[v2,30/40] afs: Make it possible to find the volumes that are using a server

Message ID	20231213135003.367397-31-dhowells@redhat.com (mailing list archive)
State	New
Headers	show Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="Jnonr231" From: David Howells <dhowells@redhat.com> To: Marc Dionne <marc.dionne@auristor.com> Cc: David Howells <dhowells@redhat.com>, linux-afs@lists.infradead.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH v2 30/40] afs: Make it possible to find the volumes that are using a server Date: Wed, 13 Dec 2023 13:49:52 +0000 Message-ID: <20231213135003.367397-31-dhowells@redhat.com> In-Reply-To: <20231213135003.367397-1-dhowells@redhat.com> References: <20231213135003.367397-1-dhowells@redhat.com> Precedence: bulk MIME-Version: 1.0 Content-Transfer-Encoding: 8bit
Series	afs: Fix probe handling, server rotation and RO volume callback handling \| expand [v2,00/40] afs: Fix probe handling, server rotation and RO volume callback handling [v2,01/40] afs: fix the usage of read_seqbegin_or_lock() in afs_lookup_volume_rcu() [v2,02/40] afs: fix the usage of read_seqbegin_or_lock() in afs_find_server*() [v2,03/40] afs: use read_seqbegin() in afs_check_validity() and afs_getattr() [v2,04/40] rxrpc_find_service_conn_rcu: fix the usage of read_seqbegin_or_lock() [v2,05/40] afs: Remove whitespace before most ')' from the trace header [v2,06/40] afs: Automatically generate trace tag enums [v2,07/40] afs: Add comments on abort handling [v2,08/40] afs: Turn the afs_addr_list address array into an array of structs [v2,09/40] rxrpc, afs: Allow afs to pin rxrpc_peer objects [v2,10/40] afs: Don't skip server addresses for which we didn't get an RTT reading [v2,11/40] afs: Rename addr_list::failed to probe_failed [v2,12/40] afs: Handle the VIO and UAEIO aborts explicitly [v2,13/40] afs: Use op->nr_iterations=-1 to indicate to begin fileserver iteration [v2,14/40] afs: Wrap most op->error accesses with inline funcs [v2,15/40] afs: Don't put afs_call in afs_wait_for_call_to_complete() [v2,16/40] afs: Simplify error handling [v2,17/40] afs: Add a tracepoint for struct afs_addr_list [v2,18/40] afs: Rename some fields [v2,19/40] afs: Use peer + service_id as call address [v2,20/40] afs: Fold the afs_addr_cursor struct in [v2,21/40] rxrpc: Create a procfile to display outstanding client conn bundles [v2,22/40] afs: Add some more info to /proc/net/afs/servers [v2,23/40] afs: Remove the unimplemented afs_cmp_addr_list() [v2,24/40] afs: Provide a way to configure address priorities [v2,25/40] afs: Mark address lists with configured priorities [v2,26/40] afs: Dispatch fileserver probes in priority order [v2,27/40] afs: Dispatch vlserver probes in priority order [v2,28/40] afs: Keep a record of the current fileserver endpoint state [v2,29/40] afs: Combine the endpoint state bools into a bitmask [v2,30/40] afs: Make it possible to find the volumes that are using a server [v2,31/40] afs: Defer volume record destruction to a workqueue [v2,32/40] afs: Move the vnode/volume validity checking code into its own file [v2,33/40] afs: Apply server breaks to mmap'd files in the call processor [v2,34/40] afs: Fix comment in afs_do_lookup() [v2,35/40] afs: Don't leave DONTUSE/NEWREPSITE servers out of server list [v2,36/40] afs: Parse the VolSync record in the reply of a number of RPC ops [v2,37/40] afs: Overhaul invalidation handling to better support RO volumes [v2,38/40] afs: Fix fileserver rotation [v2,39/40] afs: Fix offline and busy message emission [v2,40/40] afs: trace: Log afs_make_call(), including server address

diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 988c2ac7cece..69716fc0ee36 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -161,6 +161,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, refcount_set(&cell->ref, 1); atomic_set(&cell->active, 0); INIT_WORK(&cell->manager, afs_manage_cell_work); + spin_lock_init(&cell->vs_lock); cell->volumes = RB_ROOT; INIT_HLIST_HEAD(&cell->proc_volumes); seqlock_init(&cell->volume_lock); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 96c1074fe78d..0b726bd2cf8c 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -414,6 +414,7 @@ struct afs_cell { unsigned int debug_id; /* The volumes belonging to this cell */ + spinlock_t vs_lock; /* Lock for server->volumes */ struct rb_root volumes; /* Tree of volumes on this server */ struct hlist_head proc_volumes; /* procfs volume list */ seqlock_t volume_lock; /* For volumes */ @@ -564,6 +565,7 @@ struct afs_server { struct hlist_node addr4_link; /* Link in net->fs_addresses4 */ struct hlist_node addr6_link; /* Link in net->fs_addresses6 */ struct hlist_node proc_link; /* Link in net->fs_proc */ + struct list_head volumes; /* RCU list of afs_server_entry objects */ struct work_struct initcb_work; /* Work for CB.InitCallBackState* */ struct afs_server *gc_next; /* Next server in manager's list */ time64_t unuse_time; /* Time at which last unused */ @@ -605,12 +607,14 @@ struct afs_server { */ struct afs_server_entry { struct afs_server *server; + struct afs_volume *volume; + struct list_head slink; /* Link in server->volumes */ }; struct afs_server_list { struct rcu_head rcu; - afs_volid_t vids[AFS_MAXTYPES]; /* Volume IDs */ refcount_t usage; + bool attached; /* T if attached to servers */ unsigned char nr_servers; unsigned char preferred; /* Preferred server */ unsigned short vnovol_mask; /* Servers to be skipped due to VNOVOL */ @@ -623,10 +627,9 @@ struct afs_server_list { * Live AFS volume management. */ struct afs_volume { - union { - struct rcu_head rcu; - afs_volid_t vid; /* volume ID */ - }; + struct rcu_head rcu; + afs_volid_t vid; /* The volume ID of this volume */ + afs_volid_t vids[AFS_MAXTYPES]; /* All associated volume IDs */ refcount_t ref; time64_t update_at; /* Time at which to next update */ struct afs_cell *cell; /* Cell to which belongs (pins ref) */ @@ -1528,10 +1531,14 @@ static inline struct afs_server_list *afs_get_serverlist(struct afs_server_list } extern void afs_put_serverlist(struct afs_net *, struct afs_server_list *); -extern struct afs_server_list *afs_alloc_server_list(struct afs_cell *, struct key *, - struct afs_vldb_entry *, - u8); +struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume, + struct key *key, + struct afs_vldb_entry *vldb); extern bool afs_annotate_server_list(struct afs_server_list *, struct afs_server_list *); +void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist); +void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist, + struct afs_server_list *old); +void afs_detach_volume_from_servers(struct afs_volume *volume, struct afs_server_list *slist); /* * super.c diff --git a/fs/afs/server.c b/fs/afs/server.c index 281625c71aff..db2f66b11b40 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -217,6 +217,7 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell, server->addr_version = alist->version; server->uuid = *uuid; rwlock_init(&server->fs_lock); + INIT_LIST_HEAD(&server->volumes); INIT_WORK(&server->initcb_work, afs_server_init_callback_work); init_waitqueue_head(&server->probe_wq); INIT_LIST_HEAD(&server->probe_link); diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index b59896b1de0a..4d6369477f54 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -24,13 +24,13 @@ void afs_put_serverlist(struct afs_net *net, struct afs_server_list *slist) /* * Build a server list from a VLDB record. */ -struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, +struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume, struct key *key, - struct afs_vldb_entry *vldb, - u8 type_mask) + struct afs_vldb_entry *vldb) { struct afs_server_list *slist; struct afs_server *server; + unsigned int type_mask = 1 << volume->type; int ret = -ENOMEM, nr_servers = 0, i, j; for (i = 0; i < vldb->nr_servers; i++) @@ -44,15 +44,12 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, refcount_set(&slist->usage, 1); rwlock_init(&slist->lock); - for (i = 0; i < AFS_MAXTYPES; i++) - slist->vids[i] = vldb->vid[i]; - /* Make sure a records exists for each server in the list. */ for (i = 0; i < vldb->nr_servers; i++) { if (!