Merge tag 'afs-next-20171113' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

Pull AFS updates from David Howells:
 "kAFS filesystem driver overhaul.

  The major points of the overhaul are:

   (1) Preliminary groundwork is laid for supporting network-namespacing
       of kAFS. The remainder of the namespacing work requires some way
       to pass namespace information to submounts triggered by an
       automount. This requires something like the mount overhaul that's
       in progress.

   (2) sockaddr_rxrpc is used in preference to in_addr for holding
       addresses internally and add support for talking to the YFS VL
       server. With this, kAFS can do everything over IPv6 as well as
       IPv4 if it's talking to servers that support it.

   (3) Callback handling is overhauled to be generally passive rather
       than active. 'Callbacks' are promises by the server to tell us
       about data and metadata changes. Callbacks are now checked when
       we next touch an inode rather than actively going and looking for
       it where possible.

   (4) File access permit caching is overhauled to store the caching
       information per-inode rather than per-directory, shared over
       subordinate files. Whilst older AFS servers only allow ACLs on
       directories (shared to the files in that directory), newer AFS
       servers break that restriction.

       To improve memory usage and to make it easier to do mass-key
       removal, permit combinations are cached and shared.

   (5) Cell database management is overhauled to allow lighter locks to
       be used and to make cell records autonomous state machines that
       look after getting their own DNS records and cleaning themselves
       up, in particular preventing races in acquiring and relinquishing
       the fscache token for the cell.

   (6) Volume caching is overhauled. The afs_vlocation record is got rid
       of to simplify things and the superblock is now keyed on the cell
       and the numeric volume ID only. The volume record is tied to a
       superblock and normal superblock management is used to mediate
       the lifetime of the volume fscache token.

   (7) File server record caching is overhauled to make server records
       independent of cells and volumes. A server can be in multiple
       cells (in such a case, the administrator must make sure that the
       VL services for all cells correctly reflect the volumes shared
       between those cells).

       Server records are now indexed using the UUID of the server
       rather than the address since a server can have multiple
       addresses.

   (8) File server rotation is overhauled to handle VMOVED, VBUSY (and
       similar), VOFFLINE and VNOVOL indications and to handle rotation
       both of servers and addresses of those servers. The rotation will
       also wait and retry if the server says it is busy.

   (9) Data writeback is overhauled. Each inode no longer stores a list
       of modified sections tagged with the key that authorised it in
       favour of noting the modified region of a page in page->private
       and storing a list of keys that made modifications in the inode.

       This simplifies things and allows other keys to be used to
       actually write to the server if a key that made a modification
       becomes useless.

  (10) Writable mmap() is implemented. This allows a kernel to be build
       entirely on AFS.

  Note that Pre AFS-3.4 servers are no longer supported, though this can
  be added back if necessary (AFS-3.4 was released in 1998)"

* tag 'afs-next-20171113' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs: (35 commits)
  afs: Protect call->state changes against signals
  afs: Trace page dirty/clean
  afs: Implement shared-writeable mmap
  afs: Get rid of the afs_writeback record
  afs: Introduce a file-private data record
  afs: Use a dynamic port if 7001 is in use
  afs: Fix directory read/modify race
  afs: Trace the sending of pages
  afs: Trace the initiation and completion of client calls
  afs: Fix documentation on # vs % prefix in mount source specification
  afs: Fix total-length calculation for multiple-page send
  afs: Only progress call state at end of Tx phase from rxrpc callback
  afs: Make use of the YFS service upgrade to fully support IPv6
  afs: Overhaul volume and server record caching and fileserver rotation
  afs: Move server rotation code into its own file
  afs: Add an address list concept
  afs: Overhaul cell database management
  afs: Overhaul permit caching
  afs: Overhaul the callback handling
  afs: Rename struct afs_call server member to cm_server
  ...

