From 88a4d7bdeec97890cd543b58dd3588f1f879f51b Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:05 -0500 Subject: NFS: Configure support for netfs when NFS fscache is configured As first steps for support of the netfs library when NFS_FSCACHE is configured, add NETFS_SUPPORT to Kconfig and add the required netfs_inode into struct nfs_inode. Using netfs requires we move the VFS inode structure to be stored inside struct netfs_inode, along with the fscache_cookie. Thus, if NFS_FSCACHE is configured, place netfs_inode inside an anonymous union so the vfs_inode memory is the same and we do not need to modify other non-fscache areas of NFS. In addition, inside the NFS fscache code, use the new helpers, netfs_inode() and netfs_i_cookie() helpers, and remove our own helper, nfs_i_fscache(). Later patches will convert NFS fscache to fully use netfs. Signed-off-by: Dave Wysochanski Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bf89fe6fc3ba..041e79a48f7a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -31,6 +31,10 @@ #include #include +#ifdef CONFIG_NFS_FSCACHE +#include +#endif + #include #include #include @@ -204,14 +208,15 @@ struct nfs_inode { /* how many bytes have been written/read and how many bytes queued up */ __u64 write_io; __u64 read_io; -#ifdef CONFIG_NFS_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; - #ifdef CONFIG_NFS_V4_2 struct nfs4_xattr_cache *xattr_cache; #endif + union { + struct inode vfs_inode; +#ifdef CONFIG_NFS_FSCACHE + struct netfs_inode netfs; /* netfs context and VFS inode */ +#endif + }; }; struct nfs4_copy_state { @@ -329,15 +334,6 @@ static inline int NFS_STALE(const struct inode *inode) return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags); } -static inline struct fscache_cookie *nfs_i_fscache(struct inode *inode) -{ -#ifdef CONFIG_NFS_FSCACHE - return NFS_I(inode)->fscache; -#else - return NULL; -#endif -} - static inline __u64 NFS_FILEID(const struct inode *inode) { return NFS_I(inode)->fileid; -- cgit v1.2.3 From 000dbe0bec058cbf2ca9e156e4a5584f5158b0f9 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:06 -0500 Subject: NFS: Convert buffered read paths to use netfs when fscache is enabled Convert the NFS buffered read code paths to corresponding netfs APIs, but only when fscache is configured and enabled. The netfs API defines struct netfs_request_ops which must be filled in by the network filesystem. For NFS, we only need to define 5 of the functions, the main one being the issue_read() function. The issue_read() function is called by the netfs layer when a read cannot be fulfilled locally, and must be sent to the server (either the cache is not active, or it is active but the data is not available). Once the read from the server is complete, netfs requires a call to netfs_subreq_terminated() which conveys either how many bytes were read successfully, or an error. Note that issue_read() is called with a structure, netfs_io_subrequest, which defines the IO requested, and contains a start and a length (both in bytes), and assumes the underlying netfs will return a either an error on the whole region, or the number of bytes successfully read. The NFS IO path is page based and the main APIs are the pgio APIs defined in pagelist.c. For the pgio APIs, there is no way for the caller to know how many RPCs will be sent and how the pages will be broken up into underlying RPCs, each of which will have their own completion and return code. In contrast, netfs is subrequest based, a single subrequest may contain multiple pages, and a single subrequest is initiated with issue_read() and terminated with netfs_subreq_terminated(). Thus, to utilze the netfs APIs, NFS needs some way to accommodate the netfs API requirement on the single response to the whole subrequest, while also minimizing disruptive changes to the NFS pgio layer. The approach taken with this patch is to allocate a small structure for each nfs_netfs_issue_read() call, store the final error and number of bytes successfully transferred in the structure, and update these values as each RPC completes. The refcount on the structure is used as a marker for the last RPC completion, is incremented in nfs_netfs_read_initiate(), and decremented inside nfs_netfs_read_completion(), when a nfs_pgio_header contains a valid pointer to the data. On the final put (which signals the final outstanding RPC is complete) in nfs_netfs_read_completion(), call netfs_subreq_terminated() with either the final error value (if one or more READs complete with an error) or the number of bytes successfully transferred (if all RPCs complete successfully). Note that when all RPCs complete successfully, the number of bytes transferred is capped to the length of the subrequest. Capping the transferred length to the subrequest length prevents "Subreq overread" warnings from netfs. This is due to the "aligned_len" in nfs_pageio_add_page(), and the corner case where NFS requests a full page at the end of the file, even when i_size reflects only a partial page (NFS overread). Signed-off-by: Dave Wysochanski Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- include/linux/nfs_page.h | 3 +++ include/linux/nfs_xdr.