Merge branch 'next' into for-linus

Prepare input updates for 6.14 merge window.

36 files changed, 2472 insertions, 794 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 721c3b221048..74c2b1d43bb9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -242,6 +242,16 @@ config FUNCTION_GRAPH_RETVAL
 	  enable it via the trace option funcgraph-retval.
 	  See Documentation/trace/ftrace.rst
 
+config FUNCTION_GRAPH_RETADDR
+	bool "Kernel Function Graph Return Address"
+	depends on FUNCTION_GRAPH_TRACER
+	default n
+	help
+	  Support recording and printing the function return address when
+	  using function graph tracer. It can be helpful to locate code line that
+	  the function is called. This feature is off by default, and you can
+	  enable it via the trace option funcgraph-retaddr.
+
 config DYNAMIC_FTRACE
 	bool "enable/disable function tracing dynamically"
 	depends on FUNCTION_TRACER
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index cd098846e251..1b8db5aee9d3 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -24,7 +24,6 @@
 #include <linux/key.h>
 #include <linux/verification.h>
 #include <linux/namei.h>
-#include <linux/fileattr.h>
 
 #include <net/bpf_sk_storage.h>
 
@@ -798,34 +797,13 @@ const struct bpf_func_proto bpf_task_pt_regs_proto = {
 	.ret_btf_id	= &bpf_task_pt_regs_ids[0],
 };
 
-BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx)
-{
-	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	struct cgroup *cgrp;
-
-	if (unlikely(idx >= array->map.max_entries))
-		return -E2BIG;
-
-	cgrp = READ_ONCE(array->ptrs[idx]);
-	if (unlikely(!cgrp))
-		return -EAGAIN;
-
-	return task_under_cgroup_hierarchy(current, cgrp);
-}
-
-static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
-	.func           = bpf_current_task_under_cgroup,
-	.gpl_only       = false,
-	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_CONST_MAP_PTR,
-	.arg2_type      = ARG_ANYTHING,
-};
-
 struct send_signal_irq_work {
 	struct irq_work irq_work;
 	struct task_struct *task;
 	u32 sig;
 	enum pid_type type;
+	bool has_siginfo;
+	struct kernel_siginfo info;
 };
 
 static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work);
@@ -833,27 +811,46 @@ static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work);
 static void do_bpf_send_signal(struct irq_work *entry)
 {
 	struct send_signal_irq_work *work;
+	struct kernel_siginfo *siginfo;
 
 	work = container_of(entry, struct send_signal_irq_work, irq_work);
-	group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type);
+	siginfo = work->has_siginfo ? &work->info : SEND_SIG_PRIV;
+
+	group_send_sig_info(work->sig, siginfo, work->task, work->type);
 	put_task_struct(work->task);
 }
 
-static int bpf_send_signal_common(u32 sig, enum pid_type type)
+static int bpf_send_signal_common(u32 sig, enum pid_type type, struct task_struct *task, u64 value)
 {
 	struct send_signal_irq_work *work = NULL;
+	struct kernel_siginfo info;
+	struct kernel_siginfo *siginfo;
+
+	if (!task) {
+		task = current;
+		siginfo = SEND_SIG_PRIV;
+	} else {
+		clear_siginfo(&info);
+		info.si_signo = sig;
+		info.si_errno = 0;
+		info.si_code = SI_KERNEL;
+		info.si_pid = 0;
+		info.si_uid = 0;
+		info.si_value.sival_ptr = (void *)(unsigned long)value;
+		siginfo = &info;
+	}
 
 	/* Similar to bpf_probe_write_user, task needs to be
 	 * in a sound condition and kernel memory access be
 	 * permitted in order to send signal to the current
 	 * task.
 	 */
-	if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING)))
+	if (unlikely(task->flags & (PF_KTHREAD | PF_EXITING)))
 		return -EPERM;
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
 	/* Task should not be pid=1 to avoid kernel panic. */
-	if (unlikely(is_global_init(current)))
+	if (unlikely(is_global_init(task)))
 		return -EPERM;
 
 	if (irqs_disabled()) {
@@ -871,19 +868,22 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
 		 * to the irq_work. The current task may change when queued
 		 * irq works get executed.
 		 */
-		work->task = get_task_struct(current);
+		work->task = get_task_struct(task);
+		work->has_siginfo = siginfo == &info;
+		if (work->has_siginfo)
+			copy_siginfo(&work->info, &info);
 		work->sig = sig;
 		work->type = type;
 		irq_work_queue(&work->irq_work);
 		return 0;
 	}
 
-	return group_send_sig_info(sig, SEND_SIG_PRIV, current, type);
+	return group_send_sig_info(sig, siginfo, task, type);
 }
 
 BPF_CALL_1(bpf_send_signal, u32, sig)
 {
-	return bpf_send_signal_common(sig, PIDTYPE_TGID);
+	return bpf_send_signal_common(sig, PIDTYPE_TGID, NULL, 0);
 }
 
 static const struct bpf_func_proto bpf_send_signal_proto = {
@@ -895,7 +895,7 @@ static const struct bpf_func_proto bpf_send_signal_proto = {
 
 BPF_CALL_1(bpf_send_signal_thread, u32, sig)
 {
-	return bpf_send_signal_common(sig, PIDTYPE_PID);
+	return bpf_send_signal_common(sig, PIDTYPE_PID, NULL, 0);
 }
 
 static const struct bpf_func_proto bpf_send_signal_thread_proto = {
@@ -1226,7 +1226,8 @@ static const struct bpf_func_proto bpf_get_func_arg_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_ANYTHING,
-	.arg3_type	= ARG_PTR_TO_LONG,
+	.arg3_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
+	.arg3_size	= sizeof(u64),
 };
 
 BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value)
@@ -1242,7 +1243,8 @@ 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,
+	.arg2_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
+	.arg2_size	= sizeof(u64),
 };
 
 BPF_CALL_1(get_func_arg_cnt, void *, ctx)
@@ -1439,73 +1441,6 @@ static int __init bpf_key_sig_kfuncs_init(void)
 late_initcall(bpf_key_sig_kfuncs_init);
 #endif /* CONFIG_KEYS */
 
-/* filesystem kfuncs */
-__bpf_kfunc_start_defs();
-
-/**
- * bpf_get_file_xattr - get xattr of a file
- * @file: file to get xattr from
- * @name__str: name of the xattr
- * @value_p: output buffer of the xattr value
- *
- * Get xattr *name__str* of *file* and store the output in *value_ptr*.
- *
- * For security reasons, only *name__str* with prefix "user." is allowed.
- *
- * Return: 0 on success, a negative value on error.
- */
-__bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str,
-				   struct bpf_dynptr *value_p)
-{
-	struct bpf_dynptr_kern *value_ptr = (struct bpf_dynptr_kern *)value_p;
-	struct dentry *dentry;
-	u32 value_len;
-	void *value;
-	int ret;
-
-	if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
-		return -EPERM;
-
-	value_len = __bpf_dynptr_size(value_ptr);
-	value = __bpf_dynptr_data_rw(value_ptr, value_len);
-	if (!value)
-		return -EINVAL;
-
-	dentry = file_dentry(file);
-	ret = inode_permission(&nop_mnt_idmap, dentry->d_inode, MAY_READ);
-	if (ret)
-		return ret;
-	return __vfs_getxattr(dentry, dentry->d_inode, name__str, value, value_len);
-}
-
-__bpf_kfunc_end_defs();
-
-BTF_KFUNCS_START(fs_kfunc_set_ids)
-BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
-BTF_KFUNCS_END(fs_kfunc_set_ids)
-
-static int bpf_get_file_xattr_filter(const struct bpf_prog *prog, u32 kfunc_id)
-{
-	if (!btf_id_set8_contains(&fs_kfunc_set_ids, kfunc_id))
-		return 0;
-
-	/* Only allow to attach from LSM hooks, to avoid recursion */
-	return prog->type != BPF_PROG_TYPE_LSM ? -EACCES : 0;
-}
-
-static const struct btf_kfunc_id_set bpf_fs_kfunc_set = {
-	.owner = THIS_MODULE,
-	.set = &fs_kfunc_set_ids,
-	.filter = bpf_get_file_xattr_filter,
-};
-
-static int __init bpf_fs_kfuncs_init(void)
-{
-	return register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set);
-}
-
-late_initcall(bpf_fs_kfuncs_init);
-
 static const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1548,8 +1483,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_numa_node_id_proto;
 	case BPF_FUNC_perf_event_read:
 		return &bpf_perf_event_read_proto;
-	case BPF_FUNC_current_task_under_cgroup:
-		return &bpf_current_task_under_cgroup_proto;
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
 	case BPF_FUNC_probe_write_user:
@@ -1578,6 +1511,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_cgrp_storage_get_proto;
 	case BPF_FUNC_cgrp_storage_delete:
 		return &bpf_cgrp_storage_delete_proto;
+	case BPF_FUNC_current_task_under_cgroup:
+		return &bpf_current_task_under_cgroup_proto;
 #endif
 	case BPF_FUNC_send_signal:
 		return &bpf_send_signal_proto;
@@ -1598,7 +1533,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
 	case BPF_FUNC_get_task_stack:
-		return &bpf_get_task_stack_proto;
+		return prog->sleepable ? &bpf_get_task_stack_sleepable_proto
+				       : &bpf_get_task_stack_proto;
 	case BPF_FUNC_copy_from_user:
 		return &bpf_copy_from_user_proto;
 	case BPF_FUNC_copy_from_user_task:
@@ -1645,6 +1581,17 @@ static inline bool is_kprobe_session(const struct bpf_prog *prog)
 	return prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION;
 }
 
+static inline bool is_uprobe_multi(const struct bpf_prog *prog)
+{
+	return prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI ||
+	       prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION;
+}
+
+static inline bool is_uprobe_session(const struct bpf_prog *prog)
+{
+	return prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION;
+}
+
 static const struct bpf_func_proto *
 kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1654,7 +1601,7 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto;
 	case BPF_FUNC_get_stack:
-		return &bpf_get_stack_proto;
+		return prog->sleepable ? &bpf_get_stack_sleepable_proto : &bpf_get_stack_proto;
 #ifdef CONFIG_BPF_KPROBE_OVERRIDE
 	case BPF_FUNC_override_return:
 		return &bpf_override_return_proto;
@@ -1662,13 +1609,13 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_func_ip:
 		if (is_kprobe_multi(prog))
 			return &bpf_get_func_ip_proto_kprobe_multi;
-		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
+		if (is_uprobe_multi(prog))
 			return &bpf_get_func_ip_proto_uprobe_multi;
 		return &bpf_get_func_ip_proto_kprobe;
 	case BPF_FUNC_get_attach_cookie:
 		if (is_kprobe_multi(prog))
 			return &bpf_get_attach_cookie_proto_kmulti;
-		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
+		if (is_uprobe_multi(prog))
 			return &bpf_get_attach_cookie_proto_umulti;
 		return &bpf_get_attach_cookie_proto_trace;
 	default:
@@ -2303,9 +2250,10 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
 		goto unlock;
 
 	old_array = bpf_event_rcu_dereference(event->tp_event->prog_array);
+	if (!old_array)
+		goto put;
+
 	ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array);
-	if (ret == -ENOENT)
-		goto unlock;
 	if (ret < 0) {
 		bpf_prog_array_delete_safe(old_array, event->prog);
 	} else {
@@ -2313,6 +2261,14 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
 		bpf_prog_array_free_sleepable(old_array);
 	}
 
+put:
+	/*
+	 * It could be that the bpf_prog is not sleepable (and will be freed
+	 * via normal RCU), but is called from a point that supports sleepable
+	 * programs and uses tasks-trace-RCU.
+	 */
+	synchronize_rcu_tasks_trace();
+
 	bpf_prog_put(event->prog);
 	event->prog = NULL;
 
@@ -3160,7 +3116,9 @@ struct bpf_uprobe {
 	loff_t offset;
 	unsigned long ref_ctr_offset;
 	u64 cookie;
+	struct uprobe *uprobe;
 	struct uprobe_consumer consumer;
+	bool session;
 };
 
 struct bpf_uprobe_multi_link {
@@ -3173,20 +3131,20 @@ struct bpf_uprobe_multi_link {
 };
 
 struct bpf_uprobe_multi_run_ctx {
-	struct bpf_run_ctx run_ctx;
+	struct bpf_session_run_ctx session_ctx;
 	unsigned long entry_ip;
 	struct bpf_uprobe *uprobe;
 };
 
-static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes,
-				  u32 cnt)
+static void bpf_uprobe_unregister(struct bpf_uprobe *uprobes, u32 cnt)
 {
 	u32 i;
 
-	for (i = 0; i < cnt; i++) {
-		uprobe_unregister(d_real_inode(path->dentry), uprobes[i].offset,
-				  &uprobes[i].consumer);
-	}
+	for (i = 0; i < cnt; i++)
+		uprobe_unregister_nosync(uprobes[i].uprobe, &uprobes[i].consumer);
+
+	if (cnt)
+		uprobe_unregister_sync();
 }
 
 static void bpf_uprobe_multi_link_release(struct bpf_link *link)
@@ -3194,7 +3152,7 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link)
 	struct bpf_uprobe_multi_link *umulti_link;
 
 	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
-	bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt);
+	bpf_uprobe_unregister(umulti_link->uprobes, umulti_link->cnt);
 	if (umulti_link->task)
 		put_task_struct(umulti_link->task);
 	path_put(&umulti_link->path);
@@ -3220,7 +3178,8 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
 	struct bpf_uprobe_multi_link *umulti_link;
 	u32 ucount = info->uprobe_multi.count;
 	int err = 0, i;
-	long left;
+	char *p, *buf;
+	long left = 0;
 
 	if (!upath ^ !upath_size)
 		return -EINVAL;
@@ -3234,26 +3193,23 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
 	info->uprobe_multi.pid = umulti_link->task ?
 				 task_pid_nr_ns(umulti_link->task, task_active_pid_ns(current)) : 0;
 
-	if (upath) {
-		char *p, *buf;
-
-		upath_size = min_t(u32, upath_size, PATH_MAX);
-
-		buf = kmalloc(upath_size, GFP_KERNEL);
-		if (!buf)
-			return -ENOMEM;
-		p = d_path(&umulti_link->path, buf, upath_size);
-		if (IS_ERR(p)) {
-			kfree(buf);
-			return PTR_ERR(p);
-		}
-		upath_size = buf + upath_size - p;
-		left = copy_to_user(upath, p, upath_size);
+	upath_size = upath_size ? min_t(u32, upath_size, PATH_MAX) : PATH_MAX;
+	buf = kmalloc(upath_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	p = d_path(&umulti_link->path, buf, upath_size);
+	if (IS_ERR(p)) {
 		kfree(buf);
-		if (left)
-			return -EFAULT;
-		info->uprobe_multi.path_size = upath_size;
+		return PTR_ERR(p);
 	}
+	upath_size = buf + upath_size - p;
+
+	if (upath)
+		left = copy_to_user(upath, p, upath_size);
+	kfree(buf);
+	if (left)
+		return -EFAULT;
+	info->uprobe_multi.path_size = upath_size;
 
 	if (!uoffsets && !ucookies && !uref_ctr_offsets)
 		return 0;
@@ -3286,19 +3242,24 @@ static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
 
 static int uprobe_prog_run(struct bpf_uprobe *uprobe,
 			   unsigned long entry_ip,
-			   struct pt_regs *regs)
+			   struct pt_regs *regs,
+			   bool is_return, void *data)
 {
 	struct bpf_uprobe_multi_link *link = uprobe->link;
 	struct bpf_uprobe_multi_run_ctx run_ctx = {
+		.session_ctx = {
+			.is_return = is_return,
+			.data = data,
+		},
 		.entry_ip = entry_ip,
 		.uprobe = uprobe,
 	};
 	struct bpf_prog *prog = link->link.prog;
 	bool sleepable = prog->sleepable;
 	struct bpf_run_ctx *old_run_ctx;
-	int err = 0;
+	int err;
 
-	if (link->task && current->mm != link->task->mm)
+	if (link->task && !same_thread_group(current, link->task))
 		return 0;
 
 	if (sleepable)
@@ -3308,7 +3269,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe,
 
 	migrate_disable();
 
-	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+	old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx);
 	err = bpf_prog_run(link->link.prog, regs);
 	bpf_reset_run_ctx(old_run_ctx);
 
@@ -3322,8 +3283,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe,
 }
 
 static bool
-uprobe_multi_link_filter(struct uprobe_consumer *con, enum uprobe_filter_ctx ctx,
-			 struct mm_struct *mm)
+uprobe_multi_link_filter(struct uprobe_consumer *con, struct mm_struct *mm)
 {
 	struct bpf_uprobe *uprobe;
 
@@ -3332,28 +3292,36 @@ uprobe_multi_link_filter(struct uprobe_consumer *con, enum uprobe_filter_ctx ctx
 }
 
 static int
-uprobe_multi_link_handler(struct uprobe_consumer *con, struct pt_regs *regs)
+uprobe_multi_link_handler(struct uprobe_consumer *con, struct pt_regs *regs,
+			  __u64 *data)
 {
 	struct bpf_uprobe *uprobe;
+	int ret;
 
 	uprobe = container_of(con, struct bpf_uprobe, consumer);
-	return uprobe_prog_run(uprobe, instruction_pointer(regs), regs);
+	ret = uprobe_prog_run(uprobe, instruction_pointer(regs), regs, false, data);
+	if (uprobe->session)
+		return ret ? UPROBE_HANDLER_IGNORE : 0;
+	return 0;
 }
 
 static int
-uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs)
+uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs,
+			      __u64 *data)
 {
 	struct bpf_uprobe *uprobe;
 
 	uprobe = container_of(con, struct bpf_uprobe, consumer);
-	return uprobe_prog_run(uprobe, func, regs);
+	uprobe_prog_run(uprobe, func, regs, true, data);
+	return 0;
 }
 
 static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
 {
 	struct bpf_uprobe_multi_run_ctx *run_ctx;
 
-	run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, run_ctx);
+	run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx,
+			       session_ctx.run_ctx);
 	return run_ctx->entry_ip;
 }
 
@@ -3361,7 +3329,8 @@ static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx)
 {
 	struct bpf_uprobe_multi_run_ctx *run_ctx;
 
-	run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx, run_ctx);
+	run_ctx = container_of(current->bpf_ctx, struct bpf_uprobe_multi_run_ctx,
+			       session_ctx.run_ctx);
 	return run_ctx->uprobe->cookie;
 }
 
@@ -3385,7 +3354,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	if (sizeof(u64) != sizeof(void *))
 		return -EOPNOTSUPP;
 
-	if (prog->expected_attach_type != BPF_TRACE_UPROBE_MULTI)
+	if (!is_uprobe_multi(prog))
 		return -EINVAL;
 
 	flags = attr->link_create.uprobe_multi.flags;
@@ -3461,11 +3430,12 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 
 		uprobes[i].link = link;
 
-		if (flags & BPF_F_UPROBE_MULTI_RETURN)
-			uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler;
-		else
+		if (!(flags & BPF_F_UPROBE_MULTI_RETURN))
 			uprobes[i].consumer.handler = uprobe_multi_link_handler;
-
+		if (flags & BPF_F_UPROBE_MULTI_RETURN || is_uprobe_session(prog))
+			uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler;
+		if (is_uprobe_session(prog))
+			uprobes[i].session = true;
 		if (pid)
 			uprobes[i].consumer.filter = uprobe_multi_link_filter;
 	}
@@ -3480,22 +3450,26 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 		      &bpf_uprobe_multi_link_lops, prog);
 
 	for (i = 0; i < cnt; i++) {
-		err = uprobe_register_refctr(d_real_inode(link->path.dentry),
-					     uprobes[i].offset,
-					     uprobes[i].ref_ctr_offset,
-					     &uprobes[i].consumer);
-		if (err) {
-			bpf_uprobe_unregister(&path, uprobes, i);
-			goto error_free;
+		uprobes[i].uprobe = uprobe_register(d_real_inode(link->path.dentry),
+						    uprobes[i].offset,
+						    uprobes[i].ref_ctr_offset,
+						    &uprobes[i].consumer);
+		if (IS_ERR(uprobes[i].uprobe)) {
+			err = PTR_ERR(uprobes[i].uprobe);
+			link->cnt = i;
+			goto error_unregister;
 		}
 	}
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err)
-		goto error_free;
+		goto error_unregister;
 
 	return bpf_link_settle(&link_primer);
 
+error_unregister:
+	bpf_uprobe_unregister(uprobes, link->cnt);
+
 error_free:
 	kvfree(uprobes);
 	kfree(link);
@@ -3550,7 +3524,7 @@ static int bpf_kprobe_multi_filter(const struct bpf_prog *prog, u32 kfunc_id)
 	if (!btf_id_set8_contains(&kprobe_multi_kfunc_set_ids, kfunc_id))
 		return 0;
 
-	if (!is_kprobe_session(prog))
+	if (!is_kprobe_session(prog) && !is_uprobe_session(prog))
 		return -EACCES;
 
 	return 0;
@@ -3568,3 +3542,16 @@ static int __init bpf_kprobe_multi_kfuncs_init(void)
 }
 
 late_initcall(bpf_kprobe_multi_kfuncs_init);
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_send_signal_task(struct task_struct *task, int sig, enum pid_type type,
+				     u64 value)
+{
+	if (type != PIDTYPE_PID && type != PIDTYPE_TGID)
+		return -EINVAL;
+
+	return bpf_send_signal_common(sig, type, task, value);
+}
+
+__bpf_kfunc_end_defs();
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index d1d5ea2d0a1b..0bf78517b5d4 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -153,7 +153,7 @@ enum {
  * SHADOW_STACK_OFFSET:	The size in long words of the shadow stack
  * SHADOW_STACK_MAX_OFFSET: The max offset of the stack for a new frame to be added
  */
-#define SHADOW_STACK_SIZE	(PAGE_SIZE)
+#define SHADOW_STACK_SIZE	(4096)
 #define SHADOW_STACK_OFFSET	(SHADOW_STACK_SIZE / sizeof(long))
 /* Leave on a buffer at the end */
 #define SHADOW_STACK_MAX_OFFSET				\
@@ -172,6 +172,8 @@ enum {
 DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph);
 int ftrace_graph_active;
 
+static struct kmem_cache *fgraph_stack_cachep;
+
 static struct fgraph_ops *fgraph_array[FGRAPH_ARRAY_SIZE];
 static unsigned long fgraph_array_bitmask;
 
@@ -390,21 +392,7 @@ void *fgraph_reserve_data(int idx, int size_bytes)
  */
 void *fgraph_retrieve_data(int idx, int *size_bytes)
 {
-	int offset = current->curr_ret_stack - 1;
-	unsigned long val;
-
-	val = get_fgraph_entry(current, offset);
-	while (__get_type(val) == FGRAPH_TYPE_DATA) {
-		if (__get_data_index(val) == idx)
-			goto found;
-		offset -= __get_data_size(val) + 1;
-		val = get_fgraph_entry(current, offset);
-	}
-	return NULL;
-found:
-	if (size_bytes)
-		*size_bytes = __get_data_size(val) * sizeof(long);
-	return get_data_type_data(current, offset);
+	return fgraph_retrieve_parent_data(idx, size_bytes, 0);
 }
 
 /**
@@ -460,8 +448,56 @@ get_ret_stack(struct task_struct *t, int offset, int *frame_offset)
 	return RET_STACK(t, offset);
 }
 
+/**
+ * fgraph_retrieve_parent_data - get data from a parent function
+ * @idx: The index into the fgraph_array (fgraph_ops::idx)
+ * @size_bytes: A pointer to retrieved data size
+ * @depth: The depth to find the parent (0 is the current function)
+ *
+ * This is similar to fgraph_retrieve_data() but can be used to retrieve
+ * data from a parent caller function.
+ *
+ * Return: a pointer to the specified parent data or NULL if not found
+ */
+void *fgraph_retrieve_parent_data(int idx, int *size_bytes, int depth)
+{
+	struct ftrace_ret_stack *ret_stack = NULL;
+	int offset = current->curr_ret_stack;
+	unsigned long val;
+
+	if (offset <= 0)
+		return NULL;
+
+	for (;;) {
+		int next_offset;
+
+		ret_stack = get_ret_stack(current, offset, &next_offset);
+		if (!ret_stack || --depth < 0)
+			break;
+		offset = next_offset;
+	}
+
+	if (!ret_stack)
+		return NULL;
+
+	offset--;
+
+	val = get_fgraph_entry(current, offset);
+	while (__get_type(val) == FGRAPH_TYPE_DATA) {
+		if (__get_data_index(val) == idx)
+			goto found;
+		offset -= __get_data_size(val) + 1;
+		val = get_fgraph_entry(current, offset);
+	}
+	return NULL;
+found:
+	if (size_bytes)
+		*size_bytes = __get_data_size(val) * sizeof(long);
+	return get_data_type_data(current, offset);
+}
+
 /* Both enabled by default (can be cleared by function_graph tracer flags */
-static bool fgraph_sleep_time = true;
+bool fgraph_sleep_time = true;
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 /*
@@ -524,7 +560,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
 			 int fgraph_idx)
 {
 	struct ftrace_ret_stack *ret_stack;
-	unsigned long long calltime;
 	unsigned long val;
 	int offset;
 
@@ -554,8 +589,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
 		return -EBUSY;
 	}
 
-	calltime = trace_clock_local();
-
 	offset = READ_ONCE(current->curr_ret_stack);
 	ret_stack = RET_STACK(current, offset);
 	offset += FGRAPH_FRAME_OFFSET;
@@ -589,7 +622,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
 
 	ret_stack->ret = ret;
 	ret_stack->func = func;
-	ret_stack->calltime = calltime;
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	ret_stack->fp = frame_pointer;
 #endif
@@ -723,7 +755,6 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 	*offset += FGRAPH_FRAME_OFFSET;
 	*ret = ret_stack->ret;
 	trace->func = ret_stack->func;
-	trace->calltime = ret_stack->calltime;
 	trace->overrun = atomic_read(&current->trace_overrun);
 	trace->depth = current->curr_ret_depth;
 	/*
@@ -868,6 +899,29 @@ ftrace_graph_get_ret_stack(struct task_struct *task, int idx)
 }
 
 /**
+ * ftrace_graph_top_ret_addr - return the top return address in the shadow stack
+ * @task: The task to read the shadow stack from.
+ *
+ * Return the first return address on the shadow stack of the @task, which is
+ * not the fgraph's return_to_handler.
+ */
+unsigned long ftrace_graph_top_ret_addr(struct task_struct *task)
+{
+	unsigned long return_handler = (unsigned long)dereference_kernel_function_descriptor(return_to_handler);
+	struct ftrace_ret_stack *ret_stack = NULL;
+	int offset = task->curr_ret_stack;
+
+	if (offset < 0)
+		return 0;
+
+	do {
+		ret_stack = get_ret_stack(task, offset, &offset);
+	} while (ret_stack && ret_stack->ret == return_handler);
+
+	return ret_stack ? ret_stack->ret : 0;
+}
+
+/**
  * ftrace_graph_ret_addr - return the original value of the return address
  * @task: The task the unwinder is being executed on
  * @idx: An initialized pointer to the next stack index to use
@@ -892,7 +946,7 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 {
 	struct ftrace_ret_stack *ret_stack;
 	unsigned long return_handler = (unsigned long)dereference_kernel_function_descriptor(return_to_handler);
-	int i = task->curr_ret_stack;
+	int i;
 
 	if (ret != return_handler)
 		return ret;
@@ -970,8 +1024,11 @@ static int alloc_retstack_tasklist(unsigned long **ret_stack_list)
 	int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE;
 	struct task_struct *g, *t;
 
