Message ID | 20210604183349.30040-4-mcroce@linux.microsoft.com (mailing list archive) |
---|---|
State | Superseded |
Delegated to: | Netdev Maintainers |
Headers | show |
Series | page_pool: recycle buffers | expand |
Context | Check | Description |
---|---|---|
netdev/cover_letter | success | Link |
netdev/fixes_present | success | Link |
netdev/patch_count | success | Link |
netdev/tree_selection | success | Clearly marked for net-next |
netdev/subject_prefix | success | Link |
netdev/cc_maintainers | warning | 6 maintainers not CCed: yhs@fb.com kpsingh@kernel.org andrii@kernel.org kafai@fb.com songliubraving@fb.com nogikh@google.com |
netdev/source_inline | success | Was 0 now: 0 |
netdev/verify_signedoff | success | Link |
netdev/module_param | success | Was 0 now: 0 |
netdev/build_32bit | success | Errors and warnings before: 6315 this patch: 6315 |
netdev/kdoc | success | Errors and warnings before: 0 this patch: 0 |
netdev/verify_fixes | success | Link |
netdev/checkpatch | success | total: 0 errors, 0 warnings, 0 checks, 173 lines checked |
netdev/build_allmodconfig_warn | success | Errors and warnings before: 6377 this patch: 6377 |
netdev/header_inline | success | Link |
On Fri, Jun 04, 2021 at 08:33:47PM +0200, Matteo Croce wrote: > diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h > index 7fcfea7e7b21..057b40ad29bd 100644 > --- a/include/linux/skbuff.h > +++ b/include/linux/skbuff.h > @@ -40,6 +40,9 @@ > #if IS_ENABLED(CONFIG_NF_CONNTRACK) > #include <linux/netfilter/nf_conntrack_common.h> > #endif > +#ifdef CONFIG_PAGE_POOL > +#include <net/page_pool.h> > +#endif I'm not a huge fan of conditional includes ... any reason to not include it always? > @@ -3088,7 +3095,13 @@ 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_address(page))) > + return; It feels weird to have a page here, convert it back to an address, then convert it back to a head page in page_pool_return_skb_page(). How about passing 'page' here, calling compound_head() in page_pool_return_skb_page() and calling virt_to_page() in skb_free_head()? > @@ -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; I'm not sure this wrapper needs to exist. > +} > + > #endif /* _NET_PAGE_POOL_H */ > diff --git a/net/core/page_pool.c b/net/core/page_pool.c > index e1321bc9d316..a03f48f45696 100644 > --- a/net/core/page_pool.c > +++ b/net/core/page_pool.c > @@ -628,3 +628,26 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) > } > } > EXPORT_SYMBOL(page_pool_update_nid); > + > +bool page_pool_return_skb_page(void *data) > +{ > + struct page_pool *pp; > + struct page *page; > + > + page = virt_to_head_page(data); > + if (unlikely(page->pp_magic != PP_SIGNATURE)) > + return false; > + > + pp = (struct page_pool *)page->pp; You don't need the cast any more. > + /* 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 12b7e90dd2b5..f769f08e7b32 100644 > --- a/net/core/skbuff.c > +++ b/net/core/skbuff.c > @@ -70,6 +70,9 @@ > #include <net/xfrm.h> > #include <net/mpls.h> > #include <net/mptcp.h> > +#ifdef CONFIG_PAGE_POOL > +#include <net/page_pool.h> > +#endif > > #include <linux/uaccess.h> > #include <trace/events/skb.h> > @@ -645,10 +648,15 @@ static void skb_free_head(struct sk_buff *skb) > { > unsigned char *head = skb->head; > > - if (skb->head_frag) > + if (skb->head_frag) { > +#ifdef CONFIG_PAGE_POOL > + if (skb->pp_recycle && page_pool_return_skb_page(head)) > + return; > +#endif put this in a header file: 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)); } then this becomes: 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)