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index a2f1ca657623..aa9f4c6ebe26 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -105,6 +105,9 @@ struct nfs_pageio_descriptor { struct pnfs_layout_segment *pg_lseg; struct nfs_io_completion *pg_io_completion; struct nfs_direct_req *pg_dreq; +#ifdef CONFIG_NFS_FSCACHE + void *pg_netfs; +#endif unsigned int pg_bsize; /* default bsize for mirrors */ u32 pg_mirror_count; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e86cf6642d21..e196ef595908 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1619,6 +1619,9 @@ struct nfs_pgio_header { const struct nfs_rw_ops *rw_ops; struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; +#ifdef CONFIG_NFS_FSCACHE + void *netfs; +#endif int pnfs_error; int error; /* merge with pnfs_error */ -- cgit v1.2.3 From 0631d5e02a1c722b90c11a47dcb6d83ef88ab47b Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:07 -0500 Subject: NFS: Remove all NFSIOS_FSCACHE counters due to conversion to netfs API The old NFSIOS_FSCACHE counters are no longer accurate or useful with the conversion to the new netfs API. The new API does not have a page based interface, and so the counters in nfs_stat_fscachecounters are no longer obtainable. The new netfs the API has extensive statistics inside /proc/fs/fscache/stats so we no longer need NFS specific fscache stats. Note this also removes the 'fsc:' line from /proc/self/mountstats so it will be a user-visible change. Signed-off-by: Dave Wysochanski Reviewed-by: Jeff Layton Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- include/linux/nfs_iostat.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h index 027874c36c88..8d946089d151 100644 --- a/include/linux/nfs_iostat.h +++ b/include/linux/nfs_iostat.h @@ -119,16 +119,4 @@ enum nfs_stat_eventcounters { __NFSIOS_COUNTSMAX, }; -/* - * NFS local caching servicing counters - */ -enum nfs_stat_fscachecounters { - NFSIOS_FSCACHE_PAGES_READ_OK, - NFSIOS_FSCACHE_PAGES_READ_FAIL, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, - NFSIOS_FSCACHE_PAGES_UNCACHED, - __NFSIOS_FSCACHEMAX, -}; - #endif /* _LINUX_NFS_IOSTAT */ -- cgit v1.2.3 From 03f5bd75a4c19714a929a0f4e7bbf36b49e874c1 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:08 -0500 Subject: NFS: Remove fscache specific trace points and NFS_INO_FSCACHE bit The NFS specific trace points are no longer needed as tracing is well covered by netfs and fscache. Signed-off-by: Dave Wysochanski Reviewed-by: Jeff Layton Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- 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 041e79a48f7a..12bb868f9a18 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -281,7 +281,6 @@ struct nfs4_copy_state { #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_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ -- cgit v1.2.3 From 3db63daabe210af32a09533fe7d8d47c711a103c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 22 Mar 2023 09:27:04 +1100 Subject: NFSv3: handle out-of-order write replies. NFSv3 includes pre/post wcc attributes which allow the client to determine if all changes to the file have been made by the client itself, or if any might have been made by some other client. If there are gaps in the pre/post ctime sequence it must be assumed that some other client changed the file in that gap and the local cache must be suspect. The next time the file is opened the cache should be invalidated. Since Commit 1c341b777501 ("NFS: Add deferred cache invalidation for close-to-open consistency violations") in linux 5.3 the Linux client has been triggering this invalidation. The chunk in nfs_update_inode() in particularly triggers. Unfortunately Linux NFS assumes that all replies will be processed in the order sent, and will arrive in the order processed. This is not true in general. Consequently Linux NFS might ignore the wcc info in a WRITE reply because the reply is in response to a WRITE that was sent before some other request for which a reply has already been seen. This is detected by Linux using the gencount tests in nfs_inode_attr_cmp(). Also, when the gencount tests pass it is still possible that the request were processed on the server in a different order, and a gap seen in the ctime sequence might be filled in by a subsequent reply, so gaps should not immediately trigger delayed invalidation. The net result is that writing to a server and then reading the file back can result in going to the server for the read rather than serving it from cache - all because a couple of replies arrived out-of-order. This is a performance regression over kernels before 5.3, though the change in 5.3 is a correctness improvement. This has been seen with Linux writing to a Netapp server which occasionally re-orders requests. In testing the majority of requests were in-order, but a few (maybe 2 or three at a time) could be re-ordered. This patch addresses the problem by recording any gaps seen in the pre/post ctime sequence and not triggering invalidation until either there are too many gaps to fit in the table, or until there are no more active writes and the remaining gaps cannot be resolved. We allocate a table of 16 gaps on demand. If the