Merge tag 'v5.17-rc4' into for-linus

Merge with mainline to get the Intel ASoC generic helpers header and
other changes.

36 files changed, 3116 insertions, 880 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 420ff4bc67fd..a5eb5e7fd624 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -70,6 +70,19 @@ config HAVE_C_RECORDMCOUNT
 	help
 	  C version of recordmcount available?
 
+config HAVE_BUILDTIME_MCOUNT_SORT
+       bool
+       help
+         An architecture selects this if it sorts the mcount_loc section
+	 at build time.
+
+config BUILDTIME_MCOUNT_SORT
+       bool
+       default y
+       depends on HAVE_BUILDTIME_MCOUNT_SORT && DYNAMIC_FTRACE
+       help
+         Sort the mcount_loc section at build time.
+
 config TRACER_MAX_TRACE
 	bool
 
@@ -915,6 +928,20 @@ config EVENT_TRACE_TEST_SYSCALLS
 	 TBD - enable a way to actually call the syscalls as we test their
 	       events
 
+config FTRACE_SORT_STARTUP_TEST
+       bool "Verify compile time sorting of ftrace functions"
+       depends on DYNAMIC_FTRACE
+       depends on BUILDTIME_MCOUNT_SORT
+       help
+	 Sorting of the mcount_loc sections that is used to find the
+	 where the ftrace knows where to patch functions for tracing
+	 and other callbacks is done at compile time. But if the sort
+	 is not done correctly, it will cause non-deterministic failures.
+	 When this is set, the sorted sections will be verified that they
+	 are in deed sorted and will warn if they are not.
+
+	 If unsure, say N
+
 config RING_BUFFER_STARTUP_TEST
        bool "Ring buffer startup self test"
        depends on RING_BUFFER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 6de5d4d63165..bedc5caceec7 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -47,6 +47,7 @@ obj-$(CONFIG_TRACING) += trace_output.o
 obj-$(CONFIG_TRACING) += trace_seq.o
 obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_TRACING) += trace_printk.o
+obj-$(CONFIG_TRACING) += 	pid_list.o
 obj-$(CONFIG_TRACING_MAP) += tracing_map.o
 obj-$(CONFIG_PREEMPTIRQ_DELAY_TEST) += preemptirq_delay_test.o
 obj-$(CONFIG_SYNTH_EVENT_GEN_TEST) += synth_event_gen_test.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index fa91f398f28b..af68a67179b4 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -34,7 +34,7 @@ static struct trace_array *blk_tr;
 static bool blk_tracer_enabled __read_mostly;
 
 static LIST_HEAD(running_trace_list);
-static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock);
+static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(running_trace_lock);
 
 /* Select an alternative, minimalistic output than the original one */
 #define TRACE_BLK_OPT_CLASSIC	0x1
@@ -121,12 +121,12 @@ static void trace_note_tsk(struct task_struct *tsk)
 	struct blk_trace *bt;
 
 	tsk->btrace_seq = blktrace_seq;
-	spin_lock_irqsave(&running_trace_lock, flags);
+	raw_spin_lock_irqsave(&running_trace_lock, flags);
 	list_for_each_entry(bt, &running_trace_list, running_list) {
 		trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm,
 			   sizeof(tsk->comm), 0);
 	}
-	spin_unlock_irqrestore(&running_trace_lock, flags);
+	raw_spin_unlock_irqrestore(&running_trace_lock, flags);
 }
 
 static void trace_note_time(struct blk_trace *bt)
@@ -666,9 +666,9 @@ static int __blk_trace_startstop(struct request_queue *q, int start)
 			blktrace_seq++;
 			smp_mb();
 			bt->trace_state = Blktrace_running;
-			spin_lock_irq(&running_trace_lock);
+			raw_spin_lock_irq(&running_trace_lock);
 			list_add(&bt->running_list, &running_trace_list);
-			spin_unlock_irq(&running_trace_lock);
+			raw_spin_unlock_irq(&running_trace_lock);
 
 			trace_note_time(bt);
 			ret = 0;
@@ -676,9 +676,9 @@ static int __blk_trace_startstop(struct request_queue *q, int start)
 	} else {
 		if (bt->trace_state == Blktrace_running) {
 			bt->trace_state = Blktrace_stopped;
-			spin_lock_irq(&running_trace_lock);
+			raw_spin_lock_irq(&running_trace_lock);
 			list_del_init(&bt->running_list);
-			spin_unlock_irq(&running_trace_lock);
+			raw_spin_unlock_irq(&running_trace_lock);
 			relay_flush(bt->rchan);
 			ret = 0;
 		}
@@ -816,7 +816,7 @@ blk_trace_request_get_cgid(struct request *rq)
  *     Records an action against a request. Will log the bio offset + size.
  *
  **/
-static void blk_add_trace_rq(struct request *rq, int error,
+static void blk_add_trace_rq(struct request *rq, blk_status_t error,
 			     unsigned int nr_bytes, u32 what, u64 cgid)
 {
 	struct blk_trace *bt;
@@ -834,7 +834,8 @@ static void blk_add_trace_rq(struct request *rq, int error,
 		what |= BLK_TC_ACT(BLK_TC_FS);
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
-			rq->cmd_flags, what, error, 0, NULL, cgid);
+			rq->cmd_flags, what, blk_status_to_errno(error), 0,
+			NULL, cgid);
 	rcu_read_unlock();
 }
 
@@ -863,7 +864,7 @@ static void blk_add_trace_rq_requeue(void *ignore, struct request *rq)
 }
 
 static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
-			int error, unsigned int nr_bytes)
+			blk_status_t error, unsigned int nr_bytes)
 {
 	blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE,
 			 blk_trace_request_get_cgid(rq));
@@ -1044,7 +1045,7 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev,
 	}
 
 	r.device_from = cpu_to_be32(dev);
-	r.device_to   = cpu_to_be32(disk_devt(rq->rq_disk));
+	r.device_to   = cpu_to_be32(disk_devt(rq->q->disk));
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
@@ -1607,9 +1608,9 @@ static int blk_trace_remove_queue(struct request_queue *q)
 
 	if (bt->trace_state == Blktrace_running) {
 		bt->trace_state = Blktrace_stopped;
-		spin_lock_irq(&running_trace_lock);
+		raw_spin_lock_irq(&running_trace_lock);
 		list_del_init(&bt->running_list);
-		spin_unlock_irq(&running_trace_lock);
+		raw_spin_unlock_irq(&running_trace_lock);
 		relay_flush(bt->rchan);
 	}
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 8e2eb950aa82..21aa30644219 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -345,7 +345,7 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = {
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE,
 };
 
@@ -394,11 +394,11 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
 	.func		= bpf_trace_printk,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 };
 
-const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
+static void __set_printk_clr_event(void)
 {
 	/*
 	 * This program might be calling bpf_trace_printk,
@@ -410,11 +410,57 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	 */
 	if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1))
 		pr_warn_ratelimited("could not enable bpf_trace_printk events");
+}
 
+const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
+{
+	__set_printk_clr_event();
 	return &bpf_trace_printk_proto;
 }
 
-#define MAX_SEQ_PRINTF_VARARGS		12
+BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data,
+	   u32, data_len)
+{
+	static char buf[BPF_TRACE_PRINTK_SIZE];
+	unsigned long flags;
+	int ret, num_args;
+	u32 *bin_args;
+
+	if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 ||
+	    (data_len && !data))
+		return -EINVAL;
+	num_args = data_len / 8;
+
+	ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args);
+	if (ret < 0)
+		return ret;
+
+	raw_spin_lock_irqsave(&trace_printk_lock, flags);
+	ret = bstr_printf(buf, sizeof(buf), fmt, bin_args);
+
+	trace_bpf_trace_printk(buf);
+	raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+
+	bpf_bprintf_cleanup();
+
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_trace_vprintk_proto = {
+	.func		= bpf_trace_vprintk,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
+	.arg4_type	= ARG_CONST_SIZE_OR_ZERO,
+};
+
+const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void)
+{
+	__set_printk_clr_event();
+	return &bpf_trace_vprintk_proto;
+}
 
 BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 	   const void *, data, u32, data_len)
@@ -422,7 +468,7 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 	int err, num_args;
 	u32 *bin_args;
 
-	if (data_len & 7 || data_len > MAX_SEQ_PRINTF_VARARGS * 8 ||
+	if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 ||
 	    (data_len && !data))
 		return -EINVAL;
 	num_args = data_len / 8;
@@ -446,9 +492,9 @@ static const struct bpf_func_proto bpf_seq_printf_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
 	.arg1_btf_id	= &btf_seq_file_ids[0],
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE,
-	.arg4_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg4_type      = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
 	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
 };
 
@@ -463,7 +509,7 @@ static const struct bpf_func_proto bpf_seq_write_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
 	.arg1_btf_id	= &btf_seq_file_ids[0],
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
@@ -487,7 +533,7 @@ static const struct bpf_func_proto bpf_seq_printf_btf_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
 	.arg1_btf_id	= &btf_seq_file_ids[0],
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 };
@@ -648,7 +694,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
@@ -718,7 +764,7 @@ const struct bpf_func_proto bpf_get_current_task_btf_proto = {
 	.func		= bpf_get_current_task_btf,
 	.gpl_only	= true,
 	.ret_type	= RET_PTR_TO_BTF_ID,
-	.ret_btf_id	= &btf_task_struct_ids[0],
+	.ret_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 };
 
 BPF_CALL_1(bpf_task_pt_regs, struct task_struct *, task)
@@ -733,7 +779,7 @@ const struct bpf_func_proto bpf_task_pt_regs_proto = {
 	.func		= bpf_task_pt_regs,
 	.gpl_only	= true,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id	= &btf_task_struct_ids[0],
+	.arg1_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 	.ret_type	= RET_PTR_TO_BTF_ID,
 	.ret_btf_id	= &bpf_task_pt_regs_ids[0],
 };
@@ -958,7 +1004,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_MEM,
 	.arg2_type	= ARG_CONST_SIZE,
-	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg4_type	= ARG_CONST_SIZE,
 	.arg5_type	= ARG_ANYTHING,
 };
@@ -966,7 +1012,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
 BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx)
 {
 	/* This helper call is inlined by verifier. */
-	return ((u64 *)ctx)[-1];
+	return ((u64 *)ctx)[-2];
 }
 
 static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = {
@@ -1017,6 +1063,81 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags)
+{
+#ifndef CONFIG_X86
+	return -ENOENT;
+#else
+	static const u32 br_entry_size = sizeof(struct perf_branch_entry);
+	u32 entry_cnt = size / br_entry_size;
+
+	entry_cnt = static_call(perf_snapshot_branch_stack)(buf, entry_cnt);
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	if (!entry_cnt)
+		return -ENOENT;
+
+	return entry_cnt * br_entry_size;
+#endif
+}
+
+static const struct bpf_func_proto bpf_get_branch_snapshot_proto = {
+	.func		= bpf_get_branch_snapshot,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+};
+
+BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value)
+{
+	/* This helper call is inlined by verifier. */
+	u64 nr_args = ((u64 *)ctx)[-1];
+
+	if ((u64) n >= nr_args)
+		return -EINVAL;
+	*value = ((u64 *)ctx)[n];
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_get_func_arg_proto = {
+	.func		= get_func_arg,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value)
+{
+	/* This helper call is inlined by verifier. */
+	u64 nr_args = ((u64 *)ctx)[-1];
+
+	*value = ((u64 *)ctx)[nr_args];
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_get_func_ret_proto = {
+	.func		= get_func_ret,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_1(get_func_arg_cnt, void *, ctx)
+{
+	/* This helper call is inlined by verifier. */
+	return ((u64 *)ctx)[-1];
+}
+
+static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = {
+	.func		= get_func_arg_cnt,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 static const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1037,8 +1158,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
-	case BPF_FUNC_ktime_get_coarse_ns:
-		return &bpf_ktime_get_coarse_ns_proto;
 	case BPF_FUNC_tail_call:
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_get_current_pid_tgid:
@@ -1132,6 +1251,12 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_snprintf_proto;
 	case BPF_FUNC_get_func_ip:
 		return &bpf_get_func_ip_proto_tracing;
+	case BPF_FUNC_get_branch_snapshot:
+		return &bpf_get_branch_snapshot_proto;
+	case BPF_FUNC_find_vma:
+		return &bpf_find_vma_proto;
+	case BPF_FUNC_trace_vprintk:
+		return bpf_get_trace_vprintk_proto();
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -1209,7 +1334,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
@@ -1324,9 +1449,6 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
 BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
 	   void *, buf, u32, size, u64, flags)
 {
-#ifndef CONFIG_X86
-	return -ENOENT;
-#else
 	static const u32 br_entry_size = sizeof(struct perf_branch_entry);
 	struct perf_branch_stack *br_stack = ctx->data->br_stack;
 	u32 to_copy;
@@ -1335,7 +1457,7 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
 		return -EINVAL;
 
 	if (unlikely(!br_stack))
-		return -EINVAL;
+		return -ENOENT;
 
 	if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE)
 		return br_stack->nr * br_entry_size;
@@ -1347,7 +1469,6 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
 	memcpy(buf, br_stack->entries, to_copy);
 
 	return to_copy;
-#endif
 }
 
 static const struct bpf_func_proto bpf_read_branch_records_proto = {
@@ -1435,7 +1556,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
@@ -1489,7 +1610,7 @@ static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 };
@@ -1530,6 +1651,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_to_tcp_request_sock_proto;
 	case BPF_FUNC_skc_to_udp6_sock:
 		return &bpf_skc_to_udp6_sock_proto;
+	case BPF_FUNC_skc_to_unix_sock:
+		return &bpf_skc_to_unix_sock_proto;
 	case BPF_FUNC_sk_storage_get:
 		return &bpf_sk_storage_get_tracing_proto;
 	case BPF_FUNC_sk_storage_delete:
@@ -1553,6 +1676,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		       NULL;
 	case BPF_FUNC_d_path:
 		return &bpf_d_path_proto;
+	case BPF_FUNC_get_func_arg:
+		return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL;
+	case BPF_FUNC_get_func_ret:
+		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;
 	default:
 		fn = raw_tp_prog_func_proto(func_id, prog);
 		if (!fn && prog->expected_attach_type == BPF_TRACE_ITER)
@@ -1566,13 +1695,7 @@ static bool raw_tp_prog_is_valid_access(int off, int size,
 					const struct bpf_prog *prog,
 					struct bpf_insn_access_aux *info)
 {
-	if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
-		return false;
-	if (type != BPF_READ)
-		return false;
-	if (off % size != 0)
-		return false;
-	return true;
+	return bpf_tracing_ctx_access(off, size, type);
 }
 
 static bool tracing_prog_is_valid_access(int off, int size,
@@ -1580,13 +1703,7 @@ static bool tracing_prog_is_valid_access(int off, int size,
 					 const struct bpf_prog *prog,
 					 struct bpf_insn_access_aux *info)
 {
-	if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
-		return false;
-	if (type != BPF_READ)
-		return false;
-	if (off % size != 0)
-		return false;
-	return btf_ctx_access(off, size, type, prog, info);
+	return bpf_tracing_btf_ctx_access(off, size, type, prog, info);
 }
 
 int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog,
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index b8a0d1d564fb..22061d38fc00 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -115,6 +115,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 {
 	struct ftrace_graph_ent trace;
 
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	/*
 	 * Skip graph tracing if the return location is served by direct trampoline,
 	 * since call sequence and return addresses are unpredictable anyway.
@@ -124,6 +125,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	if (ftrace_direct_func_count &&
 	    ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE))
 		return -EBUSY;
+#endif
 	trace.func = func;
 	trace.depth = ++current->curr_ret_depth;
 
@@ -333,10 +335,10 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 #endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */
 
 static struct ftrace_ops graph_ops = {
-	.func			= ftrace_stub,
+	.func			= ftrace_graph_func,
 	.flags			= FTRACE_OPS_FL_INITIALIZED |
 				   FTRACE_OPS_FL_PID |
-				   FTRACE_OPS_FL_STUB,
+				   FTRACE_OPS_GRAPH_STUB,
 #ifdef FTRACE_GRAPH_TRAMP_ADDR
 	.trampoline		= FTRACE_GRAPH_TRAMP_ADDR,
 	/* trampoline_size is only needed for dynamically allocated tramps */
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index feebf57c6458..f9feb197b2da 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -119,14 +119,9 @@ 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;
 
-#if ARCH_SUPPORTS_FTRACE_OPS
-static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op, struct ftrace_regs *fregs);
-#else
-/* See comment below, where ftrace_ops_list_func is defined */
-static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
-#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
-#endif
+/* Defined by vmlinux.lds.h see the commment 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);
 
 static inline void ftrace_ops_init(struct ftrace_ops *ops)
 {
@@ -323,7 +318,7 @@ int __register_ftrace_function(struct ftrace_ops *ops)
 	if (!ftrace_enabled && (ops->flags & FTRACE_OPS_FL_PERMANENT))
 		return -EBUSY;
 
-	if (!core_kernel_data((unsigned long)ops))
+	if (!is_kernel_core_data((unsigned long)ops))
 		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
 
 	add_ftrace_ops(&ftrace_ops_list, ops);
@@ -581,7 +576,7 @@ static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
 	       FTRACE_PROFILE_HASH_SIZE * sizeof(struct hlist_head));
 }
 
-int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
+static int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
 {
 	struct ftrace_profile_page *pg;
 	int functions;
@@ -988,8 +983,9 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
 		}
 	}
 
-	entry = tracefs_create_file("function_profile_enabled", 0644,
-				    d_tracer, NULL, &ftrace_profile_fops);
+	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");
 }
@@ -2394,6 +2390,39 @@ unsigned long ftrace_find_rec_direct(unsigned long ip)
 	return entry->direct;
 }
 
+static struct ftrace_func_entry*
+ftrace_add_rec_direct(unsigned long ip, unsigned long addr,
+		      struct ftrace_hash **free_hash)
+{
+	struct ftrace_func_entry *entry;
+
+	if (ftrace_hash_empty(direct_functions) ||
+	    direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
+		struct ftrace_hash *new_hash;
+		int size = ftrace_hash_empty(direct_functions) ? 0 :
+			direct_functions->count + 1;
+
+		if (size < 32)
+			size = 32;
+
+		new_hash = dup_hash(direct_functions, size);
+		if (!new_hash)
+			return NULL;
+
+		*free_hash = direct_functions;
+		direct_functions = new_hash;
+	}
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return NULL;
+
+	entry->ip = ip;
+	entry->direct = addr;
+	__add_hash_entry(direct_functions, entry);
+	return entry;
+}
+
 static void call_direct_funcs(unsigned long ip, unsigned long pip,
 			      struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
@@ -5110,39 +5139,16 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 	}
 
 	ret = -ENOMEM;
-	if (ftrace_hash_empty(direct_functions) ||
-	    direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
-		struct ftrace_hash *new_hash;
-		int size = ftrace_hash_empty(direct_functions) ? 0 :
-			direct_functions->count + 1;
-
-		if (size < 32)
-			size = 32;
-
-		new_hash = dup_hash(direct_functions, size);
-		if (!new_hash)
-			goto out_unlock;
-
-		free_hash = direct_functions;
-		direct_functions = new_hash;
-	}
-
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		goto out_unlock;
-
 	direct = ftrace_find_direct_func(addr);
 	if (!direct) {
 		direct = ftrace_alloc_direct_func(addr);
-		if (!direct) {
-			kfree(entry);
+		if (!direct)
 			goto out_unlock;
-		}
 	}
 
-	entry->ip = ip;
-	entry->direct = addr;
-	__add_hash_entry(direct_functions, entry);
+	entry = ftrace_add_rec_direct(ip, addr, &free_hash);
+	if (!entry)
+		goto out_unlock;
 
 	ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0);
 	if (ret)
@@ -5211,6 +5217,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 {
 	struct ftrace_direct_func *direct;
 	struct ftrace_func_entry *entry;
+	struct ftrace_hash *hash;
 	int ret = -ENODEV;
 
 	mutex_lock(&direct_mutex);
@@ -5219,7 +5226,8 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 	if (!entry)
 		goto out_unlock;
 
-	if (direct_functions->count == 1)
+	hash = direct_ops.func_hash->filter_hash;
+	if (hash->count == 1)
 		unregister_ftrace_function(&direct_ops);
 
 	ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0);
@@ -5395,6 +5403,221 @@ int modify_ftrace_direct(unsigned long ip,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(modify_ftrace_direct);
+
+#define MULTI_FLAGS (FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_DIRECT | \
+		     FTRACE_OPS_FL_SAVE_REGS)
+
+static int check_direct_multi(struct ftrace_ops *ops)
+{
+	if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED))
+		return -EINVAL;
+	if ((ops->flags & MULTI_FLAGS) != MULTI_FLAGS)
+		return -EINVAL;
+	return 0;
+}
+
+static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long addr)
+{
+	struct ftrace_func_entry *entry, *del;
+	int size, i;
+
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			del = __ftrace_lookup_ip(direct_functions, entry->ip);
+			if (del && del->direct == addr) {
+				remove_hash_entry(direct_functions, del);
+				kfree(del);
+			}
+		}
+	}
+}
+
+/**
+ * register_ftrace_direct_multi - Call a custom trampoline directly
+ * for multiple functions registered in @ops
+ * @ops: The address of the struct ftrace_ops object
+ * @addr: The address of the trampoline to call at @ops functions
+ *
+ * This is used to connect a direct calls to @addr from the nop locations
+ * of the functions registered in @ops (with by ftrace_set_filter_ip
+ * function).
+ *
+ * The location that it calls (@addr) must be able to handle a direct call,
+ * and save the parameters of the function being traced, and restore them
+ * (or inject new ones if needed), before returning.
+ *
+ * Returns:
+ *  0 on success
+ *  -EINVAL  - The @ops object was already registered with this call or
+ *             when there are no functions in @ops object.
+ *  -EBUSY   - Another direct function is already attached (there can be only one)
+ *  -ENODEV  - @ip does not point to a ftrace nop location (or not supported)
+ *  -ENOMEM  - There was an allocation failure.
+ */
+int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	struct ftrace_hash *hash, *free_hash = NULL;
+	struct ftrace_func_entry *entry, *new;
+	int err = -EBUSY, size, i;
+
+	if (ops->func || ops->trampoline)
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED))
+		return -EINVAL;
+	if (ops->flags & FTRACE_OPS_FL_ENABLED)
+		return -EINVAL;
+
+	hash = ops->func_hash->filter_hash;
+	if (ftrace_hash_empty(hash))
+		return -EINVAL;
+
+	mutex_lock(&direct_mutex);
+
+	/* Make sure requested entries are not already registered.. */
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			if (ftrace_find_rec_direct(entry->ip))
+				goto out_unlock;
+		}
+	}
+
+	/* ... and insert them to direct_functions hash. */
+	err = -ENOMEM;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			new = ftrace_add_rec_direct(entry->ip, addr, &free_hash);
+			if (!new)
+				goto out_remove;
+			entry->direct = addr;
+		}
+	}
+
+	ops->func = call_direct_funcs;
+	ops->flags = MULTI_FLAGS;
+	ops->trampoline = FTRACE_REGS_ADDR;
+
+	err = register_ftrace_function(ops);
+
+ out_remove:
+	if (err)
+		remove_direct_functions_hash(hash, addr);
+
+ out_unlock:
+	mutex_unlock(&direct_mutex);
+
+	if (free_hash) {
+		synchronize_rcu_tasks();
+		free_ftrace_hash(free_hash);
+	}
+	return err;
+}
+EXPORT_SYMBOL_GPL(register_ftrace_direct_multi);
+
+/**
+ * unregister_ftrace_direct_multi - Remove calls to custom trampoline
+ * previously registered by register_ftrace_direct_multi for @ops object.
+ * @ops: The address of the struct ftrace_ops object
+ *
+ * This is used to remove a direct calls to @addr from the nop locations
+ * of the functions registered in @ops (with by ftrace_set_filter_ip
+ * function).
+ *
+ * Returns:
+ *  0 on success
+ *  -EINVAL - The @ops object was not properly registered.
+ */
+int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	struct ftrace_hash *hash = ops->func_hash->filter_hash;
+	int err;
+
+	if (check_direct_multi(ops))
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return -EINVAL;
+
+	mutex_lock(&direct_mutex);
+	err = unregister_ftrace_function(ops);
+	remove_direct_functions_hash(hash, addr);
+	mutex_unlock(&direct_mutex);
+
+	/* cleanup for possible another register call */
+	ops->func = NULL;
+	ops->trampoline = 0;
+	return err;
+}
+EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
+
+/**
+ * modify_ftrace_direct_multi - Modify an existing direct 'multi' call
+ * to call something else
+ * @ops: The address of the struct ftrace_ops object
+ * @addr: The address of the new trampoline to call at @ops functions
+ *
+ * This is used to unregister currently registered direct caller and
+ * register new one @addr on functions registered in @ops object.
+ *
+ * Note there's window between ftrace_shutdown and ftrace_startup calls
+ * where there will be no callbacks called.
+ *
+ * Returns: zero on success. Non zero on error, which includes:
+ *  -EINVAL - The @ops object was not properly registered.
+ */
+int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	struct ftrace_hash *hash;
+	struct ftrace_func_entry *entry, *iter;
+	static struct ftrace_ops tmp_ops = {
+		.func		= ftrace_stub,
+		.flags		= FTRACE_OPS_FL_STUB,
+	};
+	int i, size;
+	int err;
+
+	if (check_direct_multi(ops))
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return -EINVAL;
+
+	mutex_lock(&direct_mutex);
+
+	/* Enable the tmp_ops to have the same functions as the direct ops */
+	ftrace_ops_init(&tmp_ops);
+	tmp_ops.func_hash = ops->func_hash;
+
+	err = register_ftrace_function(&tmp_ops);
+	if (err)
+		goto out_direct;
+
+	/*
+	 * Now the ftrace_ops_list_func() is called to do the direct callers.
+	 * We can safely change the direct functions attached to each entry.
+	 */
+	mutex_lock(&ftrace_lock);
+
+	hash = ops->func_hash->filter_hash;
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(iter, &hash->buckets[i], hlist) {
+			entry = __ftrace_lookup_ip(direct_functions, iter->ip);
+			if (!entry)
+				continue;
+			entry->direct = addr;
+		}
+	}
+
+	mutex_unlock(&ftrace_lock);
+
+	/* Removing the tmp_ops will add the updated direct callers to the functions */
+	unregister_ftrace_function(&tmp_ops);
+
+ out_direct:
+	mutex_unlock(&direct_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi);
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 /**
@@ -6109,10 +6332,10 @@ void ftrace_create_filter_files(struct ftrace_ops *ops,
 				struct dentry *parent)
 {
 
-	trace_create_file("set_ftrace_filter", 0644, parent,
+	trace_create_file("set_ftrace_filter", TRACE_MODE_WRITE, parent,
 			  ops, &ftrace_filter_fops);
 
-	trace_create_file("set_ftrace_notrace", 0644, parent,
+	trace_create_file("set_ftrace_notrace", TRACE_MODE_WRITE, parent,
 			  ops, &ftrace_notrace_fops);
 }
 
@@ -6139,19 +6362,19 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops)
 static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer)
 {
 
-	trace_create_file("available_filter_functions", 0444,
+	trace_create_file("available_filter_functions", TRACE_MODE_READ,
 			d_tracer, NULL, &ftrace_avail_fops);
 
-	trace_create_file("enabled_functions", 0444,
+	trace_create_file("enabled_functions", TRACE_MODE_READ,
 			d_tracer, NULL, &ftrace_enabled_fops);
 
 	ftrace_create_filter_files(&global_ops, d_tracer);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	trace_create_file("set_graph_function", 0644, d_tracer,
+	trace_create_file("set_graph_function", TRACE_MODE_WRITE, d_tracer,
 				    NULL,
 				    &ftrace_graph_fops);
-	trace_create_file("set_graph_notrace", 0644, d_tracer,
+	trace_create_file("set_graph_notrace", TRACE_MODE_WRITE, d_tracer,
 				    NULL,
 				    &ftrace_graph_notrace_fops);
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -6171,6 +6394,27 @@ static int ftrace_cmp_ips(const void *a, const void *b)
 	return 0;
 }
 
+#ifdef CONFIG_FTRACE_SORT_STARTUP_TEST
+static void test_is_sorted(unsigned long *start, unsigned long count)
+{
+	int i;
+
+	for (i = 1; i < count; i++) {
+		if (WARN(start[i - 1] > start[i],
+			 "[%d] %pS at %lx is not sorted with %pS at %lx\n", i,
+			 (void *)start[i - 1], start[i - 1],
+			 (void *)start[i], start[i]))
+			break;
+	}
+	if (i == count)
+		pr_info("ftrace section at %px sorted properly\n", start);
+}
+#else
+static void test_is_sorted(unsigned long *start, unsigned long count)
+{
+}
+#endif
+
 static int ftrace_process_locs(struct module *mod,
 			       unsigned long *start,
 			       unsigned long *end)
@@ -6189,8 +6433,17 @@ static int ftrace_process_locs(struct module *mod,
 	if (!count)
 		return 0;
 
-	sort(start, count, sizeof(*start),
-	     ftrace_cmp_ips, NULL);
+	/*
+	 * Sorting mcount in vmlinux at build time depend on
+	 * CONFIG_BUILDTIME_MCOUNT_SORT, while mcount loc in
+	 * modules can not be sorted at build time.
+	 */
+	if (!IS_ENABLED(CONFIG_BUILDTIME_MCOUNT_SORT) || mod) {
+		sort(start, count, sizeof(*start),
+		     ftrace_cmp_ips, NULL);
+	} else {
+		test_is_sorted(start, count);
+	}
 
 	start_pg = ftrace_allocate_pages(count);
 	if (!start_pg)
@@ -6846,6 +7099,11 @@ void __init ftrace_free_init_mem(void)
 	ftrace_free_mem(NULL, start, end);
 }
 
