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, 85 insertions, 0 deletions

diff --git a/include/net/ping.h b/include/net/ping.h
new file mode 100644
index 000000000..bcbdb5a13
--- /dev/null
+++ b/include/net/ping.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Definitions for the "ping" module.
+ */
+#ifndef _PING_H
+#define _PING_H
+
+#include <net/icmp.h>
+#include <net/netns/hash.h>
+
+/* PING_HTABLE_SIZE must be power of 2 */
+#define PING_HTABLE_SIZE 	64
+#define PING_HTABLE_MASK 	(PING_HTABLE_SIZE-1)
+
+#define GID_T_MAX (((gid_t)~0U) - 1)
+
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+struct pingv6_ops {
+	int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len);
+	void (*ip6_datagram_recv_common_ctl)(struct sock *sk,
+					     struct msghdr *msg,
+					     struct sk_buff *skb);
+	void (*ip6_datagram_recv_specific_ctl)(struct sock *sk,
+					       struct msghdr *msg,
+					       struct sk_buff *skb);
+	int (*icmpv6_err_convert)(u8 type, u8 code, int *err);
+	void (*ipv6_icmp_error)(struct sock *sk, struct sk_buff *skb, int err,
+				__be16 port, u32 info, u8 *payload);
+	int (*ipv6_chk_addr)(struct net *net, const struct in6_addr *addr,
+			     const struct net_device *dev, int strict);
+};
+
+struct ping_iter_state {
+	struct seq_net_private  p;
+	int			bucket;
+	sa_family_t		family;
+};
+
+extern struct proto ping_prot;
+#if IS_ENABLED(CONFIG_IPV6)
+extern struct pingv6_ops pingv6_ops;
+#endif
+
+struct pingfakehdr {
+	struct icmphdr icmph;
+	struct msghdr *msg;
+	sa_family_t family;
+	__wsum wcheck;
+};
+
+int  ping_get_port(struct sock *sk, unsigned short ident);
+void ping_unhash(struct sock *sk);
+
+int  ping_init_sock(struct sock *sk);
+void ping_close(struct sock *sk, long timeout);
+int  ping_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
+void ping_err(struct sk_buff *skb, int offset, u32 info);
+int  ping_getfrag(void *from, char *to, int offset, int fraglen, int odd,
+		  struct sk_buff *);
+
+int  ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		  int flags);
+int  ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+			 void *user_icmph, size_t icmph_len);
+int  ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+enum skb_drop_reason ping_rcv(struct sk_buff *skb);
+
+#ifdef CONFIG_PROC_FS
+void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family);
+void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+void ping_seq_stop(struct seq_file *seq, void *v);
+
+int __init ping_proc_init(void);
+void ping_proc_exit(void);
+#endif
+
+void __init ping_init(void);
+int  __init pingv6_init(void);
+void pingv6_exit(void);
+
+#endif /* _PING_H */