Merge tag 'trace-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:

 - Allow kernel trace instance creation to specify what events are
   created

   Inside the kernel, a subsystem may create a tracing instance that it
   can use to send events to user space. This sub-system may not care
   about the thousands of events that exist in eventfs. Allow the
   sub-system to specify what sub-systems of events it cares about, and
   only those events are exposed to this instance.

 - Allow the ring buffer to be broken up into bigger sub-buffers than
   just the architecture page size.

   A new tracefs file called "buffer_subbuf_size_kb" is created. The
   user can now specify a minimum size the sub-buffer may be in
   kilobytes. Note, that the implementation currently make the
   sub-buffer size a power of 2 pages (1, 2, 4, 8, 16, ...) but the user
   only writes in kilobyte size, and the sub-buffer will be updated to
   the next size that it will can accommodate it. If the user writes in
   10, it will change the size to be 4 pages on x86 (16K), as that is
   the next available size that can hold 10K pages.

 - Update the debug output when a corrupt time is detected in the ring
   buffer. If the ring buffer detects inconsistent timestamps, there's a
   debug config options that will dump the contents of the meta data of
   the sub-buffer that is used for debugging. Add some more information
   to this dump that helps with debugging.

 - Add more timestamp debugging checks (only triggers when the config is
   enabled)

 - Increase the trace_seq iterator to 2 page sizes.

 - Allow strings written into tracefs_marker to be larger. Up to just
   under 2 page sizes (based on what trace_seq can hold).

 - Increase the trace_maker_raw write to be as big as a sub-buffer can
   hold.

 - Remove 32 bit time stamp logic, now that the rb_time_cmpxchg() has
   been removed.

 - More selftests were added.

 - Some code clean ups as well.

* tag 'trace-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (29 commits)
  ring-buffer: Remove stale comment from ring_buffer_size()
  tracing histograms: Simplify parse_actions() function
  tracing/selftests: Remove exec permissions from trace_marker.tc test
  ring-buffer: Use subbuf_order for buffer page masking
  tracing: Update subbuffer with kilobytes not page order
  ringbuffer/selftest: Add basic selftest to test changing subbuf order
  ring-buffer: Add documentation on the buffer_subbuf_order file
  ring-buffer: Just update the subbuffers when changing their allocation order
  ring-buffer: Keep the same size when updating the order
  tracing: Stop the tracing while changing the ring buffer subbuf size
  tracing: Update snapshot order along with main buffer order
  ring-buffer: Make sure the spare sub buffer used for reads has same size
  ring-buffer: Do no swap cpu buffers if order is different
  ring-buffer: Clear pages on error in ring_buffer_subbuf_order_set() failure
  ring-buffer: Read and write to ring buffers with custom sub buffer size
  ring-buffer: Set new size of the ring buffer sub page
  ring-buffer: Add interface for configuring trace sub buffer size
  ring-buffer: Page size per ring buffer
  ring-buffer: Have ring_buffer_print_page_header() be able to access ring_buffer_iter
  ring-buffer: Check if absolute timestamp goes backwards
  ...

Documentation/trace/ftrace.rst

@@ -218,6 +218,27 @@ of ftrace. Here is a list of some of the key files:
 
 	This displays the total combined size of all the trace buffers.
 
+  buffer_subbuf_size_kb:
+
+	This sets or displays the sub buffer size. The ring buffer is broken up
+	into several same size "sub buffers". An event can not be bigger than
+	the size of the sub buffer. Normally, the sub buffer is the size of the
+	architecture's page (4K on x86). The sub buffer also contains meta data
+	at the start which also limits the size of an event.  That means when
+	the sub buffer is a page size, no event can be larger than the page
+	size minus the sub buffer meta data.
+
+	Note, the buffer_subbuf_size_kb is a way for the user to specify the
+	minimum size of the subbuffer. The kernel may make it bigger due to the
+	implementation details, or simply fail the operation if the kernel can
+	not handle the request.
+
+	Changing the sub buffer size allows for events to be larger than the
+	page size.
+
+	Note: When changing the sub-buffer size, tracing is stopped and any
+	data in the ring buffer and the snapshot buffer will be discarded.
+
   free_buffer:
 
 	If a process is performing tracing, and the ring buffer	should be

drivers/scsi/qla2xxx/qla_os.c

@@ -2889,7 +2889,7 @@ static void qla2x00_iocb_work_fn(struct work_struct *work)
 static void
 qla_trace_init(void)
 {
-	qla_trc_array = trace_array_get_by_name("qla2xxx");
+	qla_trc_array = trace_array_get_by_name("qla2xxx", NULL);
 	if (!qla_trc_array) {
 		ql_log(ql_log_fatal, NULL, 0x0001,
 		       "Unable to create qla2xxx trace instance, instance logging will be disabled.\n");

include/linux/ring_buffer.h

@@ -141,6 +141,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter);
 bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter);
 
 unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu);
+unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer);
 
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu);
 void ring_buffer_reset_online_cpus(struct trace_buffer *buffer);
@@ -191,15 +192,24 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer);
 size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu);
 size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu);
 
-void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu);
-void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data);
-int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page,
+struct buffer_data_read_page;
+struct buffer_data_read_page *
+ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu);
+void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu,
+				struct buffer_data_read_page *page);
+int ring_buffer_read_page(struct trace_buffer *buffer,
+			  struct buffer_data_read_page *data_page,
 			  size_t len, int cpu, int full);
+void *ring_buffer_read_page_data(struct buffer_data_read_page *page);
 
 struct trace_seq;
 
 int ring_buffer_print_entry_header(struct trace_seq *s);
-int ring_buffer_print_page_header(struct trace_seq *s);
+int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s);
+
+int ring_buffer_subbuf_order_get(struct trace_buffer *buffer);
+int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order);
+int ring_buffer_subbuf_size_get(struct trace_buffer *buffer);
 
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,

include/linux/trace.h

@@ -51,7 +51,7 @@ int trace_array_printk(struct trace_array *tr, unsigned long ip,
 		       const char *fmt, ...);
 int trace_array_init_printk(struct trace_array *tr);
 void trace_array_put(struct trace_array *tr);
-struct trace_array *trace_array_get_by_name(const char *name);
+struct trace_array *trace_array_get_by_name(const char *name, const char *systems);
 int trace_array_destroy(struct trace_array *tr);
 
 /* For osnoise tracer */
@@ -84,7 +84,7 @@ static inline int trace_array_init_printk(struct trace_array *tr)
 static inline void trace_array_put(struct trace_array *tr)
 {
 }
-static inline struct trace_array *trace_array_get_by_name(const char *name)
+static inline struct trace_array *trace_array_get_by_name(const char *name, const char *systems)
 {
 	return NULL;
 }

include/linux/trace_seq.h

@@ -8,11 +8,14 @@
 
 /*
  * Trace sequences are used to allow a function to call several other functions
- * to create a string of data to use (up to a max of PAGE_SIZE).
+ * to create a string of data to use.
  */
 
+#define TRACE_SEQ_BUFFER_SIZE	(PAGE_SIZE * 2 - \
+	(sizeof(struct seq_buf) + sizeof(size_t) + sizeof(int)))
+
 struct trace_seq {
-	char			buffer[PAGE_SIZE];
+	char			buffer[TRACE_SEQ_BUFFER_SIZE];
 	struct seq_buf		seq;
 	size_t			readpos;
 	int			full;
@@ -21,7 +24,7 @@ struct trace_seq {
 static inline void
 trace_seq_init(struct trace_seq *s)
 {
-	seq_buf_init(&s->seq, s->buffer, PAGE_SIZE);
+	seq_buf_init(&s->seq, s->buffer, TRACE_SEQ_BUFFER_SIZE);
 	s->full = 0;
 	s->readpos = 0;
 }

kernel/trace/ring_buffer.c

@@ -27,6 +27,7 @@
 #include <linux/cpu.h>
 #include <linux/oom.h>
 
+#include <asm/local64.h>
 #include <asm/local.h>
 
 /*
@@ -317,6 +318,11 @@ struct buffer_data_page {
 	unsigned char	 data[] RB_ALIGN_DATA;	/* data of buffer page */
 };
 
+struct buffer_data_read_page {
+	unsigned		order;	/* order of the page */
+	struct buffer_data_page	*data;	/* actual data, stored in this page */
+};
+
 /*
  * Note, the buffer_page list must be first. The buffer pages
  * are allocated in cache lines, which means that each buffer
@@ -331,6 +337,7 @@ struct buffer_page {
 	unsigned	 read;		/* index for next read */
 	local_t		 entries;	/* entries on this page */
 	unsigned long	 real_end;	/* real end of data */
+	unsigned	 order;		/* order of the page */
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
@@ -361,7 +368,7 @@ static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage)
 
 static void free_buffer_page(struct buffer_page *bpage)
 {
-	free_page((unsigned long)bpage->page);
+	free_pages((unsigned long)bpage->page, bpage->order);
 	kfree(bpage);
 }
 
@@ -373,41 +380,6 @@ static inline bool test_time_stamp(u64 delta)
 	return !!(delta & TS_DELTA_TEST);
 }
 
-#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
-
-/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
-#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
-
-int ring_buffer_print_page_header(struct trace_seq *s)
-{
-	struct buffer_data_page field;
-
-	trace_seq_printf(s, "\tfield: u64 timestamp;\t"
-			 "offset:0;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)sizeof(field.time_stamp),
-			 (unsigned int)is_signed_type(u64));
-
-	trace_seq_printf(s, "\tfield: local_t commit;\t"
-			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)offsetof(typeof(field), commit),
-			 (unsigned int)sizeof(field.commit),
-			 (unsigned int)is_signed_type(long));
-
-	trace_seq_printf(s, "\tfield: int overwrite;\t"
-			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)offsetof(typeof(field), commit),
-			 1,
-			 (unsigned int)is_signed_type(long));
-
-	trace_seq_printf(s, "\tfield: char data;\t"
-			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
-			 (unsigned int)offsetof(typeof(field), data),
-			 (unsigned int)BUF_PAGE_SIZE,
-			 (unsigned int)is_signed_type(char));
-
-	return !trace_seq_has_overflowed(s);
-}
-
 struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
@@ -463,27 +435,9 @@ enum {
 	RB_CTX_MAX
 };
 
-#if BITS_PER_LONG == 32
-#define RB_TIME_32
-#endif
-
-/* To test on 64 bit machines */
-//#define RB_TIME_32
-
-#ifdef RB_TIME_32
-
-struct rb_time_struct {
-	local_t		cnt;
-	local_t		top;
-	local_t		bottom;
-	local_t		msb;
-};
-#else
-#include <asm/local64.h>
 struct rb_time_struct {
 	local64_t	time;
 };
-#endif
 typedef struct rb_time_struct rb_time_t;
 
 #define MAX_NEST	5
@@ -557,6 +511,10 @@ struct trace_buffer {
 
 	struct rb_irq_work		irq_work;
 	bool				time_stamp_abs;
+
+	unsigned int			subbuf_size;
+	unsigned int			subbuf_order;
+	unsigned int			max_data_size;
 };
 
 struct ring_buffer_iter {
@@ -570,150 +528,48 @@ struct ring_buffer_iter {
 	u64				read_stamp;
 	u64				page_stamp;
 	struct ring_buffer_event	*event;
+	size_t				event_size;
 	int				missed_events;
 };
 
-#ifdef RB_TIME_32
-
-/*
- * On 32 bit machines, local64_t is very expensive. As the ring
- * buffer doesn't need all the features of a true 64 bit atomic,
- * on 32 bit, it uses these functions (64 still uses local64_t).
- *
- * For the ring buffer, 64 bit required operations for the time is
- * the following:
- *
- *  - Reads may fail if it interrupted a modification of the time stamp.
- *      It will succeed if it did not interrupt another write even if
- *      the read itself is interrupted by a write.
- *      It returns whether it was successful or not.
- *
- *  - Writes always succeed and will overwrite other writes and writes
- *      that were done by events interrupting the current write.
- *
- *  - A write followed by a read of the same time stamp will always succeed,
- *      but may not contain the same value.
- *
- *  - A cmpxchg will fail if it interrupted another write or cmpxchg.
- *      Other than that, it acts like a normal cmpxchg.
- *
- * The 60 bit time stamp is broken up by 30 bits in a top and bottom half
- *  (bottom being the least significant 30 bits of the 60 bit time stamp).
- *
- * The two most significant bits of each half holds a 2 bit counter (0-3).
- * Each update will increment this counter by one.
- * When reading the top and bottom, if the two counter bits match then the
- *  top and bottom together make a valid 60 bit number.
- */
-#define RB_TIME_SHIFT	30
-#define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1)
-#define RB_TIME_MSB_SHIFT	 60
-
-static inline int rb_time_cnt(unsigned long val)
+int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s)
 {
-	return (val >> RB_TIME_SHIFT) & 3;
-}
-
-static inline u64 rb_time_val(unsigned long top, unsigned long bottom)
-{
-	u64 val;
-
-	val = top & RB_TIME_VAL_MASK;
-	val <<= RB_TIME_SHIFT;
-	val |= bottom & RB_TIME_VAL_MASK;
-
-	return val;
-}
-
-static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
-{
-	unsigned long top, bottom, msb;
-	unsigned long c;
-
-	/*
-	 * If the read is interrupted by a write, then the cnt will
-	 * be different. Loop until both top and bottom have been read
-	 * without interruption.
-	 */
-	do {
-		c = local_read(&t->cnt);
-		top = local_read(&t->top);
-		bottom = local_read(&t->bottom);
-		msb = local_read(&t->msb);
-	} while (c != local_read(&t->cnt));
-
-	*cnt = rb_time_cnt(top);
-
-	/* If top, msb or bottom counts don't match, this interrupted a write */
-	if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom))
-		return false;
-
-	/* The shift to msb will lose its cnt bits */
-	*ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT);
-	return true;
-}
-
-static bool rb_time_read(rb_time_t *t, u64 *ret)
-{
-	unsigned long cnt;
-
-	return __rb_time_read(t, ret, &cnt);
-}
-
-static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt)
-{
-	return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT);
-}
-
-static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom,
-				 unsigned long *msb)
-{
-	*top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK);
-	*bottom = (unsigned long)(val & RB_TIME_VAL_MASK);
-	*msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT);
-}
+	struct buffer_data_page field;
 
-static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt)
-{
-	val = rb_time_val_cnt(val, cnt);
-	local_set(t, val);
-}
+	trace_seq_printf(s, "\tfield: u64 timestamp;\t"
+			 "offset:0;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)sizeof(field.time_stamp),
+			 (unsigned int)is_signed_type(u64));
 
-static void rb_time_set(rb_time_t *t, u64 val)
-{
-	unsigned long cnt, top, bottom, msb;
+	trace_seq_printf(s, "\tfield: local_t commit;\t"
+			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)offsetof(typeof(field), commit),
+			 (unsigned int)sizeof(field.commit),
+			 (unsigned int)is_signed_type(long));
 
-	rb_time_split(val, &top, &bottom, &msb);
+	trace_seq_printf(s, "\tfield: int overwrite;\t"
+			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)offsetof(typeof(field), commit),
+			 1,
+			 (unsigned int)is_signed_type(long));
 
-	/* Writes always succeed with a valid number even if it gets interrupted. */
-	do {
-		cnt = local_inc_return(&t->cnt);
-		rb_time_val_set(&t->top, top, cnt);
-		rb_time_val_set(&t->bottom, bottom, cnt);
-		rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt);
-	} while (cnt != local_read(&t->cnt));
-}
+	trace_seq_printf(s, "\tfield: char data;\t"
+			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
+			 (unsigned int)offsetof(typeof(field), data),
+			 (unsigned int)buffer->subbuf_size,
+			 (unsigned int)is_signed_type(char));
 
-static inline bool
-rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
-{
-	return local_try_cmpxchg(l, &expect, set);
+	return !trace_seq_has_overflowed(s);
 }
 
-#else /* 64 bits */
-
-/* local64_t always succeeds */
-
-static inline bool rb_time_read(rb_time_t *t, u64 *ret)
+static inline void rb_time_read(rb_time_t *t, u64 *ret)
 {
 	*ret = local64_read(&t->time);
-	return true;
 }
 static void rb_time_set(rb_time_t *t, u64 val)
 {
 	local64_set(&t->time, val);
 }
-#endif
 
 /*
  * Enable this to make sure that the event passed to
@@ -820,10 +676,7 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer,
 	WARN_ONCE(1, "nest (%d) greater than max", nest);
 
  fail:
-	/* Can only fail on 32 bit */
-	if (!rb_time_read(&cpu_buffer->write_stamp, &ts))
-		/* Screw it, just read the current time */
-		ts = rb_time_stamp(cpu_buffer->buffer);
+	rb_time_read(&cpu_buffer->write_stamp, &ts);
 
 	return ts;
 }
@@ -1619,10 +1472,12 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
 		list_add(&bpage->list, pages);
 
-		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, 0);
+		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags,
+					cpu_buffer->buffer->subbuf_order);
 		if (!page)
 			goto free_pages;
 		bpage->page = page_address(page);
+		bpage->order = cpu_buffer->buffer->subbuf_order;
 		rb_init_page(bpage->page);
 
 		if (user_thread && fatal_signal_pending(current))
@@ -1701,7 +1556,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 	rb_check_bpage(cpu_buffer, bpage);
 
 	cpu_buffer->reader_page = bpage;
-	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0);
+
+	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, cpu_buffer->buffer->subbuf_order);
 	if (!page)
 		goto fail_free_reader;
 	bpage->page = page_address(page);
@@ -1784,7 +1640,14 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
 		goto fail_free_buffer;
 
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	/* Default buffer page size - one system page */
+	buffer->subbuf_order = 0;
+	buffer->subbuf_size = PAGE_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;
@@ -2103,7 +1966,7 @@ static void update_pages_handler(struct work_struct *work)
  * @size: the new size.
  * @cpu_id: the cpu buffer to resize
  *
- * Minimum size is 2 * BUF_PAGE_SIZE.
+ * Minimum size is 2 * buffer->subbuf_size.
  *
  * Returns 0 on success and < 0 on failure.
  */
@@ -2125,7 +1988,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 	    !cpumask_test_cpu(cpu_id, buffer->cpumask))
 		return 0;
 
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
 
 	/* we need a minimum of two pages */
 	if (nr_pages < 2)
@@ -2372,7 +2235,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
 	 */
 	barrier();
 
-	if ((iter->head + length) > commit || length > BUF_PAGE_SIZE)
+	if ((iter->head + length) > commit || length > iter->event_size)
 		/* Writer corrupted the read? */
 		goto reset;
 
@@ -2412,11 +2275,13 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
 }
 
 static __always_inline unsigned
-rb_event_index(struct ring_buffer_event *event)
+rb_event_index(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event)
 {
 	unsigned long addr = (unsigned long)event;
 
-	return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
+	addr &= (PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1;
+
+	return addr - BUF_PAGE_HDR_SIZE;
 }
 
 static void rb_inc_iter(struct ring_buffer_iter *iter)
@@ -2605,6 +2470,7 @@ static inline void
 rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	      unsigned long tail, struct rb_event_info *info)
 {
+	unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size);
 	struct buffer_page *tail_page = info->tail_page;
 	struct ring_buffer_event *event;
 	unsigned long length = info->length;
@@ -2613,13 +2479,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	 * Only the event that crossed the page boundary
 	 * must fill the old tail_page with padding.
 	 */
-	if (tail >= BUF_PAGE_SIZE) {
+	if (tail >= bsize) {
 		/*
 		 * If the page was filled, then we still need
 		 * to update the real_end. Reset it to zero
 		 * and the reader will ignore it.
 		 */
-		if (tail == BUF_PAGE_SIZE)
+		if (tail == bsize)
 			tail_page->real_end = 0;
 
 		local_sub(length, &tail_page->write);
@@ -2647,7 +2513,7 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	 * If we are less than the minimum size, we don't need to
 	 * worry about it.
 	 */
-	if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) {
+	if (tail > (bsize - RB_EVNT_MIN_SIZE)) {
 		/* No room for any events */
 
 		/* Mark the rest of the page with padding */
@@ -2662,19 +2528,19 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	}
 
 	/* Put in a discarded event */
-	event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE;
+	event->array[0] = (bsize - tail) - RB_EVNT_HDR_SIZE;
 	event->type_len = RINGBUF_TYPE_PADDING;
 	/* time delta must be non zero */
 	event->time_delta = 1;
 
 	/* account for padding bytes */
-	local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+	local_add(bsize - tail, &cpu_buffer->entries_bytes);
 
 	/* Make sure the padding is visible before the tail_page->write update */
 	smp_wmb();
 
 	/* Set write to end of buffer */
-	length = (tail + length) - BUF_PAGE_SIZE;
+	length = (tail + length) - bsize;
 	local_sub(length, &tail_page->write);
 }
 
@@ -2788,7 +2654,8 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 
 /* Slow path */
 static struct ring_buffer_event *
-rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
+rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+		  struct ring_buffer_event *event, u64 delta, bool abs)
 {
 	if (abs)
 		event->type_len = RINGBUF_TYPE_TIME_STAMP;
@@ -2796,7 +2663,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
 		event->type_len = RINGBUF_TYPE_TIME_EXTEND;
 
 	/* Not the first event on the page, or not delta? */
-	if (abs || rb_event_index(event)) {
+	if (abs || rb_event_index(cpu_buffer, event)) {
 		event->time_delta = delta & TS_MASK;
 		event->array[0] = delta >> TS_SHIFT;
 	} else {
@@ -2826,7 +2693,7 @@ rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
 		  (unsigned long long)info->ts,
 		  (unsigned long long)info->before,
 		  (unsigned long long)info->after,
-		  (unsigned long long)(rb_time_read(&cpu_buffer->write_stamp, &write_stamp) ? write_stamp : 0),
+		  (unsigned long long)({rb_time_read(&cpu_buffer->write_stamp, &write_stamp); write_stamp;}),
 		  sched_clock_stable() ? "" :
 		  "If you just came from a suspend/resume,\n"
 		  "please switch to the trace global clock:\n"
@@ -2870,7 +2737,7 @@ static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
 		if (!abs)
 			info->delta = 0;
 	}
-	*event = rb_add_time_stamp(*event, info->delta, abs);
+	*event = rb_add_time_stamp(cpu_buffer, *event, info->delta, abs);
 	*length -= RB_LEN_TIME_EXTEND;
 	*delta = 0;
 }
@@ -2954,10 +2821,10 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	struct buffer_page *bpage;
 	unsigned long addr;
 
-	new_index = rb_event_index(event);
+	new_index = rb_event_index(cpu_buffer, event);
 	old_index = new_index + rb_event_ts_length(event);
 	addr = (unsigned long)event;
-	addr &= PAGE_MASK;
+	addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1);
 
 	bpage = READ_ONCE(cpu_buffer->tail_page);
 
@@ -3344,6 +3211,76 @@ EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
 #define CHECK_FULL_PAGE		1L
 
 #ifdef CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS
+
+static const char *show_irq_str(int bits)
+{
+	const char *type[] = {
+		".",	// 0
+		"s",	// 1
+		"h",	// 2
+		"Hs",	// 3
+		"n",	// 4
+		"Ns",	// 5
+		"Nh",	// 6
+		"NHs",	// 7
+	};
+
+	return type[bits];
+}
+
+/* Assume this is an trace event */
+static const char *show_flags(struct ring_buffer_event *event)
+{
+	struct trace_entry *entry;
+	int bits = 0;
+
+	if (rb_event_data_length(event) - RB_EVNT_HDR_SIZE < sizeof(*entry))
+		return "X";
+
+	entry = ring_buffer_event_data(event);
+
+	if (entry->flags & TRACE_FLAG_SOFTIRQ)
+		bits |= 1;
+
+	if (entry->flags & TRACE_FLAG_HARDIRQ)
+		bits |= 2;
+
+	if (entry->flags & TRACE_FLAG_NMI)
+		bits |= 4;
+
+	return show_irq_str(bits);
+}
+
+static const char *show_irq(struct ring_buffer_event *event)
+{
+	struct trace_entry *entry;
+
+	if (rb_event_data_length(event) - RB_EVNT_HDR_SIZE < sizeof(*entry))
+		return "";
+
+	entry = ring_buffer_event_data(event);
+	if (entry->flags & TRACE_FLAG_IRQS_OFF)
+		return "d";
+	return "";
+}
+
+static const char *show_interrupt_level(void)
+{
+	unsigned long pc = preempt_count();
+	unsigned char level = 0;
+
+	if (pc & SOFTIRQ_OFFSET)
+		level |= 1;
+
+	if (pc & HARDIRQ_MASK)
+		level |= 2;
+
+	if (pc & NMI_MASK)
+		level |= 4;
+
+	return show_irq_str(level);
+}
+
 static void dump_buffer_page(struct buffer_data_page *bpage,
 			     struct rb_event_info *info,
 			     unsigned long tail)
@@ -3364,34 +3301,57 @@ static void dump_buffer_page(struct buffer_data_page *bpage,
 		case RINGBUF_TYPE_TIME_EXTEND:
 			delta = rb_event_time_stamp(event);
 			ts += delta;
-			pr_warn("  [%lld] delta:%lld TIME EXTEND\n", ts, delta);
+			pr_warn(" 0x%x: [%lld] delta:%lld TIME EXTEND\n",
+				e, ts, delta);
 			break;
 
 		case RINGBUF_TYPE_TIME_STAMP:
 			delta = rb_event_time_stamp(event);
 			ts = rb_fix_abs_ts(delta, ts);
-			pr_warn("  [%lld] absolute:%lld TIME STAMP\n", ts, delta);
+			pr_warn(" 0x%x:  [%lld] absolute:%lld TIME STAMP\n",
+				e, ts, delta);
 			break;
 
 		case RINGBUF_TYPE_PADDING:
 			ts += event->time_delta;
-			pr_warn("  [%lld] delta:%d PADDING\n", ts, event->time_delta);
+			pr_warn(" 0x%x:  [%lld] delta:%d PADDING\n",
+				e, ts, event->time_delta);
 			break;
 
 		case RINGBUF_TYPE_DATA:
 			ts += event->time_delta;
-			pr_warn("  [%lld] delta:%d\n", ts, event->time_delta);
+			pr_warn(" 0x%x:  [%lld] delta:%d %s%s\n",
+				e, ts, event->time_delta,
+				show_flags(event), show_irq(event));
 			break;
 
 		default:
 			break;
 		}
 	}
+	pr_warn("expected end:0x%lx last event actually ended at:0x%x\n", tail, e);
 }
 
 static DEFINE_PER_CPU(atomic_t, checking);
 static atomic_t ts_dump;
 
+#define buffer_warn_return(fmt, ...)					\
+	do {								\
+		/* If another report is happening, ignore this one */	\
+		if (atomic_inc_return(&ts_dump) != 1) {			\
+			atomic_dec(&ts_dump);				\
+			goto out;					\
+		}							\
+		atomic_inc(&cpu_buffer->record_disabled);		\
+		pr_warn(fmt, ##__VA_ARGS__);				\
+		dump_buffer_page(bpage, info, tail);			\
+		atomic_dec(&ts_dump);					\
+		/* There's some cases in boot up that this can happen */ \
+		if (WARN_ON_ONCE(system_state != SYSTEM_BOOTING))	\
+			/* Do not re-enable checking */			\
+			return;						\
+	} while (0)
+
 /*
  * Check if the current event time stamp matches the deltas on
  * the buffer page.
@@ -3445,7 +3405,12 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 
 		case RINGBUF_TYPE_TIME_STAMP:
 			delta = rb_event_time_stamp(event);
-			ts = rb_fix_abs_ts(delta, ts);
+			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:
@@ -3462,23 +3427,11 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 	}
 	if ((full && ts > info->ts) ||
 	    (!full && ts + info->delta != info->ts)) {
-		/* If another report is happening, ignore this one */
-		if (atomic_inc_return(&ts_dump) != 1) {
-			atomic_dec(&ts_dump);
-			goto out;
-		}
-		atomic_inc(&cpu_buffer->record_disabled);
-		/* There's some cases in boot up that this can happen */
-		WARN_ON_ONCE(system_state != SYSTEM_BOOTING);
-		pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s\n",
-			cpu_buffer->cpu,
-			ts + info->delta, info->ts, info->delta,
-			info->before, info->after,
-			full ? " (full)" : "");
-		dump_buffer_page(bpage, info, tail);
-		atomic_dec(&ts_dump);
-		/* Do not re-enable checking */
-		return;
+		buffer_warn_return("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s context:%s\n",
+				   cpu_buffer->cpu,
+				   ts + info->delta, info->ts, info->delta,
+				   info->before, info->after,
+				   full ? " (full)" : "", show_interrupt_level());
 	}
 out:
 	atomic_dec(this_cpu_ptr(&checking));
@@ -3498,16 +3451,14 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	struct ring_buffer_event *event;
 	struct buffer_page *tail_page;
 	unsigned long tail, write, w;
-	bool a_ok;
-	bool b_ok;
 
 	/* Don't let the compiler play games with cpu_buffer->tail_page */
 	tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page);
 
  /*A*/	w = local_read(&tail_page->write) & RB_WRITE_MASK;
 	barrier();
-	b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
-	a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+	rb_time_read(&cpu_buffer->before_stamp, &info->before);
+	rb_time_read(&cpu_buffer->write_stamp, &info->after);
 	barrier();
 	info->ts = rb_time_stamp(cpu_buffer->buffer);
 
@@ -3522,7 +3473,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		if (!w) {
 			/* Use the sub-buffer timestamp */
 			info->delta = 0;
-		} else if (unlikely(!a_ok || !b_ok || info->before != info->after)) {
+		} else if (unlikely(info->before != info->after)) {
 			info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND;
 			info->length += RB_LEN_TIME_EXTEND;
 		} else {
@@ -3544,7 +3495,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	tail = write - info->length;
 
 	/* See if we shot pass the end of this buffer page */
-	if (unlikely(write > BUF_PAGE_SIZE)) {
+	if (unlikely(write > cpu_buffer->buffer->subbuf_size)) {
 		check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
 		return rb_move_tail(cpu_buffer, tail, info);
 	}
@@ -3571,8 +3522,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		/* SLOW PATH - Interrupted between A and C */
 
 		/* Save the old before_stamp */
-		a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
-		RB_WARN_ON(cpu_buffer, !a_ok);
+		rb_time_read(&cpu_buffer->before_stamp, &info->before);
 
 		/*
 		 * Read a new timestamp and update the before_stamp to make
@@ -3584,9 +3534,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		rb_time_set(&cpu_buffer->before_stamp, ts);
 
 		barrier();
- /*E*/		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-		/* Was interrupted before here, write_stamp must be valid */
-		RB_WARN_ON(cpu_buffer, !a_ok);
+ /*E*/		rb_time_read(&cpu_buffer->write_stamp, &info->after);
 		barrier();
  /*F*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
 		    info->after == info->before && info->after < ts) {
@@ -3678,7 +3626,7 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
 		add_ts_default = RB_ADD_STAMP_ABSOLUTE;
 		info.length += RB_LEN_TIME_EXTEND;
-		if (info.length > BUF_MAX_DATA_SIZE)
+		if (info.length > cpu_buffer->buffer->max_data_size)
 			goto out_fail;
 	} else {
 		add_ts_default = RB_ADD_STAMP_NONE;
@@ -3753,7 +3701,7 @@ ring_buffer_lock_reserve(struct trace_buffer *buffer, unsigned long length)
 	if (unlikely(atomic_read(&cpu_buffer->record_disabled)))
 		goto out;
 
-	if (unlikely(length > BUF_MAX_DATA_SIZE))
+	if (unlikely(length > buffer->max_data_size))
 		goto out;
 
 	if (unlikely(trace_recursive_lock(cpu_buffer)))
@@ -3787,7 +3735,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer,
 	struct buffer_page *bpage = cpu_buffer->commit_page;
 	struct buffer_page *start;
 
-	addr &= PAGE_MASK;
+	addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1);
 
 	/* Do the likely case first */
 	if (likely(bpage->page == (void *)addr)) {
@@ -3903,7 +3851,7 @@ int ring_buffer_write(struct trace_buffer *buffer,
 	if (atomic_read(&cpu_buffer->record_disabled))
 		goto out;
 
-	if (length > BUF_MAX_DATA_SIZE)
+	if (length > buffer->max_data_size)
 		goto out;
 
 	if (unlikely(trace_recursive_lock(cpu_buffer)))
@@ -4483,6 +4431,7 @@ static struct buffer_page *
 rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = NULL;
+	unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size);
 	unsigned long overwrite;
 	unsigned long flags;
 	int nr_loops = 0;
@@ -4618,7 +4567,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 #define USECS_WAIT	1000000
         for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) {
 		/* If the write is past the end of page, a writer is still updating it */
-		if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE))
+		if (likely(!reader || rb_page_write(reader) <= bsize))
 			break;
 
 		udelay(1);
@@ -5062,7 +5011,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
 		return NULL;
 
 	/* Holds the entire event: data and meta data */
-	iter->event = kmalloc(BUF_PAGE_SIZE, flags);
+	iter->event_size = buffer->subbuf_size;
+	iter->event = kmalloc(iter->event_size, flags);
 	if (!iter->event) {
 		kfree(iter);
 		return NULL;
@@ -5178,19 +5128,28 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_advance);
  */
 unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
 {
-	/*
-	 * Earlier, this method returned
-	 *	BUF_PAGE_SIZE * buffer->nr_pages
-	 * Since the nr_pages field is now removed, we have converted this to
-	 * return the per cpu buffer value.
-	 */
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
-	return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages;
+	return buffer->subbuf_size * buffer->buffers[cpu]->nr_pages;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
+/**
+ * ring_buffer_max_event_size - return the max data size of an event
+ * @buffer: The ring buffer.
+ *
+ * Returns the maximum size an event can be.
+ */
+unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer)
+{
+	/* If abs timestamp is requested, events have a timestamp too */
+	if (ring_buffer_time_stamp_abs(buffer))
+		return buffer->max_data_size - RB_LEN_TIME_EXTEND;
+	return buffer->max_data_size;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_max_event_size);
+
 static void rb_clear_buffer_page(struct buffer_page *page)
 {
 	local_set(&page->write, 0);
@@ -5461,6 +5420,9 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a,
 	if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages)
 		goto out;
 
+	if (buffer_a->subbuf_order != buffer_b->subbuf_order)
+		goto out;
+
 	ret = -EAGAIN;
 
 	if (atomic_read(&buffer_a->record_disabled))
@@ -5532,40 +5494,48 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
  * Returns:
  *  The page allocated, or ERR_PTR
  */
-void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
+struct buffer_data_read_page *
+ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct buffer_data_page *bpage = NULL;
+	struct buffer_data_read_page *bpage = NULL;
 	unsigned long flags;
 	struct page *page;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return ERR_PTR(-ENODEV);
 
+	bpage = kzalloc(sizeof(*bpage), GFP_KERNEL);
+	if (!bpage)
+		return ERR_PTR(-ENOMEM);
+
+	bpage->order = buffer->subbuf_order;
 	cpu_buffer = buffer->buffers[cpu];
 	local_irq_save(flags);
 	arch_spin_lock(&cpu_buffer->lock);
 
 	if (cpu_buffer->free_page) {
-		bpage = cpu_buffer->free_page;
+		bpage->data = cpu_buffer->free_page;
 		cpu_buffer->free_page = NULL;
 	}
 
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
-	if (bpage)
+	if (bpage->data)
 		goto out;
 
-	page = alloc_pages_node(cpu_to_node(cpu),
-				GFP_KERNEL | __GFP_NORETRY, 0);
-	if (!page)
+	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY,
+				cpu_buffer->buffer->subbuf_order);
+	if (!page) {
+		kfree(bpage);
 		return ERR_PTR(-ENOMEM);
+	}
 
-	bpage = page_address(page);
+	bpage->data = page_address(page);
 
  out:
-	rb_init_page(bpage);
+	rb_init_page(bpage->data);
 
 	return bpage;
 }
@@ -5575,14 +5545,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
  * ring_buffer_free_read_page - free an allocated read page
  * @buffer: the buffer the page was allocate for
  * @cpu: the cpu buffer the page came from
- * @data: the page to free
+ * @data_page: the page to free
  *
  * Free a page allocated from ring_buffer_alloc_read_page.
  */
-void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data)
+void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu,
+				struct buffer_data_read_page *data_page)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct buffer_data_page *bpage = data;
+	struct buffer_data_page *bpage = data_page->data;
 	struct page *page = virt_to_page(bpage);
 	unsigned long flags;
 