+int __init __weak ftrace_dyn_arch_init(void)
+{
+	return 0;
+}
+
 void __init ftrace_init(void)
 {
 	extern unsigned long __start_mcount_loc[];
@@ -6977,16 +7235,15 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 	struct ftrace_ops *op;
 	int bit;
 
+	/*
+	 * The ftrace_test_and_set_recursion() will disable preemption,
+	 * which is required since some of the ops may be dynamically
+	 * allocated, they must be freed after a synchronize_rcu().
+	 */
 	bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START);
 	if (bit < 0)
 		return;
 
-	/*
-	 * Some of the ops may be dynamically allocated,
-	 * they must be freed after a synchronize_rcu().
-	 */
-	preempt_disable_notrace();
-
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
 		/* Stub functions don't need to be called nor tested */
 		if (op->flags & FTRACE_OPS_FL_STUB)
@@ -7010,7 +7267,6 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 		}
 	} while_for_each_ftrace_op(op);
 out:
-	preempt_enable_notrace();
 	trace_clear_recursion(bit);
 }
 
@@ -7026,21 +7282,23 @@ out:
  * Note, CONFIG_DYNAMIC_FTRACE_WITH_REGS expects a full regs to be saved.
  * An architecture can pass partial regs with ftrace_ops and still
  * set the ARCH_SUPPORTS_FTRACE_OPS.
+ *
+ * In vmlinux.lds.h, ftrace_ops_list_func() is defined to be
+ * arch_ftrace_ops_list_func.
  */
 #if ARCH_SUPPORTS_FTRACE_OPS
-static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op, struct ftrace_regs *fregs)
+void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+			       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, fregs);
 }
-NOKPROBE_SYMBOL(ftrace_ops_list_func);
 #else
-static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
+void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
 }
-NOKPROBE_SYMBOL(ftrace_ops_no_ops);
 #endif
+NOKPROBE_SYMBOL(arch_ftrace_ops_list_func);
 
 /*
  * If there's only one function registered but it does not support
@@ -7056,12 +7314,9 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 	if (bit < 0)
 		return;
 
-	preempt_disable_notrace();
-
 	if (!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching())
 		op->func(ip, parent_ip, op, fregs);
 
-	preempt_enable_notrace();
 	trace_clear_recursion(bit);
 }
 NOKPROBE_SYMBOL(ftrace_ops_assist_func);
@@ -7184,10 +7439,10 @@ static void clear_ftrace_pids(struct trace_array *tr, int type)
 	synchronize_rcu();
 
 	if ((type & TRACE_PIDS) && pid_list)
-		trace_free_pid_list(pid_list);
+		trace_pid_list_free(pid_list);
 
 	if ((type & TRACE_NO_PIDS) && no_pid_list)
-		trace_free_pid_list(no_pid_list);
+		trace_pid_list_free(no_pid_list);
 }
 
 void ftrace_clear_pids(struct trace_array *tr)
@@ -7428,7 +7683,7 @@ pid_write(struct file *filp, const char __user *ubuf,
 
 	if (filtered_pids) {
 		synchronize_rcu();
-		trace_free_pid_list(filtered_pids);
+		trace_pid_list_free(filtered_pids);
 	} else if (pid_list && !other_pids) {
 		/* Register a probe to set whether to ignore the tracing of a task */
 		register_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr);
@@ -7494,10 +7749,10 @@ static const struct file_operations ftrace_no_pid_fops = {
 
 void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 {
-	trace_create_file("set_ftrace_pid", 0644, d_tracer,
+	trace_create_file("set_ftrace_pid", TRACE_MODE_WRITE, d_tracer,
 			    tr, &ftrace_pid_fops);
-	trace_create_file("set_ftrace_notrace_pid", 0644, d_tracer,
-			    tr, &ftrace_no_pid_fops);
+	trace_create_file("set_ftrace_notrace_pid", TRACE_MODE_WRITE,
+			  d_tracer, tr, &ftrace_no_pid_fops);
 }
 
 void __init ftrace_init_tracefs_toplevel(struct trace_array *tr,
diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c
new file mode 100644
index 000000000000..a2ef1d18126a
--- /dev/null
+++ b/kernel/trace/pid_list.c
@@ -0,0 +1,495 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 VMware Inc, Steven Rostedt <rostedt@goodmis.org>
+ */
+#include <linux/spinlock.h>
+#include <linux/irq_work.h>
+#include <linux/slab.h>
+#include "trace.h"
+
+/* See pid_list.h for details */
+
+static inline union lower_chunk *get_lower_chunk(struct trace_pid_list *pid_list)
+{
+	union lower_chunk *chunk;
+
+	lockdep_assert_held(&pid_list->lock);
+
+	if (!pid_list->lower_list)
+		return NULL;
+
+	chunk = pid_list->lower_list;
+	pid_list->lower_list = chunk->next;
+	pid_list->free_lower_chunks--;
+	WARN_ON_ONCE(pid_list->free_lower_chunks < 0);
+	chunk->next = NULL;
+	/*
+	 * If a refill needs to happen, it can not happen here
+	 * as the scheduler run queue locks are held.
+	 */
+	if (pid_list->free_lower_chunks <= CHUNK_REALLOC)
+		irq_work_queue(&pid_list->refill_irqwork);
+
+	return chunk;
+}
+
+static inline union upper_chunk *get_upper_chunk(struct trace_pid_list *pid_list)
+{
+	union upper_chunk *chunk;
+
+	lockdep_assert_held(&pid_list->lock);
+
+	if (!pid_list->upper_list)
+		return NULL;
+
+	chunk = pid_list->upper_list;
+	pid_list->upper_list = chunk->next;
+	pid_list->free_upper_chunks--;
+	WARN_ON_ONCE(pid_list->free_upper_chunks < 0);
+	chunk->next = NULL;
+	/*
+	 * If a refill needs to happen, it can not happen here
+	 * as the scheduler run queue locks are held.
+	 */
+	if (pid_list->free_upper_chunks <= CHUNK_REALLOC)
+		irq_work_queue(&pid_list->refill_irqwork);
+
+	return chunk;
+}
+
+static inline void put_lower_chunk(struct trace_pid_list *pid_list,
+				   union lower_chunk *chunk)
+{
+	lockdep_assert_held(&pid_list->lock);
+
+	chunk->next = pid_list->lower_list;
+	pid_list->lower_list = chunk;
+	pid_list->free_lower_chunks++;
+}
+
+static inline void put_upper_chunk(struct trace_pid_list *pid_list,
+				   union upper_chunk *chunk)
+{
+	lockdep_assert_held(&pid_list->lock);
+
+	chunk->next = pid_list->upper_list;
+	pid_list->upper_list = chunk;
+	pid_list->free_upper_chunks++;
+}
+
+static inline bool upper_empty(union upper_chunk *chunk)
+{
+	/*
+	 * If chunk->data has no lower chunks, it will be the same
+	 * as a zeroed bitmask. Use find_first_bit() to test it
+	 * and if it doesn't find any bits set, then the array
+	 * is empty.
+	 */
+	int bit = find_first_bit((unsigned long *)chunk->data,
+				 sizeof(chunk->data) * 8);
+	return bit >= sizeof(chunk->data) * 8;
+}
+
+static inline int pid_split(unsigned int pid, unsigned int *upper1,
+			     unsigned int *upper2, unsigned int *lower)
+{
+	/* MAX_PID should cover all pids */
+	BUILD_BUG_ON(MAX_PID < PID_MAX_LIMIT);
+
+	/* In case a bad pid is passed in, then fail */
+	if (unlikely(pid >= MAX_PID))
+		return -1;
+
+	*upper1 = (pid >> UPPER1_SHIFT) & UPPER_MASK;
+	*upper2 = (pid >> UPPER2_SHIFT) & UPPER_MASK;
+	*lower = pid & LOWER_MASK;
+
+	return 0;
+}
+
+static inline unsigned int pid_join(unsigned int upper1,
+				    unsigned int upper2, unsigned int lower)
+{
+	return ((upper1 & UPPER_MASK) << UPPER1_SHIFT) |
+		((upper2 & UPPER_MASK) << UPPER2_SHIFT) |
+		(lower & LOWER_MASK);
+}
+
+/**
+ * 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.
+ *
+ * Tests if @pid is 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.
+ *
+ * Return true if the pid is in the list, false otherwise.
+ */
+bool trace_pid_list_is_set(struct trace_pid_list *pid_list, unsigned int pid)
+{
+	union upper_chunk *upper_chunk;
+	union lower_chunk *lower_chunk;
+	unsigned long flags;
+	unsigned int upper1;
+	unsigned int upper2;
+	unsigned int lower;
+	bool ret = false;
+
+	if (!pid_list)
+		return false;
+
+	if (pid_split(pid, &upper1, &upper2, &lower) < 0)
+		return false;
+
+	raw_spin_lock_irqsave(&pid_list->lock, flags);
+	upper_chunk = pid_list->upper[upper1];
+	if (upper_chunk) {
+		lower_chunk = upper_chunk->data[upper2];
+		if (lower_chunk)
+			ret = test_bit(lower, lower_chunk->data);
+	}
+	raw_spin_unlock_irqrestore(&pid_list->lock, flags);
+
+	return ret;
+}
+
+/**
+ * trace_pid_list_set - add a pid to the list
+ * @pid_list: The pid list to add the @pid to.
+ * @pid: The pid to add.
+ *
+ * Adds @pid to @pid_list. This is usually done explicitly by a user
+ * adding a task to be traced, or indirectly by the fork function
+ * when children should be traced and a task's pid is in the list.
+ *
+ * Return 0 on success, negative otherwise.
+ */
+int trace_pid_list_set(struct trace_pid_list *pid_list, unsigned int pid)
+{
+	union upper_chunk *upper_chunk;
+	union lower_chunk *lower_chunk;
+	unsigned long flags;
+	unsigned int upper1;
+	unsigned int upper2;
+	unsigned int lower;
+	int ret;
+
+	if (!pid_list)
+		return -ENODEV;
+
+	if (pid_split(pid, &upper1, &upper2, &lower) < 0)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&pid_list->lock, flags);
+	upper_chunk = pid_list->upper[upper1];
+	if (!upper_chunk) {
+		upper_chunk = get_upper_chunk(pid_list);
+		if (!upper_chunk) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		pid_list->upper[upper1] = upper_chunk;
+	}
+	lower_chunk = upper_chunk->data[upper2];
+	if (!lower_chunk) {
+		lower_chunk = get_lower_chunk(pid_list);
+		if (!lower_chunk) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		upper_chunk->data[upper2] = lower_chunk;
+	}
+	set_bit(lower, lower_chunk->data);
+	ret = 0;
+ out:
+	raw_spin_unlock_irqrestore(&pid_list->lock, flags);
+	return ret;
+}
+
+/**
+ * trace_pid_list_clear - remove a pid from the list
+ * @pid_list: The pid list to remove the @pid from.
+ * @pid: The pid to remove.
+ *
+ * Removes @pid from @pid_list. This is usually done explicitly by a user
+ * removing tasks from tracing, or indirectly by the exit function
+ * when a task that is set to be traced exits.
+ *
+ * Return 0 on success, negative otherwise.
+ */
+int trace_pid_list_clear(struct trace_pid_list *pid_list, unsigned int pid)
+{
+	union upper_chunk *upper_chunk;
+	union lower_chunk *lower_chunk;
+	unsigned long flags;
+	unsigned int upper1;
+	unsigned int upper2;
+	unsigned int lower;
+
+	if (!pid_list)
+		return -ENODEV;
+
+	if (pid_split(pid, &upper1, &upper2, &lower) < 0)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&pid_list->lock, flags);
+	upper_chunk = pid_list->upper[upper1];
+	if (!upper_chunk)
+		goto out;
+
+	lower_chunk = upper_chunk->data[upper2];
+	if (!lower_chunk)
+		goto out;
+
+	clear_bit(lower, lower_chunk->data);
+
+	/* if there's no more bits set, add it to the free list */
+	if (find_first_bit(lower_chunk->data, LOWER_MAX) >= LOWER_MAX) {
+		put_lower_chunk(pid_list, lower_chunk);
+		upper_chunk->data[upper2] = NULL;
+		if (upper_empty(upper_chunk)) {
+			put_upper_chunk(pid_list, upper_chunk);
+			pid_list->upper[upper1] = NULL;
+		}
+	}
+ out:
+	raw_spin_unlock_irqrestore(&pid_list->lock, flags);
+	return 0;
+}
+
+/**
+ * trace_pid_list_next - return the next pid in the list
+ * @pid_list: The pid list to examine.
+ * @pid: The pid to start from
+ * @next: The pointer to place the pid that is set starting from @pid.
+ *
+ * Looks for the next consecutive pid that is in @pid_list starting
+ * at the pid specified by @pid. If one is set (including @pid), then
+ * that pid is placed into @next.
+ *
+ * Return 0 when a pid is found, -1 if there are no more pids included.
+ */
+int trace_pid_list_next(struct trace_pid_list *pid_list, unsigned int pid,
+			unsigned int *next)
+{
+	union upper_chunk *upper_chunk;
+	union lower_chunk *lower_chunk;
+	unsigned long flags;
+	unsigned int upper1;
+	unsigned int upper2;
+	unsigned int lower;
+
+	if (!pid_list)
+		return -ENODEV;
+
+	if (pid_split(pid, &upper1, &upper2, &lower) < 0)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&pid_list->lock, flags);
+	for (; upper1 <= UPPER_MASK; upper1++, upper2 = 0) {
+		upper_chunk = pid_list->upper[upper1];
+
+		if (!upper_chunk)
+			continue;
+
+		for (; upper2 <= UPPER_MASK; upper2++, lower = 0) {
+			lower_chunk = upper_chunk->data[upper2];
+			if (!lower_chunk)
+				continue;
+
+			lower = find_next_bit(lower_chunk->data, LOWER_MAX,
+					    lower);
+			if (lower < LOWER_MAX)
+				goto found;
+		}
+	}
+
+ found:
+	raw_spin_unlock_irqrestore(&pid_list->lock, flags);
+	if (upper1 > UPPER_MASK)
+		return -1;
+
+	*next = pid_join(upper1, upper2, lower);
+	return 0;
+}
+
+/**
+ * trace_pid_list_first - return the first pid in the list
+ * @pid_list: The pid list to examine.
+ * @pid: The pointer to place the pid first found pid that is set.
+ *
+ * Looks for the first pid that is set in @pid_list, and places it
+ * into @pid if found.
+ *
+ * Return 0 when a pid is found, -1 if there are no pids set.
+ */
+int trace_pid_list_first(struct trace_pid_list *pid_list, unsigned int *pid)
+{
+	return trace_pid_list_next(pid_list, 0, pid);
+}
+
+static void pid_list_refill_irq(struct irq_work *iwork)
+{
+	struct trace_pid_list *pid_list = container_of(iwork, struct trace_pid_list,
+						       refill_irqwork);
+	union upper_chunk *upper = NULL;
+	union lower_chunk *lower = NULL;
+	union upper_chunk **upper_next = &upper;
+	union lower_chunk **lower_next = &lower;
+	int upper_count;
+	int lower_count;
+	int ucnt = 0;
+	int lcnt = 0;
+
+ again:
+	raw_spin_lock(&pid_list->lock);
+	upper_count = CHUNK_ALLOC - pid_list->free_upper_chunks;
+	lower_count = CHUNK_ALLOC - pid_list->free_lower_chunks;
+	raw_spin_unlock(&pid_list->lock);
+
+	if (upper_count <= 0 && lower_count <= 0)
+		return;
+
+	while (upper_count-- > 0) {
+		union upper_chunk *chunk;
+
+		chunk = kzalloc(sizeof(*chunk), GFP_KERNEL);
+		if (!chunk)
+			break;
+		*upper_next = chunk;
+		upper_next = &chunk->next;
+		ucnt++;
+	}
+
+	while (lower_count-- > 0) {
+		union lower_chunk *chunk;
+
+		chunk = kzalloc(sizeof(*chunk), GFP_KERNEL);
+		if (!chunk)
+			break;
+		*lower_next = chunk;
+		lower_next = &chunk->next;
+		lcnt++;
+	}
+
+	raw_spin_lock(&pid_list->lock);
+	if (upper) {
+		*upper_next = pid_list->upper_list;
+		pid_list->upper_list = upper;
+		pid_list->free_upper_chunks += ucnt;
+	}
+	if (lower) {
+		*lower_next = pid_list->lower_list;
+		pid_list->lower_list = lower;
+		pid_list->free_lower_chunks += lcnt;
+	}
+	raw_spin_unlock(&pid_list->lock);
+
+	/*
+	 * On success of allocating all the chunks, both counters
+	 * will be less than zero. If they are not, then an allocation
+	 * failed, and we should not try again.
+	 */
+	if (upper_count >= 0 || lower_count >= 0)
+		return;
+	/*
+	 * When the locks were released, free chunks could have
+	 * been used and allocation needs to be done again. Might as
+	 * well allocate it now.
+	 */
+	goto again;
+}
+
+/**
+ * trace_pid_list_alloc - create a new pid_list
+ *
+ * Allocates a new pid_list to store pids into.
+ *
+ * Returns the pid_list on success, NULL otherwise.
+ */
+struct trace_pid_list *trace_pid_list_alloc(void)
+{
+	struct trace_pid_list *pid_list;
+	int i;
+
+	/* According to linux/thread.h, pids can be no bigger that 30 bits */
+	WARN_ON_ONCE(pid_max > (1 << 30));
+
+	pid_list = kzalloc(sizeof(*pid_list), GFP_KERNEL);
+	if (!pid_list)
+		return NULL;
+
+	init_irq_work(&pid_list->refill_irqwork, pid_list_refill_irq);
+
+	raw_spin_lock_init(&pid_list->lock);
+
+	for (i = 0; i < CHUNK_ALLOC; i++) {
+		union upper_chunk *chunk;
+
+		chunk = kzalloc(sizeof(*chunk), GFP_KERNEL);
+		if (!chunk)
+			break;
+		chunk->next = pid_list->upper_list;
+		pid_list->upper_list = chunk;
+		pid_list->free_upper_chunks++;
+	}
+
+	for (i = 0; i < CHUNK_ALLOC; i++) {
+		union lower_chunk *chunk;
+
+		chunk = kzalloc(sizeof(*chunk), GFP_KERNEL);
+		if (!chunk)
+			break;
+		chunk->next = pid_list->lower_list;
+		pid_list->lower_list = chunk;
+		pid_list->free_lower_chunks++;
+	}
+
+	return pid_list;
+}
+
+/**
+ * trace_pid_list_free - Frees an allocated pid_list.
+ *
+ * Frees the memory for a pid_list that was allocated.
+ */
+void trace_pid_list_free(struct trace_pid_list *pid_list)
+{
+	union upper_chunk *upper;
+	union lower_chunk *lower;
+	int i, j;
+
+	if (!pid_list)
+		return;
+
+	irq_work_sync(&pid_list->refill_irqwork);
+
+	while (pid_list->lower_list) {
+		union lower_chunk *chunk;
+
+		chunk = pid_list->lower_list;
+		pid_list->lower_list = pid_list->lower_list->next;
+		kfree(chunk);
+	}
+
+	while (pid_list->upper_list) {
+		union upper_chunk *chunk;
+
+		chunk = pid_list->upper_list;
+		pid_list->upper_list = pid_list->upper_list->next;
+		kfree(chunk);
+	}
+
+	for (i = 0; i < UPPER1_SIZE; i++) {
+		upper = pid_list->upper[i];
+		if (upper) {
+			for (j = 0; j < UPPER2_SIZE; j++) {
+				lower = upper->data[j];
+				kfree(lower);
+			}
+			kfree(upper);
+		}
+	}
+	kfree(pid_list);
+}
diff --git a/kernel/trace/pid_list.h b/kernel/trace/pid_list.h
new file mode 100644
index 000000000000..62e73f1ac85f
--- /dev/null
+++ b/kernel/trace/pid_list.h
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Do not include this file directly. */
+
+#ifndef _TRACE_INTERNAL_PID_LIST_H
+#define _TRACE_INTERNAL_PID_LIST_H
+
+/*
+ * In order to keep track of what pids to trace, a tree is created much
+ * like page tables are used. This creates a sparse bit map, where
+ * the tree is filled in when needed. A PID is at most 30 bits (see
+ * linux/thread.h), and is broken up into 3 sections based on the bit map
+ * of the bits. The 8 MSB is the "upper1" section. The next 8 MSB is the
+ * "upper2" section and the 14 LSB is the "lower" section.
+ *
+ * A trace_pid_list structure holds the "upper1" section, in an
+ * array of 256 pointers (1 or 2K in size) to "upper_chunk" unions, where
+ * each has an array of 256 pointers (1 or 2K in size) to the "lower_chunk"
+ * structures, where each has an array of size 2K bytes representing a bitmask
+ * of the 14 LSB of the PID (256 * 8 = 2048)
+ *
+ * When a trace_pid_list is allocated, it includes the 256 pointer array
+ * of the upper1 unions. Then a "cache" of upper and lower is allocated
+ * where these will be assigned as needed.
+ *
+ * When a bit is set in the pid_list bitmask, the pid to use has
+ * the 8 MSB masked, and this is used to index the array in the
+ * pid_list to find the next upper union. If the element is NULL,
+ * then one is retrieved from the upper_list cache. If none is
+ * available, then -ENOMEM is returned.
+ *
+ * The next 8 MSB is used to index into the "upper2" section. If this
+ * element is NULL, then it is retrieved from the lower_list cache.
+ * Again, if one is not available -ENOMEM is returned.
+ *
+ * Finally the 14 LSB of the PID is used to set the bit in the 16384
+ * bitmask (made up of 2K bytes).
+ *
+ * When the second upper section or the lower section has their last
+ * bit cleared, they are added back to the free list to be reused
+ * when needed.
+ */
+
+#define UPPER_BITS	8
+#define UPPER_MAX	(1 << UPPER_BITS)
+#define UPPER1_SIZE	(1 << UPPER_BITS)
+#define UPPER2_SIZE	(1 << UPPER_BITS)
+
+#define LOWER_BITS	14
+#define LOWER_MAX	(1 << LOWER_BITS)
+#define LOWER_SIZE	(LOWER_MAX / BITS_PER_LONG)
+
+#define UPPER1_SHIFT	(LOWER_BITS + UPPER_BITS)
+#define UPPER2_SHIFT	LOWER_BITS
+#define LOWER_MASK	(LOWER_MAX - 1)
+
+#define UPPER_MASK	(UPPER_MAX - 1)
+
+/* According to linux/thread.h pids can not be bigger than or equal to 1 << 30 */
+#define MAX_PID		(1 << 30)
+
+/* Just keep 6 chunks of both upper and lower in the cache on alloc */
+#define CHUNK_ALLOC 6
+
+/* Have 2 chunks free, trigger a refill of the cache */
+#define CHUNK_REALLOC 2
+
+union lower_chunk {
+	union lower_chunk		*next;
+	unsigned long			data[LOWER_SIZE]; // 2K in size
+};
+
+union upper_chunk {
+	union upper_chunk		*next;
+	union lower_chunk		*data[UPPER2_SIZE]; // 1 or 2K in size
+};
+
+struct trace_pid_list {
+	raw_spinlock_t			lock;
+	struct irq_work			refill_irqwork;
+	union upper_chunk		*upper[UPPER1_SIZE]; // 1 or 2K in size
+	union upper_chunk		*upper_list;
+	union lower_chunk		*lower_list;
+	int				free_upper_chunks;
+	int				free_lower_chunks;
+};
+
+#endif /* _TRACE_INTERNAL_PID_LIST_H */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c5a3fbf19617..05dfc7a12d3d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3167,14 +3167,9 @@ static __always_inline int
 trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	unsigned int val = cpu_buffer->current_context;
-	unsigned long pc = preempt_count();
-	int bit;
+	int bit = interrupt_context_level();
 
-	if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
-		bit = RB_CTX_NORMAL;
-	else
-		bit = pc & NMI_MASK ? RB_CTX_NMI :
-			pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;
+	bit = RB_CTX_NORMAL - bit;
 
 	if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) {
 		/*
@@ -5233,6 +5228,9 @@ void ring_buffer_reset(struct trace_buffer *buffer)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	int cpu;
 
+	/* prevent another thread from changing buffer sizes */
+	mutex_lock(&buffer->mutex);
+
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
 
@@ -5251,6 +5249,8 @@ void ring_buffer_reset(struct trace_buffer *buffer)
 		atomic_dec(&cpu_buffer->record_disabled);
 		atomic_dec(&cpu_buffer->resize_disabled);
 	}
+
+	mutex_unlock(&buffer->mutex);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_reset);
 
@@ -5898,16 +5898,13 @@ static __init int test_ringbuffer(void)
 		rb_data[cpu].buffer = buffer;
 		rb_data[cpu].cpu = cpu;
 		rb_data[cpu].cnt = cpu;
-		rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
-						 "rbtester/%d", cpu);
+		rb_threads[cpu] = kthread_run_on_cpu(rb_test, &rb_data[cpu],
+						     cpu, "rbtester/%u");
 		if (WARN_ON(IS_ERR(rb_threads[cpu]))) {
 			pr_cont("FAILED\n");
 			ret = PTR_ERR(rb_threads[cpu]);
 			goto out_free;
 		}
-
-		kthread_bind(rb_threads[cpu], cpu);
- 		wake_up_process(rb_threads[cpu]);
 	}
 
 	/* Now create the rb hammer! */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index bc677cd64224..7c2578efde26 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -252,6 +252,10 @@ __setup("trace_clock=", set_trace_boot_clock);
 
 static int __init set_tracepoint_printk(char *str)
 {
+	/* Ignore the "tp_printk_stop_on_boot" param */
+	if (*str == '_')
+		return 0;
+
 	if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0))
 		tracepoint_printk = 1;
 	return 1;
@@ -512,12 +516,6 @@ int call_filter_check_discard(struct trace_event_call *call, void *rec,
 	return 0;
 }
 
-void trace_free_pid_list(struct trace_pid_list *pid_list)
-{
-	vfree(pid_list->pids);
-	kfree(pid_list);
-}
-
 /**
  * trace_find_filtered_pid - check if a pid exists in a filtered_pid list
  * @filtered_pids: The list of pids to check
@@ -528,14 +526,7 @@ void trace_free_pid_list(struct trace_pid_list *pid_list)
 bool
 trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
 {
-	/*
-	 * If pid_max changed after filtered_pids was created, we
-	 * by default ignore all pids greater than the previous pid_max.
-	 */
-	if (search_pid >= filtered_pids->pid_max)
-		return false;
-
-	return test_bit(search_pid, filtered_pids->pids);
+	return trace_pid_list_is_set(filtered_pids, search_pid);
 }
 
 /**
@@ -592,15 +583,11 @@ void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
 			return;
 	}
 
-	/* Sorry, but we don't support pid_max changing after setting */
-	if (task->pid >= pid_list->pid_max)
-		return;
-
 	/* "self" is set for forks, and NULL for exits */
 	if (self)
-		set_bit(task->pid, pid_list->pids);
+		trace_pid_list_set(pid_list, task->pid);
 	else
-		clear_bit(task->pid, pid_list->pids);
+		trace_pid_list_clear(pid_list, task->pid);
 }
 
 /**
@@ -617,18 +604,19 @@ void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
  */
 void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos)
 {
-	unsigned long pid = (unsigned long)v;
+	long pid = (unsigned long)v;
+	unsigned int next;
 
 	(*pos)++;
 
 	/* pid already is +1 of the actual previous bit */
-	pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid);
+	if (trace_pid_list_next(pid_list, pid, &next) < 0)
+		return NULL;
 
-	/* Return pid + 1 to allow zero to be represented */
-	if (pid < pid_list->pid_max)
-		return (void *)(pid + 1);
+	pid = next;
 
-	return NULL;
+	/* Return pid + 1 to allow zero to be represented */
+	return (void *)(pid + 1);
 }
 
 /**
@@ -645,12 +633,14 @@ void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos)
 void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos)
 {
 	unsigned long pid;
+	unsigned int first;
 	loff_t l = 0;
 
-	pid = find_first_bit(pid_list->pids, pid_list->pid_max);
-	if (pid >= pid_list->pid_max)
+	if (trace_pid_list_first(pid_list, &first) < 0)
 		return NULL;
 
+	pid = first;
+
 	/* Return pid + 1 so that zero can be the exit value */
 	for (pid++; pid && l < *pos;
 	     pid = (unsigned long)trace_pid_next(pid_list, (void *)pid, &l))
@@ -686,7 +676,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	unsigned long val;
 	int nr_pids = 0;
 	ssize_t read = 0;
-	ssize_t ret = 0;
+	ssize_t ret;
 	loff_t pos;
 	pid_t pid;
 
@@ -699,34 +689,23 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	 * the user. If the operation fails, then the current list is
 	 * not modified.
 	 */
-	pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
+	pid_list = trace_pid_list_alloc();
 	if (!pid_list) {
 		trace_parser_put(&parser);
 		return -ENOMEM;
 	}
 
-	pid_list->pid_max = READ_ONCE(pid_max);
-
-	/* Only truncating will shrink pid_max */
-	if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max)
-		pid_list->pid_max = filtered_pids->pid_max;
-
-	pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
-	if (!pid_list->pids) {
-		trace_parser_put(&parser);
-		kfree(pid_list);
-		return -ENOMEM;
-	}
-
 	if (filtered_pids) {
 		/* copy the current bits to the new max */
-		for_each_set_bit(pid, filtered_pids->pids,
-				 filtered_pids->pid_max) {
-			set_bit(pid, pid_list->pids);
+		ret = trace_pid_list_first(filtered_pids, &pid);
+		while (!ret) {
+			trace_pid_list_set(pid_list, pid);
+			ret = trace_pid_list_next(filtered_pids, pid + 1, &pid);
 			nr_pids++;
 		}
 	}
 
