diff options
Diffstat (limited to 'fs')
266 files changed, 4087 insertions, 3142 deletions
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index e78956c..34c59f1 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -144,7 +144,7 @@ extern void v9fs_session_close(struct v9fs_session_info *v9ses); extern void v9fs_session_cancel(struct v9fs_session_info *v9ses); extern void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses); extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nameidata); + unsigned int flags); extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d); extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d); extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index d529437..64600b5 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -100,13 +100,13 @@ static void v9fs_dentry_release(struct dentry *dentry) } } -static int v9fs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) +static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) { struct p9_fid *fid; struct inode *inode; struct v9fs_inode *v9inode; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 57ccb75..cbf9dbb 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -712,88 +712,34 @@ error: } /** - * v9fs_vfs_create - VFS hook to create files + * v9fs_vfs_create - VFS hook to create a regular file + * + * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open(). This is only called + * for mknod(2). + * * @dir: directory inode that is being created * @dentry: dentry that is being deleted * @mode: create permissions - * @nd: path information * */ static int v9fs_vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { - int err; - u32 perm; - int flags; - struct file *filp; - struct v9fs_inode *v9inode; - struct v9fs_session_info *v9ses; - struct p9_fid *fid, *inode_fid; - - err = 0; - fid = NULL; - v9ses = v9fs_inode2v9ses(dir); - perm = unixmode2p9mode(v9ses, mode); - if (nd) - flags = nd->intent.open.flags; - else - flags = O_RDWR; + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); + u32 perm = unixmode2p9mode(v9ses, mode); + struct p9_fid *fid; - fid = v9fs_create(v9ses, dir, dentry, NULL, perm, - v9fs_uflags2omode(flags, - v9fs_proto_dotu(v9ses))); - if (IS_ERR(fid)) { - err = PTR_ERR(fid); - fid = NULL; - goto error; - } + /* P9_OEXCL? */ + fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_ORDWR); + if (IS_ERR(fid)) + return PTR_ERR(fid); v9fs_invalidate_inode_attr(dir); - /* if we are opening a file, assign the open fid to the file */ - if (nd) { - v9inode = V9FS_I(dentry->d_inode); - mutex_lock(&v9inode->v_mutex); - if (v9ses->cache && !v9inode->writeback_fid && - ((flags & O_ACCMODE) != O_RDONLY)) { - /* - * clone a fid and add it to writeback_fid - * we do it during open time instead of - * page dirty time via write_begin/page_mkwrite - * because we want write after unlink usecase - * to work. - */ - inode_fid = v9fs_writeback_fid(dentry); - if (IS_ERR(inode_fid)) { - err = PTR_ERR(inode_fid); - mutex_unlock(&v9inode->v_mutex); - goto error; - } - v9inode->writeback_fid = (void *) inode_fid; - } - mutex_unlock(&v9inode->v_mutex); - filp = lookup_instantiate_filp(nd, dentry, generic_file_open); - if (IS_ERR(filp)) { - err = PTR_ERR(filp); - goto error; - } - - filp->private_data = fid; -#ifdef CONFIG_9P_FSCACHE - if (v9ses->cache) - v9fs_cache_inode_set_cookie(dentry->d_inode, filp); -#endif - } else - p9_client_clunk(fid); + p9_client_clunk(fid); return 0; - -error: - if (fid) - p9_client_clunk(fid); - - return err; } /** @@ -839,7 +785,7 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode */ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nameidata) + unsigned int flags) { struct dentry *res; struct super_block *sb; @@ -849,8 +795,8 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, char *name; int result = 0; - p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p nameidata: %p\n", - dir, dentry->d_name.name, dentry, nameidata); + p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p flags: %x\n", + dir, dentry->d_name.name, dentry, flags); if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); @@ -910,6 +856,86 @@ error: return ERR_PTR(result); } +static int +v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned flags, umode_t mode, + int *opened) +{ + int err; + u32 perm; + struct v9fs_inode *v9inode; + struct v9fs_session_info *v9ses; + struct p9_fid *fid, *inode_fid; + struct dentry *res = NULL; + + if (d_unhashed(dentry)) { + res = v9fs_vfs_lookup(dir, dentry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + if (res) + dentry = res; + } + + /* Only creates */ + if (!(flags & O_CREAT) || dentry->d_inode) + return finish_no_open(file, res); + + err = 0; + fid = NULL; + v9ses = v9fs_inode2v9ses(dir); + perm = unixmode2p9mode(v9ses, mode); + fid = v9fs_create(v9ses, dir, dentry, NULL, perm, + v9fs_uflags2omode(flags, + v9fs_proto_dotu(v9ses))); + if (IS_ERR(fid)) { + err = PTR_ERR(fid); + fid = NULL; + goto error; + } + + v9fs_invalidate_inode_attr(dir); + v9inode = V9FS_I(dentry->d_inode); + mutex_lock(&v9inode->v_mutex); + if (v9ses->cache && !v9inode->writeback_fid && + ((flags & O_ACCMODE) != O_RDONLY)) { + /* + * clone a fid and add it to writeback_fid + * we do it during open time instead of + * page dirty time via write_begin/page_mkwrite + * because we want write after unlink usecase + * to work. + */ + inode_fid = v9fs_writeback_fid(dentry); + if (IS_ERR(inode_fid)) { + err = PTR_ERR(inode_fid); + mutex_unlock(&v9inode->v_mutex); + goto error; + } + v9inode->writeback_fid = (void *) inode_fid; + } + mutex_unlock(&v9inode->v_mutex); + err = finish_open(file, dentry, generic_file_open, opened); + if (err) + goto error; + + file->private_data = fid; +#ifdef CONFIG_9P_FSCACHE + if (v9ses->cache) + v9fs_cache_inode_set_cookie(dentry->d_inode, file); +#endif + + *opened |= FILE_CREATED; +out: + dput(res); + return err; + +error: + if (fid) + p9_client_clunk(fid); + goto out; +} + /** * v9fs_vfs_unlink - VFS unlink hook to delete an inode * @i: inode that is being unlinked @@ -1488,6 +1514,7 @@ out: static const struct inode_operations v9fs_dir_inode_operations_dotu = { .create = v9fs_vfs_create, .lookup = v9fs_vfs_lookup, + .atomic_open = v9fs_vfs_atomic_open, .symlink = v9fs_vfs_symlink, .link = v9fs_vfs_link, .unlink = v9fs_vfs_unlink, @@ -1502,6 +1529,7 @@ static const struct inode_operations v9fs_dir_inode_operations_dotu = { static const struct inode_operations v9fs_dir_inode_operations = { .create = v9fs_vfs_create, .lookup = v9fs_vfs_lookup, + .atomic_open = v9fs_vfs_atomic_open, .unlink = v9fs_vfs_unlink, .mkdir = v9fs_vfs_mkdir, .rmdir = v9fs_vfs_rmdir, diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index e3dd2a1..4089554 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -230,20 +230,25 @@ int v9fs_open_to_dotl_flags(int flags) * @dir: directory inode that is being created * @dentry: dentry that is being deleted * @mode: create permissions - * @nd: path information * */ static int v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, - struct nameidata *nd) + bool excl) +{ + return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0); +} + +static int +v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned flags, umode_t omode, + int *opened) { int err = 0; gid_t gid; - int flags; umode_t mode; char *name = NULL; - struct file *filp; struct p9_qid qid; struct inode *inode; struct p9_fid *fid = NULL; @@ -251,19 +256,23 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, struct p9_fid *dfid, *ofid, *inode_fid; struct v9fs_session_info *v9ses; struct posix_acl *pacl = NULL, *dacl = NULL; + struct dentry *res = NULL; - v9ses = v9fs_inode2v9ses(dir); - if (nd) - flags = nd->intent.open.flags; - else { - /* - * create call without LOOKUP_OPEN is due - * to mknod of regular files. So use mknod - * operation. - */ - return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0); + if (d_unhashed(dentry)) { + res = v9fs_vfs_lookup(dir, dentry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + if (res) + dentry = res; } + /* Only creates */ + if (!(flags & O_CREAT) || dentry->d_inode) + return finish_no_open(file, res); + + v9ses = v9fs_inode2v9ses(dir); + name = (char *) dentry->d_name.name; p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n", name, flags, omode); @@ -272,7 +281,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, if (IS_ERR(dfid)) { err = PTR_ERR(dfid); p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err); - return err; + goto out; } /* clone a fid to use for creation */ @@ -280,7 +289,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, if (IS_ERR(ofid)) { err = PTR_ERR(ofid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); - return err; + goto out; } gid = v9fs_get_fsgid_for_create(dir); @@ -345,17 +354,18 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, } mutex_unlock(&v9inode->v_mutex); /* Since we are opening a file, assign the open fid to the file */ - filp = lookup_instantiate_filp(nd, dentry, generic_file_open); - if (IS_ERR(filp)) { - err = PTR_ERR(filp); + err = finish_open(file, dentry, generic_file_open, opened); + if (err) goto err_clunk_old_fid; - } - filp->private_data = ofid; + file->private_data = ofid; #ifdef CONFIG_9P_FSCACHE if (v9ses->cache) - v9fs_cache_inode_set_cookie(inode, filp); + v9fs_cache_inode_set_cookie(inode, file); #endif - return 0; + *opened |= FILE_CREATED; +out: + dput(res); + return err; error: if (fid) @@ -364,7 +374,7 @@ err_clunk_old_fid: if (ofid) p9_client_clunk(ofid); v9fs_set_create_acl(NULL, &dacl, &pacl); - return err; + goto out; } /** @@ -982,6 +992,7 @@ out: const struct inode_operations v9fs_dir_inode_operations_dotl = { .create = v9fs_vfs_create_dotl, + .atomic_open = v9fs_vfs_atomic_open_dotl, .lookup = v9fs_vfs_lookup, .link = v9fs_vfs_link_dotl, .symlink = v9fs_vfs_symlink_dotl, diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 8c92a9b..137d503 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -89,7 +89,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, if (v9ses->cache) sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_CACHE_SIZE; - sb->s_flags = flags | MS_ACTIVE | MS_DIRSYNC | MS_NOATIME; + sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME; if (!v9ses->cache) sb->s_flags |= MS_SYNCHRONOUS; @@ -137,7 +137,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, goto close_session; } - sb = sget(fs_type, NULL, v9fs_set_super, v9ses); + sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses); if (IS_ERR(sb)) { retval = PTR_ERR(sb); goto clunk_fid; diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c index 3d83075a..b3be2e7 100644 --- a/fs/adfs/dir.c +++ b/fs/adfs/dir.c @@ -266,7 +266,7 @@ const struct dentry_operations adfs_dentry_operations = { }; static struct dentry * -adfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +adfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode = NULL; struct object_info obj; diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 06fdcc9..bdaec92 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -246,7 +246,6 @@ static struct inode *adfs_alloc_inode(struct super_block *sb) static void adfs_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - INIT_LIST_HEAD(&inode->i_dentry); kmem_cache_free(adfs_inode_cachep, ADFS_I(inode)); } diff --git a/fs/affs/affs.h b/fs/affs/affs.h index 1fceb32..6e21641 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -3,6 +3,7 @@ #include <linux/buffer_head.h> #include <linux/amigaffs.h> #include <linux/mutex.h> +#include <linux/workqueue.h> /* AmigaOS allows file names with up to 30 characters length. * Names longer than that will be silently truncated. If you @@ -100,6 +101,10 @@ struct affs_sb_info { char *s_prefix; /* Prefix for volumes and assigns. */ char s_volume[32]; /* Volume prefix for absolute symlinks. */ spinlock_t symlink_lock; /* protects the previous two */ + struct super_block *sb; /* the VFS superblock object */ + int work_queued; /* non-zero delayed work is queued */ + struct delayed_work sb_work; /* superblock flush delayed work */ + spinlock_t work_lock; /* protects sb_work and work_queued */ }; #define SF_INTL 0x0001 /* International filesystem. */ @@ -120,6 +125,8 @@ static inline struct affs_sb_info *AFFS_SB(struct super_block *sb) return sb->s_fs_info; } +void affs_mark_sb_dirty(struct super_block *sb); + /* amigaffs.c */ extern int affs_insert_hash(struct inode *inode, struct buffer_head *bh); @@ -146,9 +153,9 @@ extern void affs_free_bitmap(struct super_block *sb); /* namei.c */ extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len); -extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *); +extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int); extern int affs_unlink(struct inode *dir, struct dentry *dentry); -extern int affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *); +extern int affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool); extern int affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); extern int affs_rmdir(struct inode *dir, struct dentry *dentry); extern int affs_link(struct dentry *olddentry, struct inode *dir, diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index 52a6407..eb82ee5 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -122,22 +122,16 @@ affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh) } static void -affs_fix_dcache(struct dentry *dentry, u32 entry_ino) +affs_fix_dcache(struct inode *inode, u32 entry_ino) { - struct inode *inode = dentry->d_inode; - void *data = dentry->d_fsdata; - struct list_head *head, *next; - + struct dentry *dentry; + struct hlist_node *p; spin_lock(&inode->i_lock); - head = &inode->i_dentry; - next = head->next; - while (next != head) { - dentry = list_entry(next, struct dentry, d_alias); + hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { if (entry_ino == (u32)(long)dentry->d_fsdata) { - dentry->d_fsdata = data; + dentry->d_fsdata = (void *)inode->i_ino; break; } - next = next->next; } spin_unlock(&inode->i_lock); } @@ -177,7 +171,11 @@ affs_remove_link(struct dentry *dentry) } affs_lock_dir(dir); - affs_fix_dcache(dentry, link_ino); + /* + * if there's a dentry for that block, make it + * refer to inode itself. + */ + affs_fix_dcache(inode, link_ino); retval = affs_remove_hash(dir, link_bh); if (retval) { affs_unlock_dir(dir); diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c index 3e26271..6e0be43 100644 --- a/fs/affs/bitmap.c +++ b/fs/affs/bitmap.c @@ -103,7 +103,7 @@ affs_free_block(struct super_block *sb, u32 block) *(__be32 *)bh->b_data = cpu_to_be32(tmp - mask); mark_buffer_dirty(bh); - sb->s_dirt = 1; + affs_mark_sb_dirty(sb); bm->bm_free++; mutex_unlock(&sbi->s_bmlock); @@ -248,7 +248,7 @@ find_bit: *(__be32 *)bh->b_data = cpu_to_be32(tmp + mask); mark_buffer_dirty(bh); - sb->s_dirt = 1; + affs_mark_sb_dirty(sb); mutex_unlock(&sbi->s_bmlock); diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 4780694..ff65884 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -211,7 +211,7 @@ affs_find_entry(struct inode *dir, struct dentry *dentry) } struct dentry * -affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct super_block *sb = dir->i_sb; struct buffer_head *bh; @@ -255,7 +255,7 @@ affs_unlink(struct inode *dir, struct dentry *dentry) } int -affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd) +affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode; diff --git a/fs/affs/super.c b/fs/affs/super.c index 0782653..c70f1e5 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -17,6 +17,7 @@ #include <linux/magic.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/writeback.h> #include "affs.h" extern struct timezone sys_tz; @@ -25,15 +26,17 @@ static int affs_statfs(struct dentry *dentry, struct kstatfs *buf); static int affs_remount (struct super_block *sb, int *flags, char *data); static void -affs_commit_super(struct super_block *sb, int wait, int clean) +affs_commit_super(struct super_block *sb, int wait) { struct affs_sb_info *sbi = AFFS_SB(sb); struct buffer_head *bh = sbi->s_root_bh; struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh); - tail->bm_flag = cpu_to_be32(clean); + lock_buffer(bh); secs_to_datestamp(get_seconds(), &tail->disk_change); affs_fix_checksum(sb, bh); + unlock_buffer(bh); + mark_buffer_dirty(bh); if (wait) sync_dirty_buffer(bh); @@ -45,9 +48,7 @@ affs_put_super(struct super_block *sb) struct affs_sb_info *sbi = AFFS_SB(sb); pr_debug("AFFS: put_super()\n"); - if (!(sb->s_flags & MS_RDONLY) && sb->s_dirt) - affs_commit_super(sb, 1, 1); - + cancel_delayed_work_sync(&sbi->sb_work); kfree(sbi->s_prefix); affs_free_bitmap(sb); affs_brelse(sbi->s_root_bh); @@ -55,26 +56,43 @@ affs_put_super(struct super_block *sb) sb->s_fs_info = NULL; } -static void -affs_write_super(struct super_block *sb) +static int +affs_sync_fs(struct super_block *sb, int wait) { - lock_super(sb); - if (!(sb->s_flags & MS_RDONLY)) - affs_commit_super(sb, 1, 2); - sb->s_dirt = 0; - unlock_super(sb); + affs_commit_super(sb, wait); + return 0; +} + +static void flush_superblock(struct work_struct *work) +{ + struct affs_sb_info *sbi; + struct super_block *sb; + + sbi = container_of(work, struct affs_sb_info, sb_work.work); + sb = sbi->sb; - pr_debug("AFFS: write_super() at %lu, clean=2\n", get_seconds()); + spin_lock(&sbi->work_lock); + sbi->work_queued = 0; + spin_unlock(&sbi->work_lock); + + affs_commit_super(sb, 1); } -static int -affs_sync_fs(struct super_block *sb, int wait) +void affs_mark_sb_dirty(struct super_block *sb) { - lock_super(sb); - affs_commit_super(sb, wait, 2); - sb->s_dirt = 0; - unlock_super(sb); - return 0; + struct affs_sb_info *sbi = AFFS_SB(sb); + unsigned long delay; + + if (sb->s_flags & MS_RDONLY) + return; + + spin_lock(&sbi->work_lock); + if (!sbi->work_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + queue_delayed_work(system_long_wq, &sbi->sb_work, delay); + sbi->work_queued = 1; + } + spin_unlock(&sbi->work_lock); } static struct kmem_cache * affs_inode_cachep; @@ -138,7 +156,6 @@ static const struct super_operations affs_sops = { .write_inode = affs_write_inode, .evict_inode = affs_evict_inode, .put_super = affs_put_super, - .write_super = affs_write_super, .sync_fs = affs_sync_fs, .statfs = affs_statfs, .remount_fs = affs_remount, @@ -305,8 +322,11 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) return -ENOMEM; sb->s_fs_info = sbi; + sbi->sb = sb; mutex_init(&sbi->s_bmlock); spin_lock_init(&sbi->symlink_lock); + spin_lock_init(&sbi->work_lock); + INIT_DELAYED_WORK(&sbi->sb_work, flush_superblock); if (!parse_options(data,&uid,&gid,&i,&reserved,&root_block, &blocksize,&sbi->s_prefix, @@ -531,6 +551,7 @@ affs_remount(struct super_block *sb, int *flags, char *data) return -EINVAL; } + flush_delayed_work_sync(&sbi->sb_work); replace_mount_options(sb, new_opts); sbi->s_flags = mount_flags; @@ -549,10 +570,9 @@ affs_remount(struct super_block *sb, int *flags, char *data) if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) return 0; - if (*flags & MS_RDONLY) { - affs_write_super(sb); + if (*flags & MS_RDONLY) affs_free_bitmap(sb); - } else + else res = affs_init_bitmap(sb, flags); return res; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index e22dc4b..db47790 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -20,16 +20,16 @@ #include "internal.h" static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd); + unsigned int flags); static int afs_dir_open(struct inode *inode, struct file *file); static int afs_readdir(struct file *file, void *dirent, filldir_t filldir); -static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd); +static int afs_d_revalidate(struct dentry *dentry, unsigned int flags); static int afs_d_delete(const struct dentry *dentry); static void afs_d_release(struct dentry *dentry); static int afs_lookup_filldir(void *_cookie, const char *name, int nlen, loff_t fpos, u64 ino, unsigned dtype); static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd); + bool excl); static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); static int afs_rmdir(struct inode *dir, struct dentry *dentry); static int afs_unlink(struct inode *dir, struct dentry *dentry); @@ -516,7 +516,7 @@ out: * look up an entry in a directory */ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct afs_vnode *vnode; struct afs_fid fid; @@ -598,7 +598,7 @@ success: * - NOTE! the hit can be a negative hit too, so we can't assume we have an * inode */ -static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd) +static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) { struct afs_vnode *vnode, *dir; struct afs_fid uninitialized_var(fid); @@ -607,7 +607,7 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd) void *dir_version; int ret; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; vnode = AFS_FS_I(dentry->d_inode); @@ -949,7 +949,7 @@ error: * create a regular file on an AFS filesystem */ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct afs_file_status status; struct afs_callback cb; diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 298cf89..9682c33 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -22,7 +22,7 @@ static struct dentry *afs_mntpt_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd); + unsigned int flags); static int afs_mntpt_open(struct inode *inode, struct file *file); static void afs_mntpt_expiry_timed_out(struct work_struct *work); @@ -104,7 +104,7 @@ out: */ static struct dentry *afs_mntpt_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { _enter("%p,%p{%p{%s},%s}", dir, diff --git a/fs/afs/super.c b/fs/afs/super.c index f02b31e..df8c604 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -395,7 +395,7 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, as->volume = vol; /* allocate a deviceless superblock */ - sb = sget(fs_type, afs_test_super, afs_set_super, as); + sb = sget(fs_type, afs_test_super, afs_set_super, flags, as); if (IS_ERR(sb)) { ret = PTR_ERR(sb); afs_put_volume(vol); @@ -406,7 +406,6 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, if (!sb->s_root) { /* initial superblock/root creation */ _debug("create"); - sb->s_flags = flags; ret = afs_fill_super(sb, ¶ms); if (ret < 0) { deactivate_locked_super(sb); @@ -56,13 +56,6 @@ static struct kmem_cache *kioctx_cachep; static struct workqueue_struct *aio_wq; -/* Used for rare fput completion. */ -static void aio_fput_routine(struct work_struct *); -static DECLARE_WORK(fput_work, aio_fput_routine); - -static DEFINE_SPINLOCK(fput_lock); -static LIST_HEAD(fput_head); - static void aio_kick_handler(struct work_struct *); static void aio_queue_work(struct kioctx *); @@ -479,7 +472,6 @@ static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch) { unsigned short allocated, to_alloc; long avail; - bool called_fput = false; struct kiocb *req, *n; struct aio_ring *ring; @@ -495,28 +487,11 @@ static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch) if (allocated == 0) goto out; -retry: spin_lock_irq(&ctx->ctx_lock); ring = kmap_atomic(ctx->ring_info.ring_pages[0]); avail = aio_ring_avail(&ctx->ring_info, ring) - ctx->reqs_active; BUG_ON(avail < 0); - if (avail == 0 && !called_fput) { - /* - * Handle a potential starvation case. It is possible that - * we hold the last reference on a struct file, causing us - * to delay the final fput to non-irq context. In this case, - * ctx->reqs_active is artificially high. Calling the fput - * routine here may free up a slot in the event completion - * ring, allowing this allocation to succeed. - */ - kunmap_atomic(ring); - spin_unlock_irq(&ctx->ctx_lock); - aio_fput_routine(NULL); - called_fput = true; - goto retry; - } - if (avail < allocated) { /* Trim back the number of requests. */ list_for_each_entry_safe(req, n, &batch->head, ki_batch) { @@ -570,36 +545,6 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) wake_up_all(&ctx->wait); } -static void aio_fput_routine(struct work_struct *data) -{ - spin_lock_irq(&fput_lock); - while (likely(!list_empty(&fput_head))) { - struct kiocb *req = list_kiocb(fput_head.next); - struct kioctx *ctx = req->ki_ctx; - - list_del(&req->ki_list); - spin_unlock_irq(&fput_lock); - - /* Complete the fput(s) */ - if (req->ki_filp != NULL) - fput(req->ki_filp); - - /* Link the iocb into the context's free list */ - rcu_read_lock(); - spin_lock_irq(&ctx->ctx_lock); - really_put_req(ctx, req); - /* - * at that point ctx might've been killed, but actual - * freeing is RCU'd - */ - spin_unlock_irq(&ctx->ctx_lock); - rcu_read_unlock(); - - spin_lock_irq(&fput_lock); - } - spin_unlock_irq(&fput_lock); -} - /* __aio_put_req * Returns true if this put was the last user of the request. */ @@ -618,21 +563,9 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) req->ki_cancel = NULL; req->ki_retry = NULL; - /* - * Try to optimize the aio and eventfd file* puts, by avoiding to - * schedule work in case it is not final fput() time. In normal cases, - * we would not be holding the last reference to the file*, so - * this function will be executed w/out any aio kthread wakeup. - */ - if (unlikely(!fput_atomic(req->ki_filp))) { - spin_lock(&fput_lock); - list_add(&req->ki_list, &fput_head); - spin_unlock(&fput_lock); - schedule_work(&fput_work); - } else { - req->ki_filp = NULL; - really_put_req(ctx, req); - } + fput(req->ki_filp); + req->ki_filp = NULL; + really_put_req(ctx, req); return 1; } @@ -171,6 +171,8 @@ int notify_change(struct dentry * dentry, struct iattr * attr) struct timespec now; unsigned int ia_valid = attr->ia_valid; + WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex)); + if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; @@ -250,5 +252,4 @@ int notify_change(struct dentry * dentry, struct iattr * attr) return error; } - EXPORT_SYMBOL(notify_change); diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index aa9103f..abf645c 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -257,8 +257,8 @@ static int autofs_dev_ioctl_open_mountpoint(const char *name, dev_t devid) * corresponding to the autofs fs we want to open. */ - filp = dentry_open(path.dentry, path.mnt, O_RDONLY, - current_cred()); + filp = dentry_open(&path, O_RDONLY, current_cred()); + path_put(&path); if (IS_ERR(filp)) { err = PTR_ERR(filp); goto out; diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 75e5f1c..e7396cf 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -32,7 +32,7 @@ static long autofs4_root_ioctl(struct file *,unsigned int,unsigned long); static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long); #endif static int autofs4_dir_open(struct inode *inode, struct file *file); -static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *); +static struct dentry *autofs4_lookup(struct inode *,struct dentry *, unsigned int); static struct vfsmount *autofs4_d_automount(struct path *); static int autofs4_d_manage(struct dentry *, bool); static void autofs4_dentry_release(struct dentry *); @@ -458,7 +458,7 @@ int autofs4_d_manage(struct dentry *dentry, bool rcu_walk) } /* Lookups in the root directory */ -static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct autofs_sb_info *sbi; struct autofs_info *ino; diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 1b35d6b..b1342ff 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -173,13 +173,13 @@ static const struct file_operations bad_file_ops = }; static int bad_inode_create (struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { return -EIO; } static struct dentry *bad_inode_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { return ERR_PTR(-EIO); } diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index e18da23..cf7f3c6 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -34,7 +34,7 @@ static int befs_readdir(struct file *, void *, filldir_t); static int befs_get_block(struct inode *, sector_t, struct buffer_head *, int); static int befs_readpage(struct file *file, struct page *page); static sector_t befs_bmap(struct address_space *mapping, sector_t block); -static struct dentry *befs_lookup(struct inode *, struct dentry *, struct nameidata *); +static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int); static struct inode *befs_iget(struct super_block *, unsigned long); static struct inode *befs_alloc_inode(struct super_block *sb); static void befs_destroy_inode(struct inode *inode); @@ -159,7 +159,7 @@ befs_get_block(struct inode *inode, sector_t block, } static struct dentry * -befs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode = NULL; struct super_block *sb = dir->i_sb; diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index d12c796..2785ef9 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -85,7 +85,7 @@ const struct file_operations bfs_dir_operations = { extern void dump_imap(const char *, struct super_block *); static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { int err; struct inode *inode; @@ -133,7 +133,7 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, } static struct dentry *bfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode = NULL; struct buffer_head *bh; diff --git a/fs/block_dev.c b/fs/block_dev.c index c2bbe1f..1e51919 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1710,3 +1710,39 @@ int __invalidate_device(struct block_device *bdev, bool kill_dirty) return res; } EXPORT_SYMBOL(__invalidate_device); + +void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) +{ + struct inode *inode, *old_inode = NULL; + + spin_lock(&inode_sb_list_lock); + list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) { + struct address_space *mapping = inode->i_mapping; + + spin_lock(&inode->i_lock); + if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) || + mapping->nrpages == 0) { + spin_unlock(&inode->i_lock); + continue; + } + __iget(inode); + spin_unlock(&inode->i_lock); + spin_unlock(&inode_sb_list_lock); + /* + * We hold a reference to 'inode' so it couldn't have been + * removed from s_inodes list while we dropped the + * inode_sb_list_lock. We cannot iput the inode now as we can + * be holding the last reference and we cannot iput it under + * inode_sb_list_lock. So we keep the reference and iput it + * later. + */ + iput(old_inode); + old_inode = inode; + + func(I_BDEV(inode), arg); + + spin_lock(&inode_sb_list_lock); + } + spin_unlock(&inode_sb_list_lock); + iput(old_inode); +} diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 3f75895..a383c18 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -179,60 +179,74 @@ static int __add_prelim_ref(struct list_head *head, u64 root_id, static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, struct ulist *parents, int level, - struct btrfs_key *key, u64 wanted_disk_byte, + struct btrfs_key *key_for_search, u64 time_seq, + u64 wanted_disk_byte, const u64 *extent_item_pos) { - int ret; - int slot = path->slots[level]; - struct extent_buffer *eb = path->nodes[level]; + int ret = 0; + int slot; + struct extent_buffer *eb; + struct btrfs_key key; struct btrfs_file_extent_item *fi; struct extent_inode_elem *eie = NULL; u64 disk_byte; - u64 wanted_objectid = key->objectid; -add_parent: - if (level == 0 && extent_item_pos) { - fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); - ret = check_extent_in_eb(key, eb, fi, *extent_item_pos, &eie); + if (level != 0) { + eb = path->nodes[level]; + ret = ulist_add(parents, eb->start, 0, GFP_NOFS); if (ret < 0) return ret; - } - ret = ulist_add(parents, eb->start, (unsigned long)eie, GFP_NOFS); - if (ret < 0) - return ret; - - if (level != 0) return 0; + } /* - * if the current leaf is full with EXTENT_DATA items, we must - * check the next one if that holds a reference as well. - * ref->count cannot be used to skip this check. - * repeat this until we don't find any additional EXTENT_DATA items. + * We normally enter this function with the path already pointing to + * the first item to check. But sometimes, we may enter it with + * slot==nritems. In that case, go to the next leaf before we continue. */ - while (1) { - eie = NULL; - ret = btrfs_next_leaf(root, path); - if (ret < 0) - return ret; - if (ret) - return 0; + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) + ret = btrfs_next_old_leaf(root, path, time_seq); + while (!ret) { eb = path->nodes[0]; - for (slot = 0; slot < btrfs_header_nritems(eb); ++slot) { - btrfs_item_key_to_cpu(eb, key, slot); - if (key->objectid != wanted_objectid || - key->type != BTRFS_EXTENT_DATA_KEY) - return 0; - fi = btrfs_item_ptr(eb, slot, - struct btrfs_file_extent_item); - disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); - if (disk_byte == wanted_disk_byte) - goto add_parent; + slot = path->slots[0]; + + btrfs_item_key_to_cpu(eb, &key, slot); + + if (key.objectid != key_for_search->objectid || + key.type != BTRFS_EXTENT_DATA_KEY) + break; + + fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); + disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); + + if (disk_byte == wanted_disk_byte) { + eie = NULL; + if (extent_item_pos) { + ret = check_extent_in_eb(&key, eb, fi, + *extent_item_pos, + &eie); + if (ret < 0) + break; + } + if (!ret) { + ret = ulist_add(parents, eb->start, + (unsigned long)eie, GFP_NOFS); + if (ret < 0) + break; + if (!extent_item_pos) { + ret = btrfs_next_old_leaf(root, path, + time_seq); + continue; + } + } } + ret = btrfs_next_old_item(root, path, time_seq); } - return 0; + if (ret > 0) + ret = 0; + return ret; } /* @@ -249,7 +263,6 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, struct btrfs_path *path; struct btrfs_root *root; struct btrfs_key root_key; - struct btrfs_key key = {0}; struct extent_buffer *eb; int ret = 0; int root_level; @@ -288,25 +301,19 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, goto out; eb = path->nodes[level]; - if (!eb) { - WARN_ON(1); - ret = 1; - goto out; - } - - if (level == 0) { - if (ret == 1 && path->slots[0] >= btrfs_header_nritems(eb)) { - ret = btrfs_next_leaf(root, path); - if (ret) - goto out; - eb = path->nodes[0]; + while (!eb) { + if (!level) { + WARN_ON(1); + ret = 1; + goto out; } - - btrfs_item_key_to_cpu(eb, &key, path->slots[0]); + level--; + eb = path->nodes[level]; } - ret = add_all_parents(root, path, parents, level, &key, - ref->wanted_disk_byte, extent_item_pos); + ret = add_all_parents(root, path, parents, level, &ref->key_for_search, + time_seq, ref->wanted_disk_byte, + extent_item_pos); out: btrfs_free_path(path); return ret; @@ -832,6 +839,7 @@ again: } ret = __add_delayed_refs(head, delayed_ref_seq, &prefs_delayed); + mutex_unlock(&head->mutex); if (ret) { spin_unlock(&delayed_refs->lock); goto out; @@ -925,8 +933,6 @@ again: } out: - if (head) - mutex_unlock(&head->mutex); btrfs_free_path(path); while (!list_empty(&prefs)) { ref = list_first_entry(&prefs, struct __prelim_ref, list); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index e616f887..12394a9 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -37,6 +37,7 @@ #define BTRFS_INODE_IN_DEFRAG 3 #define BTRFS_INODE_DELALLOC_META_RESERVED 4 #define BTRFS_INODE_HAS_ORPHAN_ITEM 5 +#define BTRFS_INODE_HAS_ASYNC_EXTENT 6 /* in memory btrfs inode */ struct btrfs_inode { diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 9cebb1f..da6e936 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -93,6 +93,7 @@ #include "print-tree.h" #include "locking.h" #include "check-integrity.h" +#include "rcu-string.h" #define BTRFSIC_BLOCK_HASHTABLE_SIZE 0x10000 #define BTRFSIC_BLOCK_LINK_HASHTABLE_SIZE 0x10000 @@ -843,13 +844,14 @@ static int btrfsic_process_superblock_dev_mirror( superblock_tmp->never_written = 0; superblock_tmp->mirror_num = 1 + superblock_mirror_num; if (state->print_mask & BTRFSIC_PRINT_MASK_SUPERBLOCK_WRITE) - printk(KERN_INFO "New initial S-block (bdev %p, %s)" - " @%llu (%s/%llu/%d)\n", - superblock_bdev, device->name, - (unsigned long long)dev_bytenr, - dev_state->name, - (unsigned long long)dev_bytenr, - superblock_mirror_num); + printk_in_rcu(KERN_INFO "New initial S-block (bdev %p, %s)" + " @%llu (%s/%llu/%d)\n", + superblock_bdev, + rcu_str_deref(device->name), + (unsigned long long)dev_bytenr, + dev_state->name, + (unsigned long long)dev_bytenr, + superblock_mirror_num); list_add(&superblock_tmp->all_blocks_node, &state->all_blocks_list); btrfsic_block_hashtable_add(superblock_tmp, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index d7a96cf..8206b39 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -467,6 +467,15 @@ static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info, return 0; } +/* + * This allocates memory and gets a tree modification sequence number when + * needed. + * + * Returns 0 when no sequence number is needed, < 0 on error. + * Returns 1 when a sequence number was added. In this case, + * fs_info->tree_mod_seq_lock was acquired and must be released by the caller + * after inserting into the rb tree. + */ static inline int tree_mod_alloc(struct btrfs_fs_info *fs_info, gfp_t flags, struct tree_mod_elem **tm_ret) { @@ -491,11 +500,11 @@ static inline int tree_mod_alloc(struct btrfs_fs_info *fs_info, gfp_t flags, */ kfree(tm); seq = 0; + spin_unlock(&fs_info->tree_mod_seq_lock); } else { __get_tree_mod_seq(fs_info, &tm->elem); seq = tm->elem.seq; } - spin_unlock(&fs_info->tree_mod_seq_lock); return seq; } @@ -521,7 +530,9 @@ tree_mod_log_insert_key_mask(struct btrfs_fs_info *fs_info, tm->slot = slot; tm->generation = btrfs_node_ptr_generation(eb, slot); - return __tree_mod_log_insert(fs_info, tm); + ret = __tree_mod_log_insert(fs_info, tm); + spin_unlock(&fs_info->tree_mod_seq_lock); + return ret; } static noinline int @@ -559,7 +570,9 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info, tm->move.nr_items = nr_items; tm->op = MOD_LOG_MOVE_KEYS; - return __tree_mod_log_insert(fs_info, tm); + ret = __tree_mod_log_insert(fs_info, tm); + spin_unlock(&fs_info->tree_mod_seq_lock); + return ret; } static noinline int @@ -580,7 +593,9 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, tm->generation = btrfs_header_generation(old_root); tm->op = MOD_LOG_ROOT_REPLACE; - return __tree_mod_log_insert(fs_info, tm); + ret = __tree_mod_log_insert(fs_info, tm); + spin_unlock(&fs_info->tree_mod_seq_lock); + return ret; } static struct tree_mod_elem * @@ -1009,11 +1024,18 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info, if (!looped && !tm) return 0; /* - * we must have key remove operations in the log before the - * replace operation. + * if there are no tree operation for the oldest root, we simply + * return it. this should only happen if that (old) root is at + * level 0. */ - BUG_ON(!tm); + if (!tm) + break; + /* + * if there's an operation that's not a root replacement, we + * found the oldest version of our root. normally, we'll find a + * MOD_LOG_KEY_REMOVE_WHILE_FREEING operation here. + */ if (tm->op != MOD_LOG_ROOT_REPLACE) break; @@ -1023,6 +1045,10 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info, looped = 1; } + /* if there's no old root to return, return what we found instead */ + if (!found) + found = tm; + return found; } @@ -1068,11 +1094,7 @@ __tree_mod_log_rewind(struct extent_buffer *eb, u64 time_seq, tm->generation); break; case MOD_LOG_KEY_ADD: - if (tm->slot != n - 1) { - o_dst = btrfs_node_key_ptr_offset(tm->slot); - o_src = btrfs_node_key_ptr_offset(tm->slot + 1); - memmove_extent_buffer(eb, o_dst, o_src, p_size); - } + /* if a move operation is needed it's in the log */ n--; break; case MOD_LOG_MOVE_KEYS: @@ -1143,45 +1165,57 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, return eb_rewin; } +/* + * get_old_root() rewinds the state of @root's root node to the given @time_seq + * value. If there are no changes, the current root->root_node is returned. If + * anything changed in between, there's a fresh buffer allocated on which the + * rewind operations are done. In any case, the returned buffer is read locked. + * Returns NULL on error (with no locks held). + */ static inline struct extent_buffer * get_old_root(struct btrfs_root *root, u64 time_seq) { struct tree_mod_elem *tm; struct extent_buffer *eb; - struct tree_mod_root *old_root; - u64 old_generation; + struct tree_mod_root *old_root = NULL; + u64 old_generation = 0; + u64 logical; + eb = btrfs_read_lock_root_node(root); tm = __tree_mod_log_oldest_root(root->fs_info, root, time_seq); if (!tm) return root->node; - old_root = &tm->old_root; - old_generation = tm->generation; - - tm = tree_mod_log_search(root->fs_info, old_root->logical, time_seq); - /* - * there was an item in the log when __tree_mod_log_oldest_root - * returned. this one must not go away, because the time_seq passed to - * us must be blocking its removal. - */ - BUG_ON(!tm); + if (tm->op == MOD_LOG_ROOT_REPLACE) { + old_root = &tm->old_root; + old_generation = tm->generation; + logical = old_root->logical; + } else { + logical = root->node->start; + } - if (old_root->logical == root->node->start) { - /* there are logged operations for the current root */ + tm = tree_mod_log_search(root->fs_info, logical, time_seq); + if (old_root) + eb = alloc_dummy_extent_buffer(logical, root->nodesize); + else eb = btrfs_clone_extent_buffer(root->node); - } else { - /* there's a root replace operation for the current root */ - eb = alloc_dummy_extent_buffer(tm->index << PAGE_CACHE_SHIFT, - root->nodesize); + btrfs_tree_read_unlock(root->node); + free_extent_buffer(root->node); + if (!eb) + return NULL; + btrfs_tree_read_lock(eb); + if (old_root) { btrfs_set_header_bytenr(eb, eb->start); btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV); btrfs_set_header_owner(eb, root->root_key.objectid); + btrfs_set_header_level(eb, old_root->level); + btrfs_set_header_generation(eb, old_generation); } - if (!eb) - return NULL; - btrfs_set_header_level(eb, old_root->level); - btrfs_set_header_generation(eb, old_generation); - __tree_mod_log_rewind(eb, time_seq, tm); + if (tm) + __tree_mod_log_rewind(eb, time_seq, tm); + else + WARN_ON(btrfs_header_level(eb) != 0); + extent_buffer_get(eb); return eb; } @@ -1650,8 +1684,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, BTRFS_NODEPTRS_PER_BLOCK(root) / 4) return 0; - btrfs_header_nritems(mid); - left = read_node_slot(root, parent, pslot - 1); if (left) { btrfs_tree_lock(left); @@ -1681,7 +1713,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, wret = push_node_left(trans, root, left, mid, 1); if (wret < 0) ret = wret; - btrfs_header_nritems(mid); } /* @@ -2615,9 +2646,7 @@ int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key, again: b = get_old_root(root, time_seq); - extent_buffer_get(b); level = btrfs_header_level(b); - btrfs_tree_read_lock(b); p->locks[level] = BTRFS_READ_LOCK; while (b) { @@ -2964,7 +2993,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, static void insert_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_disk_key *key, u64 bytenr, - int slot, int level, int tree_mod_log) + int slot, int level) { struct extent_buffer *lower; int nritems; @@ -2977,7 +3006,7 @@ static void insert_ptr(struct btrfs_trans_handle *trans, BUG_ON(slot > nritems); BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(root)); if (slot != nritems) { - if (tree_mod_log && level) + if (level) tree_mod_log_eb_move(root->fs_info, lower, slot + 1, slot, nritems - slot); memmove_extent_buffer(lower, @@ -2985,7 +3014,7 @@ static void insert_ptr(struct btrfs_trans_handle *trans, btrfs_node_key_ptr_offset(slot), (nritems - slot) * sizeof(struct btrfs_key_ptr)); } - if (tree_mod_log && level) { + if (level) { ret = tree_mod_log_insert_key(root->fs_info, lower, slot, MOD_LOG_KEY_ADD); BUG_ON(ret < 0); @@ -3073,7 +3102,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(split); insert_ptr(trans, root, path, &disk_key, split->start, - path->slots[level + 1] + 1, level + 1, 1); + path->slots[level + 1] + 1, level + 1); if (path->slots[level] >= mid) { path->slots[level] -= mid; @@ -3610,7 +3639,7 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, btrfs_set_header_nritems(l, mid); btrfs_item_key(right, &disk_key, 0); insert_ptr(trans, root, path, &disk_key, right->start, - path->slots[1] + 1, 1, 0); + path->slots[1] + 1, 1); btrfs_mark_buffer_dirty(right); btrfs_mark_buffer_dirty(l); @@ -3817,7 +3846,7 @@ again: if (mid <= slot) { btrfs_set_header_nritems(right, 0); insert_ptr(trans, root, path, &disk_key, right->start, - path->slots[1] + 1, 1, 0); + path->slots[1] + 1, 1); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -3826,7 +3855,7 @@ again: } else { btrfs_set_header_nritems(right, 0); insert_ptr(trans, root, path, &disk_key, right->start, - path->slots[1], 1, 0); + path->slots[1], 1); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -5001,6 +5030,12 @@ next: */ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) { + return btrfs_next_old_leaf(root, path, 0); +} + +int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, + u64 time_seq) +{ int slot; int level; struct extent_buffer *c; @@ -5025,7 +5060,10 @@ again: path->keep_locks = 1; path->leave_spinning = 1; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (time_seq) + ret = btrfs_search_old_slot(root, &key, path, time_seq); + else + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); path->keep_locks = 0; if (ret < 0) @@ -5081,6 +5119,18 @@ again: if (!path->skip_locking) { ret = btrfs_try_tree_read_lock(next); + if (!ret && time_seq) { + /* + * If we don't get the lock, we may be racing + * with push_leaf_left, holding that lock while + * itself waiting for the leaf we've currently + * locked. To solve this situation, we give up + * on our lock and cycle. + */ + btrfs_release_path(path); + cond_resched(); + goto again; + } if (!ret) { btrfs_set_path_blocking(path); btrfs_tree_read_lock(next); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0236d03..fa5c45b 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2753,13 +2753,20 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans, } int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path); -static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) +int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, + u64 time_seq); +static inline int btrfs_next_old_item(struct btrfs_root *root, + struct btrfs_path *p, u64 time_seq) { ++p->slots[0]; if (p->slots[0] >= btrfs_header_nritems(p->nodes[0])) - return btrfs_next_leaf(root, p); + return btrfs_next_old_leaf(root, p, time_seq); return 0; } +static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) +{ + return btrfs_next_old_item(root, p, 0); +} int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf); int __must_check btrfs_drop_snapshot(struct btrfs_root *root, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index c18d044..2399f40 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1879,3 +1879,21 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root) } } } + +void btrfs_destroy_delayed_inodes(struct btrfs_root *root) +{ + struct btrfs_delayed_root *delayed_root; + struct btrfs_delayed_node *curr_node, *prev_node; + + delayed_root = btrfs_get_delayed_root(root); + + curr_node = btrfs_first_delayed_node(delayed_root); + while (curr_node) { + __btrfs_kill_delayed_node(curr_node); + + prev_node = curr_node; + curr_node = btrfs_next_delayed_node(curr_node); + btrfs_release_delayed_node(prev_node); + } +} + diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index 7083d08..f5aa402 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -124,6 +124,9 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev); /* Used for drop dead root */ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root); +/* Used for clean the transaction */ +void btrfs_destroy_delayed_inodes(struct btrfs_root *root); + /* Used for readdir() */ void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list, struct list_head *del_list); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7ae51de..2936ca4 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -44,6 +44,7 @@ #include "free-space-cache.h" #include "inode-map.h" #include "check-integrity.h" +#include "rcu-string.h" static struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); @@ -2118,7 +2119,7 @@ int open_ctree(struct super_block *sb, features = btrfs_super_incompat_flags(disk_super); features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; - if (tree_root->fs_info->compress_type & BTRFS_COMPRESS_LZO) + if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO) features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; /* @@ -2353,12 +2354,17 @@ retry_root_backup: BTRFS_CSUM_TREE_OBJECTID, csum_root); if (ret) goto recovery_tree_root; - csum_root->track_dirty = 1; fs_info->generation = generation; fs_info->last_trans_committed = generation; + ret = btrfs_recover_balance(fs_info); + if (ret) { + printk(KERN_WARNING "btrfs: failed to recover balance\n"); + goto fail_block_groups; + } + ret = btrfs_init_dev_stats(fs_info); if (ret) { printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n", @@ -2484,20 +2490,23 @@ retry_root_backup: goto fail_trans_kthread; } - if (!