From 8c9a6f549e65912825e31dc1e0e3f7995984649d Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 9 Apr 2024 14:05:53 -0700 Subject: io_uring: separate header for exported net bits We're exporting some io_uring bits to networking, e.g. for implementing a net callback for io_uring cmds, but we don't want to expose more than needed. Add a separate header for networking. Signed-off-by: Pavel Begunkov Signed-off-by: David Wei Link: https://lore.kernel.org/r/20240409210554.1878789-1-dw@davidwei.uk Signed-off-by: Jens Axboe --- net/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/socket.c b/net/socket.c index e5f3af49a8b6..01a71ae10c35 100644 --- a/net/socket.c +++ b/net/socket.c @@ -88,7 +88,7 @@ #include #include #include -#include +#include #include #include -- cgit v1.2.3-58-ga151 From 7ab4f16f9e2440e797eae88812f800458e5879d2 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 19 Apr 2024 12:08:39 +0100 Subject: net: extend ubuf_info callback to ops structure We'll need to associate additional callbacks with ubuf_info, introduce a structure holding ubuf_info callbacks. Apart from a more smarter io_uring notification management introduced in next patches, it can be used to generalise msg_zerocopy_put_abort() and also store ->sg_from_iter, which is currently passed in struct msghdr. Reviewed-by: Jens Axboe Reviewed-by: David Ahern Signed-off-by: Pavel Begunkov Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/all/a62015541de49c0e2a8a0377a1d5d0a5aeb07016.1713369317.git.asml.silence@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/tap.c | 2 +- drivers/net/tun.c | 2 +- drivers/net/xen-netback/common.h | 5 ++--- drivers/net/xen-netback/interface.c | 2 +- drivers/net/xen-netback/netback.c | 11 ++++++++--- drivers/vhost/net.c | 8 ++++++-- include/linux/skbuff.h | 19 +++++++++++-------- io_uring/notif.c | 18 +++++++++++++----- net/core/skbuff.c | 16 ++++++++++------ 9 files changed, 53 insertions(+), 30 deletions(-) (limited to 'net') diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 9f0495e8df4d..bfdd3875fe86 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -754,7 +754,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control, skb_zcopy_init(skb, msg_control); } else if (msg_control) { struct ubuf_info *uarg = msg_control; - uarg->callback(NULL, uarg, false); + uarg->ops->complete(NULL, uarg, false); } dev_queue_xmit(skb); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 0b3f21cba552..b7401d990680 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1906,7 +1906,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_zcopy_init(skb, msg_control); } else if (msg_control) { struct ubuf_info *uarg = msg_control; - uarg->callback(NULL, uarg, false); + uarg->ops->complete(NULL, uarg, false); } skb_reset_network_header(skb); diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 1fcbd83f7ff2..17421da139f2 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -390,9 +390,8 @@ bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); void xenvif_carrier_on(struct xenvif *vif); -/* Callback from stack when TX packet can be released */ -void xenvif_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf, - bool zerocopy_success); +/* Callbacks from stack when TX packet can be released */ +extern const struct ubuf_info_ops xenvif_ubuf_ops; static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue) { diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 7cff90aa8d24..65db5f14465f 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -593,7 +593,7 @@ int xenvif_init_queue(struct xenvif_queue *queue) for (i = 0; i < MAX_PENDING_REQS; i++) { queue->pending_tx_info[i].callback_struct = (struct ubuf_info_msgzc) - { { .callback = xenvif_zerocopy_callback }, + { { .ops = &xenvif_ubuf_ops }, { { .ctx = NULL, .desc = i } } }; queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index ef76850d9bcd..bab7e43ea05b 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1156,7 +1156,7 @@ static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *s uarg = skb_shinfo(skb)->destructor_arg; /* increase inflight counter to offset decrement in callback */ atomic_inc(&queue->inflight_packets); - uarg->callback(NULL, uarg, true); + uarg->ops->complete(NULL, uarg, true); skb_shinfo(skb)->destructor_arg = NULL; /* Fill the skb with the new (local) frags. */ @@ -1278,8 +1278,9 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) return work_done; } -void xenvif_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf_base, - bool