+	if (WARN_ON_ONCE(!fgraph_stack_cachep))
+		return -ENOMEM;
+
 	for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) {
-		ret_stack_list[i] = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
+		ret_stack_list[i] = kmem_cache_alloc(fgraph_stack_cachep, GFP_KERNEL);
 		if (!ret_stack_list[i]) {
 			start = 0;
 			end = i;
@@ -1002,7 +1059,7 @@ unlock:
 	rcu_read_unlock();
 free:
 	for (i = start; i < end; i++)
-		kfree(ret_stack_list[i]);
+		kmem_cache_free(fgraph_stack_cachep, ret_stack_list[i]);
 	return ret;
 }
 
@@ -1012,9 +1069,7 @@ ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
 				struct task_struct *next,
 				unsigned int prev_state)
 {
-	struct ftrace_ret_stack *ret_stack;
 	unsigned long long timestamp;
-	int offset;
 
 	/*
 	 * Does the user want to count the time a function was asleep.
@@ -1031,17 +1086,7 @@ ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
 	if (!next->ftrace_timestamp)
 		return;
 
-	/*
-	 * Update all the counters in next to make up for the
-	 * time next was sleeping.
-	 */
-	timestamp -= next->ftrace_timestamp;
-
-	for (offset = next->curr_ret_stack; offset > 0; ) {
-		ret_stack = get_ret_stack(next, offset, &offset);
-		if (ret_stack)
-			ret_stack->calltime += timestamp;
-	}
+	next->ftrace_sleeptime += timestamp - next->ftrace_timestamp;
 }
 
 static DEFINE_PER_CPU(unsigned long *, idle_ret_stack);
@@ -1077,9 +1122,12 @@ void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
 	if (ftrace_graph_active) {
 		unsigned long *ret_stack;
 
+		if (WARN_ON_ONCE(!fgraph_stack_cachep))
+			return;
+
 		ret_stack = per_cpu(idle_ret_stack, cpu);
 		if (!ret_stack) {
-			ret_stack = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
+			ret_stack = kmem_cache_alloc(fgraph_stack_cachep, GFP_KERNEL);
 			if (!ret_stack)
 				return;
 			per_cpu(idle_ret_stack, cpu) = ret_stack;
@@ -1099,7 +1147,10 @@ void ftrace_graph_init_task(struct task_struct *t)
 	if (ftrace_graph_active) {
 		unsigned long *ret_stack;
 
-		ret_stack = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
+		if (WARN_ON_ONCE(!fgraph_stack_cachep))
+			return;
+
+		ret_stack = kmem_cache_alloc(fgraph_stack_cachep, GFP_KERNEL);
 		if (!ret_stack)
 			return;
 		graph_init_task(t, ret_stack);
@@ -1114,7 +1165,11 @@ void ftrace_graph_exit_task(struct task_struct *t)
 	/* NULL must become visible to IRQs before we free it: */
 	barrier();
 
-	kfree(ret_stack);
+	if (ret_stack) {
+		if (WARN_ON_ONCE(!fgraph_stack_cachep))
+			return;
+		kmem_cache_free(fgraph_stack_cachep, ret_stack);
+	}
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -1160,19 +1215,14 @@ void fgraph_update_pid_func(void)
 static int start_graph_tracing(void)
 {
 	unsigned long **ret_stack_list;
-	int ret, cpu;
+	int ret;
 
-	ret_stack_list = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
+	ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE,
+				 sizeof(*ret_stack_list), GFP_KERNEL);
 
 	if (!ret_stack_list)
 		return -ENOMEM;
 
-	/* The cpu_boot init_task->ret_stack will never be freed */
-	for_each_online_cpu(cpu) {
-		if (!idle_task(cpu)->ret_stack)
-			ftrace_graph_init_idle_task(idle_task(cpu), cpu);
-	}
-
 	do {
 		ret = alloc_retstack_tasklist(ret_stack_list);
 	} while (ret == -EAGAIN);
@@ -1206,18 +1256,24 @@ static void init_task_vars(int idx)
 	read_unlock(&tasklist_lock);
 }
 
-static void ftrace_graph_enable_direct(bool enable_branch)
+static void ftrace_graph_enable_direct(bool enable_branch, struct fgraph_ops *gops)
 {
 	trace_func_graph_ent_t func = NULL;
 	trace_func_graph_ret_t retfunc = NULL;
 	int i;
 
-	for_each_set_bit(i, &fgraph_array_bitmask,
-			 sizeof(fgraph_array_bitmask) * BITS_PER_BYTE) {
-		func = fgraph_array[i]->entryfunc;
-		retfunc = fgraph_array[i]->retfunc;
-		fgraph_direct_gops = fgraph_array[i];
-	 }
+	if (gops) {
+		func = gops->entryfunc;
+		retfunc = gops->retfunc;
+		fgraph_direct_gops = gops;
+	} else {
+		for_each_set_bit(i, &fgraph_array_bitmask,
+				 sizeof(fgraph_array_bitmask) * BITS_PER_BYTE) {
+			func = fgraph_array[i]->entryfunc;
+			retfunc = fgraph_array[i]->retfunc;
+			fgraph_direct_gops = fgraph_array[i];
+		}
+	}
 	if (WARN_ON_ONCE(!func))
 		return;
 
@@ -1236,13 +1292,41 @@ static void ftrace_graph_disable_direct(bool disable_branch)
 	fgraph_direct_gops = &fgraph_stub;
 }
 
+/* The cpu_boot init_task->ret_stack will never be freed */
+static int fgraph_cpu_init(unsigned int cpu)
+{
+	if (!idle_task(cpu)->ret_stack)
+		ftrace_graph_init_idle_task(idle_task(cpu), cpu);
+	return 0;
+}
+
 int register_ftrace_graph(struct fgraph_ops *gops)
 {
+	static bool fgraph_initialized;
 	int command = 0;
 	int ret = 0;
 	int i = -1;
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
+
+	if (!fgraph_stack_cachep) {
+		fgraph_stack_cachep = kmem_cache_create("fgraph_stack",
+							SHADOW_STACK_SIZE,
+							SHADOW_STACK_SIZE, 0, NULL);
+		if (!fgraph_stack_cachep)
+			return -ENOMEM;
+	}
+
+	if (!fgraph_initialized) {
+		ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "fgraph:online",
+					fgraph_cpu_init, NULL);
+		if (ret < 0) {
+			pr_warn("fgraph: Error to init cpu hotplug support\n");
+			return ret;
+		}
+		fgraph_initialized = true;
+		ret = 0;
+	}
 
 	if (!fgraph_array[0]) {
 		/* The array must always have real data on it */
@@ -1252,12 +1336,8 @@ int register_ftrace_graph(struct fgraph_ops *gops)
 	}
 
 	i = fgraph_lru_alloc_index();
-	if (i < 0 || WARN_ON_ONCE(fgraph_array[i] != &fgraph_stub)) {
-		ret = -ENOSPC;
-		goto out;
-	}
-
-	fgraph_array[i] = gops;
+	if (i < 0 || WARN_ON_ONCE(fgraph_array[i] != &fgraph_stub))
+		return -ENOSPC;
 	gops->idx = i;
 
 	ftrace_graph_active++;
@@ -1266,7 +1346,7 @@ int register_ftrace_graph(struct fgraph_ops *gops)
 		ftrace_graph_disable_direct(true);
 
 	if (ftrace_graph_active == 1) {
-		ftrace_graph_enable_direct(false);
+		ftrace_graph_enable_direct(false, gops);
 		register_pm_notifier(&ftrace_suspend_notifier);
 		ret = start_graph_tracing();
 		if (ret)
@@ -1281,20 +1361,19 @@ int register_ftrace_graph(struct fgraph_ops *gops)
 	} else {
 		init_task_vars(gops->idx);
 	}
-
 	/* Always save the function, and reset at unregistering */
 	gops->saved_func = gops->entryfunc;
 
 	ret = ftrace_startup_subops(&graph_ops, &gops->ops, command);
+	if (!ret)
+		fgraph_array[i] = gops;
+
 error:
 	if (ret) {
-		fgraph_array[i] = &fgraph_stub;
 		ftrace_graph_active--;
 		gops->saved_func = NULL;
 		fgraph_lru_release_index(i);
 	}
-out:
-	mutex_unlock(&ftrace_lock);
 	return ret;
 }
 
@@ -1302,17 +1381,17 @@ void unregister_ftrace_graph(struct fgraph_ops *gops)
 {
 	int command = 0;
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
 
 	if (unlikely(!ftrace_graph_active))
-		goto out;
+		return;
 
 	if (unlikely(gops->idx < 0 || gops->idx >= FGRAPH_ARRAY_SIZE ||
 		     fgraph_array[gops->idx] != gops))
-		goto out;
+		return;
 
 	if (fgraph_lru_release_index(gops->idx) < 0)
-		goto out;
+		return;
 
 	fgraph_array[gops->idx] = &fgraph_stub;
 
@@ -1324,7 +1403,7 @@ void unregister_ftrace_graph(struct fgraph_ops *gops)
 	ftrace_shutdown_subops(&graph_ops, &gops->ops, command);
 
 	if (ftrace_graph_active == 1)
-		ftrace_graph_enable_direct(true);
+		ftrace_graph_enable_direct(true, NULL);
 	else if (!ftrace_graph_active)
 		ftrace_graph_disable_direct(false);
 
@@ -1334,7 +1413,5 @@ void unregister_ftrace_graph(struct fgraph_ops *gops)
 		unregister_pm_notifier(&ftrace_suspend_notifier);
 		unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 	}
- out:
 	gops->saved_func = NULL;
-	mutex_unlock(&ftrace_lock);
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4c28dd177ca6..9b17efb1a87d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -820,10 +820,16 @@ void ftrace_graph_graph_time_control(bool enable)
 	fgraph_graph_time = enable;
 }
 
+struct profile_fgraph_data {
+	unsigned long long		calltime;
+	unsigned long long		subtime;
+	unsigned long long		sleeptime;
+};
+
 static int profile_graph_entry(struct ftrace_graph_ent *trace,
 			       struct fgraph_ops *gops)
 {
-	struct ftrace_ret_stack *ret_stack;
+	struct profile_fgraph_data *profile_data;
 
 	function_profile_call(trace->func, 0, NULL, NULL);
 
@@ -831,9 +837,13 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace,
 	if (!current->ret_stack)
 		return 0;
 
-	ret_stack = ftrace_graph_get_ret_stack(current, 0);
-	if (ret_stack)
-		ret_stack->subtime = 0;
+	profile_data = fgraph_reserve_data(gops->idx, sizeof(*profile_data));
+	if (!profile_data)
+		return 0;
+
+	profile_data->subtime = 0;
+	profile_data->sleeptime = current->ftrace_sleeptime;
+	profile_data->calltime = trace_clock_local();
 
 	return 1;
 }
@@ -841,33 +851,42 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace,
 static void profile_graph_return(struct ftrace_graph_ret *trace,
 				 struct fgraph_ops *gops)
 {
-	struct ftrace_ret_stack *ret_stack;
+	struct profile_fgraph_data *profile_data;
 	struct ftrace_profile_stat *stat;
 	unsigned long long calltime;
+	unsigned long long rettime = trace_clock_local();
 	struct ftrace_profile *rec;
 	unsigned long flags;
+	int size;
 
 	local_irq_save(flags);
 	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
 		goto out;
 
+	profile_data = fgraph_retrieve_data(gops->idx, &size);
+
 	/* If the calltime was zero'd ignore it */
-	if (!trace->calltime)
+	if (!profile_data || !profile_data->calltime)
 		goto out;
 
-	calltime = trace->rettime - trace->calltime;
+	calltime = rettime - profile_data->calltime;
+
+	if (!fgraph_sleep_time) {
+		if (current->ftrace_sleeptime)
+			calltime -= current->ftrace_sleeptime - profile_data->sleeptime;
+	}
 
 	if (!fgraph_graph_time) {
+		struct profile_fgraph_data *parent_data;
 
 		/* Append this call time to the parent time to subtract */
-		ret_stack = ftrace_graph_get_ret_stack(current, 1);
-		if (ret_stack)
-			ret_stack->subtime += calltime;
+		parent_data = fgraph_retrieve_parent_data(gops->idx, &size, 1);
+		if (parent_data)
+			parent_data->subtime += calltime;
 
-		ret_stack = ftrace_graph_get_ret_stack(current, 0);
-		if (ret_stack && ret_stack->subtime < calltime)
-			calltime -= ret_stack->subtime;
+		if (profile_data->subtime && profile_data->subtime < calltime)
+			calltime -= profile_data->subtime;
 		else
 			calltime = 0;
 	}
@@ -883,6 +902,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace,
 }
 
 static struct fgraph_ops fprofiler_ops = {
+	.ops = {
+		.flags = FTRACE_OPS_FL_INITIALIZED,
+		INIT_OPS_HASH(fprofiler_ops.ops)
+	},
 	.entryfunc = &profile_graph_entry,
 	.retfunc = &profile_graph_return,
 };
@@ -3663,7 +3686,8 @@ static int ftrace_hash_move_and_update_subops(struct ftrace_ops *subops,
 }
 
 
-static u64		ftrace_update_time;
+u64			ftrace_update_time;
+u64			ftrace_total_mod_time;
 unsigned long		ftrace_update_tot_cnt;
 unsigned long		ftrace_number_of_pages;
 unsigned long		ftrace_number_of_groups;
@@ -3683,7 +3707,7 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 	bool init_nop = ftrace_need_init_nop();
 	struct ftrace_page *pg;
 	struct dyn_ftrace *p;
-	u64 start, stop;
+	u64 start, stop, update_time;
 	unsigned long update_cnt = 0;
 	unsigned long rec_flags = 0;
 	int i;
@@ -3727,7 +3751,11 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 	}
 
 	stop = ftrace_now(raw_smp_processor_id());
-	ftrace_update_time = stop - start;
+	update_time = stop - start;
+	if (mod)
+		ftrace_total_mod_time += update_time;
+	else
+		ftrace_update_time = update_time;
 	ftrace_update_tot_cnt += update_cnt;
 
 	return 0;
@@ -4806,15 +4834,13 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod)
 		mod_g.len = strlen(mod_g.search);
 	}
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
 
 	if (unlikely(ftrace_disabled))
-		goto out_unlock;
+		return 0;
 
-	if (func_g.type == MATCH_INDEX) {
-		found = add_rec_by_index(hash, &func_g, clear_filter);
-		goto out_unlock;
-	}
+	if (func_g.type == MATCH_INDEX)
+		return add_rec_by_index(hash, &func_g, clear_filter);
 
 	do_for_each_ftrace_rec(pg, rec) {
 
@@ -4823,16 +4849,12 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod)
 
 		if (ftrace_match_record(rec, &func_g, mod_match, exclude_mod)) {
 			ret = enter_record(hash, rec, clear_filter);
-			if (ret < 0) {
-				found = ret;
-				goto out_unlock;
-			}
+			if (ret < 0)
+				return ret;
 			found = 1;
 		}
 		cond_resched();
 	} while_for_each_ftrace_rec();
- out_unlock:
-	mutex_unlock(&ftrace_lock);
 
 	return found;
 }
@@ -4930,14 +4952,14 @@ static int cache_mod(struct trace_array *tr,
 {
 	struct ftrace_mod_load *ftrace_mod, *n;
 	struct list_head *head = enable ? &tr->mod_trace : &tr->mod_notrace;
-	int ret;
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
 
 	/* We do not cache inverse filters */
 	if (func[0] == '!') {
+		int ret = -EINVAL;
+
 		func++;
-		ret = -EINVAL;
 
 		/* Look to remove this hash */
 		list_for_each_entry_safe(ftrace_mod, n, head, list) {
@@ -4953,20 +4975,15 @@ static int cache_mod(struct trace_array *tr,
 				continue;
 			}
 		}
-		goto out;
+		return ret;
 	}
 
-	ret = -EINVAL;
 	/* We only care about modules that have not been loaded yet */
 	if (module_exists(module))
-		goto out;
+		return -EINVAL;
 
 	/* Save this string off, and execute it when the module is loaded */
-	ret = ftrace_add_mod(tr, func, module, enable);
- out:
-	mutex_unlock(&ftrace_lock);
-
-	return ret;
+	return ftrace_add_mod(tr, func, module, enable);
 }
 
 static int
@@ -5076,6 +5093,9 @@ ftrace_mod_callback(struct trace_array *tr, struct ftrace_hash *hash,
 	char *func;
 	int ret;
 
+	if (!tr)
+		return -ENODEV;
+
 	/* match_records() modifies func, and we need the original */
 	func = kstrdup(func_orig, GFP_KERNEL);
 	if (!func)
@@ -5276,7 +5296,7 @@ static void release_probe(struct ftrace_func_probe *probe)
 {
 	struct ftrace_probe_ops *probe_ops;
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
 
 	WARN_ON(probe->ref <= 0);
 
@@ -5294,7 +5314,6 @@ static void release_probe(struct ftrace_func_probe *probe)
 		list_del(&probe->list);
 		kfree(probe);
 	}
-	mutex_unlock(&ftrace_lock);
 }
 
 static void acquire_probe_locked(struct ftrace_func_probe *probe)
@@ -6805,12 +6824,10 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer)
 
 	func_g.len = strlen(func_g.search);
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
 
-	if (unlikely(ftrace_disabled)) {
-		mutex_unlock(&ftrace_lock);
+	if (unlikely(ftrace_disabled))
 		return -ENODEV;
-	}
 
 	do_for_each_ftrace_rec(pg, rec) {
 
@@ -6826,7 +6843,7 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer)
 				if (entry)
 					continue;
 				if (add_hash_entry(hash, rec->ip) == NULL)
-					goto out;
+					return 0;
 			} else {
 				if (entry) {
 					free_hash_entry(hash, entry);
@@ -6835,13 +6852,8 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer)
 			}
 		}
 	} while_for_each_ftrace_rec();
-out:
-	mutex_unlock(&ftrace_lock);
 
-	if (fail)
-		return -EINVAL;
-
-	return 0;
+	return fail ? -EINVAL : 0;
 }
 
 static ssize_t
@@ -7920,7 +7932,7 @@ out:
 void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 			       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	kmsan_unpoison_memory(fregs, sizeof(*fregs));
+	kmsan_unpoison_memory(fregs, ftrace_regs_size());
 	__ftrace_ops_list_func(ip, parent_ip, NULL, fregs);
 }
 #else
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cebd879a30cb..7e257e855dd1 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -32,6 +32,8 @@
 #include <asm/local64.h>
 #include <asm/local.h>
 
+#include "trace.h"
+
 /*
  * The "absolute" timestamp in the buffer is only 59 bits.
  * If a clock has the 5 MSBs set, it needs to be saved and
@@ -42,6 +44,21 @@
 
 static void update_pages_handler(struct work_struct *work);
 
+#define RING_BUFFER_META_MAGIC	0xBADFEED
+
+struct ring_buffer_meta {
+	int		magic;
+	int		struct_size;
+	unsigned long	text_addr;
+	unsigned long	data_addr;
+	unsigned long	first_buffer;
+	unsigned long	head_buffer;
+	unsigned long	commit_buffer;
+	__u32		subbuf_size;
+	__u32		nr_subbufs;
+	int		buffers[];
+};
+
 /*
  * The ring buffer header is special. We must manually up keep it.
  */
@@ -342,7 +359,8 @@ struct buffer_page {
 	local_t		 entries;	/* entries on this page */
 	unsigned long	 real_end;	/* real end of data */
 	unsigned	 order;		/* order of the page */
-	u32		 id;		/* ID for external mapping */
+	u32		 id:30;		/* ID for external mapping */
+	u32		 range:1;	/* Mapped via a range */
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
@@ -373,7 +391,9 @@ static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage)
 
 static void free_buffer_page(struct buffer_page *bpage)
 {
-	free_pages((unsigned long)bpage->page, bpage->order);
+	/* Range pages are not to be freed */
+	if (!bpage->range)
+		free_pages((unsigned long)bpage->page, bpage->order);
 	kfree(bpage);
 }
 
@@ -462,6 +482,8 @@ struct ring_buffer_per_cpu {
 	unsigned long			nr_pages;
 	unsigned int			current_context;
 	struct list_head		*pages;
+	/* pages generation counter, incremented when the list changes */
+	unsigned long			cnt;
 	struct buffer_page		*head_page;	/* read from head */
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
@@ -491,9 +513,11 @@ struct ring_buffer_per_cpu {
 	unsigned long			pages_removed;
 
 	unsigned int			mapped;
+	unsigned int			user_mapped;	/* user space mapping */
 	struct mutex			mapping_lock;
 	unsigned long			*subbuf_ids;	/* ID to subbuf VA */
 	struct trace_buffer_meta	*meta_page;
+	struct ring_buffer_meta		*ring_meta;
 
 	/* ring buffer pages to update, > 0 to add, < 0 to remove */
 	long				nr_pages_to_update;
@@ -523,6 +547,12 @@ struct trace_buffer {
 	struct rb_irq_work		irq_work;
 	bool				time_stamp_abs;
 
+	unsigned long			range_addr_start;
+	unsigned long			range_addr_end;
+
+	long				last_text_delta;
+	long				last_data_delta;
+
 	unsigned int			subbuf_size;
 	unsigned int			subbuf_order;
 	unsigned int			max_data_size;
@@ -1239,6 +1269,11 @@ static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer)
 	 * Set the previous list pointer to have the HEAD flag.
 	 */
 	rb_set_list_to_head(head->list.prev);
+
+	if (cpu_buffer->ring_meta) {
+		struct ring_buffer_meta *meta = cpu_buffer->ring_meta;
+		meta->head_buffer = (unsigned long)head->page;
+	}
 }
 
 static void rb_list_head_clear(struct list_head *list)
@@ -1442,45 +1477,567 @@ static void rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
 	RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK);
 }
 
+static bool rb_check_links(struct ring_buffer_per_cpu *cpu_buffer,
+			   struct list_head *list)
+{
+	if (RB_WARN_ON(cpu_buffer,
+		       rb_list_head(rb_list_head(list->next)->prev) != list))
+		return false;
+
+	if (RB_WARN_ON(cpu_buffer,
+		       rb_list_head(rb_list_head(list->prev)->next) != list))
+		return false;
+
+	return true;
+}
+
 /**
  * rb_check_pages - integrity check of buffer pages
  * @cpu_buffer: CPU buffer with pages to test
  *
  * As a safety measure we check to make sure the data pages have not
  * been corrupted.
- *
- * Callers of this function need to guarantee that the list of pages doesn't get
- * modified during the check. In particular, if it's possible that the function
- * is invoked with concurrent readers which can swap in a new reader page then
- * the caller should take cpu_buffer->reader_lock.
  */
 static void rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	struct list_head *head = rb_list_head(cpu_buffer->pages);
-	struct list_head *tmp;
+	struct list_head *head, *tmp;
+	unsigned long buffer_cnt;
+	unsigned long flags;
+	int nr_loops = 0;
 
-	if (RB_WARN_ON(cpu_buffer,
-			rb_list_head(rb_list_head(head->next)->prev) != head))
+	/*
+	 * Walk the linked list underpinning the ring buffer and validate all
+	 * its next and prev links.
+	 *
+	 * The check acquires the reader_lock to avoid concurrent processing
+	 * with code that could be modifying the list. However, the lock cannot
+	 * be held for the entire duration of the walk, as this would make the
+	 * time when interrupts are disabled non-deterministic, dependent on the
+	 * ring buffer size. Therefore, the code releases and re-acquires the
+	 * lock after checking each page. The ring_buffer_per_cpu.cnt variable
+	 * is then used to detect if the list was modified while the lock was
+	 * not held, in which case the check needs to be restarted.
+	 *
+	 * The code attempts to perform the check at most three times before
+	 * giving up. This is acceptable because this is only a self-validation
+	 * to detect problems early on. In practice, the list modification
+	 * operations are fairly spaced, and so this check typically succeeds at
+	 * most on the second try.
+	 */
+again:
+	if (++nr_loops > 3)
 		return;
 
