter(filter);
 	kfree(edata);
 	kfree(trigger);
 
@@ -840,9 +889,66 @@ static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[
 	if (ret)
 		return ret;
 
-	if (ep->tp.args[i].code->op == FETCH_OP_TP_ARG)
+	if (ep->tp.args[i].code->op == FETCH_OP_TP_ARG) {
 		ret = trace_eprobe_tp_arg_update(ep, i);
+		if (ret)
+			trace_probe_log_err(0, BAD_ATTACH_ARG);
+	}
+
+	/* Handle symbols "@" */
+	if (!ret)
+		ret = traceprobe_update_arg(&ep->tp.args[i]);
+
+	return ret;
+}
+
+static int trace_eprobe_parse_filter(struct trace_eprobe *ep, int argc, const char *argv[])
+{
+	struct event_filter *dummy = NULL;
+	int i, ret, len = 0;
+	char *p;
+
+	if (argc == 0) {
+		trace_probe_log_err(0, NO_EP_FILTER);
+		return -EINVAL;
+	}
+
+	/* Recover the filter string */
+	for (i = 0; i < argc; i++)
+		len += strlen(argv[i]) + 1;
+
+	ep->filter_str = kzalloc(len, GFP_KERNEL);
+	if (!ep->filter_str)
+		return -ENOMEM;
+
+	p = ep->filter_str;
+	for (i = 0; i < argc; i++) {
+		ret = snprintf(p, len, "%s ", argv[i]);
+		if (ret < 0)
+			goto error;
+		if (ret > len) {
+			ret = -E2BIG;
+			goto error;
+		}
+		p += ret;
+		len -= ret;
+	}
+	p[-1] = '\0';
+
+	/*
+	 * Ensure the filter string can be parsed correctly. Note, this
+	 * filter string is for the original event, not for the eprobe.
+	 */
+	ret = create_event_filter(top_trace_array(), ep->event, ep->filter_str,
+				  true, &dummy);
+	free_event_filter(dummy);
+	if (ret)
+		goto error;
 
+	return 0;
+error:
+	kfree(ep->filter_str);
+	ep->filter_str = NULL;
 	return ret;
 }
 
@@ -850,8 +956,8 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 {
 	/*
 	 * Argument syntax:
-	 *      e[:[GRP/]ENAME] SYSTEM.EVENT [FETCHARGS]
-	 * Fetch args:
+	 *      e[:[GRP/][ENAME]] SYSTEM.EVENT [FETCHARGS] [if FILTER]
+	 * Fetch args (no space):
 	 *  <name>=$<field>[:TYPE]
 	 */
 	const char *event = NULL, *group = EPROBE_EVENT_SYSTEM;
@@ -860,8 +966,9 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 	struct trace_eprobe *ep = NULL;
 	char buf1[MAX_EVENT_NAME_LEN];
 	char buf2[MAX_EVENT_NAME_LEN];
-	int ret = 0;
-	int i;
+	char gbuf[MAX_EVENT_NAME_LEN];
+	int ret = 0, filter_idx = 0;
+	int i, filter_cnt;
 
 	if (argc < 2 || argv[0][0] != 'e')
 		return -ECANCELED;
@@ -871,25 +978,33 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 	event = strchr(&argv[0][1], ':');
 	if (event) {
 		event++;
-		ret = traceprobe_parse_event_name(&event, &group, buf1,
+		ret = traceprobe_parse_event_name(&event, &group, gbuf,
 						  event - argv[0]);
 		if (ret)
 			goto parse_error;
-	} else {
-		strscpy(buf1, argv[1], MAX_EVENT_NAME_LEN);
-		sanitize_event_name(buf1);
-		event = buf1;
 	}
-	if (!is_good_name(event) || !is_good_name(group))
-		goto parse_error;
 
+	trace_probe_log_set_index(1);
 	sys_event = argv[1];
-	ret = traceprobe_parse_event_name(&sys_event, &sys_name, buf2,
-					  sys_event - argv[1]);
-	if (ret || !sys_name)
-		goto parse_error;
-	if (!is_good_name(sys_event) || !is_good_name(sys_name))
+	ret = traceprobe_parse_event_name(&sys_event, &sys_name, buf2, 0);
+	if (ret || !sys_event || !sys_name) {
+		trace_probe_log_err(0, NO_EVENT_INFO);
 		goto parse_error;
+	}
+
+	if (!event) {
+		strscpy(buf1, sys_event, MAX_EVENT_NAME_LEN);
+		event = buf1;
+	}
+
+	for (i = 2; i < argc; i++) {
+		if (!strcmp(argv[i], "if")) {
+			filter_idx = i + 1;
+			filter_cnt = argc - filter_idx;
+			argc = i;
+			break;
+		}
+	}
 
 	mutex_lock(&event_mutex);
 	event_call = find_and_get_event(sys_name, sys_event);
@@ -898,12 +1013,22 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 
 	if (IS_ERR(ep)) {
 		ret = PTR_ERR(ep);
+		if (ret == -ENODEV)
+			trace_probe_log_err(0, BAD_ATTACH_EVENT);
 		/* This must return -ENOMEM or missing event, else there is a bug */
 		WARN_ON_ONCE(ret != -ENOMEM && ret != -ENODEV);
 		ep = NULL;
 		goto error;
 	}
 
+	if (filter_idx) {
+		trace_probe_log_set_index(filter_idx);
+		ret = trace_eprobe_parse_filter(ep, filter_cnt, argv + filter_idx);
+		if (ret)
+			goto parse_error;
+	} else
+		ep->filter_str = NULL;
+
 	argc -= 2; argv += 2;
 	/* parse arguments */
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index a114549720d6..61e3a2620fa3 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -157,7 +157,7 @@ static void perf_trace_event_unreg(struct perf_event *p_event)
 	int i;
 
 	if (--tp_event->perf_refcount > 0)
-		goto out;
+		return;
 
 	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);
 
@@ -176,8 +176,6 @@ static void perf_trace_event_unreg(struct perf_event *p_event)
 			perf_trace_buf[i] = NULL;
 		}
 	}
-out:
-	trace_event_put_ref(tp_event);
 }
 
 static int perf_trace_event_open(struct perf_event *p_event)
@@ -241,6 +239,7 @@ void perf_trace_destroy(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	trace_event_put_ref(p_event->tp_event);
 	mutex_unlock(&event_mutex);
 }
 
@@ -292,6 +291,7 @@ void perf_kprobe_destroy(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	trace_event_put_ref(p_event->tp_event);
 	mutex_unlock(&event_mutex);
 
 	destroy_local_trace_kprobe(p_event->tp_event);
@@ -347,6 +347,7 @@ void perf_uprobe_destroy(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	trace_event_put_ref(p_event->tp_event);
 	mutex_unlock(&event_mutex);
 	destroy_local_trace_uprobe(p_event->tp_event);
 }
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3147614c1812..f71ea6e79b3c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -40,6 +40,14 @@ static LIST_HEAD(ftrace_generic_fields);
 static LIST_HEAD(ftrace_common_fields);
 static bool eventdir_initialized;
 
+static LIST_HEAD(module_strings);
+
+struct module_string {
+	struct list_head	next;
+	struct module		*module;
+	char			*str;
+};
+
 #define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
 
 static struct kmem_cache *field_cachep;
@@ -168,6 +176,7 @@ static int trace_define_generic_fields(void)
 
 	__generic_field(int, CPU, FILTER_CPU);
 	__generic_field(int, cpu, FILTER_CPU);
+	__generic_field(int, common_cpu, FILTER_CPU);
 	__generic_field(char *, COMM, FILTER_COMM);
 	__generic_field(char *, comm, FILTER_COMM);
 
@@ -399,7 +408,14 @@ static void test_event_printk(struct trace_event_call *call)
 				a = strchr(fmt + i, '&');
 				if ((a && (a < r)) || test_field(r, call))
 					dereference_flags &= ~(1ULL << arg);
+			} else if ((r = strstr(fmt + i, "__get_dynamic_array(")) &&
+				   (!c || r < c)) {
+				dereference_flags &= ~(1ULL << arg);
+			} else if ((r = strstr(fmt + i, "__get_sockaddr(")) &&
+				   (!c || r < c)) {
+				dereference_flags &= ~(1ULL << arg);
 			}
+
 		next_arg:
 			i--;
 			arg++;
@@ -759,7 +775,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
 
 static void
 event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
-		    struct task_struct *prev, struct task_struct *next)
+					struct task_struct *prev,
+					struct task_struct *next,
+					unsigned int prev_state)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *no_pid_list;
@@ -783,7 +801,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
 
 static void
 event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
-		    struct task_struct *prev, struct task_struct *next)
+					 struct task_struct *prev,
+					 struct task_struct *next,
+					 unsigned int prev_state)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *no_pid_list;
@@ -1705,9 +1725,9 @@ static LIST_HEAD(event_subsystems);
 
 static int subsystem_open(struct inode *inode, struct file *filp)
 {
+	struct trace_subsystem_dir *dir = NULL, *iter_dir;
+	struct trace_array *tr = NULL, *iter_tr;
 	struct event_subsystem *system = NULL;
-	struct trace_subsystem_dir *dir = NULL; /* Initialize for gcc */
-	struct trace_array *tr;
 	int ret;
 
 	if (tracing_is_disabled())
@@ -1716,10 +1736,12 @@ static int subsystem_open(struct inode *inode, struct file *filp)
 	/* Make sure the system still exists */
 	mutex_lock(&event_mutex);
 	mutex_lock(&trace_types_lock);
-	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
-		list_for_each_entry(dir, &tr->systems, list) {
-			if (dir == inode->i_private) {
+	list_for_each_entry(iter_tr, &ftrace_trace_arrays, list) {
+		list_for_each_entry(iter_dir, &iter_tr->systems, list) {
+			if (iter_dir == inode->i_private) {
 				/* Don't open systems with no events */
+				tr = iter_tr;
+				dir = iter_dir;
 				if (dir->nr_events) {
 					__get_system_dir(dir);
 					system = dir->subsystem;
@@ -1735,9 +1757,6 @@ static int subsystem_open(struct inode *inode, struct file *filp)
 	if (!system)
 		return -ENODEV;
 
-	/* Some versions of gcc think dir can be uninitialized here */
-	WARN_ON(!dir);
-
 	/* Still need to increment the ref count of the system */
 	if (trace_array_get(tr) < 0) {
 		put_system(dir);
@@ -2262,8 +2281,8 @@ static struct dentry *
 event_subsystem_dir(struct trace_array *tr, const char *name,
 		    struct trace_event_file *file, struct dentry *parent)
 {
+	struct event_subsystem *system, *iter;
 	struct trace_subsystem_dir *dir;
-	struct event_subsystem *system;
 	struct dentry *entry;
 
 	/* First see if we did not already create this dir */
@@ -2277,13 +2296,13 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 	}
 
 	/* Now see if the system itself exists. */
-	list_for_each_entry(system, &event_subsystems, list) {
-		if (strcmp(system->name, name) == 0)
+	system = NULL;
+	list_for_each_entry(iter, &event_subsystems, list) {
+		if (strcmp(iter->name, name) == 0) {
+			system = iter;
 			break;
+		}
 	}
-	/* Reset system variable when not found */
-	if (&system->list == &event_subsystems)
-		system = NULL;
 
 	dir = kmalloc(sizeof(*dir), GFP_KERNEL);
 	if (!dir)
@@ -2633,6 +2652,76 @@ static void update_event_printk(struct trace_event_call *call,
 	}
 }
 
+static void add_str_to_module(struct module *module, char *str)
+{
+	struct module_string *modstr;
+
+	modstr = kmalloc(sizeof(*modstr), GFP_KERNEL);
+
+	/*
+	 * If we failed to allocate memory here, then we'll just
+	 * let the str memory leak when the module is removed.
+	 * If this fails to allocate, there's worse problems than
+	 * a leaked string on module removal.
+	 */
+	if (WARN_ON_ONCE(!modstr))
+		return;
+
+	modstr->module = module;
+	modstr->str = str;
+
+	list_add(&modstr->next, &module_strings);
+}
+
+static void update_event_fields(struct trace_event_call *call,
+				struct trace_eval_map *map)
+{
+	struct ftrace_event_field *field;
+	struct list_head *head;
+	char *ptr;
+	char *str;
+	int len = strlen(map->eval_string);
+
+	/* Dynamic events should never have field maps */
+	if (WARN_ON_ONCE(call->flags & TRACE_EVENT_FL_DYNAMIC))
+		return;
+
+	head = trace_get_fields(call);
+	list_for_each_entry(field, head, link) {
+		ptr = strchr(field->type, '[');
+		if (!ptr)
+			continue;
+		ptr++;
+
+		if (!isalpha(*ptr) && *ptr != '_')
+			continue;
+
+		if (strncmp(map->eval_string, ptr, len) != 0)
+			continue;
+
+		str = kstrdup(field->type, GFP_KERNEL);
+		if (WARN_ON_ONCE(!str))
+			return;
+		ptr = str + (ptr - field->type);
+		ptr = eval_replace(ptr, map, len);
+		/* enum/sizeof string smaller than value */
+		if (WARN_ON_ONCE(!ptr)) {
+			kfree(str);
+			continue;
+		}
+
+		/*
+		 * If the event is part of a module, then we need to free the string
+		 * when the module is removed. Otherwise, it will stay allocated
+		 * until a reboot.
+		 */
+		if (call->module)
+			add_str_to_module(call->module, str);
+
+		field->type = str;
+	}
+}
+
 void trace_event_eval_update(struct trace_eval_map **map, int len)
 {
 	struct trace_event_call *call, *p;
@@ -2668,6 +2757,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 					first = false;
 				}
 				update_event_printk(call, map[i]);
+				update_event_fields(call, map[i]);
 			}
 		}
 	}
@@ -2758,6 +2848,7 @@ int trace_add_event_call(struct trace_event_call *call)
 	mutex_unlock(&trace_types_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(trace_add_event_call);
 
 /*
  * Must be called under locking of trace_types_lock, event_mutex and
@@ -2789,7 +2880,10 @@ static int probe_remove_event_call(struct trace_event_call *call)
 		 * TRACE_REG_UNREGISTER.
 		 */
 		if (file->flags & EVENT_FILE_FL_ENABLED)
-			return -EBUSY;
+			goto busy;
+
+		if (file->flags & EVENT_FILE_FL_WAS_ENABLED)
+			tr->clear_trace = true;
 		/*
 		 * The do_for_each_event_file_safe() is
 		 * a double loop. After finding the call for this
@@ -2802,6 +2896,12 @@ static int probe_remove_event_call(struct trace_event_call *call)
 	__trace_remove_event_call(call);
 
 	return 0;
+ busy:
+	/* No need to clear the trace now */
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		tr->clear_trace = false;
+	}
+	return -EBUSY;
 }
 
 /* Remove an event_call */
@@ -2819,6 +2919,7 @@ int trace_remove_event_call(struct trace_event_call *call)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(trace_remove_event_call);
 
 #define for_each_event(event, start, end)			\
 	for (event = start;					\
@@ -2853,6 +2954,7 @@ static void trace_module_add_events(struct module *mod)
 static void trace_module_remove_events(struct module *mod)
 {
 	struct trace_event_call *call, *p;
+	struct module_string *modstr, *m;
 
 	down_write(&trace_event_sem);
 	list_for_each_entry_safe(call, p, &ftrace_events, list) {
@@ -2861,6 +2963,14 @@ static void trace_module_remove_events(struct module *mod)
 		if (call->module == mod)
 			__trace_remove_event_call(call);
 	}
+	/* Check for any strings allocade for this module */
+	list_for_each_entry_safe(modstr, m, &module_strings, next) {
+		if (modstr->module != mod)
+			continue;
+		list_del(&modstr->next);
+		kfree(modstr->str);
+		kfree(modstr);
+	}
 	up_write(&trace_event_sem);
 
 	/*
@@ -2871,7 +2981,7 @@ static void trace_module_remove_events(struct module *mod)
 	 * over from this module may be passed to the new module events and
 	 * unexpected results may occur.
 	 */
-	tracing_reset_all_online_cpus();
+	tracing_reset_all_online_cpus_unlocked();
 }
 
 static int trace_module_notify(struct notifier_block *self,
@@ -3446,12 +3556,10 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 	struct dentry *d_events;
 	struct dentry *entry;
 
-	entry = tracefs_create_file("set_event", TRACE_MODE_WRITE, parent,
-				    tr, &ftrace_set_event_fops);
-	if (!entry) {
-		pr_warn("Could not create tracefs 'set_event' entry\n");
+	entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent,
+				  tr, &ftrace_set_event_fops);
+	if (!entry)
 		return -ENOMEM;
-	}
 
 	d_events = tracefs_create_dir("events", parent);
 	if (!d_events) {
@@ -3466,16 +3574,12 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 
 	/* There are not as crucial, just warn if they are not created */
 
-	entry = tracefs_create_file("set_event_pid", TRACE_MODE_WRITE, parent,
-				    tr, &ftrace_set_event_pid_fops);
-	if (!entry)
-		pr_warn("Could not create tracefs 'set_event_pid' entry\n");
+	trace_create_file("set_event_pid", TRACE_MODE_WRITE, parent,
+			  tr, &ftrace_set_event_pid_fops);
 
-	entry = tracefs_create_file("set_event_notrace_pid",
-				    TRACE_MODE_WRITE, parent, tr,
-				    &ftrace_set_event_notrace_pid_fops);
-	if (!entry)
-		pr_warn("Could not create tracefs 'set_event_notrace_pid' entry\n");
+	trace_create_file("set_event_notrace_pid",
+			  TRACE_MODE_WRITE, parent, tr,
+			  &ftrace_set_event_notrace_pid_fops);
 
 	/* ring buffer internal formats */
 	trace_create_file("header_page", TRACE_MODE_READ, d_events,
@@ -3690,17 +3794,14 @@ static __init int event_trace_init_fields(void)
 __init int event_trace_init(void)
 {
 	struct trace_array *tr;
-	struct dentry *entry;
 	int ret;
 
 	tr = top_trace_array();
 	if (!tr)
 		return -ENODEV;
 
-	entry = tracefs_create_file("available_events", TRACE_MODE_READ,
-				    NULL, tr, &ftrace_avail_fops);
-	if (!entry)
-		pr_warn("Could not create tracefs 'available_events' entry\n");
+	trace_create_file("available_events", TRACE_MODE_READ,
+			  NULL, tr, &ftrace_avail_fops);
 
 	ret = early_event_add_tracer(NULL, tr);
 	if (ret)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index b458a9afa2c0..96acc2b71ac7 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -43,6 +43,42 @@ enum filter_op_ids { OPS };
 
 static const char * ops[] = { OPS };
 
+enum filter_pred_fn {
+	FILTER_PRED_FN_NOP,
+	FILTER_PRED_FN_64,
+	FILTER_PRED_FN_S64,
+	FILTER_PRED_FN_U64,
+	FILTER_PRED_FN_32,
+	FILTER_PRED_FN_S32,
+	FILTER_PRED_FN_U32,
+	FILTER_PRED_FN_16,
+	FILTER_PRED_FN_S16,
+	FILTER_PRED_FN_U16,
+	FILTER_PRED_FN_8,
+	FILTER_PRED_FN_S8,
+	FILTER_PRED_FN_U8,
+	FILTER_PRED_FN_COMM,
+	FILTER_PRED_FN_STRING,
+	FILTER_PRED_FN_STRLOC,
+	FILTER_PRED_FN_STRRELLOC,
+	FILTER_PRED_FN_PCHAR_USER,
+	FILTER_PRED_FN_PCHAR,
+	FILTER_PRED_FN_CPU,
+	FILTER_PRED_FN_,
+	FILTER_PRED_TEST_VISITED,
+};
+
+struct filter_pred {
+	enum filter_pred_fn 	fn_num;
+	u64 			val;
+	struct regex		regex;
+	unsigned short		*ops;
+	struct ftrace_event_field *field;
+	int 			offset;
+	int			not;
+	int 			op;
+};
+
 /*
  * pred functions are OP_LE, OP_LT, OP_GE, OP_GT, and OP_BAND
  * pred_funcs_##type below must match the order of them above.
@@ -590,44 +626,48 @@ out_free:
 	return ERR_PTR(ret);
 }
 
+enum pred_cmp_types {
+	PRED_CMP_TYPE_NOP,
+	PRED_CMP_TYPE_LT,
+	PRED_CMP_TYPE_LE,
+	PRED_CMP_TYPE_GT,
+	PRED_CMP_TYPE_GE,
+	PRED_CMP_TYPE_BAND,
+};
+
 #define DEFINE_COMPARISON_PRED(type)					\
-static int filter_pred_LT_##type(struct filter_pred *pred, void *event)	\
-{									\
-	type *addr = (type *)(event + pred->offset);			\
-	type val = (type)pred->val;					\
-	return *addr < val;						\
-}									\
-static int filter_pred_LE_##type(struct filter_pred *pred, void *event)	\
-{									\
-	type *addr = (type *)(event + pred->offset);			\
-	type val = (type)pred->val;					\
-	return *addr <= val;						\
-}									\
-static int filter_pred_GT_##type(struct filter_pred *pred, void *event)	\
+static int filter_pred_##type(struct filter_pred *pred, void *event)	\
 {									\
-	type *addr = (type *)(event + pred->offset);			\
-	type val = (type)pred->val;					\
-	return *addr > val;					\
-}									\
-static int filter_pred_GE_##type(struct filter_pred *pred, void *event)	\
-{									\
-	type *addr = (type *)(event + pred->offset);			\
-	type val = (type)pred->val;					\
-	return *addr >= val;						\
-}									\
-static int filter_pred_BAND_##type(struct filter_pred *pred, void *event) \
-{									\
-	type *addr = (type *)(event + pred->offset);			\
-	type val = (type)pred->val;					\
-	return !!(*addr & val);						\
-}									\
-static const filter_pred_fn_t pred_funcs_##type[] = {			\
-	filter_pred_LE_##type,						\
-	filter_pred_LT_##type,						\
-	filter_pred_GE_##type,						\
-	filter_pred_GT_##type,						\
-	filter_pred_BAND_##type,					\
-};
+	switch (pred->op) {						\
+	case OP_LT: {							\
+		type *addr = (type *)(event + pred->offset);		\
+		type val = (type)pred->val;				\
+		return *addr < val;					\
+	}								\
+	case OP_LE: {					\
+		type *addr = (type *)(event + pred->offset);		\
+		type val = (type)pred->val;				\
+		return *addr <= val;					\
+	}								\
+	case OP_GT: {					\
+		type *addr = (type *)(event + pred->offset);		\
+		type val = (type)pred->val;				\
+		return *addr > val;					\
+	}								\
+	case OP_GE: {					\
+		type *addr = (type *)(event + pred->offset);		\
+		type val = (type)pred->val;				\
+		return *addr >= val;					\
+	}								\
+	case OP_BAND: {					\
+		type *addr = (type *)(event + pred->offset);		\
+		type val = (type)pred->val;				\
+		return !!(*addr & val);					\
+	}								\
+	default:							\
+		return 0;						\
+	}								\
+}
 
