diff options
Diffstat (limited to 'fs')
204 files changed, 1879 insertions, 1059 deletions
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 8b75463cb211..af03c2a901eb 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -94,13 +94,13 @@ 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_SIZE; - sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME; + sb->s_flags |= SB_ACTIVE | SB_DIRSYNC | SB_NOATIME; if (!v9ses->cache) - sb->s_flags |= MS_SYNCHRONOUS; + sb->s_flags |= SB_SYNCHRONOUS; #ifdef CONFIG_9P_FS_POSIX_ACL if ((v9ses->flags & V9FS_ACL_MASK) == V9FS_POSIX_ACL) - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; #endif return 0; diff --git a/fs/adfs/super.c b/fs/adfs/super.c index c9fdfb112933..cfda2c7caedc 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -213,7 +213,7 @@ static int parse_options(struct super_block *sb, char *options) static int adfs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_NODIRATIME; + *flags |= SB_NODIRATIME; return parse_options(sb, data); } @@ -372,7 +372,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) struct inode *root; int ret = -EINVAL; - sb->s_flags |= MS_NODIRATIME; + sb->s_flags |= SB_NODIRATIME; asb = kzalloc(sizeof(*asb), GFP_KERNEL); if (!asb) diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index 185d5ab7e986..0f0e6925e97d 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -453,7 +453,7 @@ affs_error(struct super_block *sb, const char *function, const char *fmt, ...) pr_crit("error (device %s): %s(): %pV\n", sb->s_id, function, &vaf); if (!sb_rdonly(sb)) pr_warn("Remounting filesystem read-only\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; va_end(args); } diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c index 2b1399611d9e..5ba9ef2742f6 100644 --- a/fs/affs/bitmap.c +++ b/fs/affs/bitmap.c @@ -250,12 +250,12 @@ int affs_init_bitmap(struct super_block *sb, int *flags) int i, res = 0; struct affs_sb_info *sbi = AFFS_SB(sb); - if (*flags & MS_RDONLY) + if (*flags & SB_RDONLY) return 0; if (!AFFS_ROOT_TAIL(sb, sbi->s_root_bh)->bm_flag) { pr_notice("Bitmap invalid - mounting %s read only\n", sb->s_id); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } @@ -288,7 +288,7 @@ int affs_init_bitmap(struct super_block *sb, int *flags) if (affs_checksum_block(sb, bh)) { pr_warn("Bitmap %u invalid - mounting %s read only.\n", bm->bm_key, sb->s_id); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; goto out; } pr_debug("read bitmap block %d: %d\n", blk, bm->bm_key); diff --git a/fs/affs/super.c b/fs/affs/super.c index 884bedab7266..1117e36134cc 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -356,7 +356,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) sb->s_magic = AFFS_SUPER_MAGIC; sb->s_op = &affs_sops; - sb->s_flags |= MS_NODIRATIME; + sb->s_flags |= SB_NODIRATIME; sbi = kzalloc(sizeof(struct affs_sb_info), GFP_KERNEL); if (!sbi) @@ -466,7 +466,7 @@ got_root: if ((chksum == FS_DCFFS || chksum == MUFS_DCFFS || chksum == FS_DCOFS || chksum == MUFS_DCOFS) && !sb_rdonly(sb)) { pr_notice("Dircache FS - mounting %s read only\n", sb->s_id); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } switch (chksum) { case MUFS_FS: @@ -488,7 +488,7 @@ got_root: /* fall thru */ case FS_OFS: affs_set_opt(sbi->s_flags, SF_OFS); - sb->s_flags |= MS_NOEXEC; + sb->s_flags |= SB_NOEXEC; break; case MUFS_DCOFS: case MUFS_INTLOFS: @@ -497,7 +497,7 @@ got_root: case FS_INTLOFS: affs_set_opt(sbi->s_flags, SF_INTL); affs_set_opt(sbi->s_flags, SF_OFS); - sb->s_flags |= MS_NOEXEC; + sb->s_flags |= SB_NOEXEC; break; default: pr_err("Unknown filesystem on device %s: %08X\n", @@ -513,7 +513,7 @@ got_root: sig, sig[3] + '0', blocksize); } - sb->s_flags |= MS_NODEV | MS_NOSUID; + sb->s_flags |= SB_NODEV | SB_NOSUID; sbi->s_data_blksize = sb->s_blocksize; if (affs_test_opt(sbi->s_flags, SF_OFS)) @@ -570,7 +570,7 @@ affs_remount(struct super_block *sb, int *flags, char *data) pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data); sync_filesystem(sb); - *flags |= MS_NODIRATIME; + *flags |= SB_NODIRATIME; memcpy(volume, sbi->s_volume, 32); if (!parse_options(data, &uid, &gid, &mode, &reserved, &root_block, @@ -596,10 +596,10 @@ affs_remount(struct super_block *sb, int *flags, char *data) memcpy(sbi->s_volume, volume, 32); spin_unlock(&sbi->symlink_lock); - if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) + if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) return 0; - if (*flags & MS_RDONLY) + if (*flags & SB_RDONLY) affs_free_bitmap(sb); else res = affs_init_bitmap(sb, flags); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index ff8d5bf4354f..23c7f395d718 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -895,20 +895,38 @@ error: * However, if we didn't have a callback promise outstanding, or it was * outstanding on a different server, then it won't break it either... */ -static int afs_dir_remove_link(struct dentry *dentry, struct key *key) +static int afs_dir_remove_link(struct dentry *dentry, struct key *key, + unsigned long d_version_before, + unsigned long d_version_after) { + bool dir_valid; int ret = 0; + /* There were no intervening changes on the server if the version + * number we got back was incremented by exactly 1. + */ + dir_valid = (d_version_after == d_version_before + 1); + if (d_really_is_positive(dentry)) { struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); - if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) - kdebug("AFS_VNODE_DELETED"); - clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); - - ret = afs_validate(vnode, key); - if (ret == -ESTALE) + if (dir_valid) { + drop_nlink(&vnode->vfs_inode); + if (vnode->vfs_inode.i_nlink == 0) { + set_bit(AFS_VNODE_DELETED, &vnode->flags); + clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + } ret = 0; + } else { + clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + + if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) + kdebug("AFS_VNODE_DELETED"); + + ret = afs_validate(vnode, key); + if (ret == -ESTALE) + ret = 0; + } _debug("nlink %d [val %d]", vnode->vfs_inode.i_nlink, ret); } @@ -923,6 +941,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) struct afs_fs_cursor fc; struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; struct key *key; + unsigned long d_version = (unsigned long)dentry->d_fsdata; int ret; _enter("{%x:%u},{%pd}", @@ -955,7 +974,9 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) afs_vnode_commit_status(&fc, dvnode, fc.cb_break); ret = afs_end_vnode_operation(&fc); if (ret == 0) - ret = afs_dir_remove_link(dentry, key); + ret = afs_dir_remove_link( + dentry, key, d_version, + (unsigned long)dvnode->status.data_version); } error_key: diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 3415eb7484f6..1e81864ef0b2 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -377,6 +377,10 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) } read_sequnlock_excl(&vnode->cb_lock); + + if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) + clear_nlink(&vnode->vfs_inode); + if (valid) goto valid; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index e03910cebdd4..804d1f905622 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -441,7 +441,10 @@ enum afs_lock_state { }; /* - * AFS inode private data + * AFS inode private data. + * + * Note that afs_alloc_inode() *must* reset anything that could incorrectly + * leak from one inode to another. */ struct afs_vnode { struct inode vfs_inode; /* the VFS's inode record */ diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index ea1460b9b71a..e1126659f043 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -885,7 +885,7 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, { struct afs_net *net = call->net; enum afs_call_state state; - u32 remote_abort; + u32 remote_abort = 0; int ret; _enter("{%s,%zu},,%zu,%d", diff --git a/fs/afs/security.c b/fs/afs/security.c index 2b00097101b3..b88b7d45fdaa 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -120,7 +120,7 @@ static void afs_hash_permits(struct afs_permits *permits) void afs_cache_permit(struct afs_vnode *vnode, struct key *key, unsigned int cb_break) { - struct afs_permits *permits, *xpermits, *replacement, *new = NULL; + struct afs_permits *permits, *xpermits, *replacement, *zap, *new = NULL; afs_access_t caller_access = READ_ONCE(vnode->status.caller_access); size_t size = 0; bool changed = false; @@ -204,7 +204,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, new = kzalloc(sizeof(struct afs_permits) + sizeof(struct afs_permit) * size, GFP_NOFS); if (!new) - return; + goto out_put; refcount_set(&new->usage, 1); new->nr_permits = size; @@ -229,8 +229,6 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, afs_hash_permits(new); - afs_put_permits(permits); - /* Now see if the permit list we want is actually already available */ spin_lock(&afs_permits_lock); @@ -262,11 +260,15 @@ found: kfree(new); spin_lock(&vnode->lock); - if (cb_break != (vnode->cb_break + vnode->cb_interest->server->cb_s_break) || - permits != rcu_access_pointer(vnode->permit_cache)) - goto someone_else_changed_it_unlock; - rcu_assign_pointer(vnode->permit_cache, replacement); + zap = rcu_access_pointer(vnode->permit_cache); + if (cb_break == (vnode->cb_break + vnode->cb_interest->server->cb_s_break) && + zap == permits) + rcu_assign_pointer(vnode->permit_cache, replacement); + else + zap = replacement; spin_unlock(&vnode->lock); + afs_put_permits(zap); +out_put: afs_put_permits(permits); return; diff --git a/fs/afs/super.c b/fs/afs/super.c index 875b5eb02242..1037dd41a622 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -496,10 +496,10 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, if (ret < 0) goto error_sb; as = NULL; - sb->s_flags |= MS_ACTIVE; + sb->s_flags |= SB_ACTIVE; } else { _debug("reuse"); - ASSERTCMP(sb->s_flags, &, MS_ACTIVE); + ASSERTCMP(sb->s_flags, &, SB_ACTIVE); afs_destroy_sbi(as); as = NULL; } @@ -536,7 +536,9 @@ static void afs_kill_super(struct super_block *sb) } /* - * initialise an inode cache slab element prior to any use + * Initialise an inode cache slab element prior to any use. Note that + * afs_alloc_inode() *must* reset anything that could incorrectly leak from one + * inode to another. */ static void afs_i_init_once(void *_vnode) { @@ -568,11 +570,21 @@ static struct inode *afs_alloc_inode(struct super_block *sb) atomic_inc(&afs_count_active_inodes); + /* Reset anything that shouldn't leak from one inode to the next. */ memset(&vnode->fid, 0, sizeof(vnode->fid)); memset(&vnode->status, 0, sizeof(vnode->status)); vnode->volume = NULL; + vnode->lock_key = NULL; + vnode->permit_cache = NULL; + vnode->cb_interest = NULL; +#ifdef CONFIG_AFS_FSCACHE + vnode->cache = NULL; +#endif + vnode->flags = 1 << AFS_VNODE_UNSET; + vnode->cb_type = 0; + vnode->lock_state = AFS_VNODE_LOCK_NONE; _leave(" = %p", &vnode->vfs_inode); return &vnode->vfs_inode; diff --git a/fs/afs/write.c b/fs/afs/write.c index cb5f8a3df577..9370e2feb999 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -198,7 +198,7 @@ int afs_write_end(struct file *file, struct address_space *mapping, ret = afs_fill_page(vnode, key, pos + copied, len - copied, page); if (ret < 0) - return ret; + goto out; } SetPageUptodate(page); } @@ -206,10 +206,12 @@ int afs_write_end(struct file *file, struct address_space *mapping, set_page_dirty(page); if (PageDirty(page)) _debug("dirtied"); + ret = copied; + +out: unlock_page(page); put_page(page); - - return copied; + return ret; } /* diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index d79ced925861..82e8f6edfb48 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -281,8 +281,8 @@ static int autofs4_mount_wait(const struct path *path, bool rcu_walk) pr_debug("waiting for mount name=%pd\n", path->dentry); status = autofs4_wait(sbi, path, NFY_MOUNT); pr_debug("mount wait done status=%d\n", status); - ino->last_used = jiffies; } + ino->last_used = jiffies; return status; } @@ -321,21 +321,16 @@ static struct dentry *autofs4_mountpoint_changed(struct path *path) */ if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) { struct dentry *parent = dentry->d_parent; + struct autofs_info *ino; struct dentry *new; new = d_lookup(parent, &dentry->d_name); if (!new) return NULL; - if (new == dentry) - dput(new); - else { - struct autofs_info *ino; - - ino = autofs4_dentry_ino(new); - ino->last_used = jiffies; - dput(path->dentry); - path->dentry = new; - } + ino = autofs4_dentry_ino(new); + ino->last_used = jiffies; + dput(path->dentry); + path->dentry = new; } return path->dentry; } diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 8fc41705c7cd..961a12dc6dc8 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -170,7 +170,6 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, mutex_unlock(&sbi->wq_mutex); - if (autofs4_write(sbi, pipe, &pkt, pktsz)) switch (ret = autofs4_write(sbi, pipe, &pkt, pktsz)) { case 0: break; diff --git a/fs/befs/ChangeLog b/fs/befs/ChangeLog index 75a461cfaca6..16f2dfe8c2f7 100644 --- a/fs/befs/ChangeLog +++ b/fs/befs/ChangeLog @@ -365,7 +365,7 @@ Version 0.4 (2001-10-28) (fs/befs/super.c) * Tell the kernel to only mount befs read-only. - By setting the MS_RDONLY flag in befs_read_super(). + By setting the SB_RDONLY flag in befs_read_super(). Not that it was possible to write before. But now the kernel won't even try. (fs/befs/super.c) diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index a92355cc453b..ee236231cafa 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -841,7 +841,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent) if (!sb_rdonly(sb)) { befs_warning(sb, "No write support. Marking filesystem read-only"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } /* @@ -948,7 +948,7 @@ static int befs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - if (!(*flags & MS_RDONLY)) + if (!(*flags & SB_RDONLY)) return -EINVAL; return 0; } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b35ce16b3df3..5982c8a71f02 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -295,7 +295,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, unsigned long len, u64 disk_start, unsigned long compressed_len, struct page **compressed_pages, - unsigned long nr_pages) + unsigned long nr_pages, + unsigned int write_flags) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct bio *bio = NULL; @@ -327,7 +328,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, bdev = fs_info->fs_devices->latest_bdev; bio = btrfs_bio_alloc(bdev, first_byte); - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + bio->bi_opf = REQ_OP_WRITE | write_flags; bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; refcount_set(&cb->pending_bios, 1); @@ -374,7 +375,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, bio_put(bio); bio = btrfs_bio_alloc(bdev, first_byte); - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + bio->bi_opf = REQ_OP_WRITE | write_flags; bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; bio_add_page(bio, page, PAGE_SIZE, 0); @@ -1528,5 +1529,5 @@ unsigned int btrfs_compress_str2level(const char *str) if (str[4] == ':' && '1' <= str[5] && str[5] <= '9' && str[6] == 0) return str[5] - '0'; - return 0; + return BTRFS_ZLIB_DEFAULT_LEVEL; } diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index da20755ebf21..0868cc554f14 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -34,6 +34,8 @@ /* Maximum size of data before compression */ #define BTRFS_MAX_UNCOMPRESSED (SZ_128K) +#define BTRFS_ZLIB_DEFAULT_LEVEL 3 + struct compressed_bio { /* number of bios pending for this compressed extent */ refcount_t pending_bios; @@ -91,7 +93,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, unsigned long len, u64 disk_start, unsigned long compressed_len, struct page **compressed_pages, - unsigned long nr_pages); + unsigned long nr_pages, + unsigned int write_flags); blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 531e0a8645b0..1e74cf826532 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1032,14 +1032,17 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) { ret = btrfs_inc_ref(trans, root, buf, 1); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) { ret = btrfs_dec_ref(trans, root, buf, 0); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; ret = btrfs_inc_ref(trans, root, cow, 1); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; } new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF; } else { @@ -1049,7 +1052,8 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; } if (new_flags != 0) { int level = btrfs_header_level(buf); @@ -1068,9 +1072,11 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; ret = btrfs_dec_ref(trans, root, buf, 1); - BUG_ON(ret); /* -ENOMEM */ + if (ret) + return ret; } clean_tree_block(fs_info, buf); *last_ref = 1; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f7df5536ab61..13c260b525a1 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2957,7 +2957,7 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info) */ static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info) { - return fs_info->sb->s_flags & MS_RDONLY || btrfs_fs_closing(fs_info); + return fs_info->sb->s_flags & SB_RDONLY || btrfs_fs_closing(fs_info); } static inline void free_fs_info(struct btrfs_fs_info *fs_info) @@ -3180,6 +3180,7 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput); int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput, int nr); int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, + unsigned int extra_bits, struct extent_state **cached_state, int dedupe); int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, struct btrfs_root *new_root, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 5d73f79ded8b..056276101c63 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -87,6 +87,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node( spin_lock(&root->inode_lock); node = radix_tree_lookup(&root->delayed_nodes_tree, ino); + if (node) { if (btrfs_inode->delayed_node) { refcount_inc(&node->refs); /* can be accessed */ @@ -94,9 +95,30 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node( spin_unlock(&root->inode_lock); return node; } - btrfs_inode->delayed_node = node; - /* can be accessed and cached in the inode */ - refcount_add(2, &node->refs); + + /* + * It's possible that we're racing into the middle of removing + * this node from the radix tree. In this case, the refcount + * was zero and it should never go back to one. Just return + * NULL like it was never in the radix at all; our release + * function is in the process of removing it. + * + * Some implementations of refcount_inc refuse to bump the + * refcount once it has hit zero. If we don't do this dance + * here, refcount_inc() may decide to just WARN_ONCE() instead + * of actually bumping the refcount. + * + * If this node is properly in the radix, we want to bump the + * refcount twice, once for the inode and once for this get + * operation. + */ + if (refcount_inc_not_zero(&node->refs)) { + refcount_inc(&node->refs); + btrfs_inode->delayed_node = node; + } else { + node = NULL; + } + spin_unlock(&root->inode_lock); return node; } @@ -254,17 +276,18 @@ static void __btrfs_release_delayed_node( mutex_unlock(&delayed_node->mutex); if (refcount_dec_and_test(&delayed_node->refs)) { - bool free = false; struct btrfs_root *root = delayed_node->root; + spin_lock(&root->inode_lock); - if (refcount_read(&delayed_node->refs) == 0) { - radix_tree_delete(&root->delayed_nodes_tree, - delayed_node->inode_id); - free = true; - } + /* + * Once our refcount goes to zero, nobody is allowed to bump it + * back up. We can delete it now. + */ + ASSERT(refcount_read(&delayed_node->refs) == 0); + radix_tree_delete(&root->delayed_nodes_tree, + delayed_node->inode_id); spin_unlock(&root->inode_lock); - if (free) - kmem_cache_free(delayed_node_cache, delayed_node); + kmem_cache_free(delayed_node_cache, delayed_node); } } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index efce9a2fa9be..a8ecccfc36de 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -610,7 +610,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, * that we don't try and read the other copies of this block, just * return -EIO. */ - if (found_level == 0 && btrfs_check_leaf(root, eb)) { + if (found_level == 0 && btrfs_check_leaf_full(root, eb)) { set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); ret = -EIO; } @@ -3231,6 +3231,7 @@ static int write_dev_supers(struct btrfs_device *device, int errors = 0; u32 crc; u64 bytenr; + int op_flags; if (max_mirrors == 0) max_mirrors = BTRFS_SUPER_MIRROR_MAX; @@ -3273,13 +3274,10 @@ static int write_dev_supers(struct btrfs_device *device, * we fua the first super. The others we allow * to go down lazy. */ - if (i == 0) { - ret = btrfsic_submit_bh(REQ_OP_WRITE, - REQ_SYNC | REQ_FUA | REQ_META | REQ_PRIO, bh); - } else { - ret = btrfsic_submit_bh(REQ_OP_WRITE, - REQ_SYNC | REQ_META | REQ_PRIO, bh); - } + op_flags = REQ_SYNC | REQ_META | REQ_PRIO; + if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER)) + op_flags |= REQ_FUA; + ret = btrfsic_submit_bh(REQ_OP_WRITE, op_flags, bh); if (ret) errors++; } @@ -3848,7 +3846,13 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) buf->len, fs_info->dirty_metadata_batch); #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY - if (btrfs_header_level(buf) == 0 && btrfs_check_leaf(root, buf)) { + /* + * Since btrfs_mark_buffer_dirty() can be called with item pointer set + * but item data not updated. + * So here we should only check item pointers, not item data. + */ + if (btrfs_header_level(buf) == 0 && + btrfs_check_leaf_relaxed(root, buf)) { btrfs_print_leaf(buf); ASSERT(0); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 7208ecef7088..2f4328511ac8 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3502,13 +3502,6 @@ again: goto again; } - /* We've already setup this transaction, go ahead and exit */ - if (block_group->cache_generation == trans->transid && - i_size_read(inode)) { - dcs = BTRFS_DC_SETUP; - goto out_put; - } - /* * We want to set the generation to 0, that way if anything goes wrong * from here on out we know not to trust this cache when we load up next @@ -3532,6 +3525,13 @@ again: } WARN_ON(ret); + /* We've already setup this transaction, go ahead and exit */ + if (block_group->cache_generation == trans->transid && + i_size_read(inode)) { + dcs = BTRFS_DC_SETUP; + goto out_put; + } + if (i_size_read(inode) > 0) { ret = btrfs_check_trunc_cache_free_space(fs_info, &fs_info->global_block_rsv); @@ -9206,6 +9206,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, ret = btrfs_del_root(trans, fs_info, &root->root_key); if (ret) { btrfs_abort_transaction(trans, ret); + err = ret; goto out_end_trans; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 16045ea86fc1..012d63870b99 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1984,7 +1984,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, struct btrfs_bio *bbio = NULL; int ret; - ASSERT(!(fs_info->sb->s_flags & MS_RDONLY)); + ASSERT(!(fs_info->sb->s_flags & SB_RDONLY)); BUG_ON(!mirror_num); bio = btrfs_io_bio_alloc(1); @@ -3253,7 +3253,7 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode, delalloc_start, delalloc_end, &page_started, - nr_written); + nr_written, wbc); /* File system has been set read-only */ if (ret) { SetPageError(page); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 4a8861379d3e..93dcae0c3183 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -116,7 +116,8 @@ struct extent_io_ops { */ int (*fill_delalloc)(void *private_data, struct page *locked_page, u64 start, u64 end, int *page_started, - unsigned long *nr_written); + unsigned long *nr_written, + struct writeback_control *wbc); int (*writepage_start_hook)(struct page *page, u64 start, u64 end); void (*writepage_end_io_hook)(struct page *page, u64 start, u64 end, @@ -365,10 +366,11 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state); static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start, - u64 end, struct extent_state **cached_state) + u64 end, unsigned int extra_bits, + struct extent_state **cached_state) { return set_extent_bit(tree, start, end, - EXTENT_DELALLOC | EXTENT_UPTODATE, + EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits, NULL, cached_state, GFP_NOFS); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f80254d82f40..eb1bac7c8553 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -477,6 +477,47 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) } } +static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, + const u64 start, + const u64 len, + struct extent_state **cached_state) +{ + u64 search_start = start; + const u64 end = start + len - 1; + + while (search_start < end) { + const u64 search_len = end - search_start + 1; + struct extent_map *em; + u64 em_len; + int ret = 0; + + em = btrfs_get_extent(inode, NULL, 0, search_start, + search_len, 0); + if (IS_ERR(em)) + return PTR_ERR(em); + + if (em->block_start != EXTENT_MAP_HOLE) + goto next; + + em_len = em->len; + if (em->start < search_start) + em_len -= search_start - em->start; + if (em_len > search_len) + em_len = search_len; + + ret = set_extent_bit(&inode->io_tree, search_start, + search_start + em_len - 1, + EXTENT_DELALLOC_NEW, + NULL, cached_state, GFP_NOFS); +next: + search_start = extent_map_end(em); + free_extent_map(em); + if (ret) + return ret; + } + return 0; +} + /* * after copy_from_user, pages need to be dirtied and we need to make * sure holes are created between the current EOF and the start of @@ -497,14 +538,34 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, u64 end_of_last_block; u64 end_pos = pos + write_bytes; loff_t isize = i_size_read(inode); + unsigned int extra_bits = 0; start_pos = pos & ~((u64) fs_info->sectorsize - 1); num_bytes = round_up(write_bytes + pos - start_pos, fs_info->sectorsize); end_of_last_block = start_pos + num_bytes - 1; + + if (!btrfs_is_free_space_inode(BTRFS_I(inode))) { + if (start_pos >= isize && + !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) { + /* + * There can't be any extents following eof in this case + * so just set the delalloc new bit for the range + * directly. + */ + extra_bits |= EXTENT_DELALLOC_NEW; + } else { + err = btrfs_find_new_delalloc_bytes(BTRFS_I(inode), + start_pos, + num_bytes, cached); + if (err) + return err; + } + } + err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, - cached, 0); + extra_bits, cached, 0); if (err) return err; @@ -1404,47 +1465,6 @@ fail: } -static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, - const u64 start, - const u64 len, - struct extent_state **cached_state) -{ - u64 search_start = start; - const u64 end = start + len - 1; - - while (search_start < end) { - const u64 search_len = end - search_start + 1; - struct extent_map *em; - u64 em_len; - int ret = 0; - - em = btrfs_get_extent(inode, NULL, 0, search_start, - search_len, 0); - if (IS_ERR(em)) - return PTR_ERR(em); - - if (em->block_start != EXTENT_MAP_HOLE) - goto next; - - em_len = em->len; - if (em->start < search_start) - em_len -= search_start - em->start; - if (em_len > search_len) - em_len = search_len; - - ret = set_extent_bit(&inode->io_tree, search_start, - search_start + em_len - 1, - EXTENT_DELALLOC_NEW, - NULL, cached_state, GFP_NOFS); -next: - search_start = extent_map_end(em); - free_extent_map(em); - if (ret) - return ret; - } - return 0; -} - /* * This function locks the extent and properly waits for data=ordered extents * to finish before allowing the pages to be modified if need. @@ -1473,10 +1493,8 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, + round_up(pos + write_bytes - start_pos, fs_info->sectorsize) - 1; - if (start_pos < inode->vfs_inode.i_size || - (inode->flags & BTRFS_INODE_PREALLOC)) { + if (start_pos < inode->vfs_inode.i_size) { struct btrfs_ordered_extent *ordered; - unsigned int clear_bits; lock_extent_bits(&inode->io_tree, start_pos, last_pos, cached_state); @@ -1498,19 +1516,10 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, } if (ordered) btrfs_put_ordered_extent(ordered); - ret = btrfs_find_new_delalloc_bytes(inode, start_pos, - last_pos - start_pos + 1, - cached_state); - clear_bits = EXTENT_DIRTY | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG; - if (ret) - clear_bits |= EXTENT_DELALLOC_NEW | EXTENT_LOCKED; - clear_extent_bit(&inode->io_tree, start_pos, - last_pos, clear_bits, - (clear_bits & EXTENT_LOCKED) ? 1 : 0, - 0, cached_state, GFP_NOFS); - if (ret) - return ret; + clear_extent_bit(&inode->io_tree, start_pos, last_pos, + EXTENT_DIRTY | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, + 0, 0, cached_state, GFP_NOFS); *lockstart = start_pos; *lockend = last_pos; ret = 1; @@ -2048,6 +2057,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) len = (u64)end - (u64)start + 1; trace_btrfs_sync_file(file, datasync); + btrfs_init_log_ctx(&ctx, inode); + /* * We write the dirty pages in the range and wait until they complete * out of the ->i_mutex. If so, we can flush the dirty pages by @@ -2194,8 +2205,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) } trans->sync = true; - btrfs_init_log_ctx(&ctx, inode); - ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx); if (ret < 0) { /* Fallthrough and commit/free transaction. */ @@ -2253,6 +2262,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = btrfs_end_transaction(trans); } out: + ASSERT(list_empty(&ctx.list)); err = file_check_and_advance_wb_err(file); if (!ret) ret = err; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index cdc9f4015ec3..4426d1c73e50 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1264,7 +1264,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, /* Lock all pages first so we can lock the extent safely. */ ret = io_ctl_prepare_pages(io_ctl, inode, 0); if (ret) - goto out; + goto out_unlock; lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, &cached_state); @@ -1358,6 +1358,7 @@ out_nospc_locked: out_nospc: cleanup_write_cache_enospc(inode, io_ctl, &cached_state); +out_unlock: if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) up_write(&block_group->data_rwsem); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b93fe05a39c7..e1a7f3cb5be9 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -378,6 +378,7 @@ struct async_cow { struct page *locked_page; u64 start; u64 end; + unsigned int write_flags; struct list_head extents; struct btrfs_work work; }; @@ -857,7 +858,8 @@ retry: async_extent->ram_size, ins.objectid, ins.offset, async_extent->pages, - async_extent->nr_pages)) { + async_extent->nr_pages, + async_cow->write_flags)) { struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; struct page *p = async_extent->pages[0]; const u64 start = async_extent->start; @@ -1191,7 +1193,8 @@ static noinline void async_cow_free(struct btrfs_work *work) static int cow_file_range_async(struct inode *inode, struct page *locked_page, u64 start, u64 end, int *page_started, - unsigned long *nr_written) + unsigned long *nr_written, + unsigned int write_flags) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct async_cow *async_cow; @@ -1208,6 +1211,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page, async_cow->root = root; async_cow->locked_page = locked_page; async_cow->start = start; + async_cow->write_flags = write_flags; if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS && !btrfs_test_opt(fs_info, FORCE_COMPRESS)) @@ -1577,11 +1581,13 @@ static inline int need_force_cow(struct inode *inode, u64 start, u64 end) */ static int run_delalloc_range(void *private_data, struct page *locked_page, u64 start, u64 end, int *page_started, - unsigned long *nr_written) + unsigned long *nr_written, + struct writeback_control *wbc) { struct inode *inode = private_data; int ret; int force_cow = need_force_cow(inode, start, end); + unsigned int write_flags = wbc_to_write_flags(wbc); if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) { ret = run_delalloc_nocow(inode, locked_page, start, end, @@ -1596,7 +1602,8 @@ static int run_delalloc_range(void *private_data, struct page *locked_page, 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); + page_started, nr_written, + write_flags); } if (ret) btrfs_cleanup_ordered_extents(inode, start, end - start + 1); @@ -2025,11 +2032,12 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans, } int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, + unsigned int extra_bits, struct extent_state **cached_state, int dedupe) { WARN_ON((end & (PAGE_SIZE - 1)) == 0); return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end, - cached_state); + extra_bits, cached_state); } /* see btrfs_writepage_start_hook for details on why this is required */ @@ -2090,7 +2098,7 @@ again: goto out; } - btrfs_set_extent_delalloc(inode, page_start, page_end, &cached_state, + btrfs_set_extent_delalloc(inode, page_start, page_end, 0, &cached_state, 0); ClearPageChecked(page); set_page_dirty(page); @@ -2997,6 +3005,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) compress_type = ordered_extent->compress_type; if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) { BUG_ON(compress_type); + btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset, + ordered_extent->len); ret = btrfs_mark_extent_written(trans, BTRFS_I(inode), ordered_extent->file_offset, ordered_extent->file_offset + @@ -4790,7 +4800,7 @@ again: EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, &cached_state, GFP_NOFS); - ret = btrfs_set_extent_delalloc(inode, block_start, block_end, + ret = btrfs_set_extent_delalloc(inode, block_start, block_end, 0, &cached_state, 0); if (ret) { unlock_extent_cached(io_tree, block_start, block_end, @@ -5438,6 +5448,14 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, goto out_err; btrfs_dir_item_key_to_cpu(path->nodes[0], di, location); + if (location->type != BTRFS_INODE_ITEM_KEY && + location->type != BTRFS_ROOT_ITEM_KEY) { + btrfs_warn(root->fs_info, +"%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location(%llu %u %llu))", + __func__, name, btrfs_ino(BTRFS_I(dir)), + location->objectid, location->type, location->offset); + goto out_err; + } out: btrfs_free_path(path); return ret; @@ -5754,8 +5772,6 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) return inode; } - BUG_ON(location.type != BTRFS_ROOT_ITEM_KEY); - index = srcu_read_lock(&fs_info->subvol_srcu); ret = fixup_tree_root_location(fs_info, dir, dentry, &location, &sub_root); @@ -9150,7 +9166,7 @@ again: EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, &cached_state, GFP_NOFS); - ret = btrfs_set_extent_delalloc(inode, page_start, end, + ret = btrfs_set_extent_delalloc(inode, page_start, end, 0, &cached_state, 0); if (ret) { unlock_extent_cached(io_tree, page_start, page_end, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fd172a93d11a..2ef8acaac688 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1172,7 +1172,7 @@ again: if (!i_done || ret) goto out; - if (!