From 394fcd8a813456b3306c423ec4227ed874dfc08b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Aug 2020 08:43:59 -0700 Subject: net: zerocopy: combine pages in zerocopy_sg_from_iter() Currently, tcp sendmsg(MSG_ZEROCOPY) is building skbs with order-0 fragments. Compared to standard sendmsg(), these skbs usually contain up to 16 fragments on arches with 4KB page sizes, instead of two. This adds considerable costs on various ndo_start_xmit() handlers, especially when IOMMU is in the picture. As high performance applications are often using huge pages, we can try to combine adjacent pages belonging to same compound page. Tested on AMD Rome platform, with IOMMU, nominal single TCP flow speed is roughly doubled (~55Gbit -> ~100Gbit), when user application is using hugepages. For reference, nominal single TCP flow speed on this platform without MSG_ZEROCOPY is ~65Gbit. Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Signed-off-by: David S. Miller --- net/core/datagram.c | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) (limited to 'net/core') diff --git a/net/core/datagram.c b/net/core/datagram.c index 639745d4f3b9..9fcaa544f11a 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -623,10 +623,11 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, while (length && iov_iter_count(from)) { struct page *pages[MAX_SKB_FRAGS]; + struct page *last_head = NULL; size_t start; ssize_t copied; unsigned long truesize; - int n = 0; + int refs, n = 0; if (frag == MAX_SKB_FRAGS) return -EMSGSIZE; @@ -649,13 +650,37 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } - while (copied) { + for (refs = 0; copied != 0; start = 0) { int size = min_t(int, copied, PAGE_SIZE - start); - skb_fill_page_desc(skb, frag++, pages[n], start, size); - start = 0; + struct page *head = compound_head(pages[n]); + + start += (pages[n] - head) << PAGE_SHIFT; copied -= size; n++; + if (frag) { + skb_frag_t *last = &skb_shinfo(skb)->frags[frag - 1]; + + if (head == skb_frag_page(last) && + start == skb_frag_off(last) + skb_frag_size(last)) { + skb_frag_size_add(last, size); + /* We combined this page, we need to release + * a reference. Since compound pages refcount + * is shared among many pages, batch the refcount + * adjustments to limit false sharing. + */ + last_head = head; + refs++; + continue; + } + } + if (refs) { + page_ref_sub(last_head, refs); + refs = 0; + } + skb_fill_page_desc(skb, frag++, head, start, size); } + if (refs) + page_ref_sub(last_head, refs); } return 0; } -- cgit v1.2.3