From 8786fde8421ce755a842051f9528674a1b1f0b9a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 22 Jan 2022 20:54:52 +0000 Subject: Convert NFS from readpages to readahead NFS is one of the last two users of the deprecated ->readpages aop. This conversion looks straightforward, but I have only compile-tested it. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 68f81d8d36de..333ea05e2531 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -601,8 +601,7 @@ nfs_have_writebacks(struct inode *inode) * linux/fs/nfs/read.c */ extern int nfs_readpage(struct file *, struct page *); -extern int nfs_readpages(struct file *, struct address_space *, - struct list_head *, unsigned); +void nfs_readahead(struct readahead_control *); /* * inline functions -- cgit v1.2.3 From 43245eca6e670ebf65908b549641c1460a9cc944 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 2 Feb 2022 17:55:02 -0500 Subject: NFSv4.1 support for NFS4_RESULT_PRESERVER_UNLINKED In 4.1+, the server is allowed to set a flag NFS4_RESULT_PRESERVE_UNLINKED in reply to the OPEN, that tells the client that it does not need to do a silly rename of an opened file when it's being removed. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 333ea05e2531..0e79dbbc759a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -277,6 +277,7 @@ struct nfs4_copy_state { #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ +#define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ -- cgit v1.2.3 From 88a6099fc3274a27814d26dd688fdc5cd7a480ee Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 Feb 2022 13:22:48 -0500 Subject: NFS: Replace last uses of NFS_INO_REVAL_PAGECACHE Now that we have more fine grained attribute revalidation, let's just get rid of NFS_INO_REVAL_PAGECACHE. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 0e79dbbc759a..ce3128e4bffa 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -356,11 +356,9 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_INVALID_CHANGE - | NFS_INO_INVALID_CTIME; + nfsi->cache_validity |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | + NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | + NFS_INO_INVALID_SIZE; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); -- cgit v1.2.3 From 41e97b7f8a15d15da03ca15e6ff7b9b7ab7f588c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 Feb 2022 13:26:19 -0500 Subject: NFS: Remove unused flag NFS_INO_REVAL_PAGECACHE Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index ce3128e4bffa..72a732a5103c 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -247,7 +247,6 @@ struct nfs4_copy_state { #define NFS_INO_INVALID_ATIME BIT(2) /* cached atime is invalid */ #define NFS_INO_INVALID_ACCESS BIT(3) /* cached access cred invalid */ #define NFS_INO_INVALID_ACL BIT(4) /* cached acls are invalid */ -#define NFS_INO_REVAL_PAGECACHE BIT(5) /* must revalidate pagecache */ #define NFS_INO_REVAL_FORCED BIT(6) /* force revalidation ignoring a delegation */ #define NFS_INO_INVALID_LABEL BIT(7) /* cached label is invalid */ #define NFS_INO_INVALID_CHANGE BIT(8) /* cached change is invalid */ -- cgit v1.2.3 From 1a93b82c59ab45f2d9f14c47f09d2e341ff02381 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 18 Feb 2022 07:07:08 -0500 Subject: NFS: constify nfs_server_capable() and nfs_have_writebacks() Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 72a732a5103c..6e10725887d1 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -363,7 +363,7 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) spin_unlock(&inode->i_lock); } -static inline int nfs_server_capable(struct inode *inode, int cap) +static inline int nfs_server_capable(const struct inode *inode, int cap) { return NFS_SERVER(inode)->caps & cap; } @@ -587,12 +587,11 @@ extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); extern void nfs_commit_free(struct nfs_commit_data *data); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); -static inline int -nfs_have_writebacks(struct inode *inode) +static inline bool nfs_have_writebacks(const struct inode *inode) { if (S_ISREG(inode->i_mode)) return atomic_long_read(&NFS_I(inode)->nrequests) != 0; - return 0; + return false; } /* -- cgit v1.2.3 From 728dd0ab37421396927749fc8cec9c2009c526c8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 22 Feb 2022 08:59:33 -0500 Subject: NFS: Don't re-read the entire page cache to find the next cookie If the page cache entry that