1 files changed, 43 insertions, 196 deletions

diff --git a/fs/afs/cache.c b/fs/afs/cache.c
index 1fe855191261..f62ff71d28c9 100644
--- a/fs/afs/cache.c
+++ b/fs/afs/cache.c
@@ -14,19 +14,6 @@
 
 static uint16_t afs_cell_cache_get_key(const void *cookie_netfs_data,
 				       void *buffer, uint16_t buflen);
-static uint16_t afs_cell_cache_get_aux(const void *cookie_netfs_data,
-				       void *buffer, uint16_t buflen);
-static enum fscache_checkaux afs_cell_cache_check_aux(void *cookie_netfs_data,
-						      const void *buffer,
-						      uint16_t buflen);
-
-static uint16_t afs_vlocation_cache_get_key(const void *cookie_netfs_data,
-					    void *buffer, uint16_t buflen);
-static uint16_t afs_vlocation_cache_get_aux(const void *cookie_netfs_data,
-					    void *buffer, uint16_t buflen);
-static enum fscache_checkaux afs_vlocation_cache_check_aux(
-	void *cookie_netfs_data, const void *buffer, uint16_t buflen);
-
 static uint16_t afs_volume_cache_get_key(const void *cookie_netfs_data,
 					 void *buffer, uint16_t buflen);
 
@@ -42,23 +29,13 @@ static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
 
 struct fscache_netfs afs_cache_netfs = {
 	.name			= "afs",
-	.version		= 0,
+	.version		= 1,
 };
 
 struct fscache_cookie_def afs_cell_cache_index_def = {
 	.name		= "AFS.cell",
 	.type		= FSCACHE_COOKIE_TYPE_INDEX,
 	.get_key	= afs_cell_cache_get_key,
-	.get_aux	= afs_cell_cache_get_aux,
-	.check_aux	= afs_cell_cache_check_aux,
-};
-
-struct fscache_cookie_def afs_vlocation_cache_index_def = {
-	.name			= "AFS.vldb",
-	.type			= FSCACHE_COOKIE_TYPE_INDEX,
-	.get_key		= afs_vlocation_cache_get_key,
-	.get_aux		= afs_vlocation_cache_get_aux,
-	.check_aux		= afs_vlocation_cache_check_aux,
 };
 
 struct fscache_cookie_def afs_volume_cache_index_def = {
@@ -95,150 +72,26 @@ static uint16_t afs_cell_cache_get_key(const void *cookie_netfs_data,
 	return klen;
 }
 
