Merge branch 'next' into for-linus

Prepare input updates for 5.20 (or 6.0) merge window.

32 files changed, 3845 insertions, 658 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a5eb5e7fd624..debbbb083286 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
@@ -133,6 +144,7 @@ config TRACING
 	select BINARY_PRINTF
 	select EVENT_TRACING
 	select TRACE_CLOCK
+	select TASKS_RCU if PREEMPTION
 
 config GENERIC_TRACER
 	bool
@@ -236,6 +248,21 @@ 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 +729,7 @@ 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 +765,21 @@ 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
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index bedc5caceec7..0d261774d6f3 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-$(CONFIG_TRACEPOINTS) += error_report-traces.o
@@ -97,6 +102,8 @@ obj-$(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
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 21dea90eaa93..fe04c6f96ca5 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)
@@ -411,7 +411,7 @@ 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;
@@ -770,19 +770,17 @@ 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);
 		__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... */
@@ -790,9 +788,10 @@ 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)
@@ -1902,7 +1901,6 @@ void blk_fill_rwbs(char *rwbs, unsigned int op)
 
 	switch (op & REQ_OP_MASK) {
 	case REQ_OP_WRITE:
-	case REQ_OP_WRITE_SAME:
 		rwbs[i++] = 'W';
 		break;
 	case REQ_OP_DISCARD:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 21aa30644219..88589d74a892 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -17,6 +17,9 @@
 #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 <net/bpf_sk_storage.h>
 
@@ -77,6 +80,8 @@ 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 +129,10 @@ 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 +340,6 @@ 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;
 
@@ -835,8 +841,6 @@ 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;
 
@@ -1036,6 +1040,30 @@ 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 +1091,21 @@ 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
@@ -1154,6 +1197,8 @@ 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 +1280,8 @@ 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 +1324,13 @@ 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);
 	}
@@ -1562,6 +1613,7 @@ 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 +1705,8 @@ 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 +1715,8 @@ 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 +1738,8 @@ 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)
@@ -2176,3 +2234,362 @@ 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 entry_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, entry_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..aac63ca9c3d1
--- /dev/null
+++ b/kernel/trace/fprobe.c
@@ -0,0 +1,324 @@
+// 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);
+	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.func != fprobe_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 6105b7036482..601ccf1b2f09 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 */
@@ -1568,17 +1567,34 @@ 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;
 }
 
 /**
@@ -2690,18 +2706,16 @@ 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 +2801,7 @@ 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 +2811,7 @@ 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,
@@ -3048,40 +3056,6 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	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;
@@ -3648,6 +3622,105 @@ 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 +3745,13 @@ 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 +4069,24 @@ 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 +4094,12 @@ 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 +4550,7 @@ 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 +4645,8 @@ 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 +4665,13 @@ 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 +4789,9 @@ 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 +4819,13 @@ 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 +5064,12 @@ 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 +5084,29 @@ 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 +5136,8 @@ 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 +5154,10 @@ 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
@@ -5110,11 +5238,16 @@ 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;
 
@@ -5151,8 +5284,6 @@ 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);
@@ -5161,6 +5292,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 	}
 
 	if (ret) {
+		remove_hash_entry(direct_functions, entry);
 		kfree(entry);
 		if (!direct->count) {
 			list_del_rcu(&direct->next);
@@ -5222,6 +5354,10 @@ 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;
@@ -5354,6 +5490,11 @@ 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;
@@ -5634,11 +5775,30 @@ 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 +5819,7 @@ 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);
 }
 
 /**
@@ -6755,6 +6915,13 @@ 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 +6958,16 @@ 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 +7268,8 @@ 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);
 }
 
@@ -7126,15 +7300,19 @@ 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;
-
 	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;
@@ -7193,9 +7371,6 @@ core_initcall(ftrace_nodyn_init);
 static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; }
 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)
 {
 }
@@ -7346,7 +7521,9 @@ 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;
@@ -7833,6 +8010,118 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 }
 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;
+
+	addr = ftrace_location(addr);
+	if (!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;
@@ -7845,7 +8134,7 @@ 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)
 {
@@ -7888,3 +8177,22 @@ 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/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..c69d82273ce7
--- /dev/null
+++ b/kernel/trace/rethook.c
@@ -0,0 +1,326 @@
+// 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)
+		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..d59b6a328b7f 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);
 
