From 8eb77cc73977d88787b37c92831b1c242e035396 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:25 +0100 Subject: [PATCH 01/34] ipv4: avoid partial copy for zc Even when zerocopy transmission is requested and possible, __ip_append_data() will still copy a small chunk of data just because it allocated some extra linear space (e.g. 148 bytes). It wastes CPU cycles on copy and iter manipulations and also misalignes potentially aligned data. Avoid such copies. And as a bonus we can allocate smaller skb. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- net/ipv4/ip_output.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 00b4bf26fd93..581d1e233260 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -969,7 +969,6 @@ static int __ip_append_data(struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; - struct ip_options *opt = cork->opt; int hh_len; int exthdrlen; @@ -977,6 +976,7 @@ static int __ip_append_data(struct sock *sk, int copy; int err; int offset = 0; + bool zc = false; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; @@ -1025,6 +1025,7 @@ static int __ip_append_data(struct sock *sk, if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; + zc = true; } else { uarg->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); @@ -1091,9 +1092,12 @@ alloc_new_skb: (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; - else { + else if (!zc) { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; + } else { + alloclen = fragheaderlen + transhdrlen; + pagedlen = datalen - transhdrlen; } alloclen += alloc_extra; From 773ba4fe9104a64a54d1c00f0fb6ffb95def2b03 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:26 +0100 Subject: [PATCH 02/34] ipv6: avoid partial copy for zc Even when zerocopy transmission is requested and possible, __ip_append_data() will still copy a small chunk of data just because it allocated some extra linear space (e.g. 128 bytes). It wastes CPU cycles on copy and iter manipulations and also misalignes potentially aligned data. Avoid such copies. And as a bonus we can allocate smaller skb. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 77e3f5970ce4..fc74ce3ed8cc 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1464,6 +1464,7 @@ static int __ip6_append_data(struct sock *sk, int copy; int err; int offset = 0; + bool zc = false; u32 tskey = 0; struct rt6_info *rt = (struct rt6_info *)cork->dst; struct ipv6_txoptions *opt = v6_cork->opt; @@ -1549,6 +1550,7 @@ emsgsize: if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; + zc = true; } else { uarg->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); @@ -1630,9 +1632,12 @@ alloc_new_skb: (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; - else { + else if (!zc) { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; + } else { + alloclen = fragheaderlen + transhdrlen; + pagedlen = datalen - transhdrlen; } alloclen += alloc_extra; From 1b4b2b09d4fb451029b112f17d34792e0277aeb2 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:27 +0100 Subject: [PATCH 03/34] skbuff: don't mix ubuf_info from different sources We should not append MSG_ZEROCOPY requests to skbuff with non MSG_ZEROCOPY ubuf_info, they might be not compatible. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- net/core/skbuff.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5b3559cb1d82..09f56bfa2771 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1212,6 +1212,10 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, const u32 byte_limit = 1 << 19; /* limit to a few TSO */ u32 bytelen, next; + /* there might be non MSG_ZEROCOPY users */ + if (uarg->callback != msg_zerocopy_callback) + return NULL; + /* realloc only when socket is locked (TCP, UDP cork), * so uarg->len and sk_zckey access is serialized */ From 2e07a521e1e424787af3bfc59615de4220856c35 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:28 +0100 Subject: [PATCH 04/34] skbuff: add SKBFL_DONT_ORPHAN flag We don't want to list every single ubuf_info callback in skb_orphan_frags(), add a flag controlling the behaviour. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 8 +++++--- net/core/skbuff.c | 2 +- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d3d10556f0fa..8e12b3b9ad6c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -686,10 +686,13 @@ enum { * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), + + SKBFL_DONT_ORPHAN = BIT(3), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) -#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY) +#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ + SKBFL_DONT_ORPHAN) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -3182,8 +3185,7 @@ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; - if (!skb_zcopy_is_nouarg(skb) && - skb_uarg(skb)->callback == msg_zerocopy_callback) + if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 09f56bfa2771..fc22b3d32052 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1193,7 +1193,7 @@ static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) uarg->len = 1; uarg->bytelen = size; uarg->zerocopy = 1; - uarg->flags = SKBFL_ZEROCOPY_FRAG; + uarg->flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN; refcount_set(&uarg->refcnt, 1); sock_hold(sk); From 7c701d92b2b5e5175dbfec875816474b802b0c45 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:29 +0100 Subject: [PATCH 05/34] skbuff: carry external ubuf_info in msghdr Make possible for network in-kernel callers like io_uring to pass in a custom ubuf_info by setting it in a new field of struct msghdr. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- include/linux/socket.h | 1 + net/compat.c | 1 + net/socket.c | 2 ++ 3 files changed, 4 insertions(+) diff --git a/include/linux/socket.h b/include/linux/socket.h index 17311ad9f9af..7bac9fc1cee0 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -69,6 +69,7 @@ struct msghdr { unsigned int msg_flags; /* flags on received message */ __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ + struct ubuf_info *msg_ubuf; }; struct user_msghdr { diff --git a/net/compat.c b/net/compat.c index 210fc3b4d0d8..6cd2e7683dd0 100644 --- a/net/compat.c +++ b/net/compat.c @@ -80,6 +80,7 @@ int __get_compat_msghdr(struct msghdr *kmsg, return -EMSGSIZE; kmsg->msg_iocb = NULL; + kmsg->msg_ubuf = NULL; *ptr = msg.msg_iov; *len = msg.msg_iovlen; return 0; diff --git a/net/socket.c b/net/socket.c index 96300cdc0625..82af3882b876 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2106,6 +2106,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; + msg.msg_ubuf = NULL; if (addr) { err = move_addr_to_kernel(addr, addr_len, &address); if (err < 0) @@ -2405,6 +2406,7 @@ int __copy_msghdr_from_user(struct msghdr *kmsg, return -EMSGSIZE; kmsg->msg_iocb = NULL; + kmsg->msg_ubuf = NULL; *uiov = msg.msg_iov; *nsegs = msg.msg_iovlen; return 0; From ebe73a284f4de8c5d401adeccd9b8fe3183b6e95 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 12 Jul 2022 21:52:30 +0100 Subject: [PATCH 06/34] net: Allow custom iter handler in msghdr Add support for custom iov_iter handling to msghdr. The idea is that in-kernel subsystems want control over how an SG is split. Signed-off-by: David Ahern [pavel: move callback into msghdr] Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 7 ++++--- include/linux/socket.h | 4 ++++ net/core/datagram.c | 14 ++++++++++---- net/core/skbuff.c | 2 +- 4 files changed, 19 insertions(+), 8 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8e12b3b9ad6c..a8a2dd4cfdfd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1776,13 +1776,14 @@ void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, bool success); -int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, - struct iov_iter *from, size_t length); +int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb, struct iov_iter *from, + size_t length); static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { - return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len); + return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, diff --git a/include/linux/socket.h b/include/linux/socket.h index 7bac9fc1cee0..3c11ef18a9cf 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -14,6 +14,8 @@ struct file; struct pid; struct cred; struct socket; +struct sock; +struct sk_buff; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) @@ -70,6 +72,8 @@ struct msghdr { __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ struct ubuf_info *msg_ubuf; + int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length); }; struct user_msghdr { diff --git a/net/core/datagram.c b/net/core/datagram.c index 50f4faeea76c..28cdb79df74d 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -613,10 +613,16 @@ fault: } EXPORT_SYMBOL(skb_copy_datagram_from_iter); -int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, - struct iov_iter *from, size_t length) +int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb, struct iov_iter *from, + size_t length) { - int frag = skb_shinfo(skb)->nr_frags; + int frag; + + if (msg && msg->sg_from_iter) + return msg->sg_from_iter(sk, skb, from, length); + + frag = skb_shinfo(skb)->nr_frags; while (length && iov_iter_count(from)) { struct page *pages[MAX_SKB_FRAGS]; @@ -702,7 +708,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) if (skb_copy_datagram_from_iter(skb, 0, from, copy)) return -EFAULT; - return __zerocopy_sg_from_iter(NULL, skb, from, ~0U); + return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U); } EXPORT_SYMBOL(zerocopy_sg_from_iter); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index fc22b3d32052..f5a3ebbc1f7e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1358,7 +1358,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, if (orig_uarg && uarg != orig_uarg) return -EEXIST; - err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len); + err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { struct sock *save_sk = skb->sk; From 753f1ca4e1e50248a1b760c9774d6d6b354562cc Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:31 +0100 Subject: [PATCH 07/34] net: introduce managed frags infrastructure Some users like io_uring can do page pinning more efficiently, so we want a way to delegate referencing to other subsystems. For that add a new flag called SKBFL_MANAGED_FRAG_REFS. When set, skb doesn't hold page references and upper layers are responsivle to managing page lifetime. It's allowed to convert skbs from managed to normal by calling skb_zcopy_downgrade_managed(). The function will take all needed page references and clear the flag. It's needed, for instance, to avoid mixing managed modes. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 25 +++++++++++++++++++++++-- net/core/skbuff.c | 29 +++++++++++++++++++++++++++-- 2 files changed, 50 insertions(+), 4 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a8a2dd4cfdfd..07004593d7ca 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -688,11 +688,16 @@ enum { SKBFL_PURE_ZEROCOPY = BIT(2), SKBFL_DONT_ORPHAN = BIT(3), + + /* page references are managed by the ubuf_info, so it's safe to + * use frags only up until ubuf_info is released + */ + SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ - SKBFL_DONT_ORPHAN) + SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -1810,6 +1815,11 @@ static inline bool skb_zcopy_pure(const struct sk_buff *skb) return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } +static inline bool skb_zcopy_managed(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; +} + static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { @@ -1884,6 +1894,14 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) } } +void __skb_zcopy_downgrade_managed(struct sk_buff *skb); + +static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) +{ + if (unlikely(skb_zcopy_managed(skb))) + __skb_zcopy_downgrade_managed(skb); +} + static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; @@ -3499,7 +3517,10 @@ 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], skb->pp_recycle); + struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (!skb_zcopy_managed(skb)) + __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); } /** diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f5a3ebbc1f7e..cf4107d80bc4 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -666,11 +666,18 @@ static void skb_release_data(struct sk_buff *skb) &shinfo->dataref)) goto exit; - skb_zcopy_clear(skb, true); + if (skb_zcopy(skb)) { + bool skip_unref = shinfo->flags & SKBFL_MANAGED_FRAG_REFS; + + skb_zcopy_clear(skb, true); + if (skip_unref) + goto free_head; + } for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); +free_head: if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); @@ -895,7 +902,10 @@ EXPORT_SYMBOL(skb_dump); */ void skb_tx_error(struct sk_buff *skb) { - skb_zcopy_clear(skb, true); + if (skb) { + skb_zcopy_downgrade_managed(skb); + skb_zcopy_clear(skb, true); + } } EXPORT_SYMBOL(skb_tx_error); @@ -1375,6 +1385,16 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); +void __skb_zcopy_downgrade_managed(struct sk_buff *skb) +{ + int i; + + skb_shinfo(skb)->flags &= ~SKBFL_MANAGED_FRAG_REFS; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) + skb_frag_ref(skb, i); +} +EXPORT_SYMBOL_GPL(__skb_zcopy_downgrade_managed); + static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, gfp_t gfp_mask) { @@ -1692,6 +1712,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, BUG_ON(skb_shared(skb)); + skb_zcopy_downgrade_managed(skb); + size = SKB_DATA_ALIGN(size); if (skb_pfmemalloc(skb)) @@ -3488,6 +3510,8 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) int pos = skb_headlen(skb); const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY; + skb_zcopy_downgrade_managed(skb); + skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ @@ -3841,6 +3865,7 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, if (skb_can_coalesce(skb, i, page, offset)) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); } else if (i < MAX_SKB_FRAGS) { + skb_zcopy_downgrade_managed(skb); get_page(page); skb_fill_page_desc(skb, i, page, offset, size); } else { From 84ce071e38a6e25ea3ea91188e5482ac1f17b3af Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:32 +0100 Subject: [PATCH 08/34] net: introduce __skb_fill_page_desc_noacc Managed pages contain pinned userspace pages and controlled by upper layers, there is no need in tracking skb->pfmemalloc for them. Introduce a helper for filling frags but ignoring page tracking, it'll be needed later. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 07004593d7ca..1111adefd906 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2550,6 +2550,22 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) return skb_headlen(skb) + __skb_pagelen(skb); } +static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, + int i, struct page *page, + int off, int size) +{ + skb_frag_t *frag = &shinfo->frags[i]; + + /* + * Propagate page pfmemalloc to the skb if we can. The problem is + * that not all callers have unique ownership of the page but rely + * on page_is_pfmemalloc doing the right thing(tm). + */ + frag->bv_page = page; + frag->bv_offset = off; + skb_frag_size_set(frag, size); +} + /** * __skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised @@ -2566,17 +2582,7 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - - /* - * Propagate page pfmemalloc to the skb if we can. The problem is - * that not all callers have unique ownership of the page but rely - * on page_is_pfmemalloc doing the right thing(tm). - */ - frag->bv_page = page; - frag->bv_offset = off; - skb_frag_size_set(frag, size); - + __skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size); page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; From c445f31b3cfaa008e110bf548c3a1f0198d332d4 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:33 +0100 Subject: [PATCH 09/34] ipv4/udp: support externally provided ubufs Teach ipv4/udp how to use external ubuf_info provided in msghdr and also prepare it for managed frags by sprinkling skb_zcopy_downgrade_managed() when it could mix managed and not managed frags. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- net/ipv4/ip_output.c | 44 +++++++++++++++++++++++++++++++------------- 1 file changed, 31 insertions(+), 13 deletions(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 581d1e233260..df7f9dfbe8be 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1017,18 +1017,35 @@ static int __ip_append_data(struct sock *sk, (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; - if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); - if (!uarg) - return -ENOBUFS; - extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ - if (rt->dst.dev->features & NETIF_F_SG && - csummode == CHECKSUM_PARTIAL) { - paged = true; - zc = true; - } else { - uarg->zerocopy = 0; - skb_zcopy_set(skb, uarg, &extra_uref); + if ((flags & MSG_ZEROCOPY) && length) { + struct msghdr *msg = from; + + if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { + if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) + return -EINVAL; + + /* Leave uarg NULL if can't zerocopy, callers should + * be able to handle it. + */ + if ((rt->dst.dev->features & NETIF_F_SG) && + csummode == CHECKSUM_PARTIAL) { + paged = true; + zc = true; + uarg = msg->msg_ubuf; + } + } else if (sock_flag(sk, SOCK_ZEROCOPY)) { + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); + if (!uarg) + return -ENOBUFS; + extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ + if (rt->dst.dev->features & NETIF_F_SG && + csummode == CHECKSUM_PARTIAL) { + paged = true; + zc = true; + } else { + uarg->zerocopy = 0; + skb_zcopy_set(skb, uarg, &extra_uref); + } } } @@ -1192,13 +1209,14 @@ alloc_new_skb: err = -EFAULT; goto error; } - } else if (!uarg || !uarg->zerocopy) { + } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; + skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; From 1fd3ae8c906c0f521238d436566323af3f0282e8 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:34 +0100 Subject: [PATCH 10/34] ipv6/udp: support externally provided ubufs Teach ipv6/udp how to use external ubuf_info provided in msghdr and also prepare it for managed frags by sprinkling skb_zcopy_downgrade_managed() when it could mix managed and not managed frags. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 44 ++++++++++++++++++++++++++++++------------- 1 file changed, 31 insertions(+), 13 deletions(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index fc74ce3ed8cc..897ca4f9b791 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1542,18 +1542,35 @@ emsgsize: rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; - if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); - if (!uarg) - return -ENOBUFS; - extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ - if (rt->dst.dev->features & NETIF_F_SG && - csummode == CHECKSUM_PARTIAL) { - paged = true; - zc = true; - } else { - uarg->zerocopy = 0; - skb_zcopy_set(skb, uarg, &extra_uref); + if ((flags & MSG_ZEROCOPY) && length) { + struct msghdr *msg = from; + + if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { + if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) + return -EINVAL; + + /* Leave uarg NULL if can't zerocopy, callers should + * be able to handle it. + */ + if ((rt->dst.dev->features & NETIF_F_SG) && + csummode == CHECKSUM_PARTIAL) { + paged = true; + zc = true; + uarg = msg->msg_ubuf; + } + } else if (sock_flag(sk, SOCK_ZEROCOPY)) { + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); + if (!uarg) + return -ENOBUFS; + extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ + if (rt->dst.dev->features & NETIF_F_SG && + csummode == CHECKSUM_PARTIAL) { + paged = true; + zc = true; + } else { + uarg->zerocopy = 0; + skb_zcopy_set(skb, uarg, &extra_uref); + } } } @@ -1747,13 +1764,14 @@ alloc_new_skb: err = -EFAULT; goto error; } - } else if (!uarg || !uarg->zerocopy) { + } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; + skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; From eb315a7d1396b1139fc7daea55f2d3191e8e7092 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:35 +0100 Subject: [PATCH 11/34] tcp: support externally provided ubufs Teach tcp how to use external ubuf_info provided in msghdr and also prepare it for managed frags by sprinkling skb_zcopy_downgrade_managed() when it could mix managed and not managed frags. Signed-off-by: Pavel Begunkov Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 028513d3e2a2..fdb80b9608fe 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1202,17 +1202,23 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) flags = msg->msg_flags; - if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { + if ((flags & MSG_ZEROCOPY) && size) { skb = tcp_write_queue_tail(sk); - uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); - if (!uarg) { - err = -ENOBUFS; - goto out_err; - } - zc = sk->sk_route_caps & NETIF_F_SG; - if (!zc) - uarg->zerocopy = 0; + if (msg->msg_ubuf) { + uarg = msg->msg_ubuf; + net_zcopy_get(uarg); + zc = sk->sk_route_caps & NETIF_F_SG; + } else if (sock_flag(sk, SOCK_ZEROCOPY)) { + uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); + if (!uarg) { + err = -ENOBUFS; + goto out_err; + } + zc = sk->sk_route_caps & NETIF_F_SG; + if (!zc) + uarg->zerocopy = 0; + } } if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && @@ -1335,8 +1341,13 @@ new_segment: copy = min_t(int, copy, pfrag->size - pfrag->offset); - if (tcp_downgrade_zcopy_pure(sk, skb) || - !sk_wmem_schedule(sk, copy)) + if (unlikely(skb_zcopy_pure(skb) || skb_zcopy_managed(skb))) { + if (tcp_downgrade_zcopy_pure(sk, skb)) + goto wait_for_space; + skb_zcopy_downgrade_managed(skb); + } + + if (!sk_wmem_schedule(sk, copy)) goto wait_for_space; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, From 2829a267fca297983b9302fa2cb833757328c857 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 21 Jul 2022 15:25:46 +0100 Subject: [PATCH 12/34] net: fix uninitialised msghdr->sg_from_iter Because of how struct msghdr is usually initialised some fields and sg_from_iter in particular might be left out not initialised, so we can't safely use it in __zerocopy_sg_from_iter(). For now use the callback only when there is ->msg_ubuf set relying on the fact that they're used together and we properly zero ->msg_ubuf. Fixes: ebe73a284f4de8 ("net: Allow custom iter handler in msghdr") Signed-off-by: Pavel Begunkov Message-Id: Signed-off-by: Jakub Kicinski --- net/core/datagram.