Merge branch 'x86/hyperv' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Topic branch for stable KVM clockource under Hyper-V.

Thanks to Christoffer Dall for resolving the ARM conflict.

10 files changed, 192 insertions, 121 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index af7dad126c13..f54dc62b599c 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -164,6 +164,7 @@ config PREEMPTIRQ_EVENTS
 	bool "Enable trace events for preempt and irq disable/enable"
 	select TRACE_IRQFLAGS
 	depends on DEBUG_PREEMPT || !PROVE_LOCKING
+	depends on TRACING
 	default n
 	help
 	  Enable tracing of disable and enable events for preemption and irqs.
@@ -354,7 +355,7 @@ config PROFILE_ANNOTATED_BRANCHES
 	  on if you need to profile the system's use of these macros.
 
 config PROFILE_ALL_BRANCHES
-	bool "Profile all if conditionals"
+	bool "Profile all if conditionals" if !FORTIFY_SOURCE
 	select TRACE_BRANCH_PROFILING
 	help
 	  This tracer profiles all branch conditions. Every if ()
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0ce99c379c30..40207c2a4113 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -343,14 +343,13 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
-static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd);
+static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd);
 
 static __always_inline u64
 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
-			u64 flags, struct perf_raw_record *raw)
+			u64 flags, struct perf_sample_data *sd)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	struct perf_sample_data *sd = this_cpu_ptr(&bpf_sd);
 	unsigned int cpu = smp_processor_id();
 	u64 index = flags & BPF_F_INDEX_MASK;
 	struct bpf_event_entry *ee;
@@ -373,8 +372,6 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 	if (unlikely(event->oncpu != cpu))
 		return -EOPNOTSUPP;
 
-	perf_sample_data_init(sd, 0, 0);
-	sd->raw = raw;
 	perf_event_output(event, sd, regs);
 	return 0;
 }
@@ -382,6 +379,7 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags, void *, data, u64, size)
 {
+	struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd);
 	struct perf_raw_record raw = {
 		.frag = {
 			.size = size,
@@ -392,7 +390,10 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
 		return -EINVAL;
 
-	return __bpf_perf_event_output(regs, map, flags, &raw);
+	perf_sample_data_init(sd, 0, 0);
+	sd->raw = &raw;
+
+	return __bpf_perf_event_output(regs, map, flags, sd);
 }
 
 static const struct bpf_func_proto bpf_perf_event_output_proto = {
@@ -407,10 +408,12 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
 };
 
 static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
+static DEFINE_PER_CPU(struct perf_sample_data, bpf_misc_sd);
 
 u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
 {
+	struct perf_sample_data *sd = this_cpu_ptr(&bpf_misc_sd);
 	struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);
 	struct perf_raw_frag frag = {
 		.copy		= ctx_copy,
@@ -428,8 +431,10 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 	};
 
 	perf_fetch_caller_regs(regs);
+	perf_sample_data_init(sd, 0, 0);
+	sd->raw = &raw;
 
-	return __bpf_perf_event_output(regs, map, flags, &raw);
+	return __bpf_perf_event_output(regs, map, flags, sd);
 }
 
 BPF_CALL_0(bpf_get_current_task)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ccdf3664e4a9..554b517c61a0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1119,15 +1119,11 @@ static struct ftrace_ops global_ops = {
 };
 
 /*
- * This is used by __kernel_text_address() to return true if the
- * address is on a dynamically allocated trampoline that would
- * not return true for either core_kernel_text() or
- * is_module_text_address().
+ * Used by the stack undwinder to know about dynamic ftrace trampolines.
  */
-bool is_ftrace_trampoline(unsigned long addr)
+struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr)
 {
-	struct ftrace_ops *op;
-	bool ret = false;
+	struct ftrace_ops *op = NULL;
 
 	/*
 	 * Some of the ops may be dynamically allocated,
@@ -1144,15 +1140,24 @@ bool is_ftrace_trampoline(unsigned long addr)
 		if (op->trampoline && op->trampoline_size)
 			if (addr >= op->trampoline &&
 			    addr < op->trampoline + op->trampoline_size) {
-				ret = true;
-				goto out;
+				preempt_enable_notrace();
+				return op;
 			}
 	} while_for_each_ftrace_op(op);
-
- out:
 	preempt_enable_notrace();
 
