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, 170 insertions, 0 deletions

diff --git a/include/net/strparser.h b/include/net/strparser.h
new file mode 100644
index 000000000..0ed73e364
--- /dev/null
+++ b/include/net/strparser.h
@@ -0,0 +1,170 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Stream Parser
+ *
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ */
+
+#ifndef __NET_STRPARSER_H_
+#define __NET_STRPARSER_H_
+
+#include <linux/skbuff.h>
+#include <net/sock.h>
+
+#define STRP_STATS_ADD(stat, count) ((stat) += (count))
+#define STRP_STATS_INCR(stat) ((stat)++)
+
+struct strp_stats {
+	unsigned long long msgs;
+	unsigned long long bytes;
+	unsigned int mem_fail;
+	unsigned int need_more_hdr;
+	unsigned int msg_too_big;
+	unsigned int msg_timeouts;
+	unsigned int bad_hdr_len;
+};
+
+struct strp_aggr_stats {
+	unsigned long long msgs;
+	unsigned long long bytes;
+	unsigned int mem_fail;
+	unsigned int need_more_hdr;
+	unsigned int msg_too_big;
+	unsigned int msg_timeouts;
+	unsigned int bad_hdr_len;
+	unsigned int aborts;
+	unsigned int interrupted;
+	unsigned int unrecov_intr;
+};
+
+struct strparser;
+
+/* Callbacks are called with lock held for the attached socket */
+struct strp_callbacks {
+	int (*parse_msg)(struct strparser *strp, struct sk_buff *skb);
+	void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb);
+	int (*read_sock)(struct strparser *strp, read_descriptor_t *desc,
+			 sk_read_actor_t recv_actor);
+	int (*read_sock_done)(struct strparser *strp, int err);
+	void (*abort_parser)(struct strparser *strp, int err);
+	void (*lock)(struct strparser *strp);
+	void (*unlock)(struct strparser *strp);
+};
+
+struct strp_msg {
+	int full_len;
+	int offset;
+};
+
+struct _strp_msg {
+	/* Internal cb structure. struct strp_msg must be first for passing
+	 * to upper layer.
+	 */
+	struct strp_msg strp;
+	int accum_len;
+};
+
+struct sk_skb_cb {
+#define SK_SKB_CB_PRIV_LEN 20
+	unsigned char data[SK_SKB_CB_PRIV_LEN];
+	/* align strp on cache line boundary within skb->cb[] */
+	unsigned char pad[4];
+	struct _strp_msg strp;
+
+	/* strp users' data follows */
+	struct tls_msg {
+		u8 control;
+	} tls;
+	/* temp_reg is a temporary register used for bpf_convert_data_end_access
+	 * when dst_reg == src_reg.
+	 */
+	u64 temp_reg;
+};
+
+static inline struct strp_msg *strp_msg(struct sk_buff *skb)
+{
+	return (struct strp_msg *)((void *)skb->cb +
+		offsetof(struct sk_skb_cb, strp));
+}
+
+/* Structure for an attached lower socket */
+struct strparser {
+	struct sock *sk;
+
+	u32 stopped : 1;
+	u32 paused : 1;
+	u32 aborted : 1;
+	u32 interrupted : 1;
+	u32 unrecov_intr : 1;
+
+	struct sk_buff **skb_nextp;
+	struct sk_buff *skb_head;
+	unsigned int need_bytes;
+	struct delayed_work msg_timer_work;
+	struct work_struct work;
+	struct strp_stats stats;
+	struct strp_callbacks cb;
+};
+
+/* Must be called with lock held for attached socket */
+static inline void strp_pause(struct strparser *strp)
+{
+	strp->paused = 1;
+}
+
+/* May be called without holding lock for attached socket */
+void strp_unpause(struct strparser *strp);
+
+static inline void save_strp_stats(struct strparser *strp,
+				   struct strp_aggr_stats *agg_stats)
+{
+	/* Save psock statistics in the mux when psock is being unattached. */
+
+#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat +=		\
+				 strp->stats._stat)
+	SAVE_PSOCK_STATS(msgs);
+	SAVE_PSOCK_STATS(bytes);
+	SAVE_PSOCK_STATS(mem_fail);
+	SAVE_PSOCK_STATS(need_more_hdr);
+	SAVE_PSOCK_STATS(msg_too_big);
+	SAVE_PSOCK_STATS(msg_timeouts);
+	SAVE_PSOCK_STATS(bad_hdr_len);
+#undef SAVE_PSOCK_STATS
+
+	if (strp->aborted)
+		agg_stats->aborts++;
+	if (strp->interrupted)
+		agg_stats->interrupted++;
+	if (strp->unrecov_intr)
+		agg_stats->unrecov_intr++;
+}
+
+static inline void aggregate_strp_stats(struct strp_aggr_stats *stats,
+					struct strp_aggr_stats *agg_stats)
+{
+#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat)
+	SAVE_PSOCK_STATS(msgs);
+	SAVE_PSOCK_STATS(bytes);
+	SAVE_PSOCK_STATS(mem_fail);
+	SAVE_PSOCK_STATS(need_more_hdr);
+	SAVE_PSOCK_STATS(msg_too_big);
+	SAVE_PSOCK_STATS(msg_timeouts);
+	SAVE_PSOCK_STATS(bad_hdr_len);
+	SAVE_PSOCK_STATS(aborts);
+	SAVE_PSOCK_STATS(interrupted);
+	SAVE_PSOCK_STATS(unrecov_intr);
+#undef SAVE_PSOCK_STATS
+
+}
+
+void strp_done(struct strparser *strp);
+void strp_stop(struct strparser *strp);
+void strp_check_rcv(struct strparser *strp);
+int strp_init(struct strparser *strp, struct sock *sk,
+	      const struct strp_callbacks *cb);
+void strp_data_ready(struct strparser *strp);
+int strp_process(struct strparser *strp, struct sk_buff *orig_skb,
+		 unsigned int orig_offset, size_t orig_len,
+		 size_t max_msg_size, long timeo);
+
+#endif /* __NET_STRPARSER_H_ */