-	if (RB_WARN_ON(cpu_buffer,
-			rb_list_head(rb_list_head(head->prev)->next) != head))
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	head = rb_list_head(cpu_buffer->pages);
+	if (!rb_check_links(cpu_buffer, head))
+		goto out_locked;
+	buffer_cnt = cpu_buffer->cnt;
+	tmp = head;
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+	while (true) {
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+		if (buffer_cnt != cpu_buffer->cnt) {
+			/* The list was updated, try again. */
+			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+			goto again;
+		}
+
+		tmp = rb_list_head(tmp->next);
+		if (tmp == head)
+			/* The iteration circled back, all is done. */
+			goto out_locked;
+
+		if (!rb_check_links(cpu_buffer, tmp))
+			goto out_locked;
+
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	}
+
+out_locked:
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+}
+
+/*
+ * Take an address, add the meta data size as well as the array of
+ * array subbuffer indexes, then align it to a subbuffer size.
+ *
+ * This is used to help find the next per cpu subbuffer within a mapped range.
+ */
+static unsigned long
+rb_range_align_subbuf(unsigned long addr, int subbuf_size, int nr_subbufs)
+{
+	addr += sizeof(struct ring_buffer_meta) +
+		sizeof(int) * nr_subbufs;
+	return ALIGN(addr, subbuf_size);
+}
+
+/*
+ * Return the ring_buffer_meta for a given @cpu.
+ */
+static void *rb_range_meta(struct trace_buffer *buffer, int nr_pages, int cpu)
+{
+	int subbuf_size = buffer->subbuf_size + BUF_PAGE_HDR_SIZE;
+	unsigned long ptr = buffer->range_addr_start;
+	struct ring_buffer_meta *meta;
+	int nr_subbufs;
+
+	if (!ptr)
+		return NULL;
+
+	/* When nr_pages passed in is zero, the first meta has already been initialized */
+	if (!nr_pages) {
+		meta = (struct ring_buffer_meta *)ptr;
+		nr_subbufs = meta->nr_subbufs;
+	} else {
+		meta = NULL;
+		/* Include the reader page */
+		nr_subbufs = nr_pages + 1;
+	}
+
+	/*
+	 * The first chunk may not be subbuffer aligned, where as
+	 * the rest of the chunks are.
+	 */
+	if (cpu) {
+		ptr = rb_range_align_subbuf(ptr, subbuf_size, nr_subbufs);
+		ptr += subbuf_size * nr_subbufs;
+
+		/* We can use multiplication to find chunks greater than 1 */
+		if (cpu > 1) {
+			unsigned long size;
+			unsigned long p;
+
+			/* Save the beginning of this CPU chunk */
+			p = ptr;
+			ptr = rb_range_align_subbuf(ptr, subbuf_size, nr_subbufs);
+			ptr += subbuf_size * nr_subbufs;
+
+			/* Now all chunks after this are the same size */
+			size = ptr - p;
+			ptr += size * (cpu - 2);
+		}
+	}
+	return (void *)ptr;
+}
+
+/* Return the start of subbufs given the meta pointer */
+static void *rb_subbufs_from_meta(struct ring_buffer_meta *meta)
+{
+	int subbuf_size = meta->subbuf_size;
+	unsigned long ptr;
+
+	ptr = (unsigned long)meta;
+	ptr = rb_range_align_subbuf(ptr, subbuf_size, meta->nr_subbufs);
+
+	return (void *)ptr;
+}
+
+/*
+ * Return a specific sub-buffer for a given @cpu defined by @idx.
+ */
+static void *rb_range_buffer(struct ring_buffer_per_cpu *cpu_buffer, int idx)
+{
+	struct ring_buffer_meta *meta;
+	unsigned long ptr;
+	int subbuf_size;
+
+	meta = rb_range_meta(cpu_buffer->buffer, 0, cpu_buffer->cpu);
+	if (!meta)
+		return NULL;
+
+	if (WARN_ON_ONCE(idx >= meta->nr_subbufs))
+		return NULL;
+
+	subbuf_size = meta->subbuf_size;
+
+	/* Map this buffer to the order that's in meta->buffers[] */
+	idx = meta->buffers[idx];
+
+	ptr = (unsigned long)rb_subbufs_from_meta(meta);
+
+	ptr += subbuf_size * idx;
+	if (ptr + subbuf_size > cpu_buffer->buffer->range_addr_end)
+		return NULL;
+
+	return (void *)ptr;
+}
+
+/*
+ * See if the existing memory contains valid ring buffer data.
+ * As the previous kernel must be the same as this kernel, all
+ * the calculations (size of buffers and number of buffers)
+ * must be the same.
+ */
+static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu,
+			  struct trace_buffer *buffer, int nr_pages)
+{
+	int subbuf_size = PAGE_SIZE;
+	struct buffer_data_page *subbuf;
+	unsigned long buffers_start;
+	unsigned long buffers_end;
+	int i;
+
+	/* Check the meta magic and meta struct size */
+	if (meta->magic != RING_BUFFER_META_MAGIC ||
+	    meta->struct_size != sizeof(*meta)) {
+		pr_info("Ring buffer boot meta[%d] mismatch of magic or struct size\n", cpu);
+		return false;
+	}
+
+	/* The subbuffer's size and number of subbuffers must match */
+	if (meta->subbuf_size != subbuf_size ||
+	    meta->nr_subbufs != nr_pages + 1) {
+		pr_info("Ring buffer boot meta [%d] mismatch of subbuf_size/nr_pages\n", cpu);
+		return false;
+	}
+
+	buffers_start = meta->first_buffer;
+	buffers_end = meta->first_buffer + (subbuf_size * meta->nr_subbufs);
+
+	/* Is the head and commit buffers within the range of buffers? */
+	if (meta->head_buffer < buffers_start ||
+	    meta->head_buffer >= buffers_end) {
+		pr_info("Ring buffer boot meta [%d] head buffer out of range\n", cpu);
+		return false;
+	}
+
+	if (meta->commit_buffer < buffers_start ||
+	    meta->commit_buffer >= buffers_end) {
+		pr_info("Ring buffer boot meta [%d] commit buffer out of range\n", cpu);
+		return false;
+	}
+
+	subbuf = rb_subbufs_from_meta(meta);
+
+	/* Is the meta buffers and the subbufs themselves have correct data? */
+	for (i = 0; i < meta->nr_subbufs; i++) {
+		if (meta->buffers[i] < 0 ||
+		    meta->buffers[i] >= meta->nr_subbufs) {
+			pr_info("Ring buffer boot meta [%d] array out of range\n", cpu);
+			return false;
+		}
+
+		if ((unsigned)local_read(&subbuf->commit) > subbuf_size) {
+			pr_info("Ring buffer boot meta [%d] buffer invalid commit\n", cpu);
+			return false;
+		}
+
+		subbuf = (void *)subbuf + subbuf_size;
+	}
+
+	return true;
+}
+
+static int rb_meta_subbuf_idx(struct ring_buffer_meta *meta, void *subbuf);
+
+static int rb_read_data_buffer(struct buffer_data_page *dpage, int tail, int cpu,
+			       unsigned long long *timestamp, u64 *delta_ptr)
+{
+	struct ring_buffer_event *event;
+	u64 ts, delta;
+	int events = 0;
+	int e;
+
+	*delta_ptr = 0;
+	*timestamp = 0;
+
+	ts = dpage->time_stamp;
+
+	for (e = 0; e < tail; e += rb_event_length(event)) {
+
+		event = (struct ring_buffer_event *)(dpage->data + e);
+
+		switch (event->type_len) {
+
+		case RINGBUF_TYPE_TIME_EXTEND:
+			delta = rb_event_time_stamp(event);
+			ts += delta;
+			break;
+
+		case RINGBUF_TYPE_TIME_STAMP:
+			delta = rb_event_time_stamp(event);
+			delta = rb_fix_abs_ts(delta, ts);
+			if (delta < ts) {
+				*delta_ptr = delta;
+				*timestamp = ts;
+				return -1;
+			}
+			ts = delta;
+			break;
+
+		case RINGBUF_TYPE_PADDING:
+			if (event->time_delta == 1)
+				break;
+			fallthrough;
+		case RINGBUF_TYPE_DATA:
+			events++;
+			ts += event->time_delta;
+			break;
+
+		default:
+			return -1;
+		}
+	}
+	*timestamp = ts;
+	return events;
+}
+
+static int rb_validate_buffer(struct buffer_data_page *dpage, int cpu)
+{
+	unsigned long long ts;
+	u64 delta;
+	int tail;
+
+	tail = local_read(&dpage->commit);
+	return rb_read_data_buffer(dpage, tail, cpu, &ts, &delta);
+}
+
+/* If the meta data has been validated, now validate the events */
+static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct ring_buffer_meta *meta = cpu_buffer->ring_meta;
+	struct buffer_page *head_page;
+	unsigned long entry_bytes = 0;
+	unsigned long entries = 0;
+	int ret;
+	int i;
+
+	if (!meta || !meta->head_buffer)
 		return;
 
-	for (tmp = rb_list_head(head->next); tmp != head; tmp = rb_list_head(tmp->next)) {
-		if (RB_WARN_ON(cpu_buffer,
-				rb_list_head(rb_list_head(tmp->next)->prev) != tmp))
-			return;
+	/* Do the reader page first */
+	ret = rb_validate_buffer(cpu_buffer->reader_page->page, cpu_buffer->cpu);
+	if (ret < 0) {
+		pr_info("Ring buffer reader page is invalid\n");
+		goto invalid;
+	}
+	entries += ret;
+	entry_bytes += local_read(&cpu_buffer->reader_page->page->commit);
+	local_set(&cpu_buffer->reader_page->entries, ret);
 
-		if (RB_WARN_ON(cpu_buffer,
-				rb_list_head(rb_list_head(tmp->prev)->next) != tmp))
-			return;
+	head_page = cpu_buffer->head_page;
+
+	/* If both the head and commit are on the reader_page then we are done. */
+	if (head_page == cpu_buffer->reader_page &&
+	    head_page == cpu_buffer->commit_page)
+		goto done;
+
+	/* Iterate until finding the commit page */
+	for (i = 0; i < meta->nr_subbufs + 1; i++, rb_inc_page(&head_page)) {
+
+		/* Reader page has already been done */
+		if (head_page == cpu_buffer->reader_page)
+			continue;
+
+		ret = rb_validate_buffer(head_page->page, cpu_buffer->cpu);
+		if (ret < 0) {
+			pr_info("Ring buffer meta [%d] invalid buffer page\n",
+				cpu_buffer->cpu);
+			goto invalid;
+		}
+		entries += ret;
+		entry_bytes += local_read(&head_page->page->commit);
+		local_set(&cpu_buffer->head_page->entries, ret);
+
+		if (head_page == cpu_buffer->commit_page)
+			break;
+	}
+
+	if (head_page != cpu_buffer->commit_page) {
+		pr_info("Ring buffer meta [%d] commit page not found\n",
+			cpu_buffer->cpu);
+		goto invalid;
+	}
+ done:
+	local_set(&cpu_buffer->entries, entries);
+	local_set(&cpu_buffer->entries_bytes, entry_bytes);
+
+	pr_info("Ring buffer meta [%d] is from previous boot!\n", cpu_buffer->cpu);
+	return;
+
+ invalid:
+	/* The content of the buffers are invalid, reset the meta data */
+	meta->head_buffer = 0;
+	meta->commit_buffer = 0;
+
+	/* Reset the reader page */
+	local_set(&cpu_buffer->reader_page->entries, 0);
+	local_set(&cpu_buffer->reader_page->page->commit, 0);
+
+	/* Reset all the subbuffers */
+	for (i = 0; i < meta->nr_subbufs - 1; i++, rb_inc_page(&head_page)) {
+		local_set(&head_page->entries, 0);
+		local_set(&head_page->page->commit, 0);
+	}
+}
+
+/* Used to calculate data delta */
+static char rb_data_ptr[] = "";
+
+#define THIS_TEXT_PTR		((unsigned long)rb_meta_init_text_addr)
+#define THIS_DATA_PTR		((unsigned long)rb_data_ptr)
+
+static void rb_meta_init_text_addr(struct ring_buffer_meta *meta)
+{
+	meta->text_addr = THIS_TEXT_PTR;
+	meta->data_addr = THIS_DATA_PTR;
+}
+
+static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages)
+{
+	struct ring_buffer_meta *meta;
+	unsigned long delta;
+	void *subbuf;
+	int cpu;
+	int i;
+
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
+		void *next_meta;
+
+		meta = rb_range_meta(buffer, nr_pages, cpu);
+
+		if (rb_meta_valid(meta, cpu, buffer, nr_pages)) {
+			/* Make the mappings match the current address */
+			subbuf = rb_subbufs_from_meta(meta);
+			delta = (unsigned long)subbuf - meta->first_buffer;
+			meta->first_buffer += delta;
+			meta->head_buffer += delta;
+			meta->commit_buffer += delta;
+			buffer->last_text_delta = THIS_TEXT_PTR - meta->text_addr;
+			buffer->last_data_delta = THIS_DATA_PTR - meta->data_addr;
+			continue;
+		}
+
+		if (cpu < nr_cpu_ids - 1)
+			next_meta = rb_range_meta(buffer, nr_pages, cpu + 1);
+		else
+			next_meta = (void *)buffer->range_addr_end;
+
+		memset(meta, 0, next_meta - (void *)meta);
+
+		meta->magic = RING_BUFFER_META_MAGIC;
+		meta->struct_size = sizeof(*meta);
+
+		meta->nr_subbufs = nr_pages + 1;
+		meta->subbuf_size = PAGE_SIZE;
+
+		subbuf = rb_subbufs_from_meta(meta);
+
+		meta->first_buffer = (unsigned long)subbuf;
+		rb_meta_init_text_addr(meta);
+
+		/*
+		 * The buffers[] array holds the order of the sub-buffers
+		 * that are after the meta data. The sub-buffers may
+		 * be swapped out when read and inserted into a different
+		 * location of the ring buffer. Although their addresses
+		 * remain the same, the buffers[] array contains the
+		 * index into the sub-buffers holding their actual order.
+		 */
+		for (i = 0; i < meta->nr_subbufs; i++) {
+			meta->buffers[i] = i;
+			rb_init_page(subbuf);
+			subbuf += meta->subbuf_size;
+		}
+	}
+}
+
+static void *rbm_start(struct seq_file *m, loff_t *pos)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = m->private;
+	struct ring_buffer_meta *meta = cpu_buffer->ring_meta;
+	unsigned long val;
+
+	if (!meta)
+		return NULL;
+
+	if (*pos > meta->nr_subbufs)
+		return NULL;
+
+	val = *pos;
+	val++;
+
+	return (void *)val;
+}
+
+static void *rbm_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+
+	return rbm_start(m, pos);
+}
+
+static int rbm_show(struct seq_file *m, void *v)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = m->private;
+	struct ring_buffer_meta *meta = cpu_buffer->ring_meta;
+	unsigned long val = (unsigned long)v;
+
+	if (val == 1) {
+		seq_printf(m, "head_buffer:   %d\n",
+			   rb_meta_subbuf_idx(meta, (void *)meta->head_buffer));
+		seq_printf(m, "commit_buffer: %d\n",
+			   rb_meta_subbuf_idx(meta, (void *)meta->commit_buffer));
+		seq_printf(m, "subbuf_size:   %d\n", meta->subbuf_size);
+		seq_printf(m, "nr_subbufs:    %d\n", meta->nr_subbufs);
+		return 0;
+	}
+
+	val -= 2;
+	seq_printf(m, "buffer[%ld]:    %d\n", val, meta->buffers[val]);
+
+	return 0;
+}
+
+static void rbm_stop(struct seq_file *m, void *p)
+{
+}
+
+static const struct seq_operations rb_meta_seq_ops = {
+	.start		= rbm_start,
+	.next		= rbm_next,
+	.show		= rbm_show,
+	.stop		= rbm_stop,
+};
+
+int ring_buffer_meta_seq_init(struct file *file, struct trace_buffer *buffer, int cpu)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &rb_meta_seq_ops);
+	if (ret)
+		return ret;
+
+	m = file->private_data;
+	m->private = buffer->buffers[cpu];
+
+	return 0;
+}
+
+/* Map the buffer_pages to the previous head and commit pages */
+static void rb_meta_buffer_update(struct ring_buffer_per_cpu *cpu_buffer,
+				  struct buffer_page *bpage)
+{
+	struct ring_buffer_meta *meta = cpu_buffer->ring_meta;
+
+	if (meta->head_buffer == (unsigned long)bpage->page)
+		cpu_buffer->head_page = bpage;
+
+	if (meta->commit_buffer == (unsigned long)bpage->page) {
+		cpu_buffer->commit_page = bpage;
+		cpu_buffer->tail_page = bpage;
 	}
 }
 
 static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 		long nr_pages, struct list_head *pages)
 {
+	struct trace_buffer *buffer = cpu_buffer->buffer;
+	struct ring_buffer_meta *meta = NULL;
 	struct buffer_page *bpage, *tmp;
 	bool user_thread = current->mm != NULL;
 	gfp_t mflags;
@@ -1515,6 +2072,10 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	 */
 	if (user_thread)
 		set_current_oom_origin();
+
+	if (buffer->range_addr_start)
+		meta = rb_range_meta(buffer, nr_pages, cpu_buffer->cpu);
+
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page;
 
@@ -1525,16 +2086,32 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
 		rb_check_bpage(cpu_buffer, bpage);
 
-		list_add(&bpage->list, pages);
-
-		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu),
-					mflags | __GFP_COMP | __GFP_ZERO,
-					cpu_buffer->buffer->subbuf_order);
-		if (!page)
-			goto free_pages;
-		bpage->page = page_address(page);
+		/*
+		 * Append the pages as for mapped buffers we want to keep
+		 * the order
+		 */
+		list_add_tail(&bpage->list, pages);
+
+		if (meta) {
+			/* A range was given. Use that for the buffer page */
+			bpage->page = rb_range_buffer(cpu_buffer, i + 1);
+			if (!bpage->page)
+				goto free_pages;
+			/* If this is valid from a previous boot */
+			if (meta->head_buffer)
+				rb_meta_buffer_update(cpu_buffer, bpage);
+			bpage->range = 1;
+			bpage->id = i + 1;
+		} else {
+			page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu),
+						mflags | __GFP_COMP | __GFP_ZERO,
+						cpu_buffer->buffer->subbuf_order);
+			if (!page)
+				goto free_pages;
+			bpage->page = page_address(page);
+			rb_init_page(bpage->page);
+		}
 		bpage->order = cpu_buffer->buffer->subbuf_order;
-		rb_init_page(bpage->page);
 
 		if (user_thread && fatal_signal_pending(current))
 			goto free_pages;
@@ -1584,6 +2161,7 @@ static struct ring_buffer_per_cpu *
 rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_meta *meta;
 	struct buffer_page *bpage;
 	struct page *page;
 	int ret;
@@ -1614,12 +2192,28 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 
 	cpu_buffer->reader_page = bpage;
 
-	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_COMP | __GFP_ZERO,
-				cpu_buffer->buffer->subbuf_order);
-	if (!page)
-		goto fail_free_reader;
-	bpage->page = page_address(page);
-	rb_init_page(bpage->page);
+	if (buffer->range_addr_start) {
+		/*
+		 * Range mapped buffers have the same restrictions as memory
+		 * mapped ones do.
+		 */
+		cpu_buffer->mapped = 1;
+		cpu_buffer->ring_meta = rb_range_meta(buffer, nr_pages, cpu);
+		bpage->page = rb_range_buffer(cpu_buffer, 0);
+		if (!bpage->page)
+			goto fail_free_reader;
+		if (cpu_buffer->ring_meta->head_buffer)
+			rb_meta_buffer_update(cpu_buffer, bpage);
+		bpage->range = 1;
+	} else {
+		page = alloc_pages_node(cpu_to_node(cpu),
+					GFP_KERNEL | __GFP_COMP | __GFP_ZERO,
+					cpu_buffer->buffer->subbuf_order);
+		if (!page)
+			goto fail_free_reader;
+		bpage->page = page_address(page);
+		rb_init_page(bpage->page);
+	}
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
 	INIT_LIST_HEAD(&cpu_buffer->new_pages);
@@ -1628,11 +2222,35 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 	if (ret < 0)
 		goto fail_free_reader;
 
-	cpu_buffer->head_page
-		= list_entry(cpu_buffer->pages, struct buffer_page, list);
-	cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
+	rb_meta_validate_events(cpu_buffer);
+
+	/* If the boot meta was valid then this has already been updated */
+	meta = cpu_buffer->ring_meta;
+	if (!meta || !meta->head_buffer ||
+	    !cpu_buffer->head_page || !cpu_buffer->commit_page || !cpu_buffer->tail_page) {
+		if (meta && meta->head_buffer &&
+		    (cpu_buffer->head_page || cpu_buffer->commit_page || cpu_buffer->tail_page)) {
+			pr_warn("Ring buffer meta buffers not all mapped\n");
+			if (!cpu_buffer->head_page)
+				pr_warn("   Missing head_page\n");
+			if (!cpu_buffer->commit_page)
+				pr_warn("   Missing commit_page\n");
+			if (!cpu_buffer->tail_page)
+				pr_warn("   Missing tail_page\n");
+		}
 
-	rb_head_page_activate(cpu_buffer);
+		cpu_buffer->head_page
+			= list_entry(cpu_buffer->pages, struct buffer_page, list);
+		cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
+
+		rb_head_page_activate(cpu_buffer);
+
+		if (cpu_buffer->ring_meta)
+			meta->commit_buffer = meta->head_buffer;
+	} else {
+		/* The valid meta buffer still needs to activate the head page */
+		rb_head_page_activate(cpu_buffer);
+	}
 
 	return cpu_buffer;
 
@@ -1669,22 +2287,14 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 	kfree(cpu_buffer);
 }
 
-/**
- * __ring_buffer_alloc - allocate a new ring_buffer
- * @size: the size in bytes per cpu that is needed.
- * @flags: attributes to set for the ring buffer.
- * @key: ring buffer reader_lock_key.
- *
- * Currently the only flag that is available is the RB_FL_OVERWRITE
- * flag. This flag means that the buffer will overwrite old data
- * when the buffer wraps. If this flag is not set, the buffer will
- * drop data when the tail hits the head.
- */
-struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
-					struct lock_class_key *key)
+static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
+					 int order, unsigned long start,
+					 unsigned long end,
+					 struct lock_class_key *key)
 {
 	struct trace_buffer *buffer;
 	long nr_pages;
+	int subbuf_size;
 	int bsize;
 	int cpu;
 	int ret;
@@ -1698,14 +2308,13 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
 		goto fail_free_buffer;
 
-	/* Default buffer page size - one system page */
-	buffer->subbuf_order = 0;
-	buffer->subbuf_size = PAGE_SIZE - BUF_PAGE_HDR_SIZE;
+	buffer->subbuf_order = order;
+	subbuf_size = (PAGE_SIZE << order);
+	buffer->subbuf_size = subbuf_size - BUF_PAGE_HDR_SIZE;
 
 	/* Max payload is buffer page size - header (8bytes) */
 	buffer->max_data_size = buffer->subbuf_size - (sizeof(u32) * 2);
 
-	nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
 	buffer->flags = flags;
 	buffer->clock = trace_clock_local;
 	buffer->reader_lock_key = key;
@@ -1713,10 +2322,6 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	init_irq_work(&buffer->irq_work.work, rb_wake_up_waiters);
 	init_waitqueue_head(&buffer->irq_work.waiters);
 
-	/* need at least two pages */
-	if (nr_pages < 2)
-		nr_pages = 2;
-
 	buffer->cpus = nr_cpu_ids;
 
 	bsize = sizeof(void *) * nr_cpu_ids;
@@ -1725,6 +2330,56 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!buffer->buffers)
 		goto fail_free_cpumask;
 
+	/* If start/end are specified, then that overrides size */
+	if (start && end) {
+		unsigned long ptr;
+		int n;
+
+		size = end - start;
+		size = size / nr_cpu_ids;
+
+		/*
+		 * The number of sub-buffers (nr_pages) is determined by the
+		 * total size allocated minus the meta data size.
+		 * Then that is divided by the number of per CPU buffers
+		 * needed, plus account for the integer array index that
+		 * will be appended to the meta data.
+		 */
+		nr_pages = (size - sizeof(struct ring_buffer_meta)) /
+			(subbuf_size + sizeof(int));
+		/* Need at least two pages plus the reader page */
+		if (nr_pages < 3)
+			goto fail_free_buffers;
+
+ again:
+		/* Make sure that the size fits aligned */
+		for (n = 0, ptr = start; n < nr_cpu_ids; n++) {
+			ptr += sizeof(struct ring_buffer_meta) +
+				sizeof(int) * nr_pages;
+			ptr = ALIGN(ptr, subbuf_size);
+			ptr += subbuf_size * nr_pages;
+		}
+		if (ptr > end) {
+			if (nr_pages <= 3)
+				goto fail_free_buffers;
+			nr_pages--;
+			goto again;
+		}
+
+		/* nr_pages should not count the reader page */
+		nr_pages--;
+		buffer->range_addr_start = start;
+		buffer->range_addr_end = end;
+
+		rb_range_meta_init(buffer, nr_pages);
+	} else {
+
+		/* need at least two pages */
+		nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
+		if (nr_pages < 2)
+			nr_pages = 2;
+	}
+
 	cpu = raw_smp_processor_id();
 	cpumask_set_cpu(cpu, buffer->cpumask);
 	buffer->buffers[cpu] = rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
@@ -1753,9 +2408,73 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	kfree(buffer);
 	return NULL;
 }
+
+/**
+ * __ring_buffer_alloc - allocate a new ring_buffer
+ * @size: the size in bytes per cpu that is needed.
+ * @flags: attributes to set for the ring buffer.
+ * @key: ring buffer reader_lock_key.
+ *
+ * Currently the only flag that is available is the RB_FL_OVERWRITE
+ * flag. This flag means that the buffer will overwrite old data
+ * when the buffer wraps. If this flag is not set, the buffer will
+ * drop data when the tail hits the head.
+ */
+struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
+					struct lock_class_key *key)
+{
+	/* Default buffer page size - one system page */
+	return alloc_buffer(size, flags, 0, 0, 0,key);
+
+}
 EXPORT_SYMBOL_GPL(__ring_buffer_alloc);
 
 /**
+ * __ring_buffer_alloc_range - allocate a new ring_buffer from existing memory
+ * @size: the size in bytes per cpu that is needed.
+ * @flags: attributes to set for the ring buffer.
+ * @order: sub-buffer order
+ * @start: start of allocated range
+ * @range_size: size of allocated range
+ * @key: ring buffer reader_lock_key.
+ *
+ * Currently the only flag that is available is the RB_FL_OVERWRITE
+ * flag. This flag means that the buffer will overwrite old data
+ * when the buffer wraps. If this flag is not set, the buffer will
+ * drop data when the tail hits the head.
+ */
+struct trace_buffer *__ring_buffer_alloc_range(unsigned long size, unsigned flags,
+					       int order, unsigned long start,
+					       unsigned long range_size,
+					       struct lock_class_key *key)
+{
+	return alloc_buffer(size, flags, order, start, start + range_size, key);
+}
+
+/**
+ * ring_buffer_last_boot_delta - return the delta offset from last boot
+ * @buffer: The buffer to return the delta from
+ * @text: Return text delta
+ * @data: Return data delta
+ *
+ * Returns: The true if the delta is non zero
+ */
+bool ring_buffer_last_boot_delta(struct trace_buffer *buffer, long *text,
+				 long *data)
+{
+	if (!buffer)
+		return false;
+
+	if (!buffer->last_text_delta)
+		return false;
+
+	*text = buffer->last_text_delta;
+	*data = buffer->last_data_delta;
+
+	return true;
+}
+
+/**
  * ring_buffer_free - free a ring buffer.
  * @buffer: the buffer to free.
  */
@@ -1862,6 +2581,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 
 	/* make sure pages points to a valid page in the ring buffer */
 	cpu_buffer->pages = next_page;
+	cpu_buffer->cnt++;
 
 	/* update head page */
 	if (head_bit)
@@ -1968,6 +2688,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 			 * pointer to point to end of list
 			 */
 			head_page->prev = last_page;
+			cpu_buffer->cnt++;
 			success = true;
 			break;
 		}
@@ -2203,12 +2924,8 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 		 */
 		synchronize_rcu();
 		for_each_buffer_cpu(buffer, cpu) {
-			unsigned long flags;
-
 			cpu_buffer = buffer->buffers[cpu];
-			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 			rb_check_pages(cpu_buffer);
-			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 		}
 		atomic_dec(&buffer->record_disabled);
 	}
@@ -2364,6 +3081,52 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
 	iter->next_event = 0;
 }
 
+/* Return the index into the sub-buffers for a given sub-buffer */
+static int rb_meta_subbuf_idx(struct ring_buffer_meta *meta, void *subbuf)
+{
+	void *subbuf_array;
+
+	subbuf_array = (void *)meta + sizeof(int) * meta->nr_subbufs;
+	subbuf_array = (void *)ALIGN((unsigned long)subbuf_array, meta->subbuf_size);
+	return (subbuf - subbuf_array) / meta->subbuf_size;
+}
+
+static void rb_update_meta_head(struct ring_buffer_per_cpu *cpu_buffer,
+				struct buffer_page *next_page)
+{
+	struct ring_buffer_meta *meta = cpu_buffer->ring_meta;
+	unsigned long old_head = (unsigned long)next_page->page;
+	unsigned long new_head;
+
+	rb_inc_page(&next_page);
+	new_head = (unsigned long)next_page->page;
+
+	/*
+	 * Only move it forward once, if something else came in and
+	 * moved it forward, then we don't want to touch it.
+	 */
+	(void)cmpxchg(&meta->head_buffer, old_head, new_head);
+}
+
+static void rb_update_meta_reader(struct ring_buffer_per_cpu *cpu_buffer,
+				  struct buffer_page *reader)
+{
+	struct ring_buffer_meta *meta = cpu_buffer->ring_meta;
+	void *old_reader = cpu_buffer->reader_page->page;
+	void *new_reader = reader->page;
+	int id;
+
+	id = reader->id;
+	cpu_buffer->reader_page->id = id;
+	reader->id = 0;
+
+	meta->buffers[0] = rb_meta_subbuf_idx(meta, new_reader);
+	meta->buffers[id] = rb_meta_subbuf_idx(meta, old_reader);
+
+	/* The head pointer is the one after the reader */
+	rb_update_meta_head(cpu_buffer, reader);
+}
+
 /*
  * rb_handle_head_page - writer hit the head page
  *
@@ -2413,6 +3176,8 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
 		local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes);
 		local_inc(&cpu_buffer->pages_lost);
 
+		if (cpu_buffer->ring_meta)
+			rb_update_meta_head(cpu_buffer, next_page);
 		/*
 		 * The entries will be zeroed out when we move the
 		 * tail page.
@@ -2974,6 +3739,10 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 		local_set(&cpu_buffer->commit_page->page->commit,
 			  rb_page_write(cpu_buffer->commit_page));
 		rb_inc_page(&cpu_buffer->commit_page);
+		if (cpu_buffer->ring_meta) {
+			struct ring_buffer_meta *meta = cpu_buffer->ring_meta;
+			meta->commit_buffer = (unsigned long)cpu_buffer->commit_page->page;
+		}
 		/* add barrier to keep gcc from optimizing too much */
 		barrier();
 	}
@@ -3288,7 +4057,7 @@ static const char *show_irq_str(int bits)
 	return type[bits];
 }
 
-/* Assume this is an trace event */
+/* Assume this is a trace event */
 static const char *show_flags(struct ring_buffer_event *event)
 {
 	struct trace_entry *entry;
@@ -3420,11 +4189,10 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 			 struct rb_event_info *info,
 			 unsigned long tail)
 {
-	struct ring_buffer_event *event;
 	struct buffer_data_page *bpage;
 	u64 ts, delta;
 	bool full = false;
-	int e;
+	int ret;
 
 	bpage = info->tail_page->page;
 
@@ -3450,39 +4218,12 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 	if (atomic_inc_return(this_cpu_ptr(&checking)) != 1)
 		goto out;
 
-	ts = bpage->time_stamp;
-
-	for (e = 0; e < tail; e += rb_event_length(event)) {
-
-		event = (struct ring_buffer_event *)(bpage->data + e);
-
-		switch (event->type_len) {
-
-		case RINGBUF_TYPE_TIME_EXTEND:
-			delta = rb_event_time_stamp(event);
-			ts += delta;
-			break;
-
-		case RINGBUF_TYPE_TIME_STAMP:
-			delta = rb_event_time_stamp(event);
-			delta = rb_fix_abs_ts(delta, ts);
-			if (delta < ts) {
-				buffer_warn_return("[CPU: %d]ABSOLUTE TIME WENT BACKWARDS: last ts: %lld absolute ts: %lld\n",
-						   cpu_buffer->cpu, ts, delta);
-			}
-			ts = delta;
-			break;
-
-		case RINGBUF_TYPE_PADDING:
-			if (event->time_delta == 1)
-				break;
-			fallthrough;
-		case RINGBUF_TYPE_DATA:
-			ts += event->time_delta;
-			break;
-
-		default:
-			RB_WARN_ON(cpu_buffer, 1);
+	ret = rb_read_data_buffer(bpage, tail, cpu_buffer->cpu, &ts, &delta);
+	if (ret < 0) {
+		if (delta < ts) {
+			buffer_warn_return("[CPU: %d]ABSOLUTE TIME WENT BACKWARDS: last ts: %lld absolute ts: %lld\n",
+					   cpu_buffer->cpu, ts, delta);
+			goto out;
 		}
 	}
 	if ((full && ts > info->ts) ||
@@ -4591,6 +5332,9 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	if (!ret)
 		goto spin;
 
+	if (cpu_buffer->ring_meta)
+		rb_update_meta_reader(cpu_buffer, reader);
+
 	/*
 	 * Yay! We succeeded in replacing the page.
 	 *
@@ -4599,6 +5343,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list;
 	rb_inc_page(&cpu_buffer->head_page);
 
+	cpu_buffer->cnt++;
 	local_inc(&cpu_buffer->pages_read);
 
 	/* Finally update the reader page to the new head */
@@ -5138,12 +5883,9 @@ void
 ring_buffer_read_finish(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
-	unsigned long flags;
 
 	/* Use this opportunity to check the integrity of the ring buffer. */
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	rb_check_pages(cpu_buffer);
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	atomic_dec(&cpu_buffer->resize_disabled);
 	kfree(iter->event);
@@ -5212,6 +5954,9 @@ static void rb_update_meta_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct trace_buffer_meta *meta = cpu_buffer->meta_page;
 
+	if (!meta)
+		return;
+
 	meta->reader.read = cpu_buffer->reader_page->read;
 	meta->reader.id = cpu_buffer->reader_page->id;
 	meta->reader.lost_events = cpu_buffer->lost_events;
@@ -5268,11 +6013,16 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->lost_events = 0;
 	cpu_buffer->last_overrun = 0;
 
-	if (cpu_buffer->mapped)
-		rb_update_meta_page(cpu_buffer);
-
 	rb_head_page_activate(cpu_buffer);
 	cpu_buffer->pages_removed = 0;
+
+	if (cpu_buffer->mapped) {
+		rb_update_meta_page(cpu_buffer);
+		if (cpu_buffer->ring_meta) {
+			struct ring_buffer_meta *meta = cpu_buffer->ring_meta;
+			meta->commit_buffer = meta->head_buffer;
+		}
+	}
 }
 
 /* Must have disabled the cpu buffer then done a synchronize_rcu */
@@ -5303,6 +6053,7 @@ static void reset_disabled_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	struct ring_buffer_meta *meta;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
@@ -5321,6 +6072,11 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
 	atomic_dec(&cpu_buffer->record_disabled);
 	atomic_dec(&cpu_buffer->resize_disabled);
 
+	/* Make sure persistent meta now uses this buffer's addresses */
+	meta = rb_range_meta(buffer, 0, cpu_buffer->cpu);
+	if (meta)
+		rb_meta_init_text_addr(meta);
+
 	mutex_unlock(&buffer->mutex);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
@@ -5335,6 +6091,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_meta *meta;
 	int cpu;
 
 	/* prevent another thread from changing buffer sizes */
@@ -5362,6 +6119,11 @@ void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
 
 		reset_disabled_cpu_buffer(cpu_buffer);
 
+		/* Make sure persistent meta now uses this buffer's addresses */
+		meta = rb_range_meta(buffer, 0, cpu_buffer->cpu);
+		if (meta)
+			rb_meta_init_text_addr(meta);
+
 		atomic_dec(&cpu_buffer->record_disabled);
 		atomic_sub(RESET_BIT, &cpu_buffer->resize_disabled);
 	}
@@ -6008,39 +6770,39 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 	}
 
 	for_each_buffer_cpu(buffer, cpu) {
+		struct buffer_data_page *old_free_data_page;
+		struct list_head old_pages;
+		unsigned long flags;
 
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			continue;
 
 		cpu_buffer = buffer->buffers[cpu];
 
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
 		/* Clear the head bit to make the link list normal to read */
 		rb_head_page_deactivate(cpu_buffer);
 
-		/* Now walk the list and free all the old sub buffers */
-		list_for_each_entry_safe(bpage, tmp, cpu_buffer->pages, list) {
-			list_del_init(&bpage->list);
-			free_buffer_page(bpage);
-		}
-		/* The above loop stopped an the last page needing to be freed */
-		bpage = list_entry(cpu_buffer->pages, struct buffer_page, list);
-		free_buffer_page(bpage);
-
-		/* Free the current reader page */
-		free_buffer_page(cpu_buffer->reader_page);
+		/*
+		 * Collect buffers from the cpu_buffer pages list and the
+		 * reader_page on old_pages, so they can be freed later when not
+		 * under a spinlock. The pages list is a linked list with no
+		 * head, adding old_pages turns it into a regular list with
+		 * old_pages being the head.
+		 */
+		list_add(&old_pages, cpu_buffer->pages);
+		list_add(&cpu_buffer->reader_page->list, &old_pages);
 
 		/* One page was allocated for the reader page */
 		cpu_buffer->reader_page = list_entry(cpu_buffer->new_pages.next,
 						     struct buffer_page, list);
 		list_del_init(&cpu_buffer->reader_page->list);
 
-		/* The cpu_buffer pages are a link list with no head */
+		/* Install the new pages, remove the head from the list */
 		cpu_buffer->pages = cpu_buffer->new_pages.next;
-		cpu_buffer->new_pages.next->prev = cpu_buffer->new_pages.prev;
-		cpu_buffer->new_pages.prev->next = cpu_buffer->new_pages.next;
-
-		/* Clear the new_pages list */
-		INIT_LIST_HEAD(&cpu_buffer->new_pages);
+		list_del_init(&cpu_buffer->new_pages);
+		cpu_buffer->cnt++;
 
 		cpu_buffer->head_page
 			= list_entry(cpu_buffer->pages, struct buffer_page, list);
@@ -6049,11 +6811,20 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 		cpu_buffer->nr_pages = cpu_buffer->nr_pages_to_update;
 		cpu_buffer->nr_pages_to_update = 0;
 
-		free_pages((unsigned long)cpu_buffer->free_page, old_order);
+		old_free_data_page = cpu_buffer->free_page;
 		cpu_buffer->free_page = NULL;
 
 		rb_head_page_activate(cpu_buffer);
 
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+		/* Free old sub buffers */
+		list_for_each_entry_safe(bpage, tmp, &old_pages, list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+		free_pages((unsigned long)old_free_data_page, old_order);
+
 		rb_check_pages(cpu_buffer);
 	}
 
@@ -6135,10 +6906,10 @@ static void rb_setup_ids_meta_page(struct ring_buffer_per_cpu *cpu_buffer,
 	/* install subbuf ID to kern VA translation */
 	cpu_buffer->subbuf_ids = subbuf_ids;
 
-	meta->meta_page_size = PAGE_SIZE;
 	meta->meta_struct_len = sizeof(*meta);
 	meta->nr_subbufs = nr_subbufs;
 	meta->subbuf_size = cpu_buffer->buffer->subbuf_size + BUF_PAGE_HDR_SIZE;
+	meta->meta_page_size = meta->subbuf_size;
 
 	rb_update_meta_page(cpu_buffer);
 }
@@ -6155,7 +6926,7 @@ rb_get_mapped_buffer(struct trace_buffer *buffer, int cpu)
 
 	mutex_lock(&cpu_buffer->mapping_lock);
 
-	if (!cpu_buffer->mapped) {
+	if (!cpu_buffer->user_mapped) {
 		mutex_unlock(&cpu_buffer->mapping_lock);
 		return ERR_PTR(-ENODEV);
 	}
@@ -6179,19 +6950,26 @@ static int __rb_inc_dec_mapped(struct ring_buffer_per_cpu *cpu_buffer,
 
 	lockdep_assert_held(&cpu_buffer->mapping_lock);
 
+	/* mapped is always greater or equal to user_mapped */
+	if (WARN_ON(cpu_buffer->mapped < cpu_buffer->user_mapped))
+		return -EINVAL;
+
 	if (inc && cpu_buffer->mapped == UINT_MAX)
 		return -EBUSY;
 
-	if (WARN_ON(!inc && cpu_buffer->mapped == 0))
+	if (WARN_ON(!inc && cpu_buffer->user_mapped == 0))
 		return -EINVAL;
 
 	mutex_lock(&cpu_buffer->buffer->mutex);
 	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
-	if (inc)
+	if (inc) {
+		cpu_buffer->user_mapped++;
 		cpu_buffer->mapped++;
-	else
+	} else {
+		cpu_buffer->user_mapped--;
 		cpu_buffer->mapped--;
+	}
 
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 	mutex_unlock(&cpu_buffer->buffer->mutex);
@@ -6214,7 +6992,7 @@ static int __rb_inc_dec_mapped(struct ring_buffer_per_cpu *cpu_buffer,
 static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer,
 			struct vm_area_struct *vma)
 {
-	unsigned long nr_subbufs, nr_pages, vma_pages, pgoff = vma->vm_pgoff;
+	unsigned long nr_subbufs, nr_pages, nr_vma_pages, pgoff = vma->vm_pgoff;
 	unsigned int subbuf_pages, subbuf_order;
 	struct page **pages;
 	int p = 0, s = 0;
@@ -6225,6 +7003,12 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer,
 	    !(vma->vm_flags & VM_MAYSHARE))
 		return -EPERM;
 
+	subbuf_order = cpu_buffer->buffer->subbuf_order;
+	subbuf_pages = 1 << subbuf_order;
+
+	if (subbuf_order && pgoff % subbuf_pages)
+		return -EINVAL;
+
 	/*
 	 * Make sure the mapping cannot become writable later. Also tell the VM
 	 * to not touch these pages (VM_DONTCOPY | VM_DONTEXPAND).
@@ -6234,37 +7018,38 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer,
 
 	lockdep_assert_held(&cpu_buffer->mapping_lock);
 
-	subbuf_order = cpu_buffer->buffer->subbuf_order;
-	subbuf_pages = 1 << subbuf_order;
-
 	nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */
-	nr_pages = ((nr_subbufs) << subbuf_order) - pgoff + 1; /* + meta-page */
+	nr_pages = ((nr_subbufs + 1) << subbuf_order) - pgoff; /* + meta-page */
 
-	vma_pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
-	if (!vma_pages || vma_pages > nr_pages)
+	nr_vma_pages = vma_pages(vma);
+	if (!nr_vma_pages || nr_vma_pages > nr_pages)
 		return -EINVAL;
 
-	nr_pages = vma_pages;
+	nr_pages = nr_vma_pages;
 
 	pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL);
 	if (!pages)
 		return -ENOMEM;
 
 	if (!pgoff) {
+		unsigned long meta_page_padding;
+
 		pages[p++] = virt_to_page(cpu_buffer->meta_page);
 
 		/*
-		 * TODO: Align sub-buffers on their size, once
-		 * vm_insert_pages() supports the zero-page.
+		 * Pad with the zero-page to align the meta-page with the
+		 * sub-buffers.
 		 */
-	} else {
-		/* Skip the meta-page */
-		pgoff--;
+		meta_page_padding = subbuf_pages - 1;
+		while (meta_page_padding-- && p < nr_pages) {
+			unsigned long __maybe_unused zero_addr =
+				vma->vm_start + (PAGE_SIZE * p);
 
-		if (pgoff % subbuf_pages) {
-			err = -EINVAL;
-			goto out;
+			pages[p++] = ZERO_PAGE(zero_addr);
 		}
+	} else {
+		/* Skip the meta-page */
+		pgoff -= subbuf_pages;
 
 		s += pgoff / subbuf_pages;
 	}
@@ -6316,7 +7101,7 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 
 	mutex_lock(&cpu_buffer->mapping_lock);
 
-	if (cpu_buffer->mapped) {
+	if (cpu_buffer->user_mapped) {
 		err = __rb_map_vma(cpu_buffer, vma);
 		if (!err)
 			err = __rb_inc_dec_mapped(cpu_buffer, true);
@@ -6347,12 +7132,15 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 	 */
 	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	rb_setup_ids_meta_page(cpu_buffer, subbuf_ids);
+
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	err = __rb_map_vma(cpu_buffer, vma);
 	if (!err) {
 		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-		cpu_buffer->mapped = 1;
+		/* This is the first time it is mapped by user */
+		cpu_buffer->mapped++;
+		cpu_buffer->user_mapped = 1;
 		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 	} else {
 		kfree(cpu_buffer->subbuf_ids);
@@ -6380,10 +7168,10 @@ int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 
 	mutex_lock(&cpu_buffer->mapping_lock);
 
-	if (!cpu_buffer->mapped) {
+	if (!cpu_buffer->user_mapped) {
 		err = -ENODEV;
 		goto out;
-	} else if (cpu_buffer->mapped > 1) {
+	} else if (cpu_buffer->user_mapped > 1) {
 		__rb_inc_dec_mapped(cpu_buffer, false);
 		goto out;
 	}
@@ -6391,7 +7179,10 @@ int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 	mutex_lock(&buffer->mutex);
 	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
-	cpu_buffer->mapped = 0;
+	/* This is the last user space mapping */
+	if (!WARN_ON_ONCE(cpu_buffer->mapped < cpu_buffer->user_mapped))
+		cpu_buffer->mapped--;
+	cpu_buffer->user_mapped = 0;
 
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 008187ebd7fe..cdc3aea12c93 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -307,14 +307,14 @@ static void ring_buffer_producer(void)
 	if (!disable_reader) {
 		if (consumer_fifo)
 			trace_printk("Running Consumer at SCHED_FIFO %s\n",
-				     consumer_fifo == 1 ? "low" : "high");
+				     str_low_high(consumer_fifo == 1));
 		else
 			trace_printk("Running Consumer at nice: %d\n",
 				     consumer_nice);
 	}
 	if (producer_fifo)
 		trace_printk("Running Producer at SCHED_FIFO %s\n",
-			     producer_fifo == 1 ? "low" : "high");
+			     str_low_high(producer_fifo == 1));
 	else
 		trace_printk("Running Producer at nice: %d\n",
 			     producer_nice);
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index df0745a42a3f..279c70e1bd74 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -41,7 +41,7 @@
  * per-task monitor, and so on), and the helper functions that glue the
  * monitor to the system via trace. Generally, a monitor includes some form
  * of trace output as a reaction for event parsing and exceptions,
- * as depicted bellow:
+ * as depicted below:
  *
  * Linux  +----- RV Monitor ----------------------------------+ Formal
  *  Realm |                                                   |  Realm
@@ -306,7 +306,6 @@ static ssize_t monitor_enable_write_data(struct file *filp, const char __user *u
 
 static const struct file_operations interface_enable_fops = {
 	.open   = simple_open,
-	.llseek = no_llseek,
 	.write  = monitor_enable_write_data,
 	.read   = monitor_enable_read_data,
 };
@@ -329,7 +328,6 @@ static ssize_t monitor_desc_read_data(struct file *filp, char __user *user_buf,
 
 static const struct file_operations interface_desc_fops = {
 	.open   = simple_open,
-	.llseek	= no_llseek,
 	.read	= monitor_desc_read_data,
 };
 
@@ -674,7 +672,6 @@ static ssize_t monitoring_on_write_data(struct file *filp, const char __user *us
 
 static const struct file_operations monitoring_on_fops = {
 	.open   = simple_open,
-	.llseek = no_llseek,
 	.write  = monitoring_on_write_data,
 	.read   = monitoring_on_read_data,
 };
diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c
index 6aae106695b6..7b49cbe388d4 100644
--- a/kernel/trace/rv/rv_reactors.c
+++ b/kernel/trace/rv/rv_reactors.c
@@ -426,7 +426,6 @@ static ssize_t reacting_on_write_data(struct file *filp, const char __user *user
 
 static const struct file_operations reacting_on_fops = {
 	.open   = simple_open,
-	.llseek = no_llseek,
 	.write  = reacting_on_write_data,
 	.read   = reacting_on_read_data,
 };
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ebe7ce2f5f4a..be62f0ea1814 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -482,7 +482,7 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_export);
 	 TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO |		\
 	 TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |			\
 	 TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS |			\
-	 TRACE_ITER_HASH_PTR)
+	 TRACE_ITER_HASH_PTR | TRACE_ITER_TRACE_PRINTK)
 
 /* trace_options that are only supported by global_trace */
 #define TOP_LEVEL_TRACE_FLAGS (TRACE_ITER_PRINTK |			\
@@ -490,7 +490,7 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_export);
 
 /* trace_flags that are default zero for instances */
 #define ZEROED_TRACE_FLAGS \
-	(TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK)
+	(TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK | TRACE_ITER_TRACE_PRINTK)
 
 /*
  * The global_trace is the descriptor that holds the top-level tracing
@@ -500,6 +500,29 @@ static struct trace_array global_trace = {
 	.trace_flags = TRACE_DEFAULT_FLAGS,
 };
 
+static struct trace_array *printk_trace = &global_trace;
+
+static __always_inline bool printk_binsafe(struct trace_array *tr)
+{
+	/*
+	 * The binary format of traceprintk can cause a crash if used
+	 * by a buffer from another boot. Force the use of the
+	 * non binary version of trace_printk if the trace_printk
+	 * buffer is a boot mapped ring buffer.
+	 */
+	return !(tr->flags & TRACE_ARRAY_FL_BOOT);
+}
+
+static void update_printk_trace(struct trace_array *tr)
+{
+	if (printk_trace == tr)
+		return;
+
+	printk_trace->trace_flags &= ~TRACE_ITER_TRACE_PRINTK;
+	printk_trace = tr;
+	tr->trace_flags |= TRACE_ITER_TRACE_PRINTK;
+}
+
 void trace_set_ring_buffer_expanded(struct trace_array *tr)
 {
 	if (!tr)
@@ -570,19 +593,6 @@ int tracing_check_open_get_tr(struct trace_array *tr)
 	return 0;
 }
 
-int call_filter_check_discard(struct trace_event_call *call, void *rec,
-			      struct trace_buffer *buffer,
-			      struct ring_buffer_event *event)
-{
-	if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
-	    !filter_match_preds(call->filter, rec)) {
-		__trace_event_discard_commit(buffer, event);
-		return 1;
-	}
-
-	return 0;
-}
-
 /**
  * trace_find_filtered_pid - check if a pid exists in a filtered_pid list
  * @filtered_pids: The list of pids to check
@@ -965,7 +975,8 @@ static inline void trace_access_lock_init(void)
 #endif
 
 #ifdef CONFIG_STACKTRACE
-static void __ftrace_trace_stack(struct trace_buffer *buffer,
+static void __ftrace_trace_stack(struct trace_array *tr,
+				 struct trace_buffer *buffer,
 				 unsigned int trace_ctx,
 				 int skip, struct pt_regs *regs);
 static inline void ftrace_trace_stack(struct trace_array *tr,
@@ -974,7 +985,8 @@ static inline void ftrace_trace_stack(struct trace_array *tr,
 				      int skip, struct pt_regs *regs);
 
 #else
-static inline void __ftrace_trace_stack(struct trace_buffer *buffer,
+static inline void __ftrace_trace_stack(struct trace_array *tr,
+					struct trace_buffer *buffer,
 					unsigned int trace_ctx,
 					int skip, struct pt_regs *regs)
 {
@@ -1117,7 +1129,7 @@ EXPORT_SYMBOL_GPL(__trace_array_puts);
  */
 int __trace_puts(unsigned long ip, const char *str, int size)
 {
-	return __trace_array_puts(&global_trace, ip, str, size);
+	return __trace_array_puts(printk_trace, ip, str, size);
 }
 EXPORT_SYMBOL_GPL(__trace_puts);
 
@@ -1128,6 +1140,7 @@ EXPORT_SYMBOL_GPL(__trace_puts);
  */
 int __trace_bputs(unsigned long ip, const char *str)
 {
+	struct trace_array *tr = READ_ONCE(printk_trace);
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer;
 	struct bputs_entry *entry;
@@ -1135,14 +1148,17 @@ int __trace_bputs(unsigned long ip, const char *str)
 	int size = sizeof(struct bputs_entry);
 	int ret = 0;
 
-	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
+	if (!printk_binsafe(tr))
+		return __trace_puts(ip, str, strlen(str));
+
+	if (!(tr->trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
 
 	trace_ctx = tracing_gen_ctx();
-	buffer = global_trace.array_buffer.buffer;
+	buffer = tr->array_buffer.buffer;
 
 	ring_buffer_nest_start(buffer);
 	event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
@@ -1155,7 +1171,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	entry->str			= str;
 
 	__buffer_unlock_commit(buffer, event);
-	ftrace_trace_stack(&global_trace, buffer, trace_ctx, 4, NULL);
+	ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL);
 
 	ret = 1;
  out:
@@ -1907,7 +1923,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	max_data->critical_start = data->critical_start;
 	max_data->critical_end = data->critical_end;
 
-	strncpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
+	strscpy(max_data->comm, tsk->comm);
 	max_data->pid = tsk->pid;
 	/*
 	 * If tsk == current, then use current_uid(), as that does not use
@@ -2226,10 +2242,6 @@ static __init int init_trace_selftests(void)
 }
 core_initcall(init_trace_selftests);
 #else
-static inline int run_tracer_selftest(struct tracer *type)
-{
-	return 0;
-}
 static inline int do_run_tracer_selftest(struct tracer *type)
 {
 	return 0;
@@ -2363,6 +2375,25 @@ void tracing_reset_online_cpus(struct array_buffer *buf)
 	ring_buffer_record_enable(buffer);
 }
 
+static void tracing_reset_all_cpus(struct array_buffer *buf)
+{
+	struct trace_buffer *buffer = buf->buffer;
+
+	if (!buffer)
+		return;
+
+	ring_buffer_record_disable(buffer);
+
+	/* Make sure all commits have finished */
+	synchronize_rcu();
+
+	buf->time_start = buffer_ftrace_now(buf, buf->cpu);
+
+	ring_buffer_reset(buffer);
+
+	ring_buffer_record_enable(buffer);
+}
+
 /* Must have trace_types_lock held */
 void tracing_reset_all_online_cpus_unlocked(void)
 {
@@ -2521,6 +2552,8 @@ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status)
 		trace_flags |= TRACE_FLAG_NEED_RESCHED;
 	if (test_preempt_need_resched())
 		trace_flags |= TRACE_FLAG_PREEMPT_RESCHED;
+	if (IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY) && tif_test_bit(TIF_NEED_RESCHED_LAZY))
+		trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY;
 	return (trace_flags << 16) | (min_t(unsigned int, pc & 0xff, 0xf)) |
 		(min_t(unsigned int, migration_disable_value(), 0xf)) << 4;
 }
@@ -2866,7 +2899,6 @@ void
 trace_function(struct trace_array *tr, unsigned long ip, unsigned long
 	       parent_ip, unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_function;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
@@ -2879,11 +2911,9 @@ trace_function(struct trace_array *tr, unsigned long ip, unsigned long
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		if (static_branch_unlikely(&trace_function_exports_enabled))
-			ftrace_exports(event, TRACE_EXPORT_FUNCTION);
-		__buffer_unlock_commit(buffer, event);
-	}
+	if (static_branch_unlikely(&trace_function_exports_enabled))
+		ftrace_exports(event, TRACE_EXPORT_FUNCTION);
+	__buffer_unlock_commit(buffer, event);
 }
 
