From 18fb76ed53865c1b5d5f0157b1b825704590beb5 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:42 -0800 Subject: [PATCH 1/8] net-zerocopy: Copy straggler unaligned data for TCP Rx. zerocopy. When TCP receive zerocopy does not successfully map the entire requested space, it outputs a 'hint' that the caller should recvmsg(). Augment zerocopy to accept a user buffer that it tries to copy this hint into - if it is possible to copy the entire hint, it will do so. This elides a recvmsg() call for received traffic that isn't exactly page-aligned in size. This was tested with RPC-style traffic of arbitrary sizes. Normally, each received message required at least one getsockopt() call, and one recvmsg() call for the remaining unaligned data. With this change, almost all of the recvmsg() calls are eliminated, leading to a savings of about 25%-50% in number of system calls for RPC-style workloads. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 2 + net/ipv4/tcp.c | 84 ++++++++++++++++++++++++++++++++-------- 2 files changed, 70 insertions(+), 16 deletions(-) diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index cfcb10b754838..62db78b9c1a0a 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -349,5 +349,7 @@ struct tcp_zerocopy_receive { __u32 recv_skip_hint; /* out: amount of bytes to skip */ __u32 inq; /* out: amount of bytes in read queue */ __s32 err; /* out: socket error */ + __u64 copybuf_address; /* in: copybuf address (small reads) */ + __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */ }; #endif /* _UAPI_LINUX_TCP_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 75a28b8f4470c..0ad70097da593 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1758,6 +1758,52 @@ int tcp_mmap(struct file *file, struct socket *sock, } EXPORT_SYMBOL(tcp_mmap); +static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, + struct sk_buff *skb, u32 copylen, + u32 *offset, u32 *seq) +{ + unsigned long copy_address = (unsigned long)zc->copybuf_address; + struct msghdr msg = {}; + struct iovec iov; + int err; + + if (copy_address != zc->copybuf_address) + return -EINVAL; + + err = import_single_range(READ, (void __user *)copy_address, + copylen, &iov, &msg.msg_iter); + if (err) + return err; + err = skb_copy_datagram_msg(skb, *offset, &msg, copylen); + if (err) + return err; + zc->recv_skip_hint -= copylen; + *offset += copylen; + *seq += copylen; + 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) +{ + 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) + offset = *seq - TCP_SKB_CB(skb)->seq; + else + skb = tcp_recv_skb(sk, *seq, &offset); + + zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset, + seq); + return zc->copybuf_len < 0 ? 0 : copylen; +} + static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, struct page **pages, unsigned long pages_to_map, @@ -1791,8 +1837,10 @@ static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc) { + u32 length = 0, offset, vma_len, avail_len, aligned_len, copylen = 0; unsigned long address = (unsigned long)zc->address; - u32 length = 0, seq, offset, zap_len; + s32 copybuf_len = zc->copybuf_len; + struct tcp_sock *tp = tcp_sk(sk); #define PAGE_BATCH_SIZE 8 struct page *pages[PAGE_BATCH_SIZE]; const skb_frag_t *frags = NULL; @@ -1800,10 +1848,12 @@ static int tcp_zerocopy_receive(struct sock *sk, struct sk_buff *skb = NULL; unsigned long pg_idx = 0; unsigned long curr_addr; - struct tcp_sock *tp; - int inq; + u32 seq = tp->copied_seq; + int inq = tcp_inq(sk); int ret; + zc->copybuf_len = 0; + if (address & (PAGE_SIZE - 1) || address != zc->address) return -EINVAL; @@ -1812,8 +1862,6 @@ static int tcp_zerocopy_receive(struct sock *sk, sock_rps_record_flow(sk); - tp = tcp_sk(sk); - mmap_read_lock(current->mm); vma = find_vma(current->mm, address); @@ -1821,17 +1869,16 @@ static int tcp_zerocopy_receive(struct sock *sk, mmap_read_unlock(current->mm); return -EINVAL; } - zc->length = min_t(unsigned long, zc->length, vma->vm_end - address); - - seq = tp->copied_seq; - inq = tcp_inq(sk); - zc->length = min_t(u32, zc->length, inq); - zap_len = zc->length & ~(PAGE_SIZE - 1); - if (zap_len) { - zap_page_range(vma, address, zap_len); + vma_len = min_t(unsigned long, zc->length, vma->vm_end - address); + avail_len = min_t(u32, vma_len, inq); + aligned_len = avail_len & ~(PAGE_SIZE - 1); + if (aligned_len) { + zap_page_range(vma, address, aligned_len); + zc->length = aligned_len; zc->recv_skip_hint = 0; } else { - zc->recv_skip_hint = zc->length; + zc->length = avail_len; + zc->recv_skip_hint = avail_len; } ret = 0; curr_addr = address; @@ -1900,13 +1947,18 @@ static int tcp_zerocopy_receive(struct sock *sk, } out: mmap_read_unlock(current->mm); - if (length) { + /* Try to copy straggler data. */ + if (!ret) + copylen = tcp_zerocopy_handle_leftover_data(zc, sk, skb, &seq, + copybuf_len); + + if (length + copylen) { WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ tcp_recv_skb(sk, seq, &offset); - tcp_cleanup_rbuf(sk, length); + tcp_cleanup_rbuf(sk, length + copylen); ret = 0; if (length == zc->length) zc->recv_skip_hint = 0; From 2cd81161848daa9c1b5ba13ceb6ff067fbb86aa9 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:43 -0800 Subject: [PATCH 2/8] net-tcp: Introduce tcp_recvmsg_locked(). Refactor tcp_recvmsg() by splitting it into locked and unlocked portions. Callers already holding the socket lock and not using ERRQUEUE/cmsg/busy polling can simply call tcp_recvmsg_locked(). This is in preparation for a short-circuit copy performed by TCP receive zerocopy for small (< PAGE_SIZE, or otherwise requested by the user) reads. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 69 ++++++++++++++++++++++++++++---------------------- 1 file changed, 39 insertions(+), 30 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0ad70097da593..72fe68014a8ca 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2080,36 +2080,28 @@ static int tcp_inq_hint(struct sock *sk) * Probably, code can be easily improved even more. */ -int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, - int flags, int *addr_len) +static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, + struct scm_timestamping_internal *tss, + int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); int copied = 0; u32 peek_seq; u32 *seq; unsigned long used; - int err, inq; + int err; int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; u32 urg_hole = 0; - struct scm_timestamping_internal tss; - int cmsg_flags; - - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); - - if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && - (sk->sk_state == TCP_ESTABLISHED)) - sk_busy_loop(sk, nonblock); - - lock_sock(sk); err = -ENOTCONN; if (sk->sk_state == TCP_LISTEN) goto out; - cmsg_flags = tp->recvmsg_inq ? 1 : 0; + if (tp->recvmsg_inq) + *cmsg_flags = 1; timeo = sock_rcvtimeo(sk, nonblock); /* Urgent data needs to be handled specially. */ @@ -2289,8 +2281,8 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, } if (TCP_SKB_CB(skb)->has_rxtstamp) { - tcp_update_recv_tstamps(skb, &tss); - cmsg_flags |= 2; + tcp_update_recv_tstamps(skb, tss); + *cmsg_flags |= 2; } if (used + offset < skb->len) @@ -2316,22 +2308,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Clean up data we have read: This will do ACK frames. */ tcp_cleanup_rbuf(sk, copied); - - release_sock(sk); - - if (cmsg_flags) { - if (cmsg_flags & 2) - tcp_recv_timestamp(msg, sk, &tss); - if (cmsg_flags & 1) { - inq = tcp_inq_hint(sk); - put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); - } - } - return copied; out: - release_sock(sk); return err; recv_urg: @@ -2342,6 +2321,36 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, err = tcp_peek_sndq(sk, msg, len); goto out; } + +int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, + int flags, int *addr_len) +{ + int