(sb->s_flags & MS_RDONLY)) { - down_read(&fs_info->cleanup_work_sem); - err = btrfs_orphan_cleanup(fs_info->fs_root); - if (!err) - err = btrfs_orphan_cleanup(fs_info->tree_root); - up_read(&fs_info->cleanup_work_sem); + if (sb->s_flags & MS_RDONLY) + return 0; - if (!err) - err = btrfs_recover_balance(fs_info->tree_root); + down_read(&fs_info->cleanup_work_sem); + if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || + (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { + up_read(&fs_info->cleanup_work_sem); + close_ctree(tree_root); + return ret; + } + up_read(&fs_info->cleanup_work_sem); - if (err) { - close_ctree(tree_root); - return err; - } + ret = btrfs_resume_balance_async(fs_info); + if (ret) { + printk(KERN_WARNING "btrfs: failed to resume balance\n"); + close_ctree(tree_root); + return ret; } return 0; @@ -2575,8 +2584,9 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) struct btrfs_device *device = (struct btrfs_device *) bh->b_private; - printk_ratelimited(KERN_WARNING "lost page write due to " - "I/O error on %s\n", device->name); + printk_ratelimited_in_rcu(KERN_WARNING "lost page write due to " + "I/O error on %s\n", + rcu_str_deref(device->name)); /* note, we dont' set_buffer_write_io_error because we have * our own ways of dealing with the IO errors */ @@ -2749,8 +2759,8 @@ static int write_dev_flush(struct btrfs_device *device, int wait) wait_for_completion(&device->flush_wait); if (bio_flagged(bio, BIO_EOPNOTSUPP)) { - printk("btrfs: disabling barriers on dev %s\n", - device->name); + printk_in_rcu("btrfs: disabling barriers on dev %s\n", + rcu_str_deref(device->name)); device->nobarriers = 1; } if (!bio_flagged(bio, BIO_UPTODATE)) { @@ -3400,7 +3410,6 @@ int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, delayed_refs = &trans->delayed_refs; -again: spin_lock(&delayed_refs->lock); if (delayed_refs->num_entries == 0) { spin_unlock(&delayed_refs->lock); @@ -3408,31 +3417,37 @@ again: return ret; } - node = rb_first(&delayed_refs->root); - while (node) { + while ((node = rb_first(&delayed_refs->root)) != NULL) { ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node); - node = rb_next(node); - - ref->in_tree = 0; - rb_erase(&ref->rb_node, &delayed_refs->root); - delayed_refs->num_entries--; atomic_set(&ref->refs, 1); if (btrfs_delayed_ref_is_head(ref)) { struct btrfs_delayed_ref_head *head; head = btrfs_delayed_node_to_head(ref); - spin_unlock(&delayed_refs->lock); - mutex_lock(&head->mutex); + if (!mutex_trylock(&head->mutex)) { + atomic_inc(&ref->refs); + spin_unlock(&delayed_refs->lock); + + /* Need to wait for the delayed ref to run */ + mutex_lock(&head->mutex); + mutex_unlock(&head->mutex); + btrfs_put_delayed_ref(ref); + + spin_lock(&delayed_refs->lock); + continue; + } + kfree(head->extent_op); delayed_refs->num_heads--; if (list_empty(&head->cluster)) delayed_refs->num_heads_ready--; list_del_init(&head->cluster); - mutex_unlock(&head->mutex); - btrfs_put_delayed_ref(ref); - goto again; } + ref->in_tree = 0; + rb_erase(&ref->rb_node, &delayed_refs->root); + delayed_refs->num_entries--; + spin_unlock(&delayed_refs->lock); btrfs_put_delayed_ref(ref); @@ -3520,11 +3535,9 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root, &(&BTRFS_I(page->mapping->host)->io_tree)->buffer, offset >> PAGE_CACHE_SHIFT); spin_unlock(&dirty_pages->buffer_lock); - if (eb) { + if (eb) ret = test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags); - atomic_set(&eb->refs, 1); - } if (PageWriteback(page)) end_page_writeback(page); @@ -3538,8 +3551,8 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root, spin_unlock_irq(&page->mapping->tree_lock); } - page->mapping->a_ops->invalidatepage(page, 0); unlock_page(page); + page_cache_release(page); } } @@ -3553,8 +3566,10 @@ static int btrfs_destroy_pinned_extent(struct btrfs_root *root, u64 start; u64 end; int ret; + bool loop = true; unpin = pinned_extents; +again: while (1) { ret = find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY); @@ -3572,6 +3587,15 @@ static int btrfs_destroy_pinned_extent(struct btrfs_root *root, cond_resched(); } + if (loop) { + if (unpin == &root->fs_info->freed_extents[0]) + unpin = &root->fs_info->freed_extents[1]; + else + unpin = &root->fs_info->freed_extents[0]; + loop = false; + goto again; + } + return 0; } @@ -3585,21 +3609,23 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, /* FIXME: cleanup wait for commit */ cur_trans->in_commit = 1; cur_trans->blocked = 1; - if (waitqueue_active(&root->fs_info->transaction_blocked_wait)) - wake_up(&root->fs_info->transaction_blocked_wait); + wake_up(&root->fs_info->transaction_blocked_wait); cur_trans->blocked = 0; - if (waitqueue_active(&root->fs_info->transaction_wait)) - wake_up(&root->fs_info->transaction_wait); + wake_up(&root->fs_info->transaction_wait); cur_trans->commit_done = 1; - if (waitqueue_active(&cur_trans->commit_wait)) - wake_up(&cur_trans->commit_wait); + wake_up(&cur_trans->commit_wait); + + btrfs_destroy_delayed_inodes(root); + btrfs_assert_delayed_root_empty(root); btrfs_destroy_pending_snapshots(cur_trans); btrfs_destroy_marked_extents(root, &cur_trans->dirty_pages, EXTENT_DIRTY); + btrfs_destroy_pinned_extent(root, + root->fs_info->pinned_extents); /* memset(cur_trans, 0, sizeof(*cur_trans)); @@ -3648,6 +3674,9 @@ int btrfs_cleanup_transaction(struct btrfs_root *root) if (waitqueue_active(&t->commit_wait)) wake_up(&t->commit_wait); + btrfs_destroy_delayed_inodes(root); + btrfs_assert_delayed_root_empty(root); + btrfs_destroy_pending_snapshots(t); btrfs_destroy_delalloc_inodes(root); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4b5a1e1..6e1d367 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2347,12 +2347,10 @@ next: return count; } - static void wait_for_more_refs(struct btrfs_delayed_ref_root *delayed_refs, - unsigned long num_refs) + unsigned long num_refs, + struct list_head *first_seq) { - struct list_head *first_seq = delayed_refs->seq_head.next; - spin_unlock(&delayed_refs->lock); pr_debug("waiting for more refs (num %ld, first %p)\n", num_refs, first_seq); @@ -2381,6 +2379,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_ref_node *ref; struct list_head cluster; + struct list_head *first_seq = NULL; int ret; u64 delayed_start; int run_all = count == (unsigned long)-1; @@ -2436,8 +2435,10 @@ again: */ consider_waiting = 1; num_refs = delayed_refs->num_entries; + first_seq = root->fs_info->tree_mod_seq_list.next; } else { - wait_for_more_refs(delayed_refs, num_refs); + wait_for_more_refs(delayed_refs, + num_refs, first_seq); /* * after waiting, things have changed. we * dropped the lock and someone else might have diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 2c8f7b2..01c21b6 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -20,6 +20,7 @@ #include "volumes.h" #include "check-integrity.h" #include "locking.h" +#include "rcu-string.h" static struct kmem_cache *extent_state_cache; static struct kmem_cache *extent_buffer_cache; @@ -1917,9 +1918,9 @@ int repair_io_failure(struct btrfs_mapping_tree *map_tree, u64 start, return -EIO; } - printk(KERN_INFO "btrfs read error corrected: ino %lu off %llu (dev %s " - "sector %llu)\n", page->mapping->host->i_ino, start, - dev->name, sector); + printk_in_rcu(KERN_INFO "btrfs read error corrected: ino %lu off %llu " + "(dev %s sector %llu)\n", page->mapping->host->i_ino, + start, rcu_str_deref(dev->name), sector); bio_put(bio); return 0; @@ -3323,6 +3324,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, writepage_t writepage, void *data, void (*flush_fn)(void *)) { + struct inode *inode = mapping->host; int ret = 0; int done = 0; int nr_to_write_done = 0; @@ -3333,6 +3335,18 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, int scanned = 0; int tag; + /* + * We have to hold onto the inode so that ordered extents can do their + * work when the IO finishes. The alternative to this is failing to add + * an ordered extent if the igrab() fails there and that is a huge pain + * to deal with, so instead just hold onto the inode throughout the + * writepages operation. If it fails here we are freeing up the inode + * anyway and we'd rather not waste our time writing out stuff that is + * going to be truncated anyway. + */ + if (!igrab(inode)) + return 0; + pagevec_init(&pvec, 0); if (wbc->range_cyclic) { index = mapping->writeback_index; /* Start from prev offset */ @@ -3427,6 +3441,7 @@ retry: index = 0; goto retry; } + btrfs_add_delayed_iput(inode); return ret; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 70dc8ca..9aa01ec 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1334,7 +1334,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, loff_t *ppos, size_t count, size_t ocount) { struct file *file = iocb->ki_filp; - struct inode *inode = fdentry(file)->d_inode; struct iov_iter i; ssize_t written; ssize_t written_buffered; @@ -1344,18 +1343,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, written = generic_file_direct_write(iocb, iov, &nr_segs, pos, ppos, count, ocount); - /* - * the generic O_DIRECT will update in-memory i_size after the - * DIOs are done. But our endio handlers that update the on - * disk i_size never update past the in memory i_size. So we - * need one more update here to catch any additions to the - * file - */ - if (inode->i_size != BTRFS_I(inode)->disk_i_size) { - btrfs_ordered_update_i_size(inode, inode->i_size, NULL); - mark_inode_dirty(inode); - } - if (written < 0 || written == count) return written; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 81296c5..6c4e2ba 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1543,29 +1543,26 @@ again: end = bitmap_info->offset + (u64)(BITS_PER_BITMAP * ctl->unit) - 1; /* - * XXX - this can go away after a few releases. - * - * since the only user of btrfs_remove_free_space is the tree logging - * stuff, and the only way to test that is under crash conditions, we - * want to have this debug stuff here just in case somethings not - * working. Search the bitmap for the space we are trying to use to - * make sure its actually there. If its not there then we need to stop - * because something has gone wrong. + * We need to search for bits in this bitmap. We could only cover some + * of the extent in this bitmap thanks to how we add space, so we need + * to search for as much as it as we can and clear that amount, and then + * go searching for the next bit. */ search_start = *offset; - search_bytes = *bytes; + search_bytes = ctl->unit; search_bytes = min(search_bytes, end - search_start + 1); ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes); BUG_ON(ret < 0 || search_start != *offset); - if (*offset > bitmap_info->offset && *offset + *bytes > end) { - bitmap_clear_bits(ctl, bitmap_info, *offset, end - *offset + 1); - *bytes -= end - *offset + 1; - *offset = end + 1; - } else if (*offset >= bitmap_info->offset && *offset + *bytes <= end) { - bitmap_clear_bits(ctl, bitmap_info, *offset, *bytes); - *bytes = 0; - } + /* We may have found more bits than what we need */ + search_bytes = min(search_bytes, *bytes); + + /* Cannot clear past the end of the bitmap */ + search_bytes = min(search_bytes, end - search_start + 1); + + bitmap_clear_bits(ctl, bitmap_info, search_start, search_bytes); + *offset += search_bytes; + *bytes -= search_bytes; if (*bytes) { struct rb_node *next = rb_next(&bitmap_info->offset_index); @@ -1596,7 +1593,7 @@ again: * everything over again. */ search_start = *offset; - search_bytes = *bytes; + search_bytes = ctl->unit; ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes); if (ret < 0 || search_start != *offset) @@ -1879,12 +1876,14 @@ int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *info; - struct btrfs_free_space *next_info = NULL; int ret = 0; spin_lock(&ctl->tree_lock); again: + if (!bytes) + goto out_lock; + info = tree_search_offset(ctl, offset, 0, 0); if (!info) { /* @@ -1905,88 +1904,48 @@ again: } } - if (info->bytes < bytes && rb_next(&info->offset_index)) { - u64 end; - next_info = rb_entry(rb_next(&info->offset_index), - struct btrfs_free_space, - offset_index); - - if (next_info->bitmap) - end = next_info->offset + - BITS_PER_BITMAP * ctl->unit - 1; - else - end = next_info->offset + next_info->bytes; - - if (next_info->bytes < bytes || - next_info->offset > offset || offset > end) { - printk(KERN_CRIT "Found free space at %llu, size %llu," - " trying to use %llu\n", - (unsigned long long)info->offset, - (unsigned long long)info->bytes, - (unsigned long long)bytes); - WARN_ON(1); - ret = -EINVAL; - goto out_lock; - } - - info = next_info; - } - - if (info->bytes == bytes) { + if (!info->bitmap) { unlink_free_space(ctl, info); - if (info->bitmap) { - kfree(info->bitmap); - ctl->total_bitmaps--; - } - kmem_cache_free(btrfs_free_space_cachep, info); - ret = 0; - goto out_lock; - } - - if (!info->bitmap && info->offset == offset) { - unlink_free_space(ctl, info); - info->offset += bytes; - info->bytes -= bytes; - ret = link_free_space(ctl, info); - WARN_ON(ret); - goto out_lock; - } + if (offset == info->offset) { + u64 to_free = min(bytes, info->bytes); + + info->bytes -= to_free; + info->offset += to_free; + if (info->bytes) { + ret = link_free_space(ctl, info); + WARN_ON(ret); + } else { + kmem_cache_free(btrfs_free_space_cachep, info); + } - if (!info->bitmap && info->offset <= offset && - info->offset + info->bytes >= offset + bytes) { - u64 old_start = info->offset; - /* - * we're freeing space in the middle of the info, - * this can happen during tree log replay - * - * first unlink the old info and then - * insert it again after the hole we're creating - */ - unlink_free_space(ctl, info); - if (offset + bytes < info->offset + info->bytes) { - u64 old_end = info->offset + info->bytes; + offset += to_free; + bytes -= to_free; + goto again; + } else { + u64 old_end = info->bytes + info->offset; - info->offset = offset + bytes; - info->bytes = old_end - info->offset; + info->bytes = offset - info->offset; ret = link_free_space(ctl, info); WARN_ON(ret); if (ret) goto out_lock; - } else { - /* the hole we're creating ends at the end - * of the info struct, just free the info - */ - kmem_cache_free(btrfs_free_space_cachep, info); - } - spin_unlock(&ctl->tree_lock); - /* step two, insert a new info struct to cover - * anything before the hole - */ - ret = btrfs_add_free_space(block_group, old_start, - offset - old_start); - WARN_ON(ret); /* -ENOMEM */ - goto out; + /* Not enough bytes in this entry to satisfy us */ + if (old_end < offset + bytes) { + bytes -= old_end - offset; + offset = old_end; + goto again; + } else if (old_end == offset + bytes) { + /* all done */ + goto out_lock; + } + spin_unlock(&ctl->tree_lock); + + ret = btrfs_add_free_space(block_group, offset + bytes, + old_end - (offset + bytes)); + WARN_ON(ret); + goto out; + } } ret = remove_from_bitmap(ctl, info, &offset, &bytes); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f6ab6f5..fb8d671 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -830,7 +830,7 @@ static noinline int cow_file_range(struct inode *inode, if (IS_ERR(trans)) { extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree, - start, end, NULL, + start, end, locked_page, EXTENT_CLEAR_UNLOCK_PAGE | EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC | @@ -963,7 +963,7 @@ out: out_unlock: extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree, - start, end, NULL, + start, end, locked_page, EXTENT_CLEAR_UNLOCK_PAGE | EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC | @@ -986,8 +986,10 @@ static noinline void async_cow_start(struct btrfs_work *work) compress_file_range(async_cow->inode, async_cow->locked_page, async_cow->start, async_cow->end, async_cow, &num_added); - if (num_added == 0) + if (num_added == 0) { + btrfs_add_delayed_iput(async_cow->inode); async_cow->inode = NULL; + } } /* @@ -1020,6 +1022,8 @@ static noinline void async_cow_free(struct btrfs_work *work) { struct async_cow *async_cow; async_cow = container_of(work, struct async_cow, work); + if (async_cow->inode) + btrfs_add_delayed_iput(async_cow->inode); kfree(async_cow); } @@ -1038,7 +1042,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page, while (start < end) { async_cow = kmalloc(sizeof(*async_cow), GFP_NOFS); BUG_ON(!async_cow); /* -ENOMEM */ - async_cow->inode = inode; + async_cow->inode = igrab(inode); async_cow->root = root; async_cow->locked_page = locked_page; async_cow->start = start; @@ -1136,8 +1140,18 @@ static noinline int run_delalloc_nocow(struct inode *inode, u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); - if (!path) + if (!path) { + extent_clear_unlock_delalloc(inode, + &BTRFS_I(inode)->io_tree, + start, end, locked_page, + EXTENT_CLEAR_UNLOCK_PAGE | + EXTENT_CLEAR_UNLOCK | + EXTENT_CLEAR_DELALLOC | + EXTENT_CLEAR_DIRTY | + EXTENT_SET_WRITEBACK | + EXTENT_END_WRITEBACK); return -ENOMEM; + } nolock = btrfs_is_free_space_inode(root, inode); @@ -1147,6 +1161,15 @@ static noinline int run_delalloc_nocow(struct inode *inode, trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { + extent_clear_unlock_delalloc(inode, + &BTRFS_I(inode)->io_tree, + start, end, locked_page, + EXTENT_CLEAR_UNLOCK_PAGE | + EXTENT_CLEAR_UNLOCK | + EXTENT_CLEAR_DELALLOC | + EXTENT_CLEAR_DIRTY | + EXTENT_SET_WRITEBACK | + EXTENT_END_WRITEBACK); btrfs_free_path(path); return PTR_ERR(trans); } @@ -1327,8 +1350,11 @@ out_check: } btrfs_release_path(path); - if (cur_offset <= end && cow_start == (u64)-1) + if (cur_offset <= end && cow_start == (u64)-1) { cow_start = cur_offset; + cur_offset = end; + } + if (cow_start != (u64)-1) { ret = cow_file_range(inode, locked_page, cow_start, end, page_started, nr_written, 1); @@ -1347,6 +1373,17 @@ error: if (!ret) ret = err; + if (ret && cur_offset < end) + extent_clear_unlock_delalloc(inode, + &BTRFS_I(inode)->io_tree, + cur_offset, end, locked_page, + EXTENT_CLEAR_UNLOCK_PAGE | + EXTENT_CLEAR_UNLOCK | + EXTENT_CLEAR_DELALLOC | + EXTENT_CLEAR_DIRTY | + EXTENT_SET_WRITEBACK | + EXTENT_END_WRITEBACK); + btrfs_free_path(path); return ret; } @@ -1361,20 +1398,23 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page, int ret; struct btrfs_root *root = BTRFS_I(inode)->root; - if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) + if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 1, nr_written); - else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC) + } else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); - else if (!btrfs_test_opt(root, COMPRESS) && - !(BTRFS_I(inode)->force_compress) && - !(BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS)) + } else if (!btrfs_test_opt(root, COMPRESS) && + !(BTRFS_I(inode)->force_compress) && + !(BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS)) { ret = cow_file_range(inode, locked_page, start, end, page_started, nr_written, 1); - else + } else { + set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, + &BTRFS_I(inode)->runtime_flags); ret = cow_file_range_async(inode, locked_page, start, end, page_started, nr_written); + } return ret; } @@ -3714,7 +3754,7 @@ void btrfs_evict_inode(struct inode *inode) btrfs_wait_ordered_range(inode, 0, (u64)-1); if (root->fs_info->log_root_recovering) { - BUG_ON(!test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &BTRFS_I(inode)->runtime_flags)); goto no_delete; } @@ -4207,7 +4247,7 @@ static void btrfs_dentry_release(struct dentry *dentry) } static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct dentry *ret; @@ -4853,7 +4893,7 @@ out_unlock: } static int btrfs_create(struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(dir)->root; @@ -5836,8 +5876,17 @@ map: bh_result->b_size = len; bh_result->b_bdev = em->bdev; set_buffer_mapped(bh_result); - if (create && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) - set_buffer_new(bh_result); + if (create) { + if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) + set_buffer_new(bh_result); + + /* + * Need to update the i_size under the extent lock so buffered + * readers will get the updated i_size when we unlock. + */ + if (start + len > i_size_read(inode)) + i_size_write(inode, start + len); + } free_extent_map(em); @@ -6320,12 +6369,48 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, */ ordered = btrfs_lookup_ordered_range(inode, lockstart, lockend - lockstart + 1); - if (!ordered) + + /* + * We need to make sure there are no buffered pages in this + * range either, we could have raced between the invalidate in + * generic_file_direct_write and locking the extent. The + * invalidate needs to happen so that reads after a write do not + * get stale data. + */ + if (!ordered && (!writing || + !test_range_bit(&BTRFS_I(inode)->io_tree, + lockstart, lockend, EXTENT_UPTODATE, 0, + cached_state))) break; + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state, GFP_NOFS); - btrfs_start_ordered_extent(inode, ordered, 1); - btrfs_put_ordered_extent(ordered); + + if (ordered) { + btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_put_ordered_extent(ordered); + } else { + /* Screw you mmap */ + ret = filemap_write_and_wait_range(file->f_mapping, + lockstart, + lockend); + if (ret) + goto out; + + /* + * If we found a page that couldn't be invalidated just + * fall back to buffered. + */ + ret = invalidate_inode_pages2_range(file->f_mapping, + lockstart >> PAGE_CACHE_SHIFT, + lockend >> PAGE_CACHE_SHIFT); + if (ret) { + if (ret == -EBUSY) + ret = 0; + goto out; + } + } + cond_resched(); } @@ -6902,7 +6987,7 @@ void btrfs_destroy_inode(struct inode *inode) struct btrfs_ordered_extent *ordered; struct btrfs_root *root = BTRFS_I(inode)->root; - WARN_ON(!list_empty(&inode->i_dentry)); + WARN_ON(!hlist_empty(&inode->i_dentry)); WARN_ON(inode->i_data.nrpages); WARN_ON(BTRFS_I(inode)->outstanding_extents); WARN_ON(BTRFS_I(inode)->reserved_extents); @@ -7054,10 +7139,13 @@ static void fixup_inode_flags(struct inode *dir, struct inode *inode) else b_inode->flags &= ~BTRFS_INODE_NODATACOW; - if (b_dir->flags & BTRFS_INODE_COMPRESS) + if (b_dir->flags & BTRFS_INODE_COMPRESS) { b_inode->flags |= BTRFS_INODE_COMPRESS; - else - b_inode->flags &= ~BTRFS_INODE_COMPRESS; + b_inode->flags &= ~BTRFS_INODE_NOCOMPRESS; + } else { + b_inode->flags &= ~(BTRFS_INODE_COMPRESS | + BTRFS_INODE_NOCOMPRESS); + } } static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 24b776c..1e9f6c0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -52,6 +52,7 @@ #include "locking.h" #include "inode-map.h" #include "backref.h" +#include "rcu-string.h" /* Mask out flags that are inappropriate for the given type of inode. */ static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags) @@ -785,39 +786,57 @@ none: return -ENOENT; } -/* - * Validaty check of prev em and next em: - * 1) no prev/next em - * 2) prev/next em is an hole/inline extent - */ -static int check_adjacent_extents(struct inode *inode, struct extent_map *em) +static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start) { struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; - struct extent_map *prev = NULL, *next = NULL; - int ret = 0; + struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct extent_map *em; + u64 len = PAGE_CACHE_SIZE; + /* + * hopefully we have this extent in the tree already, try without + * the full extent lock + */ read_lock(&em_tree->lock); - prev = lookup_extent_mapping(em_tree, em->start - 1, (u64)-1); - next = lookup_extent_mapping(em_tree, em->start + em->len, (u64)-1); + em = lookup_extent_mapping(em_tree, start, len); read_unlock(&em_tree->lock); - if ((!prev || prev->block_start >= EXTENT_MAP_LAST_BYTE) && - (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)) - ret = 1; - free_extent_map(prev); - free_extent_map(next); + if (!em) { + /* get the big lock and read metadata off disk */ + lock_extent(io_tree, start, start + len - 1); + em = btrfs_get_extent(inode, NULL, 0, start, len, 0); + unlock_extent(io_tree, start, start + len - 1); + if (IS_ERR(em)) + return NULL; + } + + return em; +} + +static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em) +{ + struct extent_map *next; + bool ret = true; + + /* this is the last extent */ + if (em->start + em->len >= i_size_read(inode)) + return false; + + next = defrag_lookup_extent(inode, em->start + em->len); + if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE) + ret = false; + + free_extent_map(next); return ret; } -static int should_defrag_range(struct inode *inode, u64 start, u64 len, - int thresh, u64 *last_len, u64 *skip, - u64 *defrag_end) +static int should_defrag_range(struct inode *inode, u64 start, int thresh, + u64 *last_len, u64 *skip, u64 *defrag_end) { - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; - struct extent_map *em = NULL; - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; + struct extent_map *em; int ret = 1; + bool next_mergeable = true; /* * make sure that once we start defragging an extent, we keep on @@ -828,23 +847,9 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len, *skip = 0; - /* - * hopefully we have this extent in the tree already, try without - * the full extent lock - */ - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, start, len); - read_unlock(&em_tree->lock); - - if (!em) { - /* get the big lock and read metadata off disk */ - lock_extent(io_tree, start, start + len - 1); - em = btrfs_get_extent(inode, NULL, 0, start, len, 0); - unlock_extent(io_tree, start, start + len - 1); - - if (IS_ERR(em)) - return 0; - } + em = defrag_lookup_extent(inode, start); + if (!em) + return 0; /* this will cover holes, and inline extents */ if (em->block_start >= EXTENT_MAP_LAST_BYTE) { @@ -852,18 +857,15 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len, goto out; } - /* If we have nothing to merge with us, just skip. */ - if (check_adjacent_extents(inode, em)) { - ret = 0; - goto out; - } + next_mergeable = defrag_check_next_extent(inode, em); /* - * we hit a real extent, if it is big don't bother defragging it again + * we hit a real extent, if it is big or the next extent is not a + * real extent, don't bother defragging it */ - if ((*last_len == 0 || *last_len >= thresh) && em->len >= thresh) + if ((*last_len == 0 || *last_len >= thresh) && + (em->len >= thresh || !next_mergeable)) ret = 0; - out: /* * last_len ends up being a counter of how many bytes we've defragged. @@ -1142,8 +1144,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, break; if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT, - PAGE_CACHE_SIZE, extent_thresh, - &last_len, &skip, &defrag_end)) { + extent_thresh, &last_len, &skip, + &defrag_end)) { unsigned long next; /* * the should_defrag function tells us how much to skip @@ -1304,6 +1306,14 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, ret = -EINVAL; goto out_free; } + if (device->fs_devices && device->fs_devices->seeding) { + printk(KERN_INFO "btrfs: resizer unable to apply on " + "seeding device %llu\n", + (unsigned long long)devid); + ret = -EINVAL; + goto out_free; + } + if (!strcmp(sizestr, "max")) new_size = device->bdev->bd_inode->i_size; else { @@ -1345,8 +1355,9 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, do_div(new_size, root->sectorsize); new_size *= root->sectorsize; - printk(KERN_INFO "btrfs: new size for %s is %llu\n", - device->name, (unsigned long long)new_size); + printk_in_rcu(KERN_INFO "btrfs: new size for %s is %llu\n", + rcu_str_deref(device->name), + (unsigned long long)new_size); if (new_size > old_size) { trans = btrfs_start_transaction(root, 0); @@ -2264,7 +2275,12 @@ static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg) di_args->total_bytes = dev->total_bytes; memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid)); if (dev->name) { - strncpy(di_args->path, dev->name, sizeof(di_args->path)); + struct rcu_string *name; + + rcu_read_lock(); + name = rcu_dereference(dev->name); + strncpy(di_args->path, name->str, sizeof(di_args->path)); + rcu_read_unlock(); di_args->path[sizeof(di_args->path) - 1] = 0; } else { di_args->path[0] = '\0'; @@ -3252,7 +3268,7 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg) if (fs_info->sb->s_flags & MS_RDONLY) return -EROFS; - ret = mnt_want_write(file->f_path.mnt); + ret = mnt_want_write_file(file); if (ret) return ret; @@ -3322,7 +3338,7 @@ out_bargs: out: mutex_unlock(&fs_info->balance_mutex); mutex_unlock(&fs_info->volume_mutex); - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); return ret; } diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 497c530..e440aa6 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -339,7 +339,7 @@ struct btrfs_ioctl_get_dev_stats { #define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64) #define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \ struct btrfs_ioctl_vol_args_v2) -#define BTRFS_IOC_SUBVOL_GETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 25, __u64) +#define BTRFS_IOC_SUBVOL_GETFLAGS _IOR(BTRFS_IOCTL_MAGIC, 25, __u64) #define BTRFS_IOC_SUBVOL_SETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 26, __u64) #define BTRFS_IOC_SCRUB _IOWR(BTRFS_IOCTL_MAGIC, 27, \ struct btrfs_ioctl_scrub_args) diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 9e138cd..643335a 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -627,7 +627,27 @@ void btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) /* start IO across the range first to instantiate any delalloc * extents */ - filemap_write_and_wait_range(inode->i_mapping, start, orig_end); + filemap_fdatawrite_range(inode->i_mapping, start, orig_end); + + /* + * So with compression we will find and lock a dirty page and clear the + * first one as dirty, setup an async extent, and immediately return + * with the entire range locked but with nobody actually marked with + * writeback. So we can't just filemap_write_and_wait_range() and + * expect it to work since it will just kick off a thread to do the + * actual work. So we need to call filemap_fdatawrite_range _again_ + * since it will wait on the page lock, which won't be unlocked until + * after the pages have been marked as writeback and so we're good to go + * from there. We have to do this otherwise we'll miss the ordered + * extents and that results in badness. Please Josef, do not think you + * know better and pull this out at some point in the future, it is + * right and you are wrong. + */ + if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, + &BTRFS_I(inode)->runtime_flags)) + filemap_fdatawrite_range(inode->i_mapping, start, orig_end); + + filemap_fdatawait_range(inode->i_mapping, start, orig_end); end = orig_end; found = 0; diff --git a/fs/btrfs/rcu-string.h b/fs/btrfs/rcu-string.h new file mode 100644 index 0000000..9e111e4 --- /dev/null +++ b/fs/btrfs/rcu-string.h @@ -0,0 +1,56 @@ +/* + * Copyright (C) 2012 Red Hat. All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +struct rcu_string { + struct rcu_head rcu; + char str[0]; +}; + +static inline struct rcu_string *rcu_string_strdup(const char *src, gfp_t mask) +{ + size_t len = strlen(src) + 1; + struct rcu_string *ret = kzalloc(sizeof(struct rcu_string) + + (len * sizeof(char)), mask); + if (!ret) + return ret; + strncpy(ret->str, src, len); + return ret; +} + +static inline void rcu_string_free(struct rcu_string *str) +{ + if (str) + kfree_rcu(str, rcu); +} + +#define printk_in_rcu(fmt, ...) do { \ + rcu_read_lock(); \ + printk(fmt, __VA_ARGS__); \ + rcu_read_unlock(); \ +} while (0) + +#define printk_ratelimited_in_rcu(fmt, ...) do { \ + rcu_read_lock(); \ + printk_ratelimited(fmt, __VA_ARGS__); \ + rcu_read_unlock(); \ +} while (0) + +#define rcu_str_deref(rcu_str) ({ \ + struct rcu_string *__str = rcu_dereference(rcu_str); \ + __str->str; \ +}) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index a38cfa4..b223620 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -26,6 +26,7 @@ #include "backref.h" #include "extent_io.h" #include "check-integrity.h" +#include "rcu-string.h" /* * This is only the first step towards a full-features scrub. It reads all @@ -320,10 +321,10 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx) * hold all of the paths here */ for (i = 0; i < ipath->fspath->elem_cnt; ++i) - printk(KERN_WARNING "btrfs: %s at logical %llu on dev " + printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev " "%s, sector %llu, root %llu, inode %llu, offset %llu, " "length %llu, links %u (path: %s)\n", swarn->errstr, - swarn->logical, swarn->dev->name, + swarn->logical, rcu_str_deref(swarn->dev->name), (unsigned long long)swarn->sector, root, inum, offset, min(isize - offset, (u64)PAGE_SIZE), nlink, (char *)(unsigned long)ipath->fspath->val[i]); @@ -332,10 +333,10 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx) return 0; err: - printk(KERN_WARNING "btrfs: %s at logical %llu on dev " + printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev " "%s, sector %llu, root %llu, inode %llu, offset %llu: path " "resolving failed with ret=%d\n", swarn->errstr, - swarn->logical, swarn->dev->name, + swarn->logical, rcu_str_deref(swarn->dev->name), (unsigned long long)swarn->sector, root, inum, offset, ret); free_ipath(ipath); @@ -390,10 +391,11 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock) do { ret = tree_backref_for_extent(&ptr, eb, ei, item_size, &ref_root, &ref_level); - printk(KERN_WARNING + printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev %s, " "sector %llu: metadata %s (level %d) in tree " - "%llu\n", errstr, swarn.logical, dev->name, + "%llu\n", errstr, swarn.logical, + rcu_str_deref(dev->name), (unsigned long long)swarn.sector, ref_level ? "node" : "leaf", ret < 0 ? -1 : ref_level, @@ -580,9 +582,11 @@ out: spin_lock(&sdev->stat_lock); ++sdev->stat.uncorrectable_errors; spin_unlock(&sdev->stat_lock); - printk_ratelimited(KERN_ERR + + printk_ratelimited_in_rcu(KERN_ERR "btrfs: unable to fixup (nodatasum) error at logical %llu on dev %s\n", - (unsigned long long)fixup->logical, sdev->dev->name); + (unsigned long long)fixup->logical, + rcu_str_deref(sdev->dev->name)); } btrfs_free_path(path); @@ -936,18 +940,20 @@ corrected_error: spin_lock(&sdev->stat_lock); sdev->stat.corrected_errors++; spin_unlock(&sdev->stat_lock); - printk_ratelimited(KERN_ERR + printk_ratelimited_in_rcu(KERN_ERR "btrfs: fixed up error at logical %llu on dev %s\n", - (unsigned long long)logical, sdev->dev->name); + (unsigned long long)logical, + rcu_str_deref(sdev->dev->name)); } } else { did_not_correct_error: spin_lock(&sdev->stat_lock); sdev->stat.uncorrectable_errors++; spin_unlock(&sdev->stat_lock); - printk_ratelimited(KERN_ERR + printk_ratelimited_in_rcu(KERN_ERR "btrfs: unable to fixup (regular) error at logical %llu on dev %s\n", - (unsigned long long)logical, sdev->dev->name); + (unsigned long long)logical, + rcu_str_deref(sdev->dev->name)); } out: diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 96eb9fe..b19d755 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -54,6 +54,7 @@ #include "version.h" #include "export.h" #include "compression.h" +#include "rcu-string.h" #define CREATE_TRACE_POINTS #include <trace/events/btrfs.h> @@ -1067,7 +1068,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } bdev = fs_devices->latest_bdev; - s = sget(fs_type, btrfs_test_super, btrfs_set_super, fs_info); + s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC, + fs_info); if (IS_ERR(s)) { error = PTR_ERR(s); goto error_close_devices; @@ -1081,7 +1083,6 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } else { char b[BDEVNAME_SIZE]; - s->s_flags = flags | MS_NOSEC; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); btrfs_sb(s)->bdev_holder = fs_type; error = btrfs_fill_super(s, fs_devices, data, @@ -1186,6 +1187,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; + ret = btrfs_resume_balance_async(fs_info); + if (ret) + goto restore; + sb->s_flags &= ~MS_RDONLY; } @@ -1482,12 +1487,44 @@ static void btrfs_fs_dirty_inode(struct inode *inode, int flags) "error %d\n", btrfs_ino(inode), ret); } +static int btrfs_show_devname(struct seq_file *m, struct dentry *root) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb); + struct btrfs_fs_devices *cur_devices; + struct btrfs_device *dev, *first_dev = NULL; + struct list_head *head; + struct rcu_string *name; + + mutex_lock(&fs_info->fs_devices->device_list_mutex); + cur_devices = fs_info->fs_devices; + while (cur_devices) { + head = &cur_devices->devices; + list_for_each_entry(dev, head, dev_list) { + if (!first_dev || dev->devid < first_dev->devid) + first_dev = dev; + } + cur_devices = cur_devices->seed; + } + + if (first_dev) { + rcu_read_lock(); + name = rcu_dereference(first_dev->name); + seq_escape(m, name->str, " \t\n\\"); + rcu_read_unlock(); + } else { + WARN_ON(1); + } + mutex_unlock(&fs_info->fs_devices->device_list_mutex); + return 0; +} + static const struct super_operations btrfs_super_ops = { .drop_inode = btrfs_drop_inode, .evict_inode = btrfs_evict_inode, .put_super = btrfs_put_super, .sync_fs = btrfs_sync_fs, .show_options = btrfs_show_options, + .show_devname = btrfs_show_devname, .write_inode = btrfs_write_inode, .dirty_inode = btrfs_fs_dirty_inode, .alloc_inode = btrfs_alloc_inode, diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 1791c6e..b72b068 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -100,6 +100,10 @@ loop: kmem_cache_free(btrfs_transaction_cachep, cur_trans); cur_trans = fs_info->running_transaction; goto loop; + } else if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) { + spin_unlock(&root->fs_info->trans_lock); + kmem_cache_free(btrfs_transaction_cachep, cur_trans); + return -EROFS; } atomic_set(&cur_trans->num_writers, 1); @@ -1213,14 +1217,20 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, static void cleanup_transaction(struct btrfs_trans_handle *trans, - struct btrfs_root *root) + struct btrfs_root *root, int err) { struct btrfs_transaction *cur_trans = trans->transaction; WARN_ON(trans->use_count > 1); + btrfs_abort_transaction(trans, root, err); + spin_lock(&root->fs_info->trans_lock); list_del_init(&cur_trans->list); + if (cur_trans == root->fs_info->running_transaction) { + root->fs_info->running_transaction = NULL; + root->fs_info->trans_no_join = 0; + } spin_unlock(&root->fs_info->trans_lock); btrfs_cleanup_one_transaction(trans->transaction, root); @@ -1526,7 +1536,7 @@ cleanup_transaction: // WARN_ON(1); if (current->journal_info == trans) current->journal_info = NULL; - cleanup_transaction(trans, root); + cleanup_transaction(trans, root, ret); return ret; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2017d0f..8abeae4 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -690,6 +690,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, kfree(name); iput(inode); + + btrfs_run_delayed_items(trans, root); return ret; } @@ -895,6 +897,7 @@ again: ret = btrfs_unlink_inode(trans, root, dir, inode, victim_name, victim_name_len); + btrfs_run_delayed_items(trans, root); } kfree(victim_name); ptr = (unsigned long)(victim_ref + 1) + victim_name_len; @@ -1475,6 +1478,9 @@ again: ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len); BUG_ON(ret); + + btrfs_run_delayed_items(trans, root); + kfree(name); iput(inode); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 7782020..ecaad40 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -35,6 +35,7 @@ #include "volumes.h" #include "async-thread.h" #include "check-integrity.h" +#include "rcu-string.h" static int init_first_rw_device(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -64,7 +65,7 @@ static void free_fs_devices(struct btrfs_fs_devices *fs_devices) device = list_entry(fs_devices->devices.next, struct btrfs_device, dev_list); list_del(&device->dev_list); - kfree(device->name); + rcu_string_free(device->name); kfree(device); } kfree(fs_devices); @@ -334,8 +335,8 @@ static noinline int device_list_add(const char *path, { struct btrfs_device *device; struct btrfs_fs_devices *fs_devices; + struct rcu_string *name; u64 found_transid = btrfs_super_generation(disk_super); - char *name; fs_devices = find_fsid(disk_super->fsid); if (!fs_devices) { @@ -369,11 +370,13 @@ static noinline int device_list_add(const char *path, memcpy(device->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE); spin_lock_init(&device->io_lock); - device->name = kstrdup(path, GFP_NOFS); - if (!device->name) { + + name = rcu_string_strdup(path, GFP_NOFS); + if (!name) { kfree(device); return -ENOMEM; } + rcu_assign_pointer(device->name, name); INIT_LIST_HEAD(&device->dev_alloc_list); /* init readahead state */ @@ -390,12 +393,12 @@ static noinline int device_list_add(const char *path, device->fs_devices = fs_devices; fs_devices->num_devices++; - } else if (!device->name || strcmp(device->name, path)) { - name = kstrdup(path, GFP_NOFS); + } else if (!device->name || strcmp(device->name->str, path)) { + name = rcu_string_strdup(path, GFP_NOFS); if (!name) return -ENOMEM; - kfree(device->name); - device->name = name; + rcu_string_free(device->name); + rcu_assign_pointer(device->name, name); if (device->missing) { fs_devices->missing_devices--; device->missing = 0; @@ -430,15 +433,22 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig) /* We have held the volume lock, it is safe to get the devices. */ list_for_each_entry(orig_dev, &orig->devices, dev_list) { + struct rcu_string *name; + device = kzalloc(sizeof(*device), GFP_NOFS); if (!device) goto error; - device->name = kstrdup(orig_dev->name, GFP_NOFS); - if (!device->name) { + /* + * This is ok to do without rcu read locked because we hold the + * uuid mutex so nothing we touch in here is going to disappear. + */ + name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS); + if (!name) { kfree(device); goto error; } + rcu_assign_pointer(device->name, name); device->devid = orig_dev->devid; device->work.func = pending_bios_fn; @@ -491,7 +501,7 @@ again: } list_del_init(&device->dev_list); fs_devices->num_devices--; - kfree(device->name); + rcu_string_free(device->name); kfree(device); } @@ -516,7 +526,7 @@ static void __free_device(struct work_struct *work) if (device->bdev) blkdev_put(device->bdev, device->mode); - kfree(device->name); + rcu_string_free(device->name); kfree(device); } @@ -540,6 +550,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) mutex_lock(&fs_devices->device_list_mutex); list_for_each_entry(device, &fs_devices->devices, dev_list) { struct btrfs_device *new_device; + struct rcu_string *name; if (device->bdev) fs_devices->open_devices--; @@ -555,8 +566,11 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) new_device = kmalloc(sizeof(*new_device), GFP_NOFS); BUG_ON(!new_device); /* -ENOMEM */ memcpy(new_device, device, sizeof(*new_device)); - new_device->name = kstrdup(device->name, GFP_NOFS); - BUG_ON(device->name && !new_device->name); /* -ENOMEM */ + + /* Safe because we are under uuid_mutex */ + name = rcu_string_strdup(device->name->str, GFP_NOFS); + BUG_ON(device->name && !name); /* -ENOMEM */ + rcu_assign_pointer(new_device->name, name); new_device->bdev = NULL; new_device->writeable = 0; new_device->in_fs_metadata = 0; @@ -621,9 +635,9 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, if (!device->name) continue; - bdev = blkdev_get_by_path(device->name, flags, holder); + bdev = blkdev_get_by_path(device->name->str, flags, holder); if (IS_ERR(bdev)) { - printk(KERN_INFO "open %s failed\n", device->name); + printk(KERN_INFO "open %s failed\n", device->name->str); goto error; } filemap_write_and_wait(bdev->bd_inode->i_mapping); @@ -1632,6 +1646,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) struct block_device *bdev; struct list_head *devices; struct super_block *sb = root->fs_info->sb; + struct rcu_string *name; u64 total_bytes; int seeding_dev = 0; int ret = 0; @@ -1671,23 +1686,24 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) goto error; } - device->name = kstrdup(device_path, GFP_NOFS); - if (!device->name) { + name = rcu_string_strdup(device_path, GFP_NOFS); + if (!name) { kfree(device); ret = -ENOMEM; goto error; } + rcu_assign_pointer(device->name, name); ret = find_next_devid(root, &device->devid); if (ret) { - kfree(device->name); + rcu_string_free(device->name); kfree(device); goto error; } trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { - kfree(device->name); + rcu_string_free(device->name); kfree(device); ret = PTR_ERR(trans); goto error; @@ -1796,7 +1812,7 @@ error_trans: unlock_chunks(root); btrfs_abort_transaction(trans, root, ret); btrfs_end_transaction(trans, root); - kfree(device->name); + rcu_string_free(device->name); kfree(device); error: blkdev_put(bdev, FMODE_EXCL); @@ -2829,31 +2845,48 @@ out: static int balance_kthread(void *data) { - struct btrfs_balance_control *bctl = - (struct btrfs_balance_control *)data; - struct btrfs_fs_info *fs_info = bctl->fs_info; + struct btrfs_fs_info *fs_info = data; int ret = 0; mutex_lock(&fs_info->volume_mutex); mutex_lock(&fs_info->balance_mutex); - set_balance_control(bctl); - - if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) { - printk(KERN_INFO "btrfs: force skipping balance\n"); - } else { + if (fs_info->balance_ctl) { printk(KERN_INFO "btrfs: continuing balance\n"); - ret = btrfs_balance(bctl, NULL); + ret = btrfs_balance(fs_info->balance_ctl, NULL); } mutex_unlock(&fs_info->balance_mutex); mutex_unlock(&fs_info->volume_mutex); + return ret; } -int btrfs_recover_balance(struct btrfs_root *tree_root) +int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info) { struct task_struct *tsk; + + spin_lock(&fs_info->balance_lock); + if (!fs_info->balance_ctl) { + spin_unlock(&fs_info->balance_lock); + return 0; + } + spin_unlock(&fs_info->balance_lock); + + if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) { + printk(KERN_INFO "btrfs: force skipping balance\n"); + return 0; + } + + tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance"); + if (IS_ERR(tsk)) + return PTR_ERR(tsk); + + return 0; +} + +int btrfs_recover_balance(struct btrfs_fs_info *fs_info) +{ struct btrfs_balance_control *bctl; struct btrfs_balance_item *item; struct btrfs_disk_balance_args disk_bargs; @@ -2866,29 +2899,30 @@ int btrfs_recover_balance(struct btrfs_root *tree_root) if (!path) return -ENOMEM; - bctl = kzalloc(sizeof(*bctl), GFP_NOFS); - if (!bctl) { - ret = -ENOMEM; - goto out; - } - key.objectid = BTRFS_BALANCE_OBJECTID; key.type = BTRFS_BALANCE_ITEM_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0); + ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); if (ret < 0) - goto out_bctl; + goto out; if (ret > 0) { /* ret = -ENOENT; */ ret = 0; - goto out_bctl; + goto out; + } + + bctl = kzalloc(sizeof(*bctl), GFP_NOFS); + if (!bctl) { + ret = -ENOMEM; + goto out; } leaf = path->nodes[0]; item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item); - bctl->fs_info = tree_root->fs_info; - bctl->flags = btrfs_balance_flags(leaf, item) | BTRFS_BALANCE_RESUME; + bctl->fs_info = fs_info; + bctl->flags = btrfs_balance_flags(leaf, item); + bctl->flags |= BTRFS_BALANCE_RESUME; btrfs_balance_data(leaf, item, &disk_bargs); btrfs_disk_balance_args_to_cpu(&bctl->data, &disk_bargs); @@ -2897,14 +2931,13 @@ int btrfs_recover_balance(struct btrfs_root *tree_root) btrfs_balance_sys(leaf, item, &disk_bargs); btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs); - tsk = kthread_run(balance_kthread, bctl, "btrfs-balance"); - if (IS_ERR(tsk)) - ret = PTR_ERR(tsk); - else - goto out; + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); -out_bctl: - kfree(bctl); + set_balance_control(bctl); + + mutex_unlock(&fs_info->balance_mutex); + mutex_unlock(&fs_info->volume_mutex); out: btrfs_free_path(path); return ret; @@ -4045,16 +4078,18 @@ static void btrfs_end_bio(struct bio *bio, int err) BUG_ON(stripe_index >= bbio->num_stripes); dev = bbio->stripes[stripe_index].dev; - if (bio->bi_rw & WRITE) - btrfs_dev_stat_inc(dev, - BTRFS_DEV_STAT_WRITE_ERRS); - else - btrfs_dev_stat_inc(dev, - BTRFS_DEV_STAT_READ_ERRS); - if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH) - btrfs_dev_stat_inc(dev, - BTRFS_DEV_STAT_FLUSH_ERRS); - btrfs_dev_stat_print_on_error(dev); + if (dev->bdev) { + if (bio->bi_rw & WRITE) + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_WRITE_ERRS); + else + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_READ_ERRS); + if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH) + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_FLUSH_ERRS); + btrfs_dev_stat_print_on_error(dev); + } } } @@ -4204,10 +4239,17 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, bio->bi_sector = bbio->stripes[dev_nr].physical >> 9; dev = bbio->stripes[dev_nr].dev; if (dev && dev->bdev && (rw != WRITE || dev->writeable)) { +#ifdef DEBUG + struct rcu_string *name; + + rcu_read_lock(); + name = rcu_dereference(dev->name); pr_debug("btrfs_map_bio: rw %d, secor=%llu, dev=%lu " "(%s id %llu), size=%u\n", rw, (u64)bio->bi_sector, (u_long)dev->bdev->bd_dev, - dev->name, dev->devid, bio->bi_size); + name->str, dev->devid, bio->bi_size); + rcu_read_unlock(); +#endif bio->bi_bdev = dev->bdev; if (async_submit) schedule_bio(root, dev, rw, bio); @@ -4694,8 +4736,9 @@ int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info) key.offset = device->devid; ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0); if (ret) { - printk(KERN_WARNING "btrfs: no dev_stats entry found for device %s (devid %llu) (OK on first mount after mkfs)\n", - device->name, (unsigned long long)device->devid); + printk_in_rcu(KERN_WARNING "btrfs: no dev_stats entry found for device %s (devid %llu) (OK on first mount after mkfs)\n", + rcu_str_deref(device->name), + (unsigned long long)device->devid); __btrfs_reset_dev_stats(device); device->dev_stats_valid = 1; btrfs_release_path(path); @@ -4747,8 +4790,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, BUG_ON(!path); ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1); if (ret < 0) { - printk(KERN_WARNING "btrfs: error %d while searching for dev_stats item for device %s!\n", - ret, device->name); + printk_in_rcu(KERN_WARNING "btrfs: error %d while searching for dev_stats item for device %s!\n", + ret, rcu_str_deref(device->name)); goto out; } @@ -4757,8 +4800,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, /* need to delete old one and insert a new one */ ret = btrfs_del_item(trans, dev_root, path); if (ret != 0) { - printk(KERN_WARNING "btrfs: delete too small dev_stats item for device %s failed %d!\n", - device->name, ret); + printk_in_rcu(KERN_WARNING "btrfs: delete too small dev_stats item for device %s failed %d!\n", + rcu_str_deref(device->name), ret); goto out; } ret = 1; @@ -4770,8 +4813,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, ret = btrfs_insert_empty_item(trans, dev_root, path, &key, sizeof(*ptr)); if (ret < 0) { - printk(KERN_WARNING "btrfs: insert dev_stats item for device %s failed %d!\n", - device->name, ret); + printk_in_rcu(KERN_WARNING "btrfs: insert dev_stats item for device %s failed %d!\n", + rcu_str_deref(device->name), ret); goto out; } } @@ -4823,9 +4866,9 @@ void btrfs_dev_stat_print_on_error(struct btrfs_device *dev) { if (!dev->dev_stats_valid) return; - printk_ratelimited(KERN_ERR + printk_ratelimited_in_rcu(KERN_ERR "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", - dev->name, + rcu_str_deref(dev->name), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_FLUSH_ERRS), @@ -4837,8 +4880,8 @@ void btrfs_dev_stat_print_on_error(struct btrfs_device *dev) static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev) { - printk(KERN_INFO "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", - dev->name, + printk_in_rcu(KERN_INFO "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", + rcu_str_deref(dev->name), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_FLUSH_ERRS), diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 3406a88..95f6637 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -58,7 +58,7 @@ struct btrfs_device { /* the mode sent to blkdev_get */ fmode_t mode; - char *name; + struct rcu_string *name; /* the internal btrfs device id */ u64 devid; @@ -281,7 +281,8 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size); int btrfs_init_new_device(struct btrfs_root *root, char *path); int btrfs_balance(struct btrfs_balance_control *bctl, struct btrfs_ioctl_balance_args *bargs); -int btrfs_recover_balance(struct btrfs_root *tree_root); +int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info); +int btrfs_recover_balance(struct btrfs_fs_info *fs_info); int btrfs_pause_balance(struct btrfs_fs_info *fs_info); int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); diff --git a/fs/buffer.c b/fs/buffer.c index 838a9cf..c7062c8 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1036,6 +1036,9 @@ grow_buffers(struct block_device *bdev, sector_t block, int size) static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, int size) { + int ret; + struct buffer_head *bh; + /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { @@ -1048,20 +1051,21 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) return NULL; } - for (;;) { - struct buffer_head * bh; - int ret; +retry: + bh = __find_get_block(bdev, block, size); + if (bh) + return bh; + ret = grow_buffers(bdev, block, size); + if (ret == 0) { + free_more_memory(); + goto retry; + } else if (ret > 0) { bh = __find_get_block(bdev, block, size); if (bh) return bh; - - ret = grow_buffers(bdev, block, size); - if (ret < 0) - return NULL; - if (ret == 0) - free_more_memory(); } + return NULL; } /* diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 7f0771d..b0b5f7c 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -567,7 +567,7 @@ lookup_again: if (ret < 0) goto create_error; start = jiffies; - ret = vfs_create(dir->d_inode, next, S_IFREG, NULL); + ret = vfs_create(dir->d_inode, next, S_IFREG, true); cachefiles_hist(cachefiles_create_histogram, start); if (ret < 0) goto create_error; diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 0e3c092..c0353df 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -891,6 +891,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) struct cachefiles_cache *cache; mm_segment_t old_fs; struct file *file; + struct path path; loff_t pos, eof; size_t len; void *data; @@ -916,10 +917,9 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) /* write the page to the backing filesystem and let it store it in its * own time */ - dget(object->backer); - mntget(cache->mnt); - file = dentry_open(object->backer, cache->mnt, O_RDWR, - cache->cache_cred); + path.mnt = cache->mnt; + path.dentry = object->backer; + file = dentry_open(&path, O_RDWR, cache->cache_cred); if (IS_ERR(file)) { ret = PTR_ERR(file); } else { diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 173b1d2..8b67304 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -54,7 +54,12 @@ (CONGESTION_ON_THRESH(congestion_kb) - \ (CONGESTION_ON_THRESH(congestion_kb) >> 2)) - +static inline struct ceph_snap_context *page_snap_context(struct page *page) +{ + if (PagePrivate(page)) + return (void *)page->private; + return NULL; +} /* * Dirty a page. Optimistically adjust accounting, on the assumption @@ -142,10 +147,9 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset) { struct inode *inode; struct ceph_inode_info *ci; - struct ceph_snap_context *snapc = (void *)page->private; + struct ceph_snap_context *snapc = page_snap_context(page); BUG_ON(!PageLocked(page)); - BUG_ON(!page->private); BUG_ON(!PagePrivate(page)); BUG_ON(!page->mapping); @@ -182,7 +186,6 @@ static int ceph_releasepage(struct page *page, gfp_t g) struct inode *inode = page->mapping ? page->mapping->host : NULL; dout("%p releasepage %p idx %lu\n", inode, page, page->index); WARN_ON(PageDirty(page)); - WARN_ON(page->private); WARN_ON(PagePrivate(page)); return 0; } @@ -443,7 +446,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) osdc = &fsc->client->osdc; /* verify this is a writeable snap context */ - snapc = (void *)page->private; + snapc = page_snap_context(page); if (snapc == NULL) { dout("writepage %p page %p not dirty?\n", inode, page); goto out; @@ -451,7 +454,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) oldest = get_oldest_context(inode, &snap_size); if (snapc->seq > oldest->seq) { dout("writepage %p page %p snapc %p not writeable - noop\n", - inode, page, (void *)page->private); + inode, page, snapc); /* we should only noop if called by kswapd */ WARN_ON((current->flags & PF_MEMALLOC) == 0); ceph_put_snap_context(oldest); @@ -591,7 +594,7 @@ static void writepages_finish(struct ceph_osd_request *req, clear_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC); - ceph_put_snap_context((void *)page->private); + ceph_put_snap_context(page_snap_context(page)); page->private = 0; ClearPagePrivate(page); dout("unlocking %d %p\n", i, page); @@ -795,7 +798,7 @@ get_more_pages: } /* only if matching snap context */ - pgsnapc = (void *)page->private; + pgsnapc = page_snap_context(page); if (pgsnapc->seq > snapc->seq) { dout("page snapc %p %lld > oldest %p %lld\n", pgsnapc, pgsnapc->seq, snapc, snapc->seq); @@ -984,7 +987,7 @@ retry_locked: BUG_ON(!ci->i_snap_realm); down_read(&mdsc->snap_rwsem); BUG_ON(!ci->i_snap_realm->cached_context); - snapc = (void *)page->private; + snapc = page_snap_context(page); if (snapc && snapc != ci->i_head_snapc) { /* * this page is already dirty in another (older) snap diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 3e8094b..00894ff 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -576,7 +576,7 @@ static int is_root_ceph_dentry(struct inode *inode, struct dentry *dentry) * the MDS so that it gets our 'caps wanted' value in a single op. */ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); struct ceph_mds_client *mdsc = fsc->mdsc; @@ -594,14 +594,6 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, if (err < 0) return ERR_PTR(err); - /* open (but not create!) intent? */ - if (nd && - (nd->flags & LOOKUP_OPEN) && - !(nd->intent.open.flags & O_CREAT)) { - int mode = nd->intent.open.create_mode & ~current->fs->umask; - return ceph_lookup_open(dir, dentry, nd, mode, 1); - } - /* can we conclude ENOENT locally? */ if (dentry->d_inode == NULL) { struct ceph_inode_info *ci = ceph_inode(dir); @@ -642,13 +634,51 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, return dentry; } +int ceph_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned flags, umode_t mode, + int *opened) +{ + int err; + struct dentry *res = NULL; + + if (!(flags & O_CREAT)) { + if (dentry->d_name.len > NAME_MAX) + return -ENAMETOOLONG; + + err = ceph_init_dentry(dentry); + if (err < 0) + return err; + + return ceph_lookup_open(dir, dentry, file, flags, mode, opened); + } + + if (d_unhashed(dentry)) { + res = ceph_lookup(dir, dentry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + if (res) + dentry = res; + } + + /* We don't deal with positive dentries here */ + if (dentry->d_inode) + return finish_no_open(file, res); + + *opened |= FILE_CREATED; + err = ceph_lookup_open(dir, dentry, file, flags, mode, opened); + dput(res); + + return err; +} + /* * If we do a create but get no trace back from the MDS, follow up with * a lookup (the VFS expects us to link up the provided dentry). */ int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry) { - struct dentry *result = ceph_lookup(dir, dentry, NULL); + struct dentry *result = ceph_lookup(dir, dentry, 0); if (result && !IS_ERR(result)) { /* @@ -700,25 +730,9 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry, } static int ceph_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { - dout("create in dir %p dentry %p name '%.*s'\n", - dir, dentry, dentry->d_name.len, dentry->d_name.name); - - if (ceph_snap(dir) != CEPH_NOSNAP) - return -EROFS; - - if (nd) { - BUG_ON((nd->flags & LOOKUP_OPEN) == 0); - dentry = ceph_lookup_open(dir, dentry, nd, mode, 0); - /* hrm, what should i do here if we get aliased? */ - if (IS_ERR(dentry)) - return PTR_ERR(dentry); - return 0; - } - - /* fall back to mknod */ - return ceph_mknod(dir, dentry, (mode & ~S_IFMT) | S_IFREG, 0); + return ceph_mknod(dir, dentry, mode, 0); } static int ceph_symlink(struct inode *dir, struct dentry *dentry, @@ -1028,12 +1042,12 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry) /* * Check if cached dentry can be trusted. */ -static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd) +static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) { int valid = 0; struct inode *dir; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry, @@ -1080,7 +1094,7 @@ static void ceph_d_release(struct dentry *dentry) } static int ceph_snapdir_d_revalidate(struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { /* * Eventually, we'll want to revalidate snapped metadata @@ -1357,6 +1371,7 @@ const struct inode_operations ceph_dir_iops = { .rmdir = ceph_unlink, .rename = ceph_rename, .create = ceph_create, + .atomic_open = ceph_atomic_open, }; const struct dentry_operations ceph_dentry_ops = { diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 988d4f3..1b81d6c 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -213,22 +213,15 @@ out: * may_open() fails, the struct *file gets cleaned up (i.e. * ceph_release gets called). So fear not! */ -/* - * flags - * path_lookup_open -> LOOKUP_OPEN - * path_lookup_create -> LOOKUP_OPEN|LOOKUP_CREATE - */ -struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, - struct nameidata *nd, int mode, - int locked_dir) +int ceph_lookup_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned flags, umode_t mode, + int *opened) { struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); struct ceph_mds_client *mdsc = fsc->mdsc; - struct file *file; struct ceph_mds_request *req; struct dentry *ret; int err; - int flags = nd->intent.open.flags; dout("ceph_lookup_open dentry %p '%.