From: Jakub Kicinski kuba@kernel.org
The page providers which try to reuse the same pages will need to hold onto the ref, even if page gets released from the pool - as in releasing the page from the pp just transfers the "ownership" reference from pp to the provider, and provider will wait for other references to be gone before feeding this page back into the pool.
Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Mina Almasry almasrymina@google.com
---
- This is implemented by Jakub in his RFC: https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.c...
I take no credit for the idea or implementation; I only added minor edits to make this workable with device memory TCP, and removed some hacky test code. This is a critical dependency of device memory TCP and thus I'm pulling it into this series to make it revewable and mergeable.
- There is a pending discussion about the acceptance of the page_pool memory provider hooks:
https://lore.kernel.org/netdev/20240403002053.2376017-3-almasrymina@google.c...
I'm unsure if the discussion has been resolved yet. There seems to be agreement that the io_uring use case without dmabuf is good but unsure about the ops. The conversation will likely continue to this iteration.
Cc: Christoph Hellwig hch@infradead.org
RFC v3 -> v1 - Removed unusued mem_provider. (Yunsheng). - Replaced memory_provider & mp_priv with netdev_rx_queue (Jakub).
--- include/net/page_pool/types.h | 12 ++++++++++ net/core/page_pool.c | 43 +++++++++++++++++++++++++++++++---- 2 files changed, 50 insertions(+), 5 deletions(-)
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index a6ebed0022160..2bf15ca6bfd48 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -52,6 +52,7 @@ struct pp_alloc_cache { * @dev: device, for DMA pre-mapping purposes * @netdev: netdev this pool will serve (leave as NULL if none or multiple) * @napi: NAPI which is the sole consumer of pages, otherwise NULL + * @queue: struct netdev_rx_queue this page_pool is being created for. * @dma_dir: DMA mapping direction * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV @@ -64,6 +65,7 @@ struct page_pool_params { int nid; struct device *dev; struct napi_struct *napi; + struct netdev_rx_queue *queue; enum dma_data_direction dma_dir; unsigned int max_len; unsigned int offset; @@ -126,6 +128,13 @@ struct page_pool_stats { }; #endif
+struct memory_provider_ops { + int (*init)(struct page_pool *pool); + void (*destroy)(struct page_pool *pool); + struct page *(*alloc_pages)(struct page_pool *pool, gfp_t gfp); + bool (*release_page)(struct page_pool *pool, struct page *page); +}; + struct page_pool { struct page_pool_params_fast p;
@@ -176,6 +185,9 @@ struct page_pool { */ struct ptr_ring ring;
+ void *mp_priv; + const struct memory_provider_ops *mp_ops; + #ifdef CONFIG_PAGE_POOL_STATS /* recycle stats are per-cpu to avoid locking */ struct page_pool_recycle_stats __percpu *recycle_stats; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 8bcc7014a61a0..ae403397df09d 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -26,6 +26,8 @@
#include "page_pool_priv.h"
+static DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers); + #define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ)
@@ -178,6 +180,7 @@ static int page_pool_init(struct page_pool *pool, int cpuid) { unsigned int ring_qsize = 1024; /* Default */ + int err;
memcpy(&pool->p, ¶ms->fast, sizeof(pool->p)); memcpy(&pool->slow, ¶ms->slow, sizeof(pool->slow)); @@ -249,10 +252,25 @@ static int page_pool_init(struct page_pool *pool, /* Driver calling page_pool_create() also call page_pool_destroy() */ refcount_set(&pool->user_cnt, 1);
+ if (pool->mp_ops) { + err = pool->mp_ops->init(pool); + if (err) { + pr_warn("%s() mem-provider init failed %d\n", __func__, + err); + goto free_ptr_ring; + } + + static_branch_inc(&page_pool_mem_providers); + } + if (pool->p.flags & PP_FLAG_DMA_MAP) get_device(pool->p.dev);
return 0; + +free_ptr_ring: + ptr_ring_cleanup(&pool->ring, NULL); + return err; }
static void page_pool_uninit(struct page_pool *pool) @@ -547,7 +565,10 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) return page;
/* Slow-path: cache empty, do real allocation */ - page = __page_pool_alloc_pages_slow(pool, gfp); + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops) + page = pool->mp_ops->alloc_pages(pool, gfp); + else + page = __page_pool_alloc_pages_slow(pool, gfp); return page; } EXPORT_SYMBOL(page_pool_alloc_pages); @@ -605,10 +626,13 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) void page_pool_return_page(struct page_pool *pool, struct page *page) { int count; + bool put;
- __page_pool_release_page_dma(pool, page); - - page_pool_clear_pp_info(page); + put = true; + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops) + put = pool->mp_ops->release_page(pool, page); + else + __page_pool_release_page_dma(pool, page);
/* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. @@ -616,7 +640,10 @@ void page_pool_return_page(struct page_pool *pool, struct page *page) count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt); trace_page_pool_state_release(pool, page, count);
- put_page(page); + if (put) { + page_pool_clear_pp_info(page); + put_page(page); + } /* An optimization would be to call __free_pages(page, pool->p.order) * knowing page is not part of page-cache (thus avoiding a * __page_cache_release() call). @@ -919,6 +946,12 @@ static void __page_pool_destroy(struct page_pool *pool)
page_pool_unlist(pool); page_pool_uninit(pool); + + if (pool->mp_ops) { + pool->mp_ops->destroy(pool); + static_branch_dec(&page_pool_mem_providers); + } + kfree(pool); }