 #ifdef CONFIG_STACKTRACE
@@ -2891,7 +2921,7 @@ trace_function(struct trace_array *tr, unsigned long ip, unsigned long
 /* Allow 4 levels of nesting: normal, softirq, irq, NMI */
 #define FTRACE_KSTACK_NESTING	4
 
-#define FTRACE_KSTACK_ENTRIES	(PAGE_SIZE / FTRACE_KSTACK_NESTING)
+#define FTRACE_KSTACK_ENTRIES	(SZ_4K / FTRACE_KSTACK_NESTING)
 
 struct ftrace_stack {
 	unsigned long		calls[FTRACE_KSTACK_ENTRIES];
@@ -2905,11 +2935,11 @@ struct ftrace_stacks {
 static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks);
 static DEFINE_PER_CPU(int, ftrace_stack_reserve);
 
-static void __ftrace_trace_stack(struct trace_buffer *buffer,
+static void __ftrace_trace_stack(struct trace_array *tr,
+				 struct trace_buffer *buffer,
 				 unsigned int trace_ctx,
 				 int skip, struct pt_regs *regs)
 {
-	struct trace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
 	unsigned int size, nr_entries;
 	struct ftrace_stack *fstack;
@@ -2952,6 +2982,20 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 		nr_entries = stack_trace_save(fstack->calls, size, skip);
 	}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* Mark entry of stack trace as trampoline code */
+	if (tr->ops && tr->ops->trampoline) {
+		unsigned long tramp_start = tr->ops->trampoline;
+		unsigned long tramp_end = tramp_start + tr->ops->trampoline_size;
+		unsigned long *calls = fstack->calls;
+
+		for (int i = 0; i < nr_entries; i++) {
+			if (calls[i] >= tramp_start && calls[i] < tramp_end)
+				calls[i] = FTRACE_TRAMPOLINE_MARKER;
+		}
+	}
+#endif
+
 	event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
 				    struct_size(entry, caller, nr_entries),
 				    trace_ctx);
@@ -2963,8 +3007,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 	memcpy(&entry->caller, fstack->calls,
 	       flex_array_size(entry, caller, nr_entries));
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		__buffer_unlock_commit(buffer, event);
+	__buffer_unlock_commit(buffer, event);
 
  out:
 	/* Again, don't let gcc optimize things here */
@@ -2982,7 +3025,7 @@ static inline void ftrace_trace_stack(struct trace_array *tr,
 	if (!(tr->trace_flags & TRACE_ITER_STACKTRACE))
 		return;
 
-	__ftrace_trace_stack(buffer, trace_ctx, skip, regs);
+	__ftrace_trace_stack(tr, buffer, trace_ctx, skip, regs);
 }
 
 void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
@@ -2991,7 +3034,7 @@ void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 
 	if (rcu_is_watching()) {
-		__ftrace_trace_stack(buffer, trace_ctx, skip, NULL);
+		__ftrace_trace_stack(tr, buffer, trace_ctx, skip, NULL);
 		return;
 	}
 
@@ -3008,7 +3051,7 @@ void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
 		return;
 
 	ct_irq_enter_irqson();
-	__ftrace_trace_stack(buffer, trace_ctx, skip, NULL);
+	__ftrace_trace_stack(tr, buffer, trace_ctx, skip, NULL);
 	ct_irq_exit_irqson();
 }
 
@@ -3025,8 +3068,8 @@ void trace_dump_stack(int skip)
 	/* Skip 1 to skip this function. */
 	skip++;
 #endif
-	__ftrace_trace_stack(global_trace.array_buffer.buffer,
-			     tracing_gen_ctx(), skip, NULL);
+	__ftrace_trace_stack(printk_trace, printk_trace->array_buffer.buffer,
+				tracing_gen_ctx(), skip, NULL);
 }
 EXPORT_SYMBOL_GPL(trace_dump_stack);
 
@@ -3037,7 +3080,6 @@ static void
 ftrace_trace_userstack(struct trace_array *tr,
 		       struct trace_buffer *buffer, unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
 
@@ -3071,8 +3113,7 @@ ftrace_trace_userstack(struct trace_array *tr,
 	memset(&entry->caller, 0, sizeof(entry->caller));
 
 	stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES);
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		__buffer_unlock_commit(buffer, event);
+	__buffer_unlock_commit(buffer, event);
 
  out_drop_count:
 	__this_cpu_dec(user_stack_count);
@@ -3241,15 +3282,17 @@ static void trace_printk_start_stop_comm(int enabled)
  */
 int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 {
-	struct trace_event_call *call = &event_bprint;
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer;
-	struct trace_array *tr = &global_trace;
+	struct trace_array *tr = READ_ONCE(printk_trace);
 	struct bprint_entry *entry;
 	unsigned int trace_ctx;
 	char *tbuffer;
 	int len = 0, size;
 
+	if (!printk_binsafe(tr))
+		return trace_vprintk(ip, fmt, args);
+
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
 
@@ -3282,10 +3325,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, tbuffer, sizeof(u32) * len);
-	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		__buffer_unlock_commit(buffer, event);
-		ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
-	}
+	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
 
 out:
 	ring_buffer_nest_end(buffer);
@@ -3305,7 +3346,6 @@ static int
 __trace_array_vprintk(struct trace_buffer *buffer,
 		      unsigned long ip, const char *fmt, va_list args)
 {
-	struct trace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
 	int len = 0, size;
 	struct print_entry *entry;
@@ -3340,10 +3380,8 @@ __trace_array_vprintk(struct trace_buffer *buffer,
 	entry->ip = ip;
 
 	memcpy(&entry->buf, tbuffer, len + 1);
-	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		__buffer_unlock_commit(buffer, event);
-		ftrace_trace_stack(&global_trace, buffer, trace_ctx, 6, NULL);
-	}
+	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL);
 
 out:
 	ring_buffer_nest_end(buffer);
@@ -3438,7 +3476,7 @@ int trace_array_printk_buf(struct trace_buffer *buffer,
 	int ret;
 	va_list ap;
 
-	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
+	if (!(printk_trace->trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
 	va_start(ap, fmt);
@@ -3450,7 +3488,7 @@ int trace_array_printk_buf(struct trace_buffer *buffer,
 __printf(2, 0)
 int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 {
-	return trace_array_vprintk(&global_trace, ip, fmt, args);
+	return trace_array_vprintk(printk_trace, ip, fmt, args);
 }
 EXPORT_SYMBOL_GPL(trace_vprintk);
 
@@ -3671,8 +3709,11 @@ static void test_can_verify(void)
 void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 			 va_list ap)
 {
+	long text_delta = 0;
+	long data_delta = 0;
 	const char *p = fmt;
 	const char *str;
+	bool good;
 	int i, j;
 
 	if (WARN_ON_ONCE(!fmt))
@@ -3681,6 +3722,17 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 	if (static_branch_unlikely(&trace_no_verify))
 		goto print;
 
+	/*
+	 * When the kernel is booted with the tp_printk command line
+	 * parameter, trace events go directly through to printk().
+	 * It also is checked by this function, but it does not
+	 * have an associated trace_array (tr) for it.
+	 */
+	if (iter->tr) {
+		text_delta = iter->tr->text_delta;
+		data_delta = iter->tr->data_delta;
+	}
+
 	/* Don't bother checking when doing a ftrace_dump() */
 	if (iter->fmt == static_fmt_buf)
 		goto print;
@@ -3691,7 +3743,10 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 
 		j = 0;
 
-		/* We only care about %s and variants */
+		/*
+		 * We only care about %s and variants
+		 * as well as %p[sS] if delta is non-zero
+		 */
 		for (i = 0; p[i]; i++) {
 			if (i + 1 >= iter->fmt_size) {
 				/*
@@ -3720,6 +3775,11 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 				}
 				if (p[i+j] == 's')
 					break;
+
+				if (text_delta && p[i+1] == 'p' &&
+				    ((p[i+2] == 's' || p[i+2] == 'S')))
+					break;
+
 				star = false;
 			}
 			j = 0;
@@ -3733,6 +3793,24 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 		iter->fmt[i] = '\0';
 		trace_seq_vprintf(&iter->seq, iter->fmt, ap);
 
+		/* Add delta to %pS pointers */
+		if (p[i+1] == 'p') {
+			unsigned long addr;
+			char fmt[4];
+
+			fmt[0] = '%';
+			fmt[1] = 'p';
+			fmt[2] = p[i+2]; /* Either %ps or %pS */
+			fmt[3] = '\0';
+
+			addr = va_arg(ap, unsigned long);
+			addr += text_delta;
+			trace_seq_printf(&iter->seq, fmt, (void *)addr);
+
+			p += i + 3;
+			continue;
+		}
+
 		/*
 		 * If iter->seq is full, the above call no longer guarantees
 		 * that ap is in sync with fmt processing, and further calls
@@ -3751,6 +3829,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 		/* The ap now points to the string data of the %s */
 		str = va_arg(ap, const char *);
 
+		good = trace_safe_str(iter, str, star, len);
+
+		/* Could be from the last boot */
+		if (data_delta && !good) {
+			str += data_delta;
+			good = trace_safe_str(iter, str, star, len);
+		}
+
 		/*
 		 * If you hit this warning, it is likely that the
 		 * trace event in question used %s on a string that
@@ -3760,8 +3846,7 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 		 * instead. See samples/trace_events/trace-events-sample.h
 		 * for reference.
 		 */
-		if (WARN_ONCE(!trace_safe_str(iter, str, star, len),
-			      "fmt: '%s' current_buffer: '%s'",
+		if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'",
 			      fmt, seq_buf_str(&iter->seq.seq))) {
 			int ret;
 
@@ -3958,6 +4043,8 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 			break;
 		entries++;
 		ring_buffer_iter_advance(buf_iter);
+		/* This could be a big loop */
+		cond_resched();
 	}
 
 	per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries;
@@ -4921,6 +5008,11 @@ static int tracing_open(struct inode *inode, struct file *file)
 static bool
 trace_ok_for_array(struct tracer *t, struct trace_array *tr)
 {
+#ifdef CONFIG_TRACER_SNAPSHOT
+	/* arrays with mapped buffer range do not have snapshots */
+	if (tr->range_addr_start && t->use_max_tr)
+		return false;
+#endif
 	return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances;
 }
 
@@ -5013,7 +5105,7 @@ static int show_traces_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int show_traces_release(struct inode *inode, struct file *file)
+static int tracing_seq_release(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
 
@@ -5054,7 +5146,7 @@ static const struct file_operations show_traces_fops = {
 	.open		= show_traces_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= show_traces_release,
+	.release	= tracing_seq_release,
 };
 
 static ssize_t
@@ -5239,7 +5331,8 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
 int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 {
 	if ((mask == TRACE_ITER_RECORD_TGID) ||
-	    (mask == TRACE_ITER_RECORD_CMD))
+	    (mask == TRACE_ITER_RECORD_CMD) ||
+	    (mask == TRACE_ITER_TRACE_PRINTK))
 		lockdep_assert_held(&event_mutex);
 
 	/* do nothing if flag is already set */
@@ -5251,6 +5344,25 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 		if (tr->current_trace->flag_changed(tr, mask, !!enabled))
 			return -EINVAL;
 
+	if (mask == TRACE_ITER_TRACE_PRINTK) {
+		if (enabled) {
+			update_printk_trace(tr);
+		} else {
+			/*
+			 * The global_trace cannot clear this.
+			 * It's flag only gets cleared if another instance sets it.
+			 */
+			if (printk_trace == &global_trace)
+				return -EINVAL;
+			/*
+			 * An instance must always have it set.
+			 * by default, that's the global_trace instane.
+			 */
+			if (printk_trace == tr)
+				update_printk_trace(&global_trace);
+		}
+	}
+
 	if (enabled)
 		tr->trace_flags |= mask;
 	else
@@ -5401,6 +5513,10 @@ static const struct file_operations tracing_iter_fops = {
 
 static const char readme_msg[] =
 	"tracing mini-HOWTO:\n\n"
+	"By default tracefs removes all OTH file permission bits.\n"
+	"When mounting tracefs an optional group id can be specified\n"
+	"which adds the group to every directory and file in tracefs:\n\n"
+	"\t e.g. mount -t tracefs [-o [gid=<gid>]] nodev /sys/kernel/tracing\n\n"
 	"# echo 0 > tracing_on : quick way to disable tracing\n"
 	"# echo 1 > tracing_on : quick way to re-enable tracing\n\n"
 	" Important files:\n"
@@ -6036,6 +6152,23 @@ out:
 	return ret;
 }
 
+static void update_last_data(struct trace_array *tr)
+{
+	if (!tr->text_delta && !tr->data_delta)
+		return;
+
+	/*
+	 * Need to clear all CPU buffers as there cannot be events
+	 * from the previous boot mixed with events with this boot
+	 * as that will cause a confusing trace. Need to clear all
+	 * CPU buffers, even for those that may currently be offline.
+	 */
+	tracing_reset_all_cpus(&tr->array_buffer);
+
+	/* Using current data now */
+	tr->text_delta = 0;
+	tr->data_delta = 0;
+}
 
 /**
  * tracing_update_buffers - used by tracing facility to expand ring buffers
@@ -6053,6 +6186,9 @@ int tracing_update_buffers(struct trace_array *tr)
 	int ret = 0;
 
 	mutex_lock(&trace_types_lock);
+
+	update_last_data(tr);
+
 	if (!tr->ring_buffer_expanded)
 		ret = __tracing_resize_ring_buffer(tr, trace_buf_size,
 						RING_BUFFER_ALL_CPUS);
@@ -6108,6 +6244,8 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 
 	mutex_lock(&trace_types_lock);
 
+	update_last_data(tr);
+
 	if (!tr->ring_buffer_expanded) {
 		ret = __tracing_resize_ring_buffer(tr, trace_buf_size,
 						RING_BUFFER_ALL_CPUS);
@@ -6856,6 +6994,37 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf,
 }
 
 static ssize_t
+tracing_last_boot_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	struct seq_buf seq;
+	char buf[64];
+
+	seq_buf_init(&seq, buf, 64);
+
+	seq_buf_printf(&seq, "text delta:\t%ld\n", tr->text_delta);
+	seq_buf_printf(&seq, "data delta:\t%ld\n", tr->data_delta);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, seq_buf_used(&seq));
+}
+
+static int tracing_buffer_meta_open(struct inode *inode, struct file *filp)
+{
+	struct trace_array *tr = inode->i_private;
+	int cpu = tracing_get_cpu(inode);
+	int ret;
+
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
+
+	ret = ring_buffer_meta_seq_init(filp, tr->array_buffer.buffer, cpu);
+	if (ret < 0)
+		__trace_array_put(tr);
+	return ret;
+}
+
+static ssize_t
 tracing_free_buffer_write(struct file *filp, const char __user *ubuf,
 			  size_t cnt, loff_t *ppos)
 {
@@ -7420,7 +7589,6 @@ static const struct file_operations tracing_pipe_fops = {
 	.read		= tracing_read_pipe,
 	.splice_read	= tracing_splice_read_pipe,
 	.release	= tracing_release_pipe,
-	.llseek		= no_llseek,
 };
 
 static const struct file_operations tracing_entries_fops = {
@@ -7431,6 +7599,13 @@ static const struct file_operations tracing_entries_fops = {
 	.release	= tracing_release_generic_tr,
 };
 
+static const struct file_operations tracing_buffer_meta_fops = {
+	.open		= tracing_buffer_meta_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= tracing_seq_release,
+};
+
 static const struct file_operations tracing_total_entries_fops = {
 	.open		= tracing_open_generic_tr,
 	.read		= tracing_total_entries_read,
@@ -7471,6 +7646,13 @@ static const struct file_operations trace_time_stamp_mode_fops = {
 	.release	= tracing_single_release_tr,
 };
 
+static const struct file_operations last_boot_fops = {
+	.open		= tracing_open_generic_tr,
+	.read		= tracing_last_boot_read,
+	.llseek		= generic_file_llseek,
+	.release	= tracing_release_generic_tr,
+};
+
 #ifdef CONFIG_TRACER_SNAPSHOT
 static const struct file_operations snapshot_fops = {
 	.open		= tracing_snapshot_open,
@@ -7485,7 +7667,6 @@ static const struct file_operations snapshot_raw_fops = {
 	.read		= tracing_buffers_read,
 	.release	= tracing_buffers_release,
 	.splice_read	= tracing_buffers_splice_read,
-	.llseek		= no_llseek,
 };
 
 #endif /* CONFIG_TRACER_SNAPSHOT */
@@ -8315,7 +8496,6 @@ static const struct file_operations tracing_buffers_fops = {
 	.flush		= tracing_buffers_flush,
 	.splice_read	= tracing_buffers_splice_read,
 	.unlocked_ioctl = tracing_buffers_ioctl,
-	.llseek		= no_llseek,
 	.mmap		= tracing_buffers_mmap,
 };
 
@@ -8400,15 +8580,22 @@ tracing_read_dyn_info(struct file *filp, char __user *ubuf,
 	char *buf;
 	int r;
 
-	/* 256 should be plenty to hold the amount needed */
-	buf = kmalloc(256, GFP_KERNEL);
+	/* 512 should be plenty to hold the amount needed */
+#define DYN_INFO_BUF_SIZE	512
+
+	buf = kmalloc(DYN_INFO_BUF_SIZE, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	r = scnprintf(buf, 256, "%ld pages:%ld groups: %ld\n",
+	r = scnprintf(buf, DYN_INFO_BUF_SIZE,
+		      "%ld pages:%ld groups: %ld\n"
+		      "ftrace boot update time = %llu (ns)\n"
+		      "ftrace module total update time = %llu (ns)\n",
 		      ftrace_update_tot_cnt,
 		      ftrace_number_of_pages,
-		      ftrace_number_of_groups);
+		      ftrace_number_of_groups,
+		      ftrace_update_time,
+		      ftrace_total_mod_time);
 
 	ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 	kfree(buf);
@@ -8663,12 +8850,17 @@ tracing_init_tracefs_percpu(struct trace_array *tr, long cpu)
 	trace_create_cpu_file("buffer_size_kb", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &tracing_entries_fops);
 
+	if (tr->range_addr_start)
+		trace_create_cpu_file("buffer_meta", TRACE_MODE_READ, d_cpu,
+				      tr, cpu, &tracing_buffer_meta_fops);
 #ifdef CONFIG_TRACER_SNAPSHOT
-	trace_create_cpu_file("snapshot", TRACE_MODE_WRITE, d_cpu,
-				tr, cpu, &snapshot_fops);
+	if (!tr->range_addr_start) {
+		trace_create_cpu_file("snapshot", TRACE_MODE_WRITE, d_cpu,
+				      tr, cpu, &snapshot_fops);
 
-	trace_create_cpu_file("snapshot_raw", TRACE_MODE_READ, d_cpu,
-				tr, cpu, &snapshot_raw_fops);
+		trace_create_cpu_file("snapshot_raw", TRACE_MODE_READ, d_cpu,
+				      tr, cpu, &snapshot_raw_fops);
+	}
 #endif
 }
 
@@ -9205,7 +9397,21 @@ allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size
 
 	buf->tr = tr;
 
-	buf->buffer = ring_buffer_alloc(size, rb_flags);
+	if (tr->range_addr_start && tr->range_addr_size) {
+		buf->buffer = ring_buffer_alloc_range(size, rb_flags, 0,
+						      tr->range_addr_start,
+						      tr->range_addr_size);
+
+		ring_buffer_last_boot_delta(buf->buffer,
+					    &tr->text_delta, &tr->data_delta);
+		/*
+		 * This is basically the same as a mapped buffer,
+		 * with the same restrictions.
+		 */
+		tr->mapped++;
+	} else {
+		buf->buffer = ring_buffer_alloc(size, rb_flags);
+	}
 	if (!buf->buffer)
 		return -ENOMEM;
 
@@ -9242,6 +9448,10 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 		return ret;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
+	/* Fix mapped buffer trace arrays do not have snapshot buffers */
+	if (tr->range_addr_start)
+		return 0;
+
 	ret = allocate_trace_buffer(tr, &tr->max_buffer,
 				    allocate_snapshot ? size : 1);
 	if (MEM_FAIL(ret, "Failed to allocate trace buffer\n")) {
@@ -9342,7 +9552,9 @@ static int trace_array_create_dir(struct trace_array *tr)
 }
 
 static struct trace_array *
-trace_array_create_systems(const char *name, const char *systems)
+trace_array_create_systems(const char *name, const char *systems,
+			   unsigned long range_addr_start,
+			   unsigned long range_addr_size)
 {
 	struct trace_array *tr;
 	int ret;
@@ -9368,6 +9580,10 @@ trace_array_create_systems(const char *name, const char *systems)
 			goto out_free_tr;
 	}
 
+	/* Only for boot up memory mapped ring buffers */
+	tr->range_addr_start = range_addr_start;
+	tr->range_addr_size = range_addr_size;
+
 	tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS;
 
 	cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
@@ -9425,7 +9641,7 @@ trace_array_create_systems(const char *name, const char *systems)
 
 static struct trace_array *trace_array_create(const char *name)
 {
-	return trace_array_create_systems(name, NULL);
+	return trace_array_create_systems(name, NULL, 0, 0);
 }
 
 static int instance_mkdir(const char *name)
@@ -9450,6 +9666,31 @@ out_unlock:
 	return ret;
 }
 
+static u64 map_pages(u64 start, u64 size)
+{
+	struct page **pages;
+	phys_addr_t page_start;
+	unsigned int page_count;
+	unsigned int i;
+	void *vaddr;
+
+	page_count = DIV_ROUND_UP(size, PAGE_SIZE);
+
+	page_start = start;
+	pages = kmalloc_array(page_count, sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		return 0;
+
+	for (i = 0; i < page_count; i++) {
+		phys_addr_t addr = page_start + i * PAGE_SIZE;
+		pages[i] = pfn_to_page(addr >> PAGE_SHIFT);
+	}
+	vaddr = vmap(pages, page_count, VM_MAP, PAGE_KERNEL);
+	kfree(pages);
+
+	return (u64)(unsigned long)vaddr;
+}
+
 /**
  * trace_array_get_by_name - Create/Lookup a trace array, given its name.
  * @name: The name of the trace array to be looked up/created.
@@ -9479,7 +9720,7 @@ struct trace_array *trace_array_get_by_name(const char *name, const char *system
 			goto out_unlock;
 	}
 
-	tr = trace_array_create_systems(name, systems);
+	tr = trace_array_create_systems(name, systems, 0, 0);
 
 	if (IS_ERR(tr))
 		tr = NULL;
@@ -9509,6 +9750,9 @@ static int __remove_instance(struct trace_array *tr)
 			set_tracer_flag(tr, 1 << i, 0);
 	}
 
+	if (printk_trace == tr)
+		update_printk_trace(&global_trace);
+
 	tracing_set_nop(tr);
 	clear_ftrace_function_probes(tr);
 	event_trace_del_tracer(tr);
@@ -9671,10 +9915,15 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	if (ftrace_create_function_files(tr, d_tracer))
 		MEM_FAIL(1, "Could not allocate function filter files");
 
+	if (tr->range_addr_start) {
+		trace_create_file("last_boot_info", TRACE_MODE_READ, d_tracer,
+				  tr, &last_boot_fops);
 #ifdef CONFIG_TRACER_SNAPSHOT
-	trace_create_file("snapshot", TRACE_MODE_WRITE, d_tracer,
-			  tr, &snapshot_fops);
+	} else {
+		trace_create_file("snapshot", TRACE_MODE_WRITE, d_tracer,
+				  tr, &snapshot_fops);
 #endif
+	}
 
 	trace_create_file("error_log", TRACE_MODE_WRITE, d_tracer,
 			  tr, &tracing_err_log_fops);
@@ -10294,6 +10543,7 @@ __init static void enable_instances(void)
 {
 	struct trace_array *tr;
 	char *curr_str;
+	char *name;
 	char *str;
 	char *tok;
 
@@ -10302,19 +10552,107 @@ __init static void enable_instances(void)
 	str = boot_instance_info;
 
 	while ((curr_str = strsep(&str, "\t"))) {
+		phys_addr_t start = 0;
+		phys_addr_t size = 0;
+		unsigned long addr = 0;
+		bool traceprintk = false;
+		bool traceoff = false;
+		char *flag_delim;
+		char *addr_delim;
 
 		tok = strsep(&curr_str, ",");
 
-		if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE))
-			do_allocate_snapshot(tok);
+		flag_delim = strchr(tok, '^');
+		addr_delim = strchr(tok, '@');
 
-		tr = trace_array_get_by_name(tok, NULL);
-		if (!tr) {
-			pr_warn("Failed to create instance buffer %s\n", curr_str);
+		if (addr_delim)
+			*addr_delim++ = '\0';
+
+		if (flag_delim)
+			*flag_delim++ = '\0';
+
+		name = tok;
+
+		if (flag_delim) {
+			char *flag;
+
+			while ((flag = strsep(&flag_delim, "^"))) {
+				if (strcmp(flag, "traceoff") == 0) {
+					traceoff = true;
+				} else if ((strcmp(flag, "printk") == 0) ||
+					   (strcmp(flag, "traceprintk") == 0) ||
+					   (strcmp(flag, "trace_printk") == 0)) {
+					traceprintk = true;
+				} else {
+					pr_info("Tracing: Invalid instance flag '%s' for %s\n",
+						flag, name);
+				}
+			}
+		}
+
+		tok = addr_delim;
+		if (tok && isdigit(*tok)) {
+			start = memparse(tok, &tok);
+			if (!start) {
+				pr_warn("Tracing: Invalid boot instance address for %s\n",
+					name);
+				continue;
+			}
+			if (*tok != ':') {
+				pr_warn("Tracing: No size specified for instance %s\n", name);
+				continue;
+			}
+			tok++;
+			size = memparse(tok, &tok);
+			if (!size) {
+				pr_warn("Tracing: Invalid boot instance size for %s\n",
+					name);
+				continue;
+			}
+		} else if (tok) {
+			if (!reserve_mem_find_by_name(tok, &start, &size)) {
+				start = 0;
+				pr_warn("Failed to map boot instance %s to %s\n", name, tok);
+				continue;
+			}
+		}
+
+		if (start) {
+			addr = map_pages(start, size);
+			if (addr) {
+				pr_info("Tracing: mapped boot instance %s at physical memory %pa of size 0x%lx\n",
+					name, &start, (unsigned long)size);
+			} else {
+				pr_warn("Tracing: Failed to map boot instance %s\n", name);
+				continue;
+			}
+		} else {
+			/* Only non mapped buffers have snapshot buffers */
+			if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE))
+				do_allocate_snapshot(name);
+		}
+
+		tr = trace_array_create_systems(name, NULL, addr, size);
+		if (IS_ERR(tr)) {
+			pr_warn("Tracing: Failed to create instance buffer %s\n", curr_str);
 			continue;
 		}
-		/* Allow user space to delete it */
-		trace_array_put(tr);
+
+		if (traceoff)
+			tracer_tracing_off(tr);
+
+		if (traceprintk)
+			update_printk_trace(tr);
+
+		/*
+		 * If start is set, then this is a mapped buffer, and
+		 * cannot be deleted by user space, so keep the reference
+		 * to it.
+		 */
+		if (start) {
+			tr->flags |= TRACE_ARRAY_FL_BOOT;
+			tr->ref++;
+		}
 
 		while ((tok = strsep(&curr_str, ","))) {
 			early_enable_events(tr, tok, true);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index bd3e3069300e..266740b4e121 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -46,6 +46,7 @@ enum trace_type {
 	TRACE_BRANCH,
 	TRACE_GRAPH_RET,
 	TRACE_GRAPH_ENT,
+	TRACE_GRAPH_RETADDR_ENT,
 	TRACE_USER_STACK,
 	TRACE_BLK,
 	TRACE_BPUTS,
@@ -336,7 +337,6 @@ struct trace_array {
 	bool			allocated_snapshot;
 	spinlock_t		snapshot_trigger_lock;
 	unsigned int		snapshot;
-	unsigned int		mapped;
 	unsigned long		max_latency;
 #ifdef CONFIG_FSNOTIFY
 	struct dentry		*d_max_latency;
@@ -344,6 +344,13 @@ struct trace_array {
 	struct irq_work		fsnotify_irqwork;
 #endif
 #endif
+	/* The below is for memory mapped ring buffer */
+	unsigned int		mapped;
+	unsigned long		range_addr_start;
+	unsigned long		range_addr_size;
+	long			text_delta;
+	long			data_delta;
+
 	struct trace_pid_list	__rcu *filtered_pids;
 	struct trace_pid_list	__rcu *filtered_no_pids;
 	/*
@@ -423,7 +430,8 @@ struct trace_array {
 };
 
 enum {
-	TRACE_ARRAY_FL_GLOBAL	= (1 << 0)
+	TRACE_ARRAY_FL_GLOBAL	= BIT(0),
+	TRACE_ARRAY_FL_BOOT	= BIT(1),
 };
 
 extern struct list_head ftrace_trace_arrays;
@@ -505,6 +513,8 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
 		IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry,	\
 			  TRACE_GRAPH_ENT);		\
+		IF_ASSIGN(var, ent, struct fgraph_retaddr_ent_entry,\
+			  TRACE_GRAPH_RETADDR_ENT);		\
 		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
 			  TRACE_GRAPH_RET);		\
 		IF_ASSIGN(var, ent, struct func_repeats_entry,		\
@@ -644,6 +654,8 @@ trace_buffer_lock_reserve(struct trace_buffer *buffer,
 			  unsigned long len,
 			  unsigned int trace_ctx);
 