*s' flags %d mode 0%o\n", dentry, dentry->d_name.len, dentry->d_name.name, flags, mode); @@ -236,7 +229,7 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, /* do the open */ req = prepare_open_request(dir->i_sb, flags, mode); if (IS_ERR(req)) - return ERR_CAST(req); + return PTR_ERR(req); req->r_dentry = dget(dentry); req->r_num_caps = 2; if (flags & O_CREAT) { @@ -254,14 +247,17 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, err = ceph_handle_notrace_create(dir, dentry); if (err) goto out; - file = lookup_instantiate_filp(nd, req->r_dentry, ceph_open); - if (IS_ERR(file)) - err = PTR_ERR(file); + err = finish_open(file, req->r_dentry, ceph_open, opened); out: ret = ceph_finish_lookup(req, dentry, err); ceph_mdsc_put_request(req); dout("ceph_lookup_open result=%p\n", ret); - return ret; + + if (IS_ERR(ret)) + return PTR_ERR(ret); + + dput(ret); + return err; } int ceph_release(struct inode *inode, struct file *file) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 1e67dd7..7076109 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -871,7 +871,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, if (ceph_test_opt(fsc->client, NOSHARE)) compare_super = NULL; - sb = sget(fs_type, compare_super, ceph_set_super, fsc); + sb = sget(fs_type, compare_super, ceph_set_super, flags, fsc); if (IS_ERR(sb)) { res = ERR_CAST(sb); goto out; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index fc35036..f4d5522 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -806,9 +806,9 @@ extern int ceph_copy_from_page_vector(struct page **pages, loff_t off, size_t len); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); extern int ceph_open(struct inode *inode, struct file *file); -extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, - struct nameidata *nd, int mode, - int locked_dir); +extern int ceph_lookup_open(struct inode *dir, struct dentry *dentry, + struct file *od, unsigned flags, + umode_t mode, int *opened); extern int ceph_release(struct inode *inode, struct file *filp); /* dir.c */ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8b6e344..a7610cf 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -257,7 +257,6 @@ cifs_alloc_inode(struct super_block *sb) static void cifs_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - INIT_LIST_HEAD(&inode->i_dentry); kmem_cache_free(cifs_inode_cachep, CIFS_I(inode)); } @@ -638,7 +637,10 @@ cifs_do_mount(struct file_system_type *fs_type, mnt_data.cifs_sb = cifs_sb; mnt_data.flags = flags; - sb = sget(fs_type, cifs_match_super, cifs_set_super, &mnt_data); + /* BB should we make this contingent on mount parm? */ + flags |= MS_NODIRATIME | MS_NOATIME; + + sb = sget(fs_type, cifs_match_super, cifs_set_super, flags, &mnt_data); if (IS_ERR(sb)) { root = ERR_CAST(sb); cifs_umount(cifs_sb); @@ -649,10 +651,6 @@ cifs_do_mount(struct file_system_type *fs_type, cFYI(1, "Use existing superblock"); cifs_umount(cifs_sb); } else { - sb->s_flags = flags; - /* BB should we make this contingent on mount parm? */ - sb->s_flags |= MS_NODIRATIME | MS_NOATIME; - rc = cifs_read_super(sb); if (rc) { root = ERR_PTR(rc); @@ -778,6 +776,7 @@ struct file_system_type cifs_fs_type = { }; const struct inode_operations cifs_dir_inode_ops = { .create = cifs_create, + .atomic_open = cifs_atomic_open, .lookup = cifs_lookup, .getattr = cifs_getattr, .unlink = cifs_unlink, diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 6536535..1c49c5a 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -45,9 +45,12 @@ extern const struct address_space_operations cifs_addr_ops_smallbuf; extern const struct inode_operations cifs_dir_inode_ops; extern struct inode *cifs_root_iget(struct super_block *); extern int cifs_create(struct inode *, struct dentry *, umode_t, - struct nameidata *); + bool excl); +extern int cifs_atomic_open(struct inode *, struct dentry *, + struct file *, unsigned, umode_t, + int *); extern struct dentry *cifs_lookup(struct inode *, struct dentry *, - struct nameidata *); + unsigned int); extern int cifs_unlink(struct inode *dir, struct dentry *dentry); extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *); extern int cifs_mknod(struct inode *, struct dentry *, umode_t, dev_t); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 20350a9..6df0cbe 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -174,6 +174,7 @@ struct smb_version_operations { void (*add_credits)(struct TCP_Server_Info *, const unsigned int); void (*set_credits)(struct TCP_Server_Info *, const int); int * (*get_credits_field)(struct TCP_Server_Info *); + __u64 (*get_next_mid)(struct TCP_Server_Info *); /* data offset from read response message */ unsigned int (*read_data_offset)(char *); /* data length from read response message */ @@ -399,6 +400,12 @@ set_credits(struct TCP_Server_Info *server, const int val) server->ops->set_credits(server, val); } +static inline __u64 +get_next_mid(struct TCP_Server_Info *server) +{ + return server->ops->get_next_mid(server); +} + /* * Macros to allow the TCP_Server_Info->net field and related code to drop out * when CONFIG_NET_NS isn't set. diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 5ec21ec..0a6cbfe 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -114,7 +114,6 @@ extern int small_smb_init_no_tc(const int smb_cmd, const int wct, void **request_buf); extern int CIFS_SessSetup(unsigned int xid, struct cifs_ses *ses, const struct nls_table *nls_cp); -extern __u64 GetNextMid(struct TCP_Server_Info *server); extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601); extern u64 cifs_UnixTimeToNT(struct timespec); extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index b5ad716..4ee522b 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -86,7 +86,31 @@ static struct { #endif /* CONFIG_CIFS_WEAK_PW_HASH */ #endif /* CIFS_POSIX */ -/* Forward declarations */ +#ifdef CONFIG_HIGHMEM +/* + * On arches that have high memory, kmap address space is limited. By + * serializing the kmap operations on those arches, we ensure that we don't + * end up with a bunch of threads in writeback with partially mapped page + * arrays, stuck waiting for kmap to come back. That situation prevents + * progress and can deadlock. + */ +static DEFINE_MUTEX(cifs_kmap_mutex); + +static inline void +cifs_kmap_lock(void) +{ + mutex_lock(&cifs_kmap_mutex); +} + +static inline void +cifs_kmap_unlock(void) +{ + mutex_unlock(&cifs_kmap_mutex); +} +#else /* !CONFIG_HIGHMEM */ +#define cifs_kmap_lock() do { ; } while(0) +#define cifs_kmap_unlock() do { ; } while(0) +#endif /* CONFIG_HIGHMEM */ /* Mark as invalid, all open files on tree connections since they were closed when session to server was lost */ @@ -268,7 +292,7 @@ small_smb_init_no_tc(const int smb_command, const int wct, return rc; buffer = (struct smb_hdr *)*request_buf; - buffer->Mid = GetNextMid(ses->server); + buffer->Mid = get_next_mid(ses->server); if (ses->capabilities & CAP_UNICODE) buffer->Flags2 |= SMBFLG2_UNICODE; if (ses->capabilities & CAP_STATUS32) @@ -402,7 +426,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifs_ses *ses) cFYI(1, "secFlags 0x%x", secFlags); - pSMB->hdr.Mid = GetNextMid(server); + pSMB->hdr.Mid = get_next_mid(server); pSMB->hdr.Flags2 |= (SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS); if ((secFlags & CIFSSEC_MUST_KRB5) == CIFSSEC_MUST_KRB5) @@ -782,7 +806,7 @@ CIFSSMBLogoff(const int xid, struct cifs_ses *ses) return rc; } - pSMB->hdr.Mid = GetNextMid(ses->server); + pSMB->hdr.Mid = get_next_mid(ses->server); if (ses->server->sec_mode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) @@ -1503,7 +1527,9 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) } /* marshal up the page array */ + cifs_kmap_lock(); len = rdata->marshal_iov(rdata, data_len); + cifs_kmap_unlock(); data_len -= len; /* issue the read if we have any iovecs left to fill */ @@ -2069,7 +2095,9 @@ cifs_async_writev(struct cifs_writedata *wdata) * and set the iov_len properly for each one. It may also set * wdata->bytes too. */ + cifs_kmap_lock(); wdata->marshal_iov(iov, wdata); + cifs_kmap_unlock(); cFYI(1, "async write at %llu %u bytes", wdata->offset, wdata->bytes); @@ -4762,7 +4790,7 @@ getDFSRetry: /* server pointer checked in called function, but should never be null here anyway */ - pSMB->hdr.Mid = GetNextMid(ses->server); + pSMB->hdr.Mid = get_next_mid(ses->server); pSMB->hdr.Tid = ses->ipc_tid; pSMB->hdr.Uid = ses->Suid; if (ses->capabilities & CAP_STATUS32) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ccafded..94b7788 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1058,13 +1058,15 @@ cifs_demultiplex_thread(void *p) if (mid_entry != NULL) { if (!mid_entry->multiRsp || mid_entry->multiEnd) mid_entry->callback(mid_entry); - } else if (!server->ops->is_oplock_break(buf, server)) { + } else if (!server->ops->is_oplock_break || + !server->ops->is_oplock_break(buf, server)) { cERROR(1, "No task to wake, unknown frame received! " "NumMids %d", atomic_read(&midCount)); cifs_dump_mem("Received Data is: ", buf, HEADER_SIZE(server)); #ifdef CONFIG_CIFS_DEBUG2 - server->ops->dump_detail(buf); + if (server->ops->dump_detail) + server->ops->dump_detail(buf); cifs_dump_mids(server); #endif /* CIFS_DEBUG2 */ @@ -1651,24 +1653,26 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, * If yes, we have encountered a double deliminator * reset the NULL character to the deliminator */ - if (tmp_end < end && tmp_end[1] == delim) + if (tmp_end < end && tmp_end[1] == delim) { tmp_end[0] = delim; - /* Keep iterating until we get to a single deliminator - * OR the end - */ - while ((tmp_end = strchr(tmp_end, delim)) != NULL && - (tmp_end[1] == delim)) { - tmp_end = (char *) &tmp_end[2]; - } + /* Keep iterating until we get to a single + * deliminator OR the end + */ + while ((tmp_end = strchr(tmp_end, delim)) + != NULL && (tmp_end[1] == delim)) { + tmp_end = (char *) &tmp_end[2]; + } - /* Reset var options to point to next element */ - if (tmp_end) { - tmp_end[0] = '\0'; - options = (char *) &tmp_end[1]; - } else - /* Reached the end of the mount option string */ - options = end; + /* Reset var options to point to next element */ + if (tmp_end) { + tmp_end[0] = '\0'; + options = (char *) &tmp_end[1]; + } else + /* Reached the end of the mount option + * string */ + options = end; + } /* Now build new password string */ temp_len = strlen(value); @@ -3441,6 +3445,18 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, #define CIFS_DEFAULT_NON_POSIX_RSIZE (60 * 1024) #define CIFS_DEFAULT_NON_POSIX_WSIZE (65536) +/* + * On hosts with high memory, we can't currently support wsize/rsize that are + * larger than we can kmap at once. Cap the rsize/wsize at + * LAST_PKMAP * PAGE_SIZE. We'll never be able to fill a read or write request + * larger than that anyway. + */ +#ifdef CONFIG_HIGHMEM +#define CIFS_KMAP_SIZE_LIMIT (LAST_PKMAP * PAGE_CACHE_SIZE) +#else /* CONFIG_HIGHMEM */ +#define CIFS_KMAP_SIZE_LIMIT (1<<24) +#endif /* CONFIG_HIGHMEM */ + static unsigned int cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) { @@ -3471,6 +3487,9 @@ cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) wsize = min_t(unsigned int, wsize, server->maxBuf - sizeof(WRITE_REQ) + 4); + /* limit to the amount that we can kmap at once */ + wsize = min_t(unsigned int, wsize, CIFS_KMAP_SIZE_LIMIT); + /* hard limit of CIFS_MAX_WSIZE */ wsize = min_t(unsigned int, wsize, CIFS_MAX_WSIZE); @@ -3491,18 +3510,15 @@ cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) * MS-CIFS indicates that servers are only limited by the client's * bufsize for reads, testing against win98se shows that it throws * INVALID_PARAMETER errors if you try to request too large a read. + * OS/2 just sends back short reads. * - * If the server advertises a MaxBufferSize of less than one page, - * assume that it also can't satisfy reads larger than that either. - * - * FIXME: Is there a better heuristic for this? + * If the server doesn't advertise CAP_LARGE_READ_X, then assume that + * it can't handle a read request larger than its MaxBufferSize either. */ if (tcon->unix_ext && (unix_cap & CIFS_UNIX_LARGE_READ_CAP)) defsize = CIFS_DEFAULT_IOSIZE; else if (server->capabilities & CAP_LARGE_READ_X) defsize = CIFS_DEFAULT_NON_POSIX_RSIZE; - else if (server->maxBuf >= PAGE_CACHE_SIZE) - defsize = CIFSMaxBufSize; else defsize = server->maxBuf - sizeof(READ_RSP); @@ -3515,6 +3531,9 @@ cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) if (!(server->capabilities & CAP_LARGE_READ_X)) rsize = min_t(unsigned int, CIFSMaxBufSize, rsize); + /* limit to the amount that we can kmap at once */ + rsize = min_t(unsigned int, rsize, CIFS_KMAP_SIZE_LIMIT); + /* hard limit of CIFS_MAX_RSIZE */ rsize = min_t(unsigned int, rsize, CIFS_MAX_RSIZE); @@ -3938,7 +3957,7 @@ CIFSTCon(unsigned int xid, struct cifs_ses *ses, header_assemble(smb_buffer, SMB_COM_TREE_CONNECT_ANDX, NULL /*no tid */ , 4 /*wct */ ); - smb_buffer->Mid = GetNextMid(ses->server); + smb_buffer->Mid = get_next_mid(ses->server); smb_buffer->Uid = ses->Suid; pSMB = (TCONX_REQ *) smb_buffer; pSMBr = (TCONX_RSP *) smb_buffer_response; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index ec4e9a2..a180265 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -133,108 +133,141 @@ cifs_bp_rename_retry: return full_path; } +/* + * Don't allow the separator character in a path component. + * The VFS will not allow "/", but "\" is allowed by posix. + */ +static int +check_name(struct dentry *direntry) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); + int i; + + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) { + for (i = 0; i < direntry->d_name.len; i++) { + if (direntry->d_name.name[i] == '\\') { + cFYI(1, "Invalid file name"); + return -EINVAL; + } + } + } + return 0; +} + + /* Inode operations in similar order to how they appear in Linux file fs.h */ -int -cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, - struct nameidata *nd) +static int cifs_do_create(struct inode *inode, struct dentry *direntry, + int xid, struct tcon_link *tlink, unsigned oflags, + umode_t mode, __u32 *oplock, __u16 *fileHandle, + int *created) { int rc = -ENOENT; - int xid; int create_options = CREATE_NOT_DIR; - __u32 oplock = 0; - int oflags; - /* - * BB below access is probably too much for mknod to request - * but we have to do query and setpathinfo so requesting - * less could fail (unless we want to request getatr and setatr - * permissions (only). At least for POSIX we do not have to - * request so much. - */ - int desiredAccess = GENERIC_READ | GENERIC_WRITE; - __u16 fileHandle; - struct cifs_sb_info *cifs_sb; - struct tcon_link *tlink; - struct cifs_tcon *tcon; + int desiredAccess; + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_tcon *tcon = tlink_tcon(tlink); char *full_path = NULL; FILE_ALL_INFO *buf = NULL; struct inode *newinode = NULL; - int disposition = FILE_OVERWRITE_IF; - - xid = GetXid(); - - cifs_sb = CIFS_SB(inode->i_sb); - tlink = cifs_sb_tlink(cifs_sb); - if (IS_ERR(tlink)) { - FreeXid(xid); - return PTR_ERR(tlink); - } - tcon = tlink_tcon(tlink); + int disposition; + *oplock = 0; if (tcon->ses->server->oplocks) - oplock = REQ_OPLOCK; - - if (nd) - oflags = nd->intent.open.file->f_flags; - else - oflags = O_RDONLY | O_CREAT; + *oplock = REQ_OPLOCK; full_path = build_path_from_dentry(direntry); if (full_path == NULL) { rc = -ENOMEM; - goto cifs_create_out; + goto out; } if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) && + !tcon->broken_posix_open && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { rc = cifs_posix_open(full_path, &newinode, - inode->i_sb, mode, oflags, &oplock, &fileHandle, xid); - /* EIO could indicate that (posix open) operation is not - supported, despite what server claimed in capability - negotiation. EREMOTE indicates DFS junction, which is not - handled in posix open */ - - if (rc == 0) { - if (newinode == NULL) /* query inode info */ + inode->i_sb, mode, oflags, oplock, fileHandle, xid); + switch (rc) { + case 0: + if (newinode == NULL) { + /* query inode info */ goto cifs_create_get_file_info; - else /* success, no need to query */ - goto cifs_create_set_dentry; - } else if ((rc != -EIO) && (rc != -EREMOTE) && - (rc != -EOPNOTSUPP) && (rc != -EINVAL)) - goto cifs_create_out; - /* else fallthrough to retry, using older open call, this is - case where server does not support this SMB level, and - falsely claims capability (also get here for DFS case - which should be rare for path not covered on files) */ - } + } + + if (!S_ISREG(newinode->i_mode)) { + /* + * The server may allow us to open things like + * FIFOs, but the client isn't set up to deal + * with that. If it's not a regular file, just + * close it and proceed as if it were a normal + * lookup. + */ + CIFSSMBClose(xid, tcon, *fileHandle); + goto cifs_create_get_file_info; + } + /* success, no need to query */ + goto cifs_create_set_dentry; + + case -ENOENT: + goto cifs_create_get_file_info; + + case -EIO: + case -EINVAL: + /* + * EIO could indicate that (posix open) operation is not + * supported, despite what server claimed in capability + * negotiation. + * + * POSIX open in samba versions 3.3.1 and earlier could + * incorrectly fail with invalid parameter. + */ + tcon->broken_posix_open = true; + break; + + case -EREMOTE: + case -EOPNOTSUPP: + /* + * EREMOTE indicates DFS junction, which is not handled + * in posix open. If either that or op not supported + * returned, follow the normal lookup. + */ + break; - if (nd) { - /* if the file is going to stay open, then we - need to set the desired access properly */ - desiredAccess = 0; - if (OPEN_FMODE(oflags) & FMODE_READ) - desiredAccess |= GENERIC_READ; /* is this too little? */ - if (OPEN_FMODE(oflags) & FMODE_WRITE) - desiredAccess |= GENERIC_WRITE; - - if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) - disposition = FILE_CREATE; - else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC)) - disposition = FILE_OVERWRITE_IF; - else if ((oflags & O_CREAT) == O_CREAT) - disposition = FILE_OPEN_IF; - else - cFYI(1, "Create flag not set in create function"); + default: + goto out; + } + /* + * fallthrough to retry, using older open call, this is case + * where server does not support this SMB level, and falsely + * claims capability (also get here for DFS case which should be + * rare for path not covered on files) + */ } + desiredAccess = 0; + if (OPEN_FMODE(oflags) & FMODE_READ) + desiredAccess |= GENERIC_READ; /* is this too little? */ + if (OPEN_FMODE(oflags) & FMODE_WRITE) + desiredAccess |= GENERIC_WRITE; + + disposition = FILE_OVERWRITE_IF; + if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) + disposition = FILE_CREATE; + else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC)) + disposition = FILE_OVERWRITE_IF; + else if ((oflags & O_CREAT) == O_CREAT) + disposition = FILE_OPEN_IF; + else + cFYI(1, "Create flag not set in create function"); + /* BB add processing to set equivalent of mode - e.g. via CreateX with ACLs */ buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); if (buf == NULL) { rc = -ENOMEM; - goto cifs_create_out; + goto out; } /* @@ -250,7 +283,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, if (tcon->ses->capabilities & CAP_NT_SMBS) rc = CIFSSMBOpen(xid, tcon, full_path, disposition, desiredAccess, create_options, - &fileHandle, &oplock, buf, cifs_sb->local_nls, + fileHandle, oplock, buf, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); else rc = -EIO; /* no NT SMB support fall into legacy open below */ @@ -259,17 +292,17 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, /* old server, retry the open legacy style */ rc = SMBLegacyOpen(xid, tcon, full_path, disposition, desiredAccess, create_options, - &fileHandle, &oplock, buf, cifs_sb->local_nls, + fileHandle, oplock, buf, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); } if (rc) { cFYI(1, "cifs_create returned 0x%x", rc); - goto cifs_create_out; + goto out; } /* If Open reported that we actually created a file then we now have to set the mode if possible */ - if ((tcon->unix_ext) && (oplock & CIFS_CREATE_ACTION)) { + if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) { struct cifs_unix_set_info_args args = { .mode = mode, .ctime = NO_CHANGE_64, @@ -278,6 +311,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, .device = 0, }; + *created |= FILE_CREATED; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { args.uid = (__u64) current_fsuid(); if (inode->i_mode & S_ISGID) @@ -288,7 +322,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, args.uid = NO_CHANGE_64; args.gid = NO_CHANGE_64; } - CIFSSMBUnixSetFileInfo(xid, tcon, &args, fileHandle, + CIFSSMBUnixSetFileInfo(xid, tcon, &args, *fileHandle, current->tgid); } else { /* BB implement mode setting via Windows security @@ -305,11 +339,11 @@ cifs_create_get_file_info: inode->i_sb, xid); else { rc = cifs_get_inode_info(&newinode, full_path, buf, - inode->i_sb, xid, &fileHandle); + inode->i_sb, xid, fileHandle); if (newinode) { if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) newinode->i_mode = mode; - if ((oplock & CIFS_CREATE_ACTION) && + if ((*oplock & CIFS_CREATE_ACTION) && (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) { newinode->i_uid = current_fsuid(); if (inode->i_mode & S_ISGID) @@ -321,40 +355,139 @@ cifs_create_get_file_info: } cifs_create_set_dentry: - if (rc == 0) - d_instantiate(direntry, newinode); - else + if (rc != 0) { cFYI(1, "Create worked, get_inode_info failed rc = %d", rc); + goto out; + } + d_drop(direntry); + d_add(direntry, newinode); - if (newinode && nd) { - struct cifsFileInfo *pfile_info; - struct file *filp; + /* ENOENT for create? How weird... */ + rc = -ENOENT; + if (!newinode) { + CIFSSMBClose(xid, tcon, *fileHandle); + goto out; + } + rc = 0; - filp = lookup_instantiate_filp(nd, direntry, generic_file_open); - if (IS_ERR(filp)) { - rc = PTR_ERR(filp); - CIFSSMBClose(xid, tcon, fileHandle); - goto cifs_create_out; - } +out: + kfree(buf); + kfree(full_path); + return rc; +} - pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock); - if (pfile_info == NULL) { - fput(filp); - CIFSSMBClose(xid, tcon, fileHandle); - rc = -ENOMEM; - } - } else { +int +cifs_atomic_open(struct inode *inode, struct dentry *direntry, + struct file *file, unsigned oflags, umode_t mode, + int *opened) +{ + int rc; + int xid; + struct tcon_link *tlink; + struct cifs_tcon *tcon; + __u16 fileHandle; + __u32 oplock; + struct file *filp; + struct cifsFileInfo *pfile_info; + + /* Posix open is only called (at lookup time) for file create now. For + * opens (rather than creates), because we do not know if it is a file + * or directory yet, and current Samba no longer allows us to do posix + * open on dirs, we could end up wasting an open call on what turns out + * to be a dir. For file opens, we wait to call posix open till + * cifs_open. It could be added to atomic_open in the future but the + * performance tradeoff of the extra network request when EISDIR or + * EACCES is returned would have to be weighed against the 50% reduction + * in network traffic in the other paths. + */ + if (!(oflags & O_CREAT)) { + struct dentry *res = cifs_lookup(inode, direntry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + return finish_no_open(file, res); + } + + rc = check_name(direntry); + if (rc) + return rc; + + xid = GetXid(); + + cFYI(1, "parent inode = 0x%p name is: %s and dentry = 0x%p", + inode, direntry->d_name.name, direntry); + + tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb)); + filp = ERR_CAST(tlink); + if (IS_ERR(tlink)) + goto free_xid; + + tcon = tlink_tcon(tlink); + + rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, + &oplock, &fileHandle, opened); + + if (rc) + goto out; + + rc = finish_open(file, direntry, generic_file_open, opened); + if (rc) { CIFSSMBClose(xid, tcon, fileHandle); + goto out; } -cifs_create_out: - kfree(buf); - kfree(full_path); + pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock); + if (pfile_info == NULL) { + CIFSSMBClose(xid, tcon, fileHandle); + fput(filp); + rc = -ENOMEM; + } + +out: cifs_put_tlink(tlink); +free_xid: FreeXid(xid); return rc; } +int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, + bool excl) +{ + int rc; + int xid = GetXid(); + /* + * BB below access is probably too much for mknod to request + * but we have to do query and setpathinfo so requesting + * less could fail (unless we want to request getatr and setatr + * permissions (only). At least for POSIX we do not have to + * request so much. + */ + unsigned oflags = O_EXCL | O_CREAT | O_RDWR; + struct tcon_link *tlink; + __u16 fileHandle; + __u32 oplock; + int created = FILE_CREATED; + + cFYI(1, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p", + inode, direntry->d_name.name, direntry); + + tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb)); + rc = PTR_ERR(tlink); + if (IS_ERR(tlink)) + goto free_xid; + + rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, + &oplock, &fileHandle, &created); + if (!rc) + CIFSSMBClose(xid, tlink_tcon(tlink), fileHandle); + + cifs_put_tlink(tlink); +free_xid: + FreeXid(xid); + + return rc; +} + int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode, dev_t device_number) { @@ -488,20 +621,15 @@ mknod_out: struct dentry * cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, - struct nameidata *nd) + unsigned int flags) { int xid; int rc = 0; /* to get around spurious gcc warning, set to zero here */ - __u32 oplock; - __u16 fileHandle = 0; - bool posix_open = false; struct cifs_sb_info *cifs_sb; struct tcon_link *tlink; struct cifs_tcon *pTcon; - struct cifsFileInfo *cfile; struct inode *newInode = NULL; char *full_path = NULL; - struct file *filp; xid = GetXid(); @@ -518,31 +646,9 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, } pTcon = tlink_tcon(tlink); - oplock = pTcon->ses->server->oplocks ? REQ_OPLOCK : 0; - - /* - * Don't allow the separator character in a path component. - * The VFS will not allow "/", but "\" is allowed by posix. - */ - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) { - int i; - for (i = 0; i < direntry->d_name.len; i++) - if (direntry->d_name.name[i] == '\\') { - cFYI(1, "Invalid file name"); - rc = -EINVAL; - goto lookup_out; - } - } - - /* - * O_EXCL: optimize away the lookup, but don't hash the dentry. Let - * the VFS handle the create. - */ - if (nd && (nd->flags & LOOKUP_EXCL)) { - d_instantiate(direntry, NULL); - rc = 0; + rc = check_name(direntry); + if (rc) goto lookup_out; - } /* can not grab the rename sem here since it would deadlock in the cases (beginning of sys_rename itself) @@ -560,80 +666,16 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, } cFYI(1, "Full path: %s inode = 0x%p", full_path, direntry->d_inode); - /* Posix open is only called (at lookup time) for file create now. - * For opens (rather than creates), because we do not know if it - * is a file or directory yet, and current Samba no longer allows - * us to do posix open on dirs, we could end up wasting an open call - * on what turns out to be a dir. For file opens, we wait to call posix - * open till cifs_open. It could be added here (lookup) in the future - * but the performance tradeoff of the extra network request when EISDIR - * or EACCES is returned would have to be weighed against the 50% - * reduction in network traffic in the other paths. - */ if (pTcon->unix_ext) { - if (nd && !(nd->flags & LOOKUP_DIRECTORY) && - (nd->flags & LOOKUP_OPEN) && !pTcon->broken_posix_open && - (nd->intent.open.file->f_flags & O_CREAT)) { - rc = cifs_posix_open(full_path, &newInode, - parent_dir_inode->i_sb, - nd->intent.open.create_mode, - nd->intent.open.file->f_flags, &oplock, - &fileHandle, xid); - /* - * The check below works around a bug in POSIX - * open in samba versions 3.3.1 and earlier where - * open could incorrectly fail with invalid parameter. - * If either that or op not supported returned, follow - * the normal lookup. - */ - switch (rc) { - case 0: - /* - * The server may allow us to open things like - * FIFOs, but the client isn't set up to deal - * with that. If it's not a regular file, just - * close it and proceed as if it were a normal - * lookup. - */ - if (newInode && !S_ISREG(newInode->i_mode)) { - CIFSSMBClose(xid, pTcon, fileHandle); - break; - } - case -ENOENT: - posix_open = true; - case -EOPNOTSUPP: - break; - default: - pTcon->broken_posix_open = true; - } - } - if (!posix_open) - rc = cifs_get_inode_info_unix(&newInode, full_path, - parent_dir_inode->i_sb, xid); - } else + rc = cifs_get_inode_info_unix(&newInode, full_path, + parent_dir_inode->i_sb, xid); + } else { rc = cifs_get_inode_info(&newInode, full_path, NULL, parent_dir_inode->i_sb, xid, NULL); + } if ((rc == 0) && (newInode != NULL)) { d_add(direntry, newInode); - if (posix_open) { - filp = lookup_instantiate_filp(nd, direntry, - generic_file_open); - if (IS_ERR(filp)) { - rc = PTR_ERR(filp); - CIFSSMBClose(xid, pTcon, fileHandle); - goto lookup_out; - } - - cfile = cifs_new_fileinfo(fileHandle, filp, tlink, - oplock); - if (cfile == NULL) { - fput(filp); - CIFSSMBClose(xid, pTcon, fileHandle); - rc = -ENOMEM; - goto lookup_out; - } - } /* since paths are not looked up by component - the parent directories are presumed to be good here */ renew_parental_timestamps(direntry); @@ -658,9 +700,9 @@ lookup_out: } static int -cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd) +cifs_d_revalidate(struct dentry *direntry, unsigned int flags) { - if (nd && (nd->flags & LOOKUP_RCU)) + if (flags & LOOKUP_RCU) return -ECHILD; if (direntry->d_inode) { @@ -689,7 +731,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd) * This may be nfsd (or something), anyway, we can't see the * intent of this. So, since this can be for creation, drop it. */ - if (!nd) + if (!flags) return 0; /* @@ -697,7 +739,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd) * case sensitive name which is specified by user if this is * for creation. */ - if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) + if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; if (time_after(jiffies, direntry->d_time + HZ) || !lookupCacheEnabled) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 253170d..513adbc 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -876,7 +876,7 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) struct cifsLockInfo *li, *tmp; struct cifs_tcon *tcon; struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); - unsigned int num, max_num; + unsigned int num, max_num, max_buf; LOCKING_ANDX_RANGE *buf, *cur; int types[] = {LOCKING_ANDX_LARGE_FILES, LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES}; @@ -892,8 +892,19 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) return rc; } - max_num = (tcon->ses->server->maxBuf - sizeof(struct smb_hdr)) / - sizeof(LOCKING_ANDX_RANGE); + /* + * Accessing maxBuf is racy with cifs_reconnect - need to store value + * and check it for zero before using. + */ + max_buf = tcon->ses->server->maxBuf; + if (!max_buf) { + mutex_unlock(&cinode->lock_mutex); + FreeXid(xid); + return -EINVAL; + } + + max_num = (max_buf - sizeof(struct smb_hdr)) / + sizeof(LOCKING_ANDX_RANGE); buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); if (!buf) { mutex_unlock(&cinode->lock_mutex); @@ -1218,7 +1229,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, int xid) int types[] = {LOCKING_ANDX_LARGE_FILES, LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES}; unsigned int i; - unsigned int max_num, num; + unsigned int max_num, num, max_buf; LOCKING_ANDX_RANGE *buf, *cur; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); @@ -1228,8 +1239,16 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, int xid) INIT_LIST_HEAD(&tmp_llist); - max_num = (tcon->ses->server->maxBuf - sizeof(struct smb_hdr)) / - sizeof(LOCKING_ANDX_RANGE); + /* + * Accessing maxBuf is racy with cifs_reconnect - need to store value + * and check it for zero before using. + */ + max_buf = tcon->ses->server->maxBuf; + if (!max_buf) + return -EINVAL; + + max_num = (max_buf - sizeof(struct smb_hdr)) / + sizeof(LOCKING_ANDX_RANGE); buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); if (!buf) return -ENOMEM; @@ -1247,46 +1266,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, int xid) continue; if (types[i] != li->type) continue; - if (!cinode->can_cache_brlcks) { - cur->Pid = cpu_to_le16(li->pid); - cur->LengthLow = cpu_to_le32((u32)li->length); - cur->LengthHigh = - cpu_to_le32((u32)(li->length>>32)); - cur->OffsetLow = cpu_to_le32((u32)li->offset); - cur->OffsetHigh = - cpu_to_le32((u32)(li->offset>>32)); - /* - * We need to save a lock here to let us add - * it again to the file's list if the unlock - * range request fails on the server. - */ - list_move(&li->llist, &tmp_llist); - if (++num == max_num) { - stored_rc = cifs_lockv(xid, tcon, - cfile->netfid, - li->type, num, - 0, buf); - if (stored_rc) { - /* - * We failed on the unlock range - * request - add all locks from - * the tmp list to the head of - * the file's list. - */ - cifs_move_llist(&tmp_llist, - &cfile->llist); - rc = stored_rc; - } else - /* - * The unlock range request - * succeed - free the tmp list. - */ - cifs_free_llist(&tmp_llist); - cur = buf; - num = 0; - } else - cur++; - } else { + if (cinode->can_cache_brlcks) { /* * We can cache brlock requests - simply remove * a lock from the file's list. @@ -1294,7 +1274,41 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, int xid) list_del(&li->llist); cifs_del_lock_waiters(li); kfree(li); + continue; } + cur->Pid = cpu_to_le16(li->pid); + cur->LengthLow = cpu_to_le32((u32)li->length); + cur->LengthHigh = cpu_to_le32((u32)(li->length>>32)); + cur->OffsetLow = cpu_to_le32((u32)li->offset); + cur->OffsetHigh = cpu_to_le32((u32)(li->offset>>32)); + /* + * We need to save a lock here to let us add it again to + * the file's list if the unlock range request fails on + * the server. + */ + list_move(&li->llist, &tmp_llist); + if (++num == max_num) { + stored_rc = cifs_lockv(xid, tcon, cfile->netfid, + li->type, num, 0, buf); + if (stored_rc) { + /* + * We failed on the unlock range + * request - add all locks from the tmp + * list to the head of the file's list. + */ + cifs_move_llist(&tmp_llist, + &cfile->llist); + rc = stored_rc; + } else + /* + * The unlock range request succeed - + * free the tmp list. + */ + cifs_free_llist(&tmp_llist); + cur = buf; + num = 0; + } else + cur++; } if (num) { stored_rc = cifs_lockv(xid, tcon, cfile->netfid, diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 745da3d..8e8bb49 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -800,7 +800,7 @@ cifs_find_inode(struct inode *inode, void *opaque) return 0; /* if it's not a directory or has no dentries, then flag it */ - if (S_ISDIR(inode->i_mode) && !list_empty(&inode->i_dentry)) + if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) fattr->cf_flags |= CIFS_FATTR_INO_COLLISION; return 1; @@ -825,9 +825,10 @@ static bool inode_has_hashed_dentries(struct inode *inode) { struct dentry *dentry; + struct hlist_node *p; spin_lock(&inode->i_lock); - list_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { if (!d_unhashed(dentry) || IS_ROOT(dentry)) { spin_unlock(&inode->i_lock); return true; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index e2552d2..557506a 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -212,93 +212,6 @@ cifs_small_buf_release(void *buf_to_free) return; } -/* - * Find a free multiplex id (SMB mid). Otherwise there could be - * mid collisions which might cause problems, demultiplexing the - * wrong response to this request. Multiplex ids could collide if - * one of a series requests takes much longer than the others, or - * if a very large number of long lived requests (byte range - * locks or FindNotify requests) are pending. No more than - * 64K-1 requests can be outstanding at one time. If no - * mids are available, return zero. A future optimization - * could make the combination of mids and uid the key we use - * to demultiplex on (rather than mid alone). - * In addition to the above check, the cifs demultiplex - * code already used the command code as a secondary - * check of the frame and if signing is negotiated the - * response would be discarded if the mid were the same - * but the signature was wrong. Since the mid is not put in the - * pending queue until later (when it is about to be dispatched) - * we do have to limit the number of outstanding requests - * to somewhat less than 64K-1 although it is hard to imagine - * so many threads being in the vfs at one time. - */ -__u64 GetNextMid(struct TCP_Server_Info *server) -{ - __u64 mid = 0; - __u16 last_mid, cur_mid; - bool collision; - - spin_lock(&GlobalMid_Lock); - - /* mid is 16 bit only for CIFS/SMB */ - cur_mid = (__u16)((server->CurrentMid) & 0xffff); - /* we do not want to loop forever */ - last_mid = cur_mid; - cur_mid++; - - /* - * This nested loop looks more expensive than it is. - * In practice the list of pending requests is short, - * fewer than 50, and the mids are likely to be unique - * on the first pass through the loop unless some request - * takes longer than the 64 thousand requests before it - * (and it would also have to have been a request that - * did not time out). - */ - while (cur_mid != last_mid) { - struct mid_q_entry *mid_entry; - unsigned int num_mids; - - collision = false; - if (cur_mid == 0) - cur_mid++; - - num_mids = 0; - list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) { - ++num_mids; - if (mid_entry->mid == cur_mid && - mid_entry->mid_state == MID_REQUEST_SUBMITTED) { - /* This mid is in use, try a different one */ - collision = true; - break; - } - } - - /* - * if we have more than 32k mids in the list, then something - * is very wrong. Possibly a local user is trying to DoS the - * box by issuing long-running calls and SIGKILL'ing them. If - * we get to 2^16 mids then we're in big trouble as this - * function could loop forever. - * - * Go ahead and assign out the mid in this situation, but force - * an eventual reconnect to clean out the pending_mid_q. - */ - if (num_mids > 32768) - server->tcpStatus = CifsNeedReconnect; - - if (!collision) { - mid = (__u64)cur_mid; - server->CurrentMid = mid; - break; - } - cur_mid++; - } - spin_unlock(&GlobalMid_Lock); - return mid; -} - /* NB: MID can not be set if treeCon not passed in, in that case it is responsbility of caller to set the mid */ void @@ -334,7 +247,7 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ , /* Uid is not converted */ buffer->Uid = treeCon->ses->Suid; - buffer->Mid = GetNextMid(treeCon->ses->server); + buffer->Mid = get_next_mid(treeCon->ses->server); } if (treeCon->Flags & SMB_SHARE_IS_IN_DFS) buffer->Flags2 |= SMBFLG2_DFS; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 0a8224d..a4217f0 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -86,9 +86,12 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name, dentry = d_lookup(parent, name); if (dentry) { - /* FIXME: check for inode number changes? */ - if (dentry->d_inode != NULL) + inode = dentry->d_inode; + /* update inode in place if i_ino didn't change */ + if (inode && CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) { + cifs_fattr_to_inode(inode, fattr); return dentry; + } d_drop(dentry); dput(dentry); } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index d9d615f..6dec38f 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -125,6 +125,94 @@ cifs_get_credits_field(struct TCP_Server_Info *server) return &server->credits; } +/* + * Find a free multiplex id (SMB mid). Otherwise there could be + * mid collisions which might cause problems, demultiplexing the + * wrong response to this request. Multiplex ids could collide if + * one of a series requests takes much longer than the others, or + * if a very large number of long lived requests (byte range + * locks or FindNotify requests) are pending. No more than + * 64K-1 requests can be outstanding at one time. If no + * mids are available, return zero. A future optimization + * could make the combination of mids and uid the key we use + * to demultiplex on (rather than mid alone). + * In addition to the above check, the cifs demultiplex + * code already used the command code as a secondary + * check of the frame and if signing is negotiated the + * response would be discarded if the mid were the same + * but the signature was wrong. Since the mid is not put in the + * pending queue until later (when it is about to be dispatched) + * we do have to limit the number of outstanding requests + * to somewhat less than 64K-1 although it is hard to imagine + * so many threads being in the vfs at one time. + */ +static __u64 +cifs_get_next_mid(struct TCP_Server_Info *server) +{ + __u64 mid = 0; + __u16 last_mid, cur_mid; + bool collision; + + spin_lock(&GlobalMid_Lock); + + /* mid is 16 bit only for CIFS/SMB */ + cur_mid = (__u16)((server->CurrentMid) & 0xffff); + /* we do not want to loop forever */ + last_mid = cur_mid; + cur_mid++; + + /* + * This nested loop looks more expensive than it is. + * In practice the list of pending requests is short, + * fewer than 50, and the mids are likely to be unique + * on the first pass through the loop unless some request + * takes longer than the 64 thousand requests before it + * (and it would also have to have been a request that + * did not time out). + */ + while (cur_mid != last_mid) { + struct mid_q_entry *mid_entry; + unsigned int num_mids; + + collision = false; + if (cur_mid == 0) + cur_mid++; + + num_mids = 0; + list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) { + ++num_mids; + if (mid_entry->mid == cur_mid && + mid_entry->mid_state == MID_REQUEST_SUBMITTED) { + /* This mid is in use, try a different one */ + collision = true; + break; + } + } + + /* + * if we have more than 32k mids in the list, then something + * is very wrong. Possibly a local user is trying to DoS the + * box by issuing long-running calls and SIGKILL'ing them. If + * we get to 2^16 mids then we're in big trouble as this + * function could loop forever. + * + * Go ahead and assign out the mid in this situation, but force + * an eventual reconnect to clean out the pending_mid_q. + */ + if (num_mids > 32768) + server->tcpStatus = CifsNeedReconnect; + + if (!collision) { + mid = (__u64)cur_mid; + server->CurrentMid = mid; + break; + } + cur_mid++; + } + spin_unlock(&GlobalMid_Lock); + return mid; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -133,6 +221,7 @@ struct smb_version_operations smb1_operations = { .add_credits = cifs_add_credits, .set_credits = cifs_set_credits, .get_credits_field = cifs_get_credits_field, + .get_next_mid = cifs_get_next_mid, .read_data_offset = cifs_read_data_offset, .read_data_length = cifs_read_data_length, .map_error = map_smb_to_linux_error, diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 1b36ffe..f25d4ea 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -365,16 +365,14 @@ cifs_setup_async_request(struct TCP_Server_Info *server, struct kvec *iov, if (mid == NULL) return -ENOMEM; - /* put it on the pending_mid_q */ - spin_lock(&GlobalMid_Lock); - list_add_tail(&mid->qhead, &server->pending_mid_q); - spin_unlock(&GlobalMid_Lock); - rc = cifs_sign_smb2(iov, nvec, server, &mid->sequence_number); - if (rc) - delete_mid(mid); + if (rc) { + DeleteMidQEntry(mid); + return rc; + } + *ret_mid = mid; - return rc; + return 0; } /* @@ -407,17 +405,21 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov, mid->callback_data = cbdata; mid->mid_state = MID_REQUEST_SUBMITTED; + /* put it on the pending_mid_q */ + spin_lock(&GlobalMid_Lock); + list_add_tail(&mid->qhead, &server->pending_mid_q); + spin_unlock(&GlobalMid_Lock); + + cifs_in_send_inc(server); rc = smb_sendv(server, iov, nvec); cifs_in_send_dec(server); cifs_save_when_sent(mid); mutex_unlock(&server->srv_mutex); - if (rc) - goto out_err; + if (rc == 0) + return 0; - return rc; -out_err: delete_mid(mid); add_credits(server, 1); wake_up(&server->request_q); @@ -779,7 +781,7 @@ send_lock_cancel(const unsigned int xid, struct cifs_tcon *tcon, pSMB->LockType = LOCKING_ANDX_CANCEL_LOCK|LOCKING_ANDX_LARGE_FILES; pSMB->Timeout = 0; - pSMB->hdr.Mid = GetNextMid(ses->server); + pSMB->hdr.Mid = get_next_mid(ses->server); return SendReceive(xid, ses, in_buf, out_buf, &bytes_returned, 0); diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 6901578..958ae0e 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -89,17 +89,13 @@ int coda_cache_check(struct inode *inode, int mask) /* this won't do any harm: just flag all children */ static void coda_flag_children(struct dentry *parent, int flag) { - struct list_head *child; struct dentry *de; spin_lock(&parent->d_lock); - list_for_each(child, &parent->d_subdirs) - { - de = list_entry(child, struct dentry, d_u.d_child); + list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) { /* don't know what to do with negative dentries */ - if ( ! de->d_inode ) - continue; - coda_flag_inode(de->d_inode, flag); + if (de->d_inode ) + coda_flag_inode(de->d_inode, flag); } spin_unlock(&parent->d_lock); return; diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 1775158..49fe52d 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -30,8 +30,8 @@ #include "coda_int.h" /* dir inode-ops */ -static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, struct nameidata *nd); -static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, struct nameidata *nd); +static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, bool excl); +static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, unsigned int flags); static int coda_link(struct dentry *old_dentry, struct inode *dir_inode, struct dentry *entry); static int coda_unlink(struct inode *dir_inode, struct dentry *entry); @@ -46,7 +46,7 @@ static int coda_rename(struct inode *old_inode, struct dentry *old_dentry, static int coda_readdir(struct file *file, void *buf, filldir_t filldir); /* dentry ops */ -static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd); +static int coda_dentry_revalidate(struct dentry *de, unsigned int flags); static int coda_dentry_delete(const struct dentry *); /* support routines */ @@ -94,7 +94,7 @@ const struct file_operations coda_dir_operations = { /* inode operations for directories */ /* access routines: lookup, readlink, permission */ -static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, struct nameidata *nd) +static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsigned int flags) { struct super_block *sb = dir->i_sb; const char *name = entry->d_name.name; @@ -188,7 +188,7 @@ static inline void coda_dir_drop_nlink(struct inode *dir) } /* creation routines: create, mknod, mkdir, link, symlink */ -static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, struct nameidata *nd) +static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool excl) { int error; const char *name=de->d_name.name; @@ -536,12 +536,12 @@ out: } /* called when a cache lookup succeeds */ -static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd) +static int coda_dentry_revalidate(struct dentry *de, unsigned int flags) { struct inode *inode; struct coda_inode_info *cii; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = de->d_inode; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 7e6c52d..7414ae2 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -442,7 +442,7 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den static struct dentry * configfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct configfs_dirent * parent_sd = dentry->d_parent->d_fsdata; struct configfs_dirent * sd; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index d013c46..28cca01 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -417,7 +417,7 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir) /* * Lookup and fill in the inode data.. */ -static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { unsigned int offset = 0; struct inode *inode = NULL; diff --git a/fs/dcache.c b/fs/dcache.c index 85c9e2b..8086636 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -218,7 +218,7 @@ static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); - WARN_ON(!list_empty(&dentry->d_alias)); + WARN_ON(!hlist_unhashed(&dentry->d_alias)); if (dname_external(dentry)) kfree(dentry->d_name.name); kmem_cache_free(dentry_cache, dentry); @@ -267,7 +267,7 @@ static void dentry_iput(struct dentry * dentry) struct inode *inode = dentry->d_inode; if (inode) { dentry->d_inode = NULL; - list_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_alias); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -291,7 +291,7 @@ static void dentry_unlink_inode(struct dentry * dentry) { struct inode *inode = dentry->d_inode; dentry->d_inode = NULL; - list_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_alias); dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); @@ -683,6 +683,8 @@ EXPORT_SYMBOL(dget_parent); /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question + * @want_discon: flag, used by d_splice_alias, to request + * that only a DISCONNECTED alias be returned. * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. @@ -691,21 +693,23 @@ EXPORT_SYMBOL(dget_parent); * of a filesystem. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer - * any other hashed alias over that. + * any other hashed alias over that one unless @want_discon is set, + * in which case only return an IS_ROOT, DCACHE_DISCONNECTED alias. */ -static struct dentry *__d_find_alias(struct inode *inode) +static struct dentry *__d_find_alias(struct inode *inode, int want_discon) { struct dentry *alias, *discon_alias; + struct hlist_node *p; again: discon_alias = NULL; - list_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { spin_lock(&alias->d_lock); if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) { if (IS_ROOT(alias) && (alias->d_flags & DCACHE_DISCONNECTED)) { discon_alias = alias; - } else { + } else if (!want_discon) { __dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; @@ -734,9 +738,9 @@ struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; - if (!list_empty(&inode->i_dentry)) { + if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); - de = __d_find_alias(inode); + de = __d_find_alias(inode, 0); spin_unlock(&inode->i_lock); } return de; @@ -750,9 +754,10 @@ EXPORT_SYMBOL(d_find_alias); void d_prune_aliases(struct inode *inode) { struct dentry *dentry; + struct hlist_node *p; restart: spin_lock(&inode->i_lock); - list_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_count) { __dget_dlock(dentry); @@ -974,7 +979,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) inode = dentry->d_inode; if (inode) { dentry->d_inode = NULL; - list_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_alias); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else @@ -1309,7 +1314,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); - INIT_LIST_HEAD(&dentry->d_alias); + INIT_HLIST_NODE(&dentry->d_alias); INIT_LIST_HEAD(&dentry->d_u.d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); @@ -1397,7 +1402,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) if (inode) { if (unlikely(IS_AUTOMOUNT(inode))) dentry->d_flags |= DCACHE_NEED_AUTOMOUNT; - list_add(&dentry->d_alias, &inode->i_dentry); + hlist_add_head(&dentry->d_alias, &inode->i_dentry); } dentry->d_inode = inode; dentry_rcuwalk_barrier(dentry); @@ -1422,7 +1427,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) void d_instantiate(struct dentry *entry, struct inode * inode) { - BUG_ON(!list_empty(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_alias)); if (inode) spin_lock(&inode->i_lock); __d_instantiate(entry, inode); @@ -1455,13 +1460,14 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, int len = entry->d_name.len; const char *name = entry->d_name.name; unsigned int hash = entry->d_name.hash; + struct hlist_node *p; if (!inode) { __d_instantiate(entry, NULL); return NULL; } - list_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or @@ -1487,7 +1493,7 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode) { struct dentry *result; - BUG_ON(!list_empty(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_alias)); if (inode) spin_lock(&inode->i_lock); @@ -1528,9 +1534,9 @@ static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; - if (list_empty(&inode->i_dentry)) + if (hlist_empty(&inode->i_dentry)) return NULL; - alias = list_first_entry(&inode->i_dentry, struct dentry, d_alias); + alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); __dget(alias); return alias; } @@ -1604,7 +1610,7 @@ struct dentry *d_obtain_alias(struct inode *inode) spin_lock(&tmp->d_lock); tmp->d_inode = inode; tmp->d_flags |= DCACHE_DISCONNECTED; - list_add(&tmp->d_alias, &inode->i_dentry); + hlist_add_head(&tmp->d_alias, &inode->i_dentry); hlist_bl_lock(&tmp->d_sb->s_anon); hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon); hlist_bl_unlock(&tmp->d_sb->s_anon); @@ -1647,8 +1653,9 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) if (inode && S_ISDIR(inode->i_mode)) { spin_lock(&inode->i_lock); - new = __d_find_any_alias(inode); + new = __d_find_alias(inode, 1); if (new) { + BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED)); spin_unlock(&inode->i_lock); security_d_instantiate(new, inode); d_move(new, dentry); @@ -2380,14 +2387,13 @@ static struct dentry *__d_unalias(struct inode *inode, struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL, *m2 = NULL; - struct dentry *ret; + struct dentry *ret = ERR_PTR(-EBUSY); /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ - ret = ERR_PTR(-EBUSY); if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; @@ -2395,8 +2401,10 @@ static struct dentry *__d_unalias(struct inode *inode, goto out_err; m2 = &alias->d_parent->d_inode->i_mutex; out_unalias: - __d_move(alias, dentry); - ret = alias; + if (likely(!d_mountpoint(alias))) { + __d_move(alias, dentry); + ret = alias; + } out_err: spin_unlock(&inode->i_lock); if (m2) @@ -2478,7 +2486,7 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode) struct dentry *alias; /* Does an aliased dentry already exist? */ - alias = __d_find_alias(inode); + alias = __d_find_alias(inode, 0); if (alias) { actual = alias; write_seqlock(&rename_lock); @@ -2618,7 +2626,7 @@ global_root: if (!slash) error = prepend(buffer, buflen, "/", 1); if (!error) - error = real_mount(vfsmnt)->mnt_ns ? 1 : 2; + error = is_mounted(vfsmnt) ? 