(inode->i_sb->s_flags & MS_ACTIVE)) + if (!(inode->i_sb->s_flags & SB_ACTIVE)) goto out; /* @@ -1333,7 +1333,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, * make sure we stop running if someone unmounts * the FS */ - if (!(inode->i_sb->s_flags & MS_ACTIVE)) + if (!(inode->i_sb->s_flags & SB_ACTIVE)) break; if (btrfs_defrag_cancelled(fs_info)) { @@ -2206,7 +2206,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, if (!path) return -ENOMEM; - ptr = &name[BTRFS_INO_LOOKUP_PATH_MAX]; + ptr = &name[BTRFS_INO_LOOKUP_PATH_MAX - 1]; key.objectid = tree_id; key.type = BTRFS_ROOT_ITEM_KEY; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 4cf2eb67eba6..f0c3f00e97cb 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3268,7 +3268,8 @@ static int relocate_file_extent_cluster(struct inode *inode, nr++; } - btrfs_set_extent_delalloc(inode, page_start, page_end, NULL, 0); + btrfs_set_extent_delalloc(inode, page_start, page_end, 0, NULL, + 0); set_page_dirty(page); unlock_extent(&BTRFS_I(inode)->io_tree, diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index c10e4c70f02d..20d3300bd268 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -3521,7 +3521,40 @@ out: } /* - * Check if ino ino1 is an ancestor of inode ino2 in the given root. + * Check if inode ino2, or any of its ancestors, is inode ino1. + * Return 1 if true, 0 if false and < 0 on error. + */ +static int check_ino_in_path(struct btrfs_root *root, + const u64 ino1, + const u64 ino1_gen, + const u64 ino2, + const u64 ino2_gen, + struct fs_path *fs_path) +{ + u64 ino = ino2; + + if (ino1 == ino2) + return ino1_gen == ino2_gen; + + while (ino > BTRFS_FIRST_FREE_OBJECTID) { + u64 parent; + u64 parent_gen; + int ret; + + fs_path_reset(fs_path); + ret = get_first_ref(root, ino, &parent, &parent_gen, fs_path); + if (ret < 0) + return ret; + if (parent == ino1) + return parent_gen == ino1_gen; + ino = parent; + } + return 0; +} + +/* + * Check if ino ino1 is an ancestor of inode ino2 in the given root for any + * possible path (in case ino2 is not a directory and has multiple hard links). * Return 1 if true, 0 if false and < 0 on error. */ static int is_ancestor(struct btrfs_root *root, @@ -3530,36 +3563,91 @@ static int is_ancestor(struct btrfs_root *root, const u64 ino2, struct fs_path *fs_path) { - u64 ino = ino2; - bool free_path = false; + bool free_fs_path = false; int ret = 0; + struct btrfs_path *path = NULL; + struct btrfs_key key; if (!fs_path) { fs_path = fs_path_alloc(); if (!fs_path) return -ENOMEM; - free_path = true; + free_fs_path = true; } - while (ino > BTRFS_FIRST_FREE_OBJECTID) { - u64 parent; - u64 parent_gen; + path = alloc_path_for_send(); + if (!path) { + ret = -ENOMEM; + goto out; + } - fs_path_reset(fs_path); - ret = get_first_ref(root, ino, &parent, &parent_gen, fs_path); - if (ret < 0) { - if (ret == -ENOENT && ino == ino2) - ret = 0; - goto out; + key.objectid = ino2; + key.type = BTRFS_INODE_REF_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out; + + while (true) { + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + u32 cur_offset = 0; + u32 item_size; + + if (slot >= btrfs_header_nritems(leaf)) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto out; + if (ret > 0) + break; + continue; } - if (parent == ino1) { - ret = parent_gen == ino1_gen ? 1 : 0; - goto out; + + btrfs_item_key_to_cpu(leaf, &key, slot); + if (key.objectid != ino2) + break; + if (key.type != BTRFS_INODE_REF_KEY && + key.type != BTRFS_INODE_EXTREF_KEY) + break; + + item_size = btrfs_item_size_nr(leaf, slot); + while (cur_offset < item_size) { + u64 parent; + u64 parent_gen; + + if (key.type == BTRFS_INODE_EXTREF_KEY) { + unsigned long ptr; + struct btrfs_inode_extref *extref; + + ptr = btrfs_item_ptr_offset(leaf, slot); + extref = (struct btrfs_inode_extref *) + (ptr + cur_offset); + parent = btrfs_inode_extref_parent(leaf, + extref); + cur_offset += sizeof(*extref); + cur_offset += btrfs_inode_extref_name_len(leaf, + extref); + } else { + parent = key.offset; + cur_offset = item_size; + } + + ret = get_inode_info(root, parent, NULL, &parent_gen, + NULL, NULL, NULL, NULL); + if (ret < 0) + goto out; + ret = check_ino_in_path(root, ino1, ino1_gen, + parent, parent_gen, fs_path); + if (ret) + goto out; } - ino = parent; + path->slots[0]++; } + ret = 0; out: - if (free_path) + btrfs_free_path(path); + if (free_fs_path) fs_path_free(fs_path); return ret; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 65af029559b5..3a4dce153645 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -107,7 +107,7 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info) return; if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; btrfs_info(fs_info, "forced readonly"); /* * Note that a running device replace operation is not @@ -137,7 +137,7 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function /* * Special case: if the error is EROFS, and we're already - * under MS_RDONLY, then it is safe here. + * under SB_RDONLY, then it is safe here. */ if (errno == -EROFS && sb_rdonly(sb)) return; @@ -168,7 +168,7 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state); /* Don't go through full error handling during mount */ - if (sb->s_flags & MS_BORN) + if (sb->s_flags & SB_BORN) btrfs_handle_error(fs_info); } @@ -507,9 +507,18 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, token == Opt_compress_force || strncmp(args[0].from, "zlib", 4) == 0) { compress_type = "zlib"; + info->compress_type = BTRFS_COMPRESS_ZLIB; - info->compress_level = - btrfs_compress_str2level(args[0].from); + info->compress_level = BTRFS_ZLIB_DEFAULT_LEVEL; + /* + * args[0] contains uninitialized data since + * for these tokens we don't expect any + * parameter. + */ + if (token != Opt_compress && + token != Opt_compress_force) + info->compress_level = + btrfs_compress_str2level(args[0].from); btrfs_set_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, NODATACOW); btrfs_clear_opt(info->mount_opt, NODATASUM); @@ -625,7 +634,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, break; case Opt_acl: #ifdef CONFIG_BTRFS_FS_POSIX_ACL - info->sb->s_flags |= MS_POSIXACL; + info->sb->s_flags |= SB_POSIXACL; break; #else btrfs_err(info, "support for ACL not compiled in!"); @@ -633,7 +642,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, goto out; #endif case Opt_noacl: - info->sb->s_flags &= ~MS_POSIXACL; + info->sb->s_flags &= ~SB_POSIXACL; break; case Opt_notreelog: btrfs_set_and_info(info, NOTREELOG, @@ -851,7 +860,7 @@ check: /* * Extra check for current option against current flag */ - if (btrfs_test_opt(info, NOLOGREPLAY) && !(new_flags & MS_RDONLY)) { + if (btrfs_test_opt(info, NOLOGREPLAY) && !(new_flags & SB_RDONLY)) { btrfs_err(info, "nologreplay must be used with ro mount option"); ret = -EINVAL; @@ -1147,7 +1156,7 @@ static int btrfs_fill_super(struct super_block *sb, sb->s_xattr = btrfs_xattr_handlers; sb->s_time_gran = 1; #ifdef CONFIG_BTRFS_FS_POSIX_ACL - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; #endif sb->s_flags |= SB_I_VERSION; sb->s_iflags |= SB_I_CGROUPWB; @@ -1180,7 +1189,7 @@ static int btrfs_fill_super(struct super_block *sb, } cleancache_init_fs(sb); - sb->s_flags |= MS_ACTIVE; + sb->s_flags |= SB_ACTIVE; return 0; fail_close: @@ -1277,7 +1286,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",flushoncommit"); if (btrfs_test_opt(info, DISCARD)) seq_puts(seq, ",discard"); - if (!(info->sb->s_flags & MS_POSIXACL)) + if (!(info->sb->s_flags & SB_POSIXACL)) seq_puts(seq, ",noacl"); if (btrfs_test_opt(info, SPACE_CACHE)) seq_puts(seq, ",space_cache"); @@ -1409,11 +1418,11 @@ static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid, mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name, newargs); if (PTR_ERR_OR_ZERO(mnt) == -EBUSY) { - if (flags & MS_RDONLY) { - mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~MS_RDONLY, + if (flags & SB_RDONLY) { + mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~SB_RDONLY, device_name, newargs); } else { - mnt = vfs_kern_mount(&btrfs_fs_type, flags | MS_RDONLY, + mnt = vfs_kern_mount(&btrfs_fs_type, flags | SB_RDONLY, device_name, newargs); if (IS_ERR(mnt)) { root = ERR_CAST(mnt); @@ -1565,7 +1574,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, u64 subvol_objectid = 0; int error = 0; - if (!(flags & MS_RDONLY)) + if (!(flags & SB_RDONLY)) mode |= FMODE_WRITE; error = btrfs_parse_early_options(data, mode, fs_type, @@ -1619,13 +1628,13 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (error) goto error_fs_info; - if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) { + if (!(flags & SB_RDONLY) && fs_devices->rw_devices == 0) { error = -EACCES; goto error_close_devices; } bdev = fs_devices->latest_bdev; - s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC, + s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | SB_NOSEC, fs_info); if (IS_ERR(s)) { error = PTR_ERR(s); @@ -1635,7 +1644,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (s->s_root) { btrfs_close_devices(fs_devices); free_fs_info(fs_info); - if ((flags ^ s->s_flags) & MS_RDONLY) + if ((flags ^ s->s_flags) & SB_RDONLY) error = -EBUSY; } else { snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); @@ -1702,11 +1711,11 @@ static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info, { if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) && (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) || - (flags & MS_RDONLY))) { + (flags & SB_RDONLY))) { /* wait for any defraggers to finish */ wait_event(fs_info->transaction_wait, (atomic_read(&fs_info->defrag_running) == 0)); - if (flags & MS_RDONLY) + if (flags & SB_RDONLY) sync_filesystem(fs_info->sb); } } @@ -1766,10 +1775,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) btrfs_resize_thread_pool(fs_info, fs_info->thread_pool_size, old_thread_pool_size); - if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) + if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) goto out; - if (*flags & MS_RDONLY) { + if (*flags & SB_RDONLY) { /* * this also happens on 'umount -rf' or on shutdown, when * the filesystem is busy. @@ -1781,10 +1790,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) /* avoid complains from lockdep et al. */ up(&fs_info->uuid_tree_rescan_sem); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; /* - * Setting MS_RDONLY will put the cleaner thread to + * Setting SB_RDONLY will put the cleaner thread to * sleep at the next loop if it's already active. * If it's already asleep, we'll leave unused block * groups on disk until we're mounted read-write again @@ -1856,7 +1865,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) goto restore; } } - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; set_bit(BTRFS_FS_OPEN, &fs_info->flags); } @@ -1866,9 +1875,9 @@ out: return 0; restore: - /* We've hit an error - don't reset MS_RDONLY */ + /* We've hit an error - don't reset SB_RDONLY */ if (sb_rdonly(sb)) - old_flags |= MS_RDONLY; + old_flags |= SB_RDONLY; sb->s_flags = old_flags; fs_info->mount_opt = old_opts; fs_info->compress_type = old_compress_type; diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index d06b1c931d05..2e7f64a3b22b 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -114,7 +114,7 @@ static int test_find_delalloc(u32 sectorsize) * |--- delalloc ---| * |--- search ---| */ - set_extent_delalloc(&tmp, 0, sectorsize - 1, NULL); + set_extent_delalloc(&tmp, 0, sectorsize - 1, 0, NULL); start = 0; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -145,7 +145,7 @@ static int test_find_delalloc(u32 sectorsize) test_msg("Couldn't find the locked page\n"); goto out_bits; } - set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, NULL); + set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, 0, NULL); start = test_start; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -200,7 +200,7 @@ static int test_find_delalloc(u32 sectorsize) * * We are re-using our test_start from above since it works out well. */ - set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL); + set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, 0, NULL); start = test_start; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index f797642c013d..30affb60da51 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -968,7 +968,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) btrfs_test_inode_set_ops(inode); /* [BTRFS_MAX_EXTENT_SIZE] */ - ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1, + ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1, 0, NULL, 0); if (ret) { test_msg("btrfs_set_extent_delalloc returned %d\n", ret); @@ -984,7 +984,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */ ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE, BTRFS_MAX_EXTENT_SIZE + sectorsize - 1, - NULL, 0); + 0, NULL, 0); if (ret) { test_msg("btrfs_set_extent_delalloc returned %d\n", ret); goto out; @@ -1018,7 +1018,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1, (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1, - NULL, 0); + 0, NULL, 0); if (ret) { test_msg("btrfs_set_extent_delalloc returned %d\n", ret); goto out; @@ -1036,7 +1036,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize, (BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1, - NULL, 0); + 0, NULL, 0); if (ret) { test_msg("btrfs_set_extent_delalloc returned %d\n", ret); goto out; @@ -1053,7 +1053,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) */ ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + sectorsize, - BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL, 0); + BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL, 0); if (ret) { test_msg("btrfs_set_extent_delalloc returned %d\n", ret); goto out; @@ -1089,7 +1089,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) */ ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + sectorsize, - BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL, 0); + BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL, 0); if (ret) { test_msg("btrfs_set_extent_delalloc returned %d\n", ret); goto out; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 114fc5f0ecc5..ce4ed6ec8f39 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -242,7 +242,8 @@ static int check_leaf_item(struct btrfs_root *root, return ret; } -int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf) +static int check_leaf(struct btrfs_root *root, struct extent_buffer *leaf, + bool check_item_data) { struct btrfs_fs_info *fs_info = root->fs_info; /* No valid key type is 0, so all key should be larger than this key */ @@ -361,10 +362,15 @@ int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf) return -EUCLEAN; } - /* Check if the item size and content meet other criteria */ - ret = check_leaf_item(root, leaf, &key, slot); - if (ret < 0) - return ret; + if (check_item_data) { + /* + * Check if the item size and content meet other + * criteria + */ + ret = check_leaf_item(root, leaf, &key, slot); + if (ret < 0) + return ret; + } prev_key.objectid = key.objectid; prev_key.type = key.type; @@ -374,6 +380,17 @@ int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf) return 0; } +int btrfs_check_leaf_full(struct btrfs_root *root, struct extent_buffer *leaf) +{ + return check_leaf(root, leaf, true); +} + +int btrfs_check_leaf_relaxed(struct btrfs_root *root, + struct extent_buffer *leaf) +{ + return check_leaf(root, leaf, false); +} + int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node) { unsigned long nr = btrfs_header_nritems(node); diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h index 96c486e95d70..3d53e8d6fda0 100644 --- a/fs/btrfs/tree-checker.h +++ b/fs/btrfs/tree-checker.h @@ -20,7 +20,19 @@ #include "ctree.h" #include "extent_io.h" -int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf); +/* + * Comprehensive leaf checker. + * Will check not only the item pointers, but also every possible member + * in item data. + */ +int btrfs_check_leaf_full(struct btrfs_root *root, struct extent_buffer *leaf); + +/* + * Less strict leaf checker. + * Will only check item pointers, not reading item data. + */ +int btrfs_check_leaf_relaxed(struct btrfs_root *root, + struct extent_buffer *leaf); int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node); #endif diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index aa7c71cff575..7bf9b31561db 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4102,7 +4102,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans, if (ordered_io_err) { ctx->io_err = -EIO; - return 0; + return ctx->io_err; } btrfs_init_map_token(&token); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index f1ecb938ba4d..a25684287501 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -189,6 +189,7 @@ static void free_fs_devices(struct btrfs_fs_devices *fs_devices) struct btrfs_device, dev_list); list_del(&device->dev_list); rcu_string_free(device->name); + bio_put(device->flush_bio); kfree(device); } kfree(fs_devices); @@ -236,7 +237,6 @@ static struct btrfs_device *__alloc_device(void) kfree(dev); return ERR_PTR(-ENOMEM); } - bio_get(dev->flush_bio); INIT_LIST_HEAD(&dev->dev_list); INIT_LIST_HEAD(&dev->dev_alloc_list); @@ -578,6 +578,7 @@ static void btrfs_free_stale_device(struct btrfs_device *cur_dev) fs_devs->num_devices--; list_del(&dev->dev_list); rcu_string_free(dev->name); + bio_put(dev->flush_bio); kfree(dev); } break; @@ -630,6 +631,7 @@ static noinline int device_list_add(const char *path, name = rcu_string_strdup(path, GFP_NOFS); if (!name) { + bio_put(device->flush_bio); kfree(device); return -ENOMEM; } @@ -742,6 +744,7 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig) name = rcu_string_strdup(orig_dev->name->str, GFP_KERNEL); if (!name) { + bio_put(device->flush_bio); kfree(device); goto error; } @@ -807,6 +810,7 @@ again: list_del_init(&device->dev_list); fs_devices->num_devices--; rcu_string_free(device->name); + bio_put(device->flush_bio); kfree(device); } @@ -1750,20 +1754,24 @@ static int btrfs_rm_dev_item(struct btrfs_fs_info *fs_info, key.offset = device->devid; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); - if (ret < 0) - goto out; - - if (ret > 0) { - ret = -ENOENT; + if (ret) { + if (ret > 0) + ret = -ENOENT; + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); goto out; } ret = btrfs_del_item(trans, root, path); - if (ret) - goto out; + if (ret) { + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + } + out: btrfs_free_path(path); - btrfs_commit_transaction(trans); + if (!ret) + ret = btrfs_commit_transaction(trans); return ret; } @@ -1993,7 +2001,7 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info, fs_devices = srcdev->fs_devices; list_del_rcu(&srcdev->dev_list); - list_del_rcu(&srcdev->dev_alloc_list); + list_del(&srcdev->dev_alloc_list); fs_devices->num_devices--; if (srcdev->missing) fs_devices->missing_devices--; @@ -2349,6 +2357,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path name = rcu_string_strdup(device_path, GFP_KERNEL); if (!name) { + bio_put(device->flush_bio); kfree(device); ret = -ENOMEM; goto error; @@ -2358,6 +2367,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { rcu_string_free(device->name); + bio_put(device->flush_bio); kfree(device); ret = PTR_ERR(trans); goto error; @@ -2384,7 +2394,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); if (seeding_dev) { - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; ret = btrfs_prepare_sprout(fs_info); if (ret) { btrfs_abort_transaction(trans, ret); @@ -2497,10 +2507,11 @@ error_sysfs: btrfs_sysfs_rm_device_link(fs_info->fs_devices, device); error_trans: if (seeding_dev) - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; if (trans) btrfs_end_transaction(trans); rcu_string_free(device->name); + bio_put(device->flush_bio); kfree(device); error: blkdev_put(bdev, FMODE_EXCL); @@ -2567,6 +2578,7 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, name = rcu_string_strdup(device_path, GFP_KERNEL); if (!name) { + bio_put(device->flush_bio); kfree(device); ret = -ENOMEM; goto error; @@ -6284,6 +6296,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, ret = find_next_devid(fs_info, &tmp); if (ret) { + bio_put(dev->flush_bio); kfree(dev); return ERR_PTR(ret); } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index ab69dcb70e8a..1b468250e947 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1440,6 +1440,29 @@ static int __close_session(struct ceph_mds_client *mdsc, return request_close_session(mdsc, session); } +static bool drop_negative_children(struct dentry *dentry) +{ + struct dentry *child; + bool all_negative = true; + + if (!d_is_dir(dentry)) + goto out; + + spin_lock(&dentry->d_lock); + list_for_each_entry(child, &dentry->d_subdirs, d_child) { + if (d_really_is_positive(child)) { + all_negative = false; + break; + } + } + spin_unlock(&dentry->d_lock); + + if (all_negative) + shrink_dcache_parent(dentry); +out: + return all_negative; +} + /* * Trim old(er) caps. * @@ -1490,16 +1513,27 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) if ((used | wanted) & ~oissued & mine) goto out; /* we need these caps */ - session->s_trim_caps--; if (oissued) { /* we aren't the only cap.. just remove us */ __ceph_remove_cap(cap, true); + session->s_trim_caps--; } else { + struct dentry *dentry; /* try dropping referring dentries */ spin_unlock(&ci->i_ceph_lock); - d_prune_aliases(inode); - dout("trim_caps_cb %p cap %p pruned, count now %d\n", - inode, cap, atomic_read(&inode->i_count)); + dentry = d_find_any_alias(inode); + if (dentry && drop_negative_children(dentry)) { + int count; + dput(dentry); + d_prune_aliases(inode); + count = atomic_read(&inode->i_count); + if (count == 1) + session->s_trim_caps--; + dout("trim_caps_cb %p cap %p pruned, count now %d\n", + inode, cap, count); + } else { + dput(dentry); + } return 0; } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index fe9fbb3f13f7..a62d2a9841dc 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -331,11 +331,11 @@ static int parse_fsopt_token(char *c, void *private) break; #ifdef CONFIG_CEPH_FS_POSIX_ACL case Opt_acl: - fsopt->sb_flags |= MS_POSIXACL; + fsopt->sb_flags |= SB_POSIXACL; break; #endif case Opt_noacl: - fsopt->sb_flags &= ~MS_POSIXACL; + fsopt->sb_flags &= ~SB_POSIXACL; break; default: BUG_ON(token); @@ -520,7 +520,7 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",nopoolperm"); #ifdef CONFIG_CEPH_FS_POSIX_ACL - if (fsopt->sb_flags & MS_POSIXACL) + if (fsopt->sb_flags & SB_POSIXACL) seq_puts(m, ",acl"); else seq_puts(m, ",noacl"); @@ -988,7 +988,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, dout("ceph_mount\n"); #ifdef CONFIG_CEPH_FS_POSIX_ACL - flags |= MS_POSIXACL; + flags |= SB_POSIXACL; #endif err = parse_mount_options(&fsopt, &opt, flags, data, dev_name); if (err < 0) { diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index cbd216b57239..350fa55a1bf7 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -42,7 +42,7 @@ #define CIFS_MOUNT_MULTIUSER 0x20000 /* multiuser mount */ #define CIFS_MOUNT_STRICT_IO 0x40000 /* strict cache mode */ #define CIFS_MOUNT_RWPIDFORWARD 0x80000 /* use pid forwarding for rw */ -#define CIFS_MOUNT_POSIXACL 0x100000 /* mirror of MS_POSIXACL in mnt_cifs_flags */ +#define CIFS_MOUNT_POSIXACL 0x100000 /* mirror of SB_POSIXACL in mnt_cifs_flags */ #define CIFS_MOUNT_CIFS_BACKUPUID 0x200000 /* backup intent bit for a user */ #define CIFS_MOUNT_CIFS_BACKUPGID 0x400000 /* backup intent bit for a group */ #define CIFS_MOUNT_MAP_SFM_CHR 0x800000 /* SFM/MAC mapping for illegal chars */ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8c8b75d33f31..31b7565b1617 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -125,7 +125,7 @@ cifs_read_super(struct super_block *sb) tcon = cifs_sb_master_tcon(cifs_sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL) - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; if (tcon->ses->capabilities & tcon->ses->server->vals->cap_large_files) sb->s_maxbytes = MAX_LFS_FILESIZE; @@ -497,7 +497,7 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_puts(s, ",cifsacl"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) seq_puts(s, ",dynperm"); - if (root->d_sb->s_flags & MS_POSIXACL) + if (root->d_sb->s_flags & SB_POSIXACL) seq_puts(s, ",acl"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) seq_puts(s, ",mfsymlinks"); @@ -573,7 +573,7 @@ static int cifs_show_stats(struct seq_file *s, struct dentry *root) static int cifs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_NODIRATIME; + *flags |= SB_NODIRATIME; return 0; } @@ -708,7 +708,7 @@ cifs_do_mount(struct file_system_type *fs_type, rc = cifs_mount(cifs_sb, volume_info); if (rc) { - if (!(flags & MS_SILENT)) + if (!(flags & SB_SILENT)) cifs_dbg(VFS, "cifs_mount failed w/return code = %d\n", rc); root = ERR_PTR(rc); @@ -720,7 +720,7 @@ cifs_do_mount(struct file_system_type *fs_type, mnt_data.flags = flags; /* BB should we make this contingent on mount parm? */ - flags |= MS_NODIRATIME | MS_NOATIME; + flags |= SB_NODIRATIME | SB_NOATIME; sb = sget(fs_type, cifs_match_super, cifs_set_super, flags, &mnt_data); if (IS_ERR(sb)) { @@ -739,7 +739,7 @@ cifs_do_mount(struct file_system_type *fs_type, goto out_super; } - sb->s_flags |= MS_ACTIVE; + sb->s_flags |= SB_ACTIVE; } root = cifs_get_root(volume_info, sb); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index e185b2853eab..b16583594d1a 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -559,8 +559,8 @@ struct smb_vol { CIFS_MOUNT_MULTIUSER | CIFS_MOUNT_STRICT_IO | \ CIFS_MOUNT_CIFS_BACKUPUID | CIFS_MOUNT_CIFS_BACKUPGID) -#define CIFS_MS_MASK (MS_RDONLY | MS_MANDLOCK | MS_NOEXEC | MS_NOSUID | \ - MS_NODEV | MS_SYNCHRONOUS) +#define CIFS_MS_MASK (SB_RDONLY | SB_MANDLOCK | SB_NOEXEC | SB_NOSUID | \ + SB_NODEV | SB_SYNCHRONOUS) struct cifs_mnt_data { struct cifs_sb_info *cifs_sb; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 7c732cb44164..ecb99079363a 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -985,7 +985,7 @@ retry_iget5_locked: } cifs_fattr_to_inode(inode, fattr); - if (sb->s_flags & MS_NOATIME) + if (sb->s_flags & SB_NOATIME) inode->i_flags |= S_NOATIME | S_NOCMTIME; if (inode->i_state & I_NEW) { inode->i_ino = hash; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index e06740436b92..ed88ab8a4774 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1406,7 +1406,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, } while (rc == -EAGAIN); if (rc) { - cifs_dbg(VFS, "ioctl error in smb2_get_dfs_refer rc=%d\n", rc); + if (rc != -ENOENT) + cifs_dbg(VFS, "ioctl error in smb2_get_dfs_refer rc=%d\n", rc); goto out; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 5331631386a2..01346b8b6edb 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2678,27 +2678,27 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, cifs_small_buf_release(req); rsp = (struct smb2_read_rsp *)rsp_iov.iov_base; - shdr = get_sync_hdr(rsp); - if (shdr->Status == STATUS_END_OF_FILE) { + if (rc) { + if (rc != -ENODATA) { + cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); + cifs_dbg(VFS, "Send error in read = %d\n", rc); + } free_rsp_buf(resp_buftype, rsp_iov.iov_base); - return 0; + return rc == -ENODATA ? 