-/*
- * provide new auxiliary cache data
- */
-static uint16_t afs_cell_cache_get_aux(const void *cookie_netfs_data,
-				       void *buffer, uint16_t bufmax)
-{
-	const struct afs_cell *cell = cookie_netfs_data;
-	uint16_t dlen;
-
-	_enter("%p,%p,%u", cell, buffer, bufmax);
-
-	dlen = cell->vl_naddrs * sizeof(cell->vl_addrs[0]);
-	dlen = min(dlen, bufmax);
-	dlen &= ~(sizeof(cell->vl_addrs[0]) - 1);
-
-	memcpy(buffer, cell->vl_addrs, dlen);
-	return dlen;
-}
-
-/*
- * check that the auxiliary data indicates that the entry is still valid
- */
-static enum fscache_checkaux afs_cell_cache_check_aux(void *cookie_netfs_data,
-						      const void *buffer,
-						      uint16_t buflen)
-{
-	_leave(" = OKAY");
-	return FSCACHE_CHECKAUX_OKAY;
-}
-
-/*****************************************************************************/
-/*
- * set the key for the index entry
- */
-static uint16_t afs_vlocation_cache_get_key(const void *cookie_netfs_data,
-					    void *buffer, uint16_t bufmax)
-{
-	const struct afs_vlocation *vlocation = cookie_netfs_data;
-	uint16_t klen;
-
-	_enter("{%s},%p,%u", vlocation->vldb.name, buffer, bufmax);
-
-	klen = strnlen(vlocation->vldb.name, sizeof(vlocation->vldb.name));
-	if (klen > bufmax)
-		return 0;
-
-	memcpy(buffer, vlocation->vldb.name, klen);
-
-	_leave(" = %u", klen);
-	return klen;
-}
-
-/*
- * provide new auxiliary cache data
- */
-static uint16_t afs_vlocation_cache_get_aux(const void *cookie_netfs_data,
-					    void *buffer, uint16_t bufmax)
-{
-	const struct afs_vlocation *vlocation = cookie_netfs_data;
-	uint16_t dlen;
-
-	_enter("{%s},%p,%u", vlocation->vldb.name, buffer, bufmax);
-
-	dlen = sizeof(struct afs_cache_vlocation);
-	dlen -= offsetof(struct afs_cache_vlocation, nservers);
-	if (dlen > bufmax)
-		return 0;
-
-	memcpy(buffer, (uint8_t *)&vlocation->vldb.nservers, dlen);
-
-	_leave(" = %u", dlen);
-	return dlen;
-}
-
-/*
- * check that the auxiliary data indicates that the entry is still valid
- */
-static
-enum fscache_checkaux afs_vlocation_cache_check_aux(void *cookie_netfs_data,
-						    const void *buffer,
-						    uint16_t buflen)
-{
-	const struct afs_cache_vlocation *cvldb;
-	struct afs_vlocation *vlocation = cookie_netfs_data;
-	uint16_t dlen;
-
-	_enter("{%s},%p,%u", vlocation->vldb.name, buffer, buflen);
-
-	/* check the size of the data is what we're expecting */
-	dlen = sizeof(struct afs_cache_vlocation);
-	dlen -= offsetof(struct afs_cache_vlocation, nservers);
-	if (dlen != buflen)
-		return FSCACHE_CHECKAUX_OBSOLETE;
-
-	cvldb = container_of(buffer, struct afs_cache_vlocation, nservers);
-
-	/* if what's on disk is more valid than what's in memory, then use the
-	 * VL record from the cache */
-	if (!vlocation->valid || vlocation->vldb.rtime == cvldb->rtime) {
-		memcpy((uint8_t *)&vlocation->vldb.nservers, buffer, dlen);
-		vlocation->valid = 1;
-		_leave(" = SUCCESS [c->m]");
-		return FSCACHE_CHECKAUX_OKAY;
-	}
-
-	/* need to update the cache if the cached info differs */
-	if (memcmp(&vlocation->vldb, buffer, dlen) != 0) {
-		/* delete if the volume IDs for this name differ */
-		if (memcmp(&vlocation->vldb.vid, &cvldb->vid,
-			   sizeof(cvldb->vid)) != 0
-		    ) {
-			_leave(" = OBSOLETE");
-			return FSCACHE_CHECKAUX_OBSOLETE;
-		}
-
-		_leave(" = UPDATE");
-		return FSCACHE_CHECKAUX_NEEDS_UPDATE;
-	}
-
-	_leave(" = OKAY");
-	return FSCACHE_CHECKAUX_OKAY;
-}
-
 /*****************************************************************************/
 /*
  * set the key for the volume index entry
  */
 static uint16_t afs_volume_cache_get_key(const void *cookie_netfs_data,
-					void *buffer, uint16_t bufmax)
+					 void *buffer, uint16_t bufmax)
 {
 	const struct afs_volume *volume = cookie_netfs_data;
-	uint16_t klen;
+	struct {
+		u64 volid;
+	} __packed key;
 
 	_enter("{%u},%p,%u", volume->type, buffer, bufmax);
 
-	klen = sizeof(volume->type);
-	if (klen > bufmax)
+	if (bufmax < sizeof(key))
 		return 0;
 
-	memcpy(buffer, &volume->type, sizeof(volume->type));
-
-	_leave(" = %u", klen);
-	return klen;
-
+	key.volid = volume->vid;
+	memcpy(buffer, &key, sizeof(key));
+	return sizeof(key);
 }
 
 /*****************************************************************************/
@@ -249,20 +102,25 @@ static uint16_t afs_vnode_cache_get_key(const void *cookie_netfs_data,
 					void *buffer, uint16_t bufmax)
 {
 	const struct afs_vnode *vnode = cookie_netfs_data;
-	uint16_t klen;
+	struct {
+		u32 vnode_id[3];
+	} __packed key;
 
 	_enter("{%x,%x,%llx},%p,%u",
 	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version,
 	       buffer, bufmax);
 
-	klen = sizeof(vnode->fid.vnode);
-	if (klen > bufmax)
-		return 0;
+	/* Allow for a 96-bit key */
+	memset(&key, 0, sizeof(key));
+	key.vnode_id[0] = vnode->fid.vnode;
+	key.vnode_id[1] = 0;
+	key.vnode_id[2] = 0;
 