+	ret = 0;
 	while (cnt > 0) {
 
 		pos = 0;
@@ -742,12 +721,13 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 		ret = -EINVAL;
 		if (kstrtoul(parser.buffer, 0, &val))
 			break;
-		if (val >= pid_list->pid_max)
-			break;
 
 		pid = (pid_t)val;
 
-		set_bit(pid, pid_list->pids);
+		if (trace_pid_list_set(pid_list, pid) < 0) {
+			ret = -1;
+			break;
+		}
 		nr_pids++;
 
 		trace_parser_clear(&parser);
@@ -756,13 +736,13 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	trace_parser_put(&parser);
 
 	if (ret < 0) {
-		trace_free_pid_list(pid_list);
+		trace_pid_list_free(pid_list);
 		return ret;
 	}
 
 	if (!nr_pids) {
 		/* Cleared the list of pids */
-		trace_free_pid_list(pid_list);
+		trace_pid_list_free(pid_list);
 		read = ret;
 		pid_list = NULL;
 	}
@@ -1004,6 +984,8 @@ __buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *ev
 		ring_buffer_write(buffer, event->array[0], &event->array[1]);
 		/* Release the temp buffer */
 		this_cpu_dec(trace_buffered_event_cnt);
+		/* ring_buffer_unlock_commit() enables preemption */
+		preempt_enable_notrace();
 	} else
 		ring_buffer_unlock_commit(buffer, event);
 }
@@ -1714,7 +1696,8 @@ static void trace_create_maxlat_file(struct trace_array *tr,
 {
 	INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn);
 	init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq);
-	tr->d_max_latency = trace_create_file("tracing_max_latency", 0644,
+	tr->d_max_latency = trace_create_file("tracing_max_latency",
+					      TRACE_MODE_WRITE,
 					      d_tracer, &tr->max_latency,
 					      &tracing_max_lat_fops);
 }
@@ -1748,8 +1731,8 @@ void latency_fsnotify(struct trace_array *tr)
 	|| defined(CONFIG_OSNOISE_TRACER)
 
 #define trace_create_maxlat_file(tr, d_tracer)				\
-	trace_create_file("tracing_max_latency", 0644, d_tracer,	\
-			  &tr->max_latency, &tracing_max_lat_fops)
+	trace_create_file("tracing_max_latency", TRACE_MODE_WRITE,	\
+			  d_tracer, &tr->max_latency, &tracing_max_lat_fops)
 
 #else
 #define trace_create_maxlat_file(tr, d_tracer)	 do { } while (0)
@@ -2624,6 +2607,8 @@ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status)
 		trace_flags |= TRACE_FLAG_HARDIRQ;
 	if (in_serving_softirq())
 		trace_flags |= TRACE_FLAG_SOFTIRQ;
+	if (softirq_count() >> (SOFTIRQ_SHIFT + 1))
+		trace_flags |= TRACE_FLAG_BH_OFF;
 
 	if (tif_need_resched())
 		trace_flags |= TRACE_FLAG_NEED_RESCHED;
@@ -2768,8 +2753,8 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
 	*current_rb = tr->array_buffer.buffer;
 
 	if (!tr->no_filter_buffering_ref &&
-	    (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) &&
-	    (entry = this_cpu_read(trace_buffered_event))) {
+	    (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED))) {
+		preempt_disable_notrace();
 		/*
 		 * Filtering is on, so try to use the per cpu buffer first.
 		 * This buffer will simulate a ring_buffer_event,
@@ -2787,33 +2772,38 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
 		 * is still quicker than no copy on match, but having
 		 * to discard out of the ring buffer on a failed match.
 		 */
-		int max_len = PAGE_SIZE - struct_size(entry, array, 1);
+		if ((entry = __this_cpu_read(trace_buffered_event))) {
+			int max_len = PAGE_SIZE - struct_size(entry, array, 1);
 
-		val = this_cpu_inc_return(trace_buffered_event_cnt);
+			val = this_cpu_inc_return(trace_buffered_event_cnt);
 
-		/*
-		 * Preemption is disabled, but interrupts and NMIs
-		 * can still come in now. If that happens after
-		 * the above increment, then it will have to go
-		 * back to the old method of allocating the event
-		 * on the ring buffer, and if the filter fails, it
-		 * will have to call ring_buffer_discard_commit()
-		 * to remove it.
-		 *
-		 * Need to also check the unlikely case that the
-		 * length is bigger than the temp buffer size.
-		 * If that happens, then the reserve is pretty much
-		 * guaranteed to fail, as the ring buffer currently
-		 * only allows events less than a page. But that may
-		 * change in the future, so let the ring buffer reserve
-		 * handle the failure in that case.
-		 */
-		if (val == 1 && likely(len <= max_len)) {
-			trace_event_setup(entry, type, trace_ctx);
-			entry->array[0] = len;
-			return entry;
+			/*
+			 * Preemption is disabled, but interrupts and NMIs
+			 * can still come in now. If that happens after
+			 * the above increment, then it will have to go
+			 * back to the old method of allocating the event
+			 * on the ring buffer, and if the filter fails, it
+			 * will have to call ring_buffer_discard_commit()
+			 * to remove it.
+			 *
+			 * Need to also check the unlikely case that the
+			 * length is bigger than the temp buffer size.
+			 * If that happens, then the reserve is pretty much
+			 * guaranteed to fail, as the ring buffer currently
+			 * only allows events less than a page. But that may
+			 * change in the future, so let the ring buffer reserve
+			 * handle the failure in that case.
+			 */
+			if (val == 1 && likely(len <= max_len)) {
+				trace_event_setup(entry, type, trace_ctx);
+				entry->array[0] = len;
+				/* Return with preemption disabled */
+				return entry;
+			}
+			this_cpu_dec(trace_buffered_event_cnt);
 		}
-		this_cpu_dec(trace_buffered_event_cnt);
+		/* __trace_buffer_lock_reserve() disables preemption */
+		preempt_enable_notrace();
 	}
 
 	entry = __trace_buffer_lock_reserve(*current_rb, type, len,
@@ -3230,7 +3220,7 @@ struct trace_buffer_struct {
 	char buffer[4][TRACE_BUF_SIZE];
 };
 
-static struct trace_buffer_struct *trace_percpu_buffer;
+static struct trace_buffer_struct __percpu *trace_percpu_buffer;
 
 /*
  * This allows for lockless recording.  If we're nested too deeply, then
@@ -3240,7 +3230,7 @@ static char *get_trace_buf(void)
 {
 	struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer);
 
-	if (!buffer || buffer->nesting >= 4)
+	if (!trace_percpu_buffer || buffer->nesting >= 4)
 		return NULL;
 
 	buffer->nesting++;
@@ -3259,7 +3249,7 @@ static void put_trace_buf(void)
 
 static int alloc_percpu_trace_buffer(void)
 {
-	struct trace_buffer_struct *buffers;
+	struct trace_buffer_struct __percpu *buffers;
 
 	if (trace_percpu_buffer)
 		return 0;
@@ -3835,6 +3825,18 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 		iter->fmt[i] = '\0';
 		trace_seq_vprintf(&iter->seq, iter->fmt, ap);
 
+		/*
+		 * If iter->seq is full, the above call no longer guarantees
+		 * that ap is in sync with fmt processing, and further calls
+		 * to va_arg() can return wrong positional arguments.
+		 *
+		 * Ensure that ap is no longer used in this case.
+		 */
+		if (iter->seq.full) {
+			p = "";
+			break;
+		}
+
 		if (star)
 			len = va_arg(ap, int);
 
@@ -4194,7 +4196,7 @@ unsigned long trace_total_entries(struct trace_array *tr)
 static void print_lat_help_header(struct seq_file *m)
 {
 	seq_puts(m, "#                    _------=> CPU#            \n"
-		    "#                   / _-----=> irqs-off        \n"
+		    "#                   / _-----=> irqs-off/BH-disabled\n"
 		    "#                  | / _----=> need-resched    \n"
 		    "#                  || / _---=> hardirq/softirq \n"
 		    "#                  ||| / _--=> preempt-depth   \n"
@@ -4235,7 +4237,7 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#                            %.*s  _-----=> irqs-off\n", prec, space);
+	seq_printf(m, "#                            %.*s  _-----=> irqs-off/BH-disabled\n", prec, space);
 	seq_printf(m, "#                            %.*s / _----=> need-resched\n", prec, space);
 	seq_printf(m, "#                            %.*s| / _---=> hardirq/softirq\n", prec, space);
 	seq_printf(m, "#                            %.*s|| / _--=> preempt-depth\n", prec, space);
@@ -4845,6 +4847,12 @@ int tracing_open_generic_tr(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static int tracing_mark_open(struct inode *inode, struct file *filp)
+{
+	stream_open(inode, filp);
+	return tracing_open_generic_tr(inode, filp);
+}
+
 static int tracing_release(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
@@ -5628,6 +5636,7 @@ static const char readme_msg[] =
 #ifdef CONFIG_HIST_TRIGGERS
 	"      hist trigger\t- If set, event hits are aggregated into a hash table\n"
 	"\t    Format: hist:keys=<field1[,field2,...]>\n"
+	"\t            [:<var1>=<field|var_ref|numeric_literal>[,<var2>=...]]\n"
 	"\t            [:values=<field1[,field2,...]>]\n"
 	"\t            [:sort=<field1[,field2,...]>]\n"
 	"\t            [:size=#entries]\n"
@@ -5639,6 +5648,16 @@ static const char readme_msg[] =
 	"\t            common_timestamp - to record current timestamp\n"
 	"\t            common_cpu - to record the CPU the event happened on\n"
 	"\n"
+	"\t    A hist trigger variable can be:\n"
+	"\t        - a reference to a field e.g. x=current_timestamp,\n"
+	"\t        - a reference to another variable e.g. y=$x,\n"
+	"\t        - a numeric literal: e.g. ms_per_sec=1000,\n"
+	"\t        - an arithmetic expression: e.g. time_secs=current_timestamp/1000\n"
+	"\n"
+	"\t    hist trigger arithmetic expressions support addition(+), subtraction(-),\n"
+	"\t    multiplication(*) and division(/) operators. An operand can be either a\n"
+	"\t    variable reference, field or numeric literal.\n"
+	"\n"
 	"\t    When a matching event is hit, an entry is added to a hash\n"
 	"\t    table using the key(s) and value(s) named, and the value of a\n"
 	"\t    sum called 'hitcount' is incremented.  Keys and values\n"
@@ -6077,7 +6096,7 @@ trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start,
 
 static void trace_create_eval_file(struct dentry *d_tracer)
 {
-	trace_create_file("eval_map", 0444, d_tracer,
+	trace_create_file("eval_map", TRACE_MODE_READ, d_tracer,
 			  NULL, &tracing_eval_map_fops);
 }
 
@@ -6718,12 +6737,9 @@ waitagain:
 		cnt = PAGE_SIZE - 1;
 
 	/* reset all but tr, trace, and overruns */
-	memset(&iter->seq, 0,
-	       sizeof(struct trace_iterator) -
-	       offsetof(struct trace_iterator, seq));
+	trace_iterator_reset(iter);
 	cpumask_clear(iter->started);
 	trace_seq_init(&iter->seq);
-	iter->pos = -1;
 
 	trace_event_read_lock();
 	trace_access_lock(iter->cpu_file);
@@ -7112,9 +7128,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (tt)
 		event_triggers_post_call(tr->trace_marker_file, tt);
 
-	if (written > 0)
-		*fpos += written;
-
 	return written;
 }
 
@@ -7173,9 +7186,6 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 
 	__buffer_unlock_commit(buffer, event);
 
-	if (written > 0)
-		*fpos += written;
-
 	return written;
 }
 
@@ -7575,16 +7585,14 @@ static const struct file_operations tracing_free_buffer_fops = {
 };
 
 static const struct file_operations tracing_mark_fops = {
-	.open		= tracing_open_generic_tr,
+	.open		= tracing_mark_open,
 	.write		= tracing_mark_write,
-	.llseek		= generic_file_llseek,
 	.release	= tracing_release_generic_tr,
 };
 
 static const struct file_operations tracing_mark_raw_fops = {
-	.open		= tracing_open_generic_tr,
+	.open		= tracing_mark_open,
 	.write		= tracing_mark_raw_write,
-	.llseek		= generic_file_llseek,
 	.release	= tracing_release_generic_tr,
 };
 
@@ -7736,7 +7744,8 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr)
 		err = kzalloc(sizeof(*err), GFP_KERNEL);
 		if (!err)
 			err = ERR_PTR(-ENOMEM);
-		tr->n_err_log_entries++;
+		else
+			tr->n_err_log_entries++;
 
 		return err;
 	}
@@ -8590,27 +8599,27 @@ tracing_init_tracefs_percpu(struct trace_array *tr, long cpu)
 	}
 
 	/* per cpu trace_pipe */
-	trace_create_cpu_file("trace_pipe", 0444, d_cpu,
+	trace_create_cpu_file("trace_pipe", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &tracing_pipe_fops);
 
 	/* per cpu trace */
-	trace_create_cpu_file("trace", 0644, d_cpu,
+	trace_create_cpu_file("trace", TRACE_MODE_WRITE, d_cpu,
 				tr, cpu, &tracing_fops);
 
-	trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu,
+	trace_create_cpu_file("trace_pipe_raw", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &tracing_buffers_fops);
 
-	trace_create_cpu_file("stats", 0444, d_cpu,
+	trace_create_cpu_file("stats", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &tracing_stats_fops);
 
-	trace_create_cpu_file("buffer_size_kb", 0444, d_cpu,
+	trace_create_cpu_file("buffer_size_kb", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &tracing_entries_fops);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-	trace_create_cpu_file("snapshot", 0644, d_cpu,
+	trace_create_cpu_file("snapshot", TRACE_MODE_WRITE, d_cpu,
 				tr, cpu, &snapshot_fops);
 
-	trace_create_cpu_file("snapshot_raw", 0444, d_cpu,
+	trace_create_cpu_file("snapshot_raw", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &snapshot_raw_fops);
 #endif
 }
@@ -8816,8 +8825,8 @@ create_trace_option_file(struct trace_array *tr,
 	topt->opt = opt;
 	topt->tr = tr;
 
-	topt->entry = trace_create_file(opt->name, 0644, t_options, topt,
-				    &trace_options_fops);
+	topt->entry = trace_create_file(opt->name, TRACE_MODE_WRITE,
+					t_options, topt, &trace_options_fops);
 
 }
 
@@ -8892,7 +8901,7 @@ create_trace_option_core_file(struct trace_array *tr,
 	if (!t_options)
 		return NULL;
 
-	return trace_create_file(option, 0644, t_options,
+	return trace_create_file(option, TRACE_MODE_WRITE, t_options,
 				 (void *)&tr->trace_flags_index[index],
 				 &trace_options_core_fops);
 }
@@ -9417,28 +9426,28 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	struct trace_event_file *file;
 	int cpu;
 
-	trace_create_file("available_tracers", 0444, d_tracer,
+	trace_create_file("available_tracers", TRACE_MODE_READ, d_tracer,
 			tr, &show_traces_fops);
 
-	trace_create_file("current_tracer", 0644, d_tracer,
+	trace_create_file("current_tracer", TRACE_MODE_WRITE, d_tracer,
 			tr, &set_tracer_fops);
 
-	trace_create_file("tracing_cpumask", 0644, d_tracer,
+	trace_create_file("tracing_cpumask", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_cpumask_fops);
 
-	trace_create_file("trace_options", 0644, d_tracer,
+	trace_create_file("trace_options", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_iter_fops);
 
-	trace_create_file("trace", 0644, d_tracer,
+	trace_create_file("trace", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_fops);
 
-	trace_create_file("trace_pipe", 0444, d_tracer,
+	trace_create_file("trace_pipe", TRACE_MODE_READ, d_tracer,
 			  tr, &tracing_pipe_fops);
 
-	trace_create_file("buffer_size_kb", 0644, d_tracer,
+	trace_create_file("buffer_size_kb", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_entries_fops);
 
-	trace_create_file("buffer_total_size_kb", 0444, d_tracer,
+	trace_create_file("buffer_total_size_kb", TRACE_MODE_READ, d_tracer,
 			  tr, &tracing_total_entries_fops);
 
 	trace_create_file("free_buffer", 0200, d_tracer,
@@ -9449,25 +9458,25 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 
 	file = __find_event_file(tr, "ftrace", "print");
 	if (file && file->dir)
-		trace_create_file("trigger", 0644, file->dir, file,
-				  &event_trigger_fops);
+		trace_create_file("trigger", TRACE_MODE_WRITE, file->dir,
+				  file, &event_trigger_fops);
 	tr->trace_marker_file = file;
 
 	trace_create_file("trace_marker_raw", 0220, d_tracer,
 			  tr, &tracing_mark_raw_fops);
 
-	trace_create_file("trace_clock", 0644, d_tracer, tr,
+	trace_create_file("trace_clock", TRACE_MODE_WRITE, d_tracer, tr,
 			  &trace_clock_fops);
 
-	trace_create_file("tracing_on", 0644, d_tracer,
+	trace_create_file("tracing_on", TRACE_MODE_WRITE, d_tracer,
 			  tr, &rb_simple_fops);
 
-	trace_create_file("timestamp_mode", 0444, d_tracer, tr,
+	trace_create_file("timestamp_mode", TRACE_MODE_READ, d_tracer, tr,
 			  &trace_time_stamp_mode_fops);
 
 	tr->buffer_percent = 50;
 
-	trace_create_file("buffer_percent", 0444, d_tracer,
+	trace_create_file("buffer_percent", TRACE_MODE_READ, d_tracer,
 			tr, &buffer_percent_fops);
 
 	create_trace_options_dir(tr);
@@ -9478,11 +9487,11 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 		MEM_FAIL(1, "Could not allocate function filter files");
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-	trace_create_file("snapshot", 0644, d_tracer,
+	trace_create_file("snapshot", TRACE_MODE_WRITE, d_tracer,
 			  tr, &snapshot_fops);
 #endif
 
-	trace_create_file("error_log", 0644, d_tracer,
+	trace_create_file("error_log", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_err_log_fops);
 
 	for_each_tracing_cpu(cpu)
@@ -9675,19 +9684,19 @@ static __init int tracer_init_tracefs(void)
 	init_tracer_tracefs(&global_trace, NULL);
 	ftrace_init_tracefs_toplevel(&global_trace, NULL);
 
-	trace_create_file("tracing_thresh", 0644, NULL,
+	trace_create_file("tracing_thresh", TRACE_MODE_WRITE, NULL,
 			&global_trace, &tracing_thresh_fops);
 
-	trace_create_file("README", 0444, NULL,
+	trace_create_file("README", TRACE_MODE_READ, NULL,
 			NULL, &tracing_readme_fops);
 
-	trace_create_file("saved_cmdlines", 0444, NULL,
+	trace_create_file("saved_cmdlines", TRACE_MODE_READ, NULL,
 			NULL, &tracing_saved_cmdlines_fops);
 
-	trace_create_file("saved_cmdlines_size", 0644, NULL,
+	trace_create_file("saved_cmdlines_size", TRACE_MODE_WRITE, NULL,
 			  NULL, &tracing_saved_cmdlines_size_fops);
 
-	trace_create_file("saved_tgids", 0444, NULL,
+	trace_create_file("saved_tgids", TRACE_MODE_READ, NULL,
 			NULL, &tracing_saved_tgids_fops);
 
 	trace_eval_init();
@@ -9699,7 +9708,7 @@ static __init int tracer_init_tracefs(void)
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-	trace_create_file("dyn_ftrace_total_info", 0444, NULL,
+	trace_create_file("dyn_ftrace_total_info", TRACE_MODE_READ, NULL,
 			NULL, &tracing_dyn_info_fops);
 #endif
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index b7c0f8e160fb..d038ddbf1bea 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -22,11 +22,16 @@
 #include <linux/ctype.h>
 #include <linux/once_lite.h>
 
+#include "pid_list.h"
+
 #ifdef CONFIG_FTRACE_SYSCALLS
 #include <asm/unistd.h>		/* For NR_SYSCALLS	     */
 #include <asm/syscall.h>	/* some archs define it here */
 #endif
 
+#define TRACE_MODE_WRITE	0640
+#define TRACE_MODE_READ		0440
+
 enum trace_type {
 	__TRACE_FIRST_TYPE = 0,
 
@@ -78,6 +83,9 @@ enum trace_type {
 #undef __dynamic_array
 #define __dynamic_array(type, item)	type	item[];
 
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(type, item)	type	item[];
+
 #undef F_STRUCT
 #define F_STRUCT(args...)		args
 
@@ -188,10 +196,14 @@ struct trace_options {
 	struct trace_option_dentry	*topts;
 };
 
-struct trace_pid_list {
-	int				pid_max;
-	unsigned long			*pids;
-};
+struct trace_pid_list *trace_pid_list_alloc(void);
+void trace_pid_list_free(struct trace_pid_list *pid_list);
+bool trace_pid_list_is_set(struct trace_pid_list *pid_list, unsigned int pid);
+int trace_pid_list_set(struct trace_pid_list *pid_list, unsigned int pid);
+int trace_pid_list_clear(struct trace_pid_list *pid_list, unsigned int pid);
+int trace_pid_list_first(struct trace_pid_list *pid_list, unsigned int *pid);
+int trace_pid_list_next(struct trace_pid_list *pid_list, unsigned int pid,
+			unsigned int *next);
 
 enum {
 	TRACE_PIDS		= BIT(0),
@@ -881,7 +893,7 @@ static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
 		 * is set, and called by an interrupt handler, we still
 		 * want to trace it.
 		 */
-		if (in_irq())
+		if (in_hardirq())
 			trace_recursion_set(TRACE_IRQ_BIT);
 		else
 			trace_recursion_clear(TRACE_IRQ_BIT);
@@ -1325,10 +1337,12 @@ __trace_event_discard_commit(struct trace_buffer *buffer,
 			     struct ring_buffer_event *event)
 {
 	if (this_cpu_read(trace_buffered_event) == event) {
-		/* Simply release the temp buffer */
+		/* Simply release the temp buffer and enable preemption */
 		this_cpu_dec(trace_buffered_event_cnt);
+		preempt_enable_notrace();
 		return;
 	}
+	/* ring_buffer_discard_commit() enables preemption */
 	ring_buffer_discard_commit(buffer, event);
 }
 
@@ -1357,14 +1371,26 @@ __event_trigger_test_discard(struct trace_event_file *file,
 	if (eflags & EVENT_FILE_FL_TRIGGER_COND)
 		*tt = event_triggers_call(file, buffer, entry, event);
 
-	if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
-	    (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
-	     !filter_match_preds(file->filter, entry))) {
-		__trace_event_discard_commit(buffer, event);
-		return true;
-	}
+	if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED |
+				    EVENT_FILE_FL_FILTERED |
+				    EVENT_FILE_FL_PID_FILTER))))
+		return false;
+
+	if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
+		goto discard;
+
+	if (file->flags & EVENT_FILE_FL_FILTERED &&
+	    !filter_match_preds(file->filter, entry))
+		goto discard;
+
+	if ((file->flags & EVENT_FILE_FL_PID_FILTER) &&
+	    trace_event_ignore_this_pid(file))
+		goto discard;
 
 	return false;
+ discard:
+	__trace_event_discard_commit(buffer, event);
+	return true;
 }
 
 /**
@@ -1444,6 +1470,7 @@ struct filter_pred {
 static inline bool is_string_field(struct ftrace_event_field *field)
 {
 	return field->filter_type == FILTER_DYN_STRING ||
+	       field->filter_type == FILTER_RDYN_STRING ||
 	       field->filter_type == FILTER_STATIC_STRING ||
 	       field->filter_type == FILTER_PTR_STRING ||
 	       field->filter_type == FILTER_COMM;
@@ -1551,15 +1578,13 @@ extern int event_enable_trigger_print(struct seq_file *m,
 				      struct event_trigger_data *data);
 extern void event_enable_trigger_free(struct event_trigger_ops *ops,
 				      struct event_trigger_data *data);
-extern int event_enable_trigger_func(struct event_command *cmd_ops,
-				     struct trace_event_file *file,
-				     char *glob, char *cmd, char *param);
+extern int event_enable_trigger_parse(struct event_command *cmd_ops,
+				      struct trace_event_file *file,
+				      char *glob, char *cmd, char *param);
 extern int event_enable_register_trigger(char *glob,
-					 struct event_trigger_ops *ops,
 					 struct event_trigger_data *data,
 					 struct trace_event_file *file);
 extern void event_enable_unregister_trigger(char *glob,
-					    struct event_trigger_ops *ops,
 					    struct event_trigger_data *test,
 					    struct trace_event_file *file);
 extern void trigger_data_free(struct event_trigger_data *data);
@@ -1585,6 +1610,30 @@ get_named_trigger_data(struct event_trigger_data *data);
 extern int register_event_command(struct event_command *cmd);
 extern int unregister_event_command(struct event_command *cmd);
 extern int register_trigger_hist_enable_disable_cmds(void);
+extern bool event_trigger_check_remove(const char *glob);
+extern bool event_trigger_empty_param(const char *param);
+extern int event_trigger_separate_filter(char *param_and_filter, char **param,
+					 char **filter, bool param_required);
+extern struct event_trigger_data *
+event_trigger_alloc(struct event_command *cmd_ops,
+		    char *cmd,
+		    char *param,
+		    void *private_data);
+extern int event_trigger_parse_num(char *trigger,
+				   struct event_trigger_data *trigger_data);
+extern int event_trigger_set_filter(struct event_command *cmd_ops,
+				    struct trace_event_file *file,
+				    char *param,
+				    struct event_trigger_data *trigger_data);
+extern void event_trigger_reset_filter(struct event_command *cmd_ops,
+				       struct event_trigger_data *trigger_data);
+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_ops - callbacks for trace event triggers
@@ -1592,10 +1641,20 @@ extern int register_trigger_hist_enable_disable_cmds(void);
  * The methods in this structure provide per-event trigger hooks for
  * various trigger operations.
  *
+ * The @init and @free methods are used during trigger setup and
+ * teardown, typically called from an event_command's @parse()
+ * function implementation.
+ *
+ * The @print method is used to print the trigger spec.
+ *
+ * The @trigger method is the function that actually implements the
+ * trigger and is called in the context of the triggering event
+ * whenever that event occurs.
+ *
  * All the methods below, except for @init() and @free(), must be
  * implemented.
  *
- * @func: The trigger 'probe' function called when the triggering
+ * @trigger: The trigger 'probe' function called when the triggering
  *	event occurs.  The data passed into this callback is the data
  *	that was supplied to the event_command @reg() function that
  *	registered the trigger (see struct event_command) along with
@@ -1624,9 +1683,10 @@ extern int register_trigger_hist_enable_disable_cmds(void);
  *	(see trace_event_triggers.c).
  */
 struct event_trigger_ops {
-	void			(*func)(struct event_trigger_data *data,
-					struct trace_buffer *buffer, void *rec,
-					struct ring_buffer_event *rbe);
+	void			(*trigger)(struct event_trigger_data *data,
+					   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,
@@ -1675,7 +1735,7 @@ struct event_trigger_ops {
  * All the methods below, except for @set_filter() and @unreg_all(),
  * must be implemented.
  *
- * @func: The callback function responsible for parsing and
+ * @parse: The callback function responsible for parsing and
  *	registering the trigger written to the 'trigger' file by the
  *	user.  It allocates the trigger instance and registers it with
  *	the appropriate trace event.  It makes use of the other
@@ -1710,21 +1770,24 @@ struct event_trigger_ops {
  *
  * @get_trigger_ops: The callback function invoked to retrieve the
  *	event_trigger_ops implementation associated with the command.
+ *	This callback function allows a single event_command to
+ *	support multiple trigger implementations via different sets of
+ *	event_trigger_ops, depending on the value of the @param
+ *	string.
  */
 struct event_command {
 	struct list_head	list;
 	char			*name;
 	enum event_trigger_type	trigger_type;
 	int			flags;
-	int			(*func)(struct event_command *cmd_ops,
-					struct trace_event_file *file,
-					char *glob, char *cmd, char *params);
+	int			(*parse)(struct event_command *cmd_ops,
+					 struct trace_event_file *file,
+					 char *glob, char *cmd,
+					 char *param_and_filter);
 	int			(*reg)(char *glob,
-				       struct event_trigger_ops *ops,
 				       struct event_trigger_data *data,
 				       struct trace_event_file *file);
 	void			(*unreg)(char *glob,
-					 struct event_trigger_ops *ops,
 					 struct event_trigger_data *data,
 					 struct trace_event_file *file);
 	void			(*unreg_all)(struct trace_event_file *file);
@@ -1905,14 +1968,7 @@ extern struct trace_iterator *tracepoint_print_iter;
  */
 static __always_inline void trace_iterator_reset(struct trace_iterator *iter)
 {
-	const size_t offset = offsetof(struct trace_iterator, seq);
-
-	/*
-	 * Keep gcc from complaining about overwriting more than just one
-	 * member in the structure.
-	 */
-	memset((char *)iter + offset, 0, sizeof(struct trace_iterator) - offset);
-
+	memset_startat(iter, 0, seq);
 	iter->pos = -1;
 }
 
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 8d252f63cd78..0580287d7a0d 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -430,6 +430,8 @@ trace_boot_init_histograms(struct trace_event_file *file,
 		/* All digit started node should be instances. */
 		if (trace_boot_compose_hist_cmd(node, buf, size) == 0) {
 			tmp = kstrdup(buf, GFP_KERNEL);
+			if (!tmp)
+				return;
 			if (trigger_process_regex(file, buf) < 0)
 				pr_err("Failed to apply hist trigger: %s\n", tmp);
 			kfree(tmp);
@@ -439,6 +441,8 @@ trace_boot_init_histograms(struct trace_event_file *file,
 	if (xbc_node_find_subkey(hnode, "keys")) {
 		if (trace_boot_compose_hist_cmd(hnode, buf, size) == 0) {
 			tmp = kstrdup(buf, GFP_KERNEL);
+			if (!tmp)
+				return;
 			if (trigger_process_regex(file, buf) < 0)
 				pr_err("Failed to apply hist trigger: %s\n", tmp);
 			kfree(tmp);
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index 1110112e55bd..e34e8182ee4b 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -262,7 +262,7 @@ static __init int init_dynamic_event(void)
 	if (ret)
 		return 0;
 
