Merge tag 'trace-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:

 - User events are finally ready!

   After lots of collaboration between various parties, we finally
   locked down on a stable interface for user events that can also work
   with user space only tracing.

   This is implemented by telling the kernel (or user space library, but
   that part is user space only and not part of this patch set), where
   the variable is that the application uses to know if something is
   listening to the trace.

   There's also an interface to tell the kernel about these events,
   which will show up in the /sys/kernel/tracing/events/user_events/
   directory, where it can be enabled.

   When it's enabled, the kernel will update the variable, to tell the
   application to start writing to the kernel.

   See https://lwn.net/Articles/927595/

 - Cleaned up the direct trampolines code to simplify arm64 addition of
   direct trampolines.

   Direct trampolines use the ftrace interface but instead of jumping to
   the ftrace trampoline, applications (mostly BPF) can register their
   own trampoline for performance reasons.

 - Some updates to the fprobe infrastructure. fprobes are more efficient
   than kprobes, as it does not need to save all the registers that
   kprobes on ftrace do. More work needs to be done before the fprobes
   will be exposed as dynamic events.

 - More updates to references to the obsolete path of
   /sys/kernel/debug/tracing for the new /sys/kernel/tracing path.

 - Add a seq_buf_do_printk() helper to seq_bufs, to print a large buffer
   line by line instead of all at once.

   There are users in production kernels that have a large data dump
   that originally used printk() directly, but the data dump was larger
   than what printk() allowed as a single print.

   Using seq_buf() to do the printing fixes that.

 - Add /sys/kernel/tracing/touched_functions that shows all functions
   that was every traced by ftrace or a direct trampoline. This is used
   for debugging issues where a traced function could have caused a
   crash by a bpf program or live patching.

 - Add a "fields" option that is similar to "raw" but outputs the fields
   of the events. It's easier to read by humans.

 - Some minor fixes and clean ups.

* tag 'trace-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (41 commits)
  ring-buffer: Sync IRQ works before buffer destruction
  tracing: Add missing spaces in trace_print_hex_seq()
  ring-buffer: Ensure proper resetting of atomic variables in ring_buffer_reset_online_cpus
  recordmcount: Fix memory leaks in the uwrite function
  tracing/user_events: Limit max fault-in attempts
  tracing/user_events: Prevent same address and bit per process
  tracing/user_events: Ensure bit is cleared on unregister
  tracing/user_events: Ensure write index cannot be negative
  seq_buf: Add seq_buf_do_printk() helper
  tracing: Fix print_fields() for __dyn_loc/__rel_loc
  tracing/user_events: Set event filter_type from type
  ring-buffer: Clearly check null ptr returned by rb_set_head_page()
  tracing: Unbreak user events
  tracing/user_events: Use print_format_fields() for trace output
  tracing/user_events: Align structs with tabs for readability
  tracing/user_events: Limit global user_event count
  tracing/user_events: Charge event allocs to cgroups
  tracing/user_events: Update documentation for ABI
  tracing/user_events: Use write ABI in example
  tracing/user_events: Add ABI self-test
  ...

1 files changed, 54 insertions, 48 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 76a2d91eecad..834b361a4a66 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -163,7 +163,7 @@ enum {
 #define extended_time(event) \
 	(event->type_len >= RINGBUF_TYPE_TIME_EXTEND)
 
-static inline int rb_null_event(struct ring_buffer_event *event)
+static inline bool rb_null_event(struct ring_buffer_event *event)
 {
 	return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
 }
@@ -363,11 +363,9 @@ static void free_buffer_page(struct buffer_page *bpage)
 /*
  * We need to fit the time_stamp delta into 27 bits.
  */
-static inline int test_time_stamp(u64 delta)
+static inline bool test_time_stamp(u64 delta)
 {
-	if (delta & TS_DELTA_TEST)
-		return 1;
-	return 0;
+	return !!(delta & TS_DELTA_TEST);
 }
 
 #define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
@@ -696,7 +694,7 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
 	return ret == expect;
 }
 
-static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
+static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
 {
 	unsigned long cnt, top, bottom, msb;
 	unsigned long cnt2, top2, bottom2, msb2;
@@ -1486,7 +1484,7 @@ rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer)
 	return NULL;
 }
 
-static int rb_head_page_replace(struct buffer_page *old,
+static bool rb_head_page_replace(struct buffer_page *old,
 				struct buffer_page *new)
 {
 	unsigned long *ptr = (unsigned long *)&old->list.prev->next;
@@ -1565,15 +1563,12 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 	}
 }
 