-	memcpy(buffer, &vnode->fid.vnode, sizeof(vnode->fid.vnode));
+	if (sizeof(key) > bufmax)
+		return 0;
 
-	_leave(" = %u", klen);
-	return klen;
+	memcpy(buffer, &key, sizeof(key));
+	return sizeof(key);
 }
 
 /*
@@ -280,6 +138,11 @@ static void afs_vnode_cache_get_attr(const void *cookie_netfs_data,
 	*size = vnode->status.size;
 }
 
+struct afs_vnode_cache_aux {
+	u64 data_version;
+	u32 fid_unique;
+} __packed;
+
 /*
  * provide new auxiliary cache data
  */
@@ -287,23 +150,21 @@ static uint16_t afs_vnode_cache_get_aux(const void *cookie_netfs_data,
 					void *buffer, uint16_t bufmax)
 {
 	const struct afs_vnode *vnode = cookie_netfs_data;
-	uint16_t dlen;
+	struct afs_vnode_cache_aux aux;
 
 	_enter("{%x,%x,%Lx},%p,%u",
 	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version,
 	       buffer, bufmax);
 
-	dlen = sizeof(vnode->fid.unique) + sizeof(vnode->status.data_version);
-	if (dlen > bufmax)
-		return 0;
+	memset(&aux, 0, sizeof(aux));
+	aux.data_version = vnode->status.data_version;
+	aux.fid_unique = vnode->fid.unique;
 
-	memcpy(buffer, &vnode->fid.unique, sizeof(vnode->fid.unique));
-	buffer += sizeof(vnode->fid.unique);
-	memcpy(buffer, &vnode->status.data_version,
-	       sizeof(vnode->status.data_version));
+	if (bufmax < sizeof(aux))
+		return 0;
 
-	_leave(" = %u", dlen);
-	return dlen;
+	memcpy(buffer, &aux, sizeof(aux));
+	return sizeof(aux);
 }
 
 /*
@@ -314,43 +175,29 @@ static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
 						       uint16_t buflen)
 {
 	struct afs_vnode *vnode = cookie_netfs_data;
-	uint16_t dlen;
+	struct afs_vnode_cache_aux aux;
 
 	_enter("{%x,%x,%llx},%p,%u",
 	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version,
 	       buffer, buflen);
 
+	memcpy(&aux, buffer, sizeof(aux));
+
 	/* check the size of the data is what we're expecting */
-	dlen = sizeof(vnode->fid.unique) + sizeof(vnode->status.data_version);
-	if (dlen != buflen) {
-		_leave(" = OBSOLETE [len %hx != %hx]", dlen, buflen);
+	if (buflen != sizeof(aux)) {
+		_leave(" = OBSOLETE [len %hx != %zx]", buflen, sizeof(aux));
 		return FSCACHE_CHECKAUX_OBSOLETE;
 	}
 
-	if (memcmp(buffer,
-		   &vnode->fid.unique,
-		   sizeof(vnode->fid.unique)
-		   ) != 0) {
-		unsigned unique;
-
-		memcpy(&unique, buffer, sizeof(unique));
-
+	if (vnode->fid.unique != aux.fid_unique) {
 		_leave(" = OBSOLETE [uniq %x != %x]",
-		       unique, vnode->fid.unique);
+		       aux.fid_unique, vnode->fid.unique);
 		return FSCACHE_CHECKAUX_OBSOLETE;
 	}
 
-	if (memcmp(buffer + sizeof(vnode->fid.unique),
-		   &vnode->status.data_version,
-		   sizeof(vnode->status.data_version)
-		   ) != 0) {
-		afs_dataversion_t version;
-
-		memcpy(&version, buffer + sizeof(vnode->fid.unique),
-		       sizeof(version));
-
+	if (vnode->status.data_version != aux.data_version) {
 		_leave(" = OBSOLETE [vers %llx != %llx]",
-		       version, vnode->status.data_version);
+		       aux.data_version, vnode->status.data_version);
 		return FSCACHE_CHECKAUX_OBSOLETE;
 	}