-	entry = tracefs_create_file("dynamic_events", 0644, NULL,
+	entry = tracefs_create_file("dynamic_events", TRACE_MODE_WRITE, NULL,
 				    NULL, &dynamic_events_ops);
 
 	/* Event list interface */
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 928867f527e7..191db32dec46 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -489,18 +489,12 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec)
 	if (trace_trigger_soft_disabled(edata->file))
 		return;
 
-	fbuffer.trace_ctx = tracing_gen_ctx();
-	fbuffer.trace_file = edata->file;
-
 	dsize = get_eprobe_size(&edata->ep->tp, rec);
-	fbuffer.regs = NULL;
-
-	fbuffer.event =
-		trace_event_buffer_lock_reserve(&fbuffer.buffer, edata->file,
-					call->event.type,
-					sizeof(*entry) + edata->ep->tp.size + dsize,
-					fbuffer.trace_ctx);
-	if (!fbuffer.event)
+
+	entry = trace_event_buffer_reserve(&fbuffer, edata->file,
+					   sizeof(*entry) + edata->ep->tp.size + dsize);
+
+	if (!entry)
 		return;
 
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
@@ -549,29 +543,29 @@ static void eprobe_trigger_func(struct event_trigger_data *data,
 }
 
 static struct event_trigger_ops eprobe_trigger_ops = {
-	.func			= eprobe_trigger_func,
+	.trigger		= eprobe_trigger_func,
 	.print			= eprobe_trigger_print,
 	.init			= eprobe_trigger_init,
 	.free			= eprobe_trigger_free,
 };
 
-static int eprobe_trigger_cmd_func(struct event_command *cmd_ops,
-				   struct trace_event_file *file,
-				   char *glob, char *cmd, char *param)
+static int eprobe_trigger_cmd_parse(struct event_command *cmd_ops,
+				    struct trace_event_file *file,
+				    char *glob, char *cmd, char *param)
 {
 	return -1;
 }
 
-static int eprobe_trigger_reg_func(char *glob, struct event_trigger_ops *ops,
-				 struct event_trigger_data *data,
-				 struct trace_event_file *file)
+static int eprobe_trigger_reg_func(char *glob,
+				   struct event_trigger_data *data,
+				   struct trace_event_file *file)
 {
 	return -1;
 }
 
-static void eprobe_trigger_unreg_func(char *glob, struct event_trigger_ops *ops,
-				    struct event_trigger_data *data,
-				    struct trace_event_file *file)
+static void eprobe_trigger_unreg_func(char *glob,
+				      struct event_trigger_data *data,
+				      struct trace_event_file *file)
 {
 
 }
@@ -586,7 +580,7 @@ static struct event_command event_trigger_cmd = {
 	.name			= "eprobe",
 	.trigger_type		= ETT_EVENT_EPROBE,
 	.flags			= EVENT_CMD_FL_NEEDS_REC,
-	.func			= eprobe_trigger_cmd_func,
+	.parse			= eprobe_trigger_cmd_parse,
 	.reg			= eprobe_trigger_reg_func,
 	.unreg			= eprobe_trigger_unreg_func,
 	.unreg_all		= NULL,
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 6aed10e2f7ce..a114549720d6 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -400,7 +400,8 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp)
 	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
 
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
-		      "perf buffer not large enough"))
+		      "perf buffer not large enough, wanted %d, have %d",
+		      size, PERF_MAX_TRACE_SIZE))
 		return NULL;
 
 	*rctxp = rctx = perf_swevent_get_recursion_context();
@@ -441,13 +442,13 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 	if (!rcu_is_watching())
 		return;
 
-	if ((unsigned long)ops->private != smp_processor_id())
-		return;
-
 	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
+	if ((unsigned long)ops->private != smp_processor_id())
+		goto out;
+
 	event = container_of(ops, struct perf_event, ftrace_ops);
 
 	/*
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 830b3b9940f4..3147614c1812 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -885,10 +885,10 @@ static void __ftrace_clear_event_pids(struct trace_array *tr, int type)
 	tracepoint_synchronize_unregister();
 
 	if ((type & TRACE_PIDS) && pid_list)
-		trace_free_pid_list(pid_list);
+		trace_pid_list_free(pid_list);
 
 	if ((type & TRACE_NO_PIDS) && no_pid_list)
-		trace_free_pid_list(no_pid_list);
+		trace_pid_list_free(no_pid_list);
 }
 
 static void ftrace_clear_event_pids(struct trace_array *tr, int type)
@@ -1967,7 +1967,7 @@ event_pid_write(struct file *filp, const char __user *ubuf,
 
 	if (filtered_pids) {
 		tracepoint_synchronize_unregister();
-		trace_free_pid_list(filtered_pids);
+		trace_pid_list_free(filtered_pids);
 	} else if (pid_list && !other_pids) {
 		register_pid_events(tr);
 	}
@@ -2312,7 +2312,8 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 	/* the ftrace system is special, do not create enable or filter files */
 	if (strcmp(name, "ftrace") != 0) {
 
-		entry = tracefs_create_file("filter", 0644, dir->entry, dir,
+		entry = tracefs_create_file("filter", TRACE_MODE_WRITE,
+					    dir->entry, dir,
 					    &ftrace_subsystem_filter_fops);
 		if (!entry) {
 			kfree(system->filter);
@@ -2320,7 +2321,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 			pr_warn("Could not create tracefs '%s/filter' entry\n", name);
 		}
 
-		trace_create_file("enable", 0644, dir->entry, dir,
+		trace_create_file("enable", TRACE_MODE_WRITE, dir->entry, dir,
 				  &ftrace_system_enable_fops);
 	}
 
@@ -2402,12 +2403,12 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	}
 
 	if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
-		trace_create_file("enable", 0644, file->dir, file,
+		trace_create_file("enable", TRACE_MODE_WRITE, file->dir, file,
 				  &ftrace_enable_fops);
 
 #ifdef CONFIG_PERF_EVENTS
 	if (call->event.type && call->class->reg)
-		trace_create_file("id", 0444, file->dir,
+		trace_create_file("id", TRACE_MODE_READ, file->dir,
 				  (void *)(long)call->event.type,
 				  &ftrace_event_id_fops);
 #endif
@@ -2423,22 +2424,22 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	 * triggers or filters.
 	 */
 	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
-		trace_create_file("filter", 0644, file->dir, file,
-				  &ftrace_event_filter_fops);
+		trace_create_file("filter", TRACE_MODE_WRITE, file->dir,
+				  file, &ftrace_event_filter_fops);
 
-		trace_create_file("trigger", 0644, file->dir, file,
-				  &event_trigger_fops);
+		trace_create_file("trigger", TRACE_MODE_WRITE, file->dir,
+				  file, &event_trigger_fops);
 	}
 
 #ifdef CONFIG_HIST_TRIGGERS
-	trace_create_file("hist", 0444, file->dir, file,
+	trace_create_file("hist", TRACE_MODE_READ, file->dir, file,
 			  &event_hist_fops);
 #endif
 #ifdef CONFIG_HIST_TRIGGERS_DEBUG
-	trace_create_file("hist_debug", 0444, file->dir, file,
+	trace_create_file("hist_debug", TRACE_MODE_READ, file->dir, file,
 			  &event_hist_debug_fops);
 #endif
-	trace_create_file("format", 0444, file->dir, call,
+	trace_create_file("format", TRACE_MODE_READ, file->dir, call,
 			  &ftrace_event_format_fops);
 
 #ifdef CONFIG_TRACE_EVENT_INJECT
@@ -2677,12 +2678,24 @@ static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)
 {
+	struct trace_pid_list *no_pid_list;
+	struct trace_pid_list *pid_list;
 	struct trace_event_file *file;
+	unsigned int first;
 
 	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
 	if (!file)
 		return NULL;
 
+	pid_list = rcu_dereference_protected(tr->filtered_pids,
+					     lockdep_is_held(&event_mutex));
+	no_pid_list = rcu_dereference_protected(tr->filtered_no_pids,
+					     lockdep_is_held(&event_mutex));
+
+	if (!trace_pid_list_first(pid_list, &first) ||
+	    !trace_pid_list_first(no_pid_list, &first))
+		file->flags |= EVENT_FILE_FL_PID_FILTER;
+
 	file->event_call = call;
 	file->tr = tr;
 	atomic_set(&file->sm_ref, 0);
@@ -3433,7 +3446,7 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 	struct dentry *d_events;
 	struct dentry *entry;
 
-	entry = tracefs_create_file("set_event", 0644, parent,
+	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");
@@ -3446,37 +3459,32 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 		return -ENOMEM;
 	}
 
-	entry = trace_create_file("enable", 0644, d_events,
+	entry = trace_create_file("enable", TRACE_MODE_WRITE, d_events,
 				  tr, &ftrace_tr_enable_fops);
-	if (!entry) {
-		pr_warn("Could not create tracefs 'enable' entry\n");
+	if (!entry)
 		return -ENOMEM;
-	}
 
 	/* There are not as crucial, just warn if they are not created */
 
-	entry = tracefs_create_file("set_event_pid", 0644, parent,
+	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");
 
-	entry = tracefs_create_file("set_event_notrace_pid", 0644, parent,
-				    tr, &ftrace_set_event_notrace_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");
 
 	/* ring buffer internal formats */
-	entry = trace_create_file("header_page", 0444, d_events,
+	trace_create_file("header_page", TRACE_MODE_READ, d_events,
 				  ring_buffer_print_page_header,
 				  &ftrace_show_header_fops);
-	if (!entry)
-		pr_warn("Could not create tracefs 'header_page' entry\n");
 
-	entry = trace_create_file("header_event", 0444, d_events,
+	trace_create_file("header_event", TRACE_MODE_READ, d_events,
 				  ring_buffer_print_entry_header,
 				  &ftrace_show_header_fops);
-	if (!entry)
-		pr_warn("Could not create tracefs 'header_event' entry\n");
 
 	tr->event_dir = d_events;
 
@@ -3689,8 +3697,8 @@ __init int event_trace_init(void)
 	if (!tr)
 		return -ENODEV;
 
-	entry = tracefs_create_file("available_events", 0444, NULL,
-				    tr, &ftrace_avail_fops);
+	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");
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index c9124038b140..b458a9afa2c0 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  */
 
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/mutex.h>
@@ -654,6 +655,52 @@ DEFINE_EQUALITY_PRED(32);
 DEFINE_EQUALITY_PRED(16);
 DEFINE_EQUALITY_PRED(8);
 
+/* user space strings temp buffer */
+#define USTRING_BUF_SIZE	1024
+
+struct ustring_buffer {
+	char		buffer[USTRING_BUF_SIZE];
+};
+
+static __percpu struct ustring_buffer *ustring_per_cpu;
+
+static __always_inline char *test_string(char *str)
+{
+	struct ustring_buffer *ubuf;
+	char *kstr;
+
+	if (!ustring_per_cpu)
+		return NULL;
+
+	ubuf = this_cpu_ptr(ustring_per_cpu);
+	kstr = ubuf->buffer;
+
+	/* For safety, do not trust the string pointer */
+	if (!strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE))
+		return NULL;
+	return kstr;
+}
+
+static __always_inline char *test_ustring(char *str)
+{
+	struct ustring_buffer *ubuf;
+	char __user *ustr;
+	char *kstr;
+
+	if (!ustring_per_cpu)
+		return NULL;
+
+	ubuf = this_cpu_ptr(ustring_per_cpu);
+	kstr = ubuf->buffer;
+
+	/* user space address? */
+	ustr = (char __user *)str;
+	if (!strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE))
+		return NULL;
+
+	return kstr;
+}
+
 /* Filter predicate for fixed sized arrays of characters */
 static int filter_pred_string(struct filter_pred *pred, void *event)
 {
@@ -667,19 +714,43 @@ static int filter_pred_string(struct filter_pred *pred, void *event)
 	return match;
 }
 
-/* Filter predicate for char * pointers */
-static int filter_pred_pchar(struct filter_pred *pred, void *event)
+static __always_inline int filter_pchar(struct filter_pred *pred, char *str)
 {
-	char **addr = (char **)(event + pred->offset);
 	int cmp, match;
-	int len = strlen(*addr) + 1;	/* including tailing '\0' */
+	int len;
 
-	cmp = pred->regex.match(*addr, &pred->regex, len);
+	len = strlen(str) + 1;	/* including tailing '\0' */
+	cmp = pred->regex.match(str, &pred->regex, len);
 
 	match = cmp ^ pred->not;
 
 	return match;
 }
+/* Filter predicate for char * pointers */
+static int filter_pred_pchar(struct filter_pred *pred, void *event)
+{
+	char **addr = (char **)(event + pred->offset);
+	char *str;
+
+	str = test_string(*addr);
+	if (!str)
+		return 0;
+
+	return filter_pchar(pred, str);
+}
+
+/* Filter predicate for char * pointers in user space*/
+static int filter_pred_pchar_user(struct filter_pred *pred, void *event)
+{
+	char **addr = (char **)(event + pred->offset);
+	char *str;
+
+	str = test_ustring(*addr);
+	if (!str)
+		return 0;
+
+	return filter_pchar(pred, str);
+}
 
 /*
  * Filter predicate for dynamic sized arrays of characters.
@@ -706,6 +777,29 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event)
 	return match;
 }
 
+/*
+ * Filter predicate for relative dynamic sized arrays of characters.
+ * These are implemented through a list of strings at the end
+ * of the entry as same as dynamic string.
+ * The difference is that the relative one records the location offset
+ * from the field itself, not the event entry.
+ */
+static int filter_pred_strrelloc(struct filter_pred *pred, void *event)
+{
+	u32 *item = (u32 *)(event + pred->offset);
+	u32 str_item = *item;
+	int str_loc = str_item & 0xffff;
+	int str_len = str_item >> 16;
+	char *addr = (char *)(&item[1]) + str_loc;
+	int cmp, match;
+
+	cmp = pred->regex.match(addr, &pred->regex, str_len);
+
+	match = cmp ^ pred->not;
+
+	return match;
+}
+
 /* Filter predicate for CPUs. */
 static int filter_pred_cpu(struct filter_pred *pred, void *event)
 {
@@ -756,7 +850,7 @@ static int filter_pred_none(struct filter_pred *pred, void *event)
  *
  * Note:
  * - @str might not be NULL-terminated if it's of type DYN_STRING
- *   or STATIC_STRING, unless @len is zero.
+ *   RDYN_STRING, or STATIC_STRING, unless @len is zero.
  */
 
 static int regex_match_full(char *str, struct regex *r, int len)
@@ -1083,6 +1177,9 @@ int filter_assign_type(const char *type)
 	if (strstr(type, "__data_loc") && strstr(type, "char"))
 		return FILTER_DYN_STRING;
 
+	if (strstr(type, "__rel_loc") && strstr(type, "char"))
+		return FILTER_RDYN_STRING;
+
 	if (strchr(type, '[') && strstr(type, "char"))
 		return FILTER_STATIC_STRING;
 
@@ -1158,6 +1255,7 @@ static int parse_pred(const char *str, void *data,
 	struct filter_pred *pred = NULL;
 	char num_buf[24];	/* Big enough to hold an address */
 	char *field_name;
+	bool ustring = false;
 	char q;
 	u64 val;
 	int len;
@@ -1192,6 +1290,12 @@ static int parse_pred(const char *str, void *data,
 		return -EINVAL;
 	}
 
+	/* See if the field is a user space string */
+	if ((len = str_has_prefix(str + i, ".ustring"))) {
+		ustring = true;
+		i += len;
+	}
+
 	while (isspace(str[i]))
 		i++;
 
@@ -1318,10 +1422,24 @@ static int parse_pred(const char *str, void *data,
 			pred->fn = filter_pred_string;
 			pred->regex.field_len = field->size;
 
-		} else if (field->filter_type == FILTER_DYN_STRING)
+		} else if (field->filter_type == FILTER_DYN_STRING) {
 			pred->fn = filter_pred_strloc;
-		else
-			pred->fn = filter_pred_pchar;
+		} else if (field->filter_type == FILTER_RDYN_STRING)
+			pred->fn = filter_pred_strrelloc;
+		else {
+
+			if (!ustring_per_cpu) {
+				/* Once allocated, keep it around for good */
+				ustring_per_cpu = alloc_percpu(struct ustring_buffer);
+				if (!ustring_per_cpu)
+					goto err_mem;
+			}
+
+			if (ustring)
+				pred->fn = filter_pred_pchar_user;
+			else
+				pred->fn = filter_pred_pchar;
+		}
 		/* go past the last quote */
 		i++;
 
@@ -1387,6 +1505,9 @@ static int parse_pred(const char *str, void *data,
 err_free:
 	kfree(pred);
 	return -EINVAL;
+err_mem:
+	kfree(pred);
+	return -ENOMEM;
 }
 
 enum {
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index f01e442716e2..ada87bfb5bb8 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -66,7 +66,10 @@
 	C(EMPTY_SORT_FIELD,	"Empty sort field"),			\
 	C(TOO_MANY_SORT_FIELDS,	"Too many sort fields (Max = 2)"),	\
 	C(INVALID_SORT_FIELD,	"Sort field must be a key or a val"),	\
-	C(INVALID_STR_OPERAND,	"String type can not be an operand in expression"),
+	C(INVALID_STR_OPERAND,	"String type can not be an operand in expression"), \
+	C(EXPECT_NUMBER,	"Expecting numeric literal"),		\
+	C(UNARY_MINUS_SUBEXPR,	"Unary minus not supported in sub-expressions"), \
+	C(DIVISION_BY_ZERO,	"Division by zero"),
 
 #undef C
 #define C(a, b)		HIST_ERR_##a
@@ -89,12 +92,16 @@ typedef u64 (*hist_field_fn_t) (struct hist_field *field,
 #define HIST_FIELD_OPERANDS_MAX	2
 #define HIST_FIELDS_MAX		(TRACING_MAP_FIELDS_MAX + TRACING_MAP_VARS_MAX)
 #define HIST_ACTIONS_MAX	8
+#define HIST_CONST_DIGITS_MAX	21
+#define HIST_DIV_SHIFT		20  /* For optimizing division by constants */
 
 enum field_op_id {
 	FIELD_OP_NONE,
 	FIELD_OP_PLUS,
 	FIELD_OP_MINUS,
 	FIELD_OP_UNARY_MINUS,
+	FIELD_OP_DIV,
+	FIELD_OP_MULT,
 };
 
 /*
@@ -152,6 +159,11 @@ struct hist_field {
 	bool                            read_once;
 
 	unsigned int			var_str_idx;
+
+	/* Numeric literals are represented as u64 */
+	u64				constant;
+	/* Used to optimize division by constants */
+	u64				div_multiplier;
 };
 
 static u64 hist_field_none(struct hist_field *field,
@@ -163,6 +175,15 @@ static u64 hist_field_none(struct hist_field *field,
 	return 0;
 }
 
+static u64 hist_field_const(struct hist_field *field,
+			   struct tracing_map_elt *elt,
+			   struct trace_buffer *buffer,
+			   struct ring_buffer_event *rbe,
+			   void *event)
+{
+	return field->constant;
+}
+
 static u64 hist_field_counter(struct hist_field *field,
 			      struct tracing_map_elt *elt,
 			      struct trace_buffer *buffer,
@@ -196,6 +217,20 @@ static u64 hist_field_dynstring(struct hist_field *hist_field,
 	return (u64)(unsigned long)addr;
 }
 
+static u64 hist_field_reldynstring(struct hist_field *hist_field,
+				   struct tracing_map_elt *elt,
+				   struct trace_buffer *buffer,
+				   struct ring_buffer_event *rbe,
+				   void *event)
+{
+	u32 *item = event + hist_field->field->offset;
+	u32 str_item = *item;
+	int str_loc = str_item & 0xffff;
+	char *addr = (char *)&item[1] + str_loc;
+
+	return (u64)(unsigned long)addr;
+}
+
 static u64 hist_field_pstring(struct hist_field *hist_field,
 			      struct tracing_map_elt *elt,
 			      struct trace_buffer *buffer,
@@ -271,6 +306,106 @@ static u64 hist_field_minus(struct hist_field *hist_field,
 	return val1 - val2;
 }
 
+static u64 hist_field_div(struct hist_field *hist_field,
+			   struct tracing_map_elt *elt,
+			   struct trace_buffer *buffer,
+			   struct ring_buffer_event *rbe,
+			   void *event)
+{
+	struct hist_field *operand1 = hist_field->operands[0];
+	struct hist_field *operand2 = hist_field->operands[1];
+
+	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+	u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);
+
+	/* Return -1 for the undefined case */
+	if (!val2)
+		return -1;
+
+	/* Use shift if the divisor is a power of 2 */
+	if (!(val2 & (val2 - 1)))
+		return val1 >> __ffs64(val2);
+
+	return div64_u64(val1, val2);
+}
+
+static u64 div_by_power_of_two(struct hist_field *hist_field,
+				struct tracing_map_elt *elt,
+				struct trace_buffer *buffer,
+				struct ring_buffer_event *rbe,
+				void *event)
+{
+	struct hist_field *operand1 = hist_field->operands[0];
+	struct hist_field *operand2 = hist_field->operands[1];
+
+	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+
+	return val1 >> __ffs64(operand2->constant);
+}
+
+static u64 div_by_not_power_of_two(struct hist_field *hist_field,
+				struct tracing_map_elt *elt,
+				struct trace_buffer *buffer,
+				struct ring_buffer_event *rbe,
+				void *event)
+{
+	struct hist_field *operand1 = hist_field->operands[0];
+	struct hist_field *operand2 = hist_field->operands[1];
+
+	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+
+	return div64_u64(val1, operand2->constant);
+}
+
+static u64 div_by_mult_and_shift(struct hist_field *hist_field,
+				struct tracing_map_elt *elt,
+				struct trace_buffer *buffer,
+				struct ring_buffer_event *rbe,
+				void *event)
+{
+	struct hist_field *operand1 = hist_field->operands[0];
+	struct hist_field *operand2 = hist_field->operands[1];
+
+	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+
+	/*
+	 * If the divisor is a constant, do a multiplication and shift instead.
+	 *
+	 * Choose Z = some power of 2. If Y <= Z, then:
+	 *     X / Y = (X * (Z / Y)) / Z
+	 *
+	 * (Z / Y) is a constant (mult) which is calculated at parse time, so:
+	 *     X / Y = (X * mult) / Z
+	 *
+	 * The division by Z can be replaced by a shift since Z is a power of 2:
+	 *     X / Y = (X * mult) >> HIST_DIV_SHIFT
+	 *
+	 * As long, as X < Z the results will not be off by more than 1.
+	 */
+	if (val1 < (1 << HIST_DIV_SHIFT)) {
+		u64 mult = operand2->div_multiplier;
+
+		return (val1 * mult + ((1 << HIST_DIV_SHIFT) - 1)) >> HIST_DIV_SHIFT;
+	}
+
+	return div64_u64(val1, operand2->constant);
+}
+
+static u64 hist_field_mult(struct hist_field *hist_field,
+			   struct tracing_map_elt *elt,
+			   struct trace_buffer *buffer,
+			   struct ring_buffer_event *rbe,
+			   void *event)
+{
+	struct hist_field *operand1 = hist_field->operands[0];
+	struct hist_field *operand2 = hist_field->operands[1];
+
+	u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event);
+	u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event);
+
+	return val1 * val2;
+}
+
 static u64 hist_field_unary_minus(struct hist_field *hist_field,
 				  struct tracing_map_elt *elt,
 				  struct trace_buffer *buffer,
@@ -341,6 +476,7 @@ enum hist_field_flags {
 	HIST_FIELD_FL_CPU		= 1 << 15,
 	HIST_FIELD_FL_ALIAS		= 1 << 16,
 	HIST_FIELD_FL_BUCKET		= 1 << 17,
+	HIST_FIELD_FL_CONST		= 1 << 18,
 };
 
 struct var_defs {
@@ -517,6 +653,25 @@ struct snapshot_context {
 	void			*key;
 };
 
+/*
+ * Returns the specific division function to use if the divisor
+ * is constant. This avoids extra branches when the trigger is hit.
+ */
+static hist_field_fn_t hist_field_get_div_fn(struct hist_field *divisor)
+{
+	u64 div = divisor->constant;
+
+	if (!(div & (div - 1)))
+		return div_by_power_of_two;
+
+	/* If the divisor is too large, do a regular division */
+	if (div > (1 << HIST_DIV_SHIFT))
+		return div_by_not_power_of_two;
+
+	divisor->div_multiplier = div64_u64((u64)(1 << HIST_DIV_SHIFT), div);
+	return div_by_mult_and_shift;
+}
+
 static void track_data_free(struct track_data *track_data)
 {
 	struct hist_elt_data *elt_data;
@@ -1516,6 +1671,12 @@ static void expr_field_str(struct hist_field *field, char *expr)
 {
 	if (field->flags & HIST_FIELD_FL_VAR_REF)
 		strcat(expr, "$");
+	else if (field->flags & HIST_FIELD_FL_CONST) {
+		char str[HIST_CONST_DIGITS_MAX];
+
+		snprintf(str, HIST_CONST_DIGITS_MAX, "%llu", field->constant);
+		strcat(expr, str);
+	}
 
 	strcat(expr, hist_field_name(field, 0));
 
@@ -1571,6 +1732,12 @@ static char *expr_str(struct hist_field *field, unsigned int level)
 	case FIELD_OP_PLUS:
 		strcat(expr, "+");
 		break;
+	case FIELD_OP_DIV:
+		strcat(expr, "/");
+		break;
+	case FIELD_OP_MULT:
+		strcat(expr, "*");
+		break;
 	default:
 		kfree(expr);
 		return NULL;
@@ -1581,34 +1748,92 @@ static char *expr_str(struct hist_field *field, unsigned int level)
 	return expr;
 }
 
-static int contains_operator(char *str)
+/*
+ * If field_op != FIELD_OP_NONE, *sep points to the root operator
+ * of the expression tree to be evaluated.
+ */
+static int contains_operator(char *str, char **sep)
 {
 	enum field_op_id field_op = FIELD_OP_NONE;
-	char *op;
+	char *minus_op, *plus_op, *div_op, *mult_op;
 
-	op = strpbrk(str, "+-");
-	if (!op)
-		return FIELD_OP_NONE;
 
-	switch (*op) {
-	case '-':
+	/*
+	 * Report the last occurrence of the operators first, so that the
+	 * expression is evaluated left to right. This is important since
+	 * subtraction and division are not associative.
+	 *
+	 *	e.g
+	 *		64/8/4/2 is 1, i.e 64/8/4/2 = ((64/8)/4)/2
+	 *		14-7-5-2 is 0, i.e 14-7-5-2 = ((14-7)-5)-2
+	 */
+
+	/*
+	 * First, find lower precedence addition and subtraction
+	 * since the expression will be evaluated recursively.
+	 */
+	minus_op = strrchr(str, '-');
+	if (minus_op) {
 		/*
-		 * Unfortunately, the modifier ".sym-offset"
-		 * can confuse things.
+		 * Unary minus is not supported in sub-expressions. If
+		 * present, it is always the next root operator.
 		 */
-		if (op - str >= 4 && !strncmp(op - 4, ".sym-offset", 11))
-			return FIELD_OP_NONE;
-
-		if (*str == '-')
+		if (minus_op == str) {
 			field_op = FIELD_OP_UNARY_MINUS;
-		else
-			field_op = FIELD_OP_MINUS;
-		break;
-	case '+':
-		field_op = FIELD_OP_PLUS;
-		break;
-	default:
-		break;
+			goto out;
+		}
+
+		field_op = FIELD_OP_MINUS;
+	}
+
+	plus_op = strrchr(str, '+');
+	if (plus_op || minus_op) {
+		/*
+		 * For operators of the same precedence use to rightmost as the
+		 * root, so that the expression is evaluated left to right.
+		 */
+		if (plus_op > minus_op)
+			field_op = FIELD_OP_PLUS;
+		goto out;
+	}
+
+	/*
+	 * Multiplication and division have higher precedence than addition and
+	 * subtraction.
+	 */
+	div_op = strrchr(str, '/');
+	if (div_op)
+		field_op = FIELD_OP_DIV;
+
+	mult_op = strrchr(str, '*');
+	/*
+	 * For operators of the same precedence use to rightmost as the
+	 * root, so that the expression is evaluated left to right.
+	 */
+	if (mult_op > div_op)
+		field_op = FIELD_OP_MULT;
+
+out:
+	if (sep) {
+		switch (field_op) {
+		case FIELD_OP_UNARY_MINUS:
+		case FIELD_OP_MINUS:
+			*sep = minus_op;
+			break;
+		case FIELD_OP_PLUS:
+			*sep = plus_op;
+			break;
+		case FIELD_OP_DIV:
+			*sep = div_op;
+			break;
+		case FIELD_OP_MULT:
+			*sep = mult_op;
+			break;
+		case FIELD_OP_NONE:
+		default:
+			*sep = NULL;
+			break;
+		}
 	}
 
 	return field_op;
@@ -1689,6 +1914,15 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 		goto out;
 	}
 
+	if (flags & HIST_FIELD_FL_CONST) {
+		hist_field->fn = hist_field_const;
+		hist_field->size = sizeof(u64);
+		hist_field->type = kstrdup("u64", GFP_KERNEL);
+		if (!hist_field->type)
+			goto free;
+		goto out;
+	}
+
 	if (flags & HIST_FIELD_FL_STACKTRACE) {
 		hist_field->fn = hist_field_none;
 		goto out;
@@ -1733,10 +1967,13 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 		if (!hist_field->type)
 			goto free;
 