-static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
+static void rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
 			  struct buffer_page *bpage)
 {
 	unsigned long val = (unsigned long)bpage;
 
-	if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK))
-		return 1;
-
-	return 0;
+	RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK);
 }
 
 /**
@@ -1583,30 +1578,28 @@ static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
  * As a safety measure we check to make sure the data pages have not
  * been corrupted.
  */
-static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
+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;
 
 	if (RB_WARN_ON(cpu_buffer,
 			rb_list_head(rb_list_head(head->next)->prev) != head))
-		return -1;
+		return;
 
 	if (RB_WARN_ON(cpu_buffer,
 			rb_list_head(rb_list_head(head->prev)->next) != head))
-		return -1;
+		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 -1;
+			return;
 
 		if (RB_WARN_ON(cpu_buffer,
 				rb_list_head(rb_list_head(tmp->prev)->next) != tmp))
-			return -1;
+			return;
 	}
-
-	return 0;
 }
 
 static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
@@ -1774,6 +1767,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 	struct list_head *head = cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 
+	irq_work_sync(&cpu_buffer->irq_work.work);
+
 	free_buffer_page(cpu_buffer->reader_page);
 
 	if (head) {
@@ -1880,6 +1875,8 @@ ring_buffer_free(struct trace_buffer *buffer)
 
 	cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
 
+	irq_work_sync(&buffer->irq_work.work);
+
 	for_each_buffer_cpu(buffer, cpu)
 		rb_free_cpu_buffer(buffer->buffers[cpu]);
 
@@ -1918,7 +1915,7 @@ static inline unsigned long rb_page_write(struct buffer_page *bpage)
 	return local_read(&bpage->write) & RB_WRITE_MASK;
 }
 
-static int
+static bool
 rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 {
 	struct list_head *tail_page, *to_remove, *next_page;
@@ -2031,12 +2028,13 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 	return nr_removed == 0;
 }
 
-static int
+static bool
 rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct list_head *pages = &cpu_buffer->new_pages;
-	int retries, success;
 	unsigned long flags;
+	bool success;
+	int retries;
 
 	/* Can be called at early boot up, where interrupts must not been enabled */
 	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
@@ -2055,15 +2053,16 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 	 * spinning.
 	 */
 	retries = 10;
-	success = 0;
+	success = false;
 	while (retries--) {
 		struct list_head *head_page, *prev_page, *r;
 		struct list_head *last_page, *first_page;
 		struct list_head *head_page_with_bit;
+		struct buffer_page *hpage = rb_set_head_page(cpu_buffer);
 
-		head_page = &rb_set_head_page(cpu_buffer)->list;
-		if (!head_page)
+		if (!hpage)
 			break;
+		head_page = &hpage->list;
 		prev_page = head_page->prev;
 
 		first_page = pages->next;
@@ -2084,7 +2083,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 			 * pointer to point to end of list
 			 */
 			head_page->prev = last_page;
-			success = 1;
+			success = true;
 			break;
 		}
 	}
@@ -2112,7 +2111,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 
 static void rb_update_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	int success;
+	bool success;
 
 	if (cpu_buffer->nr_pages_to_update > 0)
 		success = rb_insert_pages(cpu_buffer);
@@ -2995,7 +2994,7 @@ static u64 rb_time_delta(struct ring_buffer_event *event)
 	}
 }
 
-static inline int
+static inline bool
 rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 		  struct ring_buffer_event *event)
 {
@@ -3016,7 +3015,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	delta = rb_time_delta(event);
 
 	if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp))
-		return 0;
+		return false;
 
 	/* Make sure the write stamp is read before testing the location */
 	barrier();
@@ -3029,7 +3028,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 		/* Something came in, can't discard */
 		if (!rb_time_cmpxchg(&cpu_buffer->write_stamp,
 				       write_stamp, write_stamp - delta))
-			return 0;
+			return false;
 
 		/*
 		 * It's possible that the event time delta is zero
@@ -3062,12 +3061,12 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 		if (index == old_index) {
 			/* update counters */
 			local_sub(event_length, &cpu_buffer->entries_bytes);
-			return 1;
+			return true;
 		}
 	}
 
 	/* could not discard */
-	return 0;
+	return false;
 }
 
 static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer)
@@ -3288,7 +3287,7 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
  * Note: The TRANSITION bit only handles a single transition between context.
  */
 
