diff options
Diffstat (limited to 'fs')
64 files changed, 2106 insertions, 1760 deletions
diff --git a/fs/9p/cache.c b/fs/9p/cache.c index 55e108e5e133..1c8dc696d516 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -49,22 +49,20 @@ int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses, void v9fs_cache_inode_get_cookie(struct inode *inode) { - struct v9fs_inode *v9inode; + struct v9fs_inode *v9inode = V9FS_I(inode); struct v9fs_session_info *v9ses; __le32 version; __le64 path; if (!S_ISREG(inode->i_mode)) return; - - v9inode = V9FS_I(inode); - if (WARN_ON(v9inode->fscache)) + if (WARN_ON(v9fs_inode_cookie(v9inode))) return; version = cpu_to_le32(v9inode->qid.version); path = cpu_to_le64(v9inode->qid.path); v9ses = v9fs_inode2v9ses(inode); - v9inode->fscache = + v9inode->netfs_ctx.cache = fscache_acquire_cookie(v9fs_session_cache(v9ses), 0, &path, sizeof(path), @@ -72,5 +70,5 @@ void v9fs_cache_inode_get_cookie(struct inode *inode) i_size_read(&v9inode->vfs_inode)); p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n", - inode, v9inode->fscache); + inode, v9fs_inode_cookie(v9inode)); } diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 08f65c40af4f..e28ddf763b3b 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -623,9 +623,7 @@ static void v9fs_sysfs_cleanup(void) static void v9fs_inode_init_once(void *foo) { struct v9fs_inode *v9inode = (struct v9fs_inode *)foo; -#ifdef CONFIG_9P_FSCACHE - v9inode->fscache = NULL; -#endif + memset(&v9inode->qid, 0, sizeof(v9inode->qid)); inode_init_once(&v9inode->vfs_inode); } diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index bc8b30205d36..ec0e8df3b2eb 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -9,6 +9,7 @@ #define FS_9P_V9FS_H #include <linux/backing-dev.h> +#include <linux/netfs.h> /** * enum p9_session_flags - option flags for each 9P session @@ -108,14 +109,15 @@ struct v9fs_session_info { #define V9FS_INO_INVALID_ATTR 0x01 struct v9fs_inode { -#ifdef CONFIG_9P_FSCACHE - struct fscache_cookie *fscache; -#endif + struct { + /* These must be contiguous */ + struct inode vfs_inode; /* the VFS's inode record */ + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; struct p9_qid qid; unsigned int cache_validity; struct p9_fid *writeback_fid; struct mutex v_mutex; - struct inode vfs_inode; }; static inline struct v9fs_inode *V9FS_I(const struct inode *inode) @@ -126,7 +128,7 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode) static inline struct fscache_cookie *v9fs_inode_cookie(struct v9fs_inode *v9inode) { #ifdef CONFIG_9P_FSCACHE - return v9inode->fscache; + return netfs_i_cookie(&v9inode->vfs_inode); #else return NULL; #endif @@ -163,6 +165,7 @@ extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses, extern const struct inode_operations v9fs_dir_inode_operations_dotl; extern const struct inode_operations v9fs_file_inode_operations_dotl; extern const struct inode_operations v9fs_symlink_inode_operations_dotl; +extern const struct netfs_request_ops v9fs_req_ops; extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid, struct super_block *sb, int new); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 76956c9d2af9..501128188343 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -28,12 +28,12 @@ #include "fid.h" /** - * v9fs_req_issue_op - Issue a read from 9P + * v9fs_issue_read - Issue a read from 9P * @subreq: The read to make */ -static void v9fs_req_issue_op(struct netfs_read_subrequest *subreq) +static void v9fs_issue_read(struct netfs_io_subrequest *subreq) { - struct netfs_read_request *rreq = subreq->rreq; + struct netfs_io_request *rreq = subreq->rreq; struct p9_fid *fid = rreq->netfs_priv; struct iov_iter to; loff_t pos = subreq->start + subreq->transferred; @@ -52,20 +52,21 @@ static void v9fs_req_issue_op(struct netfs_read_subrequest *subreq) } /** - * v9fs_init_rreq - Initialise a read request + * v9fs_init_request - Initialise a read request * @rreq: The read request * @file: The file being read from */ -static void v9fs_init_rreq(struct netfs_read_request *rreq, struct file *file) +static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file) { struct p9_fid *fid = file->private_data; refcount_inc(&fid->count); rreq->netfs_priv = fid; + return 0; } /** - * v9fs_req_cleanup - Cleanup request initialized by v9fs_init_rreq + * v9fs_req_cleanup - Cleanup request initialized by v9fs_init_request * @mapping: unused mapping of request to cleanup * @priv: private data to cleanup, a fid, guaranted non-null. */ @@ -77,21 +78,10 @@ static void v9fs_req_cleanup(struct address_space *mapping, void *priv) } /** - * v9fs_is_cache_enabled - Determine if caching is enabled for an inode - * @inode: The inode to check - */ -static bool v9fs_is_cache_enabled(struct inode *inode) -{ - struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(inode)); - - return fscache_cookie_enabled(cookie) && cookie->cache_priv; -} - -/** * v9fs_begin_cache_operation - Begin a cache operation for a read * @rreq: The read request */ -static int v9fs_begin_cache_operation(struct netfs_read_request *rreq) +static int v9fs_begin_cache_operation(struct netfs_io_request *rreq) { #ifdef CONFIG_9P_FSCACHE struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(rreq->inode)); @@ -102,37 +92,14 @@ static int v9fs_begin_cache_operation(struct netfs_read_request *rreq) #endif } -static const struct netfs_read_request_ops v9fs_req_ops = { - .init_rreq = v9fs_init_rreq, - .is_cache_enabled = v9fs_is_cache_enabled, +const struct netfs_request_ops v9fs_req_ops = { + .init_request = v9fs_init_request, .begin_cache_operation = v9fs_begin_cache_operation, - .issue_op = v9fs_req_issue_op, + .issue_read = v9fs_issue_read, .cleanup = v9fs_req_cleanup, }; /** - * v9fs_vfs_readpage - read an entire page in from 9P - * @file: file being read - * @page: structure to page - * - */ -static int v9fs_vfs_readpage(struct file *file, struct page *page) -{ - struct folio *folio = page_folio(page); - - return netfs_readpage(file, folio, &v9fs_req_ops, NULL); -} - -/** - * v9fs_vfs_readahead - read a set of pages from 9P - * @ractl: The readahead parameters - */ -static void v9fs_vfs_readahead(struct readahead_control *ractl) -{ - netfs_readahead(ractl, &v9fs_req_ops, NULL); -} - -/** * v9fs_release_page - release the private state associated with a page * @page: The page to be released * @gfp: The caller's allocation restrictions @@ -308,8 +275,7 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata, - &v9fs_req_ops, NULL); + retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata); if (retval < 0) return retval; @@ -370,8 +336,8 @@ static bool v9fs_dirty_folio(struct address_space *mapping, struct folio *folio) #endif const struct address_space_operations v9fs_addr_operations = { - .readpage = v9fs_vfs_readpage, - .readahead = v9fs_vfs_readahead, + .readpage = netfs_readpage, + .readahead = netfs_readahead, .dirty_folio = v9fs_dirty_folio, .writepage = v9fs_vfs_writepage, .write_begin = v9fs_write_begin, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 84c3cf7dffa5..55367ecb9442 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -231,9 +231,6 @@ struct inode *v9fs_alloc_inode(struct super_block *sb) v9inode = alloc_inode_sb(sb, v9fs_inode_cache, GFP_KERNEL); if (!v9inode) return NULL; -#ifdef CONFIG_9P_FSCACHE - v9inode->fscache = NULL; -#endif v9inode->writeback_fid = NULL; v9inode->cache_validity = 0; mutex_init(&v9inode->v_mutex); @@ -250,6 +247,14 @@ void v9fs_free_inode(struct inode *inode) kmem_cache_free(v9fs_inode_cache, V9FS_I(inode)); } +/* + * Set parameters for the netfs library + */ +static void v9fs_set_netfs_context(struct inode *inode) +{ + netfs_i_context_init(inode, &v9fs_req_ops); +} + int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t rdev) { @@ -338,6 +343,8 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, err = -EINVAL; goto error; } + + v9fs_set_netfs_context(inode); error: return err; diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index db832cc931c8..f120bcb8bf73 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -76,6 +76,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) /* there shouldn't be an existing inode */ BUG_ON(!(inode->i_state & I_NEW)); + netfs_i_context_init(inode, NULL); inode->i_size = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; if (root) { diff --git a/fs/afs/file.c b/fs/afs/file.c index 0f9fdb284a20..26292a110a8f 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -19,13 +19,11 @@ #include "internal.h" static int afs_file_mmap(struct file *file, struct vm_area_struct *vma); -static int afs_readpage(struct file *file, struct page *page); static int afs_symlink_readpage(struct file *file, struct page *page); static void afs_invalidate_folio(struct folio *folio, size_t offset, size_t length); static int afs_releasepage(struct page *page, gfp_t gfp_flags); -static void afs_readahead(struct readahead_control *ractl); static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); static void afs_vm_open(struct vm_area_struct *area); static void afs_vm_close(struct vm_area_struct *area); @@ -52,8 +50,8 @@ const struct inode_operations afs_file_inode_operations = { }; const struct address_space_operations afs_file_aops = { - .readpage = afs_readpage, - .readahead = afs_readahead, + .readpage = netfs_readpage, + .readahead = netfs_readahead, .dirty_folio = afs_dirty_folio, .launder_folio = afs_launder_folio, .releasepage = afs_releasepage, @@ -240,7 +238,7 @@ void afs_put_read(struct afs_read *req) static void afs_fetch_data_notify(struct afs_operation *op) { struct afs_read *req = op->fetch.req; - struct netfs_read_subrequest *subreq = req->subreq; + struct netfs_io_subrequest *subreq = req->subreq; int error = op->error; if (error == -ECONNABORTED) @@ -310,7 +308,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req) return afs_do_sync_operation(op); } -static void afs_req_issue_op(struct netfs_read_subrequest *subreq) +static void afs_issue_read(struct netfs_io_subrequest *subreq) { struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode); struct afs_read *fsreq; @@ -359,19 +357,13 @@ static int afs_symlink_readpage(struct file *file, struct page *page) return ret; } -static void afs_init_rreq(struct netfs_read_request *rreq, struct file *file) +static int afs_init_request(struct netfs_io_request *rreq, struct file *file) { rreq->netfs_priv = key_get(afs_file_key(file)); + return 0; } -static bool afs_is_cache_enabled(struct inode *inode) -{ - struct fscache_cookie *cookie = afs_vnode_cache(AFS_FS_I(inode)); - - return fscache_cookie_enabled(cookie) && cookie->cache_priv; -} - -static int afs_begin_cache_operation(struct netfs_read_request *rreq) +static int afs_begin_cache_operation(struct netfs_io_request *rreq) { #ifdef CONFIG_AFS_FSCACHE struct afs_vnode *vnode = AFS_FS_I(rreq->inode); @@ -396,27 +388,14 @@ static void afs_priv_cleanup(struct address_space *mapping, void *netfs_priv) key_put(netfs_priv); } -const struct netfs_read_request_ops afs_req_ops = { - .init_rreq = afs_init_rreq, - .is_cache_enabled = afs_is_cache_enabled, +const struct netfs_request_ops afs_req_ops = { + .init_request = afs_init_request, .begin_cache_operation = afs_begin_cache_operation, .check_write_begin = afs_check_write_begin, - .issue_op = afs_req_issue_op, + .issue_read = afs_issue_read, .cleanup = afs_priv_cleanup, }; -static int afs_readpage(struct file *file, struct page *page) -{ - struct folio *folio = page_folio(page); - - return netfs_readpage(file, folio, &afs_req_ops, NULL); -} - -static void afs_readahead(struct readahead_control *ractl) -{ - netfs_readahead(ractl, &afs_req_ops, NULL); -} - int afs_write_inode(struct inode *inode, struct writeback_control *wbc) { fscache_unpin_writeback(wbc, afs_vnode_cache(AFS_FS_I(inode))); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 5964f8aee090..2fe402483ad5 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -54,6 +54,14 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren } /* + * Set parameters for the netfs library + */ +static void afs_set_netfs_context(struct afs_vnode *vnode) +{ + netfs_i_context_init(&vnode->vfs_inode, &afs_req_ops); +} + +/* * Initialise an inode from the vnode status. */ static int afs_inode_init_from_status(struct afs_operation *op, @@ -128,6 +136,7 @@ static int afs_inode_init_from_status(struct afs_operation *op, } afs_set_i_size(vnode, status->size); + afs_set_netfs_context(vnode); vnode->invalid_before = status->data_version; inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); @@ -237,6 +246,7 @@ static void afs_apply_status(struct afs_operation *op, * idea of what the size should be that's not the same as * what's on the server. */ + vnode->netfs_ctx.remote_i_size = status->size; if (change_size) { afs_set_i_size(vnode, status->size); inode->i_ctime = t; @@ -420,7 +430,7 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) struct afs_vnode_cache_aux aux; if (vnode->status.type != AFS_FTYPE_FILE) { - vnode->cache = NULL; + vnode->netfs_ctx.cache = NULL; return; } @@ -430,12 +440,14 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) key.vnode_id_ext[1] = htonl(vnode->fid.vnode_hi); afs_set_cache_aux(vnode, &aux); - vnode->cache = fscache_acquire_cookie( - vnode->volume->cache, - vnode->status.type == AFS_FTYPE_FILE ? 0 : FSCACHE_ADV_SINGLE_CHUNK, - &key, sizeof(key), - &aux, sizeof(aux), - vnode->status.size); + afs_vnode_set_cache(vnode, + fscache_acquire_cookie( + vnode->volume->cache, + vnode->status.type == AFS_FTYPE_FILE ? + 0 : FSCACHE_ADV_SINGLE_CHUNK, + &key, sizeof(key), + &aux, sizeof(aux), + vnode->status.size)); #endif } @@ -528,6 +540,7 @@ struct inode *afs_root_iget(struct super_block *sb, struct key *key) vnode = AFS_FS_I(inode); vnode->cb_v_break = as->volume->cb_v_break, + afs_set_netfs_context(vnode); op = afs_alloc_operation(key, as->volume); if (IS_ERR(op)) { @@ -786,11 +799,8 @@ void afs_evict_inode(struct inode *inode) afs_put_wb_key(wbk); } -#ifdef CONFIG_AFS_FSCACHE - fscache_relinquish_cookie(vnode->cache, + fscache_relinquish_cookie(afs_vnode_cache(vnode), test_bit(AFS_VNODE_DELETED, &vnode->flags)); - vnode->cache = NULL; -#endif afs_prune_wb_keys(vnode); afs_put_permits(rcu_access_pointer(vnode->permit_cache)); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index dc5032e10244..7b7ef945dc78 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -207,7 +207,7 @@ struct afs_read { loff_t file_size; /* File size returned by server */ struct key *key; /* The key to use to reissue the read */ struct afs_vnode *vnode; /* The file being read into. */ - struct netfs_read_subrequest *subreq; /* Fscache helper read request this belongs to */ + struct netfs_io_subrequest *subreq; /* Fscache helper read request this belongs to */ afs_dataversion_t data_version; /* Version number returned by server */ refcount_t usage; unsigned int call_debug_id; @@ -619,15 +619,16 @@ enum afs_lock_state { * leak from one inode to another. */ struct afs_vnode { - struct inode vfs_inode; /* the VFS's inode record */ + struct { + /* These must be contiguous */ + struct inode vfs_inode; /* the VFS's inode record */ + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; struct afs_volume *volume; /* volume on which vnode resides */ struct afs_fid fid; /* the file identifier for this inode */ struct afs_file_status status; /* AFS status info for this file */ afs_dataversion_t invalid_before; /* Child dentries are invalid before this */ -#ifdef CONFIG_AFS_FSCACHE - struct fscache_cookie *cache; /* caching cookie */ -#endif struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */ struct mutex io_lock; /* Lock for serialising I/O on this mutex */ struct rw_semaphore validate_lock; /* lock for validating this vnode */ @@ -674,12 +675,20 @@ struct afs_vnode { static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode) { #ifdef CONFIG_AFS_FSCACHE - return vnode->cache; + return netfs_i_cookie(&vnode->vfs_inode); #else return NULL; #endif } +static inline void afs_vnode_set_cache(struct afs_vnode *vnode, + struct fscache_cookie *cookie) +{ +#ifdef CONFIG_AFS_FSCACHE + vnode->netfs_ctx.cache = cookie; +#endif +} + /* * cached security record for one user's attempt to access a vnode */ @@ -1063,7 +1072,7 @@ extern const struct address_space_operations afs_file_aops; extern const struct address_space_operations afs_symlink_aops; extern const struct inode_operations afs_file_inode_operations; extern const struct file_operations afs_file_operations; -extern const struct netfs_read_request_ops afs_req_ops; +extern const struct netfs_request_ops afs_req_ops; extern int afs_cache_wb_key(struct afs_vnode *, struct afs_file *); extern void afs_put_wb_key(struct afs_wb_key *); diff --git a/fs/afs/super.c b/fs/afs/super.c index 7592c0f469f1..1fea195b0b27 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -688,13 +688,11 @@ static struct inode *afs_alloc_inode(struct super_block *sb) /* Reset anything that shouldn't leak from one inode to the next. */ memset(&vnode->fid, 0, sizeof(vnode->fid)); memset(&vnode->status, 0, sizeof(vnode->status)); + afs_vnode_set_cache(vnode, NULL); vnode->volume = NULL; vnode->lock_key = NULL; vnode->permit_cache = NULL; -#ifdef CONFIG_AFS_FSCACHE - vnode->cache = NULL; -#endif vnode->flags = 1 << AFS_VNODE_UNSET; vnode->lock_state = AFS_VNODE_LOCK_NONE; diff --git a/fs/afs/write.c b/fs/afs/write.c index e1c17081d18e..6bcf1475511b 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -60,8 +60,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata, - &afs_req_ops, NULL); + ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata); if (ret < 0) return ret; @@ -355,9 +354,10 @@ static const struct afs_operation_ops afs_store_data_operation = { static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t pos, bool laundering) { + struct netfs_i_context *ictx = &vnode->netfs_ctx; struct afs_operation *op; struct afs_wb_key *wbk = NULL; - loff_t size = iov_iter_count(iter), i_size; + loff_t size = iov_iter_count(iter); int ret = -ENOKEY; _enter("%s{%llx:%llu.%u},%llx,%llx", @@ -379,15 +379,13 @@ static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t return -ENOMEM; } - i_size = i_size_read(&vnode->vfs_inode); - afs_op_set_vnode(op, 0, vnode); op->file[0].dv_delta = 1; op->file[0].modification = true; op->store.write_iter = iter; op->store.pos = pos; op->store.size = size; - op->store.i_size = max(pos + size, i_size); + op->store.i_size = max(pos + size, ictx->remote_i_size); op->store.laundering = laundering; op->mtime = vnode->vfs_inode.i_mtime; op->flags |= AFS_OPERATION_UNINTR; diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index bc7c7a7d9260..9dc81e781f2b 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -380,18 +380,18 @@ presubmission_error: * Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ -static enum netfs_read_source cachefiles_prepare_read(struct netfs_read_subrequest *subreq, +static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *subreq, loff_t i_size) { enum cachefiles_prepare_read_trace why; - struct netfs_read_request *rreq = subreq->rreq; + struct netfs_io_request *rreq = subreq->rreq; struct netfs_cache_resources *cres = &rreq->cache_resources; struct cachefiles_object *object; struct cachefiles_cache *cache; struct fscache_cookie *cookie = fscache_cres_cookie(cres); const struct cred *saved_cred; struct file *file = cachefiles_cres_file(cres); - enum netfs_read_source ret = NETFS_DOWNLOAD_FROM_SERVER; + enum netfs_io_source ret = NETFS_DOWNLOAD_FROM_SERVER; loff_t off, to; ino_t ino = file ? file_inode(file)->i_ino : 0; @@ -404,7 +404,7 @@ static enum netfs_read_source cachefiles_prepare_read(struct netfs_read_subreque } if (test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) { - __set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + __set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); why = cachefiles_trace_read_no_data; goto out_no_object; } @@ -473,7 +473,7 @@ static enum netfs_read_source cachefiles_prepare_read(struct netfs_read_subreque goto out; download_and_store: - __set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + __set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); out: cachefiles_end_secure(cache, saved_cred); out_no_object: diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c7a0ab0d298b..aa25bffd4823 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -182,7 +182,7 @@ static int ceph_releasepage(struct page *page, gfp_t gfp) return 1; } -static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq) +static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq) { struct inode *inode = rreq->inode; struct ceph_inode_info *ci = ceph_inode(inode); @@ -199,7 +199,7 @@ static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq) rreq->len = roundup(rreq->len, lo->stripe_unit); } -static bool ceph_netfs_clamp_length(struct netfs_read_subrequest *subreq) +static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq) { struct inode *inode = subreq->rreq->inode; struct ceph_fs_client *fsc = ceph_inode_to_client(inode); @@ -218,7 +218,7 @@ static void finish_netfs_read(struct ceph_osd_request *req) { struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode); struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0); - struct netfs_read_subrequest *subreq = req->r_priv; + struct netfs_io_subrequest *subreq = req->r_priv; int num_pages; int err = req->r_result; @@ -244,9 +244,9 @@ static void finish_netfs_read(struct ceph_osd_request *req) iput(req->r_inode); } -static bool ceph_netfs_issue_op_inline(struct netfs_read_subrequest *subreq) +static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) { - struct netfs_read_request *rreq = subreq->rreq; + struct netfs_io_request *rreq = subreq->rreq; struct inode *inode = rreq->inode; struct ceph_mds_reply_info_parsed *rinfo; struct ceph_mds_reply_info_in *iinfo; @@ -258,7 +258,7 @@ static bool ceph_netfs_issue_op_inline(struct netfs_read_subrequest *subreq) size_t len; __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - __clear_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); if (subreq->start >= inode->i_size) goto out; @@ -297,9 +297,9 @@ out: return true; } -static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq) +static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) { - struct netfs_read_request *rreq = subreq->rreq; + struct netfs_io_request *rreq = subreq->rreq; struct inode *inode = rreq->inode; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); @@ -353,6 +353,45 @@ out: dout("%s: result %d\n", __func__, err); } +static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) +{ + struct inode *inode = rreq->inode; + int got = 0, want = CEPH_CAP_FILE_CACHE; + int ret = 0; + + if (rreq->origin != NETFS_READAHEAD) + return 0; + + if (file) { + struct ceph_rw_context *rw_ctx; + struct ceph_file_info *fi = file->private_data; + + rw_ctx = ceph_find_rw_context(fi); + if (rw_ctx) + return 0; + } + + /* + * readahead callers do not necessarily hold Fcb caps + * (e.g. fadvise, madvise). + */ + ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got); + if (ret < 0) { + dout("start_read %p, error getting cap\n", inode); + return ret; + } + + if (!