From e0537c9f828dc9500e5ffc9211099c495b72f402 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Tue, 19 Nov 2024 13:43:22 -0800 Subject: SUNRPC: only put task on cl_tasks list after the RPC call slot is reserved. Under heavy write load, we've seen the cl_tasks list grows to millions of entries. Even though the list is extremely long, the system still runs fine until the user wants to get the information of all active RPC tasks by doing: When this happens, tasks_start acquires the cl_lock to walk the cl_tasks list, returning one entry at a time to the caller. The cl_lock is held until all tasks on this list have been processed. While the cl_lock is held, completed RPC tasks have to spin wait in rpc_task_release_client for the cl_lock. If there are millions of entries in the cl_tasks list it will take a long time before tasks_stop is called and the cl_lock is released. The spin wait tasks can use up all the available CPUs in the system, preventing other jobs to run, this causes the system to temporarily lock up. This patch fixes this problem by delaying inserting the RPC task on the cl_tasks list until the RPC call slot is reserved. This limits the length of the cl_tasks to the number of call slots available in the system. Signed-off-by: Dai Ngo Signed-off-by: Anna Schumaker --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 5321585c778f..fec976e58174 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -93,6 +93,7 @@ struct rpc_clnt { const struct cred *cl_cred; unsigned int cl_max_connect; /* max number of transports not to the same IP */ struct super_block *pipefs_sb; + atomic_t cl_task_count; }; /* -- cgit v1.2.3 From 3feec68563dda59517f83d19123aa287a1dfd068 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 15 Nov 2024 20:40:53 -0500 Subject: nfs/localio: add direct IO enablement with sync and async IO support This commit simply adds the required O_DIRECT plumbing. It doesn't address the fact that NFS doesn't ensure all writes are page aligned (nor device logical block size aligned as required by O_DIRECT). Because NFS will read-modify-write for IO that isn't aligned, LOCALIO will not use O_DIRECT semantics by default if/when an application requests the use of O_DIRECT. Allow the use of O_DIRECT semantics by: 1: Adding a flag to the nfs_pgio_header struct to allow the NFS O_DIRECT layer to signal that O_DIRECT was used by the application 2: Adding a 'localio_O_DIRECT_semantics' NFS module parameter that when enabled will cause LOCALIO to use O_DIRECT semantics (this may cause IO to fail if applications do not properly align their IO). This commit is derived from code developed by Weston Andros Adamson. Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 559273a0f16d..80766ff0a47c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1637,6 +1637,7 @@ enum { NFS_IOHDR_RESEND_PNFS, NFS_IOHDR_RESEND_MDS, NFS_IOHDR_UNSTABLE_WRITES, + NFS_IOHDR_ODIRECT, }; struct nfs_io_completion; -- cgit v1.2.3 From a61466315d7afca032342183a57e62d5e3a3157c Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 15 Nov 2024 20:40:54 -0500 Subject: nfsd: add nfsd_file_{get,put} to 'nfs_to' nfsd_localio_operations In later a commit LOCALIO must call both nfsd_file_get and nfsd_file_put to manage extra nfsd_file references. Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Acked-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/nfslocalio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index 9202f4b24343..ab6a2a53f505 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -56,6 +56,8 @@ struct nfsd_localio_operations { const struct nfs_fh *, const fmode_t); struct net *(*nfsd_file_put_local)(struct nfsd_file *); + struct nfsd_file *(*nfsd_file_get)(struct nfsd_file *); + void (*nfsd_file_put)(struct nfsd_file *); struct file *(*nfsd_file_file)(struct nfsd_file *); } ____cacheline_aligned; -- cgit v1.2.3 From b49f049a22227df701bfbca083d6cc859496e615 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 15 Nov 2024 20:40:55 -0500 Subject: nfs_common: rename functions that invalidate LOCALIO nfs_clients Rename nfs_uuid_invalidate_one_client to nfs_localio_disable_client. Rename nfs_uuid_invalidate_clients to nfs_localio_invalidate_clients. Signed-off-by: Mike Snitzer Reviewed-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/nfslocalio.