diff options
Diffstat (limited to 'fs')
146 files changed, 1576 insertions, 1058 deletions
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index e00cf8109b3f..053d1cef6e13 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -162,27 +162,27 @@ static int v9fs_xattr_handler_set(const struct xattr_handler *handler, return v9fs_xattr_set(dentry, full_name, value, size, flags); } -static struct xattr_handler v9fs_xattr_user_handler = { +static const struct xattr_handler v9fs_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, .get = v9fs_xattr_handler_get, .set = v9fs_xattr_handler_set, }; -static struct xattr_handler v9fs_xattr_trusted_handler = { +static const struct xattr_handler v9fs_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, .get = v9fs_xattr_handler_get, .set = v9fs_xattr_handler_set, }; #ifdef CONFIG_9P_FS_SECURITY -static struct xattr_handler v9fs_xattr_security_handler = { +static const struct xattr_handler v9fs_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .get = v9fs_xattr_handler_get, .set = v9fs_xattr_handler_set, }; #endif -const struct xattr_handler *v9fs_xattr_handlers[] = { +const struct xattr_handler * const v9fs_xattr_handlers[] = { &v9fs_xattr_user_handler, &v9fs_xattr_trusted_handler, #ifdef CONFIG_9P_FS_SECURITY diff --git a/fs/9p/xattr.h b/fs/9p/xattr.h index b5636e544c8a..3ad5a802352a 100644 --- a/fs/9p/xattr.h +++ b/fs/9p/xattr.h @@ -10,7 +10,7 @@ #include <net/9p/9p.h> #include <net/9p/client.h> -extern const struct xattr_handler *v9fs_xattr_handlers[]; +extern const struct xattr_handler * const v9fs_xattr_handlers[]; ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, void *buffer, size_t buffer_size); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index da73b97e19a9..23e2cc4efe41 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1541,7 +1541,7 @@ int afs_launder_folio(struct folio *); /* * xattr.c */ -extern const struct xattr_handler *afs_xattr_handlers[]; +extern const struct xattr_handler * const afs_xattr_handlers[]; /* * yfsclient.c diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c index 9048d8ccc715..64b2c0224f62 100644 --- a/fs/afs/xattr.c +++ b/fs/afs/xattr.c @@ -353,7 +353,7 @@ static const struct xattr_handler afs_xattr_afs_volume_handler = { .get = afs_xattr_get_volume, }; -const struct xattr_handler *afs_xattr_handlers[] = { +const struct xattr_handler * const afs_xattr_handlers[] = { &afs_xattr_afs_acl_handler, &afs_xattr_afs_cell_handler, &afs_xattr_afs_fid_handler, diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h index d5a44fa88acf..8c1d587b3eef 100644 --- a/fs/autofs/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -25,6 +25,8 @@ #include <linux/completion.h> #include <linux/file.h> #include <linux/magic.h> +#include <linux/fs_context.h> +#include <linux/fs_parser.h> /* This is the range of ioctl() numbers we claim as ours */ #define AUTOFS_IOC_FIRST AUTOFS_IOC_READY @@ -205,20 +207,34 @@ static inline void managed_dentry_clear_managed(struct dentry *dentry) /* Initializing function */ -int autofs_fill_super(struct super_block *, void *, int); +extern const struct fs_parameter_spec autofs_param_specs[]; +int autofs_init_fs_context(struct fs_context *fc); struct autofs_info *autofs_new_ino(struct autofs_sb_info *); void autofs_clean_ino(struct autofs_info *); -static inline int autofs_prepare_pipe(struct file *pipe) +static inline int autofs_check_pipe(struct file *pipe) { if (!(pipe->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (!S_ISFIFO(file_inode(pipe)->i_mode)) return -EINVAL; + return 0; +} + +static inline void autofs_set_packet_pipe_flags(struct file *pipe) +{ /* We want a packet pipe */ pipe->f_flags |= O_DIRECT; /* We don't expect -EAGAIN */ pipe->f_flags &= ~O_NONBLOCK; +} + +static inline int autofs_prepare_pipe(struct file *pipe) +{ + int ret = autofs_check_pipe(pipe); + if (ret < 0) + return ret; + autofs_set_packet_pipe_flags(pipe); return 0; } diff --git a/fs/autofs/init.c b/fs/autofs/init.c index d3f55e874338..b5e4dfa04ed0 100644 --- a/fs/autofs/init.c +++ b/fs/autofs/init.c @@ -7,16 +7,11 @@ #include <linux/init.h> #include "autofs_i.h" -static struct dentry *autofs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) -{ - return mount_nodev(fs_type, flags, data, autofs_fill_super); -} - struct file_system_type autofs_fs_type = { .owner = THIS_MODULE, .name = "autofs", - .mount = autofs_mount, + .init_fs_context = autofs_init_fs_context, + .parameters = autofs_param_specs, .kill_sb = autofs_kill_sb, }; MODULE_ALIAS_FS("autofs"); diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 9d06aa350c31..a5083d447a62 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -6,7 +6,6 @@ #include <linux/seq_file.h> #include <linux/pagemap.h> -#include <linux/parser.h> #include "autofs_i.h" @@ -110,189 +109,179 @@ static const struct super_operations autofs_sops = { .evict_inode = autofs_evict_inode, }; -enum {Opt_err, Opt_fd, Opt_uid, Opt_gid, Opt_pgrp, Opt_minproto, Opt_maxproto, - Opt_indirect, Opt_direct, Opt_offset, Opt_strictexpire, - Opt_ignore}; - -static const match_table_t tokens = { - {Opt_fd, "fd=%u"}, - {Opt_uid, "uid=%u"}, - {Opt_gid, "gid=%u"}, - {Opt_pgrp, "pgrp=%u"}, - {Opt_minproto, "minproto=%u"}, - {Opt_maxproto, "maxproto=%u"}, - {Opt_indirect, "indirect"}, - {Opt_direct, "direct"}, - {Opt_offset, "offset"}, - {Opt_strictexpire, "strictexpire"}, - {Opt_ignore, "ignore"}, - {Opt_err, NULL} +enum { + Opt_direct, + Opt_fd, + Opt_gid, + Opt_ignore, + Opt_indirect, + Opt_maxproto, + Opt_minproto, + Opt_offset, + Opt_pgrp, + Opt_strictexpire, + Opt_uid, }; -static int parse_options(char *options, - struct inode *root, int *pgrp, bool *pgrp_set, - struct autofs_sb_info *sbi) +const struct fs_parameter_spec autofs_param_specs[] = { + fsparam_flag ("direct", Opt_direct), + fsparam_fd ("fd", Opt_fd), + fsparam_u32 ("gid", Opt_gid), + fsparam_flag ("ignore", Opt_ignore), + fsparam_flag ("indirect", Opt_indirect), + fsparam_u32 ("maxproto", Opt_maxproto), + fsparam_u32 ("minproto", Opt_minproto), + fsparam_flag ("offset", Opt_offset), + fsparam_u32 ("pgrp", Opt_pgrp), + fsparam_flag ("strictexpire", Opt_strictexpire), + fsparam_u32 ("uid", Opt_uid), + {} +}; + +struct autofs_fs_context { + kuid_t uid; + kgid_t gid; + int pgrp; + bool pgrp_set; +}; + +/* + * Open the fd. We do it here rather than in get_tree so that it's done in the + * context of the system call that passed the data and not the one that + * triggered the superblock creation, lest the fd gets reassigned. + */ +static int autofs_parse_fd(struct fs_context *fc, struct autofs_sb_info *sbi, + struct fs_parameter *param, + struct fs_parse_result *result) { - char *p; - substring_t args[MAX_OPT_ARGS]; - int option; - int pipefd = -1; - kuid_t uid; - kgid_t gid; + struct file *pipe; + int ret; - root->i_uid = current_uid(); - root->i_gid = current_gid(); + if (param->type == fs_value_is_file) { + /* came through the new api */ + pipe = param->file; + param->file = NULL; + } else { + pipe = fget(result->uint_32); + } + if (!pipe) { + errorf(fc, "could not open pipe file descriptor"); + return -EBADF; + } - sbi->min_proto = AUTOFS_MIN_PROTO_VERSION; - sbi->max_proto = AUTOFS_MAX_PROTO_VERSION; + ret = autofs_check_pipe(pipe); + if (ret < 0) { + errorf(fc, "Invalid/unusable pipe"); + if (param->type != fs_value_is_file) + fput(pipe); + return -EBADF; + } - sbi->pipefd = -1; + autofs_set_packet_pipe_flags(pipe); - if (!options) - return 1; - - while ((p = strsep(&options, ",")) != NULL) { - int token; - - if (!*p) - continue; - - token = match_token(p, tokens, args); - switch (token) { - case Opt_fd: - if (match_int(args, &pipefd)) - return 1; - sbi->pipefd = pipefd; - break; - case Opt_uid: - if (match_int(args, &option)) - return 1; - uid = make_kuid(current_user_ns(), option); - if (!uid_valid(uid)) - return 1; - root->i_uid = uid; - break; - case Opt_gid: - if (match_int(args, &option)) - return 1; - gid = make_kgid(current_user_ns(), option); - if (!gid_valid(gid)) - return 1; - root->i_gid = gid; - break; - case Opt_pgrp: - if (match_int(args, &option)) - return 1; - *pgrp = option; - *pgrp_set = true; - break; - case Opt_minproto: - if (match_int(args, &option)) - return 1; - sbi->min_proto = option; - break; - case Opt_maxproto: - if (match_int(args, &option)) - return 1; - sbi->max_proto = option; - break; - case Opt_indirect: - set_autofs_type_indirect(&sbi->type); - break; - case Opt_direct: - set_autofs_type_direct(&sbi->type); - break; - case Opt_offset: - set_autofs_type_offset(&sbi->type); - break; - case Opt_strictexpire: - sbi->flags |= AUTOFS_SBI_STRICTEXPIRE; - break; - case Opt_ignore: - sbi->flags |= AUTOFS_SBI_IGNORE; - break; - default: - return 1; - } + if (sbi->pipe) + fput(sbi->pipe); + + sbi->pipefd = result->uint_32; + sbi->pipe = pipe; + + return 0; +} + +static int autofs_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct autofs_fs_context *ctx = fc->fs_private; + struct autofs_sb_info *sbi = fc->s_fs_info; + struct fs_parse_result result; + kuid_t uid; + kgid_t gid; + int opt; + + opt = fs_parse(fc, autofs_param_specs, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_fd: + return autofs_parse_fd(fc, sbi, param, &result); + case Opt_uid: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + return invalfc(fc, "Invalid uid"); + ctx->uid = uid; + break; + case Opt_gid: + gid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(gid)) + return invalfc(fc, "Invalid gid"); + ctx->gid = gid; + break; + case Opt_pgrp: + ctx->pgrp = result.uint_32; + ctx->pgrp_set = true; + break; + case Opt_minproto: + sbi->min_proto = result.uint_32; + break; + case Opt_maxproto: + sbi->max_proto = result.uint_32; + break; + case Opt_indirect: + set_autofs_type_indirect(&sbi->type); + break; + case Opt_direct: + set_autofs_type_direct(&sbi->type); + break; + case Opt_offset: + set_autofs_type_offset(&sbi->type); + break; + case Opt_strictexpire: + sbi->flags |= AUTOFS_SBI_STRICTEXPIRE; + break; + case Opt_ignore: + sbi->flags |= AUTOFS_SBI_IGNORE; } - return (sbi->pipefd < 0); + + return 0; } -int autofs_fill_super(struct super_block *s, void *data, int silent) +static struct autofs_sb_info *autofs_alloc_sbi(void) { - struct inode *root_inode; - struct dentry *root; - struct file *pipe; struct autofs_sb_info *sbi; - struct autofs_info *ino; - int pgrp = 0; - bool pgrp_set = false; - int ret = -EINVAL; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) - return -ENOMEM; - pr_debug("starting up, sbi = %p\n", sbi); + return NULL; - s->s_fs_info = sbi; sbi->magic = AUTOFS_SBI_MAGIC; - sbi->pipefd = -1; - sbi->pipe = NULL; - sbi->exp_timeout = 0; - sbi->oz_pgrp = NULL; - sbi->sb = s; - sbi->version = 0; - sbi->sub_version = 0; sbi->flags = AUTOFS_SBI_CATATONIC; + sbi->min_proto = AUTOFS_MIN_PROTO_VERSION; + sbi->max_proto = AUTOFS_MAX_PROTO_VERSION; + sbi->pipefd = -1; + set_autofs_type_indirect(&sbi->type); - sbi->min_proto = 0; - sbi->max_proto = 0; mutex_init(&sbi->wq_mutex); mutex_init(&sbi->pipe_mutex); spin_lock_init(&sbi->fs_lock); - sbi->queues = NULL; spin_lock_init(&sbi->lookup_lock); INIT_LIST_HEAD(&sbi->active_list); INIT_LIST_HEAD(&sbi->expiring_list); - s->s_blocksize = 1024; - s->s_blocksize_bits = 10; - s->s_magic = AUTOFS_SUPER_MAGIC; - s->s_op = &autofs_sops; - s->s_d_op = &autofs_dentry_operations; - s->s_time_gran = 1; - /* - * Get the root inode and dentry, but defer checking for errors. - */ - ino = autofs_new_ino(sbi); - if (!ino) { - ret = -ENOMEM; - goto fail_free; - } - root_inode = autofs_get_inode(s, S_IFDIR | 0755); - root = d_make_root(root_inode); - if (!root) { - ret = -ENOMEM; - goto fail_ino; - } - pipe = NULL; - - root->d_fsdata = ino; + return sbi; +} - /* Can this call block? */ - if (parse_options(data, root_inode, &pgrp, &pgrp_set, sbi)) { - pr_err("called with bogus options\n"); - goto fail_dput; - } +static int autofs_validate_protocol(struct fs_context *fc) +{ + struct autofs_sb_info *sbi = fc->s_fs_info; /* Test versions first */ if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION || sbi->min_proto > AUTOFS_MAX_PROTO_VERSION) { - pr_err("kernel does not match daemon version " + errorf(fc, "kernel does not match daemon version " "daemon (%d, %d) kernel (%d, %d)\n", sbi->min_proto, sbi->max_proto, AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION); - goto fail_dput; + return -EINVAL; } /* Establish highest kernel protocol version */ @@ -300,13 +289,62 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) sbi->version = AUTOFS_MAX_PROTO_VERSION; else sbi->version = sbi->max_proto; - sbi->sub_version = AUTOFS_PROTO_SUBVERSION; - if (pgrp_set) { - sbi->oz_pgrp = find_get_pid(pgrp); + switch (sbi->version) { + case 4: + sbi->sub_version = 7; + break; + case 5: + sbi->sub_version = AUTOFS_PROTO_SUBVERSION; + break; + default: + sbi->sub_version = 0; + } + + return 0; +} + +static int autofs_fill_super(struct super_block *s, struct fs_context *fc) +{ + struct autofs_fs_context *ctx = fc->fs_private; + struct autofs_sb_info *sbi = s->s_fs_info; + struct inode *root_inode; + struct dentry *root; + struct autofs_info *ino; + int ret = -ENOMEM; + + pr_debug("starting up, sbi = %p\n", sbi); + + sbi->sb = s; + s->s_blocksize = 1024; + s->s_blocksize_bits = 10; + s->s_magic = AUTOFS_SUPER_MAGIC; + s->s_op = &autofs_sops; + s->s_d_op = &autofs_dentry_operations; + s->s_time_gran = 1; + + /* + * Get the root inode and dentry, but defer checking for errors. + */ + ino = autofs_new_ino(sbi); + if (!ino) + goto fail; + + root_inode = autofs_get_inode(s, S_IFDIR | 0755); + root_inode->i_uid = ctx->uid; + root_inode->i_gid = ctx->gid; + + root = d_make_root(root_inode); + if (!root) + goto fail_ino; + + root->d_fsdata = ino; + + if (ctx->pgrp_set) { + sbi->oz_pgrp = find_get_pid(ctx->pgrp); if (!sbi->oz_pgrp) { - pr_err("could not find process group %d\n", - pgrp); + ret = invalf(fc, "Could not find process group %d", + ctx->pgrp); goto fail_dput; } } else { @@ -321,16 +359,7 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) pr_debug("pipe fd = %d, pgrp = %u\n", sbi->pipefd, pid_nr(sbi->oz_pgrp)); - pipe = fget(sbi->pipefd); - if (!pipe) { - pr_err("could not open pipe file descriptor\n"); - goto fail_put_pid; - } - ret = autofs_prepare_pipe(pipe); - if (ret < 0) - goto fail_fput; - sbi->pipe = pipe; sbi->flags &= ~AUTOFS_SBI_CATATONIC; /* @@ -342,22 +371,82 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) /* * Failure ... clean up. */ -fail_fput: - pr_err("pipe file descriptor does not contain proper ops\n"); - fput(pipe); -fail_put_pid: - put_pid(sbi->oz_pgrp); fail_dput: dput(root); - goto fail_free; + goto fail; fail_ino: autofs_free_ino(ino); -fail_free: - kfree(sbi); - s->s_fs_info = NULL; +fail: return ret; } +/* + * Validate the parameters and then request a superblock. + */ +static int autofs_get_tree(struct fs_context *fc) +{ + struct autofs_sb_info *sbi = fc->s_fs_info; + int ret; + + ret = autofs_validate_protocol(fc); + if (ret) + return ret; + + if (sbi->pipefd < 0) + return invalf(fc, "No control pipe specified"); + + return get_tree_nodev(fc, autofs_fill_super); +} + +static void autofs_free_fc(struct fs_context *fc) +{ + struct autofs_fs_context *ctx = fc->fs_private; + struct autofs_sb_info *sbi = fc->s_fs_info; + + if (sbi) { + if (sbi->pipe) + fput(sbi->pipe); + kfree(sbi); + } + kfree(ctx); +} + +static const struct fs_context_operations autofs_context_ops = { + .free = autofs_free_fc, + .parse_param = autofs_parse_param, + .get_tree = autofs_get_tree, +}; + +/* + * Set up the filesystem mount context. + */ +int autofs_init_fs_context(struct fs_context *fc) +{ + struct autofs_fs_context *ctx; + struct autofs_sb_info *sbi; + + ctx = kzalloc(sizeof(struct autofs_fs_context), GFP_KERNEL); + if (!ctx) + goto nomem; + + ctx->uid = current_uid(); + ctx->gid = current_gid(); + + sbi = autofs_alloc_sbi(); + if (!sbi) + goto nomem_ctx; + + fc->fs_private = ctx; + fc->s_fs_info = sbi; + fc->ops = &autofs_context_ops; + return 0; + +nomem_ctx: + kfree(ctx); +nomem: + return -ENOMEM; +} + struct inode *autofs_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index b7d54efb4728..a4a809efc92f 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -3196,12 +3196,14 @@ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache, * We still need to do a tree search to find out the parents. This is for * TREE_BLOCK_REF backref (keyed or inlined). * + * @trans: Transaction handle. * @ref_key: The same as @ref_key in handle_direct_tree_backref() * @tree_key: The first key of this tree block. * @path: A clean (released) path, to avoid allocating path every time * the function get called. */ -static int handle_indirect_tree_backref(struct btrfs_backref_cache *cache, +static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans, + struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_key *ref_key, struct btrfs_key *tree_key, @@ -3315,7 +3317,7 @@ static int handle_indirect_tree_backref(struct btrfs_backref_cache *cache, * If we know the block isn't shared we can avoid * checking its backrefs. */ - if (btrfs_block_can_be_shared(root, eb)) + if (btrfs_block_can_be_shared(trans, root, eb)) upper->checked = 0; else upper->checked = 1; @@ -3363,11 +3365,13 @@ out: * links aren't yet bi-directional. Needs to finish such links. * Use btrfs_backref_finish_upper_links() to finish such linkage. * + * @trans: Transaction handle. * @path: Released path for indirect tree backref lookup * @iter: Released backref iter for extent tree search * @node_key: The first key of the tree block */ -int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache, +int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_backref_iter *iter, struct btrfs_key *node_key, @@ -3467,8 +3471,8 @@ int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache, * offset means the root objectid. We need to search * the tree to get its parent bytenr. */ - ret = handle_indirect_tree_backref(cache, path, &key, node_key, - cur); + ret = handle_indirect_tree_backref(trans, cache, path, + &key, node_key, cur); if (ret < 0) goto out; } diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index 1616e3e3f1e4..71d535e03dca 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -540,7 +540,8 @@ static inline void btrfs_backref_panic(struct btrfs_fs_info *fs_info, bytenr); } -int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache, +int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_backref_iter *iter, struct btrfs_key *node_key, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index da519c1b6ad0..617d4827eec2 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -367,7 +367,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, /* * check if the tree block can be shared by multiple trees */ -int btrfs_block_can_be_shared(struct btrfs_root *root, +int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf) { /* @@ -376,11 +377,21 @@ int btrfs_block_can_be_shared(struct btrfs_root *root, * not allocated by tree relocation, we know the block is not shared. */ if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && - buf != root->node && buf != root->commit_root && + buf != root->node && (btrfs_header_generation(buf) <= btrfs_root_last_snapshot(&root->root_item) || - btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))) - return 1; + btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))) { + if (buf != root->commit_root) + return 1; + /* + * An extent buffer that used to be the commit root may still be + * shared because the tree height may have increased and it + * became a child of a higher level root. This can happen when + * snapshotting a subvolume created in the current transaction. + */ + if (btrfs_header_generation(buf) == trans->transid) + return 1; + } return 0; } @@ -415,7 +426,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, * are only allowed for blocks use full backrefs. */ - if (btrfs_block_can_be_shared(root, buf)) { + if (btrfs_block_can_be_shared(trans, root, buf)) { ret = btrfs_lookup_extent_info(trans, fs_info, buf->start, btrfs_header_level(buf), 1, &refs, &flags); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9419f4e37a58..ff40acd63a37 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -540,7 +540,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer **cow_ret, u64 new_root_objectid); -int btrfs_block_can_be_shared(struct btrfs_root *root, +int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf); int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level, int slot); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 1f39f8b5f8f4..c401908eb468 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -313,7 +313,7 @@ static struct btrfs_delayed_item *btrfs_alloc_delayed_item(u16 data_len, { struct btrfs_delayed_item *item; - item = kmalloc(sizeof(*item) + data_len, GFP_NOFS); + item = kmalloc(struct_size(item, data, data_len), GFP_NOFS); if (item) { item->data_len = data_len; item->type = type; diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index dc1085b2a397..1da213197f55 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -95,7 +95,7 @@ struct btrfs_delayed_item { bool logged; /* The maximum leaf size is 64K, so u16 is more than enough. */ u16 data_len; - char data[]; + char data[] __counted_by(data_len); }; static inline void btrfs_init_delayed_root( diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index fff22ed55c42..6b5b6cec13c4 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -247,6 +247,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, { struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; + struct bdev_handle *bdev_handle; struct block_device *bdev; u64 devid = BTRFS_DEV_REPLACE_DEVID; int ret = 0; @@ -257,12 +258,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return -EINVAL; } - bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE, - fs_info->bdev_holder, NULL); - if (IS_ERR(bdev)) { + bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE, + fs_info->bdev_holder, NULL); + if (IS_ERR(bdev_handle)) { btrfs_err(fs_info, "target device %s is invalid!", device_path); - return PTR_ERR(bdev); + return PTR_ERR(bdev_handle); } + bdev = bdev_handle->bdev; if (!btrfs_check_device_zone_type(fs_info, bdev)) { btrfs_err(fs_info, @@ -313,9 +315,9 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, device->commit_bytes_used = device->bytes_used; device->fs_info = fs_info; device->bdev = bdev; + device->bdev_handle = bdev_handle; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); - device->holder = fs_info->bdev_holder; device->dev_stats_valid = 1; set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); device->fs_devices = fs_devices; @@ -334,7 +336,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return 0; error: - blkdev_put(bdev, fs_info->bdev_holder); + bdev_release(bdev_handle); return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8e7d03bc1b56..108edf8ffedf 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2676,8 +2676,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ioctl_vol_args_v2 *vol_args; - struct block_device *bdev = NULL; - void *holder; + struct bdev_handle *bdev_handle = NULL; int ret; bool cancel = false; @@ -2714,7 +2713,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) goto err_drop; /* Exclusive operation is now claimed */ - ret = btrfs_rm_device(fs_info, &args, &bdev, &holder); + ret = btrfs_rm_device(fs_info, &args, &bdev_handle); btrfs_exclop_finish(fs_info); @@ -2728,8 +2727,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) } err_drop: mnt_drop_write_file(file); - if (bdev) - blkdev_put(bdev, holder); + if (bdev_handle) + bdev_release(bdev_handle); out: btrfs_put_dev_args_from_path(&args); kfree(vol_args); @@ -2742,8 +2741,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ioctl_vol_args *vol_args; - struct block_device *bdev = NULL; - void *holder; + struct bdev_handle *bdev_handle = NULL; int ret; bool cancel = false; @@ -2770,15 +2768,15 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE, cancel); if (ret == 0) { - ret = btrfs_rm_device(fs_info, &args, &bdev, &holder); + ret = btrfs_rm_device(fs_info, &args, &bdev_handle); if (!ret) btrfs_info(fs_info, "disk deleted %s", vol_args->name); btrfs_exclop_finish(fs_info); } mnt_drop_write_file(file); - if (bdev) - blkdev_put(bdev, holder); + if (bdev_handle) + bdev_release(bdev_handle); out: btrfs_put_dev_args_from_path(&args); kfree(vol_args); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 9951a0caf5bb..c6d4bb8cbe29 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -466,6 +466,7 @@ static bool handle_useless_nodes(struct reloc_control *rc, * cached. */ static noinline_for_stack struct btrfs_backref_node *build_backref_tree( + struct btrfs_trans_handle *trans, struct reloc_control *rc, struct btrfs_key *node_key, int level, u64 bytenr) { @@ -499,8 +500,8 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree( /* Breadth-first search to build backref cache */ do { - ret = btrfs_backref_add_tree_node(cache, path, iter, node_key, - cur); + ret = btrfs_backref_add_tree_node(trans, cache, path, iter, + node_key, cur); if (ret < 0) { err = ret; goto out; @@ -2803,7 +2804,7 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, /* Do tree relocation */ rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { - node = build_backref_tree(rc, &block->key, + node = build_backref_tree(trans, rc, &block->key, block->level, block->bytenr); if (IS_ERR(node)) { err = PTR_ERR(node); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index f49e597e197f..1a093ec0f7e3 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -954,10 +954,6 @@ static int btrfs_parse_subvol_options(const char *options, char **subvol_name, *subvol_objectid = subvolid; break; - case Opt_err: - btrfs_err(NULL, "unrecognized mount option '%s'", p); - error = -EINVAL; - goto out; default: break; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 5a5a8d488a7b..1f38affa4d9c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -511,37 +511,39 @@ static struct btrfs_fs_devices *find_fsid_with_metadata_uuid( static int btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder, - int flush, struct block_device **bdev, + int flush, struct bdev_handle **bdev_handle, struct btrfs_super_block **disk_super) { + struct block_device *bdev; int ret; - *bdev = blkdev_get_by_path(device_path, flags, holder, NULL); + *bdev_handle = bdev_open_by_path(device_path, flags, holder, NULL); - if (IS_ERR(*bdev)) { - ret = PTR_ERR(*bdev); + if (IS_ERR(*bdev_handle)) { + ret = PTR_ERR(*bdev_handle); goto error; } + bdev = (*bdev_handle)->bdev; if (flush) - sync_blockdev(*bdev); - ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE); + sync_blockdev(bdev); + ret = set_blocksize(bdev, BTRFS_BDEV_BLOCKSIZE); if (ret) { - blkdev_put(*bdev, holder); + bdev_release(*bdev_handle); goto error; } - invalidate_bdev(*bdev); - *disk_super = btrfs_read_dev_super(*bdev); + invalidate_bdev(bdev); + *disk_super = btrfs_read_dev_super(bdev); if (IS_ERR(*disk_super)) { ret = PTR_ERR(*disk_super); - blkdev_put(*bdev, holder); + bdev_release(*bdev_handle); goto error; } return 0; error: - *bdev = NULL; + *bdev_handle = NULL; return ret; } @@ -613,7 +615,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, struct btrfs_device *device, blk_mode_t flags, void *holder) { - struct block_device *bdev; + struct bdev_handle *bdev_handle; struct btrfs_super_block *disk_super; u64 devid; int ret; @@ -624,7 +626,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, return -EINVAL; ret = btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1, - &bdev, &disk_super); + &bdev_handle, &disk_super); if (ret) return ret; @@ -648,21 +650,21 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); fs_devices->seeding = true; } else { - if (bdev_read_only(bdev)) + if (bdev_read_only(bdev_handle->bdev)) clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); else set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); } - if (!bdev_nonrot(bdev)) + if (!bdev_nonrot(bdev_handle->bdev)) fs_devices->rotating = true; - if (bdev_max_discard_sectors(bdev)) + if (bdev_max_discard_sectors(bdev_handle->bdev)) fs_devices->discardable = true; - device->bdev = bdev; + device->bdev_handle = bdev_handle; + device->bdev = bdev_handle->bdev; clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); - device->holder = holder; fs_devices->open_devices++; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && @@ -676,7 +678,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, error_free_page: btrfs_release_disk_super(disk_super); - blkdev_put(bdev, holder); + bdev_release(bdev_handle); return -EINVAL; } @@ -1068,9 +1070,10 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, if (device->devid == BTRFS_DEV_REPLACE_DEVID) continue; - if (device->bdev) { - blkdev_put(device->bdev, device->holder); + if (device->bdev_handle) { + bdev_release(device->bdev_handle); device->bdev = NULL; + device->bdev_handle = NULL; fs_devices->open_devices--; } if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { @@ -1115,7 +1118,7 @@ static void btrfs_close_bdev(struct btrfs_device *device) invalidate_bdev(device->bdev); } - blkdev_put(device->bdev, device->holder); + bdev_release(device->bdev_handle); } static void btrfs_close_one_device(struct btrfs_device *device) @@ -1363,7 +1366,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags) struct btrfs_super_block *disk_super; bool new_device_added = false; struct btrfs_device *device = NULL; - struct block_device *bdev; + struct bdev_handle *bdev_handle; u64 bytenr, bytenr_orig; int ret; @@ -1386,18 +1389,19 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags) * values temporarily, as the device paths of the fsid are the only * required information for assembling the volume. */ - bdev = blkdev_get_by_path(path, flags, NULL, NULL); - if (IS_ERR(bdev)) - return ERR_CAST(bdev); + bdev_handle = bdev_open_by_path(path, flags, NULL, NULL); + if (IS_ERR(bdev_handle)) + return ERR_CAST(bdev_handle); bytenr_orig = btrfs_sb_offset(0); - ret = btrfs_sb_log_location_bdev(bdev, 0, READ, &bytenr); + ret = btrfs_sb_log_location_bdev(bdev_handle->bdev, 0, READ, &bytenr); if (ret) { device = ERR_PTR(ret); goto error_bdev_put; } - disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr_orig); + disk_super = btrfs_read_disk_super(bdev_handle->bdev, bytenr, + bytenr_orig); if (IS_ERR(disk_super)) { device = ERR_CAST(disk_super); goto error_bdev_put; @@ -1410,7 +1414,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags) btrfs_release_disk_super(disk_super); error_bdev_put: - blkdev_put(bdev, NULL); + bdev_release(bdev_handle); return device; } @@ -2087,7 +2091,7 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, - struct block_device **bdev, void **holder) + struct bdev_handle **bdev_handle) { struct btrfs_trans_handle *trans; struct btrfs_device *device; @@ -2196,7 +2200,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, btrfs_assign_next_active_device(device, NULL); - if (device->bdev) { + if (device->bdev_handle) { cur_devices->open_devices--; /* remove sysfs entry */ btrfs_sysfs_remove_device(device); @@ -2212,9 +2216,9 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, * free the device. * * We cannot call btrfs_close_bdev() here because we're holding the sb - * write lock, and blkdev_put() will pull in the ->open_mutex on the - * block device and it's dependencies. Instead just flush the device - * and let the caller do the final blkdev_put. + * write lock, and bdev_release() will pull in the ->open_mutex on + * the block device and it's dependencies. Instead just flush the + * device and let the caller do the final bdev_release. */ if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { btrfs_scratch_superblocks(fs_info, device->bdev, @@ -2225,8 +2229,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, } } - *bdev = device->bdev; - *holder = device->holder; + *bdev_handle = device->bdev_handle; synchronize_rcu(); btrfs_free_device(device); @@ -2363,7 +2366,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, const char *path) { struct btrfs_super_block *disk_super; - struct block_device *bdev; + struct bdev_handle *bdev_handle; int ret; if (!path || !path[0]) @@ -2381,7 +2384,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, } ret = btrfs_get_bdev_and_sb(path, BLK_OPEN_READ, NULL, 0, - &bdev, &disk_super); + &bdev_handle, &disk_super); if (ret) { btrfs_put_dev_args_from_path(args); return ret; @@ -2394,7 +2397,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, else memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE); btrfs_release_disk_super(disk_super); - blkdev_put(bdev, NULL); + bdev_release(bdev_handle); return 0; } @@ -2614,7 +2617,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path struct btrfs_root *root = fs_info->dev_root; struct btrfs_trans_handle *trans; struct btrfs_device *device; - struct block_device *bdev; + struct bdev_handle *bdev_handle; struct super_block *sb = fs_info->sb; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_fs_devices *seed_devices = NULL; @@ -2627,12 +2630,12 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path if (sb_rdonly(sb) && !fs_devices->seeding) return -EROFS; - bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE, - fs_info->bdev_holder, NULL); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); + bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE, + fs_info->bdev_holder, NULL); + if (IS_ERR(bdev_handle)) + return PTR_ERR(bdev_handle); - if (!btrfs_check_device_zone_type(fs_info, bdev)) { + if (!btrfs_check_device_zone_type(fs_info, bdev_handle->bdev)) { ret = -EINVAL; goto error; } @@ -2644,11 +2647,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path locked = true; } - sync_blockdev(bdev); + sync_blockdev(bdev_handle->bdev); rcu_read_lock(); list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) { - if (device->bdev == bdev) { + if (device->bdev == bdev_handle->bdev) { ret = -EEXIST; rcu_read_unlock(); goto error; @@ -2664,7 +2667,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path } device->fs_info = fs_info; - device->bdev = bdev; + device->bdev_handle = bdev_handle; + device->bdev = bdev_handle->bdev; ret = lookup_bdev(device_path, &device->devt); if (ret) goto error_free_device; @@ -2685,12 +2689,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path device->io_align = fs_info->sectorsize; device->sector_size = fs_info->sectorsize; device->total_bytes = - round_down(bdev_nr_bytes(bdev), fs_info->sectorsize); + round_down(bdev_nr_bytes(device->bdev), fs_info->sectorsize); device->disk_total_bytes = device->total_bytes; device->commit_total_bytes = device->total_bytes; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); - device->holder = fs_info->bdev_holder; device->dev_stats_valid = 1; set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); @@ -2726,7 +2729,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path atomic64_add(device->total_bytes, &fs_info->free_chunk_space); - if (!bdev_nonrot(bdev)) + if (!bdev_nonrot(device->bdev)) fs_devices->rotating = true; orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy); @@ -2848,7 +2851,7 @@ error_free_zone: error_free_device: btrfs_free_device(device); error: - blkdev_put(bdev, fs_info->bdev_holder); + bdev_release(bdev_handle); if (locked) { mutex_unlock(&uuid_mutex); up_write(&sb->s_umount); @@ -5109,7 +5112,7 @@ static void init_alloc_chunk_ctl_policy_regular( ASSERT(space_info); ctl->max_chunk_size = READ_ONCE(space_info->chunk_size); - ctl->max_stripe_size = ctl->max_chunk_size; + ctl->max_stripe_size = min_t(u64, ctl->max_chunk_size, SZ_1G); if (ctl->type & BTRFS_BLOCK_GROUP_SYSTEM) ctl->devs_max = min_t(int, ctl->devs_max, BTRFS_MAX_DEVS_SYS_CHUNK); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 2128a032c3b7..1702cb7cac00 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -90,13 +90,11 @@ struct btrfs_device { u64 generation; + struct bdev_handle *bdev_handle; struct block_device *bdev; struct btrfs_zoned_device_info *zone_info; - /* block device holder for blkdev_get/put */ - void *holder; - /* * Device's major-minor number. Must be set even if the device is not * opened (bdev == NULL), unless the device is missing. @@ -629,7 +627,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args); int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, - struct block_device **bdev, void **holder); + struct bdev_handle **bdev_handle); void __exit btrfs_cleanup_fs_uuids(void); int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len); int btrfs_grow_device(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 96828a13dd43..a9f8b173a99f 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -442,7 +442,7 @@ static const struct xattr_handler btrfs_btrfs_xattr_handler = { .set = btrfs_xattr_handler_set_prop, }; -const struct xattr_handler *btrfs_xattr_handlers[] = { +const struct xattr_handler * const btrfs_xattr_handlers[] = { &btrfs_security_xattr_handler, &btrfs_trusted_xattr_handler, &btrfs_user_xattr_handler, diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h index 1cd3fc0a8f17..118118ca3e1d 100644 --- a/fs/btrfs/xattr.h +++ b/fs/btrfs/xattr.h @@ -8,7 +8,7 @@ #include <linux/xattr.h> -extern const struct xattr_handler *btrfs_xattr_handlers[]; +extern const struct xattr_handler * const btrfs_xattr_handlers[]; int btrfs_getxattr(struct inode *inode, const char *name, void *buffer, size_t size); diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c index e1f31b86fd48..5b5112c78462 100644 --- a/fs/ceph/crypto.c +++ b/fs/ceph/crypto.c @@ -460,7 +460,7 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname, out: fscrypt_fname_free_buffer(&_tname); out_inode: - if ((dir != fname->dir) && !IS_ERR(dir)) { + if (dir != fname->dir) { if ((dir->i_state & I_NEW)) discard_new_inode(dir); else diff --git a/fs/ceph/file.c b/fs/ceph/file.c index b96d4e74ae99..649600d0a7b6 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2969,7 +2969,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, ret = do_splice_direct(src_file, &src_off, dst_file, &dst_off, src_objlen, flags); /* Abort on short copies or on error */ - if (ret < src_objlen) { + if (ret < (long)src_objlen) { dout("Failed partial copy (%zd)\n", ret); goto out; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index e846752b9a1f..2e2a303b9e64 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -769,9 +769,7 @@ int ceph_fill_file_size(struct inode *inode, int issued, ci->i_truncate_seq = truncate_seq; /* the MDS should have revoked these caps */ - WARN_ON_ONCE(issued & (CEPH_CAP_FILE_EXCL | - CEPH_CAP_FILE_RD | - CEPH_CAP_FILE_WR | + WARN_ON_ONCE(issued & (CEPH_CAP_FILE_RD | CEPH_CAP_FILE_LAZYIO)); /* * If we hold relevant caps, or in the case where we're diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index e4cfa3b02187..de798444bb97 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -861,8 +861,8 @@ int ceph_wait_on_conflict_unlink(struct dentry *dentry) if (!d_same_name(udentry, pdentry, &dname)) goto next; + found = dget_dlock(udentry); spin_unlock(&udentry->d_lock); - found = dget(udentry); break; next: spin_unlock(&udentry->d_lock); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 51c7f2b14f6f..98844fc8a2f7 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1119,7 +1119,7 @@ ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t); extern ssize_t ceph_listxattr(struct dentry *, char *, size_t); extern struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci); extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci); -extern const struct xattr_handler *ceph_xattr_handlers[]; +extern const struct xattr_handler * const ceph_xattr_handlers[]; struct ceph_acl_sec_ctx { #ifdef CONFIG_CEPH_FS_POSIX_ACL diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 0deae4a0f5f1..097ce7f74073 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1446,7 +1446,7 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx) * List of handlers for synthetic system.* attributes. Other * attributes are handled directly. */ -const struct xattr_handler *ceph_xattr_handlers[] = { +const struct xattr_handler * const ceph_xattr_handlers[] = { &ceph_other_xattr_handler, NULL, }; diff --git a/fs/char_dev.c b/fs/char_dev.c index 950b6919fb87..6ba032442b39 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -350,7 +350,7 @@ static struct kobject *cdev_get(struct cdev *p) struct module *owner = p->owner; struct kobject *kobj; - if (owner && !try_module_get(owner)) + if (!try_module_get(owner)) return NULL; kobj = kobject_get_unless_zero(&p->kobj); if (!kobj) diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 9168b2ec9497..60dbfa0f8805 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -495,7 +495,7 @@ static void cramfs_kill_sb(struct super_block *sb) sb->s_mtd = NULL; } else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) { sync_blockdev(sb->s_bdev); - blkdev_put(sb->s_bdev, sb); + bdev_release(sb->s_bdev_handle); } kfree(sbi); } diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index f2ed0c0266cb..c586c5db18b5 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -702,6 +702,6 @@ int ecryptfs_set_f_namelen(long *namelen, long lower_namelen, int ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat, loff_t offset); -extern const struct xattr_handler *ecryptfs_xattr_handlers[]; +extern const struct xattr_handler * const ecryptfs_xattr_handlers[]; #endif /* #ifndef ECRYPTFS_KERNEL_H */ diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 992d9c7e64ae..a25dd3d20008 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1210,7 +1210,7 @@ static const struct xattr_handler ecryptfs_xattr_handler = { .set = ecryptfs_xattr_set, }; -const struct xattr_handler *ecryptfs_xattr_handlers[] = { +const struct xattr_handler * const ecryptfs_xattr_handlers[] = { &ecryptfs_xattr_handler, NULL }; diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 0c2c99c58b5e..f6a0a1748521 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -222,7 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - map->m_bdev = dif->bdev; + map->m_bdev = dif->bdev_handle->bdev; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; map->m_fscache = dif->fscache; @@ -240,7 +240,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - map->m_bdev = dif->bdev; + map->m_bdev = dif->bdev_handle->bdev; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; map->m_fscache = dif->fscache; diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 4ff88d0dd980..cf04e21bfda2 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -47,7 +47,7 @@ typedef u32 erofs_blk_t; struct erofs_device_info { char *path; struct erofs_fscache *fscache; - struct block_device *bdev; + struct bdev_handle *bdev_handle; struct dax_device *dax_dev; u64 dax_part_off; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 3700af9ee173..6fd04781fec5 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -227,7 +227,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, struct erofs_sb_info *sbi = EROFS_SB(sb); struct erofs_fscache *fscache; struct erofs_deviceslot *dis; - struct block_device *bdev; + struct bdev_handle *bdev_handle; void *ptr; ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *pos), EROFS_KMAP); @@ -251,13 +251,13 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, return PTR_ERR(fscache); dif->fscache = fscache; } else if (!sbi->devs->flatdev) { - bdev = blkdev_get_by_path(dif->path, BLK_OPEN_READ, sb->s_type, - NULL); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); - dif->bdev = bdev; - dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off, - NULL, NULL); + bdev_handle = bdev_open_by_path(dif->path, BLK_OPEN_READ, + sb->s_type, NULL); + if (IS_ERR(bdev_handle)) + return PTR_ERR(bdev_handle); + dif->bdev_handle = bdev_handle; + dif->dax_dev = fs_dax_get_by_bdev(bdev_handle->bdev, + &dif->dax_part_off, NULL, NULL); } dif->blocks = le32_to_cpu(dis->blocks); @@ -806,8 +806,8 @@ static int erofs_release_device_info(int