From d1a6150ca6166d76bbda77afa27ee46c010fcdc0 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:44 -0800 Subject: [PATCH] net-zerocopy: Refactor skb frag fast-forward op. [ Upstream commit 7fba5309efe24e4f0284ef4b8663cdf401035e72 ] Refactor skb frag fast-forwarding for tcp receive zerocopy. This is part of a patch set that introduces short-circuited hybrid copies for small receive operations, which results in roughly 33% fewer syscalls for small RPC scenarios. skb_advance_to_frag(), given a skb and an offset into the skb, iterates from the first frag for the skb until we're at the frag specified by the offset. Assuming the offset provided refers to how many bytes in the skb are already read, the returned frag points to the next frag we may read from, while offset_frag is set to the number of bytes from this frag that we have already read. If frag is not null and offset_frag is equal to 0, then we may be able to map this frag's page into the process address space with vm_insert_page(). However, if offset_frag is not equal to 0, then we cannot do so. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ba6e4c6db3b0..b3721cff4502 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1746,6 +1746,28 @@ int tcp_mmap(struct file *file, struct socket *sock, } EXPORT_SYMBOL(tcp_mmap); +static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, + u32 *offset_frag) +{ + skb_frag_t *frag; + + offset_skb -= skb_headlen(skb); + if ((int)offset_skb < 0 || skb_has_frag_list(skb)) + return NULL; + + frag = skb_shinfo(skb)->frags; + while (offset_skb) { + if (skb_frag_size(frag) > offset_skb) { + *offset_frag = offset_skb; + return frag; + } + offset_skb -= skb_frag_size(frag); + ++frag; + } + *offset_frag = 0; + return frag; +} + static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) @@ -1872,6 +1894,8 @@ static int tcp_zerocopy_receive(struct sock *sk, curr_addr = address; while (length + PAGE_SIZE <= zc->length) { if (zc->recv_skip_hint < PAGE_SIZE) { + u32 offset_frag; + /* If we're here, finish the current batch. */ if (pg_idx) { ret = tcp_zerocopy_vm_insert_batch(vma, pages, @@ -1892,16 +1916,9 @@ static int tcp_zerocopy_receive(struct sock *sk, skb = tcp_recv_skb(sk, seq, &offset); } zc->recv_skip_hint = skb->len - offset; - offset -= skb_headlen(skb); - if ((int)offset < 0 || skb_has_frag_list(skb)) + frags = skb_advance_to_frag(skb, offset, &offset_frag); + if (!frags || offset_frag) break; - frags = skb_shinfo(skb)->frags; - while (offset) { - if (skb_frag_size(frags) > offset) - goto out; - offset -= skb_frag_size(frags); - frags++; - } } if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) { int remaining = zc->recv_skip_hint; -- 2.25.1