-		if (field->filter_type == FILTER_STATIC_STRING)
+		if (field->filter_type == FILTER_STATIC_STRING) {
 			hist_field->fn = hist_field_string;
-		else if (field->filter_type == FILTER_DYN_STRING)
+			hist_field->size = field->size;
+		} else if (field->filter_type == FILTER_DYN_STRING) {
 			hist_field->fn = hist_field_dynstring;
+		} else if (field->filter_type == FILTER_RDYN_STRING)
+			hist_field->fn = hist_field_reldynstring;
 		else
 			hist_field->fn = hist_field_pstring;
 	} else {
@@ -1925,7 +2162,7 @@ static char *field_name_from_var(struct hist_trigger_data *hist_data,
 
 		if (strcmp(var_name, name) == 0) {
 			field = hist_data->attrs->var_defs.expr[i];
-			if (contains_operator(field) || is_var_ref(field))
+			if (contains_operator(field, NULL) || is_var_ref(field))
 				continue;
 			return field;
 		}
@@ -2002,7 +2239,11 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 			*flags |= HIST_FIELD_FL_HEX;
 		else if (strcmp(modifier, "sym") == 0)
 			*flags |= HIST_FIELD_FL_SYM;
-		else if (strcmp(modifier, "sym-offset") == 0)
+		/*
+		 * 'sym-offset' occurrences in the trigger string are modified
+		 * to 'symXoffset' to simplify arithmetic expression parsing.
+		 */
+		else if (strcmp(modifier, "symXoffset") == 0)
 			*flags |= HIST_FIELD_FL_SYM_OFFSET;
 		else if ((strcmp(modifier, "execname") == 0) &&
 			 (strcmp(field_name, "common_pid") == 0))
@@ -2090,6 +2331,29 @@ static struct hist_field *create_alias(struct hist_trigger_data *hist_data,
 	return alias;
 }
 
+static struct hist_field *parse_const(struct hist_trigger_data *hist_data,
+				      char *str, char *var_name,
+				      unsigned long *flags)
+{
+	struct trace_array *tr = hist_data->event_file->tr;
+	struct hist_field *field = NULL;
+	u64 constant;
+
+	if (kstrtoull(str, 0, &constant)) {
+		hist_err(tr, HIST_ERR_EXPECT_NUMBER, errpos(str));
+		return NULL;
+	}
+
+	*flags |= HIST_FIELD_FL_CONST;
+	field = create_hist_field(hist_data, NULL, *flags, var_name);
+	if (!field)
+		return NULL;
+
+	field->constant = constant;
+
+	return field;
+}
+
 static struct hist_field *parse_atom(struct hist_trigger_data *hist_data,
 				     struct trace_event_file *file, char *str,
 				     unsigned long *flags, char *var_name)
@@ -2100,6 +2364,15 @@ static struct hist_field *parse_atom(struct hist_trigger_data *hist_data,
 	unsigned long buckets = 0;
 	int ret = 0;
 
+	if (isdigit(str[0])) {
+		hist_field = parse_const(hist_data, str, var_name, flags);
+		if (!hist_field) {
+			ret = -EINVAL;
+			goto out;
+		}
+		return hist_field;
+	}
+
 	s = strchr(str, '.');
 	if (s) {
 		s = strchr(++s, '.');
@@ -2156,21 +2429,24 @@ static struct hist_field *parse_atom(struct hist_trigger_data *hist_data,
 static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 				     struct trace_event_file *file,
 				     char *str, unsigned long flags,
-				     char *var_name, unsigned int level);
+				     char *var_name, unsigned int *n_subexprs);
 
 static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
 				      struct trace_event_file *file,
 				      char *str, unsigned long flags,
-				      char *var_name, unsigned int level)
+				      char *var_name, unsigned int *n_subexprs)
 {
 	struct hist_field *operand1, *expr = NULL;
 	unsigned long operand_flags;
 	int ret = 0;
 	char *s;
 
+	/* Unary minus operator, increment n_subexprs */
+	++*n_subexprs;
+
 	/* we support only -(xxx) i.e. explicit parens required */
 
-	if (level > 3) {
+	if (*n_subexprs > 3) {
 		hist_err(file->tr, HIST_ERR_TOO_MANY_SUBEXPR, errpos(str));
 		ret = -EINVAL;
 		goto free;
@@ -2187,8 +2463,16 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
 	}
 
 	s = strrchr(str, ')');
-	if (s)
+	if (s) {
+		 /* unary minus not supported in sub-expressions */
+		if (*(s+1) != '\0') {
+			hist_err(file->tr, HIST_ERR_UNARY_MINUS_SUBEXPR,
+				 errpos(str));
+			ret = -EINVAL;
+			goto free;
+		}
 		*s = '\0';
+	}
 	else {
 		ret = -EINVAL; /* no closing ')' */
 		goto free;
@@ -2202,7 +2486,7 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
 	}
 
 	operand_flags = 0;
-	operand1 = parse_expr(hist_data, file, str, operand_flags, NULL, ++level);
+	operand1 = parse_expr(hist_data, file, str, operand_flags, NULL, n_subexprs);
 	if (IS_ERR(operand1)) {
 		ret = PTR_ERR(operand1);
 		goto free;
@@ -2219,6 +2503,8 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
 		(HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
 	expr->fn = hist_field_unary_minus;
 	expr->operands[0] = operand1;
+	expr->size = operand1->size;
+	expr->is_signed = operand1->is_signed;
 	expr->operator = FIELD_OP_UNARY_MINUS;
 	expr->name = expr_str(expr, 0);
 	expr->type = kstrdup_const(operand1->type, GFP_KERNEL);
@@ -2233,9 +2519,15 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
 	return ERR_PTR(ret);
 }
 
+/*
+ * If the operands are var refs, return pointers the
+ * variable(s) referenced in var1 and var2, else NULL.
+ */
 static int check_expr_operands(struct trace_array *tr,
 			       struct hist_field *operand1,
-			       struct hist_field *operand2)
+			       struct hist_field *operand2,
+			       struct hist_field **var1,
+			       struct hist_field **var2)
 {
 	unsigned long operand1_flags = operand1->flags;
 	unsigned long operand2_flags = operand2->flags;
@@ -2248,6 +2540,7 @@ static int check_expr_operands(struct trace_array *tr,
 		if (!var)
 			return -EINVAL;
 		operand1_flags = var->flags;
+		*var1 = var;
 	}
 
 	if ((operand2_flags & HIST_FIELD_FL_VAR_REF) ||
@@ -2258,6 +2551,7 @@ static int check_expr_operands(struct trace_array *tr,
 		if (!var)
 			return -EINVAL;
 		operand2_flags = var->flags;
+		*var2 = var;
 	}
 
 	if ((operand1_flags & HIST_FIELD_FL_TIMESTAMP_USECS) !=
@@ -2272,74 +2566,102 @@ static int check_expr_operands(struct trace_array *tr,
 static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 				     struct trace_event_file *file,
 				     char *str, unsigned long flags,
-				     char *var_name, unsigned int level)
+				     char *var_name, unsigned int *n_subexprs)
 {
 	struct hist_field *operand1 = NULL, *operand2 = NULL, *expr = NULL;
-	unsigned long operand_flags;
+	struct hist_field *var1 = NULL, *var2 = NULL;
+	unsigned long operand_flags, operand2_flags;
 	int field_op, ret = -EINVAL;
 	char *sep, *operand1_str;
+	hist_field_fn_t op_fn;
+	bool combine_consts;
 
-	if (level > 3) {
+	if (*n_subexprs > 3) {
 		hist_err(file->tr, HIST_ERR_TOO_MANY_SUBEXPR, errpos(str));
 		return ERR_PTR(-EINVAL);
 	}
 
-	field_op = contains_operator(str);
+	field_op = contains_operator(str, &sep);
 
 	if (field_op == FIELD_OP_NONE)
 		return parse_atom(hist_data, file, str, &flags, var_name);
 
 	if (field_op == FIELD_OP_UNARY_MINUS)
-		return parse_unary(hist_data, file, str, flags, var_name, ++level);
+		return parse_unary(hist_data, file, str, flags, var_name, n_subexprs);
 
-	switch (field_op) {
-	case FIELD_OP_MINUS:
-		sep = "-";
-		break;
-	case FIELD_OP_PLUS:
-		sep = "+";
-		break;
-	default:
-		goto free;
-	}
+	/* Binary operator found, increment n_subexprs */
+	++*n_subexprs;
 
-	operand1_str = strsep(&str, sep);
-	if (!operand1_str || !str)
-		goto free;
+	/* Split the expression string at the root operator */
+	if (!sep)
+		return ERR_PTR(-EINVAL);
+
+	*sep = '\0';
+	operand1_str = str;
+	str = sep+1;
+
+	/* Binary operator requires both operands */
+	if (*operand1_str == '\0' || *str == '\0')
+		return ERR_PTR(-EINVAL);
 
 	operand_flags = 0;
-	operand1 = parse_atom(hist_data, file, operand1_str,
-			      &operand_flags, NULL);
-	if (IS_ERR(operand1)) {
-		ret = PTR_ERR(operand1);
-		operand1 = NULL;
-		goto free;
-	}
+
+	/* LHS of string is an expression e.g. a+b in a+b+c */
+	operand1 = parse_expr(hist_data, file, operand1_str, operand_flags, NULL, n_subexprs);
+	if (IS_ERR(operand1))
+		return ERR_CAST(operand1);
+
 	if (operand1->flags & HIST_FIELD_FL_STRING) {
 		hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str));
 		ret = -EINVAL;
-		goto free;
+		goto free_op1;
 	}
 
-	/* rest of string could be another expression e.g. b+c in a+b+c */
+	/* RHS of string is another expression e.g. c in a+b+c */
 	operand_flags = 0;
-	operand2 = parse_expr(hist_data, file, str, operand_flags, NULL, ++level);
+	operand2 = parse_expr(hist_data, file, str, operand_flags, NULL, n_subexprs);
 	if (IS_ERR(operand2)) {
 		ret = PTR_ERR(operand2);
-		operand2 = NULL;
-		goto free;
+		goto free_op1;
 	}
 	if (operand2->flags & HIST_FIELD_FL_STRING) {
 		hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
 		ret = -EINVAL;
-		goto free;
+		goto free_operands;
 	}
 
-	ret = check_expr_operands(file->tr, operand1, operand2);
+	switch (field_op) {
+	case FIELD_OP_MINUS:
+		op_fn = hist_field_minus;
+		break;
+	case FIELD_OP_PLUS:
+		op_fn = hist_field_plus;
+		break;
+	case FIELD_OP_DIV:
+		op_fn = hist_field_div;
+		break;
+	case FIELD_OP_MULT:
+		op_fn = hist_field_mult;
+		break;
+	default:
+		ret = -EINVAL;
+		goto free_operands;
+	}
+
+	ret = check_expr_operands(file->tr, operand1, operand2, &var1, &var2);
 	if (ret)
-		goto free;
+		goto free_operands;
 
-	flags |= HIST_FIELD_FL_EXPR;
+	operand_flags = var1 ? var1->flags : operand1->flags;
+	operand2_flags = var2 ? var2->flags : operand2->flags;
+
+	/*
+	 * If both operands are constant, the expression can be
+	 * collapsed to a single constant.
+	 */
+	combine_consts = operand_flags & operand2_flags & HIST_FIELD_FL_CONST;
+
+	flags |= combine_consts ? HIST_FIELD_FL_CONST : HIST_FIELD_FL_EXPR;
 
 	flags |= operand1->flags &
 		(HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
@@ -2347,44 +2669,80 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 	expr = create_hist_field(hist_data, NULL, flags, var_name);
 	if (!expr) {
 		ret = -ENOMEM;
-		goto free;
+		goto free_operands;
 	}
 
 	operand1->read_once = true;
 	operand2->read_once = true;
 
+	/* The operands are now owned and free'd by 'expr' */
 	expr->operands[0] = operand1;
 	expr->operands[1] = operand2;
 
-	/* The operand sizes should be the same, so just pick one */
-	expr->size = operand1->size;
+	if (field_op == FIELD_OP_DIV &&
+			operand2_flags & HIST_FIELD_FL_CONST) {
+		u64 divisor = var2 ? var2->constant : operand2->constant;
 
-	expr->operator = field_op;
-	expr->name = expr_str(expr, 0);
-	expr->type = kstrdup_const(operand1->type, GFP_KERNEL);
-	if (!expr->type) {
-		ret = -ENOMEM;
-		goto free;
+		if (!divisor) {
+			hist_err(file->tr, HIST_ERR_DIVISION_BY_ZERO, errpos(str));
+			ret = -EDOM;
+			goto free_expr;
+		}
+
+		/*
+		 * Copy the divisor here so we don't have to look it up
+		 * later if this is a var ref
+		 */
+		operand2->constant = divisor;
+		op_fn = hist_field_get_div_fn(operand2);
 	}
 
-	switch (field_op) {
-	case FIELD_OP_MINUS:
-		expr->fn = hist_field_minus;
-		break;
-	case FIELD_OP_PLUS:
-		expr->fn = hist_field_plus;
-		break;
-	default:
-		ret = -EINVAL;
-		goto free;
+	if (combine_consts) {
+		if (var1)
+			expr->operands[0] = var1;
+		if (var2)
+			expr->operands[1] = var2;
+
+		expr->constant = op_fn(expr, NULL, NULL, NULL, NULL);
+
+		expr->operands[0] = NULL;
+		expr->operands[1] = NULL;
+
+		/*
+		 * var refs won't be destroyed immediately
+		 * See: destroy_hist_field()
+		 */
+		destroy_hist_field(operand2, 0);
+		destroy_hist_field(operand1, 0);
+
+		expr->name = expr_str(expr, 0);
+	} else {
+		expr->fn = op_fn;
+
+		/* The operand sizes should be the same, so just pick one */
+		expr->size = operand1->size;
+		expr->is_signed = operand1->is_signed;
+
+		expr->operator = field_op;
+		expr->type = kstrdup_const(operand1->type, GFP_KERNEL);
+		if (!expr->type) {
+			ret = -ENOMEM;
+			goto free_expr;
+		}
+
+		expr->name = expr_str(expr, 0);
 	}
 
 	return expr;
- free:
-	destroy_hist_field(operand1, 0);
+
+free_operands:
 	destroy_hist_field(operand2, 0);
-	destroy_hist_field(expr, 0);
+free_op1:
+	destroy_hist_field(operand1, 0);
+	return ERR_PTR(ret);
 
+free_expr:
+	destroy_hist_field(expr, 0);
 	return ERR_PTR(ret);
 }
 
@@ -2406,9 +2764,9 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data,
 }
 
 static struct event_command trigger_hist_cmd;
-static int event_hist_trigger_func(struct event_command *cmd_ops,
-				   struct trace_event_file *file,
-				   char *glob, char *cmd, char *param);
+static int event_hist_trigger_parse(struct event_command *cmd_ops,
+				    struct trace_event_file *file,
+				    char *glob, char *cmd, char *param);
 
 static bool compatible_keys(struct hist_trigger_data *target_hist_data,
 			    struct hist_trigger_data *hist_data,
@@ -2611,8 +2969,8 @@ create_field_var_hist(struct hist_trigger_data *target_hist_data,
 	var_hist->hist_data = hist_data;
 
 	/* Create the new histogram with our variable */
-	ret = event_hist_trigger_func(&trigger_hist_cmd, file,
-				      "", "hist", cmd);
+	ret = event_hist_trigger_parse(&trigger_hist_cmd, file,
+				       "", "hist", cmd);
 	if (ret) {
 		kfree(cmd);
 		kfree(var_hist->cmd);
@@ -2690,8 +3048,10 @@ static inline void __update_field_vars(struct tracing_map_elt *elt,
 		if (val->flags & HIST_FIELD_FL_STRING) {
 			char *str = elt_data->field_var_str[j++];
 			char *val_str = (char *)(uintptr_t)var_val;
+			unsigned int size;
 
-			strscpy(str, val_str, STR_VAR_LEN_MAX);
+			size = min(val->size, STR_VAR_LEN_MAX);
+			strscpy(str, val_str, size);
 			var_val = (u64)(uintptr_t)str;
 		}
 		tracing_map_set_var(elt, var_idx, var_val);
@@ -3416,7 +3776,7 @@ static int check_synth_field(struct synth_event *event,
 
 	if (strcmp(field->type, hist_field->type) != 0) {
 		if (field->size != hist_field->size ||
-		    field->is_signed != hist_field->is_signed)
+		    (!field->is_string && field->is_signed != hist_field->is_signed))
 			return -EINVAL;
 	}
 
@@ -3578,6 +3938,7 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
 
 			var_ref_idx = find_var_ref_idx(hist_data, var_ref);
 			if (WARN_ON(var_ref_idx < 0)) {
+				kfree(p);
 				ret = var_ref_idx;
 				goto err;
 			}
@@ -3751,9 +4112,9 @@ static int __create_val_field(struct hist_trigger_data *hist_data,
 			      unsigned long flags)
 {
 	struct hist_field *hist_field;
-	int ret = 0;
+	int ret = 0, n_subexprs = 0;
 
-	hist_field = parse_expr(hist_data, file, field_str, flags, var_name, 0);
+	hist_field = parse_expr(hist_data, file, field_str, flags, var_name, &n_subexprs);
 	if (IS_ERR(hist_field)) {
 		ret = PTR_ERR(hist_field);
 		goto out;
@@ -3894,7 +4255,7 @@ static int create_key_field(struct hist_trigger_data *hist_data,
 	struct hist_field *hist_field = NULL;
 	unsigned long flags = 0;
 	unsigned int key_size;
-	int ret = 0;
+	int ret = 0, n_subexprs = 0;
 
 	if (WARN_ON(key_idx >= HIST_FIELDS_MAX))
 		return -EINVAL;
@@ -3907,7 +4268,7 @@ static int create_key_field(struct hist_trigger_data *hist_data,
 		hist_field = create_hist_field(hist_data, NULL, flags, NULL);
 	} else {
 		hist_field = parse_expr(hist_data, file, field_str, flags,
-					NULL, 0);
+					NULL, &n_subexprs);
 		if (IS_ERR(hist_field)) {
 			ret = PTR_ERR(hist_field);
 			goto out;
@@ -4578,6 +4939,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
 			if (hist_field->flags & HIST_FIELD_FL_STRING) {
 				unsigned int str_start, var_str_idx, idx;
 				char *str, *val_str;
+				unsigned int size;
 
 				str_start = hist_data->n_field_var_str +
 					hist_data->n_save_var_str;
@@ -4586,7 +4948,9 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
 
 				str = elt_data->field_var_str[idx];
 				val_str = (char *)(uintptr_t)hist_val;
-				strscpy(str, val_str, STR_VAR_LEN_MAX);
+
+				size = min(hist_field->size, STR_VAR_LEN_MAX);
+				strscpy(str, val_str, size);
 
 				hist_val = (u64)(uintptr_t)str;
 			}
@@ -4617,7 +4981,8 @@ static inline void add_to_key(char *compound_key, void *key,
 		struct ftrace_event_field *field;
 
 		field = key_field->field;
-		if (field->filter_type == FILTER_DYN_STRING)
+		if (field->filter_type == FILTER_DYN_STRING ||
+		    field->filter_type == FILTER_RDYN_STRING)
 			size = *(u32 *)(rec + field->offset) >> 16;
 		else if (field->filter_type == FILTER_STATIC_STRING)
 			size = field->size;
@@ -4706,7 +5071,6 @@ static void hist_trigger_stacktrace_print(struct seq_file *m,
 					  unsigned long *stacktrace_entries,
 					  unsigned int max_entries)
 {
-	char str[KSYM_SYMBOL_LEN];
 	unsigned int spaces = 8;
 	unsigned int i;
 
@@ -4715,8 +5079,7 @@ static void hist_trigger_stacktrace_print(struct seq_file *m,
 			return;
 
 		seq_printf(m, "%*c", 1 + spaces, ' ');
-		sprint_symbol(str, stacktrace_entries[i]);
-		seq_printf(m, "%s\n", str);
+		seq_printf(m, "%pS\n", (void*)stacktrace_entries[i]);
 	}
 }
 
@@ -4726,7 +5089,6 @@ static void hist_trigger_print_key(struct seq_file *m,
 				   struct tracing_map_elt *elt)
 {
 	struct hist_field *key_field;
-	char str[KSYM_SYMBOL_LEN];
 	bool multiline = false;
 	const char *field_name;
 	unsigned int i;
@@ -4747,14 +5109,12 @@ static void hist_trigger_print_key(struct seq_file *m,
 			seq_printf(m, "%s: %llx", field_name, uval);
 		} else if (key_field->flags & HIST_FIELD_FL_SYM) {
 			uval = *(u64 *)(key + key_field->offset);
-			sprint_symbol_no_offset(str, uval);
-			seq_printf(m, "%s: [%llx] %-45s", field_name,
-				   uval, str);
+			seq_printf(m, "%s: [%llx] %-45ps", field_name,
+				   uval, (void *)(uintptr_t)uval);
 		} else if (key_field->flags & HIST_FIELD_FL_SYM_OFFSET) {
 			uval = *(u64 *)(key + key_field->offset);
-			sprint_symbol(str, uval);
-			seq_printf(m, "%s: [%llx] %-55s", field_name,
-				   uval, str);
+			seq_printf(m, "%s: [%llx] %-55pS", field_name,
+				   uval, (void *)(uintptr_t)uval);
 		} else if (key_field->flags & HIST_FIELD_FL_EXECNAME) {
 			struct hist_elt_data *elt_data = elt->private_data;
 			char *comm;
@@ -4950,6 +5310,8 @@ static void hist_field_debug_show_flags(struct seq_file *m,
 
 	if (flags & HIST_FIELD_FL_ALIAS)
 		seq_puts(m, "        HIST_FIELD_FL_ALIAS\n");
+	else if (flags & HIST_FIELD_FL_CONST)
+		seq_puts(m, "        HIST_FIELD_FL_CONST\n");
 }
 
 static int hist_field_debug_show(struct seq_file *m,
@@ -4971,6 +5333,9 @@ static int hist_field_debug_show(struct seq_file *m,
 			   field->var.idx);
 	}
 
+	if (field->flags & HIST_FIELD_FL_CONST)
+		seq_printf(m, "      constant: %llu\n", field->constant);
+
 	if (field->flags & HIST_FIELD_FL_ALIAS)
 		seq_printf(m, "      var_ref_idx (into hist_data->var_refs[]): %u\n",
 			   field->var_ref_idx);
@@ -5213,6 +5578,8 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
 
 	if (hist_field->flags & HIST_FIELD_FL_CPU)
 		seq_puts(m, "common_cpu");
+	else if (hist_field->flags & HIST_FIELD_FL_CONST)
+		seq_printf(m, "%llu", hist_field->constant);
 	else if (field_name) {
 		if (hist_field->flags & HIST_FIELD_FL_VAR_REF ||
 		    hist_field->flags & HIST_FIELD_FL_ALIAS)
@@ -5366,8 +5733,8 @@ static void unregister_field_var_hists(struct hist_trigger_data *hist_data)
 	for (i = 0; i < hist_data->n_field_var_hists; i++) {
 		file = hist_data->field_var_hists[i]->hist_data->event_file;
 		cmd = hist_data->field_var_hists[i]->cmd;
-		ret = event_hist_trigger_func(&trigger_hist_cmd, file,
-					      "!hist", "hist", cmd);
+		ret = event_hist_trigger_parse(&trigger_hist_cmd, file,
+					       "!hist", "hist", cmd);
 		WARN_ON_ONCE(ret < 0);
 	}
 }
@@ -5396,7 +5763,7 @@ static void event_hist_trigger_free(struct event_trigger_ops *ops,
 }
 
 static struct event_trigger_ops event_hist_trigger_ops = {
-	.func			= event_hist_trigger,
+	.trigger		= event_hist_trigger,
 	.print			= event_hist_trigger_print,
 	.init			= event_hist_trigger_init,
 	.free			= event_hist_trigger_free,
@@ -5430,7 +5797,7 @@ static void event_hist_trigger_named_free(struct event_trigger_ops *ops,
 }
 
 static struct event_trigger_ops event_hist_trigger_named_ops = {
-	.func			= event_hist_trigger,
+	.trigger		= event_hist_trigger,
 	.print			= event_hist_trigger_print,
 	.init			= event_hist_trigger_named_init,
 	.free			= event_hist_trigger_named_free,
@@ -5547,7 +5914,7 @@ static bool hist_trigger_match(struct event_trigger_data *data,
 	return true;
 }
 
-static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
+static int hist_register_trigger(char *glob,
 				 struct event_trigger_data *data,
 				 struct trace_event_file *file)
 {
@@ -5699,7 +6066,7 @@ static bool hist_trigger_check_refs(struct event_trigger_data *data,
 	return false;
 }
 
-static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops,
+static void hist_unregister_trigger(char *glob,
 				    struct event_trigger_data *data,
 				    struct trace_event_file *file)
 {
@@ -5783,9 +6150,9 @@ static void hist_unreg_all(struct trace_event_file *file)
 	}
 }
 
-static int event_hist_trigger_func(struct event_command *cmd_ops,
-				   struct trace_event_file *file,
-				   char *glob, char *cmd, char *param)
+static int event_hist_trigger_parse(struct event_command *cmd_ops,
+				    struct trace_event_file *file,
+				    char *glob, char *cmd, char *param)
 {
 	unsigned int hist_trigger_bits = TRACING_MAP_BITS_DEFAULT;
 	struct event_trigger_data *trigger_data;
@@ -5795,12 +6162,14 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
 	struct synth_event *se;
 	const char *se_name;
 	bool remove = false;
-	char *trigger, *p;
+	char *trigger, *p, *start;
 	int ret = 0;
 
 	lockdep_assert_held(&event_mutex);
 
-	if (glob && strlen(glob)) {
+	WARN_ON(!glob);
+
+	if (strlen(glob)) {
 		hist_err_clear();
 		last_cmd_set(file, param);
 	}
@@ -5833,7 +6202,7 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
 			continue;
 		}
 		break;
-	} while (p);
+	} while (1);
 
 	if (!p)
 		param = NULL;
@@ -5843,6 +6212,16 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
 		trigger = strstrip(trigger);
 	}
 
+	/*
+	 * To simplify arithmetic expression parsing, replace occurrences of
+	 * '.sym-offset' modifier with '.symXoffset'
+	 */
+	start = strstr(trigger, ".sym-offset");
+	while (start) {
+		*(start + 4) = 'X';
+		start = strstr(start + 11, ".sym-offset");
+	}
+
 	attrs = parse_hist_trigger_attrs(file->tr, trigger);
 	if (IS_ERR(attrs))
 		return PTR_ERR(attrs);
@@ -5889,7 +6268,7 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
 			goto out_free;
 		}
 
-		cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+		cmd_ops->unreg(glob+1, trigger_data, file);
 		se_name = trace_event_name(file->event_call);
 		se = find_synth_event(se_name);
 		if (se)
@@ -5898,7 +6277,7 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
 		goto out_free;
 	}
 
-	ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
+	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
@@ -5941,7 +6320,7 @@ enable:
 
 	return ret;
  out_unreg:
-	cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+	cmd_ops->unreg(glob+1, trigger_data, file);
  out_free:
 	if (cmd_ops->set_filter)
 		cmd_ops->set_filter(NULL, trigger_data, NULL);
@@ -5958,7 +6337,7 @@ static struct event_command trigger_hist_cmd = {
 	.name			= "hist",
 	.trigger_type		= ETT_EVENT_HIST,
 	.flags			= EVENT_CMD_FL_NEEDS_REC,
-	.func			= event_hist_trigger_func,
+	.parse			= event_hist_trigger_parse,
 	.reg			= hist_register_trigger,
 	.unreg			= hist_unregister_trigger,
 	.unreg_all		= hist_unreg_all,
@@ -6010,28 +6389,28 @@ hist_enable_count_trigger(struct event_trigger_data *data,
 }
 
 static struct event_trigger_ops hist_enable_trigger_ops = {
-	.func			= hist_enable_trigger,
+	.trigger		= hist_enable_trigger,
 	.print			= event_enable_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_enable_trigger_free,
 };
 
 static struct event_trigger_ops hist_enable_count_trigger_ops = {
-	.func			= hist_enable_count_trigger,
+	.trigger		= hist_enable_count_trigger,
 	.print			= event_enable_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_enable_trigger_free,
 };
 
 static struct event_trigger_ops hist_disable_trigger_ops = {
-	.func			= hist_enable_trigger,
+	.trigger		= hist_enable_trigger,
 	.print			= event_enable_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_enable_trigger_free,
 };
 
 static struct event_trigger_ops hist_disable_count_trigger_ops = {
-	.func			= hist_enable_count_trigger,
+	.trigger		= hist_enable_count_trigger,
 	.print			= event_enable_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_enable_trigger_free,
@@ -6073,7 +6452,7 @@ static void hist_enable_unreg_all(struct trace_event_file *file)
 static struct event_command trigger_hist_enable_cmd = {
 	.name			= ENABLE_HIST_STR,
 	.trigger_type		= ETT_HIST_ENABLE,
-	.func			= event_enable_trigger_func,
+	.parse			= event_enable_trigger_parse,
 	.reg			= event_enable_register_trigger,
 	.unreg			= event_enable_unregister_trigger,
 	.unreg_all		= hist_enable_unreg_all,
@@ -6084,7 +6463,7 @@ static struct event_command trigger_hist_enable_cmd = {
 static struct event_command trigger_hist_disable_cmd = {
 	.name			= DISABLE_HIST_STR,
 	.trigger_type		= ETT_HIST_ENABLE,
-	.func			= event_enable_trigger_func,
+	.parse			= event_enable_trigger_parse,
 	.reg			= event_enable_register_trigger,
 	.unreg			= event_enable_unregister_trigger,
 	.unreg_all		= hist_enable_unreg_all,
diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c
index c188045c5f97..d6b4935a78c0 100644
--- a/kernel/trace/trace_events_inject.c
+++ b/kernel/trace/trace_events_inject.c
@@ -168,10 +168,14 @@ static void *trace_alloc_entry(struct trace_event_call *call, int *size)
 			continue;
 		if (field->filter_type == FILTER_STATIC_STRING)
 			continue;
-		if (field->filter_type == FILTER_DYN_STRING) {
+		if (field->filter_type == FILTER_DYN_STRING ||
+		    field->filter_type == FILTER_RDYN_STRING) {
 			u32 *str_item;
 			int str_loc = entry_size & 0xffff;
 
