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, 74 insertions, 0 deletions

diff --git a/drivers/md/dm-pcache/segment.h b/drivers/md/dm-pcache/segment.h
new file mode 100644
index 000000000..deca1ddcb
--- /dev/null
+++ b/drivers/md/dm-pcache/segment.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _PCACHE_SEGMENT_H
+#define _PCACHE_SEGMENT_H
+
+#include <linux/bio.h>
+#include <linux/bitfield.h>
+
+#include "pcache_internal.h"
+
+struct pcache_segment_info {
+	struct pcache_meta_header	header;
+	__u32			flags;
+	__u32			next_seg;
+};
+
+#define PCACHE_SEG_INFO_FLAGS_HAS_NEXT		BIT(0)
+
+#define PCACHE_SEG_INFO_FLAGS_TYPE_MASK         GENMASK(4, 1)
+#define PCACHE_SEGMENT_TYPE_CACHE_DATA		1
+
+static inline bool segment_info_has_next(struct pcache_segment_info *seg_info)
+{
+	return (seg_info->flags & PCACHE_SEG_INFO_FLAGS_HAS_NEXT);
+}
+
+static inline void segment_info_set_type(struct pcache_segment_info *seg_info, u8 type)
+{
+	seg_info->flags &= ~PCACHE_SEG_INFO_FLAGS_TYPE_MASK;
+	seg_info->flags |= FIELD_PREP(PCACHE_SEG_INFO_FLAGS_TYPE_MASK, type);
+}
+
+static inline u8 segment_info_get_type(struct pcache_segment_info *seg_info)
+{
+	return FIELD_GET(PCACHE_SEG_INFO_FLAGS_TYPE_MASK, seg_info->flags);
+}
+
+struct pcache_segment_pos {
+	struct pcache_segment	*segment;	/* Segment associated with the position */
+	u32			off;		/* Offset within the segment */
+};
+
+struct pcache_segment_init_options {
+	u8			type;
+	u32			seg_id;
+	u32			data_off;
+
+	struct pcache_segment_info	*seg_info;
+};
+
+struct pcache_segment {
+	struct pcache_cache_dev	*cache_dev;
+
+	void			*data;
+	u32			data_size;
+	u32			seg_id;
+
+	struct pcache_segment_info	*seg_info;
+};
+
+int segment_copy_to_bio(struct pcache_segment *segment,
+		      u32 data_off, u32 data_len, struct bio *bio, u32 bio_off);
+int segment_copy_from_bio(struct pcache_segment *segment,
+			u32 data_off, u32 data_len, struct bio *bio, u32 bio_off);
+
+static inline void segment_pos_advance(struct pcache_segment_pos *seg_pos, u32 len)
+{
+	BUG_ON(seg_pos->off + len > seg_pos->segment->data_size);
+
+	seg_pos->off += len;
+}
+
+void pcache_segment_init(struct pcache_cache_dev *cache_dev, struct pcache_segment *segment,
+		      struct pcache_segment_init_options *options);
+#endif /* _PCACHE_SEGMENT_H */