diff options
Diffstat (limited to 'include/linux/nfs_fs.h')
| -rw-r--r-- | include/linux/nfs_fs.h | 275 |
1 files changed, 189 insertions, 86 deletions
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a2c6455ea3fa..67ae2c3f41d2 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -31,6 +31,10 @@ #include <linux/sunrpc/auth.h> #include <linux/sunrpc/clnt.h> +#ifdef CONFIG_NFS_FSCACHE +#include <linux/netfs.h> +#endif + #include <linux/nfs.h> #include <linux/nfs2.h> #include <linux/nfs3.h> @@ -41,9 +45,14 @@ #include <linux/mempool.h> /* - * These are the default flags for swap requests + * These are the default for number of transports to different server IPs */ -#define NFS_RPC_SWAPFLAGS (RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS) +#define NFS_MAX_TRANSPORTS 16 + +/* + * Size of the NFS directory verifier + */ +#define NFS_DIR_VERIFIER_SIZE 2 /* * NFSv3/v4 Access mode cache entry @@ -51,7 +60,10 @@ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; - const struct cred * cred; + kuid_t fsuid; + kgid_t fsgid; + struct group_info *group_info; + u64 timestamp; __u32 mask; struct rcu_head rcu_head; }; @@ -65,34 +77,58 @@ 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; fl_owner_t flock_owner; struct dentry *dentry; const struct cred *cred; - struct rpc_cred *ll_cred; /* low-level cred - use to check for expiry */ + struct rpc_cred __rcu *ll_cred; /* low-level cred - use to check for expiry */ struct nfs4_state *state; fmode_t mode; + int error; unsigned long flags; -#define NFS_CONTEXT_RESEND_WRITES (1) #define NFS_CONTEXT_BAD (2) #define NFS_CONTEXT_UNLOCK (3) - int error; +#define NFS_CONTEXT_FILE_OPEN (4) - 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 { struct list_head list; - const struct cred *cred; + atomic_t cache_hits; + atomic_t cache_misses; unsigned long attr_gencount; + __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; - __u64 dup_cookie; - signed char duped; + __u64 last_cookie; + pgoff_t page_index; + unsigned int dtsize; + bool force_clear; + bool eof; + struct rcu_head rcu_head; }; /* @@ -143,35 +179,72 @@ struct nfs_inode { unsigned long attrtimeo_timestamp; unsigned long attr_gencount; - /* "Generation counter" for the attribute cache. This is - * bumped whenever we update the metadata on the - * server. - */ - unsigned long cache_change_attribute; struct rb_root access_cache; struct list_head access_cache_entry_lru; struct list_head access_cache_inode_lru; - /* - * This is the cookie verifier used for NFSv3 readdir - * operations - */ - __be32 cookieverf[2]; - - atomic_long_t nrequests; - struct nfs_mds_commit_info commit_info; + union { + /* Directory */ + struct { + /* "Generation counter" for the attribute cache. + * This is bumped whenever we update the metadata + * on the server. + */ + unsigned long cache_change_attribute; + /* + * This is the cookie verifier used for NFSv3 readdir + * operations + */ + __be32 cookieverf[NFS_DIR_VERIFIER_SIZE]; + /* Readers: in-flight sillydelete RPC calls */ + /* Writers: rmdir */ + struct rw_semaphore rmdir_sem; + }; + /* Regular file */ + struct { + atomic_long_t nrequests; + atomic_long_t redirtied_pages; + struct nfs_mds_commit_info commit_info; + struct mutex commit_mutex; + }; + }; /* Open contexts for shared mmap writes */ struct list_head open_files; - /* Readers: in-flight sillydelete RPC calls */ - /* Writers: rmdir */ - struct rw_semaphore rmdir_sem; - struct mutex commit_mutex; - - /* track last access to cached pages */ - unsigned long page_index; + /* 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; @@ -186,14 +259,15 @@ 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 { @@ -229,7 +303,6 @@ 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 */ @@ -241,22 +314,24 @@ struct nfs4_copy_state { BIT(13) /* Deferred cache invalidation */ #define NFS_INO_INVALID_BLOCKS BIT(14) /* cached blocks are invalid */ #define NFS_INO_INVALID_XATTR BIT(15) /* xattrs are invalid */ +#define NFS_INO_INVALID_NLINK BIT(16) /* cached nlinks is invalid */ +#define NFS_INO_INVALID_MODE BIT(17) /* cached mode is invalid */ #define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ | NFS_INO_INVALID_CTIME \ | NFS_INO_INVALID_MTIME \ | NFS_INO_INVALID_SIZE \ + | NFS_INO_INVALID_NLINK \ + | NFS_INO_INVALID_MODE \ | NFS_INO_INVALID_OTHER) /* inode metadata is invalid */ /* * 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_FSCACHE (5) /* inode can be cached by FS-Cache */ -#define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ +#define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ @@ -309,15 +384,6 @@ 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; @@ -333,17 +399,15 @@ 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); } -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; } @@ -368,27 +432,28 @@ extern void nfs_zap_caches(struct inode *); extern void