id, void *ptr, void *data) struct erofs_device_info *dif = ptr; fs_put_dax(dif->dax_dev, NULL); - if (dif->bdev) - blkdev_put(dif->bdev, &erofs_fs_type); + if (dif->bdev_handle) + bdev_release(dif->bdev_handle); erofs_fscache_unregister_cookie(dif->fscache); dif->fscache = NULL; kfree(dif->path); diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index 09d341675e89..b58316b49a43 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -168,7 +168,7 @@ const struct xattr_handler __maybe_unused erofs_xattr_security_handler = { }; #endif -const struct xattr_handler *erofs_xattr_handlers[] = { +const struct xattr_handler * const erofs_xattr_handlers[] = { &erofs_xattr_user_handler, &erofs_xattr_trusted_handler, #ifdef CONFIG_EROFS_FS_SECURITY diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h index f16283cb8c93..b246cd0e135e 100644 --- a/fs/erofs/xattr.h +++ b/fs/erofs/xattr.h @@ -23,7 +23,7 @@ static inline const char *erofs_xattr_prefix(unsigned int idx, { const struct xattr_handler *handler = NULL; - static const struct xattr_handler *xattr_handler_map[] = { + static const struct xattr_handler * const xattr_handler_map[] = { [EROFS_XATTR_INDEX_USER] = &erofs_xattr_user_handler, #ifdef CONFIG_EROFS_FS_POSIX_ACL [EROFS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, @@ -44,7 +44,7 @@ static inline const char *erofs_xattr_prefix(unsigned int idx, return xattr_prefix(handler); } -extern const struct xattr_handler *erofs_xattr_handlers[]; +extern const struct xattr_handler * const erofs_xattr_handlers[]; int erofs_xattr_prefixes_init(struct super_block *sb); void erofs_xattr_prefixes_cleanup(struct super_block *sb); diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 20f741184673..e849241ebb8f 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -98,7 +98,7 @@ static struct buffer_head *ext2_xattr_cache_find(struct inode *, static void ext2_xattr_rehash(struct ext2_xattr_header *, struct ext2_xattr_entry *); -static const struct xattr_handler *ext2_xattr_handler_map[] = { +static const struct xattr_handler * const ext2_xattr_handler_map[] = { [EXT2_XATTR_INDEX_USER] = &ext2_xattr_user_handler, #ifdef CONFIG_EXT2_FS_POSIX_ACL [EXT2_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, @@ -110,7 +110,7 @@ static const struct xattr_handler *ext2_xattr_handler_map[] = { #endif }; -const struct xattr_handler *ext2_xattr_handlers[] = { +const struct xattr_handler * const ext2_xattr_handlers[] = { &ext2_xattr_user_handler, &ext2_xattr_trusted_handler, #ifdef CONFIG_EXT2_FS_SECURITY diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h index 7925f596e8e2..6a4966949047 100644 --- a/fs/ext2/xattr.h +++ b/fs/ext2/xattr.h @@ -72,7 +72,7 @@ extern void ext2_xattr_delete_inode(struct inode *); extern struct mb_cache *ext2_xattr_create_cache(void); extern void ext2_xattr_destroy_cache(struct mb_cache *cache); -extern const struct xattr_handler *ext2_xattr_handlers[]; +extern const struct xattr_handler * const ext2_xattr_handlers[]; # else /* CONFIG_EXT2_FS_XATTR */ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index df58577ecc3a..8da5fb680210 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1547,7 +1547,7 @@ struct ext4_sb_info { unsigned long s_commit_interval; u32 s_max_batch_time; u32 s_min_batch_time; - struct block_device *s_journal_bdev; + struct bdev_handle *s_journal_bdev_handle; #ifdef CONFIG_QUOTA /* Names of quota files with journalled quota */ char __rcu *s_qf_names[EXT4_MAXQUOTAS]; diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index cdf9bfe10137..11e6f33677a2 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -576,8 +576,9 @@ static bool ext4_getfsmap_is_valid_device(struct super_block *sb, if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX || fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev)) return true; - if (EXT4_SB(sb)->s_journal_bdev && - fm->fmr_device == new_encode_dev(EXT4_SB(sb)->s_journal_bdev->bd_dev)) + if (EXT4_SB(sb)->s_journal_bdev_handle && + fm->fmr_device == + new_encode_dev(EXT4_SB(sb)->s_journal_bdev_handle->bdev->bd_dev)) return true; return false; } @@ -647,9 +648,9 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head, memset(handlers, 0, sizeof(handlers)); handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev); handlers[0].gfd_fn = ext4_getfsmap_datadev; - if (EXT4_SB(sb)->s_journal_bdev) { + if (EXT4_SB(sb)->s_journal_bdev_handle) { handlers[1].gfd_dev = new_encode_dev( - EXT4_SB(sb)->s_journal_bdev->bd_dev); + EXT4_SB(sb)->s_journal_bdev_handle->bdev->bd_dev); handlers[1].gfd_fn = ext4_getfsmap_logdev; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c642adf54599..42a44990d99c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1351,14 +1351,14 @@ static void ext4_put_super(struct super_block *sb) sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); - if (sbi->s_journal_bdev) { + if (sbi->s_journal_bdev_handle) { /* * Invalidate the journal device's buffers. We don't want them * floating about in memory - the physical journal device may * hotswapped, and it breaks the `ro-after' testing code. */ - sync_blockdev(sbi->s_journal_bdev); - invalidate_bdev(sbi->s_journal_bdev); + sync_blockdev(sbi->s_journal_bdev_handle->bdev); + invalidate_bdev(sbi->s_journal_bdev_handle->bdev); } ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); @@ -4233,7 +4233,7 @@ int ext4_calculate_overhead(struct super_block *sb) * Add the internal journal blocks whether the journal has been * loaded or not */ - if (sbi->s_journal && !sbi->s_journal_bdev) + if (sbi->s_journal && !sbi->s_journal_bdev_handle) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ @@ -5670,9 +5670,9 @@ failed_mount: #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); brelse(sbi->s_sbh); - if (sbi->s_journal_bdev) { - invalidate_bdev(sbi->s_journal_bdev); - blkdev_put(sbi->s_journal_bdev, sb); + if (sbi->s_journal_bdev_handle) { + invalidate_bdev(sbi->s_journal_bdev_handle->bdev); + bdev_release(sbi->s_journal_bdev_handle); } out_fail: invalidate_bdev(sb->s_bdev); @@ -5842,12 +5842,13 @@ static journal_t *ext4_open_inode_journal(struct super_block *sb, return journal; } -static struct block_device *ext4_get_journal_blkdev(struct super_block *sb, +static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb, dev_t j_dev, ext4_fsblk_t *j_start, ext4_fsblk_t *j_len) { struct buffer_head *bh; struct block_device *bdev; + struct bdev_handle *bdev_handle; int hblock, blocksize; ext4_fsblk_t sb_block; unsigned long offset; @@ -5856,16 +5857,17 @@ static struct block_device *ext4_get_journal_blkdev(struct super_block *sb, /* see get_tree_bdev why this is needed and safe */ up_write(&sb->s_umount); - bdev = blkdev_get_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb, - &fs_holder_ops); + bdev_handle = bdev_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE, + sb, &fs_holder_ops); down_write(&sb->s_umount); - if (IS_ERR(bdev)) { + if (IS_ERR(bdev_handle)) { ext4_msg(sb, KERN_ERR, "failed to open journal device unknown-block(%u,%u) %ld", - MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev)); - return ERR_CAST(bdev); + MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_handle)); + return bdev_handle; } + bdev = bdev_handle->bdev; blocksize = sb->s_blocksize; hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { @@ -5912,12 +5914,12 @@ static struct block_device *ext4_get_journal_blkdev(struct super_block *sb, *j_start = sb_block + 1; *j_len = ext4_blocks_count(es); brelse(bh); - return bdev; + return bdev_handle; out_bh: brelse(bh); out_bdev: - blkdev_put(bdev, sb); + bdev_release(bdev_handle); return ERR_PTR(errno); } @@ -5927,14 +5929,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb, journal_t *journal; ext4_fsblk_t j_start; ext4_fsblk_t j_len; - struct block_device *journal_bdev; + struct bdev_handle *bdev_handle; int errno = 0; - journal_bdev = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); - if (IS_ERR(journal_bdev)) - return ERR_CAST(journal_bdev); + bdev_handle = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); + if (IS_ERR(bdev_handle)) + return ERR_CAST(bdev_handle); - journal = jbd2_journal_init_dev(journal_bdev, sb->s_bdev, j_start, + journal = jbd2_journal_init_dev(bdev_handle->bdev, sb->s_bdev, j_start, j_len, sb->s_blocksize); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "failed to create device journal"); @@ -5949,14 +5951,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb, goto out_journal; } journal->j_private = sb; - EXT4_SB(sb)->s_journal_bdev = journal_bdev; + EXT4_SB(sb)->s_journal_bdev_handle = bdev_handle; ext4_init_journal_params(sb, journal); return journal; out_journal: jbd2_journal_destroy(journal); out_bdev: - blkdev_put(journal_bdev, sb); + bdev_release(bdev_handle); return ERR_PTR(errno); } @@ -7300,12 +7302,12 @@ static inline int ext3_feature_set_ok(struct super_block *sb) static void ext4_kill_sb(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct block_device *journal_bdev = sbi ? sbi->s_journal_bdev : NULL; + struct bdev_handle *handle = sbi ? sbi->s_journal_bdev_handle : NULL; kill_block_super(sb); - if (journal_bdev) - blkdev_put(journal_bdev, sb); + if (handle) + bdev_release(handle); } static struct file_system_type ext4_fs_type = { diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index b9467ff8d4e9..82dc5e673d5c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -98,7 +98,7 @@ static const struct xattr_handler * const ext4_xattr_handler_map[] = { [EXT4_XATTR_INDEX_HURD] = &ext4_xattr_hurd_handler, }; -const struct xattr_handler *ext4_xattr_handlers[] = { +const struct xattr_handler * const ext4_xattr_handlers[] = { &ext4_xattr_user_handler, &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 824faf0b15a8..bd97c4aa8177 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -193,7 +193,7 @@ extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); extern void ext4_evict_ea_inode(struct inode *inode); -extern const struct xattr_handler *ext4_xattr_handlers[]; +extern const struct xattr_handler * const ext4_xattr_handlers[]; extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index cb9927a6d0c8..9043cedfa12b 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1234,6 +1234,7 @@ struct f2fs_bio_info { #define FDEV(i) (sbi->devs[i]) #define RDEV(i) (raw_super->devs[i]) struct f2fs_dev_info { + struct bdev_handle *bdev_handle; struct block_device *bdev; char path[MAX_PATH_LEN]; unsigned int total_segments; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index ca965136c09f..6172ecd95bd9 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1562,7 +1562,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) for (i = 0; i < sbi->s_ndevs; i++) { if (i > 0) - blkdev_put(FDEV(i).bdev, sbi->sb); + bdev_release(FDEV(i).bdev_handle); #ifdef CONFIG_BLK_DEV_ZONED kvfree(FDEV(i).blkz_seq); #endif @@ -4198,7 +4198,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) for (i = 0; i < max_devices; i++) { if (i == 0) - FDEV(0).bdev = sbi->sb->s_bdev; + FDEV(0).bdev_handle = sbi->sb->s_bdev_handle; else if (!RDEV(i).path[0]) break; @@ -4218,13 +4218,14 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) FDEV(i).end_blk = FDEV(i).start_blk + (FDEV(i).total_segments << sbi->log_blocks_per_seg) - 1; - FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path, - mode, sbi->sb, NULL); + FDEV(i).bdev_handle = bdev_open_by_path( + FDEV(i).path, mode, sbi->sb, NULL); } } - if (IS_ERR(FDEV(i).bdev)) - return PTR_ERR(FDEV(i).bdev); + if (IS_ERR(FDEV(i).bdev_handle)) + return PTR_ERR(FDEV(i).bdev_handle); + FDEV(i).bdev = FDEV(i).bdev_handle->bdev; /* to release errored devices */ sbi->s_ndevs = i + 1; diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index a657284faee3..4314456854f6 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -189,7 +189,7 @@ const struct xattr_handler f2fs_xattr_security_handler = { .set = f2fs_xattr_generic_set, }; -static const struct xattr_handler *f2fs_xattr_handler_map[] = { +static const struct xattr_handler * const f2fs_xattr_handler_map[] = { [F2FS_XATTR_INDEX_USER] = &f2fs_xattr_user_handler, #ifdef CONFIG_F2FS_FS_POSIX_ACL [F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, @@ -202,7 +202,7 @@ static const struct xattr_handler *f2fs_xattr_handler_map[] = { [F2FS_XATTR_INDEX_ADVISE] = &f2fs_xattr_advise_handler, }; -const struct xattr_handler *f2fs_xattr_handlers[] = { +const struct xattr_handler * const f2fs_xattr_handlers[] = { &f2fs_xattr_user_handler, &f2fs_xattr_trusted_handler, #ifdef CONFIG_F2FS_FS_SECURITY diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index b1811c392e6f..a005ffdcf717 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -125,7 +125,7 @@ extern const struct xattr_handler f2fs_xattr_trusted_handler; extern const struct xattr_handler f2fs_xattr_advise_handler; extern const struct xattr_handler f2fs_xattr_security_handler; -extern const struct xattr_handler *f2fs_xattr_handlers[]; +extern const struct xattr_handler * const f2fs_xattr_handlers[]; extern int f2fs_setxattr(struct inode *, int, const char *, const void *, size_t, struct page *, int); diff --git a/fs/file.c b/fs/file.c index 3e4a4dfa38fc..5fb0b146e79e 100644 --- a/fs/file.c +++ b/fs/file.c @@ -604,6 +604,9 @@ void fd_install(unsigned int fd, struct file *file) struct files_struct *files = current->files; struct fdtable *fdt; + if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) + return; + rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { @@ -853,8 +856,104 @@ void do_close_on_exec(struct files_struct *files) spin_unlock(&files->file_lock); } +static struct file *__get_file_rcu(struct file __rcu **f) +{ + struct file __rcu *file; + struct file __rcu *file_reloaded; + struct file __rcu *file_reloaded_cmp; + + file = rcu_dereference_raw(*f); + if (!file) + return NULL; + + if (unlikely(!atomic_long_inc_not_zero(&file->f_count))) + return ERR_PTR(-EAGAIN); + + file_reloaded = rcu_dereference_raw(*f); + + /* + * Ensure that all accesses have a dependency on the load from + * rcu_dereference_raw() above so we get correct ordering + * between reuse/allocation and the pointer check below. + */ + file_reloaded_cmp = file_reloaded; + OPTIMIZER_HIDE_VAR(file_reloaded_cmp); + + /* + * atomic_long_inc_not_zero() above provided a full memory + * barrier when we acquired a reference. + * + * This is paired with the write barrier from assigning to the + * __rcu protected file pointer so that if that pointer still + * matches the current file, we know we have successfully + * acquired a reference to the right file. + * + * If the pointers don't match the file has been reallocated by + * SLAB_TYPESAFE_BY_RCU. + */ + if (file == file_reloaded_cmp) + return file_reloaded; + + fput(file); + return ERR_PTR(-EAGAIN); +} + +/** + * get_file_rcu - try go get a reference to a file under rcu + * @f: the file to get a reference on + * + * This function tries to get a reference on @f carefully verifying that + * @f hasn't been reused. + * + * This function should rarely have to be used and only by users who + * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. + * + * Return: Returns @f with the reference count increased or NULL. + */ +struct file *get_file_rcu(struct file __rcu **f) +{ + for (;;) { + struct file __rcu *file; + + file = __get_file_rcu(f); + if (unlikely(!file)) + return NULL; + + if (unlikely(IS_ERR(file))) + continue; + + return file; + } +} +EXPORT_SYMBOL_GPL(get_file_rcu); + +/** + * get_file_active - try go get a reference to a file + * @f: the file to get a reference on + * + * In contast to get_file_rcu() the pointer itself isn't part of the + * reference counting. + * + * This function should rarely have to be used and only by users who + * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. + * + * Return: Returns @f with the reference count increased or NULL. + */ +struct file *get_file_active(struct file **f) +{ + struct file __rcu *file; + + rcu_read_lock(); + file = __get_file_rcu(f); + rcu_read_unlock(); + if (IS_ERR(file)) + file = NULL; + return file; +} +EXPORT_SYMBOL_GPL(get_file_active); + static inline struct file *__fget_files_rcu(struct files_struct *files, - unsigned int fd, fmode_t mask) + unsigned int fd, fmode_t mask) { for (;;) { struct file *file; @@ -865,12 +964,6 @@ static inline struct file *__fget_files_rcu(struct files_struct *files, return NULL; fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds); - file = rcu_dereference_raw(*fdentry); - if (unlikely(!file)) - return NULL; - - if (unlikely(file->f_mode & mask)) - return NULL; /* * Ok, we have a file pointer. However, because we do @@ -879,10 +972,15 @@ static inline struct file *__fget_files_rcu(struct files_struct *files, * * Such a race can take two forms: * - * (a) the file ref already went down to zero, - * and get_file_rcu() fails. Just try again: + * (a) the file ref already went down to zero and the + * file hasn't been reused yet or the file count + * isn't zero but the file has already been reused. */ - if (unlikely(!get_file_rcu(file))) + file = __get_file_rcu(fdentry); + if (unlikely(!file)) + return NULL; + + if (unlikely(IS_ERR(file))) continue; /* @@ -893,13 +991,21 @@ static inline struct file *__fget_files_rcu(struct files_struct *files, * * If so, we need to put our ref and try again. */ - if (unlikely(rcu_dereference_raw(files->fdt) != fdt) || - unlikely(rcu_dereference_raw(*fdentry) != file)) { + if (unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* + * This isn't the file we're looking for or we're not + * allowed to get a reference to it. + */ + if (unlikely(file->f_mode & mask)) { + fput(file); + return NULL; + } + + /* * Ok, we have a ref to the file, and checked that it * still exists. */ @@ -948,7 +1054,14 @@ struct file *fget_task(struct task_struct *task, unsigned int fd) return file; } -struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd) +struct file *lookup_fdget_rcu(unsigned int fd) +{ + return __fget_files_rcu(current->files, fd, 0); + +} +EXPORT_SYMBOL_GPL(lookup_fdget_rcu); + +struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; @@ -957,13 +1070,13 @@ struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd) task_lock(task); files = task->files; if (files) - file = files_lookup_fd_rcu(files, fd); + file = __fget_files_rcu(files, fd, 0); task_unlock(task); return file; } -struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *ret_fd) +struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; @@ -974,7 +1087,7 @@ struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *ret files = task->files; if (files) { for (; fd < files_fdtable(files)->max_fds; fd++) { - file = files_lookup_fd_rcu(files, fd); + file = __fget_files_rcu(files, fd, 0); if (file) break; } @@ -983,7 +1096,7 @@ struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *ret *ret_fd = fd; return file; } -EXPORT_SYMBOL(task_lookup_next_fd_rcu); +EXPORT_SYMBOL(task_lookup_next_fdget_rcu); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. @@ -1272,12 +1385,16 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; + struct file *f; int retval = oldfd; rcu_read_lock(); - if (!files_lookup_fd_rcu(files, oldfd)) + f = __fget_files_rcu(files, oldfd, 0); + if (!f) retval = -EBADF; rcu_read_unlock(); + if (f) + fput(f); return retval; } return ksys_dup3(oldfd, newfd, 0); diff --git a/fs/file_table.c b/fs/file_table.c index ee21b3da9d08..fa92743ba6a9 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -44,10 +44,10 @@ static struct kmem_cache *filp_cachep __read_mostly; static struct percpu_counter nr_files __cacheline_aligned_in_smp; -/* Container for backing file with optional real path */ +/* Container for backing file with optional user path */ struct backing_file { struct file file; - struct path real_path; + struct path user_path; }; static inline struct backing_file *backing_file(struct file *f) @@ -55,31 +55,36 @@ static inline struct backing_file *backing_file(struct file *f) return container_of(f, struct backing_file, file); } -struct path *backing_file_real_path(struct file *f) +struct path *backing_file_user_path(struct file *f) { - return &backing_file(f)->real_path; + return &backing_file(f)->user_path; } -EXPORT_SYMBOL_GPL(backing_file_real_path); +EXPORT_SYMBOL_GPL(backing_file_user_path); -static void file_free_rcu(struct rcu_head *head) +static inline void file_free(struct file *f) { - struct file *f = container_of(head, struct file, f_rcuhead); - + security_file_free(f); + if (likely(!(f->f_mode & FMODE_NOACCOUNT))) + percpu_counter_dec(&nr_files); put_cred(f->f_cred); - if (unlikely(f->f_mode & FMODE_BACKING)) + if (unlikely(f->f_mode & FMODE_BACKING)) { + path_put(backing_file_user_path(f)); kfree(backing_file(f)); - else + } else { kmem_cache_free(filp_cachep, f); + } } -static inline void file_free(struct file *f) +void release_empty_file(struct file *f) { - security_file_free(f); - if (unlikely(f->f_mode & FMODE_BACKING)) - path_put(backing_file_real_path(f)); - if (likely(!(f->f_mode & FMODE_NOACCOUNT))) - percpu_counter_dec(&nr_files); - call_rcu(&f->f_rcuhead, file_free_rcu); + WARN_ON_ONCE(f->f_mode & (FMODE_BACKING | FMODE_OPENED)); + if (atomic_long_dec_and_test(&f->f_count)) { + security_file_free(f); + put_cred(f->f_cred); + if (likely(!