(got & want)) { + dout("start_read %p, no cache cap\n", inode); + return -EACCES; + } + if (ret == 0) + return -EACCES; + + rreq->netfs_priv = (void *)(uintptr_t)got; + return 0; +} + static void ceph_readahead_cleanup(struct address_space *mapping, void *priv) { struct inode *inode = mapping->host; @@ -363,64 +402,16 @@ static void ceph_readahead_cleanup(struct address_space *mapping, void *priv) ceph_put_cap_refs(ci, got); } -static const struct netfs_read_request_ops ceph_netfs_read_ops = { - .is_cache_enabled = ceph_is_cache_enabled, +const struct netfs_request_ops ceph_netfs_ops = { + .init_request = ceph_init_request, .begin_cache_operation = ceph_begin_cache_operation, - .issue_op = ceph_netfs_issue_op, + .issue_read = ceph_netfs_issue_read, .expand_readahead = ceph_netfs_expand_readahead, .clamp_length = ceph_netfs_clamp_length, .check_write_begin = ceph_netfs_check_write_begin, .cleanup = ceph_readahead_cleanup, }; -/* read a single page, without unlocking it. */ -static int ceph_readpage(struct file *file, struct page *subpage) -{ - struct folio *folio = page_folio(subpage); - struct inode *inode = file_inode(file); - struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_vino vino = ceph_vino(inode); - size_t len = folio_size(folio); - u64 off = folio_file_pos(folio); - - dout("readpage ino %llx.%llx file %p off %llu len %zu folio %p index %lu\n inline %d", - vino.ino, vino.snap, file, off, len, folio, folio_index(folio), - ci->i_inline_version != CEPH_INLINE_NONE); - - return netfs_readpage(file, folio, &ceph_netfs_read_ops, NULL); -} - -static void ceph_readahead(struct readahead_control *ractl) -{ - struct inode *inode = file_inode(ractl->file); - struct ceph_file_info *fi = ractl->file->private_data; - struct ceph_rw_context *rw_ctx; - int got = 0; - int ret = 0; - - if (ceph_inode(inode)->i_inline_version != CEPH_INLINE_NONE) - return; - - rw_ctx = ceph_find_rw_context(fi); - if (!rw_ctx) { - /* - * readahead callers do not necessarily hold Fcb caps - * (e.g. fadvise, madvise). - */ - int want = CEPH_CAP_FILE_CACHE; - - ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got); - if (ret < 0) - dout("start_read %p, error getting cap\n", inode); - else if (!(got & want)) - dout("start_read %p, no cache cap\n", inode); - - if (ret <= 0) - return; - } - netfs_readahead(ractl, &ceph_netfs_read_ops, (void *)(uintptr_t)got); -} - #ifdef CONFIG_CEPH_FSCACHE static void ceph_set_page_fscache(struct page *page) { @@ -1327,8 +1318,7 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, struct folio *folio = NULL; int r; - r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL, - &ceph_netfs_read_ops, NULL); + r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL); if (r == 0) folio_wait_fscache(folio); if (r < 0) { @@ -1382,8 +1372,8 @@ out: } const struct address_space_operations ceph_aops = { - .readpage = ceph_readpage, - .readahead = ceph_readahead, + .readpage = netfs_readpage, + .readahead = netfs_readahead, .writepage = ceph_writepage, .writepages = ceph_writepages_start, .write_begin = ceph_write_begin, diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 7d22850623ef..ddea99922073 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -29,26 +29,25 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) if (!(inode->i_state & I_NEW)) return; - WARN_ON_ONCE(ci->fscache); + WARN_ON_ONCE(ci->netfs_ctx.cache); - ci->fscache = fscache_acquire_cookie(fsc->fscache, 0, - &ci->i_vino, sizeof(ci->i_vino), - &ci->i_version, sizeof(ci->i_version), - i_size_read(inode)); + ci->netfs_ctx.cache = + fscache_acquire_cookie(fsc->fscache, 0, + &ci->i_vino, sizeof(ci->i_vino), + &ci->i_version, sizeof(ci->i_version), + i_size_read(inode)); } -void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci) +void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci) { - struct fscache_cookie *cookie = ci->fscache; - - fscache_relinquish_cookie(cookie, false); + fscache_relinquish_cookie(ceph_fscache_cookie(ci), false); } void ceph_fscache_use_cookie(struct inode *inode, bool will_modify) { struct ceph_inode_info *ci = ceph_inode(inode); - fscache_use_cookie(ci->fscache, will_modify); + fscache_use_cookie(ceph_fscache_cookie(ci), will_modify); } void ceph_fscache_unuse_cookie(struct inode *inode, bool update) @@ -58,9 +57,10 @@ void ceph_fscache_unuse_cookie(struct inode *inode, bool update) if (update) { loff_t i_size = i_size_read(inode); - fscache_unuse_cookie(ci->fscache, &ci->i_version, &i_size); + fscache_unuse_cookie(ceph_fscache_cookie(ci), + &ci->i_version, &i_size); } else { - fscache_unuse_cookie(ci->fscache, NULL, NULL); + fscache_unuse_cookie(ceph_fscache_cookie(ci), NULL, NULL); } } @@ -69,14 +69,14 @@ void ceph_fscache_update(struct inode *inode) struct ceph_inode_info *ci = ceph_inode(inode); loff_t i_size = i_size_read(inode); - fscache_update_cookie(ci->fscache, &ci->i_version, &i_size); + fscache_update_cookie(ceph_fscache_cookie(ci), &ci->i_version, &i_size); } void ceph_fscache_invalidate(struct inode *inode, bool dio_write) { struct ceph_inode_info *ci = ceph_inode(inode); - fscache_invalidate(ceph_inode(inode)->fscache, + fscache_invalidate(ceph_fscache_cookie(ci), &ci->i_version, i_size_read(inode), dio_write ? FSCACHE_INVAL_DIO_WRITE : 0); } diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h index b90f3016994d..7255b790a4c1 100644 --- a/fs/ceph/cache.h +++ b/fs/ceph/cache.h @@ -26,14 +26,9 @@ void ceph_fscache_unuse_cookie(struct inode *inode, bool update); void ceph_fscache_update(struct inode *inode); void ceph_fscache_invalidate(struct inode *inode, bool dio_write); -static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci) -{ - ci->fscache = NULL; -} - static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci) { - return ci->fscache; + return netfs_i_cookie(&ci->vfs_inode); } static inline void ceph_fscache_resize(struct inode *inode, loff_t to) @@ -62,7 +57,7 @@ static inline int ceph_fscache_dirty_folio(struct address_space *mapping, return fscache_dirty_folio(mapping, folio, ceph_fscache_cookie(ci)); } -static inline int ceph_begin_cache_operation(struct netfs_read_request *rreq) +static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq) { struct fscache_cookie *cookie = ceph_fscache_cookie(ceph_inode(rreq->inode)); @@ -91,10 +86,6 @@ static inline void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc) { } -static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci) -{ -} - static inline void ceph_fscache_register_inode_cookie(struct inode *inode) { } @@ -144,7 +135,7 @@ static inline bool ceph_is_cache_enabled(struct inode *inode) return false; } -static inline int ceph_begin_cache_operation(struct netfs_read_request *rreq) +static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq) { return -ENOBUFS; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index d80911dc91c2..63113e2a4890 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -459,6 +459,9 @@ struct inode *ceph_alloc_inode(struct super_block *sb) dout("alloc_inode %p\n", &ci->vfs_inode); + /* Set parameters for the netfs library */ + netfs_i_context_init(&ci->vfs_inode, &ceph_netfs_ops); + spin_lock_init(&ci->i_ceph_lock); ci->i_version = 0; @@ -544,9 +547,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb) INIT_WORK(&ci->i_work, ceph_inode_work); ci->i_work_mask = 0; memset(&ci->i_btime, '\0', sizeof(ci->i_btime)); - - ceph_fscache_inode_init(ci); - return &ci->vfs_inode; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index a1ecc410a495..20ceab74e871 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -17,13 +17,11 @@ #include <linux/posix_acl.h> #include <linux/refcount.h> #include <linux/security.h> +#include <linux/netfs.h> +#include <linux/fscache.h> #include <linux/ceph/libceph.h> -#ifdef CONFIG_CEPH_FSCACHE -#include <linux/fscache.h> -#endif - /* large granularity for statfs utilization stats to facilitate * large volume sizes on 32-bit machines. */ #define CEPH_BLOCK_SHIFT 22 /* 4 MB */ @@ -318,6 +316,11 @@ struct ceph_inode_xattrs_info { * Ceph inode. */ struct ceph_inode_info { + struct { + /* These must be contiguous */ + struct inode vfs_inode; + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; struct ceph_vino i_vino; /* ceph ino + snap */ spinlock_t i_ceph_lock; @@ -428,11 +431,6 @@ struct ceph_inode_info { struct work_struct i_work; unsigned long i_work_mask; - -#ifdef CONFIG_CEPH_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; /* at end */ }; static inline struct ceph_inode_info * @@ -1216,6 +1214,7 @@ extern void __ceph_touch_fmode(struct ceph_inode_info *ci, /* addr.c */ extern const struct address_space_operations ceph_aops; +extern const struct netfs_request_ops ceph_netfs_ops; extern int ceph_mmap(struct file *file, struct vm_area_struct *vma); extern int ceph_uninline_data(struct file *file); extern int ceph_pool_perm_check(struct inode *inode, int need); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 48b343d03430..0a4085ced40f 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -16,6 +16,7 @@ #include <linux/mempool.h> #include <linux/workqueue.h> #include <linux/utsname.h> +#include <linux/netfs.h> #include "cifs_fs_sb.h" #include "cifsacl.h" #include <crypto/internal/hash.h> @@ -1402,6 +1403,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file); */ struct cifsInodeInfo { + struct { + /* These must be contiguous */ + struct inode vfs_inode; /* the VFS's inode record */ + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; bool can_cache_brlcks; struct list_head llist; /* locks helb by this inode */ /* @@ -1432,10 +1438,6 @@ struct cifsInodeInfo { u64 uniqueid; /* server inode number */ u64 createtime; /* creation time on server */ __u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for this inode */ -#ifdef CONFIG_CIFS_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; struct list_head deferred_closes; /* list of deferred closes */ spinlock_t deferred_lock; /* protection on deferred list */ bool lease_granted; /* Flag to indicate whether lease or oplock is granted. */ diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 33af72e0ac0c..a638b29e9062 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -103,7 +103,7 @@ void cifs_fscache_get_inode_cookie(struct inode *inode) cifs_fscache_fill_coherency(&cifsi->vfs_inode, &cd); - cifsi->fscache = + cifsi->netfs_ctx.cache = fscache_acquire_cookie(tcon->fscache, 0, &cifsi->uniqueid, sizeof(cifsi->uniqueid), &cd, sizeof(cd), @@ -126,22 +126,15 @@ void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) void cifs_fscache_release_inode_cookie(struct inode *inode) { struct cifsInodeInfo *cifsi = CIFS_I(inode); + struct fscache_cookie *cookie = cifs_inode_cookie(inode); - if (cifsi->fscache) { - cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cifsi->fscache); - fscache_relinquish_cookie(cifsi->fscache, false); - cifsi->fscache = NULL; + if (cookie) { + cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cookie); + fscache_relinquish_cookie(cookie, false); + cifsi->netfs_ctx.cache = NULL; } } -static inline void fscache_end_operation(struct netfs_cache_resources *cres) -{ - const struct netfs_cache_ops *ops = fscache_operation_valid(cres); - - if (ops) - ops->end_operation(cres); -} - /* * Fallback page reading interface. */ diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index 55129908e2c1..52355c0912ae 100644 --- a/fs/cifs/fscache.h +++ b/fs/cifs/fscache.h @@ -61,7 +61,7 @@ void cifs_fscache_fill_coherency(struct inode *inode, static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { - return CIFS_I(inode)->fscache; + return netfs_i_cookie(inode); } static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index f121c21590dc..ed1c9ed737f2 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -71,17 +71,6 @@ static inline void fscache_see_cookie(struct fscache_cookie *cookie, } /* - * io.c - */ -static inline void fscache_end_operation(struct netfs_cache_resources *cres) -{ - const struct netfs_cache_ops *ops = fscache_operation_valid(cres); - - if (ops) - ops->end_operation(cres); -} - -/* * main.c */ extern unsigned fscache_debug; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index d67108489148..39080b2d6cf8 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -606,9 +606,9 @@ out: return ret; } -static inline __be64 *gfs2_indirect_init(struct metapath *mp, - struct gfs2_glock *gl, unsigned int i, - unsigned offset, u64 bn) +static inline void gfs2_indirect_init(struct metapath *mp, + struct gfs2_glock *gl, unsigned int i, + unsigned offset, u64 bn) { __be64 *ptr = (__be64 *)(mp->mp_bh[i - 1]->b_data + ((i > 1) ? sizeof(struct gfs2_meta_header) : @@ -621,7 +621,6 @@ static inline __be64 *gfs2_indirect_init(struct metapath *mp, gfs2_buffer_clear_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header)); ptr += offset; *ptr = cpu_to_be64(bn); - return ptr; } enum alloc_state { @@ -2146,7 +2145,7 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize) ret = do_shrink(inode, newsize); out: - gfs2_rs_delete(ip, NULL); + gfs2_rs_delete(ip); gfs2_qa_put(ip); return ret; } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 8c39a8571b1f..22b41acfbbc3 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -706,7 +706,7 @@ static int gfs2_release(struct inode *inode, struct file *file) if (file->f_mode & FMODE_WRITE) { if (gfs2_rs_active(&ip->i_res)) - gfs2_rs_delete(ip, &inode->i_writecount); + gfs2_rs_delete(ip); gfs2_qa_put(ip); } return 0; @@ -775,8 +775,7 @@ static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i, size_t *window_size) { size_t count = iov_iter_count(i); - char __user *p; - int pages = 1; + size_t size, offs; if (likely(!count)) return false; @@ -785,18 +784,20 @@ static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i, if (!iter_is_iovec(i)) return false; + size = PAGE_SIZE; + offs = offset_in_page(i->iov[0].iov_base + i->iov_offset); if (*prev_count != count || !*window_size) { - int pages, nr_dirtied; + size_t nr_dirtied; - pages = min_t(int, BIO_MAX_VECS, DIV_ROUND_UP(count, PAGE_SIZE)); + size = ALIGN(offs + count, PAGE_SIZE); + size = min_t(size_t, size, SZ_1M); nr_dirtied = max(current->nr_dirtied_pause - - current->nr_dirtied, 1); - pages = min(pages, nr_dirtied); + current->nr_dirtied, 8); + size = min(size, nr_dirtied << PAGE_SHIFT); } *prev_count = count; - p = i->iov[0].iov_base + i->iov_offset; - *window_size = (size_t)PAGE_SIZE * pages - offset_in_page(p); + *window_size = size - offs; return true; } @@ -851,9 +852,9 @@ retry_under_glock: leftover = fault_in_iov_iter_writeable(to, window_size); gfs2_holder_disallow_demote(gh); if (leftover != window_size) { - if (!gfs2_holder_queued(gh)) - goto retry; - goto retry_under_glock; + if (gfs2_holder_queued(gh)) + goto retry_under_glock; + goto retry; } } if (gfs2_holder_queued(gh)) @@ -920,9 +921,9 @@ retry_under_glock: leftover = fault_in_iov_iter_readable(from, window_size); gfs2_holder_disallow_demote(gh); if (leftover != window_size) { - if (!gfs2_holder_queued(gh)) - goto retry; - goto retry_under_glock; + if (gfs2_holder_queued(gh)) + goto retry_under_glock; + goto retry; } } out: @@ -950,20 +951,19 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) * and retry. */ - if (iocb->ki_flags & IOCB_DIRECT) { - ret = gfs2_file_direct_read(iocb, to, &gh); - if (likely(ret != -ENOTBLK)) - return ret; - iocb->ki_flags &= ~IOCB_DIRECT; - } + if (iocb->ki_flags & IOCB_DIRECT) + return gfs2_file_direct_read(iocb, to, &gh); + + pagefault_disable(); iocb->ki_flags |= IOCB_NOIO; ret = generic_file_read_iter(iocb, to); iocb->ki_flags &= ~IOCB_NOIO; + pagefault_enable(); if (ret >= 0) { if (!iov_iter_count(to)) return ret; written = ret; - } else { + } else if (ret != -EFAULT) { if (ret != -EAGAIN) return ret; if (iocb->ki_flags & IOCB_NOWAIT) @@ -989,12 +989,11 @@ retry_under_glock: leftover = fault_in_iov_iter_writeable(to, window_size); gfs2_holder_disallow_demote(&gh); if (leftover != window_size) { - if (!gfs2_holder_queued(&gh)) { - if (written) - goto out_uninit; - goto retry; - } - goto retry_under_glock; + if (gfs2_holder_queued(&gh)) + goto retry_under_glock; + if (written) + goto out_uninit; + goto retry; } } if (gfs2_holder_queued(&gh)) @@ -1068,12 +1067,11 @@ retry_under_glock: gfs2_holder_disallow_demote(gh); if (leftover != window_size) { from->count = min(from->count, window_size - leftover); - if (!gfs2_holder_queued(gh)) { - if (read) - goto out_uninit; - goto retry; - } - goto retry_under_glock; + if (gfs2_holder_queued(gh)) + goto retry_under_glock; + if (read && !