1 : 2; goto out; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index b80bc84..d17c20f 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -54,13 +54,12 @@ static struct inode *debugfs_get_inode(struct super_block *sb, umode_t mode, dev break; case S_IFLNK: inode->i_op = &debugfs_link_operations; - inode->i_fop = fops; inode->i_private = data; break; case S_IFDIR: inode->i_op = &simple_dir_inode_operations; - inode->i_fop = fops ? fops : &simple_dir_operations; - inode->i_private = data; + inode->i_fop = &simple_dir_operations; + inode->i_private = NULL; /* directory inodes start off with i_nlink == 2 * (for "." entry) */ @@ -91,13 +90,12 @@ static int debugfs_mknod(struct inode *dir, struct dentry *dentry, return error; } -static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, - void *data, const struct file_operations *fops) +static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { int res; mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR; - res = debugfs_mknod(dir, dentry, mode, 0, data, fops); + res = debugfs_mknod(dir, dentry, mode, 0, NULL, NULL); if (!res) { inc_nlink(dir); fsnotify_mkdir(dir, dentry); @@ -106,10 +104,10 @@ static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, } static int debugfs_link(struct inode *dir, struct dentry *dentry, umode_t mode, - void *data, const struct file_operations *fops) + void *data) { mode = (mode & S_IALLUGO) | S_IFLNK; - return debugfs_mknod(dir, dentry, mode, 0, data, fops); + return debugfs_mknod(dir, dentry, mode, 0, data, NULL); } static int debugfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, @@ -293,13 +291,19 @@ static struct file_system_type debug_fs_type = { .kill_sb = kill_litter_super, }; -static int debugfs_create_by_name(const char *name, umode_t mode, - struct dentry *parent, - struct dentry **dentry, - void *data, - const struct file_operations *fops) +struct dentry *__create_file(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops) { - int error = 0; + struct dentry *dentry = NULL; + int error; + + pr_debug("debugfs: creating file '%s'\n",name); + + error = simple_pin_fs(&debug_fs_type, &debugfs_mount, + &debugfs_mount_count); + if (error) + goto exit; /* If the parent is not specified, we create it in the root. * We need the root dentry to do this, which is in the super @@ -309,30 +313,35 @@ static int debugfs_create_by_name(const char *name, umode_t mode, if (!parent) parent = debugfs_mount->mnt_root; - *dentry = NULL; + dentry = NULL; mutex_lock(&parent->d_inode->i_mutex); - *dentry = lookup_one_len(name, parent, strlen(name)); - if (!IS_ERR(*dentry)) { + dentry = lookup_one_len(name, parent, strlen(name)); + if (!IS_ERR(dentry)) { switch (mode & S_IFMT) { case S_IFDIR: - error = debugfs_mkdir(parent->d_inode, *dentry, mode, - data, fops); + error = debugfs_mkdir(parent->d_inode, dentry, mode); + break; case S_IFLNK: - error = debugfs_link(parent->d_inode, *dentry, mode, - data, fops); + error = debugfs_link(parent->d_inode, dentry, mode, + data); break; default: - error = debugfs_create(parent->d_inode, *dentry, mode, + error = debugfs_create(parent->d_inode, dentry, mode, data, fops); break; } - dput(*dentry); + dput(dentry); } else - error = PTR_ERR(*dentry); + error = PTR_ERR(dentry); mutex_unlock(&parent->d_inode->i_mutex); - return error; + if (error) { + dentry = NULL; + simple_release_fs(&debugfs_mount, &debugfs_mount_count); + } +exit: + return dentry; } /** @@ -365,25 +374,15 @@ struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { - struct dentry *dentry = NULL; - int error; - - pr_debug("debugfs: creating file '%s'\n",name); - - error = simple_pin_fs(&debug_fs_type, &debugfs_mount, - &debugfs_mount_count); - if (error) - goto exit; - - error = debugfs_create_by_name(name, mode, parent, &dentry, - data, fops); - if (error) { - dentry = NULL; - simple_release_fs(&debugfs_mount, &debugfs_mount_count); - goto exit; + switch (mode & S_IFMT) { + case S_IFREG: + case 0: + break; + default: + BUG(); } -exit: - return dentry; + + return __create_file(name, mode, parent, data, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file); @@ -407,8 +406,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_file); */ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) { - return debugfs_create_file(name, - S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, + return __create_file(name, S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, parent, NULL, NULL); } EXPORT_SYMBOL_GPL(debugfs_create_dir); @@ -446,8 +444,7 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, if (!link) return NULL; - result = debugfs_create_file(name, S_IFLNK | S_IRWXUGO, parent, link, - NULL); + result = __create_file(name, S_IFLNK | S_IRWXUGO, parent, link, NULL); if (!result) kfree(link); return result; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 979c1e3..14afbab 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -439,15 +439,15 @@ static struct dentry *devpts_mount(struct file_system_type *fs_type, return ERR_PTR(error); if (opts.newinstance) - s = sget(fs_type, NULL, set_anon_super, NULL); + s = sget(fs_type, NULL, set_anon_super, flags, NULL); else - s = sget(fs_type, compare_init_pts_sb, set_anon_super, NULL); + s = sget(fs_type, compare_init_pts_sb, set_anon_super, flags, + NULL); if (IS_ERR(s)) return ERR_CAST(s); if (!s->s_root) { - s->s_flags = flags; error = devpts_fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) goto out_undo_sget; diff --git a/fs/direct-io.c b/fs/direct-io.c index 0c85fae..1faf4cb 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1258,7 +1258,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, */ BUG_ON(retval == -EIOCBQUEUED); if (dio->is_async && retval == 0 && dio->result && - ((rw & READ) || (dio->result == sdio.size))) + ((rw == READ) || (dio->result == sdio.size))) retval = -EIOCBQUEUED; if (retval != -EIOCBQUEUED) diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c index 534c1d4..1b5d9af 100644 --- a/fs/ecryptfs/dentry.c +++ b/fs/ecryptfs/dentry.c @@ -32,7 +32,7 @@ /** * ecryptfs_d_revalidate - revalidate an ecryptfs dentry * @dentry: The ecryptfs dentry - * @nd: The associated nameidata + * @flags: lookup flags * * Called when the VFS needs to revalidate a dentry. This * is called whenever a name lookup finds a dentry in the @@ -42,32 +42,20 @@ * Returns 1 if valid, 0 otherwise. * */ -static int ecryptfs_d_revalidate(struct dentry *dentry, struct nameidata *nd) +static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags) { struct dentry *lower_dentry; struct vfsmount *lower_mnt; - struct dentry *dentry_save = NULL; - struct vfsmount *vfsmount_save = NULL; int rc = 1; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; lower_dentry = ecryptfs_dentry_to_lower(dentry); lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry); if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate) goto out; - if (nd) { - dentry_save = nd->path.dentry; - vfsmount_save = nd->path.mnt; - nd->path.dentry = lower_dentry; - nd->path.mnt = lower_mnt; - } - rc = lower_dentry->d_op->d_revalidate(lower_dentry, nd); - if (nd) { - nd->path.dentry = dentry_save; - nd->path.mnt = vfsmount_save; - } + rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags); if (dentry->d_inode) { struct inode *lower_inode = ecryptfs_inode_to_lower(dentry->d_inode); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 867b64c..989e034 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -550,20 +550,6 @@ extern struct kmem_cache *ecryptfs_key_record_cache; extern struct kmem_cache *ecryptfs_key_sig_cache; extern struct kmem_cache *ecryptfs_global_auth_tok_cache; extern struct kmem_cache *ecryptfs_key_tfm_cache; -extern struct kmem_cache *ecryptfs_open_req_cache; - -struct ecryptfs_open_req { -#define ECRYPTFS_REQ_PROCESSED 0x00000001 -#define ECRYPTFS_REQ_DROPPED 0x00000002 -#define ECRYPTFS_REQ_ZOMBIE 0x00000004 - u32 flags; - struct file **lower_file; - struct dentry *lower_dentry; - struct vfsmount *lower_mnt; - wait_queue_head_t wait; - struct mutex mux; - struct list_head kthread_ctl_list; -}; struct inode *ecryptfs_get_inode(struct inode *lower_inode, struct super_block *sb); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index a07441a..ffa2be5 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -173,7 +173,7 @@ ecryptfs_do_create(struct inode *directory_inode, inode = ERR_CAST(lower_dir_dentry); goto out; } - rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, NULL); + rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, true); if (rc) { printk(KERN_ERR "%s: Failure to create dentry in lower fs; " "rc = [%d]\n", __func__, rc); @@ -240,7 +240,6 @@ out: * @dir: The inode of the directory in which to create the file. * @dentry: The eCryptfs dentry * @mode: The mode of the new file. - * @nd: nameidata * * Creates a new file. * @@ -248,7 +247,7 @@ out: */ static int ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { struct inode *ecryptfs_inode; int rc; @@ -270,8 +269,8 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry, iput(ecryptfs_inode); goto out; } - d_instantiate(ecryptfs_dentry, ecryptfs_inode); unlock_new_inode(ecryptfs_inode); + d_instantiate(ecryptfs_dentry, ecryptfs_inode); out: return rc; } @@ -374,7 +373,7 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry, */ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, struct dentry *ecryptfs_dentry, - struct nameidata *ecryptfs_nd) + unsigned int flags) { char *encrypted_and_encoded_name = NULL; size_t encrypted_and_encoded_name_size; diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index 69f994a..809e67d 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -27,7 +27,12 @@ #include <linux/mount.h> #include "ecryptfs_kernel.h" -struct kmem_cache *ecryptfs_open_req_cache; +struct ecryptfs_open_req { + struct file **lower_file; + struct path path; + struct completion done; + struct list_head kthread_ctl_list; +}; static struct ecryptfs_kthread_ctl { #define ECRYPTFS_KTHREAD_ZOMBIE 0x00000001 @@ -67,18 +72,10 @@ static int ecryptfs_threadfn(void *ignored) req = list_first_entry(&ecryptfs_kthread_ctl.req_list, struct ecryptfs_open_req, kthread_ctl_list); - mutex_lock(&req->mux); list_del(&req->kthread_ctl_list); - if (!(req->flags & ECRYPTFS_REQ_ZOMBIE)) { - dget(req->lower_dentry); - mntget(req->lower_mnt); - (*req->lower_file) = dentry_open( - req->lower_dentry, req->lower_mnt, - (O_RDWR | O_LARGEFILE), current_cred()); - req->flags |= ECRYPTFS_REQ_PROCESSED; - } - wake_up(&req->wait); - mutex_unlock(&req->mux); + *req->lower_file = dentry_open(&req->path, + (O_RDWR | O_LARGEFILE), current_cred()); + complete(&req->done); } mutex_unlock(&ecryptfs_kthread_ctl.mux); } @@ -111,10 +108,9 @@ void ecryptfs_destroy_kthread(void) ecryptfs_kthread_ctl.flags |= ECRYPTFS_KTHREAD_ZOMBIE; list_for_each_entry(req, &ecryptfs_kthread_ctl.req_list, kthread_ctl_list) { - mutex_lock(&req->mux); - req->flags |= ECRYPTFS_REQ_ZOMBIE; - wake_up(&req->wait); - mutex_unlock(&req->mux); + list_del(&req->kthread_ctl_list); + *req->lower_file = ERR_PTR(-EIO); + complete(&req->done); } mutex_unlock(&ecryptfs_kthread_ctl.mux); kthread_stop(ecryptfs_kthread); @@ -136,34 +132,26 @@ int ecryptfs_privileged_open(struct file **lower_file, struct vfsmount *lower_mnt, const struct cred *cred) { - struct ecryptfs_open_req *req; + struct ecryptfs_open_req req; int flags = O_LARGEFILE; int rc = 0; + init_completion(&req.done); + req.lower_file = lower_file; + req.path.dentry = lower_dentry; + req.path.mnt = lower_mnt; + /* Corresponding dput() and mntput() are done when the * lower file is fput() when all eCryptfs files for the inode are * released. */ - dget(lower_dentry); - mntget(lower_mnt); flags |= IS_RDONLY(lower_dentry->d_inode) ? O_RDONLY : O_RDWR; - (*lower_file) = dentry_open(lower_dentry, lower_mnt, flags, cred); + (*lower_file) = dentry_open(&req.path, flags, cred); if (!IS_ERR(*lower_file)) goto out; - if (flags & O_RDONLY) { + if ((flags & O_ACCMODE) == O_RDONLY) { rc = PTR_ERR((*lower_file)); goto out; } - req = kmem_cache_alloc(ecryptfs_open_req_cache, GFP_KERNEL); - if (!req) { - rc = -ENOMEM; - goto out; - } - mutex_init(&req->mux); - req->lower_file = lower_file; - req->lower_dentry = lower_dentry; - req->lower_mnt = lower_mnt; - init_waitqueue_head(&req->wait); - req->flags = 0; mutex_lock(&ecryptfs_kthread_ctl.mux); if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) { rc = -EIO; @@ -171,27 +159,14 @@ int ecryptfs_privileged_open(struct file **lower_file, printk(KERN_ERR "%s: We are in the middle of shutting down; " "aborting privileged request to open lower file\n", __func__); - goto out_free; + goto out; } - list_add_tail(&req->kthread_ctl_list, &ecryptfs_kthread_ctl.req_list); + list_add_tail(&req.kthread_ctl_list, &ecryptfs_kthread_ctl.req_list); mutex_unlock(&ecryptfs_kthread_ctl.mux); wake_up(&ecryptfs_kthread_ctl.wait); - wait_event(req->wait, (req->flags != 0)); - mutex_lock(&req->mux); - BUG_ON(req->flags == 0); - if (req->flags & ECRYPTFS_REQ_DROPPED - || req->flags & ECRYPTFS_REQ_ZOMBIE) { - rc = -EIO; - printk(KERN_WARNING "%s: Privileged open request dropped\n", - __func__); - goto out_unlock; - } - if (IS_ERR(*req->lower_file)) - rc = PTR_ERR(*req->lower_file); -out_unlock: - mutex_unlock(&req->mux); -out_free: - kmem_cache_free(ecryptfs_open_req_cache, req); + wait_for_completion(&req.done); + if (IS_ERR(*lower_file)) + rc = PTR_ERR(*lower_file); out: return rc; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 6895493..1c0b3b6 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -499,13 +499,12 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags goto out; } - s = sget(fs_type, NULL, set_anon_super, NULL); + s = sget(fs_type, NULL, set_anon_super, flags, NULL); if (IS_ERR(s)) { rc = PTR_ERR(s); goto out; } - s->s_flags = flags; rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY); if (rc) goto out1; @@ -682,11 +681,6 @@ static struct ecryptfs_cache_info { .name = "ecryptfs_key_tfm_cache", .size = sizeof(struct ecryptfs_key_tfm), }, - { - .cache = &ecryptfs_open_req_cache, - .name = "ecryptfs_open_req_cache", - .size = sizeof(struct ecryptfs_open_req), - }, }; static void ecryptfs_free_kmem_caches(void) diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 3a06f40..c0038f6 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -49,7 +49,10 @@ ecryptfs_miscdev_poll(struct file *file, poll_table *pt) mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) { + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EINVAL; + } mutex_lock(&daemon->mux); mutex_unlock(&ecryptfs_daemon_hash_mux); if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { @@ -122,6 +125,7 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file) goto out_unlock_daemon; } daemon->flags |= ECRYPTFS_DAEMON_MISCDEV_OPEN; + file->private_data = daemon; atomic_inc(&ecryptfs_num_miscdev_opens); out_unlock_daemon: mutex_unlock(&daemon->mux); @@ -152,9 +156,9 @@ ecryptfs_miscdev_release(struct inode *inode, struct file *file) mutex_lock(&ecryptfs_daemon_hash_mux); rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) + daemon = file->private_data; mutex_lock(&daemon->mux); - BUG_ON(daemon->pid != task_pid(current)); BUG_ON(!(daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN)); daemon->flags &= ~ECRYPTFS_DAEMON_MISCDEV_OPEN; atomic_dec(&ecryptfs_num_miscdev_opens); @@ -191,31 +195,32 @@ int ecryptfs_send_miscdev(char *data, size_t data_size, struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type, u16 msg_flags, struct ecryptfs_daemon *daemon) { - int rc = 0; + struct ecryptfs_message *msg; - mutex_lock(&msg_ctx->mux); - msg_ctx->msg = kmalloc((sizeof(*msg_ctx->msg) + data_size), - GFP_KERNEL); - if (!msg_ctx->msg) { - rc = -ENOMEM; + msg = kmalloc((sizeof(*msg) + data_size), GFP_KERNEL); + if (!msg) { printk(KERN_ERR "%s: Out of memory whilst attempting " "to kmalloc(%zd, GFP_KERNEL)\n", __func__, - (sizeof(*msg_ctx->msg) + data_size)); - goto out_unlock; + (sizeof(*msg) + data_size)); + return -ENOMEM; } + + mutex_lock(&msg_ctx->mux); + msg_ctx->msg = msg; msg_ctx->msg->index = msg_ctx->index; msg_ctx->msg->data_len = data_size; msg_ctx->type = msg_type; memcpy(msg_ctx->msg->data, data, data_size); msg_ctx->msg_size = (sizeof(*msg_ctx->msg) + data_size); - mutex_lock(&daemon->mux); list_add_tail(&msg_ctx->daemon_out_list, &daemon->msg_ctx_out_queue); + mutex_unlock(&msg_ctx->mux); + + mutex_lock(&daemon->mux); daemon->num_queued_msg_ctx++; wake_up_interruptible(&daemon->wait); mutex_unlock(&daemon->mux); -out_unlock: - mutex_unlock(&msg_ctx->mux); - return rc; + + return 0; } /* @@ -269,8 +274,16 @@ ecryptfs_miscdev_read(struct file *file, char __user *buf, size_t count, mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) { + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EINVAL; + } mutex_lock(&daemon->mux); + if (task_pid(current) != daemon->pid) { + mutex_unlock(&daemon->mux); + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EPERM; + } if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { rc = 0; mutex_unlock(&ecryptfs_daemon_hash_mux); @@ -307,9 +320,6 @@ check_list: * message from the queue; try again */ goto check_list; } - BUG_ON(euid != daemon->euid); - BUG_ON(current_user_ns() != daemon->user_ns); - BUG_ON(task_pid(current) != daemon->pid); msg_ctx = list_first_entry(&daemon->msg_ctx_out_queue, struct ecryptfs_msg_ctx, daemon_out_list); BUG_ON(!msg_ctx); diff --git a/fs/efs/efs.h b/fs/efs/efs.h index d8305b5..5528926 100644 --- a/fs/efs/efs.h +++ b/fs/efs/efs.h @@ -129,7 +129,7 @@ extern struct inode *efs_iget(struct super_block *, unsigned long); extern efs_block_t efs_map_block(struct inode *, efs_block_t); extern int efs_get_block(struct inode *, sector_t, struct buffer_head *, int); -extern struct dentry *efs_lookup(struct inode *, struct dentry *, struct nameidata *); +extern struct dentry *efs_lookup(struct inode *, struct dentry *, unsigned int); extern struct dentry *efs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); extern struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid, diff --git a/fs/efs/namei.c b/fs/efs/namei.c index 832b10d..96f66d2 100644 --- a/fs/efs/namei.c +++ b/fs/efs/namei.c @@ -58,7 +58,8 @@ static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len) return(0); } -struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { +struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ efs_ino_t inodenum; struct inode *inode = NULL; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 74598f6..1c8b556 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1710,7 +1710,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ - if ((epds.events & EPOLLWAKEUP) && !capable(CAP_EPOLLWAKEUP)) + if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) epds.events &= ~EPOLLWAKEUP; /* @@ -819,10 +819,10 @@ static int exec_mmap(struct mm_struct *mm) /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; - sync_mm_rss(old_mm); mm_release(tsk, old_mm); if (old_mm) { + sync_mm_rss(old_mm); /* * Make sure that if there is a core dump in progress * for the old mm, we get out and die instead of going diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index fc7161d..4731fd9 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -46,7 +46,7 @@ static inline int exofs_add_nondir(struct dentry *dentry, struct inode *inode) } static struct dentry *exofs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode; ino_t ino; @@ -60,7 +60,7 @@ static struct dentry *exofs_lookup(struct inode *dir, struct dentry *dentry, } static int exofs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode = exofs_new_inode(dir, mode); int err = PTR_ERR(inode); diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c index 49cf230..24a49d4 100644 --- a/fs/exofs/ore.c +++ b/fs/exofs/ore.c @@ -735,13 +735,7 @@ static int _prepare_for_striping(struct ore_io_state *ios) out: ios->numdevs = devs_in_group; ios->pages_consumed = cur_pg; - if (unlikely(ret)) { - if (length == ios->length) - return ret; - else - ios->length -= length; - } - return 0; + return ret; } int ore_create(struct ore_io_state *ios) diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c index d222c77..5f376d1 100644 --- a/fs/exofs/ore_raid.c +++ b/fs/exofs/ore_raid.c @@ -144,26 +144,26 @@ static void _sp2d_reset(struct __stripe_pages_2d *sp2d, { unsigned data_devs = sp2d->data_devs; unsigned group_width = data_devs + sp2d->parity; - unsigned p; + int p, c; if (!sp2d->needed) return; - for (p = 0; p < sp2d->pages_in_unit; p++) { - struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; - - if (_1ps->write_count < group_width) { - unsigned c; + for (c = data_devs - 1; c >= 0; --c) + for (p = sp2d->pages_in_unit - 1; p >= 0; --p) { + struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; - for (c = 0; c < data_devs; c++) - if (_1ps->page_is_read[c]) { - struct page *page = _1ps->pages[c]; + if (_1ps->page_is_read[c]) { + struct page *page = _1ps->pages[c]; - r4w->put_page(priv, page); - _1ps->page_is_read[c] = false; - } + r4w->put_page(priv, page); + _1ps->page_is_read[c] = false; + } } + for (p = 0; p < sp2d->pages_in_unit; p++) { + struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; + memset(_1ps->pages, 0, group_width * sizeof(*_1ps->pages)); _1ps->write_count = 0; _1ps->tx = NULL; @@ -461,16 +461,12 @@ static void _mark_read4write_pages_uptodate(struct ore_io_state *ios, int ret) * ios->sp2d[p][*], xor is calculated the same way. These pages are * allocated/freed and don't go through cache */ -static int _read_4_write(struct ore_io_state *ios) +static int _read_4_write_first_stripe(struct ore_io_state *ios) { - struct ore_io_state *ios_read; struct ore_striping_info read_si; struct __stripe_pages_2d *sp2d = ios->sp2d; u64 offset = ios->si.first_stripe_start; - u64 last_stripe_end; - unsigned bytes_in_stripe = ios->si.bytes_in_stripe; - unsigned i, c, p, min_p = sp2d->pages_in_unit, max_p = -1; - int ret; + unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1; if (offset == ios->offset) /* Go to start collect $200 */ goto read_last_stripe; @@ -478,6 +474,9 @@ static int _read_4_write(struct ore_io_state *ios) min_p = _sp2d_min_pg(sp2d); max_p = _sp2d_max_pg(sp2d); + ORE_DBGMSG("stripe_start=0x%llx ios->offset=0x%llx min_p=%d max_p=%d\n", + offset, ios->offset, min_p, max_p); + for (c = 0; ; c++) { ore_calc_stripe_info(ios->layout, offset, 0, &read_si); read_si.obj_offset += min_p * PAGE_SIZE; @@ -512,6 +511,18 @@ static int _read_4_write(struct ore_io_state *ios) } read_last_stripe: + return 0; +} + +static int _read_4_write_last_stripe(struct ore_io_state *ios) +{ + struct ore_striping_info read_si; + struct __stripe_pages_2d *sp2d = ios->sp2d; + u64 offset; + u64 last_stripe_end; + unsigned bytes_in_stripe = ios->si.bytes_in_stripe; + unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1; + offset = ios->offset + ios->length; if (offset % PAGE_SIZE) _add_to_r4w_last_page(ios, &offset); @@ -527,15 +538,15 @@ read_last_stripe: c = _dev_order(ios->layout->group_width * ios->layout->mirrors_p1, ios->layout->mirrors_p1, read_si.par_dev, read_si.dev); - BUG_ON(ios->si.first_stripe_start + bytes_in_stripe != last_stripe_end); - /* unaligned IO must be within a single stripe */ - if (min_p == sp2d->pages_in_unit) { /* Didn't do it yet */ min_p = _sp2d_min_pg(sp2d); max_p = _sp2d_max_pg(sp2d); } + ORE_DBGMSG("offset=0x%llx stripe_end=0x%llx min_p=%d max_p=%d\n", + offset, last_stripe_end, min_p, max_p); + while (offset < last_stripe_end) { struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; @@ -568,6 +579,15 @@ read_last_stripe: } read_it: + return 0; +} + +static int _read_4_write_execute(struct ore_io_state *ios) +{ + struct ore_io_state *ios_read; + unsigned i; + int ret; + ios_read = ios->ios_read_4_write; if (!ios_read) return 0; @@ -591,6 +611,8 @@ read_it: } _mark_read4write_pages_uptodate(ios_read, ret); + ore_put_io_state(ios_read); + ios->ios_read_4_write = NULL; /* Might need a reuse at last stripe */ return 0; } @@ -626,8 +648,11 @@ int _ore_add_parity_unit(struct ore_io_state *ios, /* If first stripe, Read in all read4write pages * (if needed) before we calculate the first parity. */ - _read_4_write(ios); + _read_4_write_first_stripe(ios); } + if (!cur_len) /* If last stripe r4w pages of last stripe */ + _read_4_write_last_stripe(ios); + _read_4_write_execute(ios); for (i = 0; i < num_pages; i++) { pages[i] = _raid_page_alloc(); @@ -654,34 +679,14 @@ int _ore_add_parity_unit(struct ore_io_state *ios, int _ore_post_alloc_raid_stuff(struct ore_io_state *ios) { - struct ore_layout *layout = ios->layout; - if (ios->parity_pages) { + struct ore_layout *layout = ios->layout; unsigned pages_in_unit = layout->stripe_unit / PAGE_SIZE; - unsigned stripe_size = ios->si.bytes_in_stripe; - u64 last_stripe, first_stripe; if (_sp2d_alloc(pages_in_unit, layout->group_width, layout->parity, &ios->sp2d)) { return -ENOMEM; } - - /* Round io down to last full strip */ - first_stripe = div_u64(ios->offset, stripe_size); - last_stripe = div_u64(ios->offset + ios->length, stripe_size); - - /* If an IO spans more then a single stripe it must end at - * a stripe boundary. The reminder at the end is pushed into the - * next IO. - */ - if (last_stripe != first_stripe) { - ios->length = last_stripe * stripe_size - ios->offset; - - BUG_ON(!ios->length); - ios->nr_pages = (ios->length + PAGE_SIZE - 1) / - PAGE_SIZE; - ios->si.length = ios->length; /*make it consistent */ - } } return 0; } diff --git a/fs/exofs/sys.c b/fs/exofs/sys.c index e32bc91..5a7b691 100644 --- a/fs/exofs/sys.c +++ b/fs/exofs/sys.c @@ -109,7 +109,7 @@ static struct kobj_type odev_ktype = { static struct kobj_type uuid_ktype = { }; -void exofs_sysfs_dbg_print() +void exofs_sysfs_dbg_print(void) { #ifdef CONFIG_EXOFS_DEBUG struct kobject *k_name, *k_tmp; diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index b0201ca..29ab099 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -19,19 +19,19 @@ #define dprintk(fmt, args...) do{}while(0) -static int get_name(struct vfsmount *mnt, struct dentry *dentry, char *name, - struct dentry *child); +static int get_name(const struct path *path, char *name, struct dentry *child); static int exportfs_get_name(struct vfsmount *mnt, struct dentry *dir, char *name, struct dentry *child) { const struct export_operations *nop = dir->d_sb->s_export_op; + struct path path = {.mnt = mnt, .dentry = dir}; if (nop->get_name) return nop->get_name(dir, name, child); else - return get_name(mnt, dir, name, child); + return get_name(&path, name, child); } /* @@ -44,13 +44,14 @@ find_acceptable_alias(struct dentry *result, { struct dentry *dentry, *toput = NULL; struct inode *inode; + struct hlist_node *p; if (acceptable(context, result)) return result; inode = result->d_inode; spin_lock(&inode->i_lock); - list_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { dget(dentry); spin_unlock(&inode->i_lock); if (toput) @@ -248,11 +249,10 @@ static int filldir_one(void * __buf, const char * name, int len, * calls readdir on the parent until it finds an entry with * the same inode number as the child, and returns that. */ -static int get_name(struct vfsmount *mnt, struct dentry *dentry, - char *name, struct dentry *child) +static int get_name(const struct path *path, char *name, struct dentry *child) { const struct cred *cred = current_cred(); - struct inode *dir = dentry->d_inode; + struct inode *dir = path->dentry->d_inode; int error; struct file *file; struct getdents_callback buffer; @@ -266,7 +266,7 @@ static int get_name(struct vfsmount *mnt, struct dentry *dentry, /* * Open the directory ... */ - file = dentry_open(dget(dentry), mntget(mnt), O_RDONLY, cred); + file = dentry_open(path, O_RDONLY, cred); error = PTR_ERR(file); if (IS_ERR(file)) goto out; diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index f663a67..73b0d95 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -41,8 +41,8 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode) { int err = ext2_add_link(dentry, inode); if (!err) { - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; } inode_dec_link_count(inode); @@ -55,7 +55,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode) * Methods themselves. */ -static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags) { struct inode * inode; ino_t ino; @@ -94,7 +94,7 @@ struct dentry *ext2_get_parent(struct dentry *child) * If the create succeeds, we fill in the inode information * with d_instantiate(). */ -static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, struct nameidata *nd) +static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, bool excl) { struct inode *inode; @@ -242,8 +242,8 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) if (err) goto out_fail; - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); out: return err; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index b3621cb..5df3d2d 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1184,6 +1184,12 @@ static int ext2_sync_fs(struct super_block *sb, int wait) struct ext2_sb_info *sbi = EXT2_SB(sb); struct ext2_super_block *es = EXT2_SB(sb)->s_es; + /* + * Write quota structures to quota file, sync_blockdev() will write + * them to disk later + */ + dquot_writeback_dquots(sb, -1); + spin_lock(&sbi->s_lock); if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) { ext2_debug("setting valid to 0\n"); diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index 92490e9..c8fff93 100644 --- a/fs/ext3/dir.c +++ b/fs/ext3/dir.c @@ -300,10 +300,11 @@ loff_t ext3_dir_llseek(struct file *file, loff_t offset, int origin) { struct inode *inode = file->f_mapping->host; int dx_dir = is_dx_dir(inode); + loff_t htree_max = ext3_get_htree_eof(file); if (likely(dx_dir)) return generic_file_llseek_size(file, offset, origin, - ext3_get_htree_eof(file)); + htree_max, htree_max); else return generic_file_llseek(file, offset, origin); } diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index eeb63df..8f4fdda 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1011,7 +1011,7 @@ errout: return NULL; } -static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags) { struct inode * inode; struct ext3_dir_entry_2 * de; @@ -1671,8 +1671,8 @@ static int ext3_add_nondir(handle_t *handle, int err = ext3_add_entry(handle, dentry, inode); if (!err) { ext3_mark_inode_dirty(handle, inode); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; } drop_nlink(inode); @@ -1690,7 +1690,7 @@ static int ext3_add_nondir(handle_t *handle, * with d_instantiate(). */ static int ext3_create (struct inode * dir, struct dentry * dentry, umode_t mode, - struct nameidata *nd) + bool excl) { handle_t *handle; struct inode * inode; @@ -1836,8 +1836,8 @@ out_clear_inode: if (err) goto out_clear_inode; - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); out_stop: brelse(dir_block); ext3_journal_stop(handle); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 8c3a44b..4ac304c 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2526,6 +2526,11 @@ static int ext3_sync_fs(struct super_block *sb, int wait) tid_t target; trace_ext3_sync_fs(sb, wait); + /* + * Writeback quota in non-journalled quota case - journalled quota has + * no dirty dquots + */ + dquot_writeback_dquots(sb, -1); if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) { if (wait) log_wait_commit(EXT3_SB(sb)->s_journal, target); diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 99b6324..cee7812 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -90,8 +90,8 @@ unsigned ext4_num_overhead_clusters(struct super_block *sb, * unusual file system layouts. */ if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) { - block_cluster = EXT4_B2C(sbi, (start - - ext4_block_bitmap(sb, gdp))); + block_cluster = EXT4_B2C(sbi, + ext4_block_bitmap(sb, gdp) - start); if (block_cluster < num_clusters) block_cluster = -1; else if (block_cluster == num_clusters) { @@ -102,7 +102,7 @@ unsigned ext4_num_overhead_clusters(struct super_block *sb, if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) { inode_cluster = EXT4_B2C(sbi, - start - ext4_inode_bitmap(sb, gdp)); + ext4_inode_bitmap(sb, gdp) - start); if (inode_cluster < num_clusters) inode_cluster = -1; else if (inode_cluster == num_clusters) { @@ -114,7 +114,7 @@ unsigned ext4_num_overhead_clusters(struct super_block *sb, itbl_blk = ext4_inode_table(sb, gdp); for (i = 0; i < sbi->s_itb_per_group; i++) { if (ext4_block_in_group(sb, itbl_blk + i, block_group)) { - c = EXT4_B2C(sbi, start - itbl_blk + i); + c = EXT4_B2C(sbi, itbl_blk + i - start); if ((c < num_clusters) || (c == inode_cluster) || (c == block_cluster) || (c == itbl_cluster)) continue; diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index aa39e60..8e07d2a 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -324,74 +324,27 @@ static inline loff_t ext4_get_htree_eof(struct file *filp) /* - * ext4_dir_llseek() based on generic_file_llseek() to handle both - * non-htree and htree directories, where the "offset" is in terms - * of the filename hash value instead of the byte offset. + * ext4_dir_llseek() calls generic_file_llseek_size to handle htree + * directories, where the "offset" is in terms of the filename hash + * value instead of the byte offset. * - * NOTE: offsets obtained *before* ext4_set_inode_flag(dir, EXT4_INODE_INDEX) - * will be invalid once the directory was converted into a dx directory + * Because we may return a 64-bit hash that is well beyond offset limits, + * we need to pass the max hash as the maximum allowable offset in + * the htree directory case. + * + * For non-htree, ext4_llseek already chooses the proper max offset. */ loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin) { struct inode *inode = file->f_mapping->host; - loff_t ret = -EINVAL; int dx_dir = is_dx_dir(inode); + loff_t htree_max = ext4_get_htree_eof(file); - mutex_lock(&inode->i_mutex); - - /* NOTE: relative offsets with dx directories might not work - * as expected, as it is difficult to figure out the - * correct offset between dx hashes */ - - switch (origin) { - case SEEK_END: - if (unlikely(offset > 0)) - goto out_err; /* not supported for directories */ - - /* so only negative offsets are left, does that have a - * meaning for directories at all? */ - if (dx_dir) - offset += ext4_get_htree_eof(file); - else - offset += inode->i_size; - break; - case SEEK_CUR: - /* - * Here we special-case the lseek(fd, 0, SEEK_CUR) - * position-querying operation. Avoid rewriting the "same" - * f_pos value back to the file because a concurrent read(), - * write() or lseek() might have altered it - */ - if (offset == 0) { - offset = file->f_pos; - goto out_ok; - } - - offset += file->f_pos; - break; - } - - if (unlikely(offset < 0)) - goto out_err; - - if (!dx_dir) { - if (offset > inode->i_sb->s_maxbytes) - goto out_err; - } else if (offset > ext4_get_htree_eof(file)) - goto out_err; - - /* Special lock needed here? */ - if (offset != file->f_pos) { - file->f_pos = offset; - file->f_version = 0; - } - -out_ok: - ret = offset; -out_err: - mutex_unlock(&inode->i_mutex); - - return ret; + if (likely(dx_dir)) + return generic_file_llseek_size(file, offset, origin, + htree_max, htree_max); + else + return ext4_llseek(file, offset, origin); } /* diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 8c7642a..782eecb 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -211,9 +211,9 @@ static int ext4_file_open(struct inode * inode, struct file * filp) } /* - * ext4_llseek() copied from generic_file_llseek() to handle both - * block-mapped and extent-mapped maxbytes values. This should - * otherwise be identical with generic_file_llseek(). + * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values + * by calling generic_file_llseek_size() with the appropriate maxbytes + * value for each. */ loff_t ext4_llseek(struct file *file, loff_t offset, int origin) { @@ -225,7 +225,8 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin) else maxbytes = inode->i_sb->s_maxbytes; - return generic_file_llseek_size(file, offset, origin, maxbytes); + return generic_file_llseek_size(file, offset, origin, + maxbytes, i_size_read(inode)); } const struct file_operations ext4_file_operations = { diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index bb6c7d8..2a1dcea 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -135,14 +135,7 @@ static int ext4_sync_parent(struct inode *inode) inode = igrab(inode); while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); - dentry = NULL; - spin_lock(&inode->i_lock); - if (!list_empty(&inode->i_dentry)) { - dentry = list_first_entry(&inode->i_dentry, - struct dentry, d_alias); - dget(dentry); - } - spin_unlock(&inode->i_lock); + dentry = d_find_any_alias(inode); if (!dentry) break; next = igrab(dentry->d_parent->d_inode); @@ -232,7 +225,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (!journal) { ret = __sync_inode(inode, datasync); - if (!ret && !list_empty(&inode->i_dentry)) + if (!ret && !hlist_empty(&inode->i_dentry)) ret = ext4_sync_parent(inode); goto out; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 8ad112a..7f7dad7 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -123,7 +123,6 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) else ext4_clear_inode_flag(inode, i); } - ei->i_flags = flags; ext4_set_inode_flags(inode); inode->i_ctime = ext4_current_time(inode); @@ -269,7 +268,6 @@ group_extend_out: err = ext4_move_extents(filp, donor_filp, me.orig_start, me.donor_start, me.len, &me.moved_len); mnt_drop_write_file(filp); - mnt_drop_write(filp->f_path.mnt); if (copy_to_user((struct move_extent __user *)arg, &me, sizeof(me))) @@ -391,7 +389,7 @@ group_add_out: if (err) return err; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) goto resizefs_out; @@ -403,7 +401,7 @@ group_add_out: } if (err == 0) err = err2; - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); resizefs_out: ext4_resize_end(sb); return err; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 5845cd9..d0d3f0e 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1312,7 +1312,7 @@ errout: return NULL; } -static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; struct ext4_dir_entry_2 *de; @@ -2072,8 +2072,8 @@ static int ext4_add_nondir(handle_t *handle, int err = ext4_add_entry(handle, dentry, inode); if (!err) { ext4_mark_inode_dirty(handle, inode); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; } drop_nlink(inode); @@ -2091,7 +2091,7 @@ static int ext4_add_nondir(handle_t *handle, * with d_instantiate(). */ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { handle_t *handle; struct inode *inode; @@ -2249,8 +2249,8 @@ out_clear_inode: err = ext4_mark_inode_dirty(handle, dir); if (err) goto out_clear_inode; - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); out_stop: brelse(dir_block); ext4_journal_stop(handle); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index eb7aa3e..d875940 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4325,6 +4325,11 @@ static int ext4_sync_fs(struct super_block *sb, int wait) trace_ext4_sync_fs(sb, wait); flush_workqueue(sbi->dio_unwritten_wq); + /* + * Writeback quota in non-journalled quota case - journalled quota has + * no dirty dquots + */ + dquot_writeback_dquots(sb, -1); if (jbd2_journal_start_commit(sbi->s_journal, &target)) { if (wait) jbd2_log_wait_commit(sbi->s_journal, target); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index a3d81eb..0038b32 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -738,22 +738,21 @@ static int fat_encode_fh(struct inode *inode, __u32 *fh, int *lenp, struct inode *parent) { int len = *lenp; - u32 ipos_h, ipos_m, ipos_l; + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + loff_t i_pos; if (len < 5) { *lenp = 5; return 255; /* no room */ } - ipos_h = MSDOS_I(inode)->i_pos >> 8; - ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24; - ipos_l = (MSDOS_I(inode)->i_pos & 0x0f) << 28; + i_pos = fat_i_pos_read(sbi, inode); *lenp = 5; fh[0] = inode->i_ino; fh[1] = inode->i_generation; - fh[2] = ipos_h; - fh[3] = ipos_m | MSDOS_I(inode)->i_logstart; - fh[4] = ipos_l; + fh[2] = i_pos >> 8; + fh[3] = ((i_pos & 0xf0) << 24) | MSDOS_I(inode)->i_logstart; + fh[4] = (i_pos & 0x0f) << 28; if (parent) fh[4] |= MSDOS_I(parent)->i_logstart; return 3; diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index c5938c9..70d993a 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -201,7 +201,7 @@ static const struct dentry_operations msdos_dentry_operations = { /***** Get inode using directory and name */ static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; @@ -265,7 +265,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name, /***** Create a file */ static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode = NULL; diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 98ae804..6cc4806 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -41,9 +41,9 @@ static int vfat_revalidate_shortname(struct dentry *dentry) return ret; } -static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd) +static int vfat_revalidate(struct dentry *dentry, unsigned int flags) { - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; /* This is not negative dentry. Always valid. */ @@ -52,9 +52,9 @@ static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd) return vfat_revalidate_shortname(dentry); } -static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd) +static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) { - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; /* @@ -74,7 +74,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd) * This may be nfsd (or something), anyway, we can't see the * intent of this. So, since this can be for creation, drop it. */ - if (!nd) + if (!flags) return 0; /* @@ -82,7 +82,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd) * case sensitive name which is specified by user if this is * for creation. */ - if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) + if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; return vfat_revalidate_shortname(dentry); @@ -714,7 +714,7 @@ static int vfat_d_anon_disconn(struct dentry *dentry) } static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; @@ -772,7 +772,7 @@ error: } static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode; @@ -14,7 +14,7 @@ #include <linux/sched.h> #include <linux/pipe_fs_i.h> -static void wait_for_partner(struct inode* inode, unsigned int *cnt) +static int wait_for_partner(struct inode* inode, unsigned int *cnt) { int cur = *cnt; @@ -23,6 +23,7 @@ static void wait_for_partner(struct inode* inode, unsigned int *cnt) if (signal_pending(current)) break; } + return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct inode* inode) @@ -67,8 +68,7 @@ static int fifo_open(struct inode *inode, struct file *filp) * seen a writer */ filp->f_version = pipe->w_counter; } else { - wait_for_partner(inode, &pipe->w_counter); - if(signal_pending(current)) + if (wait_for_partner(inode, &pipe->w_counter)) goto err_rd; } } @@ -90,8 +90,7 @@ static int fifo_open(struct inode *inode, struct file *filp) wake_up_partner(inode); if (!pipe->readers) { - wait_for_partner(inode, &pipe->r_counter); - if (signal_pending(current)) + if (wait_for_partner(inode, &pipe->r_counter)) goto err_wr; } break; diff --git a/fs/file_table.c b/fs/file_table.c index a305d9e..b3fc4d6 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -23,6 +23,8 @@ #include <linux/lglock.h> #include <linux/percpu_counter.h> #include <linux/percpu.h> +#include <linux/hardirq.h> +#include <linux/task_work.h> #include <linux/ima.h> #include <linux/atomic.h> @@ -251,7 +253,6 @@ static void __fput(struct file *file) } fops_put(file->f_op); put_pid(file->f_owner.pid); - file_sb_list_del(file); if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_dec(inode); if (file->f_mode & FMODE_WRITE) @@ -263,10 +264,77 @@ static void __fput(struct file *file) mntput(mnt); } +static DEFINE_SPINLOCK(delayed_fput_lock); +static LIST_HEAD(delayed_fput_list); +static void delayed_fput(struct work_struct *unused) +{ + LIST_HEAD(head); + spin_lock_irq(&delayed_fput_lock); + list_splice_init(&delayed_fput_list, &head); + spin_unlock_irq(&delayed_fput_lock); + while (!list_empty(&head)) { + struct file *f = list_first_entry(&head, struct file, f_u.fu_list); + list_del_init(&f->f_u.fu_list); + __fput(f); + } +} + +static void ____fput(struct callback_head *work) +{ + __fput(container_of(work, struct file, f_u.fu_rcuhead)); +} + +/* + * If kernel thread really needs to have the final fput() it has done + * to complete, call this. The only user right now is the boot - we + * *do* need to make sure our writes to binaries on initramfs has + * not left us with opened struct file waiting for __fput() - execve() + * won't work without that. Please, don't add more callers without + * very good reasons; in particular, never call that with locks + * held and never call that from a thread that might need to do + * some work on any kind of umount. + */ +void flush_delayed_fput(void) +{ + delayed_fput(NULL); +} + +static DECLARE_WORK(delayed_fput_work, delayed_fput); + void fput(struct file *file) { - if (atomic_long_dec_and_test(&file->f_count)) + if (atomic_long_dec_and_test(&file->f_count)) { + struct task_struct *task = current; + file_sb_list_del(file); + if (unlikely(in_interrupt() || task->flags & PF_KTHREAD)) { + unsigned long flags; + spin_lock_irqsave(&delayed_fput_lock, flags); + list_add(&file->f_u.fu_list, &delayed_fput_list); + schedule_work(&delayed_fput_work); + spin_unlock_irqrestore(&delayed_fput_lock, flags); + return; + } + init_task_work(&file->f_u.fu_rcuhead, ____fput); + task_work_add(task, &file->f_u.fu_rcuhead, true); + } +} + +/* + * synchronous analog of fput(); for kernel threads that might be needed + * in some umount() (and thus can't use flush_delayed_fput() without + * risking deadlocks), need to wait for completion of __fput() and know + * for this specific struct file it won't involve anything that would + * need them. Use only if you really need it - at the very least, + * don't blindly convert fput() by kernel thread to that. + */ +void __fput_sync(struct file *file) +{ + if (atomic_long_dec_and_test(&file->f_count)) { + struct task_struct *task = current; + file_sb_list_del(file); + BUG_ON(!(task->flags & PF_KTHREAD)); __fput(file); + } } EXPORT_SYMBOL(fput); @@ -483,10 +551,8 @@ void mark_files_ro(struct super_block *sb) { struct file *f; -retry: lg_global_lock(&files_lglock); do_file_list_for_each_entry(sb, f) { - struct vfsmount *mnt; if (!S_ISREG(f->f_path.dentry->d_inode->i_mode)) continue; if (!file_count(f)) @@ -499,12 +565,7 @@ retry: if (file_check_writeable(f) != 0) continue; file_release_write(f); - mnt = mntget(f->f_path.mnt); - /* This can sleep, so we can't hold the spinlock. */ - lg_global_unlock(&files_lglock); - mnt_drop_write(mnt); - mntput(mnt); - goto retry; + mnt_drop_write_file(f); } while_file_list_for_each_entry; lg_global_unlock(&files_lglock); } diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c index 3360f1e..bd447e8 100644 --- a/fs/freevxfs/vxfs_lookup.c +++ b/fs/freevxfs/vxfs_lookup.c @@ -48,7 +48,7 @@ #define VXFS_BLOCK_PER_PAGE(sbp) ((PAGE_CACHE_SIZE / (sbp)->s_blocksize)) -static struct dentry * vxfs_lookup(struct inode *, struct dentry *, struct nameidata *); +static struct dentry * vxfs_lookup(struct inode *, struct dentry *, unsigned int); static int vxfs_readdir(struct file *, void *, filldir_t); const struct inode_operations vxfs_dir_inode_ops = { @@ -203,7 +203,7 @@ vxfs_inode_by_name(struct inode *dip, struct dentry *dp) * in the return pointer. */ static struct dentry * -vxfs_lookup(struct inode *dip, struct dentry *dp, struct nameidata *nd) +vxfs_lookup(struct inode *dip, struct dentry *dp, unsigned int flags) { struct inode *ip = NULL; ino_t ino; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8d2fb8c..8f660dd 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -664,6 +664,7 @@ static long writeback_sb_inodes(struct super_block *sb, /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ + spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; @@ -1314,6 +1315,8 @@ void writeback_inodes_sb_nr(struct super_block *sb, .reason = reason, }; + if (sb->s_bdi == &noop_backing_dev_info) + return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_queue_work(sb->s_bdi, &work); wait_for_completion(&done); @@ -1397,6 +1400,9 @@ void sync_inodes_sb(struct super_block *sb) .reason = WB_REASON_SYNC, }; + /* Nothing to do? */ + if (sb->s_bdi == &noop_backing_dev_info) + return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_queue_work(sb->s_bdi, &work); diff --git a/fs/fs_struct.c b/fs/fs_struct.c index e159e68..5df4775 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -6,18 +6,6 @@ #include <linux/fs_struct.h> #include "internal.h" -static inline void path_get_longterm(struct path *path) -{ - path_get(path); - mnt_make_longterm(path->mnt); -} - -static inline void path_put_longterm(struct path *path) -{ - mnt_make_shortterm(path->mnt); - path_put(path); -} - /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. @@ -26,7 +14,7 @@ void set_fs_root(struct fs_struct *fs, struct path *path) { struct path old_root; - path_get_longterm(path); + path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_root = fs->root; @@ -34,7 +22,7 @@ void set_fs_root(struct fs_struct *fs, struct path *path) write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_root.dentry) - path_put_longterm(&old_root); + path_put(&old_root); } /* @@ -45,7 +33,7 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path) { struct path old_pwd; - path_get_longterm(path); + path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_pwd = fs->pwd; @@ -54,7 +42,7 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path) spin_unlock(&fs->lock); if (old_pwd.dentry) - path_put_longterm(&old_pwd); + path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) @@ -84,7 +72,7 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root) write_seqcount_end(&fs->seq); while (hits--) { count++; - path_get_longterm(new_root); + path_get(new_root); } spin_unlock(&fs->lock); } @@ -92,13 +80,13 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root) } while_each_thread(g, p); read_unlock(&tasklist_lock); while (count--) - path_put_longterm(old_root); + path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { - path_put_longterm(&fs->root); - path_put_longterm(&fs->pwd); + path_put(&fs->root); + path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } @@ -132,9 +120,9 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old) spin_lock(&old->lock); fs->root = old->root; - path_get_longterm(&fs->root); + path_get(&fs->root); fs->pwd = old->pwd; - path_get_longterm(&fs->pwd); + path_get(&fs->pwd); spin_unlock(&old->lock); } return fs; diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 42593c5..03ff5b1 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -75,19 +75,13 @@ static ssize_t fuse_conn_limit_write(struct file *file, const char __user *buf, unsigned global_limit) { unsigned long t; - char tmp[32]; unsigned limit = (1 << 16) - 1; int err; - if (*ppos || count >= sizeof(tmp) - 1) - return -EINVAL; - - if (copy_from_user(tmp, buf, count)) + if (*ppos) return -EINVAL; - tmp[count] = '\0'; - - err = strict_strtoul(tmp, 0, &t); + err = kstrtoul_from_user(buf, count, 0, &t); if (err) return err; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index df5ac04..8964cf3 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -154,7 +154,7 @@ u64 fuse_get_attr_version(struct fuse_conn *fc) * the lookup once more. If the lookup results in the same inode, * then refresh the attributes, timeouts and mark the dentry valid. */ -static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) +static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) { struct inode *inode; @@ -174,7 +174,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) if (!inode) return 0; - if (nd && (nd->flags & LOOKUP_RCU)) + if (flags & LOOKUP_RCU) return -ECHILD; fc = get_fuse_conn(inode); @@ -249,7 +249,7 @@ static struct dentry *fuse_d_add_directory(struct dentry *entry, /* This tries to shrink the subtree below alias */ fuse_invalidate_entry(alias); dput(alias); - if (!list_empty(&inode->i_dentry)) + if (!hlist_empty(&inode->i_dentry)) return ERR_PTR(-EBUSY); } else { dput(alias); @@ -316,7 +316,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name, } static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, - struct nameidata *nd) + unsigned int flags) { int err; struct fuse_entry_out outarg; @@ -370,7 +370,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, * 'mknod' + 'open' requests. */ static int fuse_create_open(struct inode *dir, struct dentry *entry, - umode_t mode, struct nameidata *nd) + struct file *file, unsigned flags, + umode_t mode, int *opened) { int err; struct inode *inode; @@ -381,15 +382,11 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, struct fuse_open_out outopen; struct fuse_entry_out outentry; struct fuse_file *ff; - struct file *file; - int flags = nd->intent.open.flags; - - if (fc->no_create) - return -ENOSYS; forget = fuse_alloc_forget(); + err = -ENOMEM; if (!forget) - return -ENOMEM; + goto out_err; req = fuse_get_req(fc); err = PTR_ERR(req); @@ -428,11 +425,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, req->out.args[1].value = &outopen; fuse_request_send(fc, req); err = req->out.h.error; - if (err) { - if (err == -ENOSYS) - fc->no_create = 1; + if (err) goto out_free_ff; - } err = -EIO; if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid)) @@ -448,28 +442,74 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, flags &= ~(O_CREAT | O_EXCL | O_TRUNC); fuse_sync_release(ff, flags); fuse_queue_forget(fc, forget, outentry.nodeid, 1); - return -ENOMEM; + err = -ENOMEM; + goto out_err; } kfree(forget); d_instantiate(entry, inode); fuse_change_entry_timeout(entry, &outentry); fuse_invalidate_attr(dir); - file = lookup_instantiate_filp(nd, entry, generic_file_open); - if (IS_ERR(file)) { + err = finish_open(file, entry, generic_file_open, opened); + if (err) { fuse_sync_release(ff, flags); - return PTR_ERR(file); + } else { + file->private_data = fuse_file_get(ff); + fuse_finish_open(inode, file); } - file->private_data = fuse_file_get(ff); - fuse_finish_open(inode, file); - return 0; + return err; - out_free_ff: +out_free_ff: fuse_file_free(ff); - out_put_request: +out_put_request: fuse_put_request(fc, req); - out_put_forget_req: +out_put_forget_req: kfree(forget); +out_err: + return err; +} + +static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t); +static int fuse_atomic_open(struct inode *dir, struct dentry *entry, + struct file *file, unsigned flags, + umode_t mode, int *opened) +{ + int err; + struct fuse_conn *fc = get_fuse_conn(dir); + struct dentry *res = NULL; + + if (d_unhashed(entry)) { + res = fuse_lookup(dir, entry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + if (res) + entry = res; + } + + if (!