[v2,33/40] afs: Apply server breaks to mmap'd files in the call processor

Message ID	20231213135003.367397-34-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="DGOuX8Ms" 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 33/40] afs: Apply server breaks to mmap'd files in the call processor Date: Wed, 13 Dec 2023 13:49:55 +0000 Message-ID: <20231213135003.367397-34-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/callback.c b/fs/afs/callback.c index 90f9b2a46ff4..f67e88076761 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -33,9 +33,8 @@ void afs_invalidate_mmap_work(struct work_struct *work) unmap_mapping_pages(vnode->netfs.inode.i_mapping, 0, 0, false); } -void afs_server_init_callback_work(struct work_struct *work) +static void afs_server_init_callback(struct afs_server *server) { - struct afs_server *server = container_of(work, struct afs_server, initcb_work); struct afs_vnode *vnode; struct afs_cell *cell = server->cell; @@ -57,15 +56,19 @@ void afs_server_init_callback_work(struct work_struct *work) */ void afs_init_callback_state(struct afs_server *server) { - rcu_read_lock(); + struct afs_cell *cell = server->cell; + + down_read(&cell->vs_lock); + do { server->cb_s_break++; atomic_inc(&server->cell->fs_s_break); if (!list_empty(&server->cell->fs_open_mmaps)) - queue_work(system_unbound_wq, &server->initcb_work); + afs_server_init_callback(server); } while ((server = rcu_dereference(server->uuid_next))); - rcu_read_unlock(); + + up_read(&cell->vs_lock); } /* @@ -112,7 +115,7 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell, struct rb_node *p; int seq = 1; - do { + for (;;) { /* Unfortunately, rbtree walking doesn't give reliable results * under just the RCU read lock, so we have to check for * changes. @@ -133,7 +136,12 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell, volume = NULL; } - } while (need_seqretry(&cell->volume_lock, seq)); + if (volume && afs_try_get_volume(volume, afs_volume_trace_get_callback)) + break; + if (!need_seqretry(&cell->volume_lock, seq)) + break; + seq |= 1; /* Want a lock next time */ + } done_seqretry(&cell->volume_lock, seq); return volume; @@ -188,12 +196,11 @@ static void afs_break_some_callbacks(struct afs_server *server, afs_volid_t vid = cbb->fid.vid; size_t i; + rcu_read_lock(); volume = afs_lookup_volume_rcu(server->cell, vid); - /* TODO: Find all matching volumes if we couldn't match the server and * break them anyway. */ - for (i = *_count; i > 0; cbb++, i--) { if (cbb->fid.vid == vid) { _debug("- Fid { vl=%08llx n=%llu u=%u }", @@ -207,6 +214,9 @@ static void afs_break_some_callbacks(struct afs_server *server, *residue++ = *cbb; } } + + rcu_read_unlock(); + afs_put_volume(volume, afs_volume_trace_put_callback); } /* @@ -219,11 +229,6 @@ void afs_break_callbacks(struct afs_server *server, size_t count, ASSERT(server != NULL); - rcu_read_lock(); - while (count > 0) afs_break_some_callbacks(server, callbacks, &count); - - rcu_read_unlock(); - return; } diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 6b389f2bcd0c..1e5cb0f6ee07 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -161,7 +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); + init_rwsem(&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 4a3d946b1d2a..5ae4ca999d65 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -414,7 +414,7 @@ struct afs_cell { unsigned int debug_id; /* The volumes belonging to this cell */ - spinlock_t vs_lock; /* Lock for server->volumes */ + struct rw_semaphore 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 */ @@ -566,7 +566,6 @@ struct afs_server { 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 */ unsigned long flags; @@ -1041,7 +1040,6 @@ void afs_get_address_preferences(struct afs_net *net, struct afs_addr_list *alis * callback.c */ extern void afs_invalidate_mmap_work(struct work_struct *); -extern void afs_server_init_callback_work(struct work_struct *work); extern void afs_init_callback_state(struct afs_server *); extern void __afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); extern void afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); diff --git a/fs/afs/server.c b/fs/afs/server.c index db2f66b11b40..e169121f603e 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -218,7 +218,6 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell, 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); spin_lock_init(&server->probe_lock); @@ -470,7 +469,6 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server) if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags)) afs_give_up_callbacks(net, server); - flush_work(&server->initcb_work); afs_put_server(net, server, afs_server_trace_destroy); } diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index 4d6369477f54..cfd900eb09ed 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -136,7 +136,7 @@ void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_l struct list_head *p; unsigned int i; - spin_lock(&volume->cell->vs_lock); + down_write(&volume->cell->vs_lock); for (i = 0; i < slist->nr_servers; i++) { se = &slist->servers[i]; @@ -147,11 +147,11 @@ void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_l if (volume->vid <= pe->volume->vid) break; } - list_add_tail_rcu(&se->slink, p); + list_add_tail(&se->slink, p); } slist->attached = true; - spin_unlock(&volume->cell->vs_lock); + up_write(&volume->cell->vs_lock); } /* @@ -164,7 +164,7 @@ void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server { unsigned int n = 0, o = 0; - spin_lock(&volume->cell->vs_lock); + down_write(&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; @@ -174,7 +174,7 @@ void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server int diff; if (pn && po && pn->server == po->server) { - list_replace_rcu(&po->slink, &pn->slink); + list_replace(&po->slink, &pn->slink); n++; o++; continue; @@ -192,15 +192,15 @@ void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server if (volume->vid <= s->volume->vid) break; } - list_add_tail_rcu(&pn->slink, p); + list_add_tail(&pn->slink, p); n++; } else { - list_del_rcu(&po->slink); + list_del(&po->slink); o++; } } - spin_unlock(&volume->cell->vs_lock); + up_write(&volume->cell->vs_lock); } /* @@ -213,11 +213,11 @@ void afs_detach_volume_from_servers(struct afs_volume *volume, struct afs_server if (!slist->attached) return; - spin_lock(&volume->cell->vs_lock); + down_write(&volume->cell->vs_lock); for (i = 0; i < slist->nr_servers; i++) - list_del_rcu(&slist->servers[i].slink); + list_del(&slist->servers[i].slink); slist->attached = false; - spin_unlock(&volume->cell->vs_lock); + up_write(&volume->cell->vs_lock); } diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index cf2fa4fddd5b..63ab23876be8 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -151,9 +151,11 @@ enum yfs_cm_operation { EM(afs_volume_trace_alloc, "ALLOC ") \ EM(afs_volume_trace_free, "FREE ") \ EM(afs_volume_trace_get_alloc_sbi, "GET sbi-alloc ") \ + EM(afs_volume_trace_get_callback, "GET callback ") \ EM(afs_volume_trace_get_cell_insert, "GET cell-insrt") \ EM(afs_volume_trace_get_new_op, "GET op-new ") \ EM(afs_volume_trace_get_query_alias, "GET cell-alias") \ + EM(afs_volume_trace_put_callback, "PUT callback ") \ EM(afs_volume_trace_put_cell_dup, "PUT cell-dup ") \ EM(afs_volume_trace_put_cell_root, "PUT cell-root ") \ EM(afs_volume_trace_put_destroy_sbi, "PUT sbi-destry") \

[v2,33/40] afs: Apply server breaks to mmap'd files in the call processor

Commit Message

Patch