[PATCH mel-git 0/3] page_pool using alloc_pages_bulk API

[PATCH mel-git 0/3] page_pool using alloc_pages_bulk API

[Jesper Dangaard Brouer]

This patchset is against Mel's tree:
 - git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux.git
 - Branch: mm-bulk-rebase-v6r5
 - https://git.kernel.org/pub/scm/linux/kernel/git/mel/linux.git/log/?h=mm-bulk-rebase-v6r5

The benchmarks are here:
 - https://github.com/xdp-project/xdp-project/blob/master/areas/mem/page_pool06_alloc_pages_bulk.org#test-on-mel-git-tree-mm-bulk-rebase-v6r5

The compiler choose a strange code layout see here:
 - https://github.com/xdp-project/xdp-project/blob/master/areas/mem/page_pool06_alloc_pages_bulk.org#strange-code-layout
 - Used: gcc (GCC) 9.3.1 20200408 (Red Hat 9.3.1-2)

Intent is for Mel to pickup these patches.
---

Jesper Dangaard Brouer (3):
      net: page_pool: refactor dma_map into own function page_pool_dma_map
      net: page_pool: use alloc_pages_bulk in refill code path
      net: page_pool: convert to use alloc_pages_bulk_array variant


 include/net/page_pool.h |    2 -
 net/core/page_pool.c    |  111 +++++++++++++++++++++++++++++++----------------
 2 files changed, 75 insertions(+), 38 deletions(-)

--

[PATCH mel-git 1/3] net: page_pool: refactor dma_map into own function page_pool_dma_map

[Jesper Dangaard Brouer]

In preparation for next patch, move the dma mapping into its own
function, as this will make it easier to follow the changes.

V2: make page_pool_dma_map return boolean (Ilias)

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
---
 net/core/page_pool.c |   45 ++++++++++++++++++++++++++-------------------
 1 file changed, 26 insertions(+), 19 deletions(-)

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index ad8b0707af04..40e1b2beaa6c 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -180,14 +180,37 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool,
 					 pool->p.dma_dir);
 }
 
+static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
+{
+	dma_addr_t dma;
+
+	/* Setup DMA mapping: use 'struct page' area for storing DMA-addr
+	 * since dma_addr_t can be either 32 or 64 bits and does not always fit
+	 * into page private data (i.e 32bit cpu with 64bit DMA caps)
+	 * This mapping is kept for lifetime of page, until leaving pool.
+	 */
+	dma = dma_map_page_attrs(pool->p.dev, page, 0,
+				 (PAGE_SIZE << pool->p.order),
+				 pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC);
+	if (dma_mapping_error(pool->p.dev, dma))
+		return false;
+
+	page->dma_addr = dma;
+
+	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+		page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
+
+	return true;
+}
+
 /* slow path */
 noinline
 static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 						 gfp_t _gfp)
 {
+	unsigned int pp_flags = pool->p.flags;
 	struct page *page;
 	gfp_t gfp = _gfp;
-	dma_addr_t dma;
 
 	/* We could always set __GFP_COMP, and avoid this branch, as
 	 * prep_new_page() can handle order-0 with __GFP_COMP.
@@ -211,30 +234,14 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 	if (!page)
 		return NULL;
 
-	if (!(pool->p.flags & PP_FLAG_DMA_MAP))
-		goto skip_dma_map;
-
-	/* Setup DMA mapping: use 'struct page' area for storing DMA-addr
-	 * since dma_addr_t can be either 32 or 64 bits and does not always fit
-	 * into page private data (i.e 32bit cpu with 64bit DMA caps)
-	 * This mapping is kept for lifetime of page, until leaving pool.
-	 */
-	dma = dma_map_page_attrs(pool->p.dev, page, 0,
-				 (PAGE_SIZE << pool->p.order),
-				 pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC);
-	if (dma_mapping_error(pool->p.dev, dma)) {
+	if ((pp_flags & PP_FLAG_DMA_MAP) &&
+	    unlikely(!page_pool_dma_map(pool, page))) {
 		put_page(page);
 		return NULL;
 	}
-	page->dma_addr = dma;
 
-	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
-		page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
-
-skip_dma_map:
 	/* Track how many pages are held 'in-flight' */
 	pool->pages_state_hold_cnt++;
-
 	trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt);
 
 	/* When page just alloc'ed is should/must have refcnt 1. */

[PATCH mel-git 2/3] net: page_pool: use alloc_pages_bulk in refill code path

[Jesper Dangaard Brouer]

There are cases where the page_pool need to refill with pages from the
page allocator. Some workloads cause the page_pool to release pages
instead of recycling these pages.