 #define DEFINE_EQUALITY_PRED(size)					\
 static int filter_pred_##size(struct filter_pred *pred, void *event)	\
@@ -836,11 +876,6 @@ static int filter_pred_comm(struct filter_pred *pred, void *event)
 	return cmp ^ pred->not;
 }
 
-static int filter_pred_none(struct filter_pred *pred, void *event)
-{
-	return 0;
-}
-
 /*
  * regex_match_foo - Basic regex callbacks
  *
@@ -986,6 +1021,19 @@ static void filter_build_regex(struct filter_pred *pred)
 	}
 }
 
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+static int test_pred_visited_fn(struct filter_pred *pred, void *event);
+#else
+static int test_pred_visited_fn(struct filter_pred *pred, void *event)
+{
+	return 0;
+}
+#endif
+
+
+static int filter_pred_fn_call(struct filter_pred *pred, void *event);
+
 /* return 1 if event matches, 0 otherwise (discard) */
 int filter_match_preds(struct event_filter *filter, void *rec)
 {
@@ -1003,7 +1051,7 @@ int filter_match_preds(struct event_filter *filter, void *rec)
 
 	for (i = 0; prog[i].pred; i++) {
 		struct filter_pred *pred = prog[i].pred;
-		int match = pred->fn(pred, rec);
+		int match = filter_pred_fn_call(pred, rec);
 		if (match == prog[i].when_to_branch)
 			i = prog[i].target;
 	}
@@ -1189,10 +1237,10 @@ int filter_assign_type(const char *type)
 	return FILTER_OTHER;
 }
 
-static filter_pred_fn_t select_comparison_fn(enum filter_op_ids op,
-					    int field_size, int field_is_signed)
+static enum filter_pred_fn select_comparison_fn(enum filter_op_ids op,
+						int field_size, int field_is_signed)
 {
-	filter_pred_fn_t fn = NULL;
+	enum filter_pred_fn fn = FILTER_PRED_FN_NOP;
 	int pred_func_index = -1;
 
 	switch (op) {
@@ -1201,50 +1249,99 @@ static filter_pred_fn_t select_comparison_fn(enum filter_op_ids op,
 		break;
 	default:
 		if (WARN_ON_ONCE(op < PRED_FUNC_START))
-			return NULL;
+			return fn;
 		pred_func_index = op - PRED_FUNC_START;
 		if (WARN_ON_ONCE(pred_func_index > PRED_FUNC_MAX))
-			return NULL;
+			return fn;
 	}
 
 	switch (field_size) {
 	case 8:
 		if (pred_func_index < 0)
-			fn = filter_pred_64;
+			fn = FILTER_PRED_FN_64;
 		else if (field_is_signed)
-			fn = pred_funcs_s64[pred_func_index];
+			fn = FILTER_PRED_FN_S64;
 		else
-			fn = pred_funcs_u64[pred_func_index];
+			fn = FILTER_PRED_FN_U64;
 		break;
 	case 4:
 		if (pred_func_index < 0)
-			fn = filter_pred_32;
+			fn = FILTER_PRED_FN_32;
 		else if (field_is_signed)
-			fn = pred_funcs_s32[pred_func_index];
+			fn = FILTER_PRED_FN_S32;
 		else
-			fn = pred_funcs_u32[pred_func_index];
+			fn = FILTER_PRED_FN_U32;
 		break;
 	case 2:
 		if (pred_func_index < 0)
-			fn = filter_pred_16;
+			fn = FILTER_PRED_FN_16;
 		else if (field_is_signed)
-			fn = pred_funcs_s16[pred_func_index];
+			fn = FILTER_PRED_FN_S16;
 		else
-			fn = pred_funcs_u16[pred_func_index];
+			fn = FILTER_PRED_FN_U16;
 		break;
 	case 1:
 		if (pred_func_index < 0)
-			fn = filter_pred_8;
+			fn = FILTER_PRED_FN_8;
 		else if (field_is_signed)
-			fn = pred_funcs_s8[pred_func_index];
+			fn = FILTER_PRED_FN_S8;
 		else
-			fn = pred_funcs_u8[pred_func_index];
+			fn = FILTER_PRED_FN_U8;
 		break;
 	}
 
 	return fn;
 }
 
+
+static int filter_pred_fn_call(struct filter_pred *pred, void *event)
+{
+	switch (pred->fn_num) {
+	case FILTER_PRED_FN_64:
+		return filter_pred_64(pred, event);
+	case FILTER_PRED_FN_S64:
+		return filter_pred_s64(pred, event);
+	case FILTER_PRED_FN_U64:
+		return filter_pred_u64(pred, event);
+	case FILTER_PRED_FN_32:
+		return filter_pred_32(pred, event);
+	case FILTER_PRED_FN_S32:
+		return filter_pred_s32(pred, event);
+	case FILTER_PRED_FN_U32:
+		return filter_pred_u32(pred, event);
+	case FILTER_PRED_FN_16:
+		return filter_pred_16(pred, event);
+	case FILTER_PRED_FN_S16:
+		return filter_pred_s16(pred, event);
+	case FILTER_PRED_FN_U16:
+		return filter_pred_u16(pred, event);
+	case FILTER_PRED_FN_8:
+		return filter_pred_8(pred, event);
+	case FILTER_PRED_FN_S8:
+		return filter_pred_s8(pred, event);
+	case FILTER_PRED_FN_U8:
+		return filter_pred_u8(pred, event);
+	case FILTER_PRED_FN_COMM:
+		return filter_pred_comm(pred, event);
+	case FILTER_PRED_FN_STRING:
+		return filter_pred_string(pred, event);
+	case FILTER_PRED_FN_STRLOC:
+		return filter_pred_strloc(pred, event);
+	case FILTER_PRED_FN_STRRELLOC:
+		return filter_pred_strrelloc(pred, event);
+	case FILTER_PRED_FN_PCHAR_USER:
+		return filter_pred_pchar_user(pred, event);
+	case FILTER_PRED_FN_PCHAR:
+		return filter_pred_pchar(pred, event);
+	case FILTER_PRED_FN_CPU:
+		return filter_pred_cpu(pred, event);
+	case FILTER_PRED_TEST_VISITED:
+		return test_pred_visited_fn(pred, event);
+	default:
+		return 0;
+	}
+}
+
 /* Called when a predicate is encountered by predicate_parse() */
 static int parse_pred(const char *str, void *data,
 		      int pos, struct filter_parse_error *pe,
@@ -1338,7 +1435,7 @@ static int parse_pred(const char *str, void *data,
 			parse_error(pe, FILT_ERR_IP_FIELD_ONLY, pos + i);
 			goto err_free;
 		}
-		pred->fn = filter_pred_none;
+		pred->fn_num = FILTER_PRED_FN_NOP;
 
 		/*
 		 * Quotes are not required, but if they exist then we need
@@ -1416,16 +1513,16 @@ static int parse_pred(const char *str, void *data,
 		filter_build_regex(pred);
 
 		if (field->filter_type == FILTER_COMM) {
-			pred->fn = filter_pred_comm;
+			pred->fn_num = FILTER_PRED_FN_COMM;
 
 		} else if (field->filter_type == FILTER_STATIC_STRING) {
-			pred->fn = filter_pred_string;
+			pred->fn_num = FILTER_PRED_FN_STRING;
 			pred->regex.field_len = field->size;
 
 		} else if (field->filter_type == FILTER_DYN_STRING) {
-			pred->fn = filter_pred_strloc;
+			pred->fn_num = FILTER_PRED_FN_STRLOC;
 		} else if (field->filter_type == FILTER_RDYN_STRING)
-			pred->fn = filter_pred_strrelloc;
+			pred->fn_num = FILTER_PRED_FN_STRRELLOC;
 		else {
 
 			if (!ustring_per_cpu) {
@@ -1436,9 +1533,9 @@ static int parse_pred(const char *str, void *data,
 			}
 
 			if (ustring)
-				pred->fn = filter_pred_pchar_user;
+				pred->fn_num = FILTER_PRED_FN_PCHAR_USER;
 			else
-				pred->fn = filter_pred_pchar;
+				pred->fn_num = FILTER_PRED_FN_PCHAR;
 		}
 		/* go past the last quote */
 		i++;
@@ -1486,10 +1583,10 @@ static int parse_pred(const char *str, void *data,
 		pred->val = val;
 
 		if (field->filter_type == FILTER_CPU)
-			pred->fn = filter_pred_cpu;
+			pred->fn_num = FILTER_PRED_FN_CPU;
 		else {
-			pred->fn = select_comparison_fn(pred->op, field->size,
-							field->is_signed);
+			pred->fn_num = select_comparison_fn(pred->op, field->size,
+							    field->is_signed);
 			if (pred->op == OP_NE)
 				pred->not = 1;
 		}
@@ -1816,7 +1913,7 @@ static void create_filter_finish(struct filter_parse_error *pe)
  * create_filter - create a filter for a trace_event_call
  * @tr: the trace array associated with these events
  * @call: trace_event_call to create a filter for
- * @filter_str: filter string
+ * @filter_string: filter string
  * @set_str: remember @filter_str and enable detailed error in filter
  * @filterp: out param for created filter (always updated on return)
  *           Must be a pointer that references a NULL pointer.
@@ -2296,7 +2393,7 @@ static void update_pred_fn(struct event_filter *filter, char *fields)
 		struct filter_pred *pred = prog[i].pred;
 		struct ftrace_event_field *field = pred->field;
 
-		WARN_ON_ONCE(!pred->fn);
+		WARN_ON_ONCE(pred->fn_num == FILTER_PRED_FN_NOP);
 
 		if (!field) {
 			WARN_ONCE(1, "all leafs should have field defined %d", i);
@@ -2306,7 +2403,7 @@ static void update_pred_fn(struct event_filter *filter, char *fields)
 		if (!strchr(fields, *field->name))
 			continue;
 
-		pred->fn = test_pred_visited_fn;
+		pred->fn_num = FILTER_PRED_TEST_VISITED;
 	}
 }
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index ada87bfb5bb8..1c82478e8dff 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -104,6 +104,38 @@ enum field_op_id {
 	FIELD_OP_MULT,
 };
 
+enum hist_field_fn {
+	HIST_FIELD_FN_NOP,
+	HIST_FIELD_FN_VAR_REF,
+	HIST_FIELD_FN_COUNTER,
+	HIST_FIELD_FN_CONST,
+	HIST_FIELD_FN_LOG2,
+	HIST_FIELD_FN_BUCKET,
+	HIST_FIELD_FN_TIMESTAMP,
+	HIST_FIELD_FN_CPU,
+	HIST_FIELD_FN_STRING,
+	HIST_FIELD_FN_DYNSTRING,
+	HIST_FIELD_FN_RELDYNSTRING,
+	HIST_FIELD_FN_PSTRING,
+	HIST_FIELD_FN_S64,
+	HIST_FIELD_FN_U64,
+	HIST_FIELD_FN_S32,
+	HIST_FIELD_FN_U32,
+	HIST_FIELD_FN_S16,
+	HIST_FIELD_FN_U16,
+	HIST_FIELD_FN_S8,
+	HIST_FIELD_FN_U8,
+	HIST_FIELD_FN_UMINUS,
+	HIST_FIELD_FN_MINUS,
+	HIST_FIELD_FN_PLUS,
+	HIST_FIELD_FN_DIV,
+	HIST_FIELD_FN_MULT,
+	HIST_FIELD_FN_DIV_POWER2,
+	HIST_FIELD_FN_DIV_NOT_POWER2,
+	HIST_FIELD_FN_DIV_MULT_SHIFT,
+	HIST_FIELD_FN_EXECNAME,
+};
+
 /*
  * A hist_var (histogram variable) contains variable information for
  * hist_fields having the HIST_FIELD_FL_VAR or HIST_FIELD_FL_VAR_REF
@@ -123,15 +155,15 @@ struct hist_var {
 struct hist_field {
 	struct ftrace_event_field	*field;
 	unsigned long			flags;
-	hist_field_fn_t			fn;
-	unsigned int			ref;
-	unsigned int			size;
-	unsigned int			offset;
-	unsigned int                    is_signed;
 	unsigned long			buckets;
 	const char			*type;
 	struct hist_field		*operands[HIST_FIELD_OPERANDS_MAX];
 	struct hist_trigger_data	*hist_data;
+	enum hist_field_fn		fn_num;
+	unsigned int			ref;
+	unsigned int			size;
+	unsigned int			offset;
+	unsigned int                    is_signed;
 
 	/*
 	 * Variable fields contain variable-specific info in var.
@@ -166,14 +198,11 @@ struct hist_field {
 	u64				div_multiplier;
 };
 
-static u64 hist_field_none(struct hist_field *field,
-			   struct tracing_map_elt *elt,
-			   struct trace_buffer *buffer,
-			   struct ring_buffer_event *rbe,
-			   void *event)
-{
-	return 0;
-}
+static u64 hist_fn_call(struct hist_field *hist_field,
+			struct tracing_map_elt *elt,
+			struct trace_buffer *buffer,
+			struct ring_buffer_event *rbe,
+			void *event);
 
 static u64 hist_field_const(struct hist_field *field,
 			   struct tracing_map_elt *elt,
@@ -250,7 +279,7 @@ static u64 hist_field_log2(struct hist_field *hist_field,
 {
 	struct hist_field *operand = hist_field->operands[0];
 
-	u64 val = operand->fn(operand, elt, buffer, rbe, event);
+	u64 val = hist_fn_call(operand, elt, buffer, rbe, event);
 
 	return (u64) ilog2(roundup_pow_of_two(val));
 }
@@ -264,7 +293,7 @@ static u64 hist_field_bucket(struct hist_field *hist_field,
 	struct hist_field *operand = hist_field->operands[0];
 	unsigned long buckets = hist_field->buckets;
 
-	u64 val = operand->fn(operand, elt, buffer, rbe, event);
+	u64 val = hist_fn_call(operand, elt, buffer, rbe, event);
 
 	if (WARN_ON_ONCE(!buckets))
 		return val;
@@ -285,8 +314,8 @@ static u64 hist_field_plus(struct hist_field *hist_field,
 	struct hist_field *operand1 = hist_field->operands[0];
 	struct hist_field *operand2 = hist_field->operands[1];
 
-	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
-	u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);
+	u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
+	u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event);
 
 	return val1 + val2;
 }
@@ -300,8 +329,8 @@ static u64 hist_field_minus(struct hist_field *hist_field,
 	struct hist_field *operand1 = hist_field->operands[0];
 	struct hist_field *operand2 = hist_field->operands[1];
 
-	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
-	u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);
+	u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
+	u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event);
 
 	return val1 - val2;
 }
@@ -315,8 +344,8 @@ static u64 hist_field_div(struct hist_field *hist_field,
 	struct hist_field *operand1 = hist_field->operands[0];
 	struct hist_field *operand2 = hist_field->operands[1];
 
-	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
-	u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);
+	u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
+	u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event);
 
 	/* Return -1 for the undefined case */
 	if (!val2)
@@ -338,7 +367,7 @@ static u64 div_by_power_of_two(struct hist_field *hist_field,
 	struct hist_field *operand1 = hist_field->operands[0];
 	struct hist_field *operand2 = hist_field->operands[1];
 
-	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+	u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
 
 	return val1 >> __ffs64(operand2->constant);
 }
@@ -352,7 +381,7 @@ static u64 div_by_not_power_of_two(struct hist_field *hist_field,
 	struct hist_field *operand1 = hist_field->operands[0];
 	struct hist_field *operand2 = hist_field->operands[1];
 
-	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+	u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
 
 	return div64_u64(val1, operand2->constant);
 }
@@ -366,7 +395,7 @@ static u64 div_by_mult_and_shift(struct hist_field *hist_field,
 	struct hist_field *operand1 = hist_field->operands[0];
 	struct hist_field *operand2 = hist_field->operands[1];
 
-	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+	u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
 
 	/*
 	 * If the divisor is a constant, do a multiplication and shift instead.
@@ -400,8 +429,8 @@ static u64 hist_field_mult(struct hist_field *hist_field,
 	struct hist_field *operand1 = hist_field->operands[0];
 	struct hist_field *operand2 = hist_field->operands[1];
 
-	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
-	u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);
+	u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event);
+	u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event);
 
 	return val1 * val2;
 }
@@ -414,7 +443,7 @@ static u64 hist_field_unary_minus(struct hist_field *hist_field,
 {
 	struct hist_field *operand = hist_field->operands[0];
 
-	s64 sval = (s64)operand->fn(operand, elt, buffer, rbe, event);
+	s64 sval = (s64)hist_fn_call(operand, elt, buffer, rbe, event);
 	u64 val = (u64)-sval;
 
 	return val;
@@ -657,19 +686,19 @@ struct snapshot_context {
  * Returns the specific division function to use if the divisor
  * is constant. This avoids extra branches when the trigger is hit.
  */
-static hist_field_fn_t hist_field_get_div_fn(struct hist_field *divisor)
+static enum hist_field_fn hist_field_get_div_fn(struct hist_field *divisor)
 {
 	u64 div = divisor->constant;
 
 	if (!(div & (div - 1)))
-		return div_by_power_of_two;
+		return HIST_FIELD_FN_DIV_POWER2;
 
 	/* If the divisor is too large, do a regular division */
 	if (div > (1 << HIST_DIV_SHIFT))
-		return div_by_not_power_of_two;
+		return HIST_FIELD_FN_DIV_NOT_POWER2;
 
 	divisor->div_multiplier = div64_u64((u64)(1 << HIST_DIV_SHIFT), div);
-	return div_by_mult_and_shift;
+	return HIST_FIELD_FN_DIV_MULT_SHIFT;
 }
 
 static void track_data_free(struct track_data *track_data)
@@ -727,11 +756,16 @@ static struct track_data *track_data_alloc(unsigned int key_len,
 	return data;
 }
 
-static char last_cmd[MAX_FILTER_STR_VAL];
+#define HIST_PREFIX "hist:"
+
+static char *last_cmd;
 static char last_cmd_loc[MAX_FILTER_STR_VAL];
 
 static int errpos(char *str)
 {
+	if (!str || !last_cmd)
+		return 0;
+
 	return err_pos(last_cmd, str);
 }
 
@@ -739,12 +773,22 @@ static void last_cmd_set(struct trace_event_file *file, char *str)
 {
 	const char *system = NULL, *name = NULL;
 	struct trace_event_call *call;
+	int len;
 
 	if (!str)
 		return;
 
-	strcpy(last_cmd, "hist:");
-	strncat(last_cmd, str, MAX_FILTER_STR_VAL - 1 - sizeof("hist:"));
+	/* sizeof() contains the nul byte */
+	len = sizeof(HIST_PREFIX) + strlen(str);
+	kfree(last_cmd);
+	last_cmd = kzalloc(len, GFP_KERNEL);
+	if (!last_cmd)
+		return;
+
+	strcpy(last_cmd, HIST_PREFIX);
+	/* Again, sizeof() contains the nul byte */
+	len -= sizeof(HIST_PREFIX);
+	strncat(last_cmd, str, len);
 
 	if (file) {
 		call = file->event_call;
@@ -757,18 +801,22 @@ static void last_cmd_set(struct trace_event_file *file, char *str)
 	}
 
 	if (system)
-		snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, "hist:%s:%s", system, name);
+		snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, HIST_PREFIX "%s:%s", system, name);
 }
 
-static void hist_err(struct trace_array *tr, u8 err_type, u8 err_pos)
+static void hist_err(struct trace_array *tr, u8 err_type, u16 err_pos)
 {
+	if (!last_cmd)
+		return;
+
 	tracing_log_err(tr, last_cmd_loc, last_cmd, err_text,
 			err_type, err_pos);
 }
 
 static void hist_err_clear(void)
 {
-	last_cmd[0] = '\0';
+	if (last_cmd)
+		last_cmd[0] = '\0';
 	last_cmd_loc[0] = '\0';
 }
 
@@ -935,7 +983,7 @@ static struct hist_field *find_any_var_ref(struct hist_trigger_data *hist_data,
  * A trigger can define one or more variables.  If any one of them is
  * currently referenced by any other trigger, this function will
  * determine that.
-
+ *
  * Typically used to determine whether or not a trigger can be removed
  * - if there are any references to a trigger's variables, it cannot.
  *
@@ -1315,38 +1363,32 @@ static const char *hist_field_name(struct hist_field *field,
 	return field_name;
 }
 
-static hist_field_fn_t select_value_fn(int field_size, int field_is_signed)
+static enum hist_field_fn select_value_fn(int field_size, int field_is_signed)
 {
-	hist_field_fn_t fn = NULL;
-
 	switch (field_size) {
 	case 8:
 		if (field_is_signed)
-			fn = hist_field_s64;
+			return HIST_FIELD_FN_S64;
 		else
-			fn = hist_field_u64;
-		break;
+			return HIST_FIELD_FN_U64;
 	case 4:
 		if (field_is_signed)
-			fn = hist_field_s32;
+			return HIST_FIELD_FN_S32;
 		else
-			fn = hist_field_u32;
-		break;
+			return HIST_FIELD_FN_U32;
 	case 2:
 		if (field_is_signed)
-			fn = hist_field_s16;
+			return HIST_FIELD_FN_S16;
 		else
-			fn = hist_field_u16;
-		break;
+			return HIST_FIELD_FN_U16;
 	case 1:
 		if (field_is_signed)
-			fn = hist_field_s8;
+			return HIST_FIELD_FN_S8;
 		else
-			fn = hist_field_u8;
-		break;
+			return HIST_FIELD_FN_U8;
 	}
 
