From 7eeba1706eba6def15f6cb2fc7b3c3b9a2651edc Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 20 Jan 2021 16:41:48 -0800 Subject: [PATCH] tcp: Add receive timestamp support for receive zerocopy. tcp_recvmsg() uses the CMSG mechanism to receive control information like packet receive timestamps. This patch adds CMSG fields to struct tcp_zerocopy_receive, and provides receive timestamps if available to the user. Signed-off-by: Arjun Roy Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 4 ++ net/ipv4/tcp.c | 116 ++++++++++++++++++++++++++++----------- 2 files changed, 88 insertions(+), 32 deletions(-) diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 16dfa40bdac3..42fc5a640df4 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -354,5 +354,9 @@ struct tcp_zerocopy_receive { __u64 copybuf_address; /* in: copybuf address (small reads) */ __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */ __u32 flags; /* in: flags */ + __u64 msg_control; /* ancillary data */ + __u64 msg_controllen; + __u32 msg_flags; + /* __u32 hole; Next we must add >1 u32 otherwise length checks fail. */ }; #endif /* _UAPI_LINUX_TCP_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7ba0bd0675cb..e1a17c6b473c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1745,6 +1745,20 @@ int tcp_set_rcvlowat(struct sock *sk, int val) } EXPORT_SYMBOL(tcp_set_rcvlowat); +static void tcp_update_recv_tstamps(struct sk_buff *skb, + struct scm_timestamping_internal *tss) +{ + if (skb->tstamp) + tss->ts[0] = ktime_to_timespec64(skb->tstamp); + else + tss->ts[0] = (struct timespec64) {0}; + + if (skb_hwtstamps(skb)->hwtstamp) + tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); + else + tss->ts[2] = (struct timespec64) {0}; +} + #ifdef CONFIG_MMU static const struct vm_operations_struct tcp_vm_ops = { }; @@ -1848,13 +1862,13 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, struct scm_timestamping_internal *tss, int *cmsg_flags); static int receive_fallback_to_copy(struct sock *sk, - struct tcp_zerocopy_receive *zc, int inq) + struct tcp_zerocopy_receive *zc, int inq, + struct scm_timestamping_internal *tss) { unsigned long copy_address = (unsigned long)zc->copybuf_address; - struct scm_timestamping_internal tss_unused; - int err, cmsg_flags_unused; struct msghdr msg = {}; struct iovec iov; + int err; zc->length = 0; zc->recv_skip_hint = 0; @@ -1868,7 +1882,7 @@ static int receive_fallback_to_copy(struct sock *sk, return err; err = tcp_recvmsg_locked(sk, &msg, inq, /*nonblock=*/1, /*flags=*/0, - &tss_unused, &cmsg_flags_unused); + tss, &zc->msg_flags); if (err < 0) return err; @@ -1909,21 +1923,27 @@ static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, return (__s32)copylen; } -static int tcp_zerocopy_handle_leftover_data(struct tcp_zerocopy_receive *zc, - struct sock *sk, - struct sk_buff *skb, - u32 *seq, - s32 copybuf_len) +static int tcp_zc_handle_leftover(struct tcp_zerocopy_receive *zc, + struct sock *sk, + struct sk_buff *skb, + u32 *seq, + s32 copybuf_len, + struct scm_timestamping_internal *tss) { u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint); if (!copylen) return 0; /* skb is null if inq < PAGE_SIZE. */ - if (skb) + if (skb) { offset = *seq - TCP_SKB_CB(skb)->seq; - else + } else { skb = tcp_recv_skb(sk, *seq, &offset); + if (TCP_SKB_CB(skb)->has_rxtstamp) { + tcp_update_recv_tstamps(skb, tss); + zc->msg_flags |= TCP_CMSG_TS; + } + } zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset, seq); @@ -2010,9 +2030,37 @@ static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, err); } +static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, + struct scm_timestamping_internal *tss); +static void tcp_zc_finalize_rx_tstamp(struct sock *sk, + struct tcp_zerocopy_receive *zc, + struct scm_timestamping_internal *tss) +{ + unsigned long msg_control_addr; + struct msghdr cmsg_dummy; + + msg_control_addr = (unsigned long)zc->msg_control; + cmsg_dummy.msg_control = (void *)msg_control_addr; + cmsg_dummy.msg_controllen = + (__kernel_size_t)zc->msg_controllen; + cmsg_dummy.msg_flags = in_compat_syscall() + ? MSG_CMSG_COMPAT : 0; + zc->msg_flags = 0; + if (zc->msg_control == msg_control_addr && + zc->msg_controllen == cmsg_dummy.msg_controllen) { + tcp_recv_timestamp(&cmsg_dummy, sk, tss); + zc->msg_control = (__u64) + ((uintptr_t)cmsg_dummy.msg_control); + zc->msg_controllen = + (__u64)cmsg_dummy.msg_controllen; + zc->msg_flags = (__u32)cmsg_dummy.msg_flags; + } +} + #define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32 static int tcp_zerocopy_receive(struct sock *sk, - struct tcp_zerocopy_receive *zc) + struct tcp_zerocopy_receive *zc, + struct scm_timestamping_internal *tss) { u32 length = 0, offset, vma_len, avail_len, copylen = 0; unsigned long address = (unsigned long)zc->address; @@ -2029,6 +2077,7 @@ static int tcp_zerocopy_receive(struct sock *sk, int ret; zc->copybuf_len = 0; + zc->msg_flags = 0; if (address & (PAGE_SIZE - 1) || address != zc->address) return -EINVAL; @@ -2039,7 +2088,7 @@ static int tcp_zerocopy_receive(struct sock *sk, sock_rps_record_flow(sk); if (inq && inq <= copybuf_len) - return receive_fallback_to_copy(sk, zc, inq); + return receive_fallback_to_copy(sk, zc, inq, tss); if (inq < PAGE_SIZE) { zc->length = 0; @@ -2084,6 +2133,11 @@ static int tcp_zerocopy_receive(struct sock *sk, } else { skb = tcp_recv_skb(sk, seq, &offset); } + + if (TCP_SKB_CB(skb)->has_rxtstamp) { + tcp_update_recv_tstamps(skb, tss); + zc->msg_flags |= TCP_CMSG_TS; + } zc->recv_skip_hint = skb->len - offset; frags = skb_advance_to_frag(skb, offset, &offset_frag); if (!frags || offset_frag) @@ -2126,8 +2180,7 @@ out: mmap_read_unlock(current->mm); /* Try to copy straggler data. */ if (!ret) - copylen = tcp_zerocopy_handle_leftover_data(zc, sk, skb, &seq, - copybuf_len); + copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss); if (length + copylen) { WRITE_ONCE(tp->copied_seq, seq); @@ -2148,20 +2201,6 @@ out: } #endif -static void tcp_update_recv_tstamps(struct sk_buff *skb, - struct scm_timestamping_internal *tss) -{ - if (skb->tstamp) - tss->ts[0] = ktime_to_timespec64(skb->tstamp); - else - tss->ts[0] = (struct timespec64) {0}; - - if (skb_hwtstamps(skb)->hwtstamp) - tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); - else - tss->ts[2] = (struct timespec64) {0}; -} - /* Similar to __sock_recv_timestamp, but does not require an skb */ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss) @@ -4105,6 +4144,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, } #ifdef CONFIG_MMU case TCP_ZEROCOPY_RECEIVE: { + struct scm_timestamping_internal tss; struct tcp_zerocopy_receive zc = {}; int err; @@ -4120,11 +4160,18 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (copy_from_user(&zc, optval, len)) return -EFAULT; lock_sock(sk); - err = tcp_zerocopy_receive(sk, &zc); + err = tcp_zerocopy_receive(sk, &zc, &tss); release_sock(sk); - if (len >= offsetofend(struct tcp_zerocopy_receive, err)) - goto zerocopy_rcv_sk_err; + if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) + goto zerocopy_rcv_cmsg; switch (len) { + case offsetofend(struct tcp_zerocopy_receive, msg_flags): + goto zerocopy_rcv_cmsg; + case offsetofend(struct tcp_zerocopy_receive, msg_controllen): + case offsetofend(struct tcp_zerocopy_receive, msg_control): + case offsetofend(struct tcp_zerocopy_receive, flags): + case offsetofend(struct tcp_zerocopy_receive, copybuf_len): + case offsetofend(struct tcp_zerocopy_receive, copybuf_address): case offsetofend(struct tcp_zerocopy_receive, err): goto zerocopy_rcv_sk_err; case offsetofend(struct tcp_zerocopy_receive, inq): @@ -4133,6 +4180,11 @@ static int do_tcp_getsockopt(struct sock *sk, int level, default: goto zerocopy_rcv_out; } +zerocopy_rcv_cmsg: + if (zc.msg_flags & TCP_CMSG_TS) + tcp_zc_finalize_rx_tstamp(sk, &zc, &tss); + else + zc.msg_flags = 0; zerocopy_rcv_sk_err: if (!err) zc.err = sock_error(sk);