@@ -5591,8 +5562,12 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data
 
 	cpu_buffer = buffer->buffers[cpu];
 
-	/* If the page is still in use someplace else, we can't reuse it */
-	if (page_ref_count(page) > 1)
+	/*
+	 * If the page is still in use someplace else, or order of the page
+	 * is different from the subbuffer order of the buffer -
+	 * we can't reuse it
+	 */
+	if (page_ref_count(page) > 1 || data_page->order != buffer->subbuf_order)
 		goto out;
 
 	local_irq_save(flags);
@@ -5607,7 +5582,8 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data
 	local_irq_restore(flags);
 
  out:
-	free_page((unsigned long)bpage);
+	free_pages((unsigned long)bpage, data_page->order);
+	kfree(data_page);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
 
@@ -5628,9 +5604,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *	rpage = ring_buffer_alloc_read_page(buffer, cpu);
  *	if (IS_ERR(rpage))
  *		return PTR_ERR(rpage);
- *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
+ *	ret = ring_buffer_read_page(buffer, rpage, len, cpu, 0);
  *	if (ret >= 0)
- *		process_page(rpage, ret);
+ *		process_page(ring_buffer_read_page_data(rpage), ret);
+ *	ring_buffer_free_read_page(buffer, cpu, rpage);
  *
  * When @full is set, the function will not return true unless
  * the writer is off the reader page.
@@ -5645,7 +5622,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *  <0 if no data has been transferred.
  */
 int ring_buffer_read_page(struct trace_buffer *buffer,
-			  void **data_page, size_t len, int cpu, int full)
+			  struct buffer_data_read_page *data_page,
+			  size_t len, int cpu, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
@@ -5670,10 +5648,12 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 
 	len -= BUF_PAGE_HDR_SIZE;
 
-	if (!data_page)
+	if (!data_page || !data_page->data)
+		goto out;
+	if (data_page->order != buffer->subbuf_order)
 		goto out;
 
-	bpage = *data_page;
+	bpage = data_page->data;
 	if (!bpage)
 		goto out;
 
@@ -5767,11 +5747,11 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		/* swap the pages */
 		rb_init_page(bpage);
 		bpage = reader->page;
-		reader->page = *data_page;
+		reader->page = data_page->data;
 		local_set(&reader->write, 0);
 		local_set(&reader->entries, 0);
 		reader->read = 0;
-		*data_page = bpage;
+		data_page->data = bpage;
 
 		/*
 		 * Use the real_end for the data size,
@@ -5793,7 +5773,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		/* If there is room at the end of the page to save the
 		 * missed events, then record it there.
 		 */
-		if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+		if (buffer->subbuf_size - commit >= sizeof(missed_events)) {
 			memcpy(&bpage->data[commit], &missed_events,
 			       sizeof(missed_events));
 			local_add(RB_MISSED_STORED, &bpage->commit);
@@ -5805,8 +5785,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 	/*
 	 * This page may be off to user land. Zero it out here.
 	 */
-	if (commit < BUF_PAGE_SIZE)
-		memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);
+	if (commit < buffer->subbuf_size)
+		memset(&bpage->data[commit], 0, buffer->subbuf_size - commit);
 
  out_unlock:
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
@@ -5816,6 +5796,209 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
+/**
+ * ring_buffer_read_page_data - get pointer to the data in the page.
+ * @page:  the page to get the data from
+ *
+ * Returns pointer to the actual data in this page.
+ */
+void *ring_buffer_read_page_data(struct buffer_data_read_page *page)
+{
+	return page->data;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_page_data);
+
+/**
+ * ring_buffer_subbuf_size_get - get size of the sub buffer.
+ * @buffer: the buffer to get the sub buffer size from
+ *
+ * Returns size of the sub buffer, in bytes.
+ */
+int ring_buffer_subbuf_size_get(struct trace_buffer *buffer)
+{
+	return buffer->subbuf_size + BUF_PAGE_HDR_SIZE;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_size_get);
+
+/**
+ * ring_buffer_subbuf_order_get - get order of system sub pages in one buffer page.
+ * @buffer: The ring_buffer to get the system sub page order from
+ *
+ * By default, one ring buffer sub page equals to one system page. This parameter
+ * is configurable, per ring buffer. The size of the ring buffer sub page can be
+ * extended, but must be an order of system page size.
+ *
+ * Returns the order of buffer sub page size, in system pages:
+ * 0 means the sub buffer size is 1 system page and so forth.
+ * In case of an error < 0 is returned.
+ */
+int ring_buffer_subbuf_order_get(struct trace_buffer *buffer)
+{
+	if (!buffer)
+		return -EINVAL;
+
+	return buffer->subbuf_order;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_get);
+
+/**
+ * ring_buffer_subbuf_order_set - set the size of ring buffer sub page.
+ * @buffer: The ring_buffer to set the new page size.
+ * @order: Order of the system pages in one sub buffer page
+ *
+ * By default, one ring buffer pages equals to one system page. This API can be
+ * used to set new size of the ring buffer page. The size must be order of
+ * system page size, that's why the input parameter @order is the order of
+ * system pages that are allocated for one ring buffer page:
+ *  0 - 1 system page
+ *  1 - 2 system pages
+ *  3 - 4 system pages
+ *  ...
+ *
+ * Returns 0 on success or < 0 in case of an error.
+ */
+int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct buffer_page *bpage, *tmp;
+	int old_order, old_size;
+	int nr_pages;
+	int psize;
+	int err;
+	int cpu;
+
+	if (!buffer || order < 0)
+		return -EINVAL;
+
+	if (buffer->subbuf_order == order)
+		return 0;
+
+	psize = (1 << order) * PAGE_SIZE;
+	if (psize <= BUF_PAGE_HDR_SIZE)
+		return -EINVAL;
+
+	old_order = buffer->subbuf_order;
+	old_size = buffer->subbuf_size;
+
+	/* prevent another thread from changing buffer sizes */
+	mutex_lock(&buffer->mutex);
+	atomic_inc(&buffer->record_disabled);
+
+	/* Make sure all commits have finished */
+	synchronize_rcu();
+
+	buffer->subbuf_order = order;
+	buffer->subbuf_size = psize - BUF_PAGE_HDR_SIZE;
+
+	/* Make sure all new buffers are allocated, before deleting the old ones */
+	for_each_buffer_cpu(buffer, cpu) {
+
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			continue;
+
+		cpu_buffer = buffer->buffers[cpu];
+
+		/* Update the number of pages to match the new size */
+		nr_pages = old_size * buffer->buffers[cpu]->nr_pages;
+		nr_pages = DIV_ROUND_UP(nr_pages, buffer->subbuf_size);
+
+		/* we need a minimum of two pages */
+		if (nr_pages < 2)
+			nr_pages = 2;
+
+		cpu_buffer->nr_pages_to_update = nr_pages;
+
+		/* Include the reader page */
+		nr_pages++;
+
+		/* Allocate the new size buffer */
+		INIT_LIST_HEAD(&cpu_buffer->new_pages);
+		if (__rb_allocate_pages(cpu_buffer, nr_pages,
+					&cpu_buffer->new_pages)) {
+			/* not enough memory for new pages */
+			err = -ENOMEM;
+			goto error;
+		}
+	}
+
+	for_each_buffer_cpu(buffer, cpu) {
+
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			continue;
+
+		cpu_buffer = buffer->buffers[cpu];
+
+		/* 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);
+
+		/* 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 */
+		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);
+
+		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;
+
+		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);
+		cpu_buffer->free_page = NULL;
+
+		rb_head_page_activate(cpu_buffer);
+
+		rb_check_pages(cpu_buffer);
+	}
+
+	atomic_dec(&buffer->record_disabled);
+	mutex_unlock(&buffer->mutex);
+
+	return 0;
+
+error:
+	buffer->subbuf_order = old_order;
+	buffer->subbuf_size = old_size;
+
+	atomic_dec(&buffer->record_disabled);
+	mutex_unlock(&buffer->mutex);
+
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		if (!cpu_buffer->nr_pages_to_update)
+			continue;
+
+		list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_set);
+
 /*
  * We only allocate new buffers, never free them if the CPU goes down.
  * If we were to free the buffer, then the user would lose any trace that was in

kernel/trace/ring_buffer_benchmark.c

@@ -104,10 +104,11 @@ static enum event_status read_event(int cpu)
 
 static enum event_status read_page(int cpu)
 {
+	struct buffer_data_read_page *bpage;
 	struct ring_buffer_event *event;
 	struct rb_page *rpage;
 	unsigned long commit;
-	void *bpage;
+	int page_size;
 	int *entry;
 	int ret;
 	int inc;
@@ -117,14 +118,15 @@ static enum event_status read_page(int cpu)
 	if (IS_ERR(bpage))
 		return EVENT_DROPPED;
 
-	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
+	page_size = ring_buffer_subbuf_size_get(buffer);
+	ret = ring_buffer_read_page(buffer, bpage, page_size, cpu, 1);
 	if (ret >= 0) {
-		rpage = bpage;
+		rpage = ring_buffer_read_page_data(bpage);
 		/* The commit may have missed event flags set, clear them */
 		commit = local_read(&rpage->commit) & 0xfffff;
 		for (i = 0; i < commit && !test_error ; i += inc) {
 
