1 files changed, 323 insertions, 4 deletions

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index eadb95ce7aac..232f00f273cb 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -243,14 +243,317 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 	spin_lock_init(&rb->event_lock);
 }
 
+/*
+ * This is called before hardware starts writing to the AUX area to
+ * obtain an output handle and make sure there's room in the buffer.
+ * When the capture completes, call perf_aux_output_end() to commit
+ * the recorded data to the buffer.
+ *
+ * The ordering is similar to that of perf_output_{begin,end}, with
+ * the exception of (B), which should be taken care of by the pmu
+ * driver, since ordering rules will differ depending on hardware.
+ */
+void *perf_aux_output_begin(struct perf_output_handle *handle,
+			    struct perf_event *event)
+{
+	struct perf_event *output_event = event;
+	unsigned long aux_head, aux_tail;
+	struct ring_buffer *rb;
+
+	if (output_event->parent)
+		output_event = output_event->parent;
+
+	/*
+	 * Since this will typically be open across pmu::add/pmu::del, we
+	 * grab ring_buffer's refcount instead of holding rcu read lock
+	 * to make sure it doesn't disappear under us.
+	 */
+	rb = ring_buffer_get(output_event);
+	if (!rb)
+		return NULL;
+
+	if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount))
+		goto err;
+
+	/*
+	 * Nesting is not supported for AUX area, make sure nested
+	 * writers are caught early
+	 */
+	if (WARN_ON_ONCE(local_xchg(&rb->aux_nest, 1)))
+		goto err_put;
+
+	aux_head = local_read(&rb->aux_head);
+
+	handle->rb = rb;
+	handle->event = event;
+	handle->head = aux_head;
+	handle->size = 0;
+
+	/*
+	 * In overwrite mode, AUX data stores do not depend on aux_tail,
+	 * therefore (A) control dependency barrier does not exist. The
+	 * (B) <-> (C) ordering is still observed by the pmu driver.
+	 */
+	if (!rb->aux_overwrite) {
+		aux_tail = ACCESS_ONCE(rb->user_page->aux_tail);
+		handle->wakeup = local_read(&rb->aux_wakeup) + rb->aux_watermark;
+		if (aux_head - aux_tail < perf_aux_size(rb))
+			handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb));
+
+		/*
+		 * handle->size computation depends on aux_tail load; this forms a
+		 * control dependency barrier separating aux_tail load from aux data
+		 * store that will be enabled on successful return
+		 */
+		if (!handle->size) { /* A, matches D */
+			event->pending_disable = 1;
+			perf_output_wakeup(handle);
+			local_set(&rb->aux_nest, 0);
+			goto err_put;
+		}
+	}
+
+	return handle->rb->aux_priv;
+
+err_put:
+	rb_free_aux(rb);
+
+err:
+	ring_buffer_put(rb);
+	handle->event = NULL;
+
+	return NULL;
+}
+
+/*
+ * Commit the data written by hardware into the ring buffer by adjusting
+ * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the
+ * pmu driver's responsibility to observe ordering rules of the hardware,
+ * so that all the data is externally visible before this is called.
+ */
+void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
+			 bool truncated)
+{
+	struct ring_buffer *rb = handle->rb;
+	unsigned long aux_head;
+	u64 flags = 0;
+
+	if (truncated)
+		flags |= PERF_AUX_FLAG_TRUNCATED;
+
+	/* in overwrite mode, driver provides aux_head via handle */
+	if (rb->aux_overwrite) {
+		flags |= PERF_AUX_FLAG_OVERWRITE;
+
+		aux_head = handle->head;
+		local_set(&rb->aux_head, aux_head);
+	} else {
+		aux_head = local_read(&rb->aux_head);
+		local_add(size, &rb->aux_head);
+	}
+
+	if (size || flags) {
+		/*
+		 * Only send RECORD_AUX if we have something useful to communicate
+		 */
+
+		perf_event_aux_event(handle->event, aux_head, size, flags);
+	}
+
+	aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
+
+	if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) {
+		perf_output_wakeup(handle);
+		local_add(rb->aux_watermark, &rb->aux_wakeup);
+	}
+	handle->event = NULL;
+
+	local_set(&rb->aux_nest, 0);
+	rb_free_aux(rb);
+	ring_buffer_put(rb);
+}
+
+/*
+ * Skip over a given number of bytes in the AUX buffer, due to, for example,
+ * hardware's alignment constraints.
+ */
+int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size)
+{
+	struct ring_buffer *rb = handle->rb;
+	unsigned long aux_head;
+
+	if (size > handle->size)
+		return -ENOSPC;
+
+	local_add(size, &rb->aux_head);
+
+	aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
+	if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) {
+		perf_output_wakeup(handle);
+		local_add(rb->aux_watermark, &rb->aux_wakeup);
+		handle->wakeup = local_read(&rb->aux_wakeup) +
+				 rb->aux_watermark;
+	}
+
+	handle->head = aux_head;
+	handle->size -= size;
+
+	return 0;
+}
+
+void *perf_get_aux(struct perf_output_handle *handle)
+{
+	/* this is only valid between perf_aux_output_begin and *_end */
+	if (!handle->event)
+		return NULL;
+
+	return handle->rb->aux_priv;
+}
+
+#define PERF_AUX_GFP	(GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY)
+
+static struct page *rb_alloc_aux_page(int node, int order)
+{
+	struct page *page;
+
+	if (order > MAX_ORDER)
+		order = MAX_ORDER;
+
+	do {
+		page = alloc_pages_node(node, PERF_AUX_GFP, order);
+	} while (!page && order--);
+
+	if (page && order) {
+		/*
+		 * Communicate the allocation size to the driver
+		 */
+		split_page(page, order);
+		SetPagePrivate(page);
+		set_page_private(page, order);
+	}
+
+	return page;
+}
+
+static void rb_free_aux_page(struct ring_buffer *rb, int idx)
+{
+	struct page *page = virt_to_page(rb->aux_pages[idx]);
+
+	ClearPagePrivate(page);
+	page->mapping = NULL;
+	__free_page(page);
+}
+
+int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
+		 pgoff_t pgoff, int nr_pages, long watermark, int flags)
+{
+	bool overwrite = !(flags & RING_BUFFER_WRITABLE);
+	int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu);
+	int ret = -ENOMEM, max_order = 0;
+
+	if (!has_aux(event))
+		return -ENOTSUPP;
+
+	if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) {
+		/*
+		 * We need to start with the max_order that fits in nr_pages,
+		 * not the other way around, hence ilog2() and not get_order.
+		 */
+		max_order = ilog2(nr_pages);
+
+		/*
+		 * PMU requests more than one contiguous chunks of memory
+		 * for SW double buffering
+		 */
+		if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) &&
+		    !overwrite) {
+			if (!max_order)
+				return -EINVAL;
+
+			max_order--;
+		}
+	}
+
+	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;) {
+		struct page *page;
+		int last, order;
+
+		order = min(max_order, ilog2(nr_pages - rb->aux_nr_pages));
+		page = rb_alloc_aux_page(node, order);
+		if (!page)
+			goto out;
+
+		for (last = rb->aux_nr_pages + (1 << page_private(page));
+		     last > rb->aux_nr_pages; rb->aux_nr_pages++)
+			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);
+
+	rb->aux_overwrite = overwrite;
+	rb->aux_watermark = watermark;
+
+	if (!rb->aux_watermark && !rb->aux_overwrite)
+		rb->aux_watermark = nr_pages << (PAGE_SHIFT - 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++)
+		rb_free_aux_page(rb, 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 +643,8 @@ 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 +719,19 @@ 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);
+}