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/datagram.c b/net/core/datagram.c index 28cdb79df74d..ecbc0f471089 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -619,7 +619,7 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, { int frag; - if (msg && msg->sg_from_iter) + if (msg && msg->msg_ubuf && msg->sg_from_iter) return msg->sg_from_iter(sk, skb, from, length); frag = skb_shinfo(skb)->nr_frags; From e02b66512738db161e83634255e9826c8cb51336 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:36 +0100 Subject: [PATCH 13/34] io_uring: initialise msghdr::msg_ubuf Initialise newly added ->msg_ubuf in io_recv() and io_send(). Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/b8f9f263875a4a36e7f26cc5d55ebe315308f57d.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/net.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/io_uring/net.c b/io_uring/net.c index e61efa31c729..bbc9c603641a 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -294,6 +294,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; + msg.msg_ubuf = NULL; flags = sr->msg_flags; if (issue_flags & IO_URING_F_NONBLOCK) @@ -783,6 +784,7 @@ retry_multishot: msg.msg_flags = 0; msg.msg_controllen = 0; msg.msg_iocb = NULL; + msg.msg_ubuf = NULL; flags = sr->msg_flags; if (force_nonblock) From e70cb60893ca64b7df06864aa16c1cf6d6c671db Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:37 +0100 Subject: [PATCH 14/34] io_uring: export io_put_task() Make io_put_task() available to non-core parts of io_uring, we'll need it for notification infrastructure. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/3686807d4c03b72e389947b0e8692d4d44334ef0.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 25 +++++++++++++++++++++++++ io_uring/io_uring.c | 11 +---------- io_uring/io_uring.h | 10 ++++++++++ io_uring/tctx.h | 26 -------------------------- 4 files changed, 36 insertions(+), 36 deletions(-) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index d54b8b7e0746..368c34d14b13 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -4,6 +4,7 @@ #include #include #include +#include #include struct io_wq_work_node { @@ -43,6 +44,30 @@ struct io_hash_table { unsigned hash_bits; }; +/* + * Arbitrary limit, can be raised if need be + */ +#define IO_RINGFD_REG_MAX 16 + +struct io_uring_task { + /* submission side */ + int cached_refs; + const struct io_ring_ctx *last; + struct io_wq *io_wq; + struct file *registered_rings[IO_RINGFD_REG_MAX]; + + struct xarray xa; + struct wait_queue_head wait; + atomic_t in_idle; + atomic_t inflight_tracked; + struct percpu_counter inflight; + + struct { /* task_work */ + struct llist_head task_list; + struct callback_head task_work; + } ____cacheline_aligned_in_smp; +}; + struct io_uring { u32 head ____cacheline_aligned_in_smp; u32 tail ____cacheline_aligned_in_smp; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 4b3fd645d023..7795cfedf6bf 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -608,7 +608,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) return ret; } -static void __io_put_task(struct task_struct *task, int nr) +void __io_put_task(struct task_struct *task, int nr) { struct io_uring_task *tctx = task->io_uring; @@ -618,15 +618,6 @@ static void __io_put_task(struct task_struct *task, int nr) put_task_struct_many(task, nr); } -/* must to be called somewhat shortly after putting a request */ -static inline void io_put_task(struct task_struct *task, int nr) -{ - if (likely(task == current)) - task->io_uring->cached_refs += nr; - else - __io_put_task(task, nr); -} - static void io_task_refs_refill(struct io_uring_task *tctx) { unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 5db0a60dc04e..b1c0c0a400d8 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -71,6 +71,7 @@ void io_wq_submit_work(struct io_wq_work *work); void io_free_req(struct io_kiocb *req); void io_queue_next(struct io_kiocb *req); +void __io_put_task(struct task_struct *task, int nr); bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all); @@ -258,4 +259,13 @@ static inline void io_commit_cqring_flush(struct io_ring_ctx *ctx) __io_commit_cqring_flush(ctx); } +/* must to be called somewhat shortly after putting a request */ +static inline void io_put_task(struct task_struct *task, int nr) +{ + if (likely(task == current)) + task->io_uring->cached_refs += nr; + else + __io_put_task(task, nr); +} + #endif diff --git a/io_uring/tctx.h b/io_uring/tctx.h index 8a33ff6e5d91..25974beed4d6 100644 --- a/io_uring/tctx.h +++ b/io_uring/tctx.h @@ -1,31 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include - -/* - * Arbitrary limit, can be raised if need be - */ -#define IO_RINGFD_REG_MAX 16 - -struct io_uring_task { - /* submission side */ - int cached_refs; - const struct io_ring_ctx *last; - struct io_wq *io_wq; - struct file *registered_rings[IO_RINGFD_REG_MAX]; - - struct xarray xa; - struct wait_queue_head wait; - atomic_t in_idle; - atomic_t inflight_tracked; - struct percpu_counter inflight; - - struct { /* task_work */ - struct llist_head task_list; - struct callback_head task_work; - } ____cacheline_aligned_in_smp; -}; - struct io_tctx_node { struct list_head ctx_node; struct task_struct *task; From eb42cebb2cf24c48f60c32856a4bba93d42659c8 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:38 +0100 Subject: [PATCH 15/34] io_uring: add zc notification infrastructure Add internal part of send zerocopy notifications. There are two main structures, the first one is struct io_notif, which carries inside struct ubuf_info and maps 1:1 to it. io_uring will be binding a number of zerocopy send requests to it and ask to complete (aka flush) it. When flushed and all attached requests and skbs complete, it'll generate one and only one CQE. There are intended to be passed into the network layer as struct msghdr::msg_ubuf. The second concept is notification slots. The userspace will be able to register an array of slots and subsequently addressing them by the index in the array. Slots are independent of each other. Each slot can have only one notifier at a time (called active notifier) but many notifiers during the lifetime. When active, a notifier not going to post any completion but the userspace can attach requests to it by specifying the corresponding slot while issueing send zc requests. Eventually, the userspace will want to "flush" the notifier losing any way to attach new requests to it, however it can use the next atomatically added notifier of this slot or of any other slot. When the network layer is done with all enqueued skbs attached to a notifier and doesn't need the specified in them user data, the flushed notifier will post a CQE. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/3ecf54c31a85762bf679b0a432c9f43ecf7e61cc.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 5 ++ io_uring/Makefile | 2 +- io_uring/io_uring.c | 8 ++- io_uring/io_uring.h | 2 + io_uring/notif.c | 102 +++++++++++++++++++++++++++++++++ io_uring/notif.h | 64 +++++++++++++++++++++ 6 files changed, 179 insertions(+), 4 deletions(-) create mode 100644 io_uring/notif.c create mode 100644 io_uring/notif.h diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 368c34d14b13..f7fab3758cb9 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -34,6 +34,9 @@ struct io_file_table { unsigned int alloc_hint; }; +struct io_notif; +struct io_notif_slot; + struct io_hash_bucket { spinlock_t lock; struct hlist_head list; @@ -237,6 +240,8 @@ struct io_ring_ctx { unsigned nr_user_files; unsigned nr_user_bufs; struct io_mapped_ubuf **user_bufs; + struct io_notif_slot *notif_slots; + unsigned nr_notif_slots; struct io_submit_state submit_state; diff --git a/io_uring/Makefile b/io_uring/Makefile index 466639c289be..8cc8e5387a75 100644 --- a/io_uring/Makefile +++ b/io_uring/Makefile @@ -7,5 +7,5 @@ obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \ openclose.o uring_cmd.o epoll.o \ statx.o net.o msg_ring.o timeout.o \ sqpoll.o fdinfo.o tctx.o poll.o \ - cancel.o kbuf.o rsrc.o rw.o opdef.o + cancel.o kbuf.o rsrc.o rw.o opdef.o notif.o obj-$(CONFIG_IO_WQ) += io-wq.o diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 7795cfedf6bf..65ac407dd74e 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -90,6 +90,7 @@ #include "rsrc.h" #include "cancel.h" #include "net.h" +#include "notif.h" #include "timeout.h" #include "poll.h" @@ -732,9 +733,8 @@ struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx) return &rings->cqes[off]; } -static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, - u64 user_data, s32 res, u32 cflags, - bool allow_overflow) +bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags, + bool allow_overflow) { struct io_uring_cqe *cqe; @@ -2491,6 +2491,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) } #endif WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); + WARN_ON_ONCE(ctx->notif_slots || ctx->nr_notif_slots); io_mem_free(ctx->rings); io_mem_free(ctx->sq_sqes); @@ -2667,6 +2668,7 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_unregister_personality(ctx, index); if (ctx->rings) io_poll_remove_all(ctx, NULL, true); + io_notif_unregister(ctx); mutex_unlock(&ctx->uring_lock); /* failed during ring init, it couldn't have issued any requests */ diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index b1c0c0a400d8..66bfd880d07f 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -33,6 +33,8 @@ void io_req_complete_post(struct io_kiocb *req); void __io_req_complete_post(struct io_kiocb *req); bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags, bool allow_overflow); +bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags, + bool allow_overflow); void __io_commit_cqring_flush(struct io_ring_ctx *ctx); struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages); diff --git a/io_uring/notif.c b/io_uring/notif.c new file mode 100644 index 000000000000..6ee948af6a49 --- /dev/null +++ b/io_uring/notif.c @@ -0,0 +1,102 @@ +#include +#include +#include +#include +#include +#include + +#include "io_uring.h" +#include "notif.h" + +static void __io_notif_complete_tw(struct callback_head *cb) +{ + struct io_notif *notif = container_of(cb, struct io_notif, task_work); + struct io_ring_ctx *ctx = notif->ctx; + + io_cq_lock(ctx); + io_fill_cqe_aux(ctx, notif->tag, 0, notif->seq, true); + io_cq_unlock_post(ctx); + + percpu_ref_put(&ctx->refs); + kfree(notif); +} + +static inline void io_notif_complete(struct io_notif *notif) +{ + __io_notif_complete_tw(¬if->task_work); +} + +static void io_notif_complete_wq(struct work_struct *work) +{ + struct io_notif *notif = container_of(work, struct io_notif, commit_work); + + io_notif_complete(notif); +} + +static void io_uring_tx_zerocopy_callback(struct sk_buff *skb, + struct ubuf_info *uarg, + bool success) +{ + struct io_notif *notif = container_of(uarg, struct io_notif, uarg); + + if (!refcount_dec_and_test(&uarg->refcnt)) + return; + INIT_WORK(¬if->commit_work, io_notif_complete_wq); + queue_work(system_unbound_wq, ¬if->commit_work); +} + +struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx, + struct