+			if (field->filter_type == FILTER_RDYN_STRING)
+				str_loc -= field->offset + field->size;
+
 			str_item = (u32 *)(entry + field->offset);
 			*str_item = str_loc; /* string length is 0. */
 		} else {
@@ -214,7 +218,8 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry)
 
 			if (field->filter_type == FILTER_STATIC_STRING) {
 				strlcpy(entry + field->offset, addr, field->size);
-			} else if (field->filter_type == FILTER_DYN_STRING) {
+			} else if (field->filter_type == FILTER_DYN_STRING ||
+				   field->filter_type == FILTER_RDYN_STRING) {
 				int str_len = strlen(addr) + 1;
 				int str_loc = entry_size & 0xffff;
 				u32 *str_item;
@@ -229,6 +234,8 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry)
 
 				strlcpy(entry + (entry_size - str_len), addr, str_len);
 				str_item = (u32 *)(entry + field->offset);
+				if (field->filter_type == FILTER_RDYN_STRING)
+					str_loc -= field->offset + field->size;
 				*str_item = (str_len << 16) | str_loc;
 			} else {
 				char **paddr;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index d54094b7a9d7..154db74dadbc 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1237,9 +1237,8 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 						  argv + consumed, &consumed,
 						  &field_version);
 			if (IS_ERR(field)) {
-				argv_free(argv);
 				ret = PTR_ERR(field);
-				goto err;
+				goto err_free_arg;
 			}
 
 			/*
@@ -1262,18 +1261,19 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 			if (cmd_version > 1 && n_fields_this_loop >= 1) {
 				synth_err(SYNTH_ERR_INVALID_CMD, errpos(field_str));
 				ret = -EINVAL;
-				goto err;
+				goto err_free_arg;
 			}
 
 			fields[n_fields++] = field;
 			if (n_fields == SYNTH_FIELDS_MAX) {
 				synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0);
 				ret = -EINVAL;
-				goto err;
+				goto err_free_arg;
 			}
 
 			n_fields_this_loop++;
 		}
+		argv_free(argv);
 
 		if (consumed < argc) {
 			synth_err(SYNTH_ERR_INVALID_CMD, 0);
@@ -1281,7 +1281,6 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 			goto err;
 		}
 
-		argv_free(argv);
 	}
 
 	if (n_fields == 0) {
@@ -1307,6 +1306,8 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 	kfree(saved_fields);
 
 	return ret;
+ err_free_arg:
+	argv_free(argv);
  err:
 	for (i = 0; i < n_fields; i++)
 		free_synth_field(fields[i]);
@@ -1978,7 +1979,7 @@ EXPORT_SYMBOL_GPL(synth_event_add_next_val);
 /**
  * synth_event_add_val - Add a named field's value to an open synth trace
  * @field_name: The name of the synthetic event field value to set
- * @val: The value to set the next field to
+ * @val: The value to set the named field to
  * @trace_state: A pointer to object tracking the piecewise trace state
  *
  * Set the value of the named field in an event that's been opened by
@@ -2053,6 +2054,13 @@ static int create_synth_event(const char *raw_command)
 
 	last_cmd_set(raw_command);
 
+	name = raw_command;
+
+	/* Don't try to process if not our system */
+	if (name[0] != 's' || name[1] != ':')
+		return -ECANCELED;
+	name += 2;
+
 	p = strpbrk(raw_command, " \t");
 	if (!p) {
 		synth_err(SYNTH_ERR_INVALID_CMD, 0);
@@ -2061,12 +2069,6 @@ static int create_synth_event(const char *raw_command)
 
 	fields = skip_spaces(p);
 
-	name = raw_command;
-
-	if (name[0] != 's' || name[1] != ':')
-		return -ECANCELED;
-	name += 2;
-
 	/* This interface accepts group name prefix */
 	if (strchr(name, '/')) {
 		len = str_has_prefix(name, SYNTH_SYSTEM "/");
@@ -2227,8 +2229,8 @@ static __init int trace_events_synth_init(void)
 	if (err)
 		goto err;
 
-	entry = tracefs_create_file("synthetic_events", 0644, NULL,
-				    NULL, &synth_events_fops);
+	entry = tracefs_create_file("synthetic_events", TRACE_MODE_WRITE,
+				    NULL, NULL, &synth_events_fops);
 	if (!entry) {
 		err = -ENODEV;
 		goto err;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 3d5c07239a2a..d00fee705f9c 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -68,7 +68,7 @@ event_triggers_call(struct trace_event_file *file,
 		if (data->paused)
 			continue;
 		if (!rec) {
-			data->ops->func(data, buffer, rec, event);
+			data->ops->trigger(data, buffer, rec, event);
 			continue;
 		}
 		filter = rcu_dereference_sched(data->filter);
@@ -78,7 +78,7 @@ event_triggers_call(struct trace_event_file *file,
 			tt |= data->cmd_ops->trigger_type;
 			continue;
 		}
-		data->ops->func(data, buffer, rec, event);
+		data->ops->trigger(data, buffer, rec, event);
 	}
 	return tt;
 }
@@ -106,7 +106,7 @@ event_triggers_post_call(struct trace_event_file *file,
 		if (data->paused)
 			continue;
 		if (data->cmd_ops->trigger_type & tt)
-			data->ops->func(data, NULL, NULL, NULL);
+			data->ops->trigger(data, NULL, NULL, NULL);
 	}
 }
 EXPORT_SYMBOL_GPL(event_triggers_post_call);
@@ -245,7 +245,7 @@ int trigger_process_regex(struct trace_event_file *file, char *buff)
 	mutex_lock(&trigger_cmd_mutex);
 	list_for_each_entry(p, &trigger_commands, list) {
 		if (strcmp(p->name, command) == 0) {
-			ret = p->func(p, file, buff, command, next);
+			ret = p->parse(p, file, buff, command, next);
 			goto out_unlock;
 		}
 	}
@@ -540,7 +540,6 @@ void update_cond_flag(struct trace_event_file *file)
 /**
  * register_trigger - Generic event_command @reg implementation
  * @glob: The raw string used to register the trigger
- * @ops: The trigger ops associated with the trigger
  * @data: Trigger-specific data to associate with the trigger
  * @file: The trace_event_file associated with the event
  *
@@ -551,7 +550,7 @@ void update_cond_flag(struct trace_event_file *file)
  *
  * Return: 0 on success, errno otherwise
  */
-static int register_trigger(char *glob, struct event_trigger_ops *ops,
+static int register_trigger(char *glob,
 			    struct event_trigger_data *data,
 			    struct trace_event_file *file)
 {
@@ -589,7 +588,6 @@ out:
 /**
  * unregister_trigger - Generic event_command @unreg implementation
  * @glob: The raw string used to register the trigger
- * @ops: The trigger ops associated with the trigger
  * @test: Trigger-specific data used to find the trigger to remove
  * @file: The trace_event_file associated with the event
  *
@@ -598,7 +596,7 @@ out:
  * Usually used directly as the @unreg method in event command
  * implementations.
  */
-static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
+static void unregister_trigger(char *glob,
 			       struct event_trigger_data *test,
 			       struct trace_event_file *file)
 {
@@ -621,8 +619,350 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
 		data->ops->free(data->ops, data);
 }
 
+/*
+ * Event trigger parsing helper functions.
+ *
+ * These functions help make it easier to write an event trigger
+ * parsing function i.e. the struct event_command.parse() callback
+ * function responsible for parsing and registering a trigger command
+ * written to the 'trigger' file.
+ *
+ * A trigger command (or just 'trigger' for short) takes the form:
+ *   [trigger] [if filter]
+ *
+ * The struct event_command.parse() callback (and other struct
+ * event_command functions) refer to several components of a trigger
+ * command.  Those same components are referenced by the event trigger
+ * parsing helper functions defined below.  These components are:
+ *
+ *   cmd               - the trigger command name
+ *   glob              - the trigger command name optionally prefaced with '!'
+ *   param_and_filter  - text following cmd and ':'
+ *   param             - text following cmd and ':' and stripped of filter
+ *   filter            - the optional filter text following (and including) 'if'
+ *
+ * To illustrate the use of these componenents, here are some concrete
+ * examples. For the following triggers:
+ *
+ *   echo 'traceon:5 if pid == 0' > trigger
+ *     - 'traceon' is both cmd and glob
+ *     - '5 if pid == 0' is the param_and_filter
+ *     - '5' is the param
+ *     - 'if pid == 0' is the filter
+ *
+ *   echo 'enable_event:sys:event:n' > trigger
+ *     - 'enable_event' is both cmd and glob
+ *     - 'sys:event:n' is the param_and_filter
+ *     - 'sys:event:n' is the param
+ *     - there is no filter
+ *
+ *   echo 'hist:keys=pid if prio > 50' > trigger
+ *     - 'hist' is both cmd and glob
+ *     - 'keys=pid if prio > 50' is the param_and_filter
+ *     - 'keys=pid' is the param
+ *     - 'if prio > 50' is the filter
+ *
+ *   echo '!enable_event:sys:event:n' > trigger
+ *     - 'enable_event' the cmd
+ *     - '!enable_event' is the glob
+ *     - 'sys:event:n' is the param_and_filter
+ *     - 'sys:event:n' is the param
+ *     - there is no filter
+ *
+ *   echo 'traceoff' > trigger
+ *     - 'traceoff' is both cmd and glob
+ *     - there is no param_and_filter
+ *     - there is no param
+ *     - there is no filter
+ *
+ * There are a few different categories of event trigger covered by
+ * these helpers:
+ *
+ *  - triggers that don't require a parameter e.g. traceon
+ *  - triggers that do require a parameter e.g. enable_event and hist
+ *  - triggers that though they may not require a param may support an
+ *    optional 'n' param (n = number of times the trigger should fire)
+ *    e.g.: traceon:5 or enable_event:sys:event:n
+ *  - triggers that do not support an 'n' param e.g. hist
+ *
+ * These functions can be used or ignored as necessary - it all
+ * depends on the complexity of the trigger, and the granularity of
+ * the functions supported reflects the fact that some implementations
+ * may need to customize certain aspects of their implementations and
+ * won't need certain functions.  For instance, the hist trigger
+ * implementation doesn't use event_trigger_separate_filter() because
+ * it has special requirements for handling the filter.
+ */
+
+/**
+ * event_trigger_check_remove - check whether an event trigger specifies remove
+ * @glob: The trigger command string, with optional remove(!) operator
+ *
+ * The event trigger callback implementations pass in 'glob' as a
+ * parameter.  This is the command name either with or without a
+ * remove(!)  operator.  This function simply parses the glob and
+ * determines whether the command corresponds to a trigger removal or
+ * a trigger addition.
+ *
+ * Return: true if this is a remove command, false otherwise
+ */
+bool event_trigger_check_remove(const char *glob)
+{
+	return (glob && glob[0] == '!') ? true : false;
+}
+
+/**
+ * event_trigger_empty_param - check whether the param is empty
+ * @param: The trigger param string
+ *
+ * The event trigger callback implementations pass in 'param' as a
+ * parameter.  This corresponds to the string following the command
+ * name minus the command name.  This function can be called by a
+ * callback implementation for any command that requires a param; a
+ * callback that doesn't require a param can ignore it.
+ *
+ * Return: true if this is an empty param, false otherwise
+ */
+bool event_trigger_empty_param(const char *param)
+{
+	return !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
+ * @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
+ * NULL, they will contain strings corresponding to the trigger and
+ * filter.
+ *
+ * There are two cases that need to be handled with respect to the
+ * passed-in param: either the param is required, or it is not
+ * required.  If @param_required is set, and there's no param, it will
+ * return -EINVAL.  If @param_required is not set and there's a param
+ * that starts with a number, that corresponds to the case of a
+ * trigger with :n (n = number of times the trigger should fire) and
+ * the parsing continues normally; otherwise the function just returns
+ * and assumes param just contains a filter and there's nothing else
+ * to do.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+int event_trigger_separate_filter(char *param_and_filter, char **param,
+				  char **filter, bool param_required)
+{
+	int ret = 0;
+
+	*param = *filter = NULL;
+
+	if (!param_and_filter) {
+		if (param_required)
+			ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Here we check for an optional param. The only legal
+	 * optional param is :n, and if that's the case, continue
+	 * below. Otherwise we assume what's left is a filter and
+	 * return it as the filter string for the caller to deal with.
+	 */
+	if (!param_required && param_and_filter && !isdigit(param_and_filter[0])) {
+		*filter = param_and_filter;
+		goto out;
+	}
+
+	/*
+	 * Separate the param from the filter (param [if filter]).
+	 * Here we have either an optional :n param or a required
+	 * param and an optional filter.
+	 */
+	*param = strsep(&param_and_filter, " \t");
+
+	/*
+	 * Here we have a filter, though it may be empty.
+	 */
+	if (param_and_filter) {
+		*filter = skip_spaces(param_and_filter);
+		if (!**filter)
+			*filter = NULL;
+	}
+out:
+	return ret;
+}
+
+/**
+ * event_trigger_alloc - allocate and init event_trigger_data for a trigger
+ * @cmd_ops: The event_command operations for the trigger
+ * @cmd: The cmd string
+ * @param: The param string
+ * @private_data: User data to associate with the event trigger
+ *
+ * Allocate an event_trigger_data instance and initialize it.  The
+ * @cmd_ops are used along with the @cmd and @param to get the
+ * trigger_ops to assign to the event_trigger_data.  @private_data can
+ * also be passed in and associated with the event_trigger_data.
+ *
+ * Use event_trigger_free() to free an event_trigger_data object.
+ *
+ * Return: The trigger_data object success, NULL otherwise
+ */
+struct event_trigger_data *event_trigger_alloc(struct event_command *cmd_ops,
+					       char *cmd,
+					       char *param,
+					       void *private_data)
+{
+	struct event_trigger_data *trigger_data;
+	struct event_trigger_ops *trigger_ops;
+
+	trigger_ops = cmd_ops->get_trigger_ops(cmd, param);
+
+	trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+	if (!trigger_data)
+		return NULL;
+
+	trigger_data->count = -1;
+	trigger_data->ops = trigger_ops;
+	trigger_data->cmd_ops = cmd_ops;
+	trigger_data->private_data = private_data;
+
+	INIT_LIST_HEAD(&trigger_data->list);
+	INIT_LIST_HEAD(&trigger_data->named_list);
+	RCU_INIT_POINTER(trigger_data->filter, NULL);
+
+	return trigger_data;
+}
+
+/**
+ * event_trigger_parse_num - parse and return the number param for a trigger
+ * @param: The param string
+ * @trigger_data: The trigger_data for the trigger
+ *
+ * Parse the :n (n = number of times the trigger should fire) param
+ * and set the count variable in the trigger_data to the parsed count.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+int event_trigger_parse_num(char *param,
+			    struct event_trigger_data *trigger_data)
+{
+	char *number;
+	int ret = 0;
+
+	if (param) {
+		number = strsep(&param, ":");
+
+		if (!strlen(number))
+			return -EINVAL;
+
+		/*
+		 * We use the callback data field (which is a pointer)
+		 * as our counter.
+		 */
+		ret = kstrtoul(number, 0, &trigger_data->count);
+	}
+
+	return ret;
+}
+
+/**
+ * event_trigger_set_filter - set an event trigger's filter
+ * @cmd_ops: The event_command operations for the trigger
+ * @file: The event file for the trigger's event
+ * @param: The string containing the filter
+ * @trigger_data: The trigger_data for the trigger
+ *
+ * Set the filter for the trigger.  If the filter is NULL, just return
+ * without error.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+int event_trigger_set_filter(struct event_command *cmd_ops,
+			     struct trace_event_file *file,
+			     char *param,
+			     struct event_trigger_data *trigger_data)
+{
+	if (param && cmd_ops->set_filter)
+		return cmd_ops->set_filter(param, trigger_data, file);
+
+	return 0;
+}
+
+/**
+ * event_trigger_reset_filter - reset an event trigger's filter
+ * @cmd_ops: The event_command operations for the trigger
+ * @trigger_data: The trigger_data for the trigger
+ *
+ * Reset the filter for the trigger to no filter.
+ */
+void event_trigger_reset_filter(struct event_command *cmd_ops,
+				struct event_trigger_data *trigger_data)
+{
+	if (cmd_ops->set_filter)
+		cmd_ops->set_filter(NULL, trigger_data, NULL);
+}
+
+/**
+ * event_trigger_register - register 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
+ * @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.
+ *
+ * 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)
+{
+	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 ret;
+}
+
+/*
+ * End event trigger parsing helper functions.
+ */
+
 /**
- * event_trigger_callback - Generic event_command @func implementation
+ * event_trigger_parse - Generic event_command @parse implementation
  * @cmd_ops: The command ops, used for trigger registration
  * @file: The trace_event_file associated with the event
  * @glob: The raw string used to register the trigger
@@ -632,15 +972,15 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
  * Common implementation for event command parsing and trigger
  * instantiation.
  *
- * Usually used directly as the @func method in event command
+ * Usually used directly as the @parse method in event command
  * implementations.
  *
  * Return: 0 on success, errno otherwise
  */
 static int
-event_trigger_callback(struct event_command *cmd_ops,
-		       struct trace_event_file *file,
-		       char *glob, char *cmd, char *param)
+event_trigger_parse(struct event_command *cmd_ops,
+		    struct trace_event_file *file,
+		    char *glob, char *cmd, char *param)
 {
 	struct event_trigger_data *trigger_data;
 	struct event_trigger_ops *trigger_ops;
@@ -673,7 +1013,7 @@ event_trigger_callback(struct event_command *cmd_ops,
 	INIT_LIST_HEAD(&trigger_data->named_list);
 
 	if (glob[0] == '!') {
-		cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+		cmd_ops->unreg(glob+1, trigger_data, file);
 		kfree(trigger_data);
 		ret = 0;
 		goto out;
@@ -708,14 +1048,14 @@ event_trigger_callback(struct event_command *cmd_ops,
  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_ops, trigger_data, file);
+	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_ops, trigger_data, file);
+		cmd_ops->unreg(glob, trigger_data, file);
 		ret = -ENOENT;
 	} else if (ret > 0)
 		ret = 0;
@@ -1023,28 +1363,28 @@ traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
 }
 
 static struct event_trigger_ops traceon_trigger_ops = {
-	.func			= traceon_trigger,
+	.trigger		= traceon_trigger,
 	.print			= traceon_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_trigger_free,
 };
 
 static struct event_trigger_ops traceon_count_trigger_ops = {
-	.func			= traceon_count_trigger,
+	.trigger		= traceon_count_trigger,
 	.print			= traceon_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_trigger_free,
 };
 
 static struct event_trigger_ops traceoff_trigger_ops = {
-	.func			= traceoff_trigger,
+	.trigger		= traceoff_trigger,
 	.print			= traceoff_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_trigger_free,
 };
 
 static struct event_trigger_ops traceoff_count_trigger_ops = {
-	.func			= traceoff_count_trigger,
+	.trigger		= traceoff_count_trigger,
 	.print			= traceoff_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_trigger_free,
@@ -1069,7 +1409,7 @@ onoff_get_trigger_ops(char *cmd, char *param)
 static struct event_command trigger_traceon_cmd = {
 	.name			= "traceon",
 	.trigger_type		= ETT_TRACE_ONOFF,
-	.func			= event_trigger_callback,
+	.parse			= event_trigger_parse,
 	.reg			= register_trigger,
 	.unreg			= unregister_trigger,
 	.get_trigger_ops	= onoff_get_trigger_ops,
@@ -1080,7 +1420,7 @@ static struct event_command trigger_traceoff_cmd = {
 	.name			= "traceoff",
 	.trigger_type		= ETT_TRACE_ONOFF,
 	.flags			= EVENT_CMD_FL_POST_TRIGGER,
-	.func			= event_trigger_callback,
+	.parse			= event_trigger_parse,
 	.reg			= register_trigger,
 	.unreg			= unregister_trigger,
 	.get_trigger_ops	= onoff_get_trigger_ops,
@@ -1116,14 +1456,14 @@ snapshot_count_trigger(struct event_trigger_data *data,
 }
 
 static int
-register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
+register_snapshot_trigger(char *glob,
 			  struct event_trigger_data *data,
 			  struct trace_event_file *file)
 {
 	if (tracing_alloc_snapshot_instance(file->tr) != 0)
 		return 0;
 
-	return register_trigger(glob, ops, data, file);
+	return register_trigger(glob, data, file);
 }
 
 static int
@@ -1135,14 +1475,14 @@ snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
 }
 
 static struct event_trigger_ops snapshot_trigger_ops = {
-	.func			= snapshot_trigger,
+	.trigger		= snapshot_trigger,
 	.print			= snapshot_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_trigger_free,
 };
 
 static struct event_trigger_ops snapshot_count_trigger_ops = {
-	.func			= snapshot_count_trigger,
+	.trigger		= snapshot_count_trigger,
 	.print			= snapshot_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_trigger_free,
@@ -1157,7 +1497,7 @@ snapshot_get_trigger_ops(char *cmd, char *param)
 static struct event_command trigger_snapshot_cmd = {
 	.name			= "snapshot",
 	.trigger_type		= ETT_SNAPSHOT,
-	.func			= event_trigger_callback,
+	.parse			= event_trigger_parse,
 	.reg			= register_snapshot_trigger,
 	.unreg			= unregister_trigger,
 	.get_trigger_ops	= snapshot_get_trigger_ops,
@@ -1226,14 +1566,14 @@ stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
 }
 
 static struct event_trigger_ops stacktrace_trigger_ops = {
-	.func			= stacktrace_trigger,
+	.trigger		= stacktrace_trigger,
 	.print			= stacktrace_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_trigger_free,
 };
 
 static struct event_trigger_ops stacktrace_count_trigger_ops = {
-	.func			= stacktrace_count_trigger,
+	.trigger		= stacktrace_count_trigger,
 	.print			= stacktrace_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_trigger_free,
@@ -1249,7 +1589,7 @@ static struct event_command trigger_stacktrace_cmd = {
 	.name			= "stacktrace",
 	.trigger_type		= ETT_STACKTRACE,
 	.flags			= EVENT_CMD_FL_POST_TRIGGER,
-	.func			= event_trigger_callback,
+	.parse			= event_trigger_parse,
 	.reg			= register_trigger,
 	.unreg			= unregister_trigger,
 	.get_trigger_ops	= stacktrace_get_trigger_ops,
@@ -1353,36 +1693,36 @@ void event_enable_trigger_free(struct event_trigger_ops *ops,
 }
 
 static struct event_trigger_ops event_enable_trigger_ops = {
-	.func			= event_enable_trigger,
+	.trigger		= event_enable_trigger,
 	.print			= event_enable_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_enable_trigger_free,
 };
 
 static struct event_trigger_ops event_enable_count_trigger_ops = {
-	.func			= event_enable_count_trigger,
+	.trigger		= event_enable_count_trigger,
 	.print			= event_enable_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_enable_trigger_free,
 };
 
 static struct event_trigger_ops event_disable_trigger_ops = {
-	.func			= event_enable_trigger,
+	.trigger		= event_enable_trigger,
 	.print			= event_enable_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_enable_trigger_free,
 };
 
 static struct event_trigger_ops event_disable_count_trigger_ops = {
-	.func			= event_enable_count_trigger,
+	.trigger		= event_enable_count_trigger,
 	.print			= event_enable_trigger_print,
 	.init			= event_trigger_init,
 	.free			= event_enable_trigger_free,
 };
 
-int event_enable_trigger_func(struct event_command *cmd_ops,
-			      struct trace_event_file *file,
-			      char *glob, char *cmd, char *param)
+int event_enable_trigger_parse(struct event_command *cmd_ops,
+			       struct trace_event_file *file,
+			       char *glob, char *cmd, char *param)
 {
 	struct trace_event_file *event_enable_file;
 	struct enable_trigger_data *enable_data;
@@ -1455,7 +1795,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 	trigger_data->private_data = enable_data;
 
 	if (glob[0] == '!') {
-		cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+		cmd_ops->unreg(glob+1, trigger_data, file);
 		kfree(trigger_data);
 		kfree(enable_data);
 		ret = 0;
@@ -1502,7 +1842,7 @@ int event_enable_trigger_func(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_ops, trigger_data, file);
+	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.
@@ -1532,7 +1872,6 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 }
 
 int event_enable_register_trigger(char *glob,
-				  struct event_trigger_ops *ops,
 				  struct event_trigger_data *data,
 				  struct trace_event_file *file)
 {
@@ -1574,7 +1913,6 @@ out:
 }
 
 void event_enable_unregister_trigger(char *glob,
-				     struct event_trigger_ops *ops,
 				     struct event_trigger_data *test,
 				     struct trace_event_file *file)
 {
@@ -1628,7 +1966,7 @@ event_enable_get_trigger_ops(char *cmd, char *param)
 static struct event_command trigger_enable_cmd = {
 	.name			= ENABLE_EVENT_STR,
 	.trigger_type		= ETT_EVENT_ENABLE,
-	.func			= event_enable_trigger_func,
+	.parse			= event_enable_trigger_parse,
 	.reg			= event_enable_register_trigger,
 	.unreg			= event_enable_unregister_trigger,
 	.get_trigger_ops	= event_enable_get_trigger_ops,
@@ -1638,7 +1976,7 @@ static struct event_command trigger_enable_cmd = {
 static struct event_command trigger_disable_cmd = {
 	.name			= DISABLE_EVENT_STR,
 	.trigger_type		= ETT_EVENT_ENABLE,
-	.func			= event_enable_trigger_func,
+	.parse			= event_enable_trigger_parse,
 	.reg			= event_enable_register_trigger,
 	.unreg			= event_enable_unregister_trigger,
 	.get_trigger_ops	= event_enable_get_trigger_ops,
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 1f0e63f5d1f9..9f1bfbe105e8 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -186,7 +186,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 		return;
 
 	trace_ctx = tracing_gen_ctx();
-	preempt_disable_notrace();
 
 	cpu = smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
@@ -194,7 +193,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 		trace_function(tr, ip, parent_ip, trace_ctx);
 
 	ftrace_test_recursion_unlock(bit);
-	preempt_enable_notrace();
 }
 
 #ifdef CONFIG_UNWINDER_ORC
@@ -298,8 +296,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (bit < 0)
 		return;
 
-	preempt_disable_notrace();
-
 	cpu = smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
 	if (atomic_read(&data->disabled))
@@ -324,7 +320,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 
 out:
 	ftrace_test_recursion_unlock(bit);
-	preempt_enable_notrace();
 }
 
 static void
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 0de6837722da..203204cadf92 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -120,7 +120,7 @@ static inline int ftrace_graph_ignore_irqs(void)
 	if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT))
 		return 0;
 
-	return in_irq();
+	return in_hardirq();
 }
 
 int trace_graph_entry(struct ftrace_graph_ent *trace)
@@ -1340,7 +1340,7 @@ static __init int init_graph_tracefs(void)
 	if (ret)
 		return 0;
 
-	trace_create_file("max_graph_depth", 0644, NULL,
+	trace_create_file("max_graph_depth", TRACE_MODE_WRITE, NULL,
 			  NULL, &graph_depth_fops);
 
 	return 0;
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 1b83d75eb103..d440ddd5fd8b 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -79,8 +79,8 @@ struct hwlat_kthread_data {
 	int			nmi_cpu;
 };
 
-struct hwlat_kthread_data hwlat_single_cpu_data;
-DEFINE_PER_CPU(struct hwlat_kthread_data, hwlat_per_cpu_data);
+static struct hwlat_kthread_data hwlat_single_cpu_data;
+static DEFINE_PER_CPU(struct hwlat_kthread_data, hwlat_per_cpu_data);
 
 /* Tells NMIs to call back to the hwlat tracer to record timestamps */
 bool trace_hwlat_callback_enabled;
@@ -491,18 +491,14 @@ static void stop_per_cpu_kthreads(void)
 static int start_cpu_kthread(unsigned int cpu)
 {
 	struct task_struct *kthread;
-	char comm[24];
 
-	snprintf(comm, 24, "hwlatd/%d", cpu);
-
-	kthread = kthread_create_on_cpu(kthread_fn, NULL, cpu, comm);
+	kthread = kthread_run_on_cpu(kthread_fn, NULL, cpu, "hwlatd/%u");
 	if (IS_ERR(kthread)) {
 		pr_err(BANNER "could not start sampling thread\n");
 		return -ENOMEM;
 	}
 
 	per_cpu(hwlat_per_cpu_data, cpu).kthread = kthread;
-	wake_up_process(kthread);
 
 	return 0;
 }
@@ -782,21 +778,21 @@ static int init_tracefs(void)
 	if (!top_dir)
 		return -ENOMEM;
 
-	hwlat_sample_window = tracefs_create_file("window", 0640,
+	hwlat_sample_window = tracefs_create_file("window", TRACE_MODE_WRITE,
 						  top_dir,
 						  &hwlat_window,
 						  &trace_min_max_fops);
 	if (!hwlat_sample_window)
 		goto err;
 
-	hwlat_sample_width = tracefs_create_file("width", 0644,
+	hwlat_sample_width = tracefs_create_file("width", TRACE_MODE_WRITE,
 						 top_dir,
 						 &hwlat_width,
 						 &trace_min_max_fops);
 	if (!hwlat_sample_width)
 		goto err;
 