+int ring_buffer_meta_seq_init(struct file *file, struct trace_buffer *buffer, int cpu);
+
 struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 						struct trace_array_cpu *data);
 
@@ -763,6 +775,8 @@ extern void trace_event_follow_fork(struct trace_array *tr, bool enable);
 extern unsigned long ftrace_update_tot_cnt;
 extern unsigned long ftrace_number_of_pages;
 extern unsigned long ftrace_number_of_groups;
+extern u64 ftrace_update_time;
+extern u64 ftrace_total_mod_time;
 void ftrace_init_trace_array(struct trace_array *tr);
 #else
 static inline void ftrace_init_trace_array(struct trace_array *tr) { }
@@ -870,6 +884,7 @@ static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash)
 #define TRACE_GRAPH_GRAPH_TIME          0x400
 #define TRACE_GRAPH_PRINT_RETVAL        0x800
 #define TRACE_GRAPH_PRINT_RETVAL_HEX    0x1000
+#define TRACE_GRAPH_PRINT_RETADDR       0x2000
 #define TRACE_GRAPH_PRINT_FILL_SHIFT	28
 #define TRACE_GRAPH_PRINT_FILL_MASK	(0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT)
 
@@ -891,6 +906,10 @@ extern void graph_trace_close(struct trace_iterator *iter);
 extern int __trace_graph_entry(struct trace_array *tr,
 			       struct ftrace_graph_ent *trace,
 			       unsigned int trace_ctx);
+extern int __trace_graph_retaddr_entry(struct trace_array *tr,
+				struct ftrace_graph_ent *trace,
+				unsigned int trace_ctx,
+				unsigned long retaddr);
 extern void __trace_graph_return(struct trace_array *tr,
 				 struct ftrace_graph_ret *trace,
 				 unsigned int trace_ctx);
@@ -1039,6 +1058,7 @@ static inline void ftrace_graph_addr_finish(struct fgraph_ops *gops, struct ftra
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 extern unsigned int fgraph_max_depth;
+extern bool fgraph_sleep_time;
 
 static inline bool
 ftrace_graph_ignore_func(struct fgraph_ops *gops, struct ftrace_graph_ent *trace)
@@ -1312,6 +1332,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		C(IRQ_INFO,		"irq-info"),		\
 		C(MARKERS,		"markers"),		\
 		C(EVENT_FORK,		"event-fork"),		\
+		C(TRACE_PRINTK,		"trace_printk_dest"),	\
 		C(PAUSE_ON_TRACE,	"pause-on-trace"),	\
 		C(HASH_PTR,		"hash-ptr"),	/* Print hashed pointer */ \
 		FUNCTION_FLAGS					\
@@ -1419,10 +1440,6 @@ struct trace_subsystem_dir {
 	int				nr_events;
 };
 
-extern int call_filter_check_discard(struct trace_event_call *call, void *rec,
-				     struct trace_buffer *buffer,
-				     struct ring_buffer_event *event);
-
 void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 				     struct trace_buffer *buffer,
 				     struct ring_buffer_event *event,
@@ -2166,4 +2183,11 @@ static inline int rv_init_interface(void)
 }
 #endif
 
+/*
+ * This is used only to distinguish
+ * function address from trampoline code.
+ * So this value has no meaning.
+ */
+#define FTRACE_TRAMPOLINE_MARKER  ((unsigned long) INT_MAX)
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index e47fdb4c92fb..6d08a5523ce0 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -30,7 +30,6 @@ static struct trace_array *branch_tracer;
 static void
 probe_likely_condition(struct ftrace_likely_data *f, int val, int expect)
 {
-	struct trace_event_call *call = &event_branch;
 	struct trace_array *tr = branch_tracer;
 	struct trace_buffer *buffer;
 	struct trace_array_cpu *data;
@@ -74,16 +73,13 @@ probe_likely_condition(struct ftrace_likely_data *f, int val, int expect)
 		p--;
 	p++;
 
-	strncpy(entry->func, f->data.func, TRACE_FUNC_SIZE);
-	strncpy(entry->file, p, TRACE_FILE_SIZE);
-	entry->func[TRACE_FUNC_SIZE] = 0;
-	entry->file[TRACE_FILE_SIZE] = 0;
+	strscpy(entry->func, f->data.func);
+	strscpy(entry->file, p);
 	entry->constant = f->constant;
 	entry->line = f->data.line;
 	entry->correct = val == expect;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 
  out:
 	current->trace_recursion &= ~TRACE_BRANCH_BIT;
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 4702efb00ff2..4cb2ebc439be 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -154,5 +154,5 @@ static atomic64_t trace_counter;
  */
 u64 notrace trace_clock_counter(void)
 {
-	return atomic64_add_return(1, &trace_counter);
+	return atomic64_inc_return(&trace_counter);
 }
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index c47422b20908..82fd174ebbe0 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -85,9 +85,35 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
 	F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth)
 );
 
-/* Function return entry */
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+
+/* Function call entry with a return address */
+FTRACE_ENTRY_PACKED(fgraph_retaddr_entry, fgraph_retaddr_ent_entry,
+
+	TRACE_GRAPH_RETADDR_ENT,
+
+	F_STRUCT(
+		__field_struct(	struct fgraph_retaddr_ent,	graph_ent	)
+		__field_packed(	unsigned long,	graph_ent,	func		)
+		__field_packed(	int,		graph_ent,	depth		)
+		__field_packed(	unsigned long,	graph_ent,	retaddr		)
+	),
+
+	F_printk("--> %ps (%d) <- %ps", (void *)__entry->func, __entry->depth,
+		(void *)__entry->retaddr)
+);
+
+#else
+
+#ifndef fgraph_retaddr_ent_entry
+#define fgraph_retaddr_ent_entry ftrace_graph_ent_entry
+#endif
+
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_RETVAL
 
+/* Function return entry */
 FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 	TRACE_GRAPH_RET,
@@ -110,6 +136,7 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 #else
 
+/* Function return entry */
 FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 	TRACE_GRAPH_RET,
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index b0e0ec85912e..be8be0c1aaf0 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -912,6 +912,11 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 		}
 	}
 
+	if (argc - 2 > MAX_TRACE_ARGS) {
+		ret = -E2BIG;
+		goto error;
+	}
+
 	mutex_lock(&event_mutex);
 	event_call = find_and_get_event(sys_name, sys_event);
 	ep = alloc_event_probe(group, event, event_call, argc - 2);
@@ -937,7 +942,7 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 
 	argc -= 2; argv += 2;
 	/* parse arguments */
-	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+	for (i = 0; i < argc; i++) {
 		trace_probe_log_set_index(i + 2);
 		ret = trace_eprobe_tp_update_arg(ep, argv, i);
 		if (ret)
@@ -958,6 +963,11 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 		goto error;
 	}
 	ret = dyn_event_add(&ep->devent, &ep->tp.event->call);
+	if (ret < 0) {
+		trace_probe_unregister_event_call(&ep->tp);
+		mutex_unlock(&event_mutex);
+		goto error;
+	}
 	mutex_unlock(&event_mutex);
 	return ret;
 parse_error:
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 05e791241812..3ff9caa4a71b 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -352,10 +352,16 @@ void perf_uprobe_destroy(struct perf_event *p_event)
 int perf_trace_add(struct perf_event *p_event, int flags)
 {
 	struct trace_event_call *tp_event = p_event->tp_event;
+	struct hw_perf_event *hwc = &p_event->hw;
 
 	if (!(flags & PERF_EF_START))
 		p_event->hw.state = PERF_HES_STOPPED;
 
+	if (is_sampling_event(p_event)) {
+		hwc->last_period = hwc->sample_period;
+		perf_swevent_set_period(p_event);
+	}
+
 	/*
 	 * If TRACE_REG_PERF_ADD returns false; no custom action was performed
 	 * and we need to take the default action of enqueueing our event on
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7266ec2a4eea..77e68efbd43e 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3149,8 +3149,6 @@ static void __trace_remove_event_call(struct trace_event_call *call)
 {
 	event_remove(call);
 	trace_destroy_fields(call);
-	free_event_filter(call->filter);
-	call->filter = NULL;
 }
 
 static int probe_remove_event_call(struct trace_event_call *call)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0c611b281a5b..78051de581e7 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1616,7 +1616,7 @@ static int parse_pred(const char *str, void *data,
 				goto err_free;
 			}
 
-			strncpy(num_buf, str + s, len);
+			memcpy(num_buf, str + s, len);
 			num_buf[len] = 0;
 
 			ret = kstrtoul(num_buf, 0, &ip);
@@ -1694,7 +1694,7 @@ static int parse_pred(const char *str, void *data,
 		if (!pred->regex)
 			goto err_mem;
 		pred->regex->len = len;
-		strncpy(pred->regex->pattern, str + s, len);
+		memcpy(pred->regex->pattern, str + s, len);
 		pred->regex->pattern[len] = 0;
 
 	} else if (!strncmp(str + i, "CPUS", 4)) {
@@ -1859,7 +1859,7 @@ static int parse_pred(const char *str, void *data,
 		if (!pred->regex)
 			goto err_mem;
 		pred->regex->len = len;
-		strncpy(pred->regex->pattern, str + s, len);
+		memcpy(pred->regex->pattern, str + s, len);
 		pred->regex->pattern[len] = 0;
 
 		filter_build_regex(pred);
@@ -1919,7 +1919,7 @@ static int parse_pred(const char *str, void *data,
 			goto err_free;
 		}
 
-		strncpy(num_buf, str + s, len);
+		memcpy(num_buf, str + s, len);
 		num_buf[len] = 0;
 
 		/* Make sure it is a value */
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 5f9119eb7c67..9c058aa8baf3 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -822,7 +822,7 @@ static inline void trace_synth(struct synth_event *event, u64 *var_ref_vals,
 {
 	struct tracepoint *tp = event->tp;
 
-	if (unlikely(atomic_read(&tp->key.enabled) > 0)) {
+	if (unlikely(static_key_enabled(&tp->key))) {
 		struct tracepoint_func *probe_func_ptr;
 		synth_probe_func_t probe_func;
 		void *__data;
@@ -1354,10 +1354,7 @@ static const char *hist_field_name(struct hist_field *field,
 	} else if (field->flags & HIST_FIELD_FL_TIMESTAMP)
 		field_name = "common_timestamp";
 	else if (field->flags & HIST_FIELD_FL_STACKTRACE) {
-		if (field->field)
-			field_name = field->field->name;
-		else
-			field_name = "common_stacktrace";
+		field_name = "common_stacktrace";
 	} else if (field->flags & HIST_FIELD_FL_HITCOUNT)
 		field_name = "hitcount";
 
@@ -1599,7 +1596,7 @@ static inline void save_comm(char *comm, struct task_struct *task)
 		return;
 	}
 
-	strncpy(comm, task->comm, TASK_COMM_LEN);
+	strscpy(comm, task->comm, TASK_COMM_LEN);
 }
 
 static void hist_elt_data_free(struct hist_elt_data *elt_data)
@@ -3405,7 +3402,7 @@ static bool cond_snapshot_update(struct trace_array *tr, void *cond_data)
 	elt_data = context->elt->private_data;
 	track_elt_data = track_data->elt.private_data;
 	if (elt_data->comm)
-		strncpy(track_elt_data->comm, elt_data->comm, TASK_COMM_LEN);
+		strscpy(track_elt_data->comm, elt_data->comm, TASK_COMM_LEN);
 
 	track_data->updated = true;
 
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 42b0d998d103..17bcad8f79de 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -1676,7 +1676,7 @@ static void update_enable_bit_for(struct user_event *user)
 	struct tracepoint *tp = &user->tracepoint;
 	char status = 0;
 
-	if (atomic_read(&tp->key.enabled) > 0) {
+	if (static_key_enabled(&tp->key)) {
 		struct tracepoint_func *probe_func_ptr;
 		user_event_func_t probe_func;
 
@@ -2280,7 +2280,7 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
 	 * It's possible key.enabled disables after this check, however
 	 * we don't mind if a few events are included in this condition.
 	 */
-	if (likely(atomic_read(&tp->key.enabled) > 0)) {
+	if (likely(static_key_enabled(&tp->key))) {
 		struct tracepoint_func *probe_func_ptr;
 		user_event_func_t probe_func;
 		struct iov_iter copy;
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 62e6a8f4aae9..c62d1629cffe 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -21,6 +21,7 @@
 #define FPROBE_EVENT_SYSTEM "fprobes"
 #define TRACEPOINT_EVENT_SYSTEM "tracepoints"
 #define RETHOOK_MAXACTIVE_MAX 4096
+#define TRACEPOINT_STUB ERR_PTR(-ENOENT)
 
 static int trace_fprobe_create(const char *raw_command);
 static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev);
@@ -385,6 +386,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 					       const char *event,
 					       const char *symbol,
 					       struct tracepoint *tpoint,
+					       struct module *mod,
 					       int maxactive,
 					       int nargs, bool is_return)
 {
@@ -405,6 +407,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 		tf->fp.entry_handler = fentry_dispatcher;
 
 	tf->tpoint = tpoint;
+	tf->mod = mod;
 	tf->fp.nr_maxactive = maxactive;
 
 	ret = trace_probe_init(&tf->tp, event, group, false, nargs);
@@ -672,6 +675,24 @@ static int unregister_fprobe_event(struct trace_fprobe *tf)
 	return trace_probe_unregister_event_call(&tf->tp);
 }
 
+static int __regsiter_tracepoint_fprobe(struct trace_fprobe *tf)
+{
+	struct tracepoint *tpoint = tf->tpoint;
+	unsigned long ip = (unsigned long)tpoint->probestub;
+	int ret;
+
+	/*
+	 * Here, we do 2 steps to enable fprobe on a tracepoint.
+	 * At first, put __probestub_##TP function on the tracepoint
+	 * and put a fprobe on the stub function.
+	 */
+	ret = tracepoint_probe_register_prio_may_exist(tpoint,
+				tpoint->probestub, NULL, 0);
+	if (ret < 0)
+		return ret;
+	return register_fprobe_ips(&tf->fp, &ip, 1);
+}
+
 /* Internal register function - just handle fprobe and flags */
 static int __register_trace_fprobe(struct trace_fprobe *tf)
 {
@@ -698,18 +719,12 @@ static int __register_trace_fprobe(struct trace_fprobe *tf)
 		tf->fp.flags |= FPROBE_FL_DISABLED;
 
 	if (trace_fprobe_is_tracepoint(tf)) {
-		struct tracepoint *tpoint = tf->tpoint;
-		unsigned long ip = (unsigned long)tpoint->probestub;
-		/*
-		 * Here, we do 2 steps to enable fprobe on a tracepoint.
-		 * At first, put __probestub_##TP function on the tracepoint
-		 * and put a fprobe on the stub function.
-		 */
-		ret = tracepoint_probe_register_prio_may_exist(tpoint,
-					tpoint->probestub, NULL, 0);
-		if (ret < 0)
-			return ret;
-		return register_fprobe_ips(&tf->fp, &ip, 1);
+
+		/* This tracepoint is not loaded yet */
+		if (tf->tpoint == TRACEPOINT_STUB)
+			return 0;
+
+		return __regsiter_tracepoint_fprobe(tf);
 	}
 
 	/* TODO: handle filter, nofilter or symbol list */
@@ -862,20 +877,106 @@ end:
 	return ret;
 }
 
+struct __find_tracepoint_cb_data {
+	const char *tp_name;
+	struct tracepoint *tpoint;
+	struct module *mod;
+};
+
+static void __find_tracepoint_module_cb(struct tracepoint *tp, struct module *mod, void *priv)
+{
+	struct __find_tracepoint_cb_data *data = priv;
+
+	if (!data->tpoint && !strcmp(data->tp_name, tp->name)) {
+		data->tpoint = tp;
+		if (!data->mod) {
+			data->mod = mod;
+			if (!try_module_get(data->mod)) {
+				data->tpoint = NULL;
+				data->mod = NULL;
+			}
+		}
+	}
+}
+
+static void __find_tracepoint_cb(struct tracepoint *tp, void *priv)
+{
+	struct __find_tracepoint_cb_data *data = priv;
+
+	if (!data->tpoint && !strcmp(data->tp_name, tp->name))
+		data->tpoint = tp;
+}
+
+/*
+ * Find a tracepoint from kernel and module. If the tracepoint is in a module,
+ * this increments the module refcount to prevent unloading until the
+ * trace_fprobe is registered to the list. After registering the trace_fprobe
+ * on the trace_fprobe list, the module refcount is decremented because
+ * tracepoint_probe_module_cb will handle it.
+ */
+static struct tracepoint *find_tracepoint(const char *tp_name,
+					  struct module **tp_mod)
+{
+	struct __find_tracepoint_cb_data data = {
+		.tp_name = tp_name,
+		.mod = NULL,
+	};
+
+	for_each_kernel_tracepoint(__find_tracepoint_cb, &data);
+
+	if (!data.tpoint && IS_ENABLED(CONFIG_MODULES)) {
+		for_each_module_tracepoint(__find_tracepoint_module_cb, &data);
+		*tp_mod = data.mod;
+	}
+
+	return data.tpoint;
+}
+
 #ifdef CONFIG_MODULES
+static void reenable_trace_fprobe(struct trace_fprobe *tf)
+{
+	struct trace_probe *tp = &tf->tp;
+
+	list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) {
+		__enable_trace_fprobe(tf);
+	}
+}
+
+static struct tracepoint *find_tracepoint_in_module(struct module *mod,
+						    const char *tp_name)
+{
+	struct __find_tracepoint_cb_data data = {
+		.tp_name = tp_name,
+		.mod = mod,
+	};
+
+	for_each_tracepoint_in_module(mod, __find_tracepoint_module_cb, &data);
+	return data.tpoint;
+}
+
 static int __tracepoint_probe_module_cb(struct notifier_block *self,
 					unsigned long val, void *data)
 {
 	struct tp_module *tp_mod = data;
+	struct tracepoint *tpoint;
 	struct trace_fprobe *tf;
 	struct dyn_event *pos;
 
-	if (val != MODULE_STATE_GOING)
+	if (val != MODULE_STATE_GOING && val != MODULE_STATE_COMING)
 		return NOTIFY_DONE;
 
 	mutex_lock(&event_mutex);
 	for_each_trace_fprobe(tf, pos) {
-		if (tp_mod->mod == tf->mod) {
+		if (val == MODULE_STATE_COMING && tf->tpoint == TRACEPOINT_STUB) {
+			tpoint = find_tracepoint_in_module(tp_mod->mod, tf->symbol);
+			if (tpoint) {
+				tf->tpoint = tpoint;
+				tf->mod = tp_mod->mod;
+				if (!WARN_ON_ONCE(__regsiter_tracepoint_fprobe(tf)) &&
+				    trace_probe_is_enabled(&tf->tp))
+					reenable_trace_fprobe(tf);
+			}
+		} else if (val == MODULE_STATE_GOING && tp_mod->mod == tf->mod) {
 			tracepoint_probe_unregister(tf->tpoint,
 					tf->tpoint->probestub, NULL);
 			tf->tpoint = NULL;
@@ -892,30 +993,6 @@ static struct notifier_block tracepoint_module_nb = {
 };
 #endif /* CONFIG_MODULES */
 
-struct __find_tracepoint_cb_data {
-	const char *tp_name;
-	struct tracepoint *tpoint;
-};
-
-static void __find_tracepoint_cb(struct tracepoint *tp, void *priv)
-{
-	struct __find_tracepoint_cb_data *data = priv;
-
-	if (!data->tpoint && !strcmp(data->tp_name, tp->name))
-		data->tpoint = tp;
-}
-
-static struct tracepoint *find_tracepoint(const char *tp_name)
-{
-	struct __find_tracepoint_cb_data data = {
-		.tp_name = tp_name,
-	};
-
-	for_each_kernel_tracepoint(__find_tracepoint_cb, &data);
-
-	return data.tpoint;
-}
-
 static int parse_symbol_and_return(int argc, const char *argv[],
 				   char **symbol, bool *is_return,
 				   bool is_tracepoint)
@@ -996,6 +1073,7 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	char abuf[MAX_BTF_ARGS_LEN];
 	char *dbuf = NULL;
 	bool is_tracepoint = false;
+	struct module *tp_mod = NULL;
 	struct tracepoint *tpoint = NULL;
 	struct traceprobe_parse_context ctx = {
 		.flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE,
@@ -1080,15 +1158,20 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 
 	if (is_tracepoint) {
 		ctx.flags |= TPARG_FL_TPOINT;
-		tpoint = find_tracepoint(symbol);
-		if (!tpoint) {
+		tpoint = find_tracepoint(symbol, &tp_mod);
+		if (tpoint) {
+			ctx.funcname = kallsyms_lookup(
+				(unsigned long)tpoint->probestub,
+				NULL, NULL, NULL, sbuf);
+		} else if (IS_ENABLED(CONFIG_MODULES)) {
+				/* This *may* be loaded afterwards */
+				tpoint = TRACEPOINT_STUB;
+				ctx.funcname = symbol;
+		} else {
 			trace_probe_log_set_index(1);
 			trace_probe_log_err(0, NO_TRACEPOINT);
 			goto parse_error;
 		}
-		ctx.funcname = kallsyms_lookup(
-				(unsigned long)tpoint->probestub,
-				NULL, NULL, NULL, sbuf);
 	} else
 		ctx.funcname = symbol;
 
@@ -1104,14 +1187,18 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 		argc = new_argc;
 		argv = new_argv;
 	}
+	if (argc > MAX_TRACE_ARGS) {
+		ret = -E2BIG;
+		goto out;
+	}
 
 	ret = traceprobe_expand_dentry_args(argc, argv, &dbuf);
 	if (ret)
 		goto out;
 
 	/* setup a probe */
-	tf = alloc_trace_fprobe(group, event, symbol, tpoint, maxactive,
-				argc, is_return);
+	tf = alloc_trace_fprobe(group, event, symbol, tpoint, tp_mod,
+				maxactive, argc, is_return);
 	if (IS_ERR(tf)) {
 		ret = PTR_ERR(tf);
 		/* This must return -ENOMEM, else there is a bug */
@@ -1119,12 +1206,8 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 		goto out;	/* We know tf is not allocated */
 	}
 
-	if (is_tracepoint)
-		tf->mod = __module_text_address(
-				(unsigned long)tf->tpoint->probestub);
-
 	/* parse arguments */
-	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+	for (i = 0; i < argc; i++) {
 		trace_probe_log_set_index(i + 2);
 		ctx.offset = 0;
 		ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], &ctx);
@@ -1155,6 +1238,8 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	}
 
 out:
+	if (tp_mod)
+		module_put(tp_mod);
 	traceprobe_finish_parse(&ctx);
 	trace_probe_log_clear();
 	kfree(new_argv);
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 3b0cea37e029..74c353164ca1 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -176,6 +176,27 @@ static void function_trace_start(struct trace_array *tr)
 	tracing_reset_online_cpus(&tr->array_buffer);
 }
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static __always_inline unsigned long
+function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs)
+{
+	unsigned long true_parent_ip;
+	int idx = 0;
+
+	true_parent_ip = parent_ip;
+	if (unlikely(parent_ip == (unsigned long)&return_to_handler) && fregs)
+		true_parent_ip = ftrace_graph_ret_addr(current, &idx, parent_ip,
+				(unsigned long *)ftrace_regs_get_stack_pointer(fregs));
+	return true_parent_ip;
+}
+#else
+static __always_inline unsigned long
+function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs)
+{
+	return parent_ip;
+}
+#endif
+
 static void
 function_trace_call(unsigned long ip, unsigned long parent_ip,
 		    struct ftrace_ops *op, struct ftrace_regs *fregs)
@@ -184,7 +205,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 	struct trace_array_cpu *data;
 	unsigned int trace_ctx;
 	int bit;
-	int cpu;
 
 	if (unlikely(!tr->function_enabled))
 		return;
@@ -193,10 +213,11 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (bit < 0)
 		return;
 
+	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
+
 	trace_ctx = tracing_gen_ctx();
 
-	cpu = smp_processor_id();
-	data = per_cpu_ptr(tr->array_buffer.data, cpu);
+	data = this_cpu_ptr(tr->array_buffer.data);
 	if (!atomic_read(&data->disabled))
 		trace_function(tr, ip, parent_ip, trace_ctx);
 
@@ -241,6 +262,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	 * recursive protection is performed.
 	 */
 	local_irq_save(flags);
+	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
 	disabled = atomic_inc_return(&data->disabled);
@@ -300,7 +322,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	unsigned int trace_ctx;
 	unsigned long flags;
 	int bit;
-	int cpu;
 
 	if (unlikely(!tr->function_enabled))
 		return;
@@ -309,8 +330,8 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (bit < 0)
 		return;
 
