[PATCH net-next v7 4/6] page_pool: introduce page_pool[_cache]_alloc() API

STALE1129d

From: Yunsheng Lin <hidden>
Date: 2023-08-16 10:05:07
Also in: lkml
Subsystem: networking [general], page pool, the rest · Maintainers: "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Jesper Dangaard Brouer, Ilias Apalodimas, Linus Torvalds

Revision v7 of 7 in this series.

Revisions (7)

2023-08-14 v6 [diff vs current]
2023-08-16 v7 current
2023-09-12 v8 [diff vs current]
2023-09-20 v9 [diff vs current]
2023-09-22 v10 [diff vs current]
2023-10-13 v11 [diff vs current]
2023-10-20 v12 [diff vs current]

Currently page pool supports the below use cases:
use case 1: allocate page without page splitting using
            page_pool_alloc_pages() API if the driver knows
            that the memory it need is always bigger than
            half of the page allocated from page pool.
use case 2: allocate page frag with page splitting using
            page_pool_alloc_frag() API if the driver knows
            that the memory it need is always smaller than
            or equal to the half of the page allocated from
            page pool.

There is emerging use case [1] & [2] that is a mix of the
above two case: the driver doesn't know the size of memory it
need beforehand, so the driver may use something like below to
allocate memory with least memory utilization and performance
penalty:

if (size << 1 > max_size)
	page = page_pool_alloc_pages();
else
	page = page_pool_alloc_frag();

To avoid the driver doing something like above, add the
page_pool[_cache]_alloc() API to support the above use case,
and update the true size of memory that is acctually allocated
by updating '*size' back to the driver in order to avoid
exacerbating truesize underestimate problem.

Rename page_pool_free() which is used in the destroy process to
__page_pool_destroy() to avoid confusion with the newly added
API.

1. https://lore.kernel.org/all/d3ae6bd3537fbce379382ac6a42f67e22f27ece2.1683896626.git.lorenzo@kernel.org/ (local)
2. https://lore.kernel.org/all/20230526054621.18371-3-liangchen.linux@gmail.com/ (local)

Signed-off-by: Yunsheng Lin <redacted>
CC: Lorenzo Bianconi <lorenzo@kernel.org>
CC: Alexander Duyck <redacted>
CC: Liang Chen <redacted>
CC: Alexander Lobakin <aleksander.lobakin@intel.com>
---
 include/net/page_pool/helpers.h | 70 +++++++++++++++++++++++++++++++++
 net/core/page_pool.c            |  4 +-
 2 files changed, 72 insertions(+), 2 deletions(-)

diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 19e8ba056868..b920224f6584 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h

@@ -109,6 +109,70 @@ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool,
 	return page_pool_alloc_frag(pool, offset, size, gfp);
 }
 
+static inline struct page *page_pool_alloc(struct page_pool *pool,
+					   unsigned int *offset,
+					   unsigned int *size, gfp_t gfp)
+{
+	unsigned int max_size = PAGE_SIZE << pool->p.order;
+	struct page *page;
+
+	*size = ALIGN(*size, dma_get_cache_alignment());
+
+	if (WARN_ON(*size > max_size))
+		return NULL;
+
+	if ((*size << 1) > max_size || PAGE_POOL_DMA_USE_PP_FRAG_COUNT) {
+		*size = max_size;
+		*offset = 0;
+		return page_pool_alloc_pages(pool, gfp);
+	}
+
+	page = __page_pool_alloc_frag(pool, offset, *size, gfp);
+	if (unlikely(!page))
+		return NULL;
+
+	/* There is very likely not enough space for another frag, so append the
+	 * remaining size to the current frag to avoid truesize underestimate
+	 * problem.
+	 */
+	if (pool->frag_offset + *size > max_size) {
+		*size = max_size - *offset;
+		pool->frag_offset = max_size;
+	}
+
+	return page;
+}
+
+static inline struct page *page_pool_dev_alloc(struct page_pool *pool,
+					       unsigned int *offset,
+					       unsigned int *size)
+{
+	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
+
+	return page_pool_alloc(pool, offset, size, gfp);
+}
+
+static inline void *page_pool_cache_alloc(struct page_pool *pool,
+					  unsigned int *size, gfp_t gfp)
+{
+	unsigned int offset;
+	struct page *page;
+
+	page = page_pool_alloc(pool, &offset, size, gfp);
+	if (unlikely(!page))
+		return NULL;
+
+	return page_address(page) + offset;
+}
+
+static inline void *page_pool_dev_cache_alloc(struct page_pool *pool,
+					      unsigned int *size)
+{
+	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
+
+	return page_pool_cache_alloc(pool, size, gfp);
+}
+
 /**
  * page_pool_get_dma_dir() - Retrieve the stored DMA direction.
  * @pool:	pool from which page was allocated

@@ -252,6 +316,12 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 	page_pool_put_full_page(pool, page, true);
 }
 
+static inline void page_pool_cache_free(struct page_pool *pool, void *data,
+					bool allow_direct)
+{
+	page_pool_put_page(pool, virt_to_head_page(data), -1, allow_direct);
+}
+
 /**
  * page_pool_get_dma_addr() - Retrieve the stored DMA address.
  * @page:	page allocated from a page pool

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index d3b8efe98d5e..6f970fc7a0a7 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c

@@ -800,7 +800,7 @@ static void page_pool_empty_ring(struct page_pool *pool)
 	}
 }
 
-static void page_pool_free(struct page_pool *pool)
+static void __page_pool_destroy(struct page_pool *pool)
 {
 	if (pool->disconnect)
 		pool->disconnect(pool);

@@ -851,7 +851,7 @@ static int page_pool_release(struct page_pool *pool)
 	page_pool_scrub(pool);
 	inflight = page_pool_inflight(pool);
 	if (!inflight)
-		page_pool_free(pool);
+		__page_pool_destroy(pool);
 
 	return inflight;
 }

-- 
2.33.0

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help