(vldb->fs_mask[i] & type_mask)) continue; - server = afs_lookup_server(cell, key, &vldb->fs_server[i], + server = afs_lookup_server(volume->cell, key, &vldb->fs_server[i], vldb->addr_version[i]); if (IS_ERR(server)) { ret = PTR_ERR(server); @@ -70,7 +67,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, break; if (j < slist->nr_servers) { if (slist->servers[j].server == server) { - afs_put_server(cell->net, server, + afs_put_server(volume->cell->net, server, afs_server_trace_put_slist_isort); continue; } @@ -81,6 +78,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, } slist->servers[j].server = server; + slist->servers[j].volume = volume; slist->nr_servers++; } @@ -92,7 +90,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, return slist; error_2: - afs_put_serverlist(cell->net, slist); + afs_put_serverlist(volume->cell->net, slist); error: return ERR_PTR(ret); } @@ -127,3 +125,99 @@ bool afs_annotate_server_list(struct afs_server_list *new, return true; } + +/* + * Attach a volume to the servers it is going to use. + */ +void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *slist) +{ + struct afs_server_entry *se, *pe; + struct afs_server *server; + struct list_head *p; + unsigned int i; + + spin_lock(&volume->cell->vs_lock); + + for (i = 0; i < slist->nr_servers; i++) { + se = &slist->servers[i]; + server = se->server; + + list_for_each(p, &server->volumes) { + pe = list_entry(p, struct afs_server_entry, slink); + if (volume->vid <= pe->volume->vid) + break; + } + list_add_tail_rcu(&se->slink, p); + } + + slist->attached = true; + spin_unlock(&volume->cell->vs_lock); +} + +/* + * Reattach a volume to the servers it is going to use when server list is + * replaced. We try to switch the attachment points to avoid rewalking the + * lists. + */ +void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server_list *new, + struct afs_server_list *old) +{ + unsigned int n = 0, o = 0; + + spin_lock(&volume->cell->vs_lock); + + while (n < new->nr_servers || o < old->nr_servers) { + struct afs_server_entry *pn = n < new->nr_servers ? &new->servers[n] : NULL; + struct afs_server_entry *po = o < old->nr_servers ? &old->servers[o] : NULL; + struct afs_server_entry *s; + struct list_head *p; + int diff; + + if (pn && po && pn->server == po->server) { + list_replace_rcu(&po->slink, &pn->slink); + n++; + o++; + continue; + } + + if (pn && po) + diff = memcmp(&pn->server->uuid, &po->server->uuid, + sizeof(pn->server->uuid)); + else + diff = pn ? -1 : 1; + + if (diff < 0) { + list_for_each(p, &pn->server->volumes) { + s = list_entry(p, struct afs_server_entry, slink); + if (volume->vid <= s->volume->vid) + break; + } + list_add_tail_rcu(&pn->slink, p); + n++; + } else { + list_del_rcu(&po->slink); + o++; + } + } + + spin_unlock(&volume->cell->vs_lock); +} + +/* + * Detach a volume from the servers it has been using. + */ +void afs_detach_volume_from_servers(struct afs_volume *volume, struct afs_server_list *slist) +{ + unsigned int i; + + if (!slist->attached) + return; + + spin_lock(&volume->cell->vs_lock); + + for (i = 0; i < slist->nr_servers; i++) + list_del_rcu(&slist->servers[i].slink); + + slist->attached = false; + spin_unlock(&volume->cell->vs_lock); +} diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c index 43788d0c18e8..63e7ed324af9 100644 --- a/fs/afs/vl_alias.c +++ b/fs/afs/vl_alias.c @@ -77,7 +77,7 @@ static