(f->f_mode & FMODE_NOACCOUNT))) + percpu_counter_dec(&nr_files); + kmem_cache_free(filp_cachep, f); + } } /* @@ -164,7 +169,6 @@ static int init_file(struct file *f, int flags, const struct cred *cred) return error; } - atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); mutex_init(&f->f_pos_lock); @@ -172,6 +176,12 @@ static int init_file(struct file *f, int flags, const struct cred *cred) f->f_mode = OPEN_FMODE(flags); /* f->f_version: 0 */ + /* + * We're SLAB_TYPESAFE_BY_RCU so initialize f_count last. While + * fget-rcu pattern users need to be able to handle spurious + * refcount bumps we should reinitialize the reused file first. + */ + atomic_long_set(&f->f_count, 1); return 0; } @@ -471,7 +481,8 @@ EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, - SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); + SLAB_TYPESAFE_BY_RCU | SLAB_HWCACHE_ALIGN | + SLAB_PANIC | SLAB_ACCOUNT, NULL); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index c1af01b2c42d..1767493dffda 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -613,6 +613,24 @@ out_free: kfree(isw); } +static bool isw_prepare_wbs_switch(struct inode_switch_wbs_context *isw, + struct list_head *list, int *nr) +{ + struct inode *inode; + + list_for_each_entry(inode, list, i_io_list) { + if (!inode_prepare_wbs_switch(inode, isw->new_wb)) + continue; + + isw->inodes[*nr] = inode; + (*nr)++; + + if (*nr >= WB_MAX_INODES_PER_ISW - 1) + return true; + } + return false; +} + /** * cleanup_offline_cgwb - detach associated inodes * @wb: target wb @@ -625,7 +643,6 @@ bool cleanup_offline_cgwb(struct bdi_writeback *wb) { struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; - struct inode *inode; int nr; bool restart = false; @@ -647,17 +664,17 @@ bool cleanup_offline_cgwb(struct bdi_writeback *wb) nr = 0; spin_lock(&wb->list_lock); - list_for_each_entry(inode, &wb->b_attached, i_io_list) { - if (!inode_prepare_wbs_switch(inode, isw->new_wb)) - continue; - - isw->inodes[nr++] = inode; - - if (nr >= WB_MAX_INODES_PER_ISW - 1) { - restart = true; - break; - } - } + /* + * In addition to the inodes that have completed writeback, also switch + * cgwbs for those inodes only with dirty timestamps. Otherwise, those + * inodes won't be written back for a long time when lazytime is + * enabled, and thus pinning the dying cgwbs. It won't break the + * bandwidth restrictions, as writeback of inode metadata is not + * accounted for. + */ + restart = isw_prepare_wbs_switch(isw, &wb->b_attached, &nr); + if (!restart) + restart = isw_prepare_wbs_switch(isw, &wb->b_dirty_time, &nr); spin_unlock(&wb->list_lock); /* no attached inodes? bail out */ diff --git a/fs/fs_context.c b/fs/fs_context.c index a0ad7a0c4680..98589aae5208 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -192,17 +192,19 @@ int vfs_parse_fs_string(struct fs_context *fc, const char *key, EXPORT_SYMBOL(vfs_parse_fs_string); /** - * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data + * vfs_parse_monolithic_sep - Parse key[=val][,key[=val]]* mount data * @fc: The superblock configuration to fill in. * @data: The data to parse + * @sep: callback for separating next option * - * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be - * called from the ->monolithic_mount_data() fs_context operation. + * Parse a blob of data that's in key[=val][,key[=val]]* form with a custom + * option separator callback. * * Returns 0 on success or the error returned by the ->parse_option() fs_context * operation on failure. */ -int generic_parse_monolithic(struct fs_context *fc, void *data) +int vfs_parse_monolithic_sep(struct fs_context *fc, void *data, + char *(*sep)(char **)) { char *options = data, *key; int ret = 0; @@ -214,7 +216,7 @@ int generic_parse_monolithic(struct fs_context *fc, void *data) if (ret) return ret; - while ((key = strsep(&options, ",")) != NULL) { + while ((key = sep(&options)) != NULL) { if (*key) { size_t v_len = 0; char *value = strchr(key, '='); @@ -233,6 +235,28 @@ int generic_parse_monolithic(struct fs_context *fc, void *data) return ret; } +EXPORT_SYMBOL(vfs_parse_monolithic_sep); + +static char *vfs_parse_comma_sep(char **s) +{ + return strsep(s, ","); +} + +/** + * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data + * @fc: The superblock configuration to fill in. + * @data: The data to parse + * + * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be + * called from the ->monolithic_mount_data() fs_context operation. + * + * Returns 0 on success or the error returned by the ->parse_option() fs_context + * operation on failure. + */ +int generic_parse_monolithic(struct fs_context *fc, void *data) +{ + return vfs_parse_monolithic_sep(fc, data, vfs_parse_comma_sep); +} EXPORT_SYMBOL(generic_parse_monolithic); /** diff --git a/fs/fsopen.c b/fs/fsopen.c index ce03f6521c88..6593ae518115 100644 --- a/fs/fsopen.c +++ b/fs/fsopen.c @@ -465,6 +465,7 @@ SYSCALL_DEFINE5(fsconfig, param.file = fget(aux); if (!param.file) goto out_key; + param.dirfd = aux; break; default: break; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index bf0b85d0b95c..6e6e721f421b 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1284,7 +1284,7 @@ ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value, size_t size); ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size); int fuse_removexattr(struct inode *inode, const char *name); -extern const struct xattr_handler *fuse_xattr_handlers[]; +extern const struct xattr_handler * const fuse_xattr_handlers[]; struct posix_acl; struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu); diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index 49c01559580f..5b423fdbb13f 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -209,7 +209,7 @@ static const struct xattr_handler fuse_xattr_handler = { .set = fuse_xattr_set, }; -const struct xattr_handler *fuse_xattr_handlers[] = { +const struct xattr_handler * const fuse_xattr_handlers[] = { &fuse_xattr_handler, NULL }; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 4a280be229a6..3772a5d9e85c 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -2719,16 +2719,19 @@ static struct file *gfs2_glockfd_next_file(struct gfs2_glockfd_iter *i) for(;; i->fd++) { struct inode *inode; - i->file = task_lookup_next_fd_rcu(i->task, &i->fd); + i->file = task_lookup_next_fdget_rcu(i->task, &i->fd); if (!i->file) { i->fd = 0; break; } + inode = file_inode(i->file); - if (inode->i_sb != i->sb) - continue; - if (get_file_rcu(i->file)) + if (inode->i_sb == i->sb) break; + + rcu_read_unlock(); + fput(i->file); + rcu_read_lock(); } rcu_read_unlock(); return i->file; diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h index ab9c83106932..b4ddf6244586 100644 --- a/fs/gfs2/super.h +++ b/fs/gfs2/super.h @@ -60,8 +60,8 @@ extern const struct export_operations gfs2_export_ops; extern const struct super_operations gfs2_super_ops; extern const struct dentry_operations gfs2_dops; -extern const struct xattr_handler *gfs2_xattr_handlers_max[]; -extern const struct xattr_handler **gfs2_xattr_handlers_min; +extern const struct xattr_handler * const gfs2_xattr_handlers_max[]; +extern const struct xattr_handler * const *gfs2_xattr_handlers_min; #endif /* __SUPER_DOT_H__ */ diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 4fea70c0fe3d..79d5c5559512 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -1494,7 +1494,7 @@ static const struct xattr_handler gfs2_xattr_trusted_handler = { .set = gfs2_xattr_set, }; -const struct xattr_handler *gfs2_xattr_handlers_max[] = { +const struct xattr_handler * const gfs2_xattr_handlers_max[] = { /* GFS2_FS_FORMAT_MAX */ &gfs2_xattr_trusted_handler, @@ -1504,4 +1504,4 @@ const struct xattr_handler *gfs2_xattr_handlers_max[] = { NULL, }; -const struct xattr_handler **gfs2_xattr_handlers_min = gfs2_xattr_handlers_max + 1; +const struct xattr_handler * const *gfs2_xattr_handlers_min = gfs2_xattr_handlers_max + 1; diff --git a/fs/hfs/attr.c b/fs/hfs/attr.c index 6341bb248247..f8395cdd1adf 100644 --- a/fs/hfs/attr.c +++ b/fs/hfs/attr.c @@ -146,7 +146,7 @@ static const struct xattr_handler hfs_type_handler = { .set = hfs_xattr_set, }; -const struct xattr_handler *hfs_xattr_handlers[] = { +const struct xattr_handler * const hfs_xattr_handlers[] = { &hfs_creator_handler, &hfs_type_handler, NULL diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 49d02524e667..b5a6ad5df357 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -215,7 +215,7 @@ extern void hfs_evict_inode(struct inode *); extern void hfs_delete_inode(struct inode *); /* attr.c */ -extern const struct xattr_handler *hfs_xattr_handlers[]; +extern const struct xattr_handler * const hfs_xattr_handlers[]; /* mdb.c */ extern int hfs_mdb_get(struct super_block *); diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index 58021e73c00b..9c9ff6b8c6f7 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -13,7 +13,7 @@ static int hfsplus_removexattr(struct inode *inode, const char *name); -const struct xattr_handler *hfsplus_xattr_handlers[] = { +const struct xattr_handler * const hfsplus_xattr_handlers[] = { &hfsplus_xattr_osx_handler, &hfsplus_xattr_user_handler, &hfsplus_xattr_trusted_handler, diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h index d14e362b3eba..15cc55e41410 100644 --- a/fs/hfsplus/xattr.h +++ b/fs/hfsplus/xattr.h @@ -17,7 +17,7 @@ extern const struct xattr_handler hfsplus_xattr_user_handler; extern const struct xattr_handler hfsplus_xattr_trusted_handler; extern const struct xattr_handler hfsplus_xattr_security_handler; -extern const struct xattr_handler *hfsplus_xattr_handlers[]; +extern const struct xattr_handler * const hfsplus_xattr_handlers[]; int __hfsplus_setxattr(struct inode *inode, const char *name, const void *value, size_t size, int flags); diff --git a/fs/init.c b/fs/init.c index 9684406a8416..e9387b6c4f30 100644 --- a/fs/init.c +++ b/fs/init.c @@ -153,8 +153,7 @@ int __init init_mknod(const char *filename, umode_t mode, unsigned int dev) if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); + mode = mode_strip_umask(d_inode(path.dentry), mode); error = security_path_mknod(&path, dentry, mode, dev); if (!error) error = vfs_mknod(mnt_idmap(path.mnt), path.dentry->d_inode, @@ -229,8 +228,7 @@ int __init init_mkdir(const char *pathname, umode_t mode) dentry = kern_path_create(AT_FDCWD, pathname, &path, LOOKUP_DIRECTORY); if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); + mode = mode_strip_umask(d_inode(path.dentry), mode); error = security_path_mkdir(&path, dentry, mode); if (!error) error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, diff --git a/fs/inode.c b/fs/inode.c index 0612ad9c0227..4f8984b97df0 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2012,7 +2012,7 @@ void touch_atime(const struct path *path) if (!sb_start_write_trylock(inode->i_sb)) return; - if (__mnt_want_write(mnt) != 0) + if (mnt_get_write_access(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to @@ -2024,7 +2024,7 @@ void touch_atime(const struct path *path) * of the fs read only, e.g. subvolumes in Btrfs. */ inode_update_time(inode, S_ATIME); - __mnt_drop_write(mnt); + mnt_put_write_access(mnt); skip_update: sb_end_write(inode->i_sb); } @@ -2138,9 +2138,9 @@ static int __file_update_time(struct file *file, int sync_mode) struct inode *inode = file_inode(file); /* try to update time settings */ - if (!__mnt_want_write_file(file)) { + if (!mnt_get_write_access_file(file)) { ret = inode_update_time(inode, sync_mode); - __mnt_drop_write_file(file); + mnt_put_write_access_file(file); } return ret; diff --git a/fs/internal.h b/fs/internal.h index d64ae03998cc..58e43341aebf 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -73,8 +73,8 @@ extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); -extern int __mnt_want_write_file(struct file *); -extern void __mnt_drop_write_file(struct file *); +int mnt_get_write_access_file(struct file *file); +void mnt_put_write_access_file(struct file *file); extern void dissolve_on_fput(struct vfsmount *); extern bool may_mount(void); @@ -94,14 +94,22 @@ extern void chroot_fs_refs(const struct path *, const struct path *); struct file *alloc_empty_file(int flags, const struct cred *cred); struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred); struct file *alloc_empty_backing_file(int flags, const struct cred *cred); +void release_empty_file(struct file *f); + +static inline void file_put_write_access(struct file *file) +{ + put_write_access(file->f_inode); + mnt_put_write_access(file->f_path.mnt); + if (unlikely(file->f_mode & FMODE_BACKING)) + mnt_put_write_access(backing_file_user_path(file)->mnt); +} static inline void put_file_access(struct file *file) { if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_dec(file->f_inode); } else if (file->f_mode & FMODE_WRITER) { - put_write_access(file->f_inode); - __mnt_drop_write(file->f_path.mnt); + file_put_write_access(file); } } @@ -130,9 +138,9 @@ static inline void sb_start_ro_state_change(struct super_block *sb) * mnt_is_readonly() making sure if mnt_is_readonly() sees SB_RDONLY * cleared, it will see s_readonly_remount set. * For RW->RO transition, the barrier pairs with the barrier in - * __mnt_want_write() before the mnt_is_readonly() check. The barrier - * makes sure if __mnt_want_write() sees MNT_WRITE_HOLD already - * cleared, it will see s_readonly_remount set. + * mnt_get_write_access() before the mnt_is_readonly() check. + * The barrier makes sure if mnt_get_write_access() sees MNT_WRITE_HOLD + * already cleared, it will see s_readonly_remount set. */ smp_wmb(); } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 5db54ca29a35..2bc0aa23fde3 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -881,8 +881,10 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ + bytes = iov_iter_count(i); +retry: offset = pos & (chunk - 1); - bytes = min(chunk - offset, iov_iter_count(i)); + bytes = min(chunk - offset, bytes); status = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags); if (unlikely(status)) @@ -933,10 +935,12 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) * halfway through, might be a race with munmap, * might be severe memory pressure. */ - if (copied) - bytes = copied; if (chunk > PAGE_SIZE) chunk /= 2; + if (copied) { + bytes = copied; + goto retry; + } } else { pos += status; written += status; diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index 3b6bdc9a49e1..00224f3a8d6e 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -920,7 +920,7 @@ struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, * do_jffs2_setxattr(inode, xprefix, xname, buffer, size, flags) * is an implementation of setxattr handler on jffs2. * -------------------------------------------------- */ -const struct xattr_handler *jffs2_xattr_handlers[] = { +const struct xattr_handler * const jffs2_xattr_handlers[] = { &jffs2_user_xattr_handler, #ifdef CONFIG_JFFS2_FS_SECURITY &jffs2_security_xattr_handler, diff --git a/fs/jffs2/xattr.h b/fs/jffs2/xattr.h index 1b5030a3349d..7e7de093ec0a 100644 --- a/fs/jffs2/xattr.h +++ b/fs/jffs2/xattr.h @@ -94,7 +94,7 @@ extern int do_jffs2_getxattr(struct inode *inode, int xprefix, const char *xname extern int do_jffs2_setxattr(struct inode *inode, int xprefix, const char *xname, const char *buffer, size_t size, int flags); -extern const struct xattr_handler *jffs2_xattr_handlers[]; +extern const struct xattr_handler * const jffs2_xattr_handlers[]; extern const struct xattr_handler jffs2_user_xattr_handler; extern const struct xattr_handler jffs2_trusted_xattr_handler; diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index e855b8fde76c..cb6d1fda66a7 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1058,7 +1058,7 @@ void jfs_syncpt(struct jfs_log *log, int hard_sync) int lmLogOpen(struct super_block *sb) { int rc; - struct block_device *bdev; + struct bdev_handle *bdev_handle; struct jfs_log *log; struct jfs_sb_info *sbi = JFS_SBI(sb); @@ -1070,7 +1070,7 @@ int lmLogOpen(struct super_block *sb) mutex_lock(&jfs_log_mutex); list_for_each_entry(log, &jfs_external_logs, journal_list) { - if (log->bdev->bd_dev == sbi->logdev) { + if (log->bdev_handle->bdev->bd_dev == sbi->logdev) { if (!uuid_equal(&log->uuid, &sbi->loguuid)) { jfs_warn("wrong uuid on JFS journal"); mutex_unlock(&jfs_log_mutex); @@ -1100,14 +1100,14 @@ int lmLogOpen(struct super_block *sb) * file systems to log may have n-to-1 relationship; */ - bdev = blkdev_get_by_dev(sbi->logdev, BLK_OPEN_READ | BLK_OPEN_WRITE, - log, NULL); - if (IS_ERR(bdev)) { - rc = PTR_ERR(bdev); + bdev_handle = bdev_open_by_dev(sbi->logdev, + BLK_OPEN_READ | BLK_OPEN_WRITE, log, NULL); + if (IS_ERR(bdev_handle)) { + rc = PTR_ERR(bdev_handle); goto free; } - log->bdev = bdev; + log->bdev_handle = bdev_handle; uuid_copy(&log->uuid, &sbi->loguuid); /* @@ -1141,7 +1141,7 @@ journal_found: lbmLogShutdown(log); close: /* close external log device */ - blkdev_put(bdev, log); + bdev_release(bdev_handle); free: /* free log descriptor */ mutex_unlock(&jfs_log_mutex); @@ -1162,7 +1162,7 @@ static int open_inline_log(struct super_block *sb) init_waitqueue_head(&log->syncwait); set_bit(log_INLINELOG, &log->flag); - log->bdev = sb->s_bdev; + log->bdev_handle = sb->s_bdev_handle; log->base = addressPXD(&JFS_SBI(sb)->logpxd); log->size = lengthPXD(&JFS_SBI(sb)->logpxd) >> (L2LOGPSIZE - sb->s_blocksize_bits); @@ -1436,7 +1436,7 @@ int lmLogClose(struct super_block *sb) { struct jfs_sb_info *sbi = JFS_SBI(sb); struct jfs_log *log = sbi->log; - struct block_device *bdev; + struct bdev_handle *bdev_handle; int rc = 0; jfs_info("lmLogClose: log:0x%p", log); @@ -1482,10 +1482,10 @@ int lmLogClose(struct super_block *sb) * external log as separate logical volume */ list_del(&log->journal_list); - bdev = log->bdev; + bdev_handle = log->bdev_handle; rc = lmLogShutdown(log); - blkdev_put(bdev, log); + bdev_release(bdev_handle); kfree(log); @@ -1972,7 +1972,7 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp) bp->l_flag |= lbmREAD; - bio = bio_alloc(log->bdev, 1, REQ_OP_READ, GFP_NOFS); + bio = bio_alloc(log->bdev_handle->bdev, 1, REQ_OP_READ, GFP_NOFS); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); @@ -2110,10 +2110,15 @@ static void lbmStartIO(struct lbuf * bp) { struct bio *bio; struct jfs_log *log = bp->l_log; + struct block_device *bdev = NULL; jfs_info("lbmStartIO"); - bio = bio_alloc(log->bdev, 1, REQ_OP_WRITE | REQ_SYNC, GFP_NOFS); + if (!log->no_integrity) + bdev = log->bdev_handle->bdev; + + bio = bio_alloc(bdev, 1, REQ_OP_WRITE | REQ_SYNC, + GFP_NOFS); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); diff --git a/fs/jfs/jfs_logmgr.h b/fs/jfs/jfs_logmgr.h index 805877ce5020..84aa2d253907 100644 --- a/fs/jfs/jfs_logmgr.h +++ b/fs/jfs/jfs_logmgr.h @@ -356,7 +356,7 @@ struct jfs_log { * before writing syncpt. */ struct list_head journal_list; /* Global list */ - struct block_device *bdev; /* 4: log lv pointer */ + struct bdev_handle *bdev_handle; /* 4: log lv pointer */ int serial; /* 4: log mount serial number */ s64 base; /* @8: log extent address (inline log ) */ diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index b83aae56a1f2..415eb65a36ff 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -430,7 +430,8 @@ int updateSuper(struct super_block *sb, uint state) if (state == FM_MOUNT) { /* record log's dev_t and mount serial number */ - j_sb->s_logdev = cpu_to_le32(new_encode_dev(sbi->log->bdev->bd_dev)); + j_sb->s_logdev = cpu_to_le32( + new_encode_dev(sbi->log->bdev_handle->bdev->bd_dev)); j_sb->s_logserial = cpu_to_le32(sbi->log->serial); } else if (state == FM_CLEAN) { /* diff --git a/fs/jfs/jfs_xattr.h b/fs/jfs/jfs_xattr.h index 0d33816d251d..ec67d8554d2c 100644 --- a/fs/jfs/jfs_xattr.h +++ b/fs/jfs/jfs_xattr.h @@ -46,7 +46,7 @@ extern int __jfs_setxattr(tid_t, struct inode *, const char *, const void *, extern ssize_t __jfs_getxattr(struct inode *, const char *, void *, size_t); extern ssize_t jfs_listxattr(struct dentry *, char *, size_t); -extern const struct xattr_handler *jfs_xattr_handlers[]; +extern const struct xattr_handler * const jfs_xattr_handlers[]; #ifdef CONFIG_JFS_SECURITY extern int jfs_init_security(tid_t, struct inode *, struct inode *, diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 8577ad494e05..0fb7afac298e 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -985,7 +985,7 @@ static const struct xattr_handler jfs_trusted_xattr_handler = { .set = jfs_xattr_set, }; -const struct xattr_handler *jfs_xattr_handlers[] = { +const struct xattr_handler * const jfs_xattr_handlers[] = { &jfs_os2_xattr_handler, &jfs_user_xattr_handler, &jfs_security_xattr_handler, diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 401c084300ed..b83054da68b3 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -445,7 +445,7 @@ static const struct xattr_handler kernfs_user_xattr_handler = { .set = kernfs_vfs_user_xattr_set, }; -const struct xattr_handler *kernfs_xattr_handlers[] = { +const struct xattr_handler * const kernfs_xattr_handlers[] = { &kernfs_trusted_xattr_handler, &kernfs_security_xattr_handler, &kernfs_user_xattr_handler, diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index a9b854cdfdb5..237f2764b941 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -127,7 +127,7 @@ extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; /* * inode.c */ -extern const struct xattr_handler *kernfs_xattr_handlers[]; +extern const struct xattr_handler * const kernfs_xattr_handlers[]; void kernfs_evict_inode(struct inode *inode); int kernfs_iop_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); diff --git a/fs/namei.c b/fs/namei.c index 567ee547492b..71c13b2990b4 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -188,7 +188,7 @@ getname_flags(const char __user *filename, int flags, int *empty) } } - result->refcnt = 1; + atomic_set(&result->refcnt, 1); /* The empty path is special. */ if (unlikely(!len)) { if (empty) @@ -249,7 +249,7 @@ getname_kernel(const char * filename) memcpy((char *)result->name, filename, len); result->uptr = NULL; result->aname = NULL; - result->refcnt = 1; + atomic_set(&result->refcnt, 1); audit_getname(result); return result; @@ -261,9 +261,10 @@ void putname(struct filename *name) if (IS_ERR(name)) return; - BUG_ON(name->refcnt <= 0); + if (WARN_ON_ONCE(!atomic_read(&name->refcnt))) + return; - if (--name->refcnt > 0) + if (!atomic_dec_and_test(&name->refcnt)) return; if (name->name != name->iname) { @@ -3104,25 +3105,6 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) EXPORT_SYMBOL(unlock_rename); /** - * mode_strip_umask - handle vfs umask stripping - * @dir: parent directory of the new inode - * @mode: mode of the new inode to be created in @dir - * - * Umask stripping depends on whether or not the filesystem