diff mbox series

[v6,5/5] dma-buf: system_heap: Allocate higher order pages if available

Message ID 20201121044955.58215-6-john.stultz@linaro.org
State Superseded
Headers show
Series dma-buf: Code rework and performance improvements for system heap | expand

Commit Message

John Stultz Nov. 21, 2020, 4:49 a.m. UTC
While the system heap can return non-contiguous pages,
try to allocate larger order pages if possible.

This will allow slight performance gains and make implementing
page pooling easier.

Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Liam Mark <lmark@codeaurora.org>
Cc: Laura Abbott <labbott@kernel.org>
Cc: Brian Starkey <Brian.Starkey@arm.com>
Cc: Hridya Valsaraju <hridya@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: Daniel Mentz <danielmentz@google.com>
Cc: Chris Goldsworthy <cgoldswo@codeaurora.org>
Cc: Ørjan Eide <orjan.eide@arm.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Ezequiel Garcia <ezequiel@collabora.com>
Cc: Simon Ser <contact@emersion.fr>
Cc: James Jones <jajones@nvidia.com>
Cc: linux-media@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Brian Starkey <brian.starkey@arm.com>

Signed-off-by: John Stultz <john.stultz@linaro.org>

---
v3:
* Use page_size() rather then opencoding it
v5:
* Add comment explaining order size rational
---
 drivers/dma-buf/heaps/system_heap.c | 89 +++++++++++++++++++++++------
 1 file changed, 71 insertions(+), 18 deletions(-)

-- 
2.17.1
diff mbox series

Patch

diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
index b1a7b355132f..de275b7ff1ed 100644
--- a/drivers/dma-buf/heaps/system_heap.c
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -40,6 +40,20 @@  struct dma_heap_attachment {
 	bool mapped;
 };
 
+#define HIGH_ORDER_GFP  (((GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN \
+				| __GFP_NORETRY) & ~__GFP_RECLAIM) \
+				| __GFP_COMP)
+#define LOW_ORDER_GFP (GFP_HIGHUSER | __GFP_ZERO | __GFP_COMP)
+static gfp_t order_flags[] = {HIGH_ORDER_GFP, LOW_ORDER_GFP, LOW_ORDER_GFP};
+/*
+ * The selection of the orders used for allocation (1MB, 64K, 4K) is designed
+ * to match with the sizes often found in IOMMUs. Using order 4 pages instead
+ * of order 0 pages can significantly improve the performance of many IOMMUs
+ * by reducing TLB pressure and time spent updating page tables.
+ */
+static const unsigned int orders[] = {8, 4, 0};
+#define NUM_ORDERS ARRAY_SIZE(orders)
+
 static struct sg_table *dup_sg_table(struct sg_table *table)
 {
 	struct sg_table *new_table;
@@ -272,8 +286,11 @@  static void system_heap_dma_buf_release(struct dma_buf *dmabuf)
 	int i;
 
 	table = &buffer->sg_table;
-	for_each_sgtable_sg(table, sg, i)
-		__free_page(sg_page(sg));
+	for_each_sg(table->sgl, sg, table->nents, i) {
+		struct page *page = sg_page(sg);
+
+		__free_pages(page, compound_order(page));
+	}
 	sg_free_table(table);
 	kfree(buffer);
 }
@@ -291,6 +308,26 @@  static const struct dma_buf_ops system_heap_buf_ops = {
 	.release = system_heap_dma_buf_release,
 };
 
+static struct page *alloc_largest_available(unsigned long size,
+					    unsigned int max_order)
+{
+	struct page *page;
+	int i;
+
+	for (i = 0; i < NUM_ORDERS; i++) {
+		if (size <  (PAGE_SIZE << orders[i]))
+			continue;
+		if (max_order < orders[i])
+			continue;
+
+		page = alloc_pages(order_flags[i], orders[i]);
+		if (!page)
+			continue;
+		return page;
+	}
+	return NULL;
+}
+
 static int system_heap_allocate(struct dma_heap *heap,
 				unsigned long len,
 				unsigned long fd_flags,
@@ -298,11 +335,13 @@  static int system_heap_allocate(struct dma_heap *heap,
 {
 	struct system_heap_buffer *buffer;
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+	unsigned long size_remaining = len;
+	unsigned int max_order = orders[0];
 	struct dma_buf *dmabuf;
 	struct sg_table *table;
 	struct scatterlist *sg;
-	pgoff_t pagecount;
-	pgoff_t pg;
+	struct list_head pages;
+	struct page *page, *tmp_page;
 	int i, ret = -ENOMEM;
 
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
@@ -314,25 +353,35 @@  static int system_heap_allocate(struct dma_heap *heap,
 	buffer->heap = heap;
 	buffer->len = len;
 
-	table = &buffer->sg_table;
-	pagecount = len / PAGE_SIZE;
-	if (sg_alloc_table(table, pagecount, GFP_KERNEL))
-		goto free_buffer;
-
-	sg = table->sgl;
-	for (pg = 0; pg < pagecount; pg++) {
-		struct page *page;
+	INIT_LIST_HEAD(&pages);
+	i = 0;
+	while (size_remaining > 0) {
 		/*
 		 * Avoid trying to allocate memory if the process
 		 * has been killed by SIGKILL
 		 */
 		if (fatal_signal_pending(current))
-			goto free_pages;
-		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+			goto free_buffer;
+
+		page = alloc_largest_available(size_remaining, max_order);
 		if (!page)
-			goto free_pages;
+			goto free_buffer;
+
+		list_add_tail(&page->lru, &pages);
+		size_remaining -= page_size(page);
+		max_order = compound_order(page);
+		i++;
+	}
+
+	table = &buffer->sg_table;
+	if (sg_alloc_table(table, i, GFP_KERNEL))
+		goto free_buffer;
+
+	sg = table->sgl;
+	list_for_each_entry_safe(page, tmp_page, &pages, lru) {
 		sg_set_page(sg, page, page_size(page), 0);
 		sg = sg_next(sg);
+		list_del(&page->lru);
 	}
 
 	/* create the dmabuf */
@@ -352,14 +401,18 @@  static int system_heap_allocate(struct dma_heap *heap,
 		/* just return, as put will call release and that will free */
 		return ret;
 	}
-
 	return ret;
 
 free_pages:
-	for_each_sgtable_sg(table, sg, i)
-		__free_page(sg_page(sg));
+	for_each_sgtable_sg(table, sg, i) {
+		struct page *p = sg_page(sg);
+
+		__free_pages(p, compound_order(p));
+	}
 	sg_free_table(table);
 free_buffer:
+	list_for_each_entry_safe(page, tmp_page, &pages, lru)
+		__free_pages(page, compound_order(page));
 	kfree(buffer);
 
 	return ret;