-	return fn;
+	return HIST_FIELD_FN_NOP;
 }
 
 static int parse_map_size(char *str)
@@ -1903,19 +1945,19 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 		goto out; /* caller will populate */
 
 	if (flags & HIST_FIELD_FL_VAR_REF) {
-		hist_field->fn = hist_field_var_ref;
+		hist_field->fn_num = HIST_FIELD_FN_VAR_REF;
 		goto out;
 	}
 
 	if (flags & HIST_FIELD_FL_HITCOUNT) {
-		hist_field->fn = hist_field_counter;
+		hist_field->fn_num = HIST_FIELD_FN_COUNTER;
 		hist_field->size = sizeof(u64);
 		hist_field->type = "u64";
 		goto out;
 	}
 
 	if (flags & HIST_FIELD_FL_CONST) {
-		hist_field->fn = hist_field_const;
+		hist_field->fn_num = HIST_FIELD_FN_CONST;
 		hist_field->size = sizeof(u64);
 		hist_field->type = kstrdup("u64", GFP_KERNEL);
 		if (!hist_field->type)
@@ -1924,14 +1966,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 	}
 
 	if (flags & HIST_FIELD_FL_STACKTRACE) {
-		hist_field->fn = hist_field_none;
+		hist_field->fn_num = HIST_FIELD_FN_NOP;
 		goto out;
 	}
 
 	if (flags & (HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_BUCKET)) {
 		unsigned long fl = flags & ~(HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_BUCKET);
-		hist_field->fn = flags & HIST_FIELD_FL_LOG2 ? hist_field_log2 :
-			hist_field_bucket;
+		hist_field->fn_num = flags & HIST_FIELD_FL_LOG2 ? HIST_FIELD_FN_LOG2 :
+			HIST_FIELD_FN_BUCKET;
 		hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
 		hist_field->size = hist_field->operands[0]->size;
 		hist_field->type = kstrdup_const(hist_field->operands[0]->type, GFP_KERNEL);
@@ -1941,14 +1983,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 	}
 
 	if (flags & HIST_FIELD_FL_TIMESTAMP) {
-		hist_field->fn = hist_field_timestamp;
+		hist_field->fn_num = HIST_FIELD_FN_TIMESTAMP;
 		hist_field->size = sizeof(u64);
 		hist_field->type = "u64";
 		goto out;
 	}
 
 	if (flags & HIST_FIELD_FL_CPU) {
-		hist_field->fn = hist_field_cpu;
+		hist_field->fn_num = HIST_FIELD_FN_CPU;
 		hist_field->size = sizeof(int);
 		hist_field->type = "unsigned int";
 		goto out;
@@ -1968,14 +2010,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 			goto free;
 
 		if (field->filter_type == FILTER_STATIC_STRING) {
-			hist_field->fn = hist_field_string;
+			hist_field->fn_num = HIST_FIELD_FN_STRING;
 			hist_field->size = field->size;
 		} else if (field->filter_type == FILTER_DYN_STRING) {
-			hist_field->fn = hist_field_dynstring;
+			hist_field->fn_num = HIST_FIELD_FN_DYNSTRING;
 		} else if (field->filter_type == FILTER_RDYN_STRING)
-			hist_field->fn = hist_field_reldynstring;
+			hist_field->fn_num = HIST_FIELD_FN_RELDYNSTRING;
 		else
-			hist_field->fn = hist_field_pstring;
+			hist_field->fn_num = HIST_FIELD_FN_PSTRING;
 	} else {
 		hist_field->size = field->size;
 		hist_field->is_signed = field->is_signed;
@@ -1983,9 +2025,9 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 		if (!hist_field->type)
 			goto free;
 
-		hist_field->fn = select_value_fn(field->size,
-						 field->is_signed);
-		if (!hist_field->fn) {
+		hist_field->fn_num = select_value_fn(field->size,
+						     field->is_signed);
+		if (hist_field->fn_num == HIST_FIELD_FN_NOP) {
 			destroy_hist_field(hist_field, 0);
 			return NULL;
 		}
@@ -2074,8 +2116,11 @@ static int init_var_ref(struct hist_field *ref_field,
 	return err;
  free:
 	kfree(ref_field->system);
+	ref_field->system = NULL;
 	kfree(ref_field->event_name);
+	ref_field->event_name = NULL;
 	kfree(ref_field->name);
+	ref_field->name = NULL;
 
 	goto out;
 }
@@ -2289,9 +2334,9 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 			/*
 			 * For backward compatibility, if field_name
 			 * was "cpu", then we treat this the same as
-			 * common_cpu.
+			 * common_cpu. This also works for "CPU".
 			 */
-			if (strcmp(field_name, "cpu") == 0) {
+			if (field && field->filter_type == FILTER_CPU) {
 				*flags |= HIST_FIELD_FL_CPU;
 			} else {
 				hist_err(tr, HIST_ERR_FIELD_NOT_FOUND,
@@ -2318,7 +2363,7 @@ static struct hist_field *create_alias(struct hist_trigger_data *hist_data,
 	if (!alias)
 		return NULL;
 
-	alias->fn = var_ref->fn;
+	alias->fn_num = var_ref->fn_num;
 	alias->operands[0] = var_ref;
 
 	if (init_var_ref(alias, var_ref, var_ref->system, var_ref->event_name)) {
@@ -2501,7 +2546,7 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
 
 	expr->flags |= operand1->flags &
 		(HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
-	expr->fn = hist_field_unary_minus;
+	expr->fn_num = HIST_FIELD_FN_UMINUS;
 	expr->operands[0] = operand1;
 	expr->size = operand1->size;
 	expr->is_signed = operand1->is_signed;
@@ -2573,7 +2618,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 	unsigned long operand_flags, operand2_flags;
 	int field_op, ret = -EINVAL;
 	char *sep, *operand1_str;
-	hist_field_fn_t op_fn;
+	enum hist_field_fn op_fn;
 	bool combine_consts;
 
 	if (*n_subexprs > 3) {
@@ -2632,16 +2677,16 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 
 	switch (field_op) {
 	case FIELD_OP_MINUS:
-		op_fn = hist_field_minus;
+		op_fn = HIST_FIELD_FN_MINUS;
 		break;
 	case FIELD_OP_PLUS:
-		op_fn = hist_field_plus;
+		op_fn = HIST_FIELD_FN_PLUS;
 		break;
 	case FIELD_OP_DIV:
-		op_fn = hist_field_div;
+		op_fn = HIST_FIELD_FN_DIV;
 		break;
 	case FIELD_OP_MULT:
-		op_fn = hist_field_mult;
+		op_fn = HIST_FIELD_FN_MULT;
 		break;
 	default:
 		ret = -EINVAL;
@@ -2697,13 +2742,16 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 		op_fn = hist_field_get_div_fn(operand2);
 	}
 
+	expr->fn_num = op_fn;
+
 	if (combine_consts) {
 		if (var1)
 			expr->operands[0] = var1;
 		if (var2)
 			expr->operands[1] = var2;
 
-		expr->constant = op_fn(expr, NULL, NULL, NULL, NULL);
+		expr->constant = hist_fn_call(expr, NULL, NULL, NULL, NULL);
+		expr->fn_num = HIST_FIELD_FN_CONST;
 
 		expr->operands[0] = NULL;
 		expr->operands[1] = NULL;
@@ -2717,8 +2765,6 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 
 		expr->name = expr_str(expr, 0);
 	} else {
-		expr->fn = op_fn;
-
 		/* The operand sizes should be the same, so just pick one */
 		expr->size = operand1->size;
 		expr->is_signed = operand1->is_signed;
@@ -2766,7 +2812,8 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data,
 static struct event_command trigger_hist_cmd;
 static int event_hist_trigger_parse(struct event_command *cmd_ops,
 				    struct trace_event_file *file,
-				    char *glob, char *cmd, char *param);
+				    char *glob, char *cmd,
+				    char *param_and_filter);
 
 static bool compatible_keys(struct hist_trigger_data *target_hist_data,
 			    struct hist_trigger_data *hist_data,
@@ -3042,7 +3089,7 @@ static inline void __update_field_vars(struct tracing_map_elt *elt,
 		struct hist_field *var = field_var->var;
 		struct hist_field *val = field_var->val;
 
-		var_val = val->fn(val, elt, buffer, rbe, rec);
+		var_val = hist_fn_call(val, elt, buffer, rbe, rec);
 		var_idx = var->var.idx;
 
 		if (val->flags & HIST_FIELD_FL_STRING) {
@@ -3179,7 +3226,7 @@ static struct field_var *create_field_var(struct hist_trigger_data *hist_data,
  * events.  However, for convenience, users are allowed to directly
  * specify an event field in an action, which will be automatically
  * converted into a variable on their behalf.
-
+ *
  * This function creates a field variable with the name var_name on
  * the hist trigger currently being defined on the target event.  If
  * subsys_name and event_name are specified, this function simply
@@ -4142,7 +4189,7 @@ static int create_val_field(struct hist_trigger_data *hist_data,
 	return __create_val_field(hist_data, val_idx, file, NULL, field_str, 0);
 }
 
-static const char *no_comm = "(no comm)";
+static const char no_comm[] = "(no comm)";
 
 static u64 hist_field_execname(struct hist_field *hist_field,
 			       struct tracing_map_elt *elt,
@@ -4163,6 +4210,74 @@ static u64 hist_field_execname(struct hist_field *hist_field,
 	return (u64)(unsigned long)(elt_data->comm);
 }
 
+static u64 hist_fn_call(struct hist_field *hist_field,
+			struct tracing_map_elt *elt,
+			struct trace_buffer *buffer,
+			struct ring_buffer_event *rbe,
+			void *event)
+{
+	switch (hist_field->fn_num) {
+	case HIST_FIELD_FN_VAR_REF:
+		return hist_field_var_ref(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_COUNTER:
+		return hist_field_counter(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_CONST:
+		return hist_field_const(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_LOG2:
+		return hist_field_log2(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_BUCKET:
+		return hist_field_bucket(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_TIMESTAMP:
+		return hist_field_timestamp(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_CPU:
+		return hist_field_cpu(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_STRING:
+		return hist_field_string(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_DYNSTRING:
+		return hist_field_dynstring(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_RELDYNSTRING:
+		return hist_field_reldynstring(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_PSTRING:
+		return hist_field_pstring(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_S64:
+		return hist_field_s64(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_U64:
+		return hist_field_u64(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_S32:
+		return hist_field_s32(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_U32:
+		return hist_field_u32(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_S16:
+		return hist_field_s16(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_U16:
+		return hist_field_u16(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_S8:
+		return hist_field_s8(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_U8:
+		return hist_field_u8(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_UMINUS:
+		return hist_field_unary_minus(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_MINUS:
+		return hist_field_minus(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_PLUS:
+		return hist_field_plus(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_DIV:
+		return hist_field_div(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_MULT:
+		return hist_field_mult(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_DIV_POWER2:
+		return div_by_power_of_two(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_DIV_NOT_POWER2:
+		return div_by_not_power_of_two(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_DIV_MULT_SHIFT:
+		return div_by_mult_and_shift(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_EXECNAME:
+		return hist_field_execname(hist_field, elt, buffer, rbe, event);
+	default:
+		return 0;
+	}
+}
+
 /* Convert a var that points to common_pid.execname to a string */
 static void update_var_execname(struct hist_field *hist_field)
 {
@@ -4174,7 +4289,7 @@ static void update_var_execname(struct hist_field *hist_field)
 	kfree_const(hist_field->type);
 	hist_field->type = "char[]";
 
-	hist_field->fn = hist_field_execname;
+	hist_field->fn_num = HIST_FIELD_FN_EXECNAME;
 }
 
 static int create_var_field(struct hist_trigger_data *hist_data,
@@ -4407,6 +4522,8 @@ 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]);
+				hist_data->attrs->var_defs.name[n_vars] = NULL;
 				ret = -ENOMEM;
 				goto free;
 			}
@@ -4430,7 +4547,7 @@ static int create_hist_fields(struct hist_trigger_data *hist_data,
 
 	ret = parse_var_defs(hist_data);
 	if (ret)
-		goto out;
+		return ret;
 
 	ret = create_val_fields(hist_data, file);
 	if (ret)
@@ -4441,8 +4558,7 @@ static int create_hist_fields(struct hist_trigger_data *hist_data,
 		goto out;
 
 	ret = create_key_fields(hist_data, file);
-	if (ret)
-		goto out;
+
  out:
 	free_var_defs(hist_data);
 
@@ -4832,7 +4948,7 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data)
 
 			if (hist_field->flags & HIST_FIELD_FL_STACKTRACE)
 				cmp_fn = tracing_map_cmp_none;
-			else if (!field)
+			else if (!field || hist_field->flags & HIST_FIELD_FL_CPU)
 				cmp_fn = tracing_map_cmp_num(hist_field->size,
 							     hist_field->is_signed);
 			else if (is_string_field(field))
@@ -4932,7 +5048,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
 
 	for_each_hist_val_field(i, hist_data) {
 		hist_field = hist_data->fields[i];
-		hist_val = hist_field->fn(hist_field, elt, buffer, rbe, rec);
+		hist_val = hist_fn_call(hist_field, elt, buffer, rbe, rec);
 		if (hist_field->flags & HIST_FIELD_FL_VAR) {
 			var_idx = hist_field->var.idx;
 
@@ -4963,7 +5079,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
 	for_each_hist_key_field(i, hist_data) {
 		hist_field = hist_data->fields[i];
 		if (hist_field->flags & HIST_FIELD_FL_VAR) {
-			hist_val = hist_field->fn(hist_field, elt, buffer, rbe, rec);
+			hist_val = hist_fn_call(hist_field, elt, buffer, rbe, rec);
 			var_idx = hist_field->var.idx;
 			tracing_map_set_var(elt, var_idx, hist_val);
 		}
@@ -5027,6 +5143,9 @@ static void event_hist_trigger(struct event_trigger_data *data,
 	void *key = NULL;
 	unsigned int i;
 
+	if (unlikely(!rbe))
+		return;
+
 	memset(compound_key, 0, hist_data->key_size);
 
 	for_each_hist_key_field(i, hist_data) {
@@ -5038,7 +5157,7 @@ static void event_hist_trigger(struct event_trigger_data *data,
 					 HIST_STACKTRACE_SKIP);
 			key = entries;
 		} else {
-			field_contents = key_field->fn(key_field, elt, buffer, rbe, rec);
+			field_contents = hist_fn_call(key_field, elt, buffer, rbe, rec);
 			if (key_field->flags & HIST_FIELD_FL_STRING) {
 				key = (void *)(unsigned long)field_contents;
 				use_compound_key = true;
@@ -5233,7 +5352,7 @@ static void hist_trigger_show(struct seq_file *m,
 		seq_puts(m, "\n\n");
 
 	seq_puts(m, "# event histogram\n#\n# trigger info: ");
-	data->ops->print(m, data->ops, data);
+	data->ops->print(m, data);
 	seq_puts(m, "#\n\n");
 
 	hist_data = data->private_data;
@@ -5465,7 +5584,7 @@ static void hist_trigger_debug_show(struct seq_file *m,
 		seq_puts(m, "\n\n");
 
 	seq_puts(m, "# event histogram\n#\n# trigger info: ");
-	data->ops->print(m, data->ops, data);
+	data->ops->print(m, data);
 	seq_puts(m, "#\n\n");
 
 	hist_data = data->private_data;
@@ -5602,7 +5721,6 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
 }
 
 static int event_hist_trigger_print(struct seq_file *m,
-				    struct event_trigger_ops *ops,
 				    struct event_trigger_data *data)
 {
 	struct hist_trigger_data *hist_data = data->private_data;
@@ -5610,7 +5728,7 @@ static int event_hist_trigger_print(struct seq_file *m,
 	bool have_var = false;
 	unsigned int i;
 
-	seq_puts(m, "hist:");
+	seq_puts(m, HIST_PREFIX);
 
 	if (data->name)
 		seq_printf(m, "%s:", data->name);
@@ -5710,8 +5828,7 @@ static int event_hist_trigger_print(struct seq_file *m,
 	return 0;
 }
 
-static int event_hist_trigger_init(struct event_trigger_ops *ops,
-				   struct event_trigger_data *data)
+static int event_hist_trigger_init(struct event_trigger_data *data)
 {
 	struct hist_trigger_data *hist_data = data->private_data;
 
@@ -5739,8 +5856,7 @@ static void unregister_field_var_hists(struct hist_trigger_data *hist_data)
 	}
 }
 
-static void event_hist_trigger_free(struct event_trigger_ops *ops,
-				    struct event_trigger_data *data)
+static void event_hist_trigger_free(struct event_trigger_data *data)
 {
 	struct hist_trigger_data *hist_data = data->private_data;
 
@@ -5769,25 +5885,23 @@ static struct event_trigger_ops event_hist_trigger_ops = {
 	.free			= event_hist_trigger_free,
 };
 
-static int event_hist_trigger_named_init(struct event_trigger_ops *ops,
-					 struct event_trigger_data *data)
+static int event_hist_trigger_named_init(struct event_trigger_data *data)
 {
 	data->ref++;
 
 	save_named_trigger(data->named_data->name, data);
 
-	event_hist_trigger_init(ops, data->named_data);
+	event_hist_trigger_init(data->named_data);
 
 	return 0;
 }
 
-static void event_hist_trigger_named_free(struct event_trigger_ops *ops,
-					  struct event_trigger_data *data)
+static void event_hist_trigger_named_free(struct event_trigger_data *data)
 {
 	if (WARN_ON_ONCE(data->ref <= 0))
 		return;
 
-	event_hist_trigger_free(ops, data->named_data);
+	event_hist_trigger_free(data->named_data);
 
 	data->ref--;
 	if (!data->ref) {
@@ -5914,6 +6028,48 @@ static bool hist_trigger_match(struct event_trigger_data *data,
 	return true;
 }
 
+static bool existing_hist_update_only(char *glob,
+				      struct event_trigger_data *data,
+				      struct trace_event_file *file)
+{
+	struct hist_trigger_data *hist_data = data->private_data;
+	struct event_trigger_data *test, *named_data = NULL;
+	bool updated = false;
+
+	if (!hist_data->attrs->pause && !hist_data->attrs->cont &&
+	    !hist_data->attrs->clear)
+		goto out;
+
+	if (hist_data->attrs->name) {
+		named_data = find_named_trigger(hist_data->attrs->name);
+		if (named_data) {
+			if (!hist_trigger_match(data, named_data, named_data,
+						true))
+				goto out;
+		}
+	}
+
+	if (hist_data->attrs->name && !named_data)
+		goto out;
+
+	list_for_each_entry(test, &file->triggers, list) {
+		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+			if (!hist_trigger_match(data, test, named_data, false))
+				continue;
+			if (hist_data->attrs->pause)
+				test->paused = true;
+			else if (hist_data->attrs->cont)
+				test->paused = false;
+			else if (hist_data->attrs->clear)
+				hist_clear(test);
+			updated = true;
+			goto out;
+		}
+	}
+ out:
+	return updated;
+}
+
 static int hist_register_trigger(char *glob,
 				 struct event_trigger_data *data,
 				 struct trace_event_file *file)
@@ -5942,19 +6098,11 @@ static int hist_register_trigger(char *glob,
 
 	list_for_each_entry(test, &file->triggers, list) {
 		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
-			if (!hist_trigger_match(data, test, named_data, false))
-				continue;
-			if (hist_data->attrs->pause)
-				test->paused = true;
-			else if (hist_data->attrs->cont)
-				test->paused = false;
-			else if (hist_data->attrs->clear)
-				hist_clear(test);
-			else {
+			if (hist_trigger_match(data, test, named_data, false)) {
 				hist_err(tr, HIST_ERR_TRIGGER_EEXIST, 0);
 				ret = -EEXIST;
+				goto out;
 			}
-			goto out;
 		}
 	}
  new:
@@ -5974,7 +6122,7 @@ static int hist_register_trigger(char *glob,
 	}
 
 	if (data->ops->init) {
-		ret = data->ops->init(data->ops, data);
+		ret = data->ops->init(data);
 		if (ret < 0)
 			goto out;
 	}
@@ -5993,8 +6141,6 @@ static int hist_register_trigger(char *glob,
 
 	if (named_data)
 		destroy_hist_data(hist_data);
-
-	ret++;
  out:
 	return ret;
 }
@@ -6070,20 +6216,19 @@ static void hist_unregister_trigger(char *glob,
 				    struct event_trigger_data *data,
 				    struct trace_event_file *file)
 {
+	struct event_trigger_data *test = NULL, *iter, *named_data = NULL;
 	struct hist_trigger_data *hist_data = data->private_data;
-	struct event_trigger_data *test, *named_data = NULL;
-	bool unregistered = false;
 
 	lockdep_assert_held(&event_mutex);
 
 	if (hist_data->attrs->name)
 		named_data = find_named_trigger(hist_data->attrs->name);
 
-	list_for_each_entry(test, &file->triggers, list) {
-		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
-			if (!hist_trigger_match(data, test, named_data, false))
+	list_for_each_entry(iter, &file->triggers, list) {
+		if (iter->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+			if (!hist_trigger_match(data, iter, named_data, false))
 				continue;
-			unregistered = true;
+			test = iter;
 			list_del_rcu(&test->list);
 			trace_event_trigger_enable_disable(file, 0);
 			update_cond_flag(file);
@@ -6091,11 +6236,11 @@ static void hist_unregister_trigger(char *glob,
 		}
 	}
 
-	if (unregistered && test->ops->free)
-		test->ops->free(test->ops, test);
+	if (test && test->ops->free)
+		test->ops->free(test);
 
 	if (hist_data->enable_timestamps) {
-		if (!hist_data->remove || unregistered)
+		if (!hist_data->remove || test)
 			tracing_set_filter_buffering(file->tr, false);
 	}
 }
@@ -6145,57 +6290,57 @@ static void hist_unreg_all(struct trace_event_file *file)
 			if (hist_data->enable_timestamps)
 				tracing_set_filter_buffering(file->tr, false);
 			if (test->ops->free)
-				test->ops->free(test->ops, test);
+				test->ops->free(test);
 		}
 	}
 }
 
 static int event_hist_trigger_parse(struct event_command *cmd_ops,
 				    struct trace_event_file *file,
-				    char *glob, char *cmd, char *param)
+				    char *glob, char *cmd,
+				    char *param_and_filter)
 {
 	unsigned int hist_trigger_bits = TRACING_MAP_BITS_DEFAULT;
 	struct event_trigger_data *trigger_data;
 	struct hist_trigger_attrs *attrs;
-	struct event_trigger_ops *trigger_ops;
 	struct hist_trigger_data *hist_data;
+	char *param, *filter, *p, *start;
 	struct synth_event *se;
 	const char *se_name;
-	bool remove = false;
-	char *trigger, *p, *start;
+	bool remove;
 	int ret = 0;
 
 	lockdep_assert_held(&event_mutex);
 
-	WARN_ON(!glob);
+	if (WARN_ON(!glob))
+		return -EINVAL;
 
-	if (strlen(glob)) {
+	if (glob[0]) {
 		hist_err_clear();
-		last_cmd_set(file, param);
+		last_cmd_set(file, param_and_filter);
 	}
 
-	if (!param)
-		return -EINVAL;
+	remove = event_trigger_check_remove(glob);
 
-	if (glob[0] == '!')
-		remove = true;
+	if (event_trigger_empty_param(param_and_filter))
+		return -EINVAL;
 
 	/*
 	 * separate the trigger from the filter (k:v [if filter])
 	 * allowing for whitespace in the trigger
 	 */
-	p = trigger = param;
+	p = param = param_and_filter;
 	do {
 		p = strstr(p, "if");
 		if (!p)
 			break;
-		if (p == param)
+		if (p == param_and_filter)
 			return -EINVAL;
 		if (*(p - 1) != ' ' && *(p - 1) != '\t') {
 			p++;
 			continue;
 		}
-		if (p >= param + strlen(param) - (sizeof("if") - 1) - 1)
+		if (p >= param_and_filter + strlen(param_and_filter) - (sizeof("if") - 1) - 1)
 			return -EINVAL;
 		if (*(p + sizeof("if") - 1) != ' ' && *(p + sizeof("if") - 1) != '\t') {
 			p++;
@@ -6205,24 +6350,24 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 	} while (1);
 
 	if (!p)
-		param = NULL;
+		filter = NULL;
 	else {
 		*(p - 1) = '\0';
-		param = strstrip(p);
-		trigger = strstrip(trigger);
+		filter = strstrip(p);
+		param = strstrip(param);
 	}
 