(flags & O_CREAT) || entry->d_inode) + goto no_open; + + /* Only creates */ + *opened |= FILE_CREATED; + + if (fc->no_create) + goto mknod; + + err = fuse_create_open(dir, entry, file, flags, mode, opened); + if (err == -ENOSYS) { + fc->no_create = 1; + goto mknod; + } +out_dput: + dput(res); return err; + +mknod: + err = fuse_mknod(dir, entry, mode, 0); + if (err) + goto out_dput; +no_open: + return finish_no_open(file, res); } /* @@ -571,14 +611,8 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, umode_t mode, } static int fuse_create(struct inode *dir, struct dentry *entry, umode_t mode, - struct nameidata *nd) + bool excl) { - if (nd) { - int err = fuse_create_open(dir, entry, mode, nd); - if (err != -ENOSYS) - return err; - /* Fall back on mknod */ - } return fuse_mknod(dir, entry, mode, 0); } @@ -775,6 +809,8 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, struct kstat *stat) { + unsigned int blkbits; + stat->dev = inode->i_sb->s_dev; stat->ino = attr->ino; stat->mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777); @@ -790,7 +826,13 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, stat->ctime.tv_nsec = attr->ctimensec; stat->size = attr->size; stat->blocks = attr->blocks; - stat->blksize = (1 << inode->i_blkbits); + + if (attr->blksize != 0) + blkbits = ilog2(attr->blksize); + else + blkbits = inode->i_sb->s_blocksize_bits; + + stat->blksize = 1 << blkbits; } static int fuse_do_getattr(struct inode *inode, struct kstat *stat, @@ -863,6 +905,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat, if (stat) { generic_fillattr(inode, stat); stat->mode = fi->orig_i_mode; + stat->ino = fi->orig_ino; } } @@ -1637,6 +1680,7 @@ static const struct inode_operations fuse_dir_inode_operations = { .link = fuse_link, .setattr = fuse_setattr, .create = fuse_create, + .atomic_open = fuse_atomic_open, .mknod = fuse_mknod, .permission = fuse_permission, .getattr = fuse_getattr, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 9562109..b321a68 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2173,6 +2173,44 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, return ret; } +long fuse_file_fallocate(struct file *file, int mode, loff_t offset, + loff_t length) +{ + struct fuse_file *ff = file->private_data; + struct fuse_conn *fc = ff->fc; + struct fuse_req *req; + struct fuse_fallocate_in inarg = { + .fh = ff->fh, + .offset = offset, + .length = length, + .mode = mode + }; + int err; + + if (fc->no_fallocate) + return -EOPNOTSUPP; + + req = fuse_get_req(fc); + if (IS_ERR(req)) + return PTR_ERR(req); + + req->in.h.opcode = FUSE_FALLOCATE; + req->in.h.nodeid = ff->nodeid; + req->in.numargs = 1; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + fuse_request_send(fc, req); + err = req->out.h.error; + if (err == -ENOSYS) { + fc->no_fallocate = 1; + err = -EOPNOTSUPP; + } + fuse_put_request(fc, req); + + return err; +} +EXPORT_SYMBOL_GPL(fuse_file_fallocate); + static const struct file_operations fuse_file_operations = { .llseek = fuse_file_llseek, .read = do_sync_read, @@ -2190,6 +2228,7 @@ static const struct file_operations fuse_file_operations = { .unlocked_ioctl = fuse_file_ioctl, .compat_ioctl = fuse_file_compat_ioctl, .poll = fuse_file_poll, + .fallocate = fuse_file_fallocate, }; static const struct file_operations fuse_direct_io_file_operations = { @@ -2206,6 +2245,7 @@ static const struct file_operations fuse_direct_io_file_operations = { .unlocked_ioctl = fuse_file_ioctl, .compat_ioctl = fuse_file_compat_ioctl, .poll = fuse_file_poll, + .fallocate = fuse_file_fallocate, /* no splice_read */ }; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 572cefc..771fb63 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -82,6 +82,9 @@ struct fuse_inode { preserve the original mode */ umode_t orig_i_mode; + /** 64 bit inode number */ + u64 orig_ino; + /** Version of last attribute change */ u64 attr_version; @@ -478,6 +481,9 @@ struct fuse_conn { /** Are BSD file locking primitives not implemented by fs? */ unsigned no_flock:1; + /** Is fallocate not implemented by fs? */ + unsigned no_fallocate:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 42678a3..1cd6165 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -91,6 +91,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) fi->nlookup = 0; fi->attr_version = 0; fi->writectr = 0; + fi->orig_ino = 0; INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); INIT_LIST_HEAD(&fi->writepages); @@ -139,6 +140,18 @@ static int fuse_remount_fs(struct super_block *sb, int *flags, char *data) return 0; } +/* + * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down + * so that it will fit. + */ +static ino_t fuse_squash_ino(u64 ino64) +{ + ino_t ino = (ino_t) ino64; + if (sizeof(ino_t) < sizeof(u64)) + ino ^= ino64 >> (sizeof(u64) - sizeof(ino_t)) * 8; + return ino; +} + void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, u64 attr_valid) { @@ -148,7 +161,7 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, fi->attr_version = ++fc->attr_version; fi->i_time = attr_valid; - inode->i_ino = attr->ino; + inode->i_ino = fuse_squash_ino(attr->ino); inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777); set_nlink(inode, attr->nlink); inode->i_uid = attr->uid; @@ -174,6 +187,8 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, fi->orig_i_mode = inode->i_mode; if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) inode->i_mode &= ~S_ISVTX; + + fi->orig_ino = attr->ino; } void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c index 0da8da2..4fddb3c 100644 --- a/fs/gfs2/dentry.c +++ b/fs/gfs2/dentry.c @@ -25,7 +25,7 @@ /** * gfs2_drevalidate - Check directory lookup consistency * @dentry: the mapping to check - * @nd: + * @flags: lookup flags * * Check to make sure the lookup necessary to arrive at this inode from its * parent is still good. @@ -33,7 +33,7 @@ * Returns: 1 if the dentry is ok, 0 if it isn't */ -static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd) +static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags) { struct dentry *parent; struct gfs2_sbd *sdp; @@ -44,7 +44,7 @@ static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd) int error; int had_lock = 0; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; parent = dget_parent(dentry); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index a9ba244..8676747 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -755,11 +755,8 @@ fail: */ static int gfs2_create(struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { - int excl = 0; - if (nd && (nd->flags & LOOKUP_EXCL)) - excl = 1; return gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0, excl); } @@ -775,7 +772,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry, */ static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode = gfs2_lookupi(dir, &dentry->d_name, 0); if (inode && !IS_ERR(inode)) { diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index b8c250f..6c90607 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1286,7 +1286,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, error = -EBUSY; goto error_bdev; } - s = sget(fs_type, test_gfs2_super, set_gfs2_super, bdev); + s = sget(fs_type, test_gfs2_super, set_gfs2_super, flags, bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); error = PTR_ERR(s); if (IS_ERR(s)) @@ -1316,7 +1316,6 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, } else { char b[BDEVNAME_SIZE]; - s->s_flags = flags; s->s_mode = mode; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); sb_set_blocksize(s, block_size(bdev)); @@ -1360,7 +1359,7 @@ static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type, dev_name, error); return ERR_PTR(error); } - s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, + s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, flags, path.dentry->d_inode->i_sb->s_bdev); path_put(&path); if (IS_ERR(s)) { diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index b97178e..27b5cc7 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1108,7 +1108,7 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, } } -int gfs2_quota_sync(struct super_block *sb, int type, int wait) +int gfs2_quota_sync(struct super_block *sb, int type) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_quota_data **qda; @@ -1154,7 +1154,7 @@ int gfs2_quota_sync(struct super_block *sb, int type, int wait) static int gfs2_quota_sync_timeo(struct super_block *sb, int type) { - return gfs2_quota_sync(sb, type, 0); + return gfs2_quota_sync(sb, type); } int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id) diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 90bf1c3..f25d98b 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -26,7 +26,7 @@ extern int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid); extern void gfs2_quota_change(struct gfs2_inode *ip, s64 change, u32 uid, u32 gid); -extern int gfs2_quota_sync(struct super_block *sb, int type, int wait); +extern int gfs2_quota_sync(struct super_block *sb, int type); extern int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id); extern int gfs2_quota_init(struct gfs2_sbd *sdp); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 713e621..f3d6bbf 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -838,7 +838,7 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) int error; flush_workqueue(gfs2_delete_workqueue); - gfs2_quota_sync(sdp->sd_vfs, 0, 1); + gfs2_quota_sync(sdp->sd_vfs, 0); gfs2_statfs_sync(sdp->sd_vfs, 0); error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE, @@ -952,6 +952,8 @@ restart: static int gfs2_sync_fs(struct super_block *sb, int wait) { struct gfs2_sbd *sdp = sb->s_fs_info; + + gfs2_quota_sync(sb, -1); if (wait && sdp) gfs2_log_flush(sdp, NULL); return 0; diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 9c2592b..73ecc34 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -168,7 +168,7 @@ static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf, if (simple_strtol(buf, NULL, 0) != 1) return -EINVAL; - gfs2_quota_sync(sdp->sd_vfs, 0, 1); + gfs2_quota_sync(sdp->sd_vfs, 0); return len; } diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index 62fc14e..422dde2 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -18,7 +18,7 @@ * hfs_lookup() */ static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { hfs_cat_rec rec; struct hfs_find_data fd; @@ -187,7 +187,7 @@ static int hfs_dir_release(struct inode *inode, struct file *file) * the directory and the name (and its length) of the new file. */ static int hfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; int res; diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index 2c16316..a67955a 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -432,7 +432,7 @@ out: if (inode->i_ino < HFS_FIRSTUSER_CNID) set_bit(HFS_FLG_ALT_MDB_DIRTY, &HFS_SB(sb)->flags); set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags); - sb->s_dirt = 1; + hfs_mark_mdb_dirty(sb); } return res; diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 1bf967c..8275175 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -14,6 +14,7 @@ #include <linux/mutex.h> #include <linux/buffer_head.h> #include <linux/fs.h> +#include <linux/workqueue.h> #include <asm/byteorder.h> #include <asm/uaccess.h> @@ -137,16 +138,15 @@ struct hfs_sb_info { gid_t s_gid; /* The gid of all files */ int session, part; - struct nls_table *nls_io, *nls_disk; - struct mutex bitmap_lock; - unsigned long flags; - u16 blockoffset; - int fs_div; + struct super_block *sb; + int work_queued; /* non-zero delayed work is queued */ + struct delayed_work mdb_work; /* MDB flush delayed work */ + spinlock_t work_lock; /* protects mdb_work and work_queued */ }; #define HFS_FLG_BITMAP_DIRTY 0 @@ -226,6 +226,9 @@ extern int hfs_compare_dentry(const struct dentry *parent, extern void hfs_asc2mac(struct super_block *, struct hfs_name *, struct qstr *); extern int hfs_mac2asc(struct super_block *, char *, const struct hfs_name *); +/* super.c */ +extern void hfs_mark_mdb_dirty(struct super_block *sb); + extern struct timezone sys_tz; /* @@ -253,7 +256,7 @@ static inline const char *hfs_mdb_name(struct super_block *sb) static inline void hfs_bitmap_dirty(struct super_block *sb) { set_bit(HFS_FLG_BITMAP_DIRTY, &HFS_SB(sb)->flags); - sb->s_dirt = 1; + hfs_mark_mdb_dirty(sb); } #define sb_bread512(sb, sec, data) ({ \ diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 761ec06..ee1bc55 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -220,7 +220,7 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, umode_t mode) insert_inode_hash(inode); mark_inode_dirty(inode); set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags); - sb->s_dirt = 1; + hfs_mark_mdb_dirty(sb); return inode; } @@ -235,7 +235,7 @@ void hfs_delete_inode(struct inode *inode) if (HFS_I(inode)->cat_key.ParID == cpu_to_be32(HFS_ROOT_CNID)) HFS_SB(sb)->root_dirs--; set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags); - sb->s_dirt = 1; + hfs_mark_mdb_dirty(sb); return; } HFS_SB(sb)->file_count--; @@ -248,7 +248,7 @@ void hfs_delete_inode(struct inode *inode) } } set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags); - sb->s_dirt = 1; + hfs_mark_mdb_dirty(sb); } void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext, @@ -489,7 +489,7 @@ out: } static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode = NULL; hfs_cat_rec rec; @@ -644,13 +644,7 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end, /* sync the superblock to buffers */ sb = inode->i_sb; - if (sb->s_dirt) { - lock_super(sb); - sb->s_dirt = 0; - if (!(sb->s_flags & MS_RDONLY)) - hfs_mdb_commit(sb); - unlock_super(sb); - } + flush_delayed_work_sync(&HFS_SB(sb)->mdb_work); /* .. finally sync the buffers to disk */ err = sync_blockdev(sb->s_bdev); if (!ret) diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 1563d5c..5fd51a5 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -260,6 +260,10 @@ void hfs_mdb_commit(struct super_block *sb) { struct hfs_mdb *mdb = HFS_SB(sb)->mdb; + if (sb->s_flags & MS_RDONLY) + return; + + lock_buffer(HFS_SB(sb)->mdb_bh); if (test_and_clear_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags)) { /* These parameters may have been modified, so write them back */ mdb->drLsMod = hfs_mtime(); @@ -283,9 +287,13 @@ void hfs_mdb_commit(struct super_block *sb) &mdb->drXTFlSize, NULL); hfs_inode_write_fork(HFS_SB(sb)->cat_tree->inode, mdb->drCTExtRec, &mdb->drCTFlSize, NULL); + + lock_buffer(HFS_SB(sb)->alt_mdb_bh); memcpy(HFS_SB(sb)->alt_mdb, HFS_SB(sb)->mdb, HFS_SECTOR_SIZE); HFS_SB(sb)->alt_mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT); HFS_SB(sb)->alt_mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT); + unlock_buffer(HFS_SB(sb)->alt_mdb_bh); + mark_buffer_dirty(HFS_SB(sb)->alt_mdb_bh); sync_dirty_buffer(HFS_SB(sb)->alt_mdb_bh); } @@ -308,7 +316,11 @@ void hfs_mdb_commit(struct super_block *sb) break; } len = min((int)sb->s_blocksize - off, size); + + lock_buffer(bh); memcpy(bh->b_data + off, ptr, len); + unlock_buffer(bh); + mark_buffer_dirty(bh); brelse(bh); block++; @@ -317,6 +329,7 @@ void hfs_mdb_commit(struct super_block *sb) size -= len; } } + unlock_buffer(HFS_SB(sb)->mdb_bh); } void hfs_mdb_close(struct super_block *sb) diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 7b4c537..4eb873e 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -29,43 +29,9 @@ static struct kmem_cache *hfs_inode_cachep; MODULE_LICENSE("GPL"); -/* - * hfs_write_super() - * - * Description: - * This function is called by the VFS only. When the filesystem - * is mounted r/w it updates the MDB on disk. - * Input Variable(s): - * struct super_block *sb: Pointer to the hfs superblock - * Output Variable(s): - * NONE - * Returns: - * void - * Preconditions: - * 'sb' points to a "valid" (struct super_block). - * Postconditions: - * The MDB is marked 'unsuccessfully unmounted' by clearing bit 8 of drAtrb - * (hfs_put_super() must set this flag!). Some MDB fields are updated - * and the MDB buffer is written to disk by calling hfs_mdb_commit(). - */ -static void hfs_write_super(struct super_block *sb) -{ - lock_super(sb); - sb->s_dirt = 0; - - /* sync everything to the buffers */ - if (!(sb->s_flags & MS_RDONLY)) - hfs_mdb_commit(sb); - unlock_super(sb); -} - static int hfs_sync_fs(struct super_block *sb, int wait) { - lock_super(sb); hfs_mdb_commit(sb); - sb->s_dirt = 0; - unlock_super(sb); - return 0; } @@ -78,13 +44,44 @@ static int hfs_sync_fs(struct super_block *sb, int wait) */ static void hfs_put_super(struct super_block *sb) { - if (sb->s_dirt) - hfs_write_super(sb); + cancel_delayed_work_sync(&HFS_SB(sb)->mdb_work); hfs_mdb_close(sb); /* release the MDB's resources */ hfs_mdb_put(sb); } +static void flush_mdb(struct work_struct *work) +{ + struct hfs_sb_info *sbi; + struct super_block *sb; + + sbi = container_of(work, struct hfs_sb_info, mdb_work.work); + sb = sbi->sb; + + spin_lock(&sbi->work_lock); + sbi->work_queued = 0; + spin_unlock(&sbi->work_lock); + + hfs_mdb_commit(sb); +} + +void hfs_mark_mdb_dirty(struct super_block *sb) +{ + struct hfs_sb_info *sbi = HFS_SB(sb); + unsigned long delay; + + if (sb->s_flags & MS_RDONLY) + return; + + spin_lock(&sbi->work_lock); + if (!sbi->work_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + queue_delayed_work(system_long_wq, &sbi->mdb_work, delay); + sbi->work_queued = 1; + } + spin_unlock(&sbi->work_lock); +} + /* * hfs_statfs() * @@ -184,7 +181,6 @@ static const struct super_operations hfs_super_operations = { .write_inode = hfs_write_inode, .evict_inode = hfs_evict_inode, .put_super = hfs_put_super, - .write_super = hfs_write_super, .sync_fs = hfs_sync_fs, .statfs = hfs_statfs, .remount_fs = hfs_remount, @@ -387,7 +383,10 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) if (!sbi) return -ENOMEM; + sbi->sb = sb; sb->s_fs_info = sbi; + spin_lock_init(&sbi->work_lock); + INIT_DELAYED_WORK(&sbi->mdb_work, flush_mdb); res = -EINVAL; if (!parse_options((char *)data, sbi)) { diff --git a/fs/hfs/sysdep.c b/fs/hfs/sysdep.c index 19cf291..91b91fd 100644 --- a/fs/hfs/sysdep.c +++ b/fs/hfs/sysdep.c @@ -13,12 +13,12 @@ /* dentry case-handling: just lowercase everything */ -static int hfs_revalidate_dentry(struct dentry *dentry, struct nameidata *nd) +static int hfs_revalidate_dentry(struct dentry *dentry, unsigned int flags) { struct inode *inode; int diff; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c index 1cad80c..4cfbe2e 100644 --- a/fs/hfsplus/bitmap.c +++ b/fs/hfsplus/bitmap.c @@ -153,7 +153,7 @@ done: kunmap(page); *max = offset + (curr - pptr) * 32 + i - start; sbi->free_blocks -= *max; - sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(sb); dprint(DBG_BITMAP, "-> %u,%u\n", start, *max); out: mutex_unlock(&sbi->alloc_mutex); @@ -228,7 +228,7 @@ out: set_page_dirty(page); kunmap(page); sbi->free_blocks += len; - sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(sb); mutex_unlock(&sbi->alloc_mutex); return 0; diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 26b53fb..6b9f921 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -25,7 +25,7 @@ static inline void hfsplus_instantiate(struct dentry *dentry, /* Find the entry inside dir named dentry->d_name */ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode = NULL; struct hfs_find_data fd; @@ -316,7 +316,7 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir, inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); sbi->file_count++; - dst_dir->i_sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(dst_dir->i_sb); out: mutex_unlock(&sbi->vh_mutex); return res; @@ -465,7 +465,7 @@ out: } static int hfsplus_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return hfsplus_mknod(dir, dentry, mode, 0); } diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 4e75ac6..558dbb4 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -153,8 +153,11 @@ struct hfsplus_sb_info { gid_t gid; int part, session; - unsigned long flags; + + int work_queued; /* non-zero delayed work is queued */ + struct delayed_work sync_work; /* FS sync delayed work */ + spinlock_t work_lock; /* protects sync_work and work_queued */ }; #define HFSPLUS_SB_WRITEBACKUP 0 @@ -428,7 +431,7 @@ int hfsplus_show_options(struct seq_file *, struct dentry *); /* super.c */ struct inode *hfsplus_iget(struct super_block *, unsigned long); -int hfsplus_sync_fs(struct super_block *sb, int wait); +void hfsplus_mark_mdb_dirty(struct super_block *sb); /* tables.c */ extern u16 hfsplus_case_fold_table[]; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 82b69ee..3d8b4a6 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -168,7 +168,7 @@ const struct dentry_operations hfsplus_dentry_operations = { }; static struct dentry *hfsplus_file_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { struct hfs_find_data fd; struct super_block *sb = dir->i_sb; @@ -431,7 +431,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode) sbi->file_count++; insert_inode_hash(inode); mark_inode_dirty(inode); - sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(sb); return inode; } @@ -442,7 +442,7 @@ void hfsplus_delete_inode(struct inode *inode) if (S_ISDIR(inode->i_mode)) { HFSPLUS_SB(sb)->folder_count--; - sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(sb); return; } HFSPLUS_SB(sb)->file_count--; @@ -455,7 +455,7 @@ void hfsplus_delete_inode(struct inode *inode) inode->i_size = 0; hfsplus_file_truncate(inode); } - sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(sb); } void hfsplus_inode_read_fork(struct inode *inode, struct hfsplus_fork_raw *fork) diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index c640ba5..09addc8 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -31,6 +31,7 @@ static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags) struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb); struct hfsplus_vh *vh = sbi->s_vhdr; struct hfsplus_vh *bvh = sbi->s_backup_vhdr; + u32 cnid = (unsigned long)dentry->d_fsdata; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -41,8 +42,12 @@ static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags) vh->finder_info[0] = bvh->finder_info[0] = cpu_to_be32(parent_ino(dentry)); - /* Bootloader */ - vh->finder_info[1] = bvh->finder_info[1] = cpu_to_be32(inode->i_ino); + /* + * Bootloader. Just using the inode here breaks in the case of + * hard links - the firmware wants the ID of the hard link file, + * but the inode points at the indirect inode + */ + vh->finder_info[1] = bvh->finder_info[1] = cpu_to_be32(cnid); /* Per spec, the OS X system folder - same as finder_info[0] here */ vh->finder_info[5] = bvh->finder_info[5] = diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index a9bca4b..4733320 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -124,7 +124,7 @@ static int hfsplus_system_write_inode(struct inode *inode) if (fork->total_size != cpu_to_be64(inode->i_size)) { set_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags); - inode->i_sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(inode->i_sb); } hfsplus_inode_write_fork(inode, fork); if (tree) @@ -161,7 +161,7 @@ static void hfsplus_evict_inode(struct inode *inode) } } -int hfsplus_sync_fs(struct super_block *sb, int wait) +static int hfsplus_sync_fs(struct super_block *sb, int wait) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct hfsplus_vh *vhdr = sbi->s_vhdr; @@ -171,9 +171,7 @@ int hfsplus_sync_fs(struct super_block *sb, int wait) if (!wait) return 0; - dprint(DBG_SUPER, "hfsplus_write_super\n"); - - sb->s_dirt = 0; + dprint(DBG_SUPER, "hfsplus_sync_fs\n"); /* * Explicitly write out the special metadata inodes. @@ -226,12 +224,34 @@ out: return error; } -static void hfsplus_write_super(struct super_block *sb) +static void delayed_sync_fs(struct work_struct *work) { - if (!(sb->s_flags & MS_RDONLY)) - hfsplus_sync_fs(sb, 1); - else - sb->s_dirt = 0; + struct hfsplus_sb_info *sbi; + + sbi = container_of(work, struct hfsplus_sb_info, sync_work.work); + + spin_lock(&sbi->work_lock); + sbi->work_queued = 0; + spin_unlock(&sbi->work_lock); + + hfsplus_sync_fs(sbi->alloc_file->i_sb, 1); +} + +void hfsplus_mark_mdb_dirty(struct super_block *sb) +{ + struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); + unsigned long delay; + + if (sb->s_flags & MS_RDONLY) + return; + + spin_lock(&sbi->work_lock); + if (!sbi->work_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + queue_delayed_work(system_long_wq, &sbi->sync_work, delay); + sbi->work_queued = 1; + } + spin_unlock(&sbi->work_lock); } static void hfsplus_put_super(struct super_block *sb) @@ -240,8 +260,7 @@ static void hfsplus_put_super(struct super_block *sb) dprint(DBG_SUPER, "hfsplus_put_super\n"); - if (!sb->s_fs_info) - return; + cancel_delayed_work_sync(&sbi->sync_work); if (!(sb->s_flags & MS_RDONLY) && sbi->s_vhdr) { struct hfsplus_vh *vhdr = sbi->s_vhdr; @@ -328,7 +347,6 @@ static const struct super_operations hfsplus_sops = { .write_inode = hfsplus_write_inode, .evict_inode = hfsplus_evict_inode, .put_super = hfsplus_put_super, - .write_super = hfsplus_write_super, .sync_fs = hfsplus_sync_fs, .statfs = hfsplus_statfs, .remount_fs = hfsplus_remount, @@ -355,6 +373,8 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) sb->s_fs_info = sbi; mutex_init(&sbi->alloc_mutex); mutex_init(&sbi->vh_mutex); + spin_lock_init(&sbi->work_lock); + INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs); hfsplus_fill_defaults(sbi); err = -EINVAL; diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index 7daf4b8..90effcc 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -56,7 +56,7 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector, DECLARE_COMPLETION_ONSTACK(wait); struct bio *bio; int ret = 0; - unsigned int io_size; + u64 io_size; loff_t start; int offset; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 2afa5bb..1241465 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -553,7 +553,7 @@ static int read_name(struct inode *ino, char *name) } int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; char *name; @@ -595,7 +595,7 @@ int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, } struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode; char *name; diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c index b8472f8..78e12b2 100644 --- a/fs/hpfs/dir.c +++ b/fs/hpfs/dir.c @@ -189,7 +189,7 @@ out: * to tell read_inode to read fnode or not. */ -struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { const unsigned char *name = dentry->d_name.name; unsigned len = dentry->d_name.len; diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index c07ef1f..ac1ead1 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -220,7 +220,7 @@ extern const struct dentry_operations hpfs_dentry_operations; /* dir.c */ -struct dentry *hpfs_lookup(struct inode *, struct dentry *, struct nameidata *); +struct dentry *hpfs_lookup(struct inode *, struct dentry *, unsigned int); extern const struct file_operations hpfs_dir_ops; /* dnode.c */ diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 9083ef8..bc90824 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -115,7 +115,7 @@ bail: return err; } -static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd) +static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { const unsigned char *name = dentry->d_name.name; unsigned len = dentry->d_name.len; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index d4f93b5..c1dffe4 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -138,7 +138,7 @@ static int file_removed(struct dentry *dentry, const char *file) } static struct dentry *hppfs_lookup(struct inode *ino, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct dentry *proc_dentry, *parent; struct qstr *name = &dentry->d_name; @@ -420,8 +420,7 @@ static int hppfs_open(struct inode *inode, struct file *file) { const struct cred *cred = file->f_cred; struct hppfs_private *data; - struct vfsmount *proc_mnt; - struct dentry *proc_dentry; + struct path path; char *host_file; int err, fd, type, filter; @@ -434,12 +433,11 @@ static int hppfs_open(struct inode *inode, struct file *file) if (host_file == NULL) goto out_free2; - proc_dentry = HPPFS_I(inode)->proc_dentry; - proc_mnt = inode->i_sb->s_fs_info; + path.mnt = inode->i_sb->s_fs_info; + path.dentry = HPPFS_I(inode)->proc_dentry; /* XXX This isn't closed anywhere */ - data->proc_file = dentry_open(dget(proc_dentry), mntget(proc_mnt), - file_mode(file->f_mode), cred); + data->proc_file = dentry_open(&path, file_mode(file->f_mode), cred); err = PTR_ERR(data->proc_file); if (IS_ERR(data->proc_file)) goto out_free1; @@ -484,8 +482,7 @@ static int hppfs_dir_open(struct inode *inode, struct file *file) { const struct cred *cred = file->f_cred; struct hppfs_private *data; - struct vfsmount *proc_mnt; - struct dentry *proc_dentry; + struct path path; int err; err = -ENOMEM; @@ -493,10 +490,9 @@ static int hppfs_dir_open(struct inode *inode, struct file *file) if (data == NULL) goto out; - proc_dentry = HPPFS_I(inode)->proc_dentry; - proc_mnt = inode->i_sb->s_fs_info; - data->proc_file = dentry_open(dget(proc_dentry), mntget(proc_mnt), - file_mode(file->f_mode), cred); + path.mnt = inode->i_sb->s_fs_info; + path.dentry = HPPFS_I(inode)->proc_dentry; + data->proc_file = dentry_open(&path, file_mode(file->f_mode), cred); err = PTR_ERR(data->proc_file); if (IS_ERR(data->proc_file)) goto out_free; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index cc9281b..e13e9bd 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -565,7 +565,7 @@ static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mod return retval; } -static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd) +static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0); } @@ -182,7 +182,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) } inode->i_private = NULL; inode->i_mapping = mapping; - INIT_LIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ + INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ #ifdef CONFIG_FS_POSIX_ACL inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; #endif diff --git a/fs/internal.h b/fs/internal.h index 18bc216..a6fd56c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -42,6 +42,11 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait) extern void __init chrdev_init(void); /* + * namei.c + */ +extern int __inode_permission(struct inode *, int); + +/* * namespace.c */ extern int copy_mount_options(const void __user *, unsigned long *); @@ -50,8 +55,6 @@ extern int copy_mount_string(const void __user *, char **); extern struct vfsmount *lookup_mnt(struct path *); extern int finish_automount(struct vfsmount *, struct path *); -extern void mnt_make_longterm(struct vfsmount *); -extern void mnt_make_shortterm(struct vfsmount *); extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); @@ -84,9 +87,6 @@ extern struct super_block *user_get_super(dev_t); /* * open.c */ -struct nameidata; -extern struct file *nameidata_to_filp(struct nameidata *); -extern void release_open_intent(struct nameidata *); struct open_flags { int open_flag; umode_t mode; diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index 0e73f63..3620ad1 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -114,7 +114,7 @@ extern int isofs_name_translate(struct iso_directory_record *, char *, struct in int get_joliet_filename(struct iso_directory_record *, unsigned char *, struct inode *); int get_acorn_filename(struct iso_directory_record *, char *, struct inode *); -extern struct dentry *isofs_lookup(struct inode *, struct dentry *, struct nameidata *); +extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int flags); extern struct buffer_head *isofs_bread(struct inode *, sector_t); extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long); diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c index 1e2946f..c167028 100644 --- a/fs/isofs/namei.c +++ b/fs/isofs/namei.c @@ -163,7 +163,7 @@ isofs_find_entry(struct inode *dir, struct dentry *dentry, return 0; } -struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int found; unsigned long uninitialized_var(block); diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index b560188..ad7774d 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -25,9 +25,9 @@ static int jffs2_readdir (struct file *, void *, filldir_t); static int jffs2_create (struct inode *,struct dentry *,umode_t, - struct nameidata *); + bool); static struct dentry *jffs2_lookup (struct inode *,struct dentry *, - struct nameidata *); + unsigned int); static int jffs2_link (struct dentry *,struct inode *,struct dentry *); static int jffs2_unlink (struct inode *,struct dentry *); static int jffs2_symlink (struct inode *,struct dentry *,const char *); @@ -74,7 +74,7 @@ const struct inode_operations jffs2_dir_inode_operations = nice and simple */ static struct dentry *jffs2_lookup(struct inode *dir_i, struct dentry *target, - struct nameidata *nd) + unsigned int flags) { struct jffs2_inode_info *dir_f; struct jffs2_full_dirent *fd = NULL, *fd_list; @@ -175,7 +175,7 @@ static int jffs2_readdir(struct file *filp, void *dirent, filldir_t filldir) static int jffs2_create(struct inode *dir_i, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { struct jffs2_raw_inode *ri; struct jffs2_inode_info *f, *dir_f; @@ -226,8 +226,8 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry, __func__, inode->i_ino, inode->i_mode, inode->i_nlink, f->inocache->pino_nlink, inode->i_mapping->nrpages); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; fail: @@ -446,8 +446,8 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char mutex_unlock(&dir_f->sem); jffs2_complete_reservation(c); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; fail: @@ -591,8 +591,8 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode mutex_unlock(&dir_f->sem); jffs2_complete_reservation(c); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; fail: @@ -766,8 +766,8 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode mutex_unlock(&dir_f->sem); jffs2_complete_reservation(c); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; fail: diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 07c91ca..3b91a7a 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -73,7 +73,7 @@ static inline void free_ea_wmap(struct inode *inode) * */ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { int rc = 0; tid_t tid; /* transaction id */ @@ -176,8 +176,8 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode, unlock_new_inode(ip); iput(ip); } else { - d_instantiate(dentry, ip); unlock_new_inode(ip); + d_instantiate(dentry, ip); } out2: @@ -309,8 +309,8 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode) unlock_new_inode(ip); iput(ip); } else { - d_instantiate(dentry, ip); unlock_new_inode(ip); + d_instantiate(dentry, ip); } out2: @@ -1043,8 +1043,8 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, unlock_new_inode(ip); iput(ip); } else { - d_instantiate(dentry, ip); unlock_new_inode(ip); + d_instantiate(dentry, ip); } out2: @@ -1424,8 +1424,8 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry, unlock_new_inode(ip); iput(ip); } else { - d_instantiate(dentry, ip); unlock_new_inode(ip); + d_instantiate(dentry, ip); } out1: @@ -1436,7 +1436,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry, return rc; } -static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, struct nameidata *nd) +static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, unsigned int flags) { struct btstack btstack; ino_t inum; @@ -1570,7 +1570,7 @@ out: return result; } -static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd) +static int jfs_ci_revalidate(struct dentry *dentry, unsigned int flags) { /* * This is not negative dentry. Always valid. @@ -1589,7 +1589,7 @@ static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd) * This may be nfsd (or something), anyway, we can't see the * intent of this. So, since this can be for creation, drop it. */ - if (!nd) + if (!flags) return 0; /* @@ -1597,7 +1597,7 @@ static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd) * case sensitive name which is specified by user if this is * for creation. */ - if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) + if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; return 1; } diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 4a82950..c55c745 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -601,6 +601,11 @@ static int jfs_sync_fs(struct super_block *sb, int wait) /* log == NULL indicates read-only mount */ if (log) { + /* + * Write quota structures to quota file, sync_blockdev() will + * write them to disk later + */ + dquot_writeback_dquots(sb, -1); jfs_flush_journal(log, wait); jfs_syncpt(log, 0); } @@ -53,7 +53,7 @@ static int simple_delete_dentry(const struct dentry *dentry) * Lookup the data. This is trivial - if the dentry didn't already * exist, we know it is negative. Set d_op to delete negative dentries. */ -struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { static const struct dentry_operations simple_dentry_operations = { .d_delete = simple_delete_dentry, @@ -222,15 +222,15 @@ struct dentry *mount_pseudo(struct file_system_type *fs_type, char *name, const struct super_operations *ops, const struct dentry_operations *dops, unsigned long magic) { - struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL); + struct super_block *s; struct dentry *dentry; struct inode *root; struct qstr d_name = QSTR_INIT(name, strlen(name)); + s = sget(fs_type, NULL, set_anon_super, MS_NOUSER, NULL); if (IS_ERR(s)) return ERR_CAST(s); - s->s_flags = MS_NOUSER; s->s_maxbytes = MAX_LFS_FILESIZE; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; @@ -308,7 +308,7 @@ static int flock_make_lock(struct file *filp, struct file_lock **lock, return 0; } -static int assign_type(struct file_lock *fl, int type) +static int assign_type(struct file_lock *fl, long type) { switch (type) { case F_RDLCK: @@ -445,7 +445,7 @@ static const struct lock_manager_operations lease_manager_ops = { /* * Initialize a lease, use the default lock manager operations */ -static int lease_init(struct file *filp, int type, struct file_lock *fl) +static int lease_init(struct file *filp, long type, struct file_lock *fl) { if (assign_type(fl, type) != 0) return -EINVAL; @@ -463,7 +463,7 @@ static int lease_init(struct file *filp, int type, struct file_lock *fl) } /* Allocate a file_lock initialised to this type of lease */ -static struct file_lock *lease_alloc(struct file *filp, int type) +static struct file_lock *lease_alloc(struct file *filp, long type) { struct file_lock *fl = locks_alloc_lock(); int error = -ENOMEM; @@ -1465,7 +1465,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp) case F_WRLCK: return generic_add_lease(filp, arg, flp); default: - BUG(); + return -EINVAL; } } EXPORT_SYMBOL(generic_setlease); diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index bea5d1b..26e4a94 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -349,7 +349,7 @@ static void logfs_set_name(struct logfs_disk_dentry *dd, struct qstr *name) } static struct dentry *logfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct page *page; struct logfs_disk_dentry *dd; @@ -502,7 +502,7 @@ static int logfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) } static int logfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; diff --git a/fs/logfs/super.c b/fs/logfs/super.c index 97bca62..345c24b 100644 --- a/fs/logfs/super.c +++ b/fs/logfs/super.c @@ -519,7 +519,7 @@ static struct dentry *logfs_get_sb_device(struct logfs_super *super, log_super("LogFS: Start mount %x\n", mount_count++); err = -EINVAL; - sb = sget(type, logfs_sb_test, logfs_sb_set, super); + sb = sget(type, logfs_sb_test, logfs_sb_set, flags | MS_NOATIME, super); if (IS_ERR(sb)) { super->s_devops->put_device(super); kfree(super); @@ -542,7 +542,6 @@ static struct dentry *logfs_get_sb_device(struct logfs_super *super, sb->s_maxbytes = (1ull << 43) - 1; sb->s_max_links = LOGFS_LINK_MAX; sb->s_op = &logfs_super_operations; - sb->s_flags = flags | MS_NOATIME; err = logfs_read_sb(sb, sb->s_flags & MS_RDONLY); if (err) diff --git a/fs/minix/namei.c b/fs/minix/namei.c index 2d0ee17..0db73d9 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -18,7 +18,7 @@ static int add_nondir(struct dentry *dentry, struct inode *inode) return err; } -static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags) { struct inode * inode = NULL; ino_t ino; @@ -55,7 +55,7 @@ static int minix_mknod(struct inode * dir, struct dentry *dentry, umode_t mode, } static int minix_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return minix_mknod(dir, dentry, mode, 0); } @@ -22,7 +22,6 @@ struct mount { struct vfsmount mnt; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; - atomic_t mnt_longterm; /* how many of the refs are longterm */ #else int mnt_count; int mnt_writers; @@ -49,6 +48,8 @@ struct mount { int mnt_ghosts; }; +#define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ + static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); @@ -59,6 +60,12 @@ static inline int mnt_has_parent(struct mount *mnt) return mnt != mnt->mnt_parent; } +static inline int is_mounted(struct vfsmount *mnt) +{ + /* neither detached nor internal? */ + return !IS_ERR_OR_NULL(real_mount(mnt)); +} + extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *, int); static inline void get_mnt_ns(struct mnt_namespace *ns) @@ -67,10 +74,12 @@ static inline void get_mnt_ns(struct mnt_namespace *ns) } struct proc_mounts { - struct seq_file m; /* must be the first element */ + struct seq_file m; struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; +#define proc_mounts(p) (container_of((p), struct proc_mounts, m)) + extern const struct seq_operations mounts_op; @@ -315,31 +315,22 @@ static inline int do_inode_permission(struct inode *inode, int mask) } /** - * inode_permission - check for access rights to a given inode - * @inode: inode to check permission on - * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...) + * __inode_permission - Check for access rights to a given inode + * @inode: Inode to check permission on + * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * - * Used to check for read/write/execute permissions on an inode. - * We use "fsuid" for this, letting us set arbitrary permissions - * for filesystem access without changing the "normal" uids which - * are used for other things. + * Check for read/write/execute permissions on an inode. * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. + * + * This does not check for a read-only file system. You probably want + * inode_permission(). */ -int inode_permission(struct inode *inode, int mask) +int __inode_permission(struct inode *inode, int mask) { int retval; if (unlikely(mask & MAY_WRITE)) { - umode_t mode = inode->i_mode; - - /* - * Nobody gets write access to a read-only fs. - */ - if (IS_RDONLY(inode) && - (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) - return -EROFS; - /* * Nobody gets write access to an immutable file. */ @@ -359,6 +350,47 @@ int inode_permission(struct inode *inode, int mask) } /** + * sb_permission - Check superblock-level permissions + * @sb: Superblock of inode to check permission on + * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) + * + * Separate out file-system wide checks from inode-specific permission checks. + */ +static int sb_permission(struct super_block *sb, struct inode *inode, int mask) +{ + if (unlikely(mask & MAY_WRITE)) { + umode_t mode = inode->i_mode; + + /* Nobody gets write access to a read-only fs. */ + if ((sb->s_flags & MS_RDONLY) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) + return -EROFS; + } + return 0; +} + +/** + * inode_permission - Check for access rights to a given inode + * @inode: Inode to check permission on + * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) + * + * Check for read/write/execute permissions on an inode. We use fs[ug]id for + * this, letting us set arbitrary permissions for filesystem access without + * changing the "normal" UIDs which are used for other things. + * + * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. + */ +int inode_permission(struct inode *inode, int mask) +{ + int retval; + + retval = sb_permission(inode->i_sb, inode, mask); + if (retval) + return retval; + return __inode_permission(inode, mask); +} + +/** * path_get - get a reference to a path * @path: path to get the reference to * @@ -395,6 +427,18 @@ EXPORT_SYMBOL(path_put); * to restart the path walk from the beginning in ref-walk mode. */ +static inline void lock_rcu_walk(void) +{ + br_read_lock(&vfsmount_lock); + rcu_read_lock(); +} + +static inline void unlock_rcu_walk(void) +{ + rcu_read_unlock(); + br_read_unlock(&vfsmount_lock); +} + /** * unlazy_walk - try to switch to ref-walk mode. * @nd: nameidata pathwalk data @@ -448,8 +492,7 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry) } mntget(nd->path.mnt); - rcu_read_unlock(); - br_read_unlock(&vfsmount_lock); + unlock_rcu_walk(); nd->flags &= ~LOOKUP_RCU; return 0; @@ -463,25 +506,9 @@ err_root: return -ECHILD; } -/** - * release_open_intent - free up open intent resources - * @nd: pointer to nameidata - */ -void release_open_intent(struct nameidata *nd) +static inline int d_revalidate(struct dentry *dentry, unsigned int flags) { - struct file *file = nd->intent.open.file; - - if (file && !IS_ERR(file)) { - if (file->f_path.dentry == NULL) - put_filp(file); - else - fput(file); - } -} - -static inline int d_revalidate(struct dentry *dentry, struct nameidata *nd) -{ - return dentry->d_op->d_revalidate(dentry, nd); + return dentry->d_op->d_revalidate(dentry, flags); } /** @@ -506,15 +533,13 @@ static int complete_walk(struct nameidata *nd) spin_lock(&dentry->d_lock); if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) { spin_unlock(&dentry->d_lock); - rcu_read_unlock(); - br_read_unlock(&vfsmount_lock); + unlock_rcu_walk(); return -ECHILD; } BUG_ON(nd->inode != dentry->d_inode); spin_unlock(&dentry->d_lock); mntget(nd->path.mnt); - rcu_read_unlock(); - br_read_unlock(&vfsmount_lock); + unlock_rcu_walk(); } if (likely(!(nd->flags & LOOKUP_JUMPED))) @@ -527,7 +552,7 @@ static int complete_walk(struct nameidata *nd) return 0; /* Note: we do not d_invalidate() */ - status = d_revalidate(dentry, nd); + status = d_revalidate(dentry, nd->flags); if (status > 0) return 0; @@ -602,10 +627,25 @@ static inline void path_to_nameidata(const struct path *path, nd->path.dentry = path->dentry; } +/* + * Helper to directly jump to a known parsed path from ->follow_link, + * caller must have taken a reference to path beforehand. + */ +void nd_jump_link(struct nameidata *nd, struct path *path) +{ + path_put(&nd->path); + + nd->path = *path; + nd->inode = nd->path.dentry->d_inode; + nd->flags |= LOOKUP_JUMPED; + + BUG_ON(nd->inode->i_op->follow_link); +} + static inline void put_link(struct nameidata *nd, struct path *link, void *cookie) { struct inode *inode = link->dentry->d_inode; - if (!IS_ERR(cookie) && inode->i_op->put_link) + if (inode->i_op->put_link) inode->i_op->put_link(link->dentry, nd, cookie); path_put(link); } @@ -613,19 +653,19 @@ static inline void put_link(struct nameidata *nd, struct path *link, void *cooki static __always_inline int follow_link(struct path *link, struct nameidata *nd, void **p) { - int error; struct dentry *dentry = link->dentry; + int error; + char *s; BUG_ON(nd->flags & LOOKUP_RCU); if (link->mnt == nd->path.mnt) mntget(link->mnt); - if (unlikely(current->total_link_count >= 40)) { - *p = ERR_PTR(-ELOOP); /* no ->put_link(), please */ - path_put(&nd->path); - return -ELOOP; - } + error = -ELOOP; + if (unlikely(current->total_link_count >= 40)) + goto out_put_nd_path; + cond_resched(); current->total_link_count++; @@ -633,30 +673,28 @@ follow_link(struct path *link, struct nameidata *nd, void **p) nd_set_link(nd, NULL); error = security_inode_follow_link(link->dentry, nd); - if (error) { - *p = ERR_PTR(error); /* no ->put_link(), please */ - path_put(&nd->path); - return error; - } + if (error) + goto out_put_nd_path; nd->last_type = LAST_BIND; *p = dentry->d_inode->i_op->follow_link(dentry, nd); error = PTR_ERR(*p); - if (!IS_ERR(*p)) { - char *s = nd_get_link(nd); - error = 0; - if (s) - error = __vfs_follow_link(nd, s); - else if (nd->last_type == LAST_BIND) { - nd->flags |= LOOKUP_JUMPED; - nd->inode = nd->path.dentry->d_inode; - if (nd->inode->i_op->follow_link) { - /* stepped on a _really_ weird one */ - path_put(&nd->path); - error = -ELOOP; - } - } + if (IS_ERR(*p)) + goto out_put_nd_path; + + error = 0; + s = nd_get_link(nd); + if (s) { + error = __vfs_follow_link(nd, s); + if (unlikely(error)) + put_link(nd, link, *p); } + + return error; + +out_put_nd_path: + path_put(&nd->path); + path_put(link); return error; } @@ -675,6 +713,16 @@ static int follow_up_rcu(struct path *path) return 1; } +/* + * follow_up - Find the mountpoint of path's vfsmount + * + * Given a path, find the mountpoint of its source file system. + * Replace @path with the path of the mountpoint in the parent mount. + * Up is towards /. + * + * Return 1 if we went up a level and 0 if we were already at the + * root. + */ int follow_up(struct path *path) { struct mount *mnt = real_mount(path->mnt); @@ -683,7 +731,7 @@ int follow_up(struct path *path) br_read_lock(&vfsmount_lock); parent = mnt->mnt_parent; - if (&parent->mnt == path->mnt) { + if (parent == mnt) { br_read_unlock(&vfsmount_lock); return 0; } @@ -946,8 +994,7 @@ failed: nd->flags &= ~LOOKUP_RCU; if (!(nd->flags & LOOKUP_ROOT)) nd->root.mnt = NULL; - rcu_read_unlock(); - br_read_unlock(&vfsmount_lock); + unlock_rcu_walk(); return -ECHILD; } @@ -1048,7 +1095,7 @@ static void follow_dotdot(struct nameidata *nd) * dir->d_inode->i_mutex must be held */ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir, - struct nameidata *nd, bool *need_lookup) + unsigned int flags, bool *need_lookup) { struct dentry *dentry; int error; @@ -1059,7 +1106,7 @@ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir, if (d_need_lookup(dentry)) { *need_lookup = true; } else if (dentry->d_flags & DCACHE_OP_REVALIDATE) { - error = d_revalidate(dentry, nd); + error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (error < 0) { dput(dentry); @@ -1089,7 +1136,7 @@ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir, * dir->d_inode->i_mutex must be held */ static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct dentry *old; @@ -1099,7 +1146,7 @@ static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry, return ERR_PTR(-ENOENT); } - old = dir->i_op->lookup(dir, dentry, nd); + old = dir->i_op->lookup(dir, dentry, flags); if (unlikely(old)) { dput(dentry); dentry = old; @@ -1108,16 +1155,16 @@ static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry, } static struct dentry *__lookup_hash(struct qstr *name, - struct dentry *base, struct nameidata *nd) + struct dentry *base, unsigned int flags) { bool need_lookup; struct dentry *dentry; - dentry = lookup_dcache(name, base, nd, &need_lookup); + dentry = lookup_dcache(name, base, flags, &need_lookup); if (!need_lookup) return dentry; - return lookup_real(base->d_inode, dentry, nd); + return lookup_real(base->d_inode, dentry, flags); } /* @@ -1167,7 +1214,7 @@ static int lookup_fast(struct nameidata *nd, struct qstr *name, if (unlikely(d_need_lookup(dentry))) goto unlazy; if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) { - status = d_revalidate(dentry, nd); + status = d_revalidate(dentry, nd->flags); if (unlikely(status <= 0)) { if (status != -ECHILD) need_reval = 0; @@ -1197,7 +1244,7 @@ unlazy: } if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval) - status = d_revalidate(dentry, nd); + status = d_revalidate(dentry, nd->flags); if (unlikely(status <= 0)) { if (status < 0) { dput(dentry); @@ -1236,7 +1283,7 @@ static int lookup_slow(struct nameidata *nd, struct qstr *name, BUG_ON(nd->inode != parent->d_inode); mutex_lock(&parent->d_inode->i_mutex); - dentry = __lookup_hash(name, parent, nd); + dentry = __lookup_hash(name, parent, nd->flags); mutex_unlock(&parent->d_inode->i_mutex); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -1284,8 +1331,7 @@ static void terminate_walk(struct nameidata *nd) nd->flags &= ~LOOKUP_RCU; if (!(nd->flags & LOOKUP_ROOT)) nd->root.mnt = NULL; - rcu_read_unlock(); - br_read_unlock(&vfsmount_lock); + unlock_rcu_walk(); } } @@ -1383,9 +1429,10 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd) void *cookie; res = follow_link(&link, nd, &cookie); - if (!res) - res = walk_component(nd, path, &nd->last, - nd->last_type, LOOKUP_FOLLOW); + if (res) + break; + res = walk_component(nd, path, &nd->last, + nd->last_type, LOOKUP_FOLLOW); put_link(nd, &link, cookie); } while (res > 0); @@ -1651,8 +1698,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, nd->path = nd->root; nd->inode = inode; if (flags & LOOKUP_RCU) { - br_read_lock(&vfsmount_lock); - rcu_read_lock(); + lock_rcu_walk(); nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } else { path_get(&nd->path); @@ -1664,8 +1710,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (*name=='/') { if (flags & LOOKUP_RCU) { - br_read_lock(&vfsmount_lock); - rcu_read_lock(); + lock_rcu_walk(); set_root_rcu(nd); } else { set_root(nd); @@ -1677,8 +1722,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, struct fs_struct *fs = current->fs; unsigned seq; - br_read_lock(&vfsmount_lock); - rcu_read_lock(); + lock_rcu_walk(); do { seq = read_seqcount_begin(&fs->seq); @@ -1713,8 +1757,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (fput_needed) *fp = file; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); - br_read_lock(&vfsmount_lock); - rcu_read_lock(); + lock_rcu_walk(); } else { path_get(&file->f_path); fput_light(file, fput_needed); @@ -1777,8 +1820,9 @@ static int path_lookupat(int dfd, const char *name, struct path link = path; nd->flags |= LOOKUP_PARENT; err = follow_link(&link, nd, &cookie); - if (!err) - err = lookup_last(nd, &path); + if (err) + break; + err = lookup_last(nd, &path); put_link(nd, &link, cookie); } } @@ -1821,9 +1865,27 @@ static int do_path_lookup(int dfd, const char *name, return retval; } -int kern_path_parent(const char *name, struct nameidata *nd) +/* does lookup, returns the object with parent locked */ +struct dentry *kern_path_locked(const char *name, struct path *path) { - return do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, nd); + struct nameidata nd; + struct dentry *d; + int err = do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, &nd); + if (err) + return ERR_PTR(err); + if (nd.last_type != LAST_NORM) { + path_put(&nd.path); + return ERR_PTR(-EINVAL); + } + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); + d = __lookup_hash(&nd.last, nd.path.dentry, 0); + if (IS_ERR(d)) { + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + path_put(&nd.path); + return d; + } + *path = nd.path; + return d; } int kern_path(const char *name, unsigned int flags, struct path *path) @@ -1866,7 +1928,7 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, */ static struct dentry *lookup_hash(struct nameidata *nd) { - return __lookup_hash(&nd->last, nd->path.dentry, nd); + return __lookup_hash(&nd->last, nd->path.dentry, nd->flags); } /** @@ -1913,7 +1975,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) if (err) return ERR_PTR(err); - return __lookup_hash(&this, base, NULL); + return __lookup_hash(&this, base, 0); } int user_path_at_empty(int dfd, const char __user *name, unsigned flags, @@ -2086,10 +2148,9 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) } int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool want_excl) { int error = may_create(dir, dentry); - if (error) return error; @@ -2100,7 +2161,7 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, error = security_inode_create(dir, dentry, mode); if (error) return error; - error = dir->i_op->create(dir, dentry, mode, nd); + error = dir->i_op->create(dir, dentry, mode, want_excl); if (!error) fsnotify_create(dir, dentry); return error; @@ -2187,21 +2248,275 @@ static inline int open_to_namei_flags(int flag) return flag; } +static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode) +{ + int error = security_path_mknod(dir, dentry, mode, 0); + if (error) + return error; + + error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); + if (error) + return error; + + return security_inode_create(dir->dentry->d_inode, dentry, mode); +} + /* - * Handle the last step of open() + * Attempt to atomically look up, create and open a file from a negative + * dentry. + * + * Returns 0 if successful. The file will have been created and attached to + * @file by the filesystem calling finish_open(). + * + * Returns 1 if the file was looked up only or didn't need creating. The + * caller will need to perform the open themselves. @path will have been + * updated to point to the new dentry. This may be negative. + * + * Returns an error code otherwise. + */ +static int atomic_open(struct nameidata *nd, struct dentry *dentry, + struct path *path, struct file *file, + const struct open_flags *op, + bool *want_write, bool need_lookup, + int *opened) +{ + struct inode *dir = nd->path.dentry->d_inode; + unsigned open_flag = open_to_namei_flags(op->open_flag); + umode_t mode; + int error; + int acc_mode; + int create_error = 0; + struct dentry *const DENTRY_NOT_SET = (void *) -1UL; + + BUG_ON(dentry->d_inode); + + /* Don't create child dentry for a dead directory. */ + if (unlikely(IS_DEADDIR(dir))) { + error = -ENOENT; + goto out; + } + + mode = op->mode & S_IALLUGO; + if ((open_flag & O_CREAT) && !IS_POSIXACL(dir)) + mode &= ~current_umask(); + + if (open_flag & O_EXCL) { + open_flag &= ~O_TRUNC; + *opened |= FILE_CREATED; + } + + /* + * Checking write permission is tricky, bacuse we don't know if we are + * going to actually need it: O_CREAT opens should work as long as the + * file exists. But checking existence breaks atomicity. The trick is + * to check access and if not granted clear O_CREAT from the flags. + * + * Another problem is returing the "right" error value (e.g. for an + * O_EXCL open we want to return EEXIST not EROFS). + */ + if ((open_flag & (O_CREAT | O_TRUNC)) || + (open_flag & O_ACCMODE) != O_RDONLY) { + error = mnt_want_write(nd->path.mnt); + if (!error) { + *want_write = true; + } else if (!(open_flag & O_CREAT)) { + /* + * No O_CREATE -> atomicity not a requirement -> fall + * back to lookup + open + */ + goto no_open; + } else if (open_flag & (O_EXCL | O_TRUNC)) { + /* Fall back and fail with the right error */ + create_error = error; + goto no_open; + } else { + /* No side effects, safe to clear O_CREAT */ + create_error = error; + open_flag &= ~O_CREAT; + } + } + + if (open_flag & O_CREAT) { + error = may_o_create(&nd->path, dentry, op->mode); + if (error) { + create_error = error; + if (open_flag & O_EXCL) + goto no_open; + open_flag &= ~O_CREAT; + } + } + + if (nd->flags & LOOKUP_DIRECTORY) + open_flag |= O_DIRECTORY; + + file->f_path.dentry = DENTRY_NOT_SET; + file->f_path.mnt = nd->path.mnt; + error = dir->i_op->atomic_open(dir, dentry, file, open_flag, mode, + opened); + if (error < 0) { + if (create_error && error == -ENOENT) + error = create_error; + goto out; + } + + acc_mode = op->acc_mode; + if (*opened & FILE_CREATED) { + fsnotify_create(dir, dentry); + acc_mode = MAY_OPEN; + } + + if (error) { /* returned 1, that is */ + if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { + error = -EIO; + goto out; + } + if (file->f_path.dentry) { + dput(dentry); + dentry = file->f_path.dentry; + } + goto looked_up; + } + + /* + * We didn't have the inode before the open, so check open permission + * here. + */ + error = may_open(&file->f_path, acc_mode, open_flag); + if (error) + fput(file); + +out: + dput(dentry); + return error; + +no_open: + if (need_lookup) { + dentry = lookup_real(dir, dentry, nd->flags); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + if (create_error) { + int open_flag = op->open_flag; + + error = create_error; + if ((open_flag & O_EXCL)) { + if (!dentry->d_inode) + goto out; + } else if (!dentry->d_inode) { + goto out; + } else if ((open_flag & O_TRUNC) && + S_ISREG(dentry->d_inode->i_mode)) { + goto out; + } + /* will fail later, go on to get the right error */ + } + } +looked_up: + path->dentry = dentry; + path->mnt = nd->path.mnt; + return 1; +} + +/* + * Look up and maybe create and open the last component. + * + * Must be called with i_mutex held on parent. + * + * Returns 0 if the file was successfully atomically created (if necessary) and + * opened. In this case the file will be returned attached to @file. + * + * Returns 1 if the file was not completely opened at this time, though lookups + * and creations will have been performed and the dentry returned in @path will + * be positive upon return if O_CREAT was specified. If O_CREAT wasn't + * specified then a negative dentry may be returned. + * + * An error code is returned otherwise. + * + * FILE_CREATE will be set in @*opened if the dentry was created and will be + * cleared otherwise prior to returning. */ -static struct file *do_last(struct nameidata *nd, struct path *path, - const struct open_flags *op, const char *pathname) +static int lookup_open(struct nameidata *nd, struct path *path, + struct file *file, + const struct open_flags *op, + bool *want_write, int *opened) { struct dentry *dir = nd->path.dentry; + struct inode *dir_inode = dir->d_inode; struct dentry *dentry; + int error; + bool need_lookup; + + *opened &= ~FILE_CREATED; + dentry = lookup_dcache(&nd->last, dir, nd->flags, &need_lookup); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + /* Cached positive dentry: will open in f_op->open */ + if (!need_lookup && dentry->d_inode) + goto out_no_open; + + if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) { + return atomic_open(nd, dentry, path, file, op, want_write, + need_lookup, opened); + } + + if (need_lookup) { + BUG_ON(dentry->d_inode); + + dentry = lookup_real(dir_inode, dentry, nd->flags); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + } + + /* Negative dentry, just create the file */ + if (!dentry->d_inode && (op->open_flag & O_CREAT)) { + umode_t mode = op->mode; + if (!IS_POSIXACL(dir->d_inode)) + mode &= ~current_umask(); + /* + * This write is needed to ensure that a + * rw->ro transition does not occur between + * the time when the file is created and when + * a permanent write count is taken through + * the 'struct file' in finish_open(). + */ + error = mnt_want_write(nd->path.mnt); + if (error) + goto out_dput; + *want_write = true; + *opened |= FILE_CREATED; + error = security_path_mknod(&nd->path, dentry, mode, 0); + if (error) + goto out_dput; + error = vfs_create(dir->d_inode, dentry, mode, + nd->flags & LOOKUP_EXCL); + if (error) + goto out_dput; + } +out_no_open: + path->dentry = dentry; + path->mnt = nd->path.mnt; + return 1; + +out_dput: + dput(dentry); + return error; +} + +/* + * Handle the last step of open() + */ +static int do_last(struct nameidata *nd, struct path *path, + struct file *file, const struct open_flags *op, + int *opened, const char *pathname) +{ + struct dentry *dir = nd->path.dentry; int open_flag = op->open_flag; - int will_truncate = open_flag & O_TRUNC; - int want_write = 0; + bool will_truncate = (open_flag & O_TRUNC) != 0; + bool want_write = false; int acc_mode = op->acc_mode; - struct file *filp; struct inode *inode; - int symlink_ok = 0; + bool symlink_ok = false; struct path save_parent = { .dentry = NULL, .mnt = NULL }; bool retried = false; int error; @@ -2214,112 +2529,99 @@ static struct file *do_last(struct nameidata *nd, struct path *path, case LAST_DOT: error = handle_dots(nd, nd->last_type); if (error) - return ERR_PTR(error); + return error; /* fallthrough */ case LAST_ROOT: error = complete_walk(nd); if (error) - return ERR_PTR(error); + return error; audit_inode(pathname, nd->path.dentry); if (open_flag & O_CREAT) { error = -EISDIR; - goto exit; + goto out; } - goto ok; + goto finish_open; case LAST_BIND: error = complete_walk(nd); if (error) - return ERR_PTR(error); + return error; audit_inode(pathname, dir); - goto ok; + goto finish_open; } if (!