From: Pavel Begunkov <[email protected]>
To: [email protected], [email protected]
Cc: Jens Axboe <[email protected]>,
[email protected], "David S . Miller" <[email protected]>,
Jakub Kicinski <[email protected]>,
David Ahern <[email protected]>,
Eric Dumazet <[email protected]>,
Willem de Bruijn <[email protected]>,
Jason Wang <[email protected]>, Wei Liu <[email protected]>,
Paul Durrant <[email protected]>,
[email protected],
"Michael S . Tsirkin" <[email protected]>,
[email protected], [email protected]
Subject: [PATCH io_uring-next/net-next v2 1/4] net: extend ubuf_info callback to ops structure
Date: Fri, 19 Apr 2024 12:08:39 +0100 [thread overview]
Message-ID: <a62015541de49c0e2a8a0377a1d5d0a5aeb07016.1713369317.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>
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 <[email protected]>
Reviewed-by: David Ahern <[email protected]>
Signed-off-by: Pavel Begunkov <[email protected]>
---
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 | 8 ++++++--
net/core/skbuff.c | 16 ++++++++++------
9 files changed, 46 insertions(+), 27 deletions(-)
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 48254fc07d64..5836995d6774 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1157,7 +1157,7 @@ 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. */
@@ -1279,8 +1279,9 @@ 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;
@@ -1313,6 +1314,10 @@ 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 4072a7ee3859..a44954264746 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;
};
@@ -1671,14 +1675,13 @@ 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);
@@ -1766,13 +1769,13 @@ 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);
@@ -1786,7 +1789,7 @@ 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 3485437b207d..53532d78a947 100644
--- a/io_uring/notif.c
+++ b/io_uring/notif.c
@@ -23,7 +23,7 @@ void io_notif_tw_complete(struct io_kiocb *notif, struct io_tw_state *ts)
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);
@@ -43,6 +43,10 @@ static void io_tx_ubuf_callback(struct sk_buff *skb, struct ubuf_info *uarg,
__io_req_task_work_add(notif, IOU_F_TWQ_LAZY_WAKE);
}
+static const struct ubuf_info_ops io_ubuf_ops = {
+ .complete = io_tx_ubuf_complete,
+};
+
struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
@@ -62,7 +66,7 @@ struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx)
nd->zc_report = false;
nd->account_pages = 0;
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 37c858dc11a6..0f4cc759824b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1652,7 +1652,7 @@ 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;
@@ -1678,7 +1678,7 @@ 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),
@@ -1789,8 +1789,8 @@ static void __msg_zerocopy_callback(struct ubuf_info_msgzc *uarg)
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);
@@ -1799,7 +1799,6 @@ 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)
{
@@ -1809,10 +1808,15 @@ 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)
--
2.44.0
next prev parent reply other threads:[~2024-04-19 11:08 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-19 11:08 [PATCH io_uring-next/net-next v2 0/4] implement io_uring notification (ubuf_info) stacking Pavel Begunkov
2024-04-19 11:08 ` Pavel Begunkov [this message]
2024-04-22 16:59 ` [PATCH io_uring-next/net-next v2 1/4] net: extend ubuf_info callback to ops structure Willem de Bruijn
2024-04-19 11:08 ` [PATCH io_uring-next/net-next v2 2/4] net: add callback for setting a ubuf_info to skb Pavel Begunkov
2024-04-22 17:01 ` Willem de Bruijn
2024-04-19 11:08 ` [PATCH io_uring-next/net-next v2 3/4] io_uring/notif: simplify io_notif_flush() Pavel Begunkov
2024-04-19 11:08 ` [PATCH io_uring-next/net-next v2 4/4] io_uring/notif: implement notification stacking Pavel Begunkov
2024-04-19 11:21 ` [PATCH io_uring-next/net-next v2 0/4] implement io_uring notification (ubuf_info) stacking Pavel Begunkov
2024-04-23 0:20 ` patchwork-bot+netdevbpf
2024-04-23 1:36 ` (subset) " Jens Axboe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=a62015541de49c0e2a8a0377a1d5d0a5aeb07016.1713369317.git.asml.silence@gmail.com \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox