From 40c80881ebef97a2ad4bba1e34edb80fd8585e8c Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Mon, 26 Aug 2024 11:21:57 +0800 Subject: nfs: Remove obsoleted declaration for nfs_read_prepare The nfs_read_prepare() have been removed since commit a4cdda59111f ("NFS: Create a common pgio_rpc_prepare function"), and now it is useless, so remove it. Signed-off-by: Gaosheng Cui Signed-off-by: Anna Schumaker --- fs/nfs/internal.h | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/nfs/internal.h') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 5902a9beca1f..b3dc7c84eef9 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -505,7 +505,6 @@ extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, struct nfs_open_context *ctx, struct folio *folio); extern void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio); -extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); /* super.c */ -- cgit From df24c483e28f7f9a421afde15d0497e61bc2d3ea Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 5 Sep 2024 15:09:52 -0400 Subject: nfs: pass struct nfsd_file to nfs_init_pgio and nfs_init_commit The nfsd_file will be passed, in future commits, by callers that enable LOCALIO support (for both regular NFS and pNFS IO). [Derived from patch authored by Weston Andros Adamson, but switched from passing struct file to struct nfsd_file] Signed-off-by: Mike Snitzer Reviewed-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/internal.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'fs/nfs/internal.h') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index b3dc7c84eef9..f0af96a665d2 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) @@ -308,7 +309,8 @@ void nfs_pgio_header_free(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, - const struct rpc_call_ops *call_ops, int how, int flags); + const struct rpc_call_ops *call_ops, int how, int flags, + struct nfsd_file *localio); void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); @@ -527,7 +529,8 @@ extern int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, - int how, int flags); + int how, int flags, + struct nfsd_file *localio); extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, struct pnfs_layout_segment *lseg, -- cgit From 70ba381e1a431245c137ed597ec6a05991c79bd9 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 5 Sep 2024 15:09:53 -0400 Subject: nfs: add LOCALIO support Add client support for bypassing NFS for localhost reads, writes, and commits. This is only useful when the client and the server are running on the same host. nfs_local_probe() is stubbed out, later commits will enable client and server handshake via a Linux-only LOCALIO auxiliary RPC protocol. This has dynamic binding with the nfsd module (via nfs_localio module which is part of nfs_common). LOCALIO will only work if nfsd is already loaded. The "localio_enabled" nfs kernel module parameter can be used to disable and enable the ability to use LOCALIO support. CONFIG_NFS_LOCALIO enables NFS client support for LOCALIO. Lastly, LOCALIO uses an nfsd_file to initiate all IO. To make proper use of nfsd_file (and nfsd's filecache) its lifetime (duration before nfsd_file_put is called) must extend until after commit, read and write operations. So rather than immediately drop the nfsd_file reference in nfs_local_open_fh(), that doesn't happen until nfs_local_pgio_release() for read/write and not until nfs_local_release_commit_data() for commit. The same applies to the reference held on nfsd's nn->nfsd_serv. Both objects' lifetimes and associated references are managed through calls to nfs_to->nfsd_file_put_local(). Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust Co-developed-by: Mike Snitzer Signed-off-by: Mike Snitzer Signed-off-by: NeilBrown # nfs_open_local_fh Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/internal.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'fs/nfs/internal.h') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index f0af96a665d2..534c1ac16c57 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -451,6 +451,51 @@ extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags); extern bool nfs_check_cache_invalid(struct inode *, unsigned long); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +/* localio.c */ +extern void nfs_local_disable(struct nfs_client *); +extern void nfs_local_probe(struct nfs_client *); +extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *, + const struct cred *, + struct nfs_fh *, + const fmode_t); +extern int nfs_local_doio(struct nfs_client *, + struct nfsd_file *, + struct nfs_pgio_header *, + const struct rpc_call_ops *); +extern int nfs_local_commit(struct nfsd_file *, + struct nfs_commit_data *, + const struct rpc_call_ops *, int); +extern bool nfs_server_is_local(const struct nfs_client *clp); + +#else /* CONFIG_NFS_LOCALIO */ +static inline void nfs_local_disable(struct nfs_client *clp) {} +static inline void nfs_local_probe(struct nfs_client *clp) {} +static inline struct nfsd_file * +nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, + struct nfs_fh *fh, const fmode_t mode) +{ + return NULL; +} +static inline int nfs_local_doio(struct nfs_client *clp, + struct nfsd_file *localio, + struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops) +{ + return -EINVAL; +} +static inline int nfs_local_commit(struct nfsd_file *localio, + struct nfs_commit_data *data, + const struct rpc_call_ops *call_ops, int how) +{ + return -EINVAL; +} +static inline bool nfs_server_is_local(const struct nfs_client *clp) +{ + return false; +} +#endif /* CONFIG_NFS_LOCALIO */ + /* super.c */ extern const struct super_operations nfs_sops; bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); -- cgit From b9f5dd57f4a52990963eeb1f1b58d00f717ece69 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 5 Sep 2024 15:09:56 -0400 Subject: nfs/localio: use dedicated workqueues for filesystem read and write For localio access, don't call filesystem read() and write() routines directly. This solves two problems: 1) localio writes need to use a normal (non-memreclaim) unbound workqueue. This avoids imposing new requirements on how underlying filesystems process frontend IO, which would cause a large amount of work to update all filesystems. Without this change, when XFS starts getting low on space, XFS flushes work on a non-memreclaim work queue, which causes a priority inversion problem: 00573 workqueue: WQ_MEM_RECLAIM writeback:wb_workfn is flushing !WQ_MEM_RECLAIM xfs-sync/vdc:xfs_flush_inodes_worker 00573 WARNING: CPU: 6 PID: 8525 at kernel/workqueue.c:3706 check_flush_dependency+0x2a4/0x328 00573 Modules linked in: 00573 CPU: 6 PID: 8525 Comm: kworker/u71:5 Not tainted 6.10.0-rc3-ktest-00032-g2b0a133403ab #18502 00573 Hardware name: linux,dummy-virt (DT) 00573 Workqueue: writeback wb_workfn (flush-0:33) 00573 pstate: 400010c5 (nZcv daIF -PAN -UAO -TCO -DIT +SSBS BTYPE=--) 00573 pc : check_flush_dependency+0x2a4/0x328 00573 lr : check_flush_dependency+0x2a4/0x328 00573 sp : ffff0000c5f06bb0 00573 x29: ffff0000c5f06bb0 x28: ffff0000c998a908 x27: 1fffe00019331521 00573 x26: ffff0000d0620900 x25: ffff0000c5f06ca0 x24: ffff8000828848c0 00573 x23: 1fffe00018be0d8e x22: ffff0000c1210000 x21: ffff0000c75fde00 00573 x20: ffff800080bfd258 x19: ffff0000cad63400 x18: ffff0000cd3a4810 00573 x17: 0000000000000000 x16: 0000000000000000 x15: ffff800080508d98 00573 x14: 0000000000000000 x13: 204d49414c434552 x12: 1fffe0001b6eeab2 00573 x11: ffff60001b6eeab2 x10: dfff800000000000 x9 : ffff60001b6eeab3 00573 x8 : 0000000000000001 x7 : 00009fffe491154e x6 : ffff0000db775593 00573 x5 : ffff0000db775590 x4 : ffff0000db775590 x3 : 0000000000000000 00573 x2 : 0000000000000027 x1 : ffff600018be0d62 x0 : dfff800000000000 00573 Call trace: 00573 check_flush_dependency+0x2a4/0x328 00573 __flush_work+0x184/0x5c8 00573 flush_work+0x18/0x28 00573 xfs_flush_inodes+0x68/0x88 00573 xfs_file_buffered_write+0x128/0x6f0 00573 xfs_file_write_iter+0x358/0x448 00573 nfs_local_doio+0x854/0x1568 00573 nfs_initiate_pgio+0x214/0x418 00573 nfs_generic_pg_pgios+0x304/0x480 00573 nfs_pageio_doio+0xe8/0x240 00573 nfs_pageio_complete+0x160/0x480 00573 nfs_writepages+0x300/0x4f0 00573 do_writepages+0x12c/0x4a0 00573 __writeback_single_inode+0xd4/0xa68 00573 writeback_sb_inodes+0x470/0xcb0 00573 __writeback_inodes_wb+0xb0/0x1d0 00573 wb_writeback+0x594/0x808 00573 wb_workfn+0x5e8/0x9e0 00573 process_scheduled_works+0x53c/0xd90 00573 worker_thread+0x370/0x8c8 00573 kthread+0x258/0x2e8 00573 ret_from_fork+0x10/0x20 2) Some filesystem writeback routines can end up taking up a lot of stack space (particularly XFS). Instead of risking running over due to the extra overhead from the NFS stack, we should just call these routines from a workqueue job. Since we need to do this to address 1) above we're able to avoid possibly blowing the stack "for free". Use of dedicated workqueues improves performance over using the system_unbound_wq. Also, the creds used to open the file are used to override_creds() in both nfs_local_call_read() and nfs_local_call_write() -- otherwise the workqueue could have elevated capabilities (which the caller may not). Lastly, care is taken to set PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO in nfs_do_local_write() to avoid writeback deadlocks. The PF_LOCAL_THROTTLE flag prevents deadlocks in balance_dirty_pages() by causing writes to only be throttled against other writes to the same bdi (it keeps the throttling local). Normally all writes to bdi(s) are throttled equally (after throughput factors are allowed for). The PF_MEMALLOC_NOIO flag prevents the lower filesystem IO from causing memory reclaim to re-enter filesystems or IO devices and so prevents deadlocks from occuring where IO that cleans pages is waiting on IO to complete. Signed-off-by: Trond Myklebust Co-developed-by: Mike Snitzer Signed-off-by: Mike Snitzer Co-developed-by: NeilBrown Signed-off-by: NeilBrown # eliminated wait_for_completion Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/internal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/nfs/internal.h') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 534c1ac16c57..430733e3eff2 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -440,6 +440,7 @@ int nfs_check_flags(int); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; +extern struct workqueue_struct *nfslocaliod_workqueue; extern struct inode *nfs_alloc_inode(struct super_block *sb); extern void nfs_free_inode(struct inode *); extern int nfs_write_inode(struct inode *, struct writeback_control *); -- cgit