(iocb->ki_flags & IOCB_DIRECT)) + goto out_uninit; + goto retry; } } out_unlock: @@ -1083,6 +1081,7 @@ out_uninit: gfs2_holder_uninit(gh); if (statfs_gh) kfree(statfs_gh); + from->count = orig_count - read; return read ? read : ret; } @@ -1497,7 +1496,6 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) if (error != GLR_TRYFAILED) break; fl_gh->gh_flags = LM_FLAG_TRY | GL_EXACT; - fl_gh->gh_error = 0; msleep(sleeptime); } if (error) { diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 6b23399eaee0..630c6550eacf 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -542,7 +542,7 @@ restart: * some reason. If this holder is the head of the list, it * means we have a blocked holder at the head, so return 1. */ - if (gh->gh_list.prev == &gl->gl_holders) + if (list_is_first(&gh->gh_list, &gl->gl_holders)) return 1; do_error(gl, 0); break; @@ -669,6 +669,8 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret) /* Check for state != intended state */ if (unlikely(state != gl->gl_target)) { + if (gh && (ret & LM_OUT_CANCELED)) + gfs2_holder_wake(gh); if (gh && !test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)) { /* move to back of queue and try next entry */ if (ret & LM_OUT_CANCELED) { @@ -1259,7 +1261,6 @@ void __gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags, gh->gh_owner_pid = get_pid(task_pid(current)); gh->gh_state = state; gh->gh_flags = flags; - gh->gh_error = 0; gh->gh_iflags = 0; gfs2_glock_hold(gl); } @@ -1565,6 +1566,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh) if (test_bit(GLF_LRU, &gl->gl_flags)) gfs2_glock_remove_from_lru(gl); + gh->gh_error = 0; spin_lock(&gl->gl_lockref.lock); add_to_queue(gh); if (unlikely((LM_FLAG_NOEXP & gh->gh_flags) && @@ -1691,6 +1693,14 @@ void gfs2_glock_dq(struct gfs2_holder *gh) struct gfs2_glock *gl = gh->gh_gl; spin_lock(&gl->gl_lockref.lock); + if (list_is_first(&gh->gh_list, &gl->gl_holders) && + !test_bit(HIF_HOLDER, &gh->gh_iflags)) { + spin_unlock(&gl->gl_lockref.lock); + gl->gl_name.ln_sbd->sd_lockstruct.ls_ops->lm_cancel(gl); + wait_on_bit(&gh->gh_iflags, HIF_WAIT, TASK_UNINTERRUPTIBLE); + spin_lock(&gl->gl_lockref.lock); + } + __gfs2_glock_dq(gh); spin_unlock(&gl->gl_lockref.lock); } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 89905f4f29bb..c8ec876f33ea 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -131,7 +131,21 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_glock *io_gl; - error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); + error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, + &ip->i_gl); + if (unlikely(error)) + goto fail; + + error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, + &io_gl); + if (unlikely(error)) + goto fail; + + if (blktype != GFS2_BLKST_UNLINKED) + gfs2_cancel_delete_work(io_gl); + error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, + &ip->i_iopen_gh); + gfs2_glock_put(io_gl); if (unlikely(error)) goto fail; @@ -161,16 +175,6 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, set_bit(GLF_INSTANTIATE_NEEDED, &ip->i_gl->gl_flags); - error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); - if (unlikely(error)) - goto fail; - if (blktype != GFS2_BLKST_UNLINKED) - gfs2_cancel_delete_work(io_gl); - error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); - gfs2_glock_put(io_gl); - if (unlikely(error)) - goto fail; - /* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */ inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1); inode->i_atime.tv_nsec = 0; @@ -716,13 +720,17 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = insert_inode_locked4(inode, ip->i_no_addr, iget_test, &ip->i_no_addr); BUG_ON(error); - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); + error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (error) goto fail_gunlock2; + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); + if (error) + goto fail_gunlock3; + error = gfs2_trans_begin(sdp, blocks, 0); if (error) - goto fail_gunlock2; + goto fail_gunlock3; if (blocks > 1) { ip->i_eattr = ip->i_no_addr + 1; @@ -731,10 +739,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, init_dinode(dip, ip, symname); gfs2_trans_end(sdp); - error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); - if (error) - goto fail_gunlock2; - glock_set_object(ip->i_gl, ip); glock_set_object(io_gl, ip); gfs2_set_iop(inode); @@ -745,14 +749,14 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (default_acl) { error = __gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); if (error) - goto fail_gunlock3; + goto fail_gunlock4; posix_acl_release(default_acl); default_acl = NULL; } if (acl) { error = __gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS); if (error) - goto fail_gunlock3; + goto fail_gunlock4; posix_acl_release(acl); acl = NULL; } @@ -760,11 +764,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = security_inode_init_security(&ip->i_inode, &dip->i_inode, name, &gfs2_initxattrs, NULL); if (error) - goto fail_gunlock3; + goto fail_gunlock4; error = link_dinode(dip, name, ip, &da); if (error) - goto fail_gunlock3; + goto fail_gunlock4; mark_inode_dirty(inode); d_instantiate(dentry, inode); @@ -782,9 +786,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, unlock_new_inode(inode); return error; -fail_gunlock3: +fail_gunlock4: glock_clear_object(ip->i_gl, ip); glock_clear_object(io_gl, ip); +fail_gunlock3: gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_gunlock2: gfs2_glock_put(io_gl); @@ -793,7 +798,7 @@ fail_free_inode: if (free_vfs_inode) /* else evict will do the put for us */ gfs2_glock_put(ip->i_gl); } - gfs2_rs_delete(ip, NULL); + gfs2_rs_deltree(&ip->i_res); gfs2_qa_put(ip); fail_free_acls: posix_acl_release(default_acl); diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 50578f881e6d..2559a79cf14b 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -261,6 +261,7 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state, int req; u32 lkf; char strname[GDLM_STRNAME_BYTES] = ""; + int error; req = make_mode(gl->gl_name.ln_sbd, req_state); lkf = make_flags(gl, flags, req); @@ -279,8 +280,14 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state, * Submit the actual lock request. */ - return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, strname, +again: + error = dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, strname, GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast); + if (error == -EBUSY) { + msleep(20); + goto again; + } + return error; } static void gdlm_put_lock(struct gfs2_glock *gl) @@ -312,8 +319,14 @@ static void gdlm_put_lock(struct gfs2_glock *gl) return; } +again: error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK, NULL, gl); + if (error == -EBUSY) { + msleep(20); + goto again; + } + if (error) { fs_err(sdp, "gdlm_unlock %x,%llx err=%d\n", gl->gl_name.ln_type, diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 0fb3c01bc557..801ad9f4f2be 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -680,13 +680,14 @@ void gfs2_rs_deltree(struct gfs2_blkreserv *rs) /** * gfs2_rs_delete - delete a multi-block reservation * @ip: The inode for this reservation - * @wcount: The inode's write count, or NULL * */ -void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount) +void gfs2_rs_delete(struct gfs2_inode *ip) { + struct inode *inode = &ip->i_inode; + down_write(&ip->i_rw_mutex); - if ((wcount == NULL) || (atomic_read(wcount) <= 1)) + if (atomic_read(&inode->i_writecount) <= 1) gfs2_rs_deltree(&ip->i_res); up_write(&ip->i_rw_mutex); } @@ -922,15 +923,15 @@ static int read_rindex_entry(struct gfs2_inode *ip) spin_lock_init(&rgd->rd_rsspin); mutex_init(&rgd->rd_mutex); - error = compute_bitstructs(rgd); - if (error) - goto fail; - error = gfs2_glock_get(sdp, rgd->rd_addr, &gfs2_rgrp_glops, CREATE, &rgd->rd_gl); if (error) goto fail; + error = compute_bitstructs(rgd); + if (error) + goto fail_glock; + rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr; rgd->rd_flags &= ~GFS2_RDF_PREFERRED; if (rgd->rd_data > sdp->sd_max_rg_data) @@ -944,6 +945,7 @@ static int read_rindex_entry(struct gfs2_inode *ip) } error = 0; /* someone else read in the rgrp; free it and ignore it */ +fail_glock: gfs2_glock_put(rgd->rd_gl); fail: @@ -1415,7 +1417,8 @@ int gfs2_fitrim(struct file *filp, void __user *argp) start = r.start >> bs_shift; end = start + (r.len >> bs_shift); - minlen = max_t(u64, r.minlen, + minlen = max_t(u64, r.minlen, sdp->sd_sb.sb_bsize); + minlen = max_t(u64, minlen, q->limits.discard_granularity) >> bs_shift; if (end <= start || minlen > sdp->sd_max_rg_data) diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 3e2ca1fb4305..46dd94e9e085 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -45,7 +45,7 @@ extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n, bool dinode, u64 *generation); extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs); -extern void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount); +extern void gfs2_rs_delete(struct gfs2_inode *ip); extern void __gfs2_free_blocks(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd, u64 bstart, u32 blen, int meta); extern void gfs2_free_meta(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd, diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index cf9cf66522b3..bdb773e5c88f 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1396,7 +1396,7 @@ out: truncate_inode_pages_final(&inode->i_data); if (ip->i_qadata) gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0); - gfs2_rs_delete(ip, NULL); + gfs2_rs_deltree(&ip->i_res); gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index b288c8ae1236..837cd55fd4c5 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -415,13 +415,15 @@ int jffs2_do_mount_fs(struct jffs2_sb_info *c) jffs2_free_ino_caches(c); jffs2_free_raw_node_refs(c); ret = -EIO; - goto out_free; + goto out_sum_exit; } jffs2_calc_trigger_levels(c); return 0; + out_sum_exit: + jffs2_sum_exit(c); out_free: kvfree(c->blocks); diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 2ac410477c4f..71f03a5d36ed 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -603,8 +603,8 @@ out_root: jffs2_free_ino_caches(c); jffs2_free_raw_node_refs(c); kvfree(c->blocks); - out_inohash: jffs2_clear_xattr_subsystem(c); + out_inohash: kfree(c->inocache_list); out_wbuf: jffs2_flash_cleanup(c); diff --git a/fs/jffs2/jffs2_fs_i.h b/fs/jffs2/jffs2_fs_i.h index 2e4a86763c07..93a2951538ce 100644 --- a/fs/jffs2/jffs2_fs_i.h +++ b/fs/jffs2/jffs2_fs_i.h @@ -18,11 +18,11 @@ #include <linux/mutex.h> struct jffs2_inode_info { - /* We need an internal mutex similar to inode->i_mutex. + /* We need an internal mutex similar to inode->i_rwsem. Unfortunately, we can't used the existing one, because either the GC would deadlock, or we'd have to release it before letting GC proceed. Or we'd have to put ugliness - into the GC code so it didn't attempt to obtain the i_mutex + into the GC code so it didn't attempt to obtain the i_rwsem for the inode(s) which are already locked */ struct mutex sem; diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index b676056826be..29671e33a171 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -136,7 +136,7 @@ int jffs2_scan_medium(struct jffs2_sb_info *c) if (!s) { JFFS2_WARNING("Can't allocate memory for summary\n"); ret = -ENOMEM; - goto out; + goto out_buf; } } @@ -275,13 +275,15 @@ int jffs2_scan_medium(struct jffs2_sb_info *c) } ret = 0; out: + jffs2_sum_reset_collected(s); + kfree(s); + out_buf: if (buf_size) kfree(flashbuf); #ifndef __ECOS else mtd_unpoint(c->mtd, 0, c->mtd->size); #endif - kfree(s); return ret; } diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile index c15bfc966d96..f684c0cd1ec5 100644 --- a/fs/netfs/Makefile +++ b/fs/netfs/Makefile @@ -1,5 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 -netfs-y := read_helper.o stats.o +netfs-y := \ + buffered_read.o \ + io.o \ + main.o \ + objects.o + +netfs-$(CONFIG_NETFS_STATS) += stats.o obj-$(CONFIG_NETFS_SUPPORT) := netfs.o diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c new file mode 100644 index 000000000000..281a88a5b8dc --- /dev/null +++ b/fs/netfs/buffered_read.c @@ -0,0 +1,428 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Network filesystem high-level buffered read support. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/export.h> +#include <linux/task_io_accounting_ops.h> +#include "internal.h" + +/* + * Unlock the folios in a read operation. We need to set PG_fscache on any + * folios we're going to write back before we unlock them. + */ +void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + unsigned int iopos, account = 0; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { + __clear_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); + } + } + + /* Walk through the pagecache and the I/O request lists simultaneously. + * We may have a mixture of cached and uncached sections and we only + * really want to write out the uncached sections. This is slightly + * complicated by the possibility that we might have huge pages with a + * mixture inside. + */ + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + iopos = 0; + subreq_failed = (subreq->error < 0); + + trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE; + unsigned int pgend = pgpos + folio_size(folio); + bool pg_failed = false; + + for (;;) { + if (!subreq) { + pg_failed = true; + break; + } + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + folio_start_fscache(folio); + pg_failed |= subreq_failed; + if (pgend < iopos + subreq->len) + break; + + account += subreq->transferred; + iopos += subreq->len; + if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + if (pgend == iopos) + break; + } + + if (!pg_failed) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio_index(folio) == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) + _debug("no unlock"); + else + folio_unlock(folio); + } + } + rcu_read_unlock(); + + task_io_account_read(account); + if (rreq->netfs_ops->done) + rreq->netfs_ops->done(rreq); +} + +static void netfs_cache_expand_readahead(struct netfs_io_request *rreq, + loff_t *_start, size_t *_len, loff_t i_size) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + + if (cres->ops && cres->ops->expand_readahead) + cres->ops->expand_readahead(cres, _start, _len, i_size); +} + +static void netfs_rreq_expand(struct netfs_io_request *rreq, + struct readahead_control *ractl) +{ + /* Give the cache a chance to change the request parameters. The + * resultant request must contain the original region. + */ + netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); + + /* Give the netfs a chance to change the request parameters. The + * resultant request must contain the original region. + */ + if (rreq->netfs_ops->expand_readahead) + rreq->netfs_ops->expand_readahead(rreq); + + /* Expand the request if the cache wants it to start earlier. Note + * that the expansion may get further extended if the VM wishes to + * insert THPs and the preferred start and/or end wind up in the middle + * of THPs. + * + * If this is the case, however, the THP size should be an integer + * multiple of the cache granule size, so we get a whole number of + * granules to deal with. + */ + if (rreq->start != readahead_pos(ractl) || + rreq->len != readahead_length(ractl)) { + readahead_expand(ractl, rreq->start, rreq->len); + rreq->start = readahead_pos(ractl); + rreq->len = readahead_length(ractl); + + trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), + netfs_read_trace_expanded); + } +} + +/** + * netfs_readahead - Helper to manage a read request + * @ractl: The description of the readahead request + * + * Fulfil a readahead request by drawing data from the cache if possible, or + * the netfs if not. Space beyond the EOF is zero-filled. Multiple I/O + * requests from different sources will get munged together. If necessary, the + * readahead window can be expanded in either direction to a more convenient + * alighment for RPC efficiency or to make storage in the cache feasible. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +void netfs_readahead(struct readahead_control *ractl) +{ + struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(ractl->mapping->host); + int ret; + + _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); + + if (readahead_count(ractl) == 0) + return; + + rreq = netfs_alloc_request(ractl->mapping, ractl->file, + readahead_pos(ractl), + readahead_length(ractl), + NETFS_READAHEAD); + if (IS_ERR(rreq)) + return; + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto cleanup_free; + } + + netfs_stat(&netfs_n_rh_readahead); + trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), + netfs_read_trace_readahead); + + netfs_rreq_expand(rreq, ractl); + + /* Drop the refs on the folios here rather than in the cache or + * filesystem. The locks will be dropped in netfs_rreq_unlock(). + */ + while (readahead_folio(ractl)) + ; + + netfs_begin_read(rreq, false); + return; + +cleanup_free: + netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); + return; +} +EXPORT_SYMBOL(netfs_readahead); + +/** + * netfs_readpage - Helper to manage a readpage request + * @file: The file to read from + * @subpage: A subpage of the folio to read + * + * Fulfil a readpage request by drawing data from the cache if possible, or the + * netfs if not. Space beyond the EOF is zero-filled. Multiple I/O requests + * from different sources will get munged together. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +int netfs_readpage(struct file *file, struct page *subpage) +{ + struct folio *folio = page_folio(subpage); + struct address_space *mapping = folio_file_mapping(folio); + struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(mapping->host); + int ret; + + _enter("%lx", folio_index(folio)); + + rreq = netfs_alloc_request(mapping, file, + folio_file_pos(folio), folio_size(folio), + NETFS_READPAGE); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto alloc_error; + } + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto discard; + } + + netfs_stat(&netfs_n_rh_readpage); + trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); + return netfs_begin_read(rreq, true); + +discard: + netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); +alloc_error: + folio_unlock(folio); + return ret; +} +EXPORT_SYMBOL(netfs_readpage); + +/* + * Prepare a folio for writing without reading first + * @folio: The folio being prepared + * @pos: starting position for the write + * @len: length of write + * @always_fill: T if the folio should always be completely filled/cleared + * + * In some cases, write_begin doesn't need to read at all: + * - full folio write + * - write that lies in a folio that is completely beyond EOF + * - write that covers the folio from start to EOF or beyond it + * + * If any of these criteria are met, then zero out the unwritten parts + * of the folio and return true. Otherwise, return false. + */ +static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len, + bool always_fill) +{ + struct inode *inode = folio_inode(folio); + loff_t i_size = i_size_read(inode); + size_t offset = offset_in_folio(folio, pos); + size_t plen = folio_size(folio); + + if (unlikely(always_fill)) { + if (pos - offset + len <= i_size) + return false; /* Page entirely before EOF */ + zero_user_segment(&folio->page, 0, plen); + folio_mark_uptodate(folio); + return true; + } + + /* Full folio write */ + if (offset == 0 && len >= plen) + return true; + + /* Page entirely beyond the end of the file */ + if (pos - offset >= i_size) + goto zero_out; + + /* Write that covers from the start of the folio to EOF or beyond */ + if (offset == 0 && (pos + len) >= i_size) + goto zero_out; + + return false; +zero_out: + zero_user_segments(&folio->page, 0, offset, offset + len, plen); + return true; +} + +/** + * netfs_write_begin - Helper to prepare for writing + * @file: The file to read from + * @mapping: The mapping to read from + * @pos: File position at which the write will begin + * @len: The length of the write (may extend beyond the end of the folio chosen) + * @aop_flags: AOP_* flags + * @_folio: Where to put the resultant folio + * @_fsdata: Place for the netfs to store a cookie + * + * Pre-read data for a write-begin request by drawing data from the cache if + * possible, or the netfs if not. Space beyond the EOF is zero-filled. + * Multiple I/O requests from different sources will get munged together. If + * necessary, the readahead window can be expanded in either direction to a + * more convenient alighment for RPC efficiency or to make storage in the cache + * feasible. + * + * The calling netfs must provide a table of operations, only one of which, + * issue_op, is mandatory. + * + * The check_write_begin() operation can be provided to check for and flush + * conflicting writes once the folio is grabbed and locked. It is passed a + * pointer to the fsdata cookie that gets returned to the VM to be passed to + * write_end. It is permitted to sleep. It should return 0 if the request + * should go ahead; unlock the folio and return -EAGAIN to cause the folio to + * be regot; or return an error. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +int netfs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned int len, unsigned int aop_flags, + struct folio **_folio, void **_fsdata) +{ + struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(file_inode(file )); + struct folio *folio; + unsigned int fgp_flags; + pgoff_t index = pos >> PAGE_SHIFT; + int ret; + + DEFINE_READAHEAD(ractl, file, NULL, mapping, index); + +retry: + fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + if (aop_flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + folio = __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (!folio) + return -ENOMEM; + + if (ctx->ops->check_write_begin) { + /* Allow the netfs (eg. ceph) to flush conflicts. */ + ret = ctx->ops->check_write_begin(file, pos, len, folio, _fsdata); + if (ret < 0) { + trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); + if (ret == -EAGAIN) + goto retry; + goto error; + } + } + + if (folio_test_uptodate(folio)) + goto have_folio; + + /* If the page is beyond the EOF, we want to clear it - unless it's + * within the cache granule containing the EOF, in which case we need + * to preload the granule. + */ + if (!netfs_is_cache_enabled(ctx) && + netfs_skip_folio_read(folio, pos, len, false)) { + netfs_stat(&netfs_n_rh_write_zskip); + goto have_folio_no_wait; + } + + rreq = netfs_alloc_request(mapping, file, + folio_file_pos(folio), folio_size(folio), + NETFS_READ_FOR_WRITE); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto error; + } + rreq->no_unlock_folio = folio_index(folio); + __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto error_put; + } + + netfs_stat(&netfs_n_rh_write_begin); + trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); + + /* Expand the request to meet caching requirements and download + * preferences. + */ + ractl._nr_pages = folio_nr_pages(folio); + netfs_rreq_expand(rreq, &ractl); + + /* We hold the folio locks, so we can drop the references */ + folio_get(folio); + while (readahead_folio(&ractl)) + ; + + ret = netfs_begin_read(rreq, true); + if (ret < 0) + goto error; + +have_folio: + ret = folio_wait_fscache_killable(folio); + if (ret < 0) + goto error; +have_folio_no_wait: + *_folio = folio; + _leave(" = 0"); + return 0; + +error_put: + netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); +error: + folio_unlock(folio); + folio_put(folio); + _leave(" = %d", ret); + return ret; +} +EXPORT_SYMBOL(netfs_write_begin); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index b7f2c4459f33..b7b0e3d18d9e 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -5,6 +5,10 @@ * Written by David Howells (dhowells@redhat.com) */ +#include <linux/netfs.h> +#include <linux/fscache.h> +#include <trace/events/netfs.h> + #ifdef pr_fmt #undef pr_fmt #endif @@ -12,11 +16,40 @@ #define pr_fmt(fmt) "netfs: " fmt /* - * read_helper.c + * buffered_read.c + */ +void netfs_rreq_unlock_folios(struct netfs_io_request *rreq); + +/* + * io.c + */ +int netfs_begin_read(struct netfs_io_request *rreq, bool sync); + +/* + * main.c */ extern unsigned int netfs_debug; /* + * objects.c + */ +struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, + struct file *file, + loff_t start, size_t len, + enum netfs_io_origin origin); +void netfs_get_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what); +void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async); +void netfs_put_request(struct netfs_io_request *rreq, bool was_async, + enum netfs_rreq_ref_trace what); +struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq); + +static inline void netfs_see_request(struct netfs_io_request *rreq, + enum netfs_rreq_ref_trace what) +{ + trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), what); +} + +/* * stats.c */ #ifdef CONFIG_NETFS_STATS @@ -55,6 +88,21 @@ static inline void netfs_stat_d(atomic_t *stat) #define netfs_stat_d(x) do {} while(0) #endif +/* + * Miscellaneous functions. + */ +static inline bool netfs_is_cache_enabled(struct netfs_i_context *ctx) +{ +#if IS_ENABLED(CONFIG_FSCACHE) + struct fscache_cookie *cookie = ctx->cache; + + return fscache_cookie_valid(cookie) && cookie->cache_priv && + fscache_cookie_enabled(cookie); +#else + return false; +#endif +} + /*****************************************************************************/ /* * debug tracing diff --git a/fs/netfs/io.c b/fs/netfs/io.c new file mode 100644 index 000000000000..428925899282 --- /dev/null +++ b/fs/netfs/io.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Network filesystem high-level read support. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/module.h> +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/uio.h> +#include <linux/sched/mm.h> +#include <linux/task_io_accounting_ops.h> +#include "internal.h" + +/* + * Clear the unread part of an I/O request. + */ +static void netfs_clear_unread(struct netfs_io_subrequest *subreq) +{ + struct iov_iter iter; + + iov_iter_xarray(&iter, READ, &subreq->rreq->mapping->i_pages, + subreq->start + subreq->transferred, + subreq->len - subreq->transferred); + iov_iter_zero(iov_iter_count(&iter), &iter); +} + +static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; + + netfs_subreq_terminated(subreq, transferred_or_error, was_async); +} + +/* + * Issue a read against the cache. + * - Eats the caller's ref on subreq. + */ +static void netfs_read_from_cache(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq, + enum netfs_read_from_hole read_hole) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct iov_iter iter; + + netfs_stat(&netfs_n_rh_read); + iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, + subreq->start + subreq->transferred, + subreq->len - subreq->transferred); + + cres->ops->read(cres, subreq->start, &iter, read_hole, + netfs_cache_read_terminated, subreq); +} + +/* + * Fill a subrequest region with zeroes. + */ +static void netfs_fill_with_zeroes(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + netfs_stat(&netfs_n_rh_zero); + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + netfs_subreq_terminated(subreq, 0, false); +} + +/* + * Ask the netfs to issue a read request to the server for us. + * + * The netfs is expected to read from subreq->pos + subreq->transferred to + * subreq->pos + subreq->len - 1. It may not backtrack and write data into the + * buffer prior to the transferred point as it might clobber dirty data + * obtained from the cache. + * + * Alternatively, the netfs is allowed to indicate one of two things: + * + * - NETFS_SREQ_SHORT_READ: A short read - it will get called again to try and + * make progress. + * + * - NETFS_SREQ_CLEAR_TAIL: A short read - the rest of the buffer will be + * cleared. + */ +static void netfs_read_from_server(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + netfs_stat(&netfs_n_rh_download); + rreq->netfs_ops->issue_read(subreq); +} + +/* + * Release those waiting. + */ +static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) +{ + trace_netfs_rreq(rreq, netfs_rreq_trace_done); + netfs_clear_subrequests(rreq, was_async); + netfs_put_request(rreq, was_async, netfs_rreq_trace_put_complete); +} + +/* + * Deal with the completion of writing the data to the cache. We have to clear + * the PG_fscache bits on the folios involved and release the caller's ref. + * + * May be called in softirq mode and we inherit a ref from the caller. + */ +static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, + bool was_async) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t unlocked = 0; + bool have_unlocked = false; + + rcu_read_lock(); + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); + + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + /* We might have multiple writes from the same huge + * folio, but we mustn't unlock a folio more than once. + */ + if (have_unlocked && folio_index(folio) <= unlocked) + continue; + unlocked = folio_index(folio); + folio_end_fscache(folio); + have_unlocked = true; + } + } + + rcu_read_unlock(); + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; + struct netfs_io_request *rreq = subreq->rreq; + + if (IS_ERR_VALUE(transferred_or_error)) { + netfs_stat(&netfs_n_rh_write_failed); + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_copy_to_cache); + } else { + netfs_stat(&netfs_n_rh_write_done); + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); + + /* If we decrement nr_copy_ops to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, was_async); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +} + +/* + * Perform any outstanding writes to the cache. We inherit a ref from the + * caller. + */ +static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct netfs_io_subrequest *subreq, *next, *p; + struct iov_iter iter; + int ret; + + trace_netfs_rreq(rreq, netfs_rreq_trace_copy); + + /* We don't want terminating writes trying to wake us up whilst we're + * still going through the list. + */ + atomic_inc(&rreq->nr_copy_ops); + + list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { + if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + list_del_init(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_no_copy); + } + } + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + /* Amalgamate adjacent writes */ + while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + next = list_next_entry(subreq, rreq_link); + if (next->start != subreq->start + subreq->len) + break; + subreq->len += next->len; + list_del_init(&next->rreq_link); + netfs_put_subrequest(next, false, + netfs_sreq_trace_put_merged); + } + + ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, + rreq->i_size, true); + if (ret < 0) { + trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); + trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); + continue; + } + + iov_iter_xarray(&iter, WRITE, &rreq->mapping->i_pages, + subreq->start, subreq->len); + + atomic_inc(&rreq->nr_copy_ops); + netfs_stat(&netfs_n_rh_write); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache); + trace_netfs_sreq(subreq, netfs_sreq_trace_write); + cres->ops->write(cres, subreq->start, &iter, + netfs_rreq_copy_terminated, subreq); + } + + /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, false); +} + +static void netfs_rreq_write_to_cache_work(struct work_struct *work) +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + + netfs_rreq_do_write_to_cache(rreq); +} + +static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) +{ + rreq->work.func = netfs_rreq_write_to_cache_work; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); +} + +/* + * Handle a short read. + */ +static void netfs_rreq_short_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + __clear_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); + __set_bit(NETFS_SREQ_SEEK_DATA_READ, &subreq->flags); + + netfs_stat(&netfs_n_rh_short_read); + trace_netfs_sreq(subreq, netfs_sreq_trace_resubmit_short); + + netfs_get_subrequest(subreq, netfs_sreq_trace_get_short_read); + atomic_inc(&rreq->nr_outstanding); + if (subreq->source == NETFS_READ_FROM_CACHE) + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); + else + netfs_read_from_server(rreq, subreq); +} + +/* + * Resubmit any short or failed operations. Returns true if we got the rreq + * ref back. + */ +static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + + WARN_ON(in_interrupt()); + + trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); + + /* We don't want terminating submissions trying to wake us up whilst + * we're still going through the list. + */ + atomic_inc(&rreq->nr_outstanding); + + __clear_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + if (subreq->error) { + if (subreq->source != NETFS_READ_FROM_CACHE) + break; + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->error = 0; + netfs_stat(&netfs_n_rh_download_instead); + trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + atomic_inc(&rreq->nr_outstanding); + netfs_read_from_server(rreq, subreq); + } else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) { + netfs_rreq_short_read(rreq, subreq); + } + } + + /* If we decrement nr_outstanding to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_outstanding)) + return true; + + wake_up_var(&rreq->nr_outstanding); + return false; +} + +/* + * Check to see if the data read is still valid. + */ +static void netfs_rreq_is_still_valid(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + + if (!rreq->netfs_ops->is_still_valid || + rreq->netfs_ops->is_still_valid(rreq)) + return; + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + if (subreq->source == NETFS_READ_FROM_CACHE) { + subreq->error = -ESTALE; + __set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + } + } +} + +/* + * Assess the state of a read request and decide what to do next. + * + * Note that we could be in an ordinary kernel thread, on a workqueue or in + * softirq context at this point. We inherit a ref from the caller. + */ +static void netfs_rreq_assess(struct netfs_io_request *rreq, bool was_async) +{ + trace_netfs_rreq(rreq, netfs_rreq_trace_assess); + +again: + netfs_rreq_is_still_valid(rreq); + + if (!test_bit(NETFS_RREQ_FAILED, &rreq->flags) && + test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags)) { + if (netfs_rreq_perform_resubmissions(rreq)) + goto again; + return; + } + + netfs_rreq_unlock_folios(rreq); + + clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); + wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + + if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) + return netfs_rreq_write_to_cache(rreq); + + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_work(struct work_struct *work) +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + netfs_rreq_assess(rreq, false); +} + +/* + * Handle the completion of all outstanding I/O operations on a read request. + * We inherit a ref from the caller. + */ +static void netfs_rreq_terminated(struct netfs_io_request *rreq, + bool was_async) +{ + if (test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags) && + was_async) { + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); + } else { + netfs_rreq_assess(rreq, was_async); + } +} + +/** + * netfs_subreq_terminated - Note the termination of an I/O operation. + * @subreq: The I/O request that has terminated. + * @transferred_or_error: The amount of data transferred or an error code. + * @was_async: The termination was asynchronous + * + * This tells the read helper that a contributory I/O operation has terminated, + * one way or another, and that it should integrate the results. + * + * The caller indicates in @transferred_or_error the outcome of the operation, + * supplying a positive value to indicate the number of bytes transferred, 0 to + * indicate a failure to transfer anything that should be retried or a negative + * error code. The helper will look after reissuing I/O operations as + * appropriate and writing downloaded data to the cache. + * + * If @was_async is true, the caller might be running in softirq or interrupt + * context and we can't sleep. + */ +void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, + ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_request *rreq = subreq->rreq; + int u; + + _enter("[%u]{%llx,%lx},%zd", + subreq->debug_index, subreq->start, subreq->flags, + transferred_or_error); + + switch (subreq->source) { + case NETFS_READ_FROM_CACHE: + netfs_stat(&netfs_n_rh_read_done); + break; + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_stat(&netfs_n_rh_download_done); + break; + default: + break; + } + + if (IS_ERR_VALUE(transferred_or_error)) { + subreq->error = transferred_or_error; + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_read); + goto failed; + } + + if (WARN(transferred_or_error > subreq->len - subreq->transferred, + "Subreq overread: R%x[%x] %zd > %zu - %zu", + rreq->debug_id, subreq->debug_index, + transferred_or_error, subreq->len, subreq->transferred)) + transferred_or_error = subreq->len - subreq->transferred; + + subreq->error = 0; + subreq->transferred += transferred_or_error; + if (subreq->transferred < subreq->len) + goto incomplete; + +complete: + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + set_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); + +out: + trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); + + /* If we decrement nr_outstanding to 0, the ref belongs to us. */ + u = atomic_dec_return(&rreq->nr_outstanding); + if (u == 0) + netfs_rreq_terminated(rreq, was_async); + else if (u == 1) + wake_up_var(&rreq->nr_outstanding); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); + return; + +incomplete: + if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) { + netfs_clear_unread(subreq); + subreq->transferred = subreq->len; + goto complete; + } + + if (transferred_or_error == 0) { + if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { + subreq->error = -ENODATA; + goto failed; + } + } else { + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + } + + __set_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); + set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + goto out; + +failed: + if (subreq->source == NETFS_READ_FROM_CACHE) { + netfs_stat(&netfs_n_rh_read_failed); + set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + } else { + netfs_stat(&netfs_n_rh_download_failed); + set_bit(NETFS_RREQ_FAILED, &rreq->flags); + rreq->error = subreq->error; + } + goto out; +} +EXPORT_SYMBOL(netfs_subreq_terminated); + +static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_subrequest *subreq, + loff_t i_size) +{ + struct netfs_io_request *rreq = subreq->rreq; + struct netfs_cache_resources *cres = &rreq->cache_resources; + + if (cres->ops) + return cres->ops->prepare_read(subreq, i_size); + if (subreq->start >= rreq->i_size) + return NETFS_FILL_WITH_ZEROES; + return NETFS_DOWNLOAD_FROM_SERVER; +} + +/* + * Work out what sort of subrequest the next one will be. + */ +static enum netfs_io_source +netfs_rreq_prepare_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + enum netfs_io_source source; + + _enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size); + + source = netfs_cache_prepare_read(subreq, rreq->i_size); + if (source == NETFS_INVALID_READ) + goto out; + + if (source == NETFS_DOWNLOAD_FROM_SERVER) { + /* Call out to the netfs to let it shrink the request to fit + * its own I/O sizes and boundaries. If it shinks it here, it + * will be called again to make simultaneous calls; if it wants + * to make serial calls, it can indicate a short read and then + * we will call it again. + */ + if (subreq->len > rreq->i_size - subreq->start) + subreq->len = rreq->i_size - subreq->start; + + if (rreq->netfs_ops->clamp_length && + !rreq->netfs_ops->clamp_length(subreq)) { + source = NETFS_INVALID_READ; + goto out; + } + } + + if (WARN_ON(subreq->len == 0)) + source = NETFS_INVALID_READ; + +out: + subreq->source = source; + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + return source; +} + +/* + * Slice off a piece of a read request and submit an I/O request for it. + */ +static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq, + unsigned int *_debug_index) +{ + struct netfs_io_subrequest *subreq; + enum netfs_io_source source; + + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) + return false; + + subreq->debug_index = (*_debug_index)++; + subreq->start = rreq->start + rreq->submitted; + subreq->len = rreq->len - rreq->submitted; + + _debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted); + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + + /* Call out to the cache to find out what it can do with the remaining + * subset. It tells us in subreq->flags what it decided should be done + * and adjusts subreq->len down if the subset crosses a cache boundary. + * + * Then when we hand the subset, it can choose to take a subset of that + * (the starts must coincide), in which case, we go around the loop + * again and ask it to download the next piece. + */ + source = netfs_rreq_prepare_read(rreq, subreq); + if (source == NETFS_INVALID_READ) + goto subreq_failed; + + atomic_inc(&rreq->nr_outstanding); + + rreq->submitted += subreq->len; + + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + switch (source) { + case NETFS_FILL_WITH_ZEROES: + netfs_fill_with_zeroes(rreq, subreq); + break; + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_read_from_server(rreq, subreq); + break; + case NETFS_READ_FROM_CACHE: + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_IGNORE); + break; + default: + BUG(); + } + + return true; + +subreq_failed: + rreq->error = subreq->error; + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_failed); + return false; +} + +/* + * Begin the process of reading in a chunk of data, where that data may be + * stitched together from multiple sources, including multiple servers and the + * local cache. + */ +int netfs_begin_read(struct netfs_io_request *rreq, bool sync) +{ + unsigned int debug_index = 0; + int ret; + + _enter("R=%x %llx-%llx", + rreq->debug_id, rreq->start, rreq->start + rreq->len - 1); + + if (rreq->len == 0) { + pr_err("Zero-sized read [R=%x]\n", rreq->debug_id); + netfs_put_request(rreq, false, netfs_rreq_trace_put_zero_len); + return -EIO; + } + + INIT_WORK(&rreq->work, netfs_rreq_work); + + if (sync) + netfs_get_request(rreq, netfs_rreq_trace_get_hold); + + /* Chop the read into slices according to what the cache and the netfs + * want and submit each one. + */ + atomic_set(&rreq->nr_outstanding, 1); + do { + if (!netfs_rreq_submit_slice(rreq, &debug_index)) + break; + + } while (rreq->submitted < rreq->len); + + if (sync) { + /* Keep nr_outstanding incremented so that the ref always belongs to + * us, and the service code isn't punted off to a random thread pool to + * process. + */ + for (;;) { + wait_var_event(&rreq->nr_outstanding, + atomic_read(&rreq->nr_outstanding) == 1); + netfs_rreq_assess(rreq, false); + if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) + break; + cond_resched(); + } + + ret = rreq->error; + if (ret == 0 && rreq->submitted < rreq->len) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } + netfs_put_request(rreq, false, netfs_rreq_trace_put_hold); + } else { + /* If we decrement nr_outstanding to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_assess(rreq, false); + ret = 0; + } + return ret; +} diff --git a/fs/netfs/main.c b/fs/netfs/main.c new file mode 100644 index 000000000000..068568702957 --- /dev/null +++ b/fs/netfs/main.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Miscellaneous bits for the netfs support library. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/module.h> +#include <linux/export.h> +#include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/netfs.h> + +MODULE_DESCRIPTION("Network fs support"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); + +unsigned netfs_debug; +module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO); +MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask"); diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c new file mode 100644 index 000000000000..e86107b30ba4 --- /dev/null +++ b/fs/netfs/objects.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Object lifetime handling and tracing. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/slab.h> +#include "internal.h" + +/* + * Allocate an I/O request and initialise it. + */ +struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, + struct file *file, + loff_t start, size_t len, + enum netfs_io_origin origin) +{ + static atomic_t debug_ids; + struct inode *inode = file ? file_inode(file) : mapping->host; + struct netfs_i_context *ctx = netfs_i_context(inode); + struct netfs_io_request *rreq; + int ret; + + rreq = kzalloc(sizeof(struct netfs_io_request), GFP_KERNEL); + if (!rreq) + return ERR_PTR(-ENOMEM); + + rreq->start = start; + rreq->len = len; + rreq->origin = origin; + rreq->netfs_ops = ctx->ops; + rreq->mapping = mapping; + rreq->inode = inode; + rreq->i_size = i_size_read(inode); + rreq->debug_id = atomic_inc_return(&debug_ids); + INIT_LIST_HEAD(&rreq->subrequests); + refcount_set(&rreq->ref, 1); + __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); + if (rreq->netfs_ops->init_request) { + ret = rreq->netfs_ops->init_request(rreq, file); + if (ret < 0) { + kfree(rreq); + return ERR_PTR(ret); + } + } + + netfs_stat(&netfs_n_rh_rreq); + return rreq; +} + +void netfs_get_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what) +{ + int r; + + __refcount_inc(&rreq->ref, &r); + trace_netfs_rreq_ref(rreq->debug_id, r + 1, what); +} + +void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async) +{ + struct netfs_io_subrequest *subreq; + + while (!list_empty(&rreq->subrequests)) { + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + list_del(&subreq->rreq_link); + netfs_put_subrequest(subreq, was_async, + netfs_sreq_trace_put_clear); + } +} + +static void netfs_free_request(struct work_struct *work) +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + + netfs_clear_subrequests(rreq, false); + if (rreq->netfs_priv) + rreq->netfs_ops->cleanup(rreq->mapping, rreq->netfs_priv); + trace_netfs_rreq(rreq, netfs_rreq_trace_free); + if (rreq->cache_resources.ops) + rreq->cache_resources.ops->end_operation(&rreq->cache_resources); + kfree(rreq); + netfs_stat_d(&netfs_n_rh_rreq); +} + +void netfs_put_request(struct netfs_io_request *rreq, bool was_async, + enum netfs_rreq_ref_trace what) +{ + unsigned int debug_id = rreq->debug_id; + bool dead; + int r; + + dead = __refcount_dec_and_test(&rreq->ref, &r); + trace_netfs_rreq_ref(debug_id, r - 1, what); + if (dead) { + if (was_async) { + rreq->work.func = netfs_free_request; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); + } else { + netfs_free_request(&rreq->work); + } + } +} + +/* + * Allocate and partially initialise an I/O request structure. + */ +struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + + subreq = kzalloc(sizeof(struct netfs_io_subrequest), GFP_KERNEL); + if (subreq) { + INIT_LIST_HEAD(&subreq->rreq_link); + refcount_set(&subreq->ref, 2); + subreq->rreq = rreq; + netfs_get_request(rreq, netfs_rreq_trace_get_subreq); + netfs_stat(&netfs_n_rh_sreq); + } + + return subreq; +} + +void netfs_get_subrequest(struct netfs_io_subrequest *subreq, + enum netfs_sreq_ref_trace what) +{ + int r; + + __refcount_inc(&subreq->ref, &r); + trace_netfs_sreq_ref(subreq->rreq->debug_id, subreq->debug_index, r + 1, + what); +} + +static void netfs_free_subrequest(struct netfs_io_subrequest *subreq, + bool was_async) +{ + struct netfs_io_request *rreq = subreq->rreq; + + trace_netfs_sreq(subreq, netfs_sreq_trace_free); + kfree(subreq); + netfs_stat_d(&netfs_n_rh_sreq); + netfs_put_request(rreq, was_async, netfs_rreq_trace_put_subreq); +} + +void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async, + enum netfs_sreq_ref_trace what) +{ + unsigned int debug_index = subreq->debug_index; + unsigned int debug_id = subreq->rreq->debug_id; + bool dead; + int r; + + dead = __refcount_dec_and_test(&subreq->ref, &r); + trace_netfs_sreq_ref(debug_id, debug_index, r - 1, what); + if (dead) + netfs_free_subrequest(subreq, was_async); +} diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c deleted file mode 100644 index 501da990c259..000000000000 --- a/fs/netfs/read_helper.c +++ /dev/null @@ -1,1205 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Network filesystem high-level read support. - * - * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/module.h> -#include <linux/export.h> -#include <linux/fs.h> -#include <linux/mm.h> -#include <linux/pagemap.h> -#include <linux/slab.h> -#include <linux/uio.h> -#include <linux/sched/mm.h> -#include <linux/task_io_accounting_ops.h> -#include <linux/netfs.h> -#include "internal.h" -#define CREATE_TRACE_POINTS -#include <trace/events/netfs.h> - -MODULE_DESCRIPTION("Network fs support"); -MODULE_AUTHOR("Red Hat, Inc."); -MODULE_LICENSE("GPL"); - -unsigned netfs_debug; -module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO); -MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask"); - -static void netfs_rreq_work(struct work_struct *); -static void __netfs_put_subrequest(struct netfs_read_subrequest *, bool); - -static void netfs_put_subrequest(struct netfs_read_subrequest *subreq, - bool was_async) -{ - if (refcount_dec_and_test(&subreq->usage)) - __netfs_put_subrequest(subreq, was_async); -} - -static struct netfs_read_request *netfs_alloc_read_request( - const struct netfs_read_request_ops *ops, void *netfs_priv, - struct file *file) -{ - static atomic_t debug_ids; - struct netfs_read_request *rreq; - - rreq = kzalloc(sizeof(struct netfs_read_request), GFP_KERNEL); - if (rreq) { - rreq->netfs_ops = ops; - rreq->netfs_priv = netfs_priv; - rreq->inode = file_inode(file); - rreq->i_size = i_size_read(rreq->inode); - rreq->debug_id = atomic_inc_return(&debug_ids); - INIT_LIST_HEAD(&rreq->subrequests); - INIT_WORK(&rreq->work, netfs_rreq_work); - refcount_set(&rreq->usage, 1); - __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - if (ops->init_rreq) - ops->init_rreq(rreq, file); - netfs_stat(&netfs_n_rh_rreq); - } - - return rreq; -} - -static void netfs_get_read_request(struct netfs_read_request *rreq) -{ - refcount_inc(&rreq->usage); -} - -static void netfs_rreq_clear_subreqs(struct netfs_read_request *rreq, - bool was_async) -{ - struct netfs_read_subrequest *subreq; - - while (!list_empty(&rreq->subrequests)) { - subreq = list_first_entry(&rreq->subrequests, - struct netfs_read_subrequest, rreq_link); - list_del(&subreq->rreq_link); - netfs_put_subrequest(subreq, was_async); - } -} - -static void netfs_free_read_request(struct work_struct *work) -{ - struct netfs_read_request *rreq = - container_of(work, struct netfs_read_request, work); - netfs_rreq_clear_subreqs(rreq, false); - if (rreq->netfs_priv) - rreq->netfs_ops->cleanup(rreq->mapping, rreq->netfs_priv); - trace_netfs_rreq(rreq, netfs_rreq_trace_free); - if (rreq->cache_resources.ops) - rreq->cache_resources.ops->end_operation(&rreq->cache_resources); - kfree(rreq); - netfs_stat_d(&netfs_n_rh_rreq); -} - -static void netfs_put_read_request(struct netfs_read_request *rreq, bool was_async) -{ - if (refcount_dec_and_test(&rreq->usage)) { - if (was_async) { - rreq->work.func = netfs_free_read_request; - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); - } else { - netfs_free_read_request(&rreq->work); - } - } -} - -/* - * Allocate and partially initialise an I/O request structure. - */ -static struct netfs_read_subrequest *netfs_alloc_subrequest( - struct netfs_read_request *rreq) -{ - struct netfs_read_subrequest *subreq; - - subreq = kzalloc(sizeof(struct netfs_read_subrequest), GFP_KERNEL); - if (subreq) { - INIT_LIST_HEAD(&subreq->rreq_link); - refcount_set(&subreq->usage, 2); - subreq->rreq = rreq; - netfs_get_read_request(rreq); - netfs_stat(&netfs_n_rh_sreq); - } - - return subreq; -} - -static void netfs_get_read_subrequest(struct netfs_read_subrequest *subreq) -{ - refcount_inc(&subreq->usage); -} - -static void __netfs_put_subrequest(struct netfs_read_subrequest *subreq, - bool was_async) -{ - struct netfs_read_request *rreq = subreq->rreq; - - trace_netfs_sreq(subreq, netfs_sreq_trace_free); - kfree(subreq); - netfs_stat_d(&netfs_n_rh_sreq); - netfs_put_read_request(rreq, was_async); -} - -/* - * Clear the unread part of an I/O request. - */ -static void netfs_clear_unread(struct netfs_read_subrequest *subreq) -{ - struct iov_iter iter; - - iov_iter_xarray(&iter, READ, &subreq->rreq->mapping->i_pages, - subreq->start + subreq->transferred, - subreq->len - subreq->transferred); - iov_iter_zero(iov_iter_count(&iter), &iter); -} - -static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_read_subrequest *subreq = priv; - - netfs_subreq_terminated(subreq, transferred_or_error, was_async); -} - -/* - * Issue a read against the cache. - * - Eats the caller's ref on subreq. - */ -static void netfs_read_from_cache(struct netfs_read_request *rreq, - struct netfs_read_subrequest *subreq, - enum netfs_read_from_hole read_hole) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - struct iov_iter iter; - - netfs_stat(&netfs_n_rh_read); - iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, - subreq->start + subreq->transferred, - subreq->len - subreq->transferred); - - cres->ops->read(cres, subreq->start, &iter, read_hole, - netfs_cache_read_terminated, subreq); -} - -/* - * Fill a subrequest region with zeroes. - */ -static void netfs_fill_with_zeroes(struct netfs_read_request *rreq, - struct netfs_read_subrequest *subreq) -{ - netfs_stat(&netfs_n_rh_zero); - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - netfs_subreq_terminated(subreq, 0, false); -} - -/* - * Ask the netfs to issue a read request to the server for us. - * - * The netfs is expected to read from subreq->pos + subreq->transferred to - * subreq->pos + subreq->len - 1. It may not backtrack and write data into the - * buffer prior to the transferred point as it might clobber dirty data - * obtained from the cache. - * - * Alternatively, the netfs is allowed to indicate one of two things: - * - * - NETFS_SREQ_SHORT_READ: A short read - it will get called again to try and - * make progress. - * - * - NETFS_SREQ_CLEAR_TAIL: A short read - the rest of the buffer will be - * cleared. - */ -static void netfs_read_from_server(struct netfs_read_request *rreq, - struct netfs_read_subrequest *subreq) -{ - netfs_stat(&netfs_n_rh_download); - rreq->netfs_ops->issue_op(subreq); -} - -/* - * Release those waiting. - */ -static void netfs_rreq_completed(struct netfs_read_request *rreq, bool was_async) -{ - trace_netfs_rreq(rreq, netfs_rreq_trace_done); - netfs_rreq_clear_subreqs(rreq, was_async); - netfs_put_read_request(rreq, was_async); -} - -/* - * Deal with the completion of writing the data to the cache. We have to clear - * the PG_fscache bits on the folios involved and release the caller's ref. - * - * May be called in softirq mode and we inherit a ref from the caller. - */ -static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq, - bool was_async) -{ - struct netfs_read_subrequest *subreq; - struct folio *folio; - pgoff_t unlocked = 0; - bool have_unlocked = false; - - rcu_read_lock(); - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); - - xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { - /* We might have multiple writes from the same huge - * folio, but we mustn't unlock a folio more than once. - */ - if (have_unlocked && folio_index(folio) <= unlocked) - continue; - unlocked = folio_index(folio); - folio_end_fscache(folio); - have_unlocked = true; - } - } - - rcu_read_unlock(); - netfs_rreq_completed(rreq, was_async); -} - -static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_read_subrequest *subreq = priv; - struct netfs_read_request *rreq = subreq->rreq; - - if (IS_ERR_VALUE(transferred_or_error)) { - netfs_stat(&netfs_n_rh_write_failed); - trace_netfs_failure(rreq, subreq, transferred_or_error, - netfs_fail_copy_to_cache); - } else { - netfs_stat(&netfs_n_rh_write_done); - } - - trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); - - /* If we decrement nr_wr_ops to 0, the ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_wr_ops)) - netfs_rreq_unmark_after_write(rreq, was_async); - - netfs_put_subrequest(subreq, was_async); -} - -/* - * Perform any outstanding writes to the cache. We inherit a ref from the - * caller. - */ -static void netfs_rreq_do_write_to_cache(struct netfs_read_request *rreq) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - struct netfs_read_subrequest *subreq, *next, *p; - struct iov_iter iter; - int ret; - - trace_netfs_rreq(rreq, netfs_rreq_trace_write); - - /* We don't want terminating writes trying to wake us up whilst we're - * still going through the list. - */ - atomic_inc(&rreq->nr_wr_ops); - - list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { - if (!test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) { - list_del_init(&subreq->rreq_link); - netfs_put_subrequest(subreq, false); - } - } - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - /* Amalgamate adjacent writes */ - while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - next = list_next_entry(subreq, rreq_link); - if (next->start != subreq->start + subreq->len) - break; - subreq->len += next->len; - list_del_init(&next->rreq_link); - netfs_put_subrequest(next, false); - } - - ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, - rreq->i_size, true); - if (ret < 0) { - trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); - trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); - continue; - } - - iov_iter_xarray(&iter, WRITE, &rreq->mapping->i_pages, - subreq->start, subreq->len); - - atomic_inc(&rreq->nr_wr_ops); - netfs_stat(&netfs_n_rh_write); - netfs_get_read_subrequest(subreq); - trace_netfs_sreq(subreq, netfs_sreq_trace_write); - cres->ops->write(cres, subreq->start, &iter, - netfs_rreq_copy_terminated, subreq); - } - - /* If we decrement nr_wr_ops to 0, the usage ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_wr_ops)) - netfs_rreq_unmark_after_write(rreq, false); -} - -static void netfs_rreq_write_to_cache_work(struct work_struct *work) -{ - struct netfs_read_request *rreq = - container_of(work, struct netfs_read_request, work); - - netfs_rreq_do_write_to_cache(rreq); -} - -static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq) -{ - rreq->work.func = netfs_rreq_write_to_cache_work; - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); -} - -/* - * Unlock the folios in a read operation. We need to set PG_fscache on any - * folios we're going to write back before we unlock them. - */ -static void netfs_rreq_unlock(struct netfs_read_request *rreq) -{ - struct netfs_read_subrequest *subreq; - struct folio *folio; - unsigned int iopos, account = 0; - pgoff_t start_page = rreq->start / PAGE_SIZE; - pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; - bool subreq_failed = false; - - XA_STATE(xas, &rreq->mapping->i_pages, start_page); - - if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { - __clear_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - __clear_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); - } - } - - /* Walk through the pagecache and the I/O request lists simultaneously. - * We may have a mixture of cached and uncached sections and we only - * really want to write out the uncached sections. This is slightly - * complicated by the possibility that we might have huge pages with a - * mixture inside. - */ - subreq = list_first_entry(&rreq->subrequests, - struct netfs_read_subrequest, rreq_link); - iopos = 0; - subreq_failed = (subreq->error < 0); - - trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); - - rcu_read_lock(); - xas_for_each(&xas, folio, last_page) { - unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE; - unsigned int pgend = pgpos + folio_size(folio); - bool pg_failed = false; - - for (;;) { - if (!subreq) { - pg_failed = true; - break; - } - if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) - folio_start_fscache(folio); - pg_failed |= subreq_failed; - if (pgend < iopos + subreq->len) - break; - - account += subreq->transferred; - iopos += subreq->len; - if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - subreq = list_next_entry(subreq, rreq_link); - subreq_failed = (subreq->error < 0); - } else { - subreq = NULL; - subreq_failed = false; - } - if (pgend == iopos) - break; - } - - if (!pg_failed) { - flush_dcache_folio(folio); - folio_mark_uptodate(folio); - } - - if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { - if (folio_index(folio) == rreq->no_unlock_folio && - test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) - _debug("no unlock"); - else - folio_unlock(folio); - } - } - rcu_read_unlock(); - - task_io_account_read(account); - if (rreq->netfs_ops->done) - rreq->netfs_ops->done(rreq); -} - -/* - * Handle a short read. - */ -static void netfs_rreq_short_read(struct netfs_read_request *rreq, - struct netfs_read_subrequest *subreq) -{ - __clear_bit(NETFS_SREQ_SHORT_READ, &subreq->flags); - __set_bit(NETFS_SREQ_SEEK_DATA_READ, &subreq->flags); - - netfs_stat(&netfs_n_rh_short_read); - trace_netfs_sreq(subreq, netfs_sreq_trace_resubmit_short); - - netfs_get_read_subrequest(subreq); - atomic_inc(&rreq->nr_rd_ops); - if (subreq->source == NETFS_READ_FROM_CACHE) - netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); - else - netfs_read_from_server(rreq, subreq); -} - -/* - * Resubmit any short or failed operations. Returns true if we got the rreq - * ref back. - */ -static bool netfs_rreq_perform_resubmissions(struct netfs_read_request *rreq) -{ - struct netfs_read_subrequest *subreq; - - WARN_ON(in_interrupt()); - - trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); - - /* We don't want terminating submissions trying to wake us up whilst - * we're still going through the list. - */ - atomic_inc(&rreq->nr_rd_ops); - - __clear_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - if (subreq->error) { - if (subreq->source != NETFS_READ_FROM_CACHE) - break; - subreq->source = NETFS_DOWNLOAD_FROM_SERVER; - subreq->error = 0; - netfs_stat(&netfs_n_rh_download_instead); - trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead); - netfs_get_read_subrequest(subreq); - atomic_inc(&rreq->nr_rd_ops); - netfs_read_from_server(rreq, subreq); - } else if (test_bit(NETFS_SREQ_SHORT_READ, &subreq->flags)) { - netfs_rreq_short_read(rreq, subreq); - } - } - - /* If we decrement nr_rd_ops to 0, the usage ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_rd_ops)) - return true; - - wake_up_var(&rreq->nr_rd_ops); - return false; -} - -/* - * Check to see if the data read is still valid. - */ -static void netfs_rreq_is_still_valid(struct netfs_read_request *rreq) -{ - struct netfs_read_subrequest *subreq; - - if (!rreq->netfs_ops->is_still_valid || - rreq->netfs_ops->is_still_valid(rreq)) - return; - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - if (subreq->source == NETFS_READ_FROM_CACHE) { - subreq->error = -ESTALE; - __set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - } - } -} - -/* - * Assess the state of a read request and decide what to do next. - * - * Note that we could be in an ordinary kernel thread, on a workqueue or in - * softirq context at this point. We inherit a ref from the caller. - */ -static void netfs_rreq_assess(struct netfs_read_request *rreq, bool was_async) -{ - trace_netfs_rreq(rreq, netfs_rreq_trace_assess); - -again: - netfs_rreq_is_still_valid(rreq); - - if (!test_bit(NETFS_RREQ_FAILED, &rreq->flags) && - test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags)) { - if (netfs_rreq_perform_resubmissions(rreq)) - goto again; - return; - } - - netfs_rreq_unlock(rreq); - - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); - - if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags)) - return netfs_rreq_write_to_cache(rreq); - - netfs_rreq_completed(rreq, was_async); -} - -static void netfs_rreq_work(struct work_struct *work) -{ - struct netfs_read_request *rreq = - container_of(work, struct netfs_read_request, work); - netfs_rreq_assess(rreq, false); -} - -/* - * Handle the completion of all outstanding I/O operations on a read request. - * We inherit a ref from the caller. - */ -static void netfs_rreq_terminated(struct netfs_read_request *rreq, - bool was_async) -{ - if (test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags) && - was_async) { - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); - } else { - netfs_rreq_assess(rreq, was_async); - } -} - -/** - * netfs_subreq_terminated - Note the termination of an I/O operation. - * @subreq: The I/O request that has terminated. - * @transferred_or_error: The amount of data transferred or an error code. - * @was_async: The termination was asynchronous - * - * This tells the read helper that a contributory I/O operation has terminated, - * one way or another, and that it should integrate the results. - * - * The caller indicates in @transferred_or_error the outcome of the operation, - * supplying a positive value to indicate the number of bytes transferred, 0 to - * indicate a failure to transfer anything that should be retried or a negative - * error code. The helper will look after reissuing I/O operations as - * appropriate and writing downloaded data to the cache. - * - * If @was_async is true, the caller might be running in softirq or interrupt - * context and we can't sleep. - */ -void netfs_subreq_terminated(struct netfs_read_subrequest *subreq, - ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_read_request *rreq = subreq->rreq; - int u; - - _enter("[%u]{%llx,%lx},%zd", - subreq->debug_index, subreq->start, subreq->flags, - transferred_or_error); - - switch (subreq->source) { - case NETFS_READ_FROM_CACHE: - netfs_stat(&netfs_n_rh_read_done); - break; - case NETFS_DOWNLOAD_FROM_SERVER: - netfs_stat(&netfs_n_rh_download_done); - break; - default: - break; - } - - if (IS_ERR_VALUE(transferred_or_error)) { - subreq->error = transferred_or_error; - trace_netfs_failure(rreq, subreq, transferred_or_error, - netfs_fail_read); - goto failed; - } - - if (WARN(transferred_or_error > subreq->len - subreq->transferred, - "Subreq overread: R%x[%x] %zd > %zu - %zu", - rreq->debug_id, subreq->debug_index, - transferred_or_error, subreq->len, subreq->transferred)) - transferred_or_error = subreq->len - subreq->transferred; - - subreq->error = 0; - subreq->transferred += transferred_or_error; - if (subreq->transferred < subreq->len) - goto incomplete; - -complete: - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) - set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); - -out: - trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - - /* If we decrement nr_rd_ops to 0, the ref belongs to us. */ - u = atomic_dec_return(&rreq->nr_rd_ops); - if (u == 0) - netfs_rreq_terminated(rreq, was_async); - else if (u == 1) - wake_up_var(&rreq->nr_rd_ops); - - netfs_put_subrequest(subreq, was_async); - return; - -incomplete: - if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) { - netfs_clear_unread(subreq); - subreq->transferred = subreq->len; - goto complete; - } - - if (transferred_or_error == 0) { - if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { - subreq->error = -ENODATA; - goto failed; - } - } else { - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - } - - __set_bit(NETFS_SREQ_SHORT_READ, &subreq->flags); - set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - goto out; - -failed: - if (subreq->source == NETFS_READ_FROM_CACHE) { - netfs_stat(&netfs_n_rh_read_failed); - set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - } else { - netfs_stat(&netfs_n_rh_download_failed); - set_bit(NETFS_RREQ_FAILED, &rreq->flags); - rreq->error = subreq->error; - } - goto out; -} -EXPORT_SYMBOL(netfs_subreq_terminated); - -static enum netfs_read_source netfs_cache_prepare_read(struct netfs_read_subrequest *subreq, - loff_t i_size) -{ - struct netfs_read_request *rreq = subreq->rreq; - struct netfs_cache_resources *cres = &rreq->cache_resources; - - if (cres->ops) - return cres->ops->prepare_read(subreq, i_size); - if (subreq->start >= rreq->i_size) - return NETFS_FILL_WITH_ZEROES; - return NETFS_DOWNLOAD_FROM_SERVER; -} - -/* - * Work out what sort of subrequest the next one will be. - */ -static enum netfs_read_source -netfs_rreq_prepare_read(struct netfs_read_request *rreq, - struct netfs_read_subrequest *subreq) -{ - enum netfs_read_source source; - - _enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size); - - source = netfs_cache_prepare_read(subreq, rreq->i_size); - if (source == NETFS_INVALID_READ) - goto out; - - if (source == NETFS_DOWNLOAD_FROM_SERVER) { - /* Call out to the netfs to let it shrink the request to fit - * its own I/O sizes and boundaries. If it shinks it here, it - * will be called again to make simultaneous calls; if it wants - * to make serial calls, it can indicate a short read and then - * we will call it again. - */ - if (subreq->len > rreq->i_size - subreq->start) - subreq->len = rreq->i_size - subreq->start; - - if (rreq->netfs_ops->clamp_length && - !rreq->netfs_ops->clamp_length(subreq)) { - source = NETFS_INVALID_READ; - goto out; - } - } - - if (WARN_ON(subreq->len == 0)) - source = NETFS_INVALID_READ; - -out: - subreq->source = source; - trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); - return source; -} - -/* - * Slice off a piece of a read request and submit an I/O request for it. - */ -static bool netfs_rreq_submit_slice(struct netfs_read_request *rreq, - unsigned int *_debug_index) -{ - struct netfs_read_subrequest *subreq; - enum netfs_read_source source; - - subreq = netfs_alloc_subrequest(rreq); - if (!subreq) - return false; - - subreq->debug_index = (*_debug_index)++; - subreq->start = rreq->start + rreq->submitted; - subreq->len = rreq->len - rreq->submitted; - - _debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted); - list_add_tail(&subreq->rreq_link, &rreq->subrequests); - - /* Call out to the cache to find out what it can do with the remaining - * subset. It tells us in subreq->flags what it decided should be done - * and adjusts subreq->len down if the subset crosses a cache boundary. - * - * Then when we hand the subset, it can choose to take a subset of that - * (the starts must coincide), in which case, we go around the loop - * again and ask it to download the next piece. - */ - source = netfs_rreq_prepare_read(rreq, subreq); - if (source == NETFS_INVALID_READ) - goto subreq_failed; - - atomic_inc(&rreq->nr_rd_ops); - - rreq->submitted += subreq->len; - - trace_netfs_sreq(subreq, netfs_sreq_trace_submit); - switch (source) { - case NETFS_FILL_WITH_ZEROES: - netfs_fill_with_zeroes(rreq, subreq); - break; - case NETFS_DOWNLOAD_FROM_SERVER: - netfs_read_from_server(rreq, subreq); - break; - case NETFS_READ_FROM_CACHE: - netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_IGNORE); - break; - default: - BUG(); - } - - return true; - -subreq_failed: - rreq->error = subreq->error; - netfs_put_subrequest(subreq, false); - return false; -} - -static void netfs_cache_expand_readahead(struct netfs_read_request *rreq, - loff_t *_start, size_t *_len, loff_t i_size) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - - if (cres->ops && cres->ops->expand_readahead) - cres->ops->expand_readahead(cres, _start, _len, i_size); -} - -static void netfs_rreq_expand(struct netfs_read_request *rreq, - struct readahead_control *ractl) -{ - /* Give the cache a chance to change the request parameters. The - * resultant request must contain the original region. - */ - netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); - - /* Give the netfs a chance to change the request parameters. The - * resultant request must contain the original region. - */ - if (rreq->netfs_ops->expand_readahead) - rreq->netfs_ops->expand_readahead(rreq); - - /* Expand the request if the cache wants it to start earlier. Note - * that the expansion may get further extended if the VM wishes to - * insert THPs and the preferred start and/or end wind up in the middle - * of THPs. - * - * If this is the case, however, the THP size should be an integer - * multiple of the cache granule size, so we get a whole number of - * granules to deal with. - */ - if (rreq->start != readahead_pos(ractl) || - rreq->len != readahead_length(ractl)) { - readahead_expand(ractl, rreq->start, rreq->len); - rreq->start = readahead_pos(ractl); - rreq->len = readahead_length(ractl); - - trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), - netfs_read_trace_expanded); - } -} - -/** - * netfs_readahead - Helper to manage a read request - * @ractl: The description of the readahead request - * @ops: The network filesystem's operations for the helper to use - * @netfs_priv: Private netfs data to be retained in the request - * - * Fulfil a readahead request by drawing data from the cache if possible, or - * the netfs if not. Space beyond the EOF is zero-filled. Multiple I/O - * requests from different sources will get munged together. If necessary, the - * readahead window can be expanded in either direction to a more convenient - * alighment for RPC efficiency or to make storage in the cache feasible. - * - * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. It may also be passed a private token, which will - * be retained in rreq->netfs_priv and will be cleaned up by ops->cleanup(). - * - * This is usable whether or not caching is enabled. - */ -void netfs_readahead(struct readahead_control *ractl, - const struct netfs_read_request_ops *ops, - void *netfs_priv) -{ - struct netfs_read_request *rreq; - unsigned int debug_index = 0; - int ret; - - _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); - - if (readahead_count(ractl) == 0) - goto cleanup; - - rreq = netfs_alloc_read_request(ops, netfs_priv, ractl->file); - if (!rreq) - goto cleanup; - rreq->mapping = ractl->mapping; - rreq->start = readahead_pos(ractl); - rreq->len = readahead_length(ractl); - - if (ops->begin_cache_operation) { - ret = ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) - goto cleanup_free; - } - - netfs_stat(&netfs_n_rh_readahead); - trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), - netfs_read_trace_readahead); - - netfs_rreq_expand(rreq, ractl); - - atomic_set(&rreq->nr_rd_ops, 1); - do { - if (!netfs_rreq_submit_slice(rreq, &debug_index)) - break; - - } while (rreq->submitted < rreq->len); - - /* Drop the refs on the folios here rather than in the cache or - * filesystem. The locks will be dropped in netfs_rreq_unlock(). - */ - while (readahead_folio(ractl)) - ; - - /* If we decrement nr_rd_ops to 0, the ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_rd_ops)) - netfs_rreq_assess(rreq, false); - return; - -cleanup_free: - netfs_put_read_request(rreq, false); - return; -cleanup: - if (netfs_priv) - ops->cleanup(ractl->mapping, netfs_priv); - return; -} -EXPORT_SYMBOL(netfs_readahead); - -/** - * netfs_readpage - Helper to manage a readpage request - * @file: The file to read from - * @folio: The folio to read - * @ops: The network filesystem's operations for the helper to use - * @netfs_priv: Private netfs data to be retained in the request - * - * Fulfil a readpage request by drawing data from the cache if possible, or the - * netfs if not. Space beyond the EOF is zero-filled. Multiple I/O requests - * from different sources will get munged together. - * - * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. It may also be passed a private token, which will - * be retained in rreq->netfs_priv and will be cleaned up by ops->cleanup(). - * - * This is usable whether or not caching is enabled. - */ -int netfs_readpage(struct file *file, - struct folio *folio, - const struct netfs_read_request_ops *ops, - void *netfs_priv) -{ - struct netfs_read_request *rreq; - unsigned int debug_index = 0; - int ret; - - _enter("%lx", folio_index(folio)); - - rreq = netfs_alloc_read_request(ops, netfs_priv, file); - if (!rreq) { - if (netfs_priv) - ops->cleanup(folio_file_mapping(folio), netfs_priv); - folio_unlock(folio); - return -ENOMEM; - } - rreq->mapping = folio_file_mapping(folio); - rreq->start = folio_file_pos(folio); - rreq->len = folio_size(folio); - - if (ops->begin_cache_operation) { - ret = ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) { - folio_unlock(folio); - goto out; - } - } - - netfs_stat(&netfs_n_rh_readpage); - trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); - - netfs_get_read_request(rreq); - - atomic_set(&rreq->nr_rd_ops, 1); - do { - if (!netfs_rreq_submit_slice(rreq, &debug_index)) - break; - - } while (rreq->submitted < rreq->len); - - /* Keep nr_rd_ops incremented so that the ref always belongs to us, and - * the service code isn't punted off to a random thread pool to - * process. - */ - do { - wait_var_event(&rreq->nr_rd_ops, atomic_read(&rreq->nr_rd_ops) == 1); - netfs_rreq_assess(rreq, false); - } while (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)); - - ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_readpage); - ret = -EIO; - } -out: - netfs_put_read_request(rreq, false); - return ret; -} -EXPORT_SYMBOL(netfs_readpage); - -/* - * Prepare a folio for writing without reading first - * @folio: The folio being prepared - * @pos: starting position for the write - * @len: length of write - * - * In some cases, write_begin doesn't need to read at all: - * - full folio write - * - write that lies in a folio that is completely beyond EOF - * - write that covers the folio from start to EOF or beyond it - * - * If any of these criteria are met, then zero out the unwritten parts - * of the folio and return true. Otherwise, return false. - */ -static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len) -{ - struct inode *inode = folio_inode(folio); - loff_t i_size = i_size_read(inode); - size_t offset = offset_in_folio(folio, pos); - - /* Full folio write */ - if (offset == 0 && len >= folio_size(folio)) - return true; - - /* pos beyond last folio in the file */ - if (pos - offset >= i_size) - goto zero_out; - - /* Write that covers from the start of the folio to EOF or beyond */ - if (offset == 0 && (pos + len) >= i_size) - goto zero_out; - - return false; -zero_out: - zero_user_segments(&folio->page, 0, offset, offset + len, folio_size(folio)); - return true; -} - -/** - * netfs_write_begin - Helper to prepare for writing - * @file: The file to read from - * @mapping: The mapping to read from - * @pos: File position at which the write will begin - * @len: The length of the write (may extend beyond the end of the folio chosen) - * @aop_flags: AOP_* flags - * @_folio: Where to put the resultant folio - * @_fsdata: Place for the netfs to store a cookie - * @ops: The network filesystem's operations for the helper to use - * @netfs_priv: Private netfs data to be retained in the request - * - * Pre-read data for a write-begin request by drawing data from the cache if - * possible, or the netfs if not. Space beyond the EOF is zero-filled. - * Multiple I/O requests from different sources will get munged together. If - * necessary, the readahead window can be expanded in either direction to a - * more convenient alighment for RPC efficiency or to make storage in the cache - * feasible. - * - * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. - * - * The check_write_begin() operation can be provided to check for and flush - * conflicting writes once the folio is grabbed and locked. It is passed a - * pointer to the fsdata cookie that gets returned to the VM to be passed to - * write_end. It is permitted to sleep. It should return 0 if the request - * should go ahead; unlock the folio and return -EAGAIN to cause the folio to - * be regot; or return an error. - * - * This is usable whether or not caching is enabled. - */ -int netfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int aop_flags, - struct folio **_folio, void **_fsdata, - const struct netfs_read_request_ops *ops, - void *netfs_priv) -{ - struct netfs_read_request *rreq; - struct folio *folio; - struct inode *inode = file_inode(file); - unsigned int debug_index = 0, fgp_flags; - pgoff_t index = pos >> PAGE_SHIFT; - int ret; - - DEFINE_READAHEAD(ractl, file, NULL, mapping, index); - -retry: - fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; - if (aop_flags & AOP_FLAG_NOFS) - fgp_flags |= FGP_NOFS; - folio = __filemap_get_folio(mapping, index, fgp_flags, - mapping_gfp_mask(mapping)); - if (!folio) - return -ENOMEM; - - if (ops->check_write_begin) { - /* Allow the netfs (eg. ceph) to flush conflicts. */ - ret = ops->check_write_begin(file, pos, len, folio, _fsdata); - if (ret < 0) { - trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); - if (ret == -EAGAIN) - goto retry; - goto error; - } - } - - if (folio_test_uptodate(folio)) - goto have_folio; - - /* If the page is beyond the EOF, we want to clear it - unless it's - * within the cache granule containing the EOF, in which case we need - * to preload the granule. - */ - if (!ops->is_cache_enabled(inode) && - netfs_skip_folio_read(folio, pos, len)) { - netfs_stat(&netfs_n_rh_write_zskip); - goto have_folio_no_wait; - } - - ret = -ENOMEM; - rreq = netfs_alloc_read_request(ops, netfs_priv, file); - if (!rreq) - goto error; - rreq->mapping = folio_file_mapping(folio); - rreq->start = folio_file_pos(folio); - rreq->len = folio_size(folio); - rreq->no_unlock_folio = folio_index(folio); - __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); - netfs_priv = NULL; - - if (ops->begin_cache_operation) { - ret = ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) - goto error_put; - } - - netfs_stat(&netfs_n_rh_write_begin); - trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); - - /* Expand the request to meet caching requirements and download - * preferences. - */ - ractl._nr_pages = folio_nr_pages(folio); - netfs_rreq_expand(rreq, &ractl); - netfs_get_read_request(rreq); - - /* We hold the folio locks, so we can drop the references */ - folio_get(folio); - while (readahead_folio(&ractl)) - ; - - atomic_set(&rreq->nr_rd_ops, 1); - do { - if (!netfs_rreq_submit_slice(rreq, &debug_index)) - break; - - } while (rreq->submitted < rreq->len); - - /* Keep nr_rd_ops incremented so that the ref always belongs to us, and - * the service code isn't punted off to a random thread pool to - * process. - */ - for (;;) { - wait_var_event(&rreq->nr_rd_ops, atomic_read(&rreq->nr_rd_ops) == 1); - netfs_rreq_assess(rreq, false); - if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) - break; - cond_resched(); - } - - ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_write_begin); - ret = -EIO; - } - netfs_put_read_request(rreq, false); - if (ret < 0) - goto error; - -have_folio: - ret = folio_wait_fscache_killable(folio); - if (ret < 0) - goto error; -have_folio_no_wait: - if (netfs_priv) - ops->cleanup(mapping, netfs_priv); - *_folio = folio; - _leave(" = 0"); - return 0; - -error_put: - netfs_put_read_request(rreq, false); -error: - folio_unlock(folio); - folio_put(folio); - if (netfs_priv) - ops->cleanup(mapping, netfs_priv); - _leave(" = %d", ret); - return ret; -} -EXPORT_SYMBOL(netfs_write_begin); diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index 9ae538c85378..5510a7a14a40 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -7,7 +7,6 @@ #include <linux/export.h> #include <linux/seq_file.h> -#include <linux/netfs.h> #include "internal.h" atomic_t netfs_n_rh_readahead; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 4dee53ceb941..f73c09a9cf0a 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -238,14 +238,6 @@ void nfs_fscache_release_file(struct inode *inode, struct file *filp) } } -static inline void fscache_end_operation(struct netfs_cache_resources *cres) -{ - const struct netfs_cache_ops *ops = fscache_operation_valid(cres); - - if (ops) - ops->end_operation(cres); -} - /* * Fallback page reading interface. */ diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 66bdaa2cf496..ca611ac09f7c 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -20,6 +20,23 @@ #include "page.h" #include "btnode.h" + +/** + * nilfs_init_btnc_inode - initialize B-tree node cache inode + * @btnc_inode: inode to be initialized + * + * nilfs_init_btnc_inode() sets up an inode for B-tree node cache. + */ +void nilfs_init_btnc_inode(struct inode *btnc_inode) +{ + struct nilfs_inode_info *ii = NILFS_I(btnc_inode); + + btnc_inode->i_mode = S_IFREG; + ii->i_flags = 0; + memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap)); + mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS); +} + void nilfs_btnode_cache_clear(struct address_space *btnc) { invalidate_mapping_pages(btnc, 0, -1); @@ -29,7 +46,7 @@ void nilfs_btnode_cache_clear(struct address_space *btnc) struct buffer_head * nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) { - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; struct buffer_head *bh; bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node)); @@ -57,7 +74,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr, struct buffer_head **pbh, sector_t *submit_ptr) { struct buffer_head *bh; - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; struct page *page; int err; @@ -157,7 +174,7 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, struct nilfs_btnode_chkey_ctxt *ctxt) { struct buffer_head *obh, *nbh; - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; __u64 oldkey = ctxt->oldkey, newkey = ctxt->newkey; int err; diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h index 11663650add7..bd5544e63a01 100644 --- a/fs/nilfs2/btnode.h +++ b/fs/nilfs2/btnode.h @@ -30,6 +30,7 @@ struct nilfs_btnode_chkey_ctxt { struct buffer_head *newbh; }; +void nilfs_init_btnc_inode(struct inode *btnc_inode); void nilfs_btnode_cache_clear(struct address_space *); struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 3594eabe1419..f544c22fff78 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -58,7 +58,8 @@ static void nilfs_btree_free_path(struct nilfs_btree_path *path) static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp) { - struct address_space *btnc = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh; bh = nilfs_btnode_create_block(btnc, ptr); @@ -470,7 +471,8 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp, const struct nilfs_btree_readahead_info *ra) { - struct address_space *btnc = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh, *ra_bh; sector_t submit_ptr = 0; int ret; @@ -1741,6 +1743,10 @@ nilfs_btree_prepare_convert_and_insert(struct nilfs_bmap *btree, __u64 key, dat = nilfs_bmap_get_dat(btree); } + ret = nilfs_attach_btree_node_cache(&NILFS_BMAP_I(btree)->vfs_inode); + if (ret < 0) + return ret; + ret = nilfs_bmap_prepare_alloc_ptr(btree, dreq, dat); if (ret < 0) return ret; @@ -1913,7 +1919,7 @@ static int nilfs_btree_prepare_update_v(struct nilfs_bmap *btree, path[level].bp_ctxt.newkey = path[level].bp_newreq.bpr_ptr; path[level].bp_ctxt.bh = path[level].bp_bh; ret = nilfs_btnode_prepare_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) { nilfs_dat_abort_update(dat, @@ -1939,7 +1945,7 @@ static void nilfs_btree_commit_update_v(struct nilfs_bmap *btree, if (buffer_nilfs_node(path[level].bp_bh)) { nilfs_btnode_commit_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); path[level].bp_bh = path[level].bp_ctxt.bh; } @@ -1958,7 +1964,7 @@ static void nilfs_btree_abort_update_v(struct nilfs_bmap *btree, &path[level].bp_newreq.bpr_req); if (buffer_nilfs_node(path[level].bp_bh)) nilfs_btnode_abort_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); } @@ -2134,7 +2140,8 @@ static void nilfs_btree_add_dirty_buffer(struct nilfs_bmap *btree, static void nilfs_btree_lookup_dirty_buffers(struct nilfs_bmap *btree, struct list_head *listp) { - struct address_space *btcache = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btcache = btnc_inode->i_mapping; struct list_head lists[NILFS_BTREE_LEVEL_MAX]; struct pagevec pvec; struct buffer_head *bh, *head; @@ -2188,12 +2195,12 @@ static int nilfs_btree_assign_p(struct nilfs_bmap *btree, path[level].bp_ctxt.newkey = blocknr; path[level].bp_ctxt.bh = *bh; ret = nilfs_btnode_prepare_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) return ret; nilfs_btnode_commit_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); *bh = path[level].bp_ctxt.bh; } @@ -2398,6 +2405,10 @@ int nilfs_btree_init(struct nilfs_bmap *bmap) if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap), bmap->b_inode)) ret = -EIO; + else + ret = nilfs_attach_btree_node_cache( + &NILFS_BMAP_I(bmap)->vfs_inode); + return ret; } diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index dc51d3b7a7bf..3b55e239705f 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -497,7 +497,9 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size, di = NILFS_DAT_I(dat); lockdep_set_class(&di->mi.mi_sem, &dat_lock_key); nilfs_palloc_setup_cache(dat, &di->palloc_cache); - nilfs_mdt_setup_shadow_map(dat, &di->shadow); + err = nilfs_mdt_setup_shadow_map(dat, &di->shadow); + if (err) + goto failed; err = nilfs_read_inode_common(dat, raw_inode); if (err) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index a8f5315f01e3..04fdd420eae7 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -126,9 +126,10 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, int nilfs_gccache_submit_read_node(struct inode *inode, sector_t pbn, __u64 vbn, struct buffer_head **out_bh) { + struct inode *btnc_inode = NILFS_I(inode)->i_assoc_inode; int ret; - ret = nilfs_btnode_submit_block(&NILFS_I(inode)->i_btnode_cache, + ret = nilfs_btnode_submit_block(btnc_inode->i_mapping, vbn ? : pbn, pbn, REQ_OP_READ, 0, out_bh, &pbn); if (ret == -EEXIST) /* internal code (cache hit) */ @@ -170,7 +171,7 @@ int nilfs_init_gcinode(struct inode *inode) ii->i_flags = 0; nilfs_bmap_init_gc(ii->i_bmap); - return 0; + return nilfs_attach_btree_node_cache(inode); } /** @@ -185,7 +186,7 @@ void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs) ii = list_first_entry(head, struct nilfs_inode_info, i_dirty); list_del_init(&ii->i_dirty); truncate_inode_pages(&ii->vfs_inode.i_data, 0); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + nilfs_btnode_cache_clear(ii->i_assoc_inode->i_mapping); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 476a4a649f38..6045cea21f52 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -29,12 +29,16 @@ * @cno: checkpoint number * @root: pointer on NILFS root object (mounted checkpoint) * @for_gc: inode for GC flag + * @for_btnc: inode for B-tree node cache flag + * @for_shadow: inode for shadowed page cache flag */ struct nilfs_iget_args { u64 ino; __u64 cno; struct nilfs_root *root; - int for_gc; + bool for_gc; + bool for_btnc; + bool for_shadow; }; static int nilfs_iget_test(struct inode *inode, void *opaque); @@ -312,7 +316,8 @@ static int nilfs_insert_inode_locked(struct inode *inode, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = false }; return insert_inode_locked4(inode, ino, nilfs_iget_test, &args); @@ -525,6 +530,19 @@ static int nilfs_iget_test(struct inode *inode, void *opaque) return 0; ii = NILFS_I(inode); + if (test_bit(NILFS_I_BTNC, &ii->i_state)) { + if (!args->for_btnc) + return 0; + } else if (args->for_btnc) { + return 0; + } + if (test_bit(NILFS_I_SHADOW, &ii->i_state)) { + if (!args->for_shadow) + return 0; + } else if (args->for_shadow) { + return 0; + } + if (!test_bit(NILFS_I_GCINODE, &ii->i_state)) return !args->for_gc; @@ -536,15 +554,17 @@ static int nilfs_iget_set(struct inode *inode, void *opaque) struct nilfs_iget_args *args = opaque; inode->i_ino = args->ino; - if (args->for_gc) { + NILFS_I(inode)->i_cno = args->cno; + NILFS_I(inode)->i_root = args->root; + if (args->root && args->ino == NILFS_ROOT_INO) + nilfs_get_root(args->root); + + if (args->for_gc) NILFS_I(inode)->i_state = BIT(NILFS_I_GCINODE); - NILFS_I(inode)->i_cno = args->cno; - NILFS_I(inode)->i_root = NULL; - } else { - if (args->root && args->ino == NILFS_ROOT_INO) - nilfs_get_root(args->root); - NILFS_I(inode)->i_root = args->root; - } + if (args->for_btnc) + NILFS_I(inode)->i_state |= BIT(NILFS_I_BTNC); + if (args->for_shadow) + NILFS_I(inode)->i_state |= BIT(NILFS_I_SHADOW); return 0; } @@ -552,7 +572,8 @@ struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = false }; return ilookup5(sb, ino, nilfs_iget_test, &args); @@ -562,7 +583,8 @@ struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = false }; return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args); @@ -593,7 +615,8 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, __u64 cno) { struct nilfs_iget_args args = { - .ino = ino, .root = NULL, .cno = cno, .for_gc = 1 + .ino = ino, .root = NULL, .cno = cno, .for_gc = true, + .for_btnc = false, .for_shadow = false }; struct inode *inode; int err; @@ -613,6 +636,113 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, return inode; } +/** + * nilfs_attach_btree_node_cache - attach a B-tree node cache to the inode + * @inode: inode object + * + * nilfs_attach_btree_node_cache() attaches a B-tree node cache to @inode, + * or does nothing if the inode already has it. This function allocates + * an additional inode to maintain page cache of B-tree nodes one-on-one. + * + * Return Value: On success, 0 is returned. On errors, one of the following + * negative error code is returned. + * + * %-ENOMEM - Insufficient memory available. + */ +int nilfs_attach_btree_node_cache(struct inode *inode) +{ + struct nilfs_inode_info *ii = NILFS_I(inode); + struct inode *btnc_inode; + struct nilfs_iget_args args; + + if (ii->i_assoc_inode) + return 0; + + args.ino = inode->i_ino; + args.root = ii->i_root; + args.cno = ii->i_cno; + args.for_gc = test_bit(NILFS_I_GCINODE, &ii->i_state) != 0; + args.for_btnc = true; + args.for_shadow = test_bit(NILFS_I_SHADOW, &ii->i_state) != 0; + + btnc_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test, + nilfs_iget_set, &args); + if (unlikely(!btnc_inode)) + return -ENOMEM; + if (btnc_inode->i_state & I_NEW) { + nilfs_init_btnc_inode(btnc_inode); + unlock_new_inode(btnc_inode); + } + NILFS_I(btnc_inode)->i_assoc_inode = inode; + NILFS_I(btnc_inode)->i_bmap = ii->i_bmap; + ii->i_assoc_inode = btnc_inode; + + return 0; +} + +/** + * nilfs_detach_btree_node_cache - detach the B-tree node cache from the inode + * @inode: inode object + * + * nilfs_detach_btree_node_cache() detaches the B-tree node cache and its + * holder inode bound to @inode, or does nothing if @inode doesn't have it. + */ +void nilfs_detach_btree_node_cache(struct inode *inode) +{ + struct nilfs_inode_info *ii = NILFS_I(inode); + struct inode *btnc_inode = ii->i_assoc_inode; + + if (btnc_inode) { + NILFS_I(btnc_inode)->i_assoc_inode = NULL; + ii->i_assoc_inode = NULL; + iput(btnc_inode); + } +} + +/** + * nilfs_iget_for_shadow - obtain inode for shadow mapping + * @inode: inode object that uses shadow mapping + * + * nilfs_iget_for_shadow() allocates a pair of inodes that holds page + * caches for shadow mapping. The page cache for data pages is set up + * in one inode and the one for b-tree node pages is set up in the + * other inode, which is attached to the former inode. + * + * Return Value: On success, a pointer to the inode for data pages is + * returned. On errors, one of the following negative error code is returned + * in a pointer type. + * + * %-ENOMEM - Insufficient memory available. + */ +struct inode *nilfs_iget_for_shadow(struct inode *inode) +{ + struct nilfs_iget_args args = { + .ino = inode->i_ino, .root = NULL, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = true + }; + struct inode *s_inode; + int err; + + s_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test, + nilfs_iget_set, &args); + if (unlikely(!s_inode)) + return ERR_PTR(-ENOMEM); + if (!(s_inode->i_state & I_NEW)) + return inode; + + NILFS_I(s_inode)->i_flags = 0; + memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap)); + mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS); + + err = nilfs_attach_btree_node_cache(s_inode); + if (unlikely(err)) { + iget_failed(s_inode); + return ERR_PTR(err); + } + unlock_new_inode(s_inode); + return s_inode; +} + void nilfs_write_inode_common(struct inode *inode, struct nilfs_inode *raw_inode, int has_bmap) { @@ -760,7 +890,8 @@ static void nilfs_clear_inode(struct inode *inode) if (test_bit(NILFS_I_BMAP, &ii->i_state)) nilfs_bmap_clear(ii->i_bmap); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + if (!test_bit(NILFS_I_BTNC, &ii->i_state)) + nilfs_detach_btree_node_cache(inode); if (ii->i_root && inode->i_ino == NILFS_ROOT_INO) nilfs_put_root(ii->i_root); diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 78db33decd72..d29a0f2b9c16 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -471,9 +471,18 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz) void nilfs_mdt_clear(struct inode *inode) { struct nilfs_mdt_info *mdi = NILFS_MDT(inode); + struct nilfs_shadow_map *shadow = mdi->mi_shadow; if (mdi->mi_palloc_cache) nilfs_palloc_destroy_cache(inode); + + if (shadow) { + struct inode *s_inode = shadow->inode; + + shadow->inode = NULL; + iput(s_inode); + mdi->mi_shadow = NULL; + } } /** @@ -507,12 +516,15 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode, struct nilfs_shadow_map *shadow) { struct nilfs_mdt_info *mi = NILFS_MDT(inode); + struct inode *s_inode; INIT_LIST_HEAD(&shadow->frozen_buffers); - address_space_init_once(&shadow->frozen_data); - nilfs_mapping_init(&shadow->frozen_data, inode); - address_space_init_once(&shadow->frozen_btnodes); - nilfs_mapping_init(&shadow->frozen_btnodes, inode); + + s_inode = nilfs_iget_for_shadow(inode); + if (IS_ERR(s_inode)) + return PTR_ERR(s_inode); + + shadow->inode = s_inode; mi->mi_shadow = shadow; return 0; } @@ -526,14 +538,15 @@ int nilfs_mdt_save_to_shadow_map(struct inode *inode) struct nilfs_mdt_info *mi = NILFS_MDT(inode); struct nilfs_inode_info *ii = NILFS_I(inode); struct nilfs_shadow_map *shadow = mi->mi_shadow; + struct inode *s_inode = shadow->inode; int ret; - ret = nilfs_copy_dirty_pages(&shadow->frozen_data, inode->i_mapping); + ret = nilfs_copy_dirty_pages(s_inode->i_mapping, inode->i_mapping); if (ret) goto out; - ret = nilfs_copy_dirty_pages(&shadow->frozen_btnodes, - &ii->i_btnode_cache); + ret = nilfs_copy_dirty_pages(NILFS_I(s_inode)->i_assoc_inode->i_mapping, + ii->i_assoc_inode->i_mapping); if (ret) goto out; @@ -549,7 +562,7 @@ int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh) struct page *page; int blkbits = inode->i_blkbits; - page = grab_cache_page(&shadow->frozen_data, bh->b_page->index); + page = grab_cache_page(shadow->inode->i_mapping, bh->b_page->index); if (!page) return -ENOMEM; @@ -581,7 +594,7 @@ nilfs_mdt_get_frozen_buffer(struct inode *inode, struct buffer_head *bh) struct page *page; int n; - page = find_lock_page(&shadow->frozen_data, bh->b_page->index); + page = find_lock_page(shadow->inode->i_mapping, bh->b_page->index); if (page) { if (page_has_buffers(page)) { n = bh_offset(bh) >> inode->i_blkbits; @@ -622,10 +635,11 @@ void nilfs_mdt_restore_from_shadow_map(struct inode *inode) nilfs_palloc_clear_cache(inode); nilfs_clear_dirty_pages(inode->i_mapping, true); - nilfs_copy_back_pages(inode->i_mapping, &shadow->frozen_data); + nilfs_copy_back_pages(inode->i_mapping, shadow->inode->i_mapping); - nilfs_clear_dirty_pages(&ii->i_btnode_cache, true); - nilfs_copy_back_pages(&ii->i_btnode_cache, &shadow->frozen_btnodes); + nilfs_clear_dirty_pages(ii->i_assoc_inode->i_mapping, true); + nilfs_copy_back_pages(ii->i_assoc_inode->i_mapping, + NILFS_I(shadow->inode)->i_assoc_inode->i_mapping); nilfs_bmap_restore(ii->i_bmap, &shadow->bmap_store); @@ -640,10 +654,11 @@ void nilfs_mdt_clear_shadow_map(struct inode *inode) { struct nilfs_mdt_info *mi = NILFS_MDT(inode); struct nilfs_shadow_map *shadow = mi->mi_shadow; + struct inode *shadow_btnc_inode = NILFS_I(shadow->inode)->i_assoc_inode; down_write(&mi->mi_sem); nilfs_release_frozen_buffers(shadow); - truncate_inode_pages(&shadow->frozen_data, 0); - truncate_inode_pages(&shadow->frozen_btnodes, 0); + truncate_inode_pages(shadow->inode->i_mapping, 0); + truncate_inode_pages(shadow_btnc_inode->i_mapping, 0); up_write(&mi->mi_sem); } diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index 8f86080a436d..9e23bab3ff12 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -18,14 +18,12 @@ /** * struct nilfs_shadow_map - shadow mapping of meta data file * @bmap_store: shadow copy of bmap state - * @frozen_data: shadowed dirty data pages - * @frozen_btnodes: shadowed dirty b-tree nodes' pages + * @inode: holder of page caches used in shadow mapping * @frozen_buffers: list of frozen buffers */ struct nilfs_shadow_map { struct nilfs_bmap_store bmap_store; - struct address_space frozen_data; - struct address_space frozen_btnodes; + struct inode *inode; struct list_head frozen_buffers; }; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index a7b81755c350..1344f7d475d3 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -28,7 +28,7 @@ * @i_xattr: <TODO> * @i_dir_start_lookup: page index of last successful search * @i_cno: checkpoint number for GC inode - * @i_btnode_cache: cached pages of b-tree nodes + * @i_assoc_inode: associated inode (B-tree node cache holder or back pointer) * @i_dirty: list for connecting dirty files * @xattr_sem: semaphore for extended attributes processing * @i_bh: buffer contains disk inode @@ -43,7 +43,7 @@ struct nilfs_inode_info { __u64 i_xattr; /* sector_t ??? */ __u32 i_dir_start_lookup; __u64 i_cno; /* check point number for GC inode */ - struct address_space i_btnode_cache; + struct inode *i_assoc_inode; struct list_head i_dirty; /* List for connecting dirty files */ #ifdef CONFIG_NILFS_XATTR @@ -75,13 +75,6 @@ NILFS_BMAP_I(const struct nilfs_bmap *bmap) return container_of(bmap, struct nilfs_inode_info, i_bmap_data); } -static inline struct inode *NILFS_BTNC_I(struct address_space *btnc) -{ - struct nilfs_inode_info *ii = - container_of(btnc, struct nilfs_inode_info, i_btnode_cache); - return &ii->vfs_inode; -} - /* * Dynamic state flags of NILFS on-memory inode (i_state) */ @@ -98,6 +91,8 @@ enum { NILFS_I_INODE_SYNC, /* dsync is not allowed for inode */ NILFS_I_BMAP, /* has bmap and btnode_cache */ NILFS_I_GCINODE, /* inode for GC, on memory only */ + NILFS_I_BTNC, /* inode for btree node cache */ + NILFS_I_SHADOW, /* inode for shadowed page cache */ }; /* @@ -267,6 +262,9 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, unsigned long ino); extern struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, __u64 cno); +int nilfs_attach_btree_node_cache(struct inode *inode); +void nilfs_detach_btree_node_cache(struct inode *inode); +struct inode *nilfs_iget_for_shadow(struct inode *inode); extern void nilfs_update_inode(struct inode *, struct buffer_head *, int); extern void nilfs_truncate(struct inode *); extern void nilfs_evict_inode(struct inode *); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 063dd16d75b5..a8e88cc38e16 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -436,22 +436,12 @@ unsigned int nilfs_page_count_clean_buffers(struct page *page, return nc; } -void nilfs_mapping_init(struct address_space *mapping, struct inode *inode) -{ - mapping->host = inode; - mapping->flags = 0; - mapping_set_gfp_mask(mapping, GFP_NOFS); - mapping->private_data = NULL; - mapping->a_ops = &empty_aops; -} - /* * NILFS2 needs clear_page_dirty() in the following two cases: * - * 1) For B-tree node pages and data pages of the dat/gcdat, NILFS2 clears - * page dirty flags when it copies back pages from the shadow cache - * (gcdat->{i_mapping,i_btnode_cache}) to its original cache - * (dat->{i_mapping,i_btnode_cache}). + * 1) For B-tree node pages and data pages of DAT file, NILFS2 clears dirty + * flag of pages when it copies back pages from shadow cache to the + * original cache. * * 2) Some B-tree operations like insertion or deletion may dispose buffers * in dirty state, and this needs to cancel the dirty state of their pages. diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index 569263b23c0c..21ddcdd4d63e 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -43,7 +43,6 @@ int nilfs_copy_dirty_pages(struct address_space *, struct address_space *); void nilfs_copy_back_pages(struct address_space *, struct address_space *); void nilfs_clear_dirty_page(struct page *, bool); void nilfs_clear_dirty_pages(struct address_space *, bool); -void nilfs_mapping_init(struct address_space *mapping, struct inode *inode); unsigned int nilfs_page_count_clean_buffers(struct page *, unsigned int, unsigned int); unsigned long nilfs_find_uncommitted_extent(struct inode *inode, diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 85a853334771..0afe0832c754 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -733,15 +733,18 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode, struct list_head *listp) { struct nilfs_inode_info *ii = NILFS_I(inode); - struct address_space *mapping = &ii->i_btnode_cache; + struct inode *btnc_inode = ii->i_assoc_inode; struct pagevec pvec; struct buffer_head *bh, *head; unsigned int i; pgoff_t index = 0; + if (!btnc_inode) + return; + pagevec_init(&pvec); - while (pagevec_lookup_tag(&pvec, mapping, &index, + while (pagevec_lookup_tag(&pvec, btnc_inode->i_mapping, &index, PAGECACHE_TAG_DIRTY)) { for (i = 0; i < pagevec_count(&pvec); i++) { bh = head = page_buffers(pvec.pages[i]); @@ -2410,7 +2413,7 @@ nilfs_remove_written_gcinodes(struct the_nilfs *nilfs, struct list_head *head) continue; list_del_init(&ii->i_dirty); truncate_inode_pages(&ii->vfs_inode.i_data, 0); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + nilfs_btnode_cache_clear(ii->i_assoc_inode->i_mapping); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 3e05c98631ec..ba108f915391 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -157,7 +157,8 @@ struct inode *nilfs_alloc_inode(struct super_block *sb) ii->i_bh = NULL; ii->i_state = 0; ii->i_cno = 0; - nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode); + ii->i_assoc_inode = NULL; + ii->i_bmap = &ii->i_bmap_data; return &ii->vfs_inode; } @@ -1377,8 +1378,6 @@ static void nilfs_inode_init_once(void *obj) #ifdef CONFIG_NILFS_XATTR