-	cpu = smp_processor_id();
-	data = per_cpu_ptr(tr->array_buffer.data, cpu);
+	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
+	data = this_cpu_ptr(tr->array_buffer.data);
 	if (atomic_read(&data->disabled))
 		goto out;
 
@@ -321,7 +342,7 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	 * TODO: think about a solution that is better than just hoping to be
 	 * lucky.
 	 */
-	last_info = per_cpu_ptr(tr->last_func_repeats, cpu);
+	last_info = this_cpu_ptr(tr->last_func_repeats);
 	if (is_repeat_check(tr, last_info, ip, parent_ip))
 		goto out;
 
@@ -356,6 +377,7 @@ function_stack_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	 * recursive protection is performed.
 	 */
 	local_irq_save(flags);
+	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
 	disabled = atomic_inc_return(&data->disabled);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 13d0387ac6a6..5504b5e4e7b4 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -31,7 +31,10 @@ struct fgraph_data {
 	struct fgraph_cpu_data __percpu *cpu_data;
 
 	/* Place to preserve last processed entry. */
-	struct ftrace_graph_ent_entry	ent;
+	union {
+		struct ftrace_graph_ent_entry	ent;
+		struct fgraph_retaddr_ent_entry	rent;
+	} ent;
 	struct ftrace_graph_ret_entry	ret;
 	int				failed;
 	int				cpu;
@@ -64,6 +67,10 @@ static struct tracer_opt trace_opts[] = {
 	/* Display function return value in hexadecimal format ? */
 	{ TRACER_OPT(funcgraph-retval-hex, TRACE_GRAPH_PRINT_RETVAL_HEX) },
 #endif
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+	/* Display function return address ? */
+	{ TRACER_OPT(funcgraph-retaddr, TRACE_GRAPH_PRINT_RETADDR) },
+#endif
 	/* Include sleep time (scheduled out) between entry and return */
 	{ TRACER_OPT(sleep-time, TRACE_GRAPH_SLEEP_TIME) },
 
@@ -83,6 +90,11 @@ static struct tracer_flags tracer_flags = {
 	.opts = trace_opts
 };
 
+static bool tracer_flags_is_set(u32 flags)
+{
+	return (tracer_flags.val & flags) == flags;
+}
+
 /*
  * DURATION column is being also used to display IRQ signs,
  * following values are used by print_graph_irq and others
@@ -102,7 +114,6 @@ int __trace_graph_entry(struct trace_array *tr,
 				struct ftrace_graph_ent *trace,
 				unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_funcgraph_entry;
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ftrace_graph_ent_entry *entry;
@@ -113,12 +124,43 @@ int __trace_graph_entry(struct trace_array *tr,
 		return 0;
 	entry	= ring_buffer_event_data(event);
 	entry->graph_ent			= *trace;
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 
 	return 1;
 }
 
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+int __trace_graph_retaddr_entry(struct trace_array *tr,
+				struct ftrace_graph_ent *trace,
+				unsigned int trace_ctx,
+				unsigned long retaddr)
+{
+	struct ring_buffer_event *event;
+	struct trace_buffer *buffer = tr->array_buffer.buffer;
+	struct fgraph_retaddr_ent_entry *entry;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RETADDR_ENT,
+					  sizeof(*entry), trace_ctx);
+	if (!event)
+		return 0;
+	entry	= ring_buffer_event_data(event);
+	entry->graph_ent.func = trace->func;
+	entry->graph_ent.depth = trace->depth;
+	entry->graph_ent.retaddr = retaddr;
+	trace_buffer_unlock_commit_nostack(buffer, event);
+
+	return 1;
+}
+#else
+int __trace_graph_retaddr_entry(struct trace_array *tr,
+				struct ftrace_graph_ent *trace,
+				unsigned int trace_ctx,
+				unsigned long retaddr)
+{
+	return 1;
+}
+#endif
+
 static inline int ftrace_graph_ignore_irqs(void)
 {
 	if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT))
@@ -127,12 +169,18 @@ static inline int ftrace_graph_ignore_irqs(void)
 	return in_hardirq();
 }
 
+struct fgraph_times {
+	unsigned long long		calltime;
+	unsigned long long		sleeptime; /* may be optional! */
+};
+
 int trace_graph_entry(struct ftrace_graph_ent *trace,
 		      struct fgraph_ops *gops)
 {
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
 	struct trace_array_cpu *data;
+	struct fgraph_times *ftimes;
 	unsigned long flags;
 	unsigned int trace_ctx;
 	long disabled;
@@ -167,6 +215,19 @@ int trace_graph_entry(struct ftrace_graph_ent *trace,
 	if (ftrace_graph_ignore_irqs())
 		return 0;
 
+	if (fgraph_sleep_time) {
+		/* Only need to record the calltime */
+		ftimes = fgraph_reserve_data(gops->idx, sizeof(ftimes->calltime));
+	} else {
+		ftimes = fgraph_reserve_data(gops->idx, sizeof(*ftimes));
+		if (ftimes)
+			ftimes->sleeptime = current->ftrace_sleeptime;
+	}
+	if (!ftimes)
+		return 0;
+
+	ftimes->calltime = trace_clock_local();
+
 	/*
 	 * Stop here if tracing_threshold is set. We only write function return
 	 * events to the ring buffer.
@@ -180,7 +241,13 @@ int trace_graph_entry(struct ftrace_graph_ent *trace,
 	disabled = atomic_inc_return(&data->disabled);
 	if (likely(disabled == 1)) {
 		trace_ctx = tracing_gen_ctx_flags(flags);
-		ret = __trace_graph_entry(tr, trace, trace_ctx);
+		if (unlikely(IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) &&
+			tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR))) {
+			unsigned long retaddr = ftrace_graph_top_ret_addr(current);
+
+			ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx, retaddr);
+		} else
+			ret = __trace_graph_entry(tr, trace, trace_ctx);
 	} else {
 		ret = 0;
 	}
@@ -223,7 +290,6 @@ void __trace_graph_return(struct trace_array *tr,
 				struct ftrace_graph_ret *trace,
 				unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_funcgraph_exit;
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ftrace_graph_ret_entry *entry;
@@ -234,8 +300,17 @@ void __trace_graph_return(struct trace_array *tr,
 		return;
 	entry	= ring_buffer_event_data(event);
 	entry->ret				= *trace;
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
+}
+
+static void handle_nosleeptime(struct ftrace_graph_ret *trace,
+			       struct fgraph_times *ftimes,
+			       int size)
+{
+	if (fgraph_sleep_time || size < sizeof(*ftimes))
+		return;
+
+	ftimes->calltime += current->ftrace_sleeptime - ftimes->sleeptime;
 }
 
 void trace_graph_return(struct ftrace_graph_ret *trace,
@@ -244,9 +319,11 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
 	struct trace_array_cpu *data;
+	struct fgraph_times *ftimes;
 	unsigned long flags;
 	unsigned int trace_ctx;
 	long disabled;
+	int size;
 	int cpu;
 
 	ftrace_graph_addr_finish(gops, trace);
@@ -256,6 +333,14 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 		return;
 	}
 
+	ftimes = fgraph_retrieve_data(gops->idx, &size);
+	if (!ftimes)
+		return;
+
+	handle_nosleeptime(trace, ftimes, size);
+
+	trace->calltime = ftimes->calltime;
+
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
@@ -271,6 +356,9 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 				      struct fgraph_ops *gops)
 {
+	struct fgraph_times *ftimes;
+	int size;
+
 	ftrace_graph_addr_finish(gops, trace);
 
 	if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) {
@@ -278,8 +366,16 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 		return;
 	}
 
+	ftimes = fgraph_retrieve_data(gops->idx, &size);
+	if (!ftimes)
+		return;
+
+	handle_nosleeptime(trace, ftimes, size);
+
+	trace->calltime = ftimes->calltime;
+
 	if (tracing_thresh &&
-	    (trace->rettime - trace->calltime < tracing_thresh))
+	    (trace->rettime - ftimes->calltime < tracing_thresh))
 		return;
 	else
 		trace_graph_return(trace, gops);
@@ -457,7 +553,7 @@ get_return_for_leaf(struct trace_iterator *iter,
 	 * then we just reuse the data from before.
 	 */
 	if (data && data->failed) {
-		curr = &data->ent;
+		curr = &data->ent.ent;
 		next = &data->ret;
 	} else {
 
@@ -487,7 +583,10 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * Save current and next entries for later reference
 			 * if the output fails.
 			 */
-			data->ent = *curr;
+			if (unlikely(curr->ent.type == TRACE_GRAPH_RETADDR_ENT))
+				data->ent.rent = *(struct fgraph_retaddr_ent_entry *)curr;
+			else
+				data->ent.ent = *curr;
 			/*
 			 * If the next event is not a return type, then
 			 * we only care about what type it is. Otherwise we can
@@ -544,6 +643,8 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *ent = iter->ent;
 
+	addr += iter->tr->text_delta;
+
 	if (addr < (unsigned long)__irqentry_text_start ||
 		addr >= (unsigned long)__irqentry_text_end)
 		return;
@@ -649,52 +750,96 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration,
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_RETVAL
-
 #define __TRACE_GRAPH_PRINT_RETVAL TRACE_GRAPH_PRINT_RETVAL
+#else
+#define __TRACE_GRAPH_PRINT_RETVAL 0
+#endif
 
-static void print_graph_retval(struct trace_seq *s, unsigned long retval,
-				bool leaf, void *func, bool hex_format)
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+#define __TRACE_GRAPH_PRINT_RETADDR TRACE_GRAPH_PRINT_RETADDR
+static void print_graph_retaddr(struct trace_seq *s, struct fgraph_retaddr_ent_entry *entry,
+				u32 trace_flags, bool comment)
+{
+	if (comment)
+		trace_seq_puts(s, " /*");
+
+	trace_seq_puts(s, " <-");
+	seq_print_ip_sym(s, entry->graph_ent.retaddr, trace_flags | TRACE_ITER_SYM_OFFSET);
+
+	if (comment)
+		trace_seq_puts(s, " */");
+}
+#else
+#define __TRACE_GRAPH_PRINT_RETADDR 0
+#define print_graph_retaddr(_seq, _entry, _tflags, _comment)		do { } while (0)
+#endif
+
+#if defined(CONFIG_FUNCTION_GRAPH_RETVAL) || defined(CONFIG_FUNCTION_GRAPH_RETADDR)
+
+static void print_graph_retval(struct trace_seq *s, struct ftrace_graph_ent_entry *entry,
+				struct ftrace_graph_ret *graph_ret, void *func,
+				u32 opt_flags, u32 trace_flags)
 {
 	unsigned long err_code = 0;
+	unsigned long retval = 0;
+	bool print_retaddr = false;
+	bool print_retval = false;
+	bool hex_format = !!(opt_flags & TRACE_GRAPH_PRINT_RETVAL_HEX);
 
-	if (retval == 0 || hex_format)
-		goto done;
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+	retval = graph_ret->retval;
+	print_retval = !!(opt_flags & TRACE_GRAPH_PRINT_RETVAL);
+#endif
 
-	/* Check if the return value matches the negative format */
-	if (IS_ENABLED(CONFIG_64BIT) && (retval & BIT(31)) &&
-		(((u64)retval) >> 32) == 0) {
-		/* sign extension */
-		err_code = (unsigned long)(s32)retval;
-	} else {
-		err_code = retval;
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+	print_retaddr = !!(opt_flags & TRACE_GRAPH_PRINT_RETADDR);
+#endif
+
+	if (print_retval && retval && !hex_format) {
+		/* Check if the return value matches the negative format */
+		if (IS_ENABLED(CONFIG_64BIT) && (retval & BIT(31)) &&
+			(((u64)retval) >> 32) == 0) {
+			err_code = sign_extend64(retval, 31);
+		} else {
+			err_code = retval;
+		}
+
+		if (!IS_ERR_VALUE(err_code))
+			err_code = 0;
 	}
 
-	if (!IS_ERR_VALUE(err_code))
-		err_code = 0;
+	if (entry) {
+		if (entry->ent.type != TRACE_GRAPH_RETADDR_ENT)
+			print_retaddr = false;
 
-done:
-	if (leaf) {
-		if (hex_format || (err_code == 0))
-			trace_seq_printf(s, "%ps(); /* = 0x%lx */\n",
-					func, retval);
+		trace_seq_printf(s, "%ps();", func);
+		if (print_retval || print_retaddr)
+			trace_seq_puts(s, " /*");
 		else
-			trace_seq_printf(s, "%ps(); /* = %ld */\n",
-					func, err_code);
+			trace_seq_putc(s, '\n');
 	} else {
+		print_retaddr = false;
+		trace_seq_printf(s, "} /* %ps", func);
+	}
+
+	if (print_retaddr)
+		print_graph_retaddr(s, (struct fgraph_retaddr_ent_entry *)entry,
+				    trace_flags, false);
+
+	if (print_retval) {
 		if (hex_format || (err_code == 0))
-			trace_seq_printf(s, "} /* %ps = 0x%lx */\n",
-					func, retval);
+			trace_seq_printf(s, " ret=0x%lx", retval);
 		else
-			trace_seq_printf(s, "} /* %ps = %ld */\n",
-					func, err_code);
+			trace_seq_printf(s, " ret=%ld", err_code);
 	}
+
+	if (!entry || print_retval || print_retaddr)
+		trace_seq_puts(s, " */\n");
 }
 
 #else
 
-#define __TRACE_GRAPH_PRINT_RETVAL 0
-
-#define print_graph_retval(_seq, _retval, _leaf, _func, _format) do {} while (0)
+#define print_graph_retval(_seq, _ent, _ret, _func, _opt_flags, _trace_flags) do {} while (0)
 
 #endif
 
@@ -710,6 +855,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 	struct ftrace_graph_ret *graph_ret;
 	struct ftrace_graph_ent *call;
 	unsigned long long duration;
+	unsigned long func;
 	int cpu = iter->cpu;
 	int i;
 
@@ -717,6 +863,8 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 	call = &entry->graph_ent;
 	duration = graph_ret->rettime - graph_ret->calltime;
 
+	func = call->func + iter->tr->text_delta;
+
 	if (data) {
 		struct fgraph_cpu_data *cpu_data;
 
@@ -743,14 +891,15 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 		trace_seq_putc(s, ' ');
 
 	/*
-	 * Write out the function return value if the option function-retval is
-	 * enabled.
+	 * Write out the function return value or return address
 	 */
-	if (flags & __TRACE_GRAPH_PRINT_RETVAL)
-		print_graph_retval(s, graph_ret->retval, true, (void *)call->func,
-				!!(flags & TRACE_GRAPH_PRINT_RETVAL_HEX));
-	else
-		trace_seq_printf(s, "%ps();\n", (void *)call->func);
+	if (flags & (__TRACE_GRAPH_PRINT_RETVAL | __TRACE_GRAPH_PRINT_RETADDR)) {
+		print_graph_retval(s, entry, graph_ret,
+				   (void *)graph_ret->func + iter->tr->text_delta,
+				   flags, tr->trace_flags);
+	} else {
+		trace_seq_printf(s, "%ps();\n", (void *)func);
+	}
 
 	print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
 			cpu, iter->ent->pid, flags);
@@ -766,6 +915,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
 	struct ftrace_graph_ent *call = &entry->graph_ent;
 	struct fgraph_data *data = iter->private;
 	struct trace_array *tr = iter->tr;
+	unsigned long func;
 	int i;
 
 	if (data) {
@@ -788,7 +938,14 @@ print_graph_entry_nested(struct trace_iterator *iter,
 	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++)
 		trace_seq_putc(s, ' ');
 
-	trace_seq_printf(s, "%ps() {\n", (void *)call->func);
+	func = call->func + iter->tr->text_delta;
+
+	trace_seq_printf(s, "%ps() {", (void *)func);
+	if (flags & __TRACE_GRAPH_PRINT_RETADDR  &&
+		entry->ent.type == TRACE_GRAPH_RETADDR_ENT)
+		print_graph_retaddr(s, (struct fgraph_retaddr_ent_entry *)entry,
+			tr->trace_flags, true);
+	trace_seq_putc(s, '\n');
 
 	if (trace_seq_has_overflowed(s))
 		return TRACE_TYPE_PARTIAL_LINE;
@@ -863,6 +1020,8 @@ check_irq_entry(struct trace_iterator *iter, u32 flags,
 	int *depth_irq;
 	struct fgraph_data *data = iter->private;
 
+	addr += iter->tr->text_delta;
+
 	/*
 	 * If we are either displaying irqs, or we got called as
 	 * a graph event and private data does not exist,
@@ -990,11 +1149,14 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 	unsigned long long duration = trace->rettime - trace->calltime;
 	struct fgraph_data *data = iter->private;
 	struct trace_array *tr = iter->tr;
+	unsigned long func;
 	pid_t pid = ent->pid;
 	int cpu = iter->cpu;
 	int func_match = 1;
 	int i;
 
+	func = trace->func + iter->tr->text_delta;
+
 	if (check_irq_return(iter, flags, trace->depth))
 		return TRACE_TYPE_HANDLED;
 
@@ -1030,11 +1192,10 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 
 	/*
 	 * Always write out the function name and its return value if the
-	 * function-retval option is enabled.
+	 * funcgraph-retval option is enabled.
 	 */
 	if (flags & __TRACE_GRAPH_PRINT_RETVAL) {
-		print_graph_retval(s, trace->retval, false, (void *)trace->func,
-			!!(flags & TRACE_GRAPH_PRINT_RETVAL_HEX));
+		print_graph_retval(s, NULL, trace, (void *)func, flags, tr->trace_flags);
 	} else {
 		/*
 		 * If the return function does not have a matching entry,
@@ -1046,7 +1207,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 		if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL))
 			trace_seq_puts(s, "}\n");
 		else
-			trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
+			trace_seq_printf(s, "} /* %ps */\n", (void *)func);
 	}
 
 	/* Overrun */
@@ -1149,7 +1310,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 	 * to print out the missing entry which would never go out.
 	 */
 	if (data && data->failed) {
-		field = &data->ent;
+		field = &data->ent.ent;
 		iter->cpu = data->cpu;
 		ret = print_graph_entry(field, s, iter, flags);
 		if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
@@ -1173,6 +1334,16 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 		saved = *field;
 		return print_graph_entry(&saved, s, iter, flags);
 	}
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+	case TRACE_GRAPH_RETADDR_ENT: {
+		struct fgraph_retaddr_ent_entry saved;
+		struct fgraph_retaddr_ent_entry *rfield;
+
+		trace_assign_type(rfield, entry);
+		saved = *rfield;
+		return print_graph_entry((struct ftrace_graph_ent_entry *)&saved, s, iter, flags);
+	}
+#endif
 	case TRACE_GRAPH_RET: {
 		struct ftrace_graph_ret_entry *field;
 		trace_assign_type(field, entry);
@@ -1367,6 +1538,13 @@ static struct trace_event graph_trace_entry_event = {
 	.funcs		= &graph_functions,
 };
 
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+static struct trace_event graph_trace_retaddr_entry_event = {
+	.type		= TRACE_GRAPH_RETADDR_ENT,
+	.funcs		= &graph_functions,
+};
+#endif
+
 static struct trace_event graph_trace_ret_event = {
 	.type		= TRACE_GRAPH_RET,
 	.funcs		= &graph_functions
@@ -1453,6 +1631,13 @@ static __init int init_graph_trace(void)
 		return 1;
 	}
 
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+	if (!register_trace_event(&graph_trace_retaddr_entry_event)) {
+		pr_warn("Warning: could not register graph trace retaddr events\n");
+		return 1;
+	}
+#endif
+
 	if (!register_trace_event(&graph_trace_ret_event)) {
 		pr_warn("Warning: could not register graph trace events\n");
 		return 1;
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index b791524a6536..b65353ec2837 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -130,7 +130,6 @@ static bool hwlat_busy;
 static void trace_hwlat_sample(struct hwlat_sample *sample)
 {
 	struct trace_array *tr = hwlat_trace;
-	struct trace_event_call *call = &event_hwlat;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct hwlat_entry *entry;
@@ -148,8 +147,7 @@ static void trace_hwlat_sample(struct hwlat_sample *sample)
 	entry->nmi_count		= sample->nmi_count;
 	entry->count			= sample->count;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
 /* Macros to encapsulate the time capturing infrastructure */
@@ -520,6 +518,8 @@ static void hwlat_hotplug_workfn(struct work_struct *dummy)
 	if (!hwlat_busy || hwlat_data.thread_mode != MODE_PER_CPU)
 		goto out_unlock;
 
+	if (!cpu_online(cpu))
+		goto out_unlock;
 	if (!cpumask_test_cpu(cpu, tr->tracing_cpumask))
 		goto out_unlock;
 
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 59857a1ee44c..1e72d20b3c2f 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -96,22 +96,19 @@ static int kdb_ftdump(int argc, const char **argv)
 {
 	int skip_entries = 0;
 	long cpu_file;
-	char *cp;
+	int err;
 	int cnt;
 	int cpu;
 
 	if (argc > 2)
 		return KDB_ARGCOUNT;
 
-	if (argc) {
-		skip_entries = simple_strtol(argv[1], &cp, 0);
-		if (*cp)
-			skip_entries = 0;
-	}
+	if (argc && kstrtoint(argv[1], 0, &skip_entries))
+		return KDB_BADINT;
 
 	if (argc == 2) {
-		cpu_file = simple_strtol(argv[2], &cp, 0);
-		if (*cp || cpu_file >= NR_CPUS || cpu_file < 0 ||
+		err = kstrtol(argv[2], 0, &cpu_file);
+		if (err || cpu_file >= NR_CPUS || cpu_file < 0 ||
 		    !cpu_online(cpu_file))
 			return KDB_BADINT;
 	} else {
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 61a6da808203..263fac44d3ca 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1013,6 +1013,10 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 		argc = new_argc;
 		argv = new_argv;
 	}
+	if (argc > MAX_TRACE_ARGS) {
+		ret = -E2BIG;
+		goto out;
+	}
 
 	ret = traceprobe_expand_dentry_args(argc, argv, &dbuf);
 	if (ret)
@@ -1029,7 +1033,7 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 	}
 
 	/* parse arguments */
-	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+	for (i = 0; i < argc; i++) {
 		trace_probe_log_set_index(i + 2);
 		ctx.offset = 0;
 		ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], &ctx);
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 64e77b513697..ba5858866b2f 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -294,7 +294,6 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 				struct trace_array_cpu *data,
 				struct mmiotrace_rw *rw)
 {
-	struct trace_event_call *call = &event_mmiotrace_rw;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_rw *entry;
@@ -310,8 +309,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 	entry	= ring_buffer_event_data(event);
 	entry->rw			= *rw;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
+	trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
 }
 
 void mmio_trace_rw(struct mmiotrace_rw *rw)
@@ -325,7 +323,6 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 				struct trace_array_cpu *data,
 				struct mmiotrace_map *map)
 {
-	struct trace_event_call *call = &event_mmiotrace_map;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_map *entry;
@@ -341,8 +338,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 	entry	= ring_buffer_event_data(event);
 	entry->map			= *map;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
+	trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
 }
 
 void mmio_trace_mapping(struct mmiotrace_map *map)
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 66a871553d4a..b9f96c77527d 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -228,6 +228,11 @@ static inline struct osnoise_variables *this_cpu_osn_var(void)
 	return this_cpu_ptr(&per_cpu_osnoise_var);
 }
 
+/*
+ * Protect the interface.
+ */
+static struct mutex interface_lock;
+
 #ifdef CONFIG_TIMERLAT_TRACER
 /*
  * Runtime information for the timer mode.
@@ -259,14 +264,20 @@ static inline void tlat_var_reset(void)
 {
 	struct timerlat_variables *tlat_var;
 	int cpu;
+
+	/* Synchronize with the timerlat interfaces */
+	mutex_lock(&interface_lock);
 	/*
 	 * So far, all the values are initialized as 0, so
 	 * zeroing the structure is perfect.
 	 */
 	for_each_cpu(cpu, cpu_online_mask) {
 		tlat_var = per_cpu_ptr(&per_cpu_timerlat_var, cpu);
+		if (tlat_var->kthread)
+			hrtimer_cancel(&tlat_var->timer);
 		memset(tlat_var, 0, sizeof(*tlat_var));
 	}
+	mutex_unlock(&interface_lock);
 }
 #else /* CONFIG_TIMERLAT_TRACER */
 #define tlat_var_reset()	do {} while (0)
@@ -332,11 +343,6 @@ struct timerlat_sample {
 #endif
 
 /*
- * Protect the interface.
- */
-static struct mutex interface_lock;
-
-/*
  * Tracer data.
  */
 static struct osnoise_data {
@@ -493,7 +499,6 @@ static void print_osnoise_headers(struct seq_file *s)
 static void
 __trace_osnoise_sample(struct osnoise_sample *sample, struct trace_buffer *buffer)
 {
-	struct trace_event_call *call = &event_osnoise;
 	struct ring_buffer_event *event;
 	struct osnoise_entry *entry;
 
@@ -511,8 +516,7 @@ __trace_osnoise_sample(struct osnoise_sample *sample, struct trace_buffer *buffe
 	entry->softirq_count	= sample->softirq_count;
 	entry->thread_count	= sample->thread_count;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
 /*
@@ -572,7 +576,6 @@ static void print_timerlat_headers(struct seq_file *s)
 static void
 __trace_timerlat_sample(struct timerlat_sample *sample, struct trace_buffer *buffer)
 {
-	struct trace_event_call *call = &event_osnoise;
 	struct ring_buffer_event *event;
 	struct timerlat_entry *entry;
 
@@ -585,8 +588,7 @@ __trace_timerlat_sample(struct timerlat_sample *sample, struct trace_buffer *buf
 	entry->context			= sample->context;
 	entry->timer_latency		= sample->timer_latency;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
 /*
@@ -648,7 +650,6 @@ static void timerlat_save_stack(int skip)
 static void
 __timerlat_dump_stack(struct trace_buffer *buffer, struct trace_stack *fstack, unsigned int size)
 {
-	struct trace_event_call *call = &event_osnoise;
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
 
@@ -662,8 +663,7 @@ __timerlat_dump_stack(struct trace_buffer *buffer, struct trace_stack *fstack, u
 	memcpy(&entry->caller, fstack->calls, size);
 	entry->size = fstack->nr_entries;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
 /*
@@ -1535,7 +1535,7 @@ static int run_osnoise(void)
 		 * This will eventually cause unwarranted noise as PREEMPT_RCU
 		 * will force preemption as the means of ending the current
 		 * grace period. We avoid this problem by calling
-		 * rcu_momentary_dyntick_idle(), which performs a zero duration
+		 * rcu_momentary_eqs(), which performs a zero duration
 		 * EQS allowing PREEMPT_RCU to end the current grace period.
 		 * This call shouldn't be wrapped inside an RCU critical
 		 * section.
@@ -1547,7 +1547,7 @@ static int run_osnoise(void)
 			if (!disable_irq)
 				local_irq_disable();
 