 	/*
 	 * To simplify arithmetic expression parsing, replace occurrences of
 	 * '.sym-offset' modifier with '.symXoffset'
 	 */
-	start = strstr(trigger, ".sym-offset");
+	start = strstr(param, ".sym-offset");
 	while (start) {
 		*(start + 4) = 'X';
 		start = strstr(start + 11, ".sym-offset");
 	}
 
-	attrs = parse_hist_trigger_attrs(file->tr, trigger);
+	attrs = parse_hist_trigger_attrs(file->tr, param);
 	if (IS_ERR(attrs))
 		return PTR_ERR(attrs);
 
@@ -6235,29 +6380,15 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 		return PTR_ERR(hist_data);
 	}
 
-	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
-
-	trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+	trigger_data = event_trigger_alloc(cmd_ops, cmd, param, hist_data);
 	if (!trigger_data) {
 		ret = -ENOMEM;
 		goto out_free;
 	}
 
-	trigger_data->count = -1;
-	trigger_data->ops = trigger_ops;
-	trigger_data->cmd_ops = cmd_ops;
-
-	INIT_LIST_HEAD(&trigger_data->list);
-	RCU_INIT_POINTER(trigger_data->filter, NULL);
-
-	trigger_data->private_data = hist_data;
-
-	/* if param is non-empty, it's supposed to be a filter */
-	if (param && cmd_ops->set_filter) {
-		ret = cmd_ops->set_filter(param, trigger_data, file);
-		if (ret < 0)
-			goto out_free;
-	}
+	ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data);
+	if (ret < 0)
+		goto out_free;
 
 	if (remove) {
 		if (!have_hist_trigger_match(trigger_data, file))
@@ -6268,7 +6399,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 			goto out_free;
 		}
 
-		cmd_ops->unreg(glob+1, trigger_data, file);
+		event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
 		se_name = trace_event_name(file->event_call);
 		se = find_synth_event(se_name);
 		if (se)
@@ -6277,17 +6408,11 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 		goto out_free;
 	}
 
-	ret = cmd_ops->reg(glob, trigger_data, file);
-	/*
-	 * The above returns on success the # of triggers registered,
-	 * but if it didn't register any it returns zero.  Consider no
-	 * triggers registered a failure too.
-	 */
-	if (!ret) {
-		if (!(attrs->pause || attrs->cont || attrs->clear))
-			ret = -ENOENT;
+	if (existing_hist_update_only(glob, trigger_data, file))
 		goto out_free;
-	} else if (ret < 0)
+
+	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+	if (ret < 0)
 		goto out_free;
 
 	if (get_named_trigger_data(trigger_data))
@@ -6312,18 +6437,15 @@ enable:
 	se = find_synth_event(se_name);
 	if (se)
 		se->ref++;
-	/* Just return zero, not the number of registered triggers */
-	ret = 0;
  out:
 	if (ret == 0)
 		hist_err_clear();
 
 	return ret;
  out_unreg:
-	cmd_ops->unreg(glob+1, trigger_data, file);
+	event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
  out_free:
-	if (cmd_ops->set_filter)
-		cmd_ops->set_filter(NULL, trigger_data, NULL);
+	event_trigger_reset_filter(cmd_ops, trigger_data);
 
 	remove_hist_vars(hist_data);
 
@@ -6444,7 +6566,7 @@ static void hist_enable_unreg_all(struct trace_event_file *file)
 			update_cond_flag(file);
 			trace_event_trigger_enable_disable(file, 0);
 			if (test->ops->free)
-				test->ops->free(test->ops, test);
+				test->ops->free(test);
 		}
 	}
 }
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 154db74dadbc..c3b582d19b62 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -17,6 +17,8 @@
 /* for gfp flag names */
 #include <linux/trace_events.h>
 #include <trace/events/mmflags.h>
+#include "trace_probe.h"
+#include "trace_probe_kernel.h"
 
 #include "trace_synth.h"
 
@@ -42,10 +44,13 @@ enum { ERRORS };
 
 static const char *err_text[] = { ERRORS };
 
-static char last_cmd[MAX_FILTER_STR_VAL];
+static char *last_cmd;
 
 static int errpos(const char *str)
 {
+	if (!str || !last_cmd)
+		return 0;
+
 	return err_pos(last_cmd, str);
 }
 
@@ -54,11 +59,16 @@ static void last_cmd_set(const char *str)
 	if (!str)
 		return;
 
-	strncpy(last_cmd, str, MAX_FILTER_STR_VAL - 1);
+	kfree(last_cmd);
+
+	last_cmd = kstrdup(str, GFP_KERNEL);
 }
 
-static void synth_err(u8 err_type, u8 err_pos)
+static void synth_err(u8 err_type, u16 err_pos)
 {
+	if (!last_cmd)
+		return;
+
 	tracing_log_err(NULL, "synthetic_events", last_cmd, err_text,
 			err_type, err_pos);
 }
@@ -401,6 +411,7 @@ static unsigned int trace_string(struct synth_trace_event *entry,
 {
 	unsigned int len = 0;
 	char *str_field;
+	int ret;
 
 	if (is_dynamic) {
 		u32 data_offset;
@@ -409,19 +420,27 @@ static unsigned int trace_string(struct synth_trace_event *entry,
 		data_offset += event->n_u64 * sizeof(u64);
 		data_offset += data_size;
 
-		str_field = (char *)entry + data_offset;
-
-		len = strlen(str_val) + 1;
-		strscpy(str_field, str_val, len);
+		len = kern_fetch_store_strlen((unsigned long)str_val);
 
 		data_offset |= len << 16;
 		*(u32 *)&entry->fields[*n_u64] = data_offset;
 
+		ret = kern_fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry);
+
 		(*n_u64)++;
 	} else {
 		str_field = (char *)&entry->fields[*n_u64];
 
-		strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+		if ((unsigned long)str_val < TASK_SIZE)
+			ret = strncpy_from_user_nofault(str_field, str_val, STR_VAR_LEN_MAX);
+		else
+#endif
+			ret = strncpy_from_kernel_nofault(str_field, str_val, STR_VAR_LEN_MAX);
+
+		if (ret < 0)
+			strcpy(str_field, FAULT_STRING);
+
 		(*n_u64) += STR_VAR_LEN_MAX / sizeof(u64);
 	}
 
@@ -454,7 +473,7 @@ static notrace void trace_event_raw_event_synth(void *__data,
 		val_idx = var_ref_idx[field_pos];
 		str_val = (char *)(long)var_ref_vals[val_idx];
 
-		len = strlen(str_val) + 1;
+		len = kern_fetch_store_strlen((unsigned long)str_val);
 
 		fields_size += len;
 	}
@@ -809,10 +828,9 @@ static int register_synth_event(struct synth_event *event)
 	}
 
 	ret = set_synth_event_print_fmt(call);
-	if (ret < 0) {
+	/* unregister_trace_event() will be called inside */
+	if (ret < 0)
 		trace_remove_event_call(call);
-		goto err;
-	}
  out:
 	return ret;
  err:
@@ -1407,7 +1425,6 @@ int synth_event_delete(const char *event_name)
 	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
@@ -1419,7 +1436,6 @@ int synth_event_delete(const char *event_name)
 		 * occur.
 		 */
 		tracing_reset_all_online_cpus();
-		mutex_unlock(&trace_types_lock);
 	}
 
 	return ret;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d00fee705f9c..918730d74932 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -84,6 +84,20 @@ event_triggers_call(struct trace_event_file *file,
 }
 EXPORT_SYMBOL_GPL(event_triggers_call);
 
+bool __trace_trigger_soft_disabled(struct trace_event_file *file)
+{
+	unsigned long eflags = file->flags;
+
+	if (eflags & EVENT_FILE_FL_TRIGGER_MODE)
+		event_triggers_call(file, NULL, NULL, NULL);
+	if (eflags & EVENT_FILE_FL_SOFT_DISABLED)
+		return true;
+	if (eflags & EVENT_FILE_FL_PID_FILTER)
+		return trace_event_ignore_this_pid(file);
+	return false;
+}
+EXPORT_SYMBOL_GPL(__trace_trigger_soft_disabled);
+
 /**
  * event_triggers_post_call - Call 'post_triggers' for a trace event
  * @file: The trace_event_file associated with the event
@@ -128,7 +142,8 @@ static bool check_user_trigger(struct trace_event_file *file)
 {
 	struct event_trigger_data *data;
 
-	list_for_each_entry_rcu(data, &file->triggers, list) {
+	list_for_each_entry_rcu(data, &file->triggers, list,
+				lockdep_is_held(&event_mutex)) {
 		if (data->flags & EVENT_TRIGGER_FL_PROBE)
 			continue;
 		return true;
@@ -174,7 +189,7 @@ static int trigger_show(struct seq_file *m, void *v)
 	}
 
 	data = list_entry(v, struct event_trigger_data, list);
-	data->ops->print(m, data->ops, data);
+	data->ops->print(m, data);
 
 	return 0;
 }
@@ -418,7 +433,6 @@ event_trigger_print(const char *name, struct seq_file *m,
 
 /**
  * event_trigger_init - Generic event_trigger_ops @init implementation
- * @ops: The trigger ops associated with the trigger
  * @data: Trigger-specific data
  *
  * Common implementation of event trigger initialization.
@@ -428,8 +442,7 @@ event_trigger_print(const char *name, struct seq_file *m,
  *
  * Return: 0 on success, errno otherwise
  */
-int event_trigger_init(struct event_trigger_ops *ops,
-		       struct event_trigger_data *data)
+int event_trigger_init(struct event_trigger_data *data)
 {
 	data->ref++;
 	return 0;
@@ -437,7 +450,6 @@ int event_trigger_init(struct event_trigger_ops *ops,
 
 /**
  * event_trigger_free - Generic event_trigger_ops @free implementation
- * @ops: The trigger ops associated with the trigger
  * @data: Trigger-specific data
  *
  * Common implementation of event trigger de-initialization.
@@ -446,8 +458,7 @@ int event_trigger_init(struct event_trigger_ops *ops,
  * implementations.
  */
 static void
-event_trigger_free(struct event_trigger_ops *ops,
-		   struct event_trigger_data *data)
+event_trigger_free(struct event_trigger_data *data)
 {
 	if (WARN_ON_ONCE(data->ref <= 0))
 		return;
@@ -501,7 +512,7 @@ clear_event_triggers(struct trace_array *tr)
 			trace_event_trigger_enable_disable(file, 0);
 			list_del_rcu(&data->list);
 			if (data->ops->free)
-				data->ops->free(data->ops, data);
+				data->ops->free(data);
 		}
 	}
 }
@@ -567,19 +578,18 @@ static int register_trigger(char *glob,
 	}
 
 	if (data->ops->init) {
-		ret = data->ops->init(data->ops, data);
+		ret = data->ops->init(data);
 		if (ret < 0)
 			goto out;
 	}
 
 	list_add_rcu(&data->list, &file->triggers);
-	ret++;
 
 	update_cond_flag(file);
-	if (trace_event_trigger_enable_disable(file, 1) < 0) {
+	ret = trace_event_trigger_enable_disable(file, 1);
+	if (ret < 0) {
 		list_del_rcu(&data->list);
 		update_cond_flag(file);
-		ret--;
 	}
 out:
 	return ret;
@@ -600,14 +610,13 @@ static void unregister_trigger(char *glob,
 			       struct event_trigger_data *test,
 			       struct trace_event_file *file)
 {
-	struct event_trigger_data *data;
-	bool unregistered = false;
+	struct event_trigger_data *data = NULL, *iter;
 
 	lockdep_assert_held(&event_mutex);
 
-	list_for_each_entry(data, &file->triggers, list) {
-		if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
-			unregistered = true;
+	list_for_each_entry(iter, &file->triggers, list) {
+		if (iter->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
+			data = iter;
 			list_del_rcu(&data->list);
 			trace_event_trigger_enable_disable(file, 0);
 			update_cond_flag(file);
@@ -615,8 +624,8 @@ static void unregister_trigger(char *glob,
 		}
 	}
 
-	if (unregistered && data->ops->free)
-		data->ops->free(data->ops, data);
+	if (data && data->ops->free)
+		data->ops->free(data);
 }
 
 /*
@@ -730,15 +739,15 @@ bool event_trigger_empty_param(const char *param)
 
 /**
  * event_trigger_separate_filter - separate an event trigger from a filter
- * @param: The param string containing trigger and possibly filter
- * @trigger: outparam, will be filled with a pointer to the trigger
+ * @param_and_filter: String containing trigger and possibly filter
+ * @param: outparam, will be filled with a pointer to the trigger
  * @filter: outparam, will be filled with a pointer to the filter
  * @param_required: Specifies whether or not the param string is required
  *
  * Given a param string of the form '[trigger] [if filter]', this
  * function separates the filter from the trigger and returns the
- * trigger in *trigger and the filter in *filter.  Either the *trigger
- * or the *filter may be set to NULL by this function - if not set to
+ * trigger in @param and the filter in @filter.  Either the @param
+ * or the @filter may be set to NULL by this function - if not set to
  * NULL, they will contain strings corresponding to the trigger and
  * filter.
  *
@@ -913,48 +922,37 @@ void event_trigger_reset_filter(struct event_command *cmd_ops,
  * @cmd_ops: The event_command operations for the trigger
  * @file: The event file for the trigger's event
  * @glob: The trigger command string, with optional remove(!) operator
- * @cmd: The cmd string
- * @param: The param string
  * @trigger_data: The trigger_data for the trigger
- * @n_registered: optional outparam, the number of triggers registered
  *
  * Register an event trigger.  The @cmd_ops are used to call the
- * cmd_ops->reg() function which actually does the registration. The
- * cmd_ops->reg() function returns the number of triggers registered,
- * which is assigned to n_registered, if n_registered is non-NULL.
+ * cmd_ops->reg() function which actually does the registration.
  *
  * Return: 0 on success, errno otherwise
  */
 int event_trigger_register(struct event_command *cmd_ops,
 			   struct trace_event_file *file,
 			   char *glob,
-			   char *cmd,
-			   char *param,
-			   struct event_trigger_data *trigger_data,
-			   int *n_registered)
+			   struct event_trigger_data *trigger_data)
 {
-	int ret;
-
-	if (n_registered)
-		*n_registered = 0;
-
-	ret = cmd_ops->reg(glob, trigger_data, file);
-	/*
-	 * The above returns on success the # of functions enabled,
-	 * but if it didn't find any functions it returns zero.
-	 * Consider no functions a failure too.
-	 */
-	if (!ret) {
-		cmd_ops->unreg(glob, trigger_data, file);
-		ret = -ENOENT;
-	} else if (ret > 0) {
-		if (n_registered)
-			*n_registered = ret;
-		/* Just return zero, not the number of enabled functions */
-		ret = 0;
-	}
+	return cmd_ops->reg(glob, trigger_data, file);
+}
 
-	return ret;
+/**
+ * event_trigger_unregister - unregister an event trigger
+ * @cmd_ops: The event_command operations for the trigger
+ * @file: The event file for the trigger's event
+ * @glob: The trigger command string, with optional remove(!) operator
+ * @trigger_data: The trigger_data for the trigger
+ *
+ * Unregister an event trigger.  The @cmd_ops are used to call the
+ * cmd_ops->unreg() function which actually does the unregistration.
+ */
+void event_trigger_unregister(struct event_command *cmd_ops,
+			      struct trace_event_file *file,
+			      char *glob,
+			      struct event_trigger_data *trigger_data)
+{
+	cmd_ops->unreg(glob, trigger_data, file);
 }
 
 /*
@@ -967,7 +965,7 @@ int event_trigger_register(struct event_command *cmd_ops,
  * @file: The trace_event_file associated with the event
  * @glob: The raw string used to register the trigger
  * @cmd: The cmd portion of the string used to register the trigger
- * @param: The params portion of the string used to register the trigger
+ * @param_and_filter: The param and filter portion of the string used to register the trigger
  *
  * Common implementation for event command parsing and trigger
  * instantiation.
@@ -980,94 +978,53 @@ int event_trigger_register(struct event_command *cmd_ops,
 static int
 event_trigger_parse(struct event_command *cmd_ops,
 		    struct trace_event_file *file,
-		    char *glob, char *cmd, char *param)
+		    char *glob, char *cmd, char *param_and_filter)
 {
 	struct event_trigger_data *trigger_data;
-	struct event_trigger_ops *trigger_ops;
-	char *trigger = NULL;
-	char *number;
+	char *param, *filter;
+	bool remove;
 	int ret;
 
-	/* separate the trigger from the filter (t:n [if filter]) */
-	if (param && isdigit(param[0])) {
-		trigger = strsep(&param, " \t");
-		if (param) {
-			param = skip_spaces(param);
-			if (!*param)
-				param = NULL;
-		}
-	}
+	remove = event_trigger_check_remove(glob);
 
-	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+	ret = event_trigger_separate_filter(param_and_filter, &param, &filter, false);
+	if (ret)
+		return ret;
 
 	ret = -ENOMEM;
-	trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+	trigger_data = event_trigger_alloc(cmd_ops, cmd, param, file);
 	if (!trigger_data)
 		goto out;
 
-	trigger_data->count = -1;
-	trigger_data->ops = trigger_ops;
-	trigger_data->cmd_ops = cmd_ops;
-	trigger_data->private_data = file;
-	INIT_LIST_HEAD(&trigger_data->list);
-	INIT_LIST_HEAD(&trigger_data->named_list);
-
-	if (glob[0] == '!') {
-		cmd_ops->unreg(glob+1, trigger_data, file);
+	if (remove) {
+		event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
 		kfree(trigger_data);
 		ret = 0;
 		goto out;
 	}
 
-	if (trigger) {
-		number = strsep(&trigger, ":");
-
-		ret = -EINVAL;
-		if (!strlen(number))
-			goto out_free;
-
-		/*
-		 * We use the callback data field (which is a pointer)
-		 * as our counter.
-		 */
-		ret = kstrtoul(number, 0, &trigger_data->count);
-		if (ret)
-			goto out_free;
-	}
-
-	if (!param) /* if param is non-empty, it's supposed to be a filter */
-		goto out_reg;
-
-	if (!cmd_ops->set_filter)
-		goto out_reg;
+	ret = event_trigger_parse_num(param, trigger_data);
+	if (ret)
+		goto out_free;
 
-	ret = cmd_ops->set_filter(param, trigger_data, file);
+	ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data);
 	if (ret < 0)
 		goto out_free;
 
- out_reg:
 	/* Up the trigger_data count to make sure reg doesn't free it on failure */
-	event_trigger_init(trigger_ops, trigger_data);
-	ret = cmd_ops->reg(glob, trigger_data, file);
-	/*
-	 * The above returns on success the # of functions enabled,
-	 * but if it didn't find any functions it returns zero.
-	 * Consider no functions a failure too.
-	 */
-	if (!ret) {
-		cmd_ops->unreg(glob, trigger_data, file);
-		ret = -ENOENT;
-	} else if (ret > 0)
-		ret = 0;
+	event_trigger_init(trigger_data);
+
+	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+	if (ret)
+		goto out_free;
 
 	/* Down the counter of trigger_data or free it if not used anymore */
-	event_trigger_free(trigger_ops, trigger_data);
+	event_trigger_free(trigger_data);
  out:
 	return ret;
 
  out_free:
-	if (cmd_ops->set_filter)
-		cmd_ops->set_filter(NULL, trigger_data, NULL);
+	event_trigger_reset_filter(cmd_ops, trigger_data);
 	kfree(trigger_data);
 	goto out;
 }
@@ -1295,6 +1252,16 @@ traceon_trigger(struct event_trigger_data *data,
 		struct trace_buffer *buffer, void *rec,
 		struct ring_buffer_event *event)
 {
+	struct trace_event_file *file = data->private_data;
+
+	if (file) {
+		if (tracer_tracing_is_on(file->tr))
+			return;
+
+		tracer_tracing_on(file->tr);
+		return;
+	}
+
 	if (tracing_is_on())
 		return;
 
@@ -1306,8 +1273,15 @@ traceon_count_trigger(struct event_trigger_data *data,
 		      struct trace_buffer *buffer, void *rec,
 		      struct ring_buffer_event *event)
 {
-	if (tracing_is_on())
-		return;
+	struct trace_event_file *file = data->private_data;
+
+	if (file) {
+		if (tracer_tracing_is_on(file->tr))
+			return;
+	} else {
+		if (tracing_is_on())
+			return;
+	}
 
 	if (!data->count)
 		return;
@@ -1315,7 +1289,10 @@ traceon_count_trigger(struct event_trigger_data *data,
 	if (data->count != -1)
 		(data->count)--;
 
-	tracing_on();
+	if (file)
+		tracer_tracing_on(file->tr);
+	else
+		tracing_on();
 }
 
 static void
@@ -1323,6 +1300,16 @@ traceoff_trigger(struct event_trigger_data *data,
 		 struct trace_buffer *buffer, void *rec,
 		 struct ring_buffer_event *event)
 {
+	struct trace_event_file *file = data->private_data;
+
+	if (file) {
+		if (!tracer_tracing_is_on(file->tr))
+			return;
+
+		tracer_tracing_off(file->tr);
+		return;
+	}
+
 	if (!tracing_is_on())
 		return;
 
@@ -1334,8 +1321,15 @@ traceoff_count_trigger(struct event_trigger_data *data,
 		       struct trace_buffer *buffer, void *rec,
 		       struct ring_buffer_event *event)
 {
-	if (!tracing_is_on())
-		return;
+	struct trace_event_file *file = data->private_data;
+
+	if (file) {
+		if (!tracer_tracing_is_on(file->tr))
+			return;
+	} else {
+		if (!tracing_is_on())
+			return;
+	}
 
 	if (!data->count)
 		return;
@@ -1343,20 +1337,21 @@ traceoff_count_trigger(struct event_trigger_data *data,
 	if (data->count != -1)
 		(data->count)--;
 