supports POSIX - * ACLs. If the filesystem doesn't support it umask stripping is done directly - * in here. If the filesystem does support POSIX ACLs umask stripping is - * deferred until the filesystem calls posix_acl_create(). - * - * Returns: mode - */ -static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) -{ - if (!IS_POSIXACL(dir)) - mode &= ~current_umask(); - return mode; -} - -/** * vfs_prepare_mode - prepare the mode to be used for a new inode * @idmap: idmap of the mount the inode was found from * @dir: parent directory of the new inode @@ -3535,7 +3517,8 @@ static const char *open_last_lookups(struct nameidata *nd, if (likely(dentry)) goto finish_lookup; - BUG_ON(nd->flags & LOOKUP_RCU); + if (WARN_ON_ONCE(nd->flags & LOOKUP_RCU)) + return ERR_PTR(-ECHILD); } else { /* create side of things */ if (nd->flags & LOOKUP_RCU) { @@ -3802,7 +3785,10 @@ static struct file *path_openat(struct nameidata *nd, WARN_ON(1); error = -EINVAL; } - fput(file); + if (unlikely(file->f_mode & FMODE_OPENED)) + fput(file); + else + release_empty_file(file); if (error == -EOPENSTALE) { if (flags & LOOKUP_RCU) error = -ECHILD; @@ -4386,11 +4372,9 @@ retry_deleg: if (!IS_ERR(dentry)) { /* Why not before? Because we want correct error value */ - if (last.name[last.len]) + if (last.name[last.len] || d_is_negative(dentry)) goto slashes; inode = dentry->d_inode; - if (d_is_negative(dentry)) - goto slashes; ihold(inode); error = security_path_unlink(&path, dentry); if (error) diff --git a/fs/namespace.c b/fs/namespace.c index e157efc54023..6bde71735efa 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -330,16 +330,16 @@ static int mnt_is_readonly(struct vfsmount *mnt) * can determine when writes are able to occur to a filesystem. */ /** - * __mnt_want_write - get write access to a mount without freeze protection + * mnt_get_write_access - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being - * frozen. When the write operation is finished, __mnt_drop_write() must be + * frozen. When the write operation is finished, mnt_put_write_access() must be * called. This is effectively a refcount. */ -int __mnt_want_write(struct vfsmount *m) +int mnt_get_write_access(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; @@ -386,6 +386,7 @@ int __mnt_want_write(struct vfsmount *m) return ret; } +EXPORT_SYMBOL_GPL(mnt_get_write_access); /** * mnt_want_write - get write access to a mount @@ -401,7 +402,7 @@ int mnt_want_write(struct vfsmount *m) int ret; sb_start_write(m->mnt_sb); - ret = __mnt_want_write(m); + ret = mnt_get_write_access(m); if (ret) sb_end_write(m->mnt_sb); return ret; @@ -409,15 +410,15 @@ int mnt_want_write(struct vfsmount *m) EXPORT_SYMBOL_GPL(mnt_want_write); /** - * __mnt_want_write_file - get write access to a file's mount + * mnt_get_write_access_file - get write access to a file's mount * @file: the file who's mount on which to take a write * - * This is like __mnt_want_write, but if the file is already open for writing it + * This is like mnt_get_write_access, but if @file is already open for write it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the check for emergency r/o remounts. This must be - * paired with __mnt_drop_write_file. + * paired with mnt_put_write_access_file. */ -int __mnt_want_write_file(struct file *file) +int mnt_get_write_access_file(struct file *file) { if (file->f_mode & FMODE_WRITER) { /* @@ -428,7 +429,7 @@ int __mnt_want_write_file(struct file *file) return -EROFS; return 0; } - return __mnt_want_write(file->f_path.mnt); + return mnt_get_write_access(file->f_path.mnt); } /** @@ -445,7 +446,7 @@ int mnt_want_write_file(struct file *file) int ret; sb_start_write(file_inode(file)->i_sb); - ret = __mnt_want_write_file(file); + ret = mnt_get_write_access_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; @@ -453,19 +454,20 @@ int mnt_want_write_file(struct file *file) EXPORT_SYMBOL_GPL(mnt_want_write_file); /** - * __mnt_drop_write - give up write access to a mount + * mnt_put_write_access - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with - * __mnt_want_write() call above. + * mnt_get_write_access() call above. */ -void __mnt_drop_write(struct vfsmount *mnt) +void mnt_put_write_access(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } +EXPORT_SYMBOL_GPL(mnt_put_write_access); /** * mnt_drop_write - give up write access to a mount @@ -477,20 +479,20 @@ void __mnt_drop_write(struct vfsmount *mnt) */ void mnt_drop_write(struct vfsmount *mnt) { - __mnt_drop_write(mnt); + mnt_put_write_access(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); -void __mnt_drop_write_file(struct file *file) +void mnt_put_write_access_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) - __mnt_drop_write(file->f_path.mnt); + mnt_put_write_access(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { - __mnt_drop_write_file(file); + mnt_put_write_access_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); @@ -1344,9 +1346,9 @@ void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); - /* avoid cacheline pingpong, hope gcc doesn't get "smart" */ + /* avoid cacheline pingpong */ if (unlikely(m->mnt_expiry_mark)) - m->mnt_expiry_mark = 0; + WRITE_ONCE(m->mnt_expiry_mark, 0); mntput_no_expire(m); } } diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index 716bc75e9ed2..b4294a8aa2d4 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -108,7 +108,7 @@ struct pnfs_block_dev { struct pnfs_block_dev *children; u64 chunk_size; - struct block_device *bdev; + struct bdev_handle *bdev_handle; u64 disk_offset; u64 pr_key; diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index 65cbb5607a5f..f318a05a80e1 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -25,17 +25,17 @@ bl_free_device(struct pnfs_block_dev *dev) } else { if (dev->pr_registered) { const struct pr_ops *ops = - dev->bdev->bd_disk->fops->pr_ops; + dev->bdev_handle->bdev->bd_disk->fops->pr_ops; int error; - error = ops->pr_register(dev->bdev, dev->pr_key, 0, - false); + error = ops->pr_register(dev->bdev_handle->bdev, + dev->pr_key, 0, false); if (error) pr_err("failed to unregister PR key.\n"); } - if (dev->bdev) - blkdev_put(dev->bdev, NULL); + if (dev->bdev_handle) + bdev_release(dev->bdev_handle); } } @@ -169,7 +169,7 @@ static bool bl_map_simple(struct pnfs_block_dev *dev, u64 offset, map->start = dev->start; map->len = dev->len; map->disk_offset = dev->disk_offset; - map->bdev = dev->bdev; + map->bdev = dev->bdev_handle->bdev; return true; } @@ -236,28 +236,26 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d, struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) { struct pnfs_block_volume *v = &volumes[idx]; - struct block_device *bdev; + struct bdev_handle *bdev_handle; dev_t dev; dev = bl_resolve_deviceid(server, v, gfp_mask); if (!dev) return -EIO; - bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, - NULL); - if (IS_ERR(bdev)) { + bdev_handle = bdev_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, + NULL, NULL); + if (IS_ERR(bdev_handle)) { printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n", - MAJOR(dev), MINOR(dev), PTR_ERR(bdev)); - return PTR_ERR(bdev); + MAJOR(dev), MINOR(dev), PTR_ERR(bdev_handle)); + return PTR_ERR(bdev_handle); } - d->bdev = bdev; - - - d->len = bdev_nr_bytes(d->bdev); + d->bdev_handle = bdev_handle; + d->len = bdev_nr_bytes(bdev_handle->bdev); d->map = bl_map_simple; printk(KERN_INFO "pNFS: using block device %s\n", - d->bdev->bd_disk->disk_name); + bdev_handle->bdev->bd_disk->disk_name); return 0; } @@ -302,10 +300,10 @@ bl_validate_designator(struct pnfs_block_volume *v) } } -static struct block_device * +static struct bdev_handle * bl_open_path(struct pnfs_block_volume *v, const char *prefix) { - struct block_device *bdev; + struct bdev_handle *bdev_handle; const char *devname; devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/%s%*phN", @@ -313,15 +311,15 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix) if (!devname) return ERR_PTR(-ENOMEM); - bdev = blkdev_get_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, - NULL); - if (IS_ERR(bdev)) { + bdev_handle = bdev_open_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE, + NULL, NULL); + if (IS_ERR(bdev_handle)) { pr_warn("pNFS: failed to open device %s (%ld)\n", - devname, PTR_ERR(bdev)); + devname, PTR_ERR(bdev_handle)); } kfree(devname); - return bdev; + return bdev_handle; } static int @@ -329,7 +327,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) { struct pnfs_block_volume *v = &volumes[idx]; - struct block_device *bdev; + struct bdev_handle *bdev_handle; const struct pr_ops *ops; int error; @@ -342,32 +340,32 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, * On other distributions like Debian, the default SCSI by-id path will * point to the dm-multipath device if one exists. */ - bdev = bl_open_path(v, "dm-uuid-mpath-0x"); - if (IS_ERR(bdev)) - bdev = bl_open_path(v, "wwn-0x"); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); - d->bdev = bdev; - - d->len = bdev_nr_bytes(d->bdev); + bdev_handle = bl_open_path(v, "dm-uuid-mpath-0x"); + if (IS_ERR(bdev_handle)) + bdev_handle = bl_open_path(v, "wwn-0x"); + if (IS_ERR(bdev_handle)) + return PTR_ERR(bdev_handle); + d->bdev_handle = bdev_handle; + + d->len = bdev_nr_bytes(d->bdev_handle->bdev); d->map = bl_map_simple; d->pr_key = v->scsi.pr_key; pr_info("pNFS: using block device %s (reservation key 0x%llx)\n", - d->bdev->bd_disk->disk_name, d->pr_key); + d->bdev_handle->bdev->bd_disk->disk_name, d->pr_key); - ops = d->bdev->bd_disk->fops->pr_ops; + ops = d->bdev_handle->bdev->bd_disk->fops->pr_ops; if (!ops) { pr_err("pNFS: block device %s does not support reservations.", - d->bdev->bd_disk->disk_name); + d->bdev_handle->bdev->bd_disk->disk_name); error = -EINVAL; goto out_blkdev_put; } - error = ops->pr_register(d->bdev, 0, d->pr_key, true); + error = ops->pr_register(d->bdev_handle->bdev, 0, d->pr_key, true); if (error) { pr_err("pNFS: failed to register key for block device %s.", - d->bdev->bd_disk->disk_name); + d->bdev_handle->bdev->bd_disk->disk_name); goto out_blkdev_put; } @@ -375,7 +373,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, return 0; out_blkdev_put: - blkdev_put(d->bdev, NULL); + bdev_release(d->bdev_handle); return error; } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index a1dc33864906..ef817a0475ff 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -2520,9 +2520,9 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo, return i; } -static int -ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) +static int ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) { + struct pnfs_layout_hdr *lo; struct nfs4_flexfile_layout *ff_layout; const int dev_count = PNFS_LAYOUTSTATS_MAXDEV; @@ -2533,11 +2533,14 @@ ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) return -ENOMEM; spin_lock(&args->inode->i_lock); - ff_layout = FF_LAYOUT_FROM_HDR(NFS_I(args->inode)->layout); - args->num_dev = ff_layout_mirror_prepare_stats(&ff_layout->generic_hdr, - &args->devinfo[0], - dev_count, - NFS4_FF_OP_LAYOUTSTATS); + lo = NFS_I(args->inode)->layout; + if (lo && pnfs_layout_is_valid(lo)) { + ff_layout = FF_LAYOUT_FROM_HDR(lo); + args->num_dev = ff_layout_mirror_prepare_stats( + &ff_layout->generic_hdr, &args->devinfo[0], dev_count, + NFS4_FF_OP_LAYOUTSTATS); + } else + args->num_dev = 0; spin_unlock(&args->inode->i_lock); if (!args->num_dev) { kfree(args->devinfo); diff --git a/fs/nfs/nfs.h b/fs/nfs/nfs.h index 5ba00610aede..0d3ce0460e35 100644 --- a/fs/nfs/nfs.h +++ b/fs/nfs/nfs.h @@ -18,7 +18,7 @@ struct nfs_subversion { const struct rpc_version *rpc_vers; /* NFS version information */ const struct nfs_rpc_ops *rpc_ops; /* NFS operations */ const struct super_operations *sops; /* NFS Super operations */ - const struct xattr_handler **xattr; /* NFS xattr handlers */ + const struct xattr_handler * const *xattr; /* NFS xattr handlers */ struct list_head list; /* List of NFS versions */ }; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 063e00aff87e..28704f924612 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -81,7 +81,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, if (status == 0) { if (nfs_should_remove_suid(inode)) { spin_lock(&inode->i_lock); - nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); + nfs_set_cache_invalid(inode, + NFS_INO_REVAL_FORCED | NFS_INO_INVALID_MODE); spin_unlock(&inode->i_lock); } status = nfs_post_op_update_inode_force_wcc(inode, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 47c5c1f86d66..827d00e2f094 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -315,7 +315,7 @@ extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct nfs_fh *, struct nfs_fattr *); extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); -extern const struct xattr_handler *nfs4_xattr_handlers[]; +extern const struct xattr_handler * const nfs4_xattr_handlers[]; extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, const struct nfs_open_context *ctx, const struct nfs_lock_context *l_ctx, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7016eaadf555..a654d7234f51 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8870,8 +8870,6 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre /* Save the EXCHANGE_ID verifier session trunk tests */ memcpy(clp->cl_confirm.data, argp->verifier.data, sizeof(clp->cl_confirm.data)); - if (resp->flags & EXCHGID4_FLAG_USE_PNFS_DS) - set_bit(NFS_CS_DS, &clp->cl_flags); out: trace_nfs4_exchange_id(clp, status); rpc_put_task(task); @@ -10739,7 +10737,7 @@ static const struct xattr_handler nfs4_xattr_nfs4_user_handler = { }; #endif -const struct xattr_handler *nfs4_xattr_handlers[] = { +const struct xattr_handler * const nfs4_xattr_handlers[] = { &nfs4_xattr_nfs4_acl_handler, #if defined(CONFIG_NFS_V4_1) &nfs4_xattr_nfs4_dacl_handler, diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 306cba0b9e69..84343aefbbd6 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2634,31 +2634,44 @@ pnfs_should_return_unused_layout(struct pnfs_layout_hdr *lo, return mode == 0; } -static int -pnfs_layout_return_unused_byserver(struct nfs_server *server, void *data) +static int pnfs_layout_return_unused_byserver(struct nfs_server *server, + void *data) { const struct pnfs_layout_range *range = data; + const struct cred *cred; struct pnfs_layout_hdr *lo; struct inode *inode; + nfs4_stateid stateid; + enum pnfs_iomode iomode; + restart: rcu_read_lock(); list_for_each_entry_rcu(lo, &server->layouts, plh_layouts) { - if (!pnfs_layout_can_be_returned(lo) || + inode = lo->plh_inode; + if (!inode || !pnfs_layout_can_be_returned(lo) || test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) continue; - inode = lo->plh_inode; spin_lock(&inode->i_lock); - if (!pnfs_should_return_unused_layout(lo, range)) { + if (!lo->plh_inode || + !pnfs_should_return_unused_layout(lo, range)) { spin_unlock(&inode->i_lock); continue; } + pnfs_get_layout_hdr(lo); + pnfs_set_plh_return_info(lo, range->iomode, 0); + if (pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + range, 0) != 0 || + !pnfs_prepare_layoutreturn(lo, &stateid, &cred, &iomode)) { + spin_unlock(&inode->i_lock); + rcu_read_unlock(); + pnfs_put_layout_hdr(lo); + cond_resched(); + goto restart; + } spin_unlock(&inode->i_lock); - inode = pnfs_grab_inode_layout_hdr(lo); - if (!inode) - continue; rcu_read_unlock(); - pnfs_mark_layout_for_return(inode, range); - iput(inode); + pnfs_send_layoutreturn(lo, &stateid, &cred, iomode, false); + pnfs_put_layout_hdr(lo); cond_resched(); goto restart; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 0d6473cb00cb..9b1cfca8112a 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1071,7 +1071,7 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx) sb->s_export_op = &nfs_export_ops; break; case 4: - sb->s_flags |= SB_POSIXACL; + sb->s_iflags |= SB_I_NOUMASK; sb->s_time_gran = 1; sb->s_time_min = S64_MIN; sb->s_time_max = S64_MAX; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 7720b5e43014..9d82d50ce0b1 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -788,6 +788,8 @@ static void nfs_inode_add_request(struct nfs_page *req) */ static void nfs_inode_remove_request(struct nfs_page *req) { + struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req)); + if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { struct folio *folio = nfs_page_to_folio(req->wb_head); struct address_space *mapping = folio_file_mapping(folio); @@ -802,7 +804,7 @@ static void nfs_inode_remove_request(struct nfs_page *req) } if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { - atomic_long_dec(&NFS_I(nfs_page_to_inode(req))->nrequests); + atomic_long_dec(&nfsi->nrequests); nfs_release_request(req); } } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 0144648c3e4d..bdb3f56026b3 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1788,6 +1788,12 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen)) goto out; + err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev; + if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) + goto out; + if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) + goto out; + retry: host_err = fh_want_write(ffhp); if (host_err) { @@ -1823,12 +1829,6 @@ retry: if (ndentry == trap) goto out_dput_new; - host_err = -EXDEV; - if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) - goto out_dput_new; - if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) - goto out_dput_new; - if ((ndentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) && nfsd_has_cached_files(ndentry)) { close_cached = true; diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index ebdcc25df0f7..869b016014d2 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -265,7 +265,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) struct dnotify_struct *dn; struct inode *inode; fl_owner_t id = current->files; - struct file *f; + struct file *f = NULL; int destroy = 0, error = 0; __u32 mask; @@ -345,7 +345,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) } rcu_read_lock(); - f = lookup_fd_rcu(fd); + f = lookup_fdget_rcu(fd); rcu_read_unlock(); /* if (f != filp) means that we lost a race and another task/thread @@ -392,6 +392,8 @@ out_err: fsnotify_put_mark(new_fsn_mark); if (dn) kmem_cache_free(dnotify_struct_cache, dn); + if (f) + fput(f); return error; } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index f69c451018e3..62fe0b679e58 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1585,16 +1585,25 @@ static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid) } /* Check if filesystem can encode a unique fid */ -static int fanotify_test_fid(struct dentry *dentry) +static int fanotify_test_fid(struct dentry *dentry, unsigned int flags) { + unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; + const struct export_operations *nop = dentry->d_sb->s_export_op; + + /* + * We need to make sure that the filesystem supports encoding of + * file handles so user can use name_to_handle_at() to compare fids + * reported with events to the file handle of watched objects. + */ + if (!nop) + return -EOPNOTSUPP; + /* - * We need to make sure that the file system supports at least - * encoding a file handle so user can use name_to_handle_at() to - * compare fid returned with event to the file handle of watched - * objects. However, even the relaxed AT_HANDLE_FID flag requires - * at least empty export_operations for ecoding unique file ids. + * For sb/mount mark, we also need to make sure that the filesystem + * supports decoding file handles, so user has a way to map back the + * reported fids to filesystem objects. */ - if (!dentry->d_sb->s_export_op) + if (mark_type != FAN_MARK_INODE && !nop->fh_to_dentry) return -EOPNOTSUPP; return 0; @@ -1812,7 +1821,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (ret) goto path_put_and_out; - ret = fanotify_test_fid(path.dentry); + ret = fanotify_test_fid(path.dentry, flags); if (ret) goto path_put_and_out; diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index a9d82bbb4729..63f70259edc0 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -1106,10 +1106,10 @@ repack: } } - /* + /* * The code below may require additional cluster (to extend attribute list) - * and / or one MFT record - * It is too complex to undo operations if -ENOSPC occurs deep inside + * and / or one MFT record + * It is too complex to undo operations if -ENOSPC occurs deep inside * in 'ni_insert_nonresident'. * Return in advance -ENOSPC here if there are no free cluster and no free MFT. */ @@ -1736,10 +1736,8 @@ repack: le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); - if (!attr_b) { - err = -ENOENT; - goto out; - } + if (!attr_b) + return -ENOENT; attr = attr_b; le = le_b; diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index 42631b31adf1..7c01735d1219 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -52,7 +52,8 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (!attr->non_res) { lsize = le32_to_cpu(attr->res.data_size); - le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); + /* attr is resident: lsize < record_size (1K or 4K) */ + le = kvmalloc(al_aligned(lsize), GFP_KERNEL); if (!le) { err = -ENOMEM; goto out; @@ -80,7 +81,17 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (err < 0) goto out; - le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); + /* attr is nonresident. + * The worst case: + * 1T (2^40) extremely fragmented file. + * cluster = 4K (2^12) => 2^28 fragments + * 2^9 fragments per one record => 2^19 records + * 2^5 bytes of ATTR_LIST_ENTRY per one record => 2^24 bytes. + * + * the result is 16M bytes per attribute list. + * Use kvmalloc to allocate in range [several Kbytes - dozen Mbytes] + */ + le = kvmalloc(al_aligned(lsize), GFP_KERNEL); if (!le) { err = -ENOMEM; goto out; diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index 107e808e06ea..63f14a0232f6 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -125,6 +125,7 @@ void wnd_close(struct wnd_bitmap *wnd) struct rb_node *node, *next; kfree(wnd->free_bits); + wnd->free_bits = NULL; run_close(&wnd->run); node = rb_first(&wnd->start_tree); @@ -659,7 +660,8 @@ int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits) wnd->bits_last = wbits; wnd->free_bits = - kcalloc(wnd->nwnd, sizeof(u16), GFP_NOFS | __GFP_NOWARN); + kvmalloc_array(wnd->nwnd, sizeof(u16), GFP_KERNEL | __GFP_ZERO); + if (!wnd->free_bits) return -ENOMEM; diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index 063a6654199b..ec0566b322d5 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -309,7 +309,11 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, return 0; } - dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + /* NTFS: symlinks are "dir + reparse" or "file + reparse" */ + if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) + dt_type = DT_LNK; + else + dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); } diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 322fb960ba5d..ad4a70b5d432 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -745,8 +745,8 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) } static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, - size_t len, unsigned int flags) + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { struct inode *inode = in->f_mapping->host; struct ntfs_inode *ni = ntfs_i(inode); diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 9f66dcf5da8f..3df2d9e34b91 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -2148,7 +2148,7 @@ out1: for (i = 0; i < pages_per_frame; i++) { pg = pages[i]; - if (i == idx) + if (i == idx || !pg) continue; unlock_page(pg); put_page(pg); @@ -3208,6 +3208,12 @@ static bool ni_update_parent(struct ntfs_inode *ni, struct NTFS_DUP_INFO *dup, if (!fname || !memcmp(&fname->dup, dup, sizeof(fname->dup))) continue; + /* Check simple case when parent inode equals current inode. */ + if (ino_get(&fname->home) == ni->vfs_inode.i_ino) { + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + continue; + } + /* ntfs_iget5 may sleep. */ dir = ntfs_iget5(sb, &fname->home, NULL); if (IS_ERR(dir)) { diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 12f28cdf5c83..98ccb6650858 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -2168,8 +2168,10 @@ file_is_valid: if (!page) { page = kmalloc(log->page_size, GFP_NOFS); - if (!page) - return -ENOMEM; + if (!page) { + err = -ENOMEM; + goto out; + } } /* diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 33afee0f5559..fbfe21dbb425 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -983,18 +983,11 @@ out: if (err) return err; - mark_inode_dirty(&ni->vfs_inode); + mark_inode_dirty_sync(&ni->vfs_inode); /* verify(!ntfs_update_mftmirr()); */ - /* - * If we used wait=1, sync_inode_metadata waits for the io for the - * inode to finish. It hangs when media is removed. - * So wait=0 is sent down to sync_inode_metadata - * and filemap_fdatawrite is used for the data blocks. - */ - err = sync_inode_metadata(&ni->vfs_inode, 0); - if (!err) - err = filemap_fdatawrite(ni->vfs_inode.i_mapping); + /* write mft record on disk. */ + err = _ni_write_inode(&ni->vfs_inode, 1); return err; } @@ -2461,10 +2454,12 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) { CLST end, i, zone_len, zlen; struct wnd_bitmap *wnd = &sbi->used.bitmap; + bool dirty = false; down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); if (!wnd_is_used(wnd, lcn, len)) { - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + /* mark volume as dirty out of wnd->rw_lock */ + dirty = true; end = lcn + len; len = 0; @@ -2518,6 +2513,8 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) out: up_write(&wnd->rw_lock); + if (dirty) + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); } /* diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 124c6e822623..cf92b2433f7a 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -729,6 +729,9 @@ static struct NTFS_DE *hdr_find_e(const struct ntfs_index *indx, u32 total = le32_to_cpu(hdr->total); u16 offs[128]; + if (unlikely(!cmp)) + return NULL; + fill_table: if (end > total) return NULL; diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index d1a646274228..ee3093be5170 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -373,7 +373,7 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry, #ifdef CONFIG_NTFS3_FS_POSIX_ACL if (IS_POSIXACL(dir)) { - /* + /* * Load in cache current acl to avoid ni_lock(dir): * ntfs_create_inode -> ntfs_init_acl -> posix_acl_create -> * ntfs_get_acl -> ntfs_get_acl_ex -> ni_lock diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 98b76d1b09e7..86aecbb01a92 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -847,7 +847,7 @@ struct OBJECT_ID { // Birth Volume Id is the Object Id of the Volume on. // which the Object Id was allocated. It never changes. struct GUID BirthVolumeId; //0x10: - + // Birth Object Id is the first Object Id that was // ever assigned to this MFT Record. I.e. If the Object Id // is changed for some reason, this field will reflect the diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 629403ede6e5..f6706143d14b 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -42,9 +42,11 @@ enum utf16_endian; #define MINUS_ONE_T ((size_t)(-1)) /* Biggest MFT / smallest cluster */ #define MAXIMUM_BYTES_PER_MFT 4096 +#define MAXIMUM_SHIFT_BYTES_PER_MFT 12 #define NTFS_BLOCKS_PER_MFT_RECORD (MAXIMUM_BYTES_PER_MFT / 512) #define MAXIMUM_BYTES_PER_INDEX 4096 +#define MAXIMUM_SHIFT_BYTES_PER_INDEX 12 #define NTFS_BLOCKS_PER_INODE (MAXIMUM_BYTES_PER_INDEX / 512) /* NTFS specific error code when fixup failed. */ @@ -495,8 +497,6 @@ int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, u32 flags); int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); -void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn, - CLST len); int ntfs_file_open(struct inode *inode, struct file *file); int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); @@ -872,7 +872,7 @@ int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode, int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry); ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size); -extern const struct xattr_handler *ntfs_xattr_handlers[]; +extern const struct xattr_handler * const ntfs_xattr_handlers[]; int ntfs_save_wsl_perm(struct inode *inode, __le16 *ea_size); void ntfs_get_wsl_perm(struct inode *inode); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index c12ebffc94da..53629b1f65e9 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -189,12 +189,19 @@ out: return err; } +/* + * mi_enum_attr - start/continue attributes enumeration in record. + * + * NOTE: mi->mrec - memory of size sbi->record_size + * here we sure that mi->mrec->total == sbi->record_size (see mi_read) + */ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) { const struct MFT_REC *rec = mi->mrec; u32 used = le32_to_cpu(rec->used); - u32 t32, off, asize; + u32 t32, off, asize, prev_type; u16 t16; + u64 data_size, alloc_size, tot_size; if (!attr) { u32 total = le32_to_cpu(rec->total); @@ -213,6 +220,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) if (!is_rec_inuse(rec)) return NULL; + prev_type = 0; attr = Add2Ptr(rec, off); } else { /* Check if input attr inside record. */ @@ -226,11 +234,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return NULL; } - if (off + asize < off) { - /* Overflow check. */ + /* Overflow check. */ + if (off + asize < off) return NULL; - } + prev_type = le32_to_cpu(attr->type); attr = Add2Ptr(attr, asize); off += asize; } @@ -250,7 +258,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) /* 0x100 is last known attribute for now. */ t32 = le32_to_cpu(attr->type); - if ((t32 & 0xf) || (t32 > 0x100)) + if (!t32 || (t32 & 0xf) || (t32 > 0x100)) + return NULL; + + /* attributes in record must be ordered by type */ + if (t32 < prev_type) return NULL; /* Check overflow and boundary. */ @@ -259,16 +271,15 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) /* Check size of attribute. */ if (!attr->non_res) { + /* Check resident fields. */ if (asize < SIZEOF_RESIDENT) return NULL; t16 = le16_to_cpu(attr->res.data_off); - if (t16 > asize) return NULL; - t32 = le32_to_cpu(attr->res.data_size); - if (t16 + t32 > asize) + if (t16 + le32_to_cpu(attr->res.data_size) > asize) return NULL; t32 = sizeof(short) * attr->name_len; @@ -278,21 +289,52 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return attr; } - /* Check some nonresident fields. */ - if (attr->name_len && - le16_to_cpu(attr->name_off) + sizeof(short) * attr->name_len > - le16_to_cpu(attr->nres.run_off)) { + /* Check nonresident fields. */ + if (attr->non_res != 1) + return NULL; + + t16 = le16_to_cpu(attr->nres.run_off); + if (t16 > asize) + return NULL; + + t32 = sizeof(short) * attr->name_len; + if (t32 && le16_to_cpu(attr->name_off) + t32 > t16) + return NULL; + + /* Check start/end vcn. */ + if (le64_to_cpu(attr->nres.svcn) > le64_to_cpu(attr->nres.evcn) + 1) return NULL; - } - if (attr->nres.svcn || !is_attr_ext(attr)) { + data_size = le64_to_cpu(attr->nres.data_size); + if (le64_to_cpu(attr->nres.valid_size) > data_size) + return NULL; + + alloc_size = le64_to_cpu(attr->nres.alloc_size); + if (data_size > alloc_size) + return NULL; + + t32 = mi->sbi->cluster_mask; + if (alloc_size & t32) + return NULL; + + if (!attr->nres.svcn && is_attr_ext(attr)) { + /* First segment of sparse/compressed attribute */ + if (asize + 8 < SIZEOF_NONRESIDENT_EX) + return NULL; + + tot_size = le64_to_cpu(attr->nres.total_size); + if (tot_size & t32) + return NULL; + + if (tot_size > alloc_size) + return NULL; + } else { if (asize + 8 < SIZEOF_NONRESIDENT) return NULL; if (attr->nres.c_unit) return NULL; - } else if (asize + 8 < SIZEOF_NONRESIDENT_EX) - return NULL; + } return attr; } diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 5661a363005e..f763e3256ccc 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -453,15 +453,23 @@ static struct proc_dir_entry *proc_info_root; * ntfs3.1 * cluster size * number of clusters + * total number of mft records + * number of used mft records ~= number of files + folders + * real state of ntfs "dirty"/"clean" + * current state of ntfs "dirty"/"clean" */ static int ntfs3_volinfo(struct seq_file *m, void *o) { struct super_block *sb = m->private; struct ntfs_sb_info *sbi = sb->s_fs_info; - seq_printf(m, "ntfs%d.%d\n%u\n%zu\n", sbi->volume.major_ver, - sbi->volume.minor_ver, sbi->cluster_size, - sbi->used.bitmap.nbits); + seq_printf(m, "ntfs%d.%d\n%u\n%zu\n\%zu\n%zu\n%s\n%s\n", + sbi->volume.major_ver, sbi->volume.minor_ver, + sbi->cluster_size, sbi->used.bitmap.nbits, + sbi->mft.bitmap.nbits, + sbi->mft.bitmap.nbits - wnd_zeroes(&sbi->mft.bitmap), + sbi->volume.real_dirty ? "dirty" : "clean", + (sbi->volume.flags & VOLUME_FLAG_DIRTY) ? "dirty" : "clean"); return 0; } @@ -488,9 +496,13 @@ static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer, { int err; struct super_block *sb = pde_data(file_inode(file)); - struct ntfs_sb_info *sbi = sb->s_fs_info; ssize_t ret = count; - u8 *label = kmalloc(count, GFP_NOFS); + u8 *label; + + if (sb_rdonly(sb)) + return -EROFS; + + label = kmalloc(count, GFP_NOFS); if (!label) return -ENOMEM; @@ -502,7 +514,7 @@ static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer, while (ret > 0 && label[ret - 1] == '\n') ret -= 1; - err = ntfs_set_label(sbi, label, ret); + err = ntfs_set_label(sb->s_fs_info, label, ret); if (err < 0) { ntfs_err(sb, "failed (%d) to write label", err); @@ -576,20 +588,30 @@ static noinline void ntfs3_put_sbi(struct ntfs_sb_info *sbi) wnd_close(&sbi->mft.bitmap); wnd_close(&sbi->used.bitmap); - if (sbi->mft.ni) + if (sbi->mft.ni) { iput(&sbi->mft.ni->vfs_inode); + sbi->mft.ni = NULL; + } - if (sbi->security.ni) + if (sbi->security.ni) { iput(&sbi->security.ni->vfs_inode); + sbi->security.ni = NULL; + } - if (sbi->reparse.ni) + if (sbi->reparse.ni) { iput(&sbi->reparse.ni->vfs_inode); + sbi->reparse.ni = NULL; + } - if (sbi->objid.ni) + if (sbi->objid.ni) { iput(&sbi->objid.ni->vfs_inode); + sbi->objid.ni = NULL; + } - if (sbi->volume.ni) + if (sbi->volume.ni) { iput(&sbi->volume.ni->vfs_inode); + sbi->volume.ni = NULL; + } ntfs_update_mftmirr(sbi, 0); @@ -836,7 +858,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, struct ntfs_sb_info *sbi = sb->s_fs_info; int err; u32 mb, gb, boot_sector_size, sct_per_clst, record_size; - u64 sectors, clusters, mlcn, mlcn2; + u64 sectors, clusters, mlcn, mlcn2, dev_size0; struct NTFS_BOOT *boot; struct buffer_head *bh; struct MFT_REC *rec; @@ -845,6 +867,9 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, u32 boot_off = 0; const char *hint = "Primary boot"; + /* Save original dev_size. Used with alternative boot. */ + dev_size0 = dev_size; + sbi->volume.blocks = dev_size >> PAGE_SHIFT; bh = ntfs_bread(sb, 0); @@ -853,6 +878,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, check_boot: err = -EINVAL; + + /* Corrupted image; do not read OOB */ + if (bh->b_size - sizeof(*boot) < boot_off) + goto out; + boot = (struct NTFS_BOOT *)Add2Ptr(bh->b_data, boot_off); if (memcmp(boot->system_id, "NTFS ", sizeof("NTFS ") - 1)) { @@ -899,9 +929,17 @@ check_boot: goto out; } - sbi->record_size = record_size = - boot->record_size < 0 ? 1 << (-boot->record_size) : - (u32)boot->record_size << cluster_bits; + if (boot->record_size >= 0) { + record_size = (u32)boot->record_size << cluster_bits; + } else if (-boot->record_size <= MAXIMUM_SHIFT_BYTES_PER_MFT) { + record_size = 1u << (-boot->record_size); + } else { + ntfs_err(sb, "%s: invalid record size %d.", hint, + boot->record_size); + goto out; + } + + sbi->record_size = record_size; sbi->record_bits = blksize_bits(record_size); sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes @@ -918,9 +956,15 @@ check_boot: goto out; } - sbi->index_size = boot->index_size < 0 ? - 1u << (-boot->index_size) : - (u32)boot->index_size << cluster_bits; + if (boot->index_size >= 0) { + sbi->index_size = (u32)boot->index_size << cluster_bits; + } else if (-boot->index_size <= MAXIMUM_SHIFT_BYTES_PER_INDEX) { + sbi->index_size = 1u << (-boot->index_size); + } else { + ntfs_err(sb, "%s: invalid index size %d.", hint, + boot->index_size); + goto out; + } /* Check index record size. */ if (sbi->index_size < SECTOR_SIZE || !is_power_of_2(sbi->index_size)) { @@ -1055,17 +1099,17 @@ check_boot: if (bh->b_blocknr && !sb_rdonly(sb)) { /* - * Alternative boot is ok but primary is not ok. - * Do not update primary boot here 'cause it may be faked boot. - * Let ntfs to be mounted and update boot later. - */ + * Alternative boot is ok but primary is not ok. + * Do not update primary boot here 'cause it may be faked boot. + * Let ntfs to be mounted and update boot later. + */ *boot2 = kmemdup(boot, sizeof(*boot), GFP_NOFS | __GFP_NOWARN); } out: - if (err == -EINVAL && !bh->b_blocknr && dev_size > PAGE_SHIFT) { + if (err == -EINVAL && !bh->b_blocknr && dev_size0 > PAGE_SHIFT) { u32 block_size = min_t(u32, sector_size, PAGE_SIZE); - u64 lbo = dev_size - sizeof(*boot); + u64 lbo = dev_size0 - sizeof(*boot); /* * Try alternative boot (last sector) @@ -1079,6 +1123,7 @@ out: boot_off = lbo & (block_size - 1); hint = "Alternative boot"; + dev_size = dev_size0; /* restore original size. */ goto check_boot; } brelse(bh); @@ -1367,7 +1412,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) } bytes = inode->i_size; - sbi->def_table = t = kmalloc(bytes, GFP_NOFS | __GFP_NOWARN); + sbi->def_table = t = kvmalloc(bytes, GFP_KERNEL); if (!t) { err = -ENOMEM; goto put_inode_out; @@ -1521,9 +1566,9 @@ load_root: if (boot2) { /* - * Alternative boot is ok but primary is not ok. - * Volume is recognized as NTFS. Update primary boot. - */ + * Alternative boot is ok but primary is not ok. + * Volume is recognized as NTFS. Update primary boot. + */ struct buffer_head *bh0 = sb_getblk(sb, 0); if (bh0) { if (buffer_locked(bh0)) @@ -1564,6 +1609,7 @@ put_inode_out: out: ntfs3_put_sbi(sbi); kfree(boot2); + ntfs3_put_sbi(sbi); return err; } @@ -1757,7 +1803,6 @@ static int __init init_ntfs_fs(void) if (IS_ENABLED(CONFIG_NTFS3_LZX_XPRESS)) pr_info("ntfs3: Read-only LZX/Xpress compression included\n"); - #ifdef CONFIG_PROC_FS /* Create "/proc/fs/ntfs3" */ proc_info_root = proc_mkdir("fs/ntfs3", NULL); @@ -1799,7 +1844,6 @@ static void __exit exit_ntfs_fs(void) if (proc_info_root) remove_proc_entry("fs/ntfs3", NULL); #endif - } MODULE_LICENSE("GPL"); diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 29fd391899e5..4274b6f31cfa 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -211,7 +211,8 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, size = le32_to_cpu(info->size); /* Enumerate all xattrs. */ - for (ret = 0, off = 0; off < size; off += ea_size) { + ret = 0; + for (off = 0; off + sizeof(struct EA_FULL) < size; off += ea_size) { ea = Add2Ptr(ea_all, off); ea_size = unpacked_ea_size(ea); @@ -219,6 +220,10 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, break; if (buffer) { + /* Check if we can use field ea->name */ + if (off + ea_size > size) + break; + if (ret + ea->name_len + 1 > bytes_per_buffer) { err = -ERANGE; goto out; @@ -1016,7 +1021,7 @@ static const struct xattr_handler ntfs_other_xattr_handler = { .list = ntfs_xattr_user_list, }; -const struct xattr_handler *ntfs_xattr_handlers[] = { +const struct xattr_handler * const ntfs_xattr_handlers[] = { &ntfs_other_xattr_handler, NULL, }; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 21472e3ed182..4d7efefa98c5 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -213,7 +213,7 @@ struct o2hb_region { unsigned int hr_num_pages; struct page **hr_slot_data; - struct block_device *hr_bdev; + struct bdev_handle *hr_bdev_handle; struct o2hb_disk_slot *hr_slots; /* live node map of this region */ @@ -261,6 +261,11 @@ struct o2hb_region { int hr_last_hb_status; }; +static inline struct block_device *reg_bdev(struct o2hb_region *reg) +{ + return reg->hr_bdev_handle ? reg->hr_bdev_handle->bdev : NULL; +} + struct o2hb_bio_wait_ctxt { atomic_t wc_num_reqs; struct completion wc_io_complete; @@ -286,7 +291,7 @@ static void o2hb_write_timeout(struct work_struct *work) hr_write_timeout_work.work); mlog(ML_ERROR, "Heartbeat write timeout to device %pg after %u " - "milliseconds\n", reg->hr_bdev, + "milliseconds\n", reg_bdev(reg), jiffies_to_msecs(jiffies - reg->hr_last_timeout_start)); if (o2hb_global_heartbeat_active()) { @@ -383,7 +388,7 @@ static void o2hb_nego_timeout(struct work_struct *work) if (!test_bit(master_node, reg->hr_nego_node_bitmap)) { printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg).\n", o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, - config_item_name(®->hr_item), reg->hr_bdev); + config_item_name(®->hr_item), reg_bdev(reg)); set_bit(master_node, reg->hr_nego_node_bitmap); } if (!bitmap_equal(reg->hr_nego_node_bitmap, live_node_bitmap, @@ -398,7 +403,8 @@ static void o2hb_nego_timeout(struct work_struct *work) } printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%pg) is down.\n", - config_item_name(®->hr_item), reg->hr_bdev); + config_item_name(®->hr_item), + reg_bdev(reg)); /* approve negotiate timeout request. */ o2hb_arm_timeout(reg); @@ -419,7 +425,7 @@ static void o2hb_nego_timeout(struct work_struct *work) /* negotiate timeout with master node. */ printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg), negotiate timeout with node %d.\n", o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, config_item_name(®->hr_item), - reg->hr_bdev, master_node); + reg_bdev(reg), master_node); ret = o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG, master_node); if (ret) @@ -436,7 +442,8 @@ static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data, nego_msg = (struct o2hb_nego_msg *)msg->buf; printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%pg).\n", - nego_msg->node_num, config_item_name(®->hr_item), reg->hr_bdev); + nego_msg->node_num, config_item_name(®->hr_item), + reg_bdev(reg)); if (nego_msg->node_num < O2NM_MAX_NODES) set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap); else @@ -451,7 +458,7 @@ static int o2hb_nego_approve_handler(struct o2net_msg *msg, u32 len, void *data, struct o2hb_region *reg = data; printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%pg).\n", - config_item_name(®->hr_item), reg->hr_bdev); + config_item_name(®->hr_item), reg_bdev(reg)); o2hb_arm_timeout(reg); return 0; } @@ -515,7 +522,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg, * GFP_KERNEL that the local node can get fenced. It would be * nicest if we could pre-allocate these bios and avoid this * all together. */ - bio = bio_alloc(reg->hr_bdev, 16, opf, GFP_ATOMIC); + bio = bio_alloc(reg_bdev(reg), 16, opf, GFP_ATOMIC); if (!bio) { mlog(ML_ERROR, "Could not alloc slots BIO!\n"); bio = ERR_PTR(-ENOMEM); @@ -687,7 +694,7 @@ static int o2hb_check_own_slot(struct o2hb_region *reg) errstr = ERRSTR3; mlog(ML_ERROR, "%s (%pg): expected(%u:0x%llx, 0x%llx), " - "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg->hr_bdev, + "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg_bdev(reg), slot->ds_node_num, (unsigned long long)slot->ds_last_generation, (unsigned long long)slot->ds_last_time, hb_block->hb_node, (unsigned long long)le64_to_cpu(hb_block->hb_generation), @@ -861,7 +868,7 @@ static void o2hb_set_quorum_device(struct o2hb_region *reg) goto unlock; printk(KERN_NOTICE "o2hb: Region %s (%pg) is now a quorum device\n", - config_item_name(®->hr_item), reg->hr_bdev); + config_item_name(®->hr_item), reg_bdev(reg)); set_bit(reg->hr_region_num, o2hb_quorum_region_bitmap); @@ -920,7 +927,7 @@ static int o2hb_check_slot(struct o2hb_region *reg, * consider it a transient miss but don't populate any * other values as they may be junk. */ mlog(ML_ERROR, "Node %d has written a bad crc to %pg\n", - slot->ds_node_num, reg->hr_bdev); + slot->ds_node_num, reg_bdev(reg)); o2hb_dump_slot(hb_block); slot->ds_equal_samples++; @@ -1003,8 +1010,8 @@ fire_callbacks: "of %u ms, but our count is %u ms.