-			if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
+			if (i >= (page_size - offsetof(struct rb_page, data))) {
 				TEST_ERROR();
 				break;
 			}

kernel/trace/trace.c

@@ -1263,10 +1263,17 @@ static void set_buffer_entries(struct array_buffer *buf, unsigned long val);
 
 int tracing_alloc_snapshot_instance(struct trace_array *tr)
 {
+	int order;
 	int ret;
 
 	if (!tr->allocated_snapshot) {
 
+		/* Make the snapshot buffer have the same order as main buffer */
+		order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
+		ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order);
+		if (ret < 0)
+			return ret;
+
 		/* allocate spare buffer */
 		ret = resize_buffer_duplicate_size(&tr->max_buffer,
 				   &tr->array_buffer, RING_BUFFER_ALL_CPUS);
@@ -1286,6 +1293,7 @@ static void free_snapshot(struct trace_array *tr)
 	 * The max_tr ring buffer has some state (e.g. ring->clock) and
 	 * we want preserve it.
 	 */
+	ring_buffer_subbuf_order_set(tr->max_buffer.buffer, 0);
 	ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS);
 	set_buffer_entries(&tr->max_buffer, 1);
 	tracing_reset_online_cpus(&tr->max_buffer);
@@ -3767,7 +3775,7 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str,
 
 	/* OK if part of the temp seq buffer */
 	if ((addr >= (unsigned long)iter->tmp_seq.buffer) &&
-	    (addr < (unsigned long)iter->tmp_seq.buffer + PAGE_SIZE))
+	    (addr < (unsigned long)iter->tmp_seq.buffer + TRACE_SEQ_BUFFER_SIZE))
 		return true;
 
 	/* Core rodata can not be freed */
@@ -5032,7 +5040,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int tracing_release_generic_tr(struct inode *inode, struct file *file)
+int tracing_release_generic_tr(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
 
@@ -6946,8 +6954,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 		goto out;
 	}
 
-	if (cnt >= PAGE_SIZE)
-		cnt = PAGE_SIZE - 1;
+	if (cnt >= TRACE_SEQ_BUFFER_SIZE)
+		cnt = TRACE_SEQ_BUFFER_SIZE - 1;
 
 	/* reset all but tr, trace, and overruns */
 	trace_iterator_reset(iter);
@@ -7292,8 +7300,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	enum event_trigger_type tt = ETT_NONE;
 	struct trace_buffer *buffer;
 	struct print_entry *entry;
+	int meta_size;
 	ssize_t written;
-	int size;
+	size_t size;
 	int len;
 
 /* Used in tracing_mark_raw_write() as well */
@@ -7306,23 +7315,44 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (!(tr->trace_flags & TRACE_ITER_MARKERS))
 		return -EINVAL;
 
-	if (cnt > TRACE_BUF_SIZE)
-		cnt = TRACE_BUF_SIZE;
-
-	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
+	if ((ssize_t)cnt < 0)
+		return -EINVAL;
 
-	size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */
+	meta_size = sizeof(*entry) + 2;  /* add '\0' and possible '\n' */
+ again:
+	size = cnt + meta_size;
 
 	/* If less than "<faulted>", then make sure we can still add that */
 	if (cnt < FAULTED_SIZE)
 		size += FAULTED_SIZE - cnt;
 
+	if (size > TRACE_SEQ_BUFFER_SIZE) {
+		cnt -= size - TRACE_SEQ_BUFFER_SIZE;
+		goto again;
+	}
+
 	buffer = tr->array_buffer.buffer;
 	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					    tracing_gen_ctx());
-	if (unlikely(!event))
+	if (unlikely(!event)) {
+		/*
+		 * If the size was greater than what was allowed, then
+		 * make it smaller and try again.
+		 */
+		if (size > ring_buffer_max_event_size(buffer)) {
+			/* cnt < FAULTED size should never be bigger than max */
+			if (WARN_ON_ONCE(cnt < FAULTED_SIZE))
+				return -EBADF;
+			cnt = ring_buffer_max_event_size(buffer) - meta_size;
+			/* The above should only happen once */
+			if (WARN_ON_ONCE(cnt + meta_size == size))
+				return -EBADF;
+			goto again;
+		}
+
 		/* Ring buffer disabled, return as if not open for write */
 		return -EBADF;
+	}
 
 	entry = ring_buffer_event_data(event);
 	entry->ip = _THIS_IP_;
@@ -7357,9 +7387,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	return written;
 }
 
-/* Limit it for now to 3K (including tag) */
-#define RAW_DATA_MAX_SIZE (1024*3)
-
 static ssize_t
 tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
@@ -7381,19 +7408,18 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 		return -EINVAL;
 
 	/* The marker must at least have a tag id */
-	if (cnt < sizeof(unsigned int) || cnt > RAW_DATA_MAX_SIZE)
+	if (cnt < sizeof(unsigned int))
 		return -EINVAL;
 
-	if (cnt > TRACE_BUF_SIZE)
-		cnt = TRACE_BUF_SIZE;
-
-	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
-
 	size = sizeof(*entry) + cnt;
 	if (cnt < FAULT_SIZE_ID)
 		size += FAULT_SIZE_ID - cnt;
 
 	buffer = tr->array_buffer.buffer;
+
+	if (size > ring_buffer_max_event_size(buffer))
+		return -EINVAL;
+
 	event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size,
 					    tracing_gen_ctx());
 	if (!event)
@@ -7578,6 +7604,7 @@ struct ftrace_buffer_info {
 	struct trace_iterator	iter;
 	void			*spare;
 	unsigned int		spare_cpu;
+	unsigned int		spare_size;
 	unsigned int		read;
 };
 
@@ -8282,6 +8309,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 {
 	struct ftrace_buffer_info *info = filp->private_data;
 	struct trace_iterator *iter = &info->iter;
+	void *trace_data;
+	int page_size;
 	ssize_t ret = 0;
 	ssize_t size;
 
@@ -8293,6 +8322,17 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 		return -EBUSY;
 #endif
 
+	page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer);
+
+	/* Make sure the spare matches the current sub buffer size */
+	if (info->spare) {
+		if (page_size != info->spare_size) {
+			ring_buffer_free_read_page(iter->array_buffer->buffer,
+						   info->spare_cpu, info->spare);
+			info->spare = NULL;
+		}
+	}
+
 	if (!info->spare) {
 		info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer,
 							  iter->cpu_file);
@@ -8301,19 +8341,20 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 			info->spare = NULL;
 		} else {
 			info->spare_cpu = iter->cpu_file;
+			info->spare_size = page_size;
 		}
 	}
 	if (!info->spare)
 		return ret;
 
 	/* Do we have previous read data to read? */
-	if (info->read < PAGE_SIZE)
+	if (info->read < page_size)
 		goto read;
 
  again:
 	trace_access_lock(iter->cpu_file);
 	ret = ring_buffer_read_page(iter->array_buffer->buffer,
-				    &info->spare,
+				    info->spare,
 				    count,
 				    iter->cpu_file, 0);
 	trace_access_unlock(iter->cpu_file);
@@ -8334,11 +8375,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
 	info->read = 0;
  read:
-	size = PAGE_SIZE - info->read;
+	size = page_size - info->read;
 	if (size > count)
 		size = count;
-
-	ret = copy_to_user(ubuf, info->spare + info->read, size);
+	trace_data = ring_buffer_read_page_data(info->spare);
+	ret = copy_to_user(ubuf, trace_data + info->read, size);
 	if (ret == size)
 		return -EFAULT;
 
@@ -8449,6 +8490,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		.spd_release	= buffer_spd_release,
 	};
 	struct buffer_ref *ref;
+	int page_size;
 	int entries, i;
 	ssize_t ret = 0;
 
@@ -8457,13 +8499,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		return -EBUSY;
 #endif
 
-	if (*ppos & (PAGE_SIZE - 1))
+	page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer);
+	if (*ppos & (page_size - 1))
 		return -EINVAL;
 
-	if (len & (PAGE_SIZE - 1)) {
-		if (len < PAGE_SIZE)
+	if (len & (page_size - 1)) {
+		if (len < page_size)
 			return -EINVAL;
-		len &= PAGE_MASK;
+		len &= (~(page_size - 1));
 	}
 
 	if (splice_grow_spd(pipe, &spd))
@@ -8473,7 +8516,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	trace_access_lock(iter->cpu_file);
 	entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file);
 
-	for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) {
+	for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= page_size) {
 		struct page *page;
 		int r;
 
@@ -8494,7 +8537,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		}
 		ref->cpu = iter->cpu_file;
 
-		r = ring_buffer_read_page(ref->buffer, &ref->page,
+		r = ring_buffer_read_page(ref->buffer, ref->page,
 					  len, iter->cpu_file, 1);
 		if (r < 0) {
 			ring_buffer_free_read_page(ref->buffer, ref->cpu,
@@ -8503,14 +8546,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 		}
 
