diff options
| -rw-r--r-- | include/net/page_pool.h | 24 | ||||
| -rw-r--r-- | net/core/page_pool.c | 36 |
2 files changed, 52 insertions, 8 deletions
diff --git a/include/net/page_pool.h b/include/net/page_pool.h index e2e1b7b1e8ba..cfbed00ba7ee 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -34,8 +34,18 @@ #include <linux/ptr_ring.h> #include <linux/dma-direction.h> -#define PP_FLAG_DMA_MAP 1 /* Should page_pool do the DMA map/unmap */ -#define PP_FLAG_ALL PP_FLAG_DMA_MAP +#define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA + * map/unmap + */ +#define PP_FLAG_DMA_SYNC_DEV BIT(1) /* If set all pages that the driver gets + * from page_pool will be + * DMA-synced-for-device according to + * the length provided by the device + * driver. + * Please note DMA-sync-for-CPU is still + * device driver responsibility + */ +#define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV) /* * Fast allocation side cache array/stack @@ -65,6 +75,8 @@ struct page_pool_params { int nid; /* Numa node id to allocate from pages from */ struct device *dev; /* device, for DMA pre-mapping purposes */ enum dma_data_direction dma_dir; /* DMA mapping direction */ + unsigned int max_len; /* max DMA sync memory size */ + unsigned int offset; /* DMA addr offset */ }; struct page_pool { @@ -151,8 +163,8 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool, #endif /* Never call this directly, use helpers below */ -void __page_pool_put_page(struct page_pool *pool, - struct page *page, bool allow_direct); +void __page_pool_put_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct); static inline void page_pool_put_page(struct page_pool *pool, struct page *page, bool allow_direct) @@ -161,14 +173,14 @@ static inline void page_pool_put_page(struct page_pool *pool, * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - __page_pool_put_page(pool, page, allow_direct); + __page_pool_put_page(pool, page, -1, allow_direct); #endif } /* Very limited use-cases allow recycle direct */ static inline void page_pool_recycle_direct(struct page_pool *pool, struct page *page) { - __page_pool_put_page(pool, page, true); + __page_pool_put_page(pool, page, -1, true); } /* Disconnects a page (from a page_pool). API users can have a need diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 6c7f78bd6421..a6aefe989043 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -47,6 +47,21 @@ static int page_pool_init(struct page_pool *pool, (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; + if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) { + /* In order to request DMA-sync-for-device the page + * needs to be mapped + */ + if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + return -EINVAL; + + if (!pool->p.max_len) + return -EINVAL; + + /* pool->p.offset has to be set according to the address + * offset used by the DMA engine to start copying rx data + */ + } + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; @@ -115,6 +130,16 @@ static struct page *__page_pool_get_cached(struct page_pool *pool) return page; } +static void page_pool_dma_sync_for_device(struct page_pool *pool, + struct page *page, + unsigned int dma_sync_size) +{ + dma_sync_size = min(dma_sync_size, pool->p.max_len); + dma_sync_single_range_for_device(pool->p.dev, page->dma_addr, + pool->p.offset, dma_sync_size, + pool->p.dma_dir); +} + /* slow path */ noinline static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, @@ -159,6 +184,9 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, } 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++; @@ -292,8 +320,8 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page) return !page_is_pfmemalloc(page) && page_to_nid(page) == pool->p.nid; } -void __page_pool_put_page(struct page_pool *pool, - struct page *page, bool allow_direct) +void __page_pool_put_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct) { /* This allocator is optimized for the XDP mode that uses * one-frame-per-page, but have fallbacks that act like the @@ -305,6 +333,10 @@ void __page_pool_put_page(struct page_pool *pool, pool_page_reusable(pool, page))) { /* Read barrier done in page_ref_count / READ_ONCE */ + if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) + page_pool_dma_sync_for_device(pool, page, + dma_sync_size); + if (allow_direct && in_serving_softirq()) if (__page_pool_recycle_direct(page, pool)) return; |