netfs: zero the tail of a short DIO/unbuffered readgrafted

The buffered read collector zero-fills the tail of a short read that
stops below the inode's i_size (netfs_clear_unread()), so a read that
races an extending write still returns the expected number of bytes.
The non-buffered collector path does no such thing: it just records
how much was transferred.

Add the same zero-fill for the non-buffered case, gated on
NETFS_SREQ_CLEAR_TAIL: a subreq's source sets that flag when a short
result from it is known to be safe to treat as a hole, as opposed to
NETFS_SREQ_HIT_EOF, which means the read genuinely ran off the end of
the file and should be reported short as-is. Only CLEAR_TAIL should
zero-fill here; a real EOF must stay a real short read.

No source currently sets CLEAR_TAIL on an unbuffered/DIO subrequest,
so this is inert on its own -- a following change teaches cifs to set
it in the one case that needs it.

Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item")
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Paulo Alcantara <pc@manguebit.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Cc: Shyam Prasad N <sprasad@microsoft.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: Bharath SM <bharathsm@microsoft.com>
Cc: stable@vger.kernel.org

1 files changed, 82 insertions, 0 deletions

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
new file mode 100644
index 000000000..3d747896b
--- /dev/null
+++ b/include/net/inet_common.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _INET_COMMON_H
+#define _INET_COMMON_H
+
+#include <linux/indirect_call_wrapper.h>
+#include <linux/net.h>
+#include <linux/netdev_features.h>
+#include <linux/types.h>
+#include <net/sock.h>
+
+extern const struct proto_ops inet_stream_ops;
+extern const struct proto_ops inet_dgram_ops;
+
+/*
+ *	INET4 prototypes used by INET6
+ */
+
+struct msghdr;
+struct net;
+struct page;
+struct sock;
+struct socket;
+
+int inet_release(struct socket *sock);
+int inet_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr,
+			int addr_len, int flags);
+int __inet_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr,
+			  int addr_len, int flags, int is_sendmsg);
+int inet_dgram_connect(struct socket *sock, struct sockaddr_unsized *uaddr,
+		       int addr_len, int flags);
+int inet_accept(struct socket *sock, struct socket *newsock,
+		struct proto_accept_arg *arg);
+void __inet_accept(struct socket *sock, struct socket *newsock,
+		   struct sock *newsk);
+int inet_send_prepare(struct sock *sk);
+int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
+void inet_splice_eof(struct socket *sock);
+int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		 int flags);
+int inet_shutdown(struct socket *sock, int how);
+int inet_listen(struct socket *sock, int backlog);
+int __inet_listen_sk(struct sock *sk, int backlog);
+void inet_sock_destruct(struct sock *sk);
+int inet_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len);
+int inet_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
+/* Don't allocate port at this moment, defer to connect. */
+#define BIND_FORCE_ADDRESS_NO_PORT	(1 << 0)
+/* Grab and release socket lock. */
+#define BIND_WITH_LOCK			(1 << 1)
+/* Called from BPF program. */
+#define BIND_FROM_BPF			(1 << 2)
+/* Skip CAP_NET_BIND_SERVICE check. */
+#define BIND_NO_CAP_NET_BIND_SERVICE	(1 << 3)
+int __inet_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len,
+		u32 flags);
+int inet_getname(struct socket *sock, struct sockaddr *uaddr,
+		 int peer);
+int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+int inet_ctl_sock_create(struct sock **sk, unsigned short family,
+			 unsigned short type, unsigned char protocol,
+			 struct net *net);
+int inet_recv_error(struct sock *sk, struct msghdr *msg, int len);
+
+struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb);
+int inet_gro_complete(struct sk_buff *skb, int nhoff);
+struct sk_buff *inet_gso_segment(struct sk_buff *skb,
+				 netdev_features_t features);
+
+static inline void inet_ctl_sock_destroy(struct sock *sk)
+{
+	if (sk)
+		sock_release(sk->sk_socket);
+}
+
+#define indirect_call_gro_receive(f2, f1, cb, head, skb)	\
+({								\
+	unlikely(gro_recursion_inc_test(skb)) ?			\
+		NAPI_GRO_CB(skb)->flush |= 1, NULL :		\
+		INDIRECT_CALL_2(cb, f2, f1, head, skb);		\
+})
+
+#endif