io_notif_slot *slot) + __must_hold(&ctx->uring_lock) +{ + struct io_notif *notif; + + notif = kzalloc(sizeof(*notif), GFP_ATOMIC | __GFP_ACCOUNT); + if (!notif) + return NULL; + + notif->seq = slot->seq++; + notif->tag = slot->tag; + notif->ctx = ctx; + notif->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN; + notif->uarg.callback = io_uring_tx_zerocopy_callback; + /* master ref owned by io_notif_slot, will be dropped on flush */ + refcount_set(¬if->uarg.refcnt, 1); + percpu_ref_get(&ctx->refs); + return notif; +} + +static void io_notif_slot_flush(struct io_notif_slot *slot) + __must_hold(&ctx->uring_lock) +{ + struct io_notif *notif = slot->notif; + + slot->notif = NULL; + + if (WARN_ON_ONCE(in_interrupt())) + return; + /* drop slot's master ref */ + if (refcount_dec_and_test(¬if->uarg.refcnt)) + io_notif_complete(notif); +} + +__cold int io_notif_unregister(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + int i; + + if (!ctx->notif_slots) + return -ENXIO; + + for (i = 0; i < ctx->nr_notif_slots; i++) { + struct io_notif_slot *slot = &ctx->notif_slots[i]; + + if (slot->notif) + io_notif_slot_flush(slot); + } + + kvfree(ctx->notif_slots); + ctx->notif_slots = NULL; + ctx->nr_notif_slots = 0; + return 0; +} \ No newline at end of file diff --git a/io_uring/notif.h b/io_uring/notif.h new file mode 100644 index 000000000000..3d7a1d242e17 --- /dev/null +++ b/io_uring/notif.h @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include + +struct io_notif { + struct ubuf_info uarg; + struct io_ring_ctx *ctx; + + /* cqe->user_data, io_notif_slot::tag if not overridden */ + u64 tag; + /* see struct io_notif_slot::seq */ + u32 seq; + + union { + struct callback_head task_work; + struct work_struct commit_work; + }; +}; + +struct io_notif_slot { + /* + * Current/active notifier. A slot holds only one active notifier at a + * time and keeps one reference to it. Flush releases the reference and + * lazily replaces it with a new notifier. + */ + struct io_notif *notif; + + /* + * Default ->user_data for this slot notifiers CQEs + */ + u64 tag; + /* + * Notifiers of a slot live in generations, we create a new notifier + * only after flushing the previous one. Track the sequential number + * for all notifiers and copy it into notifiers's cqe->cflags + */ + u32 seq; +}; + +int io_notif_unregister(struct io_ring_ctx *ctx); + +struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx, + struct io_notif_slot *slot); + +static inline struct io_notif *io_get_notif(struct io_ring_ctx *ctx, + struct io_notif_slot *slot) +{ + if (!slot->notif) + slot->notif = io_alloc_notif(ctx, slot); + return slot->notif; +} + +static inline struct io_notif_slot *io_get_notif_slot(struct io_ring_ctx *ctx, + int idx) + __must_hold(&ctx->uring_lock) +{ + if (idx >= ctx->nr_notif_slots) + return NULL; + idx = array_index_nospec(idx, ctx->nr_notif_slots); + return &ctx->notif_slots[idx]; +} From eb4a299b2f95437af6183946c2a2e850621cefdb Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:39 +0100 Subject: [PATCH 16/34] io_uring: cache struct io_notif kmalloc'ing struct io_notif is too expensive when done frequently, cache them as many other resources in io_uring. Keep two list, the first one is from where we're getting notifiers, it's protected by ->uring_lock. The second is protected by ->completion_lock, to which we queue released notifiers. Then we splice one list into another when needed. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/9dec18f7fcbab9f4bd40b96e5ae158b119945230.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 7 +++++ io_uring/io_uring.c | 3 ++ io_uring/notif.c | 57 +++++++++++++++++++++++++++++----- io_uring/notif.h | 5 +++ 4 files changed, 65 insertions(+), 7 deletions(-) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index f7fab3758cb9..144493cbadb5 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -249,6 +249,9 @@ struct io_ring_ctx { struct xarray io_bl_xa; struct list_head io_buffers_cache; + /* struct io_notif cache, protected by uring_lock */ + struct list_head notif_list; + struct io_hash_table cancel_table_locked; struct list_head cq_overflow_list; struct io_alloc_cache apoll_cache; @@ -259,6 +262,10 @@ struct io_ring_ctx { struct io_wq_work_list locked_free_list; unsigned int locked_free_nr; + /* struct io_notif cache protected by completion_lock */ + struct list_head notif_list_locked; + unsigned int notif_locked_nr; + const struct cred *sq_creds; /* cred used for __io_sq_thread() */ struct io_sq_data *sq_data; /* if using sq thread polling */ diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 65ac407dd74e..20e65d45ca1c 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -321,6 +321,8 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_WQ_LIST(&ctx->locked_free_list); INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); + INIT_LIST_HEAD(&ctx->notif_list); + INIT_LIST_HEAD(&ctx->notif_list_locked); return ctx; err: kfree(ctx->dummy_ubuf); @@ -2493,6 +2495,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); WARN_ON_ONCE(ctx->notif_slots || ctx->nr_notif_slots); + io_notif_cache_purge(ctx); io_mem_free(ctx->rings); io_mem_free(ctx->sq_sqes); diff --git a/io_uring/notif.c b/io_uring/notif.c index 6ee948af6a49..b257db2120b4 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -15,10 +15,12 @@ static void __io_notif_complete_tw(struct callback_head *cb) io_cq_lock(ctx); io_fill_cqe_aux(ctx, notif->tag, 0, notif->seq, true); + + list_add(¬if->cache_node, &ctx->notif_list_locked); + ctx->notif_locked_nr++; io_cq_unlock_post(ctx); percpu_ref_put(&ctx->refs); - kfree(notif); } static inline void io_notif_complete(struct io_notif *notif) @@ -45,21 +47,62 @@ static void io_uring_tx_zerocopy_callback(struct sk_buff *skb, queue_work(system_unbound_wq, ¬if->commit_work); } +static void io_notif_splice_cached(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + spin_lock(&ctx->completion_lock); + list_splice_init(&ctx->notif_list_locked, &ctx->notif_list); + ctx->notif_locked_nr = 0; + spin_unlock(&ctx->completion_lock); +} + +void io_notif_cache_purge(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + io_notif_splice_cached(ctx); + + while (!list_empty(&ctx->notif_list)) { + struct io_notif *notif = list_first_entry(&ctx->notif_list, + struct io_notif, cache_node); + + list_del(¬if->cache_node); + kfree(notif); + } +} + +static inline bool io_notif_has_cached(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + if (likely(!list_empty(&ctx->notif_list))) + return true; + if (data_race(READ_ONCE(ctx->notif_locked_nr) <= IO_NOTIF_SPLICE_BATCH)) + return false; + io_notif_splice_cached(ctx); + return !list_empty(&ctx->notif_list); +} + struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx, struct io_notif_slot *slot) __must_hold(&ctx->uring_lock) { struct io_notif *notif; - notif = kzalloc(sizeof(*notif), GFP_ATOMIC | __GFP_ACCOUNT); - if (!notif) - return NULL; + if (likely(io_notif_has_cached(ctx))) { + notif = list_first_entry(&ctx->notif_list, + struct io_notif, cache_node); + list_del(¬if->cache_node); + } else { + notif = kzalloc(sizeof(*notif), GFP_ATOMIC | __GFP_ACCOUNT); + if (!notif) + return NULL; + /* pre-initialise some fields */ + notif->ctx = ctx; + notif->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN; + notif->uarg.callback = io_uring_tx_zerocopy_callback; + } notif->seq = slot->seq++; notif->tag = slot->tag; - notif->ctx = ctx; - notif->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN; - notif->uarg.callback = io_uring_tx_zerocopy_callback; /* master ref owned by io_notif_slot, will be dropped on flush */ refcount_set(¬if->uarg.refcnt, 1); percpu_ref_get(&ctx->refs); diff --git a/io_uring/notif.h b/io_uring/notif.h index 3d7a1d242e17..b23c9c0515bb 100644 --- a/io_uring/notif.h +++ b/io_uring/notif.h @@ -5,6 +5,8 @@ #include #include +#define IO_NOTIF_SPLICE_BATCH 32 + struct io_notif { struct ubuf_info uarg; struct io_ring_ctx *ctx; @@ -13,6 +15,8 @@ struct io_notif { u64 tag; /* see struct io_notif_slot::seq */ u32 seq; + /* hook into ctx->notif_list and ctx->notif_list_locked */ + struct list_head cache_node; union { struct callback_head task_work; @@ -41,6 +45,7 @@ struct io_notif_slot { }; int io_notif_unregister(struct io_ring_ctx *ctx); +void io_notif_cache_purge(struct io_ring_ctx *ctx); struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx, struct io_notif_slot *slot); From e58d498e81baa9fd8acf5132d8b2d4f829361f6b Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:40 +0100 Subject: [PATCH 17/34] io_uring: complete notifiers in tw We need a task context to post CQEs but using wq is too expensive. Try to complete notifiers using task_work and fall back to wq if fails. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/089799ab665b10b78fdc614ae6d59fa7ef0d5f91.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/notif.c | 22 +++++++++++++++++++--- io_uring/notif.h | 3 +++ 2 files changed, 22 insertions(+), 3 deletions(-) diff --git a/io_uring/notif.c b/io_uring/notif.c index b257db2120b4..aec74f88fc33 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -13,6 +13,11 @@ static void __io_notif_complete_tw(struct callback_head *cb) struct io_notif *notif = container_of(cb, struct io_notif, task_work); struct io_ring_ctx *ctx = notif->ctx; + if (likely(notif->task)) { + io_put_task(notif->task, 1); + notif->task = NULL; + } + io_cq_lock(ctx); io_fill_cqe_aux(ctx, notif->tag, 0, notif->seq, true); @@ -43,6 +48,14 @@ static void io_uring_tx_zerocopy_callback(struct sk_buff *skb, if (!refcount_dec_and_test(&uarg->refcnt)) return; + + if (likely(notif->task)) { + init_task_work(¬if->task_work, __io_notif_complete_tw); + if (likely(!task_work_add(notif->task, ¬if->task_work, + TWA_SIGNAL))) + return; + } + INIT_WORK(¬if->commit_work, io_notif_complete_wq); queue_work(system_unbound_wq, ¬if->commit_work); } @@ -134,12 +147,15 @@ __cold int io_notif_unregister(struct io_ring_ctx *ctx) for (i = 0; i < ctx->nr_notif_slots; i++) { struct io_notif_slot *slot = &ctx->notif_slots[i]; - if (slot->notif) - io_notif_slot_flush(slot); + if (!slot->notif) + continue; + if (WARN_ON_ONCE(slot->notif->task)) + slot->notif->task = NULL; + io_notif_slot_flush(slot); } kvfree(ctx->notif_slots); ctx->notif_slots = NULL; ctx->nr_notif_slots = 0; return 0; -} \ No newline at end of file +} diff --git a/io_uring/notif.h b/io_uring/notif.h index b23c9c0515bb..23ca7620fff9 100644 --- a/io_uring/notif.h +++ b/io_uring/notif.h @@ -11,6 +11,9 @@ struct io_notif { struct ubuf_info uarg; struct io_ring_ctx *ctx; + /* complete via tw if ->task is non-NULL, fallback to wq otherwise */ + struct task_struct *task; + /* cqe->user_data, io_notif_slot::tag if not overridden */ u64 tag; /* see struct io_notif_slot::seq */ From 68ef5578efc8893489400b1ec30af66dab4f75ff Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:41 +0100 Subject: [PATCH 18/34] io_uring: add rsrc referencing for notifiers In preparation to zerocopy sends with fixed buffers make notifiers to reference the rsrc node to protect the used fixed buffers. We can't just grab it for a send request as notifiers can likely outlive requests that used it. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/3cd7a01d26837945b6982fa9cf15a63230f2ed4f.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/notif.c | 5 +++++ io_uring/notif.h | 1 + io_uring/rsrc.h | 12 +++++++++--- 3 files changed, 15 insertions(+), 3 deletions(-) diff --git a/io_uring/notif.c b/io_uring/notif.c index aec74f88fc33..0a2e98bd74f6 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -7,10 +7,12 @@ #include "io_uring.h" #include "notif.h" +#include "rsrc.h" static void __io_notif_complete_tw(struct callback_head *cb) { struct io_notif *notif = container_of(cb, struct io_notif, task_work); + struct io_rsrc_node *rsrc_node = notif->rsrc_node; struct io_ring_ctx *ctx = notif->ctx; if (likely(notif->task)) { @@ -25,6 +27,7 @@ static void __io_notif_complete_tw(struct callback_head *cb) ctx->notif_locked_nr++; io_cq_unlock_post(ctx); + io_rsrc_put_node(rsrc_node, 1); percpu_ref_put(&ctx->refs); } @@ -119,6 +122,8 @@ struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx, /* master ref owned by io_notif_slot, will be dropped on flush */ refcount_set(¬if->uarg.refcnt, 1); percpu_ref_get(&ctx->refs); + notif->rsrc_node = ctx->rsrc_node; + io_charge_rsrc_node(ctx); return notif; } diff --git a/io_uring/notif.h b/io_uring/notif.h index 23ca7620fff9..1dd48efb7744 100644 --- a/io_uring/notif.h +++ b/io_uring/notif.h @@ -10,6 +10,7 @@ struct io_notif { struct ubuf_info uarg; struct io_ring_ctx *ctx; + struct io_rsrc_node *rsrc_node; /* complete via tw if ->task is non-NULL, fallback to wq otherwise */ struct task_struct *task; diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 87f58315b247..af342fd239d0 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -135,6 +135,13 @@ static inline void io_req_put_rsrc_locked(struct io_kiocb *req, } } +static inline void io_charge_rsrc_node(struct io_ring_ctx *ctx) +{ + ctx->rsrc_cached_refs--; + if (unlikely(ctx->rsrc_cached_refs < 0)) + io_rsrc_refs_refill(ctx); +} + static inline void io_req_set_rsrc_node(struct io_kiocb *req, struct io_ring_ctx *ctx, unsigned int issue_flags) @@ -144,9 +151,8 @@ static inline void io_req_set_rsrc_node(struct io_kiocb *req, if (!(issue_flags & IO_URING_F_UNLOCKED)) { lockdep_assert_held(&ctx->uring_lock); - ctx->rsrc_cached_refs--; - if (unlikely(ctx->rsrc_cached_refs < 0)) - io_rsrc_refs_refill(ctx); + + io_charge_rsrc_node(ctx); } else { percpu_ref_get(&req->rsrc_node->refs); } From bc24d6bd32df0be19df3d30e74be4ba56493c0e2 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:42 +0100 Subject: [PATCH 19/34] io_uring: add notification slot registration Let the userspace to register and unregister notification slots. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/a0aa8161fe3ebb2a4cc6e5dbd0cffb96e6881cf5.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 17 ++++++++++++++ io_uring/io_uring.c | 9 ++++++++ io_uring/notif.c | 43 +++++++++++++++++++++++++++++++++++ io_uring/notif.h | 3 +++ 4 files changed, 72 insertions(+) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 4c9b11e2e991..dcfc7a0bda0c 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -457,6 +457,10 @@ enum { /* register a range of fixed file slots for automatic slot allocation */ IORING_REGISTER_FILE_ALLOC_RANGE = 25, + /* zerocopy notification API */ + IORING_REGISTER_NOTIFIERS = 26, + IORING_UNREGISTER_NOTIFIERS = 27, + /* this goes last */ IORING_REGISTER_LAST }; @@ -503,6 +507,19 @@ struct io_uring_rsrc_update2 { __u32 resv2; }; +struct io_uring_notification_slot { + __u64 tag; + __u64 resv[3]; +}; + +struct io_uring_notification_register { + __u32 nr_slots; + __u32 resv; + __u64 resv2; + __u64 data; + __u64 resv3; +}; + /* Skip updating fd indexes set to this value in the fd table */ #define IORING_REGISTER_FILES_SKIP (-2) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 20e65d45ca1c..cae11374456e 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3870,6 +3870,15 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_register_file_alloc_range(ctx, arg); break; + case IORING_REGISTER_NOTIFIERS: + ret = io_notif_register(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_NOTIFIERS: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_notif_unregister(ctx); + break; default: ret = -EINVAL; break; diff --git a/io_uring/notif.c b/io_uring/notif.c index 0a2e98bd74f6..e6d98dc208c7 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -162,5 +162,48 @@ __cold int io_notif_unregister(struct io_ring_ctx *ctx) kvfree(ctx->notif_slots); ctx->notif_slots = NULL; ctx->nr_notif_slots = 0; + io_notif_cache_purge(ctx); + return 0; +} + +__cold int io_notif_register(struct io_ring_ctx *ctx, + void __user *arg, unsigned int size) + __must_hold(&ctx->uring_lock) +{ + struct io_uring_notification_slot __user *slots; + struct io_uring_notification_slot slot; + struct io_uring_notification_register reg; + unsigned i; + + if (ctx->nr_notif_slots) + return -EBUSY; + if (size != sizeof(reg)) + return -EINVAL; + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + if (!reg.nr_slots || reg.nr_slots > IORING_MAX_NOTIF_SLOTS) + return -EINVAL; + if (reg.resv || reg.resv2 || reg.resv3) + return -EINVAL; + + slots = u64_to_user_ptr(reg.data); + ctx->notif_slots = kvcalloc(reg.nr_slots, sizeof(ctx->notif_slots[0]), + GFP_KERNEL_ACCOUNT); + if (!ctx->notif_slots) + return -ENOMEM; + + for (i = 0; i < reg.nr_slots; i++, ctx->nr_notif_slots++) { + struct io_notif_slot *notif_slot = &ctx->notif_slots[i]; + + if (copy_from_user(&slot, &slots[i], sizeof(slot))) { + io_notif_unregister(ctx); + return -EFAULT; + } + if (slot.resv[0] | slot.resv[1] | slot.resv[2]) { + io_notif_unregister(ctx); + return -EINVAL; + } + notif_slot->tag = slot.tag; + } return 0; } diff --git a/io_uring/notif.h b/io_uring/notif.h index 1dd48efb7744..00efe164bdc4 100644 --- a/io_uring/notif.h +++ b/io_uring/notif.h @@ -6,6 +6,7 @@ #include #define IO_NOTIF_SPLICE_BATCH 32 +#define IORING_MAX_NOTIF_SLOTS (1U << 10) struct io_notif { struct ubuf_info uarg; @@ -48,6 +49,8 @@ struct io_notif_slot { u32 seq; }; +int io_notif_register(struct io_ring_ctx *ctx, + void __user *arg, unsigned int size); int io_notif_unregister(struct io_ring_ctx *ctx); void io_notif_cache_purge(struct io_ring_ctx *ctx); From 06a5464be84e4ae48394d34441baf34bf9706827 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:43 +0100 Subject: [PATCH 20/34] io_uring: wire send zc request type Add a new io_uring opcode IORING_OP_SENDZC. The main distinction from IORING_OP_SEND is that the user should specify a notification slot index in sqe::notification_idx and the buffers are safe to reuse only when the used notification is flushed and completes. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/a80387c6a68ce9cf99b3b6ef6f71068468761fb7.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 5 ++ io_uring/net.c | 94 +++++++++++++++++++++++++++++++++++ io_uring/net.h | 3 ++ io_uring/opdef.c | 15 ++++++ 4 files changed, 117 insertions(+) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index dcfc7a0bda0c..82bf2991e9bd 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -66,6 +66,10 @@ struct io_uring_sqe { union { __s32 splice_fd_in; __u32 file_index; + struct { + __u16 notification_idx; + __u16 __pad; + }; }; union { struct { @@ -197,6 +201,7 @@ enum io_uring_op { IORING_OP_GETXATTR, IORING_OP_SOCKET, IORING_OP_URING_CMD, + IORING_OP_SENDZC_NOTIF, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/net.c b/io_uring/net.c index bbc9c603641a..89a8678ce69b 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -14,6 +14,7 @@ #include "kbuf.h" #include "alloc_cache.h" #include "net.h" +#include "notif.h" #if defined(CONFIG_NET) struct io_shutdown { @@ -59,6 +60,15 @@ struct io_sr_msg { unsigned int flags; }; +struct io_sendzc { + struct file *file; + void __user *buf; + size_t len; + u16 slot_idx; + unsigned msg_flags; + unsigned flags; +}; + #define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -834,6 +844,90 @@ out_free: return ret; } +int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sendzc *zc = io_kiocb_to_cmd(req); + + if (READ_ONCE(sqe->addr2) || READ_ONCE(sqe->__pad2[0]) || + READ_ONCE(sqe->addr3)) + return -EINVAL; + + zc->flags = READ_ONCE(sqe->ioprio); + if (zc->flags & ~IORING_RECVSEND_POLL_FIRST) + return -EINVAL; + + zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); + zc->len = READ_ONCE(sqe->len); + zc->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; + zc->slot_idx = READ_ONCE(sqe->notification_idx); + if (zc->msg_flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + zc->msg_flags |= MSG_CMSG_COMPAT; +#endif + return 0; +} + +int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_sendzc *zc = io_kiocb_to_cmd(req); + struct io_notif_slot *notif_slot; + struct io_notif *notif; + struct msghdr msg; + struct iovec iov; + struct socket *sock; + unsigned msg_flags; + int ret, min_ret = 0; + + if (!(req->flags & REQ_F_POLLED) && + (zc->flags & IORING_RECVSEND_POLL_FIRST)) + return -EAGAIN; + + if (issue_flags & IO_URING_F_UNLOCKED) + return -EAGAIN; + sock = sock_from_file(req->file); + if (unlikely(!sock)) + return -ENOTSOCK; + + notif_slot = io_get_notif_slot(ctx, zc->slot_idx); + if (!notif_slot) + return -EINVAL; + notif = io_get_notif(ctx, notif_slot); + if (!notif) + return -ENOMEM; + + msg.msg_name = NULL; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_namelen = 0; + + ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter); + if (unlikely(ret)) + return ret; + + msg_flags = zc->msg_flags | MSG_ZEROCOPY; + if (issue_flags & IO_URING_F_NONBLOCK) + msg_flags |= MSG_DONTWAIT; + if (msg_flags & MSG_WAITALL) + min_ret = iov_iter_count(&msg.msg_iter); + + msg.msg_flags = msg_flags; + msg.msg_ubuf = ¬if->uarg; + msg.sg_from_iter = NULL; + ret = sock_sendmsg(sock, &msg); + + if (unlikely(ret < min_ret)) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return -EAGAIN; + return ret == -ERESTARTSYS ? -EINTR : ret; + } + + io_req_set_res(req, ret, 0); + return IOU_OK; +} + int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_accept *accept = io_kiocb_to_cmd(req); diff --git a/io_uring/net.h b/io_uring/net.h index db20ce9d6546..7c438d39c089 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -52,6 +52,9 @@ int io_connect_prep_async(struct io_kiocb *req); int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_connect(struct io_kiocb *req, unsigned int issue_flags); +int io_sendzc(struct io_kiocb *req, unsigned int issue_flags); +int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); + void io_netmsg_cache_free(struct io_cache_entry *entry); #else static inline void io_netmsg_cache_free(struct io_cache_entry *entry) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index a7b84b43e6c2..7ab19bbf3126 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -470,6 +470,21 @@ const struct io_op_def io_op_defs[] = { .issue = io_uring_cmd, .prep_async = io_uring_cmd_prep_async, }, + [IORING_OP_SENDZC_NOTIF] = { + .name = "SENDZC_NOTIF", + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollout = 1, + .audit_skip = 1, + .ioprio = 1, +#if defined(CONFIG_NET) + .prep = io_sendzc_prep, + .issue = io_sendzc, +#else + .prep = io_eopnotsupp_prep, +#endif + + }, }; const char *io_uring_get_opcode(u8 opcode) From e29e3bd4b968d50bfb3bbdcee6bfdc340f7792cf Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:44 +0100 Subject: [PATCH 21/34] io_uring: account locked pages for non-fixed zc Fixed buffers are RLIMIT_MEMLOCK accounted, however it doesn't cover iovec based zerocopy sends. Do the accounting on the io_uring side. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/19b6e3975440f59f1f6199c7ee7acf977b4eecdc.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/net.c | 1 + io_uring/notif.c | 6 ++++++ 2 files changed, 7 insertions(+) diff --git a/io_uring/net.c b/io_uring/net.c index 89a8678ce69b..2d04a70b0632 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -906,6 +906,7 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter); if (unlikely(ret)) return ret; + mm_account_pinned_pages(¬if->uarg.mmp, zc->len); msg_flags = zc->msg_flags | MSG_ZEROCOPY; if (issue_flags & IO_URING_F_NONBLOCK) diff --git a/io_uring/notif.c b/io_uring/notif.c index e6d98dc208c7..c5179e5c1cd6 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -14,7 +14,13 @@ static void __io_notif_complete_tw(struct callback_head *cb) struct io_notif *notif = container_of(cb, struct io_notif, task_work); struct io_rsrc_node *rsrc_node = notif->rsrc_node; struct io_ring_ctx *ctx = notif->ctx; + struct mmpin *mmp = ¬if->uarg.mmp; + if (mmp->user) { + atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm); + free_uid(mmp->user); + mmp->user = NULL; + } if (likely(notif->task)) { io_put_task(notif->task, 1); notif->task = NULL; From 092aeedb750a9fad0f0252d6067fc91d76ca44bd Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:45 +0100 Subject: [PATCH 22/34] io_uring: allow to pass addr into sendzc Allow to specify an address to zerocopy sends making it more like sendto(2). Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/70417a8f7c5b51ab454690bae08adc0c187f89e8.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- io_uring/net.c | 18 ++++++++++++++++-- 2 files changed, 17 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 82bf2991e9bd..0736e2773a5d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -68,7 +68,7 @@ struct io_uring_sqe { __u32 file_index; struct { __u16 notification_idx; - __u16 __pad; + __u16 addr_len; }; }; union { diff --git a/io_uring/net.c b/io_uring/net.c index 2d04a70b0632..61414d865cd7 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -67,6 +67,8 @@ struct io_sendzc { u16 slot_idx; unsigned msg_flags; unsigned flags; + unsigned addr_len; + void __user *addr; }; #define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) @@ -848,8 +850,7 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sendzc *zc = io_kiocb_to_cmd(req); - if (READ_ONCE(sqe->addr2) || READ_ONCE(sqe->__pad2[0]) || - READ_ONCE(sqe->addr3)) + if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)) return -EINVAL; zc->flags = READ_ONCE(sqe->ioprio); @@ -862,6 +863,10 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) zc->slot_idx = READ_ONCE(sqe->notification_idx); if (zc->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; + + zc->addr = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + zc->addr_len = READ_ONCE(sqe->addr_len); + #ifdef CONFIG_COMPAT if (req->ctx->compat) zc->msg_flags |= MSG_CMSG_COMPAT; @@ -871,6 +876,7 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) { + struct sockaddr_storage address; struct io_ring_ctx *ctx = req->ctx; struct io_sendzc *zc = io_kiocb_to_cmd(req); struct io_notif_slot *notif_slot; @@ -908,6 +914,14 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) return ret; mm_account_pinned_pages(¬if->uarg.mmp, zc->len); + if (zc->addr) { + ret = move_addr_to_kernel(zc->addr, zc->addr_len, &address); + if (unlikely(ret < 0)) + return ret; + msg.msg_name = (struct sockaddr *)&address; + msg.msg_namelen = zc->addr_len; + } + msg_flags = zc->msg_flags | MSG_ZEROCOPY; if (issue_flags & IO_URING_F_NONBLOCK) msg_flags |= MSG_DONTWAIT; From 10c7d33ecd51619e453cf6aeee8e326f8ba5cfea Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:46 +0100 Subject: [PATCH 23/34] io_uring: sendzc with fixed buffers Allow zerocopy sends to use fixed buffers. There is an optimisation for this case, the network layer don't need to reference the pages, see SKBFL_MANAGED_FRAG_REFS, so io_uring have to ensure validity of fixed buffers until the notifier is released. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/e1d8bd1b5934e541d90c1824eb4020ae3f5f43f3.1657643355.git.asml.silence@gmail.com [axboe: fold in 32-bit pointer cast warning fix] Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 6 +++++- io_uring/net.c | 29 ++++++++++++++++++++++++----- 2 files changed, 29 insertions(+), 6 deletions(-) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0736e2773a5d..f1a9ff9b9ea7 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -272,9 +272,13 @@ enum io_uring_op { * IORING_RECV_MULTISHOT Multishot recv. Sets IORING_CQE_F_MORE if * the handler will continue to report * CQEs on behalf of the same SQE. + * + * IORING_RECVSEND_FIXED_BUF Use registered buffers, the index is stored in + * the buf_index field. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) -#define IORING_RECV_MULTISHOT (1U << 1) +#define IORING_RECV_MULTISHOT (1U << 1) +#define IORING_RECVSEND_FIXED_BUF (1U << 2) /* * accept flags stored in sqe->ioprio diff --git a/io_uring/net.c b/io_uring/net.c index 61414d865cd7..ab443c52dcfd 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -15,6 +15,7 @@ #include "alloc_cache.h" #include "net.h" #include "notif.h" +#include "rsrc.h" #if defined(CONFIG_NET) struct io_shutdown { @@ -849,13 +850,23 @@ out_free: int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sendzc *zc = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)) return -EINVAL; zc->flags = READ_ONCE(sqe->ioprio); - if (zc->flags & ~IORING_RECVSEND_POLL_FIRST) + if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_FIXED_BUF)) return -EINVAL; + if (zc->flags & IORING_RECVSEND_FIXED_BUF) { + unsigned idx = READ_ONCE(sqe->buf_index); + + if (unlikely(idx >= ctx->nr_user_bufs)) + return -EFAULT; + idx = array_index_nospec(idx, ctx->nr_user_bufs); + req->imu = READ_ONCE(ctx->user_bufs[idx]); + io_req_set_rsrc_node(req, ctx, 0); + } zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); zc->len = READ_ONCE(sqe->len); @@ -909,10 +920,18 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) msg.msg_controllen = 0; msg.msg_namelen = 0; - ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter); - if (unlikely(ret)) - return ret; - mm_account_pinned_pages(¬if->uarg.mmp, zc->len); + if (zc->flags & IORING_RECVSEND_FIXED_BUF) { + ret = io_import_fixed(WRITE, &msg.msg_iter, req->imu, + (u64)(uintptr_t)zc->buf, zc->len); + if (unlikely(ret)) + return ret; + } else { + ret = import_single_range(WRITE, zc->buf, zc->len, &iov, + &msg.msg_iter); + if (unlikely(ret)) + return ret; + mm_account_pinned_pages(¬if->uarg.mmp, zc->len); + } if (zc->addr) { ret = move_addr_to_kernel(zc->addr, zc->addr_len, &address); From 63809137ebb58f0aa2ce359117422686e3304f45 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:47 +0100 Subject: [PATCH 24/34] io_uring: flush notifiers after sendzc Allow to flush notifiers as a part of sendzc request by setting IORING_SENDZC_FLUSH flag. When the sendzc request succeedes it will flush the used [active] notifier. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/e0b4d9a6797e2fd6092824fe42953db7a519bbc8.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 4 ++++ io_uring/io_uring.c | 11 +---------- io_uring/io_uring.h | 10 ++++++++++ io_uring/net.c | 5 ++++- io_uring/notif.c | 2 +- io_uring/notif.h | 11 +++++++++++ 6 files changed, 31 insertions(+), 12 deletions(-) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index f1a9ff9b9ea7..45272eb37d10 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -275,10 +275,14 @@ enum io_uring_op { * * IORING_RECVSEND_FIXED_BUF Use registered buffers, the index is stored in * the buf_index field. + * + * IORING_RECVSEND_NOTIF_FLUSH Flush a notification after a successful + * successful. Only for zerocopy sends. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) #define IORING_RECV_MULTISHOT (1U << 1) #define IORING_RECVSEND_FIXED_BUF (1U << 2) +#define IORING_RECVSEND_NOTIF_FLUSH (1U << 3) /* * accept flags stored in sqe->ioprio diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index cae11374456e..1d600a63643b 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -621,7 +621,7 @@ void __io_put_task(struct task_struct *task, int nr) put_task_struct_many(task, nr); } -static void io_task_refs_refill(struct io_uring_task *tctx) +void io_task_refs_refill(struct io_uring_task *tctx) { unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; @@ -630,15 +630,6 @@ static void io_task_refs_refill(struct io_uring_task *tctx) tctx->cached_refs += refill; } -static inline void io_get_task_refs(int nr) -{ - struct io_uring_task *tctx = current->io_uring; - - tctx->cached_refs -= nr; - if (unlikely(tctx->cached_refs < 0)) - io_task_refs_refill(tctx); -} - static __cold void io_uring_drop_tctx_refs(struct task_struct *task) { struct io_uring_task *tctx = task->io_uring; diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 66bfd880d07f..cc81a9d1fd4d 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -74,6 +74,7 @@ void io_wq_submit_work(struct io_wq_work *work); void io_free_req(struct io_kiocb *req); void io_queue_next(struct io_kiocb *req); void __io_put_task(struct task_struct *task, int nr); +void io_task_refs_refill(struct io_uring_task *tctx); bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all); @@ -270,4 +271,13 @@ static inline void io_put_task(struct task_struct *task, int nr) __io_put_task(task, nr); } +static inline void io_get_task_refs(int nr) +{ + struct io_uring_task *tctx = current->io_uring; + + tctx->cached_refs -= nr; + if (unlikely(tctx->cached_refs < 0)) + io_task_refs_refill(tctx); +} + #endif diff --git a/io_uring/net.c b/io_uring/net.c index ab443c52dcfd..9ac2ce37c522 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -856,7 +856,8 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EINVAL; zc->flags = READ_ONCE(sqe->ioprio); - if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_FIXED_BUF)) + if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | + IORING_RECVSEND_FIXED_BUF | IORING_RECVSEND_NOTIF_FLUSH)) return -EINVAL; if (zc->flags & IORING_RECVSEND_FIXED_BUF) { unsigned idx = READ_ONCE(sqe->buf_index); @@ -958,6 +959,8 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) return ret == -ERESTARTSYS ? -EINTR : ret; } + if (zc->flags & IORING_RECVSEND_NOTIF_FLUSH) + io_notif_slot_flush_submit(notif_slot, 0); io_req_set_res(req, ret, 0); return IOU_OK; } diff --git a/io_uring/notif.c b/io_uring/notif.c index c5179e5c1cd6..a93887451bbb 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -133,7 +133,7 @@ struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx, return notif; } -static void io_notif_slot_flush(struct io_notif_slot *slot) +void io_notif_slot_flush(struct io_notif_slot *slot) __must_hold(&ctx->uring_lock) { struct io_notif *notif = slot->notif; diff --git a/io_uring/notif.h b/io_uring/notif.h index 00efe164bdc4..6cd73d7b965b 100644 --- a/io_uring/notif.h +++ b/io_uring/notif.h @@ -54,6 +54,7 @@ int io_notif_register(struct io_ring_ctx *ctx, int io_notif_unregister(struct io_ring_ctx *ctx); void io_notif_cache_purge(struct io_ring_ctx *ctx); +void io_notif_slot_flush(struct io_notif_slot *slot); struct io_notif *io_alloc_notif(struct io_ring_ctx *ctx, struct io_notif_slot *slot); @@ -74,3 +75,13 @@ static inline struct io_notif_slot *io_get_notif_slot(struct io_ring_ctx *ctx, idx = array_index_nospec(idx, ctx->nr_notif_slots); return &ctx->notif_slots[idx]; } + +static inline void io_notif_slot_flush_submit(struct io_notif_slot *slot, + unsigned int issue_flags) +{ + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + slot->notif->task = current; + io_get_task_refs(1); + } + io_notif_slot_flush(slot); +} From 4379d5f15b3fd4224c37841029178aa8082a242e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:48 +0100 Subject: [PATCH 25/34] io_uring: rename IORING_OP_FILES_UPDATE IORING_OP_FILES_UPDATE will be a more generic opcode serving different resource types, rename it into IORING_OP_RSRC_UPDATE and add subtype handling. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/0a907133907d9af3415a8a7aa1802c6aa97c03c6.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 12 +++++++++++- io_uring/opdef.c | 9 +++++---- io_uring/rsrc.c | 17 +++++++++++++++-- io_uring/rsrc.h | 4 ++-- 4 files changed, 33 insertions(+), 9 deletions(-) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 45272eb37d10..210a00ab6301 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -174,7 +174,8 @@ enum io_uring_op { IORING_OP_FALLOCATE, IORING_OP_OPENAT, IORING_OP_CLOSE, - IORING_OP_FILES_UPDATE, + IORING_OP_RSRC_UPDATE, + IORING_OP_FILES_UPDATE = IORING_OP_RSRC_UPDATE, IORING_OP_STATX, IORING_OP_READ, IORING_OP_WRITE, @@ -223,6 +224,7 @@ enum io_uring_op { #define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5) #define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) #define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) + /* * sqe->splice_flags * extends splice(2) flags @@ -289,6 +291,14 @@ enum io_uring_op { */ #define IORING_ACCEPT_MULTISHOT (1U << 0) + +/* + * IORING_OP_RSRC_UPDATE flags + */ +enum { + IORING_RSRC_UPDATE_FILES, +}; + /* * IORING_OP_MSG_RING command types, stored in sqe->addr */ diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 7ab19bbf3126..72dd2b2d8a9d 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -246,12 +246,13 @@ const struct io_op_def io_op_defs[] = { .prep = io_close_prep, .issue = io_close, }, - [IORING_OP_FILES_UPDATE] = { + [IORING_OP_RSRC_UPDATE] = { .audit_skip = 1, .iopoll = 1, - .name = "FILES_UPDATE", - .prep = io_files_update_prep, - .issue = io_files_update, + .name = "RSRC_UPDATE", + .prep = io_rsrc_update_prep, + .issue = io_rsrc_update, + .ioprio = 1, }, [IORING_OP_STATX] = { .audit_skip = 1, diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 7f66b0e25674..fc2b337e6c25 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -21,6 +21,7 @@ struct io_rsrc_update { u64 arg; u32 nr_args; u32 offset; + int type; }; static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, @@ -657,7 +658,7 @@ __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; } -int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_rsrc_update *up = io_kiocb_to_cmd(req); @@ -671,6 +672,7 @@ int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (!up->nr_args) return -EINVAL; up->arg = READ_ONCE(sqe->addr); + up->type = READ_ONCE(sqe->ioprio); return 0; } @@ -713,7 +715,7 @@ static int io_files_update_with_index_alloc(struct io_kiocb *req, return ret; } -int io_files_update(struct io_kiocb *req, unsigned int issue_flags) +static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_rsrc_update *up = io_kiocb_to_cmd(req); struct io_ring_ctx *ctx = req->ctx; @@ -742,6 +744,17 @@ int io_files_update(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } +int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rsrc_update *up = io_kiocb_to_cmd(req); + + switch (up->type) { + case IORING_RSRC_UPDATE_FILES: + return io_files_update(req, issue_flags); + } + return -EINVAL; +} + int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, struct io_rsrc_node *node, void *rsrc) { diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index af342fd239d0..21813a23215f 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -167,6 +167,6 @@ static inline u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) return &data->tags[table_idx][off]; } -int io_files_update(struct io_kiocb *req, unsigned int issue_flags); -int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags); +int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); #endif From 492dddb4f6e3a5839c27d41ff1fecdbe6c3ab851 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:49 +0100 Subject: [PATCH 26/34] io_uring: add zc notification flush requests Overlay notification control onto IORING_OP_RSRC_UPDATE (former IORING_OP_FILES_UPDATE). It allows to flush a range of zc notifications from slots with indexes [sqe->off, sqe->off+sqe->len). If sqe->arg is not zero, it also copies sqe->arg as a new tag for all flushed notifications. Note, it doesn't flush a notification of a slot if there was no requests attached to it (since last flush or registration). Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/df13e2363400682a73dd9e71c3b990b8d1ff0333.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/rsrc.c | 38 +++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 210a00ab6301..1463cfecb56b 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -297,6 +297,7 @@ enum io_uring_op { */ enum { IORING_RSRC_UPDATE_FILES, + IORING_RSRC_UPDATE_NOTIF, }; /* diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index fc2b337e6c25..9165fdf64269 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -15,6 +15,7 @@ #include "io_uring.h" #include "openclose.h" #include "rsrc.h" +#include "notif.h" struct io_rsrc_update { struct file *file; @@ -744,6 +745,41 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } +static int io_notif_update(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rsrc_update *up = io_kiocb_to_cmd(req); + struct io_ring_ctx *ctx = req->ctx; + unsigned len = up->nr_args; + unsigned idx_end, idx = up->offset; + int ret = 0; + + io_ring_submit_lock(ctx, issue_flags); + if (unlikely(check_add_overflow(idx, len, &idx_end))) { + ret = -EOVERFLOW; + goto out; + } + if (unlikely(idx_end > ctx->nr_notif_slots)) { + ret = -EINVAL; + goto out; + } + + for (; idx < idx_end; idx++) { + struct io_notif_slot *slot = &ctx->notif_slots[idx]; + + if (!slot->notif) + continue; + if (up->arg) + slot->tag = up->arg; + io_notif_slot_flush_submit(slot, issue_flags); + } +out: + io_ring_submit_unlock(ctx, issue_flags); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} + int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_rsrc_update *up = io_kiocb_to_cmd(req); @@ -751,6 +787,8 @@ int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags) switch (up->type) { case IORING_RSRC_UPDATE_FILES: return io_files_update(req, issue_flags); + case IORING_RSRC_UPDATE_NOTIF: + return io_notif_update(req, issue_flags); } return -EINVAL; } From 3ff1a0d395c00e42ee15f561431e0c04097595b9 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:50 +0100 Subject: [PATCH 27/34] io_uring: enable managed frags with register buffers io_uring's registered buffers infra has a good performant way of pinning pages, so let's use SKBFL_MANAGED_FRAG_REFS when our requests are purely register buffer backed. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/278731d3f20caf346cfc025fbee0b4c9ee4ed751.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/net.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 55 insertions(+), 1 deletion(-) diff --git a/io_uring/net.c b/io_uring/net.c index 9ac2ce37c522..62be89837d82 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -886,6 +886,60 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } +static int io_sg_from_iter(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + int frag = shinfo->nr_frags; + int ret = 0; + struct bvec_iter bi; + ssize_t copied = 0; + unsigned long truesize = 0; + + if (!shinfo->nr_frags) + shinfo->flags |= SKBFL_MANAGED_FRAG_REFS; + + if (!skb_zcopy_managed(skb) || !iov_iter_is_bvec(from)) { + skb_zcopy_downgrade_managed(skb); + return __zerocopy_sg_from_iter(NULL, sk, skb, from, length); + } + + bi.bi_size = min(from->count, length); + bi.bi_bvec_done = from->iov_offset; + bi.bi_idx = 0; + + while (bi.bi_size && frag < MAX_SKB_FRAGS) { + struct bio_vec v = mp_bvec_iter_bvec(from->bvec, bi); + + copied += v.bv_len; + truesize += PAGE_ALIGN(v.bv_len + v.bv_offset); + __skb_fill_page_desc_noacc(shinfo, frag++, v.bv_page, + v.bv_offset, v.bv_len); + bvec_iter_advance_single(from->bvec, &bi, v.bv_len); + } + if (bi.bi_size) + ret = -EMSGSIZE; + + shinfo->nr_frags = frag; + from->bvec += bi.bi_idx; + from->nr_segs -= bi.bi_idx; + from->count = bi.bi_size; + from->iov_offset = bi.bi_bvec_done; + + skb->data_len += copied; + skb->len += copied; + skb->truesize += truesize; + + if (sk && sk->sk_type == SOCK_STREAM) { + sk_wmem_queued_add(sk, truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_charge(sk, truesize); + } else { + refcount_add(truesize, &skb->sk->sk_wmem_alloc); + } + return ret; +} + int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) { struct sockaddr_storage address; @@ -950,7 +1004,7 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags) msg.msg_flags = msg_flags; msg.msg_ubuf = ¬if->uarg; - msg.sg_from_iter = NULL; + msg.sg_from_iter = io_sg_from_iter; ret = sock_sendmsg(sock, &msg); if (unlikely(ret < min_ret)) { From d8b6171bd58a5ffb9ad1dcfa60372db1b4db6d0d Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Jul 2022 21:52:51 +0100 Subject: [PATCH 28/34] selftests/io_uring: test zerocopy send Add selftests for io_uring zerocopy sends and io_uring's notification infrastructure. It's largely influenced by msg_zerocopy and uses it on the receive side. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/03d5ec78061cf52db420f88ed0b48eb8f47ce9f7.1657643355.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- tools/testing/selftests/net/Makefile | 1 + .../selftests/net/io_uring_zerocopy_tx.c | 605 ++++++++++++++++++ .../selftests/net/io_uring_zerocopy_tx.sh | 131 ++++ 3 files changed, 737 insertions(+) create mode 100644 tools/testing/selftests/net/io_uring_zerocopy_tx.c create mode 100755 tools/testing/selftests/net/io_uring_zerocopy_tx.