 /*
@@ -468,6 +476,7 @@ struct rb_time_struct {
 	local_t		cnt;
 	local_t		top;
 	local_t		bottom;
+	local_t		msb;
 };
 #else
 #include <asm/local64.h>
@@ -569,7 +578,6 @@ 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 +602,7 @@ 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 +622,7 @@ 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 +634,7 @@ 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 +643,8 @@ 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 +660,12 @@ 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 +676,16 @@ 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 +700,8 @@ 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 +717,18 @@ 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 +799,24 @@ 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 +845,10 @@ 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);
@@ -2754,8 +2790,15 @@ 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;
 
@@ -3304,7 +3347,7 @@ 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 +3423,7 @@ 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 +4410,7 @@ 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 +4441,7 @@ 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;
 
@@ -4650,6 +4695,7 @@ 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 +4787,7 @@ 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);
 		}
@@ -6011,10 +6058,10 @@ 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/trace.c b/kernel/trace/trace.c
index eb44418574f9..a8cfac0611bc 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)
 {
@@ -230,6 +231,15 @@ 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)
@@ -711,13 +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;
@@ -743,7 +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;
 	}
 
@@ -1164,7 +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
@@ -1532,6 +1544,7 @@ 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
 };
 
@@ -2825,7 +2838,7 @@ 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)
@@ -2853,14 +2866,14 @@ 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,
@@ -3663,12 +3676,17 @@ 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))
@@ -3854,7 +3872,7 @@ 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;
@@ -4234,7 +4252,7 @@ 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);
@@ -4258,9 +4276,7 @@ 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);
 
@@ -4274,17 +4290,11 @@ 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
@@ -5460,7 +5470,7 @@ 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"
@@ -5469,7 +5479,7 @@ 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"
@@ -6317,12 +6327,18 @@ 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);
 }
 
@@ -6408,9 +6424,7 @@ 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) {
 		ret = tracing_alloc_snapshot_instance(tr);
 		if (ret < 0)
@@ -6439,7 +6453,7 @@ 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;
 
@@ -6453,11 +6467,9 @@ 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;
 
@@ -7725,7 +7737,7 @@ 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;
 };
 
@@ -7733,26 +7745,52 @@ 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;
 
 	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;
 	}
 
 	err = list_first_entry(&tr->err_log, struct tracing_log_err, list);
+	kfree(err->cmd);
+	err->cmd = kzalloc(len, GFP_KERNEL);
+	if (!err->cmd)
+		return ERR_PTR(-ENOMEM);
 	list_del(&err->list);
 
 	return err;
@@ -7813,22 +7851,25 @@ 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;
@@ -7846,7 +7887,7 @@ 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;
@@ -7874,9 +7915,9 @@ 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, ' ');
@@ -9132,6 +9173,7 @@ 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);
 }
@@ -9564,6 +9606,7 @@ 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)
 {
@@ -9589,6 +9632,8 @@ 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 */
@@ -9671,15 +9716,8 @@ 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();
 
@@ -9701,8 +9739,6 @@ 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
@@ -9717,6 +9753,24 @@ 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);
+	}
 
 	return 0;
 }
@@ -10122,6 +10176,14 @@ 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 c5b09c31e077..ff816fb41e48 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1573,13 +1573,12 @@ 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);
@@ -1587,8 +1586,7 @@ 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);
@@ -1629,10 +1627,11 @@ 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
@@ -1686,12 +1685,9 @@ 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);
 };
 
@@ -1877,7 +1873,7 @@ 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
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..076b447a1b88 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -255,19 +255,14 @@ 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 541aa13581b9..7d4478525c66 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -511,20 +511,17 @@ __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 */
@@ -549,7 +546,8 @@ 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;
 }
@@ -650,7 +648,7 @@ 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 eprobe_data *edata;
 
@@ -658,14 +656,16 @@ static int disable_eprobe(struct trace_eprobe *ep,
 	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);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3147614c1812..181f08186d32 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;
@@ -399,7 +407,14 @@ 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 +774,9 @@ 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 +800,9 @@ 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 +1724,9 @@ 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 +1735,12 @@ 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 +1756,6 @@ 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 +2280,8 @@ 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 +2295,13 @@ 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 +2651,76 @@ 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 +2756,7 @@ 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 +2847,7 @@ 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
@@ -2819,6 +2909,7 @@ 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 +2944,7 @@ 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 +2953,14 @@ 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);
 