0 : rc; } - if (rc) { - cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); - cifs_dbg(VFS, "Send error in read = %d\n", rc); - } else { - *nbytes = le32_to_cpu(rsp->DataLength); - if ((*nbytes > CIFS_MAX_MSGSIZE) || - (*nbytes > io_parms->length)) { - cifs_dbg(FYI, "bad length %d for count %d\n", - *nbytes, io_parms->length); - rc = -EIO; - *nbytes = 0; - } + *nbytes = le32_to_cpu(rsp->DataLength); + if ((*nbytes > CIFS_MAX_MSGSIZE) || + (*nbytes > io_parms->length)) { + cifs_dbg(FYI, "bad length %d for count %d\n", + *nbytes, io_parms->length); + rc = -EIO; + *nbytes = 0; } + shdr = get_sync_hdr(rsp); + if (*buf) { memcpy(*buf, (char *)shdr + rsp->DataOffset, *nbytes); free_rsp_buf(resp_buftype, rsp_iov.iov_base); diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 52f975d848a0..316af84674f1 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -117,7 +117,7 @@ static int cifs_xattr_set(const struct xattr_handler *handler, #ifdef CONFIG_CIFS_POSIX if (!value) goto out; - if (sb->s_flags & MS_POSIXACL) + if (sb->s_flags & SB_POSIXACL) rc = CIFSSMBSetPosixACL(xid, pTcon, full_path, value, (const int)size, ACL_TYPE_ACCESS, cifs_sb->local_nls, @@ -129,7 +129,7 @@ static int cifs_xattr_set(const struct xattr_handler *handler, #ifdef CONFIG_CIFS_POSIX if (!value) goto out; - if (sb->s_flags & MS_POSIXACL) + if (sb->s_flags & SB_POSIXACL) rc = CIFSSMBSetPosixACL(xid, pTcon, full_path, value, (const int)size, ACL_TYPE_DEFAULT, cifs_sb->local_nls, @@ -266,7 +266,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler, case XATTR_ACL_ACCESS: #ifdef CONFIG_CIFS_POSIX - if (sb->s_flags & MS_POSIXACL) + if (sb->s_flags & SB_POSIXACL) rc = CIFSSMBGetPosixACL(xid, pTcon, full_path, value, size, ACL_TYPE_ACCESS, cifs_sb->local_nls, @@ -276,7 +276,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler, case XATTR_ACL_DEFAULT: #ifdef CONFIG_CIFS_POSIX - if (sb->s_flags & MS_POSIXACL) + if (sb->s_flags & SB_POSIXACL) rc = CIFSSMBGetPosixACL(xid, pTcon, full_path, value, size, ACL_TYPE_DEFAULT, cifs_sb->local_nls, diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 6f0a6a4d5faa..97424cf206c0 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -96,7 +96,7 @@ void coda_destroy_inodecache(void) static int coda_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_NOATIME; + *flags |= SB_NOATIME; return 0; } @@ -188,7 +188,7 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent) mutex_unlock(&vc->vc_mutex); sb->s_fs_info = vc; - sb->s_flags |= MS_NOATIME; + sb->s_flags |= SB_NOATIME; sb->s_blocksize = 4096; /* XXXXX what do we put here?? */ sb->s_blocksize_bits = 12; sb->s_magic = CODA_SUPER_MAGIC; diff --git a/fs/cramfs/Kconfig b/fs/cramfs/Kconfig index f937082f3244..58e2fe40b2a0 100644 --- a/fs/cramfs/Kconfig +++ b/fs/cramfs/Kconfig @@ -34,6 +34,7 @@ config CRAMFS_BLOCKDEV config CRAMFS_MTD bool "Support CramFs image directly mapped in physical memory" depends on CRAMFS && MTD + depends on CRAMFS=m || MTD=y default y if !CRAMFS_BLOCKDEV help This option allows the CramFs driver to load data directly from diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 9a2ab419ba62..017b0ab19bc4 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -505,7 +505,7 @@ static void cramfs_kill_sb(struct super_block *sb) static int cramfs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } @@ -592,7 +592,7 @@ static int cramfs_finalize_super(struct super_block *sb, struct inode *root; /* Set it all up.. */ - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; sb->s_op = &cramfs_ops; root = get_cramfs_inode(sb, cramfs_root, 0); if (IS_ERR(root)) diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index f2677c90d96e..025d66a705db 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -560,8 +560,8 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags * Set the POSIX ACL flag based on whether they're enabled in the lower * mount. */ - s->s_flags = flags & ~MS_POSIXACL; - s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL; + s->s_flags = flags & ~SB_POSIXACL; + s->s_flags |= path.dentry->d_sb->s_flags & SB_POSIXACL; /** * Force a read-only eCryptfs mount when: @@ -569,7 +569,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags * 2) The ecryptfs_encrypted_view mount option is specified */ if (sb_rdonly(path.dentry->d_sb) || mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) - s->s_flags |= MS_RDONLY; + s->s_flags |= SB_RDONLY; s->s_maxbytes = path.dentry->d_sb->s_maxbytes; s->s_blocksize = path.dentry->d_sb->s_blocksize; @@ -602,7 +602,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags ecryptfs_set_dentry_private(s->s_root, root_info); root_info->lower_path = path; - s->s_flags |= MS_ACTIVE; + s->s_flags |= SB_ACTIVE; return dget(s->s_root); out_free: diff --git a/fs/efs/super.c b/fs/efs/super.c index 65b59009555b..6ffb7ba1547a 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -116,7 +116,7 @@ static void destroy_inodecache(void) static int efs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } @@ -311,7 +311,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) #ifdef DEBUG pr_info("forcing read-only mode\n"); #endif - s->s_flags |= MS_RDONLY; + s->s_flags |= SB_RDONLY; } s->s_op = &efs_superblock_operations; s->s_export_op = &efs_export_ops; diff --git a/fs/exec.c b/fs/exec.c index 1d6243d9f2b6..7eb8d21bcab9 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1216,15 +1216,14 @@ killed: return -EAGAIN; } -char *get_task_comm(char *buf, struct task_struct *tsk) +char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk) { - /* buf must be at least sizeof(tsk->comm) in size */ task_lock(tsk); - strncpy(buf, tsk->comm, sizeof(tsk->comm)); + strncpy(buf, tsk->comm, buf_size); task_unlock(tsk); return buf; } -EXPORT_SYMBOL_GPL(get_task_comm); +EXPORT_SYMBOL_GPL(__get_task_comm); /* * These functions flushes out all traces of the currently running executable @@ -1350,9 +1349,14 @@ void setup_new_exec(struct linux_binprm * bprm) current->sas_ss_sp = current->sas_ss_size = 0; - /* Figure out dumpability. */ + /* + * Figure out dumpability. Note that this checking only of current + * is wrong, but userspace depends on it. This should be testing + * bprm->secureexec instead. + */ if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || - bprm->secureexec) + !(uid_eq(current_euid(), current_uid()) && + gid_eq(current_egid(), current_gid()))) set_dumpable(current->mm, suid_dumpable); else set_dumpable(current->mm, SUID_DUMP_USER); diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index e1b3724bebf2..33db13365c5e 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -548,7 +548,7 @@ do_more: } mark_buffer_dirty(bitmap_bh); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) sync_dirty_buffer(bitmap_bh); group_adjust_blocks(sb, block_group, desc, bh2, group_freed); @@ -1424,7 +1424,7 @@ allocated: percpu_counter_sub(&sbi->s_freeblocks_counter, num); mark_buffer_dirty(bitmap_bh); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) sync_dirty_buffer(bitmap_bh); *errp = 0; diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index a1fc3dabca41..6484199b35d1 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -145,7 +145,7 @@ void ext2_free_inode (struct inode * inode) else ext2_release_inode(sb, block_group, is_directory); mark_buffer_dirty(bitmap_bh); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) sync_dirty_buffer(bitmap_bh); brelse(bitmap_bh); @@ -517,7 +517,7 @@ repeat_in_this_group: goto fail; got: mark_buffer_dirty(bitmap_bh); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) sync_dirty_buffer(bitmap_bh); brelse(bitmap_bh); diff --git a/fs/ext2/super.c b/fs/ext2/super.c index e2b6be03e69b..7646818ab266 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -75,7 +75,7 @@ void ext2_error(struct super_block *sb, const char *function, if (test_opt(sb, ERRORS_RO)) { ext2_msg(sb, KERN_CRIT, "error: remounting filesystem read-only"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } } @@ -656,7 +656,7 @@ static int ext2_setup_super (struct super_block * sb, ext2_msg(sb, KERN_ERR, "error: revision level too high, " "forcing read-only mode"); - res = MS_RDONLY; + res = SB_RDONLY; } if (read_only) return res; @@ -924,9 +924,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi->s_resuid = opts.s_resuid; sbi->s_resgid = opts.s_resgid; - sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | + sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | ((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? - MS_POSIXACL : 0); + SB_POSIXACL : 0); sb->s_iflags |= SB_I_CGROUPWB; if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV && @@ -1178,7 +1178,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) ext2_msg(sb, KERN_WARNING, "warning: mounting ext3 filesystem as ext2"); if (ext2_setup_super (sb, es, sb_rdonly(sb))) - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; ext2_write_super(sb); return 0; @@ -1341,9 +1341,9 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data) "dax flag with busy inodes while remounting"); new_opts.s_mount_opt ^= EXT2_MOUNT_DAX; } - if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) + if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) goto out_set; - if (*flags & MS_RDONLY) { + if (*flags & SB_RDONLY) { if (le16_to_cpu(es->s_state) & EXT2_VALID_FS || !(sbi->s_mount_state & EXT2_VALID_FS)) goto out_set; @@ -1379,7 +1379,7 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data) */ sbi->s_mount_state = le16_to_cpu(es->s_state); if (!ext2_setup_super (sb, es, 0)) - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; spin_unlock(&sbi->s_lock); ext2_write_super(sb); @@ -1392,8 +1392,8 @@ out_set: sbi->s_mount_opt = new_opts.s_mount_opt; sbi->s_resuid = new_opts.s_resuid; sbi->s_resgid = new_opts.s_resgid; - sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | - ((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0); + sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | + ((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? SB_POSIXACL : 0); spin_unlock(&sbi->s_lock); return 0; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 07bca11749d4..c941251ac0c0 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4722,6 +4722,7 @@ retry: EXT4_INODE_EOFBLOCKS); } ext4_mark_inode_dirty(handle, inode); + ext4_update_inode_fsync_trans(handle, inode, 1); ret2 = ext4_journal_stop(handle); if (ret2) break; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b4267d72f249..b32cf263750d 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -816,6 +816,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, #ifdef CONFIG_EXT4_FS_POSIX_ACL struct posix_acl *p = get_acl(dir, ACL_TYPE_DEFAULT); + if (IS_ERR(p)) + return ERR_CAST(p); if (p) { int acl_size = p->a_count * sizeof(ext4_acl_entry); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0992d76f7ab1..534a9130f625 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -149,6 +149,15 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, */ int ext4_inode_is_fast_symlink(struct inode *inode) { + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + int ea_blocks = EXT4_I(inode)->i_file_acl ? + EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; + + if (ext4_has_inline_data(inode)) + return 0; + + return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); + } return S_ISLNK(inode->i_mode) && inode->i_size && (inode->i_size < EXT4_N_BLOCKS * 4); } @@ -2742,7 +2751,7 @@ static int ext4_writepages(struct address_space *mapping, * If the filesystem has aborted, it is read-only, so return * right away instead of dumping stack traces later on that * will obscure the real source of the problem. We test - * EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because + * EXT4_MF_FS_ABORTED instead of sb->s_flag's SB_RDONLY because * the latter could be true if the filesystem is mounted * read-only, and in that case, ext4_writepages should * *never* be called, so if that ever happens, we would want @@ -5183,7 +5192,7 @@ static int ext4_do_update_inode(handle_t *handle, ext4_inode_csum_set(inode, raw_inode, ei); spin_unlock(&ei->i_raw_lock); - if (inode->i_sb->s_flags & MS_LAZYTIME) + if (inode->i_sb->s_flags & SB_LAZYTIME) ext4_update_other_inodes_time(inode->i_sb, inode->i_ino, bh->b_data); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 798b3ac680db..e750d68fbcb5 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1399,6 +1399,10 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, "falling back\n")); } nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb); + if (!nblocks) { + ret = NULL; + goto cleanup_and_exit; + } start = EXT4_I(dir)->i_dir_start_lookup; if (start >= nblocks) start = 0; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0556cd036b69..7c46693a14d7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -422,7 +422,7 @@ static void ext4_handle_error(struct super_block *sb) * before ->s_flags update */ smp_wmb(); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } if (test_opt(sb, ERRORS_PANIC)) { if (EXT4_SB(sb)->s_journal && @@ -635,7 +635,7 @@ void __ext4_abort(struct super_block *sb, const char *function, * before ->s_flags update */ smp_wmb(); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; if (EXT4_SB(sb)->s_journal) jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); save_error_info(sb, function, line); @@ -1682,10 +1682,10 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, sb->s_flags |= SB_I_VERSION; return 1; case Opt_lazytime: - sb->s_flags |= MS_LAZYTIME; + sb->s_flags |= SB_LAZYTIME; return 1; case Opt_nolazytime: - sb->s_flags &= ~MS_LAZYTIME; + sb->s_flags &= ~SB_LAZYTIME; return 1; } @@ -2116,7 +2116,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { ext4_msg(sb, KERN_ERR, "revision level too high, " "forcing read-only mode"); - res = MS_RDONLY; + res = SB_RDONLY; } if (read_only) goto done; @@ -2429,7 +2429,7 @@ static void ext4_orphan_cleanup(struct super_block *sb, if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { /* don't clear list on RO mount w/ errors */ - if (es->s_last_orphan && !(s_flags & MS_RDONLY)) { + if (es->s_last_orphan && !(s_flags & SB_RDONLY)) { ext4_msg(sb, KERN_INFO, "Errors on filesystem, " "clearing orphan list.\n"); es->s_last_orphan = 0; @@ -2438,19 +2438,19 @@ static void ext4_orphan_cleanup(struct super_block *sb, return; } - if (s_flags & MS_RDONLY) { + if (s_flags & SB_RDONLY) { ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs"); - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; } #ifdef CONFIG_QUOTA /* Needed for iput() to work correctly and not trash data */ - sb->s_flags |= MS_ACTIVE; + sb->s_flags |= SB_ACTIVE; /* * Turn on quotas which were not enabled for read-only mounts if * filesystem has quota feature, so that they are updated correctly. */ - if (ext4_has_feature_quota(sb) && (s_flags & MS_RDONLY)) { + if (ext4_has_feature_quota(sb) && (s_flags & SB_RDONLY)) { int ret = ext4_enable_quotas(sb); if (!ret) @@ -2539,7 +2539,7 @@ static void ext4_orphan_cleanup(struct super_block *sb, } } #endif - sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + sb->s_flags = s_flags; /* Restore SB_RDONLY status */ } /* @@ -2741,7 +2741,7 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) if (ext4_has_feature_readonly(sb)) { ext4_msg(sb, KERN_INFO, "filesystem is read-only"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; return 1; } @@ -3623,8 +3623,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_iflags |= SB_I_CGROUPWB; } - sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | - (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0); + sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | + (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV && (ext4_has_compat_features(sb) || @@ -4199,7 +4199,7 @@ no_journal: } if (ext4_setup_super(sb, es, sb_rdonly(sb))) - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; /* determine the minimum size of new large inodes, if present */ if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE && @@ -4693,7 +4693,7 @@ static int ext4_commit_super(struct super_block *sb, int sync) * the clock is set in the future, and this will cause e2fsck * to complain and force a full file system check. */ - if (!(sb->s_flags & MS_RDONLY)) + if (!(sb->s_flags & SB_RDONLY)) es->s_wtime = cpu_to_le32(get_seconds()); if (sb->s_bdev->bd_part) es->s_kbytes_written = @@ -5047,8 +5047,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) ext4_abort(sb, "Abort forced by user"); - sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | - (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0); + sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | + (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); es = sbi->s_es; @@ -5057,16 +5057,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); } - if (*flags & MS_LAZYTIME) - sb->s_flags |= MS_LAZYTIME; + if (*flags & SB_LAZYTIME) + sb->s_flags |= SB_LAZYTIME; - if ((bool)(*flags & MS_RDONLY) != sb_rdonly(sb)) { + if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) { err = -EROFS; goto restore_opts; } - if (*flags & MS_RDONLY) { + if (*flags & SB_RDONLY) { err = sync_filesystem(sb); if (err < 0) goto restore_opts; @@ -5078,7 +5078,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) * First of all, the unconditional stuff we have to do * to disable replay of the journal when we next remount */ - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; /* * OK, test if we are remounting a valid rw partition @@ -5140,7 +5140,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_clear_journal_err(sb, es); sbi->s_mount_state = le16_to_cpu(es->s_state); if (!ext4_setup_super(sb, es, 0)) - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; if (ext4_has_feature_mmp(sb)) if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block))) { @@ -5164,7 +5164,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } ext4_setup_system_zone(sb); - if (sbi->s_journal == NULL && !(old_sb_flags & MS_RDONLY)) + if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) ext4_commit_super(sb, 1); #ifdef CONFIG_QUOTA @@ -5182,7 +5182,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } #endif - *flags = (*flags & ~MS_LAZYTIME) | (sb->s_flags & MS_LAZYTIME); + *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME); ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data); kfree(orig_data); return 0; diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index dd2e73e10857..4aa69bc1c70a 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -617,17 +617,17 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG)) return 0; - if (s_flags & MS_RDONLY) { + if (s_flags & SB_RDONLY) { f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs"); - sbi->sb->s_flags &= ~MS_RDONLY; + sbi->sb->s_flags &= ~SB_RDONLY; } #ifdef CONFIG_QUOTA /* Needed for iput() to work correctly and not trash data */ - sbi->sb->s_flags |= MS_ACTIVE; + sbi->sb->s_flags |= SB_ACTIVE; /* Turn on quotas so that they are updated correctly */ - quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY); + quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY); #endif start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); @@ -658,7 +658,7 @@ out: if (quota_enabled) f2fs_quota_off_umount(sbi->sb); #endif - sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */ return err; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index f4e094e816c6..6abf26c31d01 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2378,7 +2378,7 @@ static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) static inline int f2fs_readonly(struct super_block *sb) { - return sb->s_flags & MS_RDONLY; + return sb->s_flags & SB_RDONLY; } static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 5d5bba462f26..d844dcb80570 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1005,7 +1005,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, cpc.reason = __get_cp_reason(sbi); gc_more: - if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) { + if (unlikely(!(sbi->sb->s_flags & SB_ACTIVE))) { ret = -EINVAL; goto stop; } diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 92c57ace1939..b3a14b0429f2 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -598,16 +598,16 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) int quota_enabled; #endif - if (s_flags & MS_RDONLY) { + if (s_flags & SB_RDONLY) { f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs"); - sbi->sb->s_flags &= ~MS_RDONLY; + sbi->sb->s_flags &= ~SB_RDONLY; } #ifdef CONFIG_QUOTA /* Needed for iput() to work correctly and not trash data */ - sbi->sb->s_flags |= MS_ACTIVE; + sbi->sb->s_flags |= SB_ACTIVE; /* Turn on quotas so that they are updated correctly */ - quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY); + quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY); #endif fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry", @@ -671,7 +671,7 @@ out: if (quota_enabled) f2fs_quota_off_umount(sbi->sb); #endif - sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */ return ret ? ret: err; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index a6c5dd450002..708155d9c2e4 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -534,10 +534,10 @@ static int parse_options(struct super_block *sb, char *options) #endif break; case Opt_lazytime: - sb->s_flags |= MS_LAZYTIME; + sb->s_flags |= SB_LAZYTIME; break; case Opt_nolazytime: - sb->s_flags &= ~MS_LAZYTIME; + sb->s_flags &= ~SB_LAZYTIME; break; #ifdef CONFIG_QUOTA case Opt_quota: @@ -1168,7 +1168,7 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, INLINE_DENTRY); set_opt(sbi, EXTENT_CACHE); set_opt(sbi, NOHEAP); - sbi->sb->s_flags |= MS_LAZYTIME; + sbi->sb->s_flags |= SB_LAZYTIME; set_opt(sbi, FLUSH_MERGE); if (f2fs_sb_mounted_blkzoned(sbi->sb)) { set_opt_mode(sbi, F2FS_MOUNT_LFS); @@ -1236,7 +1236,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) #endif /* recover superblocks we couldn't write due to previous RO mount */ - if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) { + if (!(*flags & SB_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) { err = f2fs_commit_super(sbi, false); f2fs_msg(sb, KERN_INFO, "Try to recover all the superblocks, ret: %d", err); @@ -1255,17 +1255,17 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) * Previous and new state of filesystem is RO, * so skip checking GC and FLUSH_MERGE conditions. */ - if (f2fs_readonly(sb) && (*flags & MS_RDONLY)) + if (f2fs_readonly(sb) && (*flags & SB_RDONLY)) goto skip; #ifdef CONFIG_QUOTA - if (!f2fs_readonly(sb) && (*flags & MS_RDONLY)) { + if (!f2fs_readonly(sb) && (*flags & SB_RDONLY)) { err = dquot_suspend(sb, -1); if (err < 0) goto restore_opts; } else { /* dquot_resume needs RW */ - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; if (sb_any_quota_suspended(sb)) { dquot_resume(sb, -1); } else if (f2fs_sb_has_quota_ino(sb)) { @@ -1288,7 +1288,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) * or if background_gc = off is passed in mount * option. Also sync the filesystem. */ - if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) { + if ((*flags & SB_RDONLY) || !test_opt(sbi, BG_GC)) { if (sbi->gc_thread) { stop_gc_thread(sbi); need_restart_gc = true; @@ -1300,7 +1300,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) need_stop_gc = true; } - if (*flags & MS_RDONLY) { + if (*flags & SB_RDONLY) { writeback_inodes_sb(sb, WB_REASON_SYNC); sync_inodes_sb(sb); @@ -1314,7 +1314,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) * We stop issue flush thread if FS is mounted as RO * or if flush_merge is not passed in mount option. */ - if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) { + if ((*flags & SB_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) { clear_opt(sbi, FLUSH_MERGE); destroy_flush_cmd_control(sbi, false); } else { @@ -1329,8 +1329,8 @@ skip: kfree(s_qf_names[i]); #endif /* Update the POSIXACL Flag */ - sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | - (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); + sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | + (test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0); return 0; restore_gc: @@ -2472,8 +2472,8 @@ try_onemore: sb->s_export_op = &f2fs_export_ops; sb->s_magic = F2FS_SUPER_MAGIC; sb->s_time_gran = 1; - sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | - (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); + sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | + (test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0); memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid)); /* init f2fs-specific super block info */ diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 48b2336692f9..bac10de678cc 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -392,7 +392,7 @@ static int fat_mirror_bhs(struct super_block *sb, struct buffer_head **bhs, memcpy(c_bh->b_data, bhs[n]->b_data, sb->s_blocksize); set_buffer_uptodate(c_bh); mark_buffer_dirty_inode(c_bh, sbi->fat_inode); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) err = sync_dirty_buffer(c_bh); brelse(c_bh); if (err) @@ -597,7 +597,7 @@ int fat_free_clusters(struct inode *inode, int cluster) } if (nr_bhs + fatent.nr_bhs > MAX_BUF_PER_PAGE) { - if (sb->s_flags & MS_SYNCHRONOUS) { + if (sb->s_flags & SB_SYNCHRONOUS) { err = fat_sync_bhs(bhs, nr_bhs); if (err) goto error; @@ -612,7 +612,7 @@ int fat_free_clusters(struct inode *inode, int cluster) fat_collect_bhs(bhs, &nr_bhs, &fatent); } while (cluster != FAT_ENT_EOF); - if (sb->s_flags & MS_SYNCHRONOUS) { + if (sb->s_flags & SB_SYNCHRONOUS) { err = fat_sync_bhs(bhs, nr_bhs); if (err) goto error; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 30c52394a7ad..20a0a89eaca5 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -779,14 +779,14 @@ static void __exit fat_destroy_inodecache(void) static int fat_remount(struct super_block *sb, int *flags, char *data) { - int new_rdonly; + bool new_rdonly; struct msdos_sb_info *sbi = MSDOS_SB(sb); - *flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME); + *flags |= SB_NODIRATIME | (sbi->options.isvfat ? 0 : SB_NOATIME); sync_filesystem(sb); /* make sure we update state on remount. */ - new_rdonly = *flags & MS_RDONLY; + new_rdonly = *flags & SB_RDONLY; if (new_rdonly != sb_rdonly(sb)) { if (new_rdonly) fat_set_state(sb, 0, 0); @@ -1352,7 +1352,7 @@ out: if (opts->unicode_xlate) opts->utf8 = 0; if (opts->nfs == FAT_NFS_NOSTALE_RO) { - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; sb->s_export_op = &fat_export_ops_nostale; } @@ -1608,7 +1608,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, return -ENOMEM; sb->s_fs_info = sbi; - sb->s_flags |= MS_NODIRATIME; + sb->s_flags |= SB_NODIRATIME; sb->s_magic = MSDOS_SUPER_MAGIC; sb->s_op = &fat_sops; sb->s_export_op = &fat_export_ops; diff --git a/fs/fat/misc.c b/fs/fat/misc.c index acc3aa30ee54..f9bdc1e01c98 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -33,7 +33,7 @@ void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...) if (opts->errors == FAT_ERRORS_PANIC) panic("FAT-fs (%s): fs panic from previous error\n", sb->s_id); else if (opts->errors == FAT_ERRORS_RO && !sb_rdonly(sb)) { - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; fat_msg(sb, KERN_ERR, "Filesystem has been set read-only"); } } diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index 7d6a105d601b..d24d2758a363 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -646,7 +646,7 @@ static void setup(struct super_block *sb) { MSDOS_SB(sb)->dir_ops = &msdos_dir_inode_operations; sb->s_d_op = &msdos_dentry_operations; - sb->s_flags |= MS_NOATIME; + sb->s_flags |= SB_NOATIME; } static int msdos_fill_super(struct super_block *sb, void *data, int silent) diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c index 455ce5b77e9b..f989efa051a0 100644 --- a/fs/freevxfs/vxfs_super.c +++ b/fs/freevxfs/vxfs_super.c @@ -116,7 +116,7 @@ vxfs_statfs(struct dentry *dentry, struct kstatfs *bufp) static int vxfs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } @@ -220,7 +220,7 @@ static int vxfs_fill_super(struct super_block *sbp, void *dp, int silent) int ret = -EINVAL; u32 j; - sbp->s_flags |= MS_RDONLY; + sbp->s_flags |= SB_RDONLY; infp = kzalloc(sizeof(*infp), GFP_KERNEL); if (!infp) { diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 08f5debd07d1..cea4836385b7 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -490,7 +490,7 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); - if (!(inode->i_sb->s_flags & MS_ACTIVE) || + if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING) || inode_to_wb(inode) == isw->new_wb) { spin_unlock(&inode->i_lock); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 2f504d615d92..624f18bbfd2b 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -130,7 +130,7 @@ static void fuse_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); - if (inode->i_sb->s_flags & MS_ACTIVE) { + if (inode->i_sb->s_flags & SB_ACTIVE) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); fuse_queue_forget(fc, fi->forget, fi->nodeid, fi->nlookup); @@ -141,7 +141,7 @@ static void fuse_evict_inode(struct inode *inode) static int fuse_remount_fs(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - if (*flags & MS_MANDLOCK) + if (*flags & SB_MANDLOCK) return -EINVAL; return 0; @@ -1056,10 +1056,10 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) int is_bdev = sb->s_bdev != NULL; err = -EINVAL; - if (sb->s_flags & MS_MANDLOCK) + if (sb->s_flags & SB_MANDLOCK) goto err; - sb->s_flags &= ~(MS_NOSEC | SB_I_VERSION); + sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION); if (!parse_fuse_opt(data, &d, is_bdev)) goto err; @@ -1109,9 +1109,9 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) goto err_dev_free; /* Handle umasking inside the fuse code */ - if (sb->s_flags & MS_POSIXACL) + if (sb->s_flags & SB_POSIXACL) fc->dont_mask = 1; - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; fc->default_permissions = d.default_permissions; fc->allow_other = d.allow_other; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index a3711f543405..ad55eb86a250 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1065,15 +1065,15 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent sdp->sd_args = *args; if (sdp->sd_args.ar_spectator) { - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; set_bit(SDF_RORECOVERY, &sdp->sd_flags); } if (sdp->sd_args.ar_posix_acl) - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; if (sdp->sd_args.ar_nobarrier) set_bit(SDF_NOBARRIERS, &sdp->sd_flags); - sb->s_flags |= MS_NOSEC; + sb->s_flags |= SB_NOSEC; sb->s_magic = GFS2_MAGIC; sb->s_op = &gfs2_super_ops; sb->s_d_op = &gfs2_dops; @@ -1257,7 +1257,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, struct gfs2_args args; struct gfs2_sbd *sdp; - if (!(flags & MS_RDONLY)) + if (!(flags & SB_RDONLY)) mode |= FMODE_WRITE; bdev = blkdev_get_by_path(dev_name, mode, fs_type); @@ -1313,15 +1313,15 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, if (s->s_root) { error = -EBUSY; - if ((flags ^ s->s_flags) & MS_RDONLY) + if ((flags ^ s->s_flags) & SB_RDONLY) goto error_super; } else { snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); sb_set_blocksize(s, block_size(bdev)); - error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0); + error = fill_super(s, &args, flags & SB_SILENT ? 1 : 0); if (error) goto error_super; - s->s_flags |= MS_ACTIVE; + s->s_flags |= SB_ACTIVE; bdev->bd_super = s; } @@ -1365,7 +1365,7 @@ static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type, pr_warn("gfs2 mount does not exist\n"); return ERR_CAST(s); } - if ((flags ^ s->s_flags) & MS_RDONLY) { + if ((flags ^ s->s_flags) & SB_RDONLY) { deactivate_locked_super(s); return ERR_PTR(-EBUSY); } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 9cb5c9a97d69..d81d46e19726 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1256,10 +1256,10 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) return -EINVAL; if (sdp->sd_args.ar_spectator) - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; - if ((sb->s_flags ^ *flags) & MS_RDONLY) { - if (*flags & MS_RDONLY) + if ((sb->s_flags ^ *flags) & SB_RDONLY) { + if (*flags & SB_RDONLY) error = gfs2_make_fs_ro(sdp); else error = gfs2_make_fs_rw(sdp); @@ -1269,9 +1269,9 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) sdp->sd_args = args; if (sdp->sd_args.ar_posix_acl) - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; else - sb->s_flags &= ~MS_POSIXACL; + sb->s_flags &= ~SB_POSIXACL; if (sdp->sd_args.ar_nobarrier) set_bit(SDF_NOBARRIERS, &sdp->sd_flags); else diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index a85ca8b2c9ba..ca8b72d0a831 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -117,7 +117,7 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) kfree(tr); up_read(&sdp->sd_log_flush_lock); - if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS) + if (sdp->sd_vfs->s_flags & SB_SYNCHRONOUS) gfs2_log_flush(sdp, NULL, NORMAL_FLUSH); if (alloced) sb_end_intwrite(sdp->sd_vfs); diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 894994d2c885..460281b1299e 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -204,11 +204,11 @@ int hfs_mdb_get(struct super_block *sb) attrib = mdb->drAtrb; if (!(attrib & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. mounting read-only.