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index db05b3764b77..9a4b30bd3a9e 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -59,6 +59,7 @@ TEST_GEN_FILES += toeplitz TEST_GEN_FILES += cmsg_sender TEST_GEN_FILES += stress_reuseport_listen TEST_PROGS += test_vxlan_vnifiltering.sh +TEST_GEN_FILES += io_uring_zerocopy_tx TEST_FILES := settings diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.c b/tools/testing/selftests/net/io_uring_zerocopy_tx.c new file mode 100644 index 000000000000..9d64c560a2d6 --- /dev/null +++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.c @@ -0,0 +1,605 @@ +/* SPDX-License-Identifier: MIT */ +/* based on linux-kernel/tools/testing/selftests/net/msg_zerocopy.c */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define NOTIF_TAG 0xfffffffULL +#define NONZC_TAG 0 +#define ZC_TAG 1 + +enum { + MODE_NONZC = 0, + MODE_ZC = 1, + MODE_ZC_FIXED = 2, + MODE_MIXED = 3, +}; + +static bool cfg_flush = false; +static bool cfg_cork = false; +static int cfg_mode = MODE_ZC_FIXED; +static int cfg_nr_reqs = 8; +static int cfg_family = PF_UNSPEC; +static int cfg_payload_len; +static int cfg_port = 8000; +static int cfg_runtime_ms = 4200; + +static socklen_t cfg_alen; +static struct sockaddr_storage cfg_dst_addr; + +static char payload[IP_MAXPACKET] __attribute__((aligned(4096))); + +struct io_sq_ring { + unsigned *head; + unsigned *tail; + unsigned *ring_mask; + unsigned *ring_entries; + unsigned *flags; + unsigned *array; +}; + +struct io_cq_ring { + unsigned *head; + unsigned *tail; + unsigned *ring_mask; + unsigned *ring_entries; + struct io_uring_cqe *cqes; +}; + +struct io_uring_sq { + unsigned *khead; + unsigned *ktail; + unsigned *kring_mask; + unsigned *kring_entries; + unsigned *kflags; + unsigned *kdropped; + unsigned *array; + struct io_uring_sqe *sqes; + + unsigned sqe_head; + unsigned sqe_tail; + + size_t ring_sz; +}; + +struct io_uring_cq { + unsigned *khead; + unsigned *ktail; + unsigned *kring_mask; + unsigned *kring_entries; + unsigned *koverflow; + struct io_uring_cqe *cqes; + + size_t ring_sz; +}; + +struct io_uring { + struct io_uring_sq sq; + struct io_uring_cq cq; + int ring_fd; +}; + +#ifdef __alpha__ +# ifndef __NR_io_uring_setup +# define __NR_io_uring_setup 535 +# endif +# ifndef __NR_io_uring_enter +# define __NR_io_uring_enter 536 +# endif +# ifndef __NR_io_uring_register +# define __NR_io_uring_register 537 +# endif +#else /* !__alpha__ */ +# ifndef __NR_io_uring_setup +# define __NR_io_uring_setup 425 +# endif +# ifndef __NR_io_uring_enter +# define __NR_io_uring_enter 426 +# endif +# ifndef __NR_io_uring_register +# define __NR_io_uring_register 427 +# endif +#endif + +#if defined(__x86_64) || defined(__i386__) +#define read_barrier() __asm__ __volatile__("":::"memory") +#define write_barrier() __asm__ __volatile__("":::"memory") +#else + +#define read_barrier() __sync_synchronize() +#define write_barrier() __sync_synchronize() +#endif + +static int io_uring_setup(unsigned int entries, struct io_uring_params *p) +{ + return syscall(__NR_io_uring_setup, entries, p); +} + +static int io_uring_enter(int fd, unsigned int to_submit, + unsigned int min_complete, + unsigned int flags, sigset_t *sig) +{ + return syscall(__NR_io_uring_enter, fd, to_submit, min_complete, + flags, sig, _NSIG / 8); +} + +static int io_uring_register_buffers(struct io_uring *ring, + const struct iovec *iovecs, + unsigned nr_iovecs) +{ + int ret; + + ret = syscall(__NR_io_uring_register, ring->ring_fd, + IORING_REGISTER_BUFFERS, iovecs, nr_iovecs); + return (ret < 0) ? -errno : ret; +} + +static int io_uring_register_notifications(struct io_uring *ring, + unsigned nr, + struct io_uring_notification_slot *slots) +{ + int ret; + struct io_uring_notification_register r = { + .nr_slots = nr, + .data = (unsigned long)slots, + }; + + ret = syscall(__NR_io_uring_register, ring->ring_fd, + IORING_REGISTER_NOTIFIERS, &r, sizeof(r)); + return (ret < 0) ? -errno : ret; +} + +static int io_uring_mmap(int fd, struct io_uring_params *p, + struct io_uring_sq *sq, struct io_uring_cq *cq) +{ + size_t size; + void *ptr; + int ret; + + sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned); + ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING); + if (ptr == MAP_FAILED) + return -errno; + sq->khead = ptr + p->sq_off.head; + sq->ktail = ptr + p->sq_off.tail; + sq->kring_mask = ptr + p->sq_off.ring_mask; + sq->kring_entries = ptr + p->sq_off.ring_entries; + sq->kflags = ptr + p->sq_off.flags; + sq->kdropped = ptr + p->sq_off.dropped; + sq->array = ptr + p->sq_off.array; + + size = p->sq_entries * sizeof(struct io_uring_sqe); + sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQES); + if (sq->sqes == MAP_FAILED) { + ret = -errno; +err: + munmap(sq->khead, sq->ring_sz); + return ret; + } + + cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe); + ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING); + if (ptr == MAP_FAILED) { + ret = -errno; + munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe)); + goto err; + } + cq->khead = ptr + p->cq_off.head; + cq->ktail = ptr + p->cq_off.tail; + cq->kring_mask = ptr + p->cq_off.ring_mask; + cq->kring_entries = ptr + p->cq_off.ring_entries; + cq->koverflow = ptr + p->cq_off.overflow; + cq->cqes = ptr + p->cq_off.cqes; + return 0; +} + +static int io_uring_queue_init(unsigned entries, struct io_uring *ring, + unsigned flags) +{ + struct io_uring_params p; + int fd, ret; + + memset(ring, 0, sizeof(*ring)); + memset(&p, 0, sizeof(p)); + p.flags = flags; + + fd = io_uring_setup(entries, &p); + if (fd < 0) + return fd; + ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq); + if (!ret) + ring->ring_fd = fd; + else + close(fd); + return ret; +} + +static int io_uring_submit(struct io_uring *ring) +{ + struct io_uring_sq *sq = &ring->sq; + const unsigned mask = *sq->kring_mask; + unsigned ktail, submitted, to_submit; + int ret; + + read_barrier(); + if (*sq->khead != *sq->ktail) { + submitted = *sq->kring_entries; + goto submit; + } + if (sq->sqe_head == sq->sqe_tail) + return 0; + + ktail = *sq->ktail; + to_submit = sq->sqe_tail - sq->sqe_head; + for (submitted = 0; submitted < to_submit; submitted++) { + read_barrier(); + sq->array[ktail++ & mask] = sq->sqe_head++ & mask; + } + if (!submitted) + return 0; + + if (*sq->ktail != ktail) { + write_barrier(); + *sq->ktail = ktail; + write_barrier(); + } +submit: + ret = io_uring_enter(ring->ring_fd, submitted, 0, + IORING_ENTER_GETEVENTS, NULL); + return ret < 0 ? -errno : ret; +} + +static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd, + const void *buf, size_t len, int flags) +{ + memset(sqe, 0, sizeof(*sqe)); + sqe->opcode = (__u8) IORING_OP_SEND; + sqe->fd = sockfd; + sqe->addr = (unsigned long) buf; + sqe->len = len; + sqe->msg_flags = (__u32) flags; +} + +static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd, + const void *buf, size_t len, int flags, + unsigned slot_idx, unsigned zc_flags) +{ + io_uring_prep_send(sqe, sockfd, buf, len, flags); + sqe->opcode = (__u8) IORING_OP_SENDZC_NOTIF; + sqe->notification_idx = slot_idx; + sqe->ioprio = zc_flags; +} + +static struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring) +{ + struct io_uring_sq *sq = &ring->sq; + + if (sq->sqe_tail + 1 - sq->sqe_head > *sq->kring_entries) + return NULL; + return &sq->sqes[sq->sqe_tail++ & *sq->kring_mask]; +} + +static int io_uring_wait_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr) +{ + struct io_uring_cq *cq = &ring->cq; + const unsigned mask = *cq->kring_mask; + unsigned head = *cq->khead; + int ret; + + *cqe_ptr = NULL; + do { + read_barrier(); + if (head != *cq->ktail) { + *cqe_ptr = &cq->cqes[head & mask]; + break; + } + ret = io_uring_enter(ring->ring_fd, 0, 1, + IORING_ENTER_GETEVENTS, NULL); + if (ret < 0) + return -errno; + } while (1); + + return 0; +} + +static inline void io_uring_cqe_seen(struct io_uring *ring) +{ + *(&ring->cq)->khead += 1; + write_barrier(); +} + +static unsigned long gettimeofday_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static void do_setsockopt(int fd, int level, int optname, int val) +{ + if (setsockopt(fd, level, optname, &val, sizeof(val))) + error(1, errno, "setsockopt %d.%d: %d", level, optname, val); +} + +static int do_setup_tx(int domain, int type, int protocol) +{ + int fd; + + fd = socket(domain, type, protocol); + if (fd == -1) + error(1, errno, "socket t"); + + do_setsockopt(fd, SOL_SOCKET, SO_SNDBUF, 1 << 21); + + if (connect(fd, (void *) &cfg_dst_addr, cfg_alen)) + error(1, errno, "connect"); + return fd; +} + +static void do_tx(int domain, int type, int protocol) +{ + struct io_uring_notification_slot b[1] = {{.tag = NOTIF_TAG}}; + struct io_uring_sqe *sqe; + struct io_uring_cqe *cqe; + unsigned long packets = 0, bytes = 0; + struct io_uring ring; + struct iovec iov; + uint64_t tstop; + int i, fd, ret; + int compl_cqes = 0; + + fd = do_setup_tx(domain, type, protocol); + + ret = io_uring_queue_init(512, &ring, 0); + if (ret) + error(1, ret, "io_uring: queue init"); + + ret = io_uring_register_notifications(&ring, 1, b); + if (ret) + error(1, ret, "io_uring: tx ctx registration"); + + iov.iov_base = payload; + iov.iov_len = cfg_payload_len; + + ret = io_uring_register_buffers(&ring, &iov, 1); + if (ret) + error(1, ret, "io_uring: buffer registration"); + + tstop = gettimeofday_ms() + cfg_runtime_ms; + do { + if (cfg_cork) + do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 1); + + for (i = 0; i < cfg_nr_reqs; i++) { + unsigned zc_flags = 0; + unsigned buf_idx = 0; + unsigned slot_idx = 0; + unsigned mode = cfg_mode; + unsigned msg_flags = 0; + + if (cfg_mode == MODE_MIXED) + mode = rand() % 3; + + sqe = io_uring_get_sqe(&ring); + + if (mode == MODE_NONZC) { + io_uring_prep_send(sqe, fd, payload, + cfg_payload_len, msg_flags); + sqe->user_data = NONZC_TAG; + } else { + if (cfg_flush) { + zc_flags |= IORING_RECVSEND_NOTIF_FLUSH; + compl_cqes++; + } + io_uring_prep_sendzc(sqe, fd, payload, + cfg_payload_len, + msg_flags, slot_idx, zc_flags); + if (mode == MODE_ZC_FIXED) { + sqe->ioprio |= IORING_RECVSEND_FIXED_BUF; + sqe->buf_index = buf_idx; + } + sqe->user_data = ZC_TAG; + } + } + + ret = io_uring_submit(&ring); + if (ret != cfg_nr_reqs) + error(1, ret, "submit"); + + for (i = 0; i < cfg_nr_reqs; i++) { + ret = io_uring_wait_cqe(&ring, &cqe); + if (ret) + error(1, ret, "wait cqe"); + + if (cqe->user_data == NOTIF_TAG) { + compl_cqes--; + i--; + } else if (cqe->user_data != NONZC_TAG && + cqe->user_data != ZC_TAG) { + error(1, cqe->res, "invalid user_data"); + } else if (cqe->res <= 0 && cqe->res != -EAGAIN) { + error(1, cqe->res, "send failed"); + } else { + if (cqe->res > 0) { + packets++; + bytes += cqe->res; + } + /* failed requests don't flush */ + if (cfg_flush && + cqe->res <= 0 && + cqe->user_data == ZC_TAG) + compl_cqes--; + } + io_uring_cqe_seen(&ring); + } + if (cfg_cork) + do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0); + } while (gettimeofday_ms() < tstop); + + if (close(fd)) + error(1, errno, "close"); + + fprintf(stderr, "tx=%lu (MB=%lu), tx/s=%lu (MB/s=%lu)\n", + packets, bytes >> 20, + packets / (cfg_runtime_ms / 1000), + (bytes >> 20) / (cfg_runtime_ms / 1000)); + + while (compl_cqes) { + ret = io_uring_wait_cqe(&ring, &cqe); + if (ret) + error(1, ret, "wait cqe"); + io_uring_cqe_seen(&ring); + compl_cqes--; + } +} + +static void do_test(int domain, int type, int protocol) +{ + int i; + + for (i = 0; i < IP_MAXPACKET; i++) + payload[i] = 'a' + (i % 26); + do_tx(domain, type, protocol); +} + +static void usage(const char *filepath) +{ + error(1, 0, "Usage: %s [-f] [-n] [-z0] [-s] " + "(-4|-6) [-t