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index ab6a2a53f505..a05d1043f2b0 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -37,8 +37,9 @@ bool nfs_uuid_begin(nfs_uuid_t *); void nfs_uuid_end(nfs_uuid_t *); void nfs_uuid_is_local(const uuid_t *, struct list_head *, struct net *, struct auth_domain *, struct module *); -void nfs_uuid_invalidate_clients(struct list_head *list); -void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid); + +void nfs_localio_disable_client(nfs_uuid_t *nfs_uuid); +void nfs_localio_invalidate_clients(struct list_head *list); /* localio needs to map filehandle -> struct nfsd_file */ extern struct nfsd_file * -- cgit v1.2.3 From 4ee7ba40007357a48447a8cbc667480acf9a006a Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 15 Nov 2024 20:40:56 -0500 Subject: nfs_common: move localio_lock to new lock member of nfs_uuid_t Remove cl_localio_lock from 'struct nfs_client' in favor of adding a lock to the nfs_uuid_t struct (which is embedded in each nfs_client). Push nfs_local_{enable,disable} implementation down to nfs_common. Those methods now call nfs_localio_{enable,disable}_client. This allows implementing nfs_localio_invalidate_clients in terms of nfs_localio_disable_client. Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 1 - include/linux/nfslocalio.h | 8 +++++++- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index b804346a9741..239d86ef166c 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -132,7 +132,6 @@ struct nfs_client { struct timespec64 cl_nfssvc_boot; seqlock_t cl_boot_lock; nfs_uuid_t cl_uuid; - spinlock_t cl_localio_lock; #endif /* CONFIG_NFS_LOCALIO */ }; diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index a05d1043f2b0..4d5583873f41 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -6,6 +6,7 @@ #ifndef __LINUX_NFSLOCALIO_H #define __LINUX_NFSLOCALIO_H + /* nfsd_file structure is purposely kept opaque to NFS client */ struct nfsd_file; @@ -19,6 +20,8 @@ struct nfsd_file; #include #include +struct nfs_client; + /* * Useful to allow a client to negotiate if localio * possible with its server. @@ -27,6 +30,8 @@ struct nfsd_file; */ typedef struct { uuid_t uuid; + /* sadly this struct is just over a cacheline, avoid bouncing */ + spinlock_t ____cacheline_aligned lock; struct list_head list; struct net __rcu *net; /* nfsd's network namespace */ struct auth_domain *dom; /* auth_domain for localio */ @@ -38,7 +43,8 @@ void nfs_uuid_end(nfs_uuid_t *); void nfs_uuid_is_local(const uuid_t *, struct list_head *, struct net *, struct auth_domain *, struct module *); -void nfs_localio_disable_client(nfs_uuid_t *nfs_uuid); +void nfs_localio_enable_client(struct nfs_client *clp); +void nfs_localio_disable_client(struct nfs_client *clp); void nfs_localio_invalidate_clients(struct list_head *list); /* localio needs to map filehandle -> struct nfsd_file */ -- cgit v1.2.3 From 86e00412254a717ffd5d38dc5ec0ee1cce6281b3 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 15 Nov 2024 20:40:57 -0500 Subject: nfs: cache all open LOCALIO nfsd_file(s) in client This commit switches from leaning heavily on NFSD's filecache (in terms of GC'd nfsd_files) back to caching nfsd_files in the client. A later commit will add the callback mechanism needed to allow NFSD to force the NFS client to cleanup all cached nfsd_files. Add nfs_fh_localio_init() and 'struct nfs_fh_localio' to cache opened nfsd_file(s) (both a RO and RW nfsd_file is able to be opened and cached for a given nfs_fh). Update nfs_local_open_fh() to cache the nfsd_file once it is opened using __nfs_local_open_fh(). Introduce nfs_close_local_fh() to clear the cached open nfsd_files and call nfs_to_nfsd_file_put_local(). Refcounting is such that: - nfs_local_open_fh() is paired with nfs_close_local_fh(). - __nfs_local_open_fh() is paired with nfs_to_nfsd_file_put_local(). - nfs_local_file_get() is paired with nfs_local_file_put(). Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 22 ++++++++++++++++++++-- include/linux/nfslocalio.h | 16 +++++++++------- 2 files changed, 29 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 039898d70954..67ae2c3f41d2 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -77,6 +77,23 @@ struct nfs_lock_context { struct rcu_head rcu_head; }; +struct nfs_file_localio { + struct nfsd_file __rcu *ro_file; + struct nfsd_file __rcu *rw_file; + struct list_head list; + void __rcu *nfs_uuid; /* opaque pointer to 'nfs_uuid_t' */ +}; + +static inline void nfs_localio_file_init(struct nfs_file_localio *nfl) +{ +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + nfl->ro_file = NULL; + nfl->rw_file = NULL; + INIT_LIST_HEAD(&nfl->list); + nfl->nfs_uuid = NULL; +#endif +} + struct nfs4_state; struct nfs_open_context { struct nfs_lock_context lock_context; @@ -87,15 +104,16 @@ struct nfs_open_context { struct nfs4_state *state; fmode_t mode; + int error; unsigned long flags; #define NFS_CONTEXT_BAD (2) #define NFS_CONTEXT_UNLOCK (3) #define NFS_CONTEXT_FILE_OPEN (4) - int error; - struct list_head list; struct nfs4_threshold *mdsthreshold; + struct list_head list; struct rcu_head rcu_head; + struct nfs_file_localio nfl; }; struct nfs_open_dir_context { diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index 4d5583873f41..7cfc6720ed26 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -6,10 +6,6 @@ #ifndef __LINUX_NFSLOCALIO_H #define __LINUX_NFSLOCALIO_H - -/* nfsd_file structure is purposely kept opaque to NFS client */ -struct nfsd_file; - #if IS_ENABLED(CONFIG_NFS_LOCALIO) #include @@ -21,6 +17,7 @@ struct nfsd_file; #include struct nfs_client; +struct nfs_file_localio; /* * Useful to allow a client to negotiate if localio @@ -52,6 +49,7 @@ extern struct nfsd_file * nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *, const struct cred *, const struct nfs_fh *, const fmode_t) __must_hold(rcu); +void nfs_close_local_fh(struct nfs_file_localio *); struct nfsd_localio_operations { bool (*nfsd_serv_try_get)(struct net *); @@ -73,7 +71,8 @@ extern const struct nfsd_localio_operations *nfs_to; struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *, struct rpc_clnt *, const struct cred *, - const struct nfs_fh *, const fmode_t); + const struct nfs_fh *, struct nfs_file_localio *, + const fmode_t); static inline void nfs_to_nfsd_net_put(struct net *net) { @@ -100,12 +99,15 @@ static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio) } #else /* CONFIG_NFS_LOCALIO */ -static inline void nfsd_localio_ops_init(void) + +struct nfs_file_localio; +static inline void nfs_close_local_fh(struct nfs_file_localio *nfl) { } -static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio) +static inline void nfsd_localio_ops_init(void) { } + #endif /* CONFIG_NFS_LOCALIO */ #endif /* __LINUX_NFSLOCALIO_H */ -- cgit v1.2.3 From b33f7dec3a67216123312c7bb752b8f6faa1c465 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 15 Nov 2024 20:40:59 -0500 Subject: nfsd: rename nfsd_serv_ prefixed methods and variables with nfsd_net_ Also update Documentation/filesystems/nfs/localio.rst accordingly and reduce the technical documentation debt that was previously captured in that document. Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Acked-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/nfslocalio.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index 7cfc6720ed26..aa2b5c6561ab 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -52,8 +52,8 @@ nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *, void nfs_close_local_fh(struct nfs_file_localio *); struct nfsd_localio_operations { - bool (*nfsd_serv_try_get)(struct net *); - void (*nfsd_serv_put)(struct net *); + bool (*nfsd_net_try_get)(struct net *); + void (*nfsd_net_put)(struct net *); struct nfsd_file *(*nfsd_open_local_fh)(struct net *, struct auth_domain *, struct rpc_clnt *, @@ -77,12 +77,12 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *, static inline void nfs_to_nfsd_net_put(struct net *net) { /* - * Once reference to nfsd_serv is dropped, NFSD could be - * unloaded, so ensure safe return from nfsd_file_put_local() - * by always taking RCU. + * Once reference to net (and associated nfsd_serv) is dropped, NFSD + * could be unloaded, so ensure safe return from nfsd_net_put() by + * always taking RCU. */ rcu_read_lock(); - nfs_to->nfsd_serv_put(net); + nfs_to->nfsd_net_put(net); rcu_read_unlock(); } -- cgit v1.2.3 From 085804110aa13eac7f763d8d5cfe3a8220e35222 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 15 Nov 2024 20:41:02 -0500 Subject: nfs_common: track all open nfsd_files per LOCALIO nfs_client This tracking