-	tracing_off();
+	if (file)
+		tracer_tracing_off(file->tr);
+	else
+		tracing_off();
 }
 
 static int
-traceon_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
-		      struct event_trigger_data *data)
+traceon_trigger_print(struct seq_file *m, struct event_trigger_data *data)
 {
 	return event_trigger_print("traceon", m, (void *)data->count,
 				   data->filter_str);
 }
 
 static int
-traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
-		       struct event_trigger_data *data)
+traceoff_trigger_print(struct seq_file *m, struct event_trigger_data *data)
 {
 	return event_trigger_print("traceoff", m, (void *)data->count,
 				   data->filter_str);
@@ -1467,8 +1462,7 @@ register_snapshot_trigger(char *glob,
 }
 
 static int
-snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
-		       struct event_trigger_data *data)
+snapshot_trigger_print(struct seq_file *m, struct event_trigger_data *data)
 {
 	return event_trigger_print("snapshot", m, (void *)data->count,
 				   data->filter_str);
@@ -1540,7 +1534,12 @@ stacktrace_trigger(struct event_trigger_data *data,
 		   struct trace_buffer *buffer,  void *rec,
 		   struct ring_buffer_event *event)
 {
-	trace_dump_stack(STACK_SKIP);
+	struct trace_event_file *file = data->private_data;
+
+	if (file)
+		__trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP);
+	else
+		trace_dump_stack(STACK_SKIP);
 }
 
 static void
@@ -1558,8 +1557,7 @@ stacktrace_count_trigger(struct event_trigger_data *data,
 }
 
 static int
-stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
-			 struct event_trigger_data *data)
+stacktrace_trigger_print(struct seq_file *m, struct event_trigger_data *data)
 {
 	return event_trigger_print("stacktrace", m, (void *)data->count,
 				   data->filter_str);
@@ -1649,7 +1647,6 @@ event_enable_count_trigger(struct event_trigger_data *data,
 }
 
 int event_enable_trigger_print(struct seq_file *m,
-			       struct event_trigger_ops *ops,
 			       struct event_trigger_data *data)
 {
 	struct enable_trigger_data *enable_data = data->private_data;
@@ -1674,8 +1671,7 @@ int event_enable_trigger_print(struct seq_file *m,
 	return 0;
 }
 
-void event_enable_trigger_free(struct event_trigger_ops *ops,
-			       struct event_trigger_data *data)
+void event_enable_trigger_free(struct event_trigger_data *data)
 {
 	struct enable_trigger_data *enable_data = data->private_data;
 
@@ -1722,39 +1718,33 @@ static struct event_trigger_ops event_disable_count_trigger_ops = {
 
 int event_enable_trigger_parse(struct event_command *cmd_ops,
 			       struct trace_event_file *file,
-			       char *glob, char *cmd, char *param)
+			       char *glob, char *cmd, char *param_and_filter)
 {
 	struct trace_event_file *event_enable_file;
 	struct enable_trigger_data *enable_data;
 	struct event_trigger_data *trigger_data;
-	struct event_trigger_ops *trigger_ops;
 	struct trace_array *tr = file->tr;
+	char *param, *filter;
+	bool enable, remove;
 	const char *system;
 	const char *event;
 	bool hist = false;
-	char *trigger;
-	char *number;
-	bool enable;
 	int ret;
 
-	if (!param)
-		return -EINVAL;
+	remove = event_trigger_check_remove(glob);
 
-	/* separate the trigger from the filter (s:e:n [if filter]) */
-	trigger = strsep(&param, " \t");
-	if (!trigger)
+	if (event_trigger_empty_param(param_and_filter))
 		return -EINVAL;
-	if (param) {
-		param = skip_spaces(param);
-		if (!*param)
-			param = NULL;
-	}
 
-	system = strsep(&trigger, ":");
-	if (!trigger)
+	ret = event_trigger_separate_filter(param_and_filter, &param, &filter, true);
+	if (ret)
+		return ret;
+
+	system = strsep(&param, ":");
+	if (!param)
 		return -EINVAL;
 
-	event = strsep(&trigger, ":");
+	event = strsep(&param, ":");
 
 	ret = -EINVAL;
 	event_enable_file = find_event_file(tr, system, event);
@@ -1770,32 +1760,24 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 #else
 	enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
 #endif
-	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
-
 	ret = -ENOMEM;
-	trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
-	if (!trigger_data)
-		goto out;
 
 	enable_data = kzalloc(sizeof(*enable_data), GFP_KERNEL);
-	if (!enable_data) {
-		kfree(trigger_data);
+	if (!enable_data)
 		goto out;
-	}
-
-	trigger_data->count = -1;
-	trigger_data->ops = trigger_ops;
-	trigger_data->cmd_ops = cmd_ops;
-	INIT_LIST_HEAD(&trigger_data->list);
-	RCU_INIT_POINTER(trigger_data->filter, NULL);
 
 	enable_data->hist = hist;
 	enable_data->enable = enable;
 	enable_data->file = event_enable_file;
-	trigger_data->private_data = enable_data;
 
-	if (glob[0] == '!') {
-		cmd_ops->unreg(glob+1, trigger_data, file);
+	trigger_data = event_trigger_alloc(cmd_ops, cmd, param, enable_data);
+	if (!trigger_data) {
+		kfree(enable_data);
+		goto out;
+	}
+
+	if (remove) {
+		event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
 		kfree(trigger_data);
 		kfree(enable_data);
 		ret = 0;
@@ -1803,35 +1785,16 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	}
 
 	/* Up the trigger_data count to make sure nothing frees it on failure */
-	event_trigger_init(trigger_ops, trigger_data);
-
-	if (trigger) {
-		number = strsep(&trigger, ":");
-
-		ret = -EINVAL;
-		if (!strlen(number))
-			goto out_free;
-
-		/*
-		 * We use the callback data field (which is a pointer)
-		 * as our counter.
-		 */
-		ret = kstrtoul(number, 0, &trigger_data->count);
-		if (ret)
-			goto out_free;
-	}
+	event_trigger_init(trigger_data);
 
-	if (!param) /* if param is non-empty, it's supposed to be a filter */
-		goto out_reg;
-
-	if (!cmd_ops->set_filter)
-		goto out_reg;
+	ret = event_trigger_parse_num(param, trigger_data);
+	if (ret)
+		goto out_free;
 
-	ret = cmd_ops->set_filter(param, trigger_data, file);
+	ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data);
 	if (ret < 0)
 		goto out_free;
 
- out_reg:
 	/* Don't let event modules unload while probe registered */
 	ret = trace_event_try_get_ref(event_enable_file->event_call);
 	if (!ret) {
@@ -1842,32 +1805,23 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	ret = trace_event_enable_disable(event_enable_file, 1, 1);
 	if (ret < 0)
 		goto out_put;
-	ret = cmd_ops->reg(glob, trigger_data, file);
-	/*
-	 * The above returns on success the # of functions enabled,
-	 * but if it didn't find any functions it returns zero.
-	 * Consider no functions a failure too.
-	 */
-	if (!ret) {
-		ret = -ENOENT;
-		goto out_disable;
-	} else if (ret < 0)
+
+	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+	if (ret)
 		goto out_disable;
-	/* Just return zero, not the number of enabled functions */
-	ret = 0;
-	event_trigger_free(trigger_ops, trigger_data);
+
+	event_trigger_free(trigger_data);
  out:
 	return ret;
-
  out_disable:
 	trace_event_enable_disable(event_enable_file, 0, 1);
  out_put:
 	trace_event_put_ref(event_enable_file->event_call);
  out_free:
-	if (cmd_ops->set_filter)
-		cmd_ops->set_filter(NULL, trigger_data, NULL);
-	event_trigger_free(trigger_ops, trigger_data);
+	event_trigger_reset_filter(cmd_ops, trigger_data);
+	event_trigger_free(trigger_data);
 	kfree(enable_data);
+
 	goto out;
 }
 
@@ -1894,19 +1848,18 @@ int event_enable_register_trigger(char *glob,
 	}
 
 	if (data->ops->init) {
-		ret = data->ops->init(data->ops, data);
+		ret = data->ops->init(data);
 		if (ret < 0)
 			goto out;
 	}
 
 	list_add_rcu(&data->list, &file->triggers);
-	ret++;
 
 	update_cond_flag(file);
-	if (trace_event_trigger_enable_disable(file, 1) < 0) {
+	ret = trace_event_trigger_enable_disable(file, 1);
+	if (ret < 0) {
 		list_del_rcu(&data->list);
 		update_cond_flag(file);
-		ret--;
 	}
 out:
 	return ret;
@@ -1917,19 +1870,18 @@ void event_enable_unregister_trigger(char *glob,
 				     struct trace_event_file *file)
 {
 	struct enable_trigger_data *test_enable_data = test->private_data;
+	struct event_trigger_data *data = NULL, *iter;
 	struct enable_trigger_data *enable_data;
-	struct event_trigger_data *data;
-	bool unregistered = false;
 
 	lockdep_assert_held(&event_mutex);
 
-	list_for_each_entry(data, &file->triggers, list) {
-		enable_data = data->private_data;
+	list_for_each_entry(iter, &file->triggers, list) {
+		enable_data = iter->private_data;
 		if (enable_data &&
-		    (data->cmd_ops->trigger_type ==
+		    (iter->cmd_ops->trigger_type ==
 		     test->cmd_ops->trigger_type) &&
 		    (enable_data->file == test_enable_data->file)) {
-			unregistered = true;
+			data = iter;
 			list_del_rcu(&data->list);
 			trace_event_trigger_enable_disable(file, 0);
 			update_cond_flag(file);
@@ -1937,8 +1889,8 @@ void event_enable_unregister_trigger(char *glob,
 		}
 	}
 
-	if (unregistered && data->ops->free)
-		data->ops->free(data->ops, data);
+	if (data && data->ops->free)
+		data->ops->free(data);
 }
 