cmsg_flags = 0, ret, inq; + struct scm_timestamping_internal tss; + + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + + if (sk_can_busy_loop(sk) && + skb_queue_empty_lockless(&sk->sk_receive_queue) && + sk->sk_state == TCP_ESTABLISHED) + sk_busy_loop(sk, nonblock); + + lock_sock(sk); + ret = tcp_recvmsg_locked(sk, msg, len, nonblock, flags, &tss, + &cmsg_flags); + release_sock(sk); + + if (cmsg_flags && ret >= 0) { + if (cmsg_flags & 2) + tcp_recv_timestamp(msg, sk, &tss); + if (cmsg_flags & 1) { + inq = tcp_inq_hint(sk); + put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); + } + } + return ret; +} EXPORT_SYMBOL(tcp_recvmsg); void tcp_set_state(struct sock *sk, int state) From 7fba5309efe24e4f0284ef4b8663cdf401035e72 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:44 -0800 Subject: [PATCH 3/8] net-zerocopy: Refactor skb frag fast-forward op. Refactor skb frag fast-forwarding for tcp receive zerocopy. This is part of a patch set that introduces short-circuited hybrid copies for small receive operations, which results in roughly 33% fewer syscalls for small RPC scenarios. skb_advance_to_frag(), given a skb and an offset into the skb, iterates from the first frag for the skb until we're at the frag specified by the offset. Assuming the offset provided refers to how many bytes in the skb are already read, the returned frag points to the next frag we may read from, while offset_frag is set to the number of bytes from this frag that we have already read. If frag is not null and offset_frag is equal to 0, then we may be able to map this frag's page into the process address space with vm_insert_page(). However, if offset_frag is not equal to 0, then we cannot do so. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 72fe68014a8ca..8372d31f4a887 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1758,6 +1758,28 @@ int tcp_mmap(struct file *file, struct socket *sock, } EXPORT_SYMBOL(tcp_mmap); +static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, + u32 *offset_frag) +{ + skb_frag_t *frag; + + offset_skb -= skb_headlen(skb); + if ((int)offset_skb < 0 || skb_has_frag_list(skb)) + return NULL; + + frag = skb_shinfo(skb)->frags; + while (offset_skb) { + if (skb_frag_size(frag) > offset_skb) { + *offset_frag = offset_skb; + return frag; + } + offset_skb -= skb_frag_size(frag); + ++frag; + } + *offset_frag = 0; + return frag; +} + static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) @@ -1884,6 +1906,8 @@ static int tcp_zerocopy_receive(struct sock *sk, curr_addr = address; while (length + PAGE_SIZE <= zc->length) { if (zc->recv_skip_hint < PAGE_SIZE) { + u32 offset_frag; + /* If we're here, finish the current batch. */ if (pg_idx) { ret = tcp_zerocopy_vm_insert_batch(vma, pages, @@ -1904,16 +1928,9 @@ static int tcp_zerocopy_receive(struct sock *sk, skb = tcp_recv_skb(sk, seq, &offset); } zc->recv_skip_hint = skb->len - offset; - offset -= skb_headlen(skb); - if ((int)offset < 0 || skb_has_frag_list(skb)) + frags = skb_advance_to_frag(skb, offset, &offset_frag); + if (!frags || offset_frag) break; - frags = skb_shinfo(skb)->frags; - while (offset) { - if (skb_frag_size(frags) > offset) - goto out; - offset -= skb_frag_size(frags); - frags++; - } } if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) { int remaining = zc->recv_skip_hint; From 98917cf0d6eda01e8c3c34d35398d46b247b6fd3 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:45 -0800 Subject: [PATCH 4/8] net-zerocopy: Refactor frag-is-remappable test. Refactor frag-is-remappable test for tcp receive zerocopy. This is part of a patch set that introduces short-circuited hybrid copies for small receive operations, which results in roughly 33% fewer syscalls for small RPC scenarios. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8372d31f4a887..aa1040b5a9776 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1780,6 +1780,26 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, return frag; } +static bool can_map_frag(const skb_frag_t *frag) +{ + return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag); +} + +static int find_next_mappable_frag(const skb_frag_t *frag, + int remaining_in_skb) +{ + int offset = 0; + + if (likely(can_map_frag(frag))) + return 0; + + while (offset < remaining_in_skb && !can_map_frag(frag)) { + offset += skb_frag_size(frag); + ++frag; + } + return offset; +} + static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) @@ -1905,6 +1925,8 @@ static int tcp_zerocopy_receive(struct sock *sk, ret = 0; curr_addr = address; while (length + PAGE_SIZE <= zc->length) { + int mappable_offset; + if (zc->recv_skip_hint < PAGE_SIZE) { u32 offset_frag; @@ -1932,15 +1954,11 @@ static int tcp_zerocopy_receive(struct sock *sk, if (!frags || offset_frag) break; } - if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) { - int remaining = zc->recv_skip_hint; - while (remaining && (skb_frag_size(frags) != PAGE_SIZE || - skb_frag_off(frags))) { - remaining -= skb_frag_size(frags); - frags++; - } - zc->recv_skip_hint -= remaining; + mappable_offset = find_next_mappable_frag(frags, + zc->recv_skip_hint); + if (mappable_offset) { + zc->recv_skip_hint = mappable_offset; break; } pages[pg_idx] = skb_frag_page(frags); From 936ced415751f744654f64977ddbf67d17a2a45a Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:46 -0800 Subject: [PATCH 5/8] net-zerocopy: Fast return if inq < PAGE_SIZE Sometimes, we may call tcp receive zerocopy when inq is 0, or inq < PAGE_SIZE, in which case we cannot remap pages. In this case, simply return the appropriate hint for regular copying without taking mmap_sem. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index aa1040b5a9776..b9e44ad2b40d9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1904,6 +1904,14 @@ static int tcp_zerocopy_receive(struct sock *sk, sock_rps_record_flow(sk); + if (inq < PAGE_SIZE) { + zc->length = 0; + zc->recv_skip_hint = inq; + if (!inq && sock_flag(sk, SOCK_DONE)) + return -EIO; + return 0; + } + mmap_read_lock(current->mm); vma = find_vma(current->mm, address); From f21a3c48039891c02063fe6dc3c3a2f8f344b345 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:47 -0800 Subject: [PATCH 6/8] net-zerocopy: Introduce short-circuit small reads. Sometimes, we may call tcp receive zerocopy when inq is 0, or inq < PAGE_SIZE, or inq is generally small enough that it is cheaper to copy rather than remap pages. In these cases, we may want to either return early (inq=0) or attempt to use the provided copy buffer to simply copy the received data. This allows us to save both system call overhead and the latency of acquiring mmap_sem in read mode for cases where it would be useless to do so. This patchset enables this behaviour by: 1. Returning quickly if inq is 0. 2. Attempting to perform a regular copy if a hybrid copybuffer is provided and it is large enough to absorb all available bytes. 3. Return quickly if no such buffer was provided and there are less than PAGE_SIZE bytes available. For small RPC ping-pong workloads, normally we would have 1 getsockopt(), 1 recvmsg() and 1 sendmsg() call per RPC. With this change, we remove the recvmsg() call entirely, reducing the syscall overhead by about 33%. In testing with small (hundreds of bytes) RPC traffic, this yields a syscall reduction of about 33% and an efficiency gain of about 3-5% when defined as QPS/CPU Util. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b9e44ad2b40d9..05ec65698b95f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1800,6 +1800,39 @@ static int find_next_mappable_frag(const skb_frag_t *frag, return offset; } +static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, + struct scm_timestamping_internal *tss, + int *cmsg_flags); +static int receive_fallback_to_copy(struct sock *sk, + struct tcp_zerocopy_receive *zc, int inq) +{ + 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; + + zc->length = 0; + zc->recv_skip_hint = 0; + + if (copy_address != zc->copybuf_address) + return -EINVAL; + + err = import_single_range(READ, (void __user *)copy_address, + inq, &iov, &msg.msg_iter); + if (err) + return err; + + err = tcp_recvmsg_locked(sk, &msg, inq, /*nonblock=*/1, /*flags=*/0, + &tss_unused, &cmsg_flags_unused); + if (err < 0) + return err; + + zc->copybuf_len = err; + return 0; +} + static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) @@ -1904,6 +1937,9 @@ 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); + if (inq < PAGE_SIZE) { zc->length = 0; zc->recv_skip_hint = inq; From 0c3936d32f754c6e9068a25b7823dc4b5bc42607 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:48 -0800 Subject: [PATCH 7/8] net-zerocopy: Set zerocopy hint when data is copied Set zerocopy hint, event when falling back to copy, so that the pending data can be efficiently received using zerocopy when possible. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 05ec65698b95f..df6dd15a59881 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1800,6 +1800,43 @@ static int find_next_mappable_frag(const skb_frag_t *frag, return offset; } +static void tcp_zerocopy_set_hint_for_skb(struct sock *sk, + struct tcp_zerocopy_receive *zc, + struct sk_buff *skb, u32 offset) +{ + u32 frag_offset, partial_frag_remainder = 0; + int mappable_offset; + skb_frag_t *frag; + + /* worst case: skip to next skb. try to improve on this case below */ + zc->recv_skip_hint = skb->len - offset; + + /* Find the frag containing this offset (and how far into that frag) */ + frag = skb_advance_to_frag(skb, offset, &frag_offset); + if (!frag) + return; + + if (frag_offset) { + struct skb_shared_info *info = skb_shinfo(skb); + + /* We read part of the last frag, must recvmsg() rest of skb. */ + if (frag == &info->frags[info->nr_frags - 1]) + return; + + /* Else, we must at least read the remainder in this frag. */ + partial_frag_remainder = skb_frag_size(frag) - frag_offset; + zc->recv_skip_hint -= partial_frag_remainder; + ++frag; + } + + /* partial_frag_remainder: If part way through a frag, must read rest. + * mappable_offset: Bytes till next mappable frag, *not* counting bytes + * in partial_frag_remainder. + */ + mappable_offset = find_next_mappable_frag(frag, zc->recv_skip_hint); + zc->recv_skip_hint = mappable_offset + partial_frag_remainder; +} + static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, struct scm_timestamping_internal *tss, @@ -1830,6 +1867,14 @@ static int receive_fallback_to_copy(struct sock *sk, return err; zc->copybuf_len = err; + if (likely(zc->copybuf_len)) { + struct sk_buff *skb; + u32 offset; + + skb = tcp_recv_skb(sk, tcp_sk(sk)->copied_seq, &offset); + if (skb) + tcp_zerocopy_set_hint_for_skb(sk, zc, skb, offset); + } return 0; } From 94ab9eb9b234ddf23af04a4bc7e8db68e67b8778 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 2 Dec 2020 14:53:49 -0800 Subject: [PATCH 8/8] net-zerocopy: Defer vm zap unless actually needed. Zapping pages is required only if we are calling vm_insert_page into a region where pages had previously been mapped. Receive zerocopy allows reusing such regions, and hitherto called zap_page_range() before calling vm_insert_page() in that range. zap_page_range() can also be triggered from userspace with madvise(MADV_DONTNEED). If userspace is configured to call this before reusing a segment, or if there was nothing mapped at this virtual address to begin with, we can avoid calling zap_page_range() under the socket lock. That said, if userspace does not do that, then we are still responsible for calling zap_page_range(). This patch adds a flag that the user can use to hint to the kernel that a zap is not required. If the flag is not set, or if an older user application does not have a flags field at all, then the kernel calls zap_page_range