Merge tag 'trace-v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:

 - Addition of faultable tracepoints

   There's a tracepoint attached to both a system call entry and exit.
   This location is known to allow page faults. The tracepoints are
   called under an rcu_read_lock() which does not allow faults that can
   sleep. This limits the ability of tracepoint handlers to page fault
   in user space system call parameters. Now these tracepoints have been
   made "faultable", allowing the callbacks to fault in user space
   parameters and record them.

   Note, only the infrastructure has been implemented. The consumers
   (perf, ftrace, BPF) now need to have their code modified to allow
   faults.

 - Fix up of BPF code for the tracepoint faultable logic

 - Update tracepoints to use the new static branch API

 - Remove trace_*_rcuidle() variants and the SRCU protection they used

 - Remove unused TRACE_EVENT_FL_FILTERED logic

 - Replace strncpy() with strscpy() and memcpy()

 - Use replace per_cpu_ptr(smp_processor_id()) with this_cpu_ptr()

 - Fix perf events to not duplicate samples when tracing is enabled

 - Replace atomic64_add_return(1, counter) with
   atomic64_inc_return(counter)

 - Make stack trace buffer 4K instead of PAGE_SIZE

 - Remove TRACE_FLAG_IRQS_NOSUPPORT flag as it was never used

 - Get the true return address for function tracer when function graph
   tracer is also running.

   When function_graph trace is running along with function tracer, the
   parent function of the function tracer sometimes is
   "return_to_handler", which is the function graph trampoline to record
   the exit of the function. Use existing logic that calls into the
   fgraph infrastructure to find the real return address.

 - Remove (un)regfunc pointers out of tracepoint structure

 - Added last minute bug fix for setting pending modules in stack
   function filter.

     echo "write*:mod:ext3" > /sys/kernel/tracing/stack_trace_filter

   Would cause a kernel NULL dereference.

 - Minor clean ups

* tag 'trace-v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (31 commits)
  ftrace: Fix regression with module command in stack_trace_filter
  tracing: Fix function name for trampoline
  ftrace: Get the true parent ip for function tracer
  tracing: Remove redundant check on field->field in histograms
  bpf: ensure RCU Tasks Trace GP for sleepable raw tracepoint BPF links
  bpf: decouple BPF link/attach hook and BPF program sleepable semantics
  bpf: put bpf_link's program when link is safe to be deallocated
  tracing: Replace strncpy() with strscpy() when copying comm
  tracing: Add might_fault() check in __DECLARE_TRACE_SYSCALL
  tracing: Fix syscall tracepoint use-after-free
  tracing: Introduce tracepoint_is_faultable()
  tracing: Introduce tracepoint extended structure
  tracing: Remove TRACE_FLAG_IRQS_NOSUPPORT
  tracing: Replace multiple deprecated strncpy with memcpy
  tracing: Make percpu stack trace buffer invariant to PAGE_SIZE
  tracing: Use atomic64_inc_return() in trace_clock_counter()
  trace/trace_event_perf: remove duplicate samples on the first tracepoint event
  tracing/bpf: Add might_fault check to syscall probes
  tracing/perf: Add might_fault check to syscall probes
  tracing/ftrace: Add might_fault check to syscall probes
  ...

22 files changed, 207 insertions, 210 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 58190ca724a2..5684e8ce132d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -35,6 +35,7 @@
 #include <linux/rcupdate_trace.h>
 #include <linux/memcontrol.h>
 #include <linux/trace_events.h>
+#include <linux/tracepoint.h>
 
 #include <net/netfilter/nf_bpf_link.h>
 #include <net/netkit.h>
@@ -3033,17 +3034,33 @@ static int bpf_obj_get(const union bpf_attr *attr)
 				attr->file_flags);
 }
 
-void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
-		   const struct bpf_link_ops *ops, struct bpf_prog *prog)
+/* bpf_link_init_sleepable() allows to specify whether BPF link itself has
+ * "sleepable" semantics, which normally would mean that BPF link's attach
+ * hook can dereference link or link's underlying program for some time after
+ * detachment due to RCU Tasks Trace-based lifetime protection scheme.
+ * BPF program itself can be non-sleepable, yet, because it's transitively
+ * reachable through BPF link, its freeing has to be delayed until after RCU
+ * Tasks Trace GP.
+ */
+void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
+			     const struct bpf_link_ops *ops, struct bpf_prog *prog,
+			     bool sleepable)
 {
 	WARN_ON(ops->dealloc && ops->dealloc_deferred);
 	atomic64_set(&link->refcnt, 1);
 	link->type = type;
+	link->sleepable = sleepable;
 	link->id = 0;
 	link->ops = ops;
 	link->prog = prog;
 }
 
