afs: Overhaul invalidation handling to better support RO volumes

Overhaul the third party-induced invalidation handling, making use of the
previously added volume-level event counters (cb_scrub and cb_ro_snapshot)
that are now being parsed out of the VolSync record returned by the
fileserver in many of its replies.

This allows better handling of RO (and Backup) volumes.  Since these are
snapshot of a RW volume that are updated atomically simultantanously across
all servers that host them, they only require a single callback promise for
the entire volume.  The currently upstream code assumes that RO volumes
operate in the same manner as RW volumes, and that each file has its own
individual callback - which means that it does a status fetch for *every*
file in a RO volume, whether or not the volume got "released" (volume
callback breaks can occur for other reasons too, such as the volumeserver
taking ownership of a volume from a fileserver).

To this end, make the following changes:

 (1) Change the meaning of the volume's cb_v_break counter so that it is
     now a hint that we need to issue a status fetch to work out the state
     of a volume.  cb_v_break is incremented by volume break callbacks and
     by server initialisation callbacks.

 (2) Add a second counter, cb_v_check, to the afs_volume struct such that
     if this differs from cb_v_break, we need to do a check.  When the
     check is complete, cb_v_check is advanced to what cb_v_break was at
     the start of the status fetch.

 (3) Move the list of mmap'd vnodes to the volume and trigger removal of
     PTEs that map to files on a volume break rather than on a server
     break.

 (4) When a server reinitialisation callback comes in, use the
     server-to-volume reverse mapping added in a preceding patch to iterate
     over all the volumes using that server and clear the volume callback
     promises for that server and the general volume promise as a whole to
     trigger reanalysis.

 (5) Replace the AFS_VNODE_CB_PROMISED flag with an AFS_NO_CB_PROMISE
     (TIME64_MIN) value in the cb_expires_at field, reducing the number of
     checks we need to make.

 (6) Change afs_check_validity() to quickly see if various event counters
     have been incremented or if the vnode or volume callback promise is
     due to expire/has expired without making any changes to the state.
     That is now left to afs_validate() as this may get more complicated in
     future as we may have to examine server records too.

 (7) Overhaul afs_validate() so that it does a single status fetch if we
     need to check the state of either the vnode or the volume - and do so
     under appropriate locking.  The function does the following steps:

     (A) If the vnode/volume is no longer seen as valid, then we take the
     vnode validation lock and, if the volume promise has expired, the
     volume check lock also.  The latter prevents redundant checks being
     made to find out if a new version of the volume got released.

     (B) If a previous RPC call found that the volsync changed unexpectedly
     or that a RO volume was updated, then we unmap all PTEs pointing to
     the file to stop mmap being used for access.

     (C) If the vnode is still seen to be of uncertain validity, then we
     perform an FS.FetchStatus RPC op to jointly update the volume status
     and the vnode status.  This assessment is done as part of parsing the
     reply:

	If the RO volume creation timestamp advances, cb_ro_snapshot is
	incremented; if either the creation or update timestamps changes in
	an unexpected way, the cb_scrub counter is incremented

	If the Data Version returned doesn't match the copy we have
	locally, then we ask for the pagecache to be zapped.  This takes
	care of handling RO update.

     (D) If cb_scrub differs between volume and vnode, the vnode's
     pagecache is zapped and the vnode's cb_scrub is updated unless the
     file is marked as having been deleted.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org

1 files changed, 17 insertions, 17 deletions

diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 4b730cbcf63e..6d0cd886b548 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -422,9 +422,6 @@ struct afs_cell {
 	/* Active fileserver interaction state. */
 	struct rb_root		fs_servers;	/* afs_server (by server UUID) */
 	seqlock_t		fs_lock;	/* For fs_servers  */
-	struct rw_semaphore	fs_open_mmaps_lock;
-	struct list_head	fs_open_mmaps;	/* List of vnodes that are mmapped */
-	atomic_t		fs_s_break;	/* Counter of CB.InitCallBackState messages */
 
 	/* VL server list. */
 	rwlock_t		vl_servers_lock; /* Lock on vl_servers */
@@ -591,9 +588,6 @@ struct afs_server {
 	/* file service access */
 	rwlock_t		fs_lock;	/* access lock */
 
-	/* callback promise management */
-	unsigned		cb_s_break;	/* Break-everything counter. */
-
 	/* Probe state */
 	struct afs_endpoint_state __rcu *endpoint_state; /* Latest endpoint/probe state */
 	unsigned long		probed_at;	/* Time last probe was dispatched (jiffies) */
@@ -615,6 +609,7 @@ struct afs_server_entry {
 	struct afs_server	*server;
 	struct afs_volume	*volume;
 	struct list_head	slink;		/* Link in server->volumes */
+	time64_t		cb_expires_at;	/* Time at which volume-level callback expires */
 	unsigned long		flags;
 #define AFS_SE_EXCLUDED		0		/* Set if server is to be excluded in rotation */
 };
@@ -668,10 +663,15 @@ struct afs_volume {
 	time64_t		update_time;	/* Volume update time (or TIME64_MIN) */
 
