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, 73 insertions, 0 deletions

diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
new file mode 100644
index 000000000..3a9001a04
--- /dev/null
+++ b/include/net/dst_ops.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_DST_OPS_H
+#define _NET_DST_OPS_H
+#include <linux/types.h>
+#include <linux/percpu_counter.h>
+#include <linux/cache.h>
+
+struct dst_entry;
+struct kmem_cachep;
+struct net_device;
+struct sk_buff;
+struct sock;
+struct net;
+
+struct dst_ops {
+	unsigned short		family;
+	unsigned int		gc_thresh;
+
+	void			(*gc)(struct dst_ops *ops);
+	struct dst_entry *	(*check)(struct dst_entry *, __u32 cookie);
+	unsigned int		(*default_advmss)(const struct dst_entry *);
+	unsigned int		(*mtu)(const struct dst_entry *);
+	u32 *			(*cow_metrics)(struct dst_entry *, unsigned long);
+	void			(*destroy)(struct dst_entry *);
+	void			(*ifdown)(struct dst_entry *,
+					  struct net_device *dev);
+	void			(*negative_advice)(struct sock *sk, struct dst_entry *);
+	void			(*link_failure)(struct sk_buff *);
+	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
+					       struct sk_buff *skb, u32 mtu,
+					       bool confirm_neigh);
+	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
+					    struct sk_buff *skb);
+	int			(*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb);
+	struct neighbour *	(*neigh_lookup)(const struct dst_entry *dst,
+						struct sk_buff *skb,
+						const void *daddr);
+	void			(*confirm_neigh)(const struct dst_entry *dst,
+						 const void *daddr);
+
+	struct kmem_cache	*kmem_cachep;
+
+	struct percpu_counter	pcpuc_entries ____cacheline_aligned_in_smp;
+};
+
+static inline int dst_entries_get_fast(struct dst_ops *dst)
+{
+	return percpu_counter_read_positive(&dst->pcpuc_entries);
+}
+
+static inline int dst_entries_get_slow(struct dst_ops *dst)
+{
+	return percpu_counter_sum_positive(&dst->pcpuc_entries);
+}
+
+#define DST_PERCPU_COUNTER_BATCH 32
+static inline void dst_entries_add(struct dst_ops *dst, int val)
+{
+	percpu_counter_add_batch(&dst->pcpuc_entries, val,
+				 DST_PERCPU_COUNTER_BATCH);
+}
+
+static inline int dst_entries_init(struct dst_ops *dst)
+{
+	return percpu_counter_init(&dst->pcpuc_entries, 0, GFP_KERNEL);
+}
+
+static inline void dst_entries_destroy(struct dst_ops *dst)
+{
+	percpu_counter_destroy(&dst->pcpuc_entries);
+}
+
+#endif