-		page = virt_to_page(ref->page);
+		page = virt_to_page(ring_buffer_read_page_data(ref->page));
 
 		spd.pages[i] = page;
-		spd.partial[i].len = PAGE_SIZE;
+		spd.partial[i].len = page_size;
 		spd.partial[i].offset = 0;
 		spd.partial[i].private = (unsigned long)ref;
 		spd.nr_pages++;
-		*ppos += PAGE_SIZE;
+		*ppos += page_size;
 
 		entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file);
 	}
@@ -9354,6 +9397,103 @@ static const struct file_operations buffer_percent_fops = {
 	.llseek		= default_llseek,
 };
 
+static ssize_t
+buffer_subbuf_size_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	size_t size;
+	char buf[64];
+	int order;
+	int r;
+
+	order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
+	size = (PAGE_SIZE << order) / 1024;
+
+	r = sprintf(buf, "%zd\n", size);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+buffer_subbuf_size_write(struct file *filp, const char __user *ubuf,
+			 size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	unsigned long val;
+	int old_order;
+	int order;
+	int pages;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	val *= 1024; /* value passed in is in KB */
+
+	pages = DIV_ROUND_UP(val, PAGE_SIZE);
+	order = fls(pages - 1);
+
+	/* limit between 1 and 128 system pages */
+	if (order < 0 || order > 7)
+		return -EINVAL;
+
+	/* Do not allow tracing while changing the order of the ring buffer */
+	tracing_stop_tr(tr);
+
+	old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer);
+	if (old_order == order)
+		goto out;
+
+	ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, order);
+	if (ret)
+		goto out;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+
+	if (!tr->allocated_snapshot)
+		goto out_max;
+
+	ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order);
+	if (ret) {
+		/* Put back the old order */
+		cnt = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, old_order);
+		if (WARN_ON_ONCE(cnt)) {
+			/*
+			 * AARGH! We are left with different orders!
+			 * The max buffer is our "snapshot" buffer.
+			 * When a tracer needs a snapshot (one of the
+			 * latency tracers), it swaps the max buffer
+			 * with the saved snap shot. We succeeded to
+			 * update the order of the main buffer, but failed to
+			 * update the order of the max buffer. But when we tried
+			 * to reset the main buffer to the original size, we
+			 * failed there too. This is very unlikely to
+			 * happen, but if it does, warn and kill all
+			 * tracing.
+			 */
+			tracing_disabled = 1;
+		}
+		goto out;
+	}
+ out_max:
+#endif
+	(*ppos)++;
+ out:
+	if (ret)
+		cnt = ret;
+	tracing_start_tr(tr);
+	return cnt;
+}
+
+static const struct file_operations buffer_subbuf_size_fops = {
+	.open		= tracing_open_generic_tr,
+	.read		= buffer_subbuf_size_read,
+	.write		= buffer_subbuf_size_write,
+	.release	= tracing_release_generic_tr,
+	.llseek		= default_llseek,
+};
+
 static struct dentry *trace_instance_dir;
 
 static void
@@ -9504,7 +9644,8 @@ static int trace_array_create_dir(struct trace_array *tr)
 	return ret;
 }
 
-static struct trace_array *trace_array_create(const char *name)
+static struct trace_array *
+trace_array_create_systems(const char *name, const char *systems)
 {
 	struct trace_array *tr;
 	int ret;
@@ -9524,6 +9665,12 @@ static struct trace_array *trace_array_create(const char *name)
 	if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL))
 		goto out_free_tr;
 
+	if (systems) {
+		tr->system_names = kstrdup_const(systems, GFP_KERNEL);
+		if (!tr->system_names)
+			goto out_free_tr;
+	}
+
 	tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS;
 
 	cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
@@ -9570,12 +9717,18 @@ static struct trace_array *trace_array_create(const char *name)
 	free_trace_buffers(tr);
 	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
+	kfree_const(tr->system_names);
 	kfree(tr->name);
 	kfree(tr);
 
 	return ERR_PTR(ret);
 }
 
+static struct trace_array *trace_array_create(const char *name)
+{
+	return trace_array_create_systems(name, NULL);
+}
+
 static int instance_mkdir(const char *name)
 {
 	struct trace_array *tr;
@@ -9601,6 +9754,7 @@ static int instance_mkdir(const char *name)
 /**
  * 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.
+ * @systems: A list of systems to create event directories for (NULL for all)
  *
  * Returns pointer to trace array with given name.
  * NULL, if it cannot be created.
@@ -9614,7 +9768,7 @@ static int instance_mkdir(const char *name)
  * trace_array_put() is called, user space can not delete it.
  *
  */
-struct trace_array *trace_array_get_by_name(const char *name)
+struct trace_array *trace_array_get_by_name(const char *name, const char *systems)
 {
 	struct trace_array *tr;
 
@@ -9626,7 +9780,7 @@ struct trace_array *trace_array_get_by_name(const char *name)
 			goto out_unlock;
 	}
 
-	tr = trace_array_create(name);
+	tr = trace_array_create_systems(name, systems);
 
 	if (IS_ERR(tr))
 		tr = NULL;
@@ -9673,6 +9827,7 @@ static int __remove_instance(struct trace_array *tr)
 
 	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
+	kfree_const(tr->system_names);
 	kfree(tr->name);
 	kfree(tr);
 
@@ -9805,6 +9960,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("buffer_percent", TRACE_MODE_WRITE, d_tracer,
 			tr, &buffer_percent_fops);
 
+	trace_create_file("buffer_subbuf_size_kb", TRACE_MODE_WRITE, d_tracer,
+			  tr, &buffer_subbuf_size_fops);
+
 	create_trace_options_dir(tr);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -10391,7 +10549,7 @@ __init static void enable_instances(void)
 		if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE))
 			do_allocate_snapshot(tok);
 
-		tr = trace_array_get_by_name(tok);
+		tr = trace_array_get_by_name(tok, NULL);
 		if (!tr) {
 			pr_warn("Failed to create instance buffer %s\n", curr_str);
 			continue;

kernel/trace/trace.h

@@ -377,6 +377,7 @@ struct trace_array {
 	unsigned char		trace_flags_index[TRACE_FLAGS_MAX_SIZE];
 	unsigned int		flags;
 	raw_spinlock_t		start_lock;
+	const char		*system_names;
 	struct list_head	err_log;
 	struct dentry		*dir;
 	struct dentry		*options;
@@ -615,6 +616,7 @@ void tracing_reset_all_online_cpus(void);
 void tracing_reset_all_online_cpus_unlocked(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 int tracing_open_generic_tr(struct inode *inode, struct file *filp);
+int tracing_release_generic_tr(struct inode *inode, struct file *file);
 int tracing_open_file_tr(struct inode *inode, struct file *filp);
 int tracing_release_file_tr(struct inode *inode, struct file *filp);
 int tracing_single_release_file_tr(struct inode *inode, struct file *filp);

kernel/trace/trace_boot.c

@@ -633,7 +633,7 @@ trace_boot_init_instances(struct xbc_node *node)
 		if (!p || *p == '\0')
 			continue;
 
-		tr = trace_array_get_by_name(p);
+		tr = trace_array_get_by_name(p, NULL);
 		if (!tr) {
 			pr_err("Failed to get trace instance %s\n", p);
 			continue;

kernel/trace/trace_events.c

@@ -1893,9 +1893,9 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 }
 
 static ssize_t
-show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+show_header_page_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 {
-	int (*func)(struct trace_seq *s) = filp->private_data;
+	struct trace_array *tr = filp->private_data;
 	struct trace_seq *s;
 	int r;
 
@@ -1908,7 +1908,31 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 
 	trace_seq_init(s);
 
-	func(s);
+	ring_buffer_print_page_header(tr->array_buffer.buffer, s);
+	r = simple_read_from_buffer(ubuf, cnt, ppos,
+				    s->buffer, trace_seq_used(s));
+
+	kfree(s);
+
+	return r;
+}
+
+static ssize_t
+show_header_event_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	ring_buffer_print_entry_header(s);
 	r = simple_read_from_buffer(ubuf, cnt, ppos,
 				    s->buffer, trace_seq_used(s));
 
@@ -2165,10 +2189,18 @@ static const struct file_operations ftrace_tr_enable_fops = {
 	.release = subsystem_release,
 };
 
-static const struct file_operations ftrace_show_header_fops = {
-	.open = tracing_open_generic,
-	.read = show_header,
+static const struct file_operations ftrace_show_header_page_fops = {
+	.open = tracing_open_generic_tr,
+	.read = show_header_page_file,
+	.llseek = default_llseek,
+	.release = tracing_release_generic_tr,
+};
+
+static const struct file_operations ftrace_show_header_event_fops = {
+	.open = tracing_open_generic_tr,
+	.read = show_header_event_file,
 	.llseek = default_llseek,
+	.release = tracing_release_generic_tr,
 };
 
 static int
@@ -2896,6 +2928,27 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 	up_write(&trace_event_sem);
 }
 
+static bool event_in_systems(struct trace_event_call *call,
+			     const char *systems)
+{
+	const char *system;
+	const char *p;
+
+	if (!systems)
+		return true;
+
+	system = call->class->system;
+	p = strstr(systems, system);
+	if (!p)
+		return false;
+
+	if (p != systems && !isspace(*(p - 1)) && *(p - 1) != ',')
+		return false;
+
+	p += strlen(system);
+	return !*p || isspace(*p) || *p == ',';
+}
+
 static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)
@@ -2905,9 +2958,12 @@ trace_create_new_event(struct trace_event_call *call,
 	struct trace_event_file *file;
 	unsigned int first;
 