 	/* Callback management */
+	struct mutex		cb_check_lock;	/* Lock to control race to check after v_break */
+	time64_t		cb_expires_at;	/* Earliest volume callback expiry time */
 	atomic_t		cb_ro_snapshot;	/* RO volume update-from-snapshot counter */
 	atomic_t		cb_v_break;	/* Volume-break event counter. */
+	atomic_t		cb_v_check;	/* Volume-break has-been-checked counter. */
 	atomic_t		cb_scrub;	/* Scrub-all-data event counter. */
 	rwlock_t		cb_v_break_lock;
+	struct rw_semaphore	open_mmaps_lock;
+	struct list_head	open_mmaps;	/* List of vnodes that are mmapped */
 
 	afs_voltype_t		type;		/* type of volume */
 	char			type_force;	/* force volume type (suppress R/O -> R/W) */
@@ -710,7 +710,6 @@ struct afs_vnode {
 	spinlock_t		wb_lock;	/* lock for wb_keys */
 	spinlock_t		lock;		/* waitqueue/flags lock */
 	unsigned long		flags;
-#define AFS_VNODE_CB_PROMISED	0		/* Set if vnode has a callback promise */
 #define AFS_VNODE_UNSET		1		/* set if vnode attributes not yet set */
 #define AFS_VNODE_DIR_VALID	2		/* Set if dir contents are valid */
 #define AFS_VNODE_ZAP_DATA	3		/* set if vnode's data should be invalidated */
@@ -736,13 +735,14 @@ struct afs_vnode {
 	struct list_head	cb_mmap_link;	/* Link in cell->fs_open_mmaps */
 	void			*cb_server;	/* Server with callback/filelock */
 	atomic_t		cb_nr_mmap;	/* Number of mmaps */
-	unsigned int		cb_fs_s_break;	/* Mass server break counter (cell->fs_s_break) */
-	unsigned int		cb_s_break;	/* Mass break counter on ->server */
-	unsigned int		cb_v_break;	/* Mass break counter on ->volume */
+	unsigned int		cb_ro_snapshot;	/* RO volume release counter on ->volume */
+	unsigned int		cb_scrub;	/* Scrub counter on ->volume */
 	unsigned int		cb_break;	/* Break counter on vnode */
+	unsigned int		cb_v_check;	/* Break check counter on ->volume */
 	seqlock_t		cb_lock;	/* Lock for ->cb_server, ->status, ->cb_*break */
 
-	time64_t		cb_expires_at;	/* time at which callback expires */
+	atomic64_t		cb_expires_at;	/* time at which callback expires */
+#define AFS_NO_CB_PROMISE TIME64_MIN
 };
 
 static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode)
@@ -839,7 +839,7 @@ struct afs_vnode_param {
 	struct afs_fid		fid;		/* Fid to access */
 	struct afs_status_cb	scb;		/* Returned status and callback promise */
 	afs_dataversion_t	dv_before;	/* Data version before the call */
-	unsigned int		cb_break_before; /* cb_break + cb_s_break before the call */
+	unsigned int		cb_break_before; /* cb_break before the call */
 	u8			dv_delta;	/* Expected change in data version */
 	bool			put_vnode:1;	/* T if we have a ref on the vnode */
 	bool			need_io_lock:1;	/* T if we need the I/O lock on this */
@@ -875,7 +875,6 @@ struct afs_operation {
 	unsigned int		debug_id;
 
 	unsigned int		cb_v_break;	/* Volume break counter before op */
-	unsigned int		cb_s_break;	/* Server break counter before op */
 
 	union {
 		struct {
@@ -1066,13 +1065,15 @@ extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback
 
 static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
 {
-	return vnode->cb_break + vnode->cb_v_break;
+	return vnode->cb_break + vnode->cb_ro_snapshot + vnode->cb_scrub;
 }
 
 static inline bool afs_cb_is_broken(unsigned int cb_break,
 				    const struct afs_vnode *vnode)
 {
-	return cb_break != (vnode->cb_break + atomic_read(&vnode->volume->cb_v_break));
+	return cb_break != (vnode->cb_break +
+			    atomic_read(&vnode->volume->cb_ro_snapshot) +
+			    atomic_read(&vnode->volume->cb_scrub));
 }
 
 /*
@@ -1564,9 +1565,8 @@ extern void afs_fs_exit(void);
 /*
  * validation.c
  */
+bool afs_check_validity(const struct afs_vnode *vnode);
 int afs_update_volume_state(struct afs_operation *op);
-bool afs_check_validity(struct afs_vnode *vnode);
-bool afs_pagecache_valid(struct afs_vnode *vnode);
 int afs_validate(struct afs_vnode *vnode, struct key *key);
 
 /*