The 2nd cqe for IORING_OP_SEND_ZC has IORING_CQE_F_NOTIF set in cqe->flags
and it will now have the number of successful completed
io_uring_tx_zerocopy_callback() callbacks in the lower 31-bits
of cqe->res, the high bit (0x80000000) is set when
io_uring_tx_zerocopy_callback() was called with success=false.
If cqe->res is still 0, zero copy wasn't used at all.
These values give userspace a change to adjust its strategy
choosing IORING_OP_SEND_ZC or IORING_OP_SEND. And it's a bit
richer than just a simple SO_EE_CODE_ZEROCOPY_COPIED indication.
Fixes: b48c312be05e8 ("io_uring/net: simplify zerocopy send user API")
Fixes: eb315a7d1396b ("tcp: support externally provided ubufs")
Fixes: 1fd3ae8c906c0 ("ipv6/udp: support externally provided ubufs")
Fixes: c445f31b3cfaa ("ipv4/udp: support externally provided ubufs")
Signed-off-by: Stefan Metzmacher <metze@xxxxxxxxx>
Cc: Pavel Begunkov <asml.silence@xxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: io-uring@xxxxxxxxxxxxxxx
Cc: Jakub Kicinski <kuba@xxxxxxxxxx>
Cc: netdev@xxxxxxxxxxxxxxx
---
io_uring/notif.c | 18 ++++++++++++++++++
net/ipv4/ip_output.c | 3 ++-
net/ipv4/tcp.c | 2 ++
net/ipv6/ip6_output.c | 3 ++-
4 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/io_uring/notif.c b/io_uring/notif.c
index e37c6569d82e..b07d2a049931 100644
--- a/io_uring/notif.c
+++ b/io_uring/notif.c
@@ -28,7 +28,24 @@ static void io_uring_tx_zerocopy_callback(struct sk_buff *skb,
struct io_notif_data *nd = container_of(uarg, struct io_notif_data, uarg);
struct io_kiocb *notif = cmd_to_io_kiocb(nd);
+ uarg->zerocopy = uarg->zerocopy & success;
+
+ if (success && notif->cqe.res < S32_MAX)
+ notif->cqe.res++;
+
if (refcount_dec_and_test(&uarg->refcnt)) {
+ /*
+ * If we hit at least one case that
+ * was not able to use zero copy,
+ * we set the high bit 0x80000000
+ * so that notif->cqe.res < 0, means it was
+ * as least copied once.
+ *
+ * The other 31 bits are the success count.
+ */
+ if (!uarg->zerocopy)
+ notif->cqe.res |= S32_MIN;
+
notif->io_task_work.func = __io_notif_complete_tw;
io_req_task_work_add(notif);
}
@@ -53,6 +70,7 @@ struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx)
nd = io_notif_to_data(notif);
nd->account_pages = 0;
+ nd->uarg.zerocopy = 1;
nd->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN;
nd->uarg.callback = io_uring_tx_zerocopy_callback;
refcount_set(&nd->uarg.refcnt, 1);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d7bd1daf022b..4bdea7a4b2f7 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1032,7 +1032,8 @@ static int __ip_append_data(struct sock *sk,
paged = true;
zc = true;
uarg = msg->msg_ubuf;
- }
+ } else
+ msg->msg_ubuf->zerocopy = 0;
} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
if (!uarg)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 970e9a2cca4a..27a22d470741 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1231,6 +1231,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
uarg = msg->msg_ubuf;
net_zcopy_get(uarg);
zc = sk->sk_route_caps & NETIF_F_SG;
+ if (!zc)
+ uarg->zerocopy = 0;
} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb));
if (!uarg) {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f152e51242cb..d85036e91cf7 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1556,7 +1556,8 @@ static int __ip6_append_data(struct sock *sk,
paged = true;
zc = true;
uarg = msg->msg_ubuf;
- }
+ } else
+ msg->msg_ubuf->zerocopy = 0;
} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
if (!uarg)
--
2.34.1