 	/*
@@ -3446,12 +3546,10 @@ 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 +3564,12 @@ 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 +3784,14 @@ 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..4b1057ab9d96 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1816,7 +1816,7 @@ 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.
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index dc7f733b4cb3..48e82e141d54 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -727,11 +727,16 @@ 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 +744,22 @@ 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 +772,22 @@ 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';
 }
 
@@ -2074,8 +2093,11 @@ 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;
 }
@@ -2766,7 +2788,8 @@ 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,
@@ -4142,7 +4165,7 @@ 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,
@@ -5233,7 +5256,7 @@ 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 +5488,7 @@ 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 +5625,6 @@ 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 +5632,7 @@ 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 +5732,7 @@ 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 +5760,7 @@ 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 +5789,23 @@ 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 +5932,48 @@ 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 +6002,11 @@ 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 +6026,7 @@ 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 +6045,6 @@ static int hist_register_trigger(char *glob,
 
 	if (named_data)
 		destroy_hist_data(hist_data);
-
-	ret++;
  out:
 	return ret;
 }
@@ -6070,20 +6120,19 @@ 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 +6140,11 @@ 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 +6194,57 @@ 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 +6254,24 @@ 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 +6284,15 @@ 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 +6303,7 @@ 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 +6312,11 @@ 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 +6341,15 @@ 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 +6470,7 @@ 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..5e8c07aef071 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -42,10 +42,13 @@ 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 +57,16 @@ 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);
 }
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 7eb9d04f1c2e..cb866c3141af 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -188,7 +188,7 @@ 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;
 }
@@ -432,7 +432,6 @@ 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.
@@ -442,8 +441,7 @@ 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;
@@ -451,7 +449,6 @@ 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.
@@ -460,8 +457,7 @@ 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;
@@ -515,7 +511,7 @@ 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);
 		}
 	}
 }
@@ -581,19 +577,18 @@ 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;
@@ -614,14 +609,13 @@ 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);
@@ -629,8 +623,8 @@ 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);
 }
 
 /*
@@ -744,15 +738,15 @@ 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.
  *
@@ -927,48 +921,37 @@ 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);
 }
 
 /*
@@ -981,7 +964,7 @@ 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.
@@ -994,94 +977,53 @@ 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;
 }
@@ -1401,16 +1343,14 @@ traceoff_count_trigger(struct event_trigger_data *data,
 }
 
 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);
@@ -1521,8 +1461,7 @@ 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);
@@ -1617,8 +1556,7 @@ 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);
@@ -1708,7 +1646,6 @@ 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;
@@ -1733,8 +1670,7 @@ 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;
 
@@ -1781,39 +1717,33 @@ 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);
@@ -1829,32 +1759,24 @@ 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;
@@ -1862,35 +1784,16 @@ 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) {
@@ -1901,32 +1804,23 @@ 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;
 }
 
@@ -1953,19 +1847,18 @@ 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;
@@ -1976,19 +1869,18 @@ 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);
@@ -1996,8 +1888,8 @@ 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..706e1686b5eb
--- /dev/null
+++ b/kernel/trace/trace_events_user.c
@@ -0,0 +1,1628 @@
+// 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/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_EVENTS (MAX_PAGES * PAGE_SIZE)
+
+/* 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
+#define MAX_FIELD_ARG_NAME 256
+
+static char *register_page_data;
+
+static DEFINE_MUTEX(reg_mutex);
+static DEFINE_HASHTABLE(register_table, 4);
+static DECLARE_BITMAP(page_bitmap, MAX_EVENTS);
+
+/*
+ * 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 zero.
+ */
+struct user_event {
+	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;
+	atomic_t refcnt;
+	int index;
+	int flags;
+	int min_size;
+};
+
+/*
+ * 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[];
+};
+
+#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(char *name, char *args, char *flags,
+			    struct user_event **newuser);
+
+static u32 user_event_key(char *name)
+{
+	return jhash(name, strlen(name), 0);
+}
+
+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(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(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") != 0)
+		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[") != 0)
+		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") != 0;
+}
+
+#define LEN_OR_ZERO (len ? len - pos : 0)
+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 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);
+
+	register_page_data[user->index] = 0;
+	clear_bit(user->index, 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(char *name, u32 *outkey)
+{
+	struct user_event *user;
+	u32 key = user_event_key(name);
+
+	*outkey = key;
+
+	hash_for_each_possible(register_table, user, node, key)
+		if (!strcmp(EVENT_NAME(user), name)) {
+			atomic_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();
+	}
+
+	register_page_data[user->index] = 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:
+	atomic_inc(&user->refcnt);
+	update_reg_page_for(user);
+	return 0;
+dec:
+	update_reg_page_for(user);
+	atomic_dec(&user->refcnt);
+	return 0;
+}
+
+static int user_event_create(const char *raw_command)
+{
+	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;
+
+	mutex_lock(&reg_mutex);
+
+	ret = user_event_parse_cmd(name, &user);
+
+	if (!ret)
+		atomic_dec(&user->refcnt);
+
+	mutex_unlock(&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 atomic_read(&user->refcnt) != 0;
+}
+
+static int user_event_free(struct dyn_event *ev)
+{
+	struct user_event *user = container_of(ev, struct user_event, devent);
+
+	if (atomic_read(&user->refcnt) != 0)
+		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, *arg_name;
+	int len, pos, i = *iout;
+	bool colon = false, match = false;
+
+	if (i >= argc)
+		return false;
+
+	len = MAX_FIELD_ARG_NAME;
+	field_name = kmalloc(len, GFP_KERNEL);
+	arg_name = kmalloc(len, GFP_KERNEL);
+
+	if (!arg_name || !field_name)
+		goto out;
+
+	pos = 0;
+
+	for (; i < argc; ++i) {
+		if (i != *iout)
+			pos += snprintf(arg_name + pos, len - pos, " ");
+
+		pos += snprintf(arg_name + pos, len - pos, argv[i]);
+
+		if (strchr(argv[i], ';')) {
+			++i;
+			colon = true;
+			break;
+		}
+	}
+
+	pos = 0;
+
+	pos += snprintf(field_name + pos, len - pos, field->type);
+	pos += snprintf(field_name + pos, len - pos, " ");
+	pos += snprintf(field_name + pos, len - pos, field->name);
+
+	if (colon)
+		pos += snprintf(field_name + pos, len - pos, ";");
+
+	*iout = i;
+
+	match = strcmp(arg_name, field_name) == 0;
+out:
+	kfree(arg_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(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(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(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->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 = USER_EVENTS_SYSTEM;
+	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 ref */
+	atomic_inc(&user->refcnt);
+
+	dyn_event_init(&user->devent, &user_event_dops);
+	dyn_event_add(&user->devent, &user->call);
+	set_bit(user->index, page_bitmap);
+	hash_add(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(char *name)
+{
+	u32 key;
+	int ret;
+	struct user_event *user = find_user_event(name, &key);
+
+	if (!user)
+		return -ENOENT;
+
+	/* Ensure we are the last ref */
+	if (atomic_read(&user->refcnt) != 1) {
+		ret = -EBUSY;
+		goto put_ref;
+	}
+
+	ret = destroy_user_event(user);
+
+	if (ret)
+		goto put_ref;
+
+	return ret;
+put_ref:
+	/* No longer have this ref */
+	atomic_dec(&user->refcnt);
+
+	return ret;
+}
+
+/*
+ * 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_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(file->private_data);
+
+	/*
+	 * 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 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(READ, (char *)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 file *file, struct user_event *user)
+{
+	struct user_event_refs *refs, *new_refs;
+	int i, size, count = 0;
+
+	refs = rcu_dereference_protected(file->private_data,
+					 lockdep_is_held(&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;