(open_flag & O_CREAT)) { if (nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW)) - symlink_ok = 1; + symlink_ok = true; /* we _can_ be in RCU mode here */ error = lookup_fast(nd, &nd->last, path, &inode); - if (unlikely(error)) { - if (error < 0) - goto exit; + if (likely(!error)) + goto finish_lookup; - error = lookup_slow(nd, &nd->last, path); - if (error < 0) - goto exit; + if (error < 0) + goto out; - inode = path->dentry->d_inode; - } - goto finish_lookup; - } - - /* create side of things */ - /* - * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED has been - * cleared when we got to the last component we are about to look up - */ - error = complete_walk(nd); - if (error) - return ERR_PTR(error); + BUG_ON(nd->inode != dir->d_inode); + } else { + /* create side of things */ + /* + * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED + * has been cleared when we got to the last component we are + * about to look up + */ + error = complete_walk(nd); + if (error) + return error; - audit_inode(pathname, dir); - error = -EISDIR; - /* trailing slashes? */ - if (nd->last.name[nd->last.len]) - goto exit; + audit_inode(pathname, dir); + error = -EISDIR; + /* trailing slashes? */ + if (nd->last.name[nd->last.len]) + goto out; + } retry_lookup: mutex_lock(&dir->d_inode->i_mutex); + error = lookup_open(nd, path, file, op, &want_write, opened); + mutex_unlock(&dir->d_inode->i_mutex); - dentry = lookup_hash(nd); - error = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - mutex_unlock(&dir->d_inode->i_mutex); - goto exit; - } + if (error <= 0) { + if (error) + goto out; - path->dentry = dentry; - path->mnt = nd->path.mnt; + if ((*opened & FILE_CREATED) || + !S_ISREG(file->f_path.dentry->d_inode->i_mode)) + will_truncate = false; - /* Negative dentry, just create the file */ - if (!dentry->d_inode) { - umode_t mode = op->mode; - if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current_umask(); - /* - * This write is needed to ensure that a - * rw->ro transition does not occur between - * the time when the file is created and when - * a permanent write count is taken through - * the 'struct file' in nameidata_to_filp(). - */ - error = mnt_want_write(nd->path.mnt); - if (error) - goto exit_mutex_unlock; - want_write = 1; + audit_inode(pathname, file->f_path.dentry); + goto opened; + } + + if (*opened & FILE_CREATED) { /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; - will_truncate = 0; + will_truncate = false; acc_mode = MAY_OPEN; - error = security_path_mknod(&nd->path, dentry, mode, 0); - if (error) - goto exit_mutex_unlock; - error = vfs_create(dir->d_inode, dentry, mode, nd); - if (error) - goto exit_mutex_unlock; - mutex_unlock(&dir->d_inode->i_mutex); - dput(nd->path.dentry); - nd->path.dentry = dentry; - goto common; + path_to_nameidata(path, nd); + goto finish_open_created; } /* * It already exists. */ - mutex_unlock(&dir->d_inode->i_mutex); audit_inode(pathname, path->dentry); + /* + * If atomic_open() acquired write access it is dropped now due to + * possible mount and symlink following (this might be optimized away if + * necessary...) + */ + if (want_write) { + mnt_drop_write(nd->path.mnt); + want_write = false; + } + error = -EEXIST; if (open_flag & O_EXCL) goto exit_dput; @@ -2338,18 +2640,18 @@ finish_lookup: error = -ENOENT; if (!inode) { path_to_nameidata(path, nd); - goto exit; + goto out; } if (should_follow_link(inode, !symlink_ok)) { if (nd->flags & LOOKUP_RCU) { if (unlikely(unlazy_walk(nd, path->dentry))) { error = -ECHILD; - goto exit; + goto out; } } BUG_ON(inode != path->dentry->d_inode); - return NULL; + return 1; } if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path->mnt) { @@ -2365,119 +2667,122 @@ finish_lookup: error = complete_walk(nd); if (error) { path_put(&save_parent); - return ERR_PTR(error); + return error; } error = -EISDIR; if ((open_flag & O_CREAT) && S_ISDIR(nd->inode->i_mode)) - goto exit; + goto out; error = -ENOTDIR; if ((nd->flags & LOOKUP_DIRECTORY) && !nd->inode->i_op->lookup) - goto exit; + goto out; audit_inode(pathname, nd->path.dentry); -ok: +finish_open: if (!S_ISREG(nd->inode->i_mode)) - will_truncate = 0; + will_truncate = false; if (will_truncate) { error = mnt_want_write(nd->path.mnt); if (error) - goto exit; - want_write = 1; + goto out; + want_write = true; } -common: +finish_open_created: error = may_open(&nd->path, acc_mode, open_flag); if (error) - goto exit; - filp = nameidata_to_filp(nd); - if (filp == ERR_PTR(-EOPENSTALE) && save_parent.dentry && !retried) { - BUG_ON(save_parent.dentry != dir); - path_put(&nd->path); - nd->path = save_parent; - nd->inode = dir->d_inode; - save_parent.mnt = NULL; - save_parent.dentry = NULL; - if (want_write) { - mnt_drop_write(nd->path.mnt); - want_write = 0; - } - retried = true; - goto retry_lookup; - } - if (!IS_ERR(filp)) { - error = ima_file_check(filp, op->acc_mode); - if (error) { - fput(filp); - filp = ERR_PTR(error); - } + goto out; + file->f_path.mnt = nd->path.mnt; + error = finish_open(file, nd->path.dentry, NULL, opened); + if (error) { + if (error == -EOPENSTALE) + goto stale_open; + goto out; } - if (!IS_ERR(filp)) { - if (will_truncate) { - error = handle_truncate(filp); - if (error) { - fput(filp); - filp = ERR_PTR(error); - } - } +opened: + error = open_check_o_direct(file); + if (error) + goto exit_fput; + error = ima_file_check(file, op->acc_mode); + if (error) + goto exit_fput; + + if (will_truncate) { + error = handle_truncate(file); + if (error) + goto exit_fput; } out: if (want_write) mnt_drop_write(nd->path.mnt); path_put(&save_parent); terminate_walk(nd); - return filp; + return error; -exit_mutex_unlock: - mutex_unlock(&dir->d_inode->i_mutex); exit_dput: path_put_conditional(path, nd); -exit: - filp = ERR_PTR(error); goto out; +exit_fput: + fput(file); + goto out; + +stale_open: + /* If no saved parent or already retried then can't retry */ + if (!save_parent.dentry || retried) + goto out; + + BUG_ON(save_parent.dentry != dir); + path_put(&nd->path); + nd->path = save_parent; + nd->inode = dir->d_inode; + save_parent.mnt = NULL; + save_parent.dentry = NULL; + if (want_write) { + mnt_drop_write(nd->path.mnt); + want_write = false; + } + retried = true; + goto retry_lookup; } static struct file *path_openat(int dfd, const char *pathname, struct nameidata *nd, const struct open_flags *op, int flags) { struct file *base = NULL; - struct file *filp; + struct file *file; struct path path; + int opened = 0; int error; - filp = get_empty_filp(); - if (!filp) + file = get_empty_filp(); + if (!file) return ERR_PTR(-ENFILE); - filp->f_flags = op->open_flag; - nd->intent.open.file = filp; - nd->intent.open.flags = open_to_namei_flags(op->open_flag); - nd->intent.open.create_mode = op->mode; + file->f_flags = op->open_flag; error = path_init(dfd, pathname, flags | LOOKUP_PARENT, nd, &base); if (unlikely(error)) - goto out_filp; + goto out; current->total_link_count = 0; error = link_path_walk(pathname, nd); if (unlikely(error)) - goto out_filp; + goto out; - filp = do_last(nd, &path, op, pathname); - while (unlikely(!filp)) { /* trailing symlink */ + error = do_last(nd, &path, file, op, &opened, pathname); + while (unlikely(error > 0)) { /* trailing symlink */ struct path link = path; void *cookie; if (!(nd->flags & LOOKUP_FOLLOW)) { path_put_conditional(&path, nd); path_put(&nd->path); - filp = ERR_PTR(-ELOOP); + error = -ELOOP; break; } nd->flags |= LOOKUP_PARENT; nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); error = follow_link(&link, nd, &cookie); if (unlikely(error)) - filp = ERR_PTR(error); - else - filp = do_last(nd, &path, op, pathname); + break; + error = do_last(nd, &path, file, op, &opened, pathname); put_link(nd, &link, cookie); } out: @@ -2485,18 +2790,20 @@ out: path_put(&nd->root); if (base) fput(base); - release_open_intent(nd); - if (filp == ERR_PTR(-EOPENSTALE)) { - if (flags & LOOKUP_RCU) - filp = ERR_PTR(-ECHILD); - else - filp = ERR_PTR(-ESTALE); + if (!(opened & FILE_OPENED)) { + BUG_ON(!error); + put_filp(file); } - return filp; - -out_filp: - filp = ERR_PTR(error); - goto out; + if (unlikely(error)) { + if (error == -EOPENSTALE) { + if (flags & LOOKUP_RCU) + error = -ECHILD; + else + error = -ESTALE; + } + file = ERR_PTR(error); + } + return file; } struct file *do_filp_open(int dfd, const char *pathname, @@ -2551,7 +2858,6 @@ struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path goto out; nd.flags &= ~LOOKUP_PARENT; nd.flags |= LOOKUP_CREATE | LOOKUP_EXCL; - nd.intent.open.flags = O_EXCL; /* * Do the final lookup. @@ -2670,7 +2976,7 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, goto out_drop_write; switch (mode & S_IFMT) { case 0: case S_IFREG: - error = vfs_create(path.dentry->d_inode,dentry,mode,NULL); + error = vfs_create(path.dentry->d_inode,dentry,mode,true); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(path.dentry->d_inode,dentry,mode, diff --git a/fs/namespace.c b/fs/namespace.c index 1e4a5fe..c53d338 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -515,8 +515,20 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry, } /* - * lookup_mnt increments the ref count before returning - * the vfsmount struct. + * lookup_mnt - Return the first child mount mounted at path + * + * "First" means first mounted chronologically. If you create the + * following mounts: + * + * mount /dev/sda1 /mnt + * mount /dev/sda2 /mnt + * mount /dev/sda3 /mnt + * + * Then lookup_mnt() on the base /mnt dentry in the root mount will + * return successively the root dentry and vfsmount of /dev/sda1, then + * /dev/sda2, then /dev/sda3, then NULL. + * + * lookup_mnt takes a reference to the found vfsmount. */ struct vfsmount *lookup_mnt(struct path *path) { @@ -621,21 +633,6 @@ static void attach_mnt(struct mount *mnt, struct path *path) list_add_tail(&mnt->mnt_child, &real_mount(path->mnt)->mnt_mounts); } -static inline void __mnt_make_longterm(struct mount *mnt) -{ -#ifdef CONFIG_SMP - atomic_inc(&mnt->mnt_longterm); -#endif -} - -/* needs vfsmount lock for write */ -static inline void __mnt_make_shortterm(struct mount *mnt) -{ -#ifdef CONFIG_SMP - atomic_dec(&mnt->mnt_longterm); -#endif -} - /* * vfsmount lock must be held for write */ @@ -649,10 +646,8 @@ static void commit_tree(struct mount *mnt) BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); - list_for_each_entry(m, &head, mnt_list) { + list_for_each_entry(m, &head, mnt_list) m->mnt_ns = n; - __mnt_make_longterm(m); - } list_splice(&head, n->list.prev); @@ -725,56 +720,60 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct super_block *sb = old->mnt.mnt_sb; - struct mount *mnt = alloc_vfsmnt(old->mnt_devname); + struct mount *mnt; + int err; - if (mnt) { - if (flag & (CL_SLAVE | CL_PRIVATE)) - mnt->mnt_group_id = 0; /* not a peer of original */ - else - mnt->mnt_group_id = old->mnt_group_id; - - if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { - int err = mnt_alloc_group_id(mnt); - if (err) - goto out_free; - } + mnt = alloc_vfsmnt(old->mnt_devname); + if (!mnt) + return ERR_PTR(-ENOMEM); - mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD; - atomic_inc(&sb->s_active); - mnt->mnt.mnt_sb = sb; - mnt->mnt.mnt_root = dget(root); - mnt->mnt_mountpoint = mnt->mnt.mnt_root; - mnt->mnt_parent = mnt; - br_write_lock(&vfsmount_lock); - list_add_tail(&mnt->mnt_instance, &sb->s_mounts); - br_write_unlock(&vfsmount_lock); + if (flag & (CL_SLAVE | CL_PRIVATE)) + mnt->mnt_group_id = 0; /* not a peer of original */ + else + mnt->mnt_group_id = old->mnt_group_id; - if (flag & CL_SLAVE) { - list_add(&mnt->mnt_slave, &old->mnt_slave_list); - mnt->mnt_master = old; - CLEAR_MNT_SHARED(mnt); - } else if (!(flag & CL_PRIVATE)) { - if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) - list_add(&mnt->mnt_share, &old->mnt_share); - if (IS_MNT_SLAVE(old)) - list_add(&mnt->mnt_slave, &old->mnt_slave); - mnt->mnt_master = old->mnt_master; - } - if (flag & CL_MAKE_SHARED) - set_mnt_shared(mnt); - - /* stick the duplicate mount on the same expiry list - * as the original if that was on one */ - if (flag & CL_EXPIRE) { - if (!list_empty(&old->mnt_expire)) - list_add(&mnt->mnt_expire, &old->mnt_expire); - } + if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { + err = mnt_alloc_group_id(mnt); + if (err) + goto out_free; } + + mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD; + atomic_inc(&sb->s_active); + mnt->mnt.mnt_sb = sb; + mnt->mnt.mnt_root = dget(root); + mnt->mnt_mountpoint = mnt->mnt.mnt_root; + mnt->mnt_parent = mnt; + br_write_lock(&vfsmount_lock); + list_add_tail(&mnt->mnt_instance, &sb->s_mounts); + br_write_unlock(&vfsmount_lock); + + if (flag & CL_SLAVE) { + list_add(&mnt->mnt_slave, &old->mnt_slave_list); + mnt->mnt_master = old; + CLEAR_MNT_SHARED(mnt); + } else if (!(flag & CL_PRIVATE)) { + if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) + list_add(&mnt->mnt_share, &old->mnt_share); + if (IS_MNT_SLAVE(old)) + list_add(&mnt->mnt_slave, &old->mnt_slave); + mnt->mnt_master = old->mnt_master; + } + if (flag & CL_MAKE_SHARED) + set_mnt_shared(mnt); + + /* stick the duplicate mount on the same expiry list + * as the original if that was on one */ + if (flag & CL_EXPIRE) { + if (!list_empty(&old->mnt_expire)) + list_add(&mnt->mnt_expire, &old->mnt_expire); + } + return mnt; out_free: free_vfsmnt(mnt); - return NULL; + return ERR_PTR(err); } static inline void mntfree(struct mount *mnt) @@ -804,7 +803,8 @@ static void mntput_no_expire(struct mount *mnt) put_again: #ifdef CONFIG_SMP br_read_lock(&vfsmount_lock); - if (likely(atomic_read(&mnt->mnt_longterm))) { + if (likely(mnt->mnt_ns)) { + /* shouldn't be the last one */ mnt_add_count(mnt, -1); br_read_unlock(&vfsmount_lock); return; @@ -939,7 +939,7 @@ EXPORT_SYMBOL(replace_mount_options); /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { - struct proc_mounts *p = container_of(m, struct proc_mounts, m); + struct proc_mounts *p = proc_mounts(m); down_read(&namespace_sem); return seq_list_start(&p->ns->list, *pos); @@ -947,7 +947,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) static void *m_next(struct seq_file *m, void *v, loff_t *pos) { - struct proc_mounts *p = container_of(m, struct proc_mounts, m); + struct proc_mounts *p = proc_mounts(m); return seq_list_next(v, &p->ns->list, pos); } @@ -959,7 +959,7 @@ static void m_stop(struct seq_file *m, void *v) static int m_show(struct seq_file *m, void *v) { - struct proc_mounts *p = container_of(m, struct proc_mounts, m); + struct proc_mounts *p = proc_mounts(m); struct mount *r = list_entry(v, struct mount, mnt_list); return p->show(m, &r->mnt); } @@ -1074,8 +1074,6 @@ void umount_tree(struct mount *mnt, int propagate, struct list_head *kill) list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); __touch_mnt_namespace(p->mnt_ns); - if (p->mnt_ns) - __mnt_make_shortterm(p); p->mnt_ns = NULL; list_del_init(&p->mnt_child); if (mnt_has_parent(p)) { @@ -1260,11 +1258,12 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, struct path path; if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt)) - return NULL; + return ERR_PTR(-EINVAL); res = q = clone_mnt(mnt, dentry, flag); - if (!q) - goto Enomem; + if (IS_ERR(q)) + return q; + q->mnt_mountpoint = mnt->mnt_mountpoint; p = mnt; @@ -1286,8 +1285,8 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, path.mnt = &q->mnt; path.dentry = p->mnt_mountpoint; q = clone_mnt(p, p->mnt.mnt_root, flag); - if (!q) - goto Enomem; + if (IS_ERR(q)) + goto out; br_write_lock(&vfsmount_lock); list_add_tail(&q->mnt_list, &res->mnt_list); attach_mnt(q, &path); @@ -1295,7 +1294,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, } } return res; -Enomem: +out: if (res) { LIST_HEAD(umount_list); br_write_lock(&vfsmount_lock); @@ -1303,9 +1302,11 @@ Enomem: br_write_unlock(&vfsmount_lock); release_mounts(&umount_list); } - return NULL; + return q; } +/* Caller should check returned pointer for errors */ + struct vfsmount *collect_mounts(struct path *path) { struct mount *tree; @@ -1313,7 +1314,9 @@ struct vfsmount *collect_mounts(struct path *path) tree = copy_tree(real_mount(path->mnt), path->dentry, CL_COPY_ALL | CL_PRIVATE); up_write(&namespace_sem); - return tree ? &tree->mnt : NULL; + if (IS_ERR(tree)) + return NULL; + return &tree->mnt; } void drop_collected_mounts(struct vfsmount *mnt) @@ -1608,14 +1611,15 @@ static int do_loopback(struct path *path, char *old_name, if (!check_mnt(real_mount(path->mnt)) || !check_mnt(old)) goto out2; - err = -ENOMEM; if (recurse) mnt = copy_tree(old, old_path.dentry, 0); else mnt = clone_mnt(old, old_path.dentry, 0); - if (!mnt) - goto out2; + if (IS_ERR(mnt)) { + err = PTR_ERR(mnt); + goto out; + } err = graft_tree(mnt, path); if (err) { @@ -2209,23 +2213,6 @@ static struct mnt_namespace *alloc_mnt_ns(void) return new_ns; } -void mnt_make_longterm(struct vfsmount *mnt) -{ - __mnt_make_longterm(real_mount(mnt)); -} - -void mnt_make_shortterm(struct vfsmount *m) -{ -#ifdef CONFIG_SMP - struct mount *mnt = real_mount(m); - if (atomic_add_unless(&mnt->mnt_longterm, -1, 1)) - return; - br_write_lock(&vfsmount_lock); - atomic_dec(&mnt->mnt_longterm); - br_write_unlock(&vfsmount_lock); -#endif -} - /* * Allocate a new namespace structure and populate it with contents * copied from the namespace of the passed in task structure. @@ -2246,10 +2233,10 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, down_write(&namespace_sem); /* First pass: copy the tree topology */ new = copy_tree(old, old->mnt.mnt_root, CL_COPY_ALL | CL_EXPIRE); - if (!new) { + if (IS_ERR(new)) { up_write(&namespace_sem); kfree(new_ns); - return ERR_PTR(-ENOMEM); + return ERR_CAST(new); } new_ns->root = new; br_write_lock(&vfsmount_lock); @@ -2265,18 +2252,13 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, q = new; while (p) { q->mnt_ns = new_ns; - __mnt_make_longterm(q); if (fs) { if (&p->mnt == fs->root.mnt) { fs->root.mnt = mntget(&q->mnt); - __mnt_make_longterm(q); - mnt_make_shortterm(&p->mnt); rootmnt = &p->mnt; } if (&p->mnt == fs->pwd.mnt) { fs->pwd.mnt = mntget(&q->mnt); - __mnt_make_longterm(q); - mnt_make_shortterm(&p->mnt); pwdmnt = &p->mnt; } } @@ -2320,7 +2302,6 @@ static struct mnt_namespace *create_mnt_ns(struct vfsmount *m) if (!IS_ERR(new_ns)) { struct mount *mnt = real_mount(m); mnt->mnt_ns = new_ns; - __mnt_make_longterm(mnt); new_ns->root = mnt; list_add(&new_ns->list, &mnt->mnt_list); } else { @@ -2615,7 +2596,7 @@ struct vfsmount *kern_mount_data(struct file_system_type *type, void *data) * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ - mnt_make_longterm(mnt); + real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } @@ -2625,7 +2606,9 @@ void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR_OR_NULL(mnt)) { - mnt_make_shortterm(mnt); + br_write_lock(&vfsmount_lock); + real_mount(mnt)->mnt_ns = NULL; + br_write_unlock(&vfsmount_lock); mntput(mnt); } } diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index aeed93a..4117e7b 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -30,8 +30,8 @@ static void ncp_do_readdir(struct file *, void *, filldir_t, static int ncp_readdir(struct file *, void *, filldir_t); -static int ncp_create(struct inode *, struct dentry *, umode_t, struct nameidata *); -static struct dentry *ncp_lookup(struct inode *, struct dentry *, struct nameidata *); +static int ncp_create(struct inode *, struct dentry *, umode_t, bool); +static struct dentry *ncp_lookup(struct inode *, struct dentry *, unsigned int); static int ncp_unlink(struct inode *, struct dentry *); static int ncp_mkdir(struct inode *, struct dentry *, umode_t); static int ncp_rmdir(struct inode *, struct dentry *); @@ -72,7 +72,7 @@ const struct inode_operations ncp_dir_inode_operations = /* * Dentry operations routines */ -static int ncp_lookup_validate(struct dentry *, struct nameidata *); +static int ncp_lookup_validate(struct dentry *, unsigned int); static int ncp_hash_dentry(const struct dentry *, const struct inode *, struct qstr *); static int ncp_compare_dentry(const struct dentry *, const struct inode *, @@ -290,7 +290,7 @@ leave_me:; static int -ncp_lookup_validate(struct dentry *dentry, struct nameidata *nd) +ncp_lookup_validate(struct dentry *dentry, unsigned int flags) { struct ncp_server *server; struct dentry *parent; @@ -302,7 +302,7 @@ ncp_lookup_validate(struct dentry *dentry, struct nameidata *nd) if (dentry == dentry->d_sb->s_root) return 1; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; parent = dget_parent(dentry); @@ -836,7 +836,7 @@ out: return result; } -static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct ncp_server *server = NCP_SERVER(dir); struct inode *inode = NULL; @@ -980,7 +980,7 @@ out: } static int ncp_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return ncp_create_new(dir, dentry, mode, 0, 0); } diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 970659d..23ff18f 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -17,7 +17,6 @@ #include <linux/kthread.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/bc_xprt.h> -#include <linux/nsproxy.h> #include <net/inet_sock.h> @@ -107,7 +106,7 @@ nfs4_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt) { int ret; - ret = svc_create_xprt(serv, "tcp", xprt->xprt_net, PF_INET, + ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET, nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); if (ret <= 0) goto out_err; @@ -115,7 +114,7 @@ nfs4_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt) dprintk("NFS: Callback listener port = %u (af %u)\n", nfs_callback_tcpport, PF_INET); - ret = svc_create_xprt(serv, "tcp", xprt->xprt_net, PF_INET6, + ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6, nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); if (ret > 0) { nfs_callback_tcpport6 = ret; @@ -184,7 +183,7 @@ nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt) * fore channel connection. * Returns the input port (0) and sets the svc_serv bc_xprt on success */ - ret = svc_create_xprt(serv, "tcp-bc", xprt->xprt_net, PF_INET, 0, + ret = svc_create_xprt(serv, "tcp-bc", &init_net, PF_INET, 0, SVC_SOCK_ANONYMOUS); if (ret < 0) { rqstp = ERR_PTR(ret); @@ -254,7 +253,7 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) char svc_name[12]; int ret = 0; int minorversion_setup; - struct net *net = current->nsproxy->net_ns; + struct net *net = &init_net; mutex_lock(&nfs_callback_mutex); if (cb_info->users++ || cb_info->task != NULL) { @@ -330,7 +329,7 @@ void nfs_callback_down(int minorversion) cb_info->users--; if (cb_info->users == 0 && cb_info->task != NULL) { kthread_stop(cb_info->task); - svc_shutdown_net(cb_info->serv, current->nsproxy->net_ns); + svc_shutdown_net(cb_info->serv, &init_net); svc_exit_thread(cb_info->rqst); cb_info->serv = NULL; cb_info->rqst = NULL; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 95bfc24..e64b01d 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -455,9 +455,9 @@ static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp, args->csa_nrclists = ntohl(*p++); args->csa_rclists = NULL; if (args->csa_nrclists) { - args->csa_rclists = kmalloc(args->csa_nrclists * - sizeof(*args->csa_rclists), - GFP_KERNEL); + args->csa_rclists = kmalloc_array(args->csa_nrclists, + sizeof(*args->csa_rclists), + GFP_KERNEL); if (unlikely(args->csa_rclists == NULL)) goto out; @@ -696,7 +696,7 @@ static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp, const struct cb_sequenceres *res) { __be32 *p; - unsigned status = res->csr_status; + __be32 status = res->csr_status; if (unlikely(status != 0)) goto out; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 7d10875..f005b5b 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -207,7 +207,6 @@ error_0: static void nfs4_shutdown_session(struct nfs_client *clp) { if (nfs4_has_session(clp)) { - nfs4_deviceid_purge_client(clp); nfs4_destroy_session(clp->cl_session); nfs4_destroy_clientid(clp); } @@ -544,8 +543,6 @@ nfs_found_client(const struct nfs_client_initdata *cl_init, smp_rmb(); - BUG_ON(clp->cl_cons_state != NFS_CS_READY); - dprintk("<-- %s found nfs_client %p for %s\n", __func__, clp, cl_init->hostname ?: ""); return clp; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index f430057..a6b1c7f 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -46,8 +46,8 @@ static int nfs_opendir(struct inode *, struct file *); static int nfs_closedir(struct inode *, struct file *); static int nfs_readdir(struct file *, void *, filldir_t); -static struct dentry *nfs_lookup(struct inode *, struct dentry *, struct nameidata *); -static int nfs_create(struct inode *, struct dentry *, umode_t, struct nameidata *); +static struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); +static int nfs_create(struct inode *, struct dentry *, umode_t, bool); static int nfs_mkdir(struct inode *, struct dentry *, umode_t); static int nfs_rmdir(struct inode *, struct dentry *); static int nfs_unlink(struct inode *, struct dentry *); @@ -111,11 +111,13 @@ const struct inode_operations nfs3_dir_inode_operations = { #ifdef CONFIG_NFS_V4 -static struct dentry *nfs_atomic_lookup(struct inode *, struct dentry *, struct nameidata *); -static int nfs_open_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd); +static int nfs_atomic_open(struct inode *, struct dentry *, + struct file *, unsigned, umode_t, + int *); const struct inode_operations nfs4_dir_inode_operations = { - .create = nfs_open_create, - .lookup = nfs_atomic_lookup, + .create = nfs_create, + .lookup = nfs_lookup, + .atomic_open = nfs_atomic_open, .link = nfs_link, .unlink = nfs_unlink, .symlink = nfs_symlink, @@ -1029,27 +1031,14 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry) } /* - * Return the intent data that applies to this particular path component - * - * Note that the current set of intents only apply to the very last - * component of the path and none of them is set before that last - * component. - */ -static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd, - unsigned int mask) -{ - return nd->flags & mask; -} - -/* * Use intent information to check whether or not we're going to do * an O_EXCL create using this path component. */ -static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd) +static int nfs_is_exclusive_create(struct inode *dir, unsigned int flags) { if (NFS_PROTO(dir)->version == 2) return 0; - return nd && nfs_lookup_check_intent(nd, LOOKUP_EXCL); + return flags & LOOKUP_EXCL; } /* @@ -1061,25 +1050,20 @@ static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd) * */ static inline -int nfs_lookup_verify_inode(struct inode *inode, struct nameidata *nd) +int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags) { struct nfs_server *server = NFS_SERVER(inode); if (IS_AUTOMOUNT(inode)) return 0; - if (nd != NULL) { - /* VFS wants an on-the-wire revalidation */ - if (nd->flags & LOOKUP_REVAL) - goto out_force; - /* This is an open(2) */ - if (nfs_lookup_check_intent(nd, LOOKUP_OPEN) != 0 && - !(server->flags & NFS_MOUNT_NOCTO) && - (S_ISREG(inode->i_mode) || - S_ISDIR(inode->i_mode))) - goto out_force; - return 0; - } - return nfs_revalidate_inode(server, inode); + /* VFS wants an on-the-wire revalidation */ + if (flags & LOOKUP_REVAL) + goto out_force; + /* This is an open(2) */ + if ((flags & LOOKUP_OPEN) && !(server->flags & NFS_MOUNT_NOCTO) && + (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) + goto out_force; + return 0; out_force: return __nfs_revalidate_inode(server, inode); } @@ -1093,10 +1077,10 @@ out_force: */ static inline int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { /* Don't revalidate a negative dentry if we're creating a new file */ - if (nd != NULL && nfs_lookup_check_intent(nd, LOOKUP_CREATE) != 0) + if (flags & LOOKUP_CREATE) return 0; if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) return 1; @@ -1114,7 +1098,7 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, * If the parent directory is seen to have changed, we throw out the * cached dentry and do a new lookup. */ -static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) +static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *dir; struct inode *inode; @@ -1123,7 +1107,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) struct nfs_fattr *fattr = NULL; int error; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; parent = dget_parent(dentry); @@ -1132,7 +1116,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) inode = dentry->d_inode; if (!inode) { - if (nfs_neg_need_reval(dir, dentry, nd)) + if (nfs_neg_need_reval(dir, dentry, flags)) goto out_bad; goto out_valid_noent; } @@ -1148,8 +1132,8 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) goto out_set_verifier; /* Force a full look up iff the parent directory has changed */ - if (!nfs_is_exclusive_create(dir, nd) && nfs_check_verifier(dir, dentry)) { - if (nfs_lookup_verify_inode(inode, nd)) + if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry)) { + if (nfs_lookup_verify_inode(inode, flags)) goto out_zap_parent; goto out_valid; } @@ -1286,7 +1270,7 @@ const struct dentry_operations nfs_dentry_operations = { .d_release = nfs_d_release, }; -static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct dentry *res; struct dentry *parent; @@ -1307,7 +1291,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru * If we're doing an exclusive create, optimize away the lookup * but don't hash the dentry. */ - if (nfs_is_exclusive_create(dir, nd)) { + if (nfs_is_exclusive_create(dir, flags)) { d_instantiate(dentry, NULL); res = NULL; goto out; @@ -1354,7 +1338,7 @@ out: } #ifdef CONFIG_NFS_V4 -static int nfs4_lookup_revalidate(struct dentry *, struct nameidata *); +static int nfs4_lookup_revalidate(struct dentry *, unsigned int); const struct dentry_operations nfs4_dentry_operations = { .d_revalidate = nfs4_lookup_revalidate, @@ -1364,24 +1348,6 @@ const struct dentry_operations nfs4_dentry_operations = { .d_release = nfs_d_release, }; -/* - * Use intent information to determine whether we need to substitute - * the NFSv4-style stateful OPEN for the LOOKUP call - */ -static int is_atomic_open(struct nameidata *nd) -{ - if (nd == NULL || nfs_lookup_check_intent(nd, LOOKUP_OPEN) == 0) - return 0; - /* NFS does not (yet) have a stateful open for directories */ - if (nd->flags & LOOKUP_DIRECTORY) - return 0; - /* Are we trying to write to a read only partition? */ - if (__mnt_is_readonly(nd->path.mnt) && - (nd->intent.open.flags & (O_CREAT|O_TRUNC|O_ACCMODE))) - return 0; - return 1; -} - static fmode_t flags_to_mode(int flags) { fmode_t res = (__force fmode_t)flags & FMODE_EXEC; @@ -1403,136 +1369,143 @@ static int do_open(struct inode *inode, struct file *filp) return 0; } -static int nfs_intent_set_file(struct nameidata *nd, struct nfs_open_context *ctx) +static int nfs_finish_open(struct nfs_open_context *ctx, + struct dentry *dentry, + struct file *file, unsigned open_flags, + int *opened) { - struct file *filp; - int ret = 0; + int err; + + if (ctx->dentry != dentry) { + dput(ctx->dentry); + ctx->dentry = dget(dentry); + } /* If the open_intent is for execute, we have an extra check to make */ if (ctx->mode & FMODE_EXEC) { - ret = nfs_may_open(ctx->dentry->d_inode, - ctx->cred, - nd->intent.open.flags); - if (ret < 0) + err = nfs_may_open(dentry->d_inode, ctx->cred, open_flags); + if (err < 0) goto out; } - filp = lookup_instantiate_filp(nd, ctx->dentry, do_open); - if (IS_ERR(filp)) - ret = PTR_ERR(filp); - else - nfs_file_set_open_context(filp, ctx); + + err = finish_open(file, dentry, do_open, opened); + if (err) + goto out; + nfs_file_set_open_context(file, ctx); + out: put_nfs_open_context(ctx); - return ret; + return err; } -static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static int nfs_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned open_flags, + umode_t mode, int *opened) { struct nfs_open_context *ctx; - struct iattr attr; - struct dentry *res = NULL; + struct dentry *res; + struct iattr attr = { .ia_valid = ATTR_OPEN }; struct inode *inode; - int open_flags; int err; - dfprintk(VFS, "NFS: atomic_lookup(%s/%ld), %s\n", + /* Expect a negative dentry */ + BUG_ON(dentry->d_inode); + + dfprintk(VFS, "NFS: atomic_open(%s/%ld), %s\n", dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); - /* Check that we are indeed trying to open this file */ - if (!is_atomic_open(nd)) + /* NFS only supports OPEN on regular files */ + if ((open_flags & O_DIRECTORY)) { + if (!d_unhashed(dentry)) { + /* + * Hashed negative dentry with O_DIRECTORY: dentry was + * revalidated and is fine, no need to perform lookup + * again + */ + return -ENOENT; + } goto no_open; - - if (dentry->d_name.len > NFS_SERVER(dir)->namelen) { - res = ERR_PTR(-ENAMETOOLONG); - goto out; - } - - /* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash - * the dentry. */ - if (nd->flags & LOOKUP_EXCL) { - d_instantiate(dentry, NULL); - goto out; } - open_flags = nd->intent.open.flags; - attr.ia_valid = ATTR_OPEN; - - ctx = create_nfs_open_context(dentry, open_flags); - res = ERR_CAST(ctx); - if (IS_ERR(ctx)) - goto out; + if (dentry->d_name.len > NFS_SERVER(dir)->namelen) + return -ENAMETOOLONG; - if (nd->flags & LOOKUP_CREATE) { - attr.ia_mode = nd->intent.open.create_mode; + if (open_flags & O_CREAT) { attr.ia_valid |= ATTR_MODE; - attr.ia_mode &= ~current_umask(); - } else - open_flags &= ~(O_EXCL | O_CREAT); - + attr.ia_mode = mode & ~current_umask(); + } if (open_flags & O_TRUNC) { attr.ia_valid |= ATTR_SIZE; attr.ia_size = 0; } - /* Open the file on the server */ + ctx = create_nfs_open_context(dentry, open_flags); + err = PTR_ERR(ctx); + if (IS_ERR(ctx)) + goto out; + nfs_block_sillyrename(dentry->d_parent); inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr); + d_drop(dentry); if (IS_ERR(inode)) { nfs_unblock_sillyrename(dentry->d_parent); put_nfs_open_context(ctx); - switch (PTR_ERR(inode)) { - /* Make a negative dentry */ - case -ENOENT: - d_add(dentry, NULL); - res = NULL; - goto out; - /* This turned out not to be a regular file */ - case -EISDIR: - case -ENOTDIR: + err = PTR_ERR(inode); + switch (err) { + case -ENOENT: + d_add(dentry, NULL); + break; + case -EISDIR: + case -ENOTDIR: + goto no_open; + case -ELOOP: + if (!(open_flags & O_NOFOLLOW)) goto no_open; - case -ELOOP: - if (!(nd->intent.open.flags & O_NOFOLLOW)) - goto no_open; + break; /* case -EINVAL: */ - default: - res = ERR_CAST(inode); - goto out; + default: + break; } + goto out; } res = d_add_unique(dentry, inode); - nfs_unblock_sillyrename(dentry->d_parent); - if (res != NULL) { - dput(ctx->dentry); - ctx->dentry = dget(res); + if (res != NULL) dentry = res; - } - err = nfs_intent_set_file(nd, ctx); - if (err < 0) { - if (res != NULL) - dput(res); - return ERR_PTR(err); - } -out: + + nfs_unblock_sillyrename(dentry->d_parent); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - return res; + + err = nfs_finish_open(ctx, dentry, file, open_flags, opened); + + dput(res); +out: + return err; + no_open: - return nfs_lookup(dir, dentry, nd); + res = nfs_lookup(dir, dentry, 0); + err = PTR_ERR(res); + if (IS_ERR(res)) + goto out; + + return finish_no_open(file, res); } -static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) +static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) { struct dentry *parent = NULL; struct inode *inode; struct inode *dir; - int openflags, ret = 0; + int ret = 0; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; - inode = dentry->d_inode; - if (!is_atomic_open(nd) || d_mountpoint(dentry)) + if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY)) + goto no_open; + if (d_mountpoint(dentry)) goto no_open; + inode = dentry->d_inode; parent = dget_parent(dentry); dir = parent->d_inode; @@ -1540,7 +1513,7 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) * optimize away revalidation of negative dentries. */ if (inode == NULL) { - if (!nfs_neg_need_reval(dir, dentry, nd)) + if (!nfs_neg_need_reval(dir, dentry, flags)) ret = 1; goto out; } @@ -1548,9 +1521,8 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) /* NFS only supports OPEN on regular files */ if (!S_ISREG(inode->i_mode)) goto no_open_dput; - openflags = nd->intent.open.flags; /* We cannot do exclusive creation on a positive dentry */ - if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL)) + if (flags & LOOKUP_EXCL) goto no_open_dput; /* Let f_op->open() actually open (and revalidate) the file */ @@ -1563,48 +1535,7 @@ out: no_open_dput: dput(parent); no_open: - return nfs_lookup_revalidate(dentry, nd); -} - -static int nfs_open_create(struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) -{ - struct nfs_open_context *ctx = NULL; - struct iattr attr; - int error; - int open_flags = O_CREAT|O_EXCL; - - dfprintk(VFS, "NFS: create(%s/%ld), %s\n", - dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); - - attr.ia_mode = mode; - attr.ia_valid = ATTR_MODE; - - if (nd) - open_flags = nd->intent.open.flags; - - ctx = create_nfs_open_context(dentry, open_flags); - error = PTR_ERR(ctx); - if (IS_ERR(ctx)) - goto out_err_drop; - - error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, ctx); - if (error != 0) - goto out_put_ctx; - if (nd) { - error = nfs_intent_set_file(nd, ctx); - if (error < 0) - goto out_err; - } else { - put_nfs_open_context(ctx); - } - return 0; -out_put_ctx: - put_nfs_open_context(ctx); -out_err_drop: - d_drop(dentry); -out_err: - return error; + return nfs_lookup_revalidate(dentry, flags); } #endif /* CONFIG_NFSV4 */ @@ -1658,11 +1589,11 @@ out_error: * reply path made it appear to have failed. */ static int nfs_create(struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { struct iattr attr; + int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT; int error; - int open_flags = O_CREAT|O_EXCL; dfprintk(VFS, "NFS: create(%s/%ld), %s\n", dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); @@ -1670,10 +1601,7 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, attr.ia_mode = mode; attr.ia_valid = ATTR_MODE; - if (nd) - open_flags = nd->intent.open.flags; - - error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, NULL); + error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags); if (error != 0) goto out_err; return 0; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index ad2775d..4825337 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -484,17 +484,22 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) list_for_each_entry_safe(req, tmp, &reqs, wb_list) { if (!nfs_pageio_add_request(&desc, req)) { + nfs_list_remove_request(req); nfs_list_add_request(req, &failed); spin_lock(cinfo.lock); dreq->flags = 0; dreq->error = -EIO; spin_unlock(cinfo.lock); } + nfs_release_request(req); } nfs_pageio_complete(&desc); - while (!list_empty(&failed)) + while (!list_empty(&failed)) { + req = nfs_list_entry(failed.next); + nfs_list_remove_request(req); nfs_unlock_and_release_request(req); + } if (put_dreq(dreq)) nfs_direct_write_complete(dreq, dreq->inode); @@ -523,9 +528,9 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) nfs_list_remove_request(req); if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) { /* Note the rewrite will go through mds */ - kref_get(&req->wb_kref); nfs_mark_request_commit(req, NULL, &cinfo); - } + } else + nfs_release_request(req); nfs_unlock_and_release_request(req); } @@ -716,12 +721,12 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) bit = NFS_IOHDR_NEED_RESCHED; else if (dreq->flags == 0) { - memcpy(&dreq->verf, &req->wb_verf, + memcpy(&dreq->verf, hdr->verf, sizeof(dreq->verf)); bit = NFS_IOHDR_NEED_COMMIT; dreq->flags = NFS_ODIRECT_DO_COMMIT; } else if (dreq->flags == NFS_ODIRECT_DO_COMMIT) { - if (memcmp(&dreq->verf, &req->wb_verf, sizeof(dreq->verf))) { + if (memcmp(&dreq->verf, hdr->verf, sizeof(dreq->verf))) { dreq->flags = NFS_ODIRECT_RESCHED_WRITES; bit = NFS_IOHDR_NEED_RESCHED; } else diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 8abfb19..a67990f 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -62,7 +62,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i */ spin_lock(&sb->s_root->d_inode->i_lock); spin_lock(&sb->s_root->d_lock); - list_del_init(&sb->s_root->d_alias); + hlist_del_init(&sb->s_root->d_alias); spin_unlock(&sb->s_root->d_lock); spin_unlock(&sb->s_root->d_inode->i_lock); } diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index b5b86a0..864c51e 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -57,6 +57,11 @@ unsigned int nfs_idmap_cache_timeout = 600; static const struct cred *id_resolver_cache; static struct key_type key_type_id_resolver_legacy; +struct idmap { + struct rpc_pipe *idmap_pipe; + struct key_construction *idmap_key_cons; + struct mutex idmap_mutex; +}; /** * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields @@ -310,9 +315,11 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, name, namelen, type, data, data_size, NULL); if (ret < 0) { + mutex_lock(&idmap->idmap_mutex); ret = nfs_idmap_request_key(&key_type_id_resolver_legacy, name, namelen, type, data, data_size, idmap); + mutex_unlock(&idmap->idmap_mutex); } return ret; } @@ -354,11 +361,6 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *typ /* idmap classic begins here */ module_param(nfs_idmap_cache_timeout, int, 0644); -struct idmap { - struct rpc_pipe *idmap_pipe; - struct key_construction *idmap_key_cons; -}; - enum { Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err }; @@ -469,6 +471,7 @@ nfs_idmap_new(struct nfs_client *clp) return error; } idmap->idmap_pipe = pipe; + mutex_init(&idmap->idmap_mutex); clp->cl_idmap = idmap; return 0; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e605d69..f729698 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1530,7 +1530,6 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi) nfsi->delegation_state = 0; init_rwsem(&nfsi->rwsem); nfsi->layout = NULL; - atomic_set(&nfsi->commit_info.rpcs_out, 0); #endif } @@ -1545,6 +1544,7 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->commit_info.list); nfsi->npages = 0; nfsi->commit_info.ncommit = 0; + atomic_set(&nfsi->commit_info.rpcs_out, 0); atomic_set(&nfsi->silly_count, 1); INIT_HLIST_HEAD(&nfsi->silly_list); init_waitqueue_head(&nfsi->waitqueue); diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 2292a0f..3187e24 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -314,7 +314,7 @@ static void nfs3_free_createdata(struct nfs3_createdata *data) */ static int nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags, struct nfs_open_context *ctx) + int flags) { struct nfs3_createdata *data; umode_t mode = sattr->ia_mode; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index c6827f93..cc5900a 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -295,7 +295,7 @@ is_ds_client(struct nfs_client *clp) extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[]; -extern const u32 nfs4_fattr_bitmap[2]; +extern const u32 nfs4_fattr_bitmap[3]; extern const u32 nfs4_statfs_bitmap[2]; extern const u32 nfs4_pathconf_bitmap[2]; extern const u32 nfs4_fsinfo_bitmap[3]; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d48dbef..c157b20 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -105,6 +105,8 @@ static int nfs4_map_errors(int err) return -EINVAL; case -NFS4ERR_SHARE_DENIED: return -EACCES; + case -NFS4ERR_MINOR_VERS_MISMATCH: + return -EPROTONOSUPPORT; default: dprintk("%s could not handle NFSv4 error %d\n", __func__, -err); @@ -116,7 +118,7 @@ static int nfs4_map_errors(int err) /* * This is our standard bitmap for GETATTR requests. */ -const u32 nfs4_fattr_bitmap[2] = { +const u32 nfs4_fattr_bitmap[3] = { FATTR4_WORD0_TYPE | FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE @@ -133,6 +135,24 @@ const u32 nfs4_fattr_bitmap[2] = { | FATTR4_WORD1_TIME_MODIFY }; +static const u32 nfs4_pnfs_open_bitmap[3] = { + FATTR4_WORD0_TYPE + | FATTR4_WORD0_CHANGE + | FATTR4_WORD0_SIZE + | FATTR4_WORD0_FSID + | FATTR4_WORD0_FILEID, + FATTR4_WORD1_MODE + | FATTR4_WORD1_NUMLINKS + | FATTR4_WORD1_OWNER + | FATTR4_WORD1_OWNER_GROUP + | FATTR4_WORD1_RAWDEV + | FATTR4_WORD1_SPACE_USED + | FATTR4_WORD1_TIME_ACCESS + | FATTR4_WORD1_TIME_METADATA + | FATTR4_WORD1_TIME_MODIFY, + FATTR4_WORD2_MDSTHRESHOLD +}; + const u32 nfs4_statfs_bitmap[2] = { FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE @@ -844,6 +864,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->o_arg.name = &dentry->d_name; p->o_arg.server = server; p->o_arg.bitmask = server->attr_bitmask; + p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0]; p->o_arg.claim = NFS4_OPEN_CLAIM_NULL; if (attrs != NULL && attrs->ia_valid != 0) { __be32 verf[2]; @@ -1820,6 +1841,7 @@ static int _nfs4_do_open(struct inode *dir, opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc(); if (!opendata->f_attr.mdsthreshold) goto err_opendata_put; + opendata->o_arg.open_bitmap = &nfs4_pnfs_open_bitmap[0]; } if (dentry->d_inode != NULL) opendata->state = nfs4_get_open_state(dentry->d_inode, sp); @@ -1880,6 +1902,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct nfs4_state *res; int status; + fmode &= FMODE_READ|FMODE_WRITE; do { status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred, &res, ctx_th); @@ -2526,6 +2549,14 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, nfs_fattr_init(fattr); + /* Deal with open(O_TRUNC) */ + if (sattr->ia_valid & ATTR_OPEN) + sattr->ia_valid &= ~(ATTR_MTIME|ATTR_CTIME|ATTR_OPEN); + + /* Optimization: if the end result is no change, don't RPC */ + if ((sattr->ia_valid & ~(ATTR_FILE)) == 0) + return 0; + /* Search for an existing open(O_WRITE) file */ if (sattr->ia_valid & ATTR_FILE) { struct nfs_open_context *ctx; @@ -2537,10 +2568,6 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } } - /* Deal with open(O_TRUNC) */ - if (sattr->ia_valid & ATTR_OPEN) - sattr->ia_valid &= ~(ATTR_MTIME|ATTR_CTIME|ATTR_OPEN); - status = nfs4_do_setattr(inode, cred, fattr, sattr, state); if (status == 0) nfs_setattr_update_inode(inode, sattr); @@ -2779,37 +2806,22 @@ static int nfs4_proc_readlink(struct inode *inode, struct page *page, } /* - * Got race? - * We will need to arrange for the VFS layer to provide an atomic open. - * Until then, this create/open method is prone to inefficiency and race - * conditions due to the lookup, create, and open VFS calls from sys_open() - * placed on the wire. - * - * Given the above sorry state of affairs, I'm simply sending an OPEN. - * The file will be opened again in the subsequent VFS open call - * (nfs4_proc_file_open). - * - * The open for read will just hang around to be used by any process that - * opens the file O_RDONLY. This will all be resolved with the VFS changes. + * This is just for mknod. open(O_CREAT) will always do ->open_context(). */ - static int nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags, struct nfs_open_context *ctx) + int flags) { - struct dentry *de = dentry; + struct nfs_open_context *ctx; struct nfs4_state *state; - struct rpc_cred *cred = NULL; - fmode_t fmode = 0; int status = 0; - if (ctx != NULL) { - cred = ctx->cred; - de = ctx->dentry; - fmode = ctx->mode; - } + ctx = alloc_nfs_open_context(dentry, FMODE_READ); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + sattr->ia_mode &= ~current_umask(); - state = nfs4_do_open(dir, de, fmode, flags, sattr, cred, NULL); + state = nfs4_do_open(dir, dentry, ctx->mode, flags, sattr, ctx->cred, NULL); d_drop(dentry); if (IS_ERR(state)) { status = PTR_ERR(state); @@ -2817,11 +2829,9 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, } d_add(dentry, igrab(state->inode)); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - if (ctx != NULL) - ctx->state = state; - else - nfs4_close_sync(state, fmode); + ctx->state = state; out: + put_nfs_open_context(ctx); return status; } @@ -5275,7 +5285,7 @@ static int _nfs4_proc_destroy_clientid(struct nfs_client *clp, status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); if (status) - pr_warn("NFS: Got error %d from the server %s on " + dprintk("NFS: Got error %d from the server %s on " "DESTROY_CLIENTID.", status, clp->cl_hostname); return status; } @@ -5746,8 +5756,7 @@ int nfs4_proc_destroy_session(struct nfs4_session *session, status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); if (status) - printk(KERN_WARNING - "NFS: Got error %d from the server on DESTROY_SESSION. " + dprintk("NFS: Got error %d from the server on DESTROY_SESSION. " "Session has been destroyed regardless...\n", status); dprintk("<-- nfs4_proc_destroy_session\n"); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index c679b9e..f38300e 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -244,6 +244,16 @@ static int nfs4_begin_drain_session(struct nfs_client *clp) return nfs4_wait_on_slot_tbl(&ses->fc_slot_table); } +static void nfs41_finish_session_reset(struct nfs_client *clp) +{ + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + /* create_session negotiated new slot table */ + clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state); + clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + nfs41_setup_state_renewal(clp); +} + int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred) { int status; @@ -259,8 +269,7 @@ do_confirm: status = nfs4_proc_create_session(clp, cred); if (status != 0) goto out; - clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); - nfs41_setup_state_renewal(clp); + nfs41_finish_session_reset(clp); nfs_mark_client_ready(clp, NFS_CS_READY); out: return status; @@ -1772,16 +1781,9 @@ static int nfs4_reset_session(struct nfs_client *clp) status = nfs4_handle_reclaim_lease_error(clp, status); goto out; } - clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); - /* create_session negotiated new slot table */ - clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state); - clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + nfs41_finish_session_reset(clp); dprintk("%s: session reset was successful for server %s!