-	hwlat_thread_mode = trace_create_file("mode", 0644,
+	hwlat_thread_mode = trace_create_file("mode", TRACE_MODE_WRITE,
 					      top_dir,
 					      NULL,
 					      &thread_mode_fops);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 3a64ba4bbad6..508f14af4f2c 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -7,6 +7,7 @@
  */
 #define pr_fmt(fmt)	"trace_kprobe: " fmt
 
+#include <linux/bpf-cgroup.h>
 #include <linux/security.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
@@ -97,7 +98,7 @@ static nokprobe_inline unsigned long trace_kprobe_offset(struct trace_kprobe *tk
 
 static nokprobe_inline bool trace_kprobe_has_gone(struct trace_kprobe *tk)
 {
-	return !!(kprobe_gone(&tk->rp.kp));
+	return kprobe_gone(&tk->rp.kp);
 }
 
 static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk,
@@ -327,11 +328,9 @@ static inline int __enable_trace_kprobe(struct trace_kprobe *tk)
 
 static void __disable_trace_kprobe(struct trace_probe *tp)
 {
-	struct trace_probe *pos;
 	struct trace_kprobe *tk;
 
-	list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
-		tk = container_of(pos, struct trace_kprobe, tp);
+	list_for_each_entry(tk, trace_probe_probe_list(tp), tp.list) {
 		if (!trace_kprobe_is_registered(tk))
 			continue;
 		if (trace_kprobe_is_return(tk))
@@ -348,7 +347,7 @@ static void __disable_trace_kprobe(struct trace_probe *tp)
 static int enable_trace_kprobe(struct trace_event_call *call,
 				struct trace_event_file *file)
 {
-	struct trace_probe *pos, *tp;
+	struct trace_probe *tp;
 	struct trace_kprobe *tk;
 	bool enabled;
 	int ret = 0;
@@ -369,8 +368,7 @@ static int enable_trace_kprobe(struct trace_event_call *call,
 	if (enabled)
 		return 0;
 
-	list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
-		tk = container_of(pos, struct trace_kprobe, tp);
+	list_for_each_entry(tk, trace_probe_probe_list(tp), tp.list) {
 		if (trace_kprobe_has_gone(tk))
 			continue;
 		ret = __enable_trace_kprobe(tk);
@@ -559,11 +557,9 @@ static bool trace_kprobe_has_same_kprobe(struct trace_kprobe *orig,
 					 struct trace_kprobe *comp)
 {
 	struct trace_probe_event *tpe = orig->tp.event;
-	struct trace_probe *pos;
 	int i;
 
-	list_for_each_entry(pos, &tpe->probes, list) {
-		orig = container_of(pos, struct trace_kprobe, tp);
+	list_for_each_entry(orig, &tpe->probes, tp.list) {
 		if (strcmp(trace_kprobe_symbol(orig),
 			   trace_kprobe_symbol(comp)) ||
 		    trace_kprobe_offset(orig) != trace_kprobe_offset(comp))
@@ -1175,15 +1171,18 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
 {
 	struct dyn_event *ev = v;
 	struct trace_kprobe *tk;
+	unsigned long nmissed;
 
 	if (!is_trace_kprobe(ev))
 		return 0;
 
 	tk = to_trace_kprobe(ev);
+	nmissed = trace_kprobe_is_return(tk) ?
+		tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed;
 	seq_printf(m, "  %-44s %15lu %15lu\n",
 		   trace_probe_name(&tk->tp),
 		   trace_kprobe_nhit(tk),
-		   tk->rp.kp.nmissed);
+		   nmissed);
 
 	return 0;
 }
@@ -1383,17 +1382,11 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
 	if (trace_trigger_soft_disabled(trace_file))
 		return;
 
-	fbuffer.trace_ctx = tracing_gen_ctx();
-	fbuffer.trace_file = trace_file;
-
 	dsize = __get_data_size(&tk->tp, regs);
 
-	fbuffer.event =
-		trace_event_buffer_lock_reserve(&fbuffer.buffer, trace_file,
-					call->event.type,
-					sizeof(*entry) + tk->tp.size + dsize,
-					fbuffer.trace_ctx);
-	if (!fbuffer.event)
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
+					   sizeof(*entry) + tk->tp.size + dsize);
+	if (!entry)
 		return;
 
 	fbuffer.regs = regs;
@@ -1430,16 +1423,11 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	if (trace_trigger_soft_disabled(trace_file))
 		return;
 
-	fbuffer.trace_ctx = tracing_gen_ctx();
-	fbuffer.trace_file = trace_file;
-
 	dsize = __get_data_size(&tk->tp, regs);
-	fbuffer.event =
-		trace_event_buffer_lock_reserve(&fbuffer.buffer, trace_file,
-					call->event.type,
-					sizeof(*entry) + tk->tp.size + dsize,
-					fbuffer.trace_ctx);
-	if (!fbuffer.event)
+
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
+					   sizeof(*entry) + tk->tp.size + dsize);
+	if (!entry)
 		return;
 
 	fbuffer.regs = regs;
@@ -1925,16 +1913,16 @@ static __init int init_kprobe_trace(void)
 	if (ret)
 		return 0;
 
-	entry = tracefs_create_file("kprobe_events", 0644, NULL,
-				    NULL, &kprobe_events_ops);
+	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");
 
 	/* Profile interface */
-	entry = tracefs_create_file("kprobe_profile", 0444, NULL,
-				    NULL, &kprobe_profile_ops);
+	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");
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index ce053619f289..870a08da5b48 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -38,8 +38,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/osnoise.h>
 
-static struct trace_array	*osnoise_trace;
-
 /*
  * Default values.
  */
@@ -51,6 +49,99 @@ static struct trace_array	*osnoise_trace;
 #define DEFAULT_TIMERLAT_PRIO	95			/* FIFO 95 */
 
 /*
+ * trace_array of the enabled osnoise/timerlat instances.
+ */
+struct osnoise_instance {
+	struct list_head	list;
+	struct trace_array	*tr;
+};
+
+static struct list_head osnoise_instances;
+
+static bool osnoise_has_registered_instances(void)
+{
+	return !!list_first_or_null_rcu(&osnoise_instances,
+					struct osnoise_instance,
+					list);
+}
+
+/*
+ * osnoise_instance_registered - check if a tr is already registered
+ */
+static int osnoise_instance_registered(struct trace_array *tr)
+{
+	struct osnoise_instance *inst;
+	int found = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+		if (inst->tr == tr)
+			found = 1;
+	}
+	rcu_read_unlock();
+
+	return found;
+}
+
+/*
+ * osnoise_register_instance - register a new trace instance
+ *
+ * Register a trace_array *tr in the list of instances running
+ * osnoise/timerlat tracers.
+ */
+static int osnoise_register_instance(struct trace_array *tr)
+{
+	struct osnoise_instance *inst;
+
+	/*
+	 * register/unregister serialization is provided by trace's
+	 * trace_types_lock.
+	 */
+	lockdep_assert_held(&trace_types_lock);
+
+	inst = kmalloc(sizeof(*inst), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD_RCU(&inst->list);
+	inst->tr = tr;
+	list_add_tail_rcu(&inst->list, &osnoise_instances);
+
+	return 0;
+}
+
+/*
+ *  osnoise_unregister_instance - unregister a registered trace instance
+ *
+ * Remove the trace_array *tr from the list of instances running
+ * osnoise/timerlat tracers.
+ */
+static void osnoise_unregister_instance(struct trace_array *tr)
+{
+	struct osnoise_instance *inst;
+	int found = 0;
+
+	/*
+	 * register/unregister serialization is provided by trace's
+	 * trace_types_lock.
+	 */
+	lockdep_assert_held(&trace_types_lock);
+
+	list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+		if (inst->tr == tr) {
+			list_del_rcu(&inst->list);
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found)
+		return;
+
+	kvfree_rcu(inst);
+}
+
+/*
  * NMI runtime info.
  */
 struct osn_nmi {
@@ -248,10 +339,56 @@ static struct osnoise_data {
 #endif
 };
 
-/*
- * Boolean variable used to inform that the tracer is currently sampling.
- */
-static bool osnoise_busy;
+#ifdef CONFIG_TIMERLAT_TRACER
+static inline bool timerlat_enabled(void)
+{
+	return osnoise_data.timerlat_tracer;
+}
+
+static inline int timerlat_softirq_exit(struct osnoise_variables *osn_var)
+{
+	struct timerlat_variables *tlat_var = this_cpu_tmr_var();
+	/*
+	 * If the timerlat is enabled, but the irq handler did
+	 * not run yet enabling timerlat_tracer, do not trace.
+	 */
+	if (!tlat_var->tracing_thread) {
+		osn_var->softirq.arrival_time = 0;
+		osn_var->softirq.delta_start = 0;
+		return 0;
+	}
+	return 1;
+}
+
+static inline int timerlat_thread_exit(struct osnoise_variables *osn_var)
+{
+	struct timerlat_variables *tlat_var = this_cpu_tmr_var();
+	/*
+	 * If the timerlat is enabled, but the irq handler did
+	 * not run yet enabling timerlat_tracer, do not trace.
+	 */
+	if (!tlat_var->tracing_thread) {
+		osn_var->thread.delta_start = 0;
+		osn_var->thread.arrival_time = 0;
+		return 0;
+	}
+	return 1;
+}
+#else /* CONFIG_TIMERLAT_TRACER */
+static inline bool timerlat_enabled(void)
+{
+	return false;
+}
+
+static inline int timerlat_softirq_exit(struct osnoise_variables *osn_var)
+{
+	return 1;
+}
+static inline int timerlat_thread_exit(struct osnoise_variables *osn_var)
+{
+	return 1;
+}
+#endif
 
 #ifdef CONFIG_PREEMPT_RT
 /*
@@ -294,19 +431,19 @@ static void print_osnoise_headers(struct seq_file *s)
 	seq_puts(s, "#                                _-----=> irqs-off\n");
 	seq_puts(s, "#                               / _----=> need-resched\n");
 	seq_puts(s, "#                              | / _---=> hardirq/softirq\n");
-	seq_puts(s, "#                              || / _--=> preempt-depth     ");
-	seq_puts(s, "                       MAX\n");
-
-	seq_puts(s, "#                              || /                         ");
+	seq_puts(s, "#                              || / _--=> preempt-depth\n");
+	seq_puts(s, "#                              ||| / _-=> migrate-disable     ");
+	seq_puts(s, "                    MAX\n");
+	seq_puts(s, "#                              |||| /     delay               ");
 	seq_puts(s, "                    SINGLE      Interference counters:\n");
 
-	seq_puts(s, "#                              ||||               RUNTIME   ");
+	seq_puts(s, "#                              |||||               RUNTIME   ");
 	seq_puts(s, "   NOISE  %% OF CPU  NOISE    +-----------------------------+\n");
 
-	seq_puts(s, "#           TASK-PID      CPU# ||||   TIMESTAMP    IN US    ");
+	seq_puts(s, "#           TASK-PID      CPU# |||||   TIMESTAMP    IN US    ");
 	seq_puts(s, "   IN US  AVAILABLE  IN US     HW    NMI    IRQ   SIRQ THREAD\n");
 
-	seq_puts(s, "#              | |         |   ||||      |           |      ");
+	seq_puts(s, "#              | |         |   |||||      |           |      ");
 	seq_puts(s, "       |    |            |      |      |      |      |      |\n");
 }
 #endif /* CONFIG_PREEMPT_RT */
@@ -315,19 +452,24 @@ static void print_osnoise_headers(struct seq_file *s)
  * osnoise_taint - report an osnoise error.
  */
 #define osnoise_taint(msg) ({							\
-	struct trace_array *tr = osnoise_trace;					\
+	struct osnoise_instance *inst;						\
+	struct trace_buffer *buffer;						\
 										\
-	trace_array_printk_buf(tr->array_buffer.buffer, _THIS_IP_, msg);	\
+	rcu_read_lock();							\
+	list_for_each_entry_rcu(inst, &osnoise_instances, list) {		\
+		buffer = inst->tr->array_buffer.buffer;				\
+		trace_array_printk_buf(buffer, _THIS_IP_, msg);			\
+	}									\
+	rcu_read_unlock();							\
 	osnoise_data.tainted = true;						\
 })
 
 /*
  * Record an osnoise_sample into the tracer buffer.
  */
-static void trace_osnoise_sample(struct osnoise_sample *sample)
+static void
+__trace_osnoise_sample(struct osnoise_sample *sample, struct trace_buffer *buffer)
 {
-	struct trace_array *tr = osnoise_trace;
-	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct trace_event_call *call = &event_osnoise;
 	struct ring_buffer_event *event;
 	struct osnoise_entry *entry;
@@ -350,6 +492,22 @@ static void trace_osnoise_sample(struct osnoise_sample *sample)
 		trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
+/*
+ * Record an osnoise_sample on all osnoise instances.
+ */
+static void trace_osnoise_sample(struct osnoise_sample *sample)
+{
+	struct osnoise_instance *inst;
+	struct trace_buffer *buffer;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+		buffer = inst->tr->array_buffer.buffer;
+		__trace_osnoise_sample(sample, buffer);
+	}
+	rcu_read_unlock();
+}
+
 #ifdef CONFIG_TIMERLAT_TRACER
 /*
  * Print the timerlat header info.
@@ -378,23 +536,20 @@ static void print_timerlat_headers(struct seq_file *s)
 	seq_puts(s, "#                               / _----=> need-resched\n");
 	seq_puts(s, "#                              | / _---=> hardirq/softirq\n");
 	seq_puts(s, "#                              || / _--=> preempt-depth\n");
-	seq_puts(s, "#                              || /\n");
-	seq_puts(s, "#                              ||||             ACTIVATION\n");
-	seq_puts(s, "#           TASK-PID      CPU# ||||   TIMESTAMP    ID     ");
-	seq_puts(s, "       CONTEXT                LATENCY\n");
-	seq_puts(s, "#              | |         |   ||||      |         |      ");
+	seq_puts(s, "#                              ||| / _-=> migrate-disable\n");
+	seq_puts(s, "#                              |||| /     delay\n");
+	seq_puts(s, "#                              |||||            ACTIVATION\n");
+	seq_puts(s, "#           TASK-PID      CPU# |||||   TIMESTAMP   ID      ");
+	seq_puts(s, "      CONTEXT                 LATENCY\n");
+	seq_puts(s, "#              | |         |   |||||      |         |      ");
 	seq_puts(s, "            |                       |\n");
 }
 #endif /* CONFIG_PREEMPT_RT */
 
-/*
- * Record an timerlat_sample into the tracer buffer.
- */
-static void trace_timerlat_sample(struct timerlat_sample *sample)
+static void
+__trace_timerlat_sample(struct timerlat_sample *sample, struct trace_buffer *buffer)
 {
-	struct trace_array *tr = osnoise_trace;
 	struct trace_event_call *call = &event_osnoise;
-	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct timerlat_entry *entry;
 
@@ -411,6 +566,22 @@ static void trace_timerlat_sample(struct timerlat_sample *sample)
 		trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
+/*
+ * Record an timerlat_sample into the tracer buffer.
+ */
+static void trace_timerlat_sample(struct timerlat_sample *sample)
+{
+	struct osnoise_instance *inst;
+	struct trace_buffer *buffer;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+		buffer = inst->tr->array_buffer.buffer;
+		__trace_timerlat_sample(sample, buffer);
+	}
+	rcu_read_unlock();
+}
+
 #ifdef CONFIG_STACKTRACE
 
 #define	MAX_CALLS	256
@@ -450,29 +621,18 @@ static void timerlat_save_stack(int skip)
 	return;
 
 }
-/*
- * timerlat_dump_stack - dump a stack trace previously saved
- *
- * Dump a saved stack trace into the trace buffer.
- */
-static void timerlat_dump_stack(void)
+
+static void
+__timerlat_dump_stack(struct trace_buffer *buffer, struct trace_stack *fstack, unsigned int size)
 {
 	struct trace_event_call *call = &event_osnoise;
-	struct trace_array *tr = osnoise_trace;
-	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
-	struct trace_stack *fstack;
 	struct stack_entry *entry;
-	unsigned int size;
-
-	preempt_disable_notrace();
-	fstack = this_cpu_ptr(&trace_stack);
-	size = fstack->stack_size;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_STACK, sizeof(*entry) + size,
 					  tracing_gen_ctx());
 	if (!event)
-		goto out;
+		return;
 
 	entry = ring_buffer_event_data(event);
 
@@ -481,12 +641,39 @@ static void timerlat_dump_stack(void)
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
 		trace_buffer_unlock_commit_nostack(buffer, event);
+}
 
-out:
+/*
+ * timerlat_dump_stack - dump a stack trace previously saved
+ */
+static void timerlat_dump_stack(u64 latency)
+{
+	struct osnoise_instance *inst;
+	struct trace_buffer *buffer;
+	struct trace_stack *fstack;
+	unsigned int size;
+
+	/*
+	 * trace only if latency > print_stack config, if enabled.
+	 */
+	if (!osnoise_data.print_stack || osnoise_data.print_stack > latency)
+		return;
+
+	preempt_disable_notrace();
+	fstack = this_cpu_ptr(&trace_stack);
+	size = fstack->stack_size;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+		buffer = inst->tr->array_buffer.buffer;
+		__timerlat_dump_stack(buffer, fstack, size);
+
+	}
+	rcu_read_unlock();
 	preempt_enable_notrace();
 }
-#else
-#define timerlat_dump_stack() do {} while (0)
+#else /* CONFIG_STACKTRACE */
+#define timerlat_dump_stack(u64 latency) do {} while (0)
 #define timerlat_save_stack(a) do {} while (0)
 #endif /* CONFIG_STACKTRACE */
 #endif /* CONFIG_TIMERLAT_TRACER */
@@ -866,21 +1053,9 @@ static void trace_softirq_exit_callback(void *data, unsigned int vec_nr)
 	if (!osn_var->sampling)
 		return;
 
-#ifdef CONFIG_TIMERLAT_TRACER
-	/*
-	 * If the timerlat is enabled, but the irq handler did
-	 * not run yet enabling timerlat_tracer, do not trace.
-	 */
-	if (unlikely(osnoise_data.timerlat_tracer)) {
-		struct timerlat_variables *tlat_var;
-		tlat_var = this_cpu_tmr_var();
-		if (!tlat_var->tracing_thread) {
-			osn_var->softirq.arrival_time = 0;
-			osn_var->softirq.delta_start = 0;
+	if (unlikely(timerlat_enabled()))
+		if (!timerlat_softirq_exit(osn_var))
 			return;
-		}
-	}
-#endif
 
 	duration = get_int_safe_duration(osn_var, &osn_var->softirq.delta_start);
 	trace_softirq_noise(vec_nr, osn_var->softirq.arrival_time, duration);
@@ -974,17 +1149,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
 	if (!osn_var->sampling)
 		return;
 
-#ifdef CONFIG_TIMERLAT_TRACER
-	if (osnoise_data.timerlat_tracer) {
-		struct timerlat_variables *tlat_var;
-		tlat_var = this_cpu_tmr_var();
-		if (!tlat_var->tracing_thread) {
-			osn_var->thread.delta_start = 0;
-			osn_var->thread.arrival_time = 0;
+	if (unlikely(timerlat_enabled()))
+		if (!timerlat_thread_exit(osn_var))
 			return;
-		}
-	}
-#endif
 
 	duration = get_int_safe_duration(osn_var, &osn_var->thread.delta_start);
 
@@ -1077,12 +1244,37 @@ diff_osn_sample_stats(struct osnoise_variables *osn_var, struct osnoise_sample *
  */
 static __always_inline void osnoise_stop_tracing(void)
 {
-	struct trace_array *tr = osnoise_trace;
+	struct osnoise_instance *inst;
+	struct trace_array *tr;
 
-	trace_array_printk_buf(tr->array_buffer.buffer, _THIS_IP_,
-			"stop tracing hit on cpu %d\n", smp_processor_id());
+	rcu_read_lock();
+	list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+		tr = inst->tr;
+		trace_array_printk_buf(tr->array_buffer.buffer, _THIS_IP_,
+				"stop tracing hit on cpu %d\n", smp_processor_id());
 
-	tracer_tracing_off(tr);
+		tracer_tracing_off(tr);
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * notify_new_max_latency - Notify a new max latency via fsnotify interface.
+ */
+static void notify_new_max_latency(u64 latency)
+{
+	struct osnoise_instance *inst;
+	struct trace_array *tr;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+		tr = inst->tr;
+		if (tr->max_latency < latency) {
+			tr->max_latency = latency;
+			latency_fsnotify(tr);
+		}
+	}
+	rcu_read_unlock();
 }
 
 /*
@@ -1096,7 +1288,6 @@ static __always_inline void osnoise_stop_tracing(void)
 static int run_osnoise(void)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
-	struct trace_array *tr = osnoise_trace;
 	u64 start, sample, last_sample;
 	u64 last_int_count, int_count;
 	s64 noise = 0, max_noise = 0;
@@ -1231,11 +1422,7 @@ static int run_osnoise(void)
 
 	trace_osnoise_sample(&s);
 
-	/* Keep a running maximum ever recorded osnoise "latency" */
-	if (max_noise > tr->max_latency) {
-		tr->max_latency = max_noise;
-		latency_fsnotify(tr);
-	}
+	notify_new_max_latency(max_noise);
 
 	if (osnoise_data.stop_tracing_total)
 		if (s.noise > osnoise_data.stop_tracing_total)
@@ -1293,7 +1480,6 @@ static int osnoise_main(void *data)
 static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
-	struct trace_array *tr = osnoise_trace;
 	struct timerlat_variables *tlat;
 	struct timerlat_sample s;
 	u64 now;
@@ -1332,9 +1518,11 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
 	 * running, the thread needs to receive the softirq delta_start. The
 	 * reason being is that the softirq will be the last to be unfolded,
 	 * resseting the thread delay to zero.
+	 *
+	 * The PREEMPT_RT is a special case, though. As softirqs run as threads
+	 * on RT, moving the thread is enough.
 	 */
-#ifndef CONFIG_PREEMPT_RT
-	if (osn_var->softirq.delta_start) {
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) && osn_var->softirq.delta_start) {
 		copy_int_safe_time(osn_var, &osn_var->thread.delta_start,
 				   &osn_var->softirq.delta_start);
 
@@ -1344,13 +1532,6 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
 		copy_int_safe_time(osn_var, &osn_var->thread.delta_start,
 				    &osn_var->irq.delta_start);
 	}
-#else /* CONFIG_PREEMPT_RT */
-	/*
-	 * The sofirqs run as threads on RT, so there is not need
-	 * to keep track of it.
-	 */
-	copy_int_safe_time(osn_var, &osn_var->thread.delta_start, &osn_var->irq.delta_start);
-#endif /* CONFIG_PREEMPT_RT */
 
 	/*
 	 * Compute the current time with the expected time.
@@ -1364,11 +1545,7 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
 
 	trace_timerlat_sample(&s);
 
-	/* Keep a running maximum ever recorded os noise "latency" */
-	if (diff > tr->max_latency) {
-		tr->max_latency = diff;
-		latency_fsnotify(tr);
-	}
+	notify_new_max_latency(diff);
 
 	if (osnoise_data.stop_tracing)
 		if (time_to_us(diff) >= osnoise_data.stop_tracing)
@@ -1456,11 +1633,7 @@ static int timerlat_main(void *data)
 
 		trace_timerlat_sample(&s);
 
-#ifdef CONFIG_STACKTRACE
-		if (osnoise_data.print_stack)
-			if (osnoise_data.print_stack <= time_to_us(diff))
-				timerlat_dump_stack();
-#endif /* CONFIG_STACKTRACE */
+		timerlat_dump_stack(time_to_us(diff));
 
 		tlat->tracing_thread = false;
 		if (osnoise_data.stop_tracing_total)
@@ -1473,6 +1646,11 @@ static int timerlat_main(void *data)
 	hrtimer_cancel(&tlat->timer);
 	return 0;
 }
+#else /* CONFIG_TIMERLAT_TRACER */
+static int timerlat_main(void *data)
+{
+	return 0;
+}
 #endif /* CONFIG_TIMERLAT_TRACER */
 
 /*
@@ -1515,17 +1693,14 @@ static int start_kthread(unsigned int cpu)
 	void *main = osnoise_main;
 	char comm[24];
 
-#ifdef CONFIG_TIMERLAT_TRACER
-	if (osnoise_data.timerlat_tracer) {
+	if (timerlat_enabled()) {
 		snprintf(comm, 24, "timerlat/%d", cpu);
 		main = timerlat_main;
 	} else {
 		snprintf(comm, 24, "osnoise/%d", cpu);
 	}
-#else
-	snprintf(comm, 24, "osnoise/%d", cpu);
-#endif
-	kthread = kthread_create_on_cpu(main, NULL, cpu, comm);
+
+	kthread = kthread_run_on_cpu(main, NULL, cpu, comm);
 
 	if (IS_ERR(kthread)) {
 		pr_err(BANNER "could not start sampling thread\n");
@@ -1534,7 +1709,6 @@ static int start_kthread(unsigned int cpu)
 	}
 
 	per_cpu(per_cpu_osnoise_var, cpu).kthread = kthread;
-	wake_up_process(kthread);
 
 	return 0;
 }
@@ -1545,7 +1719,7 @@ static int start_kthread(unsigned int cpu)
  * This starts the kernel thread that will look for osnoise on many
  * cpus.
  */
-static int start_per_cpu_kthreads(struct trace_array *tr)
+static int start_per_cpu_kthreads(void)
 {
 	struct cpumask *current_mask = &save_cpumask;
 	int retval = 0;
@@ -1553,13 +1727,9 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
 
 	cpus_read_lock();
 	/*
-	 * Run only on CPUs in which trace and osnoise are allowed to run.
-	 */
-	cpumask_and(current_mask, tr->tracing_cpumask, &osnoise_cpumask);
-	/*
-	 * And the CPU is online.
+	 * Run only on online CPUs in which osnoise is allowed to run.
 	 */
-	cpumask_and(current_mask, cpu_online_mask, current_mask);
+	cpumask_and(current_mask, cpu_online_mask, &osnoise_cpumask);
 
 	for_each_possible_cpu(cpu)
 		per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
@@ -1580,13 +1750,11 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
 #ifdef CONFIG_HOTPLUG_CPU
 static void osnoise_hotplug_workfn(struct work_struct *dummy)
 {
-	struct trace_array *tr = osnoise_trace;
 	unsigned int cpu = smp_processor_id();
 
-
 	mutex_lock(&trace_types_lock);
 
-	if (!osnoise_busy)
+	if (!osnoise_has_registered_instances())
 		goto out_unlock_trace;
 
 	mutex_lock(&interface_lock);
@@ -1595,9 +1763,6 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy)
 	if (!cpumask_test_cpu(cpu, &osnoise_cpumask))
 		goto out_unlock;
 
-	if (!cpumask_test_cpu(cpu, tr->tracing_cpumask))
-		goto out_unlock;
-
 	start_kthread(cpu);
 
 out_unlock:
@@ -1686,9 +1851,6 @@ out_unlock:
 	return count;
 }
 
-static void osnoise_tracer_start(struct trace_array *tr);
-static void osnoise_tracer_stop(struct trace_array *tr);
-
 /*
  * osnoise_cpus_write - Write function for "cpus" entry
  * @filp: The active open file structure
@@ -1700,19 +1862,15 @@ static void osnoise_tracer_stop(struct trace_array *tr);
  * interface to the osnoise trace. By default, it lists all  CPUs,
  * in this way, allowing osnoise threads to run on any online CPU
  * of the system. It serves to restrict the execution of osnoise to the
- * set of CPUs writing via this interface. Note that osnoise also
- * respects the "tracing_cpumask." Hence, osnoise threads will run only
- * on the set of CPUs allowed here AND on "tracing_cpumask." Why not
- * have just "tracing_cpumask?" Because the user might be interested
- * in tracing what is running on other CPUs. For instance, one might
- * run osnoise in one HT CPU while observing what is running on the
- * sibling HT CPU.
+ * set of CPUs writing via this interface. Why not use "tracing_cpumask"?
+ * Because the user might be interested in tracing what is running on
+ * other CPUs. For instance, one might run osnoise in one HT CPU
+ * while observing what is running on the sibling HT CPU.
  */
 static ssize_t
 osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
 		   loff_t *ppos)
 {
-	struct trace_array *tr = osnoise_trace;
 	cpumask_var_t osnoise_cpumask_new;
 	int running, err;
 	char buf[256];
@@ -1731,13 +1889,12 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
 		goto err_free;
 
 	/*
-	 * trace_types_lock is taken to avoid concurrency on start/stop
-	 * and osnoise_busy.
+	 * trace_types_lock is taken to avoid concurrency on start/stop.
 	 */
 	mutex_lock(&trace_types_lock);
-	running = osnoise_busy;
+	running = osnoise_has_registered_instances();
 	if (running)
-		osnoise_tracer_stop(tr);
+		stop_per_cpu_kthreads();
 
 	mutex_lock(&interface_lock);
 	/*
@@ -1751,7 +1908,7 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
 	mutex_unlock(&interface_lock);
 
 	if (running)
-		osnoise_tracer_start(tr);
+		start_per_cpu_kthreads();
 	mutex_unlock(&trace_types_lock);
 
 	free_cpumask_var(osnoise_cpumask_new);
@@ -1835,6 +1992,47 @@ static const struct file_operations cpus_fops = {
 	.llseek		= generic_file_llseek,
 };
 