\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } if ((attrib & cpu_to_be16(HFS_SB_ATTRIB_SLOCK))) { pr_warn("filesystem is marked locked, mounting read-only.\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } if (!sb_rdonly(sb)) { /* Mark the volume uncleanly unmounted in case we crash */ diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 7e0d65e9586c..173876782f73 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -114,18 +114,18 @@ static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf) static int hfs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_NODIRATIME; - if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) + *flags |= SB_NODIRATIME; + if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) return 0; - if (!(*flags & MS_RDONLY)) { + if (!(*flags & SB_RDONLY)) { if (!(HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. leaving read-only.\n"); - sb->s_flags |= MS_RDONLY; - *flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; + *flags |= SB_RDONLY; } else if (HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_SLOCK)) { pr_warn("filesystem is marked locked, leaving read-only.\n"); - sb->s_flags |= MS_RDONLY; - *flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; + *flags |= SB_RDONLY; } } return 0; @@ -407,7 +407,7 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &hfs_super_operations; sb->s_xattr = hfs_xattr_handlers; - sb->s_flags |= MS_NODIRATIME; + sb->s_flags |= SB_NODIRATIME; mutex_init(&sbi->bitmap_lock); res = hfs_mdb_get(sb); diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index e5bb2de2262a..1d458b716957 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -329,9 +329,9 @@ static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf) static int hfsplus_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) + if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) return 0; - if (!(*flags & MS_RDONLY)) { + if (!(*flags & SB_RDONLY)) { struct hfsplus_vh *vhdr = HFSPLUS_SB(sb)->s_vhdr; int force = 0; @@ -340,20 +340,20 @@ static int hfsplus_remount(struct super_block *sb, int *flags, char *data) if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) { pr_warn("filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. leaving read-only.\n"); - sb->s_flags |= MS_RDONLY; - *flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; + *flags |= SB_RDONLY; } else if (force) { /* nothing */ } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) { pr_warn("filesystem is marked locked, leaving read-only.\n"); - sb->s_flags |= MS_RDONLY; - *flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; + *flags |= SB_RDONLY; } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) { pr_warn("filesystem is marked journaled, leaving read-only.\n"); - sb->s_flags |= MS_RDONLY; - *flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; + *flags |= SB_RDONLY; } } return 0; @@ -455,16 +455,16 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) { pr_warn("Filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. mounting read-only.\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } else if (test_and_clear_bit(HFSPLUS_SB_FORCE, &sbi->flags)) { /* nothing */ } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) { pr_warn("Filesystem is marked locked, mounting read-only.\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } else if ((vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) && !sb_rdonly(sb)) { pr_warn("write access to a journaled filesystem is not supported, use the force option at your own risk, mounting read-only.\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } err = -EINVAL; diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c index 8d6b7e35faf9..c83ece7facc5 100644 --- a/fs/hpfs/dir.c +++ b/fs/hpfs/dir.c @@ -150,7 +150,6 @@ static int hpfs_readdir(struct file *file, struct dir_context *ctx) if (unlikely(ret < 0)) goto out; ctx->pos = ((loff_t) hpfs_de_as_down_as_possible(inode->i_sb, hpfs_inode->i_dno) << 4) + 1; - file->f_version = inode->i_version; } next_pos = ctx->pos; if (!(de = map_pos_dirent(inode, &next_pos, &qbh))) { diff --git a/fs/hpfs/dnode.c b/fs/hpfs/dnode.c index 3b834563b1f1..a4ad18afbdec 100644 --- a/fs/hpfs/dnode.c +++ b/fs/hpfs/dnode.c @@ -419,7 +419,6 @@ int hpfs_add_dirent(struct inode *i, c = 1; goto ret; } - i->i_version++; c = hpfs_add_to_dnode(i, dno, name, namelen, new_de, 0); ret: return c; @@ -726,7 +725,6 @@ int hpfs_remove_dirent(struct inode *i, dnode_secno dno, struct hpfs_dirent *de, return 2; } } - i->i_version++; for_all_poss(i, hpfs_pos_del, (t = get_pos(dnode, de)) + 1, 1); hpfs_delete_de(i->i_sb, dnode, de); hpfs_mark_4buffers_dirty(qbh); diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c index e0e60b148400..7c49f1ef0c85 100644 --- a/fs/hpfs/map.c +++ b/fs/hpfs/map.c @@ -288,7 +288,7 @@ struct dnode *hpfs_map_dnode(struct super_block *s, unsigned secno, goto bail; } if (((31 + de->namelen + de->down*4 + 3) & ~3) != le16_to_cpu(de->length)) { - if (((31 + de->namelen + de->down*4 + 3) & ~3) < le16_to_cpu(de->length) && s->s_flags & MS_RDONLY) goto ok; + if (((31 + de->namelen + de->down*4 + 3) & ~3) < le16_to_cpu(de->length) && s->s_flags & SB_RDONLY) goto ok; hpfs_error(s, "namelen does not match dirent size in dnode %08x, dirent %03x, last %03x", secno, p, pp); goto bail; } diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 1516fb4e28f4..f2c3ebcd309c 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -78,7 +78,7 @@ void hpfs_error(struct super_block *s, const char *fmt, ...) else { pr_cont("; remounting read-only\n"); mark_dirty(s, 0); - s->s_flags |= MS_RDONLY; + s->s_flags |= SB_RDONLY; } } else if (sb_rdonly(s)) pr_cont("; going on - but anything won't be destroyed because it's read-only\n"); @@ -235,7 +235,6 @@ static struct inode *hpfs_alloc_inode(struct super_block *sb) ei = kmem_cache_alloc(hpfs_inode_cachep, GFP_NOFS); if (!ei) return NULL; - ei->vfs_inode.i_version = 1; return &ei->vfs_inode; } @@ -457,7 +456,7 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data) sync_filesystem(s); - *flags |= MS_NOATIME; + *flags |= SB_NOATIME; hpfs_lock(s); uid = sbi->sb_uid; gid = sbi->sb_gid; @@ -488,7 +487,7 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data) sbi->sb_eas = eas; sbi->sb_chk = chk; sbi->sb_chkdsk = chkdsk; sbi->sb_err = errs; sbi->sb_timeshift = timeshift; - if (!(*flags & MS_RDONLY)) mark_dirty(s, 1); + if (!(*flags & SB_RDONLY)) mark_dirty(s, 1); hpfs_unlock(s); return 0; @@ -614,7 +613,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) goto bail4; } - s->s_flags |= MS_NOATIME; + s->s_flags |= SB_NOATIME; /* Fill superblock stuff */ s->s_magic = HPFS_SUPER_MAGIC; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 1e76730aac0d..8a85f3f53446 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -639,11 +639,11 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, mutex_unlock(&hugetlb_fault_mutex_table[hash]); /* - * page_put due to reference from alloc_huge_page() * unlock_page because locked by add_to_page_cache() + * page_put due to reference from alloc_huge_page() */ - put_page(page); unlock_page(page); + put_page(page); } if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) diff --git a/fs/inode.c b/fs/inode.c index fd401028a309..03102d6ef044 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -416,7 +416,7 @@ void inode_add_lru(struct inode *inode) { if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) && - !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE) + !atomic_read(&inode->i_count) && inode->i_sb->s_flags & SB_ACTIVE) inode_lru_list_add(inode); } @@ -595,7 +595,7 @@ static void dispose_list(struct list_head *head) * @sb: superblock to operate on * * Make sure that no inodes with zero refcount are retained. This is - * called by superblock shutdown after having MS_ACTIVE flag removed, + * called by superblock shutdown after having SB_ACTIVE flag removed, * so any inode reaching zero refcount during or after that call will * be immediately evicted. */ @@ -1492,7 +1492,7 @@ static void iput_final(struct inode *inode) else drop = generic_drop_inode(inode); - if (!drop && (sb->s_flags & MS_ACTIVE)) { + if (!drop && (sb->s_flags & SB_ACTIVE)) { inode_add_lru(inode); spin_unlock(&inode->i_lock); return; @@ -1644,7 +1644,7 @@ int generic_update_time(struct inode *inode, struct timespec *time, int flags) if (flags & S_MTIME) inode->i_mtime = *time; - if (!(inode->i_sb->s_flags & MS_LAZYTIME) || (flags & S_VERSION)) + if (!(inode->i_sb->s_flags & SB_LAZYTIME) || (flags & S_VERSION)) iflags |= I_DIRTY_SYNC; __mark_inode_dirty(inode, iflags); return 0; @@ -1691,7 +1691,7 @@ bool __atime_needs_update(const struct path *path, struct inode *inode, if (IS_NOATIME(inode)) return false; - if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode)) + if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; if (mnt->mnt_flags & MNT_NOATIME) diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 447a24d77b89..bc258a4402f6 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -114,7 +114,7 @@ static void destroy_inodecache(void) static int isofs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - if (!(*flags & MS_RDONLY)) + if (!(*flags & SB_RDONLY)) return -EROFS; return 0; } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index e96c6b05e43e..d8c274d39ddb 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -409,10 +409,10 @@ int jffs2_do_remount_fs(struct super_block *sb, int *flags, char *data) mutex_unlock(&c->alloc_sem); } - if (!(*flags & MS_RDONLY)) + if (!(*flags & SB_RDONLY)) jffs2_start_garbage_collect_thread(c); - *flags |= MS_NOATIME; + *flags |= SB_NOATIME; return 0; } diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index 824e61ede465..c2fbec19c616 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -59,7 +59,7 @@ static inline void jffs2_init_inode_info(struct jffs2_inode_info *f) } -#define jffs2_is_readonly(c) (OFNI_BS_2SFFJ(c)->s_flags & MS_RDONLY) +#define jffs2_is_readonly(c) (OFNI_BS_2SFFJ(c)->s_flags & SB_RDONLY) #define SECTOR_ADDR(x) ( (((unsigned long)(x) / c->sector_size) * c->sector_size) ) #ifndef CONFIG_JFFS2_FS_WRITEBUFFER diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 153f1c6eb169..f60dee7faf03 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -301,10 +301,10 @@ static int jffs2_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &jffs2_super_operations; sb->s_export_op = &jffs2_export_ops; - sb->s_flags = sb->s_flags | MS_NOATIME; + sb->s_flags = sb->s_flags | SB_NOATIME; sb->s_xattr = jffs2_xattr_handlers; #ifdef CONFIG_JFFS2_FS_POSIX_ACL - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; #endif ret = jffs2_do_fill_super(sb, data, silent); return ret; diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 2f7b3af5b8b7..90373aebfdca 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -87,7 +87,7 @@ static void jfs_handle_error(struct super_block *sb) else if (sbi->flag & JFS_ERR_REMOUNT_RO) { jfs_err("ERROR: (device %s): remounting filesystem as read-only", sb->s_id); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } /* nothing is done for continue beyond marking the superblock dirty */ @@ -477,7 +477,7 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data) return rc; } - if (sb_rdonly(sb) && !(*flags & MS_RDONLY)) { + if (sb_rdonly(sb) && !(*flags & SB_RDONLY)) { /* * Invalidate any previously read metadata. fsck may have * changed the on-disk data since we mounted r/o @@ -488,12 +488,12 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data) ret = jfs_mount_rw(sb, 1); /* mark the fs r/w for quota activity */ - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; dquot_resume(sb, -1); return ret; } - if (!sb_rdonly(sb) && (*flags & MS_RDONLY)) { + if (!sb_rdonly(sb) && (*flags & SB_RDONLY)) { rc = dquot_suspend(sb, -1); if (rc < 0) return rc; @@ -545,7 +545,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) sbi->flag = flag; #ifdef CONFIG_JFS_POSIX_ACL - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; #endif if (newLVSize) { diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 95a7c88baed9..26dd9a50f383 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -335,7 +335,7 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, deactivate_locked_super(sb); return ERR_PTR(error); } - sb->s_flags |= MS_ACTIVE; + sb->s_flags |= SB_ACTIVE; mutex_lock(&kernfs_mutex); list_add(&info->node, &root->supers); diff --git a/fs/libfs.c b/fs/libfs.c index 3aabe553fc45..7ff3cb904acd 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -246,7 +246,7 @@ struct dentry *mount_pseudo_xattr(struct file_system_type *fs_type, char *name, struct inode *root; struct qstr d_name = QSTR_INIT(name, strlen(name)); - s = sget_userns(fs_type, NULL, set_anon_super, MS_KERNMOUNT|MS_NOUSER, + s = sget_userns(fs_type, NULL, set_anon_super, SB_KERNMOUNT|SB_NOUSER, &init_user_ns, NULL); if (IS_ERR(s)) return ERR_CAST(s); @@ -277,7 +277,7 @@ struct dentry *mount_pseudo_xattr(struct file_system_type *fs_type, char *name, d_instantiate(dentry, root); s->s_root = dentry; s->s_d_op = dops; - s->s_flags |= MS_ACTIVE; + s->s_flags |= SB_ACTIVE; return dget(s->s_root); Enomem: @@ -578,7 +578,7 @@ int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *c spin_lock(&pin_fs_lock); if (unlikely(!*mount)) { spin_unlock(&pin_fs_lock); - mnt = vfs_kern_mount(type, MS_KERNMOUNT, type->name, NULL); + mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (IS_ERR(mnt)) return PTR_ERR(mnt); spin_lock(&pin_fs_lock); diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 0d4e590e0549..826a89184f90 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -578,8 +578,10 @@ static void nlm_complain_hosts(struct net *net) if (ln->nrhosts == 0) return; - printk(KERN_WARNING "lockd: couldn't shutdown host module for net %p!\n", net); - dprintk("lockd: %lu hosts left in net %p:\n", ln->nrhosts, net); + pr_warn("lockd: couldn't shutdown host module for net %x!\n", + net->ns.inum); + dprintk("lockd: %lu hosts left in net %x:\n", ln->nrhosts, + net->ns.inum); } else { if (nrhosts == 0) return; @@ -590,9 +592,9 @@ static void nlm_complain_hosts(struct net *net) for_each_host(host, chain, nlm_server_hosts) { if (net && host->net != net) continue; - dprintk(" %s (cnt %d use %d exp %ld net %p)\n", + dprintk(" %s (cnt %d use %d exp %ld net %x)\n", host->h_name, atomic_read(&host->h_count), - host->h_inuse, host->h_expires, host->net); + host->h_inuse, host->h_expires, host->net->ns.inum); } } @@ -605,7 +607,8 @@ nlm_shutdown_hosts_net(struct net *net) mutex_lock(&nlm_host_mutex); /* First, make all hosts eligible for gc */ - dprintk("lockd: nuking all hosts in net %p...\n", net); + dprintk("lockd: nuking all hosts in net %x...\n", + net ? net->ns.inum : 0); for_each_host(host, chain, nlm_server_hosts) { if (net && host->net != net) continue; @@ -618,9 +621,8 @@ nlm_shutdown_hosts_net(struct net *net) /* Then, perform a garbage collection pass */ nlm_gc_hosts(net); - mutex_unlock(&nlm_host_mutex); - nlm_complain_hosts(net); + mutex_unlock(&nlm_host_mutex); } /* @@ -646,7 +648,8 @@ nlm_gc_hosts(struct net *net) struct hlist_node *next; struct nlm_host *host; - dprintk("lockd: host garbage collection for net %p\n", net); + dprintk("lockd: host garbage collection for net %x\n", + net ? net->ns.inum : 0); for_each_host(host, chain, nlm_server_hosts) { if (net && host->net != net) continue; @@ -662,9 +665,10 @@ nlm_gc_hosts(struct net *net) if (atomic_read(&host->h_count) || host->h_inuse || time_before(jiffies, host->h_expires)) { dprintk("nlm_gc_hosts skipping %s " - "(cnt %d use %d exp %ld net %p)\n", + "(cnt %d use %d exp %ld net %x)\n", host->h_name, atomic_read(&host->h_count), - host->h_inuse, host->h_expires, host->net); + host->h_inuse, host->h_expires, + host->net->ns.inum); continue; } nlm_destroy_host_locked(host); diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 9fbbd11f9ecb..96cfb2967ac7 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -110,7 +110,8 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, clnt = nsm_create(host->net, host->nodename); if (IS_ERR(clnt)) { dprintk("lockd: failed to create NSM upcall transport, " - "status=%ld, net=%p\n", PTR_ERR(clnt), host->net); + "status=%ld, net=%x\n", PTR_ERR(clnt), + host->net->ns.inum); return PTR_ERR(clnt); } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index a8e3777c94dc..9c36d614bf89 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -57,6 +57,9 @@ static struct task_struct *nlmsvc_task; static struct svc_rqst *nlmsvc_rqst; unsigned long nlmsvc_timeout; +atomic_t nlm_ntf_refcnt = ATOMIC_INIT(0); +DECLARE_WAIT_QUEUE_HEAD(nlm_ntf_wq); + unsigned int lockd_net_id; /* @@ -259,7 +262,7 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net) if (error < 0) goto err_bind; set_grace_period(net); - dprintk("lockd_up_net: per-net data created; net=%p\n", net); + dprintk("%s: per-net data created; net=%x\n", __func__, net->ns.inum); return 0; err_bind: @@ -274,12 +277,15 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net) if (ln->nlmsvc_users) { if (--ln->nlmsvc_users == 0) { nlm_shutdown_hosts_net(net); + cancel_delayed_work_sync(&ln->grace_period_end); + locks_end_grace(&ln->lockd_manager); svc_shutdown_net(serv, net); - dprintk("lockd_down_net: per-net data destroyed; net=%p\n", net); + dprintk("%s: per-net data destroyed; net=%x\n", + __func__, net->ns.inum); } } else { - printk(KERN_ERR "lockd_down_net: no users! task=%p, net=%p\n", - nlmsvc_task, net); + pr_err("%s: no users! task=%p, net=%x\n", + __func__, nlmsvc_task, net->ns.inum); BUG(); } } @@ -290,7 +296,8 @@ static int lockd_inetaddr_event(struct notifier_block *this, struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct sockaddr_in sin; - if (event != NETDEV_DOWN) + if ((event != NETDEV_DOWN) || + !atomic_inc_not_zero(&nlm_ntf_refcnt)) goto out; if (nlmsvc_rqst) { @@ -301,6 +308,8 @@ static int lockd_inetaddr_event(struct notifier_block *this, svc_age_temp_xprts_now(nlmsvc_rqst->rq_server, (struct sockaddr *)&sin); } + atomic_dec(&nlm_ntf_refcnt); + wake_up(&nlm_ntf_wq); out: return NOTIFY_DONE; @@ -317,7 +326,8 @@ static int lockd_inet6addr_event(struct notifier_block *this, struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; struct sockaddr_in6 sin6; - if (event != NETDEV_DOWN) + if ((event != NETDEV_DOWN) || + !atomic_inc_not_zero(&nlm_ntf_refcnt)) goto out; if (nlmsvc_rqst) { @@ -329,6 +339,8 @@ static int lockd_inet6addr_event(struct notifier_block *this, svc_age_temp_xprts_now(nlmsvc_rqst->rq_server, (struct sockaddr *)&sin6); } + atomic_dec(&nlm_ntf_refcnt); + wake_up(&nlm_ntf_wq); out: return NOTIFY_DONE; @@ -345,10 +357,12 @@ static void lockd_unregister_notifiers(void) #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&lockd_inet6addr_notifier); #endif + wait_event(nlm_ntf_wq, atomic_read(&nlm_ntf_refcnt) == 0); } static void lockd_svc_exit_thread(void) { + atomic_dec(&nlm_ntf_refcnt); lockd_unregister_notifiers(); svc_exit_thread(nlmsvc_rqst); } @@ -373,6 +387,7 @@ static int lockd_start_svc(struct svc_serv *serv) goto out_rqst; } + atomic_inc(&nlm_ntf_refcnt); svc_sock_update_bufs(serv); serv->sv_maxconn = nlm_max_connections; @@ -676,6 +691,17 @@ static int lockd_init_net(struct net *net) static void lockd_exit_net(struct net *net) { + struct lockd_net *ln = net_generic(net, lockd_net_id); + + WARN_ONCE(!list_empty(&ln->lockd_manager.list), + "net %x %s: lockd_manager.list is not empty\n", + net->ns.inum, __func__); + WARN_ONCE(!list_empty(&ln->nsm_handles), + "net %x %s: nsm_handles list is not empty\n", + net->ns.inum, __func__); + WARN_ONCE(delayed_work_pending(&ln->grace_period_end), + "net %x %s: grace_period_end was not cancelled\n", + net->ns.inum, __func__); } static struct pernet_operations lockd_net_ops = { diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index a563ddbc19e6..4ec3d6e03e76 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -370,7 +370,7 @@ nlmsvc_mark_resources(struct net *net) { struct nlm_host hint; - dprintk("lockd: nlmsvc_mark_resources for net %p\n", net); + dprintk("lockd: %s for net %x\n", __func__, net ? net->ns.inum : 0); hint.net = net; nlm_traverse_files(&hint, nlmsvc_mark_host, NULL); } diff --git a/fs/locks.c b/fs/locks.c index 1bd71c4d663a..21b4dfa289ee 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -141,7 +141,7 @@ static inline bool is_remote_lock(struct file *filp) { - return likely(!(filp->f_path.dentry->d_sb->s_flags & MS_NOREMOTELOCK)); + return likely(!(filp->f_path.dentry->d_sb->s_flags & SB_NOREMOTELOCK)); } static bool lease_breaking(struct file_lock *fl) diff --git a/fs/mbcache.c b/fs/mbcache.c index d818fd236787..b8b8b9ced9f8 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -269,6 +269,9 @@ static unsigned long mb_cache_count(struct shrinker *shrink, struct mb_cache *cache = container_of(shrink, struct mb_cache, c_shrink); + /* Unlikely, but not impossible */ + if (unlikely(cache->c_entry_count < 0)) + return 0; return cache->c_entry_count; } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index b6829d679643..72e308c3e66b 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -125,9 +125,9 @@ static int minix_remount (struct super_block * sb, int * flags, char * data) sync_filesystem(sb); ms = sbi->s_ms; - if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) + if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) return 0; - if (*flags & MS_RDONLY) { + if (*flags & SB_RDONLY) { if (ms->s_state & MINIX_VALID_FS || !(sbi->s_mount_state & MINIX_VALID_FS)) return 0; diff --git a/fs/namei.c b/fs/namei.c index f0c7a7b9b6ca..9cc91fb7f156 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1129,18 +1129,9 @@ static int follow_automount(struct path *path, struct nameidata *nd, * of the daemon to instantiate them before they can be used. */ if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | - LOOKUP_OPEN | LOOKUP_CREATE | - LOOKUP_AUTOMOUNT))) { - /* Positive dentry that isn't meant to trigger an - * automount, EISDIR will allow it to be used, - * otherwise there's no mount here "now" so return - * ENOENT. - */ - if (path->dentry->d_inode) - return -EISDIR; - else - return -ENOENT; - } + LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && + path->dentry->d_inode) + return -EISDIR; if (path->dentry->d_sb->s_user_ns != &init_user_ns) return -EACCES; diff --git a/fs/namespace.c b/fs/namespace.c index e158ec6b527b..9d1374ab6e06 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2826,6 +2826,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, SB_DIRSYNC | SB_SILENT | SB_POSIXACL | + SB_LAZYTIME | SB_I_VERSION); if (flags & MS_REMOUNT) diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 129f1937fa2c..41de88cdc053 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -103,7 +103,7 @@ static void destroy_inodecache(void) static int ncp_remount(struct super_block *sb, int *flags, char* data) { sync_filesystem(sb); - *flags |= MS_NODIRATIME; + *flags |= SB_NODIRATIME; return 0; } @@ -547,7 +547,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent) else default_bufsize = 1024; - sb->s_flags |= MS_NODIRATIME; /* probably even noatime */ + sb->s_flags |= SB_NODIRATIME; /* probably even noatime */ sb->s_maxbytes = 0xFFFFFFFFU; sb->s_blocksize = 1024; /* Eh... Is this correct? */ sb->s_blocksize_bits = 10; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 0ac2fb1c6b63..b9129e2befea 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -291,12 +291,23 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat const struct sockaddr *sap = data->addr; struct nfs_net *nn = net_generic(data->net, nfs_net_id); +again: list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr; /* Don't match clients that failed to initialise properly */ if (clp->cl_cons_state < 0) continue; + /* If a client is still initializing then we need to wait */ + if (clp->cl_cons_state > NFS_CS_READY) { + refcount_inc(&clp->cl_count); + spin_unlock(&nn->nfs_client_lock); + nfs_wait_client_init_complete(clp); + nfs_put_client(clp); + spin_lock(&nn->nfs_client_lock); + goto again; + } + /* Different NFS versions cannot share the same nfs_client */ if (clp->rpc_ops != data->nfs_mod->rpc_ops) continue; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e51ae52ed14f..2f3f86726f5b 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1256,7 +1256,7 @@ static int nfs_dentry_delete(const struct dentry *dentry) /* Unhash it, so that ->d_iput() would be called */ return 1; } - if (!(dentry->d_sb->s_flags & MS_ACTIVE)) { + if (!(dentry->d_sb->s_flags & SB_ACTIVE)) { /* Unhash it, so that ancestors of killed async unlink * files will be cleaned up during umount */ return 1; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 38b93d54c02e..b992d2382ffa 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -752,7 +752,7 @@ int nfs_getattr(const struct path *path, struct kstat *stat, * Note that we only have to check the vfsmount flags here: * - NFS always sets S_NOATIME by so checking it would give a * bogus result - * - NFS never sets MS_NOATIME or MS_NODIRATIME so there is + * - NFS never sets SB_NOATIME or SB_NODIRATIME so there is * no point in checking those. */ if ((path->mnt->mnt_flags & MNT_NOATIME) || diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 5ab17fd4700a..8357ff69962f 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -10,7 +10,7 @@ #include <linux/nfs_page.h> #include <linux/wait_bit.h> -#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS) +#define NFS_MS_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) extern const struct export_operations nfs_export_ops; diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 12bbab0becb4..65a7e5da508c 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -404,15 +404,19 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, if (error < 0) goto error; - if (!nfs4_has_session(clp)) - nfs_mark_client_ready(clp, NFS_CS_READY); - error = nfs4_discover_server_trunking(clp, &old); if (error < 0) goto error; - if (clp != old) + if (clp != old) { clp->cl_preserve_clid = true; + /* + * Mark the client as having failed initialization so other + * processes walking the nfs_client_list in nfs_match_client() + * won't try to use it. + */ + nfs_mark_client_ready(clp, -EPERM); + } nfs_put_client(clp); clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags); return old; @@ -539,6 +543,9 @@ int nfs40_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + if (pos == new) + goto found; + status = nfs4_match_client(pos, new, &prev, nn); if (status < 0) goto out_unlock; @@ -559,6 +566,7 @@ int nfs40_walk_client_list(struct nfs_client *new, * way that a SETCLIENTID_CONFIRM to pos can succeed is * if new and pos point to the same server: */ +found: refcount_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); @@ -572,6 +580,7 @@ int nfs40_walk_client_list(struct nfs_client *new, case 0: nfs4_swap_callback_idents(pos, new); pos->cl_confirm = new->cl_confirm; + nfs_mark_client_ready(pos, NFS_CS_READY); prev = NULL; *result = pos; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 54fd56d715a8..e4f4a09ed9f4 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -71,8 +71,8 @@ const nfs4_stateid zero_stateid = { }; const nfs4_stateid invalid_stateid = { { - .seqid = cpu_to_be32(0xffffffffU), - .other = { 0 }, + /* Funky initialiser keeps older gcc versions happy */ + .data = { 0xff, 0xff, 0xff, 0xff, 0 }, }, .type = NFS4_INVALID_STATEID_TYPE, }; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 43cadb28db6e..29bacdc56f6a 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -813,9 +813,9 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root) */ seq_printf(m, "\n\topts:\t"); seq_puts(m, sb_rdonly(root->d_sb) ? "ro" : "rw"); - seq_puts(m, root->d_sb->s_flags & MS_SYNCHRONOUS ? ",sync" : ""); - seq_puts(m, root->d_sb->s_flags & MS_NOATIME ? ",noatime" : ""); - seq_puts(m, root->d_sb->s_flags & MS_NODIRATIME ? ",nodiratime" : ""); + seq_puts(m, root->d_sb->s_flags & SB_SYNCHRONOUS ? ",sync" : ""); + seq_puts(m, root->d_sb->s_flags & SB_NOATIME ? ",noatime" : ""); + seq_puts(m, root->d_sb->s_flags & SB_NODIRATIME ? ",nodiratime" : ""); nfs_show_mount_options(m, nfss, 1); seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ); @@ -2296,11 +2296,11 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) /* * noac is a special case. It implies -o sync, but that's not * necessarily reflected in the mtab options. do_remount_sb - * will clear MS_SYNCHRONOUS if -o sync wasn't specified in the + * will clear SB_SYNCHRONOUS if -o sync wasn't specified in the * remount options, so we have to explicitly reset it. */ if (data->flags & NFS_MOUNT_NOAC) - *flags |= MS_SYNCHRONOUS; + *flags |= SB_SYNCHRONOUS; /* compare new mount options with old ones */ error = nfs_compare_remount_data(nfss, data); @@ -2349,7 +2349,7 @@ void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info) /* The VFS shouldn't apply the umask to mode bits. We will do * so ourselves when necessary. */ - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; sb->s_time_gran = 1; sb->s_export_op = &nfs_export_ops; } @@ -2379,7 +2379,7 @@ static void nfs_clone_super(struct super_block *sb, /* The VFS shouldn't apply the umask to mode bits. We will do * so ourselves when necessary. */ - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; } nfs_initialise_sb(sb); @@ -2600,11 +2600,11 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, /* -o noac implies -o sync */ if (server->flags & NFS_MOUNT_NOAC) - sb_mntdata.mntflags |= MS_SYNCHRONOUS; + sb_mntdata.mntflags |= SB_SYNCHRONOUS; if (mount_info->cloned != NULL && mount_info->cloned->sb != NULL) - if (mount_info->cloned->sb->s_flags & MS_SYNCHRONOUS) - sb_mntdata.mntflags |= MS_SYNCHRONOUS; + if (mount_info->cloned->sb->s_flags & SB_SYNCHRONOUS) + sb_mntdata.mntflags |= SB_SYNCHRONOUS; /* Get a superblock - note that we may end up sharing one that already exists */ s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata); @@ -2641,7 +2641,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, if (error) goto error_splat_root; - s->s_flags |= MS_ACTIVE; + s->s_flags |= SB_ACTIVE; out: return mntroot; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5b5f464f6f2a..4a379d7918f2 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1890,6 +1890,8 @@ int nfs_commit_inode(struct inode *inode, int how) if (res) error = nfs_generic_commit_list(inode, &head, how, &cinfo); nfs_commit_end(cinfo.mds); + if (res == 0) + return res; if (error < 0) goto out_error; if (!may_wait) diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c index 897b299db55e..5be08f02a76b 100644 --- a/fs/nfs_common/grace.c +++ b/fs/nfs_common/grace.c @@ -30,7 +30,11 @@ locks_start_grace(struct net *net, struct lock_manager *lm) struct list_head *grace_list = net_generic(net, grace_net_id); spin_lock(&grace_lock); - list_add(&lm->list, grace_list); + if (list_empty(&lm->list)) + list_add(&lm->list, grace_list); + else + WARN(1, "double list_add attempt detected in net %x %s\n", + net->ns.inum, (net == &init_net) ? "(init_net)" : ""); spin_unlock(&grace_lock); } EXPORT_SYMBOL_GPL(locks_start_grace); @@ -104,7 +108,9 @@ grace_exit_net(struct net *net) { struct list_head *grace_list = net_generic(net, grace_net_id); - BUG_ON(!list_empty(grace_list)); + WARN_ONCE(!list_empty(grace_list), + "net %x %s: grace_list is not empty\n", + net->ns.inum, __func__); } static struct pernet_operations grace_net_ops = { diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 697f8ae7792d..f650e475d8f0 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -60,6 +60,9 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) gi->gid[i] = exp->ex_anon_gid; else gi->gid[i] = rqgi->gid[i]; + + /* Each thread allocates its own gi, no race */ + groups_sort(gi); } } else { gi = get_group_info(rqgi); diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 46b48dbbdd32..8ceb25a10ea0 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -232,7 +232,7 @@ static struct cache_head *expkey_alloc(void) return NULL; } -static struct cache_detail svc_expkey_cache_template = { +static const struct cache_detail svc_expkey_cache_template = { .owner = THIS_MODULE, .hash_size = EXPKEY_HASHMAX, .name = "nfsd.fh", @@ -748,7 +748,7 @@ static struct cache_head *svc_export_alloc(void) return NULL; } -static struct cache_detail svc_export_cache_template = { +static const struct cache_detail svc_export_cache_template = { .owner = THIS_MODULE, .hash_size = EXPORT_HASHMAX, .name = "nfsd.export", @@ -1230,7 +1230,7 @@ nfsd_export_init(struct net *net) int rv; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - dprintk("nfsd: initializing export module (net: %p).