\n", __func__, clp->cl_hostname); - - /* Let the state manager reestablish state */ - if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) - nfs41_setup_state_renewal(clp); out: if (cred) put_rpccred(cred); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index ee4a74d..18fae29 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1198,12 +1198,13 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c } static void encode_getfattr_open(struct xdr_stream *xdr, const u32 *bitmask, + const u32 *open_bitmap, struct compound_hdr *hdr) { encode_getattr_three(xdr, - bitmask[0] & nfs4_fattr_bitmap[0], - bitmask[1] & nfs4_fattr_bitmap[1], - bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD, + bitmask[0] & open_bitmap[0], + bitmask[1] & open_bitmap[1], + bitmask[2] & open_bitmap[2], hdr); } @@ -2221,7 +2222,7 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, encode_putfh(xdr, args->fh, &hdr); encode_open(xdr, args, &hdr); encode_getfh(xdr, &hdr); - encode_getfattr_open(xdr, args->bitmask, &hdr); + encode_getfattr_open(xdr, args->bitmask, args->open_bitmap, &hdr); encode_nops(&hdr); } @@ -4359,7 +4360,10 @@ static int decode_attr_mdsthreshold(struct xdr_stream *xdr, if (unlikely(bitmap[2] & (FATTR4_WORD2_MDSTHRESHOLD - 1U))) return -EIO; - if (likely(bitmap[2] & FATTR4_WORD2_MDSTHRESHOLD)) { + if (bitmap[2] & FATTR4_WORD2_MDSTHRESHOLD) { + /* Did the server return an unrequested attribute? */ + if (unlikely(res == NULL)) + return -EREMOTEIO; p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; @@ -4372,6 +4376,7 @@ static int decode_attr_mdsthreshold(struct xdr_stream *xdr, __func__); status = decode_first_threshold_item4(xdr, res); + bitmap[2] &= ~FATTR4_WORD2_MDSTHRESHOLD; } return status; out_overflow: diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index b47277ba..f50d3e8 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -454,7 +454,10 @@ int objio_read_pagelist(struct nfs_read_data *rdata) objios->ios->done = _read_done; dprintk("%s: offset=0x%llx length=0x%x\n", __func__, rdata->args.offset, rdata->args.count); - return ore_read(objios->ios); + ret = ore_read(objios->ios); + if (unlikely(ret)) + objio_free_result(&objios->oir); + return ret; } /* @@ -486,8 +489,16 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) struct nfs_write_data *wdata = objios->oir.rpcdata; struct address_space *mapping = wdata->header->inode->i_mapping; pgoff_t index = offset / PAGE_SIZE; - struct page *page = find_get_page(mapping, index); + struct page *page; + loff_t i_size = i_size_read(wdata->header->inode); + + if (offset >= i_size) { + *uptodate = true; + dprintk("%s: g_zero_page index=0x%lx\n", __func__, index); + return ZERO_PAGE(0); + } + page = find_get_page(mapping, index); if (!page) { page = find_or_create_page(mapping, index, GFP_NOFS); if (unlikely(!page)) { @@ -507,8 +518,10 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) static void __r4w_put_page(void *priv, struct page *page) { - dprintk("%s: index=0x%lx\n", __func__, page->index); - page_cache_release(page); + dprintk("%s: index=0x%lx\n", __func__, + (page == ZERO_PAGE(0)) ? -1UL : page->index); + if (ZERO_PAGE(0) != page) + page_cache_release(page); return; } @@ -539,8 +552,10 @@ int objio_write_pagelist(struct nfs_write_data *wdata, int how) dprintk("%s: offset=0x%llx length=0x%x\n", __func__, wdata->args.offset, wdata->args.count); ret = ore_write(objios->ios); - if (unlikely(ret)) + if (unlikely(ret)) { + objio_free_result(&objios->oir); return ret; + } if (objios->sync) _write_done(objios->ios, objios); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b8323aa..bbc49ca 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -70,6 +70,10 @@ find_pnfs_driver(u32 id) spin_lock(&pnfs_spinlock); local = find_pnfs_driver_locked(id); + if (local != NULL && !try_module_get(local->owner)) { + dprintk("%s: Could not grab reference on module\n", __func__); + local = NULL; + } spin_unlock(&pnfs_spinlock); return local; } @@ -80,6 +84,9 @@ unset_pnfs_layoutdriver(struct nfs_server *nfss) if (nfss->pnfs_curr_ld) { if (nfss->pnfs_curr_ld->clear_layoutdriver) nfss->pnfs_curr_ld->clear_layoutdriver(nfss); + /* Decrement the MDS count. Purge the deviceid cache if zero */ + if (atomic_dec_and_test(&nfss->nfs_client->cl_mds_count)) + nfs4_deviceid_purge_client(nfss->nfs_client); module_put(nfss->pnfs_curr_ld->owner); } nfss->pnfs_curr_ld = NULL; @@ -115,10 +122,6 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh, goto out_no_driver; } } - if (!try_module_get(ld_type->owner)) { - dprintk("%s: Could not grab reference on module\n", __func__); - goto out_no_driver; - } server->pnfs_curr_ld = ld_type; if (ld_type->set_layoutdriver && ld_type->set_layoutdriver(server, mntfh)) { @@ -127,6 +130,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh, module_put(ld_type->owner); goto out_no_driver; } + /* Bump the MDS count */ + atomic_inc(&server->nfs_client->cl_mds_count); dprintk("%s: pNFS module for %u set\n", __func__, id); return; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 29fd23c..64f90d8 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -365,7 +365,7 @@ static inline bool pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src, struct nfs_server *nfss) { - return (dst && src && src->bm != 0 && + return (dst && src && src->bm != 0 && nfss->pnfs_curr_ld && nfss->pnfs_curr_ld->id == src->l_type); } diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index a706b6b..4433806 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -259,7 +259,7 @@ static void nfs_free_createdata(const struct nfs_createdata *data) static int nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags, struct nfs_open_context *ctx) + int flags) { struct nfs_createdata *data; struct rpc_message msg = { @@ -651,7 +651,7 @@ static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data) /* Emulate the eof flag, which isn't normally needed in NFSv2 * as it is guaranteed to always return the file attributes */ - if (data->args.offset + data->args.count >= data->res.fattr->size) + if (data->args.offset + data->res.count >= data->res.fattr->size) data->res.eof = 1; } return 0; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ff656c0..8b2a297 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1867,6 +1867,7 @@ static int nfs23_validate_mount_data(void *options, if (data == NULL) goto out_no_data; + args->version = NFS_DEFAULT_VERSION; switch (data->version) { case 1: data->namlen = 0; @@ -2418,7 +2419,7 @@ static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type, sb_mntdata.mntflags |= MS_SYNCHRONOUS; /* Get a superblock - note that we may end up sharing one that already exists */ - s = sget(fs_type, compare_super, nfs_set_super, &sb_mntdata); + s = sget(fs_type, compare_super, nfs_set_super, flags, &sb_mntdata); if (IS_ERR(s)) { mntroot = ERR_CAST(s); goto out_err_nosb; @@ -2637,6 +2638,8 @@ static int nfs4_validate_mount_data(void *options, if (data == NULL) goto out_no_data; + args->version = 4; + switch (data->version) { case 1: if (data->host_addrlen > sizeof(args->nfs_server.address)) @@ -2857,6 +2860,8 @@ static struct dentry *nfs4_try_mount(int flags, const char *dev_name, dfprintk(MOUNT, "--> nfs4_try_mount()\n"); + mount_info->fill_super = nfs4_fill_super; + export_path = data->nfs_server.export_path; data->nfs_server.export_path = "/"; root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info, diff --git a/fs/nfs/write.c b/fs/nfs/write.c index e6fe3d6..4d6861c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -80,6 +80,7 @@ struct nfs_write_header *nfs_writehdr_alloc(void) INIT_LIST_HEAD(&hdr->rpc_list); spin_lock_init(&hdr->lock); atomic_set(&hdr->refcnt, 0); + hdr->verf = &p->verf; } return p; } @@ -619,6 +620,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) goto next; } if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) { + memcpy(&req->wb_verf, hdr->verf, sizeof(req->wb_verf)); nfs_mark_request_commit(req, hdr->lseg, &cinfo); goto next; } @@ -1255,15 +1257,14 @@ static void nfs_writeback_release_common(void *calldata) struct nfs_write_data *data = calldata; struct nfs_pgio_header *hdr = data->header; int status = data->task.tk_status; - struct nfs_page *req = hdr->req; if ((status >= 0) && nfs_write_need_commit(data)) { spin_lock(&hdr->lock); if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) ; /* Do nothing */ else if (!test_and_set_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) - memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); - else if (memcmp(&req->wb_verf, &data->verf, sizeof(req->wb_verf))) + memcpy(hdr->verf, &data->verf, sizeof(*hdr->verf)); + else if (memcmp(hdr->verf, &data->verf, sizeof(*hdr->verf))) set_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags); spin_unlock(&hdr->lock); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8fdc9ec..94effd5 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -900,7 +900,7 @@ static void free_session(struct kref *kref) struct nfsd4_session *ses; int mem; - BUG_ON(!spin_is_locked(&client_lock)); + lockdep_assert_held(&client_lock); ses = container_of(kref, struct nfsd4_session, se_ref); nfsd4_del_conns(ses); spin_lock(&nfsd_drc_lock); @@ -1080,7 +1080,7 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) static inline void free_client(struct nfs4_client *clp) { - BUG_ON(!spin_is_locked(&client_lock)); + lockdep_assert_held(&client_lock); while (!list_empty(&clp->cl_sessions)) { struct nfsd4_session *ses; ses = list_entry(clp->cl_sessions.next, struct nfsd4_session, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index c8bd9c3..4700a0a 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -745,7 +745,7 @@ __be32 nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp) { - struct dentry *dentry; + struct path path; struct inode *inode; int flags = O_RDONLY|O_LARGEFILE; __be32 err; @@ -762,8 +762,9 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, if (err) goto out; - dentry = fhp->fh_dentry; - inode = dentry->d_inode; + path.mnt = fhp->fh_export->ex_path.mnt; + path.dentry = fhp->fh_dentry; + inode = path.dentry->d_inode; /* Disallow write access to files with the append-only bit set * or any access when mandatory locking enabled @@ -792,8 +793,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, else flags = O_WRONLY|O_LARGEFILE; } - *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_path.mnt), - flags, current_cred()); + *filp = dentry_open(&path, flags, current_cred()); if (IS_ERR(*filp)) host_err = PTR_ERR(*filp); else { @@ -1329,7 +1329,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, err = 0; switch (type) { case S_IFREG: - host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL); + host_err = vfs_create(dirp, dchild, iap->ia_mode, true); if (!host_err) nfsd_check_ignore_resizing(iap); break; @@ -1492,7 +1492,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; } - host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL); + host_err = vfs_create(dirp, dchild, iap->ia_mode, true); if (host_err < 0) { fh_drop_write(fhp); goto out_nfserr; diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 08a07a2..57ceaf3 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -191,6 +191,8 @@ void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs) while (!list_empty(head)) { 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); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index b728479..1d0c0b8 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -63,7 +63,7 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode) */ static struct dentry * -nilfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; ino_t ino; @@ -85,7 +85,7 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) * with d_instantiate(). */ static int nilfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; struct nilfs_transaction_info ti; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 0e72ad6..88e11fb 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2309,6 +2309,8 @@ nilfs_remove_written_gcinodes(struct the_nilfs *nilfs, struct list_head *head) if (!test_bit(NILFS_I_UPDATED, &ii->i_state)) continue; list_del_init(&ii->i_dirty); + truncate_inode_pages(&ii->vfs_inode.i_data, 0); + nilfs_btnode_cache_clear(&ii->i_btnode_cache); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 1099a76..d57c42f9 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1288,7 +1288,8 @@ nilfs_mount(struct file_system_type *fs_type, int flags, err = -EBUSY; goto failed; } - s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, sd.bdev); + s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, flags, + sd.bdev); mutex_unlock(&sd.bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) { err = PTR_ERR(s); @@ -1301,7 +1302,6 @@ nilfs_mount(struct file_system_type *fs_type, int flags, s_new = true; /* New superblock instance created */ - s->s_flags = flags; s->s_mode = mode; strlcpy(s->s_id, bdevname(sd.bdev, b), sizeof(s->s_id)); sb_set_blocksize(s, block_size(sd.bdev)); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 3568c8a..d438036 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -61,8 +61,6 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group, static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event) { int client_fd; - struct dentry *dentry; - struct vfsmount *mnt; struct file *new_file; pr_debug("%s: group=%p event=%p\n", __func__, group, event); @@ -81,12 +79,10 @@ static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event) * we need a new file handle for the userspace program so it can read even if it was * originally opened O_WRONLY. */ - dentry = dget(event->path.dentry); - mnt = mntget(event->path.mnt); /* it's possible this event was an overflow event. in that case dentry and mnt * are NULL; That's fine, just don't call dentry open */ - if (dentry && mnt) - new_file = dentry_open(dentry, mnt, + if (event->path.dentry && event->path.mnt) + new_file = dentry_open(&event->path, group->fanotify_data.f_flags | FMODE_NONOTIFY, current_cred()); else diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index b39c5c1..6baadb5 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -52,6 +52,7 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt) void __fsnotify_update_child_dentry_flags(struct inode *inode) { struct dentry *alias; + struct hlist_node *p; int watched; if (!S_ISDIR(inode->i_mode)) @@ -63,7 +64,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ - list_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 358273e..436f360 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -101,7 +101,7 @@ * Locking: Caller must hold i_mutex on the directory. */ static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent, - struct nameidata *nd) + unsigned int flags) { ntfs_volume *vol = NTFS_SB(dir_ino->i_sb); struct inode *dent_inode; diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index e5ba348..8db4b58 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -49,14 +49,13 @@ void ocfs2_dentry_attach_gen(struct dentry *dentry) } -static int ocfs2_dentry_revalidate(struct dentry *dentry, - struct nameidata *nd) +static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode; int ret = 0; /* if all else fails, just return false */ struct ocfs2_super *osb; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; @@ -170,13 +169,11 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno, int skip_unhashed) { - struct list_head *p; - struct dentry *dentry = NULL; + struct hlist_node *p; + struct dentry *dentry; spin_lock(&inode->i_lock); - list_for_each(p, &inode->i_dentry) { - dentry = list_entry(p, struct dentry, d_alias); - + hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { spin_lock(&dentry->d_lock); if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) { trace_ocfs2_find_local_alias(dentry->d_name.len, @@ -184,16 +181,13 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode, dget_dlock(dentry); spin_unlock(&dentry->d_lock); - break; + spin_unlock(&inode->i_lock); + return dentry; } spin_unlock(&dentry->d_lock); - - dentry = NULL; } - spin_unlock(&inode->i_lock); - - return dentry; + return NULL; } DEFINE_SPINLOCK(dentry_attach_lock); diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index e31d6ae..83b6f98 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -526,7 +526,7 @@ bail: static int dlmfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { int status = 0; struct inode *inode; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 81a4cd2..4f7795f 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -456,7 +456,7 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level, stats->ls_gets++; stats->ls_total += ktime_to_ns(kt); /* overflow */ - if (unlikely(stats->ls_gets) == 0) { + if (unlikely(stats->ls_gets == 0)) { stats->ls_gets++; stats->ls_total = ktime_to_ns(kt); } @@ -3932,6 +3932,8 @@ unqueue: static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb, struct ocfs2_lock_res *lockres) { + unsigned long flags; + assert_spin_locked(&lockres->l_lock); if (lockres->l_flags & OCFS2_LOCK_FREEING) { @@ -3945,21 +3947,22 @@ static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb, lockres_or_flags(lockres, OCFS2_LOCK_QUEUED); - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (list_empty(&lockres->l_blocked_list)) { list_add_tail(&lockres->l_blocked_list, &osb->blocked_lock_list); osb->blocked_lock_count++; } - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); } static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) { unsigned long processed; + unsigned long flags; struct ocfs2_lock_res *lockres; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); /* grab this early so we know to try again if a state change and * wake happens part-way through our work */ osb->dc_work_sequence = osb->dc_wake_sequence; @@ -3972,38 +3975,40 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) struct ocfs2_lock_res, l_blocked_list); list_del_init(&lockres->l_blocked_list); osb->blocked_lock_count--; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); BUG_ON(!processed); processed--; ocfs2_process_blocked_lock(osb, lockres); - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); } - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); } static int ocfs2_downconvert_thread_lists_empty(struct ocfs2_super *osb) { int empty = 0; + unsigned long flags; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (list_empty(&osb->blocked_lock_list)) empty = 1; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); return empty; } static int ocfs2_downconvert_thread_should_wake(struct ocfs2_super *osb) { int should_wake = 0; + unsigned long flags; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (osb->dc_work_sequence != osb->dc_wake_sequence) should_wake = 1; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); return should_wake; } @@ -4033,10 +4038,12 @@ static int ocfs2_downconvert_thread(void *arg) void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb) { - spin_lock(&osb->dc_task_lock); + unsigned long flags; + + spin_lock_irqsave(&osb->dc_task_lock, flags); /* make sure the voting thread gets a swipe at whatever changes * the caller may have made to the voting state */ osb->dc_wake_sequence++; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); wake_up(&osb->dc_event); } diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 2f5b92e..70b5863 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -923,8 +923,6 @@ out_unlock: ocfs2_inode_unlock(inode, 0); out: - if (ret && ret != -ENXIO) - ret = -ENXIO; return ret; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 061591a..7602783 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1950,7 +1950,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, if (ret < 0) mlog_errno(ret); - if (file->f_flags & O_SYNC) + if (file && (file->f_flags & O_SYNC)) handle->h_sync = 1; ocfs2_commit_trans(osb, handle); @@ -2422,8 +2422,10 @@ out_dio: unaligned_dio = 0; } - if (unaligned_dio) + if (unaligned_dio) { + ocfs2_iocb_clear_unaligned_aio(iocb); atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio); + } out: if (rw_level != -1) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 9f39c64..f1fd074 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -98,7 +98,7 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb, #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64))) static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { int status; u64 blkno; @@ -618,7 +618,7 @@ static int ocfs2_mkdir(struct inode *dir, static int ocfs2_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { int ret; diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 92fcd57..0a86e30 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -399,8 +399,6 @@ int ocfs2_global_read_info(struct super_block *sb, int type) msecs_to_jiffies(oinfo->dqi_syncms)); out_err: - if (status) - mlog_errno(status); return status; out_unlock: ocfs2_unlock_global_qf(oinfo, 0); diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c index f00576e..fb5b3ff 100644 --- a/fs/omfs/dir.c +++ b/fs/omfs/dir.c @@ -285,13 +285,13 @@ static int omfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) } static int omfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return omfs_add_node(dir, dentry, mode | S_IFREG); } static struct dentry *omfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct buffer_head *bh; struct inode *inode = NULL; @@ -397,10 +397,10 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct file *file; struct inode *inode; - int error; + int error, fput_needed; error = -EBADF; - file = fget(fd); + file = fget_raw_light(fd, &fput_needed); if (!file) goto out; @@ -414,7 +414,7 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) if (!error) set_fs_pwd(current->fs, &file->f_path); out_putf: - fput(file); + fput_light(file, fput_needed); out: return error; } @@ -537,25 +537,6 @@ static int chown_common(struct path *path, uid_t user, gid_t group) return error; } -SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) -{ - struct path path; - int error; - - error = user_path(filename, &path); - if (error) - goto out; - error = mnt_want_write(path.mnt); - if (error) - goto out_release; - error = chown_common(&path, user, group); - mnt_drop_write(path.mnt); -out_release: - path_put(&path); -out: - return error; -} - SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag) { @@ -583,23 +564,15 @@ out: return error; } -SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) +SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { - struct path path; - int error; + return sys_fchownat(AT_FDCWD, filename, user, group, 0); +} - error = user_lpath(filename, &path); - if (error) - goto out; - error = mnt_want_write(path.mnt); - if (error) - goto out_release; - error = chown_common(&path, user, group); - mnt_drop_write(path.mnt); -out_release: - path_put(&path); -out: - return error; +SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) +{ + return sys_fchownat(AT_FDCWD, filename, user, group, + AT_SYMLINK_NOFOLLOW); } SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) @@ -667,10 +640,9 @@ int open_check_o_direct(struct file *f) return 0; } -static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, - struct file *f, - int (*open)(struct inode *, struct file *), - const struct cred *cred) +static int do_dentry_open(struct file *f, + int (*open)(struct inode *, struct file *), + const struct cred *cred) { static const struct file_operations empty_fops = {}; struct inode *inode; @@ -682,9 +654,9 @@ static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, if (unlikely(f->f_flags & O_PATH)) f->f_mode = FMODE_PATH; - inode = dentry->d_inode; + inode = f->f_path.dentry->d_inode; if (f->f_mode & FMODE_WRITE) { - error = __get_file_write_access(inode, mnt); + error = __get_file_write_access(inode, f->f_path.mnt); if (error) goto cleanup_file; if (!special_file(inode->i_mode)) @@ -692,14 +664,12 @@ static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, } f->f_mapping = inode->i_mapping; - f->f_path.dentry = dentry; - f->f_path.mnt = mnt; f->f_pos = 0; file_sb_list_add(f, inode->i_sb); if (unlikely(f->f_mode & FMODE_PATH)) { f->f_op = &empty_fops; - return f; + return 0; } f->f_op = fops_get(inode->i_fop); @@ -726,10 +696,11 @@ static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); - return f; + return 0; cleanup_all: fops_put(f->f_op); + file_sb_list_del(f); if (f->f_mode & FMODE_WRITE) { put_write_access(inode); if (!special_file(inode->i_mode)) { @@ -740,124 +711,62 @@ cleanup_all: * here, so just reset the state. */ file_reset_write(f); - mnt_drop_write(mnt); + mnt_drop_write(f->f_path.mnt); } } - file_sb_list_del(f); - f->f_path.dentry = NULL; - f->f_path.mnt = NULL; cleanup_file: - dput(dentry); - mntput(mnt); - return ERR_PTR(error); -} - -static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, - struct file *f, - int (*open)(struct inode *, struct file *), - const struct cred *cred) -{ - struct file *res = do_dentry_open(dentry, mnt, f, open, cred); - if (!IS_ERR(res)) { - int error = open_check_o_direct(f); - if (error) { - fput(res); - res = ERR_PTR(error); - } - } else { - put_filp(f); - } - return res; + path_put(&f->f_path); + f->f_path.mnt = NULL; + f->f_path.dentry = NULL; + return error; } /** - * lookup_instantiate_filp - instantiates the open intent filp - * @nd: pointer to nameidata + * finish_open - finish opening a file + * @od: opaque open data * @dentry: pointer to dentry * @open: open callback * - * Helper for filesystems that want to use lookup open intents and pass back - * a fully instantiated struct file to the caller. - * This function is meant to be called from within a filesystem's - * lookup method. - * Beware of calling it for non-regular files! Those ->open methods might block - * (e.g. in fifo_open), leaving you with parent locked (and in case of fifo, - * leading to a deadlock, as nobody can open that fifo anymore, because - * another process to open fifo will block on locked parent when doing lookup). - * Note that in case of error, nd->intent.open.file is destroyed, but the - * path information remains valid. + * This can be used to finish opening a file passed to i_op->atomic_open(). + * * If the open callback is set to NULL, then the standard f_op->open() * filesystem callback is substituted. */ -struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, - int (*open)(struct inode *, struct file *)) +int finish_open(struct file *file, struct dentry *dentry, + int (*open)(struct inode *, struct file *), + int *opened) { - const struct cred *cred = current_cred(); + int error; + BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */ - if (IS_ERR(nd->intent.open.file)) - goto out; - if (IS_ERR(dentry)) - goto out_err; - nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt), - nd->intent.open.file, - open, cred); -out: - return nd->intent.open.file; -out_err: - release_open_intent(nd); - nd->intent.open.file = ERR_CAST(dentry); - goto out; + mntget(file->f_path.mnt); + file->f_path.dentry = dget(dentry); + + error = do_dentry_open(file, open, current_cred()); + if (!error) + *opened |= FILE_OPENED; + + return error; } -EXPORT_SYMBOL_GPL(lookup_instantiate_filp); +EXPORT_SYMBOL(finish_open); /** - * nameidata_to_filp - convert a nameidata to an open filp. - * @nd: pointer to nameidata - * @flags: open flags + * finish_no_open - finish ->atomic_open() without opening the file + * + * @od: opaque open data + * @dentry: dentry or NULL (as returned from ->lookup()) * - * Note that this function destroys the original nameidata + * This can be used to set the result of a successful lookup in ->atomic_open(). + * The filesystem's atomic_open() method shall return NULL after calling this. */ -struct file *nameidata_to_filp(struct nameidata *nd) +int finish_no_open(struct file *file, struct dentry *dentry) { - const struct cred *cred = current_cred(); - struct file *filp; - - /* Pick up the filp from the open intent */ - filp = nd->intent.open.file; - - /* Has the filesystem initialised the file for us? */ - if (filp->f_path.dentry != NULL) { - nd->intent.open.file = NULL; - } else { - struct file *res; - - path_get(&nd->path); - res = do_dentry_open(nd->path.dentry, nd->path.mnt, - filp, NULL, cred); - if (!IS_ERR(res)) { - int error; - - nd->intent.open.file = NULL; - BUG_ON(res != filp); - - error = open_check_o_direct(filp); - if (error) { - fput(filp); - filp = ERR_PTR(error); - } - } else { - /* Allow nd->intent.open.file to be recycled */ - filp = res; - } - } - return filp; + file->f_path.dentry = dentry; + return 1; } +EXPORT_SYMBOL(finish_no_open); -/* - * dentry_open() will have done dput(dentry) and mntput(mnt) if it returns an - * error. - */ -struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags, +struct file *dentry_open(const struct path *path, int flags, const struct cred *cred) { int error; @@ -866,18 +775,28 @@ struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags, validate_creds(cred); /* We must always pass in a valid mount pointer. */ - BUG_ON(!mnt); + BUG_ON(!path->mnt); error = -ENFILE; f = get_empty_filp(); - if (f == NULL) { - dput(dentry); - mntput(mnt); + if (f == NULL) return ERR_PTR(error); - } f->f_flags = flags; - return __dentry_open(dentry, mnt, f, NULL, cred); + f->f_path = *path; + path_get(&f->f_path); + error = do_dentry_open(f, NULL, cred); + if (!error) { + error = open_check_o_direct(f); + if (error) { + fput(f); + f = ERR_PTR(error); + } + } else { + put_filp(f); + f = ERR_PTR(error); + } + return f; } EXPORT_SYMBOL(dentry_open); diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index bc49c975d..4a34779 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -170,13 +170,13 @@ static const struct file_operations openprom_operations = { .llseek = generic_file_llseek, }; -static struct dentry *openpromfs_lookup(struct inode *, struct dentry *, struct nameidata *); +static struct dentry *openpromfs_lookup(struct inode *, struct dentry *, unsigned int); static const struct inode_operations openprom_inode_operations = { .lookup = openpromfs_lookup, }; -static struct dentry *openpromfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *openpromfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct op_inode_info *ent_oi, *oi = OP_I(dir); struct device_node *dp, *child; @@ -237,8 +237,9 @@ int propagate_mnt(struct mount *dest_mnt, struct dentry *dest_dentry, source = get_source(m, prev_dest_mnt, prev_src_mnt, &type); - if (!(child = copy_tree(source, source->mnt.mnt_root, type))) { - ret = -ENOMEM; + child = copy_tree(source, source->mnt.mnt_root, type); + if (IS_ERR(child)) { + ret = PTR_ERR(child); list_splice(tree_list, tmp_list.prev); goto out; } diff --git a/fs/proc/base.c b/fs/proc/base.c index 616f41a..2772208 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1427,16 +1427,19 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path) static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; + struct path path; int error = -EACCES; - /* We don't need a base pointer in the /proc filesystem */ - path_put(&nd->path); - /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; - error = PROC_I(inode)->op.proc_get_link(dentry, &nd->path); + error = PROC_I(inode)->op.proc_get_link(dentry, &path); + if (error) + goto out; + + nd_jump_link(nd, &path); + return NULL; out: return ERR_PTR(error); } @@ -1601,13 +1604,13 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) * made this apply to all per process world readable and executable * directories. */ -int pid_revalidate(struct dentry *dentry, struct nameidata *nd) +int pid_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; const struct cred *cred; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; @@ -1781,7 +1784,7 @@ static int proc_fd_link(struct dentry *dentry, struct path *path) return proc_fd_info(dentry->d_inode, path, NULL); } -static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) +static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; @@ -1789,7 +1792,7 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) struct files_struct *files; const struct cred *cred; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; @@ -1803,7 +1806,7 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) rcu_read_lock(); file = fcheck_files(files, fd); if (file) { - unsigned i_mode, f_mode = file->f_mode; + unsigned f_mode = file->f_mode; rcu_read_unlock(); put_files_struct(files); @@ -1819,12 +1822,14 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) inode->i_gid = GLOBAL_ROOT_GID; } - i_mode = S_IFLNK; - if (f_mode & FMODE_READ) - i_mode |= S_IRUSR | S_IXUSR; - if (f_mode & FMODE_WRITE) - i_mode |= S_IWUSR | S_IXUSR; - inode->i_mode = i_mode; + if (S_ISLNK(inode->i_mode)) { + unsigned i_mode = S_IFLNK; + if (f_mode & FMODE_READ) + i_mode |= S_IRUSR | S_IXUSR; + if (f_mode & FMODE_WRITE) + i_mode |= S_IWUSR | S_IXUSR; + inode->i_mode = i_mode; + } security_task_to_inode(task, inode); put_task_struct(task); @@ -1859,13 +1864,14 @@ static struct dentry *proc_fd_instantiate(struct inode *dir, ei = PROC_I(inode); ei->fd = fd; + inode->i_mode = S_IFLNK; inode->i_op = &proc_pid_link_inode_operations; inode->i_size = 64; ei->op.proc_get_link = proc_fd_link; d_set_d_op(dentry, &tid_fd_dentry_operations); d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (tid_fd_revalidate(dentry, NULL)) + if (tid_fd_revalidate(dentry, 0)) error = NULL; out: @@ -1953,7 +1959,7 @@ out_no_task: } static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { return proc_lookupfd_common(dir, dentry, proc_fd_instantiate); } @@ -2000,7 +2006,7 @@ static int dname_to_vma_addr(struct dentry *dentry, return 0; } -static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd) +static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; bool exact_vma_exists = false; @@ -2010,7 +2016,7 @@ static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd) struct inode *inode; int status = 0; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; if (!capable(CAP_SYS_ADMIN)) { @@ -2142,7 +2148,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, } static struct dentry *proc_map_files_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; @@ -2368,7 +2374,7 @@ static struct dentry *proc_fdinfo_instantiate(struct inode *dir, d_set_d_op(dentry, &tid_fd_dentry_operations); d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (tid_fd_revalidate(dentry, NULL)) + if (tid_fd_revalidate(dentry, 0)) error = NULL; out: @@ -2377,7 +2383,7 @@ static struct dentry *proc_fdinfo_instantiate(struct inode *dir, static struct dentry *proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate); } @@ -2427,7 +2433,7 @@ static struct dentry *proc_pident_instantiate(struct inode *dir, d_set_d_op(dentry, &pid_dentry_operations); d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, NULL)) + if (pid_revalidate(dentry, 0)) error = NULL; out: return error; @@ -2627,7 +2633,7 @@ static const struct file_operations proc_attr_dir_operations = { }; static struct dentry *proc_attr_dir_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); @@ -3111,7 +3117,8 @@ static const struct file_operations proc_tgid_base_operations = { .llseek = default_llseek, }; -static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ +static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ return proc_pident_lookup(dir, dentry, tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } @@ -3234,13 +3241,13 @@ static struct dentry *proc_pid_instantiate(struct inode *dir, d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, NULL)) + if (pid_revalidate(dentry, 0)) error = NULL; out: return error; } -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct dentry *result; struct task_struct *task; @@ -3467,7 +3474,8 @@ static int proc_tid_base_readdir(struct file * filp, tid_base_stuff,ARRAY_SIZE(tid_base_stuff)); } -static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ +static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ return proc_pident_lookup(dir, dentry, tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); } @@ -3505,13 +3513,13 @@ static struct dentry *proc_task_instantiate(struct inode *dir, d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, NULL)) + if (pid_revalidate(dentry, 0)) error = NULL; out: return error; } -static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct dentry *result = ERR_PTR(-ENOENT); struct task_struct *task; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 2edf34f..b3647fe 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -446,7 +446,7 @@ out_unlock: } struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { return proc_lookup_de(PDE(dir), dir, dentry); } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index eca4aca..e1167a1 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -106,7 +106,7 @@ void pde_users_dec(struct proc_dir_entry *pde); extern spinlock_t proc_subdir_lock; -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *); +struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int); int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir); unsigned long task_vsize(struct mm_struct *); unsigned long task_statm(struct mm_struct *, @@ -132,7 +132,7 @@ int proc_remount(struct super_block *sb, int *flags, char *data); * of the /proc/<pid> subdirectories. */ int proc_readdir(struct file *, void *, filldir_t); -struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *); +struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int); @@ -142,7 +142,7 @@ typedef struct dentry *instantiate_t(struct inode *, struct dentry *, int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir, const char *name, int len, instantiate_t instantiate, struct task_struct *task, const void *ptr); -int pid_revalidate(struct dentry *dentry, struct nameidata *nd); +int pid_revalidate(struct dentry *dentry, unsigned int flags); struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task); extern const struct dentry_operations pid_dentry_operations; int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 0d9e23a..b178ed7 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -56,7 +56,7 @@ static struct dentry *proc_ns_instantiate(struct inode *dir, d_set_d_op(dentry, &pid_dentry_operations); d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, NULL)) + if (pid_revalidate(dentry, 0)) error = NULL; out: return error; @@ -140,7 +140,7 @@ const struct file_operations proc_ns_dir_operations = { }; static struct dentry *proc_ns_dir_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { struct dentry *error; struct task_struct *task = get_proc_task(dir); diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c index 927cbd1..df7dd08 100644 --- a/fs/proc/proc_devtree.c +++ b/fs/proc/proc_devtree.c @@ -101,6 +101,11 @@ void proc_device_tree_update_prop(struct proc_dir_entry *pde, { struct proc_dir_entry *ent; + if (!oldprop) { + proc_device_tree_add_prop(pde, newprop); + return; + } + for (ent = pde->subdir; ent != NULL; ent = ent->next) if (ent->data == oldprop) break; diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 06e1cc1..fe72cd0 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -119,7 +119,7 @@ static struct net *get_proc_task_net(struct inode *dir) } static struct dentry *proc_tgid_net_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { struct dentry *de; struct net *net; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 3476bca..dfafeb2 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -433,7 +433,7 @@ static struct ctl_table_header *grab_header(struct inode *inode) } static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct ctl_table_header *head = grab_header(dir); struct ctl_table_header *h = NULL; @@ -794,9 +794,9 @@ static const struct inode_operations proc_sys_dir_operations = { .getattr = proc_sys_getattr, }; -static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd) +static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags) { - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; return !PROC_I(dentry->d_inode)->sysctl->unregistering; } diff --git a/fs/proc/root.c b/fs/proc/root.c index 7c30fce..9a2d9fd 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -111,7 +111,7 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, options = data; } - sb = sget(fs_type, proc_test_super, proc_set_super, ns); + sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns); if (IS_ERR(sb)) return ERR_CAST(sb); @@ -121,7 +121,6 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, } if (!sb->s_root) { - sb->s_flags = flags; err = proc_fill_super(sb); if (err) { deactivate_locked_super(sb); @@ -200,13 +199,12 @@ static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct return 0; } -static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { - if (!proc_lookup(dir, dentry, nd)) { + if (!proc_lookup(dir, dentry, flags)) return NULL; - } - return proc_pid_lookup(dir, dentry, nd); + return proc_pid_lookup(dir, dentry, flags); } static int proc_root_readdir(struct file * filp, diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 5e289a7..5fe34c3 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -17,7 +17,7 @@ static unsigned mounts_poll(struct file *file, poll_table *wait) { - struct proc_mounts *p = file->private_data; + struct proc_mounts *p = proc_mounts(file->private_data); struct mnt_namespace *ns = p->ns; unsigned res = POLLIN | POLLRDNORM; @@ -121,7 +121,7 @@ out: static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) { - struct proc_mounts *p = m->private; + struct proc_mounts *p = proc_mounts(m); struct mount *r = real_mount(mnt); struct super_block *sb = mnt->mnt_sb; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; @@ -268,7 +268,6 @@ static int mounts_open_common(struct inode *inode, struct file *file, if (ret) goto err_free; - p->m.private = p; p->ns = ns; p->root = root; p->m.poll_event = ns->event; @@ -288,7 +287,7 @@ static int mounts_open_common(struct inode *inode, struct file *file, static int mounts_release(struct inode *inode, struct file *file) { - struct proc_mounts *p = file->private_data; + struct proc_mounts *p = proc_mounts(file->private_data); path_put(&p->root); put_mnt_ns(p->ns); return seq_release(inode, file); diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index aeb19e6..11a2aa2 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -258,7 +258,7 @@ fail: return rc; } -int pstore_fill_super(struct super_block *sb, void *data, int silent) +static int pstore_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 82c585f..03ce7a9 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -94,20 +94,15 @@ static const char *get_reason_str(enum kmsg_dump_reason reason) * as we can from the end of the buffer. */ static void pstore_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *s1, unsigned long l1, - const char *s2, unsigned long l2) + enum kmsg_dump_reason reason) { - unsigned long s1_start, s2_start; - unsigned long l1_cpy, l2_cpy; - unsigned long size, total = 0; - char *dst; + unsigned long total = 0; const char *why; u64 id; - int hsize, ret; unsigned int part = 1; unsigned long flags = 0; int is_locked = 0; + int ret; why = get_reason_str(reason); @@ -119,30 +114,25 @@ static void pstore_dump(struct kmsg_dumper *dumper, spin_lock_irqsave(&psinfo->buf_lock, flags); oopscount++; while (total < kmsg_bytes) { + char *dst; + unsigned long size; + int hsize; + size_t len; + dst = psinfo->buf; hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part); size = psinfo->bufsize - hsize; dst += hsize; - l2_cpy = min(l2, size); - l1_cpy = min(l1, size - l2_cpy); - - if (l1_cpy + l2_cpy == 0) + if (!kmsg_dump_get_buffer(dumper, true, dst, size, &len)) break; - s2_start = l2 - l2_cpy; - s1_start = l1 - l1_cpy; - - memcpy(dst, s1 + s1_start, l1_cpy); - memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); - ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part, - hsize + l1_cpy + l2_cpy, psinfo); + hsize + len, psinfo); if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_new_entry = 1; - l1 -= l1_cpy; - l2 -= l2_cpy; - total += l1_cpy + l2_cpy; + + total += hsize + len; part++; } if (in_nmi()) { diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 9123cce..453030f 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -106,6 +106,8 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, time->tv_sec = 0; time->tv_nsec = 0; + /* Update old/shadowed buffer. */ + persistent_ram_save_old(prz); size = persistent_ram_old_size(prz); *buf = kmalloc(size, GFP_KERNEL); if (*buf == NULL) @@ -184,6 +186,7 @@ static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, return -EINVAL; persistent_ram_free_old(cxt->przs[id]); + persistent_ram_zap(cxt->przs[id]); return 0; } diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 31f8d18..c5fbdbb 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -250,23 +250,24 @@ static void notrace persistent_ram_update(struct persistent_ram_zone *prz, persistent_ram_update_ecc(prz, start, count); } -static void __init -persistent_ram_save_old(struct persistent_ram_zone *prz) +void persistent_ram_save_old(struct persistent_ram_zone *prz) { struct persistent_ram_buffer *buffer = prz->buffer; size_t size = buffer_size(prz); size_t start = buffer_start(prz); - char *dest; - persistent_ram_ecc_old(prz); + if (!size) + return; - dest = kmalloc(size, GFP_KERNEL); - if (dest == NULL) { + if (!prz->old_log) { + persistent_ram_ecc_old(prz); + prz->old_log = kmalloc(size, GFP_KERNEL); + } + if (!prz->old_log) { pr_err("persistent_ram: failed to allocate buffer\n"); return; } - prz->old_log = dest; prz->old_log_size = size; memcpy(prz->old_log, &buffer->data[start], size - start); memcpy(prz->old_log + size - start, &buffer->data[0], start); @@ -319,6 +320,13 @@ void persistent_ram_free_old(struct persistent_ram_zone *prz) prz->old_log_size = 0; } +void persistent_ram_zap(struct persistent_ram_zone *prz) +{ + atomic_set(&prz->buffer->start, 0); + atomic_set(&prz->buffer->size, 0); + persistent_ram_update_header_ecc(prz); +} + static void *persistent_ram_vmap(phys_addr_t start, size_t size) { struct page **pages; @@ -405,6 +413,7 @@ static int __init persistent_ram_post_init(struct persistent_ram_zone *prz, bool " size %zu, start %zu\n", buffer_size(prz), buffer_start(prz)); persistent_ram_save_old(prz); + return 0; } } else { pr_info("persistent_ram: no valid data in buffer" @@ -412,8 +421,7 @@ static int __init persistent_ram_post_init(struct persistent_ram_zone *prz, bool } prz->buffer->sig = PERSISTENT_RAM_SIG; - atomic_set(&prz->buffer->start, 0); - atomic_set(&prz->buffer->size, 0); + persistent_ram_zap(prz); return 0; } @@ -448,7 +456,6 @@ struct persistent_ram_zone * __init persistent_ram_new(phys_addr_t start, goto err; persistent_ram_post_init(prz, ecc); - persistent_ram_update_header_ecc(prz); return prz; err: diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c index a512c0b..d024505 100644 --- a/fs/qnx4/namei.c +++ b/fs/qnx4/namei.c @@ -95,7 +95,7 @@ static struct buffer_head *qnx4_find_entry(int len, struct inode *dir, return NULL; } -struct dentry * qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +struct dentry * qnx4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int ino; struct qnx4_inode_entry *de; diff --git a/fs/qnx4/qnx4.h b/fs/qnx4/qnx4.h index 244d462..34e2d32 100644 --- a/fs/qnx4/qnx4.h +++ b/fs/qnx4/qnx4.h @@ -23,7 +23,7 @@ struct qnx4_inode_info { }; extern struct inode *qnx4_iget(struct super_block *, unsigned long); -extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd); +extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); extern unsigned long qnx4_count_free_blocks(struct super_block *sb); extern unsigned long qnx4_block_map(struct inode *inode, long iblock); diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index e44012d..2049c81 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -622,7 +622,6 @@ static struct inode *qnx6_alloc_inode(struct super_block *sb) static void qnx6_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - INIT_LIST_HEAD(&inode->i_dentry); kmem_cache_free(qnx6_inode_cachep, QNX6_I(inode)); } diff --git a/fs/qnx6/namei.c b/fs/qnx6/namei.c index 8a97289..0561326 100644 --- a/fs/qnx6/namei.c +++ b/fs/qnx6/namei.c @@ -13,7 +13,7 @@ #include "qnx6.h" struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { unsigned ino; struct page *page; diff --git a/fs/qnx6/qnx6.h b/fs/qnx6/qnx6.h index 6c5e02a..b00fcc9 100644 --- a/fs/qnx6/qnx6.h +++ b/fs/qnx6/qnx6.h @@ -45,7 +45,7 @@ struct qnx6_inode_info { extern struct inode *qnx6_iget(struct super_block *sb, unsigned ino); extern struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd); + unsigned int flags); #ifdef CONFIG_QNX6FS_DEBUG extern void qnx6_superblock_debug(struct qnx6_super_block *, diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 10cbe84..d679fc4 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -595,12 +595,14 @@ out: } EXPORT_SYMBOL(dquot_scan_active); -int dquot_quota_sync(struct super_block *sb, int type, int wait) +/* Write all dquot structures to quota files */ +int dquot_writeback_dquots(struct super_block *sb, int type) { struct list_head *dirty; struct dquot *dquot; struct quota_info *dqopt = sb_dqopt(sb); int cnt; + int err, ret = 0; mutex_lock(&dqopt->dqonoff_mutex); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { @@ -624,7 +626,9 @@ int dquot_quota_sync(struct super_block *sb, int type, int wait) atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); dqstats_inc(DQST_LOOKUPS); - sb->dq_op->write_dquot(dquot); + err = sb->dq_op->write_dquot(dquot); + if (!ret && err) + err = ret; dqput(dquot); spin_lock(&dq_list_lock); } @@ -638,7 +642,21 @@ int dquot_quota_sync(struct super_block *sb, int type, int wait) dqstats_inc(DQST_SYNCS); mutex_unlock(&dqopt->dqonoff_mutex); - if (!wait || (dqopt->flags & DQUOT_QUOTA_SYS_FILE)) + return ret; +} +EXPORT_SYMBOL(dquot_writeback_dquots); + +/* Write all dquot structures to disk and make them visible from userspace */ +int dquot_quota_sync(struct super_block *sb, int type) +{ + struct quota_info *dqopt = sb_dqopt(sb); + int cnt; + int ret; + + ret = dquot_writeback_dquots(sb, type); + if (ret) + return ret; + if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) return 0; /* This is not very clever (and fast) but currently I don't know about diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 9a39120..c659f92 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -47,7 +47,7 @@ static int check_quotactl_permission(struct super_block *sb, int type, int cmd, static void quota_sync_one(struct super_block *sb, void *arg) { if (sb->s_qcop && sb->s_qcop->quota_sync) - sb->s_qcop->quota_sync(sb, *(int *)arg, 1); + sb->s_qcop->quota_sync(sb, *(int *)arg); } static int quota_sync_all(int type) @@ -270,7 +270,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, case Q_SYNC: if (!sb->s_qcop->quota_sync) return -ENOSYS; - return sb->s_qcop->quota_sync(sb, type, 1); + return sb->s_qcop->quota_sync(sb, type); case Q_XQUOTAON: case Q_XQUOTAOFF: case Q_XQUOTARM: diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index fbb0b47..d5378d0 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -110,6 +110,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) /* prevent the page from being discarded on memory pressure */ SetPageDirty(page); + SetPageUptodate(page); unlock_page(page); put_page(page); diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index a1fdabe..eab8c09 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -114,7 +114,7 @@ static int ramfs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) return retval; } -static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd) +static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return ramfs_mknod(dir, dentry, mode | S_IFREG, 0); } diff --git a/fs/read_write.c b/fs/read_write.c index c20614f..1adfb69 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -55,10 +55,11 @@ static loff_t lseek_execute(struct file *file, struct inode *inode, * @file: file structure to seek on * @offset: file offset to seek to * @origin: type of seek - * @size: max size of file system + * @size: max size of this file in file system + * @eof: offset used for SEEK_END position * * This is a variant of generic_file_llseek that allows passing in a custom - * file size. + * maximum file size and a custom EOF position, for e.g. hashed directories * * Synchronization: * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) @@ -67,13 +68,13 @@ static loff_t lseek_execute(struct file *file, struct inode *inode, */ loff_t generic_file_llseek_size(struct file *file, loff_t offset, int origin, - loff_t maxsize) + loff_t maxsize, loff_t eof) { struct inode *inode = file->f_mapping->host; switch (origin) { case SEEK_END: - offset += i_size_read(inode); + offset += eof; break; case SEEK_CUR: /* @@ -99,7 +100,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int origin, * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ - if (offset >= i_size_read(inode)) + if (offset >= eof) return -ENXIO; break; case SEEK_HOLE: @@ -107,9 +108,9 @@ generic_file_llseek_size(struct file *file, loff_t offset, int origin, * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ - if (offset >= i_size_read(inode)) + if (offset >= eof) return -ENXIO; - offset = i_size_read(inode); + offset = eof; break; } @@ -132,7 +133,8 @@ loff_t generic_file_llseek(struct file *file, loff_t offset, int origin) struct inode *inode = file->f_mapping->host; return generic_file_llseek_size(file, offset, origin, - inode->i_sb->s_maxbytes); + inode->i_sb->s_maxbytes, + i_size_read(inode)); } EXPORT_SYMBOL(generic_file_llseek); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 84e8a69..8567fb8 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -322,7 +322,7 @@ static int reiserfs_find_entry(struct inode *dir, const char *name, int namelen, } static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { int retval; int lock_depth; @@ -573,7 +573,7 @@ static int new_inode_init(struct inode *inode, struct inode *dir, umode_t mode) } static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { int retval; struct inode *inode; @@ -634,8 +634,8 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod reiserfs_update_inode_transaction(inode); reiserfs_update_inode_transaction(dir); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); retval = journal_end(&th, dir->i_sb, jbegin_count); out_failed: @@ -712,8 +712,8 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode goto out_failed; } - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); retval = journal_end(&th, dir->i_sb, jbegin_count); out_failed: @@ -800,8 +800,8 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode // the above add_entry did not update dir's stat data reiserfs_update_sd(&th, dir); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); retval = journal_end(&th, dir->i_sb, jbegin_count); out_failed: reiserfs_write_unlock_once(dir->i_sb, lock_depth); @@ -1096,8 +1096,8 @@ static int reiserfs_symlink(struct inode *parent_dir, goto out_failed; } - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); retval = journal_end(&th, parent_dir->i_sb, jbegin_count); out_failed: reiserfs_write_unlock(parent_dir->i_sb); diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c index 2c1ade6..e60e870 100644 --- a/fs/reiserfs/procfs.c +++ b/fs/reiserfs/procfs.c @@ -403,7 +403,7 @@ static void *r_start(struct seq_file *m, loff_t * pos) if (l) return NULL; - if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, s))) + if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, 0, s))) return NULL; up_write(&s->s_umount); diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 651ce76..7a37dab 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -68,6 +68,11 @@ static int reiserfs_sync_fs(struct super_block *s, int wait) { struct reiserfs_transaction_handle th; + /* + * Writeback quota in non-journalled quota case - journalled quota has + * no dirty dquots + */ + dquot_writeback_dquots(s, -1); reiserfs_write_lock(s); if (!journal_begin(&th, s, 1)) if (!journal_end_sync(&th, s, 1)) diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 46fc1c2..d319963 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -62,7 +62,7 @@ static int xattr_create(struct inode *dir, struct dentry *dentry, int mode) { BUG_ON(!mutex_is_locked(&dir->i_mutex)); - return dir->i_op->create(dir, dentry, mode, NULL); + return dir->i_op->create(dir, dentry, mode, true); } #endif @@ -942,7 +942,7 @@ int reiserfs_permission(struct inode *inode, int mask) return generic_permission(inode, mask); } -static int xattr_hide_revalidate(struct dentry *dentry, struct nameidata *nd) +static int xattr_hide_revalidate(struct dentry *dentry, unsigned int flags) { return -EPERM; } diff --git a/fs/romfs/super.c b/fs/romfs/super.c index e64f6b5..77c5f21 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -210,7 +210,7 @@ out: * look up an entry in a directory */ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { unsigned long offset, maxoff; struct inode *inode; diff --git a/fs/splice.c b/fs/splice.c index c9f1318..7bf08fa 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -273,13 +273,16 @@ void spd_release_page(struct splice_pipe_desc *spd, unsigned int i) * Check if we need to grow the arrays holding pages and partial page * descriptions. */ -int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) +int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { - if (pipe->buffers <= PIPE_DEF_BUFFERS) + unsigned int buffers = ACCESS_ONCE(pipe->buffers); + + spd->nr_pages_max = buffers; + if (buffers <= PIPE_DEF_BUFFERS) return 0; - spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL); - spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL); + spd->pages = kmalloc(buffers * sizeof(struct page *), GFP_KERNEL); + spd->partial = kmalloc(buffers * sizeof(struct partial_page), GFP_KERNEL); if (spd->pages && spd->partial) return 0; @@ -289,10 +292,9 @@ int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) return -ENOMEM; } -void splice_shrink_spd(struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd) +void splice_shrink_spd(struct splice_pipe_desc *spd) { - if (pipe->buffers <= PIPE_DEF_BUFFERS) + if (spd->nr_pages_max <= PIPE_DEF_BUFFERS) return; kfree(spd->pages); @@ -315,6 +317,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &page_cache_pipe_buf_ops, .spd_release = spd_release_page, @@ -326,7 +329,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, index = *ppos >> PAGE_CACHE_SHIFT; loff = *ppos & ~PAGE_CACHE_MASK; req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - nr_pages = min(req_pages, pipe->buffers); + nr_pages = min(req_pages, spd.nr_pages_max); /* * Lookup the (hopefully) full range of pages we need. @@ -497,7 +500,7 @@ fill_it: if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return error; } @@ -598,6 +601,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &default_pipe_buf_ops, .spd_release = spd_release_page, @@ -608,8 +612,8 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, res = -ENOMEM; vec = __vec; - if (pipe->buffers > PIPE_DEF_BUFFERS) { - vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL); + if (spd.nr_pages_max > PIPE_DEF_BUFFERS) { + vec = kmalloc(spd.nr_pages_max * sizeof(struct iovec), GFP_KERNEL); if (!vec) goto shrink_ret; } @@ -617,7 +621,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, offset = *ppos & ~PAGE_CACHE_MASK; nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) { + for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) { struct page *page; page = alloc_page(GFP_USER); @@ -665,7 +669,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, shrink_ret: if (vec != __vec) kfree(vec); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return res; err: @@ -1614,6 +1618,7 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &user_page_pipe_buf_ops, .spd_release = spd_release_page, @@ -1629,13 +1634,13 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages, spd.partial, false, - pipe->buffers); + spd.nr_pages_max); if (spd.nr_pages <= 0) ret = spd.nr_pages; else ret = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return ret; } diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c index abcc58f..7834a51 100644 --- a/fs/squashfs/namei.c +++ b/fs/squashfs/namei.c @@ -134,7 +134,7 @@ out: static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { const unsigned char *name = dentry->d_name.name; int len = dentry->d_name.len; @@ -105,11 +105,12 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc) /** * alloc_super - create new superblock * @type: filesystem type superblock should belong to + * @flags: the mount flags * * Allocates and initializes a new &struct super_block. alloc_super() * returns a pointer new superblock or %NULL if allocation had failed. */ -static struct super_block *alloc_super(struct file_system_type *type) +static struct super_block *alloc_super(struct file_system_type *type, int flags) { struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER); static const struct super_operations default_op; @@ -136,6 +137,7 @@ static struct super_block *alloc_super(struct file_system_type *type) #else INIT_LIST_HEAD(&s->s_files); #endif + s->s_flags = flags; s->s_bdi = &default_backing_dev_info; INIT_HLIST_NODE(&s->s_instances); INIT_HLIST_BL_HEAD(&s->s_anon); @@ -415,11 +417,13 @@ EXPORT_SYMBOL(generic_shutdown_super); * @type: filesystem type superblock should belong to * @test: comparison callback * @set: setup callback + * @flags: mount flags * @data: argument to each of them */ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), + int flags, void *data) { struct super_block *s = NULL; @@ -450,7 +454,7 @@ retry: } if (!s) { spin_unlock(&sb_lock); - s = alloc_super(type); + s = alloc_super(type, flags); if (!s) return ERR_PTR(-ENOMEM); goto retry; @@ -925,13 +929,12 @@ struct dentry *mount_ns(struct file_system_type *fs_type, int flags, { struct super_block *sb; - sb = sget(fs_type, ns_test_super, ns_set_super, data); + sb = sget(fs_type, ns_test_super, ns_set_super, flags, data); if (IS_ERR(sb)) return ERR_CAST(sb); if (!sb->s_root) { int err; - sb->s_flags = flags; err = fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (err) { deactivate_locked_super(sb); @@ -992,7 +995,8 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, error = -EBUSY; goto error_bdev; } - s = sget(fs_type, test_bdev_super, set_bdev_super, bdev); + s = sget(fs_type, test_bdev_super, set_bdev_super, flags | MS_NOSEC, + bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) goto error_s; @@ -1017,7 +1021,6 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, } else { char b[BDEVNAME_SIZE]; - s->s_flags = flags | MS_NOSEC; s->s_mode = mode; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); sb_set_blocksize(s, block_size(bdev)); @@ -1062,13 +1065,11 @@ struct dentry *mount_nodev(struct file_system_type *fs_type, int (*fill_super)(struct super_block *, void *, int)) { int error; - struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL); + struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL); if (IS_ERR(s)) return ERR_CAST(s); - s->s_flags = flags; - error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); @@ -1091,11 +1092,10 @@ struct dentry *mount_single(struct file_system_type *fs_type, struct super_block *s; int error; - s = sget(fs_type, compare_single, set_anon_super, NULL); + s = sget(fs_type, compare_single, set_anon_super, flags, NULL); if (IS_ERR(s)) return ERR_CAST(s); if (!s->s_root) { - s->s_flags = flags; error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); @@ -29,16 +29,6 @@ */ static int __sync_filesystem(struct super_block *sb, int wait) { - /* - * This should be safe, as we require bdi backing to actually - * write out data in the first place - */ - if (sb->s_bdi == &noop_backing_dev_info) - return 0; - - if (sb->s_qcop && sb->s_qcop->quota_sync) - sb->s_qcop->quota_sync(sb, -1, wait); - if (wait) sync_inodes_sb(sb); else @@ -77,29 +67,48 @@ int sync_filesystem(struct super_block *sb) } EXPORT_SYMBOL_GPL(sync_filesystem); -static void sync_one_sb(struct super_block *sb, void *arg) +static void sync_inodes_one_sb(struct super_block *sb, void *arg) { if (!