enables __nfsd_file_cache_purge() to call nfs_localio_invalidate_clients(), upon shutdown or export change, to nfs_close_local_fh() all open nfsd_files that are still cached by the LOCALIO nfs clients associated with nfsd_net that is being shutdown. Now that the client must track all open nfsd_files there was more work than necessary being done with the global nfs_uuids_lock contended. This manifested in various RCU issues, e.g.: hrtimer: interrupt took 47969440 ns rcu: INFO: rcu_sched detected stalls on CPUs/tasks: Use nfs_uuid->lock to protect all nfs_uuid_t members, instead of nfs_uuids_lock, once nfs_uuid_is_local() adds the client to nn->local_clients. Also add 'local_clients_lock' to 'struct nfsd_net' to protect nn->local_clients. And store a pointer to spinlock in the 'list_lock' member of nfs_uuid_t so nfs_localio_disable_client() can use it to avoid taking the global nfs_uuids_lock. In combination, these split out locks eliminate the use of the single nfslocalio.c global nfs_uuids_lock in the IO paths (open and close). Also refactored associated fs/nfs_common/nfslocalio.c methods' locking to reduce work performed with spinlocks held in general. Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/nfslocalio.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index aa2b5c6561ab..c68a529230c1 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -30,19 +30,23 @@ typedef struct { /* sadly this struct is just over a cacheline, avoid bouncing */ spinlock_t ____cacheline_aligned lock; struct list_head list; + spinlock_t *list_lock; /* nn->local_clients_lock */ struct net __rcu *net; /* nfsd's network namespace */ struct auth_domain *dom; /* auth_domain for localio */ + /* Local files to close when net is shut down or exports change */ + struct list_head files; } nfs_uuid_t; void nfs_uuid_init(nfs_uuid_t *); bool nfs_uuid_begin(nfs_uuid_t *); void nfs_uuid_end(nfs_uuid_t *); -void nfs_uuid_is_local(const uuid_t *, struct list_head *, +void nfs_uuid_is_local(const uuid_t *, struct list_head *, spinlock_t *, struct net *, struct auth_domain *, struct module *); void nfs_localio_enable_client(struct nfs_client *clp); void nfs_localio_disable_client(struct nfs_client *clp); -void nfs_localio_invalidate_clients(struct list_head *list); +void nfs_localio_invalidate_clients(struct list_head *nn_local_clients, + spinlock_t *nn_local_clients_lock); /* localio needs to map filehandle -> struct nfsd_file */ extern struct nfsd_file * -- cgit v1.2.3 From 779a395189c692eec0246e7df63e2a3c0f0c8508 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 15 Nov 2024 20:41:04 -0500 Subject: nfs/localio: remove redundant code and simplify LOCALIO enablement Remove nfs_local_enable and nfs_local_disable, instead use nfs_localio_enable_client and nfs_localio_disable_client. Discontinue use of the NFS_CS_LOCAL_IO bit in the nfs_client struct's cl_flags to reflect that LOCALIO is enabled; instead just test if the net member of the nfs_uuid_t struct is set. Also remove NFS_CS_LOCAL_IO. Lastly, remove trace_nfs_local_enable and trace_nfs_local_disable because comparable traces are available from nfs_localio.ko. Suggested-by: NeilBrown Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 1 - include/linux/nfslocalio.h | 4 ++++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 239d86ef166c..ed66df1093e8 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -50,7 +50,6 @@ struct nfs_client { #define NFS_CS_DS 7 /* - Server is a DS */ #define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */ #define NFS_CS_PNFS 9 /* - Server used for pnfs */ -#define NFS_CS_LOCAL_IO 10 /* - client is local */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index c68a529230c1..05817d6ef3d1 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -111,6 +111,10 @@ static inline void nfs_close_local_fh(struct nfs_file_localio *nfl) static inline void nfsd_localio_ops_init(void) { } +struct nfs_client; +static inline void nfs_localio_disable_client(struct nfs_client *clp) +{ +} #endif /* CONFIG_NFS_LOCALIO */ -- cgit v1.2.3 From 76d4cb6345da0f2cd505e552157258325bcc8bcd Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 15 Nov 2024 20:41:05 -0500 Subject: nfs: probe for LOCALIO when v4 client reconnects to server Introduce nfs_local_probe_async() for the NFS client to initiate if/when it reconnects with server. For NFSv4 it is a simple matter to call nfs_local_probe_async() from nfs4_do_reclaim (during NFSv4 grace). Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index ed66df1093e8..f00bfcee7120 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -131,6 +131,7 @@ struct nfs_client { struct timespec64 cl_nfssvc_boot; seqlock_t cl_boot_lock; nfs_uuid_t cl_uuid; + struct work_struct cl_local_probe_work; #endif /* CONFIG_NFS_LOCALIO */ }; -- cgit v1.2.3 From 4a489220aa8c9daf5f02396c28cebade9f9ab563 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 15 Nov 2024 20:41:06 -0500 Subject: nfs: probe for LOCALIO when v3 client reconnects to server Re-enabling NFSv3 LOCALIO is made more complex (than NFSv4) because v3 is stateless. As such, the hueristic used to identify a LOCALIO probe point is more adhoc by nature: if/when NFSv3 client IO begins to complete again in terms of normal RPC-based NFSv3 server IO, attempt nfs_local_probe_async(). Care is taken to throttle the frequency of nfs_local_probe_async(), otherwise there could be a flood of repeat calls to nfs_local_probe_async(). The throttle is admin controlled using a new module parameter for nfsv3, e.g.: echo 512 > /sys/module/nfsv3/parameters/nfs3_localio_probe_throttle Probe for NFSv3 LOCALIO every N IO requests (512 in this case). Must be power-of-2, defaults to 0 (probing disabled). On systems that expect to use LOCALIO with NFSv3 the admin should configure the 'nfs3_localio_probe_throttle' module parameter. This commit backfills module parameter documentation in localio.rst Signed-off-by: Mike Snitzer Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/nfslocalio.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index 05817d6ef3d1..9aa8a43843d7 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -27,7 +27,8 @@ struct nfs_file_localio; */ typedef struct { uuid_t uuid; - /* sadly this struct is just over a cacheline, avoid bouncing */ + unsigned nfs3_localio_probe_count; + /* this struct is over a cacheline, avoid bouncing */ spinlock_t ____cacheline_aligned lock; struct list_head list; spinlock_t *list_lock; /* nn->local_clients_lock */ -- cgit v1.2.3 From ead11ac50ad4b8ef1b64806e962ea984862d96ad Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 13 Jan 2025 17:29:03 -0500 Subject: nfs: fix incorrect error handling in LOCALIO nfs4_stat_to_errno() expects a NFSv4 error code as an argument and returns a POSIX errno. The problem is LOCALIO is passing nfs4_stat_to_errno() the POSIX errno return values from filp->f_op->read_iter(), filp->f_op->write_iter() and vfs_fsync_range(). So the POSIX errno that nfs_local_pgio_done() and nfs_local_commit_done() are passing to nfs4_stat_to_errno() are failing to match any NFSv4 error code, which results in nfs4_stat_to_errno() defaulting to returning -EREMOTEIO. This causes assertions in upper layers due to -EREMOTEIO not being a valid NFSv4 error code. Fix this by updating nfs_local_pgio_done() and nfs_local_commit_done() to use the new nfs_localio_errno_to_nfs4_stat() to map a POSIX errno to an NFSv4 error code. Care was taken to factor out nfs4_errtbl_common[] to avoid duplicating the same NFS error to errno table. nfs4_errtbl_common[] is checked first by both nfs4_stat_to_errno and nfs_localio_errno_to_nfs4_stat before they check their own more specialized tables (nfs4_errtbl[] and nfs4_errtbl_localio[] respectively). While auditing the associated error mapping tables, the (ab)use of -1 for the last table entry was removed in favor of using ARRAY_SIZE to iterate the nfs_errtbl[] and nfs4_errtbl[]. And 'errno_NFSERR_IO' was removed because it caused needless obfuscation. Fixes: 70ba381e1a431 ("nfs: add LOCALIO support") Reported-by: Trond Myklebust Signed-off-by: Mike Snitzer Signed-off-by: Anna Schumaker --- include/linux/nfs_common.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h index 5fc02df88252..a541c3a02887 100644 --- a/include/linux/nfs_common.h +++ b/include/linux/nfs_common.h @@ -9,9 +9,10 @@ #include /* Mapping from NFS error code to "errno" error code. */ -#define errno_NFSERR_IO EIO int nfs_stat_to_errno(enum nfs_stat status); int nfs4_stat_to_errno(int stat); +__u32 nfs_localio_errno_to_nfs4_stat(int errno); + #endif /* _LINUX_NFS_COMMON_H */ -- cgit v1.2.3