\n", net); + dprintk("nfsd: initializing export module (net: %x).\n", net->ns.inum); nn->svc_export_cache = cache_create_net(&svc_export_cache_template, net); if (IS_ERR(nn->svc_export_cache)) @@ -1278,7 +1278,7 @@ nfsd_export_shutdown(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - dprintk("nfsd: shutting down export module (net: %p).\n", net); + dprintk("nfsd: shutting down export module (net: %x).\n", net->ns.inum); cache_unregister_net(nn->svc_expkey_cache, net); cache_unregister_net(nn->svc_export_cache, net); @@ -1286,5 +1286,5 @@ nfsd_export_shutdown(struct net *net) cache_destroy_net(nn->svc_export_cache, net); svcauth_unix_purge(net); - dprintk("nfsd: export shutdown complete (net: %p).\n", net); + dprintk("nfsd: export shutdown complete (net: %x).\n", net->ns.inum); } diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 1c91391f4805..36358d435cb0 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -119,6 +119,9 @@ struct nfsd_net { u32 clverifier_counter; struct svc_serv *nfsd_serv; + + wait_queue_head_t ntf_wq; + atomic_t ntf_refcnt; }; /* Simple check to find out if a given net was properly initialized */ diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 6b9b6cca469f..a5bb76593ce7 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -178,7 +178,7 @@ static struct ent *idtoname_lookup(struct cache_detail *, struct ent *); static struct ent *idtoname_update(struct cache_detail *, struct ent *, struct ent *); -static struct cache_detail idtoname_cache_template = { +static const struct cache_detail idtoname_cache_template = { .owner = THIS_MODULE, .hash_size = ENT_HASHMAX, .name = "nfs4.idtoname", @@ -341,7 +341,7 @@ static struct ent *nametoid_update(struct cache_detail *, struct ent *, struct ent *); static int nametoid_parse(struct cache_detail *, char *, int); -static struct cache_detail nametoid_cache_template = { +static const struct cache_detail nametoid_cache_template = { .owner = THIS_MODULE, .hash_size = ENT_HASHMAX, .name = "nfs4.nametoid", diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index b82817767b9d..b29b5a185a2c 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -63,12 +63,16 @@ static const stateid_t zero_stateid = { static const stateid_t currentstateid = { .si_generation = 1, }; +static const stateid_t close_stateid = { + .si_generation = 0xffffffffU, +}; static u64 current_sessionid = 1; #define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t))) #define ONE_STATEID(stateid) (!memcmp((stateid), &one_stateid, sizeof(stateid_t))) #define CURRENT_STATEID(stateid) (!memcmp((stateid), ¤tstateid, sizeof(stateid_t))) +#define CLOSE_STATEID(stateid) (!memcmp((stateid), &close_stateid, sizeof(stateid_t))) /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); @@ -83,6 +87,11 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid); */ static DEFINE_SPINLOCK(state_lock); +enum nfsd4_st_mutex_lock_subclass { + OPEN_STATEID_MUTEX = 0, + LOCK_STATEID_MUTEX = 1, +}; + /* * A waitqueue for all in-progress 4.0 CLOSE operations that are waiting for * the refcount on the open stateid to drop. @@ -3562,7 +3571,9 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) /* ignore lock owners */ if (local->st_stateowner->so_is_open_owner == 0) continue; - if (local->st_stateowner == &oo->oo_owner) { + if (local->st_stateowner != &oo->oo_owner) + continue; + if (local->st_stid.sc_type == NFS4_OPEN_STID) { ret = local; refcount_inc(&ret->st_stid.sc_count); break; @@ -3571,6 +3582,52 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) return ret; } +static __be32 +nfsd4_verify_open_stid(struct nfs4_stid *s) +{ + __be32 ret = nfs_ok; + + switch (s->sc_type) { + default: + break; + case NFS4_CLOSED_STID: + case NFS4_CLOSED_DELEG_STID: + ret = nfserr_bad_stateid; + break; + case NFS4_REVOKED_DELEG_STID: + ret = nfserr_deleg_revoked; + } + return ret; +} + +/* Lock the stateid st_mutex, and deal with races with CLOSE */ +static __be32 +nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp) +{ + __be32 ret; + + mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX); + ret = nfsd4_verify_open_stid(&stp->st_stid); + if (ret != nfs_ok) + mutex_unlock(&stp->st_mutex); + return ret; +} + +static struct nfs4_ol_stateid * +nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) +{ + struct nfs4_ol_stateid *stp; + for (;;) { + spin_lock(&fp->fi_lock); + stp = nfsd4_find_existing_open(fp, open); + spin_unlock(&fp->fi_lock); + if (!stp || nfsd4_lock_ol_stateid(stp) == nfs_ok) + break; + nfs4_put_stid(&stp->st_stid); + } + return stp; +} + static struct nfs4_openowner * alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, struct nfsd4_compound_state *cstate) @@ -3613,8 +3670,9 @@ init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open) stp = open->op_stp; /* We are moving these outside of the spinlocks to avoid the warnings */ mutex_init(&stp->st_mutex); - mutex_lock(&stp->st_mutex); + mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); +retry: spin_lock(&oo->oo_owner.so_client->cl_lock); spin_lock(&fp->fi_lock); @@ -3639,7 +3697,11 @@ out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&oo->oo_owner.so_client->cl_lock); if (retstp) { - mutex_lock(&retstp->st_mutex); + /* Handle races with CLOSE */ + if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { + nfs4_put_stid(&retstp->st_stid); + goto retry; + } /* To keep mutex tracking happy */ mutex_unlock(&stp->st_mutex); stp = retstp; @@ -4449,6 +4511,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf struct nfs4_ol_stateid *stp = NULL; struct nfs4_delegation *dp = NULL; __be32 status; + bool new_stp = false; /* * Lookup file; if found, lookup stateid and check open request, @@ -4460,9 +4523,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf status = nfs4_check_deleg(cl, open, &dp); if (status) goto out; - spin_lock(&fp->fi_lock); - stp = nfsd4_find_existing_open(fp, open); - spin_unlock(&fp->fi_lock); + stp = nfsd4_find_and_lock_existing_open(fp, open); } else { open->op_file = NULL; status = nfserr_bad_stateid; @@ -4470,35 +4531,31 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf goto out; } + if (!stp) { + stp = init_open_stateid(fp, open); + if (!open->op_stp) + new_stp = true; + } + /* * OPEN the file, or upgrade an existing OPEN. * If truncate fails, the OPEN fails. + * + * stp is already locked. */ - if (stp) { + if (!new_stp) { /* Stateid was found, this is an OPEN upgrade */ - mutex_lock(&stp->st_mutex); status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open); if (status) { mutex_unlock(&stp->st_mutex); goto out; } } else { - /* stp is returned locked. */ - stp = init_open_stateid(fp, open); - /* See if we lost the race to some other thread */ - if (stp->st_access_bmap != 0) { - status = nfs4_upgrade_open(rqstp, fp, current_fh, - stp, open); - if (status) { - mutex_unlock(&stp->st_mutex); - goto out; - } - goto upgrade_out; - } status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open); if (status) { - mutex_unlock(&stp->st_mutex); + stp->st_stid.sc_type = NFS4_CLOSED_STID; release_open_stateid(stp); + mutex_unlock(&stp->st_mutex); goto out; } @@ -4507,7 +4564,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf if (stp->st_clnt_odstate == open->op_odstate) open->op_odstate = NULL; } -upgrade_out: + nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid); mutex_unlock(&stp->st_mutex); @@ -4734,7 +4791,7 @@ nfs4_laundromat(struct nfsd_net *nn) spin_unlock(&nn->blocked_locks_lock); while (!list_empty(&reaplist)) { - nbl = list_first_entry(&nn->blocked_locks_lru, + nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); posix_unblock_lock(&nbl->nbl_lock); @@ -4855,6 +4912,18 @@ static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_s return nfserr_old_stateid; } +static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_stid *s, bool has_session) +{ + __be32 ret; + + spin_lock(&s->sc_lock); + ret = nfsd4_verify_open_stid(s); + if (ret == nfs_ok) + ret = check_stateid_generation(in, &s->sc_stateid, has_session); + spin_unlock(&s->sc_lock); + return ret; +} + static __be32 nfsd4_check_openowner_confirmed(struct nfs4_ol_stateid *ols) { if (ols->st_stateowner->so_is_open_owner && @@ -4868,7 +4937,8 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) struct nfs4_stid *s; __be32 status = nfserr_bad_stateid; - if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) + if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || + CLOSE_STATEID(stateid)) return status; /* Client debugging aid. */ if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) { @@ -4883,7 +4953,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) s = find_stateid_locked(cl, stateid); if (!s) goto out_unlock; - status = check_stateid_generation(stateid, &s->sc_stateid, 1); + status = nfsd4_stid_check_stateid_generation(stateid, s, 1); if (status) goto out_unlock; switch (s->sc_type) { @@ -4926,7 +4996,8 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, else if (typemask & NFS4_DELEG_STID) typemask |= NFS4_REVOKED_DELEG_STID; - if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) + if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || + CLOSE_STATEID(stateid)) return nfserr_bad_stateid; status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn); if (status == nfserr_stale_clientid) { @@ -5044,7 +5115,7 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, &s, nn); if (status) return status; - status = check_stateid_generation(stateid, &s->sc_stateid, + status = nfsd4_stid_check_stateid_generation(stateid, s, nfsd4_has_session(cstate)); if (status) goto out; @@ -5098,7 +5169,9 @@ nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s) struct nfs4_ol_stateid *stp = openlockstateid(s); __be32 ret; - mutex_lock(&stp->st_mutex); + ret = nfsd4_lock_ol_stateid(stp); + if (ret) + goto out_put_stid; ret = check_stateid_generation(stateid, &s->sc_stateid, 1); if (ret) @@ -5109,11 +5182,13 @@ nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s) lockowner(stp->st_stateowner))) goto out; + stp->st_stid.sc_type = NFS4_CLOSED_STID; release_lock_stateid(stp); ret = nfs_ok; out: mutex_unlock(&stp->st_mutex); +out_put_stid: nfs4_put_stid(s); return ret; } @@ -5133,6 +5208,7 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, s = find_stateid_locked(cl, stateid); if (!s) goto out_unlock; + spin_lock(&s->sc_lock); switch (s->sc_type) { case NFS4_DELEG_STID: ret = nfserr_locks_held; @@ -5144,11 +5220,13 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, ret = nfserr_locks_held; break; case NFS4_LOCK_STID: + spin_unlock(&s->sc_lock); refcount_inc(&s->sc_count); spin_unlock(&cl->cl_lock); ret = nfsd4_free_lock_stateid(stateid, s); goto out; case NFS4_REVOKED_DELEG_STID: + spin_unlock(&s->sc_lock); dp = delegstateid(s); list_del_init(&dp->dl_recall_lru); spin_unlock(&cl->cl_lock); @@ -5157,6 +5235,7 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; /* Default falls through and returns nfserr_bad_stateid */ } + spin_unlock(&s->sc_lock); out_unlock: spin_unlock(&cl->cl_lock); out: @@ -5179,15 +5258,9 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ status = nfsd4_check_seqid(cstate, sop, seqid); if (status) return status; - if (stp->st_stid.sc_type == NFS4_CLOSED_STID - || stp->st_stid.sc_type == NFS4_REVOKED_DELEG_STID) - /* - * "Closed" stateid's exist *only* to return - * nfserr_replay_me from the previous step, and - * revoked delegations are kept only for free_stateid. - */ - return nfserr_bad_stateid; - mutex_lock(&stp->st_mutex); + status = nfsd4_lock_ol_stateid(stp); + if (status != nfs_ok) + return status; status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); if (status == nfs_ok) status = nfs4_check_fh(current_fh, &stp->st_stid); @@ -5367,7 +5440,6 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) bool unhashed; LIST_HEAD(reaplist); - s->st_stid.sc_type = NFS4_CLOSED_STID; spin_lock(&clp->cl_lock); unhashed = unhash_open_stateid(s, &reaplist); @@ -5407,10 +5479,17 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfsd4_bump_seqid(cstate, status); if (status) goto out; + + stp->st_stid.sc_type = NFS4_CLOSED_STID; nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid); - mutex_unlock(&stp->st_mutex); nfsd4_close_open_stateid(stp); + mutex_unlock(&stp->st_mutex); + + /* See RFC5661 sectionm 18.2.4 */ + if (stp->st_stid.sc_client->cl_minorversion) + memcpy(&close->cl_stateid, &close_stateid, + sizeof(close->cl_stateid)); /* put reference from nfs4_preprocess_seqid_op */ nfs4_put_stid(&stp->st_stid); @@ -5436,7 +5515,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; dp = delegstateid(s); - status = check_stateid_generation(stateid, &dp->dl_stid.sc_stateid, nfsd4_has_session(cstate)); + status = nfsd4_stid_check_stateid_generation(stateid, &dp->dl_stid, nfsd4_has_session(cstate)); if (status) goto put_stateid; @@ -5642,14 +5721,41 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, return ret; } -static void +static struct nfs4_ol_stateid * +find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp) +{ + struct nfs4_ol_stateid *lst; + struct nfs4_client *clp = lo->lo_owner.so_client; + + lockdep_assert_held(&clp->cl_lock); + + list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) { + if (lst->st_stid.sc_type != NFS4_LOCK_STID) + continue; + if (lst->st_stid.sc_file == fp) { + refcount_inc(&lst->st_stid.sc_count); + return lst; + } + } + return NULL; +} + +static struct nfs4_ol_stateid * init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, struct nfs4_file *fp, struct inode *inode, struct nfs4_ol_stateid *open_stp) { struct nfs4_client *clp = lo->lo_owner.so_client; + struct nfs4_ol_stateid *retstp; - lockdep_assert_held(&clp->cl_lock); + mutex_init(&stp->st_mutex); + mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); +retry: + spin_lock(&clp->cl_lock); + spin_lock(&fp->fi_lock); + retstp = find_lock_stateid(lo, fp); + if (retstp) + goto out_unlock; refcount_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = NFS4_LOCK_STID; @@ -5659,29 +5765,22 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; - mutex_init(&stp->st_mutex); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); - spin_lock(&fp->fi_lock); list_add(&stp->st_perfile, &fp->fi_stateids); +out_unlock: spin_unlock(&fp->fi_lock); -} - -static struct nfs4_ol_stateid * -find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp) -{ - struct nfs4_ol_stateid *lst; - struct nfs4_client *clp = lo->lo_owner.so_client; - - lockdep_assert_held(&clp->cl_lock); - - list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) { - if (lst->st_stid.sc_file == fp) { - refcount_inc(&lst->st_stid.sc_count); - return lst; + spin_unlock(&clp->cl_lock); + if (retstp) { + if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { + nfs4_put_stid(&retstp->st_stid); + goto retry; } + /* To keep mutex tracking happy */ + mutex_unlock(&stp->st_mutex); + stp = retstp; } - return NULL; + return stp; } static struct nfs4_ol_stateid * @@ -5694,26 +5793,25 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi, struct nfs4_openowner *oo = openowner(ost->st_stateowner); struct nfs4_client *clp = oo->oo_owner.so_client; + *new = false; spin_lock(&clp->cl_lock); lst = find_lock_stateid(lo, fi); - if (lst == NULL) { - spin_unlock(&clp->cl_lock); - ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid); - if (ns == NULL) - return NULL; - - spin_lock(&clp->cl_lock); - lst = find_lock_stateid(lo, fi); - if (likely(!lst)) { - lst = openlockstateid(ns); - init_lock_stateid(lst, lo, fi, inode, ost); - ns = NULL; - *new = true; - } - } spin_unlock(&clp->cl_lock); - if (ns) + if (lst != NULL) { + if (nfsd4_lock_ol_stateid(lst) == nfs_ok) + goto out; + nfs4_put_stid(&lst->st_stid); + } + ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid); + if (ns == NULL) + return NULL; + + lst = init_lock_stateid(openlockstateid(ns), lo, fi, inode, ost); + if (lst == openlockstateid(ns)) + *new = true; + else nfs4_put_stid(ns); +out: return lst; } @@ -5750,7 +5848,6 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_lockowner *lo; struct nfs4_ol_stateid *lst; unsigned int strhashval; - bool hashed; lo = find_lockowner_str(cl, &lock->lk_new_owner); if (!lo) { @@ -5766,25 +5863,12 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, goto out; } -retry: lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); if (lst == NULL) { status = nfserr_jukebox; goto out; } - mutex_lock(&lst->st_mutex); - - /* See if it's still hashed to avoid race with FREE_STATEID */ - spin_lock(&cl->cl_lock); - hashed = !list_empty(&lst->st_perfile); - spin_unlock(&cl->cl_lock); - - if (!hashed) { - mutex_unlock(&lst->st_mutex); - nfs4_put_stid(&lst->st_stid); - goto retry; - } status = nfs_ok; *plst = lst; out: @@ -5990,14 +6074,16 @@ out: seqid_mutating_err(ntohl(status))) lock_sop->lo_owner.so_seqid++; - mutex_unlock(&lock_stp->st_mutex); - /* * If this is a new, never-before-used stateid, and we are * returning an error, then just go ahead and release it. */ - if (status && new) + if (status && new) { + lock_stp->st_stid.sc_type = NFS4_CLOSED_STID; release_lock_stateid(lock_stp); + } + + mutex_unlock(&lock_stp->st_mutex); nfs4_put_stid(&lock_stp->st_stid); } @@ -7017,6 +7103,10 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]); nn->conf_name_tree = RB_ROOT; nn->unconf_name_tree = RB_ROOT; + nn->boot_time = get_seconds(); + nn->grace_ended = false; + nn->nfsd4_manager.block_opens = true; + INIT_LIST_HEAD(&nn->nfsd4_manager.list); INIT_LIST_HEAD(&nn->client_lru); INIT_LIST_HEAD(&nn->close_lru); INIT_LIST_HEAD(&nn->del_recall_lru); @@ -7074,9 +7164,6 @@ nfs4_state_start_net(struct net *net) ret = nfs4_state_create_net(net); if (ret) return ret; - nn->boot_time = get_seconds(); - nn->grace_ended = false; - nn->nfsd4_manager.block_opens = true; locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); printk(KERN_INFO "NFSD: starting %ld-second grace period (net %x)\n", @@ -7153,7 +7240,7 @@ nfs4_state_shutdown_net(struct net *net) spin_unlock(&nn->blocked_locks_lock); while (!list_empty(&reaplist)) { - nbl = list_first_entry(&nn->blocked_locks_lru, + nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); posix_unblock_lock(&nbl->nbl_lock); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 6493df6b1bd5..d107b4426f7e 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1241,6 +1241,9 @@ static __net_init int nfsd_init_net(struct net *net) nn->nfsd4_grace = 90; nn->clverifier_counter = prandom_u32(); nn->clientid_counter = prandom_u32(); + + atomic_set(&nn->ntf_refcnt, 0); + init_waitqueue_head(&nn->ntf_wq); return 0; out_idmap_error: diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 33117d4ffce0..89cb484f1cfb 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -335,7 +335,8 @@ static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event, struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct sockaddr_in sin; - if (event != NETDEV_DOWN) + if ((event != NETDEV_DOWN) || + !atomic_inc_not_zero(&nn->ntf_refcnt)) goto out; if (nn->nfsd_serv) { @@ -344,6 +345,8 @@ static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event, sin.sin_addr.s_addr = ifa->ifa_local; svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin); } + atomic_dec(&nn->ntf_refcnt); + wake_up(&nn->ntf_wq); out: return NOTIFY_DONE; @@ -363,7 +366,8 @@ static int nfsd_inet6addr_event(struct notifier_block *this, struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct sockaddr_in6 sin6; - if (event != NETDEV_DOWN) + if ((event != NETDEV_DOWN) || + !atomic_inc_not_zero(&nn->ntf_refcnt)) goto out; if (nn->nfsd_serv) { @@ -374,7 +378,8 @@ static int nfsd_inet6addr_event(struct notifier_block *this, sin6.sin6_scope_id = ifa->idev->dev->ifindex; svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6); } - + atomic_dec(&nn->ntf_refcnt); + wake_up(&nn->ntf_wq); out: return NOTIFY_DONE; } @@ -391,6 +396,7 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); + atomic_dec(&nn->ntf_refcnt); /* check if the notifier still has clients */ if (atomic_dec_return(&nfsd_notifier_refcount) == 0) { unregister_inetaddr_notifier(&nfsd_inetaddr_notifier); @@ -398,6 +404,7 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) unregister_inet6addr_notifier(&nfsd_inet6addr_notifier); #endif } + wait_event(nn->ntf_wq, atomic_read(&nn->ntf_refcnt) == 0); /* * write_ports can create the server without actually starting @@ -517,6 +524,7 @@ int nfsd_create_serv(struct net *net) register_inet6addr_notifier(&nfsd_inet6addr_notifier); #endif } + atomic_inc(&nn->ntf_refcnt); ktime_get_real_ts64(&nn->nfssvc_boot); /* record boot time */ return 0; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index f572538dcc4f..9f3ffba41533 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1979,7 +1979,7 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, struct the_nilfs *nilfs) { struct nilfs_inode_info *ii, *n; - int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE); + int during_mount = !(sci->sc_super->s_flags & SB_ACTIVE); int defer_iput = false; spin_lock(&nilfs->ns_inode_lock); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 3ce20cd44a20..3073b646e1ba 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -141,7 +141,7 @@ void __nilfs_error(struct super_block *sb, const char *function, if (nilfs_test_opt(nilfs, ERRORS_RO)) { printk(KERN_CRIT "Remounting filesystem read-only\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } } @@ -869,7 +869,7 @@ int nilfs_store_magic_and_option(struct super_block *sb, /* FS independent flags */ #ifdef NILFS_ATIME_DISABLE - sb->s_flags |= MS_NOATIME; + sb->s_flags |= SB_NOATIME; #endif nilfs_set_default_options(sb, sbp); @@ -1133,7 +1133,7 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) err = -EINVAL; goto restore_opts; } - sb->s_flags = (sb->s_flags & ~MS_POSIXACL); + sb->s_flags = (sb->s_flags & ~SB_POSIXACL); err = -EINVAL; @@ -1143,12 +1143,12 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) + if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) goto out; - if (*flags & MS_RDONLY) { + if (*flags & SB_RDONLY) { /* Shutting down log writer */ nilfs_detach_log_writer(sb); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; /* * Remounting a valid RW partition RDONLY, so set @@ -1178,7 +1178,7 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; root = NILFS_I(d_inode(sb->s_root))->i_root; err = nilfs_attach_log_writer(sb, root); @@ -1212,7 +1212,7 @@ static int nilfs_parse_snapshot_option(const char *option, const char *msg = NULL; int err; - if (!(sd->flags & MS_RDONLY)) { + if (!(sd->flags & SB_RDONLY)) { msg = "read-only option is not specified"; goto parse_error; } @@ -1286,7 +1286,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags, struct dentry *root_dentry; int err, s_new = false; - if (!(flags & MS_RDONLY)) + if (!(flags & SB_RDONLY)) mode |= FMODE_WRITE; sd.bdev = blkdev_get_by_path(dev_name, mode, fs_type); @@ -1327,14 +1327,14 @@ nilfs_mount(struct file_system_type *fs_type, int flags, snprintf(s->s_id, sizeof(s->s_id), "%pg", sd.bdev); sb_set_blocksize(s, block_size(sd.bdev)); - err = nilfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0); + err = nilfs_fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (err) goto failed_super; - s->s_flags |= MS_ACTIVE; + s->s_flags |= SB_ACTIVE; } else if (!sd.cno) { if (nilfs_tree_is_busy(s->s_root)) { - if ((flags ^ s->s_flags) & MS_RDONLY) { + if ((flags ^ s->s_flags) & SB_RDONLY) { nilfs_msg(s, KERN_ERR, "the device already has a %s mount.", sb_rdonly(s) ? "read-only" : "read/write"); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index afebb5067cec..1a85317e83f0 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -220,7 +220,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) if (!valid_fs) { nilfs_msg(sb, KERN_WARNING, "mounting unchecked fs"); - if (s_flags & MS_RDONLY) { + if (s_flags & SB_RDONLY) { nilfs_msg(sb, KERN_INFO, "recovery required for readonly filesystem"); nilfs_msg(sb, KERN_INFO, @@ -286,7 +286,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) if (valid_fs) goto skip_recovery; - if (s_flags & MS_RDONLY) { + if (s_flags & SB_RDONLY) { __u64 features; if (nilfs_test_opt(nilfs, NORECOVERY)) { @@ -309,7 +309,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) err = -EROFS; goto failed_unload; } - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; } else if (nilfs_test_opt(nilfs, NORECOVERY)) { nilfs_msg(sb, KERN_ERR, "recovery cancelled because norecovery option was specified for a read/write mount"); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 81d8959b6aef..219b269c737e 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -67,7 +67,7 @@ void fsnotify_unmount_inodes(struct super_block *sb) /* * If i_count is zero, the inode cannot have any watches and - * doing an __iget/iput with MS_ACTIVE clear would actually + * doing an __iget/iput with SB_ACTIVE clear would actually * evict all inodes with zero i_count from icache which is * unnecessarily violent and may in fact be illegal to do. */ diff --git a/fs/nsfs.c b/fs/nsfs.c index ef243e14b6eb..7c6f76d29f56 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -255,5 +255,5 @@ void __init nsfs_init(void) nsfs_mnt = kern_mount(&nsfs); if (IS_ERR(nsfs_mnt)) panic("can't set nsfs up\n"); - nsfs_mnt->mnt_sb->s_flags &= ~MS_NOUSER; + nsfs_mnt->mnt_sb->s_flags &= ~SB_NOUSER; } diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 3f70f041dbe9..bb7159f697f2 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -473,7 +473,7 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt) #ifndef NTFS_RW /* For read-only compiled driver, enforce read-only flag. */ - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; #else /* NTFS_RW */ /* * For the read-write compiled driver, if we are remounting read-write, @@ -487,7 +487,7 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt) * When remounting read-only, mark the volume clean if no volume errors * have occurred. */ - if (sb_rdonly(sb) && !(*flags & MS_RDONLY)) { + if (sb_rdonly(sb) && !(*flags & SB_RDONLY)) { static const char *es = ". Cannot remount read-write."; /* Remounting read-write. */ @@ -548,7 +548,7 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt) NVolSetErrors(vol); return -EROFS; } - } else if (!sb_rdonly(sb) && (*flags & MS_RDONLY)) { + } else if (!sb_rdonly(sb) && (*flags & SB_RDONLY)) { /* Remounting read-only. */ if (!NVolErrors(vol)) { if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) @@ -1799,7 +1799,7 @@ static bool load_system_files(ntfs_volume *vol) es3); goto iput_mirr_err_out; } - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; ntfs_error(sb, "%s. Mounting read-only%s", !vol->mftmirr_ino ? es1 : es2, es3); } else @@ -1937,7 +1937,7 @@ get_ctx_vol_failed: es1, es2); goto iput_vol_err_out; } - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); } else ntfs_warning(sb, "%s. Will not be able to remount " @@ -1974,7 +1974,7 @@ get_ctx_vol_failed: } goto iput_logfile_err_out; } - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); } else ntfs_warning(sb, "%s. Will not be able to remount " @@ -2019,7 +2019,7 @@ get_ctx_vol_failed: es1, es2); goto iput_root_err_out; } - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); } else ntfs_warning(sb, "%s. Will not be able to remount " @@ -2042,7 +2042,7 @@ get_ctx_vol_failed: goto iput_root_err_out; } ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; /* * Do not set NVolErrors() because ntfs_remount() might manage * to set the dirty flag in which case all would be well. @@ -2055,7 +2055,7 @@ get_ctx_vol_failed: * If (still) a read-write mount, set the NT4 compatibility flag on * newer NTFS version volumes. */ - if (!(sb->s_flags & MS_RDONLY) && (vol->major_ver > 1) && + if (!(sb->s_flags & SB_RDONLY) && (vol->major_ver > 1) && ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) { static const char *es1 = "Failed to set NT4 compatibility flag"; static const char *es2 = ". Run chkdsk."; @@ -2069,7 +2069,7 @@ get_ctx_vol_failed: goto iput_root_err_out; } ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; NVolSetErrors(vol); } #endif @@ -2087,7 +2087,7 @@ get_ctx_vol_failed: goto iput_root_err_out; } ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; NVolSetErrors(vol); } #endif /* NTFS_RW */ @@ -2128,7 +2128,7 @@ get_ctx_vol_failed: es1, es2); goto iput_quota_err_out; } - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); } else ntfs_warning(sb, "%s. Will not be able to remount " @@ -2150,7 +2150,7 @@ get_ctx_vol_failed: goto iput_quota_err_out; } ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; NVolSetErrors(vol); } /* @@ -2171,7 +2171,7 @@ get_ctx_vol_failed: es1, es2); goto iput_usnjrnl_err_out; } - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); } else ntfs_warning(sb, "%s. Will not be able to remount " @@ -2194,7 +2194,7 @@ get_ctx_vol_failed: goto iput_usnjrnl_err_out; } ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; NVolSetErrors(vol); } #endif /* NTFS_RW */ @@ -2728,7 +2728,7 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) lockdep_off(); ntfs_debug("Entering."); #ifndef NTFS_RW - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; #endif /* ! NTFS_RW */ /* Allocate a new ntfs_volume and place it in sb->s_fs_info. */ sb->s_fs_info = kmalloc(sizeof(ntfs_volume), GFP_NOFS); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index dc455d45a66a..a1d051055472 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -227,7 +227,7 @@ int ocfs2_should_update_atime(struct inode *inode, return 0; if ((inode->i_flags & S_NOATIME) || - ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))) + ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode))) return 0; /* diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 040bbb6a6e4b..80efa5699fb0 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -675,9 +675,9 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data) } /* We're going to/from readonly mode. */ - if ((bool)(*flags & MS_RDONLY) != sb_rdonly(sb)) { + if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { /* Disable quota accounting before remounting RO */ - if (*flags & MS_RDONLY) { + if (*flags & SB_RDONLY) { ret = ocfs2_susp_quotas(osb, 0); if (ret < 0) goto out; @@ -691,8 +691,8 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data) goto unlock_osb; } - if (*flags & MS_RDONLY) { - sb->s_flags |= MS_RDONLY; + if (*flags & SB_RDONLY) { + sb->s_flags |= SB_RDONLY; osb->osb_flags |= OCFS2_OSB_SOFT_RO; } else { if (osb->osb_flags & OCFS2_OSB_ERROR_FS) { @@ -709,14 +709,14 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data) ret = -EINVAL; goto unlock_osb; } - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; osb->osb_flags &= ~OCFS2_OSB_SOFT_RO; } trace_ocfs2_remount(sb->s_flags, osb->osb_flags, *flags); unlock_osb: spin_unlock(&osb->osb_lock); /* Enable quota accounting after remounting RW */ - if (!ret && !(*flags & MS_RDONLY)) { + if (!ret && !