For these workload it can improve performance to bulk alloc pages from
the page-allocator to refill the alloc cache.

For XDP-redirect workload with 100G mlx5 driver (that use page_pool)
redirecting xdp_frame packets into a veth, that does XDP_PASS to create
an SKB from the xdp_frame, which then cannot return the page to the
page_pool.

Performance results under GitHub xdp-project[1]:
 [1] https://github.com/xdp-project/xdp-project/blob/master/areas/mem/page_pool06_alloc_pages_bulk.org

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 net/core/page_pool.c |   72 ++++++++++++++++++++++++++++++++------------------
 1 file changed, 46 insertions(+), 26 deletions(-)

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 40e1b2beaa6c..3bf6e7f5fc89 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -203,38 +203,17 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
 	return true;
 }
 
-/* slow path */
-noinline
-static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
-						 gfp_t _gfp)
+static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
+						 gfp_t gfp)
 {
-	unsigned int pp_flags = pool->p.flags;
 	struct page *page;
-	gfp_t gfp = _gfp;
-
-	/* We could always set __GFP_COMP, and avoid this branch, as
-	 * prep_new_page() can handle order-0 with __GFP_COMP.
-	 */
-	if (pool->p.order)
-		gfp |= __GFP_COMP;
-
-	/* FUTURE development:
-	 *
-	 * Current slow-path essentially falls back to single page
-	 * allocations, which doesn't improve performance.  This code
-	 * need bulk allocation support from the page allocator code.
-	 */
 
-	/* Cache was empty, do real allocation */
-#ifdef CONFIG_NUMA
+	gfp |= __GFP_COMP;
 	page = alloc_pages_node(pool->p.nid, gfp, pool->p.order);
-#else
-	page = alloc_pages(gfp, pool->p.order);
-#endif
-	if (!page)
+	if (unlikely(!page))
 		return NULL;
 
-	if ((pp_flags & PP_FLAG_DMA_MAP) &&
+	if ((pool->p.flags & PP_FLAG_DMA_MAP) &&
 	    unlikely(!page_pool_dma_map(pool, page))) {
 		put_page(page);
 		return NULL;
@@ -243,6 +222,47 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 	/* Track how many pages are held 'in-flight' */
 	pool->pages_state_hold_cnt++;
 	trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt);
+	return page;
+}
+
+/* slow path */
+noinline
+static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
+						 gfp_t gfp)
+{
+	const int bulk = PP_ALLOC_CACHE_REFILL;
+	unsigned int pp_flags = pool->p.flags;
+	unsigned int pp_order = pool->p.order;
+	struct page *page, *next;
+	LIST_HEAD(page_list);
+
+	/* Don't support bulk alloc for high-order pages */
+	if (unlikely(pp_order))
+		return __page_pool_alloc_page_order(pool, gfp);
+
+	if (unlikely(!alloc_pages_bulk_list(gfp, bulk, &page_list)))
+		return NULL;
+
+	list_for_each_entry_safe(page, next, &page_list, lru) {
+		list_del(&page->lru);
+		if ((pp_flags & PP_FLAG_DMA_MAP) &&
+		    unlikely(!page_pool_dma_map(pool, page))) {
+			put_page(page);
+			continue;
+		}
+		/* Alloc cache have room as it is empty on function call */
+		pool->alloc.cache[pool->alloc.count++] = page;
+		/* Track how many pages are held 'in-flight' */
+		pool->pages_state_hold_cnt++;
+		trace_page_pool_state_hold(pool, page,
+					   pool->pages_state_hold_cnt);
+	}
+
+	/* Return last page */
+	if (likely(pool->alloc.count > 0))
+		page = pool->alloc.cache[--pool->alloc.count];
+	else
+		page = NULL;
 
 	/* When page just alloc'ed is should/must have refcnt 1. */
 	return page;

[PATCH mel-git 3/3] net: page_pool: convert to use alloc_pages_bulk_array variant

[Jesper Dangaard Brouer]

