diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 47ffc683015d29a793dc7de33e2036264a11685a..a15e9e2146ba06a791c09ca11b15b1987fe7cac8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,6 +37,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif @@ -664,6 +665,8 @@ typedef unsigned char *sk_buff_data_t; * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves + * @pp_recycle: mark the packet for recycling instead of freeing (implies + * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed @@ -784,10 +787,12 @@ struct sk_buff { fclone:2, peeked:1, head_frag:1, - pfmemalloc:1; + pfmemalloc:1, + pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif + /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() */ @@ -3034,7 +3039,13 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) */ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { - put_page(skb_frag_page(frag)); + struct page *page = skb_frag_page(frag); + +#ifdef CONFIG_PAGE_POOL + if (recycle && page_pool_return_skb_page(page)) + return; +#endif + put_page(page); } /** @@ -3046,7 +3057,7 @@ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { - __skb_frag_unref(&skb_shinfo(skb)->frags[f], false); + __skb_frag_unref(&skb_shinfo(skb)->frags[f], skb->pp_recycle); } /** @@ -4661,5 +4672,21 @@ static inline bool skb_csum_is_sctp(struct sk_buff *skb) return skb->csum_not_inet; } +#ifdef CONFIG_PAGE_POOL +static inline void skb_mark_for_recycle(struct sk_buff *skb, struct page *page, + struct page_pool *pp) +{ + skb->pp_recycle = 1; + page_pool_store_mem_info(page, pp); +} +#endif + +static inline bool skb_pp_recycle(struct sk_buff *skb, void *data) +{ + if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) + return false; + return page_pool_return_skb_page(virt_to_page(data)); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b4b6de909c934b3cc858d592590cf43c5d15d721..3dd62dd73027d53c348783f9ee30c030ebaec3b9 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -146,6 +146,8 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) return pool->p.dma_dir; } +bool page_pool_return_skb_page(struct page *page); + struct page_pool *page_pool_create(const struct page_pool_params *params); #ifdef CONFIG_PAGE_POOL @@ -251,4 +253,11 @@ static inline void page_pool_ring_unlock(struct page_pool *pool) spin_unlock_bh(&pool->ring.producer_lock); } +/* Store mem_info on struct page and use it while recycling skb frags */ +static inline +void page_pool_store_mem_info(struct page *page, struct page_pool *pp) +{ + page->pp = pp; +} + #endif /* _NET_PAGE_POOL_H */ diff --git a/net/core/page_pool.c b/net/core/page_pool.c index e1321bc9d316dcfc8d20e85e1a789b669a13ad4c..5e4eb45b139c7138ad3fe2d223dc1ac1d405cdd1 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -628,3 +628,25 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) } } EXPORT_SYMBOL(page_pool_update_nid); + +bool page_pool_return_skb_page(struct page *page) +{ + struct page_pool *pp; + + page = compound_head(page); + if (unlikely(page->pp_magic != PP_SIGNATURE)) + return false; + + pp = page->pp; + + /* Driver set this to memory recycling info. Reset it on recycle. + * This will *not* work for NIC using a split-page memory model. + * The page will be returned to the pool here regardless of the + * 'flipped' fragment being in use or not. + */ + page->pp = NULL; + page_pool_put_full_page(pp, page, false); + + return true; +} +EXPORT_SYMBOL(page_pool_return_skb_page); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9580a6603d6f019eb57c2e6c39db11a623f07413..e7bf21d7d5316025ffef6b96f00e949a9ce7a112 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -69,6 +69,7 @@ #include #include #include +#include #include #include @@ -598,10 +599,13 @@ static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; - if (skb->head_frag) + if (skb->head_frag) { + if (skb_pp_recycle(skb, head)) + return; skb_free_frag(head); - else + } else { kfree(head); + } } static void skb_release_data(struct sk_buff *skb) @@ -617,7 +621,7 @@ static void skb_release_data(struct sk_buff *skb) skb_zcopy_clear(skb, true); for (i = 0; i < shinfo->nr_frags; i++) - __skb_frag_unref(&shinfo->frags[i], false); + __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); @@ -1004,6 +1008,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) n->nohdr = 0; n->peeked = 0; C(pfmemalloc); + C(pp_recycle); n->destructor = NULL; C(tail); C(end); @@ -3419,7 +3424,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, skb_frag_size(fragfrom)); - __skb_frag_unref(fragfrom, false); + __skb_frag_unref(fragfrom, skb->pp_recycle); } /* Reposition in the original skb */ @@ -5192,6 +5197,13 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; + /* The page pool signature of struct page will eventually figure out + * which pages can be recycled or not but for now let's prohibit slab + * allocated and page_pool allocated SKBs from being coalesced. + */ + if (to->pp_recycle != from->pp_recycle) + return false; + if (len <= skb_tailroom(to)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));