(*flags & SB_RDONLY)) { if (sb_any_quota_suspended(sb)) ret = ocfs2_susp_quotas(osb, 1); else @@ -724,7 +724,7 @@ unlock_osb: if (ret < 0) { /* Return back changes... */ spin_lock(&osb->osb_lock); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; osb->osb_flags |= OCFS2_OSB_SOFT_RO; spin_unlock(&osb->osb_lock); goto out; @@ -744,9 +744,9 @@ unlock_osb: if (!ocfs2_is_hard_readonly(osb)) ocfs2_set_journal_params(osb); - sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | + sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? - MS_POSIXACL : 0); + SB_POSIXACL : 0); } out: return ret; @@ -1057,10 +1057,10 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) sb->s_magic = OCFS2_SUPER_MAGIC; - sb->s_flags = (sb->s_flags & ~(MS_POSIXACL | MS_NOSEC)) | - ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0); + sb->s_flags = (sb->s_flags & ~(SB_POSIXACL | SB_NOSEC)) | + ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? SB_POSIXACL : 0); - /* Hard readonly mode only if: bdev_read_only, MS_RDONLY, + /* Hard readonly mode only if: bdev_read_only, SB_RDONLY, * heartbeat=none */ if (bdev_read_only(sb->s_bdev)) { if (!sb_rdonly(sb)) { @@ -2057,7 +2057,7 @@ static int ocfs2_initialize_super(struct super_block *sb, sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; sb->s_xattr = ocfs2_xattr_handlers; sb->s_time_gran = 1; - sb->s_flags |= MS_NOATIME; + sb->s_flags |= SB_NOATIME; /* this is needed to support O_LARGEFILE */ cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits); bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits); @@ -2568,7 +2568,7 @@ static int ocfs2_handle_error(struct super_block *sb) return rv; pr_crit("OCFS2: File system is now read-only.\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; ocfs2_set_ro_flag(osb, 0); } diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 5fdf269ba82e..c5898c59d411 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -901,7 +901,7 @@ static int ocfs2_xattr_list_entry(struct super_block *sb, case OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS: case OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT: - if (!(sb->s_flags & MS_POSIXACL)) + if (!(sb->s_flags & SB_POSIXACL)) return 0; break; diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index 13215f26e321..2200662a9bf1 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -369,7 +369,7 @@ static struct inode *openprom_iget(struct super_block *sb, ino_t ino) static int openprom_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_NOATIME; + *flags |= SB_NOATIME; return 0; } @@ -386,7 +386,7 @@ static int openprom_fill_super(struct super_block *s, void *data, int silent) struct op_inode_info *oi; int ret; - s->s_flags |= MS_NOATIME; + s->s_flags |= SB_NOATIME; s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = OPENPROM_SUPER_MAGIC; diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 366750eef201..36f1390b5ed7 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -40,7 +40,7 @@ static int orangefs_show_options(struct seq_file *m, struct dentry *root) { struct orangefs_sb_info_s *orangefs_sb = ORANGEFS_SB(root->d_sb); - if (root->d_sb->s_flags & MS_POSIXACL) + if (root->d_sb->s_flags & SB_POSIXACL) seq_puts(m, ",acl"); if (orangefs_sb->flags & ORANGEFS_OPT_INTR) seq_puts(m, ",intr"); @@ -60,7 +60,7 @@ static int parse_mount_options(struct super_block *sb, char *options, * Force any potential flags that might be set from the mount * to zero, ie, initialize to unset. */ - sb->s_flags &= ~MS_POSIXACL; + sb->s_flags &= ~SB_POSIXACL; orangefs_sb->flags &= ~ORANGEFS_OPT_INTR; orangefs_sb->flags &= ~ORANGEFS_OPT_LOCAL_LOCK; @@ -73,7 +73,7 @@ static int parse_mount_options(struct super_block *sb, char *options, token = match_token(p, tokens, args); switch (token) { case Opt_acl: - sb->s_flags |= MS_POSIXACL; + sb->s_flags |= SB_POSIXACL; break; case Opt_intr: orangefs_sb->flags |= ORANGEFS_OPT_INTR; @@ -507,7 +507,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst, ret = orangefs_fill_sb(sb, &new_op->downcall.resp.fs_mount, data, - flags & MS_SILENT ? 1 : 0); + flags & SB_SILENT ? 1 : 0); if (ret) { d = ERR_PTR(ret); diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index cbfc196e5dc5..5ac415466861 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -24,6 +24,16 @@ config OVERLAY_FS_REDIRECT_DIR an overlay which has redirects on a kernel that doesn't support this feature will have unexpected results. +config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW + bool "Overlayfs: follow redirects even if redirects are turned off" + default y + depends on OVERLAY_FS + help + Disable this to get a possibly more secure configuration, but that + might not be backward compatible with previous kernels. + + For more information, see Documentation/filesystems/overlayfs.txt + config OVERLAY_FS_INDEX bool "Overlayfs: turn on inodes index feature by default" depends on OVERLAY_FS diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index e13921824c70..f9788bc116a8 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -887,7 +887,8 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir) spin_unlock(&dentry->d_lock); } else { kfree(redirect); - pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err); + pr_warn_ratelimited("overlayfs: failed to set redirect (%i)\n", + err); /* Fall back to userspace copy-up */ err = -EXDEV; } diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 625ed8066570..beb945e1963c 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -435,7 +435,7 @@ int ovl_verify_index(struct dentry *index, struct ovl_path *lower, /* Check if index is orphan and don't warn before cleaning it */ if (d_inode(index)->i_nlink == 1 && - ovl_get_nlink(index, origin.dentry, 0) == 0) + ovl_get_nlink(origin.dentry, index, 0) == 0) err = -ENOENT; dput(origin.dentry); @@ -681,6 +681,22 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, if (d.stop) break; + /* + * Following redirects can have security consequences: it's like + * a symlink into the lower layer without the permission checks. + * This is only a problem if the upper layer is untrusted (e.g + * comes from an USB drive). This can allow a non-readable file + * or directory to become readable. + * + * Only following redirects when redirects are enabled disables + * this attack vector when not necessary. + */ + err = -EPERM; + if (d.redirect && !ofs->config.redirect_follow) { + pr_warn_ratelimited("overlay: refusing to follow redirect for (%pd2)\n", dentry); + goto out_put; + } + if (d.redirect && d.redirect[0] == '/' && poe != roe) { poe = roe; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 13eab09a6b6f..b489099ccd49 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -180,7 +180,7 @@ static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry) static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode) { struct dentry *ret = vfs_tmpfile(dentry, mode, 0); - int err = IS_ERR(ret) ? PTR_ERR(ret) : 0; + int err = PTR_ERR_OR_ZERO(ret); pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err); return ret; diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 752bab645879..9d0bc03bf6e4 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -14,6 +14,8 @@ struct ovl_config { char *workdir; bool default_permissions; bool redirect_dir; + bool redirect_follow; + const char *redirect_mode; bool index; }; diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 0daa4354fec4..8c98578d27a1 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -499,7 +499,7 @@ out: return err; fail: - pr_warn_ratelimited("overlay: failed to look up (%s) for ino (%i)\n", + pr_warn_ratelimited("overlayfs: failed to look up (%s) for ino (%i)\n", p->name, err); goto out; } @@ -663,7 +663,10 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx) return PTR_ERR(rdt.cache); } - return iterate_dir(od->realfile, &rdt.ctx); + err = iterate_dir(od->realfile, &rdt.ctx); + ctx->pos = rdt.ctx.pos; + + return err; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index be03578181d2..76440feb79f6 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -33,6 +33,13 @@ module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644); MODULE_PARM_DESC(ovl_redirect_dir_def, "Default to on or off for the redirect_dir feature"); +static bool ovl_redirect_always_follow = + IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW); +module_param_named(redirect_always_follow, ovl_redirect_always_follow, + bool, 0644); +MODULE_PARM_DESC(ovl_redirect_always_follow, + "Follow redirects even if redirect_dir feature is turned off"); + static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX); module_param_named(index, ovl_index_def, bool, 0644); MODULE_PARM_DESC(ovl_index_def, @@ -232,6 +239,7 @@ static void ovl_free_fs(struct ovl_fs *ofs) kfree(ofs->config.lowerdir); kfree(ofs->config.upperdir); kfree(ofs->config.workdir); + kfree(ofs->config.redirect_mode); if (ofs->creator_cred) put_cred(ofs->creator_cred); kfree(ofs); @@ -244,6 +252,7 @@ static void ovl_put_super(struct super_block *sb) ovl_free_fs(ofs); } +/* Sync real dirty inodes in upper filesystem (if it exists) */ static int ovl_sync_fs(struct super_block *sb, int wait) { struct ovl_fs *ofs = sb->s_fs_info; @@ -252,14 +261,24 @@ static int ovl_sync_fs(struct super_block *sb, int wait) if (!ofs->upper_mnt) return 0; - upper_sb = ofs->upper_mnt->mnt_sb; - if (!upper_sb->s_op->sync_fs) + + /* + * If this is a sync(2) call or an emergency sync, all the super blocks + * will be iterated, including upper_sb, so no need to do anything. + * + * If this is a syncfs(2) call, then we do need to call + * sync_filesystem() on upper_sb, but enough if we do it when being + * called with wait == 1. + */ + if (!wait) return 0; - /* real inodes have already been synced by sync_filesystem(ovl_sb) */ + upper_sb = ofs->upper_mnt->mnt_sb; + down_read(&upper_sb->s_umount); - ret = upper_sb->s_op->sync_fs(upper_sb, wait); + ret = sync_filesystem(upper_sb); up_read(&upper_sb->s_umount); + return ret; } @@ -295,6 +314,11 @@ static bool ovl_force_readonly(struct ovl_fs *ofs) return (!ofs->upper_mnt || !ofs->workdir); } +static const char *ovl_redirect_mode_def(void) +{ + return ovl_redirect_dir_def ? "on" : "off"; +} + /** * ovl_show_options * @@ -313,12 +337,10 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry) } if (ofs->config.default_permissions) seq_puts(m, ",default_permissions"); - if (ofs->config.redirect_dir != ovl_redirect_dir_def) - seq_printf(m, ",redirect_dir=%s", - ofs->config.redirect_dir ? "on" : "off"); + if (strcmp(ofs->config.redirect_mode, ovl_redirect_mode_def()) != 0) + seq_printf(m, ",redirect_dir=%s", ofs->config.redirect_mode); if (ofs->config.index != ovl_index_def) - seq_printf(m, ",index=%s", - ofs->config.index ? "on" : "off"); + seq_printf(m, ",index=%s", ofs->config.index ? "on" : "off"); return 0; } @@ -326,7 +348,7 @@ static int ovl_remount(struct super_block *sb, int *flags, char *data) { struct ovl_fs *ofs = sb->s_fs_info; - if (!(*flags & MS_RDONLY) && ovl_force_readonly(ofs)) + if (!(*flags & SB_RDONLY) && ovl_force_readonly(ofs)) return -EROFS; return 0; @@ -348,8 +370,7 @@ enum { OPT_UPPERDIR, OPT_WORKDIR, OPT_DEFAULT_PERMISSIONS, - OPT_REDIRECT_DIR_ON, - OPT_REDIRECT_DIR_OFF, + OPT_REDIRECT_DIR, OPT_INDEX_ON, OPT_INDEX_OFF, OPT_ERR, @@ -360,8 +381,7 @@ static const match_table_t ovl_tokens = { {OPT_UPPERDIR, "upperdir=%s"}, {OPT_WORKDIR, "workdir=%s"}, {OPT_DEFAULT_PERMISSIONS, "default_permissions"}, - {OPT_REDIRECT_DIR_ON, "redirect_dir=on"}, - {OPT_REDIRECT_DIR_OFF, "redirect_dir=off"}, + {OPT_REDIRECT_DIR, "redirect_dir=%s"}, {OPT_INDEX_ON, "index=on"}, {OPT_INDEX_OFF, "index=off"}, {OPT_ERR, NULL} @@ -390,10 +410,37 @@ static char *ovl_next_opt(char **s) return sbegin; } +static int ovl_parse_redirect_mode(struct ovl_config *config, const char *mode) +{ + if (strcmp(mode, "on") == 0) { + config->redirect_dir = true; + /* + * Does not make sense to have redirect creation without + * redirect following. + */ + config->redirect_follow = true; + } else if (strcmp(mode, "follow") == 0) { + config->redirect_follow = true; + } else if (strcmp(mode, "off") == 0) { + if (ovl_redirect_always_follow) + config->redirect_follow = true; + } else if (strcmp(mode, "nofollow") != 0) { + pr_err("overlayfs: bad mount option \"redirect_dir=%s\"\n", + mode); + return -EINVAL; + } + + return 0; +} + static int ovl_parse_opt(char *opt, struct ovl_config *config) { char *p; + config->redirect_mode = kstrdup(ovl_redirect_mode_def(), GFP_KERNEL); + if (!config->redirect_mode) + return -ENOMEM; + while ((p = ovl_next_opt(&opt)) != NULL) { int token; substring_t args[MAX_OPT_ARGS]; @@ -428,12 +475,11 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) config->default_permissions = true; break; - case OPT_REDIRECT_DIR_ON: - config->redirect_dir = true; - break; - - case OPT_REDIRECT_DIR_OFF: - config->redirect_dir = false; + case OPT_REDIRECT_DIR: + kfree(config->redirect_mode); + config->redirect_mode = match_strdup(&args[0]); + if (!config->redirect_mode) + return -ENOMEM; break; case OPT_INDEX_ON: @@ -458,7 +504,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) config->workdir = NULL; } - return 0; + return ovl_parse_redirect_mode(config, config->redirect_mode); } #define OVL_WORKDIR_NAME "work" @@ -1160,7 +1206,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (!cred) goto out_err; - ofs->config.redirect_dir = ovl_redirect_dir_def; ofs->config.index = ovl_index_def; err = ovl_parse_opt((char *) data, &ofs->config); if (err) @@ -1190,7 +1235,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) goto out_err; if (!ofs->workdir) - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; sb->s_stack_depth = ofs->upper_mnt->mnt_sb->s_stack_depth; sb->s_time_gran = ofs->upper_mnt->mnt_sb->s_time_gran; @@ -1203,7 +1248,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) /* If the upper fs is nonexistent, we mark overlayfs r/o too */ if (!ofs->upper_mnt) - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; else if (ofs->upper_mnt->mnt_sb != ofs->same_sb) ofs->same_sb = NULL; @@ -1213,7 +1258,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) goto out_free_oe; if (!ofs->indexdir) - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } /* Show index=off/on in /proc/mounts for any of the reasons above */ @@ -1227,7 +1272,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &ovl_super_operations; sb->s_xattr = ovl_xattr_handlers; sb->s_fs_info = ofs; - sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK; + sb->s_flags |= SB_POSIXACL | SB_NOREMOTELOCK; err = -ENOMEM; root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, 0)); diff --git a/fs/proc/base.c b/fs/proc/base.c index 31934cb9dfc8..60316b52d659 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -443,8 +443,7 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, save_stack_trace_tsk(task, &trace); for (i = 0; i < trace.nr_entries; i++) { - seq_printf(m, "[<%pK>] %pB\n", - (void *)entries[i], (void *)entries[i]); + seq_printf(m, "[<0>] %pB\n", (void *)entries[i]); } unlock_trace(task); } @@ -2269,7 +2268,7 @@ static int show_timer(struct seq_file *m, void *v) notify = timer->it_sigev_notify; seq_printf(m, "ID: %d\n", timer->it_id); - seq_printf(m, "signal: %d/%p\n", + seq_printf(m, "signal: %d/%px\n", timer->sigq->info.si_signo, timer->sigq->info.si_value.sival_ptr); seq_printf(m, "notify: %s/%s.%d\n", diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 225f541f7078..dd0f82622427 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -483,7 +483,7 @@ int proc_fill_super(struct super_block *s, void *data, int silent) /* User space would break if executables or devices appear on proc */ s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV; - s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC; + s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC; s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = PROC_SUPER_MAGIC; diff --git a/fs/proc/root.c b/fs/proc/root.c index 4e42aba97f2e..ede8e64974be 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -91,7 +91,7 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, { struct pid_namespace *ns; - if (flags & MS_KERNMOUNT) { + if (flags & SB_KERNMOUNT) { ns = data; data = NULL; } else { diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 7b635d173213..b786840facd9 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -45,10 +45,10 @@ struct proc_fs_info { static int show_sb_opts(struct seq_file *m, struct super_block *sb) { static const struct proc_fs_info fs_info[] = { - { MS_SYNCHRONOUS, ",sync" }, - { MS_DIRSYNC, ",dirsync" }, - { MS_MANDLOCK, ",mand" }, - { MS_LAZYTIME, ",lazytime" }, + { SB_SYNCHRONOUS, ",sync" }, + { SB_DIRSYNC, ",dirsync" }, + { SB_MANDLOCK, ",mand" }, + { SB_LAZYTIME, ",lazytime" }, { 0, NULL } }; const struct proc_fs_info *fs_infop; diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 3a67cfb142d8..3d46fe302fcb 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -47,7 +47,7 @@ static int qnx4_remount(struct super_block *sb, int *flags, char *data) sync_filesystem(sb); qs = qnx4_sb(sb); qs->Version = QNX4_VERSION; - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } @@ -199,7 +199,7 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent) s->s_op = &qnx4_sops; s->s_magic = QNX4_SUPER_MAGIC; - s->s_flags |= MS_RDONLY; /* Yup, read-only yet */ + s->s_flags |= SB_RDONLY; /* Yup, read-only yet */ /* Check the superblock signature. Since the qnx4 code is dangerous, we should leave as quickly as possible diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 1192422a1c56..4aeb26bcb4d0 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -56,7 +56,7 @@ static int qnx6_show_options(struct seq_file *seq, struct dentry *root) static int qnx6_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } @@ -427,7 +427,7 @@ mmi_success: } s->s_op = &qnx6_sops; s->s_magic = QNX6_SUPER_MAGIC; - s->s_flags |= MS_RDONLY; /* Yup, read-only yet */ + s->s_flags |= SB_RDONLY; /* Yup, read-only yet */ /* ease the later tree level calculations */ sbi = QNX6_SB(s); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 39f1b0b0c76f..020c597ef9b6 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -941,12 +941,13 @@ static int dqinit_needed(struct inode *inode, int type) } /* This routine is guarded by s_umount semaphore */ -static void add_dquot_ref(struct super_block *sb, int type) +static int add_dquot_ref(struct super_block *sb, int type) { struct inode *inode, *old_inode = NULL; #ifdef CONFIG_QUOTA_DEBUG int reserved = 0; #endif + int err = 0; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { @@ -966,7 +967,11 @@ static void add_dquot_ref(struct super_block *sb, int type) reserved = 1; #endif iput(old_inode); - __dquot_initialize(inode, type); + err = __dquot_initialize(inode, type); + if (err) { + iput(inode); + goto out; + } /* * We hold a reference to 'inode' so it couldn't have been @@ -981,7 +986,7 @@ static void add_dquot_ref(struct super_block *sb, int type) } spin_unlock(&sb->s_inode_list_lock); iput(old_inode); - +out: #ifdef CONFIG_QUOTA_DEBUG if (reserved) { quota_error(sb, "Writes happened before quota was turned on " @@ -989,6 +994,7 @@ static void add_dquot_ref(struct super_block *sb, int type) "Please run quotacheck(8)"); } #endif + return err; } /* @@ -2379,10 +2385,11 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, dqopt->flags |= dquot_state_flag(flags, type); spin_unlock(&dq_state_lock); - add_dquot_ref(sb, type); - - return 0; + error = add_dquot_ref(sb, type); + if (error) + dquot_disable(sb, type, flags); + return error; out_file_init: dqopt->files[type] = NULL; iput(inode); @@ -2985,7 +2992,8 @@ static int __init dquot_init(void) pr_info("VFS: Dquot-cache hash table entries: %ld (order %ld," " %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order)); - register_shrinker(&dqcache_shrinker); + if (register_shrinker(&dqcache_shrinker)) + panic("Cannot register dquot shrinker"); return 0; } diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 11a48affa882..b13fc024d2ee 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2106,7 +2106,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, journal_end(th); goto out_inserted_sd; } - } else if (inode->i_sb->s_flags & MS_POSIXACL) { + } else if (inode->i_sb->s_flags & SB_POSIXACL) { reiserfs_warning(inode->i_sb, "jdm-13090", "ACLs aren't enabled in the fs, " "but vfs thinks they are!"); diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 69ff280bdfe8..70057359fbaf 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -1960,7 +1960,7 @@ static int do_journal_release(struct reiserfs_transaction_handle *th, /* * Cancel flushing of old commits. Note that neither of these works * will be requeued because superblock is being shutdown and doesn't - * have MS_ACTIVE set. + * have SB_ACTIVE set. */ reiserfs_cancel_old_flush(sb); /* wait for all commits to finish */ @@ -4302,7 +4302,7 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, int flags) * Avoid queueing work when sb is being shut down. Transaction * will be flushed on journal shutdown. */ - if (sb->s_flags & MS_ACTIVE) + if (sb->s_flags & SB_ACTIVE) queue_delayed_work(REISERFS_SB(sb)->commit_wq, &journal->j_work, HZ / 10); } @@ -4393,7 +4393,7 @@ void reiserfs_abort_journal(struct super_block *sb, int errno) if (!journal->j_errno) journal->j_errno = errno; - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; set_bit(J_ABORTED, &journal->j_state); #ifdef CONFIG_REISERFS_CHECK diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index 64f49cafbc5b..7e288d97adcb 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -390,7 +390,7 @@ void __reiserfs_error(struct super_block *sb, const char *id, return; reiserfs_info(sb, "Remounting filesystem read-only\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; reiserfs_abort_journal(sb, -EIO); } @@ -409,7 +409,7 @@ void reiserfs_abort(struct super_block *sb, int errno, const char *fmt, ...) printk(KERN_CRIT "REISERFS abort (device %s): %s\n", sb->s_id, error_buf); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; reiserfs_abort_journal(sb, errno); } diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 5464ec517702..1fc934d24459 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -121,7 +121,7 @@ void reiserfs_schedule_old_flush(struct super_block *s) * Avoid scheduling flush when sb is being shut down. It can race * with journal shutdown and free still queued delayed work. */ - if (sb_rdonly(s) || !(s->s_flags & MS_ACTIVE)) + if (sb_rdonly(s) || !(s->s_flags & SB_ACTIVE)) return; spin_lock(&sbi->old_work_lock); @@ -252,11 +252,11 @@ static int finish_unfinished(struct super_block *s) #ifdef CONFIG_QUOTA /* Needed for iput() to work correctly and not trash data */ - if (s->s_flags & MS_ACTIVE) { + if (s->s_flags & SB_ACTIVE) { ms_active_set = 0; } else { ms_active_set = 1; - s->s_flags |= MS_ACTIVE; + s->s_flags |= SB_ACTIVE; } /* Turn on quotas so that they are updated correctly */ for (i = 0; i < REISERFS_MAXQUOTAS; i++) { @@ -411,7 +411,7 @@ static int finish_unfinished(struct super_block *s) reiserfs_write_lock(s); if (ms_active_set) /* Restore the flag back */ - s->s_flags &= ~MS_ACTIVE; + s->s_flags &= ~SB_ACTIVE; #endif pathrelse(&path); if (done) @@ -1521,7 +1521,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) goto out_err_unlock; } - if (*mount_flags & MS_RDONLY) { + if (*mount_flags & SB_RDONLY) { reiserfs_write_unlock(s); reiserfs_xattr_init(s, *mount_flags); /* remount read-only */ @@ -1567,7 +1567,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) REISERFS_SB(s)->s_mount_state = sb_umount_state(rs); /* now it is safe to call journal_begin */ - s->s_flags &= ~MS_RDONLY; + s->s_flags &= ~SB_RDONLY; err = journal_begin(&th, s, 10); if (err) goto out_err_unlock; @@ -1575,7 +1575,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) /* Mount a partition which is read-only, read-write */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); REISERFS_SB(s)->s_mount_state = sb_umount_state(rs); - s->s_flags &= ~MS_RDONLY; + s->s_flags &= ~SB_RDONLY; set_sb_umount_state(rs, REISERFS_ERROR_FS); if (!old_format_only(s)) set_sb_mnt_count(rs, sb_mnt_count(rs) + 1); @@ -1590,7 +1590,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) goto out_err_unlock; reiserfs_write_unlock(s); - if (!(*mount_flags & MS_RDONLY)) { + if (!(*mount_flags & SB_RDONLY)) { dquot_resume(s, -1); reiserfs_write_lock(s); finish_unfinished(s); @@ -2055,7 +2055,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) if (bdev_read_only(s->s_bdev) && !sb_rdonly(s)) { SWARN(silent, s, "clm-7000", "Detected readonly device, marking FS readonly"); - s->s_flags |= MS_RDONLY; + s->s_flags |= SB_RDONLY; } args.objectid = REISERFS_ROOT_OBJECTID; args.dirid = REISERFS_ROOT_PARENT_OBJECTID; @@ -2591,7 +2591,6 @@ out: return err; if (inode->i_size < off + len - towrite) i_size_write(inode, off + len - towrite); - inode->i_version++; inode->i_mtime = inode->i_ctime = current_time(inode); mark_inode_dirty(inode); return len - towrite; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 46492fb37a4c..5dbf5324bdda 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -959,7 +959,7 @@ int reiserfs_lookup_privroot(struct super_block *s) /* * We need to take a copy of the mount flags since things like - * MS_RDONLY don't get set until *after* we're called. + * SB_RDONLY don't get set until *after* we're called. * mount_flags != mount_options */ int reiserfs_xattr_init(struct super_block *s, int mount_flags) @@ -971,7 +971,7 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags) if (err) goto error; - if (d_really_is_negative(privroot) && !(mount_flags & MS_RDONLY)) { + if (d_really_is_negative(privroot) && !(mount_flags & SB_RDONLY)) { inode_lock(d_inode(s->s_root)); err = create_privroot(REISERFS_SB(s)->priv_root); inode_unlock(d_inode(s->s_root)); @@ -999,11 +999,11 @@ error: clear_bit(REISERFS_POSIXACL, &REISERFS_SB(s)->s_mount_opt); } - /* The super_block MS_POSIXACL must mirror the (no)acl mount option. */ + /* The super_block SB_POSIXACL must mirror the (no)acl mount option. */ if (reiserfs_posixacl(s)) - s->s_flags |= MS_POSIXACL; + s->s_flags |= SB_POSIXACL; else - s->s_flags &= ~MS_POSIXACL; + s->s_flags &= ~SB_POSIXACL; return err; } diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 0186fe6d39f3..8f06fd1f3d69 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -451,7 +451,7 @@ static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf) static int romfs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } @@ -502,7 +502,7 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_maxbytes = 0xFFFFFFFF; sb->s_magic = ROMFS_MAGIC; - sb->s_flags |= MS_RDONLY | MS_NOATIME; + sb->s_flags |= SB_RDONLY | SB_NOATIME; sb->s_op = &romfs_super_ops; #ifdef CONFIG_ROMFS_ON_MTD diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index cf01e15a7b16..8a73b97217c8 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -195,7 +195,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) (u64) le64_to_cpu(sblk->id_table_start)); sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; sb->s_op = &squashfs_super_ops; err = -ENOMEM; @@ -373,7 +373,7 @@ static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf) static int squashfs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } diff --git a/fs/statfs.c b/fs/statfs.c index b072a8bab71a..5b2a24f0f263 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -35,11 +35,11 @@ static int flags_by_mnt(int mnt_flags) static int flags_by_sb(int s_flags) { int flags = 0; - if (s_flags & MS_SYNCHRONOUS) + if (s_flags & SB_SYNCHRONOUS) flags |= ST_SYNCHRONOUS; - if (s_flags & MS_MANDLOCK) + if (s_flags & SB_MANDLOCK) flags |= ST_MANDLOCK; - if (s_flags & MS_RDONLY) + if (s_flags & SB_RDONLY) flags |= ST_RDONLY; return flags; } diff --git a/fs/super.c b/fs/super.c index d4e33e8f1e6f..06bd25d90ba5 100644 --- a/fs/super.c +++ b/fs/super.c @@ -191,6 +191,24 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, INIT_LIST_HEAD(&s->s_mounts); s->s_user_ns = get_user_ns(user_ns); + init_rwsem(&s->s_umount); + lockdep_set_class(&s->s_umount, &type->s_umount_key); + /* + * sget() can have s_umount recursion. + * + * When it cannot find a suitable sb, it allocates a new + * one (this one), and tries again to find a suitable old + * one. + * + * In case that succeeds, it will acquire the s_umount + * lock of the old one. Since these are clearly distrinct + * locks, and this object isn't exposed yet, there's no + * risk of deadlocks. + * + * Annotate this by putting this lock in a different + * subclass. + */ + down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); if (security_sb_alloc(s)) goto fail; @@ -218,25 +236,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, goto fail; if (list_lru_init_memcg(&s->s_inode_lru)) goto fail; - - init_rwsem(&s->s_umount); - lockdep_set_class(&s->s_umount, &type->s_umount_key); - /* - * sget() can have s_umount recursion. - * - * When it cannot find a suitable sb, it allocates a new - * one (this one), and tries again to find a suitable old - * one. - * - * In case that succeeds, it will acquire the s_umount - * lock of the old one. Since these are clearly distrinct - * locks, and this object isn't exposed yet, there's no - * risk of deadlocks. - * - * Annotate this by putting this lock in a different - * subclass. - */ - down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); s->s_count = 1; atomic_set(&s->s_active, 1); mutex_init(&s->s_vfs_rename_mutex); @@ -518,7 +517,11 @@ retry: hlist_add_head(&s->s_instances, &type->fs_supers); spin_unlock(&sb_lock); get_filesystem(type); - register_shrinker(&s->s_shrink); + err = register_shrinker(&s->s_shrink); + if (err) { + deactivate_locked_super(s); + s = ERR_PTR(err); + } return s; } diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 20b8f82e115b..fb49510c5dcf 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -30,7 +30,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, void *ns; bool new_sb; - if (!(flags & MS_KERNMOUNT)) { + if (!(flags & SB_KERNMOUNT)) { if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) return ERR_PTR(-EPERM); } diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 3c47b7d5d4cf..bec9f79adb25 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -63,7 +63,7 @@ static int sysv_remount(struct super_block *sb, int *flags, char *data) sync_filesystem(sb); if (sbi->s_forced_ro) - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } diff --git a/fs/sysv/super.c b/fs/sysv/super.c index 0d56e486b392..89765ddfb738 100644 --- a/fs/sysv/super.c +++ b/fs/sysv/super.c @@ -333,7 +333,7 @@ static int complete_read_super(struct super_block *sb, int silent, int size) /* set up enough so that it can read an inode */ sb->s_op = &sysv_sops; if (sbi->s_forced_ro) - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; if (sbi->s_truncate) sb->s_d_op = &sysv_dentry_operations; root_inode = sysv_iget(sb, SYSV_ROOT_INO); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index a02aa59d1e24..dfe85069586e 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1406,7 +1406,7 @@ int ubifs_update_time(struct inode *inode, struct timespec *time, if (flags & S_MTIME) inode->i_mtime = *time; - if (!(inode->i_sb->s_flags & MS_LAZYTIME)) + if (!