Using the API variant alloc_pages_bulk_array from page_pool
was done in a separate patch to ease benchmarking the
variants separately.  Maintainers can squash patch if preferred.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
 include/net/page_pool.h |    2 +-
 net/core/page_pool.c    |   22 ++++++++++++++++------
 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index b5b195305346..6d517a37c18b 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -65,7 +65,7 @@
 #define PP_ALLOC_CACHE_REFILL	64
 struct pp_alloc_cache {
 	u32 count;
-	void *cache[PP_ALLOC_CACHE_SIZE];
+	struct page *cache[PP_ALLOC_CACHE_SIZE];
 };
 
 struct page_pool_params {
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 3bf6e7f5fc89..9ec1aa9640ad 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -233,24 +233,34 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 	const int bulk = PP_ALLOC_CACHE_REFILL;
 	unsigned int pp_flags = pool->p.flags;
 	unsigned int pp_order = pool->p.order;
-	struct page *page, *next;
-	LIST_HEAD(page_list);
+	struct page *page;
+	int i, nr_pages;
 
 	/* Don't support bulk alloc for high-order pages */
 	if (unlikely(pp_order))
 		return __page_pool_alloc_page_order(pool, gfp);
 
-	if (unlikely(!alloc_pages_bulk_list(gfp, bulk, &page_list)))
+	/* Unnecessary as alloc cache is empty, but guarantees zero count */
+	if (unlikely(pool->alloc.count > 0))
+		return pool->alloc.cache[--pool->alloc.count];
+
+	/* Mark empty alloc.cache slots "empty" for alloc_pages_bulk_array */
+	memset(&pool->alloc.cache, 0, sizeof(void *) * bulk);
+
+	nr_pages = alloc_pages_bulk_array(gfp, bulk, pool->alloc.cache);
+	if (unlikely(!nr_pages))
 		return NULL;
 
-	list_for_each_entry_safe(page, next, &page_list, lru) {
-		list_del(&page->lru);
+	/* Pages have been filled into alloc.cache array, but count is zero and
+	 * page element have not been (possibly) DMA mapped.
+	 */
+	for (i = 0; i < nr_pages; i++) {
+		page = pool->alloc.cache[i];
 		if ((pp_flags & PP_FLAG_DMA_MAP) &&
 		    unlikely(!page_pool_dma_map(pool, page))) {
 			put_page(page);
 			continue;
 		}
-		/* Alloc cache have room as it is empty on function call */
 		pool->alloc.cache[pool->alloc.count++] = page;
 		/* Track how many pages are held 'in-flight' */
 		pool->pages_state_hold_cnt++;

Re: [PATCH mel-git 3/3] net: page_pool: convert to use alloc_pages_bulk_array variant

[Mel Gorman]

On Wed, Mar 24, 2021 at 10:34:59PM +0100, Jesper Dangaard Brouer wrote:
> Using the API variant alloc_pages_bulk_array from page_pool
> was done in a separate patch to ease benchmarking the
> variants separately.  Maintainers can squash patch if preferred.
> 
> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>

I decided to squash the patches and add some details from your github page
in case it ever disappears and I hope that's ok. This is the version of
the patch I'm currently looking at.

---8<---
Subject: [PATCH] net: page_pool: use alloc_pages_bulk in refill code path

From: Jesper Dangaard Brouer <brouer@redhat.com>

There are cases where the page_pool need to refill with pages from the
page allocator. Some workloads cause the page_pool to release pages
instead of recycling these pages.

For these workload it can improve performance to bulk alloc pages from
the page-allocator to refill the alloc cache.

For XDP-redirect workload with 100G mlx5 driver (that use page_pool)
redirecting xdp_frame packets into a veth, that does XDP_PASS to create
an SKB from the xdp_frame, which then cannot return the page to the
page_pool.

Performance results under GitHub xdp-project[1]:
 [1] https://github.com/xdp-project/xdp-project/blob/master/areas/mem/page_pool06_alloc_pages_bulk.org

Mel: The patch "net: page_pool: convert to use alloc_pages_bulk_array
variant" was squashed with this patch. From the test page, the array
variant was superior with one of the test results as follows.