was last read gets invalidated for some reason, then make sure we can re-create it on the next call to readdir. This, combined with the cache page validation, allows us to reuse the cached value of page-index on successive calls to nfs_readdir. Credit is due to Benjamin Coddington for showing that the concept works, and that it allows for improved cache sharing between processes even in the case where pages are lost due to LRU or active invalidation. Suggested-by: Benjamin Coddington Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 6e10725887d1..1c533f2c1f36 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -105,6 +105,7 @@ struct nfs_open_dir_context { __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; __u64 dup_cookie; + __u64 last_cookie; pgoff_t page_index; signed char duped; bool eof; -- cgit v1.2.3 From 580f236737d13ee25d5b0b1d124f50014fe6833b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 7 Feb 2022 13:37:00 -0500 Subject: NFS: Adjust the amount of readahead performed by NFS readdir The current NFS readdir code will always try to maximise the amount of readahead it performs on the assumption that we can cache anything that isn't immediately read by the process. There are several cases where this assumption breaks down, including when the 'ls -l' heuristic kicks in to try to force use of readdirplus as a batch replacement for lookup/getattr. This patch therefore tries to tone down the amount of readahead we perform, and adjust it to try to match the amount of data being requested by user space. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 1c533f2c1f36..691a27936849 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -107,6 +107,7 @@ struct nfs_open_dir_context { __u64 dup_cookie; __u64 last_cookie; pgoff_t page_index; + unsigned int dtsize; signed char duped; bool eof; }; -- cgit v1.2.3 From 230bc98f7a2a49eb472d184bdec91fd3096384b3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 17 Feb 2022 11:08:24 -0500 Subject: NFS: Improve heuristic for readdirplus The heuristic for readdirplus is designed to try to detect 'ls -l' and similar patterns. It does so by looking for cache hit/miss patterns in both the attribute cache and in the dcache of the files in a given directory, and then sets a flag for the readdirplus code to interpret. The problem with this approach is that a single attribute or dcache miss can cause the NFS code to force a refresh of the attributes for the entire set of files contained in the directory. To be able to make a more nuanced decision, let's sample the number of hits and misses in the set of open directory descriptors. That allows us to set thresholds at which we start preferring READDIRPLUS over regular READDIR, or at which we start to force a re-read of the remaining readdir cache using READDIRPLUS. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 691a27936849..20a4cf0acad2 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -101,6 +101,8 @@ struct nfs_open_context { struct nfs_open_dir_context { struct list_head list; + atomic_t cache_hits; + atomic_t cache_misses; unsigned long attr_gencount; __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; @@ -110,6 +112,7 @@ struct nfs_open_dir_context { unsigned int dtsize; signed char duped; bool eof; + struct rcu_head rcu_head; }; /* @@ -274,13 +277,11 @@ struct nfs4_copy_state { /* * Bit offsets in flags field */ -#define NFS_INO_ADVISE_RDPLUS (0) /* advise readdirplus */ #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ -#define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ -- cgit v1.2.3 From f648022faa68ef76058aa121d1aa3a967d59cae8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 23 Feb 2022 11:31:51 -0500 Subject: NFS: Convert readdir page cache to use a cookie based index Instead of using a linear index to address the pages, use the cookie of the first entry, since that is what we use to match the page anyway. This allows us to avoid re-reading the entire cache on a seekdir() type of operation. The latter is very common when re-exporting NFS, and is a major performance drain. The change does affect our duplicate cookie detection, since we can no longer rely on the page index as a linear offset for detecting whether we looped backwards. However since we no longer do a linear search through all the pages on each call to nfs_readdir(), this is less of a concern than it was previously. The other downside is that invalidate_mapping_pages() no longer can use the page index to avoid clearing pages that have been read. A subsequent patch will restore the functionality this provides to the 'ls -l' heuristic. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 20a4cf0acad2..42aad886d3c0 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -106,11 +106,9 @@ struct nfs_open_dir_context { unsigned long attr_gencount; __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; - __u64 dup_cookie; __u64 last_cookie; pgoff_t page_index; unsigned int dtsize; - signed char duped; bool eof; struct rcu_head rcu_head; }; -- cgit v1.2.3 From b0365ccb0712efacf99936e94e92eb7ae63de4d5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 23 Feb 2022 13:29:59 -0500 Subject: NFS: Fix up forced readdirplus Avoid clearing the entire readdir page cache if we're just doing forced readdirplus for the 'ls -l' heuristic. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 42aad886d3c0..3893386ceaed 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -109,6 +109,7 @@ struct nfs_open_dir_context { __u64 last_cookie; pgoff_t page_index; unsigned int dtsize; + bool force_clear; bool eof; struct rcu_head rcu_head; }; -- cgit v1.2.3 From 0adf85b445c7fbc5d2df1f8c1bc54d62c4340237 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 27 Feb 2022 12:46:24 -0500 Subject: NFS: Optimise away the previous cookie field Replace the 'previous cookie' field in struct nfs_entry with the array->last_cookie. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 728cb0c1f0b6..82f7c2730b9a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -745,8 +745,7 @@ struct nfs_auth_info { */ struct nfs_entry { __u64 ino; - __u64 cookie, - prev_cookie; + __u64 cookie; const char * name; unsigned int len; int eof; -- cgit v1.2.3 From a41b05edfedb939440e83666f23de3ef9af33acf Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Mar 2022 10:41:44 +1100 Subject: SUNRPC/auth: async tasks mustn't block waiting for memory When memory is short, new worker threads cannot be created and we depend on the minimum one rpciod thread to be able to handle everything. So it must not block waiting for memory. mempools are particularly a problem as memory can only be released back to the mempool by an async rpc task running. If all available workqueue threads are waiting on the mempool, no thread is available to return anything. lookup_cred() can block on a mempool or kmalloc - and this can cause deadlocks. So add a new RPCAUTH_LOOKUP flag for async lookups and don't block on memory. If the -ENOMEM gets back to call_refreshresult(), wait a short while and try again. HZ>>4 is chosen as it is used elsewhere for -ENOMEM retries. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 98da816b5fc2..3e6ce288a7fc 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -99,6 +99,7 @@ struct rpc_auth_create_args { /* Flags for rpcauth_lookupcred() */ #define RPCAUTH_LOOKUP_NEW 0x01 /* Accept an uninitialised cred */ +#define RPCAUTH_LOOKUP_ASYNC 0x02 /* Don't block waiting for memory */ /* * Client authentication ops -- cgit v1.2.3 From 89c2be8a951654758dffeaaa6272328d9c8f29be Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Mar 2022 10:41:44 +1100 Subject: NFS: discard NFS_RPC_SWAPFLAGS and RPC_TASK_ROOTCREDS NFS_RPC_SWAPFLAGS is only used for READ requests. It sets RPC_TASK_SWAPPER which gives some memory-allocation priority to requests. This is not needed for swap READ - though it is for writes where it is set via a different mechanism. RPC_TASK_ROOTCREDS causes the 'machine' credential to be used. This is not needed as the root credential is saved when the swap file is opened, and this is used for all IO. So NFS_RPC_SWAPFLAGS isn't needed, and as it is the only user of RPC_TASK_ROOTCREDS, that isn't needed either. Remove both. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 5 ----- include/linux/sunrpc/sched.h | 1 - 2 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 3893386ceaed..9074ed0b65aa 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -45,11 +45,6 @@ */ #define NFS_MAX_TRANSPORTS 16 -/* - * These are the default flags for swap requests - */ -#define NFS_RPC_SWAPFLAGS (RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS) - /* * Size of the NFS directory verifier */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index db964bb63912..56710f8056d3 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -124,7 +124,6 @@ struct rpc_task_setup { #define RPC_TASK_MOVEABLE 0x0004 /* nfs4.1+ rpc tasks */ #define RPC_TASK_NULLCREDS 0x0010 /* Use AUTH_NULL credential */ #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ -#define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ #define RPC_TASK_NO_ROUND_ROBIN 0x0100 /* send requests on "main" xprt */ #define RPC_TASK_SOFT 0x0200 /* Use soft timeouts */ -- cgit v1.2.3 From 4dc73c679114a2f408567e2e44770ed934190db2 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Mar 2022 10:41:44 +1100 Subject: NFSv4: keep state manager thread active if swap is enabled If we are swapping over NFSv4, we may not be able to allocate memory to start the state-manager thread at the time when we need it. So keep it always running when swap is enabled, and just signal it to start. This requires updating and testing the cl_swapper count on the root rpc_clnt after following all ->cl_parent links. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 82f7c2730b9a..49ba486aea5f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1797,6 +1797,8 @@ struct nfs_rpc_ops { struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); int (*discover_trunking)(struct nfs_server *, struct nfs_fh *); + void (*enable_swap)(struct inode *inode); + void (*disable_swap)(struct inode *inode); }; /* -- cgit v1.2.3 From 64158668ac8b31626a8ce48db4cad08496eb8340 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Mar 2022 10:41:44 +1100 Subject: NFS: swap IO handling is slightly different for O_DIRECT IO 1/ Taking the i_rwsem for swap IO triggers lockdep warnings regarding possible deadlocks with "fs_reclaim". These deadlocks could, I believe, eventuate if a buffered read on the swapfile was attempted. We don't need coherence with the page cache for a swap file, and buffered writes are forbidden anyway. There is no other need for i_rwsem during direct IO. So never take it for swap_rw() 2/ generic_write_checks() explicitly forbids writes to swap, and performs checks that are not needed for swap. So bypass it for swap_rw(). Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 9074ed0b65aa..c47c448befc8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -508,10 +508,10 @@ static inline const struct cred *nfs_file_cred(struct file *file) * linux/fs/nfs/direct.c */ extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *); -extern ssize_t nfs_file_direct_read(struct kiocb *iocb, - struct iov_iter *iter); -extern ssize_t nfs_file_direct_write(struct kiocb *iocb, - struct iov_iter *iter); +ssize_t nfs_file_direct_read(struct kiocb *iocb, + struct iov_iter *iter, bool swap); +ssize_t nfs_file_direct_write(struct kiocb *iocb, + struct iov_iter *iter, bool swap); /* * linux/fs/nfs/dir.c -- cgit v1.2.3 From a43bf604446414103b7535f38e739b65601c4fb2 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 16 Mar 2022 18:24:26 -0400 Subject: NFSv4.1 provide mount option to toggle trunking discovery Introduce a new mount option -- trunkdiscovery,notrunkdiscovery -- to toggle whether or not the client will engage in actively discovery of trunking locations. v2 make notrunkdiscovery default Signed-off-by: Olga Kornievskaia Fixes: 1976b2b31462 ("NFSv4.1 query for fs_location attr on a new file system") Signed-off-by: Trond Myklebust --- 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 ca0959e51e81..b0e3fd550122 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -151,6 +151,7 @@ struct nfs_server { #define NFS_MOUNT_SOFTREVAL 0x800000 #define NFS_MOUNT_WRITE_EAGER 0x01000000 #define NFS_MOUNT_WRITE_WAIT 0x02000000 +#define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000 unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ -- cgit v1.2.3 From 89f42494f92f448747bd8a7ab1ae8b5d5520577d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 16 Mar 2022 19:10:43 -0400 Subject: SUNRPC: Don't call connect() more than once on a TCP socket Avoid socket state races due to repeated calls to ->connect() using the same socket. If connect() returns 0 due to the connection having completed, but we are in fact in a closing state, then we may leave the XPRT_CONNECTING flag set on the transport. Reported-by: Enrico Scholz Fixes: 3be232f11a3c ("SUNRPC: Prevent immediate close+reconnect") Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 8c2a712cb242..689062afdd61 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -89,5 +89,6 @@ struct sock_xprt { #define XPRT_SOCK_WAKE_WRITE (5) #define XPRT_SOCK_WAKE_PENDING (6) #define XPRT_SOCK_WAKE_DISCONNECT (7) +#define XPRT_SOCK_CONNECT_SENT (8) #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ -- cgit v1.2.3 From 2790a624d43084de590884934969e19c7a82316a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 15 Mar 2022 08:12:40 -0400 Subject: SUNRPC: Replace internal use of SOCKWQ_ASYNC_NOSPACE The socket's SOCKWQ_ASYNC_NOSPACE can be cleared by various actors in the socket layer, so replace it with our own flag in the transport sock_state field. Reported-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 689062afdd61..3eb0079669c5 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -90,5 +90,6 @@ struct sock_xprt { #define XPRT_SOCK_WAKE_PENDING (6) #define XPRT_SOCK_WAKE_DISCONNECT (7) #define XPRT_SOCK_CONNECT_SENT (8) +#define XPRT_SOCK_NOSPACE (9) #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ -- cgit v1.2.3 From 33e5c765bc1ea5e06ea7603637f14d727e6fcdf3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 14 Mar 2022 22:02:22 -0400 Subject: NFS: Fix memory allocation in rpc_malloc() When in a low memory situation, we do want rpciod to kick off direct reclaim in the case where that helps, however we don't want it looping forever in mempool_alloc(). So first try allocating from the slab using GFP_KERNEL | __GFP_NORETRY, and then fall back to a GFP_NOWAIT allocation from the mempool. Ditto for rpc_alloc_task() Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 56710f8056d3..1d7a3e51b795 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -262,6 +262,7 @@ void rpc_destroy_mempool(void); extern struct workqueue_struct *rpciod_workqueue; extern struct workqueue_struct *xprtiod_workqueue; void rpc_prepare_task(struct rpc_task *task); +gfp_t rpc_task_gfp_mask(void); static inline int rpc_wait_for_completion_task(struct rpc_task *task) { -- cgit v1.2.3 From 515dcdcd48736576c6f5c197814da6f81c60a21e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 21 Mar 2022 12:34:19 -0400 Subject: NFS: nfsiod should not block forever in mempool_alloc() The concern is that since nfsiod is sometimes required to kick off a commit, it can get locked up waiting forever in mempool_alloc() instead of failing gracefully and leaving the commit until later. Try to allocate from the slab first, with GFP_KERNEL | __GFP_NORETRY, then fall back to a non-blocking attempt to allocate from the memory pool. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c47c448befc8..db305abafc9e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -580,7 +580,7 @@ extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_page(struct inode *inode, struct page *page); extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); -extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); +extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); -- cgit v1.2.3 From 421ab1be43bd015ffe744f4ea25df4f19d1ce6fe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 25 Mar 2022 10:37:31 -0400 Subject: SUNRPC: Do not dereference non-socket transports in sysfs Do not cast the struct xprt to a sock_xprt unless we know it is a UDP or TCP transport. Otherwise the call to lock the mutex will scribble over whatever structure is actually there. This has been seen to cause hard system lockups when the underlying transport was RDMA. Fixes: b49ea673e119 ("SUNRPC: lock against ->sock changing during sysfs read") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 +++ include/linux/sunrpc/xprtsock.h | 1 - 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 955ea4d7af0b..eef5e87c03b4 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -139,6 +139,9 @@ struct rpc_xprt_ops { void (*rpcbind)(struct rpc_task *task); void (*set_port)(struct rpc_xprt *xprt, unsigned short port); void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); + int (*get_srcaddr)(struct rpc_xprt *xprt, char *buf, + size_t buflen); + unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); void (*prepare_request)(struct rpc_rqst *req); diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 3eb0079669c5..38284f25eddf 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -10,7 +10,6 @@ int init_socket_xprt(void); void cleanup_socket_xprt(void); -unsigned short get_srcport(struct rpc_xprt *); #define RPC_MIN_RESVPORT (1U) #define RPC_MAX_RESVPORT (65535U) -- cgit v1.2.3