allocation fails we revert to current behaviour which is of little cost as we are unlikely to be able to cache the writes anyway. In the table we store "start->end" pair when iversion is updated and "end<-start" pairs pre/post pairs reported by the server. Usually these exactly cancel out and so nothing is stored. When there are out-of-order replies we do store gaps and these will eventually be cancelled against later replies when this client is the only writer. If the final write is out-of-order there may be one gap remaining when the file is closed. This will be noticed and if there is precisely on gap and if the iversion can be advanced to match it, then we do so. This patch makes no attempt to handle directories correctly. The same problem potentially exists in the out-of-order replies to create/unlink requests can cause future lookup requires to be sent to the server unnecessarily. A similar scheme using the same primitives could be used to notice and handle out-of-order replies. Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 12bb868f9a18..279262057a92 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -195,6 +195,39 @@ struct nfs_inode { /* Open contexts for shared mmap writes */ struct list_head open_files; + /* Keep track of out-of-order replies. + * The ooo array contains start/end pairs of + * numbers from the changeid sequence when + * the inode's iversion has been updated. + * It also contains end/start pair (i.e. reverse order) + * of sections of the changeid sequence that have + * been seen in replies from the server. + * Normally these should match and when both + * A:B and B:A are found in ooo, they are both removed. + * And if a reply with A:B causes an iversion update + * of A:B, then neither are added. + * When a reply has pre_change that doesn't match + * iversion, then the changeid pair and any consequent + * change in iversion ARE added. Later replies + * might fill in the gaps, or possibly a gap is caused + * by a change from another client. + * When a file or directory is opened, if the ooo table + * is not empty, then we assume the gaps were due to + * another client and we invalidate the cached data. + * + * We can only track a limited number of concurrent gaps. + * Currently that limit is 16. + * We allocate the table on demand. If there is insufficient + * memory, then we probably cannot cache the file anyway + * so there is no loss. + */ + struct { + int cnt; + struct { + u64 start, end; + } gap[16]; + } *ooo; + #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ @@ -612,6 +645,20 @@ nfs_fileid_to_ino_t(u64 fileid) return ino; } +static inline void nfs_ooo_clear(struct nfs_inode *nfsi) +{ + nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; + kfree(nfsi->ooo); + nfsi->ooo = NULL; +} + +static inline bool nfs_ooo_test(struct nfs_inode *nfsi) +{ + return (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) || + (nfsi->ooo && nfsi->ooo->cnt > 0); + +} + #define NFS_JUKEBOX_RETRY_TIME (5 * HZ) /* We need to block new opens while a file is being unlinked. -- cgit v1.2.3 From 691d0b782066a6eeeecbfceb7910a8f6184e6105 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Tue, 18 Apr 2023 13:19:02 -0700 Subject: SUNRPC: remove the maximum number of retries in call_bind_status Currently call_bind_status places a hard limit of 3 to the number of retries on EACCES error. This limit was done to prevent NLM unlock requests from being hang forever when the server keeps returning garbage. However this change causes problem for cases when NLM service takes longer than 9 seconds to register with the port mapper after a restart. This patch removes this hard coded limit and let the RPC handles the retry based on the standard hard/soft task semantics. Fixes: 0b760113a3a1 ("NLM: Don't hang forever on NLM unlock requests") Reported-by: Helen Chao Tested-by: Helen Chao Signed-off-by: Dai Ngo Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/sunrpc/sched.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index b8ca3ecaf8d7..8ada7dc802d3 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -90,8 +90,7 @@ struct rpc_task { #endif unsigned char tk_priority : 2,/* Task priority */ tk_garb_retry : 2, - tk_cred_retry : 2, - tk_rebind_retry : 2; + tk_cred_retry : 2; }; typedef void (*rpc_action)(struct rpc_task *); -- cgit v1.2.3 From fbd2a05f29a95d5b42b294bf47e55a711424965b Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Thu, 6 Apr 2023 15:16:52 -0400 Subject: NFSv4.2: Rework scratch handling for READ_PLUS Instead of using a tiny, static scratch buffer, we should use a kmalloc()-ed buffer that is allocated when checking for read plus usage. This lets us use the buffer before decoding any part of the READ_PLUS operation instead of setting it right before segment decoding, meaning it should be a little more robust. 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 e196ef595908..29a1b39794bf 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -670,6 +670,7 @@ struct nfs_pgio_res { struct { unsigned int replen; /* used by read */ int eof; /* used by read */ + void * scratch; /* used by read */ }; struct { struct nfs_writeverf * verf; /* used by write */ -- cgit v1.2.3