	Kernel		XDP stats       CPU     pps           Delta
	Baseline	XDP-RX CPU      total   3,771,046       n/a
	List		XDP-RX CPU      total   3,940,242    +4.49%
	Array		XDP-RX CPU      total   4,249,224   +12.68%

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 include/net/page_pool.h |  2 +-
 net/core/page_pool.c    | 82 +++++++++++++++++++++++++++++++++----------------
 2 files changed, 57 insertions(+), 27 deletions(-)

diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index b5b195305346..6d517a37c18b 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -65,7 +65,7 @@
 #define PP_ALLOC_CACHE_REFILL	64
 struct pp_alloc_cache {
 	u32 count;
-	void *cache[PP_ALLOC_CACHE_SIZE];
+	struct page *cache[PP_ALLOC_CACHE_SIZE];
 };
 
 struct page_pool_params {
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 40e1b2beaa6c..9ec1aa9640ad 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -203,38 +203,17 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
 	return true;
 }
 
-/* slow path */
-noinline
-static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
-						 gfp_t _gfp)
+static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
+						 gfp_t gfp)
 {
-	unsigned int pp_flags = pool->p.flags;
 	struct page *page;
-	gfp_t gfp = _gfp;
-
-	/* We could always set __GFP_COMP, and avoid this branch, as
-	 * prep_new_page() can handle order-0 with __GFP_COMP.
-	 */
-	if (pool->p.order)
-		gfp |= __GFP_COMP;
-
-	/* FUTURE development:
-	 *
-	 * Current slow-path essentially falls back to single page
-	 * allocations, which doesn't improve performance.  This code
-	 * need bulk allocation support from the page allocator code.
-	 */
 
-	/* Cache was empty, do real allocation */
-#ifdef CONFIG_NUMA
+	gfp |= __GFP_COMP;
 	page = alloc_pages_node(pool->p.nid, gfp, pool->p.order);
-#else
-	page = alloc_pages(gfp, pool->p.order);
-#endif
-	if (!page)
+	if (unlikely(!page))
 		return NULL;
 
-	if ((pp_flags & PP_FLAG_DMA_MAP) &&
+	if ((pool->p.flags & PP_FLAG_DMA_MAP) &&
 	    unlikely(!page_pool_dma_map(pool, page))) {
 		put_page(page);
 		return NULL;
@@ -243,6 +222,57 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 	/* Track how many pages are held 'in-flight' */
 	pool->pages_state_hold_cnt++;
 	trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt);
+	return page;
+}
+
+/* slow path */
+noinline
+static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
+						 gfp_t gfp)
+{
+	const int bulk = PP_ALLOC_CACHE_REFILL;
+	unsigned int pp_flags = pool->p.flags;
+	unsigned int pp_order = pool->p.order;
+	struct page *page;
+	int i, nr_pages;
+
+	/* Don't support bulk alloc for high-order pages */
+	if (unlikely(pp_order))
+		return __page_pool_alloc_page_order(pool, gfp);
+
+	/* Unnecessary as alloc cache is empty, but guarantees zero count */
+	if (unlikely(pool->alloc.count > 0))
+		return pool->alloc.cache[--pool->alloc.count];
+
+	/* Mark empty alloc.cache slots "empty" for alloc_pages_bulk_array */
+	memset(&pool->alloc.cache, 0, sizeof(void *) * bulk);
+
+	nr_pages = alloc_pages_bulk_array(gfp, bulk, pool->alloc.cache);
+	if (unlikely(!nr_pages))
+		return NULL;
+
+	/* Pages have been filled into alloc.cache array, but count is zero and
+	 * page element have not been (possibly) DMA mapped.
+	 */
+	for (i = 0; i < nr_pages; i++) {
+		page = pool->alloc.cache[i];
+		if ((pp_flags & PP_FLAG_DMA_MAP) &&
+		    unlikely(!page_pool_dma_map(pool, page))) {
+			put_page(page);
+			continue;
+		}
+		pool->alloc.cache[pool->alloc.count++] = page;
+		/* Track how many pages are held 'in-flight' */
+		pool->pages_state_hold_cnt++;
+		trace_page_pool_state_hold(pool, page,
+					   pool->pages_state_hold_cnt);
+	}
+
+	/* Return last page */
+	if (likely(pool->alloc.count > 0))
+		page = pool->alloc.cache[--pool->alloc.count];
+	else
+		page = NULL;
 
 	/* When page just alloc'ed is should/must have refcnt 1. */
 	return page;