int afs_compare_volume_slists(const struct afs_volume *vol_a, lb = rcu_dereference(vol_b->servers); for (i = 0; i < AFS_MAXTYPES; i++) - if (la->vids[i] != lb->vids[i]) + if (vol_a->vids[i] != vol_b->vids[i]) return 0; while (a < la->nr_servers && b < lb->nr_servers) { diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 115c081a8e2c..aefb982dee9a 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -72,11 +72,11 @@ static void afs_remove_volume_from_cell(struct afs_volume *volume) */ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, struct afs_vldb_entry *vldb, - unsigned long type_mask) + struct afs_server_list **_slist) { struct afs_server_list *slist; struct afs_volume *volume; - int ret = -ENOMEM; + int ret = -ENOMEM, i; volume = kzalloc(sizeof(struct afs_volume), GFP_KERNEL); if (!volume) @@ -95,13 +95,16 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, rwlock_init(&volume->cb_v_break_lock); memcpy(volume->name, vldb->name, vldb->name_len + 1); - slist = afs_alloc_server_list(params->cell, params->key, vldb, type_mask); + for (i = 0; i < AFS_MAXTYPES; i++) + volume->vids[i] = vldb->vid[i]; + + slist = afs_alloc_server_list(volume, params->key, vldb); if (IS_ERR(slist)) { ret = PTR_ERR(slist); goto error_1; } - refcount_set(&slist->usage, 1); + *_slist = slist; rcu_assign_pointer(volume->servers, slist); trace_afs_volume(volume->vid, 1, afs_volume_trace_alloc); return volume; @@ -117,17 +120,19 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, * Look up or allocate a volume record. */ static struct afs_volume *afs_lookup_volume(struct afs_fs_context *params, - struct afs_vldb_entry *vldb, - unsigned long type_mask) + struct afs_vldb_entry *vldb) { + struct afs_server_list *slist; struct afs_volume *candidate, *volume; - candidate = afs_alloc_volume(params, vldb, type_mask); + candidate = afs_alloc_volume(params, vldb, &slist); if (IS_ERR(candidate)) return candidate; volume = afs_insert_volume_into_cell(params->cell, candidate); - if (volume != candidate) + if (volume == candidate) + afs_attach_volume_to_servers(volume, slist); + else afs_put_volume(params->net, candidate, afs_volume_trace_put_cell_dup); return volume; } @@ -208,8 +213,7 @@ struct afs_volume *afs_create_volume(struct afs_fs_context *params) goto error; } - type_mask = 1UL << params->type; - volume = afs_lookup_volume(params, vldb, type_mask); + volume = afs_lookup_volume(params, vldb); error: kfree(vldb); @@ -221,14 +225,17 @@ struct afs_volume *afs_create_volume(struct afs_fs_context *params) */ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume) { + struct afs_server_list *slist = rcu_access_pointer(volume->servers); + _enter("%p", volume); #ifdef CONFIG_AFS_FSCACHE ASSERTCMP(volume->cache, ==, NULL); #endif + afs_detach_volume_from_servers(volume, slist); afs_remove_volume_from_cell(volume); - afs_put_serverlist(net, rcu_access_pointer(volume->servers)); + afs_put_serverlist(net, slist); afs_put_cell(volume->cell, afs_cell_trace_put_vol); trace_afs_volume(volume->vid, refcount_read(&volume->ref), afs_volume_trace_free); @@ -362,8 +369,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) } /* See if the volume's server list got updated. */ - new = afs_alloc_server_list(volume->cell, key, - vldb, (1 << volume->type)); + new = afs_alloc_server_list(volume, key, vldb); if (IS_ERR(new)) { ret = PTR_ERR(new); goto error_vldb; @@ -384,9 +390,11 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) volume->update_at = ktime_get_real_seconds() + afs_volume_record_life; write_unlock(&volume->servers_lock); - ret = 0; + if (discard == old) + afs_reattach_volume_to_servers(volume, new, old); afs_put_serverlist(volume->cell->net, discard); + ret = 0; error_vldb: kfree(vldb); error:

[v2,30/40] afs: Make it possible to find the volumes that are using a server

Commit Message

Patch