 static struct event_trigger_ops *
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
new file mode 100644
index 000000000000..539b08ae7020
--- /dev/null
+++ b/kernel/trace/trace_events_user.c
@@ -0,0 +1,1914 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, Microsoft Corporation.
+ *
+ * Authors:
+ *   Beau Belgrave <beaub@linux.microsoft.com>
+ */
+
+#include <linux/bitmap.h>
+#include <linux/cdev.h>
+#include <linux/hashtable.h>
+#include <linux/list.h>
+#include <linux/io.h>
+#include <linux/uio.h>
+#include <linux/ioctl.h>
+#include <linux/jhash.h>
+#include <linux/refcount.h>
+#include <linux/trace_events.h>
+#include <linux/tracefs.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+/* Reminder to move to uapi when everything works */
+#ifdef CONFIG_COMPILE_TEST
+#include <linux/user_events.h>
+#else
+#include <uapi/linux/user_events.h>
+#endif
+#include "trace.h"
+#include "trace_dynevent.h"
+
+#define USER_EVENTS_PREFIX_LEN (sizeof(USER_EVENTS_PREFIX)-1)
+
+#define FIELD_DEPTH_TYPE 0
+#define FIELD_DEPTH_NAME 1
+#define FIELD_DEPTH_SIZE 2
+
+/*
+ * Limits how many trace_event calls user processes can create:
+ * Must be a power of two of PAGE_SIZE.
+ */
+#define MAX_PAGE_ORDER 0
+#define MAX_PAGES (1 << MAX_PAGE_ORDER)
+#define MAX_BYTES (MAX_PAGES * PAGE_SIZE)
+#define MAX_EVENTS (MAX_BYTES * 8)
+
+/* Limit how long of an event name plus args within the subsystem. */
+#define MAX_EVENT_DESC 512
+#define EVENT_NAME(user_event) ((user_event)->tracepoint.name)
+#define MAX_FIELD_ARRAY_SIZE 1024
+
+/*
+ * The MAP_STATUS_* macros are used for taking a index and determining the
+ * appropriate byte and the bit in the byte to set/reset for an event.
+ *
+ * The lower 3 bits of the index decide which bit to set.
+ * The remaining upper bits of the index decide which byte to use for the bit.
+ *
+ * This is used when an event has a probe attached/removed to reflect live
+ * status of the event wanting tracing or not to user-programs via shared
+ * memory maps.
+ */
+#define MAP_STATUS_BYTE(index) ((index) >> 3)
+#define MAP_STATUS_MASK(index) BIT((index) & 7)
+
+/*
+ * Internal bits (kernel side only) to keep track of connected probes:
+ * These are used when status is requested in text form about an event. These
+ * bits are compared against an internal byte on the event to determine which
+ * probes to print out to the user.
+ *
+ * These do not reflect the mapped bytes between the user and kernel space.
+ */
+#define EVENT_STATUS_FTRACE BIT(0)
+#define EVENT_STATUS_PERF BIT(1)
+#define EVENT_STATUS_OTHER BIT(7)
+
+/*
+ * Stores the pages, tables, and locks for a group of events.
+ * Each logical grouping of events has its own group, with a
+ * matching page for status checks within user programs. This
+ * allows for isolation of events to user programs by various
+ * means.
+ */
+struct user_event_group {
+	struct page *pages;
+	char *register_page_data;
+	char *system_name;
+	struct hlist_node node;
+	struct mutex reg_mutex;
+	DECLARE_HASHTABLE(register_table, 8);
+	DECLARE_BITMAP(page_bitmap, MAX_EVENTS);
+};
+
+/* Group for init_user_ns mapping, top-most group */
+static struct user_event_group *init_group;
+
+/*
+ * Stores per-event properties, as users register events
+ * within a file a user_event might be created if it does not
+ * already exist. These are globally used and their lifetime
+ * is tied to the refcnt member. These cannot go away until the
+ * refcnt reaches one.
+ */
+struct user_event {
+	struct user_event_group *group;
+	struct tracepoint tracepoint;
+	struct trace_event_call call;
+	struct trace_event_class class;
+	struct dyn_event devent;
+	struct hlist_node node;
+	struct list_head fields;
+	struct list_head validators;
+	refcount_t refcnt;
+	int index;
+	int flags;
+	int min_size;
+	char status;
+};
+
+/*
+ * Stores per-file events references, as users register events
+ * within a file this structure is modified and freed via RCU.
+ * The lifetime of this struct is tied to the lifetime of the file.
+ * These are not shared and only accessible by the file that created it.
+ */
+struct user_event_refs {
+	struct rcu_head rcu;
+	int count;
+	struct user_event *events[];
+};
+
+struct user_event_file_info {
+	struct user_event_group *group;
+	struct user_event_refs *refs;
+};
+
+#define VALIDATOR_ENSURE_NULL (1 << 0)
+#define VALIDATOR_REL (1 << 1)
+
+struct user_event_validator {
+	struct list_head link;
+	int offset;
+	int flags;
+};
+
+typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i,
+				   void *tpdata, bool *faulted);
+
+static int user_event_parse(struct user_event_group *group, char *name,
+			    char *args, char *flags,
+			    struct user_event **newuser);
+
+static u32 user_event_key(char *name)
+{
+	return jhash(name, strlen(name), 0);
+}
+
+static void set_page_reservations(char *pages, bool set)
+{
+	int page;
+
+	for (page = 0; page < MAX_PAGES; ++page) {
+		void *addr = pages + (PAGE_SIZE * page);
+
+		if (set)
+			SetPageReserved(virt_to_page(addr));
+		else
+			ClearPageReserved(virt_to_page(addr));
+	}
+}
+
+static void user_event_group_destroy(struct user_event_group *group)
+{
+	if (group->register_page_data)
+		set_page_reservations(group->register_page_data, false);
+
+	if (group->pages)
+		__free_pages(group->pages, MAX_PAGE_ORDER);
+
+	kfree(group->system_name);
+	kfree(group);
+}
+
+static char *user_event_group_system_name(struct user_namespace *user_ns)
+{
+	char *system_name;
+	int len = sizeof(USER_EVENTS_SYSTEM) + 1;
+
+	if (user_ns != &init_user_ns) {
+		/*
+		 * Unexpected at this point:
+		 * We only currently support init_user_ns.
+		 * When we enable more, this will trigger a failure so log.
+		 */
+		pr_warn("user_events: Namespace other than init_user_ns!\n");
+		return NULL;
+	}
+
+	system_name = kmalloc(len, GFP_KERNEL);
+
+	if (!system_name)
+		return NULL;
+
+	snprintf(system_name, len, "%s", USER_EVENTS_SYSTEM);
+
+	return system_name;
+}
+
+static inline struct user_event_group
+*user_event_group_from_user_ns(struct user_namespace *user_ns)
+{
+	if (user_ns == &init_user_ns)
+		return init_group;
+
+	return NULL;
+}
+
+static struct user_event_group *current_user_event_group(void)
+{
+	struct user_namespace *user_ns = current_user_ns();
+	struct user_event_group *group = NULL;
+
+	while (user_ns) {
+		group = user_event_group_from_user_ns(user_ns);
+
+		if (group)
+			break;
+
+		user_ns = user_ns->parent;
+	}
+
+	return group;
+}
+
+static struct user_event_group
+*user_event_group_create(struct user_namespace *user_ns)
+{
+	struct user_event_group *group;
+
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
+
+	if (!group)
+		return NULL;
+
+	group->system_name = user_event_group_system_name(user_ns);
+
+	if (!group->system_name)
+		goto error;
+
+	group->pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, MAX_PAGE_ORDER);
+
+	if (!group->pages)
+		goto error;
+
+	group->register_page_data = page_address(group->pages);
+
+	set_page_reservations(group->register_page_data, true);
+
+	/* Zero all bits beside 0 (which is reserved for failures) */
+	bitmap_zero(group->page_bitmap, MAX_EVENTS);
+	set_bit(0, group->page_bitmap);
+
+	mutex_init(&group->reg_mutex);
+	hash_init(group->register_table);
+
+	return group;
+error:
+	if (group)
+		user_event_group_destroy(group);
+
+	return NULL;
+};
+
+static __always_inline
+void user_event_register_set(struct user_event *user)
+{
+	int i = user->index;
+
+	user->group->register_page_data[MAP_STATUS_BYTE(i)] |= MAP_STATUS_MASK(i);
+}
+
+static __always_inline
+void user_event_register_clear(struct user_event *user)
+{
+	int i = user->index;
+
+	user->group->register_page_data[MAP_STATUS_BYTE(i)] &= ~MAP_STATUS_MASK(i);
+}
+
+static __always_inline __must_check
+bool user_event_last_ref(struct user_event *user)
+{
+	return refcount_read(&user->refcnt) == 1;
+}
+
+static __always_inline __must_check
+size_t copy_nofault(void *addr, size_t bytes, struct iov_iter *i)
+{
+	size_t ret;
+
+	pagefault_disable();
+
+	ret = copy_from_iter_nocache(addr, bytes, i);
+
+	pagefault_enable();
+
+	return ret;
+}
+
+static struct list_head *user_event_get_fields(struct trace_event_call *call)
+{
+	struct user_event *user = (struct user_event *)call->data;
+
+	return &user->fields;
+}
+
+/*
+ * Parses a register command for user_events
+ * Format: event_name[:FLAG1[,FLAG2...]] [field1[;field2...]]
+ *
+ * Example event named 'test' with a 20 char 'msg' field with an unsigned int
+ * 'id' field after:
+ * test char[20] msg;unsigned int id
+ *
+ * NOTE: Offsets are from the user data perspective, they are not from the
+ * trace_entry/buffer perspective. We automatically add the common properties
+ * sizes to the offset for the user.
+ *
+ * Upon success user_event has its ref count increased by 1.
+ */
+static int user_event_parse_cmd(struct user_event_group *group,
+				char *raw_command, struct user_event **newuser)
+{
+	char *name = raw_command;
+	char *args = strpbrk(name, " ");
+	char *flags;
+
+	if (args)
+		*args++ = '\0';
+
+	flags = strpbrk(name, ":");
+
+	if (flags)
+		*flags++ = '\0';
+
+	return user_event_parse(group, name, args, flags, newuser);
+}
+
+static int user_field_array_size(const char *type)
+{
+	const char *start = strchr(type, '[');
+	char val[8];
+	char *bracket;
+	int size = 0;
+
+	if (start == NULL)
+		return -EINVAL;
+
+	if (strscpy(val, start + 1, sizeof(val)) <= 0)
+		return -EINVAL;
+
+	bracket = strchr(val, ']');
+
+	if (!bracket)
+		return -EINVAL;
+
+	*bracket = '\0';
+
+	if (kstrtouint(val, 0, &size))
+		return -EINVAL;
+
+	if (size > MAX_FIELD_ARRAY_SIZE)
+		return -EINVAL;
+
+	return size;
+}
+
+static int user_field_size(const char *type)
+{
+	/* long is not allowed from a user, since it's ambigious in size */
+	if (strcmp(type, "s64") == 0)
+		return sizeof(s64);
+	if (strcmp(type, "u64") == 0)
+		return sizeof(u64);
+	if (strcmp(type, "s32") == 0)
+		return sizeof(s32);
+	if (strcmp(type, "u32") == 0)
+		return sizeof(u32);
+	if (strcmp(type, "int") == 0)
+		return sizeof(int);
+	if (strcmp(type, "unsigned int") == 0)
+		return sizeof(unsigned int);
+	if (strcmp(type, "s16") == 0)
+		return sizeof(s16);
+	if (strcmp(type, "u16") == 0)
+		return sizeof(u16);
+	if (strcmp(type, "short") == 0)
+		return sizeof(short);
+	if (strcmp(type, "unsigned short") == 0)
+		return sizeof(unsigned short);
+	if (strcmp(type, "s8") == 0)
+		return sizeof(s8);
+	if (strcmp(type, "u8") == 0)
+		return sizeof(u8);
+	if (strcmp(type, "char") == 0)
+		return sizeof(char);
+	if (strcmp(type, "unsigned char") == 0)
+		return sizeof(unsigned char);
+	if (str_has_prefix(type, "char["))
+		return user_field_array_size(type);
+	if (str_has_prefix(type, "unsigned char["))
+		return user_field_array_size(type);
+	if (str_has_prefix(type, "__data_loc "))
+		return sizeof(u32);
+	if (str_has_prefix(type, "__rel_loc "))
+		return sizeof(u32);
+
+	/* Uknown basic type, error */
+	return -EINVAL;
+}
+
+static void user_event_destroy_validators(struct user_event *user)
+{
+	struct user_event_validator *validator, *next;
+	struct list_head *head = &user->validators;
+
+	list_for_each_entry_safe(validator, next, head, link) {
+		list_del(&validator->link);
+		kfree(validator);
+	}
+}
+
+static void user_event_destroy_fields(struct user_event *user)
+{
+	struct ftrace_event_field *field, *next;
+	struct list_head *head = &user->fields;
+
+	list_for_each_entry_safe(field, next, head, link) {
+		list_del(&field->link);
+		kfree(field);
+	}
+}
+
+static int user_event_add_field(struct user_event *user, const char *type,
+				const char *name, int offset, int size,
+				int is_signed, int filter_type)
+{
+	struct user_event_validator *validator;
+	struct ftrace_event_field *field;
+	int validator_flags = 0;
+
+	field = kmalloc(sizeof(*field), GFP_KERNEL);
+
+	if (!field)
+		return -ENOMEM;
+
+	if (str_has_prefix(type, "__data_loc "))
+		goto add_validator;
+
+	if (str_has_prefix(type, "__rel_loc ")) {
+		validator_flags |= VALIDATOR_REL;
+		goto add_validator;
+	}
+
+	goto add_field;
+
+add_validator:
+	if (strstr(type, "char") != NULL)
+		validator_flags |= VALIDATOR_ENSURE_NULL;
+
+	validator = kmalloc(sizeof(*validator), GFP_KERNEL);
+
+	if (!validator) {
+		kfree(field);
+		return -ENOMEM;
+	}
+
+	validator->flags = validator_flags;
+	validator->offset = offset;
+
+	/* Want sequential access when validating */
+	list_add_tail(&validator->link, &user->validators);
+
+add_field:
+	field->type = type;
+	field->name = name;
+	field->offset = offset;
+	field->size = size;
+	field->is_signed = is_signed;
+	field->filter_type = filter_type;
+
+	list_add(&field->link, &user->fields);
+
+	/*
+	 * Min size from user writes that are required, this does not include
+	 * the size of trace_entry (common fields).
+	 */
+	user->min_size = (offset + size) - sizeof(struct trace_entry);
+
+	return 0;
+}
+
+/*
+ * Parses the values of a field within the description
+ * Format: type name [size]
+ */
+static int user_event_parse_field(char *field, struct user_event *user,
+				  u32 *offset)
+{
+	char *part, *type, *name;
+	u32 depth = 0, saved_offset = *offset;
+	int len, size = -EINVAL;
+	bool is_struct = false;
+
+	field = skip_spaces(field);
+
+	if (*field == '\0')
+		return 0;
+
+	/* Handle types that have a space within */
+	len = str_has_prefix(field, "unsigned ");
+	if (len)
+		goto skip_next;
+
+	len = str_has_prefix(field, "struct ");
+	if (len) {
+		is_struct = true;
+		goto skip_next;
+	}
+
+	len = str_has_prefix(field, "__data_loc unsigned ");
+	if (len)
+		goto skip_next;
+
+	len = str_has_prefix(field, "__data_loc ");
+	if (len)
+		goto skip_next;
+
+	len = str_has_prefix(field, "__rel_loc unsigned ");
+	if (len)
+		goto skip_next;
+
+	len = str_has_prefix(field, "__rel_loc ");
+	if (len)
+		goto skip_next;
+
+	goto parse;
+skip_next:
+	type = field;
+	field = strpbrk(field + len, " ");
+
+	if (field == NULL)
+		return -EINVAL;
+
+	*field++ = '\0';
+	depth++;
+parse:
+	name = NULL;
+
+	while ((part = strsep(&field, " ")) != NULL) {
+		switch (depth++) {
+		case FIELD_DEPTH_TYPE:
+			type = part;
+			break;
+		case FIELD_DEPTH_NAME:
+			name = part;
+			break;
+		case FIELD_DEPTH_SIZE:
+			if (!is_struct)
+				return -EINVAL;
+
+			if (kstrtou32(part, 10, &size))
+				return -EINVAL;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (depth < FIELD_DEPTH_SIZE || !name)
+		return -EINVAL;
+
+	if (depth == FIELD_DEPTH_SIZE)
+		size = user_field_size(type);
+
+	if (size == 0)
+		return -EINVAL;
+
+	if (size < 0)
+		return size;
+
+	*offset = saved_offset + size;
+
+	return user_event_add_field(user, type, name, saved_offset, size,
+				    type[0] != 'u', FILTER_OTHER);
+}
+
+static int user_event_parse_fields(struct user_event *user, char *args)
+{
+	char *field;
+	u32 offset = sizeof(struct trace_entry);
+	int ret = -EINVAL;
+
+	if (args == NULL)
+		return 0;
+
+	while ((field = strsep(&args, ";")) != NULL) {
+		ret = user_event_parse_field(field, user, &offset);
+
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static struct trace_event_fields user_event_fields_array[1];
+
+static const char *user_field_format(const char *type)
+{
+	if (strcmp(type, "s64") == 0)
+		return "%lld";
+	if (strcmp(type, "u64") == 0)
+		return "%llu";
+	if (strcmp(type, "s32") == 0)
+		return "%d";
+	if (strcmp(type, "u32") == 0)
+		return "%u";
+	if (strcmp(type, "int") == 0)
+		return "%d";
+	if (strcmp(type, "unsigned int") == 0)
+		return "%u";
+	if (strcmp(type, "s16") == 0)
+		return "%d";
+	if (strcmp(type, "u16") == 0)
+		return "%u";
+	if (strcmp(type, "short") == 0)
+		return "%d";
+	if (strcmp(type, "unsigned short") == 0)
+		return "%u";
+	if (strcmp(type, "s8") == 0)
+		return "%d";
+	if (strcmp(type, "u8") == 0)
+		return "%u";
+	if (strcmp(type, "char") == 0)
+		return "%d";
+	if (strcmp(type, "unsigned char") == 0)
+		return "%u";
+	if (strstr(type, "char[") != NULL)
+		return "%s";
+
+	/* Unknown, likely struct, allowed treat as 64-bit */
+	return "%llu";
+}
+
+static bool user_field_is_dyn_string(const char *type, const char **str_func)
+{
+	if (str_has_prefix(type, "__data_loc ")) {
+		*str_func = "__get_str";
+		goto check;
+	}
+
+	if (str_has_prefix(type, "__rel_loc ")) {
+		*str_func = "__get_rel_str";
+		goto check;
+	}
+
+	return false;
+check:
+	return strstr(type, "char") != NULL;
+}
+
+#define LEN_OR_ZERO (len ? len - pos : 0)
+static int user_dyn_field_set_string(int argc, const char **argv, int *iout,
+				     char *buf, int len, bool *colon)
+{
+	int pos = 0, i = *iout;
+
+	*colon = false;
+
+	for (; i < argc; ++i) {
+		if (i != *iout)
+			pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
+
+		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", argv[i]);
+
+		if (strchr(argv[i], ';')) {
+			++i;
+			*colon = true;
+			break;
+		}
+	}
+
+	/* Actual set, advance i */
+	if (len != 0)
+		*iout = i;
+
+	return pos + 1;
+}
+
+static int user_field_set_string(struct ftrace_event_field *field,
+				 char *buf, int len, bool colon)
+{
+	int pos = 0;
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", field->type);
+	pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", field->name);
+
+	if (colon)
+		pos += snprintf(buf + pos, LEN_OR_ZERO, ";");
+
+	return pos + 1;
+}
+
+static int user_event_set_print_fmt(struct user_event *user, char *buf, int len)
+{
+	struct ftrace_event_field *field, *next;
+	struct list_head *head = &user->fields;
+	int pos = 0, depth = 0;
+	const char *str_func;
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+
+	list_for_each_entry_safe_reverse(field, next, head, link) {
+		if (depth != 0)
+			pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
+
+		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s=%s",
+				field->name, user_field_format(field->type));
+
+		depth++;
+	}
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+
+	list_for_each_entry_safe_reverse(field, next, head, link) {
+		if (user_field_is_dyn_string(field->type, &str_func))
+			pos += snprintf(buf + pos, LEN_OR_ZERO,
+					", %s(%s)", str_func, field->name);
+		else
+			pos += snprintf(buf + pos, LEN_OR_ZERO,
+					", REC->%s", field->name);
+	}
+
+	return pos + 1;
+}
+#undef LEN_OR_ZERO
+
+static int user_event_create_print_fmt(struct user_event *user)
+{
+	char *print_fmt;
+	int len;
+
+	len = user_event_set_print_fmt(user, NULL, 0);
+
+	print_fmt = kmalloc(len, GFP_KERNEL);
+
+	if (!print_fmt)
+		return -ENOMEM;
+
+	user_event_set_print_fmt(user, print_fmt, len);
+
+	user->call.print_fmt = print_fmt;
+
+	return 0;
+}
+
+static enum print_line_t user_event_print_trace(struct trace_iterator *iter,
+						int flags,
+						struct trace_event *event)
+{
+	/* Unsafe to try to decode user provided print_fmt, use hex */
+	trace_print_hex_dump_seq(&iter->seq, "", DUMP_PREFIX_OFFSET, 16,
+				 1, iter->ent, iter->ent_size, true);
+
+	return trace_handle_return(&iter->seq);
+}
+
+static struct trace_event_functions user_event_funcs = {
+	.trace = user_event_print_trace,
+};
+
+static int user_event_set_call_visible(struct user_event *user, bool visible)
+{
+	int ret;
+	const struct cred *old_cred;
+	struct cred *cred;
+
+	cred = prepare_creds();
+
+	if (!cred)
+		return -ENOMEM;
+
+	/*
+	 * While by default tracefs is locked down, systems can be configured
+	 * to allow user_event files to be less locked down. The extreme case
+	 * being "other" has read/write access to user_events_data/status.
+	 *
+	 * When not locked down, processes may not have permissions to
+	 * add/remove calls themselves to tracefs. We need to temporarily
+	 * switch to root file permission to allow for this scenario.
+	 */
+	cred->fsuid = GLOBAL_ROOT_UID;
+
+	old_cred = override_creds(cred);
+
+	if (visible)
+		ret = trace_add_event_call(&user->call);
+	else
+		ret = trace_remove_event_call(&user->call);
+
+	revert_creds(old_cred);
+	put_cred(cred);
+
+	return ret;
+}
+
+static int destroy_user_event(struct user_event *user)
+{
+	int ret = 0;
+
+	/* Must destroy fields before call removal */
+	user_event_destroy_fields(user);
+
+	ret = user_event_set_call_visible(user, false);
+
+	if (ret)
+		return ret;
+
+	dyn_event_remove(&user->devent);
+
+	user_event_register_clear(user);
+	clear_bit(user->index, user->group->page_bitmap);
+	hash_del(&user->node);
+
+	user_event_destroy_validators(user);
+	kfree(user->call.print_fmt);
+	kfree(EVENT_NAME(user));
+	kfree(user);
+
+	return ret;
+}
+
+static struct user_event *find_user_event(struct user_event_group *group,
+					  char *name, u32 *outkey)
+{
+	struct user_event *user;
+	u32 key = user_event_key(name);
+
+	*outkey = key;
+
+	hash_for_each_possible(group->register_table, user, node, key)
+		if (!strcmp(EVENT_NAME(user), name)) {
+			refcount_inc(&user->refcnt);
+			return user;
+		}
+
+	return NULL;
+}
+
+static int user_event_validate(struct user_event *user, void *data, int len)
+{
+	struct list_head *head = &user->validators;
+	struct user_event_validator *validator;
+	void *pos, *end = data + len;
+	u32 loc, offset, size;
+
+	list_for_each_entry(validator, head, link) {
+		pos = data + validator->offset;
+
+		/* Already done min_size check, no bounds check here */
+		loc = *(u32 *)pos;
+		offset = loc & 0xffff;
+		size = loc >> 16;
+
+		if (likely(validator->flags & VALIDATOR_REL))
+			pos += offset + sizeof(loc);
+		else
+			pos = data + offset;
+
+		pos += size;
+
+		if (unlikely(pos > end))
+			return -EFAULT;
+
+		if (likely(validator->flags & VALIDATOR_ENSURE_NULL))
+			if (unlikely(*(char *)(pos - 1) != '\0'))
+				return -EFAULT;
+	}
+
+	return 0;
+}
+
+/*
+ * Writes the user supplied payload out to a trace file.
+ */
+static void user_event_ftrace(struct user_event *user, struct iov_iter *i,
+			      void *tpdata, bool *faulted)
+{
+	struct trace_event_file *file;
+	struct trace_entry *entry;
+	struct trace_event_buffer event_buffer;
+	size_t size = sizeof(*entry) + i->count;
+
+	file = (struct trace_event_file *)tpdata;
+
+	if (!file ||
+	    !(file->flags & EVENT_FILE_FL_ENABLED) ||
+	    trace_trigger_soft_disabled(file))
+		return;
+
+	/* Allocates and fills trace_entry, + 1 of this is data payload */
+	entry = trace_event_buffer_reserve(&event_buffer, file, size);
+
+	if (unlikely(!entry))
+		return;
+
+	if (unlikely(!copy_nofault(entry + 1, i->count, i)))
+		goto discard;
+
+	if (!list_empty(&user->validators) &&
+	    unlikely(user_event_validate(user, entry, size)))
+		goto discard;
+
+	trace_event_buffer_commit(&event_buffer);
+
+	return;
+discard:
+	*faulted = true;
+	__trace_event_discard_commit(event_buffer.buffer,
+				     event_buffer.event);
+}
+
+#ifdef CONFIG_PERF_EVENTS
+/*
+ * Writes the user supplied payload out to perf ring buffer.
+ */
+static void user_event_perf(struct user_event *user, struct iov_iter *i,
+			    void *tpdata, bool *faulted)
+{
+	struct hlist_head *perf_head;
+
+	perf_head = this_cpu_ptr(user->call.perf_events);
+
+	if (perf_head && !hlist_empty(perf_head)) {
+		struct trace_entry *perf_entry;
+		struct pt_regs *regs;
+		size_t size = sizeof(*perf_entry) + i->count;
+		int context;
+
+		perf_entry = perf_trace_buf_alloc(ALIGN(size, 8),
+						  &regs, &context);
+
+		if (unlikely(!perf_entry))
+			return;
+
+		perf_fetch_caller_regs(regs);
+
+		if (unlikely(!copy_nofault(perf_entry + 1, i->count, i)))
+			goto discard;
+
+		if (!list_empty(&user->validators) &&
+		    unlikely(user_event_validate(user, perf_entry, size)))
+			goto discard;
+
+		perf_trace_buf_submit(perf_entry, size, context,
+				      user->call.event.type, 1, regs,
+				      perf_head, NULL);
+
+		return;
+discard:
+		*faulted = true;
+		perf_swevent_put_recursion_context(context);
+	}
+}
+#endif
+
+/*
+ * Update the register page that is shared between user processes.
+ */
+static void update_reg_page_for(struct user_event *user)
+{
+	struct tracepoint *tp = &user->tracepoint;
+	char status = 0;
+
+	if (atomic_read(&tp->key.enabled) > 0) {
+		struct tracepoint_func *probe_func_ptr;
+		user_event_func_t probe_func;
+
+		rcu_read_lock_sched();
+
+		probe_func_ptr = rcu_dereference_sched(tp->funcs);
+
+		if (probe_func_ptr) {
+			do {
+				probe_func = probe_func_ptr->func;
+
+				if (probe_func == user_event_ftrace)
+					status |= EVENT_STATUS_FTRACE;
+#ifdef CONFIG_PERF_EVENTS
+				else if (probe_func == user_event_perf)
+					status |= EVENT_STATUS_PERF;
+#endif
+				else
+					status |= EVENT_STATUS_OTHER;
+			} while ((++probe_func_ptr)->func);
+		}
+
+		rcu_read_unlock_sched();
+	}
+
+	if (status)
+		user_event_register_set(user);
+	else
+		user_event_register_clear(user);
+
+	user->status = status;
+}
+
+/*
+ * Register callback for our events from tracing sub-systems.
+ */
+static int user_event_reg(struct trace_event_call *call,
+			  enum trace_reg type,
+			  void *data)
+{
+	struct user_event *user = (struct user_event *)call->data;
+	int ret = 0;
+
+	if (!user)
+		return -ENOENT;
+
+	switch (type) {
+	case TRACE_REG_REGISTER:
+		ret = tracepoint_probe_register(call->tp,
+						call->class->probe,
+						data);
+		if (!ret)
+			goto inc;
+		break;
+
+	case TRACE_REG_UNREGISTER:
+		tracepoint_probe_unregister(call->tp,
+					    call->class->probe,
+					    data);
+		goto dec;
+
+#ifdef CONFIG_PERF_EVENTS
+	case TRACE_REG_PERF_REGISTER:
+		ret = tracepoint_probe_register(call->tp,
+						call->class->perf_probe,
+						data);
+		if (!ret)
+			goto inc;
+		break;
+
+	case TRACE_REG_PERF_UNREGISTER:
+		tracepoint_probe_unregister(call->tp,
+					    call->class->perf_probe,
+					    data);
+		goto dec;
+
+	case TRACE_REG_PERF_OPEN:
+	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
+		break;
+#endif
+	}
+
+	return ret;
+inc:
+	refcount_inc(&user->refcnt);
+	update_reg_page_for(user);
+	return 0;
+dec:
+	update_reg_page_for(user);
+	refcount_dec(&user->refcnt);
+	return 0;
+}
+
+static int user_event_create(const char *raw_command)
+{
+	struct user_event_group *group;
+	struct user_event *user;
+	char *name;
+	int ret;
+
+	if (!str_has_prefix(raw_command, USER_EVENTS_PREFIX))
+		return -ECANCELED;
+
+	raw_command += USER_EVENTS_PREFIX_LEN;
+	raw_command = skip_spaces(raw_command);
+
+	name = kstrdup(raw_command, GFP_KERNEL);
+
+	if (!name)
+		return -ENOMEM;
+
+	group = current_user_event_group();
+
+	if (!group) {
+		kfree(name);
+		return -ENOENT;
+	}
+
+	mutex_lock(&group->reg_mutex);
+
+	ret = user_event_parse_cmd(group, name, &user);
+
+	if (!ret)
+		refcount_dec(&user->refcnt);
+
+	mutex_unlock(&group->reg_mutex);
+
+	if (ret)
+		kfree(name);
+
+	return ret;
+}
+
+static int user_event_show(struct seq_file *m, struct dyn_event *ev)
+{
+	struct user_event *user = container_of(ev, struct user_event, devent);
+	struct ftrace_event_field *field, *next;
+	struct list_head *head;
+	int depth = 0;
+
+	seq_printf(m, "%s%s", USER_EVENTS_PREFIX, EVENT_NAME(user));
+
+	head = trace_get_fields(&user->call);
+
+	list_for_each_entry_safe_reverse(field, next, head, link) {
+		if (depth == 0)
+			seq_puts(m, " ");
+		else
+			seq_puts(m, "; ");
+
+		seq_printf(m, "%s %s", field->type, field->name);
+
+		if (str_has_prefix(field->type, "struct "))
+			seq_printf(m, " %d", field->size);
+
+		depth++;
+	}
+
+	seq_puts(m, "\n");
+
+	return 0;
+}
+
+static bool user_event_is_busy(struct dyn_event *ev)
+{
+	struct user_event *user = container_of(ev, struct user_event, devent);
+
+	return !user_event_last_ref(user);
+}
+
+static int user_event_free(struct dyn_event *ev)
+{
+	struct user_event *user = container_of(ev, struct user_event, devent);
+
+	if (!user_event_last_ref(user))
+		return -EBUSY;
+
+	return destroy_user_event(user);
+}
+
+static bool user_field_match(struct ftrace_event_field *field, int argc,
+			     const char **argv, int *iout)
+{
+	char *field_name = NULL, *dyn_field_name = NULL;
+	bool colon = false, match = false;
+	int dyn_len, len;
+
+	if (*iout >= argc)
+		return false;
+
+	dyn_len = user_dyn_field_set_string(argc, argv, iout, dyn_field_name,
+					    0, &colon);
+
+	len = user_field_set_string(field, field_name, 0, colon);
+
+	if (dyn_len != len)
+		return false;
+
+	dyn_field_name = kmalloc(dyn_len, GFP_KERNEL);
+	field_name = kmalloc(len, GFP_KERNEL);
+
+	if (!dyn_field_name || !field_name)
+		goto out;
+
+	user_dyn_field_set_string(argc, argv, iout, dyn_field_name,
+				  dyn_len, &colon);
+
+	user_field_set_string(field, field_name, len, colon);
+
+	match = strcmp(dyn_field_name, field_name) == 0;
+out:
+	kfree(dyn_field_name);
+	kfree(field_name);
+
+	return match;
+}
+
+static bool user_fields_match(struct user_event *user, int argc,
+			      const char **argv)
+{
+	struct ftrace_event_field *field, *next;
+	struct list_head *head = &user->fields;
+	int i = 0;
+
+	list_for_each_entry_safe_reverse(field, next, head, link)
+		if (!user_field_match(field, argc, argv, &i))
+			return false;
+
+	if (i != argc)
+		return false;
+
+	return true;
+}
+
+static bool user_event_match(const char *system, const char *event,
+			     int argc, const char **argv, struct dyn_event *ev)
+{
+	struct user_event *user = container_of(ev, struct user_event, devent);
+	bool match;
+
+	match = strcmp(EVENT_NAME(user), event) == 0 &&
+		(!system || strcmp(system, USER_EVENTS_SYSTEM) == 0);
+
+	if (match && argc > 0)
+		match = user_fields_match(user, argc, argv);
+
+	return match;
+}
+
+static struct dyn_event_operations user_event_dops = {
+	.create = user_event_create,
+	.show = user_event_show,
+	.is_busy = user_event_is_busy,
+	.free = user_event_free,
+	.match = user_event_match,
+};
+
+static int user_event_trace_register(struct user_event *user)
+{
+	int ret;
+
+	ret = register_trace_event(&user->call.event);
+
+	if (!ret)
+		return -ENODEV;
+
+	ret = user_event_set_call_visible(user, true);
+
+	if (ret)
+		unregister_trace_event(&user->call.event);
+
+	return ret;
+}
+
+/*
+ * Parses the event name, arguments and flags then registers if successful.
+ * The name buffer lifetime is owned by this method for success cases only.
+ * Upon success the returned user_event has its ref count increased by 1.
+ */
+static int user_event_parse(struct user_event_group *group, char *name,
+			    char *args, char *flags,
+			    struct user_event **newuser)
+{
+	int ret;
+	int index;
+	u32 key;
+	struct user_event *user;
+
+	/* Prevent dyn_event from racing */
+	mutex_lock(&event_mutex);
+	user = find_user_event(group, name, &key);
+	mutex_unlock(&event_mutex);
+
+	if (user) {
+		*newuser = user;
+		/*
+		 * Name is allocated by caller, free it since it already exists.
+		 * Caller only worries about failure cases for freeing.
+		 */
+		kfree(name);
+		return 0;
+	}
+
+	index = find_first_zero_bit(group->page_bitmap, MAX_EVENTS);
+
+	if (index == MAX_EVENTS)
+		return -EMFILE;
+
+	user = kzalloc(sizeof(*user), GFP_KERNEL);
+
+	if (!user)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&user->class.fields);
+	INIT_LIST_HEAD(&user->fields);
+	INIT_LIST_HEAD(&user->validators);
+
+	user->group = group;
+	user->tracepoint.name = name;
+
+	ret = user_event_parse_fields(user, args);
+
+	if (ret)
+		goto put_user;
+
+	ret = user_event_create_print_fmt(user);
+
+	if (ret)
+		goto put_user;
+
+	user->call.data = user;
+	user->call.class = &user->class;
+	user->call.name = name;
+	user->call.flags = TRACE_EVENT_FL_TRACEPOINT;
+	user->call.tp = &user->tracepoint;
+	user->call.event.funcs = &user_event_funcs;
+	user->class.system = group->system_name;
+
+	user->class.fields_array = user_event_fields_array;
+	user->class.get_fields = user_event_get_fields;
+	user->class.reg = user_event_reg;
+	user->class.probe = user_event_ftrace;
+#ifdef CONFIG_PERF_EVENTS
+	user->class.perf_probe = user_event_perf;
+#endif
+
+	mutex_lock(&event_mutex);
+
+	ret = user_event_trace_register(user);
+
+	if (ret)
+		goto put_user_lock;
+
+	user->index = index;
+
+	/* Ensure we track self ref and caller ref (2) */
+	refcount_set(&user->refcnt, 2);
+
+	dyn_event_init(&user->devent, &user_event_dops);
+	dyn_event_add(&user->devent, &user->call);
+	set_bit(user->index, group->page_bitmap);
+	hash_add(group->register_table, &user->node, key);
+
+	mutex_unlock(&event_mutex);
+
+	*newuser = user;
+	return 0;
+put_user_lock:
+	mutex_unlock(&event_mutex);
+put_user:
+	user_event_destroy_fields(user);
+	user_event_destroy_validators(user);
+	kfree(user);
+	return ret;
+}
+
+/*
+ * Deletes a previously created event if it is no longer being used.
+ */
+static int delete_user_event(struct user_event_group *group, char *name)
+{
+	u32 key;
+	struct user_event *user = find_user_event(group, name, &key);
+
+	if (!user)
+		return -ENOENT;
+
+	refcount_dec(&user->refcnt);
+
+	if (!user_event_last_ref(user))
+		return -EBUSY;
+
+	return destroy_user_event(user);
+}
+
+/*
+ * Validates the user payload and writes via iterator.
+ */
+static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
+{
+	struct user_event_file_info *info = file->private_data;
+	struct user_event_refs *refs;
+	struct user_event *user = NULL;
+	struct tracepoint *tp;
+	ssize_t ret = i->count;
+	int idx;
+
+	if (unlikely(copy_from_iter(&idx, sizeof(idx), i) != sizeof(idx)))
+		return -EFAULT;
+
+	rcu_read_lock_sched();
+
+	refs = rcu_dereference_sched(info->refs);
+
+	/*
+	 * The refs->events array is protected by RCU, and new items may be
+	 * added. But the user retrieved from indexing into the events array
+	 * shall be immutable while the file is opened.
+	 */
+	if (likely(refs && idx < refs->count))
+		user = refs->events[idx];
+
+	rcu_read_unlock_sched();
+
+	if (unlikely(user == NULL))
+		return -ENOENT;
+
+	if (unlikely(i->count < user->min_size))
+		return -EINVAL;
+
+	tp = &user->tracepoint;
+
+	/*
+	 * It's possible key.enabled disables after this check, however
+	 * we don't mind if a few events are included in this condition.
+	 */
+	if (likely(atomic_read(&tp->key.enabled) > 0)) {
+		struct tracepoint_func *probe_func_ptr;
+		user_event_func_t probe_func;
+		struct iov_iter copy;
+		void *tpdata;
+		bool faulted;
+
+		if (unlikely(fault_in_iov_iter_readable(i, i->count)))
+			return -EFAULT;
+
+		faulted = false;
+
+		rcu_read_lock_sched();
+
+		probe_func_ptr = rcu_dereference_sched(tp->funcs);
+
+		if (probe_func_ptr) {
+			do {
+				copy = *i;
+				probe_func = probe_func_ptr->func;
+				tpdata = probe_func_ptr->data;
+				probe_func(user, &copy, tpdata, &faulted);
+			} while ((++probe_func_ptr)->func);
+		}
+
+		rcu_read_unlock_sched();
+
+		if (unlikely(faulted))
+			return -EFAULT;
+	}
+
+	return ret;
+}
+
+static int user_events_open(struct inode *node, struct file *file)
+{
+	struct user_event_group *group;
+	struct user_event_file_info *info;
+
+	group = current_user_event_group();
+
+	if (!group)
+		return -ENOENT;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+
+	if (!info)
+		return -ENOMEM;
+
+	info->group = group;
+
+	file->private_data = info;
+
+	return 0;
+}
+
+static ssize_t user_events_write(struct file *file, const char __user *ubuf,
+				 size_t count, loff_t *ppos)
+{
+	struct iovec iov;
+	struct iov_iter i;
+
+	if (unlikely(*ppos != 0))
+		return -EFAULT;
+
+	if (unlikely(import_single_range(WRITE, (char __user *)ubuf,
+					 count, &iov, &i)))
+		return -EFAULT;
+
+	return user_events_write_core(file, &i);
+}
+
+static ssize_t user_events_write_iter(struct kiocb *kp, struct iov_iter *i)
+{
+	return user_events_write_core(kp->ki_filp, i);
+}
+
+static int user_events_ref_add(struct user_event_file_info *info,
+			       struct user_event *user)
+{
+	struct user_event_group *group = info->group;
+	struct user_event_refs *refs, *new_refs;
+	int i, size, count = 0;
+
+	refs = rcu_dereference_protected(info->refs,
+					 lockdep_is_held(&group->reg_mutex));
+
+	if (refs) {
+		count = refs->count;
+
+		for (i = 0; i < count; ++i)
+			if (refs->events[i] == user)
+				return i;
+	}
+
+	size = struct_size(refs, events, count + 1);
+
+	new_refs = kzalloc(size, GFP_KERNEL);
+
+	if (!new_refs)
+		return -ENOMEM;
+
+	new_refs->count = count + 1;
+
+	for (i = 0; i < count; ++i)
+		new_refs->events[i] = refs->events[i];
+
+	new_refs->events[i] = user;
+
+	refcount_inc(&user->refcnt);
+
+	rcu_assign_pointer(info->refs, new_refs);
+
+	if (refs)
+		kfree_rcu(refs, rcu);
+
+	return i;
+}
+
+static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg)
+{
+	u32 size;
+	long ret;
+
+	ret = get_user(size, &ureg->size);
+
+	if (ret)
+		return ret;
+
+	if (size > PAGE_SIZE)
+		return -E2BIG;
+
+	if (size < offsetofend(struct user_reg, write_index))
+		return -EINVAL;
+
+	ret = copy_struct_from_user(kreg, sizeof(*kreg), ureg, size);
+
+	if (ret)
+		return ret;
+
+	kreg->size = size;
+
+	return 0;
+}
+
+/*
+ * Registers a user_event on behalf of a user process.
+ */
+static long user_events_ioctl_reg(struct user_event_file_info *info,
+				  unsigned long uarg)
+{
+	struct user_reg __user *ureg = (struct user_reg __user *)uarg;
+	struct user_reg reg;
+	struct user_event *user;
+	char *name;
+	long ret;
+
+	ret = user_reg_get(ureg, &reg);
+
+	if (ret)
+		return ret;
+
+	name = strndup_user((const char __user *)(uintptr_t)reg.name_args,
+			    MAX_EVENT_DESC);
+
+	if (IS_ERR(name)) {
+		ret = PTR_ERR(name);
+		return ret;
+	}
+
+	ret = user_event_parse_cmd(info->group, name, &user);
+
+	if (ret) {
+		kfree(name);
+		return ret;
+	}
+
+	ret = user_events_ref_add(info, user);
+
+	/* No longer need parse ref, ref_add either worked or not */
+	refcount_dec(&user->refcnt);
+
+	/* Positive number is index and valid */
+	if (ret < 0)
+		return ret;
+
+	put_user((u32)ret, &ureg->write_index);
+	put_user(user->index, &ureg->status_bit);
+
+	return 0;
+}
+
+/*
+ * Deletes a user_event on behalf of a user process.
+ */
+static long user_events_ioctl_del(struct user_event_file_info *info,
+				  unsigned long uarg)
+{
+	void __user *ubuf = (void __user *)uarg;
+	char *name;
+	long ret;
+
+	name = strndup_user(ubuf, MAX_EVENT_DESC);
+
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	/* event_mutex prevents dyn_event from racing */
+	mutex_lock(&event_mutex);
+	ret = delete_user_event(info->group, name);
+	mutex_unlock(&event_mutex);
+
+	kfree(name);
+
+	return ret;
+}
+
+/*
+ * Handles the ioctl from user mode to register or alter operations.
+ */
+static long user_events_ioctl(struct file *file, unsigned int cmd,
+			      unsigned long uarg)
+{
+	struct user_event_file_info *info = file->private_data;
+	struct user_event_group *group = info->group;
+	long ret = -ENOTTY;
+
+	switch (cmd) {
+	case DIAG_IOCSREG:
+		mutex_lock(&group->reg_mutex);
+		ret = user_events_ioctl_reg(info, uarg);
+		mutex_unlock(&group->reg_mutex);
+		break;
+
+	case DIAG_IOCSDEL:
+		mutex_lock(&group->reg_mutex);
+		ret = user_events_ioctl_del(info, uarg);
+		mutex_unlock(&group->reg_mutex);
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Handles the final close of the file from user mode.
+ */
+static int user_events_release(struct inode *node, struct file *file)
+{
+	struct user_event_file_info *info = file->private_data;
+	struct user_event_group *group;
+	struct user_event_refs *refs;
+	struct user_event *user;
+	int i;
+
+	if (!info)
+		return -EINVAL;
+
+	group = info->group;
+
+	/*
+	 * Ensure refs cannot change under any situation by taking the
+	 * register mutex during the final freeing of the references.
+	 */
+	mutex_lock(&group->reg_mutex);
+
+	refs = info->refs;
+
+	if (!refs)
+		goto out;
+
+	/*
+	 * The lifetime of refs has reached an end, it's tied to this file.
+	 * The underlying user_events are ref counted, and cannot be freed.
+	 * After this decrement, the user_events may be freed elsewhere.
+	 */
+	for (i = 0; i < refs->count; ++i) {
+		user = refs->events[i];
+
+		if (user)
+			refcount_dec(&user->refcnt);
+	}
+out:
+	file->private_data = NULL;
+
+	mutex_unlock(&group->reg_mutex);
+
+	kfree(refs);
+	kfree(info);
+
+	return 0;
+}
+
+static const struct file_operations user_data_fops = {
+	.open = user_events_open,
+	.write = user_events_write,
+	.write_iter = user_events_write_iter,
+	.unlocked_ioctl	= user_events_ioctl,
+	.release = user_events_release,
+};
+
+static struct user_event_group *user_status_group(struct file *file)
+{
+	struct seq_file *m = file->private_data;
+
+	if (!m)
+		return NULL;
+
+	return m->private;
+}
+
+/*
+ * Maps the shared page into the user process for checking if event is enabled.
+ */
+static int user_status_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	char *pages;
+	struct user_event_group *group = user_status_group(file);
+	unsigned long size = vma->vm_end - vma->vm_start;
+
+	if (size != MAX_BYTES)
+		return -EINVAL;
+
+	if (!group)
+		return -EINVAL;
+
+	pages = group->register_page_data;
+
+	return remap_pfn_range(vma, vma->vm_start,
+			       virt_to_phys(pages) >> PAGE_SHIFT,
+			       size, vm_get_page_prot(VM_READ));
+}
+
+static void *user_seq_start(struct seq_file *m, loff_t *pos)
+{
+	if (*pos)
+		return NULL;
+
+	return (void *)1;
+}
+
+static void *user_seq_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	++*pos;
+	return NULL;
+}
+
+static void user_seq_stop(struct seq_file *m, void *p)
+{
+}
+
+static int user_seq_show(struct seq_file *m, void *p)
+{
+	struct user_event_group *group = m->private;
+	struct user_event *user;
+	char status;
+	int i, active = 0, busy = 0, flags;
+
+	if (!group)
+		return -EINVAL;
+
+	mutex_lock(&group->reg_mutex);
+
+	hash_for_each(group->register_table, i, user, node) {
+		status = user->status;
+		flags = user->flags;
+
+		seq_printf(m, "%d:%s", user->index, EVENT_NAME(user));
+
+		if (flags != 0 || status != 0)
+			seq_puts(m, " #");
+
+		if (status != 0) {
+			seq_puts(m, " Used by");
+			if (status & EVENT_STATUS_FTRACE)
+				seq_puts(m, " ftrace");
+			if (status & EVENT_STATUS_PERF)
+				seq_puts(m, " perf");
+			if (status & EVENT_STATUS_OTHER)
+				seq_puts(m, " other");
+			busy++;
+		}
+
+		seq_puts(m, "\n");
+		active++;
+	}
+
+	mutex_unlock(&group->reg_mutex);
+
+	seq_puts(m, "\n");
+	seq_printf(m, "Active: %d\n", active);
+	seq_printf(m, "Busy: %d\n", busy);
+	seq_printf(m, "Max: %ld\n", MAX_EVENTS);
+
+	return 0;
+}
+
+static const struct seq_operations user_seq_ops = {
+	.start = user_seq_start,
+	.next  = user_seq_next,
+	.stop  = user_seq_stop,
+	.show  = user_seq_show,
+};
+
+static int user_status_open(struct inode *node, struct file *file)
+{
+	struct user_event_group *group;
+	int ret;
+
+	group = current_user_event_group();
+
+	if (!group)
+		return -ENOENT;
+
+	ret = seq_open(file, &user_seq_ops);
+
+	if (!ret) {
+		/* Chain group to seq_file */
+		struct seq_file *m = file->private_data;
+
+		m->private = group;
+	}
+
+	return ret;
+}
+
+static const struct file_operations user_status_fops = {
+	.open = user_status_open,
+	.mmap = user_status_mmap,
+	.read = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
+/*
+ * Creates a set of tracefs files to allow user mode interactions.
+ */
+static int create_user_tracefs(void)
+{
+	struct dentry *edata, *emmap;
+
+	edata = tracefs_create_file("user_events_data", TRACE_MODE_WRITE,
+				    NULL, NULL, &user_data_fops);
+
+	if (!edata) {
+		pr_warn("Could not create tracefs 'user_events_data' entry\n");
+		goto err;
+	}
+
+	/* mmap with MAP_SHARED requires writable fd */
+	emmap = tracefs_create_file("user_events_status", TRACE_MODE_WRITE,
+				    NULL, NULL, &user_status_fops);
+
+	if (!emmap) {
+		tracefs_remove(edata);
+		pr_warn("Could not create tracefs 'user_events_mmap' entry\n");
+		goto err;
+	}
+
+	return 0;
+err:
+	return -ENODEV;
+}
+
+static int __init trace_events_user_init(void)
+{
+	int ret;
+
+	init_group = user_event_group_create(&init_user_ns);
+
+	if (!init_group)
+		return -ENOMEM;
+
+	ret = create_user_tracefs();
+
+	if (ret) {
+		pr_warn("user_events could not register with tracefs\n");
+		user_event_group_destroy(init_group);
+		init_group = NULL;
+		return ret;
+	}
+
+	if (dyn_event_register(&user_event_dops))
+		pr_warn("user_events could not register with dyn_events\n");
+
+	return 0;
+}
+
+fs_initcall(trace_events_user_init);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 508f14af4f2c..5a75b039e586 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -20,6 +20,7 @@
 #include "trace_kprobe_selftest.h"
 #include "trace_probe.h"
 #include "trace_probe_tmpl.h"
+#include "trace_probe_kernel.h"
 