(sb->s_flags & MS_RDONLY)) - __sync_filesystem(sb, *(int *)arg); + sync_inodes_sb(sb); } -/* - * Sync all the data for all the filesystems (called by sys_sync() and - * emergency sync) - */ -static void sync_filesystems(int wait) + +static void sync_fs_one_sb(struct super_block *sb, void *arg) { - iterate_supers(sync_one_sb, &wait); + if (!(sb->s_flags & MS_RDONLY) && sb->s_op->sync_fs) + sb->s_op->sync_fs(sb, *(int *)arg); +} + +static void fdatawrite_one_bdev(struct block_device *bdev, void *arg) +{ + filemap_fdatawrite(bdev->bd_inode->i_mapping); +} + +static void fdatawait_one_bdev(struct block_device *bdev, void *arg) +{ + filemap_fdatawait(bdev->bd_inode->i_mapping); } /* - * sync everything. Start out by waking pdflush, because that writes back - * all queues in parallel. + * Sync everything. We start by waking flusher threads so that most of + * writeback runs on all devices in parallel. Then we sync all inodes reliably + * which effectively also waits for all flusher threads to finish doing + * writeback. At this point all data is on disk so metadata should be stable + * and we tell filesystems to sync their metadata via ->sync_fs() calls. + * Finally, we writeout all block devices because some filesystems (e.g. ext2) + * just write metadata (such as inodes or bitmaps) to block device page cache + * and do not sync it on their own in ->sync_fs(). */ SYSCALL_DEFINE0(sync) { + int nowait = 0, wait = 1; + wakeup_flusher_threads(0, WB_REASON_SYNC); - sync_filesystems(0); - sync_filesystems(1); + iterate_supers(sync_inodes_one_sb, NULL); + iterate_supers(sync_fs_one_sb, &nowait); + iterate_supers(sync_fs_one_sb, &wait); + iterate_bdevs(fdatawrite_one_bdev, NULL); + iterate_bdevs(fdatawait_one_bdev, NULL); if (unlikely(laptop_mode)) laptop_sync_completion(); return 0; @@ -107,12 +116,18 @@ SYSCALL_DEFINE0(sync) static void do_sync_work(struct work_struct *work) { + int nowait = 0; + /* * Sync twice to reduce the possibility we skipped some inodes / pages * because they were temporarily locked */ - sync_filesystems(0); - sync_filesystems(0); + iterate_supers(sync_inodes_one_sb, &nowait); + iterate_supers(sync_fs_one_sb, &nowait); + iterate_bdevs(fdatawrite_one_bdev, NULL); + iterate_supers(sync_inodes_one_sb, &nowait); + iterate_supers(sync_fs_one_sb, &nowait); + iterate_bdevs(fdatawrite_one_bdev, NULL); printk("Emergency Sync complete\n"); kfree(work); } diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index e6bb9b2..a5cf784 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -300,15 +300,15 @@ void release_sysfs_dirent(struct sysfs_dirent * sd) static int sysfs_dentry_delete(const struct dentry *dentry) { struct sysfs_dirent *sd = dentry->d_fsdata; - return !!(sd->s_flags & SYSFS_FLAG_REMOVED); + return !(sd && !(sd->s_flags & SYSFS_FLAG_REMOVED)); } -static int sysfs_dentry_revalidate(struct dentry *dentry, struct nameidata *nd) +static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags) { struct sysfs_dirent *sd; int is_dir; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; sd = dentry->d_fsdata; @@ -355,18 +355,15 @@ out_bad: return 0; } -static void sysfs_dentry_iput(struct dentry *dentry, struct inode *inode) +static void sysfs_dentry_release(struct dentry *dentry) { - struct sysfs_dirent * sd = dentry->d_fsdata; - - sysfs_put(sd); - iput(inode); + sysfs_put(dentry->d_fsdata); } -static const struct dentry_operations sysfs_dentry_ops = { +const struct dentry_operations sysfs_dentry_ops = { .d_revalidate = sysfs_dentry_revalidate, .d_delete = sysfs_dentry_delete, - .d_iput = sysfs_dentry_iput, + .d_release = sysfs_dentry_release, }; struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type) @@ -764,7 +761,7 @@ int sysfs_create_dir(struct kobject * kobj) } static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct dentry *ret = NULL; struct dentry *parent = dentry->d_parent; @@ -786,6 +783,7 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, ret = ERR_PTR(-ENOENT); goto out_unlock; } + dentry->d_fsdata = sysfs_get(sd); /* attach dentry and inode */ inode = sysfs_get_inode(dir->i_sb, sd); @@ -795,16 +793,7 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, } /* instantiate and hash dentry */ - ret = d_find_alias(inode); - if (!ret) { - d_set_d_op(dentry, &sysfs_dentry_ops); - dentry->d_fsdata = sysfs_get(sd); - d_add(dentry, inode); - } else { - d_move(ret, dentry); - iput(inode); - } - + ret = d_materialise_unique(dentry, inode); out_unlock: mutex_unlock(&sysfs_mutex); return ret; diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 52c3bdb6..71eb7e2 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -68,6 +68,7 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent) } root->d_fsdata = &sysfs_root; sb->s_root = root; + sb->s_d_op = &sysfs_dentry_ops; return 0; } @@ -117,13 +118,12 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) info->ns[type] = kobj_ns_grab_current(type); - sb = sget(fs_type, sysfs_test_super, sysfs_set_super, info); + sb = sget(fs_type, sysfs_test_super, sysfs_set_super, flags, info); if (IS_ERR(sb) || sb->s_fs_info != info) free_sysfs_super_info(info); if (IS_ERR(sb)) return ERR_CAST(sb); if (!sb->s_root) { - sb->s_flags = flags; error = sysfs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (error) { deactivate_locked_super(sb); diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index 661a963..d73c093 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -157,6 +157,7 @@ extern struct kmem_cache *sysfs_dir_cachep; */ extern struct mutex sysfs_mutex; extern spinlock_t sysfs_assoc_lock; +extern const struct dentry_operations sysfs_dentry_ops; extern const struct file_operations sysfs_dir_operations; extern const struct inode_operations sysfs_dir_inode_operations; diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 08d0b25..80e1e2b 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -43,7 +43,6 @@ static int sysv_sync_fs(struct super_block *sb, int wait) * then attach current time stamp. * But if the filesystem was marked clean, keep it clean. */ - sb->s_dirt = 0; old_time = fs32_to_cpu(sbi, *sbi->s_sb_time); if (sbi->s_type == FSTYPE_SYSV4) { if (*sbi->s_sb_state == cpu_to_fs32(sbi, 0x7c269d38 - old_time)) @@ -57,23 +56,12 @@ static int sysv_sync_fs(struct super_block *sb, int wait) return 0; } -static void sysv_write_super(struct super_block *sb) -{ - if (!(sb->s_flags & MS_RDONLY)) - sysv_sync_fs(sb, 1); - else - sb->s_dirt = 0; -} - static int sysv_remount(struct super_block *sb, int *flags, char *data) { struct sysv_sb_info *sbi = SYSV_SB(sb); - lock_super(sb); + if (sbi->s_forced_ro) *flags |= MS_RDONLY; - if (*flags & MS_RDONLY) - sysv_write_super(sb); - unlock_super(sb); return 0; } @@ -81,9 +69,6 @@ static void sysv_put_super(struct super_block *sb) { struct sysv_sb_info *sbi = SYSV_SB(sb); - if (sb->s_dirt) - sysv_write_super(sb); - if (!(sb->s_flags & MS_RDONLY)) { /* XXX ext2 also updates the state here */ mark_buffer_dirty(sbi->s_bh1); @@ -357,7 +342,6 @@ const struct super_operations sysv_sops = { .write_inode = sysv_write_inode, .evict_inode = sysv_evict_inode, .put_super = sysv_put_super, - .write_super = sysv_write_super, .sync_fs = sysv_sync_fs, .remount_fs = sysv_remount, .statfs = sysv_statfs, diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index d7466e2..1c0d5f2 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -43,7 +43,7 @@ const struct dentry_operations sysv_dentry_operations = { .d_hash = sysv_hash, }; -static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { struct inode * inode = NULL; ino_t ino; @@ -80,7 +80,7 @@ static int sysv_mknod(struct inode * dir, struct dentry * dentry, umode_t mode, return err; } -static int sysv_create(struct inode * dir, struct dentry * dentry, umode_t mode, struct nameidata *nd) +static int sysv_create(struct inode * dir, struct dentry * dentry, umode_t mode, bool excl) { return sysv_mknod(dir, dentry, mode, 0); } diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h index 11b0767..0bc35fd 100644 --- a/fs/sysv/sysv.h +++ b/fs/sysv/sysv.h @@ -117,7 +117,6 @@ static inline void dirty_sb(struct super_block *sb) mark_buffer_dirty(sbi->s_bh1); if (sbi->s_bh1 != sbi->s_bh2) mark_buffer_dirty(sbi->s_bh2); - sb->s_dirt = 1; } diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 685a837..bb31672 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2802,6 +2802,8 @@ static ssize_t dfs_file_read(struct file *file, char __user *u, size_t count, val = d->chk_fs; else if (dent == d->dfs_tst_rcvry) val = d->tst_rcvry; + else if (dent == d->dfs_ro_error) + val = c->ro_error; else return -EINVAL; @@ -2885,6 +2887,8 @@ static ssize_t dfs_file_write(struct file *file, const char __user *u, d->chk_fs = val; else if (dent == d->dfs_tst_rcvry) d->tst_rcvry = val; + else if (dent == d->dfs_ro_error) + c->ro_error = !!val; else return -EINVAL; @@ -2918,6 +2922,9 @@ int dbg_debugfs_init_fs(struct ubifs_info *c) struct dentry *dent; struct ubifs_debug_info *d = c->dbg; + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + n = snprintf(d->dfs_dir_name, UBIFS_DFS_DIR_LEN + 1, UBIFS_DFS_DIR_NAME, c->vi.ubi_num, c->vi.vol_id); if (n == UBIFS_DFS_DIR_LEN) { @@ -2993,6 +3000,13 @@ int dbg_debugfs_init_fs(struct ubifs_info *c) goto out_remove; d->dfs_tst_rcvry = dent; + fname = "ro_error"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_ro_error = dent; + return 0; out_remove: @@ -3010,7 +3024,8 @@ out: */ void dbg_debugfs_exit_fs(struct ubifs_info *c) { - debugfs_remove_recursive(c->dbg->dfs_dir); + if (IS_ENABLED(CONFIG_DEBUG_FS)) + debugfs_remove_recursive(c->dbg->dfs_dir); } struct ubifs_global_debug_info ubifs_dbg; @@ -3095,6 +3110,9 @@ int dbg_debugfs_init(void) const char *fname; struct dentry *dent; + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + fname = "ubifs"; dent = debugfs_create_dir(fname, NULL); if (IS_ERR_OR_NULL(dent)) @@ -3159,7 +3177,8 @@ out: */ void dbg_debugfs_exit(void) { - debugfs_remove_recursive(dfs_rootdir); + if (IS_ENABLED(CONFIG_DEBUG_FS)) + debugfs_remove_recursive(dfs_rootdir); } /** diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index 486a8e0..8b8cc4e 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -79,6 +79,10 @@ typedef int (*dbg_znode_callback)(struct ubifs_info *c, * @dfs_chk_lprops: debugfs knob to enable UBIFS LEP properties extra checks * @dfs_chk_fs: debugfs knob to enable UBIFS contents extra checks * @dfs_tst_rcvry: debugfs knob to enable UBIFS recovery testing + * @dfs_ro_error: debugfs knob to switch UBIFS to R/O mode (different to + * re-mounting to R/O mode because it does not flush any buffers + * and UBIFS just starts returning -EROFS on all write + * operations) */ struct ubifs_debug_info { struct ubifs_zbranch old_zroot; @@ -122,6 +126,7 @@ struct ubifs_debug_info { struct dentry *dfs_chk_lprops; struct dentry *dfs_chk_fs; struct dentry *dfs_tst_rcvry; + struct dentry *dfs_ro_error; }; /** diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index a6d42ef..c95681c 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -184,7 +184,7 @@ static int dbg_check_name(const struct ubifs_info *c, } static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { int err; union ubifs_key key; @@ -246,7 +246,7 @@ out: } static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; struct ubifs_info *c = dir->i_sb->s_fs_info; @@ -969,7 +969,7 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry, struct ubifs_budget_req ino_req = { .dirtied_ino = 1, .dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) }; struct timespec time; - unsigned int saved_nlink; + unsigned int uninitialized_var(saved_nlink); /* * Budget request settings: deletion direntry, new direntry, removing diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c index 2559d17..28ec13a 100644 --- a/fs/ubifs/find.c +++ b/fs/ubifs/find.c @@ -939,8 +939,8 @@ static int find_dirtiest_idx_leb(struct ubifs_info *c) } dbg_find("LEB %d, dirty %d and free %d flags %#x", lp->lnum, lp->dirty, lp->free, lp->flags); - ubifs_assert(lp->flags | LPROPS_TAKEN); - ubifs_assert(lp->flags | LPROPS_INDEX); + ubifs_assert(lp->flags & LPROPS_TAKEN); + ubifs_assert(lp->flags & LPROPS_INDEX); return lnum; } diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index b02734d..cebf17e 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -176,7 +176,7 @@ int ubifs_orphan_start_commit(struct ubifs_info *c) *last = orphan; last = &orphan->cnext; } - *last = orphan->cnext; + *last = NULL; c->cmt_orphans = c->new_orphans; c->new_orphans = 0; dbg_cmt("%d orphans to commit", c->cmt_orphans); @@ -382,7 +382,7 @@ static int consolidate(struct ubifs_info *c) last = &orphan->cnext; cnt += 1; } - *last = orphan->cnext; + *last = NULL; ubifs_assert(cnt == c->tot_orphans - c->new_orphans); c->cmt_orphans = cnt; c->ohead_lnum = c->orph_first; diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index 3a2da7e..eba46d4 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -1007,7 +1007,7 @@ out: */ int ubifs_replay_journal(struct ubifs_info *c) { - int err, i, lnum, offs, free; + int err, lnum, free; BUILD_BUG_ON(UBIFS_TRUN_KEY > 5); @@ -1025,25 +1025,17 @@ int ubifs_replay_journal(struct ubifs_info *c) dbg_mnt("start replaying the journal"); c->replaying = 1; lnum = c->ltail_lnum = c->lhead_lnum; - offs = c->lhead_offs; - for (i = 0; i < c->log_lebs; i++, lnum++) { - if (lnum >= UBIFS_LOG_LNUM + c->log_lebs) { - /* - * The log is logically circular, we reached the last - * LEB, switch to the first one. - */ - lnum = UBIFS_LOG_LNUM; - offs = 0; - } - err = replay_log_leb(c, lnum, offs, c->sbuf); + lnum = UBIFS_LOG_LNUM; + do { + err = replay_log_leb(c, lnum, 0, c->sbuf); if (err == 1) /* We hit the end of the log */ break; if (err) goto out; - offs = 0; - } + lnum = ubifs_next_log_lnum(c, lnum); + } while (lnum != UBIFS_LOG_LNUM); err = replay_buds(c); if (err) diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index ef3d1ba..15e2fc5 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -718,8 +718,12 @@ static int fixup_free_space(struct ubifs_info *c) lnum = ubifs_next_log_lnum(c, lnum); } - /* Fixup the current log head */ - err = fixup_leb(c, c->lhead_lnum, c->lhead_offs); + /* + * Fixup the log head which contains the only a CS node at the + * beginning. + */ + err = fixup_leb(c, c->lhead_lnum, + ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size)); if (err) goto out; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 5862dd9..1c766c3 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2136,7 +2136,7 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, dbg_gen("opened ubi%d_%d", c->vi.ubi_num, c->vi.vol_id); - sb = sget(fs_type, sb_test, sb_set, c); + sb = sget(fs_type, sb_test, sb_set, flags, c); if (IS_ERR(sb)) { err = PTR_ERR(sb); kfree(c); @@ -2153,7 +2153,6 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, goto out_deact; } } else { - sb->s_flags = flags; err = ubifs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (err) goto out_deact; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 1802417..544b279 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -251,7 +251,7 @@ out_ok: } static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode = NULL; struct fileIdentDesc cfi; @@ -551,7 +551,7 @@ static int udf_delete_entry(struct inode *inode, struct fileIdentDesc *fi, } static int udf_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct udf_fileident_bh fibh; struct inode *inode; diff --git a/fs/udf/super.c b/fs/udf/super.c index ac8a348..8d86a87 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -56,6 +56,7 @@ #include <linux/seq_file.h> #include <linux/bitmap.h> #include <linux/crc-itu-t.h> +#include <linux/log2.h> #include <asm/byteorder.h> #include "udf_sb.h" @@ -1215,16 +1216,65 @@ out_bh: return ret; } +static int udf_load_sparable_map(struct super_block *sb, + struct udf_part_map *map, + struct sparablePartitionMap *spm) +{ + uint32_t loc; + uint16_t ident; + struct sparingTable *st; + struct udf_sparing_data *sdata = &map->s_type_specific.s_sparing; + int i; + struct buffer_head *bh; + + map->s_partition_type = UDF_SPARABLE_MAP15; + sdata->s_packet_len = le16_to_cpu(spm->packetLength); + if (!is_power_of_2(sdata->s_packet_len)) { + udf_err(sb, "error loading logical volume descriptor: " + "Invalid packet length %u\n", + (unsigned)sdata->s_packet_len); + return -EIO; + } + if (spm->numSparingTables > 4) { + udf_err(sb, "error loading logical volume descriptor: " + "Too many sparing tables (%d)\n", + (int)spm->numSparingTables); + return -EIO; + } + + for (i = 0; i < spm->numSparingTables; i++) { + loc = le32_to_cpu(spm->locSparingTable[i]); + bh = udf_read_tagged(sb, loc, loc, &ident); + if (!bh) + continue; + + st = (struct sparingTable *)bh->b_data; + if (ident != 0 || + strncmp(st->sparingIdent.ident, UDF_ID_SPARING, + strlen(UDF_ID_SPARING)) || + sizeof(*st) + le16_to_cpu(st->reallocationTableLen) > + sb->s_blocksize) { + brelse(bh); + continue; + } + + sdata->s_spar_map[i] = bh; + } + map->s_partition_func = udf_get_pblock_spar15; + return 0; +} + static int udf_load_logicalvol(struct super_block *sb, sector_t block, struct kernel_lb_addr *fileset) { struct logicalVolDesc *lvd; - int i, j, offset; + int i, offset; uint8_t type; struct udf_sb_info *sbi = UDF_SB(sb); struct genericPartitionMap *gpm; uint16_t ident; struct buffer_head *bh; + unsigned int table_len; int ret = 0; bh = udf_read_tagged(sb, block, block, &ident); @@ -1232,15 +1282,20 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, return 1; BUG_ON(ident != TAG_IDENT_LVD); lvd = (struct logicalVolDesc *)bh->b_data; - - i = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps)); - if (i != 0) { - ret = i; + table_len = le32_to_cpu(lvd->mapTableLength); + if (sizeof(*lvd) + table_len > sb->s_blocksize) { + udf_err(sb, "error loading logical volume descriptor: " + "Partition table too long (%u > %lu)\n", table_len, + sb->s_blocksize - sizeof(*lvd)); goto out_bh; } + ret = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps)); + if (ret) + goto out_bh; + for (i = 0, offset = 0; - i < sbi->s_partitions && offset < le32_to_cpu(lvd->mapTableLength); + i < sbi->s_partitions && offset < table_len; i++, offset += gpm->partitionMapLength) { struct udf_part_map *map = &sbi->s_partmaps[i]; gpm = (struct genericPartitionMap *) @@ -1275,38 +1330,9 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, } else if (!strncmp(upm2->partIdent.ident, UDF_ID_SPARABLE, strlen(UDF_ID_SPARABLE))) { - uint32_t loc; - struct sparingTable *st; - struct sparablePartitionMap *spm = - (struct sparablePartitionMap *)gpm; - - map->s_partition_type = UDF_SPARABLE_MAP15; - map->s_type_specific.s_sparing.s_packet_len = - le16_to_cpu(spm->packetLength); - for (j = 0; j < spm->numSparingTables; j++) { - struct buffer_head *bh2; - - loc = le32_to_cpu( - spm->locSparingTable[j]); - bh2 = udf_read_tagged(sb, loc, loc, - &ident); - map->s_type_specific.s_sparing. - s_spar_map[j] = bh2; - - if (bh2 == NULL) - continue; - - st = (struct sparingTable *)bh2->b_data; - if (ident != 0 || strncmp( - st->sparingIdent.ident, - UDF_ID_SPARING, - strlen(UDF_ID_SPARING))) { - brelse(bh2); - map->s_type_specific.s_sparing. - s_spar_map[j] = NULL; - } - } - map->s_partition_func = udf_get_pblock_spar15; + if (udf_load_sparable_map(sb, map, + (struct sparablePartitionMap *)gpm) < 0) + goto out_bh; } else if (!strncmp(upm2->partIdent.ident, UDF_ID_METADATA, strlen(UDF_ID_METADATA))) { diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index 42694e1..1b3e410 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -116,7 +116,7 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); unlock_super (sb); UFSD("EXIT\n"); @@ -214,7 +214,7 @@ do_more: goto do_more; } - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); unlock_super (sb); UFSD("EXIT\n"); return; @@ -557,7 +557,7 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment, ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); UFSD("EXIT, fragment %llu\n", (unsigned long long)fragment); @@ -677,7 +677,7 @@ succed: ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); result += cgno * uspi->s_fpg; UFSD("EXIT3, result %llu\n", (unsigned long long)result); diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 4ec5c10..e84cbe2 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -116,7 +116,7 @@ void ufs_free_inode (struct inode * inode) if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); unlock_super (sb); UFSD("EXIT\n"); } @@ -288,7 +288,7 @@ cg_found: ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); inode->i_ino = cg * uspi->s_ipg + bit; inode_init_owner(inode, dir, mode); diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index a2281ca..90d74b8 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -46,7 +46,7 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode) return err; } -static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags) { struct inode * inode = NULL; ino_t ino; @@ -71,7 +71,7 @@ static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, stru * with d_instantiate(). */ static int ufs_create (struct inode * dir, struct dentry * dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; int err; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 302f340..444927e 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -302,7 +302,7 @@ void ufs_error (struct super_block * sb, const char * function, if (!(sb->s_flags & MS_RDONLY)) { usb1->fs_clean = UFS_FSBAD; ubh_mark_buffer_dirty(USPI_UBH(uspi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); sb->s_flags |= MS_RDONLY; } va_start (args, fmt); @@ -334,7 +334,7 @@ void ufs_panic (struct super_block * sb, const char * function, if (!(sb->s_flags & MS_RDONLY)) { usb1->fs_clean = UFS_FSBAD; ubh_mark_buffer_dirty(USPI_UBH(uspi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); } va_start (args, fmt); vsnprintf (error_buf, sizeof(error_buf), fmt, args); @@ -691,6 +691,83 @@ static void ufs_put_super_internal(struct super_block *sb) UFSD("EXIT\n"); } +static int ufs_sync_fs(struct super_block *sb, int wait) +{ + struct ufs_sb_private_info * uspi; + struct ufs_super_block_first * usb1; + struct ufs_super_block_third * usb3; + unsigned flags; + + lock_ufs(sb); + lock_super(sb); + + UFSD("ENTER\n"); + + flags = UFS_SB(sb)->s_flags; + uspi = UFS_SB(sb)->s_uspi; + usb1 = ubh_get_usb_first(uspi); + usb3 = ubh_get_usb_third(uspi); + + usb1->fs_time = cpu_to_fs32(sb, get_seconds()); + if ((flags & UFS_ST_MASK) == UFS_ST_SUN || + (flags & UFS_ST_MASK) == UFS_ST_SUNOS || + (flags & UFS_ST_MASK) == UFS_ST_SUNx86) + ufs_set_fs_state(sb, usb1, usb3, + UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time)); + ufs_put_cstotal(sb); + + UFSD("EXIT\n"); + unlock_super(sb); + unlock_ufs(sb); + + return 0; +} + +static void delayed_sync_fs(struct work_struct *work) +{ + struct ufs_sb_info *sbi; + + sbi = container_of(work, struct ufs_sb_info, sync_work.work); + + spin_lock(&sbi->work_lock); + sbi->work_queued = 0; + spin_unlock(&sbi->work_lock); + + ufs_sync_fs(sbi->sb, 1); +} + +void ufs_mark_sb_dirty(struct super_block *sb) +{ + struct ufs_sb_info *sbi = UFS_SB(sb); + unsigned long delay; + + spin_lock(&sbi->work_lock); + if (!sbi->work_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + queue_delayed_work(system_long_wq, &sbi->sync_work, delay); + sbi->work_queued = 1; + } + spin_unlock(&sbi->work_lock); +} + +static void ufs_put_super(struct super_block *sb) +{ + struct ufs_sb_info * sbi = UFS_SB(sb); + + UFSD("ENTER\n"); + + if (!(sb->s_flags & MS_RDONLY)) + ufs_put_super_internal(sb); + cancel_delayed_work_sync(&sbi->sync_work); + + ubh_brelse_uspi (sbi->s_uspi); + kfree (sbi->s_uspi); + kfree (sbi); + sb->s_fs_info = NULL; + UFSD("EXIT\n"); + return; +} + static int ufs_fill_super(struct super_block *sb, void *data, int silent) { struct ufs_sb_info * sbi; @@ -716,6 +793,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) if (!sbi) goto failed_nomem; sb->s_fs_info = sbi; + sbi->sb = sb; UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY)); @@ -727,6 +805,8 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) } #endif mutex_init(&sbi->mutex); + spin_lock_init(&sbi->work_lock); + INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs); /* * Set default mount options * Parse mount options @@ -1191,68 +1271,6 @@ failed_nomem: return -ENOMEM; } -static int ufs_sync_fs(struct super_block *sb, int wait) -{ - struct ufs_sb_private_info * uspi; - struct ufs_super_block_first * usb1; - struct ufs_super_block_third * usb3; - unsigned flags; - - lock_ufs(sb); - lock_super(sb); - - UFSD("ENTER\n"); - - flags = UFS_SB(sb)->s_flags; - uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(uspi); - usb3 = ubh_get_usb_third(uspi); - - usb1->fs_time = cpu_to_fs32(sb, get_seconds()); - if ((flags & UFS_ST_MASK) == UFS_ST_SUN || - (flags & UFS_ST_MASK) == UFS_ST_SUNOS || - (flags & UFS_ST_MASK) == UFS_ST_SUNx86) - ufs_set_fs_state(sb, usb1, usb3, - UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time)); - ufs_put_cstotal(sb); - sb->s_dirt = 0; - - UFSD("EXIT\n"); - unlock_super(sb); - unlock_ufs(sb); - - return 0; -} - -static void ufs_write_super(struct super_block *sb) -{ - if (!(sb->s_flags & MS_RDONLY)) - ufs_sync_fs(sb, 1); - else - sb->s_dirt = 0; -} - -static void ufs_put_super(struct super_block *sb) -{ - struct ufs_sb_info * sbi = UFS_SB(sb); - - UFSD("ENTER\n"); - - if (sb->s_dirt) - ufs_write_super(sb); - - if (!(sb->s_flags & MS_RDONLY)) - ufs_put_super_internal(sb); - - ubh_brelse_uspi (sbi->s_uspi); - kfree (sbi->s_uspi); - kfree (sbi); - sb->s_fs_info = NULL; - UFSD("EXIT\n"); - return; -} - - static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) { struct ufs_sb_private_info * uspi; @@ -1308,7 +1326,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) ufs_set_fs_state(sb, usb1, usb3, UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time)); ubh_mark_buffer_dirty (USPI_UBH(uspi)); - sb->s_dirt = 0; sb->s_flags |= MS_RDONLY; } else { /* @@ -1458,7 +1475,6 @@ static const struct super_operations ufs_super_ops = { .write_inode = ufs_write_inode, .evict_inode = ufs_evict_inode, .put_super = ufs_put_super, - .write_super = ufs_write_super, .sync_fs = ufs_sync_fs, .statfs = ufs_statfs, .remount_fs = ufs_remount, diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 528750b..343e6fc 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -20,6 +20,10 @@ struct ufs_sb_info { unsigned s_mount_opt; struct mutex mutex; struct task_struct *mutex_owner; + struct super_block *sb; + int work_queued; /* non-zero if the delayed work is queued */ + struct delayed_work sync_work; /* FS sync delayed work */ + spinlock_t work_lock; /* protects sync_work and work_queued */ }; struct ufs_inode_info { @@ -123,6 +127,7 @@ extern __printf(3, 4) void ufs_error(struct super_block *, const char *, const char *, ...); extern __printf(3, 4) void ufs_panic(struct super_block *, const char *, const char *, ...); +void ufs_mark_sb_dirty(struct super_block *sb); /* symlink.c */ extern const struct inode_operations ufs_fast_symlink_inode_operations; diff --git a/fs/ufs/ufs_fs.h b/fs/ufs/ufs_fs.h index 8aba544..0cbd5d3 100644 --- a/fs/ufs/ufs_fs.h +++ b/fs/ufs/ufs_fs.h @@ -34,6 +34,7 @@ #include <linux/kernel.h> #include <linux/stat.h> #include <linux/fs.h> +#include <linux/workqueue.h> #include <asm/div64.h> typedef __u64 __bitwise __fs64; diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 229641f..4f33c32 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -1074,12 +1074,13 @@ restart: * If we couldn't get anything, give up. */ if (bno_cur_lt == NULL && bno_cur_gt == NULL) { + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); + if (!forced++) { trace_xfs_alloc_near_busy(args); xfs_log_force(args->mp, XFS_LOG_SYNC); goto restart; } - trace_xfs_alloc_size_neither(args); args->agbno = NULLAGBLOCK; return 0; @@ -2433,15 +2434,24 @@ xfs_alloc_vextent_worker( current_restore_flags_nested(&pflags, PF_FSTRANS); } - -int /* error */ +/* + * Data allocation requests often come in with little stack to work on. Push + * them off to a worker thread so there is lots of stack to use. Metadata + * requests, OTOH, are generally from low stack usage paths, so avoid the + * context switch overhead here. + */ +int xfs_alloc_vextent( - xfs_alloc_arg_t *args) /* allocation argument structure */ + struct xfs_alloc_arg *args) { DECLARE_COMPLETION_ONSTACK(done); + if (!args->userdata) + return __xfs_alloc_vextent(args); + + args->done = &done; - INIT_WORK(&args->work, xfs_alloc_vextent_worker); + INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker); queue_work(xfs_alloc_wq, &args->work); wait_for_completion(&done); return args->result; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index ae31c31..8dad722 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -981,10 +981,15 @@ xfs_vm_writepage( imap_valid = 0; } } else { - if (PageUptodate(page)) { + if (PageUptodate(page)) ASSERT(buffer_mapped(bh)); - imap_valid = 0; - } + /* + * This buffer is not uptodate and will not be + * written to disk. Ensure that we will put any + * subsequent writeable buffers into a new + * ioend. + */ + imap_valid = 0; continue; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 172d3cc..269b35c 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -201,14 +201,7 @@ xfs_buf_alloc( bp->b_length = numblks; bp->b_io_length = numblks; bp->b_flags = flags; - - /* - * We do not set the block number here in the buffer because we have not - * finished initialising the buffer. We insert the buffer into the cache - * in this state, so this ensures that we are unable to do IO on a - * buffer that hasn't been fully initialised. - */ - bp->b_bn = XFS_BUF_DADDR_NULL; + bp->b_bn = blkno; atomic_set(&bp->b_pin_count, 0); init_waitqueue_head(&bp->b_waiters); @@ -567,11 +560,6 @@ xfs_buf_get( if (bp != new_bp) xfs_buf_free(new_bp); - /* - * Now we have a workable buffer, fill in the block number so - * that we can do IO on it. - */ - bp->b_bn = blkno; bp->b_io_length = bp->b_length; found: @@ -772,7 +760,7 @@ xfs_buf_get_uncached( int error, i; xfs_buf_t *bp; - bp = xfs_buf_alloc(target, 0, numblks, 0); + bp = xfs_buf_alloc(target, XFS_BUF_DADDR_NULL, numblks, 0); if (unlikely(bp == NULL)) goto fail; @@ -1001,27 +989,6 @@ xfs_buf_ioerror_alert( (__uint64_t)XFS_BUF_ADDR(bp), func, bp->b_error, bp->b_length); } -int -xfs_bwrite( - struct xfs_buf *bp) -{ - int error; - - ASSERT(xfs_buf_islocked(bp)); - - bp->b_flags |= XBF_WRITE; - bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q); - - xfs_bdstrat_cb(bp); - - error = xfs_buf_iowait(bp); - if (error) { - xfs_force_shutdown(bp->b_target->bt_mount, - SHUTDOWN_META_IO_ERROR); - } - return error; -} - /* * Called when we want to stop a buffer from getting written or read. * We attach the EIO error, muck with its flags, and call xfs_buf_ioend @@ -1091,14 +1058,7 @@ xfs_bioerror_relse( return EIO; } - -/* - * All xfs metadata buffers except log state machine buffers - * get this attached as their b_bdstrat callback function. - * This is so that we can catch a buffer - * after prematurely unpinning it to forcibly shutdown the filesystem. - */ -int +STATIC int xfs_bdstrat_cb( struct xfs_buf *bp) { @@ -1119,6 +1079,27 @@ xfs_bdstrat_cb( return 0; } +int +xfs_bwrite( + struct xfs_buf *bp) +{ + int error; + + ASSERT(xfs_buf_islocked(bp)); + + bp->b_flags |= XBF_WRITE; + bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q); + + xfs_bdstrat_cb(bp); + + error = xfs_buf_iowait(bp); + if (error) { + xfs_force_shutdown(bp->b_target->bt_mount, + SHUTDOWN_META_IO_ERROR); + } + return error; +} + /* * Wrapper around bdstrat so that we can stop data from going to disk in case * we are shutting down the filesystem. Typically user data goes thru this @@ -1255,7 +1236,7 @@ xfs_buf_iorequest( */ atomic_set(&bp->b_io_remaining, 1); _xfs_buf_ioapply(bp); - _xfs_buf_ioend(bp, 0); + _xfs_buf_ioend(bp, 1); xfs_buf_rele(bp); } diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 7f1d139..79344c4 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -180,7 +180,6 @@ extern void xfs_buf_unlock(xfs_buf_t *); extern int xfs_bwrite(struct xfs_buf *bp); extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *); -extern int xfs_bdstrat_cb(struct xfs_buf *); extern void xfs_buf_ioend(xfs_buf_t *, int); extern void xfs_buf_ioerror(xfs_buf_t *, int); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 45df2b8..d9e4511 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -954,7 +954,7 @@ xfs_buf_iodone_callbacks( if (!XFS_BUF_ISSTALE(bp)) { bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE; - xfs_bdstrat_cb(bp); + xfs_buf_iorequest(bp); } else { xfs_buf_relse(bp); } diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 6cdbf90c..d041d47 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -505,6 +505,14 @@ xfs_inode_item_push( } /* + * Stale inode items should force out the iclog. + */ + if (ip->i_flags & XFS_ISTALE) { + rval = XFS_ITEM_PINNED; + goto out_unlock; + } + + /* * Someone else is already flushing the inode. Nothing we can do * here but wait for the flush to finish and remove the item from * the AIL. @@ -514,15 +522,6 @@ xfs_inode_item_push( goto out_unlock; } - /* - * Stale inode items should force out the iclog. - */ - if (ip->i_flags & XFS_ISTALE) { - xfs_ifunlock(ip); - xfs_iunlock(ip, XFS_ILOCK_SHARED); - return XFS_ITEM_PINNED; - } - ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 3a05a41..1f1535d 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -208,6 +208,7 @@ xfs_open_by_handle( struct inode *inode; struct dentry *dentry; fmode_t fmode; + struct path path; if (!capable(CAP_SYS_ADMIN)) return -XFS_ERROR(EPERM); @@ -252,8 +253,10 @@ xfs_open_by_handle( goto out_dput; } - filp = dentry_open(dentry, mntget(parfilp->f_path.mnt), - hreq->oflags, cred); + path.mnt = parfilp->f_path.mnt; + path.dentry = dentry; + filp = dentry_open(&path, hreq->oflags, cred); + dput(dentry); if (IS_ERR(filp)) { put_unused_fd(fd); return PTR_ERR(filp); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 1a25fd8..9c4340f 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -179,7 +179,7 @@ xfs_vn_create( struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool flags) { return xfs_vn_mknod(dir, dentry, mode, 0); } @@ -197,7 +197,7 @@ STATIC struct dentry * xfs_vn_lookup( struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct xfs_inode *cip; struct xfs_name name; @@ -222,7 +222,7 @@ STATIC struct dentry * xfs_vn_ci_lookup( struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct xfs_inode *ip; struct xfs_name xname; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index f30d980..d90d4a3 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -38,13 +38,21 @@ kmem_zone_t *xfs_log_ticket_zone; /* Local miscellaneous function prototypes */ -STATIC int xlog_commit_record(struct log *log, struct xlog_ticket *ticket, - xlog_in_core_t **, xfs_lsn_t *); +STATIC int +xlog_commit_record( + struct xlog *log, + struct xlog_ticket *ticket, + struct xlog_in_core **iclog, + xfs_lsn_t *commitlsnp); + STATIC xlog_t * xlog_alloc_log(xfs_mount_t *mp, xfs_buftarg_t *log_target, xfs_daddr_t blk_offset, int num_bblks); -STATIC int xlog_space_left(struct log *log, atomic64_t *head); +STATIC int +xlog_space_left( + struct xlog *log, + atomic64_t *head); STATIC int xlog_sync(xlog_t *log, xlog_in_core_t *iclog); STATIC void xlog_dealloc_log(xlog_t *log); @@ -64,8 +72,10 @@ STATIC void xlog_state_switch_iclogs(xlog_t *log, int eventual_size); STATIC void xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog); -STATIC void xlog_grant_push_ail(struct log *log, - int need_bytes); +STATIC void +xlog_grant_push_ail( + struct xlog *log, + int need_bytes); STATIC void xlog_regrant_reserve_log_space(xlog_t *log, xlog_ticket_t *ticket); STATIC void xlog_ungrant_log_space(xlog_t *log, @@ -73,7 +83,9 @@ STATIC void xlog_ungrant_log_space(xlog_t *log, #if defined(DEBUG) STATIC void xlog_verify_dest_ptr(xlog_t *log, char *ptr); -STATIC void xlog_verify_grant_tail(struct log *log); +STATIC void +xlog_verify_grant_tail( + struct xlog *log); STATIC void xlog_verify_iclog(xlog_t *log, xlog_in_core_t *iclog, int count, boolean_t syncing); STATIC void xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog, @@ -89,9 +101,9 @@ STATIC int xlog_iclogs_empty(xlog_t *log); static void xlog_grant_sub_space( - struct log *log, - atomic64_t *head, - int bytes) + struct xlog *log, + atomic64_t *head, + int bytes) { int64_t head_val = atomic64_read(head); int64_t new, old; @@ -115,9 +127,9 @@ xlog_grant_sub_space( static void xlog_grant_add_space( - struct log *log, - atomic64_t *head, - int bytes) + struct xlog *log, + atomic64_t *head, + int bytes) { int64_t head_val = atomic64_read(head); int64_t new, old; @@ -165,7 +177,7 @@ xlog_grant_head_wake_all( static inline int xlog_ticket_reservation( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic) { @@ -182,7 +194,7 @@ xlog_ticket_reservation( STATIC bool xlog_grant_head_wake( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, int *free_bytes) { @@ -204,7 +216,7 @@ xlog_grant_head_wake( STATIC int xlog_grant_head_wait( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic, int need_bytes) @@ -256,7 +268,7 @@ shutdown: */ STATIC int xlog_grant_head_check( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic, int *need_bytes) @@ -323,7 +335,7 @@ xfs_log_regrant( struct xfs_mount *mp, struct xlog_ticket *tic) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; int need_bytes; int error = 0; @@ -389,7 +401,7 @@ xfs_log_reserve( bool permanent, uint t_type) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xlog_ticket *tic; int need_bytes; int error = 0; @@ -465,7 +477,7 @@ xfs_log_done( struct xlog_in_core **iclog, uint flags) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; xfs_lsn_t lsn = 0; if (XLOG_FORCED_SHUTDOWN(log) || @@ -810,6 +822,7 @@ xfs_log_unmount_write(xfs_mount_t *mp) void xfs_log_unmount(xfs_mount_t *mp) { + cancel_delayed_work_sync(&mp->m_sync_work); xfs_trans_ail_destroy(mp); xlog_dealloc_log(mp->m_log); } @@ -838,7 +851,7 @@ void xfs_log_space_wake( struct xfs_mount *mp) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; int free_bytes; if (XLOG_FORCED_SHUTDOWN(log)) @@ -916,7 +929,7 @@ xfs_lsn_t xlog_assign_tail_lsn_locked( struct xfs_mount *mp) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xfs_log_item *lip; xfs_lsn_t tail_lsn; @@ -965,7 +978,7 @@ xlog_assign_tail_lsn( */ STATIC int xlog_space_left( - struct log *log, + struct xlog *log, atomic64_t *head) { int free_bytes; @@ -1277,7 +1290,7 @@ out: */ STATIC int xlog_commit_record( - struct log *log, + struct xlog *log, struct xlog_ticket *ticket, struct xlog_in_core **iclog, xfs_lsn_t *commitlsnp) @@ -1311,7 +1324,7 @@ xlog_commit_record( */ STATIC void xlog_grant_push_ail( - struct log *log, + struct xlog *log, int need_bytes) { xfs_lsn_t threshold_lsn = 0; @@ -1790,7 +1803,7 @@ xlog_write_start_rec( static xlog_op_header_t * xlog_write_setup_ophdr( - struct log *log, + struct xlog *log, struct xlog_op_header *ophdr, struct xlog_ticket *ticket, uint flags) @@ -1873,7 +1886,7 @@ xlog_write_setup_copy( static int xlog_write_copy_finish( - struct log *log, + struct xlog *log, struct xlog_in_core *iclog, uint flags, int *record_cnt, @@ -1958,7 +1971,7 @@ xlog_write_copy_finish( */ int xlog_write( - struct log *log, + struct xlog *log, struct xfs_log_vec *log_vector, struct xlog_ticket *ticket, xfs_lsn_t *start_lsn, @@ -2821,7 +2834,7 @@ _xfs_log_force( uint flags, int *log_flushed) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xlog_in_core *iclog; xfs_lsn_t lsn; @@ -2969,7 +2982,7 @@ _xfs_log_force_lsn( uint flags, int *log_flushed) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xlog_in_core *iclog; int already_slept = 0; @@ -3147,7 +3160,7 @@ xfs_log_ticket_get( */ xlog_ticket_t * xlog_ticket_alloc( - struct log *log, + struct xlog *log, int unit_bytes, int cnt, char client, @@ -3278,7 +3291,7 @@ xlog_ticket_alloc( */ void xlog_verify_dest_ptr( - struct log *log, + struct xlog *log, char *ptr) { int i; @@ -3307,7 +3320,7 @@ xlog_verify_dest_ptr( */ STATIC void xlog_verify_grant_tail( - struct log *log) + struct xlog *log) { int tail_cycle, tail_blocks; int cycle, space; diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 7d6197c..ddc4529 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -44,7 +44,7 @@ */ static struct xlog_ticket * xlog_cil_ticket_alloc( - struct log *log) + struct xlog *log) { struct xlog_ticket *tic; @@ -72,7 +72,7 @@ xlog_cil_ticket_alloc( */ void xlog_cil_init_post_recovery( - struct log *log) + struct xlog *log) { log->l_cilp->xc_ctx->ticket = xlog_cil_ticket_alloc(log); log->l_cilp->xc_ctx->sequence = 1; @@ -182,7 +182,7 @@ xlog_cil_prepare_log_vecs( */ STATIC void xfs_cil_prepare_item( - struct log *log, + struct xlog *log, struct xfs_log_vec *lv, int *len, int *diff_iovecs) @@ -231,7 +231,7 @@ xfs_cil_prepare_item( */ static void xlog_cil_insert_items( - struct log *log, + struct xlog *log, struct xfs_log_vec *log_vector, struct xlog_ticket *ticket) { @@ -373,7 +373,7 @@ xlog_cil_committed( */ STATIC int xlog_cil_push( - struct log *log) + struct xlog *log) { struct xfs_cil *cil = log->l_cilp; struct xfs_log_vec *lv; @@ -601,7 +601,7 @@ xlog_cil_push_work( */ static void xlog_cil_push_background( - struct log *log) + struct xlog *log) { struct xfs_cil *cil = log->l_cilp; @@ -629,7 +629,7 @@ xlog_cil_push_background( static void xlog_cil_push_foreground( - struct log *log, + struct xlog *log, xfs_lsn_t push_seq) { struct xfs_cil *cil = log->l_cilp; @@ -683,7 +683,7 @@ xfs_log_commit_cil( xfs_lsn_t *commit_lsn, int flags) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; int log_flags = 0; struct xfs_log_vec *log_vector; @@ -754,7 +754,7 @@ xfs_log_commit_cil( */ xfs_lsn_t xlog_cil_force_lsn( - struct log *log, + struct xlog *log, xfs_lsn_t sequence) { struct xfs_cil *cil = log->l_cilp; @@ -833,7 +833,7 @@ xfs_log_item_in_current_chkpt( */ int xlog_cil_init( - struct log *log) + struct xlog *log) { struct xfs_cil *cil; struct xfs_cil_ctx *ctx; @@ -869,7 +869,7 @@ xlog_cil_init( void xlog_cil_destroy( - struct log *log) + struct xlog *log) { if (log->l_cilp->xc_ctx) { if (log->l_cilp->xc_ctx->ticket) diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 5bc3326..72eba22 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -19,7 +19,7 @@ #define __XFS_LOG_PRIV_H__ struct xfs_buf; -struct log; +struct xlog; struct xlog_ticket; struct xfs_mount; @@ -352,7 +352,7 @@ typedef struct xlog_in_core { struct xlog_in_core *ic_next; struct xlog_in_core *ic_prev; struct xfs_buf *ic_bp; - struct log *ic_log; + struct xlog *ic_log; int ic_size; int ic_offset; int ic_bwritecnt; @@ -409,7 +409,7 @@ struct xfs_cil_ctx { * operations almost as efficient as the old logging methods. */ struct xfs_cil { - struct log *xc_log; + struct xlog *xc_log; struct list_head xc_cil; spinlock_t xc_cil_lock; struct xfs_cil_ctx *xc_ctx; @@ -487,7 +487,7 @@ struct xlog_grant_head { * overflow 31 bits worth of byte offset, so using a byte number will mean * that round off problems won't occur when releasing partial reservations. */ -typedef struct log { +typedef struct xlog { /* The following fields don't need locking */ struct xfs_mount *l_mp; /* mount point */ struct xfs_ail *l_ailp; /* AIL log is working with */ @@ -553,9 +553,14 @@ extern int xlog_recover_finish(xlog_t *log); extern void xlog_pack_data(xlog_t *log, xlog_in_core_t *iclog, int); extern kmem_zone_t *xfs_log_ticket_zone; -struct xlog_ticket *xlog_ticket_alloc(struct log *log, int unit_bytes, - int count, char client, bool permanent, - xfs_km_flags_t alloc_flags); +struct xlog_ticket * +xlog_ticket_alloc( + struct xlog *log, + int unit_bytes, + int count, + char client, + bool permanent, + xfs_km_flags_t alloc_flags); static inline void @@ -567,9 +572,14 @@ xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes) } void xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket); -int xlog_write(struct log *log, struct xfs_log_vec *log_vector, - struct xlog_ticket *tic, xfs_lsn_t *start_lsn, - xlog_in_core_t **commit_iclog, uint flags); +int +xlog_write( + struct xlog *log, + struct xfs_log_vec *log_vector, + struct xlog_ticket *tic, + xfs_lsn_t *start_lsn, + struct xlog_in_core **commit_iclog, + uint flags); /* * When we crack an atomic LSN, we sample it first so that the value will not @@ -629,17 +639,23 @@ xlog_assign_grant_head(atomic64_t *head, int cycle, int space) /* * Committed Item List interfaces */ -int xlog_cil_init(struct log *log); -void xlog_cil_init_post_recovery(struct log *log); -void xlog_cil_destroy(struct log *log); +int +xlog_cil_init(struct xlog *log); +void +xlog_cil_init_post_recovery(struct xlog *log); +void +xlog_cil_destroy(struct xlog *log); /* * CIL force routines */ -xfs_lsn_t xlog_cil_force_lsn(struct log *log, xfs_lsn_t sequence); +xfs_lsn_t +xlog_cil_force_lsn( + struct xlog *log, + xfs_lsn_t sequence); static inline void -xlog_cil_force(struct log *log) +xlog_cil_force(struct xlog *log) { xlog_cil_force_lsn(log, log->l_cilp->xc_current_sequence); } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index ca38690..a7be98a 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1471,8 +1471,8 @@ xlog_recover_add_item( STATIC int xlog_recover_add_to_cont_trans( - struct log *log, - xlog_recover_t *trans, + struct xlog *log, + struct xlog_recover *trans, xfs_caddr_t dp, int len) { @@ -1517,8 +1517,8 @@ xlog_recover_add_to_cont_trans( */ STATIC int xlog_recover_add_to_trans( - struct log *log, - xlog_recover_t *trans, + struct xlog *log, + struct xlog_recover *trans, xfs_caddr_t dp, int len) { @@ -1588,8 +1588,8 @@ xlog_recover_add_to_trans( */ STATIC int xlog_recover_reorder_trans( - struct log *log, - xlog_recover_t *trans, + struct xlog *log, + struct xlog_recover *trans, int pass) { xlog_recover_item_t *item, *n; @@ -1642,8 +1642,8 @@ xlog_recover_reorder_trans( */ STATIC int xlog_recover_buffer_pass1( - struct log *log, - xlog_recover_item_t *item) + struct xlog *log, + struct xlog_recover_item *item) { xfs_buf_log_format_t *buf_f = item->ri_buf[0].i_addr; struct list_head *bucket; @@ -1696,7 +1696,7 @@ xlog_recover_buffer_pass1( */ STATIC int xlog_check_buffer_cancelled( - struct log *log, + struct xlog *log, xfs_daddr_t blkno, uint len, ushort flags) @@ -2689,9 +2689,9 @@ xlog_recover_free_trans( STATIC int xlog_recover_commit_pass1( - struct log *log, - struct xlog_recover *trans, - xlog_recover_item_t *item) + struct xlog *log, + struct xlog_recover *trans, + struct xlog_recover_item *item) { trace_xfs_log_recover_item_recover(log, trans, item, XLOG_RECOVER_PASS1); @@ -2716,10 +2716,10 @@ xlog_recover_commit_pass1( STATIC int xlog_recover_commit_pass2( - struct log *log, - struct xlog_recover *trans, - struct list_head *buffer_list, - xlog_recover_item_t *item) + struct xlog *log, + struct xlog_recover *trans, + struct list_head *buffer_list, + struct xlog_recover_item *item) { trace_xfs_log_recover_item_recover(log, trans, item, XLOG_RECOVER_PASS2); @@ -2753,7 +2753,7 @@ xlog_recover_commit_pass2( */ STATIC int xlog_recover_commit_trans( - struct log *log, + struct xlog *log, struct xlog_recover *trans, int pass) { @@ -2793,8 +2793,8 @@ out: STATIC int xlog_recover_unmount_trans( - struct log *log, - xlog_recover_t *trans) + struct xlog *log, + struct xlog_recover *trans) { /* Do nothing now */ xfs_warn(log->l_mp, "%s: Unmount LR", __func__); diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 8b89c5a..90c1fc9 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -53,7 +53,7 @@ typedef struct xfs_trans_reservations { #include "xfs_sync.h" -struct log; +struct xlog; struct xfs_mount_args; struct xfs_inode; struct xfs_bmbt_irec; @@ -133,7 +133,7 @@ typedef struct xfs_mount { uint m_readio_blocks; /* min read size blocks */ uint m_writeio_log; /* min write size log bytes */ uint m_writeio_blocks; /* min write size blocks */ - struct log *m_log; /* log specific stuff */ + struct xlog *m_log; /* log specific stuff */ int m_logbufs; /* number of log buffers */ int m_logbsize; /* size of each log buffer */ uint m_rsumlevels; /* rt summary levels */ diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c index c9d3409..1e9ee06 100644 --- a/fs/xfs/xfs_sync.c +++ b/fs/xfs/xfs_sync.c @@ -386,23 +386,23 @@ xfs_sync_worker( * We shouldn't write/force the log if we are in the mount/unmount * process or on a read only filesystem. The workqueue still needs to be * active in both cases, however, because it is used for inode reclaim - * during these times. Use the s_umount semaphore to provide exclusion - * with unmount. + * during these times. Use the MS_ACTIVE flag to avoid doing anything + * during mount. Doing work during unmount is avoided by calling + * cancel_delayed_work_sync on this work queue before tearing down + * the ail and the log in xfs_log_unmount. */ - if (down_read_trylock(&mp->m_super->s_umount)) { - if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { - /* dgc: errors ignored here */ - if (mp->m_super->s_frozen == SB_UNFROZEN && - xfs_log_need_covered(mp)) - error = xfs_fs_log_dummy(mp); - else - xfs_log_force(mp, 0); - - /* start pushing all the metadata that is currently - * dirty */ - xfs_ail_push_all(mp->m_ail); - } - up_read(&mp->m_super->s_umount); + if (!(mp->m_super->s_flags & MS_ACTIVE) && + !(mp->m_flags & XFS_MOUNT_RDONLY)) { + /* dgc: errors ignored here */ + if (mp->m_super->s_frozen == SB_UNFROZEN && + xfs_log_need_covered(mp)) + error = xfs_fs_log_dummy(mp); + else + xfs_log_force(mp, 0); + + /* start pushing all the metadata that is currently + * dirty */ + xfs_ail_push_all(mp->m_ail); } /* queue us up again */ diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 7cf9d35..caf5dab 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -32,7 +32,7 @@ struct xfs_da_node_entry; struct xfs_dquot; struct xfs_log_item; struct xlog_ticket; -struct log; +struct xlog; struct xlog_recover; struct xlog_recover_item; struct xfs_buf_log_format; @@ -762,7 +762,7 @@ DEFINE_DQUOT_EVENT(xfs_dqflush_force); DEFINE_DQUOT_EVENT(xfs_dqflush_done); DECLARE_EVENT_CLASS(xfs_loggrant_class, - TP_PROTO(struct log *log, struct xlog_ticket *tic), + TP_PROTO(struct xlog *log, struct xlog_ticket *tic), TP_ARGS(log, tic), TP_STRUCT__entry( __field(dev_t, dev) @@ -830,7 +830,7 @@ DECLARE_EVENT_CLASS(xfs_loggrant_class, #define DEFINE_LOGGRANT_EVENT(name) \ DEFINE_EVENT(xfs_loggrant_class, name, \ - TP_PROTO(struct log *log, struct xlog_ticket *tic), \ + TP_PROTO(struct xlog *log, struct xlog_ticket *tic), \ TP_ARGS(log, tic)) DEFINE_LOGGRANT_EVENT(xfs_log_done_nonperm); DEFINE_LOGGRANT_EVENT(xfs_log_done_perm); @@ -1664,7 +1664,7 @@ DEFINE_SWAPEXT_EVENT(xfs_swap_extent_before); DEFINE_SWAPEXT_EVENT(xfs_swap_extent_after); DECLARE_EVENT_CLASS(xfs_log_recover_item_class, - TP_PROTO(struct log *log, struct xlog_recover *trans, + TP_PROTO(struct xlog *log, struct xlog_recover *trans, struct xlog_recover_item *item, int pass), TP_ARGS(log, trans, item, pass), TP_STRUCT__entry( @@ -1698,7 +1698,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_item_class, #define DEFINE_LOG_RECOVER_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_item_class, name, \ - TP_PROTO(struct log *log, struct xlog_recover *trans, \ + TP_PROTO(struct xlog *log, struct xlog_recover *trans, \ struct xlog_recover_item *item, int pass), \ TP_ARGS(log, trans, item, pass)) @@ -1709,7 +1709,7 @@ DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_reorder_tail); DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_recover); DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class, - TP_PROTO(struct log *log, struct xfs_buf_log_format *buf_f), + TP_PROTO(struct xlog *log, struct xfs_buf_log_format *buf_f), TP_ARGS(log, buf_f), TP_STRUCT__entry( __field(dev_t, dev) @@ -1739,7 +1739,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class, #define DEFINE_LOG_RECOVER_BUF_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_buf_item_class, name, \ - TP_PROTO(struct log *log, struct xfs_buf_log_format *buf_f), \ + TP_PROTO(struct xlog *log, struct xfs_buf_log_format *buf_f), \ TP_ARGS(log, buf_f)) DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_not_cancel); @@ -1752,7 +1752,7 @@ DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_reg_buf); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_dquot_buf); DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class, - TP_PROTO(struct log *log, struct xfs_inode_log_format *in_f), + TP_PROTO(struct xlog *log, struct xfs_inode_log_format *in_f), TP_ARGS(log, in_f), TP_STRUCT__entry( __field(dev_t, dev) @@ -1790,7 +1790,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class, ) #define DEFINE_LOG_RECOVER_INO_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_ino_item_class, name, \ - TP_PROTO(struct log *log, struct xfs_inode_log_format *in_f), \ + TP_PROTO(struct xlog *log, struct xfs_inode_log_format *in_f), \ TP_ARGS(log, in_f)) DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_recover); |