-static __always_inline int
+static __always_inline bool
 trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	unsigned int val = cpu_buffer->current_context;
@@ -3305,14 +3304,14 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 		bit = RB_CTX_TRANSITION;
 		if (val & (1 << (bit + cpu_buffer->nest))) {
 			do_ring_buffer_record_recursion();
-			return 1;
+			return true;
 		}
 	}
 
 	val |= (1 << (bit + cpu_buffer->nest));
 	cpu_buffer->current_context = val;
 
-	return 0;
+	return false;
 }
 
 static __always_inline void
@@ -4069,10 +4068,10 @@ void ring_buffer_record_off(struct trace_buffer *buffer)
 	unsigned int rd;
 	unsigned int new_rd;
 
+	rd = atomic_read(&buffer->record_disabled);
 	do {
-		rd = atomic_read(&buffer->record_disabled);
 		new_rd = rd | RB_BUFFER_OFF;
-	} while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
+	} while (!atomic_try_cmpxchg(&buffer->record_disabled, &rd, new_rd));
 }
 EXPORT_SYMBOL_GPL(ring_buffer_record_off);
 
@@ -4092,10 +4091,10 @@ void ring_buffer_record_on(struct trace_buffer *buffer)
 	unsigned int rd;
 	unsigned int new_rd;
 
+	rd = atomic_read(&buffer->record_disabled);
 	do {
-		rd = atomic_read(&buffer->record_disabled);
 		new_rd = rd & ~RB_BUFFER_OFF;
-	} while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
+	} while (!atomic_try_cmpxchg(&buffer->record_disabled, &rd, new_rd));
 }
 EXPORT_SYMBOL_GPL(ring_buffer_record_on);
 
@@ -4502,7 +4501,6 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 	default:
 		RB_WARN_ON(cpu_buffer, 1);
 	}
-	return;
 }
 
 static void
@@ -4533,7 +4531,6 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
 	default:
 		RB_WARN_ON(iter->cpu_buffer, 1);
 	}
-	return;
 }
 
 static struct buffer_page *
@@ -4543,7 +4540,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	unsigned long overwrite;
 	unsigned long flags;
 	int nr_loops = 0;
-	int ret;
+	bool ret;
 
 	local_irq_save(flags);
 	arch_spin_lock(&cpu_buffer->lock);
@@ -4953,7 +4950,6 @@ rb_reader_unlock(struct ring_buffer_per_cpu *cpu_buffer, bool locked)
 {
 	if (likely(locked))
 		raw_spin_unlock(&cpu_buffer->reader_lock);
-	return;
 }
 
 /**
@@ -5345,6 +5341,9 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
+/* Flag to ensure proper resetting of atomic variables */
+#define RESET_BIT	(1 << 30)
+
 /**
  * ring_buffer_reset_online_cpus - reset a ring buffer per CPU buffer
  * @buffer: The ring buffer to reset a per cpu buffer of
@@ -5361,20 +5360,27 @@ void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
 	for_each_online_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
 
-		atomic_inc(&cpu_buffer->resize_disabled);
+		atomic_add(RESET_BIT, &cpu_buffer->resize_disabled);
 		atomic_inc(&cpu_buffer->record_disabled);
 	}
 
 	/* Make sure all commits have finished */
 	synchronize_rcu();
 
-	for_each_online_buffer_cpu(buffer, cpu) {
+	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
 
+		/*
+		 * If a CPU came online during the synchronize_rcu(), then
+		 * ignore it.
+		 */
+		if (!(atomic_read(&cpu_buffer->resize_disabled) & RESET_BIT))
+			continue;
+
 		reset_disabled_cpu_buffer(cpu_buffer);
 
 		atomic_dec(&cpu_buffer->record_disabled);
-		atomic_dec(&cpu_buffer->resize_disabled);
+		atomic_sub(RESET_BIT, &cpu_buffer->resize_disabled);
 	}
 
 	mutex_unlock(&buffer->mutex);
@@ -5424,8 +5430,8 @@ bool ring_buffer_empty(struct trace_buffer *buffer)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags;
 	bool dolock;
+	bool ret;
 	int cpu;
-	int ret;
 
 	/* yes this is racy, but if you don't like the race, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
@@ -5454,7 +5460,7 @@ bool ring_buffer_empty_cpu(struct trace_buffer *buffer, int cpu)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags;
 	bool dolock;
-	int ret;
+	bool ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return true;