On Fri, Jun 04, 2021 at 08:41:52PM +0100, Matthew Wilcox wrote: > On Fri, Jun 04, 2021 at 08:33:47PM +0200, Matteo Croce wrote: > > diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h > > index 7fcfea7e7b21..057b40ad29bd 100644 > > --- a/include/linux/skbuff.h > > +++ b/include/linux/skbuff.h > > @@ -40,6 +40,9 @@ > > #if IS_ENABLED(CONFIG_NF_CONNTRACK) > > #include <linux/netfilter/nf_conntrack_common.h> > > #endif > > +#ifdef CONFIG_PAGE_POOL > > +#include <net/page_pool.h> > > +#endif > > I'm not a huge fan of conditional includes ... any reason to not include > it always? I think we can. I'll check and change it. > > > @@ -3088,7 +3095,13 @@ 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_address(page))) > > + return; > > It feels weird to have a page here, convert it back to an address, > then convert it back to a head page in page_pool_return_skb_page(). > How about passing 'page' here, calling compound_head() in > page_pool_return_skb_page() and calling virt_to_page() in skb_free_head()? > Sure, sounds reasonable. > > @@ -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; > > I'm not sure this wrapper needs to exist. > > > +} > > + > > #endif /* _NET_PAGE_POOL_H */ > > diff --git a/net/core/page_pool.c b/net/core/page_pool.c > > index e1321bc9d316..a03f48f45696 100644 > > --- a/net/core/page_pool.c > > +++ b/net/core/page_pool.c > > @@ -628,3 +628,26 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) > > } > > } > > EXPORT_SYMBOL(page_pool_update_nid); > > + > > +bool page_pool_return_skb_page(void *data) > > +{ > > + struct page_pool *pp; > > + struct page *page; > > + > > + page = virt_to_head_page(data); > > + if (unlikely(page->pp_magic != PP_SIGNATURE)) > > + return false; > > + > > + pp = (struct page_pool *)page->pp; > > You don't need the cast any more. > True > > + /* 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 12b7e90dd2b5..f769f08e7b32 100644 > > --- a/net/core/skbuff.c > > +++ b/net/core/skbuff.c > > @@ -70,6 +70,9 @@ > > #include <net/xfrm.h> > > #include <net/mpls.h> > > #include <net/mptcp.h> > > +#ifdef CONFIG_PAGE_POOL > > +#include <net/page_pool.h> > > +#endif > > > > #include <linux/uaccess.h> > > #include <trace/events/skb.h> > > @@ -645,10 +648,15 @@ static void skb_free_head(struct sk_buff *skb) > > { > > unsigned char *head = skb->head; > > > > - if (skb->head_frag) > > + if (skb->head_frag) { > > +#ifdef CONFIG_PAGE_POOL > > + if (skb->pp_recycle && page_pool_return_skb_page(head)) > > + return; > > +#endif > > put this in a header file: > > 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)); > } > > then this becomes: > > if (skb->head_frag) { > if (skb_pp_recycle(skb, head)) > return; > > skb_free_frag(head); > > - else > > + } else { > > kfree(head); > > + } > > } > > ok Thanks for having a look Cheers /Ilias
On Fri, Jun 4, 2021 at 9:42 PM Matthew Wilcox <willy@infradead.org> wrote: > > On Fri, Jun 04, 2021 at 08:33:47PM +0200, Matteo Croce wrote: > > diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h > > index 7fcfea7e7b21..057b40ad29bd 100644 > > --- a/include/linux/skbuff.h > > +++ b/include/linux/skbuff.h > > @@ -40,6 +40,9 @@ > > #if IS_ENABLED(CONFIG_NF_CONNTRACK) > > #include <linux/netfilter/nf_conntrack_common.h> > > #endif > > +#ifdef CONFIG_PAGE_POOL > > +#include <net/page_pool.h> > > +#endif > > I'm not a huge fan of conditional includes ... any reason to not include > it always? > Nope, I tried without the conditional on a system without CONFIG_PAGE_POOL and it compiles fine > > @@ -3088,7 +3095,13 @@ 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_address(page))) > > + return; > > It feels weird to have a page here, convert it back to an address, > then convert it back to a head page in page_pool_return_skb_page(). > How about passing 'page' here, calling compound_head() in > page_pool_return_skb_page() and calling virt_to_page() in skb_free_head()? > I like it. > > @@ -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; > > I'm not sure this wrapper needs to exist. > I admit that this wrapper was bigger in the previous versions, but it's used by drivers which handle skb fragments (e.g. mvneta) to set the pointer for each frag. We can open code it, but it will be less straightforward. > > +} > > + > > #endif /* _NET_PAGE_POOL_H */ > > diff --git a/net/core/page_pool.c