From 4d2bb0bfe8741a8778e0053f31a4e0f0cba80e8b Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 12 Feb 2024 10:50:55 +0100 Subject: xdp: rely on skb pointer reference in do_xdp_generic and netif_receive_generic_xdp Rely on skb pointer reference instead of the skb pointer in do_xdp_generic and netif_receive_generic_xdp routine signatures. This is a preliminary patch to add multi-buff support for xdp running in generic mode where we will need to reallocate the skb to avoid linearization and we will need to make it visible to do_xdp_generic() caller. Acked-by: Jesper Dangaard Brouer Reviewed-by: Toke Hoiland-Jorgensen Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/c09415b1f48c8620ef4d76deed35050a7bddf7c2.1707729884.git.lorenzo@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 07cefa32eafa..a3f9c95da51e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3958,7 +3958,7 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog); void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); -int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); +int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb); int netif_rx(struct sk_buff *skb); int __netif_rx(struct sk_buff *skb); -- cgit v1.3 From e6d5dbdd20aa6a86974af51deb9414cd2e7794cb Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 12 Feb 2024 10:50:56 +0100 Subject: xdp: add multi-buff support for xdp running in generic mode Similar to native xdp, do not always linearize the skb in netif_receive_generic_xdp routine but create a non-linear xdp_buff to be processed by the eBPF program. This allow to add multi-buffer support for xdp running in generic mode. Acked-by: Jesper Dangaard Brouer Reviewed-by: Toke Hoiland-Jorgensen Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/1044d6412b1c3e95b40d34993fd5f37cd2f319fd.1707729884.git.lorenzo@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 ++ net/core/dev.c | 70 +++++++++++++++++++++++++++----------- net/core/skbuff.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 144 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2dde34c29203..def3d8689c3d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3446,6 +3446,8 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } +int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, + struct bpf_prog *prog); bool napi_pp_put_page(struct page *page, bool napi_safe); static inline void diff --git a/net/core/dev.c b/net/core/dev.c index ffeb0e0279fe..2d02ca8a3da5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4874,6 +4874,12 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, skb_headlen(skb) + mac_len, true); + if (skb_is_nonlinear(skb)) { + skb_shinfo(skb)->xdp_frags_size = skb->data_len; + xdp_buff_set_frags_flag(xdp); + } else { + xdp_buff_clear_frags_flag(xdp); + } orig_data_end = xdp->data_end; orig_data = xdp->data; @@ -4903,6 +4909,14 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, skb->len += off; /* positive on grow, negative on shrink */ } + /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers + * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. + */ + if (xdp_buff_has_frags(xdp)) + skb->data_len = skb_shinfo(skb)->xdp_frags_size; + else + skb->data_len = 0; + /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; if ((orig_eth_type != eth->h_proto) || @@ -4936,12 +4950,35 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, return act; } +static int +netif_skb_check_for_xdp(struct sk_buff **pskb, struct bpf_prog *prog) +{ + struct sk_buff *skb = *pskb; + int err, hroom, troom; + + if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog)) + return 0; + + /* In case we have to go down the path and also linearize, + * then lets do the pskb_expand_head() work just once here. + */ + hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); + troom = skb->tail + skb->data_len - skb->end; + err = pskb_expand_head(skb, + hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, + troom > 0 ? troom + 128 : 0, GFP_ATOMIC); + if (err) + return err; + + return skb_linearize(skb); +} + static u32 netif_receive_generic_xdp(struct sk_buff **pskb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct sk_buff *skb = *pskb; - u32 act = XDP_DROP; + u32 mac_len, act = XDP_DROP; /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. @@ -4949,41 +4986,36 @@ static u32 netif_receive_generic_xdp(struct sk_buff **pskb, if (skb_is_redirected(skb)) return XDP_PASS; - /* XDP packets must be linear and must have sufficient headroom - * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also - * native XDP provides, thus we need to do it here as well. + /* XDP packets must have sufficient headroom of XDP_PACKET_HEADROOM + * bytes. This is the guarantee that also native XDP provides, + * thus we need to do it here as well. */ + mac_len = skb->data - skb_mac_header(skb); + __skb_push(skb, mac_len); + if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { - int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); - int troom = skb->tail + skb->data_len - skb->end; - - /* In case we have to go down the path and also linearize, - * then lets do the pskb_expand_head() work just once here. - */ - if (pskb_expand_head(skb, - hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, - troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) - goto do_drop; - if (skb_linearize(skb)) + if (netif_skb_check_for_xdp(pskb, xdp_prog)) goto do_drop; } - act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog); + __skb_pull(*pskb, mac_len); + + act = bpf_prog_run_generic_xdp(*pskb, xdp, xdp_prog); switch (act) { case XDP_REDIRECT: case XDP_TX: case XDP_PASS: break; default: - bpf_warn_invalid_xdp_action(skb->dev, xdp_prog, act); + bpf_warn_invalid_xdp_action((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: - trace_xdp_exception(skb->dev, xdp_prog, act); + trace_xdp_exception((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_DROP: do_drop: - kfree_skb(skb); + kfree_skb(*pskb); break; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9e5eb47b4025..bdb94749f05d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -895,6 +895,97 @@ static bool is_pp_page(struct page *page) return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; } +static int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, + unsigned int headroom) +{ +#if IS_ENABLED(CONFIG_PAGE_POOL) + u32 size, truesize, len, max_head_size, off; + struct sk_buff *skb = *pskb, *nskb; + int err, i, head_off; + void *data; + + /* XDP does not support fraglist so we need to linearize + * the skb. + */ + if (skb_has_frag_list(skb)) + return -EOPNOTSUPP; + + max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom); + if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE) + return -ENOMEM; + + size = min_t(u32, skb->len, max_head_size); + truesize = SKB_HEAD_ALIGN(size) + headroom; + data = page_pool_dev_alloc_va(pool, &truesize); + if (!data) + return -ENOMEM; + + nskb = napi_build_skb(data, truesize); + if (!nskb) { + page_pool_free_va(pool, data, true); + return -ENOMEM; + } + + skb_reserve(nskb, headroom); + skb_copy_header(nskb, skb); + skb_mark_for_recycle(nskb); + + err = skb_copy_bits(skb, 0, nskb->data, size); + if (err) { + consume_skb(nskb); + return err; + } + skb_put(nskb, size); + + head_off = skb_headroom(nskb) - skb_headroom(skb); + skb_headers_offset_update(nskb, head_off); + + off = size; + len = skb->len - off; + for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) { + struct page *page; + u32 page_off; + + size = min_t(u32, len, PAGE_SIZE); + truesize = size; + + page = page_pool_dev_alloc(pool, &page_off, &truesize); + if (!data) { + consume_skb(nskb); + return -ENOMEM; + } + + skb_add_rx_frag(nskb, i, page, page_off, size, truesize); + err = skb_copy_bits(skb, off, page_address(page) + page_off, + size); + if (err) { + consume_skb(nskb); + return err; + } + + len -= size; + off += size; + } + + consume_skb(skb); + *pskb = nskb; + + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, + struct bpf_prog *prog) +{ + if (!prog->aux->xdp_has_frags) + return -EINVAL; + + return skb_pp_cow_data(pool, pskb, XDP_PACKET_HEADROOM); +} +EXPORT_SYMBOL(skb_cow_data_for_xdp); + #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(struct page *page, bool napi_safe) { -- cgit v1.3 From 27accb3cc08a0ec4e348356774042d5fa5f30cce Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 12 Feb 2024 10:50:57 +0100 Subject: veth: rely on skb_pp_cow_data utility routine Rely on skb_pp_cow_data utility routine and remove duplicated code. Acked-by: Jesper Dangaard Brouer Reviewed-by: Toke Hoiland-Jorgensen Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/029cc14cce41cb242ee7efdcf32acc81f1ce4e9f.1707729884.git.lorenzo@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/veth.c | 74 ++------------------------------------------------ include/linux/skbuff.h | 2 ++ net/core/skbuff.c | 5 ++-- 3 files changed, 7 insertions(+), 74 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/veth.c b/drivers/net/veth.c index de1f13837782..500b9dfccd08 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -729,80 +729,10 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, if (skb_shared(skb) || skb_head_is_locked(skb) || skb_shinfo(skb)->nr_frags || skb_headroom(skb) < XDP_PACKET_HEADROOM) { - u32 size, len, max_head_size, off, truesize, page_offset; - struct sk_buff *nskb; - struct page *page; - int i, head_off; - void *va; - - /* We need a private copy of the skb and data buffers since - * the ebpf program can modify it. We segment the original skb - * into order-0 pages without linearize it. - * - * Make sure we have enough space for linear and paged area - */ - max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - - VETH_XDP_HEADROOM); - if (skb->len > PAGE_SIZE * MAX_SKB_FRAGS + max_head_size) - goto drop; - - size = min_t(u32, skb->len, max_head_size); - truesize = SKB_HEAD_ALIGN(size) + VETH_XDP_HEADROOM; - - /* Allocate skb head */ - va = page_pool_dev_alloc_va(rq->page_pool, &truesize); - if (!va) - goto drop; - - nskb = napi_build_skb(va, truesize); - if (!nskb) { - page_pool_free_va(rq->page_pool, va, true); + if (skb_pp_cow_data(rq->page_pool, pskb, XDP_PACKET_HEADROOM)) goto drop; - } - - skb_reserve(nskb, VETH_XDP_HEADROOM); - skb_copy_header(nskb, skb); - skb_mark_for_recycle(nskb); - - if (skb_copy_bits(skb, 0, nskb->data, size)) { - consume_skb(nskb); - goto drop; - } - skb_put(nskb, size); - head_off = skb_headroom(nskb) - skb_headroom(skb); - skb_headers_offset_update(nskb, head_off); - - /* Allocate paged area of new skb */ - off = size; - len = skb->len - off; - - for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) { - size = min_t(u32, len, PAGE_SIZE); - truesize = size; - - page = page_pool_dev_alloc(rq->page_pool, &page_offset, - &truesize); - if (!page) { - consume_skb(nskb); - goto drop; - } - - skb_add_rx_frag(nskb, i, page, page_offset, size, - truesize); - if (skb_copy_bits(skb, off, - page_address(page) + page_offset, - size)) { - consume_skb(nskb); - goto drop; - } - - len -= size; - off += size; - } - - consume_skb(skb); - skb = nskb; + skb = *pskb; } /* SKB "head" area always have tailroom for skb_shared_info */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index def3d8689c3d..696e7680656f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3446,6 +3446,8 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } +int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, + unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); bool napi_pp_put_page(struct page *page, bool napi_safe); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bdb94749f05d..0d9a489e6ae1 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -895,8 +895,8 @@ static bool is_pp_page(struct page *page) return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; } -static int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, - unsigned int headroom) +int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, + unsigned int headroom) { #if IS_ENABLED(CONFIG_PAGE_POOL) u32 size, truesize, len, max_head_size, off; @@ -975,6 +975,7 @@ static int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, return -EOPNOTSUPP; #endif } +EXPORT_SYMBOL(skb_pp_cow_data); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog) -- cgit v1.3