+	if (!event_in_systems(call, tr->system_names))
+		return NULL;
+
 	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
 	if (!file)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	pid_list = rcu_dereference_protected(tr->filtered_pids,
 					     lockdep_is_held(&event_mutex));
@@ -2972,8 +3028,17 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr)
 	struct trace_event_file *file;
 
 	file = trace_create_new_event(call, tr);
+	/*
+	 * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed
+	 * allocation, or NULL if the event is not part of the tr->system_names.
+	 * When the event is not part of the tr->system_names, return zero, not
+	 * an error.
+	 */
 	if (!file)
-		return -ENOMEM;
+		return 0;
+
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	if (eventdir_initialized)
 		return event_create_dir(tr->event_dir, file);
@@ -3012,8 +3077,17 @@ __trace_early_add_new_event(struct trace_event_call *call,
 	int ret;
 
 	file = trace_create_new_event(call, tr);
+	/*
+	 * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed
+	 * allocation, or NULL if the event is not part of the tr->system_names.
+	 * When the event is not part of the tr->system_names, return zero, not
+	 * an error.
+	 */
 	if (!file)
-		return -ENOMEM;
+		return 0;
+
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	ret = event_define_fields(call);
 	if (ret)
@@ -3752,17 +3826,16 @@ static int events_callback(const char *name, umode_t *mode, void **data,
 		return 1;
 	}
 
-	if (strcmp(name, "header_page") == 0)
-		*data = ring_buffer_print_page_header;
-
-	else if (strcmp(name, "header_event") == 0)
-		*data = ring_buffer_print_entry_header;
+	if (strcmp(name, "header_page") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &ftrace_show_header_page_fops;
 
-	else
+	} else if (strcmp(name, "header_event") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &ftrace_show_header_event_fops;
+	} else
 		return 0;
 
-	*mode = TRACE_MODE_READ;
-	*fops = &ftrace_show_header_fops;
 	return 1;
 }
 

kernel/trace/trace_events_hist.c

@@ -4805,36 +4805,35 @@ static int parse_actions(struct hist_trigger_data *hist_data)
 	int len;
 
 	for (i = 0; i < hist_data->attrs->n_actions; i++) {
+		enum handler_id hid = 0;
+		char *action_str;
+
 		str = hist_data->attrs->action_str[i];
 
-		if ((len = str_has_prefix(str, "onmatch("))) {
-			char *action_str = str + len;
+		if ((len = str_has_prefix(str, "onmatch(")))
+			hid = HANDLER_ONMATCH;
+		else if ((len = str_has_prefix(str, "onmax(")))
+			hid = HANDLER_ONMAX;
+		else if ((len = str_has_prefix(str, "onchange(")))
+			hid = HANDLER_ONCHANGE;
 
-			data = onmatch_parse(tr, action_str);
-			if (IS_ERR(data)) {
-				ret = PTR_ERR(data);
-				break;
-			}
-		} else if ((len = str_has_prefix(str, "onmax("))) {
-			char *action_str = str + len;
+		action_str = str + len;
 
-			data = track_data_parse(hist_data, action_str,
-						HANDLER_ONMAX);
-			if (IS_ERR(data)) {
-				ret = PTR_ERR(data);
-				break;
-			}
-		} else if ((len = str_has_prefix(str, "onchange("))) {
-			char *action_str = str + len;
+		switch (hid) {
+		case HANDLER_ONMATCH:
+			data = onmatch_parse(tr, action_str);
+			break;
+		case HANDLER_ONMAX:
+		case HANDLER_ONCHANGE:
+			data = track_data_parse(hist_data, action_str, hid);
+			break;
+		default:
+			data = ERR_PTR(-EINVAL);
+			break;
+		}
 
-			data = track_data_parse(hist_data, action_str,
-						HANDLER_ONCHANGE);
-			if (IS_ERR(data)) {
-				ret = PTR_ERR(data);
-				break;
-			}
-		} else {
-			ret = -EINVAL;
+		if (IS_ERR(data)) {
+			ret = PTR_ERR(data);
 			break;
 		}
 

kernel/trace/trace_seq.c

@@ -13,9 +13,6 @@
  * trace_seq_init() more than once to reset the trace_seq to start
  * from scratch.
  * 
- * The buffer size is currently PAGE_SIZE, although it may become dynamic
- * in the future.
- *
  * A write to the buffer will either succeed or fail. That is, unlike
  * sprintf() there will not be a partial write (well it may write into
  * the buffer but it wont update the pointers). This allows users to

samples/ftrace/sample-trace-array.c

@@ -105,7 +105,7 @@ static int __init sample_trace_array_init(void)
 	 * NOTE: This function increments the reference counter
 	 * associated with the trace array - "tr".
 	 */
-	tr = trace_array_get_by_name("sample-instance");
+	tr = trace_array_get_by_name("sample-instance", "sched,timer,kprobes");
 
 	if (!tr)
 		return -1;

tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Change the ringbuffer sub-buffer size
+# requires: buffer_subbuf_size_kb
+# flags: instance
+
+get_buffer_data_size() {
+	sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_buffer_data_offset() {
+	sed -ne 's/^.*data.*offset:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_event_header_size() {
+	type_len=`sed -ne 's/^.*type_len.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	time_len=`sed -ne 's/^.*time_delta.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	array_len=`sed -ne 's/^.*array.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	total_bits=$((type_len+time_len+array_len))
+	total_bits=$((total_bits+7))
+	echo $((total_bits/8))
+}
+
+get_print_event_buf_offset() {
+	sed -ne 's/^.*buf.*offset:\([0-9][0-9]*\).*/\1/p' events/ftrace/print/format
+}
+
+event_header_size=`get_event_header_size`
+print_header_size=`get_print_event_buf_offset`
+
+data_offset=`get_buffer_data_offset`
+
+marker_meta=$((event_header_size+print_header_size))
+
+make_str() {
+        cnt=$1
+	printf -- 'X%.0s' $(seq $cnt)
+}
+
+write_buffer() {
+	size=$1
+
+	str=`make_str $size`
+
+	# clear the buffer
+	echo > trace
+
+	# write the string into the marker
+	echo $str > trace_marker
+
+	echo $str
+}
+
+test_buffer() {
+	size_kb=$1
+	page_size=$((size_kb*1024))
+
+	size=`get_buffer_data_size`
+
+	# the size must be greater than or equal to page_size - data_offset
+	page_size=$((page_size-data_offset))
+	if [ $size -lt $page_size ]; then
+		exit fail
+	fi
+
+	# Now add a little more the meta data overhead will overflow
+
+	str=`write_buffer $size`
+
+	# Make sure the line was broken
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; exit}' trace`
+
+	if [ "$new_str" = "$str" ]; then
+		exit fail;
+	fi
+
+	# Make sure the entire line can be found
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; }' trace`
+
+	if [ "$new_str" != "$str" ]; then
+		exit fail;
+	fi
+}
+
+ORIG=`cat buffer_subbuf_size_kb`
+
+# Could test bigger sizes than 32K, but then creating the string
+# to write into the ring buffer takes too long
+for a in 4 8 16 32 ; do
+	echo $a > buffer_subbuf_size_kb
+	test_buffer $a
+done
+
+echo $ORIG > buffer_subbuf_size_kb
+

tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Basic tests on writing to trace_marker
+# requires: trace_marker
+# flags: instance
+
+get_buffer_data_size() {
+	sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_buffer_data_offset() {
+	sed -ne 's/^.*data.*offset:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+get_event_header_size() {
+	type_len=`sed -ne 's/^.*type_len.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	time_len=`sed -ne 's/^.*time_delta.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	array_len=`sed -ne 's/^.*array.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event`
+	total_bits=$((type_len+time_len+array_len))
+	total_bits=$((total_bits+7))
+	echo $((total_bits/8))
+}
+
+get_print_event_buf_offset() {
+	sed -ne 's/^.*buf.*offset:\([0-9][0-9]*\).*/\1/p' events/ftrace/print/format
+}
+
+event_header_size=`get_event_header_size`
+print_header_size=`get_print_event_buf_offset`
+
+data_offset=`get_buffer_data_offset`
+
+marker_meta=$((event_header_size+print_header_size))
+
+make_str() {
+        cnt=$1
+	# subtract two for \n\0 as marker adds these
+	cnt=$((cnt-2))
+	printf -- 'X%.0s' $(seq $cnt)
+}
+
+write_buffer() {
+	size=$1
+
+	str=`make_str $size`
+
+	# clear the buffer
+	echo > trace
+
+	# write the string into the marker
+	echo -n $str > trace_marker
+
+	echo $str
+}
+
+test_buffer() {
+
+	size=`get_buffer_data_size`
+	oneline_size=$((size-marker_meta))
+	echo size = $size
+	echo meta size = $marker_meta
+
+	# Now add a little more the meta data overhead will overflow
+
+	str=`write_buffer $size`
+
+	# Make sure the line was broken
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; exit}' trace`
+
+	if [ "$new_str" = "$str" ]; then
+		exit fail;
+	fi
+
+	# Make sure the entire line can be found
+	new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; }' trace`
+
+	if [ "$new_str" != "$str" ]; then
+		exit fail;
+	fi
+}
+
+test_buffer