nfs_set_inode_stale(struct inode *inode); extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *); + struct nfs_fattr *); struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); -extern int nfs_getattr(const struct path *, struct kstat *, u32, unsigned int); -extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); +extern int nfs_getattr(struct mnt_idmap *, const struct path *, + struct kstat *, u32, unsigned int); +extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *, const struct cred *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); -extern int nfs_permission(struct inode *, int); +extern int nfs_permission(struct mnt_idmap *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); -extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); +extern int nfs_revalidate_inode(struct inode *inode, unsigned long flags); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); +extern int nfs_clear_invalid_mapping(struct address_space *mapping); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); -extern int nfs_setattr(struct dentry *, struct iattr *); +extern int nfs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); -extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, - struct nfs4_label *label); +extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode); @@ -404,9 +469,22 @@ extern void nfs_fattr_set_barrier(struct nfs_fattr *fattr); extern unsigned long nfs_inc_attr_generation_counter(void); extern struct nfs_fattr *nfs_alloc_fattr(void); +extern struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server); + +static inline void nfs4_label_free(struct nfs4_label *label) +{ +#ifdef CONFIG_NFS_V4_SECURITY_LABEL + if (label) { + kfree(label->label); + kfree(label); + } +#endif +} static inline void nfs_free_fattr(const struct nfs_fattr *fattr) { + if (fattr) + nfs4_label_free(fattr->label); kfree(fattr); } @@ -476,11 +554,11 @@ 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); +int nfs_swap_rw(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 @@ -494,14 +572,16 @@ extern void nfs_set_verifier(struct dentry * dentry, unsigned long verf); extern void nfs_clear_verifier_delegated(struct inode *inode); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, - struct nfs_fh *fh, struct nfs_fattr *fattr, - struct nfs4_label *label); + struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, - struct nfs_fattr *fattr, struct nfs4_label *label); + struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); -extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, - bool may_block); +extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, + u32 *mask, bool may_block); +extern int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned int open_flags, + umode_t mode); /* * linux/fs/nfs/symlink.c @@ -536,10 +616,10 @@ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *); * linux/fs/nfs/write.c */ extern int nfs_congestion_kb; -extern int nfs_writepage(struct page *page, struct writeback_control *wbc); extern int nfs_writepages(struct address_space *, struct writeback_control *); -extern int nfs_flush_incompatible(struct file *file, struct page *page); -extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int); +extern int nfs_flush_incompatible(struct file *file, struct folio *folio); +extern int nfs_update_folio(struct file *file, struct folio *folio, + unsigned int offset, unsigned int count); /* * Try to write back everything synchronously (but check the @@ -547,26 +627,26 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned */ extern int nfs_sync_inode(struct inode *inode); 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_wb_folio(struct inode *inode, struct folio *folio); +int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); 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); +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo); +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) { - return atomic_long_read(&NFS_I(inode)->nrequests) != 0; + if (S_ISREG(inode->i_mode)) + return atomic_long_read(&NFS_I(inode)->nrequests) != 0; + return false; } /* * 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); -extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, - struct page *); +int nfs_read_folio(struct file *, struct folio *); +void nfs_readahead(struct readahead_control *); /* * inline functions @@ -586,8 +666,31 @@ 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. + * If it is opened *before* we decide to unlink, we will silly-rename + * instead. If it is opened *after*, then we need to create or will fail. + * If we allow the two to race, we could end up with a file that is open + * but deleted on the server resulting in ESTALE. + * So use ->d_fsdata to record when the unlink is happening + * and block dentry revalidation while it is set. + */ +#define NFS_FSDATA_BLOCKED ((void*)1) # undef ifdebug # ifdef NFS_DEBUG |