-	return ret;
+	return NULL;
+}
+
+/*
+ * This is used by __kernel_text_address() to return true if the
+ * address is on a dynamically allocated trampoline that would
+ * not return true for either core_kernel_text() or
+ * is_module_text_address().
+ */
+bool is_ftrace_trampoline(unsigned long addr)
+{
+	return ftrace_ops_trampoline(addr) != NULL;
 }
 
 struct ftrace_page {
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 91874a95060d..5af2842dea96 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -280,6 +280,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 /* Missed count stored at end */
 #define RB_MISSED_STORED	(1 << 30)
 
+#define RB_MISSED_FLAGS		(RB_MISSED_EVENTS|RB_MISSED_STORED)
+
 struct buffer_data_page {
 	u64		 time_stamp;	/* page time stamp */
 	local_t		 commit;	/* write committed index */
@@ -331,7 +333,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
  */
 size_t ring_buffer_page_len(void *page)
 {
-	return local_read(&((struct buffer_data_page *)page)->commit)
+	struct buffer_data_page *bpage = page;
+
+	return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
 		+ BUF_PAGE_HDR_SIZE;
 }
 
@@ -1799,12 +1803,6 @@ void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
 
-static __always_inline void *
-__rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
-{
-	return bpage->data + index;
-}
-
 static __always_inline void *__rb_page_index(struct buffer_page *bpage, unsigned index)
 {
 	return bpage->page->data + index;
@@ -2536,29 +2534,58 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
  * The lock and unlock are done within a preempt disable section.
  * The current_context per_cpu variable can only be modified
  * by the current task between lock and unlock. But it can
- * be modified more than once via an interrupt. There are four
- * different contexts that we need to consider.
+ * be modified more than once via an interrupt. To pass this
+ * information from the lock to the unlock without having to
+ * access the 'in_interrupt()' functions again (which do show
+ * a bit of overhead in something as critical as function tracing,
+ * we use a bitmask trick.
+ *
+ *  bit 0 =  NMI context
+ *  bit 1 =  IRQ context
+ *  bit 2 =  SoftIRQ context
+ *  bit 3 =  normal context.
+ *
+ * This works because this is the order of contexts that can
+ * preempt other contexts. A SoftIRQ never preempts an IRQ
+ * context.
+ *
+ * When the context is determined, the corresponding bit is
+ * checked and set (if it was set, then a recursion of that context
+ * happened).
+ *
+ * On unlock, we need to clear this bit. To do so, just subtract
+ * 1 from the current_context and AND it to itself.
  *
- *  Normal context.
- *  SoftIRQ context
- *  IRQ context
- *  NMI context
+ * (binary)
+ *  101 - 1 = 100
+ *  101 & 100 = 100 (clearing bit zero)
  *
- * If for some reason the ring buffer starts to recurse, we
- * only allow that to happen at most 4 times (one for each
- * context). If it happens 5 times, then we consider this a
- * recusive loop and do not let it go further.
+ *  1010 - 1 = 1001
+ *  1010 & 1001 = 1000 (clearing bit 1)
+ *
+ * The least significant bit can be cleared this way, and it
+ * just so happens that it is the same bit corresponding to
+ * the current context.
  */
 
 static __always_inline int
 trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	if (cpu_buffer->current_context >= 4)
+	unsigned int val = cpu_buffer->current_context;
+	unsigned long pc = preempt_count();
+	int bit;
+
+	if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
+		bit = RB_CTX_NORMAL;
+	else
+		bit = pc & NMI_MASK ? RB_CTX_NMI :
+			pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;
+
+	if (unlikely(val & (1 << bit)))
 		return 1;
 
-	cpu_buffer->current_context++;
-	/* Interrupts must see this update */
-	barrier();
+	val |= (1 << bit);
+	cpu_buffer->current_context = val;
 
 	return 0;
 }
@@ -2566,9 +2593,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 static __always_inline void
 trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	/* Don't let the dec leak out */
-	barrier();
-	cpu_buffer->current_context--;
+	cpu_buffer->current_context &= cpu_buffer->current_context - 1;
 }
 
 /**
@@ -4406,8 +4431,13 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct buffer_data_page *bpage = data;
+	struct page *page = virt_to_page(bpage);
 	unsigned long flags;
 
+	/* If the page is still in use someplace else, we can't reuse it */
+	if (page_ref_count(page) > 1)
+		goto out;
+
 	local_irq_save(flags);
 	arch_spin_lock(&cpu_buffer->lock);
 
@@ -4419,6 +4449,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
+ out:
 	free_page((unsigned long)bpage);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 73e67b68c53b..4f3a8e24b426 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -362,7 +362,7 @@ trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct
 }
 
