[RFC v2 3/7] perf: support high-order allocations for AUX space

[Alexander Shishkin]

Some pmus (such as BTS or Intel PT without multiple-entry ToPA capability)
don't support scatter-gather and will prefer larger contiguous areas for
their output regions.

This patch adds a new pmu capability to request higher order allocations.

Signed-off-by: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
---
 include/linux/perf_event.h  |  1 +
 kernel/events/ring_buffer.c | 51 +++++++++++++++++++++++++++++++++++++++------
 2 files changed, 46 insertions(+), 6 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 75b9e6d..b316971 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -275,6 +275,7 @@ struct pmu {
  * struct pmu::capabilities flags
  */
 #define PERF_PMU_CAP_NO_INTERRUPT	1
+#define PERF_PMU_CAP_AUX_NO_SG		2
 
 /**
  * enum perf_event_active_state - the states of a event
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index ed259a4..e66ed76 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -242,29 +242,68 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 	spin_lock_init(&rb->event_lock);
 }
 
+#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, int flags)
 {
 	bool overwrite = !!(flags & RING_BUFFER_WRITABLE);
 	int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu);
-	int ret = -ENOMEM;
+	int ret = -ENOMEM, order = 0;
 
 	if (!has_aux(event))
 		return -ENOTSUPP;
 
+	if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG)
+		order = get_order(nr_pages * PAGE_SIZE);
+
 	rb->aux_pages = kzalloc_node(nr_pages * sizeof(void *), GFP_KERNEL, node);
 	if (!rb->aux_pages)
 		return -ENOMEM;
 
-	for (rb->aux_nr_pages = 0; rb->aux_nr_pages < nr_pages;
-	     rb->aux_nr_pages++) {
+	for (rb->aux_nr_pages = 0; rb->aux_nr_pages < nr_pages;) {
 		struct page *page;
+		int last;
 
-		page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
+		page = rb_alloc_aux_page(node, order);
 		if (!page)
 			goto out;
 
-		rb->aux_pages[rb->aux_nr_pages] = page_address(page);
+		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,
@@ -289,7 +328,7 @@ void rb_free_aux(struct ring_buffer *rb, struct perf_event *event)
 		event->pmu->free_aux(rb->aux_priv);
 
 	for (pg = 0; pg < rb->aux_nr_pages; pg++)
-		free_page((unsigned long)rb->aux_pages[pg]);
+		rb_free_aux_page(rb, pg);
 
 	kfree(rb->aux_pages);
 	rb->aux_nr_pages = 0;
-- 
2.0.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/