b/net/core/page_pool.c > > index e1321bc9d316..a03f48f45696 100644 > > --- a/net/core/page_pool.c > > +++ b/net/core/page_pool.c > > @@ -628,3 +628,26 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) > > } > > } > > EXPORT_SYMBOL(page_pool_update_nid); > > + > > +bool page_pool_return_skb_page(void *data) > > +{ > > + struct page_pool *pp; > > + struct page *page; > > + > > + page = virt_to_head_page(data); > > + if (unlikely(page->pp_magic != PP_SIGNATURE)) > > + return false; > > + > > + pp = (struct page_pool *)page->pp; > > You don't need the cast any more. > Right. > > + /* 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 12b7e90dd2b5..f769f08e7b32 100644 > > --- a/net/core/skbuff.c > > +++ b/net/core/skbuff.c > > @@ -70,6 +70,9 @@ > > #include <net/xfrm.h> > > #include <net/mpls.h> > > #include <net/mptcp.h> > > +#ifdef CONFIG_PAGE_POOL > > +#include <net/page_pool.h> > > +#endif > > > > #include <linux/uaccess.h> > > #include <trace/events/skb.h> > > @@ -645,10 +648,15 @@ static void skb_free_head(struct sk_buff *skb) > > { > > unsigned char *head = skb->head; > > > > - if (skb->head_frag) > > + if (skb->head_frag) { > > +#ifdef CONFIG_PAGE_POOL > > + if (skb->pp_recycle && page_pool_return_skb_page(head)) > > + return; > > +#endif > > put this in a header file: > > 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)); > } > > then this becomes: > > 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) Done. I'll send a v8 soon.
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7fcfea7e7b21..057b40ad29bd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -40,6 +40,9 @@ #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif +#ifdef CONFIG_PAGE_POOL +#include <net/page_pool.h> +#endif /* The interface for checksum offload between the stack and networking drivers * is as follows... @@ -667,6 +670,8 @@ 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 @@ -791,10 +796,12 @@ 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() */ @@ -3088,7 +3095,13 @@ 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_address(page))) + return; +#endif + put_page(page); } /** @@ -3100,7 +3113,7 @@ 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); } /** @@ -4699,5 +4712,14 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) #endif } +#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 + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b4b6de909c93..7b9b6a1c61f5 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(void *data); + 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 e1321bc9d316..a03f48f45696 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -628,3 +628,26 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) } } EXPORT_SYMBOL(page_pool_update_nid); + +bool page_pool_return_skb_page(void *data) +{ + struct page_pool *pp; + struct page *page; + + page = virt_to_head_page(data); + if (unlikely(page->pp_magic != PP_SIGNATURE)) + return false; + + pp = (struct page_pool *)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 12b7e90dd2b5..f769f08e7b32 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -70,6 +70,9 @@ #include <net/xfrm.h> #include <net/mpls.h> #include <net/mptcp.h> +#ifdef CONFIG_PAGE_POOL +#include <net/page_pool.h> +#endif #include <linux/uaccess.h> #include <trace/events/skb.h> @@ -645,10 +648,15 @@ static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; - if (skb->head_frag) + if (skb->head_frag) { +#ifdef CONFIG_PAGE_POOL + if (skb->pp_recycle && page_pool_return_skb_page(head)) + return; +#endif skb_free_frag(head); - else + } else { kfree(head); + } } static void skb_release_data(struct sk_buff *skb) @@ -664,7 +672,7 @@ 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); @@ -1046,6 +1054,7 @@ 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); @@ -3495,7 +3504,7 @@ 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 */ @@ -5285,6 +5294,13 @@ 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));