perf: Add AUX area to ring buffer for raw data streams

This patch introduces "AUX space" in the perf mmap buffer, intended for
exporting high bandwidth data streams to userspace, such as instruction
flow traces.

AUX space is a ring buffer, defined by aux_{offset,size} fields in the
user_page structure, and read/write pointers aux_{head,tail}, which abide
by the same rules as data_* counterparts of the main perf buffer.

In order to allocate/mmap AUX, userspace needs to set up aux_offset to
such an offset that will be greater than data_offset+data_size and
aux_size to be the desired buffer size. Both need to be page aligned.
Then, same aux_offset and aux_size should be passed to mmap() call and
if everything adds up, you should have an AUX buffer as a result.

Pages that are mapped into this buffer also come out of user's mlock
rlimit plus perf_event_mlock_kb allowance.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kaixu Xia <kaixu.xia@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Robert Richter <rric@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@infradead.org
Cc: adrian.hunter@intel.com
Cc: kan.liang@intel.com
Cc: markus.t.metzger@intel.com
Cc: mathieu.poirier@linaro.org
Link: http://lkml.kernel.org/r/1421237903-181015-3-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 23 insertions, 0 deletions

diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 569b2187..0f6d080 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -35,6 +35,16 @@ struct ring_buffer {
 	unsigned long			mmap_locked;
 	struct user_struct		*mmap_user;
 
+	/* AUX area */
+	unsigned long			aux_pgoff;
+	int				aux_nr_pages;
+	atomic_t			aux_mmap_count;
+	unsigned long			aux_mmap_locked;
+	void				(*free_aux)(void *);
+	atomic_t			aux_refcount;
+	void				**aux_pages;
+	void				*aux_priv;
+
 	struct perf_event_mmap_page	*user_page;
 	void				*data_pages[0];
 };
@@ -43,6 +53,14 @@ extern void rb_free(struct ring_buffer *rb);
 extern struct ring_buffer *
 rb_alloc(int nr_pages, long watermark, int cpu, int flags);
 extern void perf_event_wakeup(struct perf_event *event);
+extern int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
+			pgoff_t pgoff, int nr_pages, int flags);
+extern void rb_free_aux(struct ring_buffer *rb);
+
+static inline bool rb_has_aux(struct ring_buffer *rb)
+{
+	return !!rb->aux_nr_pages;
+}
 
 extern void
 perf_event_header__init_id(struct perf_event_header *header,
@@ -81,6 +99,11 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb)
 	return rb->nr_pages << (PAGE_SHIFT + page_order(rb));
 }
 
+static inline unsigned long perf_aux_size(struct ring_buffer *rb)
+{
+	return rb->aux_nr_pages << PAGE_SHIFT;
+}
+
 #define DEFINE_OUTPUT_COPY(func_name, memcpy_func)			\
 static inline unsigned long						\
 func_name(struct perf_output_handle *handle,				\