 #define KPROBE_EVENT_SYSTEM "kprobes"
 #define KRETPROBE_MAXACTIVE_MAX 4096
@@ -32,7 +33,7 @@ static int __init set_kprobe_boot_events(char *str)
 	strlcpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE);
 	disable_tracing_selftest("running kprobe events");
 
-	return 0;
+	return 1;
 }
 __setup("kprobe_event=", set_kprobe_boot_events);
 
@@ -163,7 +164,8 @@ static bool trace_kprobe_match(const char *system, const char *event,
 {
 	struct trace_kprobe *tk = to_trace_kprobe(ev);
 
-	return strcmp(trace_probe_name(&tk->tp), event) == 0 &&
+	return (event[0] == '\0' ||
+		strcmp(trace_probe_name(&tk->tp), event) == 0) &&
 	    (!system || strcmp(trace_probe_group_name(&tk->tp), system) == 0) &&
 	    trace_kprobe_match_command_head(tk, argc, argv);
 }
@@ -708,11 +710,11 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 	/*
 	 * Argument syntax:
 	 *  - Add kprobe:
-	 *      p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
+	 *      p[:[GRP/][EVENT]] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
 	 *  - Add kretprobe:
-	 *      r[MAXACTIVE][:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
+	 *      r[MAXACTIVE][:[GRP/][EVENT]] [MOD:]KSYM[+0] [FETCHARGS]
 	 *    Or
-	 *      p:[GRP/]EVENT] [MOD:]KSYM[+0]%return [FETCHARGS]
+	 *      p[:[GRP/][EVENT]] [MOD:]KSYM[+0]%return [FETCHARGS]
 	 *
 	 * Fetch args:
 	 *  $retval	: fetch return value
@@ -739,6 +741,7 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 	long offset = 0;
 	void *addr = NULL;
 	char buf[MAX_EVENT_NAME_LEN];
+	char gbuf[MAX_EVENT_NAME_LEN];
 	unsigned int flags = TPARG_FL_KERNEL;
 
 	switch (argv[0][0]) {
@@ -833,11 +836,13 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 
 	trace_probe_log_set_index(0);
 	if (event) {
-		ret = traceprobe_parse_event_name(&event, &group, buf,
+		ret = traceprobe_parse_event_name(&event, &group, gbuf,
 						  event - argv[0]);
 		if (ret)
 			goto parse_error;
-	} else {
+	}
+
+	if (!event) {
 		/* Make a new event name */
 		if (symbol)
 			snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_%ld",
@@ -1219,29 +1224,14 @@ static const struct file_operations kprobe_profile_ops = {
 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 kern_fetch_store_strlen_user(addr);
 }
 
 /* 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 = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
-		len++;
-	} while (c && ret == 0 && len < MAX_STRING_SIZE);
-
-	return (ret < 0) ? ret : len;
+	return kern_fetch_store_strlen(addr);
 }
 
 /*
@@ -1251,21 +1241,7 @@ fetch_store_strlen(unsigned long addr)
 static nokprobe_inline int
 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;
-
-	if (unlikely(!maxlen))
-		return -ENOMEM;
-
-	__dest = get_loc_data(dest, base);
-
-	ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
-	if (ret >= 0)
-		*(u32 *)dest = make_data_loc(ret, __dest - base);
-
-	return ret;
+	return kern_fetch_store_string_user(addr, dest, base);
 }
 
 /*
@@ -1275,29 +1251,7 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base)
 static nokprobe_inline int
 fetch_store_string(unsigned long addr, void *dest, void *base)
 {
-	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);
-
-	/*
-	 * 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);
-
-	return ret;
+	return kern_fetch_store_string(addr, dest, base);
 }
 
 static nokprobe_inline int
@@ -1433,7 +1387,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	fbuffer.regs = regs;
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
 	entry->func = (unsigned long)tk->rp.kp.addr;
-	entry->ret_ip = (unsigned long)ri->ret_addr;
+	entry->ret_ip = get_kretprobe_retaddr(ri);
 	store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
@@ -1628,7 +1582,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		return;
 
 	entry->func = (unsigned long)tk->rp.kp.addr;
-	entry->ret_ip = (unsigned long)ri->ret_addr;
+	entry->ret_ip = get_kretprobe_retaddr(ri);
 	store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL);
@@ -1718,8 +1672,17 @@ static int
 kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	struct kretprobe *rp = get_kretprobe(ri);
-	struct trace_kprobe *tk = container_of(rp, struct trace_kprobe, rp);
+	struct trace_kprobe *tk;
 
+	/*
+	 * There is a small chance that get_kretprobe(ri) returns NULL when
+	 * the kretprobe is unregister on another CPU between kretprobe's
+	 * trampoline_handler and this function.
+	 */
+	if (unlikely(!rp))
+		return 0;
+
+	tk = container_of(rp, struct trace_kprobe, rp);
 	raw_cpu_inc(*tk->nhit);
 
 	if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
@@ -1907,25 +1870,18 @@ core_initcall(init_kprobe_trace_early);
 static __init int init_kprobe_trace(void)
 {
 	int ret;
-	struct dentry *entry;
 
 	ret = tracing_init_dentry();
 	if (ret)
 		return 0;
 
-	entry = tracefs_create_file("kprobe_events", TRACE_MODE_WRITE,
-				    NULL, NULL, &kprobe_events_ops);
-
 	/* Event list interface */
-	if (!entry)
-		pr_warn("Could not create tracefs 'kprobe_events' entry\n");
+	trace_create_file("kprobe_events", TRACE_MODE_WRITE,
+			  NULL, NULL, &kprobe_events_ops);
 
 	/* Profile interface */
-	entry = tracefs_create_file("kprobe_profile", TRACE_MODE_READ,
-				    NULL, NULL, &kprobe_profile_ops);
-
-	if (!entry)
-		pr_warn("Could not create tracefs 'kprobe_profile' entry\n");
+	trace_create_file("kprobe_profile", TRACE_MODE_READ,
+			  NULL, NULL, &kprobe_profile_ops);
 
 	setup_boot_kprobe_events();
 
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 870a08da5b48..4300c5dc4e5d 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -917,7 +917,7 @@ void osnoise_trace_irq_entry(int id)
 void osnoise_trace_irq_exit(int id, const char *desc)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
-	int duration;
+	s64 duration;
 
 	if (!osn_var->sampling)
 		return;
@@ -1048,7 +1048,7 @@ static void trace_softirq_entry_callback(void *data, unsigned int vec_nr)
 static void trace_softirq_exit_callback(void *data, unsigned int vec_nr)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
-	int duration;
+	s64 duration;
 
 	if (!osn_var->sampling)
 		return;
@@ -1144,7 +1144,7 @@ thread_entry(struct osnoise_variables *osn_var, struct task_struct *t)
 static void
 thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
 {
-	int duration;
+	s64 duration;
 
 	if (!osn_var->sampling)
 		return;
@@ -1167,8 +1167,10 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
  * used to record the beginning and to report the end of a thread noise window.
  */
 static void
-trace_sched_switch_callback(void *data, bool preempt, struct task_struct *p,
-			    struct task_struct *n)
+trace_sched_switch_callback(void *data, bool preempt,
+			    struct task_struct *p,
+			    struct task_struct *n,
+			    unsigned int prev_state)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
 
@@ -1387,6 +1389,26 @@ static int run_osnoise(void)
 		}
 
 		/*
+		 * In some cases, notably when running on a nohz_full CPU with
+		 * a stopped tick PREEMPT_RCU has no way to account for QSs.
+		 * This will eventually cause unwarranted noise as PREEMPT_RCU
+		 * will force preemption as the means of ending the current
+		 * grace period. We avoid this problem by calling
+		 * rcu_momentary_dyntick_idle(), which performs a zero duration
+		 * EQS allowing PREEMPT_RCU to end the current grace period.
+		 * This call shouldn't be wrapped inside an RCU critical
+		 * section.
+		 *
+		 * Note that in non PREEMPT_RCU kernels QSs are handled through
+		 * cond_resched()
+		 */
+		if (IS_ENABLED(CONFIG_PREEMPT_RCU)) {
+			local_irq_disable();
+			rcu_momentary_dyntick_idle();
+			local_irq_enable();
+		}
+
+		/*
 		 * For the non-preemptive kernel config: let threads runs, if
 		 * they so wish.
 		 */
@@ -1437,6 +1459,37 @@ static struct cpumask osnoise_cpumask;
 static struct cpumask save_cpumask;
 
