IORING_CQE_F_COPIED

[Stefan Metzmacher <metze@samba.org>]

Hi Pavel,

In the tests I made I used this version of IORING_CQE_F_COPIED:
https://git.samba.org/?p=metze/linux/wip.git;a=commitdiff;h=645d3b584c417a247d92d71baa6266a5f3d0d17d
(also inlined at the end)

Would that something we want for 6.1? (Should I post that with a useful commit message, after doing some more tests)

metze

  include/uapi/linux/io_uring.h | 1 +
  io_uring/notif.c              | 5 +++++
  net/ipv4/ip_output.c          | 3 ++-
  net/ipv4/tcp.c                | 2 ++
  net/ipv6/ip6_output.c         | 3 ++-
  5 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 04729989e6ee..efeab6a9b4f3 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -341,6 +341,7 @@ struct io_uring_cqe {
  #define IORING_CQE_F_MORE		(1U << 1)
  #define IORING_CQE_F_SOCK_NONEMPTY	(1U << 2)
  #define IORING_CQE_F_NOTIF		(1U << 3)
+#define IORING_CQE_F_COPIED		(1U << 4)

  enum {
  	IORING_CQE_BUFFER_SHIFT		= 16,
diff --git a/io_uring/notif.c b/io_uring/notif.c
index e37c6569d82e..2162d1af0b60 100644
--- a/io_uring/notif.c
+++ b/io_uring/notif.c
@@ -18,6 +18,8 @@ static void __io_notif_complete_tw(struct io_kiocb *notif, bool *locked)
  		__io_unaccount_mem(ctx->user, nd->account_pages);
  		nd->account_pages = 0;
  	}
+	if (!nd->uarg.zerocopy)
+		notif->cqe.flags |= IORING_CQE_F_COPIED;
  	io_req_task_complete(notif, locked);
  }

@@ -28,6 +30,8 @@ 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 (refcount_dec_and_test(&uarg->refcnt)) {
  		notif->io_task_work.func = __io_notif_complete_tw;
  		io_req_task_work_add(notif);
@@ -53,6 +57,7 @@ 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 04e2034f2f8e..64d263a8ece8 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 cdf26724d7db..d3a2ed9f22df 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1247,6 +1247,8 @@ 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 bb0f469a5247..3d75dd05ff98 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1559,7 +1559,8 @@ 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)