 /**
- * trace_pid_filter_add_remove - Add or remove a task from a pid_list
+ * trace_pid_filter_add_remove_task - Add or remove a task from a pid_list
  * @pid_list: The list to modify
  * @self: The current task for fork or NULL for exit
  * @task: The task to add or remove
@@ -925,7 +925,7 @@ static void tracing_snapshot_instance(struct trace_array *tr)
 }
 
 /**
- * trace_snapshot - take a snapshot of the current buffer.
+ * tracing_snapshot - take a snapshot of the current buffer.
  *
  * This causes a swap between the snapshot buffer and the current live
  * tracing buffer. You can use this to take snapshots of the live
@@ -1004,9 +1004,9 @@ int tracing_alloc_snapshot(void)
 EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
 
 /**
- * trace_snapshot_alloc - allocate and take a snapshot of the current buffer.
+ * tracing_snapshot_alloc - allocate and take a snapshot of the current buffer.
  *
- * This is similar to trace_snapshot(), but it will allocate the
+ * This is similar to tracing_snapshot(), but it will allocate the
  * snapshot buffer if it isn't already allocated. Use this only
  * where it is safe to sleep, as the allocation may sleep.
  *
@@ -1303,7 +1303,7 @@ unsigned long __read_mostly	tracing_thresh;
 /*
  * Copy the new maximum trace into the separate maximum-trace
  * structure. (this way the maximum trace is permanently saved,
- * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
+ * for later retrieval via /sys/kernel/tracing/tracing_max_latency)
  */
 static void
 __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
@@ -2374,6 +2374,15 @@ void trace_event_buffer_commit(struct trace_event_buffer *fbuffer)
 }
 EXPORT_SYMBOL_GPL(trace_event_buffer_commit);
 
+/*
+ * Skip 3:
+ *
+ *   trace_buffer_unlock_commit_regs()
+ *   trace_event_buffer_commit()
+ *   trace_event_raw_event_xxx()
+*/
+# define STACK_SKIP 3
+
 void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 				     struct ring_buffer *buffer,
 				     struct ring_buffer_event *event,
@@ -2383,16 +2392,12 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 	__buffer_unlock_commit(buffer, event);
 
 	/*
-	 * If regs is not set, then skip the following callers:
-	 *   trace_buffer_unlock_commit_regs
-	 *   event_trigger_unlock_commit
-	 *   trace_event_buffer_commit
-	 *   trace_event_raw_event_sched_switch
+	 * If regs is not set, then skip the necessary functions.
 	 * Note, we can still get here via blktrace, wakeup tracer
 	 * and mmiotrace, but that's ok if they lose a function or
-	 * two. They are that meaningful.
+	 * two. They are not that meaningful.
 	 */
-	ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs);
+	ftrace_trace_stack(tr, buffer, flags, regs ? 0 : STACK_SKIP, pc, regs);
 	ftrace_trace_userstack(buffer, flags, pc);
 }
 
@@ -2415,7 +2420,7 @@ trace_process_export(struct trace_export *export,
 
 	entry = ring_buffer_event_data(event);
 	size = ring_buffer_event_length(event);
-	export->write(entry, size);
+	export->write(export, entry, size);
 }
 
 static DEFINE_MUTEX(ftrace_export_lock);
@@ -2579,11 +2584,13 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	trace.skip		= skip;
 
 	/*
-	 * Add two, for this function and the call to save_stack_trace()
+	 * Add one, for this function and the call to save_stack_trace()
 	 * If regs is set, then these functions will not be in the way.
 	 */
+#ifndef CONFIG_UNWINDER_ORC
 	if (!regs)
-		trace.skip += 2;
+		trace.skip++;
+#endif
 
 	/*
 	 * Since events can happen in NMIs there's no safe way to
@@ -2682,17 +2689,6 @@ void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 	if (unlikely(in_nmi()))
 		return;
 
-	/*
-	 * It is possible that a function is being traced in a
-	 * location that RCU is not watching. A call to
-	 * rcu_irq_enter() will make sure that it is, but there's
-	 * a few internal rcu functions that could be traced
-	 * where that wont work either. In those cases, we just
-	 * do nothing.
-	 */
-	if (unlikely(rcu_irq_enter_disabled()))
-		return;
-
 	rcu_irq_enter_irqson();
 	__ftrace_trace_stack(buffer, flags, skip, pc, NULL);
 	rcu_irq_exit_irqson();
@@ -2711,11 +2707,10 @@ void trace_dump_stack(int skip)
 
 	local_save_flags(flags);
 
-	/*
-	 * Skip 3 more, seems to get us at the caller of
-	 * this function.
-	 */
-	skip += 3;
+#ifndef CONFIG_UNWINDER_ORC
+	/* Skip 1 to skip this function. */
+	skip++;
+#endif
 	__ftrace_trace_stack(global_trace.trace_buffer.buffer,
 			     flags, skip, preempt_count(), NULL);
 }
@@ -4178,37 +4173,30 @@ static const struct file_operations show_traces_fops = {
 	.llseek		= seq_lseek,
 };
 
-/*
- * The tracer itself will not take this lock, but still we want
- * to provide a consistent cpumask to user-space:
- */
-static DEFINE_MUTEX(tracing_cpumask_update_lock);
-
-/*
- * Temporary storage for the character representation of the
- * CPU bitmask (and one more byte for the newline):
- */
-static char mask_str[NR_CPUS + 1];
-
 static ssize_t
 tracing_cpumask_read(struct file *filp, char __user *ubuf,
 		     size_t count, loff_t *ppos)
 {
 	struct trace_array *tr = file_inode(filp)->i_private;
+	char *mask_str;
 	int len;
 
-	mutex_lock(&tracing_cpumask_update_lock);
+	len = snprintf(NULL, 0, "%*pb\n",
+		       cpumask_pr_args(tr->tracing_cpumask)) + 1;
+	mask_str = kmalloc(len, GFP_KERNEL);
+	if (!mask_str)
+		return -ENOMEM;
 
-	len = snprintf(mask_str, count, "%*pb\n",
+	len = snprintf(mask_str, len, "%*pb\n",
 		       cpumask_pr_args(tr->tracing_cpumask));
 	if (len >= count) {
 		count = -EINVAL;
 		goto out_err;
 	}
-	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
+	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
 
 out_err:
-	mutex_unlock(&tracing_cpumask_update_lock);
+	kfree(mask_str);
 
 	return count;
 }
@@ -4228,8 +4216,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	if (err)
 		goto err_unlock;
 
-	mutex_lock(&tracing_cpumask_update_lock);
-
 	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 	for_each_tracing_cpu(cpu) {
@@ -4252,8 +4238,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	local_irq_enable();
 
 	cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
-
-	mutex_unlock(&tracing_cpumask_update_lock);
 	free_cpumask_var(tracing_cpumask_new);
 
 	return count;
@@ -6780,7 +6764,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		.spd_release	= buffer_spd_release,
 	};
 	struct buffer_ref *ref;
-	int entries, size, i;
+	int entries, i;
 	ssize_t ret = 0;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -6834,14 +6818,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 		}
 
-		/*
-		 * zero out any left over data, this is going to
-		 * user land.
-		 */
-		size = ring_buffer_page_len(ref->page);
-		if (size < PAGE_SIZE)
-			memset(ref->page + size, 0, PAGE_SIZE - size);
-
 		page = virt_to_page(ref->page);
 
 		spd.pages[i] = page;
@@ -7599,6 +7575,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
 	buf->data = alloc_percpu(struct trace_array_cpu);
 	if (!buf->data) {
 		ring_buffer_free(buf->buffer);
+		buf->buffer = NULL;
 		return -ENOMEM;
 	}
 
@@ -7622,7 +7599,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 				    allocate_snapshot ? size : 1);
 	if (WARN_ON(ret)) {
 		ring_buffer_free(tr->trace_buffer.buffer);
+		tr->trace_buffer.buffer = NULL;
 		free_percpu(tr->trace_buffer.data);
+		tr->trace_buffer.data = NULL;
 		return -ENOMEM;
 	}
 	tr->allocated_snapshot = allocate_snapshot;
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index 79f838a75077..22fee766081b 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -165,7 +165,7 @@ static int benchmark_event_kthread(void *arg)
 		 * this thread will never voluntarily schedule which would
 		 * block synchronize_rcu_tasks() indefinitely.
 		 */
-		cond_resched_rcu_qs();
+		cond_resched();
 	}
 
 	return 0;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index ec0f9aa4e151..1b87157edbff 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2213,6 +2213,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 {
 	struct trace_event_call *call, *p;
 	const char *last_system = NULL;
+	bool first = false;
 	int last_i;
 	int i;
 
@@ -2220,15 +2221,28 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 	list_for_each_entry_safe(call, p, &ftrace_events, list) {
 		/* events are usually grouped together with systems */
 		if (!last_system || call->class->system != last_system) {
+			first = true;
 			last_i = 0;
 			last_system = call->class->system;
 		}
 