init_rwsem(&ii->xattr_sem); #endif - address_space_init_once(&ii->i_btnode_cache); - ii->i_bmap = &ii->i_bmap_data; inode_init_once(&ii->vfs_inode); } diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 273f65e0aaba..0b6f551a342a 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -337,7 +337,6 @@ void ocfs2_unlock_global_qf(struct ocfs2_mem_dqinfo *oinfo, int ex) /* Read information header from global quota file */ int ocfs2_global_read_info(struct super_block *sb, int type) { - struct inode *gqinode = NULL; unsigned int ino[OCFS2_MAXQUOTAS] = { USER_QUOTA_SYSTEM_INODE, GROUP_QUOTA_SYSTEM_INODE }; struct ocfs2_global_disk_dqinfo dinfo; @@ -346,29 +345,31 @@ int ocfs2_global_read_info(struct super_block *sb, int type) u64 pcount; int status; + oinfo->dqi_gi.dqi_sb = sb; + oinfo->dqi_gi.dqi_type = type; + ocfs2_qinfo_lock_res_init(&oinfo->dqi_gqlock, oinfo); + oinfo->dqi_gi.dqi_entry_size = sizeof(struct ocfs2_global_disk_dqblk); + oinfo->dqi_gi.dqi_ops = &ocfs2_global_ops; + oinfo->dqi_gqi_bh = NULL; + oinfo->dqi_gqi_count = 0; + /* Read global header */ - gqinode = ocfs2_get_system_file_inode(OCFS2_SB(sb), ino[type], + oinfo->dqi_gqinode = ocfs2_get_system_file_inode(OCFS2_SB(sb), ino[type], OCFS2_INVALID_SLOT); - if (!gqinode) { + if (!oinfo->dqi_gqinode) { mlog(ML_ERROR, "failed to get global quota inode (type=%d)\n", type); status = -EINVAL; goto out_err; } - oinfo->dqi_gi.dqi_sb = sb; - oinfo->dqi_gi.dqi_type = type; - oinfo->dqi_gi.dqi_entry_size = sizeof(struct ocfs2_global_disk_dqblk); - oinfo->dqi_gi.dqi_ops = &ocfs2_global_ops; - oinfo->dqi_gqi_bh = NULL; - oinfo->dqi_gqi_count = 0; - oinfo->dqi_gqinode = gqinode; + status = ocfs2_lock_global_qf(oinfo, 0); if (status < 0) { mlog_errno(status); goto out_err; } - status = ocfs2_extent_map_get_blocks(gqinode, 0, &oinfo->dqi_giblk, + status = ocfs2_extent_map_get_blocks(oinfo->dqi_gqinode, 0, &oinfo->dqi_giblk, &pcount, NULL); if (status < 0) goto out_unlock; diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 0e4b16d4c037..b1a8b046f4c2 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -702,8 +702,6 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) info->dqi_priv = oinfo; oinfo->dqi_type = type; INIT_LIST_HEAD(&oinfo->dqi_chunk); - oinfo->dqi_gqinode = NULL; - ocfs2_qinfo_lock_res_init(&oinfo->dqi_gqlock, oinfo); oinfo->dqi_rec = NULL; oinfo->dqi_lqi_bh = NULL; oinfo->dqi_libh = NULL; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index dbe72f664abf..86151889548e 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -349,20 +349,97 @@ out_budg: return err; } -static int do_tmpfile(struct inode *dir, struct dentry *dentry, - umode_t mode, struct inode **whiteout) +static struct inode *create_whiteout(struct inode *dir, struct dentry *dentry) +{ + int err; + umode_t mode = S_IFCHR | WHITEOUT_MODE; + struct inode *inode; + struct ubifs_info *c = dir->i_sb->s_fs_info; + struct fscrypt_name nm; + + /* + * Create an inode('nlink = 1') for whiteout without updating journal, + * let ubifs_jnl_rename() store it on flash to complete rename whiteout + * atomically. + */ + + dbg_gen("dent '%pd', mode %#hx in dir ino %lu", + dentry, mode, dir->i_ino); + + err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + if (err) + return ERR_PTR(err); + + inode = ubifs_new_inode(c, dir, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_free; + } + + init_special_inode(inode, inode->i_mode, WHITEOUT_DEV); + ubifs_assert(c, inode->i_op == &ubifs_file_inode_operations); + + err = ubifs_init_security(dir, inode, &dentry->d_name); + if (err) + goto out_inode; + + /* The dir size is updated by do_rename. */ + insert_inode_hash(inode); + + return inode; + +out_inode: + make_bad_inode(inode); + iput(inode); +out_free: + fscrypt_free_filename(&nm); + ubifs_err(c, "cannot create whiteout file, error %d", err); + return ERR_PTR(err); +} + +/** + * lock_2_inodes - a wrapper for locking two UBIFS inodes. + * @inode1: first inode + * @inode2: second inode + * + * We do not implement any tricks to guarantee strict lock ordering, because + * VFS has already done it for us on the @i_mutex. So this is just a simple + * wrapper function. + */ +static void lock_2_inodes(struct inode *inode1, struct inode *inode2) +{ + mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_1); + mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_2); +} + +/** + * unlock_2_inodes - a wrapper for unlocking two UBIFS inodes. + * @inode1: first inode + * @inode2: second inode + */ +static void unlock_2_inodes(struct inode *inode1, struct inode *inode2) +{ + mutex_unlock(&ubifs_inode(inode2)->ui_mutex); + mutex_unlock(&ubifs_inode(inode1)->ui_mutex); +} + +static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; struct ubifs_info *c = dir->i_sb->s_fs_info; - struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1}; + struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, + .dirtied_ino = 1}; struct ubifs_budget_req ino_req = { .dirtied_ino = 1 }; - struct ubifs_inode *ui, *dir_ui = ubifs_inode(dir); + struct ubifs_inode *ui; int err, instantiated = 0; struct fscrypt_name nm; /* - * Budget request settings: new dirty inode, new direntry, - * budget for dirtied inode will be released via writeback. + * Budget request settings: new inode, new direntry, changing the + * parent directory inode. + * Allocate budget separately for new dirtied inode, the budget will + * be released via writeback. */ dbg_gen("dent '%pd', mode %#hx in dir ino %lu", @@ -392,42 +469,30 @@ static int do_tmpfile(struct inode *dir, struct dentry *dentry, } ui = ubifs_inode(inode); - if (whiteout) { - init_special_inode(inode, inode->i_mode, WHITEOUT_DEV); - ubifs_assert(c, inode->i_op == &ubifs_file_inode_operations); - } - err = ubifs_init_security(dir, inode, &dentry->d_name); if (err) goto out_inode; mutex_lock(&ui->ui_mutex); insert_inode_hash(inode); - - if (whiteout) { - mark_inode_dirty(inode); - drop_nlink(inode); - *whiteout = inode; - } else { - d_tmpfile(dentry, inode); - } + d_tmpfile(dentry, inode); ubifs_assert(c, ui->dirty); instantiated = 1; mutex_unlock(&ui->ui_mutex); - mutex_lock(&dir_ui->ui_mutex); + lock_2_inodes(dir, inode); err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0); if (err) goto out_cancel; - mutex_unlock(&dir_ui->ui_mutex); + unlock_2_inodes(dir, inode); ubifs_release_budget(c, &req); return 0; out_cancel: - mutex_unlock(&dir_ui->ui_mutex); + unlock_2_inodes(dir, inode); out_inode: make_bad_inode(inode); if (!instantiated) @@ -441,12 +506,6 @@ out_budg: return err; } -static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, - struct dentry *dentry, umode_t mode) -{ - return do_tmpfile(dir, dentry, mode, NULL); -} - /** * vfs_dent_type - get VFS directory entry type. * @type: UBIFS directory entry type @@ -660,32 +719,6 @@ static int ubifs_dir_release(struct inode *dir, struct file *file) return 0; } -/** - * lock_2_inodes - a wrapper for locking two UBIFS inodes. - * @inode1: first inode - * @inode2: second inode - * - * We do not implement any tricks to guarantee strict lock ordering, because - * VFS has already done it for us on the @i_mutex. So this is just a simple - * wrapper function. - */ -static void lock_2_inodes(struct inode *inode1, struct inode *inode2) -{ - mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_1); - mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_2); -} - -/** - * unlock_2_inodes - a wrapper for unlocking two UBIFS inodes. - * @inode1: first inode - * @inode2: second inode - */ -static void unlock_2_inodes(struct inode *inode1, struct inode *inode2) -{ - mutex_unlock(&ubifs_inode(inode2)->ui_mutex); - mutex_unlock(&ubifs_inode(inode1)->ui_mutex); -} - static int ubifs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { @@ -949,7 +982,8 @@ static int ubifs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, struct ubifs_inode *dir_ui = ubifs_inode(dir); struct ubifs_info *c = dir->i_sb->s_fs_info; int err, sz_change; - struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1 }; + struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, + .dirtied_ino = 1}; struct fscrypt_name nm; /* @@ -1264,17 +1298,19 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, .dirtied_ino = 3 }; struct ubifs_budget_req ino_req = { .dirtied_ino = 1, .dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) }; + struct ubifs_budget_req wht_req; struct timespec64 time; unsigned int saved_nlink; struct fscrypt_name old_nm, new_nm; /* - * Budget request settings: deletion direntry, new direntry, removing - * the old inode, and changing old and new parent directory inodes. + * Budget request settings: + * req: deletion direntry, new direntry, removing the old inode, + * and changing old and new parent directory inodes. + * + * wht_req: new whiteout inode for RENAME_WHITEOUT. * - * However, this operation also marks the target inode as dirty and - * does not write it, so we allocate budget for the target inode - * separately. + * ino_req: marks the target inode as dirty and does not write it. */ dbg_gen("dent '%pd' ino %lu in dir ino %lu to dent '%pd' in dir ino %lu flags 0x%x", @@ -1331,20 +1367,44 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, goto out_release; } - err = do_tmpfile(old_dir, old_dentry, S_IFCHR | WHITEOUT_MODE, &whiteout); - if (err) { + /* + * The whiteout inode without dentry is pinned in memory, + * umount won't happen during rename process because we + * got parent dentry. + */ + whiteout = create_whiteout(old_dir, old_dentry); + if (IS_ERR(whiteout)) { + err = PTR_ERR(whiteout); kfree(dev); goto out_release; } - spin_lock(&whiteout->i_lock); - whiteout->i_state |= I_LINKABLE; - spin_unlock(&whiteout->i_lock); - whiteout_ui = ubifs_inode(whiteout); whiteout_ui->data = dev; whiteout_ui->data_len = ubifs_encode_dev(dev, MKDEV(0, 0)); ubifs_assert(c, !whiteout_ui->dirty); + + memset(&wht_req, 0, sizeof(struct ubifs_budget_req)); + wht_req.new_ino = 1; + wht_req.new_ino_d = ALIGN(whiteout_ui->data_len, 8); + /* + * To avoid deadlock between space budget (holds ui_mutex and + * waits wb work) and writeback work(waits ui_mutex), do space + * budget before ubifs inodes locked. + */ + err = ubifs_budget_space(c, &wht_req); + if (err) { + /* + * Whiteout inode can not be written on flash by + * ubifs_jnl_write_inode(), because it's neither + * dirty nor zero-nlink. + */ + iput(whiteout); + goto out_release; + } + + /* Add the old_dentry size to the old_dir size. */ + old_sz -= CALC_DENT_SIZE(fname_len(&old_nm)); } lock_4_inodes(old_dir, new_dir, new_inode, whiteout); @@ -1416,29 +1476,11 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, sync = IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir); if (unlink && IS_SYNC(new_inode)) sync = 1; - } - - if (whiteout) { - struct ubifs_budget_req wht_req = { .dirtied_ino = 1, - .dirtied_ino_d = \ - ALIGN(ubifs_inode(whiteout)->data_len, 8) }; - - err = ubifs_budget_space(c, &wht_req); - if (err) { - kfree(whiteout_ui->data); - whiteout_ui->data_len = 0; - iput(whiteout); - goto out_release; - } - - inc_nlink(whiteout); - mark_inode_dirty(whiteout); - - spin_lock(&whiteout->i_lock); - whiteout->i_state &= ~I_LINKABLE; - spin_unlock(&whiteout->i_lock); - - iput(whiteout); + /* + * S_SYNC flag of whiteout inherits from the old_dir, and we + * have already checked the old dir inode. So there is no need + * to check whiteout. + */ } err = ubifs_jnl_rename(c, old_dir, old_inode, &old_nm, new_dir, @@ -1449,6 +1491,11 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, unlock_4_inodes(old_dir, new_dir, new_inode, whiteout); ubifs_release_budget(c, &req); + if (whiteout) { + ubifs_release_budget(c, &wht_req); + iput(whiteout); + } + mutex_lock(&old_inode_ui->ui_mutex); release = old_inode_ui->dirty; mark_inode_dirty_sync(old_inode); @@ -1457,11 +1504,16 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, if (release) ubifs_release_budget(c, &ino_req); if (IS_SYNC(old_inode)) - err = old_inode->i_sb->s_op->write_inode(old_inode, NULL); + /* + * Rename finished here. Although old inode cannot be updated + * on flash, old ctime is not a big problem, don't return err + * code to userspace. + */ + old_inode->i_sb->s_op->write_inode(old_inode, NULL); fscrypt_free_filename(&old_nm); fscrypt_free_filename(&new_nm); - return err; + return 0; out_cancel: if (unlink) { @@ -1482,11 +1534,11 @@ out_cancel: inc_nlink(old_dir); } } + unlock_4_inodes(old_dir, new_dir, new_inode, whiteout); if (whiteout) { - drop_nlink(whiteout); + ubifs_release_budget(c, &wht_req); iput(whiteout); } - unlock_4_inodes(old_dir, new_dir, new_inode, whiteout); out_release: ubifs_release_budget(c, &ino_req); ubifs_release_budget(c, &req); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 8a9ffc2d4167..0383fbdc95ff 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -570,7 +570,7 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, } if (!PagePrivate(page)) { - SetPagePrivate(page); + attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); __set_page_dirty_nobuffers(page); } @@ -947,7 +947,7 @@ static int do_writepage(struct page *page, int len) release_existing_page_budget(c); atomic_long_dec(&c->dirty_pg_cnt); - ClearPagePrivate(page); + detach_page_private(page); ClearPageChecked(page); kunmap(page); @@ -1304,7 +1304,7 @@ static void ubifs_invalidate_folio(struct folio *folio, size_t offset, release_existing_page_budget(c); atomic_long_dec(&c->dirty_pg_cnt); - folio_clear_private(folio); + folio_detach_private(folio); folio_clear_checked(folio); } @@ -1471,8 +1471,8 @@ static int ubifs_migrate_page(struct address_space *mapping, return rc; if (PagePrivate(page)) { - ClearPagePrivate(page); - SetPagePrivate(newpage); + detach_page_private(page); + attach_page_private(newpage, (void *)1); } if (mode != MIGRATE_SYNC_NO_COPY) @@ -1496,7 +1496,7 @@ static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags) return 0; ubifs_assert(c, PagePrivate(page)); ubifs_assert(c, 0); - ClearPagePrivate(page); + detach_page_private(page); ClearPageChecked(page); return 1; } @@ -1567,7 +1567,7 @@ static vm_fault_t ubifs_vm_page_mkwrite(struct vm_fault *vmf) else { if (!PageChecked(page)) ubifs_convert_page_budget(c); - SetPagePrivate(page); + attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); __set_page_dirty_nobuffers(page); } diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index 789a7813f3fa..1607a3c76681 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -854,16 +854,42 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) */ n = aligned_len >> c->max_write_shift; if (n) { - n <<= c->max_write_shift; + int m = n - 1; + dbg_io("write %d bytes to LEB %d:%d", n, wbuf->lnum, wbuf->offs); - err = ubifs_leb_write(c, wbuf->lnum, buf + written, - wbuf->offs, n); + + if (m) { + /* '(n-1)<<c->max_write_shift < len' is always true. */ + m <<= c->max_write_shift; + err = ubifs_leb_write(c, wbuf->lnum, buf + written, + wbuf->offs, m); + if (err) + goto out; + wbuf->offs += m; + aligned_len -= m; + len -= m; + written += m; + } + + /* + * The non-written len of buf may be less than 'n' because + * parameter 'len' is not 8 bytes aligned, so here we read + * min(len, n) bytes from buf. + */ + n = 1 << c->max_write_shift; + memcpy(wbuf->buf, buf + written, min(len, n)); + if (n > len) { + ubifs_assert(c, n - len < 8); + ubifs_pad(c, wbuf->buf + len, n - len); + } + + err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, wbuf->offs, n); if (err) goto out; wbuf->offs += n; aligned_len -= n; - len -= n; + len -= min(len, n); written += n; } diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index c6a863487780..71bcebe45f9c 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -108,7 +108,7 @@ static int setflags(struct inode *inode, int flags) struct ubifs_inode *ui = ubifs_inode(inode); struct ubifs_info *c = inode->i_sb->s_fs_info; struct ubifs_budget_req req = { .dirtied_ino = 1, - .dirtied_ino_d = ui->data_len }; + .dirtied_ino_d = ALIGN(ui->data_len, 8) }; err = ubifs_budget_space(c, &req); if (err) diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 8ea680dba61e..75dab0ae3939 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -1207,9 +1207,9 @@ out_free: * @sync: non-zero if the write-buffer has to be synchronized * * This function implements the re-name operation which may involve writing up - * to 4 inodes and 2 directory entries. It marks the written inodes as clean - * and returns zero on success. In case of failure, a negative error code is - * returned. + * to 4 inodes(new inode, whiteout inode, old and new parent directory inodes) + * and 2 directory entries. It marks the written inodes as clean and returns + * zero on success. In case of failure, a negative error code is returned. */ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, const struct inode *old_inode, @@ -1222,14 +1222,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, void *p; union ubifs_key key; struct ubifs_dent_node *dent, *dent2; - int err, dlen1, dlen2, ilen, lnum, offs, len, orphan_added = 0; + int err, dlen1, dlen2, ilen, wlen, lnum, offs, len, orphan_added = 0; int aligned_dlen1, aligned_dlen2, plen = UBIFS_INO_NODE_SZ; int last_reference = !!(new_inode && new_inode->i_nlink == 0); int move = (old_dir != new_dir); - struct ubifs_inode *new_ui; + struct ubifs_inode *new_ui, *whiteout_ui; u8 hash_old_dir[UBIFS_HASH_ARR_SZ]; u8 hash_new_dir[UBIFS_HASH_ARR_SZ]; u8 hash_new_inode[UBIFS_HASH_ARR_SZ]; + u8 hash_whiteout_inode[UBIFS_HASH_ARR_SZ]; u8 hash_dent1[UBIFS_HASH_ARR_SZ]; u8 hash_dent2[UBIFS_HASH_ARR_SZ]; @@ -1249,9 +1250,20 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, } else ilen = 0; + if (whiteout) { + whiteout_ui = ubifs_inode(whiteout); + ubifs_assert(c, mutex_is_locked(&whiteout_ui->ui_mutex)); + ubifs_assert(c, whiteout->i_nlink == 1); + ubifs_assert(c, !whiteout_ui->dirty); + wlen = UBIFS_INO_NODE_SZ; + wlen += whiteout_ui->data_len; + } else + wlen = 0; + aligned_dlen1 = ALIGN(dlen1, 8); aligned_dlen2 = ALIGN(dlen2, 8); - len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + ALIGN(plen, 8); + len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + + ALIGN(wlen, 8) + ALIGN(plen, 8); if (move) len += plen; @@ -1313,6 +1325,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, p += ALIGN(ilen, 8); } + if (whiteout) { + pack_inode(c, p, whiteout, 0); + err = ubifs_node_calc_hash(c, p, hash_whiteout_inode); + if (err) + goto out_release; + + p += ALIGN(wlen, 8); + } + if (!move) { pack_inode(c, p, old_dir, 1); err = ubifs_node_calc_hash(c, p, hash_old_dir); @@ -1352,6 +1373,9 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, if (new_inode) ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf, new_inode->i_ino); + if (whiteout) + ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf, + whiteout->i_ino); } release_head(c, BASEHD); @@ -1368,8 +1392,6 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, hash_dent2, old_nm); if (err) goto out_ro; - - ubifs_delete_orphan(c, whiteout->i_ino); } else { err = ubifs_add_dirt(c, lnum, dlen2); if (err) @@ -1390,6 +1412,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, offs += ALIGN(ilen, 8); } + if (whiteout) { + ino_key_init(c, &key, whiteout->i_ino); + err = ubifs_tnc_add(c, &key, lnum, offs, wlen, + hash_whiteout_inode); + if (err) + goto out_ro; + offs += ALIGN(wlen, 8); + } + ino_key_init(c, &key, old_dir->i_ino); err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_old_dir); if (err) @@ -1410,6 +1441,11 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, new_ui->synced_i_size = new_ui->ui_size; spin_unlock(&new_ui->ui_lock); } + /* + * No need to mark whiteout inode clean. + * Whiteout doesn't have non-zero size, no need to update + * synced_i_size for whiteout_ui. + */ mark_inode_clean(c, ubifs_inode(old_dir)); if (move) mark_inode_clean(c, ubifs_inode(new_dir)); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index f55828c0a300..008fa46ef61e 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -381,7 +381,7 @@ struct ubifs_gced_idx_leb { * @ui_mutex exists for two main reasons. At first it prevents inodes from * being written back while UBIFS changing them, being in the middle of an VFS * operation. This way UBIFS makes sure the inode fields are consistent. For - * example, in 'ubifs_rename()' we change 3 inodes simultaneously, and + * example, in 'ubifs_rename()' we change 4 inodes simultaneously, and * write-back must not write any of them before we have finished. * * The second reason is budgeting - UBIFS has to budget all operations. If an diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile index 0cc87423de82..0e51c0025a16 100644 --- a/fs/unicode/Makefile +++ b/fs/unicode/Makefile @@ -33,7 +33,7 @@ $(obj)/utf8data.c: $(obj)/mkutf8data $(filter %.txt, $(cmd_utf8data)) FORCE else $(obj)/utf8data.c: $(src)/utf8data.c_shipped FORCE - $(call if_changed,shipped) + $(call if_changed,copy) endif |