(inode->i_sb->s_flags & SB_LAZYTIME)) iflags |= I_DIRTY_SYNC; release = ui->dirty; diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index 3be28900bf37..fe77e9625e84 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -84,7 +84,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err) if (!c->ro_error) { c->ro_error = 1; c->no_chk_data_crc = 0; - c->vfs_sb->s_flags |= MS_RDONLY; + c->vfs_sb->s_flags |= SB_RDONLY; ubifs_warn(c, "switched to read-only mode, error %d", err); dump_stack(); } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 7503e7cdf870..0beb285b143d 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -968,7 +968,7 @@ static int parse_standard_option(const char *option) pr_notice("UBIFS: parse %s\n", option); if (!strcmp(option, "sync")) - return MS_SYNCHRONOUS; + return SB_SYNCHRONOUS; return 0; } @@ -1160,8 +1160,8 @@ static int mount_ubifs(struct ubifs_info *c) size_t sz; c->ro_mount = !!sb_rdonly(c->vfs_sb); - /* Suppress error messages while probing if MS_SILENT is set */ - c->probing = !!(c->vfs_sb->s_flags & MS_SILENT); + /* Suppress error messages while probing if SB_SILENT is set */ + c->probing = !!(c->vfs_sb->s_flags & SB_SILENT); err = init_constants_early(c); if (err) @@ -1852,7 +1852,7 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) return err; } - if (c->ro_mount && !(*flags & MS_RDONLY)) { + if (c->ro_mount && !(*flags & SB_RDONLY)) { if (c->ro_error) { ubifs_msg(c, "cannot re-mount R/W due to prior errors"); return -EROFS; @@ -1864,7 +1864,7 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) err = ubifs_remount_rw(c); if (err) return err; - } else if (!c->ro_mount && (*flags & MS_RDONLY)) { + } else if (!c->ro_mount && (*flags & SB_RDONLY)) { if (c->ro_error) { ubifs_msg(c, "cannot re-mount R/O due to prior errors"); return -EROFS; @@ -2117,7 +2117,7 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, */ ubi = open_ubi(name, UBI_READONLY); if (IS_ERR(ubi)) { - if (!(flags & MS_SILENT)) + if (!(flags & SB_SILENT)) pr_err("UBIFS error (pid: %d): cannot open \"%s\", error %d", current->pid, name, (int)PTR_ERR(ubi)); return ERR_CAST(ubi); @@ -2143,18 +2143,18 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, kfree(c); /* A new mount point for already mounted UBIFS */ dbg_gen("this ubi volume is already mounted"); - if (!!(flags & MS_RDONLY) != c1->ro_mount) { + if (!!(flags & SB_RDONLY) != c1->ro_mount) { err = -EBUSY; goto out_deact; } } else { - err = ubifs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0); + err = ubifs_fill_super(sb, data, flags & SB_SILENT ? 1 : 0); if (err) goto out_deact; /* We do not support atime */ - sb->s_flags |= MS_ACTIVE; + sb->s_flags |= SB_ACTIVE; #ifndef CONFIG_UBIFS_ATIME_SUPPORT - sb->s_flags |= MS_NOATIME; + sb->s_flags |= SB_NOATIME; #else ubifs_msg(c, "full atime support is enabled."); #endif diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 63c7468147eb..5ee7af879cc4 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1201,7 +1201,7 @@ struct ubifs_debug_info; * @need_recovery: %1 if the file-system needs recovery * @replaying: %1 during journal replay * @mounting: %1 while mounting - * @probing: %1 while attempting to mount if MS_SILENT mount flag is set + * @probing: %1 while attempting to mount if SB_SILENT mount flag is set * @remounting_rw: %1 while re-mounting from R/O mode to R/W mode * @replay_list: temporary list used during journal replay * @replay_buds: list of buds to replay @@ -1850,7 +1850,7 @@ __printf(2, 3) void ubifs_warn(const struct ubifs_info *c, const char *fmt, ...); /* * A conditional variant of 'ubifs_err()' which doesn't output anything - * if probing (ie. MS_SILENT set). + * if probing (ie. SB_SILENT set). */ #define ubifs_errc(c, fmt, ...) \ do { \ diff --git a/fs/udf/super.c b/fs/udf/super.c index f80e0a0f24d3..f73239a9a97d 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -650,7 +650,7 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options) sync_filesystem(sb); if (lvidiu) { int write_rev = le16_to_cpu(lvidiu->minUDFWriteRev); - if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & MS_RDONLY)) + if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & SB_RDONLY)) return -EACCES; } @@ -673,10 +673,10 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options) sbi->s_dmode = uopt.dmode; write_unlock(&sbi->s_cred_lock); - if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) + if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) goto out_unlock; - if (*flags & MS_RDONLY) + if (*flags & SB_RDONLY) udf_close_lvid(sb); else udf_open_lvid(sb); diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index b5cd79065ef9..e727ee07dbe4 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -115,7 +115,7 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) ubh_mark_buffer_dirty (USPI_UBH(uspi)); ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); @@ -205,7 +205,7 @@ do_more: ubh_mark_buffer_dirty (USPI_UBH(uspi)); ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); if (overflow) { @@ -567,7 +567,7 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment, ubh_mark_buffer_dirty (USPI_UBH(uspi)); ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); @@ -688,7 +688,7 @@ cg_found: succed: ubh_mark_buffer_dirty (USPI_UBH(uspi)); ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 916b4a428933..e1ef0f0a1353 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -112,7 +112,7 @@ void ufs_free_inode (struct inode * inode) ubh_mark_buffer_dirty (USPI_UBH(uspi)); ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); @@ -146,14 +146,14 @@ static void ufs2_init_inodes_chunk(struct super_block *sb, set_buffer_uptodate(bh); mark_buffer_dirty(bh); unlock_buffer(bh); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) sync_dirty_buffer(bh); brelse(bh); } fs32_add(sb, &ucg->cg_u.cg_u2.cg_initediblk, uspi->s_inopb); ubh_mark_buffer_dirty(UCPI_UBH(ucpi)); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); UFSD("EXIT\n"); @@ -284,7 +284,7 @@ cg_found: } ubh_mark_buffer_dirty (USPI_UBH(uspi)); ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); @@ -330,7 +330,7 @@ cg_found: ufs2_inode->ui_birthnsec = cpu_to_fs32(sb, ts.tv_nsec); mark_buffer_dirty(bh); unlock_buffer(bh); - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) sync_dirty_buffer(bh); brelse(bh); } diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 6440003f8ddc..4d497e9c6883 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -282,7 +282,7 @@ void ufs_error (struct super_block * sb, const char * function, usb1->fs_clean = UFS_FSBAD; ubh_mark_buffer_dirty(USPI_UBH(uspi)); ufs_mark_sb_dirty(sb); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } va_start(args, fmt); vaf.fmt = fmt; @@ -320,7 +320,7 @@ void ufs_panic (struct super_block * sb, const char * function, va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; pr_crit("panic (device %s): %s: %pV\n", sb->s_id, function, &vaf); va_end(args); @@ -905,7 +905,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) if (!sb_rdonly(sb)) { if (!silent) pr_info("ufstype=old is supported read-only\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } break; @@ -921,7 +921,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) if (!sb_rdonly(sb)) { if (!silent) pr_info("ufstype=nextstep is supported read-only\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } break; @@ -937,7 +937,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) if (!sb_rdonly(sb)) { if (!silent) pr_info("ufstype=nextstep-cd is supported read-only\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } break; @@ -953,7 +953,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) if (!sb_rdonly(sb)) { if (!silent) pr_info("ufstype=openstep is supported read-only\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } break; @@ -968,7 +968,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) if (!sb_rdonly(sb)) { if (!silent) pr_info("ufstype=hp is supported read-only\n"); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } break; default: @@ -1125,21 +1125,21 @@ magic_found: break; case UFS_FSACTIVE: pr_err("%s(): fs is active\n", __func__); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; break; case UFS_FSBAD: pr_err("%s(): fs is bad\n", __func__); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; break; default: pr_err("%s(): can't grok fs_clean 0x%x\n", __func__, usb1->fs_clean); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; break; } } else { pr_err("%s(): fs needs fsck\n", __func__); - sb->s_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } /* @@ -1328,7 +1328,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) return -EINVAL; } - if ((bool)(*mount_flags & MS_RDONLY) == sb_rdonly(sb)) { + if ((bool)(*mount_flags & SB_RDONLY) == sb_rdonly(sb)) { UFS_SB(sb)->s_mount_opt = new_mount_opt; mutex_unlock(&UFS_SB(sb)->s_lock); return 0; @@ -1337,7 +1337,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) /* * fs was mouted as rw, remounting ro */ - if (*mount_flags & MS_RDONLY) { + if (*mount_flags & SB_RDONLY) { ufs_put_super_internal(sb); usb1->fs_time = cpu_to_fs32(sb, get_seconds()); if ((flags & UFS_ST_MASK) == UFS_ST_SUN @@ -1346,7 +1346,7 @@ 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_flags |= MS_RDONLY; + sb->s_flags |= SB_RDONLY; } else { /* * fs was mounted as ro, remounting rw @@ -1370,7 +1370,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) mutex_unlock(&UFS_SB(sb)->s_lock); return -EPERM; } - sb->s_flags &= ~MS_RDONLY; + sb->s_flags &= ~SB_RDONLY; #endif } UFS_SB(sb)->s_mount_opt = new_mount_opt; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index ac9a4e65ca49..41a75f9f23fd 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -570,11 +570,14 @@ out: static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { + struct userfaultfd_ctx *release_new_ctx; + if (WARN_ON_ONCE(current->flags & PF_EXITING)) goto out; ewq->ctx = ctx; init_waitqueue_entry(&ewq->wq, current); + release_new_ctx = NULL; spin_lock(&ctx->event_wqh.lock); /* @@ -601,8 +604,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, new = (struct userfaultfd_ctx *) (unsigned long) ewq->msg.arg.reserved.reserved1; - - userfaultfd_ctx_put(new); + release_new_ctx = new; } break; } @@ -617,6 +619,20 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, __set_current_state(TASK_RUNNING); spin_unlock(&ctx->event_wqh.lock); + if (release_new_ctx) { + struct vm_area_struct *vma; + struct mm_struct *mm = release_new_ctx->mm; + + /* the various vma->vm_userfaultfd_ctx still points to it */ + down_write(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) + if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) + vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + up_write(&mm->mmap_sem); + + userfaultfd_ctx_put(release_new_ctx); + } + /* * ctx may go away after this if the userfault pseudo fd is * already released. diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 0da80019a917..83ed7715f856 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -702,7 +702,7 @@ xfs_alloc_ag_vextent( ASSERT(args->agbno % args->alignment == 0); /* if not file data, insert new block into the reverse map btree */ - if (args->oinfo.oi_owner != XFS_RMAP_OWN_UNKNOWN) { + if (!xfs_rmap_should_skip_owner_update(&args->oinfo)) { error = xfs_rmap_alloc(args->tp, args->agbp, args->agno, args->agbno, args->len, &args->oinfo); if (error) @@ -1682,7 +1682,7 @@ xfs_free_ag_extent( bno_cur = cnt_cur = NULL; mp = tp->t_mountp; - if (oinfo->oi_owner != XFS_RMAP_OWN_UNKNOWN) { + if (!xfs_rmap_should_skip_owner_update(oinfo)) { error = xfs_rmap_free(tp, agbp, agno, bno, len, oinfo); if (error) goto error0; diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 6249c92671de..a76914db72ef 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -212,6 +212,7 @@ xfs_attr_set( int flags) { struct xfs_mount *mp = dp->i_mount; + struct xfs_buf *leaf_bp = NULL; struct xfs_da_args args; struct xfs_defer_ops dfops; struct xfs_trans_res tres; @@ -327,9 +328,16 @@ xfs_attr_set( * GROT: another possible req'mt for a double-split btree op. */ xfs_defer_init(args.dfops, args.firstblock); - error = xfs_attr_shortform_to_leaf(&args); + error = xfs_attr_shortform_to_leaf(&args, &leaf_bp); if (error) goto out_defer_cancel; + /* + * Prevent the leaf buffer from being unlocked so that a + * concurrent AIL push cannot grab the half-baked leaf + * buffer and run into problems with the write verifier. + */ + xfs_trans_bhold(args.trans, leaf_bp); + xfs_defer_bjoin(args.dfops, leaf_bp); xfs_defer_ijoin(args.dfops, dp); error = xfs_defer_finish(&args.trans, args.dfops); if (error) @@ -337,13 +345,14 @@ xfs_attr_set( /* * Commit the leaf transformation. We'll need another (linked) - * transaction to add the new attribute to the leaf. + * transaction to add the new attribute to the leaf, which + * means that we have to hold & join the leaf buffer here too. */ - error = xfs_trans_roll_inode(&args.trans, dp); if (error) goto out; - + xfs_trans_bjoin(args.trans, leaf_bp); + leaf_bp = NULL; } if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) @@ -374,8 +383,9 @@ xfs_attr_set( out_defer_cancel: xfs_defer_cancel(&dfops); - args.trans = NULL; out: + if (leaf_bp) + xfs_trans_brelse(args.trans, leaf_bp); if (args.trans) xfs_trans_cancel(args.trans); xfs_iunlock(dp, XFS_ILOCK_EXCL); diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 53cc8b986eac..601eaa36f1ad 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -735,10 +735,13 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args) } /* - * Convert from using the shortform to the leaf. + * Convert from using the shortform to the leaf. On success, return the + * buffer so that we can keep it locked until we're totally done with it. */ int -xfs_attr_shortform_to_leaf(xfs_da_args_t *args) +xfs_attr_shortform_to_leaf( + struct xfs_da_args *args, + struct xfs_buf **leaf_bp) { xfs_inode_t *dp; xfs_attr_shortform_t *sf; @@ -818,7 +821,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args) sfe = XFS_ATTR_SF_NEXTENTRY(sfe); } error = 0; - + *leaf_bp = bp; out: kmem_free(tmpbuffer); return error; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index f7dda0c237b0..894124efb421 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -48,7 +48,8 @@ void xfs_attr_shortform_create(struct xfs_da_args *args); void xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff); int xfs_attr_shortform_lookup(struct xfs_da_args *args); int xfs_attr_shortform_getvalue(struct xfs_da_args *args); -int xfs_attr_shortform_to_leaf(struct xfs_da_args *args); +int xfs_attr_shortform_to_leaf(struct xfs_da_args *args, + struct xfs_buf **leaf_bp); int xfs_attr_shortform_remove(struct xfs_da_args *args); int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp); int xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 08df809e2315..1bddbba6b80c 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -5136,7 +5136,7 @@ __xfs_bunmapi( * blowing out the transaction with a mix of EFIs and reflink * adjustments. */ - if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) + if (tp && xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res)); else max_len = len; @@ -5662,7 +5662,8 @@ xfs_bmap_collapse_extents( *done = true; goto del_cursor; } - XFS_WANT_CORRUPTED_RETURN(mp, !isnullstartblock(got.br_startblock)); + XFS_WANT_CORRUPTED_GOTO(mp, !isnullstartblock(got.br_startblock), + del_cursor); new_startoff = got.br_startoff - offset_shift_fsb; if (xfs_iext_peek_prev_extent(ifp, &icur, &prev)) { @@ -5767,7 +5768,8 @@ xfs_bmap_insert_extents( goto del_cursor; } } - XFS_WANT_CORRUPTED_RETURN(mp, !isnullstartblock(got.br_startblock)); + XFS_WANT_CORRUPTED_GOTO(mp, !isnullstartblock(got.br_startblock), + del_cursor); if (stop_fsb >= got.br_startoff + got.br_blockcount) { error = -EIO; diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 072ebfe1d6ae..087fea02c389 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -249,6 +249,10 @@ xfs_defer_trans_roll( for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE); + /* Hold the (previously bjoin'd) buffer locked across the roll. */ + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) + xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]); + trace_xfs_defer_trans_roll((*tp)->t_mountp, dop); /* Roll the transaction. */ @@ -264,6 +268,12 @@ xfs_defer_trans_roll( for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0); + /* Rejoin the buffers and dirty them so the log moves forward. */ + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) { + xfs_trans_bjoin(*tp, dop->dop_bufs[i]); + xfs_trans_bhold(*tp, dop->dop_bufs[i]); + } + return error; } @@ -295,6 +305,31 @@ xfs_defer_ijoin( } } + ASSERT(0); + return -EFSCORRUPTED; +} + +/* + * Add this buffer to the deferred op. Each joined buffer is relogged + * each time we roll the transaction. + */ +int +xfs_defer_bjoin( + struct xfs_defer_ops *dop, + struct xfs_buf *bp) +{ + int i; + + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS; i++) { + if (dop->dop_bufs[i] == bp) + return 0; + else if (dop->dop_bufs[i] == NULL) { + dop->dop_bufs[i] = bp; + return 0; + } + } + + ASSERT(0); return -EFSCORRUPTED; } @@ -493,9 +528,7 @@ xfs_defer_init( struct xfs_defer_ops *dop, xfs_fsblock_t *fbp) { - dop->dop_committed = false; - dop->dop_low = false; - memset(&dop->dop_inodes, 0, sizeof(dop->dop_inodes)); + memset(dop, 0, sizeof(struct xfs_defer_ops)); *fbp = NULLFSBLOCK; INIT_LIST_HEAD(&dop->dop_intake); INIT_LIST_HEAD(&dop->dop_pending); diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index d4f046dd44bd..045beacdd37d 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -59,6 +59,7 @@ enum xfs_defer_ops_type { }; #define XFS_DEFER_OPS_NR_INODES 2 /* join up to two inodes */ +#define XFS_DEFER_OPS_NR_BUFS 2 /* join up to two buffers */ struct xfs_defer_ops { bool dop_committed; /* did any trans commit? */ @@ -66,8 +67,9 @@ struct xfs_defer_ops { struct list_head dop_intake; /* unlogged pending work */ struct list_head dop_pending; /* logged pending work */ - /* relog these inodes with each roll */ + /* relog these with each roll */ struct xfs_inode *dop_inodes[XFS_DEFER_OPS_NR_INODES]; + struct xfs_buf *dop_bufs[XFS_DEFER_OPS_NR_BUFS]; }; void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type, @@ -77,6 +79,7 @@ void xfs_defer_cancel(struct xfs_defer_ops *dop); void xfs_defer_init(struct xfs_defer_ops *dop, xfs_fsblock_t *fbp); bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop); int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip); +int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp); /* Description of a deferred type. */ struct xfs_defer_op_type { diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index de3f04a98656..3b57ef0f2f76 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -920,8 +920,7 @@ STATIC xfs_agnumber_t xfs_ialloc_ag_select( xfs_trans_t *tp, /* transaction pointer */ xfs_ino_t parent, /* parent directory inode number */ - umode_t mode, /* bits set to indicate file type */ - int okalloc) /* ok to allocate more space */ + umode_t mode) /* bits set to indicate file type */ { xfs_agnumber_t agcount; /* number of ag's in the filesystem */ xfs_agnumber_t agno; /* current ag number */ @@ -978,9 +977,6 @@ xfs_ialloc_ag_select( return agno; } - if (!okalloc) - goto nextag; - if (!pag->pagf_init) { error = xfs_alloc_pagf_init(mp, tp, agno, flags); if (error) @@ -1680,7 +1676,6 @@ xfs_dialloc( struct xfs_trans *tp, xfs_ino_t parent, umode_t mode, - int okalloc, struct xfs_buf **IO_agbp, xfs_ino_t *inop) { @@ -1692,6 +1687,7 @@ xfs_dialloc( int noroom = 0; xfs_agnumber_t start_agno; struct xfs_perag *pag; + int okalloc = 1; if (*IO_agbp) { /* @@ -1707,7 +1703,7 @@ xfs_dialloc( * We do not have an agbp, so select an initial allocation * group for inode allocation. */ - start_agno = xfs_ialloc_ag_select(tp, parent, mode, okalloc); + start_agno = xfs_ialloc_ag_select(tp, parent, mode); if (start_agno == NULLAGNUMBER) { *inop = NULLFSINO; return 0; diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index d2bdcd5e7312..66a8de0b1caa 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -81,7 +81,6 @@ xfs_dialloc( struct xfs_trans *tp, /* transaction pointer */ xfs_ino_t parent, /* parent inode (directory) */ umode_t mode, /* mode bits for new inode */ - int okalloc, /* ok to allocate more space */ struct xfs_buf **agbp, /* buf for a.g. inode header */ xfs_ino_t *inop); /* inode number allocated */ diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c index 89bf16b4d937..b0f31791c7e6 100644 --- a/fs/xfs/libxfs/xfs_iext_tree.c +++ b/fs/xfs/libxfs/xfs_iext_tree.c @@ -632,8 +632,6 @@ xfs_iext_insert( struct xfs_iext_leaf *new = NULL; int nr_entries, i; - trace_xfs_iext_insert(ip, cur, state, _RET_IP_); - if (ifp->if_height == 0) xfs_iext_alloc_root(ifp, cur); else if (ifp->if_height == 1) @@ -661,6 +659,8 @@ xfs_iext_insert( xfs_iext_set(cur_rec(cur), irec); ifp->if_bytes += sizeof(struct xfs_iext_rec); + trace_xfs_iext_insert(ip, cur, state, _RET_IP_); + if (new) xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2); } diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 585b35d34142..c40d26763075 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1488,27 +1488,12 @@ __xfs_refcount_cow_alloc( xfs_extlen_t aglen, struct xfs_defer_ops *dfops) { - int error; - trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_private.a.agno, agbno, aglen); /* Add refcount btree reservation */ - error = xfs_refcount_adjust_cow(rcur, agbno, aglen, + return xfs_refcount_adjust_cow(rcur, agbno, aglen, XFS_REFCOUNT_ADJUST_COW_ALLOC, dfops); - if (error) - return error; - - /* Add rmap entry */ - if (xfs_sb_version_hasrmapbt(&rcur->bc_mp->m_sb)) { - error = xfs_rmap_alloc_extent(rcur->bc_mp, dfops, - rcur->bc_private.a.agno, - agbno, aglen, XFS_RMAP_OWN_COW); - if (error) - return error; - } - - return error; } /* @@ -1521,27 +1506,12 @@ __xfs_refcount_cow_free( xfs_extlen_t aglen, struct xfs_defer_ops *dfops) { - int error; - trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_private.a.agno, agbno, aglen); /* Remove refcount btree reservation */ - error = xfs_refcount_adjust_cow(rcur, agbno, aglen, + return xfs_refcount_adjust_cow(rcur, agbno, aglen, XFS_REFCOUNT_ADJUST_COW_FREE, dfops); - if (error) - return error; - - /* Remove rmap entry */ - if (xfs_sb_version_hasrmapbt(&rcur->bc_mp->m_sb)) { - error = xfs_rmap_free_extent(rcur->bc_mp, dfops, - rcur->bc_private.a.agno, - agbno, aglen, XFS_RMAP_OWN_COW); - if (error) - return error; - } - - return error; } /* Record a CoW staging extent in the refcount btree. */ @@ -1552,11 +1522,19 @@ xfs_refcount_alloc_cow_extent( xfs_fsblock_t fsb, xfs_extlen_t len) { + int error; + if (!xfs_sb_version_hasreflink(&mp->m_sb)) return 0; - return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW, + error = __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW, fsb, len); + if (error) + return error; + + /* Add rmap entry */ + return xfs_rmap_alloc_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb), + XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); } /* Forget a CoW staging event in the refcount btree. */ @@ -1567,9 +1545,17 @@ xfs_refcount_free_cow_extent( xfs_fsblock_t fsb, xfs_extlen_t len) { + int error; + if (!xfs_sb_version_hasreflink(&mp->m_sb)) return 0; + /* Remove rmap entry */ + error = xfs_rmap_free_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb), + XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); + if (error) + return error; + return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_FREE_COW, fsb, len); } diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index dd019cee1b3b..50db920ceeeb 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -368,6 +368,51 @@ xfs_rmap_lookup_le_range( } /* + * Perform all the relevant owner checks for a removal op. If we're doing an + * unknown-owner removal then we have no owner information to check. + */ +static int +xfs_rmap_free_check_owner( + struct xfs_mount *mp, + uint64_t ltoff, + struct xfs_rmap_irec *rec, + xfs_fsblock_t bno, + xfs_filblks_t len, + uint64_t owner, + uint64_t offset, + unsigned int flags) +{ + int error = 0; + + if (owner == XFS_RMAP_OWN_UNKNOWN) + return 0; + + /* Make sure the unwritten flag matches. */ + XFS_WANT_CORRUPTED_GOTO(mp, (flags & XFS_RMAP_UNWRITTEN) == + (rec->rm_flags & XFS_RMAP_UNWRITTEN), out); + + /* Make sure the owner matches what we expect to find in the tree. */ + XFS_WANT_CORRUPTED_GOTO(mp, owner == rec->rm_owner, out); + + /* Check the offset, if necessary. */ + if (XFS_RMAP_NON_INODE_OWNER(owner)) + goto out; + + if (flags & XFS_RMAP_BMBT_BLOCK) { + XFS_WANT_CORRUPTED_GOTO(mp, rec->rm_flags & XFS_RMAP_BMBT_BLOCK, + out); + } else { + XFS_WANT_CORRUPTED_GOTO(mp, rec->rm_offset <= offset, out); + XFS_WANT_CORRUPTED_GOTO(mp, + ltoff + rec->rm_blockcount >= offset + len, + out); + } + +out: + return error; +} + +/* * Find the extent in the rmap btree and remove it. * * The record we find should always be an exact match for the extent that we're @@ -444,33 +489,40 @@ xfs_rmap_unmap( goto out_done; } - /* Make sure the unwritten flag matches. */ - XFS_WANT_CORRUPTED_GOTO(mp, (flags & XFS_RMAP_UNWRITTEN) == - (ltrec.rm_flags & XFS_RMAP_UNWRITTEN), out_error); + /* + * If we're doing an unknown-owner removal for EFI recovery, we expect + * to find the full range in the rmapbt or nothing at all. If we + * don't find any rmaps overlapping either end of the range, we're + * done. Hopefully this means that the EFI creator already queued + * (and finished) a RUI to remove the rmap. + */ + if (owner == XFS_RMAP_OWN_UNKNOWN && + ltrec.rm_startblock + ltrec.rm_blockcount <= bno) { + struct xfs_rmap_irec rtrec; + + error = xfs_btree_increment(cur, 0, &i); + if (error) + goto out_error; + if (i == 0) + goto out_done; + error = xfs_rmap_get_rec(cur, &rtrec, &i); + if (error) + goto out_error; + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, out_error); + if (rtrec.rm_startblock >= bno + len) + goto out_done; + } /* Make sure the extent we found covers the entire freeing range. */ XFS_WANT_CORRUPTED_GOTO(mp, ltrec.rm_startblock <= bno && - ltrec.rm_startblock + ltrec.rm_blockcount >= - bno + len, out_error); + ltrec.rm_startblock + ltrec.rm_blockcount >= + bno + len, out_error); - /* Make sure the owner matches what we expect to find in the tree. */ - XFS_WANT_CORRUPTED_GOTO(mp, owner == ltrec.rm_owner || - XFS_RMAP_NON_INODE_OWNER(owner), out_error); - - /* Check the offset, if necessary. */ - if (!XFS_RMAP_NON_INODE_OWNER(owner)) { - if (flags & XFS_RMAP_BMBT_BLOCK) { - XFS_WANT_CORRUPTED_GOTO(mp, - ltrec.rm_flags & XFS_RMAP_BMBT_BLOCK, - out_error); - } else { - XFS_WANT_CORRUPTED_GOTO(mp, - ltrec.rm_offset <= offset, out_error); - XFS_WANT_CORRUPTED_GOTO(mp, - ltoff + ltrec.rm_blockcount >= offset + len, - out_error); - } - } + /* Check owner information. */ + error = xfs_rmap_free_check_owner(mp, ltoff, <rec, bno, len, owner, + offset, flags); + if (error) + goto out_error; if (ltrec.rm_startblock == bno && ltrec.rm_blockcount == len) { /* exact match, simply remove the record from rmap tree */ @@ -664,6 +716,7 @@ xfs_rmap_map( flags |= XFS_RMAP_UNWRITTEN; trace_xfs_rmap_map(mp, cur->bc_private.a.agno, bno, len, unwritten, oinfo); + ASSERT(!xfs_rmap_should_skip_owner_update(oinfo)); /* * For the initial lookup, look for an exact match or the left-adjacent diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 466ede637080..0fcd5b1ba729 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -61,7 +61,21 @@ static inline void xfs_rmap_skip_owner_update( struct xfs_owner_info *oi) { - oi->oi_owner = XFS_RMAP_OWN_UNKNOWN; + xfs_rmap_ag_owner(oi, XFS_RMAP_OWN_NULL); +} + +static inline bool +xfs_rmap_should_skip_owner_update( + struct xfs_owner_info *oi) +{ + return oi->oi_owner == XFS_RMAP_OWN_NULL; +} + +static inline void +xfs_rmap_any_owner_update( + struct xfs_owner_info *oi) +{ + xfs_rmap_ag_owner(oi, XFS_RMAP_OWN_UNKNOWN); } /* Reverse mapping functions. */ diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 637b7a892313..f120fb20452f 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -318,8 +318,20 @@ xfs_scrub_dinode( /* di_mode */ mode = be16_to_cpu(dip->di_mode); - if (mode & ~(S_IALLUGO | S_IFMT)) + switch (mode & S_IFMT) { + case S_IFLNK: + case S_IFREG: + case S_IFDIR: + case S_IFCHR: + case S_IFBLK: + case S_IFIFO: + case S_IFSOCK: + /* mode is recognized */ + break; + default: xfs_scrub_ino_set_corrupt(sc, ino, bp); + break; + } /* v1/v2 fields */ switch (dip->di_version) { diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index 8e58ba842946..3d9037eceaf1 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -107,7 +107,7 @@ xfs_scrub_quota_item( unsigned long long rcount; xfs_ino_t fs_icount; - offset = id * qi->qi_dqperchunk; + offset = id / qi->qi_dqperchunk; /* * We fed $id and DQNEXT into the xfs_qm_dqget call, which means @@ -207,7 +207,7 @@ xfs_scrub_quota( xfs_dqid_t id = 0; uint dqtype; int nimaps; - int error; + int error = 0; if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp)) return -ENOENT; diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 9c42c4efd01e..ab3aef2ae823 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -46,7 +46,6 @@ #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" -#include "scrub/scrub.h" #include "scrub/btree.h" /* diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c index 472080e75788..86daed0e3a45 100644 --- a/fs/xfs/scrub/trace.c +++ b/fs/xfs/scrub/trace.c @@ -26,7 +26,6 @@ #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_da_format.