+void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
+		   const struct bpf_link_ops *ops, struct bpf_prog *prog)
+{
+	bpf_link_init_sleepable(link, type, ops, prog, false);
+}
+
 static void bpf_link_free_id(int id)
 {
 	if (!id)
@@ -3076,12 +3093,24 @@ void bpf_link_inc(struct bpf_link *link)
 	atomic64_inc(&link->refcnt);
 }
 
+static void bpf_link_dealloc(struct bpf_link *link)
+{
+	/* now that we know that bpf_link itself can't be reached, put underlying BPF program */
+	if (link->prog)
+		bpf_prog_put(link->prog);
+
+	/* free bpf_link and its containing memory */
+	if (link->ops->dealloc_deferred)
+		link->ops->dealloc_deferred(link);
+	else
+		link->ops->dealloc(link);
+}
+
 static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu)
 {
 	struct bpf_link *link = container_of(rcu, struct bpf_link, rcu);
 
-	/* free bpf_link and its containing memory */
-	link->ops->dealloc_deferred(link);
+	bpf_link_dealloc(link);
 }
 
 static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
@@ -3096,26 +3125,27 @@ static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
 static void bpf_link_free(struct bpf_link *link)
 {
 	const struct bpf_link_ops *ops = link->ops;
-	bool sleepable = false;
 
 	bpf_link_free_id(link->id);
-	if (link->prog) {
-		sleepable = link->prog->sleepable;
-		/* detach BPF program, clean up used resources */
+	/* detach BPF program, clean up used resources */
+	if (link->prog)
 		ops->release(link);
-		bpf_prog_put(link->prog);
-	}
 	if (ops->dealloc_deferred) {
-		/* schedule BPF link deallocation; if underlying BPF program
-		 * is sleepable, we need to first wait for RCU tasks trace
-		 * sync, then go through "classic" RCU grace period
+		/* Schedule BPF link deallocation, which will only then
+		 * trigger putting BPF program refcount.
+		 * If underlying BPF program is sleepable or BPF link's target
+		 * attach hookpoint is sleepable or otherwise requires RCU GPs
+		 * to ensure link and its underlying BPF program is not
+		 * reachable anymore, we need to first wait for RCU tasks
+		 * trace sync, and then go through "classic" RCU grace period
 		 */
-		if (sleepable)
+		if (link->sleepable || (link->prog && link->prog->sleepable))
 			call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp);
 		else
 			call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
-	} else if (ops->dealloc)
-		ops->dealloc(link);
+	} else if (ops->dealloc) {
+		bpf_link_dealloc(link);
+	}
 }
 
 static void bpf_link_put_deferred(struct work_struct *work)
@@ -3936,8 +3966,9 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
 		err = -ENOMEM;
 		goto out_put_btp;
 	}
-	bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT,
-		      &bpf_raw_tp_link_lops, prog);
+	bpf_link_init_sleepable(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT,
+				&bpf_raw_tp_link_lops, prog,
+				tracepoint_is_faultable(btp->tp));
 	link->btp = btp;
 	link->cookie = cookie;
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 71e53eaba8bc..9b17efb1a87d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5093,6 +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)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 103b30b1c73b..3ef047ed9705 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -593,19 +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
@@ -988,7 +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,
@@ -997,7 +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)
 {
@@ -1934,7 +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
@@ -2908,7 +2897,6 @@ 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;
@@ -2921,11 +2909,9 @@ 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
@@ -2933,7 +2919,7 @@ 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];
@@ -2947,11 +2933,11 @@ 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;
@@ -2994,6 +2980,20 @@ 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);
@@ -3005,8 +3005,7 @@ 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 */
@@ -3024,7 +3023,7 @@ 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,
@@ -3033,7 +3032,7 @@ 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;
 	}
 
@@ -3050,7 +3049,7 @@ 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();
 }
 
@@ -3067,8 +3066,8 @@ void trace_dump_stack(int skip)
 	/* Skip 1 to skip this function. */
 	skip++;
 #endif
-	__ftrace_trace_stack(printk_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);
 
@@ -3079,7 +3078,6 @@ 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;
 
@@ -3113,8 +3111,7 @@ 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);
@@ -3283,7 +3280,6 @@ 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 = READ_ONCE(printk_trace);
@@ -3327,10 +3323,8 @@ 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);
@@ -3350,7 +3344,6 @@ 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;
@@ -3385,10 +3378,8 @@ __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(printk_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);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3307dad4d917..266740b4e121 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1440,10 +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,
@@ -2187,4 +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_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_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 03c5a0d300a5..5504b5e4e7b4 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -114,7 +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;
@@ -125,8 +124,7 @@ 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;
 }
@@ -292,7 +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;
@@ -303,8 +300,7 @@ 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 ha