+#ifdef CONFIG_TIMERLAT_TRACER
+#ifdef CONFIG_STACKTRACE
+static int init_timerlat_stack_tracefs(struct dentry *top_dir)
+{
+	struct dentry *tmp;
+
+	tmp = tracefs_create_file("print_stack", TRACE_MODE_WRITE, top_dir,
+				  &osnoise_print_stack, &trace_min_max_fops);
+	if (!tmp)
+		return -ENOMEM;
+
+	return 0;
+}
+#else /* CONFIG_STACKTRACE */
+static int init_timerlat_stack_tracefs(struct dentry *top_dir)
+{
+	return 0;
+}
+#endif /* CONFIG_STACKTRACE */
+
+/*
+ * init_timerlat_tracefs - A function to initialize the timerlat interface files
+ */
+static int init_timerlat_tracefs(struct dentry *top_dir)
+{
+	struct dentry *tmp;
+
+	tmp = tracefs_create_file("timerlat_period_us", TRACE_MODE_WRITE, top_dir,
+				  &timerlat_period, &trace_min_max_fops);
+	if (!tmp)
+		return -ENOMEM;
+
+	return init_timerlat_stack_tracefs(top_dir);
+}
+#else /* CONFIG_TIMERLAT_TRACER */
+static int init_timerlat_tracefs(struct dentry *top_dir)
+{
+	return 0;
+}
+#endif /* CONFIG_TIMERLAT_TRACER */
+
 /*
  * init_tracefs - A function to initialize the tracefs interface files
  *
@@ -1856,42 +2054,33 @@ static int init_tracefs(void)
 	if (!top_dir)
 		return 0;
 
-	tmp = tracefs_create_file("period_us", 0640, top_dir,
+	tmp = tracefs_create_file("period_us", TRACE_MODE_WRITE, top_dir,
 				  &osnoise_period, &trace_min_max_fops);
 	if (!tmp)
 		goto err;
 
-	tmp = tracefs_create_file("runtime_us", 0644, top_dir,
+	tmp = tracefs_create_file("runtime_us", TRACE_MODE_WRITE, top_dir,
 				  &osnoise_runtime, &trace_min_max_fops);
 	if (!tmp)
 		goto err;
 
-	tmp = tracefs_create_file("stop_tracing_us", 0640, top_dir,
+	tmp = tracefs_create_file("stop_tracing_us", TRACE_MODE_WRITE, top_dir,
 				  &osnoise_stop_tracing_in, &trace_min_max_fops);
 	if (!tmp)
 		goto err;
 
-	tmp = tracefs_create_file("stop_tracing_total_us", 0640, top_dir,
+	tmp = tracefs_create_file("stop_tracing_total_us", TRACE_MODE_WRITE, top_dir,
 				  &osnoise_stop_tracing_total, &trace_min_max_fops);
 	if (!tmp)
 		goto err;
 
-	tmp = trace_create_file("cpus", 0644, top_dir, NULL, &cpus_fops);
-	if (!tmp)
-		goto err;
-#ifdef CONFIG_TIMERLAT_TRACER
-#ifdef CONFIG_STACKTRACE
-	tmp = tracefs_create_file("print_stack", 0640, top_dir,
-				  &osnoise_print_stack, &trace_min_max_fops);
+	tmp = trace_create_file("cpus", TRACE_MODE_WRITE, top_dir, NULL, &cpus_fops);
 	if (!tmp)
 		goto err;
-#endif
 
-	tmp = tracefs_create_file("timerlat_period_us", 0640, top_dir,
-				  &timerlat_period, &trace_min_max_fops);
-	if (!tmp)
+	ret = init_timerlat_tracefs(top_dir);
+	if (ret)
 		goto err;
-#endif
 
 	return 0;
 
@@ -1932,74 +2121,122 @@ out_unhook_irq:
 	return -EINVAL;
 }
 
-static int __osnoise_tracer_start(struct trace_array *tr)
+static void osnoise_unhook_events(void)
+{
+	unhook_thread_events();
+	unhook_softirq_events();
+	unhook_irq_events();
+}
+
+/*
+ * osnoise_workload_start - start the workload and hook to events
+ */
+static int osnoise_workload_start(void)
 {
 	int retval;
 
+	/*
+	 * Instances need to be registered after calling workload
+	 * start. Hence, if there is already an instance, the
+	 * workload was already registered. Otherwise, this
+	 * code is on the way to register the first instance,
+	 * and the workload will start.
+	 */
+	if (osnoise_has_registered_instances())
+		return 0;
+
 	osn_var_reset_all();
 
 	retval = osnoise_hook_events();
 	if (retval)
 		return retval;
+
 	/*
-	 * Make sure NMIs see reseted values.
+	 * Make sure that ftrace_nmi_enter/exit() see reset values
+	 * before enabling trace_osnoise_callback_enabled.
 	 */
 	barrier();
 	trace_osnoise_callback_enabled = true;
 
-	retval = start_per_cpu_kthreads(tr);
+	retval = start_per_cpu_kthreads();
 	if (retval) {
-		unhook_irq_events();
+		trace_osnoise_callback_enabled = false;
+		/*
+		 * Make sure that ftrace_nmi_enter/exit() see
+		 * trace_osnoise_callback_enabled as false before continuing.
+		 */
+		barrier();
+
+		osnoise_unhook_events();
 		return retval;
 	}
 
-	osnoise_busy = true;
-
 	return 0;
 }
 
+/*
+ * osnoise_workload_stop - stop the workload and unhook the events
+ */
+static void osnoise_workload_stop(void)
+{
+	/*
+	 * Instances need to be unregistered before calling
+	 * stop. Hence, if there is a registered instance, more
+	 * than one instance is running, and the workload will not
+	 * yet stop. Otherwise, this code is on the way to disable
+	 * the last instance, and the workload can stop.
+	 */
+	if (osnoise_has_registered_instances())
+		return;
+
+	trace_osnoise_callback_enabled = false;
+	/*
+	 * Make sure that ftrace_nmi_enter/exit() see
+	 * trace_osnoise_callback_enabled as false before continuing.
+	 */
+	barrier();
+
+	stop_per_cpu_kthreads();
+
+	osnoise_unhook_events();
+}
+
 static void osnoise_tracer_start(struct trace_array *tr)
 {
 	int retval;
 
-	if (osnoise_busy)
+	/*
+	 * If the instance is already registered, there is no need to
+	 * register it again.
+	 */
+	if (osnoise_instance_registered(tr))
 		return;
 
-	retval = __osnoise_tracer_start(tr);
+	retval = osnoise_workload_start();
 	if (retval)
 		pr_err(BANNER "Error starting osnoise tracer\n");
 
+	osnoise_register_instance(tr);
 }
 
 static void osnoise_tracer_stop(struct trace_array *tr)
 {
-	if (!osnoise_busy)
-		return;
-
-	trace_osnoise_callback_enabled = false;
-	barrier();
-
-	stop_per_cpu_kthreads();
-
-	unhook_irq_events();
-	unhook_softirq_events();
-	unhook_thread_events();
-
-	osnoise_busy = false;
+	osnoise_unregister_instance(tr);
+	osnoise_workload_stop();
 }
 
 static int osnoise_tracer_init(struct trace_array *tr)
 {
-
-	/* Only allow one instance to enable this */
-	if (osnoise_busy)
+	/*
+	 * Only allow osnoise tracer if timerlat tracer is not running
+	 * already.
+	 */
+	if (timerlat_enabled())
 		return -EBUSY;
 
-	osnoise_trace = tr;
 	tr->max_latency = 0;
 
 	osnoise_tracer_start(tr);
-
 	return 0;
 }
 
@@ -2023,45 +2260,55 @@ static void timerlat_tracer_start(struct trace_array *tr)
 {
 	int retval;
 
-	if (osnoise_busy)
+	/*
+	 * If the instance is already registered, there is no need to
+	 * register it again.
+	 */
+	if (osnoise_instance_registered(tr))
 		return;
 
-	osnoise_data.timerlat_tracer = 1;
-
-	retval = __osnoise_tracer_start(tr);
+	retval = osnoise_workload_start();
 	if (retval)
-		goto out_err;
+		pr_err(BANNER "Error starting timerlat tracer\n");
+
+	osnoise_register_instance(tr);
 
 	return;
-out_err:
-	pr_err(BANNER "Error starting timerlat tracer\n");
 }
 
 static void timerlat_tracer_stop(struct trace_array *tr)
 {
 	int cpu;
 
-	if (!osnoise_busy)
-		return;
-
-	for_each_online_cpu(cpu)
-		per_cpu(per_cpu_osnoise_var, cpu).sampling = 0;
+	osnoise_unregister_instance(tr);
 
-	osnoise_tracer_stop(tr);
+	/*
+	 * Instruct the threads to stop only if this is the last instance.
+	 */
+	if (!osnoise_has_registered_instances()) {
+		for_each_online_cpu(cpu)
+			per_cpu(per_cpu_osnoise_var, cpu).sampling = 0;
+	}
 
-	osnoise_data.timerlat_tracer = 0;
+	osnoise_workload_stop();
 }
 
 static int timerlat_tracer_init(struct trace_array *tr)
 {
-	/* Only allow one instance to enable this */
-	if (osnoise_busy)
+	/*
+	 * Only allow timerlat tracer if osnoise tracer is not running already.
+	 */
+	if (osnoise_has_registered_instances() && !osnoise_data.timerlat_tracer)
 		return -EBUSY;
 
-	osnoise_trace = tr;
+	/*
+	 * If this is the first instance, set timerlat_tracer to block
+	 * osnoise tracer start.
+	 */
+	if (!osnoise_has_registered_instances())
+		osnoise_data.timerlat_tracer = 1;
 
 	tr->max_latency = 0;
-
 	timerlat_tracer_start(tr);
 
 	return 0;
@@ -2070,6 +2317,13 @@ static int timerlat_tracer_init(struct trace_array *tr)
 static void timerlat_tracer_reset(struct trace_array *tr)
 {
 	timerlat_tracer_stop(tr);
+
+	/*
+	 * If this is the last instance, reset timerlat_tracer allowing
+	 * osnoise to be started.
+	 */
+	if (!osnoise_has_registered_instances())
+		osnoise_data.timerlat_tracer = 0;
 }
 
 static struct tracer timerlat_tracer __read_mostly = {
@@ -2081,6 +2335,16 @@ static struct tracer timerlat_tracer __read_mostly = {
 	.print_header	= print_timerlat_headers,
 	.allow_instances = true,
 };
+
+__init static int init_timerlat_tracer(void)
+{
+	return register_tracer(&timerlat_tracer);
+}
+#else /* CONFIG_TIMERLAT_TRACER */
+__init static int init_timerlat_tracer(void)
+{
+	return 0;
+}
 #endif /* CONFIG_TIMERLAT_TRACER */
 
 __init static int init_osnoise_tracer(void)
@@ -2097,15 +2361,16 @@ __init static int init_osnoise_tracer(void)
 		return ret;
 	}
 
-#ifdef CONFIG_TIMERLAT_TRACER
-	ret = register_tracer(&timerlat_tracer);
+	ret = init_timerlat_tracer();
 	if (ret) {
-		pr_err(BANNER "Error registering timerlat\n");
+		pr_err(BANNER "Error registering timerlat!\n");
 		return ret;
 	}
-#endif
+
 	osnoise_init_hotplug_support();
 
+	INIT_LIST_HEAD_RCU(&osnoise_instances);
+
 	init_tracefs();
 
 	return 0;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index c2ca40e8595b..8aa493d25c73 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/mm.h>
 
@@ -346,22 +347,12 @@ int trace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...)
 }
 EXPORT_SYMBOL_GPL(trace_output_call);
 
-#ifdef CONFIG_KRETPROBES
-static inline const char *kretprobed(const char *name)
+static inline const char *kretprobed(const char *name, unsigned long addr)
 {
-	static const char tramp_name[] = "kretprobe_trampoline";
-	int size = sizeof(tramp_name);
-
-	if (strncmp(tramp_name, name, size) == 0)
+	if (is_kretprobe_trampoline(addr))
 		return "[unknown/kretprobe'd]";
 	return name;
 }
-#else
-static inline const char *kretprobed(const char *name)
-{
-	return name;
-}
-#endif /* CONFIG_KRETPROBES */
 
 void
 trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset)
@@ -374,7 +365,7 @@ trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset)
 		sprint_symbol(str, address);
 	else
 		kallsyms_lookup(address, NULL, NULL, NULL, str);
-	name = kretprobed(str);
+	name = kretprobed(str, address);
 
 	if (name && strlen(name)) {
 		trace_seq_puts(s, name);
@@ -454,14 +445,18 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 	char irqs_off;
 	int hardirq;
 	int softirq;
+	int bh_off;
 	int nmi;
 
 	nmi = entry->flags & TRACE_FLAG_NMI;
 	hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
 	softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
+	bh_off = entry->flags & TRACE_FLAG_BH_OFF;
 
 	irqs_off =
+		(entry->flags & TRACE_FLAG_IRQS_OFF && bh_off) ? 'D' :
 		(entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
+		bh_off ? 'b' :
 		(entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' :
 		'.';
 
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 4b320fe7df70..29f6e95439b6 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -384,7 +384,7 @@ static __init int init_trace_printk_function_export(void)
 	if (ret)
 		return 0;
 
-	trace_create_file("printk_formats", 0444, NULL,
+	trace_create_file("printk_formats", TRACE_MODE_READ, NULL,
 				    NULL, &ftrace_formats_fops);
 
 	return 0;
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 3ed2a3f37297..73d90179b51b 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -356,6 +356,8 @@ static int __parse_imm_string(char *str, char **pbuf, int offs)
 		return -EINVAL;
 	}
 	*pbuf = kstrndup(str, len - 1, GFP_KERNEL);
+	if (!*pbuf)
+		return -ENOMEM;
 	return 0;
 }
 
@@ -1138,8 +1140,7 @@ int trace_probe_remove_file(struct trace_probe *tp,
 		return -ENOENT;
 
 	list_del_rcu(&link->list);
-	synchronize_rcu();
-	kfree(link);
+	kvfree_rcu(link);
 
 	if (list_empty(&tp->event->files))
 		trace_probe_clear_flag(tp, TP_FLAG_TRACE);
diff --git a/kernel/trace/trace_recursion_record.c b/kernel/trace/trace_recursion_record.c
index b2edac1fe156..4d4b78c8ca25 100644
--- a/kernel/trace/trace_recursion_record.c
+++ b/kernel/trace/trace_recursion_record.c
@@ -226,8 +226,8 @@ __init static int create_recursed_functions(void)
 {
 	struct dentry *dentry;
 
-	dentry = trace_create_file("recursed_functions", 0644, NULL, NULL,
-				   &recursed_functions_fops);
+	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");
 	return 0;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index adf7ef194005..afd937a46496 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -287,6 +287,40 @@ static int trace_selftest_ops(struct trace_array *tr, int cnt)
 	if (trace_selftest_test_probe3_cnt != 4)
 		goto out_free;
 
+	/* Remove trace function from probe 3 */
+	func1_name = "!" __stringify(DYN_FTRACE_TEST_NAME);
+	len1 = strlen(func1_name);
+
+	ftrace_set_filter(&test_probe3, func1_name, len1, 0);
+
+	DYN_FTRACE_TEST_NAME();
+
+	print_counts();
+
+	if (trace_selftest_test_probe1_cnt != 3)
+		goto out_free;
+	if (trace_selftest_test_probe2_cnt != 2)
+		goto out_free;
+	if (trace_selftest_test_probe3_cnt != 4)
+		goto out_free;
+	if (cnt > 1) {
+		if (trace_selftest_test_global_cnt == 0)
+			goto out_free;
+	}
+	if (trace_selftest_test_dyn_cnt == 0)
+		goto out_free;
+
+	DYN_FTRACE_TEST_NAME2();
+
+	print_counts();
+
+	if (trace_selftest_test_probe1_cnt != 3)
+		goto out_free;
+	if (trace_selftest_test_probe2_cnt != 3)
+		goto out_free;
+	if (trace_selftest_test_probe3_cnt != 5)
+		goto out_free;
+
 	ret = 0;
  out_free:
 	unregister_ftrace_function(dyn_ops);
@@ -750,6 +784,12 @@ static struct fgraph_ops fgraph_ops __initdata  = {
 	.retfunc		= &trace_graph_return,
 };
 
+#if defined(CONFIG_DYNAMIC_FTRACE) && \
+    defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS)
+#define TEST_DIRECT_TRAMP
+noinline __noclone static void trace_direct_tramp(void) { }
+#endif
+
 /*
  * Pretty much the same than for the function tracer from which the selftest
  * has been borrowed.
@@ -760,6 +800,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 {
 	int ret;
 	unsigned long count;
+	char *func_name __maybe_unused;
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 	if (ftrace_filter_param) {
@@ -808,8 +849,57 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 		goto out;
 	}
 
-	/* Don't test dynamic tracing, the function tracer already did */
+#ifdef TEST_DIRECT_TRAMP
+	tracing_reset_online_cpus(&tr->array_buffer);
+	set_graph_array(tr);
+
+	/*
+	 * Some archs *cough*PowerPC*cough* add characters to the
+	 * start of the function names. We simply put a '*' to
+	 * accommodate them.
+	 */
+	func_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
+	ftrace_set_global_filter(func_name, strlen(func_name), 1);
+
+	/*
+	 * Register direct function together with graph tracer
+	 * and make sure we get graph trace.
+	 */
+	ret = register_ftrace_direct((unsigned long) DYN_FTRACE_TEST_NAME,
+				     (unsigned long) trace_direct_tramp);
+	if (ret)
+		goto out;
+
+	ret = register_ftrace_graph(&fgraph_ops);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
+
+	DYN_FTRACE_TEST_NAME();
+
+	count = 0;
 
+	tracing_stop();
+	/* check the trace buffer */
+	ret = trace_test_buffer(&tr->array_buffer, &count);
+
+	unregister_ftrace_graph(&fgraph_ops);
+
+	ret = unregister_ftrace_direct((unsigned long) DYN_FTRACE_TEST_NAME,
+				       (unsigned long) trace_direct_tramp);
+	if (ret)
+		goto out;
+
+	tracing_start();
+
+	if (!ret && !count) {
+		ret = -1;
+		goto out;
+	}
+#endif
+
+	/* Don't test dynamic tracing, the function tracer already did */
 out:
 	/* Stop it if we failed */
 	if (ret)
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 63c285042051..5a48dba912ea 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -559,14 +559,14 @@ static __init int stack_trace_init(void)
 	if (ret)
 		return 0;
 
-	trace_create_file("stack_max_size", 0644, NULL,
+	trace_create_file("stack_max_size", TRACE_MODE_WRITE, NULL,
 			&stack_trace_max_size, &stack_max_size_fops);
 
-	trace_create_file("stack_trace", 0444, NULL,
+	trace_create_file("stack_trace", TRACE_MODE_READ, NULL,
 			NULL, &stack_trace_fops);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-	trace_create_file("stack_trace_filter", 0644, NULL,
+	trace_create_file("stack_trace_filter", TRACE_MODE_WRITE, NULL,
 			  &trace_ops, &stack_trace_filter_fops);
 #endif
 
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 8d141c3825a9..bb247beec447 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -297,9 +297,9 @@ static int init_stat_file(struct stat_session *session)
 	if (!stat_dir && (ret = tracing_stat_init()))
 		return ret;
 
-	session->file = tracefs_create_file(session->ts->name, 0644,
-					    stat_dir,
-					    session, &tracing_stat_fops);
+	session->file = tracefs_create_file(session->ts->name, TRACE_MODE_WRITE,
+					    stat_dir, session,
+					    &tracing_stat_fops);
 	if (!session->file)
 		return -ENOMEM;
 	return 0;
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 8bfcd3b09422..f755bde42fd0 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -323,8 +323,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 
 	trace_ctx = tracing_gen_ctx();
 
-	buffer = tr->array_buffer.buffer;
-	event = trace_buffer_lock_reserve(buffer,
+	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
 			sys_data->enter_event->event.type, size, trace_ctx);
 	if (!event)
 		return;
@@ -367,8 +366,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 
 	trace_ctx = tracing_gen_ctx();
 
-	buffer = tr->array_buffer.buffer;
-	event = trace_buffer_lock_reserve(buffer,
+	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
 			sys_data->exit_event->event.type, sizeof(*entry),
 			trace_ctx);
 	if (!event)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 225ce569bf8f..9711589273cd 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -7,6 +7,7 @@
  */
 #define pr_fmt(fmt)	"trace_uprobe: " fmt
 
+#include <linux/bpf-cgroup.h>
 #include <linux/security.h>
 #include <linux/ctype.h>
 #include <linux/module.h>
@@ -409,12 +410,10 @@ static bool trace_uprobe_has_same_uprobe(struct trace_uprobe *orig,
 					 struct trace_uprobe *comp)
 {
 	struct trace_probe_event *tpe = orig->tp.event;
-	struct trace_probe *pos;
 	struct inode *comp_inode = d_real_inode(comp->path.dentry);
 	int i;
 
-	list_for_each_entry(pos, &tpe->probes, list) {
-		orig = container_of(pos, struct trace_uprobe, tp);
+	list_for_each_entry(orig, &tpe->probes, tp.list) {
 		if (comp_inode != d_real_inode(orig->path.dentry) ||
 		    comp->offset != orig->offset)
 			continue;
@@ -949,8 +948,7 @@ static void __uprobe_trace_func(struct trace_uprobe *tu,
 				struct trace_event_file *trace_file)
 {
 	struct uprobe_trace_entry_head *entry;
-	struct trace_buffer *buffer;
-	struct ring_buffer_event *event;
+	struct trace_event_buffer fbuffer;
 	void *data;
 	int size, esize;
 	struct trace_event_call *call = trace_probe_event_call(&tu->tp);
@@ -965,12 +963,10 @@ static void __uprobe_trace_func(struct trace_uprobe *tu,
 
 	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
 	size = esize + tu->tp.size + dsize;
-	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
-						call->event.type, size, 0);
-	if (!event)
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file, size);
+	if (!entry)
 		return;
 
-	entry = ring_buffer_event_data(event);
 	if (is_ret_probe(tu)) {
 		entry->vaddr[0] = func;
 		entry->vaddr[1] = instruction_pointer(regs);
@@ -982,7 +978,7 @@ static void __uprobe_trace_func(struct trace_uprobe *tu,
 
 	memcpy(data, ucb->buf, tu->tp.size + dsize);
 
-	event_trigger_unlock_commit(trace_file, buffer, event, entry, 0);
+	trace_event_buffer_commit(&fbuffer);
 }
 
 /* uprobe handler */
@@ -1075,14 +1071,12 @@ static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter)
 
 static void __probe_event_disable(struct trace_probe *tp)
 {
-	struct trace_probe *pos;
 	struct trace_uprobe *tu;
 
 	tu = container_of(tp, struct trace_uprobe, tp);
 	WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter));
 
-	list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
-		tu = container_of(pos, struct trace_uprobe, tp);
+	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
 		if (!tu->inode)
 			continue;
 
@@ -1094,7 +1088,7 @@ static void __probe_event_disable(struct trace_probe *tp)
 static int probe_event_enable(struct trace_event_call *call,
 			struct trace_event_file *file, filter_func_t filter)
 {
-	struct trace_probe *pos, *tp;
+	struct trace_probe *tp;
 	struct trace_uprobe *tu;
 	bool enabled;
 	int ret;
@@ -1129,8 +1123,7 @@ static int probe_event_enable(struct trace_event_call *call,
 	if (ret)
 		goto err_flags;
 
-	list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
-		tu = container_of(pos, struct trace_uprobe, tp);
+	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
 		ret = trace_uprobe_enable(tu, filter);
 		if (ret) {
 			__probe_event_disable(tp);
@@ -1275,7 +1268,7 @@ static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter,
 static int uprobe_perf_close(struct trace_event_call *call,
 			     struct perf_event *event)
 {
-	struct trace_probe *pos, *tp;
+	struct trace_probe *tp;
 	struct trace_uprobe *tu;
 	int ret = 0;
 
@@ -1287,8 +1280,7 @@ static int uprobe_perf_close(struct trace_event_call *call,
 	if (trace_uprobe_filter_remove(tu->tp.event->filter, event))
 		return 0;
 
-	list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
-		tu = container_of(pos, struct trace_uprobe, tp);
+	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
 		ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
 		if (ret)
 			break;
@@ -1300,7 +1292,7 @@ static int uprobe_perf_close(struct trace_event_call *call,
 static int uprobe_perf_open(struct trace_event_call *call,
 			    struct perf_event *event)
 {
-	struct trace_probe *pos, *tp;
+	struct trace_probe *tp;
 	struct trace_uprobe *tu;
 	int err = 0;
 
@@ -1312,7 +1304,7 @@ static int uprobe_perf_open(struct trace_event_call *call,
 	if (trace_uprobe_filter_add(tu->tp.event->filter, event))
 		return 0;
 
-	list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
 		err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
 		if (err) {
 			uprobe_perf_close(call, event);
@@ -1618,6 +1610,11 @@ create_local_trace_uprobe(char *name, unsigned long offs,
 	tu->path = path;
 	tu->ref_ctr_offset = ref_ctr_offset;
 	tu->filename = kstrdup(name, GFP_KERNEL);
+	if (!tu->filename) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
 	init_trace_event_call(tu);
 
 	ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
@@ -1655,10 +1652,10 @@ static __init int init_uprobe_trace(void)
 	if (ret)
 		return 0;
 
-	trace_create_file("uprobe_events", 0644, NULL,
+	trace_create_file("uprobe_events", TRACE_MODE_WRITE, NULL,
 				    NULL, &uprobe_events_ops);
 	/* Profile interface */
-	trace_create_file("uprobe_profile", 0444, NULL,
+	trace_create_file("uprobe_profile", TRACE_MODE_READ, NULL,
 				    NULL, &uprobe_profile_ops);
 	return 0;
 }
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index d6bddb157ef2..9628b5571846 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -15,6 +15,7 @@
 #include <linux/jhash.h>
 #include <linux/slab.h>
 #include <linux/sort.h>
+#include <linux/kmemleak.h>
 
 #include "tracing_map.h"
 #include "trace.h"
@@ -307,6 +308,7 @@ static void tracing_map_array_free(struct tracing_map_array *a)
 	for (i = 0; i < a->n_pages; i++) {
 		if (!a->pages[i])
 			break;
+		kmemleak_free(a->pages[i]);
 		free_page((unsigned long)a->pages[i]);
 	}
 
@@ -342,6 +344,7 @@ static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
 		a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL);
 		if (!a->pages[i])
 			goto free;
+		kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL);
 	}
  out:
 	return a;
@@ -834,29 +837,35 @@ int tracing_map_init(struct tracing_map *map)
 	return err;
 }
 
-static int cmp_entries_dup(const struct tracing_map_sort_entry **a,
-			   const struct tracing_map_sort_entry **b)
+static int cmp_entries_dup(const void *A, const void *B)
 {
+	const struct tracing_map_sort_entry *a, *b;
 	int ret = 0;
 
-	if (memcmp((*a)->key, (*b)->key, (*a)->elt->map->key_size))
+	a = *(const struct tracing_map_sort_entry **)A;
+	b = *(const struct tracing_map_sort_entry **)B;
+
+	if (memcmp(a->key, b->key, a->elt->map->key_size))
 		ret = 1;
 
 	return ret;
 }
 
-static int cmp_entries_sum(const struct tracing_map_sort_entry **a,
-			   const struct tracing_map_sort_entry **b)
+static int cmp_entries_sum(const void *A, const void *B)
 {
 	const struct tracing_map_elt *elt_a, *elt_b;
+	const struct tracing_map_sort_entry *a, *b;
 	struct tracing_map_sort_key *sort_key;
 	struct tracing_map_field *field;
 	tracing_map_cmp_fn_t cmp_fn;
 	void *val_a, *val_b;
 	int ret = 0;
 
-	elt_a = (*a)->elt;
-	elt_b = (*b)->elt;
+	a = *(const struct tracing_map_sort_entry **)A;
+	b = *(const struct tracing_map_sort_entry **)B;
+
+	elt_a = a->elt;
+	elt_b = b->elt;
 
 	sort_key = &elt_a->map->sort_key;
 
@@ -873,18 +882,21 @@ static int cmp_entries_sum(const struct tracing_map_sort_entry **a,
 	return ret;
 }
 
-static int cmp_entries_key(const struct tracing_map_sort_entry **a,
-			   const struct tracing_map_sort_entry **b)
+static int cmp_entries_key(const void *A, const void *B)
 {
 	const struct tracing_map_elt *elt_a, *elt_b;
+	const struct tracing_map_sort_entry *a, *b;
 	struct tracing_map_sort_key *sort_key;
 	struct tracing_map_field *field;
 	tracing_map_cmp_fn_t cmp_fn;
 	void *val_a, *val_b;
 	int ret = 0;
 
-	elt_a = (*a)->elt;
-	elt_b = (*b)->elt;
+	a = *(const struct tracing_map_sort_entry **)A;
+	b = *(const struct tracing_map_sort_entry **)B;
+
+	elt_a = a->elt;
+	elt_b = b->elt;
 
 	sort_key = &elt_a->map->sort_key;
 
@@ -989,10 +1001,8 @@ static void sort_secondary(struct tracing_map *map,
 			   struct tracing_map_sort_key *primary_key,
 			   struct tracing_map_sort_key *secondary_key)
 {
-	int (*primary_fn)(const struct tracing_map_sort_entry **,
-			  const struct tracing_map_sort_entry **);
-	int (*secondary_fn)(const struct tracing_map_sort_entry **,
-			    const struct tracing_map_sort_entry **);
+	int (*primary_fn)(const void *, const void *);
+	int (*secondary_fn)(const void *, const void *);
 	unsigned i, start = 0, n_sub = 1;
 
 	if (is_key(map, primary_key->field_idx))
@@ -1061,8 +1071,7 @@ int tracing_map_sort_entries(struct tracing_map *map,
 			     unsigned int n_sort_keys,
 			     struct tracing_map_sort_entry ***sort_entries)
 {
-	int (*cmp_entries_fn)(const struct tracing_map_sort_entry **,
-			      const struct tracing_map_sort_entry **);
+	int (*cmp_entries_fn)(const void *, const void *);
 	struct tracing_map_sort_entry *sort_entry, **entries;
 	int i, n_entries, ret;