+		/*
+		 * Since calls are grouped by systems, the likelyhood that the
+		 * next call in the iteration belongs to the same system as the
+		 * previous call is high. As an optimization, we skip seaching
+		 * for a map[] that matches the call's system if the last call
+		 * was from the same system. That's what last_i is for. If the
+		 * call has the same system as the previous call, then last_i
+		 * will be the index of the first map[] that has a matching
+		 * system.
+		 */
 		for (i = last_i; i < len; i++) {
 			if (call->class->system == map[i]->system) {
 				/* Save the first system if need be */
-				if (!last_i)
+				if (first) {
 					last_i = i;
+					first = false;
+				}
 				update_event_printk(call, map[i]);
 			}
 		}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index f2ac9d44f6c4..87411482a46f 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1123,13 +1123,22 @@ static __init int register_trigger_snapshot_cmd(void) { return 0; }
 #endif /* CONFIG_TRACER_SNAPSHOT */
 
 #ifdef CONFIG_STACKTRACE
+#ifdef CONFIG_UNWINDER_ORC
+/* Skip 2:
+ *   event_triggers_post_call()
+ *   trace_event_raw_event_xxx()
+ */
+# define STACK_SKIP 2
+#else
 /*
- * Skip 3:
+ * Skip 4:
  *   stacktrace_trigger()
  *   event_triggers_post_call()
+ *   trace_event_buffer_commit()
  *   trace_event_raw_event_xxx()
  */
-#define STACK_SKIP 3
+#define STACK_SKIP 4
+#endif
 
 static void
 stacktrace_trigger(struct event_trigger_data *data, void *rec)
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 27f7ad12c4b1..b611cd36e22d 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -154,6 +154,24 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 	preempt_enable_notrace();
 }
 
+#ifdef CONFIG_UNWINDER_ORC
+/*
+ * Skip 2:
+ *
+ *   function_stack_trace_call()
+ *   ftrace_call()
+ */
+#define STACK_SKIP 2
+#else
+/*
+ * Skip 3:
+ *   __trace_stack()
+ *   function_stack_trace_call()
+ *   ftrace_call()
+ */
+#define STACK_SKIP 3
+#endif
+
 static void
 function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 			  struct ftrace_ops *op, struct pt_regs *pt_regs)
@@ -180,15 +198,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (likely(disabled == 1)) {
 		pc = preempt_count();
 		trace_function(tr, ip, parent_ip, flags, pc);
-		/*
-		 * skip over 5 funcs:
-		 *    __ftrace_trace_stack,
-		 *    __trace_stack,
-		 *    function_stack_trace_call
-		 *    ftrace_list_func
-		 *    ftrace_call
-		 */
-		__trace_stack(tr, flags, 5, pc);
+		__trace_stack(tr, flags, STACK_SKIP, pc);
 	}
 
 	atomic_dec(&data->disabled);
@@ -367,14 +377,27 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip,
 	tracer_tracing_off(tr);
 }
 
+#ifdef CONFIG_UNWINDER_ORC
 /*
- * Skip 4:
+ * Skip 3:
+ *
+ *   function_trace_probe_call()
+ *   ftrace_ops_assist_func()
+ *   ftrace_call()
+ */
+#define FTRACE_STACK_SKIP 3
+#else
+/*
+ * Skip 5:
+ *
+ *   __trace_stack()
  *   ftrace_stacktrace()
  *   function_trace_probe_call()
- *   ftrace_ops_list_func()
+ *   ftrace_ops_assist_func()
  *   ftrace_call()
  */
-#define STACK_SKIP 4
+#define FTRACE_STACK_SKIP 5
+#endif
 
 static __always_inline void trace_stack(struct trace_array *tr)
 {
@@ -384,7 +407,7 @@ static __always_inline void trace_stack(struct trace_array *tr)
 	local_save_flags(flags);
 	pc = preempt_count();
 
-	__trace_stack(tr, flags, STACK_SKIP, pc);
+	__trace_stack(tr, flags, FTRACE_STACK_SKIP, pc);
 }
 
 static void
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 734accc02418..3c7bfc4bf5e9 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -209,6 +209,10 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (__this_cpu_read(disable_stack_tracer) != 1)
 		goto out;
 
+	/* If rcu is not watching, then save stack trace can fail */
+	if (!rcu_is_watching())
+		goto out;
+
 	ip += MCOUNT_INSN_SIZE;
 
 	check_stack(ip, &stack);