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_trans.h" diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index a3eeaba156c5..4fc526a27a94 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -399,7 +399,7 @@ xfs_map_blocks( (ip->i_df.if_flags & XFS_IFEXTENTS)); ASSERT(offset <= mp->m_super->s_maxbytes); - if (offset + count > mp->m_super->s_maxbytes) + if (offset > mp->m_super->s_maxbytes - count) count = mp->m_super->s_maxbytes - offset; end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count); offset_fsb = XFS_B_TO_FSBT(mp, offset); @@ -896,13 +896,13 @@ xfs_writepage_map( struct writeback_control *wbc, struct inode *inode, struct page *page, - loff_t offset, - uint64_t end_offset) + uint64_t end_offset) { LIST_HEAD(submit_list); struct xfs_ioend *ioend, *next; struct buffer_head *bh, *head; ssize_t len = i_blocksize(inode); + uint64_t offset; int error = 0; int count = 0; int uptodate = 1; @@ -1146,7 +1146,7 @@ xfs_do_writepage( end_offset = offset; } - return xfs_writepage_map(wpc, wbc, inode, page, offset, end_offset); + return xfs_writepage_map(wpc, wbc, inode, page, end_offset); redirty: redirty_page_for_writepage(wbc, page); @@ -1265,7 +1265,7 @@ xfs_map_trim_size( if (mapping_size > size) mapping_size = size; if (offset < i_size_read(inode) && - offset + mapping_size >= i_size_read(inode)) { + (xfs_ufsize_t)offset + mapping_size >= i_size_read(inode)) { /* limit mapping to block that spans EOF */ mapping_size = roundup_64(i_size_read(inode) - offset, i_blocksize(inode)); @@ -1312,7 +1312,7 @@ xfs_get_blocks( lockmode = xfs_ilock_data_map_shared(ip); ASSERT(offset <= mp->m_super->s_maxbytes); - if (offset + size > mp->m_super->s_maxbytes) + if (offset > mp->m_super->s_maxbytes - size) size = mp->m_super->s_maxbytes - offset; end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size); offset_fsb = XFS_B_TO_FSBT(mp, offset); diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index dd136f7275e4..e5fb008d75e8 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -389,7 +389,8 @@ xfs_bud_init( int xfs_bui_recover( struct xfs_mount *mp, - struct xfs_bui_log_item *buip) + struct xfs_bui_log_item *buip, + struct xfs_defer_ops *dfops) { int error = 0; unsigned int bui_type; @@ -404,9 +405,7 @@ xfs_bui_recover( xfs_exntst_t state; struct xfs_trans *tp; struct xfs_inode *ip = NULL; - struct xfs_defer_ops dfops; struct xfs_bmbt_irec irec; - xfs_fsblock_t firstfsb; ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags)); @@ -464,7 +463,6 @@ xfs_bui_recover( if (VFS_I(ip)->i_nlink == 0) xfs_iflags_set(ip, XFS_IRECOVERY); - xfs_defer_init(&dfops, &firstfsb); /* Process deferred bmap item. */ state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ? @@ -479,16 +477,16 @@ xfs_bui_recover( break; default: error = -EFSCORRUPTED; - goto err_dfops; + goto err_inode; } xfs_trans_ijoin(tp, ip, 0); count = bmap->me_len; - error = xfs_trans_log_finish_bmap_update(tp, budp, &dfops, type, + error = xfs_trans_log_finish_bmap_update(tp, budp, dfops, type, ip, whichfork, bmap->me_startoff, bmap->me_startblock, &count, state); if (error) - goto err_dfops; + goto err_inode; if (count > 0) { ASSERT(type == XFS_BMAP_UNMAP); @@ -496,16 +494,11 @@ xfs_bui_recover( irec.br_blockcount = count; irec.br_startoff = bmap->me_startoff; irec.br_state = state; - error = xfs_bmap_unmap_extent(tp->t_mountp, &dfops, ip, &irec); + error = xfs_bmap_unmap_extent(tp->t_mountp, dfops, ip, &irec); if (error) - goto err_dfops; + goto err_inode; } - /* Finish transaction, free inodes. */ - error = xfs_defer_finish(&tp, &dfops); - if (error) - goto err_dfops; - set_bit(XFS_BUI_RECOVERED, &buip->bui_flags); error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -513,8 +506,6 @@ xfs_bui_recover( return error; -err_dfops: - xfs_defer_cancel(&dfops); err_inode: xfs_trans_cancel(tp); if (ip) { diff --git a/fs/xfs/xfs_bmap_item.h b/fs/xfs/xfs_bmap_item.h index c867daae4a3c..24b354a2c836 100644 --- a/fs/xfs/xfs_bmap_item.h +++ b/fs/xfs/xfs_bmap_item.h @@ -93,6 +93,7 @@ struct xfs_bud_log_item *xfs_bud_init(struct xfs_mount *, struct xfs_bui_log_item *); void xfs_bui_item_free(struct xfs_bui_log_item *); void xfs_bui_release(struct xfs_bui_log_item *); -int xfs_bui_recover(struct xfs_mount *mp, struct xfs_bui_log_item *buip); +int xfs_bui_recover(struct xfs_mount *mp, struct xfs_bui_log_item *buip, + struct xfs_defer_ops *dfops); #endif /* __XFS_BMAP_ITEM_H__ */ diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 4db6e8d780f6..4c6e86d861fd 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1815,22 +1815,27 @@ xfs_alloc_buftarg( btp->bt_daxdev = dax_dev; if (xfs_setsize_buftarg_early(btp, bdev)) - goto error; + goto error_free; if (list_lru_init(&btp->bt_lru)) - goto error; + goto error_free; if (percpu_counter_init(&btp->bt_io_count, 0, GFP_KERNEL)) - goto error; + goto error_lru; btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count; btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan; btp->bt_shrinker.seeks = DEFAULT_SEEKS; btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE; - register_shrinker(&btp->bt_shrinker); + if (register_shrinker(&btp->bt_shrinker)) + goto error_pcpu; return btp; -error: +error_pcpu: + percpu_counter_destroy(&btp->bt_io_count); +error_lru: + list_lru_destroy(&btp->bt_lru); +error_free: kmem_free(btp); return NULL; } diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index d57c2db64e59..f248708c10ff 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -970,14 +970,22 @@ xfs_qm_dqflush_done( * holding the lock before removing the dquot from the AIL. */ if ((lip->li_flags & XFS_LI_IN_AIL) && - lip->li_lsn == qip->qli_flush_lsn) { + ((lip->li_lsn == qip->qli_flush_lsn) || + (lip->li_flags & XFS_LI_FAILED))) { /* xfs_trans_ail_delete() drops the AIL lock. */ spin_lock(&ailp->xa_lock); - if (lip->li_lsn == qip->qli_flush_lsn) + if (lip->li_lsn == qip->qli_flush_lsn) { xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE); - else + } else { + /* + * Clear the failed state since we are about to drop the + * flush lock + */ + if (lip->li_flags & XFS_LI_FAILED) + xfs_clear_li_failed(lip); spin_unlock(&ailp->xa_lock); + } } /* diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 2c7a1629e064..664dea105e76 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -137,6 +137,26 @@ xfs_qm_dqunpin_wait( wait_event(dqp->q_pinwait, (atomic_read(&dqp->q_pincount) == 0)); } +/* + * Callback used to mark a buffer with XFS_LI_FAILED when items in the buffer + * have been failed during writeback + * + * this informs the AIL that the dquot is already flush locked on the next push, + * and acquires a hold on the buffer to ensure that it isn't reclaimed before + * dirty data makes it to disk. + */ +STATIC void +xfs_dquot_item_error( + struct xfs_log_item *lip, + struct xfs_buf *bp) +{ + struct xfs_dquot *dqp; + + dqp = DQUOT_ITEM(lip)->qli_dquot; + ASSERT(!completion_done(&dqp->q_flush)); + xfs_set_li_failed(lip, bp); +} + STATIC uint xfs_qm_dquot_logitem_push( struct xfs_log_item *lip, @@ -144,13 +164,28 @@ xfs_qm_dquot_logitem_push( __acquires(&lip->li_ailp->xa_lock) { struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; - struct xfs_buf *bp = NULL; + struct xfs_buf *bp = lip->li_buf; uint rval = XFS_ITEM_SUCCESS; int error; if (atomic_read(&dqp->q_pincount) > 0) return XFS_ITEM_PINNED; + /* + * The buffer containing this item failed to be written back + * previously. Resubmit the buffer for IO + */ + if (lip->li_flags & XFS_LI_FAILED) { + if (!xfs_buf_trylock(bp)) + return XFS_ITEM_LOCKED; + + if (!xfs_buf_resubmit_failed_buffers(bp, lip, buffer_list)) + rval = XFS_ITEM_FLUSHING; + + xfs_buf_unlock(bp); + return rval; + } + if (!xfs_dqlock_nowait(dqp)) return XFS_ITEM_LOCKED; @@ -242,7 +277,8 @@ static const struct xfs_item_ops xfs_dquot_item_ops = { .iop_unlock = xfs_qm_dquot_logitem_unlock, .iop_committed = xfs_qm_dquot_logitem_committed, .iop_push = xfs_qm_dquot_logitem_push, - .iop_committing = xfs_qm_dquot_logitem_committing + .iop_committing = xfs_qm_dquot_logitem_committing, + .iop_error = xfs_dquot_item_error }; /* diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 44f8c5451210..64da90655e95 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -538,7 +538,7 @@ xfs_efi_recover( return error; efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents); - xfs_rmap_skip_owner_update(&oinfo); + xfs_rmap_any_owner_update(&oinfo); for (i = 0; i < efip->efi_format.efi_nextents; i++) { extp = &efip->efi_format.efi_extents[i]; error = xfs_trans_free_extent(tp, efdp, extp->ext_start, diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 8f22fc579dbb..60a2e128cb6a 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -571,6 +571,11 @@ xfs_growfs_data_private( * this doesn't actually exist in the rmap btree. */ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL); + error = xfs_rmap_free(tp, bp, agno, + be32_to_cpu(agf->agf_length) - new, + new, &oinfo); + if (error) + goto error0; error = xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, agno, be32_to_cpu(agf->agf_length) - new), diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 43005fbe8b1e..3861d61fb265 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -870,7 +870,7 @@ xfs_eofblocks_worker( * based on the 'speculative_cow_prealloc_lifetime' tunable (5m by default). * (We'll just piggyback on the post-EOF prealloc space workqueue.) */ -STATIC void +void xfs_queue_cowblocks( struct xfs_mount *mp) { @@ -1536,8 +1536,23 @@ xfs_inode_free_quota_eofblocks( return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_eofblocks); } +static inline unsigned long +xfs_iflag_for_tag( + int tag) +{ + switch (tag) { + case XFS_ICI_EOFBLOCKS_TAG: + return XFS_IEOFBLOCKS; + case XFS_ICI_COWBLOCKS_TAG: + return XFS_ICOWBLOCKS; + default: + ASSERT(0); + return 0; + } +} + static void -__xfs_inode_set_eofblocks_tag( +__xfs_inode_set_blocks_tag( xfs_inode_t *ip, void (*execute)(struct xfs_mount *mp), void (*set_tp)(struct xfs_mount *mp, xfs_agnumber_t agno, @@ -1552,10 +1567,10 @@ __xfs_inode_set_eofblocks_tag( * Don't bother locking the AG and looking up in the radix trees * if we already know that we have the tag set. */ - if (ip->i_flags & XFS_IEOFBLOCKS) + if (ip->i_flags & xfs_iflag_for_tag(tag)) return; spin_lock(&ip->i_flags_lock); - ip->i_flags |= XFS_IEOFBLOCKS; + ip->i_flags |= xfs_iflag_for_tag(tag); spin_unlock(&ip->i_flags_lock); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); @@ -1587,13 +1602,13 @@ xfs_inode_set_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_eofblocks_tag(ip); - return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_eofblocks, + return __xfs_inode_set_blocks_tag(ip, xfs_queue_eofblocks, trace_xfs_perag_set_eofblocks, XFS_ICI_EOFBLOCKS_TAG); } static void -__xfs_inode_clear_eofblocks_tag( +__xfs_inode_clear_blocks_tag( xfs_inode_t *ip, void (*clear_tp)(struct xfs_mount *mp, xfs_agnumber_t agno, int error, unsigned long caller_ip), @@ -1603,7 +1618,7 @@ __xfs_inode_clear_eofblocks_tag( struct xfs_perag *pag; spin_lock(&ip->i_flags_lock); - ip->i_flags &= ~XFS_IEOFBLOCKS; + ip->i_flags &= ~xfs_iflag_for_tag(tag); spin_unlock(&ip->i_flags_lock); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); @@ -1630,7 +1645,7 @@ xfs_inode_clear_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_eofblocks_tag(ip); - return __xfs_inode_clear_eofblocks_tag(ip, + return __xfs_inode_clear_blocks_tag(ip, trace_xfs_perag_clear_eofblocks, XFS_ICI_EOFBLOCKS_TAG); } @@ -1724,7 +1739,7 @@ xfs_inode_set_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_cowblocks_tag(ip); - return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks, + return __xfs_inode_set_blocks_tag(ip, xfs_queue_cowblocks, trace_xfs_perag_set_cowblocks, XFS_ICI_COWBLOCKS_TAG); } @@ -1734,6 +1749,6 @@ xfs_inode_clear_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_cowblocks_tag(ip); - return __xfs_inode_clear_eofblocks_tag(ip, + return __xfs_inode_clear_blocks_tag(ip, trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG); } diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index bff4d85e5498..d4a77588eca1 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -81,6 +81,7 @@ void xfs_inode_clear_cowblocks_tag(struct xfs_inode *ip); int xfs_icache_free_cowblocks(struct xfs_mount *, struct xfs_eofblocks *); int xfs_inode_free_quota_cowblocks(struct xfs_inode *ip); void xfs_cowblocks_worker(struct work_struct *); +void xfs_queue_cowblocks(struct xfs_mount *); int xfs_inode_ag_iterator(struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, int flags, void *args), diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 61d1cb7dc10d..6f95bdb408ce 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -749,7 +749,6 @@ xfs_ialloc( xfs_nlink_t nlink, dev_t rdev, prid_t prid, - int okalloc, xfs_buf_t **ialloc_context, xfs_inode_t **ipp) { @@ -765,7 +764,7 @@ xfs_ialloc( * Call the space management code to pick * the on-disk inode to be allocated. */ - error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, okalloc, + error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, ialloc_context, &ino); if (error) return error; @@ -957,7 +956,6 @@ xfs_dir_ialloc( xfs_nlink_t nlink, dev_t rdev, prid_t prid, /* project id */ - int okalloc, /* ok to allocate new space */ xfs_inode_t **ipp, /* pointer to inode; it will be locked. */ int *committed) @@ -988,8 +986,8 @@ xfs_dir_ialloc( * transaction commit so that no other process can steal * the inode(s) that we've just allocated. */ - code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, okalloc, - &ialloc_context, &ip); + code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, &ialloc_context, + &ip); /* * Return an error if we were unable to allocate a new inode. @@ -1061,7 +1059,7 @@ xfs_dir_ialloc( * this call should always succeed. */ code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, - okalloc, &ialloc_context, &ip); + &ialloc_context, &ip); /* * If we get an error at this point, return to the caller @@ -1182,11 +1180,6 @@ xfs_create( xfs_flush_inodes(mp); error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); } - if (error == -ENOSPC) { - /* No space at all so try a "no-allocation" reservation */ - resblks = 0; - error = xfs_trans_alloc(mp, tres, 0, 0, 0, &tp); - } if (error) goto out_release_inode; @@ -1203,19 +1196,13 @@ xfs_create( if (error) goto out_trans_cancel; - if (!resblks) { - error = xfs_dir_canenter(tp, dp, name); - if (error) - goto out_trans_cancel; - } - /* * A newly created regular or special file just has one directory * entry pointing to them, but a directory also the "." entry * pointing to itself. */ - error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, - prid, resblks > 0, &ip, NULL); + error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, prid, &ip, + NULL); if (error) goto out_trans_cancel; @@ -1340,11 +1327,6 @@ xfs_create_tmpfile( tres = &M_RES(mp)->tr_create_tmpfile; error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); - if (error == -ENOSPC) { - /* No space at all so try a "no-allocation" reservation */ - resblks = 0; - error = xfs_trans_alloc(mp, tres, 0, 0, 0, &tp); - } if (error) goto out_release_inode; @@ -1353,8 +1335,7 @@ xfs_create_tmpfile( if (error) goto out_trans_cancel; - error = xfs_dir_ialloc(&tp, dp, mode, 1, 0, - prid, resblks > 0, &ip, NULL); + error = xfs_dir_ialloc(&tp, dp, mode, 1, 0, prid, &ip, NULL); if (error) goto out_trans_cancel; @@ -1506,6 +1487,24 @@ xfs_link( return error; } +/* Clear the reflink flag and the cowblocks tag if possible. */ +static void +xfs_itruncate_clear_reflink_flags( + struct xfs_inode *ip) +{ + struct xfs_ifork *dfork; + struct xfs_ifork *cfork; + + if (!xfs_is_reflink_inode(ip)) + return; + dfork = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + cfork = XFS_IFORK_PTR(ip, XFS_COW_FORK); + if (dfork->if_bytes == 0 && cfork->if_bytes == 0) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + if (cfork->if_bytes == 0) + xfs_inode_clear_cowblocks_tag(ip); +} + /* * Free up the underlying blocks past new_size. The new size must be smaller * than the current size. This routine can be used both for the attribute and @@ -1602,15 +1601,7 @@ xfs_itruncate_extents( if (error) goto out; - /* - * Clear the reflink flag if there are no data fork blocks and - * there are no extents staged in the cow fork. - */ - if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) { - if (ip->i_d.di_nblocks == 0) - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; - xfs_inode_clear_cowblocks_tag(ip); - } + xfs_itruncate_clear_reflink_flags(ip); /* * Always re-log the inode so that our permanent transaction can keep @@ -2401,6 +2392,24 @@ retry: } /* + * Free any local-format buffers sitting around before we reset to + * extents format. + */ +static inline void +xfs_ifree_local_data( + struct xfs_inode *ip, + int whichfork) +{ + struct xfs_ifork *ifp; + + if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL) + return; + + ifp = XFS_IFORK_PTR(ip, whichfork); + xfs_idata_realloc(ip, -ifp->if_bytes, whichfork); +} + +/* * This is called to return an inode to the inode free list. * The inode should already be truncated to 0 length and have * no pages associated with it. This routine also assumes that @@ -2437,6 +2446,9 @@ xfs_ifree( if (error) return error; + xfs_ifree_local_data(ip, XFS_DATA_FORK); + xfs_ifree_local_data(ip, XFS_ATTR_FORK); + VFS_I(ip)->i_mode = 0; /* mark incore inode as free */ ip->i_d.di_flags = 0; ip->i_d.di_dmevmask = 0; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index cc13c3763721..d383e392ec9d 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -232,6 +232,7 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip) * log recovery to replay a bmap operation on the inode. */ #define XFS_IRECOVERY (1 << 11) +#define XFS_ICOWBLOCKS (1 << 12)/* has the cowblocks tag set */ /* * Per-lifetime flags need to be reset when re-using a reclaimable inode during @@ -428,7 +429,7 @@ xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip); xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip); int xfs_dir_ialloc(struct xfs_trans **, struct xfs_inode *, umode_t, - xfs_nlink_t, dev_t, prid_t, int, + xfs_nlink_t, dev_t, prid_t, struct xfs_inode **, int *); /* from xfs_file.c */ diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 33eb4fb2e3fd..66e1edbfb2b2 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1006,7 +1006,7 @@ xfs_file_iomap_begin( } ASSERT(offset <= mp->m_super->s_maxbytes); - if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes) + if (offset > mp->m_super->s_maxbytes - length) length = mp->m_super->s_maxbytes - offset; offset_fsb = XFS_B_TO_FSBT(mp, offset); end_fsb = XFS_B_TO_FSB(mp, offset + length); @@ -1213,7 +1213,7 @@ xfs_xattr_iomap_begin( ASSERT(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL); error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, - &nimaps, XFS_BMAPI_ENTIRE | XFS_BMAPI_ATTRFORK); + &nimaps, XFS_BMAPI_ATTRFORK); out_unlock: xfs_iunlock(ip, lockmode); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 38d4227895ae..a503af96d780 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -781,17 +781,17 @@ xfs_log_mount_finish( * something to an unlinked inode, the irele won't cause * premature truncation and freeing of the inode, which results * in log recovery failure. We have to evict the unreferenced - * lru inodes after clearing MS_ACTIVE because we don't + * lru inodes after clearing SB_ACTIVE because we don't * otherwise clean up the lru if there's a subsequent failure in * xfs_mountfs, which leads to us leaking the inodes if nothing * else (e.g. quotacheck) references the inodes before the * mount failure occurs. */ - mp->m_super->s_flags |= MS_ACTIVE; + mp->m_super->s_flags |= SB_ACTIVE; error = xlog_recover_finish(mp->m_log); if (!error) xfs_log_work_queue(mp); - mp->m_super->s_flags &= ~MS_ACTIVE; + mp->m_super->s_flags &= ~SB_ACTIVE; evict_inodes(mp->m_super); /* diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 87b1c331f9eb..28d1abfe835e 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -24,6 +24,7 @@ #include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" +#include "xfs_defer.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_inode.h" @@ -4716,7 +4717,8 @@ STATIC int xlog_recover_process_cui( struct xfs_mount *mp, struct xfs_ail *ailp, - struct xfs_log_item *lip) + struct xfs_log_item *lip, + struct xfs_defer_ops *dfops) { struct xfs_cui_log_item *cuip; int error; @@ -4729,7 +4731,7 @@ xlog_recover_process_cui( return 0; spin_unlock(&ailp->xa_lock); - error = xfs_cui_recover(mp, cuip); + error = xfs_cui_recover(mp, cuip, dfops); spin_lock(&ailp->xa_lock); return error; @@ -4756,7 +4758,8 @@ STATIC int xlog_recover_process_bui( struct xfs_mount *mp, struct xfs_ail *ailp, - struct xfs_log_item *lip) + struct xfs_log_item *lip, + struct xfs_defer_ops *dfops) { struct xfs_bui_log_item *buip; int error; @@ -4769,7 +4772,7 @@ xlog_recover_process_bui( return 0; spin_unlock(&ailp->xa_lock); - error = xfs_bui_recover(mp, buip); + error = xfs_bui_recover(mp, buip, dfops); spin_lock(&ailp->xa_lock); return error; @@ -4805,6 +4808,46 @@ static inline bool xlog_item_is_intent(struct xfs_log_item *lip) } } +/* Take all the collected deferred ops and finish them in order. */ +static int +xlog_finish_defer_ops( + struct xfs_mount *mp, + struct xfs_defer_ops *dfops) +{ + struct xfs_trans *tp; + int64_t freeblks; + uint resblks; + int error; + + /* + * We're finishing the defer_ops that accumulated as a result of + * recovering unfinished intent items during log recovery. We + * reserve an itruncate transaction because it is the largest + * permanent transaction type. Since we're the only user of the fs + * right now, take 93% (15/16) of the available free blocks. Use + * weird math to avoid a 64-bit division. + */ + freeblks = percpu_counter_sum(&mp->m_fdblocks); + if (freeblks <= 0) + return -ENOSPC; + resblks = min_t(int64_t, UINT_MAX, freeblks); + resblks = (resblks * 15) >> 4; + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, resblks, + 0, XFS_TRANS_RESERVE, &tp); + if (error) + return error; + + error = xfs_defer_finish(&tp, dfops); + if (error) + goto out_cancel; + + return xfs_trans_commit(tp); + +out_cancel: + xfs_trans_cancel(tp); + return error; +} + /* * When this is called, all of the log intent items which did not have * corresponding log done items should be in the AIL. What we do now @@ -4825,10 +4868,12 @@ STATIC int xlog_recover_process_intents( struct xlog *log) { - struct xfs_log_item *lip; - int error = 0; + struct xfs_defer_ops dfops; struct xfs_ail_cursor cur; + struct xfs_log_item *lip; struct xfs_ail *ailp; + xfs_fsblock_t firstfsb; + int error = 0; #if defined(DEBUG) || defined(XFS_WARN) xfs_lsn_t last_lsn; #endif @@ -4839,6 +4884,7 @@ xlog_recover_process_intents( #if defined(DEBUG) || defined(XFS_WARN) last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block); #endif + xfs_defer_init(&dfops, &firstfsb); while (lip != NULL) { /* * We're done when we see something other than an intent. @@ -4859,6 +4905,12 @@ xlog_recover_process_intents( */ ASSERT(XFS_LSN_CMP(last_lsn, lip->li_lsn) >= 0); + /* + * NOTE: If your intent processing routine can create more + * deferred ops, you /must/ attach them to the dfops in this + * routine or else those subsequent intents will get + * replayed in the wrong order! + */ switch (lip->li_type) { case XFS_LI_EFI: error = xlog_recover_process_efi(log->l_mp, ailp, lip); @@ -4867,10 +4919,12 @@ xlog_recover_process_intents( error = xlog_recover_process_rui(log->l_mp, ailp, lip); break; case XFS_LI_CUI: - error = xlog_recover_process_cui(log->l_mp, ailp, lip); + error = xlog_recover_process_cui(log->l_mp, ailp, lip, + &dfops); break; case XFS_LI_BUI: - error = xlog_recover_process_bui(log->l_mp, ailp, lip); + error = xlog_recover_process_bui(log->l_mp, ailp, lip, + &dfops); break; } if (error) @@ -4880,6 +4934,11 @@ xlog_recover_process_intents( out: xfs_trans_ail_cursor_done(&cur); spin_unlock(&ailp->xa_lock); + if (error) + xfs_defer_cancel(&dfops); + else + error = xlog_finish_defer_ops(log->l_mp, &dfops); + return error; } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 010a13a201aa..b897b11afb2c 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -48,7 +48,7 @@ STATIC int xfs_qm_init_quotainos(xfs_mount_t *); STATIC int xfs_qm_init_quotainfo(xfs_mount_t *); - +STATIC void xfs_qm_destroy_quotainos(xfs_quotainfo_t *qi); STATIC void xfs_qm_dqfree_one(struct xfs_dquot *dqp); /* * We use the batch lookup interface to iterate over the dquots as it @@ -695,9 +695,17 @@ xfs_qm_init_quotainfo( qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan; qinf->qi_shrinker.seeks = DEFAULT_SEEKS; qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE; - register_shrinker(&qinf->qi_shrinker); + + error = register_shrinker(&qinf->qi_shrinker); + if (error) + goto out_free_inos; + return 0; +out_free_inos: + mutex_destroy(&qinf->qi_quotaofflock); + mutex_destroy(&qinf->qi_tree_lock); + xfs_qm_destroy_quotainos(qinf); out_free_lru: list_lru_destroy(&qinf->qi_lru); out_free_qinf: @@ -706,7 +714,6 @@ out_free_qinf: return error; } - /* * Gets called when unmounting a filesystem or when all quotas get * turned off. @@ -723,19 +730,8 @@ xfs_qm_destroy_quotainfo( unregister_shrinker(&qi->qi_shrinker); list_lru_destroy(&qi->qi_lru); - - if (qi->qi_uquotaip) { - IRELE(qi->qi_uquotaip); - qi->qi_uquotaip = NULL; /* paranoia */ - } - if (qi->qi_gquotaip) { - IRELE(qi->qi_gquotaip); - qi->qi_gquotaip = NULL; - } - if (qi->qi_pquotaip) { - IRELE(qi->qi_pquotaip); - qi->qi_pquotaip = NULL; - } + xfs_qm_destroy_quotainos(qi); + mutex_destroy(&qi->qi_tree_lock); mutex_destroy(&qi->qi_quotaofflock); kmem_free(qi); mp->m_quotainfo = NULL; @@ -793,8 +789,8 @@ xfs_qm_qino_alloc( return error; if (need_alloc) { - error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, 1, ip, - &committed); + error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, ip, + &committed); if (error) { xfs_trans_cancel(tp); return error; @@ -1600,6 +1596,24 @@ error_rele: } STATIC void +xfs_qm_destroy_quotainos( + xfs_quotainfo_t *qi) +{ + if (qi->qi_uquotaip) { + IRELE(qi->qi_uquotaip); + qi->qi_uquotaip = NULL; /* paranoia */ + } + if (qi->qi_gquotaip) { + IRELE(qi->qi_gquotaip); + qi->qi_gquotaip = NULL; + } + if (qi->qi_pquotaip) { + IRELE(qi->qi_pquotaip); + qi->qi_pquotaip = NULL; + } +} + +STATIC void xfs_qm_dqfree_one( struct xfs_dquot *dqp) { diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 8f2e2fac4255..3a55d6fc271b 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -393,7 +393,8 @@ xfs_cud_init( int xfs_cui_recover( struct xfs_mount *mp, - struct xfs_cui_log_item *cuip) + struct xfs_cui_log_item *cuip, + struct xfs_defer_ops *dfops) { int i; int error = 0; @@ -405,11 +406,9 @@ xfs_cui_recover( struct xfs_trans *tp; struct xfs_btree_cur *rcur = NULL; enum xfs_refcount_intent_type type; - xfs_fsblock_t firstfsb; xfs_fsblock_t new_fsb; xfs_extlen_t new_len; struct xfs_bmbt_irec irec; - struct xfs_defer_ops dfops; bool requeue_only = false; ASSERT(!test_bit(XFS_CUI_RECOVERED, &cuip->cui_flags)); @@ -465,7 +464,6 @@ xfs_cui_recover( return error; cudp = xfs_trans_get_cud(tp, cuip); - xfs_defer_init(&dfops, &firstfsb); for (i = 0; i < cuip->cui_format.cui_nextents; i++) { refc = &cuip->cui_format.cui_extents[i]; refc_type = refc->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK; @@ -485,7 +483,7 @@ xfs_cui_recover( new_len = refc->pe_len; } else error = xfs_trans_log_finish_refcount_update(tp, cudp, - &dfops, type, refc->pe_startblock, refc->pe_len, + dfops, type, refc->pe_startblock, refc->pe_len, &new_fsb, &new_len, &rcur); if (error) goto abort_error; @@ -497,21 +495,21 @@ xfs_cui_recover( switch (type) { case XFS_REFCOUNT_INCREASE: error = xfs_refcount_increase_extent( - tp->t_mountp, &dfops, &irec); + tp->t_mountp, dfops, &irec); break; case XFS_REFCOUNT_DECREASE: error = xfs_refcount_decrease_extent( - tp->t_mountp, &dfops, &irec); + tp->t_mountp, dfops, &irec); break; case XFS_REFCOUNT_ALLOC_COW: error = xfs_refcount_alloc_cow_extent( - tp->t_mountp, &dfops, + tp->t_mountp, dfops, irec.br_startblock, irec.br_blockcount); break; case XFS_REFCOUNT_FREE_COW: error = xfs_refcount_free_cow_extent( - tp->t_mountp, &dfops, + tp->t_mountp, dfops, irec.br_startblock, irec.br_blockcount); break; @@ -525,17 +523,12 @@ xfs_cui_recover( } xfs_refcount_finish_one_cleanup(tp, rcur, error); - error = xfs_defer_finish(&tp, &dfops); - if (error) - goto abort_defer; set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags); error = xfs_trans_commit(tp); return error; abort_error: xfs_refcount_finish_one_cleanup(tp, rcur, error); -abort_defer: - xfs_defer_cancel(&dfops); xfs_trans_cancel(tp); return error; } diff --git a/fs/xfs/xfs_refcount_item.h b/fs/xfs/xfs_refcount_item.h index 5b74dddfa64b..0e5327349a13 100644 --- a/fs/xfs/xfs_refcount_item.h +++ b/fs/xfs/xfs_refcount_item.h @@ -96,6 +96,7 @@ struct xfs_cud_log_item *xfs_cud_init(struct xfs_mount *, struct xfs_cui_log_item *); void xfs_cui_item_free(struct xfs_cui_log_item *); void xfs_cui_release(struct xfs_cui_log_item *); -int xfs_cui_recover(struct xfs_mount *mp, struct xfs_cui_log_item *cuip); +int xfs_cui_recover(struct xfs_mount *mp, struct xfs_cui_log_item *cuip, + struct xfs_defer_ops *dfops); #endif /* __XFS_REFCOUNT_ITEM_H__ */ diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index cc041a29eb70..47aea2e82c26 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -49,8 +49,6 @@ #include "xfs_alloc.h" #include "xfs_quota_defs.h" #include "xfs_quota.h" -#include "xfs_btree.h" -#include "xfs_bmap_btree.h" #include "xfs_reflink.h" #include "xfs_iomap.h" #include "xfs_rmap_btree.h" @@ -456,6 +454,8 @@ retry: if (error) goto out_bmap_cancel; + xfs_inode_set_cowblocks_tag(ip); + /* Finish up. */ error = xfs_defer_finish(&tp, &dfops); if (error) @@ -492,8 +492,9 @@ xfs_reflink_find_cow_mapping( struct xfs_iext_cursor icur; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)); - ASSERT(xfs_is_reflink_inode(ip)); + if (!xfs_is_reflink_inode(ip)) + return false; offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset); if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got)) return false; @@ -612,6 +613,9 @@ xfs_reflink_cancel_cow_blocks( /* Remove the mapping from the CoW fork. */ xfs_bmap_del_extent_cow(ip, &icur, &got, &del); + } else { + /* Didn't do anything, push cursor back. */ + xfs_iext_prev(ifp, &icur); } next_extent: if (!xfs_iext_get_extent(ifp, &icur, &got)) @@ -727,7 +731,7 @@ xfs_reflink_end_cow( (unsigned int)(end_fsb - offset_fsb), XFS_DATA_FORK); error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write, - resblks, 0, 0, &tp); + resblks, 0, XFS_TRANS_RESERVE, &tp); if (error) goto out; @@ -1293,6 +1297,17 @@ xfs_reflink_remap_range( trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); + /* + * Clear out post-eof preallocations because we don't have page cache + * backing the delayed allocations and they'll never get freed on + * their own. + */ + if (xfs_can_free_eofblocks(dest, true)) { + ret = xfs_free_eofblocks(dest); + if (ret) + goto out_unlock; + } + /* Set flags and remap blocks. */ ret = xfs_reflink_set_inode_flag(src, dest); if (ret) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index f663022353c0..1dacccc367f8 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -212,9 +212,9 @@ xfs_parseargs( */ if (sb_rdonly(sb)) mp->m_flags |= XFS_MOUNT_RDONLY; - if (sb->s_flags & MS_DIRSYNC) + if (sb->s_flags & SB_DIRSYNC) mp->m_flags |= XFS_MOUNT_DIRSYNC; - if (sb->s_flags & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) mp->m_flags |= XFS_MOUNT_WSYNC; /* @@ -1312,7 +1312,7 @@ xfs_fs_remount( } /* ro -> rw */ - if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) { + if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & SB_RDONLY)) { if (mp->m_flags & XFS_MOUNT_NORECOVERY) { xfs_warn(mp, "ro->rw transition prohibited on norecovery mount"); @@ -1360,6 +1360,7 @@ xfs_fs_remount( xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; } + xfs_queue_cowblocks(mp); /* Create the per-AG metadata reservation pool .*/ error = xfs_fs_reserve_ag_blocks(mp); @@ -1368,7 +1369,15 @@ xfs_fs_remount( } /* rw -> ro */ - if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) { + if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & SB_RDONLY)) { + /* Get rid of any leftover CoW reservations... */ + cancel_delayed_work_sync(&mp->m_cowblocks_work); + error = xfs_icache_free_cowblocks(mp, NULL); + if (error) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; + } + /* Free the per-AG metadata reservation pool. */ error = xfs_fs_unreserve_ag_blocks(mp); if (error) { diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 5f2f32408011..fcc5dfc70aa0 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -30,7 +30,7 @@ extern void xfs_qm_exit(void); #ifdef CONFIG_XFS_POSIX_ACL # define XFS_ACL_STRING "ACLs, " -# define set_posix_acl_flag(sb) ((sb)->s_flags |= MS_POSIXACL) +# define set_posix_acl_flag(sb) ((sb)->s_flags |= SB_POSIXACL) #else # define XFS_ACL_STRING # define set_posix_acl_flag(sb) do { } while (0) diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 68d3ca2c4968..2e9e793a8f9d 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -232,11 +232,6 @@ xfs_symlink( resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, resblks, 0, 0, &tp); - if (error == -ENOSPC && fs_blocks == 0) { - resblks = 0; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, 0, 0, 0, - &tp); - } if (error) goto out_release_inode; @@ -260,14 +255,6 @@ xfs_symlink( goto out_trans_cancel; /* - * Check for ability to enter directory entry, if no space reserved. - */ - if (!resblks) { - error = xfs_dir_canenter(tp, dp, link_name); - if (error) - goto out_trans_cancel; - } - /* * Initialize the bmap freelist prior to calling either * bmapi or the directory create code. */ @@ -277,7 +264,7 @@ xfs_symlink( * Allocate an inode for the symlink. */ error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0, - prid, resblks > 0, &ip, NULL); + prid, &ip, NULL); if (error) goto out_trans_cancel; diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c index 5d95fe348294..35f3546b6af5 100644 --- a/fs/xfs/xfs_trace.c +++ b/fs/xfs/xfs_trace.c @@ -24,7 +24,6 @@ #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_da_format.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_da_btree.h" |