zerocopy_success) +static void xenvif_zerocopy_callback(struct sk_buff *skb, + struct ubuf_info *ubuf_base, + bool zerocopy_success) { unsigned long flags; pending_ring_idx_t index; @@ -1312,6 +1313,10 @@ void xenvif_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf_base, xenvif_skb_zerocopy_complete(queue); } +const struct ubuf_info_ops xenvif_ubuf_ops = { + .complete = xenvif_zerocopy_callback, +}; + static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue) { struct gnttab_unmap_grant_ref *gop; diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index c64ded183f8d..f16279351db5 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -380,7 +380,7 @@ static void vhost_zerocopy_signal_used(struct vhost_net *net, } } -static void vhost_zerocopy_callback(struct sk_buff *skb, +static void vhost_zerocopy_complete(struct sk_buff *skb, struct ubuf_info *ubuf_base, bool success) { struct ubuf_info_msgzc *ubuf = uarg_to_msgzc(ubuf_base); @@ -408,6 +408,10 @@ static void vhost_zerocopy_callback(struct sk_buff *skb, rcu_read_unlock_bh(); } +static const struct ubuf_info_ops vhost_ubuf_ops = { + .complete = vhost_zerocopy_complete, +}; + static inline unsigned long busy_clock(void) { return local_clock() >> 10; @@ -879,7 +883,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS; ubuf->ctx = nvq->ubufs; ubuf->desc = nvq->upend_idx; - ubuf->ubuf.callback = vhost_zerocopy_callback; + ubuf->ubuf.ops = &vhost_ubuf_ops; ubuf->ubuf.flags = SKBFL_ZEROCOPY_FRAG; refcount_set(&ubuf->ubuf.refcnt, 1); msg.msg_control = &ctl; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d24aec064e8..a110e97e074a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -527,6 +527,11 @@ enum { #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) +struct ubuf_info_ops { + void (*complete)(struct sk_buff *, struct ubuf_info *, + bool zerocopy_success); +}; + /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. @@ -536,8 +541,7 @@ enum { * The desc field is used to track userspace buffer index. */ struct ubuf_info { - void (*callback)(struct sk_buff *, struct ubuf_info *, - bool zerocopy_success); + const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; @@ -1662,14 +1666,13 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; + struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); 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 msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length); @@ -1757,13 +1760,13 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) - uarg->callback(NULL, uarg, true); + uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { - if (uarg->callback == msg_zerocopy_callback) + if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); @@ -1777,7 +1780,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (uarg) { if (!skb_zcopy_is_nouarg(skb)) - uarg->callback(skb, uarg, zerocopy_success); + uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } diff --git a/io_uring/notif.c b/io_uring/notif.c index d3e703c37aba..204f0fc7d966 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -24,7 +24,7 @@ static void io_notif_complete_tw_ext(struct io_kiocb *notif, struct io_tw_state io_req_task_complete(notif, ts); } -static void io_tx_ubuf_callback(struct sk_buff *skb, struct ubuf_info *uarg, +static void io_tx_ubuf_complete(struct sk_buff *skb, struct ubuf_info *uarg, bool success) { struct io_notif_data *nd = container_of(uarg, struct io_notif_data, uarg); @@ -45,19 +45,27 @@ static void io_tx_ubuf_callback_ext(struct sk_buff *skb, struct ubuf_info *uarg, else if (!success && !nd->zc_copied) WRITE_ONCE(nd->zc_copied, true); } - io_tx_ubuf_callback(skb, uarg, success); + io_tx_ubuf_complete(skb, uarg, success); } +static const struct ubuf_info_ops io_ubuf_ops = { + .complete = io_tx_ubuf_complete, +}; + +static const struct ubuf_info_ops io_ubuf_ops_ext = { + .complete = io_tx_ubuf_callback_ext, +}; + void io_notif_set_extended(struct io_kiocb *notif) { struct io_notif_data *nd = io_notif_to_data(notif); - if (nd->uarg.callback != io_tx_ubuf_callback_ext) { + if (nd->uarg.ops != &io_ubuf_ops_ext) { nd->account_pages = 0; nd->zc_report = false; nd->zc_used = false; nd->zc_copied = false; - nd->uarg.callback = io_tx_ubuf_callback_ext; + nd->uarg.ops = &io_ubuf_ops_ext; notif->io_task_work.func = io_notif_complete_tw_ext; } } @@ -80,7 +88,7 @@ struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx) nd = io_notif_to_data(notif); nd->uarg.flags = IO_NOTIF_UBUF_FLAGS; - nd->uarg.callback = io_tx_ubuf_callback; + nd->uarg.ops = &io_ubuf_ops; refcount_set(&nd->uarg.refcnt, 1); return notif; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b99127712e67..9d36750459f3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1708,7 +1708,7 @@ static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) return NULL; } - uarg->ubuf.callback = msg_zerocopy_callback; + uarg->ubuf.ops = &msg_zerocopy_ubuf_ops; uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; uarg->len = 1; uarg->bytelen = size; @@ -1734,7 +1734,7 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, u32 bytelen, next; /* there might be non MSG_ZEROCOPY users */ - if (uarg->callback != msg_zerocopy_callback) + if (uarg->ops != &msg_zerocopy_ubuf_ops) return NULL; /* realloc only when socket is locked (TCP, UDP cork), @@ -1845,8 +1845,8 @@ release: sock_put(sk); } -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success) +static void msg_zerocopy_complete(struct sk_buff *skb, struct ubuf_info *uarg, + bool success) { struct ubuf_info_msgzc *uarg_zc = uarg_to_msgzc(uarg); @@ -1855,7 +1855,6 @@ void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, if (refcount_dec_and_test(&uarg->refcnt)) __msg_zerocopy_callback(uarg_zc); } -EXPORT_SYMBOL_GPL(msg_zerocopy_callback); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) { @@ -1865,10 +1864,15 @@ void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) uarg_to_msgzc(uarg)->len--; if (have_uref) - msg_zerocopy_callback(NULL, uarg, true); + msg_zerocopy_complete(NULL, uarg, true); } EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort); +const struct ubuf_info_ops msg_zerocopy_ubuf_ops = { + .complete = msg_zerocopy_complete, +}; +EXPORT_SYMBOL_GPL(msg_zerocopy_ubuf_ops); + int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg) -- cgit v1.2.3-58-ga151 From 65bada80dec1f2108a751644773b2120bd789934 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 19 Apr 2024 12:08:40 +0100 Subject: net: add callback for setting a ubuf_info to skb At the moment an skb can only have one ubuf_info associated with it, which might be a performance problem for zerocopy sends in cases like TCP via io_uring. Add a callback for assigning ubuf_info to skb, this way we will implement smarter assignment later like linking ubuf_info together. Note, it's an optional callback, which should be compatible with skb_zcopy_set(), that's because the net stack might potentially decide to clone an skb and take another reference to ubuf_info whenever it wishes. Also, a correct implementation should always be able to bind to an skb without prior ubuf_info, otherwise we could end up in a situation when the send would not be able to progress. Reviewed-by: Jens Axboe Reviewed-by: David Ahern Signed-off-by: Pavel Begunkov Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/all/b7918aadffeb787c84c9e72e34c729dc04f3a45d.1713369317.git.asml.silence@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 ++ net/core/skbuff.c | 20 ++++++++++++++------ 2 files changed, 16 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a110e97e074a..ced69f37977f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -530,6 +530,8 @@ enum { struct ubuf_info_ops { void (*complete)(struct sk_buff *, struct ubuf_info *, bool zerocopy_success); + /* has to be compatible with skb_zcopy_set() */ + int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); }; /* diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9d36750459f3..4a0c10685cd2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1880,11 +1880,18 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct ubuf_info *orig_uarg = skb_zcopy(skb); int err, orig_len = skb->len; - /* An skb can only point to one uarg. This edge case happens when - * TCP appends to an skb, but zerocopy_realloc triggered a new alloc. - */ - if (orig_uarg && uarg != orig_uarg) - return -EEXIST; + if (uarg->ops->link_skb) { + err = uarg->ops->link_skb(skb, uarg); + if (err) + return err; + } else { + /* An skb can only point to one uarg. This edge case happens + * when TCP appends to an skb, but zerocopy_realloc triggered + * a new alloc. + */ + if (orig_uarg && uarg != orig_uarg) + return -EEXIST; + } err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { @@ -1898,7 +1905,8 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, return err; } - skb_zcopy_set(skb, uarg, NULL); + if (!uarg->ops->link_skb) + skb_zcopy_set(skb, uarg, NULL); return skb->len - orig_len; } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); -- cgit v1.2.3-58-ga151