+
+	atomic_inc(&user->refcnt);
+
+	rcu_assign_pointer(file->private_data, 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;
+
+	return copy_struct_from_user(kreg, sizeof(*kreg), ureg, size);
+}
+
+/*
+ * Registers a user_event on behalf of a user process.
+ */
+static long user_events_ioctl_reg(struct file *file, 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(name, &user);
+
+	if (ret) {
+		kfree(name);
+		return ret;
+	}
+
+	ret = user_events_ref_add(file, user);
+
+	/* No longer need parse ref, ref_add either worked or not */
+	atomic_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_index);
+
+	return 0;
+}
+
+/*
+ * Deletes a user_event on behalf of a user process.
+ */
+static long user_events_ioctl_del(struct file *file, 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(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)
+{
+	long ret = -ENOTTY;
+
+	switch (cmd) {
+	case DIAG_IOCSREG:
+		mutex_lock(&reg_mutex);
+		ret = user_events_ioctl_reg(file, uarg);
+		mutex_unlock(&reg_mutex);
+		break;
+
+	case DIAG_IOCSDEL:
+		mutex_lock(&reg_mutex);
+		ret = user_events_ioctl_del(file, uarg);
+		mutex_unlock(&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_refs *refs;
+	struct user_event *user;
+	int i;
+
+	/*
+	 * Ensure refs cannot change under any situation by taking the
+	 * register mutex during the final freeing of the references.
+	 */
+	mutex_lock(&reg_mutex);
+
+	refs = file->private_data;
+
+	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)
+			atomic_dec(&user->refcnt);
+	}
+out:
+	file->private_data = NULL;
+
+	mutex_unlock(&reg_mutex);
+
+	kfree(refs);
+
+	return 0;
+}
+
+static const struct file_operations user_data_fops = {
+	.write = user_events_write,
+	.write_iter = user_events_write_iter,
+	.unlocked_ioctl	= user_events_ioctl,
+	.release = user_events_release,
+};
+
+/*
+ * 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)
+{
+	unsigned long size = vma->vm_end - vma->vm_start;
+
+	if (size != MAX_EVENTS)
+		return -EINVAL;
+
+	return remap_pfn_range(vma, vma->vm_start,
+			       virt_to_phys(register_page_data) >> 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 *user;
+	char status;
+	int i, active = 0, busy = 0, flags;
+
+	mutex_lock(&reg_mutex);
+
+	hash_for_each(register_table, i, user, node) {
+		status = register_page_data[user->index];
+		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(&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)
+{
+	return seq_open(file, &user_seq_ops);
+}
+
+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 void set_page_reservations(bool set)
+{
+	int page;
+
+	for (page = 0; page < MAX_PAGES; ++page) {
+		void *addr = register_page_data + (PAGE_SIZE * page);
+
+		if (set)
+			SetPageReserved(virt_to_page(addr));
+		else
+			ClearPageReserved(virt_to_page(addr));
+	}
+}
+
+static int __init trace_events_user_init(void)
+{
+	struct page *pages;
+	int ret;
+
+	/* Zero all bits beside 0 (which is reserved for failures) */
+	bitmap_zero(page_bitmap, MAX_EVENTS);
+	set_bit(0, page_bitmap);
+
+	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, MAX_PAGE_ORDER);
+	if (!pages)
+		return -ENOMEM;
+	register_page_data = page_address(pages);
+
+	set_page_reservations(true);
+
+	ret = create_user_tracefs();
+
+	if (ret) {
+		pr_warn("user_events could not register with tracefs\n");
+		set_page_reservations(false);
+		__free_pages(pages, MAX_PAGE_ORDER);
+		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 b62fd785b599..a245ea673715 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1433,7 +1433,7 @@ __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 +1628,7 @@ 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 +1718,17 @@ 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 +1916,18 @@ 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 5e3c62a08fc0..313439920a8c 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -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();
 
@@ -1576,11 +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);
 
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..95b58bd757ce 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);
@@ -94,7 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	lockdep_hardirqs_on_prepare();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
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 abcadbe933bb..a2d301f58ced 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -895,6 +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..b69e207012c9 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 */
@@ -296,9 +296,7 @@ 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 +319,16 @@ 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 +337,7 @@ 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 +356,15 @@ 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..c3dc4f859a6b 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -546,7 +546,6 @@ static int __trace_uprobe_create(int argc, const char **argv)
 	bool is_return = false;
 	int i, ret;
 
-	ret = 0;
 	ref_ctr_offset = 0;
 
 	switch (argv[0][0]) {
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9628b5571846..9901708ce6b8 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -1045,7 +1045,8 @@ 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