 /*
+ * osnoise_sleep - sleep until the next period
+ */
+static void osnoise_sleep(void)
+{
+	u64 interval;
+	ktime_t wake_time;
+
+	mutex_lock(&interface_lock);
+	interval = osnoise_data.sample_period - osnoise_data.sample_runtime;
+	mutex_unlock(&interface_lock);
+
+	/*
+	 * differently from hwlat_detector, the osnoise tracer can run
+	 * without a pause because preemption is on.
+	 */
+	if (!interval) {
+		/* Let synchronize_rcu_tasks() make progress */
+		cond_resched_tasks_rcu_qs();
+		return;
+	}
+
+	wake_time = ktime_add_us(ktime_get(), interval);
+	__set_current_state(TASK_INTERRUPTIBLE);
+
+	while (schedule_hrtimeout_range(&wake_time, 0, HRTIMER_MODE_ABS)) {
+		if (kthread_should_stop())
+			break;
+	}
+}
+
+/*
  * osnoise_main - The osnoise detection kernel thread
  *
  * Calls run_osnoise() function to measure the osnoise for the configured runtime,
@@ -1444,30 +1497,10 @@ static struct cpumask save_cpumask;
  */
 static int osnoise_main(void *data)
 {
-	u64 interval;
 
 	while (!kthread_should_stop()) {
-
 		run_osnoise();
-
-		mutex_lock(&interface_lock);
-		interval = osnoise_data.sample_period - osnoise_data.sample_runtime;
-		mutex_unlock(&interface_lock);
-
-		do_div(interval, USEC_PER_MSEC);
-
-		/*
-		 * differently from hwlat_detector, the osnoise tracer can run
-		 * without a pause because preemption is on.
-		 */
-		if (interval < 1) {
-			/* Let synchronize_rcu_tasks() make progress */
-			cond_resched_tasks_rcu_qs();
-			continue;
-		}
-
-		if (msleep_interruptible(interval))
-			break;
+		osnoise_sleep();
 	}
 
 	return 0;
@@ -1545,11 +1578,27 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
 
 	trace_timerlat_sample(&s);
 
-	notify_new_max_latency(diff);
+	if (osnoise_data.stop_tracing) {
+		if (time_to_us(diff) >= osnoise_data.stop_tracing) {
+
+			/*
+			 * At this point, if stop_tracing is set and <= print_stack,
+			 * print_stack is set and would be printed in the thread handler.
+			 *
+			 * Thus, print the stack trace as it is helpful to define the
+			 * root cause of an IRQ latency.
+			 */
+			if (osnoise_data.stop_tracing <= osnoise_data.print_stack) {
+				timerlat_save_stack(0);
+				timerlat_dump_stack(time_to_us(diff));
+			}
 
-	if (osnoise_data.stop_tracing)
-		if (time_to_us(diff) >= osnoise_data.stop_tracing)
 			osnoise_stop_tracing();
+			notify_new_max_latency(diff);
+
+			return HRTIMER_NORESTART;
+		}
+	}
 
 	wake_up_process(tlat->kthread);
 
@@ -1737,8 +1786,9 @@ static int start_per_cpu_kthreads(void)
 	for_each_cpu(cpu, current_mask) {
 		retval = start_kthread(cpu);
 		if (retval) {
+			cpus_read_unlock();
 			stop_per_cpu_kthreads();
-			break;
+			return retval;
 		}
 	}
 
@@ -2189,6 +2239,17 @@ static void osnoise_workload_stop(void)
 	if (osnoise_has_registered_instances())
 		return;
 
+	/*
+	 * If callbacks were already disabled in a previous stop
+	 * call, there is no need to disable then again.
+	 *
+	 * For instance, this happens when tracing is stopped via:
+	 * echo 0 > tracing_on
+	 * echo nop > current_tracer.
+	 */
+	if (!trace_osnoise_callback_enabled)
+		return;
+
 	trace_osnoise_callback_enabled = false;
 	/*
 	 * Make sure that ftrace_nmi_enter/exit() see
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 8aa493d25c73..67f47ea27921 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -692,7 +692,7 @@ static LIST_HEAD(ftrace_event_list);
 
 static int trace_search_list(struct list_head **list)
 {
-	struct trace_event *e;
+	struct trace_event *e = NULL, *iter;
 	int next = __TRACE_LAST_TYPE;
 
 	if (list_empty(&ftrace_event_list)) {
@@ -704,9 +704,11 @@ static int trace_search_list(struct list_head **list)
 	 * We used up all possible max events,
 	 * lets see if somebody freed one.
 	 */
-	list_for_each_entry(e, &ftrace_event_list, list) {
-		if (e->type != next)
+	list_for_each_entry(iter, &ftrace_event_list, list) {
+		if (iter->type != next) {
+			e = iter;
 			break;
+		}
 		next++;
 	}
 
@@ -714,7 +716,10 @@ static int trace_search_list(struct list_head **list)
 	if (next > TRACE_EVENT_TYPE_MAX)
 		return 0;
 
-	*list = &e->list;
+	if (e)
+		*list = &e->list;
+	else
+		*list = &ftrace_event_list;
 	return next;
 }
 
@@ -778,9 +783,8 @@ int register_trace_event(struct trace_event *event)
 
 		list_add_tail(&event->list, list);
 
-	} else if (event->type > __TRACE_LAST_TYPE) {
-		printk(KERN_WARNING "Need to add type to trace.h\n");
-		WARN_ON(1);
+	} else if (WARN(event->type > __TRACE_LAST_TYPE,
+			"Need to add type to trace.h")) {
 		goto out;
 	} else {
 		/* Is this event already used */
@@ -1571,13 +1575,8 @@ __init static int init_events(void)
 
 	for (i = 0; events[i]; i++) {
 		event = events[i];
-
 		ret = register_trace_event(event);
-		if (!ret) {
-			printk(KERN_WARNING "event %d failed to register\n",
-			       event->type);
-			WARN_ON_ONCE(1);
-		}
+		WARN_ONCE(!ret, "event %d failed to register", event->type);
 	}
 
 	return 0;
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index f4938040c228..1e130da1b742 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -46,7 +46,7 @@ void trace_hardirqs_on(void)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on);
@@ -94,15 +94,15 @@ __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);
+	lockdep_hardirqs_on_prepare();
+	lockdep_hardirqs_on(caller_addr);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
 NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
 
 __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
-	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirqs_off(caller_addr);
 
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 73d90179b51b..36dff277de46 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -257,6 +257,10 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
 	}
 	len = strlen(event);
 	if (len == 0) {
+		if (slash) {
+			*pevent = NULL;
+			return 0;
+		}
 		trace_probe_log_err(offset, NO_EVENT_NAME);
 		return -EINVAL;
 	} else if (len > MAX_EVENT_NAME_LEN) {
@@ -279,7 +283,14 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 	int ret = 0;
 	int len;
 
-	if (strcmp(arg, "retval") == 0) {
+	if (flags & TPARG_FL_TPOINT) {
+		if (code->data)
+			return -EFAULT;
+		code->data = kstrdup(arg, GFP_KERNEL);
+		if (!code->data)
+			return -ENOMEM;
+		code->op = FETCH_OP_TP_ARG;
+	} else if (strcmp(arg, "retval") == 0) {
 		if (flags & TPARG_FL_RETURN) {
 			code->op = FETCH_OP_RETVAL;
 		} else {
@@ -303,7 +314,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 			}
 		} else
 			goto inval_var;
-	} else if (strcmp(arg, "comm") == 0) {
+	} else if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) {
 		code->op = FETCH_OP_COMM;
 #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
 	} else if (((flags & TPARG_FL_MASK) ==
@@ -319,13 +330,6 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 		code->op = FETCH_OP_ARG;
 		code->param = (unsigned int)param - 1;
 #endif
-	} else if (flags & TPARG_FL_TPOINT) {
-		if (code->data)
-			return -EFAULT;
-		code->data = kstrdup(arg, GFP_KERNEL);
-		if (!code->data)
-			return -ENOMEM;
-		code->op = FETCH_OP_TP_ARG;
 	} else
 		goto inval_var;
 
@@ -380,6 +384,11 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 		break;
 
 	case '%':	/* named register */
+		if (flags & TPARG_FL_TPOINT) {
+			/* eprobes do not handle registers */
+			trace_probe_log_err(offs, BAD_VAR);
+			break;
+		}
 		ret = regs_query_register_offset(arg + 1);
 		if (ret >= 0) {
 			code->op = FETCH_OP_REG;
@@ -613,9 +622,11 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 
 	/*
 	 * Since $comm and immediate string can not be dereferenced,
-	 * we can find those by strcmp.
+	 * we can find those by strcmp. But ignore for eprobes.
 	 */
-	if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) {
+	if (!(flags & TPARG_FL_TPOINT) &&
+	    (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 ||
+	     strncmp(arg, "\\\"", 2) == 0)) {
 		/* The type of $comm must be "string", and not an array. */
 		if (parg->count || (t && strcmp(t, "string")))
 			goto out;
@@ -871,15 +882,15 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
 	switch (ptype) {
 	case PROBE_PRINT_NORMAL:
 		fmt = "(%lx)";
-		arg = "REC->" FIELD_STRING_IP;
+		arg = ", REC->" FIELD_STRING_IP;
 		break;
 	case PROBE_PRINT_RETURN:
 		fmt = "(%lx <- %lx)";
-		arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+		arg = ", REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
 		break;
 	case PROBE_PRINT_EVENT:
-		fmt = "(%u)";
-		arg = "REC->" FIELD_STRING_TYPE;
+		fmt = "";
+		arg = "";
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -903,7 +914,7 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
 					parg->type->fmt);
 	}
 
-	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", arg);
 
 	for (i = 0; i < tp->nr_args; i++) {
 		parg = tp->args + i;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 99e7a5df025e..de38f1c03776 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -38,7 +38,6 @@
 #define FIELD_STRING_IP		"__probe_ip"
 #define FIELD_STRING_RETIP	"__probe_ret_ip"
 #define FIELD_STRING_FUNC	"__probe_func"
-#define FIELD_STRING_TYPE	"__probe_type"
 
 #undef DEFINE_FIELD
 #define DEFINE_FIELD(type, item, name, is_signed)			\
@@ -443,7 +442,11 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(FAIL_REG_PROBE,	"Failed to register probe event"),\
 	C(DIFF_PROBE_TYPE,	"Probe type is different from existing probe"),\
 	C(DIFF_ARG_TYPE,	"Argument type or name is different from existing probe"),\
-	C(SAME_PROBE,		"There is already the exact same probe event"),
+	C(SAME_PROBE,		"There is already the exact same probe event"),\
+	C(NO_EVENT_INFO,	"This requires both group and event name to attach"),\
+	C(BAD_ATTACH_EVENT,	"Attached event does not exist"),\
+	C(BAD_ATTACH_ARG,	"Attached event does not have this field"),\
+	C(NO_EP_FILTER,		"No filter rule after 'if'"),
 
 #undef C
 #define C(a, b)		TP_ERR_##a
diff --git a/kernel/trace/trace_probe_kernel.h b/kernel/trace/trace_probe_kernel.h
new file mode 100644
index 000000000000..77dbd9ff9782
--- /dev/null
+++ b/kernel/trace/trace_probe_kernel.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TRACE_PROBE_KERNEL_H_
+#define __TRACE_PROBE_KERNEL_H_
+
+#define FAULT_STRING "(fault)"
+
+/*
+ * This depends on trace_probe.h, but can not include it due to
+ * the way trace_probe_tmpl.h is used by trace_kprobe.c and trace_eprobe.c.
+ * Which means that any other user must include trace_probe.h before including
+ * this file.
+ */
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
+kern_fetch_store_strlen_user(unsigned long addr)
+{
+	const void __user *uaddr =  (__force const void __user *)addr;
+	int ret;
+
+	ret = strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
+	/*
+	 * strnlen_user_nofault returns zero on fault, insert the
+	 * FAULT_STRING when that occurs.
+	 */
+	if (ret <= 0)
+		return strlen(FAULT_STRING) + 1;
+	return ret;
+}
+
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
+kern_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 kern_fetch_store_strlen_user(addr);
+#endif
+
+	do {
+		ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
+		len++;
+	} while (c && ret == 0 && len < MAX_STRING_SIZE);
+
+	/* For faults, return enough to hold the FAULT_STRING */
+	return (ret < 0) ? strlen(FAULT_STRING) + 1 : len;
+}
+
+static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void *base, int len)
+{
+	if (ret >= 0) {
+		*(u32 *)dest = make_data_loc(ret, __dest - base);
+	} else {
+		strscpy(__dest, FAULT_STRING, len);
+		ret = strlen(__dest) + 1;
+	}
+}
+
+/*
+ * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf
+ * with max length and relative data location.
+ */
+static nokprobe_inline int
+kern_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;
+
+	if (unlikely(!maxlen))
+		return -ENOMEM;
+
+	__dest = get_loc_data(dest, base);
+
+	ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
+	set_data_loc(ret, dest, __dest, base, maxlen);
+
+	return ret;
+}
+
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max
+ * length and relative data location.
+ */
+static nokprobe_inline int
+kern_fetch_store_string(unsigned long addr, void *dest, void *base)
+{
+	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 kern_fetch_store_string_user(addr, dest, base);
+#endif
+
+	if (unlikely(!maxlen))
+		return -ENOMEM;
+
+	__dest = get_loc_data(dest, base);
+
+	/*
+	 * Try to get string again, since the string can be changed while
+	 * probing.
+	 */
+	ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
+	set_data_loc(ret, dest, __dest, base, maxlen);
+
+	return ret;
+}
+
+#endif /* __TRACE_PROBE_KERNEL_H_ */
diff --git a/kernel/trace/trace_recursion_record.c b/kernel/trace/trace_recursion_record.c
index 4d4b78c8ca25..a520b11afb0d 100644
--- a/kernel/trace/trace_recursion_record.c
+++ b/kernel/trace/trace_recursion_record.c
@@ -224,12 +224,9 @@ static const struct file_operations recursed_functions_fops = {
 
 __init static int create_recursed_functions(void)
 {
-	struct dentry *dentry;
 
-	dentry = trace_create_file("recursed_functions", TRACE_MODE_WRITE,
-				   NULL, NULL, &recursed_functions_fops);
-	if (!dentry)
-		pr_warn("WARNING: Failed to create recursed_functions\n");
+	trace_create_file("recursed_functions", TRACE_MODE_WRITE,
+			  NULL, NULL, &recursed_functions_fops);
 	return 0;
 }
 
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index e304196d7c28..c9ffdcfe622e 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -22,7 +22,8 @@ static DEFINE_MUTEX(sched_register_mutex);
 
 static void
 probe_sched_switch(void *ignore, bool preempt,
-		   struct task_struct *prev, struct task_struct *next)
+		   struct task_struct *prev, struct task_struct *next,
+		   unsigned int prev_state)
 {
 	int flags;
 
@@ -44,7 +45,7 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee)
 
 	if (!flags)
 		return;
-	tracing_record_taskinfo(current, flags);
+	tracing_record_taskinfo_sched_switch(current, wakee, flags);
 }
 
 static int tracing_sched_register(void)
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 2402de520eca..330aee1c1a49 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -426,7 +426,8 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 
 static void notrace
 probe_wakeup_sched_switch(void *ignore, bool preempt,
-			  struct task_struct *prev, struct task_struct *next)
+			  struct task_struct *prev, struct task_struct *next,
+			  unsigned int prev_state)
 {
 	struct trace_array_cpu *data;
 	u64 T0, T1, delta;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index afd937a46496..a2d301f58ced 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -784,9 +784,7 @@ static struct fgraph_ops fgraph_ops __initdata  = {
 	.retfunc		= &trace_graph_return,
 };
 
-#if defined(CONFIG_DYNAMIC_FTRACE) && \
-    defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS)
-#define TEST_DIRECT_TRAMP
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 noinline __noclone static void trace_direct_tramp(void) { }
 #endif
 
@@ -849,7 +847,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 		goto out;
 	}
 
-#ifdef TEST_DIRECT_TRAMP
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	tracing_reset_online_cpus(&tr->array_buffer);
 	set_graph_array(tr);
 
@@ -897,6 +895,9 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 		ret = -1;
 		goto out;
 	}
+
+	/* Enable tracing on all functions again */
+	ftrace_set_global_filter(NULL, 0, 1);
 #endif
 
 	/* Don't test dynamic tracing, the function tracer already did */
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index f755bde42fd0..942ddbdace4a 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -154,7 +154,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags,
 			goto end;
 
 		/* parameter types */
-		if (tr->trace_flags & TRACE_ITER_VERBOSE)
+		if (tr && tr->trace_flags & TRACE_ITER_VERBOSE)
 			trace_seq_printf(s, "%s ", entry->types[i]);
 
 		/* parameter values */
@@ -201,8 +201,6 @@ print_syscall_exit(struct trace_iterator *iter, int flags,
 	return trace_handle_return(s);
 }
 
-extern char *__bad_type_size(void);
-
 #define SYSCALL_FIELD(_type, _name) {					\
 	.type = #_type, .name = #_name,					\
 	.size = sizeof(_type), .align = __alignof__(_type),		\
@@ -296,9 +294,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	struct trace_event_file *trace_file;
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
-	struct ring_buffer_event *event;
-	struct trace_buffer *buffer;
-	unsigned int trace_ctx;
+	struct trace_event_buffer fbuffer;
 	unsigned long args[6];
 	int syscall_nr;
 	int size;
@@ -321,20 +317,16 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-	trace_ctx = tracing_gen_ctx();
-
-	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
-			sys_data->enter_event->event.type, size, trace_ctx);
-	if (!event)
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file, size);
+	if (!entry)
 		return;
 
-	entry = ring_buffer_event_data(event);
+	entry = ring_buffer_event_data(fbuffer.event);
 	entry->nr = syscall_nr;
 	syscall_get_arguments(current, regs, args);
 	memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
-	event_trigger_unlock_commit(trace_file, buffer, event, entry,
-				    trace_ctx);
+	trace_event_buffer_commit(&fbuffer);
 }
 
 static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -343,9 +335,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	struct trace_event_file *trace_file;
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
-	struct ring_buffer_event *event;
-	struct trace_buffer *buffer;
-	unsigned int trace_ctx;
+	struct trace_event_buffer fbuffer;
 	int syscall_nr;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
@@ -364,20 +354,15 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
-	trace_ctx = tracing_gen_ctx();
-
-	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
-			sys_data->exit_event->event.type, sizeof(*entry),
-			trace_ctx);
-	if (!event)
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry));
+	if (!entry)
 		return;
 
-	entry = ring_buffer_event_data(event);
+	entry = ring_buffer_event_data(fbuffer.event);
 	entry->nr = syscall_nr;
 	entry->ret = syscall_get_return_value(current, regs);
 
-	event_trigger_unlock_commit(trace_file, buffer, event, entry,
-				    trace_ctx);
+	trace_event_buffer_commit(&fbuffer);
 }
 
 static int reg_event_syscall_enter(struct trace_event_file *file,
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 9711589273cd..fb58e86dd117 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -16,6 +16,7 @@
 #include <linux/namei.h>
 #include <linux/string.h>
 #include <linux/rculist.h>
+#include <linux/filter.h>
 
 #include "trace_dynevent.h"
 #include "trace_probe.h"
@@ -312,7 +313,8 @@ static bool trace_uprobe_match(const char *system, const char *event,
 {
 	struct trace_uprobe *tu = to_trace_uprobe(ev);
 
-	return strcmp(trace_probe_name(&tu->tp), event) == 0 &&
+	return (event[0] == '\0' ||
+		strcmp(trace_probe_name(&tu->tp), event) == 0) &&
 	   (!system || strcmp(trace_probe_group_name(&tu->tp), system) == 0) &&
 	   trace_uprobe_match_command_head(tu, argc, argv);
 }
@@ -532,7 +534,7 @@ end:
 
 /*
  * Argument syntax:
- *  - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET[%return][(REF)] [FETCHARGS]
+ *  - Add uprobe: p|r[:[GRP/][EVENT]] PATH:OFFSET[%return][(REF)] [FETCHARGS]
  */
 static int __trace_uprobe_create(int argc, const char **argv)
 {
@@ -540,13 +542,13 @@ static int __trace_uprobe_create(int argc, const char **argv)
 	const char *event = NULL, *group = UPROBE_EVENT_SYSTEM;
 	char *arg, *filename, *rctr, *rctr_end, *tmp;
 	char buf[MAX_EVENT_NAME_LEN];
+	char gbuf[MAX_EVENT_NAME_LEN];
 	enum probe_print_type ptype;
 	struct path path;
 	unsigned long offset, ref_ctr_offset;
 	bool is_return = false;
 	int i, ret;
 
-	ret = 0;
 	ref_ctr_offset = 0;
 
 	switch (argv[0][0]) {
@@ -645,11 +647,13 @@ static int __trace_uprobe_create(int argc, const char **argv)
 	/* setup a probe */
 	trace_probe_log_set_index(0);
 	if (event) {
-		ret = traceprobe_parse_event_name(&event, &group, buf,
+		ret = traceprobe_parse_event_name(&event, &group, gbuf,
 						  event - argv[0]);
 		if (ret)
 			goto fail_address_parse;
-	} else {
+	}
+
+	if (!event) {
 		char *tail;
 		char *ptr;
 
@@ -1343,15 +1347,15 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 	int size, esize;
 	int rctx;
 
+#ifdef CONFIG_BPF_EVENTS
 	if (bpf_prog_array_valid(call)) {
 		u32 ret;
 
-		preempt_disable();
-		ret = trace_call_bpf(call, regs);
-		preempt_enable();
+		ret = bpf_prog_run_array_sleepable(call->prog_array, regs, bpf_prog_run);
 		if (!ret)
 			return;
 	}
+#endif /* CONFIG_BPF_EVENTS */
 
 	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
 
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9628b5571846..c774e560f2f9 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -961,7 +961,7 @@ create_sort_entry(void *key, struct tracing_map_elt *elt)
 static void detect_dups(struct tracing_map_sort_entry **sort_entries,
 		      int n_entries, unsigned int key_size)
 {
-	unsigned int dups = 0, total_dups = 0;
+	unsigned int total_dups = 0;
 	int i;
 	void *key;
 
@@ -974,11 +974,10 @@ static void detect_dups(struct tracing_map_sort_entry **sort_entries,
 	key = sort_entries[0]->key;
 	for (i = 1; i < n_entries; i++) {
 		if (!memcmp(sort_entries[i]->key, key, key_size)) {
-			dups++; total_dups++;
+			total_dups++;
 			continue;
 		}
 		key = sort_entries[i]->key;
-		dups = 0;
 	}
 
 	WARN_ONCE(total_dups > 0,
@@ -1045,7 +1044,8 @@ static void sort_secondary(struct tracing_map *map,
 /**
  * tracing_map_sort_entries - Sort the current set of tracing_map_elts in a map
  * @map: The tracing_map
- * @sort_key: The sort key to use for sorting
+ * @sort_keys: The sort key to use for sorting
+ * @n_sort_keys: hitcount, always have at least one
  * @sort_entries: outval: pointer to allocated and sorted array of entries
  *
  * tracing_map_sort_entries() sorts the current set of entries in the