-			rcu_momentary_dyntick_idle();
+			rcu_momentary_eqs();
 
 			if (!disable_irq)
 				local_irq_enable();
@@ -1612,6 +1612,7 @@ out:
 
 static struct cpumask osnoise_cpumask;
 static struct cpumask save_cpumask;
+static struct cpumask kthread_cpumask;
 
 /*
  * osnoise_sleep - sleep until the next period
@@ -1675,6 +1676,7 @@ static inline int osnoise_migration_pending(void)
 	 */
 	mutex_lock(&interface_lock);
 	this_cpu_osn_var()->kthread = NULL;
+	cpumask_clear_cpu(smp_processor_id(), &kthread_cpumask);
 	mutex_unlock(&interface_lock);
 
 	return 1;
@@ -1945,11 +1947,12 @@ static void stop_kthread(unsigned int cpu)
 {
 	struct task_struct *kthread;
 
-	kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread;
+	kthread = xchg_relaxed(&(per_cpu(per_cpu_osnoise_var, cpu).kthread), NULL);
 	if (kthread) {
-		if (test_bit(OSN_WORKLOAD, &osnoise_options)) {
+		if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask) &&
+		    !WARN_ON(!test_bit(OSN_WORKLOAD, &osnoise_options))) {
 			kthread_stop(kthread);
-		} else {
+		} else if (!WARN_ON(test_bit(OSN_WORKLOAD, &osnoise_options))) {
 			/*
 			 * This is a user thread waiting on the timerlat_fd. We need
 			 * to close all users, and the best way to guarantee this is
@@ -1958,7 +1961,6 @@ static void stop_kthread(unsigned int cpu)
 			kill_pid(kthread->thread_pid, SIGKILL, 1);
 			put_task_struct(kthread);
 		}
-		per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
 	} else {
 		/* if no workload, just return */
 		if (!test_bit(OSN_WORKLOAD, &osnoise_options)) {
@@ -1967,7 +1969,6 @@ static void stop_kthread(unsigned int cpu)
 			 */
 			per_cpu(per_cpu_osnoise_var, cpu).sampling = false;
 			barrier();
-			return;
 		}
 	}
 }
@@ -1999,6 +2000,10 @@ static int start_kthread(unsigned int cpu)
 	void *main = osnoise_main;
 	char comm[24];
 
+	/* Do not start a new thread if it is already running */
+	if (per_cpu(per_cpu_osnoise_var, cpu).kthread)
+		return 0;
+
 	if (timerlat_enabled()) {
 		snprintf(comm, 24, "timerlat/%d", cpu);
 		main = timerlat_main;
@@ -2021,6 +2026,7 @@ static int start_kthread(unsigned int cpu)
 	}
 
 	per_cpu(per_cpu_osnoise_var, cpu).kthread = kthread;
+	cpumask_set_cpu(cpu, &kthread_cpumask);
 
 	return 0;
 }
@@ -2048,8 +2054,15 @@ static int start_per_cpu_kthreads(void)
 	 */
 	cpumask_and(current_mask, cpu_online_mask, &osnoise_cpumask);
 
-	for_each_possible_cpu(cpu)
-		per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
+	for_each_possible_cpu(cpu) {
+		if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask)) {
+			struct task_struct *kthread;
+
+			kthread = xchg_relaxed(&(per_cpu(per_cpu_osnoise_var, cpu).kthread), NULL);
+			if (!WARN_ON(!kthread))
+				kthread_stop(kthread);
+		}
+	}
 
 	for_each_cpu(cpu, current_mask) {
 		retval = start_kthread(cpu);
@@ -2078,6 +2091,8 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy)
 	mutex_lock(&interface_lock);
 	cpus_read_lock();
 
+	if (!cpu_online(cpu))
+		goto out_unlock;
 	if (!cpumask_test_cpu(cpu, &osnoise_cpumask))
 		goto out_unlock;
 
@@ -2579,7 +2594,8 @@ static int timerlat_fd_release(struct inode *inode, struct file *file)
 	osn_var = per_cpu_ptr(&per_cpu_osnoise_var, cpu);
 	tlat_var = per_cpu_ptr(&per_cpu_timerlat_var, cpu);
 
-	hrtimer_cancel(&tlat_var->timer);
+	if (tlat_var->kthread)
+		hrtimer_cancel(&tlat_var->timer);
 	memset(tlat_var, 0, sizeof(*tlat_var));
 
 	osn_var->sampling = 0;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index d8b302d01083..da748b7cbc4d 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -460,20 +460,31 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 		(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' :
 		'.';
 
-	switch (entry->flags & (TRACE_FLAG_NEED_RESCHED |
+	switch (entry->flags & (TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY |
 				TRACE_FLAG_PREEMPT_RESCHED)) {
+	case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED:
+		need_resched = 'B';
+		break;
 	case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_PREEMPT_RESCHED:
 		need_resched = 'N';
 		break;
+	case TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED:
+		need_resched = 'L';
+		break;
+	case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY:
+		need_resched = 'b';
+		break;
 	case TRACE_FLAG_NEED_RESCHED:
 		need_resched = 'n';
 		break;
 	case TRACE_FLAG_PREEMPT_RESCHED:
 		need_resched = 'p';
 		break;
+	case TRACE_FLAG_NEED_RESCHED_LAZY:
+		need_resched = 'l';
+		break;
 	default:
 		need_resched = '.';
 		break;
@@ -990,8 +1001,11 @@ enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags,
 }
 
 static void print_fn_trace(struct trace_seq *s, unsigned long ip,
-			   unsigned long parent_ip, int flags)
+			   unsigned long parent_ip, long delta, int flags)
 {
+	ip += delta;
+	parent_ip += delta;
+
 	seq_print_ip_sym(s, ip, flags);
 
 	if ((flags & TRACE_ITER_PRINT_PARENT) && parent_ip) {
@@ -1009,7 +1023,7 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, iter->ent);
 
-	print_fn_trace(s, field->ip, field->parent_ip, flags);
+	print_fn_trace(s, field->ip, field->parent_ip, iter->tr->text_delta, flags);
 	trace_seq_putc(s, '\n');
 
 	return trace_handle_return(s);
@@ -1230,6 +1244,7 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 	struct trace_seq *s = &iter->seq;
 	unsigned long *p;
 	unsigned long *end;
+	long delta = iter->tr->text_delta;
 
 	trace_assign_type(field, iter->ent);
 	end = (unsigned long *)((long)iter->ent + iter->ent_size);
@@ -1242,7 +1257,11 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 			break;
 
 		trace_seq_puts(s, " => ");
-		seq_print_ip_sym(s, *p, flags);
+		if ((*p) == FTRACE_TRAMPOLINE_MARKER) {
+			trace_seq_puts(s, "[FTRACE TRAMPOLINE]\n");
+			continue;
+		}
+		seq_print_ip_sym(s, (*p) + delta, flags);
 		trace_seq_putc(s, '\n');
 	}
 
@@ -1587,10 +1606,13 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
 {
 	struct print_entry *field;
 	struct trace_seq *s = &iter->seq;
+	unsigned long ip;
 
 	trace_assign_type(field, iter->ent);
 
-	seq_print_ip_sym(s, field->ip, flags);
+	ip = field->ip + iter->tr->text_delta;
+
+	seq_print_ip_sym(s, ip, flags);
 	trace_seq_printf(s, ": %s", field->buf);
 
 	return trace_handle_return(s);
@@ -1674,7 +1696,7 @@ trace_func_repeats_print(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, iter->ent);
 
-	print_fn_trace(s, field->ip, field->parent_ip, flags);
+	print_fn_trace(s, field->ip, field->parent_ip, iter->tr->text_delta, flags);
 	trace_seq_printf(s, " (repeats: %u, last_ts:", field->count);
 	trace_print_time(s, iter,
 			 iter->ts - FUNC_REPEATS_GET_DELTA_TS(field));
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index e37446f7916e..0c42b15c3800 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/ftrace.h>
 #include <linux/kprobes.h>
+#include <linux/hardirq.h>
 #include "trace.h"
 
 #define CREATE_TRACE_POINTS
@@ -20,13 +21,29 @@
  * tooling: these calls will only happen with RCU enabled, which can
  * use a regular tracepoint.
  *
- * On older architectures, use the rcuidle tracing methods (which
- * aren't NMI-safe - so exclude NMI contexts):
+ * On older architectures, RCU may not be watching in idle. In that
+ * case, wake up RCU to watch while calling the tracepoint. These
+ * aren't NMI-safe - so exclude NMI contexts:
  */
 #ifdef CONFIG_ARCH_WANTS_NO_INSTR
-#define trace(point)	trace_##point
+#define trace(point, args)	trace_##point(args)
 #else
-#define trace(point)	if (!in_nmi()) trace_##point##_rcuidle
+#define trace(point, args)					\
+	do {							\
+		if (trace_##point##_enabled()) {		\
+			bool exit_rcu = false;			\
+			if (in_nmi())				\
+				break;				\
+			if (!IS_ENABLED(CONFIG_TINY_RCU) &&	\
+			    is_idle_task(current)) {		\
+				ct_irq_enter();			\
+				exit_rcu = true;		\
+			}					\
+			trace_##point(args);			\
+			if (exit_rcu)				\
+				ct_irq_exit();			\
+		}						\
+	} while (0)
 #endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -42,7 +59,7 @@ static DEFINE_PER_CPU(int, tracing_irq_cpu);
 void trace_hardirqs_on_prepare(void)
 {
 	if (this_cpu_read(tracing_irq_cpu)) {
-		trace(irq_enable)(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_enable, TP_ARGS(CALLER_ADDR0, CALLER_ADDR1));
 		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
@@ -53,7 +70,7 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_prepare);
 void trace_hardirqs_on(void)
 {
 	if (this_cpu_read(tracing_irq_cpu)) {
-		trace(irq_enable)(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_enable, TP_ARGS(CALLER_ADDR0, CALLER_ADDR1));
 		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
@@ -75,7 +92,7 @@ void trace_hardirqs_off_finish(void)
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
-		trace(irq_disable)(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_disable, TP_ARGS(CALLER_ADDR0, CALLER_ADDR1));
 	}
 
 }
@@ -89,7 +106,7 @@ void trace_hardirqs_off(void)
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
-		trace(irq_disable)(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_disable, TP_ARGS(CALLER_ADDR0, CALLER_ADDR1));
 	}
 }
 EXPORT_SYMBOL(trace_hardirqs_off);
@@ -100,13 +117,13 @@ NOKPROBE_SYMBOL(trace_hardirqs_off);
 
 void trace_preempt_on(unsigned long a0, unsigned long a1)
 {
-	trace(preempt_enable)(a0, a1);
+	trace(preempt_enable, TP_ARGS(a0, a1));
 	tracer_preempt_on(a0, a1);
 }
 
 void trace_preempt_off(unsigned long a0, unsigned long a1)
 {
-	trace(preempt_disable)(a0, a1);
+	trace(preempt_disable, TP_ARGS(a0, a1));
 	tracer_preempt_off(a0, a1);
 }
 #endif
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 39877c80d6cb..16a5e368e7b7 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -276,7 +276,7 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
 		}
 		trace_probe_log_err(offset, NO_EVENT_NAME);
 		return -EINVAL;
-	} else if (len > MAX_EVENT_NAME_LEN) {
+	} else if (len >= MAX_EVENT_NAME_LEN) {
 		trace_probe_log_err(offset, EVENT_TOO_LONG);
 		return -EINVAL;
 	}
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 8a407adb0e1c..573b5d8e8a28 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -187,7 +187,7 @@ static inline char *get_saved_cmdlines(int idx)
 
 static inline void set_cmdline(int idx, const char *cmdline)
 {
-	strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
+	strscpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
 }
 
 static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 130ca7e7787e..d6c7f18daa15 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -378,7 +378,6 @@ tracing_sched_switch_trace(struct trace_array *tr,
 			   struct task_struct *next,
 			   unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_context_switch;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
@@ -396,8 +395,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_state		= task_state_index(next);
 	entry->next_cpu	= task_cpu(next);
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
+	trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
 }
 
 static void
@@ -406,7 +404,6 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 			   struct task_struct *curr,
 			   unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_wakeup;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
@@ -424,8 +421,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_state		= task_state_index(wakee);
 	entry->next_cpu			= task_cpu(wakee);
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
+	trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
 }
 
 static void notrace
@@ -547,7 +543,7 @@ probe_wakeup(void *ignore, struct task_struct *p)
 	 *  - wakeup_dl handles tasks belonging to sched_dl class only.
 	 */
 	if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
-	    (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+	    (wakeup_rt && !rt_or_dl_task(p)) ||
 	    (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
 		return;
 
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 97f1e4bc47dc..38b5754790c9 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -17,6 +17,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_PRINT:
 	case TRACE_BRANCH:
 	case TRACE_GRAPH_ENT:
+	case TRACE_GRAPH_RETADDR_ENT:
 	case TRACE_GRAPH_RET:
 		return 1;
 	}
@@ -942,7 +943,7 @@ static __init int test_graph_storage_multi(void)
 {
 	struct fgraph_fixture *fixture;
 	bool printed = false;
-	int i, ret;
+	int i, j, ret;
 
 	pr_cont("PASSED\n");
 	pr_info("Testing multiple fgraph storage on a function: ");
@@ -953,22 +954,35 @@ static __init int test_graph_storage_multi(void)
 		if (ret && ret != -ENODEV) {
 			pr_cont("*Could not set filter* ");
 			printed = true;
-			goto out;
+			goto out2;
 		}
+	}
 
+	for (j = 0; j < ARRAY_SIZE(store_bytes); j++) {
+		fixture = &store_bytes[j];
 		ret = register_ftrace_graph(&fixture->gops);
 		if (ret) {
 			pr_warn("Failed to init store_bytes fgraph tracing\n");
 			printed = true;
-			goto out;
+			goto out1;
 		}
 	}
 
 	DYN_FTRACE_TEST_NAME();
-out:
+out1:
+	while (--j >= 0) {
+		fixture = &store_bytes[j];
+		unregister_ftrace_graph(&fixture->gops);
+
+		if (fixture->error_str && !printed) {
+			pr_cont("*** %s ***", fixture->error_str);
+			printed = true;
+		}
+	}
+out2:
 	while (--i >= 0) {
 		fixture = &store_bytes[i];
-		unregister_ftrace_graph(&fixture->gops);
+		ftrace_free_filter(&fixture->gops.ops);
 
 		if (fixture->error_str && !printed) {
 			pr_cont("*** %s ***", fixture->error_str);
@@ -1472,7 +1486,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	/* reset the max latency */
 	tr->max_latency = 0;
 
-	while (p->on_rq) {
+	while (task_is_runnable(p)) {
 		/*
 		 * Sleep to make sure the -deadline thread is asleep too.
 		 * On virtual machines we can't rely on timings,
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 9c581d6da843..46aab0ab9350 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -299,6 +299,13 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	int syscall_nr;
 	int size;
 
+	/*
+	 * Syscall probe called with preemption enabled, but the ring
+	 * buffer and per-cpu data require preemption to be disabled.
+	 */
+	might_fault();
+	guard(preempt_notrace)();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
@@ -338,6 +345,13 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	struct trace_event_buffer fbuffer;
 	int syscall_nr;
 
+	/*
+	 * Syscall probe called with preemption enabled, but the ring
+	 * buffer and per-cpu data require preemption to be disabled.
+	 */
+	might_fault();
+	guard(preempt_notrace)();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
@@ -564,6 +578,7 @@ static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *re
 	BUILD_BUG_ON(sizeof(param.ent) < sizeof(void *));
 
 	/* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
+	perf_fetch_caller_regs(regs);
 	*(struct pt_regs **)&param = regs;
 	param.syscall_nr = rec->nr;
 	for (i = 0; i < sys_data->nb_args; i++)
@@ -575,6 +590,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
+	struct pt_regs *fake_regs;
 	struct hlist_head *head;
 	unsigned long args[6];
 	bool valid_prog_array;
@@ -582,6 +598,13 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int rctx;
 	int size;
 
+	/*
+	 * Syscall probe called with preemption enabled, but the ring
+	 * buffer and per-cpu data require preemption to be disabled.
+	 */
+	might_fault();
+	guard(preempt_notrace)();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
@@ -602,7 +625,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	size = ALIGN(size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	rec = perf_trace_buf_alloc(size, NULL, &rctx);
+	rec = perf_trace_buf_alloc(size, &fake_regs, &rctx);
 	if (!rec)
 		return;
 
@@ -611,7 +634,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
 	if ((valid_prog_array &&
-	     !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
+	     !perf_call_bpf_enter(sys_data->enter_event, fake_regs, sys_data, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
 		return;
@@ -666,6 +689,7 @@ static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *reg
 	} __aligned(8) param;
 
 	/* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
+	perf_fetch_caller_regs(regs);
 	*(struct pt_regs **)&param = regs;
 	param.syscall_nr = rec->nr;
 	param.ret = rec->ret;
@@ -676,12 +700,20 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_exit *rec;
+	struct pt_regs *fake_regs;
 	struct hlist_head *head;
 	bool valid_prog_array;
 	int syscall_nr;
 	int rctx;
 	int size;
 
+	/*
+	 * Syscall probe called with preemption enabled, but the ring
+	 * buffer and per-cpu data require preemption to be disabled.
+	 */
+	might_fault();
+	guard(preempt_notrace)();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
@@ -701,7 +733,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	rec = perf_trace_buf_alloc(size, NULL, &rctx);
+	rec = perf_trace_buf_alloc(size, &fake_regs, &rctx);
 	if (!rec)
 		return;
 
@@ -709,7 +741,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	rec->ret = syscall_get_return_value(current, regs);
 
 	if ((valid_prog_array &&
-	     !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) ||
+	     !perf_call_bpf_exit(sys_data->exit_event, fake_regs, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
 		return;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index c98e3b3386ba..4875e7f5de3d 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -17,6 +17,7 @@
 #include <linux/string.h>
 #include <linux/rculist.h>
 #include <linux/filter.h>
+#include <linux/percpu.h>
 
 #include "trace_dynevent.h"
 #include "trace_probe.h"
@@ -58,11 +59,11 @@ struct trace_uprobe {
 	struct dyn_event		devent;
 	struct uprobe_consumer		consumer;
 	struct path			path;
-	struct inode			*inode;
 	char				*filename;
+	struct uprobe			*uprobe;
 	unsigned long			offset;
 	unsigned long			ref_ctr_offset;
-	unsigned long			nhit;
+	unsigned long __percpu		*nhits;
 	struct trace_probe		tp;
 };
 
@@ -88,9 +89,11 @@ static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev)
 static int register_uprobe_event(struct trace_uprobe *tu);
 static int unregister_uprobe_event(struct trace_uprobe *tu);
 
-static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
+static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs,
+			     __u64 *data);
 static int uretprobe_dispatcher(struct uprobe_consumer *con,
-				unsigned long func, struct pt_regs *regs);
+				unsigned long func, struct pt_regs *regs,
+				__u64 *data);
 
 #ifdef CONFIG_STACK_GROWSUP
 static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
@@ -337,6 +340,12 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 	if (!tu)
 		return ERR_PTR(-ENOMEM);
 
+	tu->nhits = alloc_percpu(unsigned long);
+	if (!tu->nhits) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
 	ret = trace_probe_init(&tu->tp, event, group, true, nargs);
 	if (ret < 0)
 		goto error;
@@ -349,6 +358,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 	return tu;
 
 error:
+	free_percpu(tu->nhits);
 	kfree(tu);
 
 	return ERR_PTR(ret);
@@ -362,6 +372,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
 	path_put(&tu->path);
 	trace_probe_cleanup(&tu->tp);
 	kfree(tu->filename);
+	free_percpu(tu->nhits);
 	kfree(tu);
 }
 
@@ -556,6 +567,8 @@ static int __trace_uprobe_create(int argc, const char **argv)
 
 	if (argc < 2)
 		return -ECANCELED;
+	if (argc - 2 > MAX_TRACE_ARGS)
+		return -E2BIG;
 
 	if (argv[0][1] == ':')
 		event = &argv[0][2];
@@ -681,7 +694,7 @@ static int __trace_uprobe_create(int argc, const char **argv)
 	tu->filename = filename;
 
 	/* parse arguments */
-	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+	for (i = 0; i < argc; i++) {
 		struct traceprobe_parse_context ctx = {
 			.flags = (is_return ? TPARG_FL_RETURN : 0) | TPARG_FL_USER,
 		};
@@ -815,13 +828,21 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
 {
 	struct dyn_event *ev = v;
 	struct trace_uprobe *tu;
+	unsigned long nhits;
+	int cpu;
 
 	if (!is_trace_uprobe(ev))
 		return 0;
 
 	tu = to_trace_uprobe(ev);
+
+	nhits = 0;
+	for_each_possible_cpu(cpu) {
+		nhits += per_cpu(*tu->nhits, cpu);
+	}
+
 	seq_printf(m, "  %s %-44s %15lu\n", tu->filename,
-			trace_probe_name(&tu->tp), tu->nhit);
+		   trace_probe_name(&tu->tp), nhits);
 	return 0;
 }
 
@@ -858,6 +879,7 @@ struct uprobe_cpu_buffer {
 };
 static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer;
 static int uprobe_buffer_refcnt;
+#define MAX_UCB_BUFFER_SIZE PAGE_SIZE
 
 static int uprobe_buffer_init(void)
 {
@@ -962,6 +984,11 @@ static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu,
 	ucb = uprobe_buffer_get();
 	ucb->dsize = tu->tp.size + dsize;
 
+	if (WARN_ON_ONCE(ucb->dsize > MAX_UCB_BUFFER_SIZE)) {
+		ucb->dsize = MAX_UCB_BUFFER_SIZE;
+		dsize = MAX_UCB_BUFFER_SIZE - tu->tp.size;
+	}
+
 	store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize);
 
 	*ucbp = ucb;
@@ -981,9 +1008,6 @@ static void __uprobe_trace_func(struct trace_uprobe *tu,
 
 	WARN_ON(call != trace_file->event_call);
 
-	if (WARN_ON_ONCE(ucb->dsize > PAGE_SIZE))
-		return;
-
 	if (trace_trigger_soft_disabled(trace_file))
 		return;
 
@@ -1078,43 +1102,40 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e
 	return trace_handle_return(s);
 }
 
-typedef bool (*filter_func_t)(struct uprobe_consumer *self,
-				enum uprobe_filter_ctx ctx,
-				struct mm_struct *mm);
+typedef bool (*filter_func_t)(struct uprobe_consumer *self, struct mm_struct *mm);
 
 static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter)
 {
-	int ret;
+	struct inode *inode = d_real_inode(tu->path.dentry);
+	struct uprobe *uprobe;
 
 	tu->consumer.filter = filter;
-	tu->inode = d_real_inode(tu->path.dentry);
-
-	if (tu->ref_ctr_offset)
-		ret = uprobe_register_refctr(tu->inode, tu->offset,
-				tu->ref_ctr_offset, &tu->consumer);
-	else
-		ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
+	uprobe = uprobe_register(inode, tu->offset, tu->ref_ctr_offset, &tu->consumer);
+	if (IS_ERR(uprobe))
+		return PTR_ERR(uprobe);
 
-	if (ret)
-		tu->inode = NULL;
-
-	return ret;
+	tu->uprobe = uprobe;
+	return 0;
 }
 
 static void __probe_event_disable(struct trace_probe *tp)
 {
 	struct trace_uprobe *tu;
+	bool sync = false;
 
 	tu = container_of(tp, struct trace_uprobe, tp);
 	WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter));
 
 	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
-		if (!tu->inode)
+		if (!tu->uprobe)
 			continue;
 
-		uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
-		tu->inode = NULL;
+		uprobe_unregister_nosync(tu->uprobe, &tu->consumer);
+		sync = true;
+		tu->uprobe = NULL;
 	}
+	if (sync)
+		uprobe_unregister_sync();
 }
 
 static int probe_event_enable(struct trace_event_call *call,
@@ -1310,7 +1331,7 @@ static int uprobe_perf_close(struct trace_event_call *call,
 		return 0;
 
 	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
-		ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
+		ret = uprobe_apply(tu->uprobe, &tu->consumer, false);
 		if (ret)
 			break;
 	}
@@ -1334,7 +1355,7 @@ static int uprobe_perf_open(struct trace_event_call *call,
 		return 0;
 
 	list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) {
-		err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+		err = uprobe_apply(tu->uprobe, &tu->consumer, true);
 		if (err) {
 			uprobe_perf_close(call, event);
 			break;
@@ -1344,8 +1365,7 @@ static int uprobe_perf_open(struct trace_event_call *call,
 	return err;
 }
 
-static bool uprobe_perf_filter(struct uprobe_consumer *uc,
-				enum uprobe_filter_ctx ctx, struct mm_struct *mm)
+static bool uprobe_perf_filter(struct uprobe_consumer *uc, struct mm_struct *mm)
 {
 	struct trace_uprobe_filter *filter;
 	struct trace_uprobe *tu;
@@ -1382,9 +1402,13 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 
 #ifdef CONFIG_BPF_EVENTS
 	if (bpf_prog_array_valid(call)) {
+		const struct bpf_prog_array *array;
 		u32 ret;
 
-		ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run);
+		rcu_read_lock_trace();
+		array = rcu_dereference_check(call->prog_array, rcu_read_lock_trace_held());
+		ret = bpf_prog_run_array_uprobe(array, regs, bpf_prog_run);
+		rcu_read_unlock_trace();
 		if (!ret)
 			return;
 	}
@@ -1431,7 +1455,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs,
 			    struct uprobe_cpu_buffer **ucbp)
 {
-	if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
+	if (!uprobe_perf_filter(&tu->consumer, current->mm))
 		return UPROBE_HANDLER_REMOVE;
 
 	if (!is_ret_probe(tu))
@@ -1504,7 +1528,8 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type,
 	}
 }
 
-static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
+static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs,
+			     __u64 *data)
 {
 	struct trace_uprobe *tu;
 	struct uprobe_dispatch_data udd;
@@ -1512,7 +1537,8 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 	int ret = 0;
 
 	tu = container_of(con, struct trace_uprobe, consumer);
-	tu->nhit++;
+
+	this_cpu_inc(*tu->nhits);
 
 	udd.tu = tu;
 	udd.bp_addr = instruction_pointer(regs);
@@ -1534,7 +1560,8 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 }
 
 static int uretprobe_dispatcher(struct uprobe_consumer *con,
-				unsigned long func, struct pt_regs *regs)
+				unsigned long func, struct pt_regs *regs,
+				__u64 *data)
 {
 	struct trace_uprobe *tu;
 	struct uprobe_dispatch_data udd;
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 3a56e7c8aa4f..1921ade45be3 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -845,15 +845,11 @@ int tracing_map_init(struct tracing_map *map)
 static int cmp_entries_dup(const void *A, const void *B)
 {
 	const struct tracing_map_sort_entry *a, *b;
-	int ret = 0;
 
 	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;
+	return memcmp(a->key, b->key, a->elt->map->key_size);
 }
 
 static int cmp_entries_sum(const void *A, const void *B)