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, 93 insertions, 4 deletions

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index eadb95ce7aac..3de9c4e9ea9f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -243,14 +243,87 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 	spin_lock_init(&rb->event_lock);
 }
 
+int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
+		 pgoff_t pgoff, int nr_pages, int flags)
+{
+	bool overwrite = !(flags & RING_BUFFER_WRITABLE);
+	int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu);
+	int ret = -ENOMEM;
+
+	if (!has_aux(event))
+		return -ENOTSUPP;
+
+	rb->aux_pages = kzalloc_node(nr_pages * sizeof(void *), GFP_KERNEL, node);
+	if (!rb->aux_pages)
+		return -ENOMEM;
+
+	rb->free_aux = event->pmu->free_aux;
+	for (rb->aux_nr_pages = 0; rb->aux_nr_pages < nr_pages;
+	     rb->aux_nr_pages++) {
+		struct page *page;
+
+		page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
+		if (!page)
+			goto out;
+
+		rb->aux_pages[rb->aux_nr_pages] = page_address(page);
+	}
+
+	rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages,
+					     overwrite);
+	if (!rb->aux_priv)
+		goto out;
+
+	ret = 0;
+
+	/*
+	 * aux_pages (and pmu driver's private data, aux_priv) will be
+	 * referenced in both producer's and consumer's contexts, thus
+	 * we keep a refcount here to make sure either of the two can
+	 * reference them safely.
+	 */
+	atomic_set(&rb->aux_refcount, 1);
+
+out:
+	if (!ret)
+		rb->aux_pgoff = pgoff;
+	else
+		rb_free_aux(rb);
+
+	return ret;
+}
+
+static void __rb_free_aux(struct ring_buffer *rb)
+{
+	int pg;
+
+	if (rb->aux_priv) {
+		rb->free_aux(rb->aux_priv);
+		rb->free_aux = NULL;
+		rb->aux_priv = NULL;
+	}
+
+	for (pg = 0; pg < rb->aux_nr_pages; pg++)
+		free_page((unsigned long)rb->aux_pages[pg]);
+
+	kfree(rb->aux_pages);
+	rb->aux_nr_pages = 0;
+}
+
+void rb_free_aux(struct ring_buffer *rb)
+{
+	if (atomic_dec_and_test(&rb->aux_refcount))
+		__rb_free_aux(rb);
+}
+
 #ifndef CONFIG_PERF_USE_VMALLOC
 
 /*
  * Back perf_mmap() with regular GFP_KERNEL-0 pages.
  */
 
-struct page *
-perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
+static struct page *
+__perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
 {
 	if (pgoff > rb->nr_pages)
 		return NULL;
@@ -340,8 +413,8 @@ static int data_page_nr(struct ring_buffer *rb)
 	return rb->nr_pages << page_order(rb);
 }
 
-struct page *
-perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
+static struct page *
+__perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
 {
 	/* The '>' counts in the user page. */
 	if (pgoff > data_page_nr(rb))
@@ -416,3 +489,19 @@ fail:
 }
 
 #endif
+
+struct page *
+perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
+{
+	if (rb->aux_nr_pages) {
+		/* above AUX space */
+		if (pgoff > rb->aux_pgoff + rb->aux_nr_pages)
+			return NULL;
+
+		/* AUX space */
+		if (pgoff >= rb->aux_pgoff)
+			return virt_to_page(rb->aux_pages[pgoff - rb->aux_pgoff]);
+	}
+
+	return __perf_mmap_to_page(rb, pgoff);
+}