as before. Also, if the flag is set but a zap is still required, the kernel performs that zap as necessary. Thus incorrectly indicating that a zap can be avoided does not change the correctness of operation. It also increases the batchsize for vm_insert_pages and prefetches the page struct for the batch since we're about to bump the refcount. An alternative mechanism could be to not have a flag, assume by default a zap is not needed, and fall back to zapping if needed. However, this would harm performance for older applications for which a zap is necessary, and thus we implement it with an explicit flag so newer applications can opt in. When using RPC-style traffic with medium sized (tens of KB) RPCs, this change yields an efficency improvement of about 30% for QPS/CPU usage. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 2 + net/ipv4/tcp.c | 147 ++++++++++++++++++++++++++------------- 2 files changed, 99 insertions(+), 50 deletions(-) diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 62db78b9c1a0a..13ceeb395eb8f 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -343,6 +343,7 @@ struct tcp_diag_md5sig { /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */ +#define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1 struct tcp_zerocopy_receive { __u64 address; /* in: address of mapping */ __u32 length; /* in/out: number of bytes to map/mapped */ @@ -351,5 +352,6 @@ struct tcp_zerocopy_receive { __s32 err; /* out: socket error */ __u64 copybuf_address; /* in: copybuf address (small reads) */ __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */ + __u32 flags; /* in: flags */ }; #endif /* _UAPI_LINUX_TCP_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index df6dd15a59881..3c99d48b65d8d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1924,51 +1924,101 @@ static int tcp_zerocopy_handle_leftover_data(struct tcp_zerocopy_receive *zc, return zc->copybuf_len < 0 ? 0 : copylen; } +static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma, + struct page **pending_pages, + unsigned long pages_remaining, + unsigned long *address, + u32 *length, + u32 *seq, + struct tcp_zerocopy_receive *zc, + u32 total_bytes_to_map, + int err) +{ + /* At least one page did not map. Try zapping if we skipped earlier. */ + if (err == -EBUSY && + zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT) { + u32 maybe_zap_len; + + maybe_zap_len = total_bytes_to_map - /* All bytes to map */ + *length + /* Mapped or pending */ + (pages_remaining * PAGE_SIZE); /* Failed map. */ + zap_page_range(vma, *address, maybe_zap_len); + err = 0; + } + + if (!err) { + unsigned long leftover_pages = pages_remaining; + int bytes_mapped; + + /* We called zap_page_range, try to reinsert. */ + err = vm_insert_pages(vma, *address, + pending_pages, + &pages_remaining); + bytes_mapped = PAGE_SIZE * (leftover_pages - pages_remaining); + *seq += bytes_mapped; + *address += bytes_mapped; + } + if (err) { + /* Either we were unable to zap, OR we zapped, retried an + * insert, and still had an issue. Either ways, pages_remaining + * is the number of pages we were unable to map, and we unroll + * some state we speculatively touched before. + */ + const int bytes_not_mapped = PAGE_SIZE * pages_remaining; + + *length -= bytes_not_mapped; + zc->recv_skip_hint += bytes_not_mapped; + } + return err; +} + static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, struct page **pages, - unsigned long pages_to_map, - unsigned long *insert_addr, - u32 *length_with_pending, + unsigned int pages_to_map, + unsigned long *address, + u32 *length, u32 *seq, - struct tcp_zerocopy_receive *zc) + struct tcp_zerocopy_receive *zc, + u32 total_bytes_to_map) { unsigned long pages_remaining = pages_to_map; - int bytes_mapped; - int ret; + unsigned int pages_mapped; + unsigned int bytes_mapped; + int err; - ret = vm_insert_pages(vma, *insert_addr, pages, &pages_remaining); - bytes_mapped = PAGE_SIZE * (pages_to_map - pages_remaining); + err = vm_insert_pages(vma, *address, pages, &pages_remaining); + pages_mapped = pages_to_map - (unsigned int)pages_remaining; + bytes_mapped = PAGE_SIZE * pages_mapped; /* Even if vm_insert_pages fails, it may have partially succeeded in * mapping (some but not all of the pages). */ *seq += bytes_mapped; - *insert_addr += bytes_mapped; - if (ret) { - /* But if vm_insert_pages did fail, we have to unroll some state - * we speculatively touched before. - */ - const int bytes_not_mapped = PAGE_SIZE * pages_remaining; - *length_with_pending -= bytes_not_mapped; - zc->recv_skip_hint += bytes_not_mapped; - } - return ret; + *address += bytes_mapped; + + if (likely(!err)) + return 0; + + /* Error: maybe zap and retry + rollback state for failed inserts. */ + return tcp_zerocopy_vm_insert_batch_error(vma, pages + pages_mapped, + pages_remaining, address, length, seq, zc, total_bytes_to_map, + err); } +#define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32 static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc) { - u32 length = 0, offset, vma_len, avail_len, aligned_len, copylen = 0; + u32 length = 0, offset, vma_len, avail_len, copylen = 0; unsigned long address = (unsigned long)zc->address; + struct page *pages[TCP_ZEROCOPY_PAGE_BATCH_SIZE]; s32 copybuf_len = zc->copybuf_len; struct tcp_sock *tp = tcp_sk(sk); - #define PAGE_BATCH_SIZE 8 - struct page *pages[PAGE_BATCH_SIZE]; const skb_frag_t *frags = NULL; + unsigned int pages_to_map = 0; struct vm_area_struct *vma; struct sk_buff *skb = NULL; - unsigned long pg_idx = 0; - unsigned long curr_addr; u32 seq = tp->copied_seq; + u32 total_bytes_to_map; int inq = tcp_inq(sk); int ret; @@ -2002,34 +2052,24 @@ static int tcp_zerocopy_receive(struct sock *sk, } vma_len = min_t(unsigned long, zc->length, vma->vm_end - address); avail_len = min_t(u32, vma_len, inq); - aligned_len = avail_len & ~(PAGE_SIZE - 1); - if (aligned_len) { - zap_page_range(vma, address, aligned_len); - zc->length = aligned_len; + total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1); + if (total_bytes_to_map) { + if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT)) + zap_page_range(vma, address, total_bytes_to_map); + zc->length = total_bytes_to_map; zc->recv_skip_hint = 0; } else { zc->length = avail_len; zc->recv_skip_hint = avail_len; } ret = 0; - curr_addr = address; while (length + PAGE_SIZE <= zc->length) { int mappable_offset; + struct page *page; if (zc->recv_skip_hint < PAGE_SIZE) { u32 offset_frag; - /* If we're here, finish the current batch. */ - if (pg_idx) { - ret = tcp_zerocopy_vm_insert_batch(vma, pages, - pg_idx, - &curr_addr, - &length, - &seq, zc); - if (ret) - goto out; - pg_idx = 0; - } if (skb) { if (zc->recv_skip_hint > 0) break; @@ -2050,24 +2090,31 @@ static int tcp_zerocopy_receive(struct sock *sk, zc->recv_skip_hint = mappable_offset; break; } - pages[pg_idx] = skb_frag_page(frags); - pg_idx++; + page = skb_frag_page(frags); + prefetchw(page); + pages[pages_to_map++] = page; length += PAGE_SIZE; zc->recv_skip_hint -= PAGE_SIZE; frags++; - if (pg_idx == PAGE_BATCH_SIZE) { - ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx, - &curr_addr, &length, - &seq, zc); + if (pages_to_map == TCP_ZEROCOPY_PAGE_BATCH_SIZE || + zc->recv_skip_hint < PAGE_SIZE) { + /* Either full batch, or we're about to go to next skb + * (and we cannot unroll failed ops across skbs). + */ + ret = tcp_zerocopy_vm_insert_batch(vma, pages, + pages_to_map, + &address, &length, + &seq, zc, + total_bytes_to_map); if (ret) goto out; - pg_idx = 0; + pages_to_map = 0; } } - if (pg_idx) { - ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx, - &curr_addr, &length, &seq, - zc); + if (pages_to_map) { + ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, + &address, &length, &seq, + zc, total_bytes_to_map); } out: mmap_read_unlock(current->mm);