\n" "Please double check your configuration values " "for 'O2CB_HEARTBEAT_THRESHOLD'\n", - slot->ds_node_num, reg->hr_bdev, slot_dead_ms, - dead_ms); + slot->ds_node_num, reg_bdev(reg), + slot_dead_ms, dead_ms); } goto out; } @@ -1143,7 +1150,7 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg) * can't be sure that the new block ever made it to * disk */ mlog(ML_ERROR, "Write error %d on device \"%pg\"\n", - write_wc.wc_error, reg->hr_bdev); + write_wc.wc_error, reg_bdev(reg)); ret = write_wc.wc_error; goto bail; } @@ -1169,7 +1176,7 @@ bail: printk(KERN_NOTICE "o2hb: Unable to stabilize " "heartbeat on region %s (%pg)\n", config_item_name(®->hr_item), - reg->hr_bdev); + reg_bdev(reg)); atomic_set(®->hr_steady_iterations, 0); reg->hr_aborted_start = 1; wake_up(&o2hb_steady_queue); @@ -1489,7 +1496,7 @@ static void o2hb_region_release(struct config_item *item) struct page *page; struct o2hb_region *reg = to_o2hb_region(item); - mlog(ML_HEARTBEAT, "hb region release (%pg)\n", reg->hr_bdev); + mlog(ML_HEARTBEAT, "hb region release (%pg)\n", reg_bdev(reg)); kfree(reg->hr_tmp_block); @@ -1502,8 +1509,8 @@ static void o2hb_region_release(struct config_item *item) kfree(reg->hr_slot_data); } - if (reg->hr_bdev) - blkdev_put(reg->hr_bdev, NULL); + if (reg->hr_bdev_handle) + bdev_release(reg->hr_bdev_handle); kfree(reg->hr_slots); @@ -1562,7 +1569,7 @@ static ssize_t o2hb_region_block_bytes_store(struct config_item *item, unsigned long block_bytes; unsigned int block_bits; - if (reg->hr_bdev) + if (reg->hr_bdev_handle) return -EINVAL; status = o2hb_read_block_input(reg, page, &block_bytes, @@ -1591,7 +1598,7 @@ static ssize_t o2hb_region_start_block_store(struct config_item *item, char *p = (char *)page; ssize_t ret; - if (reg->hr_bdev) + if (reg->hr_bdev_handle) return -EINVAL; ret = kstrtoull(p, 0, &tmp); @@ -1616,7 +1623,7 @@ static ssize_t o2hb_region_blocks_store(struct config_item *item, unsigned long tmp; char *p = (char *)page; - if (reg->hr_bdev) + if (reg->hr_bdev_handle) return -EINVAL; tmp = simple_strtoul(p, &p, 0); @@ -1635,8 +1642,8 @@ static ssize_t o2hb_region_dev_show(struct config_item *item, char *page) { unsigned int ret = 0; - if (to_o2hb_region(item)->hr_bdev) - ret = sprintf(page, "%pg\n", to_o2hb_region(item)->hr_bdev); + if (to_o2hb_region(item)->hr_bdev_handle) + ret = sprintf(page, "%pg\n", reg_bdev(to_o2hb_region(item))); return ret; } @@ -1745,7 +1752,10 @@ out: return ret; } -/* this is acting as commit; we set up all of hr_bdev and hr_task or nothing */ +/* + * this is acting as commit; we set up all of hr_bdev_handle and hr_task or + * nothing + */ static ssize_t o2hb_region_dev_store(struct config_item *item, const char *page, size_t count) @@ -1759,7 +1769,7 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, ssize_t ret = -EINVAL; int live_threshold; - if (reg->hr_bdev) + if (reg->hr_bdev_handle) goto out; /* We can't heartbeat without having had our node number @@ -1785,16 +1795,15 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, if (!S_ISBLK(f.file->f_mapping->host->i_mode)) goto out2; - reg->hr_bdev = blkdev_get_by_dev(f.file->f_mapping->host->i_rdev, - BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, - NULL); - if (IS_ERR(reg->hr_bdev)) { - ret = PTR_ERR(reg->hr_bdev); - reg->hr_bdev = NULL; + reg->hr_bdev_handle = bdev_open_by_dev(f.file->f_mapping->host->i_rdev, + BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, NULL); + if (IS_ERR(reg->hr_bdev_handle)) { + ret = PTR_ERR(reg->hr_bdev_handle); + reg->hr_bdev_handle = NULL; goto out2; } - sectsize = bdev_logical_block_size(reg->hr_bdev); + sectsize = bdev_logical_block_size(reg_bdev(reg)); if (sectsize != reg->hr_block_bytes) { mlog(ML_ERROR, "blocksize %u incorrect for device, expected %d", @@ -1890,12 +1899,12 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, if (hb_task && o2hb_global_heartbeat_active()) printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%pg)\n", - config_item_name(®->hr_item), reg->hr_bdev); + config_item_name(®->hr_item), reg_bdev(reg)); out3: if (ret < 0) { - blkdev_put(reg->hr_bdev, NULL); - reg->hr_bdev = NULL; + bdev_release(reg->hr_bdev_handle); + reg->hr_bdev_handle = NULL; } out2: fdput(f); @@ -2085,7 +2094,7 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group, printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%pg)\n", ((atomic_read(®->hr_steady_iterations) == 0) ? "stopped" : "start aborted"), config_item_name(item), - reg->hr_bdev); + reg_bdev(reg)); } /* diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index b562cfef888a..3b81213ed7b8 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -87,14 +87,14 @@ static struct ocfs2_xattr_def_value_root def_xv = { .xv.xr_list.l_count = cpu_to_le16(1), }; -const struct xattr_handler *ocfs2_xattr_handlers[] = { +const struct xattr_handler * const ocfs2_xattr_handlers[] = { &ocfs2_xattr_user_handler, &ocfs2_xattr_trusted_handler, &ocfs2_xattr_security_handler, NULL }; -static const struct xattr_handler *ocfs2_xattr_handler_map[OCFS2_XATTR_MAX] = { +static const struct xattr_handler * const ocfs2_xattr_handler_map[OCFS2_XATTR_MAX] = { [OCFS2_XATTR_INDEX_USER] = &ocfs2_xattr_user_handler, [OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, [OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h index 00308b57f64f..65e9aa743919 100644 --- a/fs/ocfs2/xattr.h +++ b/fs/ocfs2/xattr.h @@ -30,7 +30,7 @@ struct ocfs2_security_xattr_info { extern const struct xattr_handler ocfs2_xattr_user_handler; extern const struct xattr_handler ocfs2_xattr_trusted_handler; extern const struct xattr_handler ocfs2_xattr_security_handler; -extern const struct xattr_handler *ocfs2_xattr_handlers[]; +extern const struct xattr_handler * const ocfs2_xattr_handlers[]; ssize_t ocfs2_listxattr(struct dentry *, char *, size_t); int ocfs2_xattr_get_nolock(struct inode *, struct buffer_head *, int, diff --git a/fs/open.c b/fs/open.c index 98f6601fbac6..02dc608d40d8 100644 --- a/fs/open.c +++ b/fs/open.c @@ -870,6 +870,30 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) return ksys_fchown(fd, user, group); } +static inline int file_get_write_access(struct file *f) +{ + int error; + + error = get_write_access(f->f_inode); + if (unlikely(error)) + return error; + error = mnt_get_write_access(f->f_path.mnt); + if (unlikely(error)) + goto cleanup_inode; + if (unlikely(f->f_mode & FMODE_BACKING)) { + error = mnt_get_write_access(backing_file_user_path(f)->mnt); + if (unlikely(error)) + goto cleanup_mnt; + } + return 0; + +cleanup_mnt: + mnt_put_write_access(f->f_path.mnt); +cleanup_inode: + put_write_access(f->f_inode); + return error; +} + static int do_dentry_open(struct file *f, struct inode *inode, int (*open)(struct inode *, struct file *)) @@ -892,14 +916,9 @@ static int do_dentry_open(struct file *f, if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_inc(inode); } else if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { - error = get_write_access(inode); + error = file_get_write_access(f); if (unlikely(error)) goto cleanup_file; - error = __mnt_want_write(f->f_path.mnt); - if (unlikely(error)) { - put_write_access(inode); - goto cleanup_file; - } f->f_mode |= FMODE_WRITER; } @@ -1163,20 +1182,19 @@ EXPORT_SYMBOL_GPL(kernel_file_open); /** * backing_file_open - open a backing file for kernel internal use - * @path: path of the file to open + * @user_path: path that the user reuqested to open * @flags: open flags * @real_path: path of the backing file * @cred: credentials for open * * Open a backing file for a stackable filesystem (e.g., overlayfs). - * @path may be on the stackable filesystem and backing inode on the - * underlying filesystem. In this case, we want to be able to return - * the @real_path of the backing inode. This is done by embedding the - * returned file into a container structure that also stores the path of - * the backing inode on the underlying filesystem, which can be - * retrieved using backing_file_real_path(). + * @user_path may be on the stackable filesystem and @real_path on the + * underlying filesystem. In this case, we want to be able to return the + * @user_path of the stackable filesystem. This is done by embedding the + * returned file into a container structure that also stores the stacked + * file's path, which can be retrieved using backing_file_user_path(). */ -struct file *backing_file_open(const struct path *path, int flags, +struct file *backing_file_open(const struct path *user_path, int flags, const struct path *real_path, const struct cred *cred) { @@ -1187,9 +1205,9 @@ struct file *backing_file_open(const struct path *path, int flags, if (IS_ERR(f)) return f; - f->f_path = *path; - path_get(real_path); - *backing_file_real_path(f) = *real_path; + path_get(user_path); + *backing_file_user_path(f) = *user_path; + f->f_path = *real_path; error = do_dentry_open(f, d_inode(real_path->dentry), NULL); if (error) { fput(f); diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index b711654ca18a..926d9c0a428a 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -103,7 +103,7 @@ enum orangefs_vfs_op_states { #define ORANGEFS_CACHE_CREATE_FLAGS 0 #endif -extern const struct xattr_handler *orangefs_xattr_handlers[]; +extern const struct xattr_handler * const orangefs_xattr_handlers[]; extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type, bool rcu); extern int orangefs_set_acl(struct mnt_idmap *idmap, diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c index 68b62689a63e..74ef75586f38 100644 --- a/fs/orangefs/xattr.c +++ b/fs/orangefs/xattr.c @@ -554,7 +554,7 @@ static const struct xattr_handler orangefs_xattr_default_handler = { .set = orangefs_xattr_set_default, }; -const struct xattr_handler *orangefs_xattr_handlers[] = { +const struct xattr_handler * const orangefs_xattr_handlers[] = { &orangefs_xattr_default_handler, NULL }; diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index 95b751507ac8..f6ff23fd101c 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -157,6 +157,34 @@ const struct fs_parameter_spec ovl_parameter_spec[] = { {} }; +static char *ovl_next_opt(char **s) +{ + char *sbegin = *s; + char *p; + + if (sbegin == NULL) + return NULL; + + for (p = sbegin; *p; p++) { + if (*p == '\\') { + p++; + if (!*p) + break; + } else if (*p == ',') { + *p = '\0'; + *s = p + 1; + return sbegin; + } + } + *s = NULL; + return sbegin; +} + +static int ovl_parse_monolithic(struct fs_context *fc, void *data) +{ + return vfs_parse_monolithic_sep(fc, data, ovl_next_opt); +} + static ssize_t ovl_parse_param_split_lowerdirs(char *str) { ssize_t nr_layers = 1, nr_colons = 0; @@ -164,7 +192,8 @@ static ssize_t ovl_parse_param_split_lowerdirs(char *str) for (s = d = str;; s++, d++) { if (*s == '\\') { - s++; + /* keep esc chars in split lowerdir */ + *d++ = *s++; } else if (*s == ':') { bool next_colon = (*(s + 1) == ':'); @@ -239,7 +268,7 @@ static void ovl_unescape(char *s) } } -static int ovl_mount_dir(const char *name, struct path *path) +static int ovl_mount_dir(const char *name, struct path *path, bool upper) { int err = -ENOMEM; char *tmp = kstrdup(name, GFP_KERNEL); @@ -248,7 +277,7 @@ static int ovl_mount_dir(const char *name, struct path *path) ovl_unescape(tmp); err = ovl_mount_dir_noesc(tmp, path); - if (!err && path->dentry->d_flags & DCACHE_OP_REAL) { + if (!err && upper && path->dentry->d_flags & DCACHE_OP_REAL) { pr_err("filesystem on '%s' not supported as upperdir\n", tmp); path_put_init(path); @@ -269,7 +298,7 @@ static int ovl_parse_param_upperdir(const char *name, struct fs_context *fc, struct path path; char *dup; - err = ovl_mount_dir(name, &path); + err = ovl_mount_dir(name, &path, true); if (err) return err; @@ -321,12 +350,6 @@ static void ovl_parse_param_drop_lowerdir(struct ovl_fs_context *ctx) * Set "/lower1", "/lower2", and "/lower3" as lower layers and * "/data1" and "/data2" as data lower layers. Any existing lower * layers are replaced. - * (2) lowerdir=:/lower4 - * Append "/lower4" to current stack of lower layers. This requires - * that there already is at least one lower layer configured. - * (3) lowerdir=::/lower5 - * Append data "/lower5" as data lower layer. This requires that - * there's at least one regular lower layer present. */ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) { @@ -348,49 +371,9 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) return 0; } - if (strncmp(name, "::", 2) == 0) { - /* - * This is a data layer. - * There must be at least one regular lower layer - * specified. - */ - if (ctx->nr == 0) { - pr_err("data lower layers without regular lower layers not allowed"); - return -EINVAL; - } - - /* Skip the leading "::". */ - name += 2; - data_layer = true; - /* - * A data layer is automatically an append as there - * must've been at least one regular lower layer. - */ - append = true; - } else if (*name == ':') { - /* - * This is a regular lower layer. - * If users want to append a layer enforce that they - * have already specified a first layer before. It's - * better to be strict. - */ - if (ctx->nr == 0) { - pr_err("cannot append layer if no previous layer has been specified"); - return -EINVAL; - } - - /* - * Once a sequence of data layers has started regular - * lower layers are forbidden. - */ - if (ctx->nr_data > 0) { - pr_err("regular lower layers cannot follow data lower layers"); - return -EINVAL; - } - - /* Skip the leading ":". */ - name++; - append = true; + if (*name == ':') { + pr_err("cannot append lower layer"); + return -EINVAL; } dup = kstrdup(name, GFP_KERNEL); @@ -472,7 +455,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) l = &ctx->lower[nr]; memset(l, 0, sizeof(*l)); - err = ovl_mount_dir_noesc(dup_iter, &l->path); + err = ovl_mount_dir(dup_iter, &l->path, false); if (err) goto out_put; @@ -682,6 +665,7 @@ static int ovl_reconfigure(struct fs_context *fc) } static const struct fs_context_operations ovl_context_ops = { + .parse_monolithic = ovl_parse_monolithic, .parse_param = ovl_parse_param, .get_tree = ovl_get_tree, .reconfigure = ovl_reconfigure, @@ -950,16 +934,23 @@ int ovl_show_options(struct seq_file *m, struct dentry *dentry) struct super_block *sb = dentry->d_sb; struct ovl_fs *ofs = OVL_FS(sb); size_t nr, nr_merged_lower = ofs->numlayer - ofs->numdatalayer; - char **lowerdatadirs = &ofs->config.lowerdirs[nr_merged_lower]; - - /* lowerdirs[] starts from offset 1 */ - seq_printf(m, ",lowerdir=%s", ofs->config.lowerdirs[1]); - /* dump regular lower layers */ - for (nr = 2; nr < nr_merged_lower; nr++) - seq_printf(m, ":%s", ofs->config.lowerdirs[nr]); - /* dump data lower layers */ - for (nr = 0; nr < ofs->numdatalayer; nr++) - seq_printf(m, "::%s", lowerdatadirs[nr]); + + /* + * lowerdirs[] starts from offset 1, then + * >= 0 regular lower layers prefixed with : and + * >= 0 data-only lower layers prefixed with :: + * + * we need to escase comma and space like seq_show_option() does and + * we also need to escape the colon separator from lowerdir paths. + */ + seq_puts(m, ",lowerdir="); + for (nr = 1; nr < ofs->numlayer; nr++) { + if (nr > 1) + seq_putc(m, ':'); + if (nr >= nr_merged_lower) + seq_putc(m, ':'); + seq_escape(m, ofs->config.lowerdirs[nr], ":, \t\n\\"); + } if (ofs->config.upperdir) { seq_show_option(m, "upperdir", ofs->config.upperdir); seq_show_option(m, "workdir", ofs->config.workdir); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 3fa2416264a4..6cd949c59fed 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -34,14 +34,22 @@ static struct dentry *ovl_d_real(struct dentry *dentry, struct dentry *real = NULL, *lower; int err; - /* It's an overlay file */ + /* + * vfs is only expected to call d_real() with NULL from d_real_inode() + * and with overlay inode from file_dentry() on an overlay file. + * + * TODO: remove @inode argument from d_real() API, remove code in this + * function that deals with non-NULL @inode and remove d_real() call + * from file_dentry(). + */ if (inode && d_inode(dentry) == inode) return dentry; + else if (inode) + goto bug; if (!d_is_reg(dentry)) { - if (!inode || inode == d_inode(dentry)) - return dentry; - goto bug; + /* d_real_inode() is only relevant for regular files */ + return dentry; } real = ovl_dentry_upper(dentry); @@ -487,13 +495,13 @@ static const struct xattr_handler ovl_other_xattr_handler = { .set = ovl_other_xattr_set, }; -static const struct xattr_handler *ovl_trusted_xattr_handlers[] = { +static const struct xattr_handler * const ovl_trusted_xattr_handlers[] = { &ovl_own_trusted_xattr_handler, &ovl_other_xattr_handler, NULL }; -static const struct xattr_handler *ovl_user_xattr_handlers[] = { +static const struct xattr_handler * const ovl_user_xattr_handlers[] = { &ovl_own_user_xattr_handler, &ovl_other_xattr_handler, NULL @@ -1488,8 +1496,16 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_xattr = ofs->config.userxattr ? ovl_user_xattr_handlers : ovl_trusted_xattr_handlers; sb->s_fs_info = ofs; +#ifdef CONFIG_FS_POSIX_ACL sb->s_flags |= SB_POSIXACL; +#endif sb->s_iflags |= SB_I_SKIP_SYNC | SB_I_IMA_UNVERIFIABLE_SIGNATURE; + /* + * Ensure that umask handling is done by the filesystems used + * for the the upper layer instead of overlayfs as that would + * lead to unexpected results. + */ + sb->s_iflags |= SB_I_NOUMASK; err = -ENOMEM; root_dentry = ovl_get_root(sb, ctx->upper.dentry, oe); diff --git a/fs/pipe.c b/fs/pipe.c index b96a5918d064..8916c455a469 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -227,6 +227,36 @@ static inline bool pipe_readable(const struct pipe_inode_info *pipe) return !pipe_empty(head, tail) || !writers; } +static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, + struct pipe_buffer *buf, + unsigned int tail) +{ + pipe_buf_release(pipe, buf); + + /* + * If the pipe has a watch_queue, we need additional protection + * by the spinlock because notifications get posted with only + * this spinlock, no mutex + */ + if (pipe_has_watch_queue(pipe)) { + spin_lock_irq(&pipe->rd_wait.lock); +#ifdef CONFIG_WATCH_QUEUE + if (buf->flags & PIPE_BUF_FLAG_LOSS) + pipe->note_loss = true; +#endif + pipe->tail = ++tail; + spin_unlock_irq(&pipe->rd_wait.lock); + return tail; + } + + /* + * Without a watch_queue, we can simply increment the tail + * without the spinlock - the mutex is enough. + */ + pipe->tail = ++tail; + return tail; +} + static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { @@ -320,17 +350,8 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) buf->len = 0; } - if (!buf->len) { - pipe_buf_release(pipe, buf); - spin_lock_irq(&pipe->rd_wait.lock); -#ifdef CONFIG_WATCH_QUEUE - if (buf->flags & PIPE_BUF_FLAG_LOSS) - pipe->note_loss = true; -#endif - tail++; - pipe->tail = tail; - spin_unlock_irq(&pipe->rd_wait.lock); - } + if (!buf->len) + tail = pipe_update_tail(pipe, buf, tail); total_len -= chars; if (!total_len) break; /* common path: read succeeded */ @@ -437,12 +458,10 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) { + if (pipe_has_watch_queue(pipe)) { ret = -EXDEV; goto out; } -#endif /* * If it wasn't empty we try to merge new data into @@ -507,16 +526,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) * it, either the reader will consume it or it'll still * be there for the next write. */ - spin_lock_irq(&pipe->rd_wait.lock); - - head = pipe->head; - if (pipe_full(head, pipe->tail, pipe->max_usage)) { - spin_unlock_irq(&pipe->rd_wait.lock); - continue; - } - pipe->head = head + 1; - spin_unlock_irq(&pipe->rd_wait.lock); /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; @@ -1324,10 +1334,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg) unsigned int nr_slots, size; long ret = 0; -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) + if (pipe_has_watch_queue(pipe)) return -EBUSY; -#endif size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; @@ -1379,10 +1387,8 @@ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) if (file->f_op != &pipefifo_fops || !pipe) return NULL; -#ifdef CONFIG_WATCH_QUEUE - if (for_splice && pipe->watch_queue) + if (for_splice && pipe_has_watch_queue(pipe)) return NULL; -#endif return pipe; } diff --git a/fs/proc/base.c b/fs/proc/base.c index c69925364090..83396ab14998 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2218,7 +2218,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path) rc = -ENOENT; vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { - *path = vma->vm_file->f_path; + *path = *file_user_path(vma->vm_file); path_get(path); rc = 0; } diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 6276b3938842..6e72e5ad42bc 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -113,10 +113,12 @@ static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode) struct file *file; rcu_read_lock(); - file = task_lookup_fd_rcu(task, fd); - if (file) - *mode = file->f_mode; + file = task_lookup_fdget_rcu(task, fd); rcu_read_unlock(); + if (file) { + *mode = file->f_mode; + fput(file); + } return !!file; } @@ -259,12 +261,13 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, char name[10 + 1]; unsigned int len; - f = task_lookup_next_fd_rcu(p, &fd); + f = task_lookup_next_fdget_rcu(p, &fd); ctx->pos = fd + 2LL; if (!f) break; data.mode = f->f_mode; rcu_read_unlock(); + fput(f); data.fd = fd; len = snprintf(name, sizeof(name), "%u", fd); diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 4d3493579458..c6e7ebc63756 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -58,7 +58,7 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region) if (file) { seq_pad(m, ' '); - seq_file_path(m, file, ""); + seq_path(m, file_user_path(file), ""); } seq_putc(m, '\n'); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3dd5be96691b..1593940ca01e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -296,7 +296,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) if (anon_name) seq_printf(m, "[anon_shmem:%s]", anon_name->name); else - seq_file_path(m, file, "\n"); + seq_path(m, file_user_path(file), "\n"); goto done; } @@ -1967,7 +1967,7 @@ static int show_numa_map(struct seq_file *m, void *v) if (file) { seq_puts(m, " file="); - seq_file_path(m, file, "\n\t= "); + seq_path(m, file_user_path(file), "\n\t= "); } else if (vma_is_initial_heap(vma)) { seq_puts(m, " heap"); } else if (vma_is_initial_stack(vma)) { diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 7cebd397cc26..bce674533000 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -157,7 +157,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) if (file) { seq_pad(m, ' '); - seq_file_path(m, file, ""); + seq_path(m, file_user_path(file), ""); } else if (mm && vma_is_initial_stack(vma)) { seq_pad(m, ' '); seq_puts(m, "[stack]"); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 9e72bfe8bbad..31e897ad5e6a 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -233,19 +233,18 @@ static void put_quota_format(struct quota_format_type *fmt) * All dquots are placed to the end of inuse_list when first created, and this * list is used for invalidate operation, which must look at every dquot. * - * When the last reference of a dquot will be dropped, the dquot will be - * added to releasing_dquots. We'd then queue work item which would call + * When the last reference of a dquot is dropped, the dquot is added to + * releasing_dquots. We'll then queue work item which will call * synchronize_srcu() and after that perform the final cleanup of all the - * dquots on the list. Both releasing_dquots and free_dquots use the - * dq_free list_head in the dquot struct. When a dquot is removed from - * releasing_dquots, a reference count is always subtracted, and if - * dq_count == 0 at that point, the dquot will be added to the free_dquots. + * dquots on the list. Each cleaned up dquot is moved to free_dquots list. + * Both releasing_dquots and free_dquots use the dq_free list_head in the dquot + * struct. * - * Unused dquots (dq_count == 0) are added to the free_dquots list when freed, - * and this list is searched whenever we need an available dquot. Dquots are - * removed from the list as soon as they are used again, and - * dqstats.free_dquots gives the number of dquots on the list. When - * dquot is invalidated it's completely released from memory. + * Unused and cleaned up dquots are in the free_dquots list and this list is + * searched whenever we need an available dquot. Dquots are removed from the + * list as soon as they are used again and dqstats.free_dquots gives the number + * of dquots on the list. When dquot is invalidated it's completely released + * from memory. * * Dirty dquots are added to the dqi_dirty_list of quota_info when mark * dirtied, and this list is searched when writing dirty dquots back to @@ -321,6 +320,7 @@ static inline void put_dquot_last(struct dquot *dquot) static inline void put_releasing_dquots(struct dquot *dquot) { list_add_tail(&dquot->dq_free, &releasing_dquots); + set_bit(DQ_RELEASING_B, &dquot->dq_flags); } static inline void remove_free_dquot(struct dquot *dquot) @@ -328,8 +328,10 @@ static inline void remove_free_dquot(struct dquot *dquot) if (list_empty(&dquot->dq_free)) return; list_del_init(&dquot->dq_free); - if (!atomic_read(&dquot->dq_count)) + if (!test_bit(DQ_RELEASING_B, &dquot->dq_flags)) dqstats_dec(DQST_FREE_DQUOTS); + else + clear_bit(DQ_RELEASING_B, &dquot->dq_flags); } static inline void put_inuse(struct dquot *dquot) @@ -581,12 +583,6 @@ restart: continue; /* Wait for dquot users */ if (atomic_read(&dquot->dq_count)) { - /* dquot in releasing_dquots, flush and retry */ - if (!list_empty(&dquot->dq_free)) { - spin_unlock(&dq_list_lock); - goto restart; - } - atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); /* @@ -606,6 +602,15 @@ restart: goto restart; } /* + * The last user already dropped its reference but dquot didn't + * get fully cleaned up yet. Restart the scan which flushes the + * work cleaning up released dquots. + */ + if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { + spin_unlock(&dq_list_lock); + goto restart; + } + /* * Quota now has no users and it has been written on last * dqput() */ @@ -696,6 +701,13 @@ int dquot_writeback_dquots(struct super_block *sb, int type) dq_dirty); WARN_ON(!dquot_active(dquot)); + /* If the dquot is releasing we should not touch it */ + if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { + spin_unlock(&dq_list_lock); + flush_delayed_work("a_release_work); + spin_lock(&dq_list_lock); + continue; + } /* Now we have active dquot from which someone is * holding reference so we can safely just increase @@ -809,18 +821,18 @@ static void quota_release_workfn(struct work_struct *work) /* Exchange the list head to avoid livelock. */ list_replace_init(&releasing_dquots, &rls_head); spin_unlock(&dq_list_lock); + synchronize_srcu(&dquot_srcu); restart: - synchronize_srcu(&dquot_srcu); spin_lock(&dq_list_lock); while (!list_empty(&rls_head)) { dquot = list_first_entry(&rls_head, struct dquot, dq_free); - /* Dquot got used again? */ - if (atomic_read(&dquot->dq_count) > 1) { - remove_free_dquot(dquot); - atomic_dec(&dquot->dq_count); - continue; - } + WARN_ON_ONCE(atomic_read(&dquot->dq_count)); + /* + * Note that DQ_RELEASING_B protects us from racing with + * invalidate_dquots() calls so we are safe to work with the + * dquot even after we drop dq_list_lock. + */ if (dquot_dirty(dquot)) { spin_unlock(&dq_list_lock); /* Commit dquot before releasing */ @@ -834,7 +846,6 @@ restart: } /* Dquot is inactive and clean, now move it to free list */ remove_free_dquot(dquot); - atomic_dec(&dquot->dq_count); put_dquot_last(dquot); } spin_unlock(&dq_list_lock); @@ -875,6 +886,7 @@ void dqput(struct dquot *dquot) BUG_ON(!list_empty(&dquot->dq_free)); #endif put_releasing_dquots(dquot); + atomic_dec(&dquot->dq_count); spin_unlock(&dq_list_lock); queue_delayed_work(system_unbound_wq, "a_release_work, 1); } @@ -963,7 +975,7 @@ we_slept: dqstats_inc(DQST_LOOKUPS); } /* Wait for dq_lock - after this we know that either dquot_release() is - * already finished or it will be canceled due to dq_count > 1 test */ + * already finished or it will be canceled due to dq_count > 0 test */ wait_on_dquot(dquot); /* Read the dquot / allocate space in quota file */ if (!dquot_active(dquot)) { diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 015bfe4e4524..171c912af50f 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -90,8 +90,7 @@ static int flush_commit_list(struct super_block *s, static int can_dirty(struct reiserfs_journal_cnode *cn); static int journal_join(struct reiserfs_transaction_handle *th, struct super_block *sb); -static void release_journal_dev(struct super_block *super, - struct reiserfs_journal *journal); +static void release_journal_dev(struct reiserfs_journal *journal); static void dirty_one_transaction(struct super_block *s, struct reiserfs_journal_list *jl); static void flush_async_commits(struct work_struct *work); @@ -1893,7 +1892,7 @@ static void free_journal_ram(struct super_block *sb) * j_header_bh is on the journal dev, make sure * not to release the journal dev until we brelse j_header_bh */ - release_journal_dev(sb, journal); + release_journal_dev(journal); vfree(journal); } @@ -2387,7 +2386,7 @@ static int journal_read(struct super_block *sb) cur_dblock = SB_ONDISK_JOURNAL_1st_BLOCK(sb); reiserfs_info(sb, "checking transaction log (%pg)\n", - journal->j_dev_bd); + journal->j_bdev_handle->bdev); start = ktime_get_seconds(); /* @@ -2448,7 +2447,7 @@ static int journal_read(struct super_block *sb) * device and journal device to be the same */ d_bh = - reiserfs_breada(journal->j_dev_bd, cur_dblock, + reiserfs_breada(journal->j_bdev_handle->bdev, cur_dblock, sb->s_blocksize, SB_ONDISK_JOURNAL_1st_BLOCK(sb) + SB_ONDISK_JOURNAL_SIZE(sb)); @@ -2587,17 +2586,11 @@ static void journal_list_init(struct super_block *sb) SB_JOURNAL(sb)->j_current_jl = alloc_journal_list(sb); } -static void release_journal_dev(struct super_block *super, - struct reiserfs_journal *journal) +static void release_journal_dev(struct reiserfs_journal *journal) { - if (journal->j_dev_bd != NULL) { - void *holder = NULL; - - if (journal->j_dev_bd->bd_dev != super->s_dev) - holder = journal; - - blkdev_put(journal->j_dev_bd, holder); - journal->j_dev_bd = NULL; + if (journal->j_bdev_handle) { + bdev_release(journal->j_bdev_handle); + journal->j_bdev_handle = NULL; } } @@ -2612,7 +2605,7 @@ static int journal_init_dev(struct super_block *super, result = 0; - journal->j_dev_bd = NULL; + journal->j_bdev_handle = NULL; jdev = SB_ONDISK_JOURNAL_DEVICE(super) ? new_decode_dev(SB_ONDISK_JOURNAL_DEVICE(super)) : super->s_dev; @@ -2623,36 +2616,37 @@ static int journal_init_dev(struct super_block *super, if ((!jdev_name || !jdev_name[0])) { if (jdev == super->s_dev) holder = NULL; - journal->j_dev_bd = blkdev_get_by_dev(jdev, blkdev_mode, holder, - NULL); - if (IS_ERR(journal->j_dev_bd)) { - result = PTR_ERR(journal->j_dev_bd); - journal->j_dev_bd = NULL; + journal->j_bdev_handle = bdev_open_by_dev(jdev, blkdev_mode, + holder, NULL); + if (IS_ERR(journal->j_bdev_handle)) { + result = PTR_ERR(journal->j_bdev_handle); + journal->j_bdev_handle = NULL; reiserfs_warning(super, "sh-458", "cannot init journal device unknown-block(%u,%u): %i", MAJOR(jdev), MINOR(jdev), result); return result; } else if (jdev != super->s_dev) - set_blocksize(journal->j_dev_bd, super->s_blocksize); + set_blocksize(journal->j_bdev_handle->bdev, + super->s_blocksize); return 0; } - journal->j_dev_bd = blkdev_get_by_path(jdev_name, blkdev_mode, holder, - NULL); - if (IS_ERR(journal->j_dev_bd)) { - result = PTR_ERR(journal->j_dev_bd); - journal->j_dev_bd = NULL; + journal->j_bdev_handle = bdev_open_by_path(jdev_name, blkdev_mode, + holder, NULL); + if (IS_ERR(journal->j_bdev_handle)) { + result = PTR_ERR(journal->j_bdev_handle); + journal->j_bdev_handle = NULL; reiserfs_warning(super, "sh-457", "journal_init_dev: Cannot open '%s': %i", jdev_name, result); return result; } - set_blocksize(journal->j_dev_bd, super->s_blocksize); + set_blocksize(journal->j_bdev_handle->bdev, super->s_blocksize); reiserfs_info(super, "journal_init_dev: journal device: %pg\n", - journal->j_dev_bd); + journal->j_bdev_handle->bdev); return 0; } @@ -2810,7 +2804,7 @@ int journal_init(struct super_block *sb, const char *j_dev_name, "journal header magic %x (device %pg) does " "not match to magic found in super block %x", jh->jh_journal.jp_journal_magic, - journal->j_dev_bd, + journal->j_bdev_handle->bdev, sb_jp_journal_magic(rs)); brelse(bhjh); goto free_and_return; @@ -2834,7 +2828,7 @@ int journal_init(struct super_block *sb, const char *j_dev_name, reiserfs_info(sb, "journal params: device %pg, size %u, " "journal first block %u, max trans len %u, max batch %u, " "max commit age %u, max trans age %u\n", - journal->j_dev_bd, + journal->j_bdev_handle->bdev, SB_ONDISK_JOURNAL_SIZE(sb), SB_ONDISK_JOURNAL_1st_BLOCK(sb), journal->j_trans_max, diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c index 3dba8acf4e83..83cb9402e0f9 100644 --- a/fs/reiserfs/procfs.c +++ b/fs/reiserfs/procfs.c @@ -354,7 +354,7 @@ static int show_journal(struct seq_file *m, void *unused) "prepare: \t%12lu\n" "prepare_retry: \t%12lu\n", DJP(jp_journal_1st_block), - SB_JOURNAL(sb)->j_dev_bd, + SB_JOURNAL(sb)->j_bdev_handle->bdev, DJP(jp_journal_dev), DJP(jp_journal_size), DJP(jp_journal_trans_max), diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 7d12b8c5b2fa..725667880e62 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -299,7 +299,7 @@ struct reiserfs_journal { /* oldest journal block. start here for traverse */ struct reiserfs_journal_cnode *j_first; - struct block_device *j_dev_bd; + struct bdev_handle *j_bdev_handle; /* first block on s_dev of reserved area journal */ int j_1st_reserved_block; @@ -1165,7 +1165,7 @@ static inline int bmap_would_wrap(unsigned bmap_nr) return bmap_nr > ((1LL << 16) - 1); } -extern const struct xattr_handler *reiserfs_xattr_handlers[]; +extern const struct xattr_handler * const reiserfs_xattr_handlers[]; /* * this says about version of key of all items (but stat data) the @@ -2809,9 +2809,12 @@ struct reiserfs_journal_header { #define journal_hash(t,sb,block) ((t)[_jhashfn((sb),(block)) & JBH_HASH_MASK]) /* We need these to make journal.c code more readable */ -#define journal_find_get_block(s, block) __find_get_block(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize) -#define journal_getblk(s, block) __getblk(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize) -#define journal_bread(s, block) __bread(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize) +#define journal_find_get_block(s, block) __find_get_block(\ + SB_JOURNAL(s)->j_bdev_handle->bdev, block, s->s_blocksize) +#define journal_getblk(s, block) __getblk(SB_JOURNAL(s)->j_bdev_handle->bdev,\ + block, s->s_blocksize) +#define journal_bread(s, block) __bread(SB_JOURNAL(s)->j_bdev_handle->bdev,\ + block, s->s_blocksize) enum reiserfs_bh_state_bits { BH_JDirty = BH_PrivateStart, /* buffer is in current transaction */ diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 6000964c2b80..998035a6388e 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -780,7 +780,7 @@ static inline bool reiserfs_posix_acl_list(const char *name, } /* This is the implementation for the xattr plugin infrastructure */ -static inline bool reiserfs_xattr_list(const struct xattr_handler **handlers, +static inline bool reiserfs_xattr_list(const struct xattr_handler * const *handlers, const char *name, struct dentry *dentry) { if (handlers) { @@ -911,7 +911,7 @@ static int create_privroot(struct dentry *dentry) { return 0; } #endif /* Actual operations that are exported to VFS-land */ -const struct xattr_handler *reiserfs_xattr_handlers[] = { +const struct xattr_handler * const reiserfs_xattr_handlers[] = { #ifdef CONFIG_REISERFS_FS_XATTR &reiserfs_xattr_user_handler, &reiserfs_xattr_trusted_handler, diff --git a/fs/romfs/super.c b/fs/romfs/super.c index c09d81b548e4..545ad44f96b8 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -594,7 +594,7 @@ static void romfs_kill_sb(struct super_block *sb) #ifdef CONFIG_ROMFS_ON_BLOCK if (sb->s_bdev) { sync_blockdev(sb->s_bdev); - blkdev_put(sb->s_bdev, sb); + bdev_release(sb->s_bdev_handle); } #endif } diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index e2be8aedb26e..fe1bf5b6e0cb 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -15,6 +15,7 @@ static struct cached_fid *init_cached_dir(const char *path); static void free_cached_dir(struct cached_fid *cfid); static void smb2_close_cached_fid(struct kref *ref); +static void cfids_laundromat_worker(struct work_struct *work); static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, const char *path, @@ -169,15 +170,18 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, return -ENOENT; } /* - * At this point we either have a lease already and we can just - * return it. If not we are guaranteed to be the only thread accessing - * this cfid. + * Return cached fid if it has a lease. Otherwise, it is either a new + * entry or laundromat worker removed it from @cfids->entries. Caller + * will put last reference if the latter. */ + spin_lock(&cfids->cfid_list_lock); if (cfid->has_lease) { + spin_unlock(&cfids->cfid_list_lock); *ret_cfid = cfid; kfree(utf16_path); return 0; } + spin_unlock(&cfids->cfid_list_lock); /* * Skip any prefix paths in @path as lookup_positive_unlocked() ends up @@ -294,9 +298,11 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, goto oshr_free; } } + spin_lock(&cfids->cfid_list_lock); cfid->dentry = dentry; cfid->time = jiffies; cfid->has_lease = true; + spin_unlock(&cfids->cfid_list_lock); oshr_free: kfree(utf16_path); @@ -305,24 +311,28 @@ oshr_free: free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); spin_lock(&cfids->cfid_list_lock); - if (rc && !cfid->has_lease) { - if (cfid->on_list) { - list_del(&cfid->entry); - cfid->on_list = false; - cfids->num_entries--; + if (!cfid->has_lease) { + if (rc) { + if (cfid->on_list) { + list_del(&cfid->entry); + cfid->on_list = false; + cfids->num_entries--; + } + rc = -ENOENT; + } else { + /* + * We are guaranteed to have two references at this + * point. One for the caller and one for a potential + * lease. Release the Lease-ref so that the directory + * will be closed when the caller closes the cached + * handle. + */ + spin_unlock(&cfids->cfid_list_lock); + kref_put(&cfid->refcount, smb2_close_cached_fid); + goto out; } - rc = -ENOENT; } spin_unlock(&cfids->cfid_list_lock); - if (!rc && !cfid->has_lease) { - /* - * We are guaranteed to have two references at this point. - * One for the caller and one for a potential lease. - * Release the Lease-ref so that the directory will be closed - * when the caller closes the cached handle. - */ - kref_put(&cfid->refcount, smb2_close_cached_fid); - } if (rc) { if (cfid->is_open) SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, @@ -330,7 +340,7 @@ oshr_free: free_cached_dir(cfid); cfid = NULL; } - +out: if (rc == 0) { *ret_cfid = cfid; atomic_inc(&tcon->num_remote_opens); @@ -572,53 +582,51 @@ static void free_cached_dir(struct cached_fid *cfid) kfree(cfid); } -static int -cifs_cfids_laundromat_thread(void *p) +static void cfids_laundromat_worker(struct work_struct *work) { - struct cached_fids *cfids = p; + struct cached_fids *cfids; struct cached_fid *cfid, *q; - struct list_head entry; + LIST_HEAD(entry); - while (!kthread_should_stop()) { - ssleep(1); - INIT_LIST_HEAD(&entry); - if (kthread_should_stop()) - return 0; - spin_lock(&cfids->cfid_list_lock); - list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { - if (time_after(jiffies, cfid->time + HZ * dir_cache_timeout)) { - list_del(&cfid->entry); - list_add(&cfid->entry, &entry); - cfids->num_entries--; - } - } - spin_unlock(&cfids->cfid_list_lock); + cfids = container_of(work, struct cached_fids, laundromat_work.work); - list_for_each_entry_safe(cfid, q, &entry, entry) { + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { + if (cfid->time && + time_after(jiffies, cfid->time + HZ * dir_cache_timeout)) { cfid->on_list = false; - list_del(&cfid->entry); + list_move(&cfid->entry, &entry); + cfids->num_entries--; + /* To prevent race with smb2_cached_lease_break() */ + kref_get(&cfid->refcount); + } + } + spin_unlock(&cfids->cfid_list_lock); + + list_for_each_entry_safe(cfid, q, &entry, entry) { + list_del(&cfid->entry); + /* + * Cancel and wait for the work to finish in case we are racing + * with it. + */ + cancel_work_sync(&cfid->lease_break); + if (cfid->has_lease) { /* - * Cancel, and wait for the work to finish in - * case we are racing with it. + * Our lease has not yet been cancelled from the server + * so we need to drop the reference. */ - cancel_work_sync(&cfid->lease_break); - if (cfid->has_lease) { - /* - * We lease has not yet been cancelled from - * the server so we need to drop the reference. - */ - spin_lock(&cfids->cfid_list_lock); - cfid->has_lease = false; - spin_unlock(&cfids->cfid_list_lock); - kref_put(&cfid->refcount, smb2_close_cached_fid); - } + spin_lock(&cfids->cfid_list_lock); + cfid->has_lease = false; + spin_unlock(&cfids->cfid_list_lock); + kref_put(&cfid->refcount, smb2_close_cached_fid); } + /* Drop the extra reference opened above */ + kref_put(&cfid->refcount, smb2_close_cached_fid); } - - return 0; + queue_delayed_work(cifsiod_wq, &cfids->laundromat_work, + dir_cache_timeout * HZ); } - struct cached_fids *init_cached_dirs(void) { struct cached_fids *cfids; @@ -629,19 +637,10 @@ struct cached_fids *init_cached_dirs(void) spin_lock_init(&cfids->cfid_list_lock); INIT_LIST_HEAD(&cfids->entries); - /* - * since we're in a cifs function already, we know that - * this will succeed. No need for try_module_get(). - */ - __module_get(THIS_MODULE); - cfids->laundromat = kthread_run(cifs_cfids_laundromat_thread, - cfids, "cifsd-cfid-laundromat"); - if (IS_ERR(cfids->laundromat)) { - cifs_dbg(VFS, "Failed to start cfids laundromat thread.\n"); - kfree(cfids); - module_put(THIS_MODULE); - return NULL; - } + INIT_DELAYED_WORK(&cfids->laundromat_work, cfids_laundromat_worker); + queue_delayed_work(cifsiod_wq, &cfids->laundromat_work, + dir_cache_timeout * HZ); + return cfids; } @@ -657,11 +656,7 @@ void free_cached_dirs(struct cached_fids *cfids) if (cfids == NULL) return; - if (cfids->laundromat) { - kthread_stop(cfids->laundromat); - cfids->laundromat = NULL; - module_put(THIS_MODULE); - } + cancel_delayed_work_sync(&cfids->laundromat_work); spin_lock(&cfids->cfid_list_lock); list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h index a82ff2cea789..81ba0fd5cc16 100644 --- a/fs/smb/client/cached_dir.h +++ b/fs/smb/client/cached_dir.h @@ -57,7 +57,7 @@ struct cached_fids { spinlock_t cfid_list_lock; int num_entries; struct list_head entries; - struct task_struct *laundromat; + struct delayed_work laundromat_work; }; extern struct cached_fids *init_cached_dirs(void); diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 41daebd220ff..8ca3d7606bb4 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -127,7 +127,7 @@ extern int cifs_symlink(struct mnt_idmap *idmap, struct inode *inode, struct dentry *direntry, const char *symname); #ifdef CONFIG_CIFS_XATTR -extern const struct xattr_handler *cifs_xattr_handlers[]; +extern const struct xattr_handler * const cifs_xattr_handlers[]; extern ssize_t cifs_listxattr(struct dentry *, char *, size_t); #else # define cifs_xattr_handlers NULL diff --git a/fs/smb/client/xattr.c b/fs/smb/client/xattr.c index 4ad5531686d8..ac199160bce6 100644 --- a/fs/smb/client/xattr.c +++ b/fs/smb/client/xattr.c @@ -478,7 +478,7 @@ static const struct xattr_handler smb3_ntsd_full_xattr_handler = { .set = cifs_xattr_set, }; -const struct xattr_handler *cifs_xattr_handlers[] = { +const struct xattr_handler * const cifs_xattr_handlers[] = { &cifs_user_xattr_handler, &cifs_os2_xattr_handler, &cifs_cifs_acl_xattr_handler, diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index acfb57de3238..658209839729 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -231,11 +231,12 @@ void set_smb2_rsp_status(struct ksmbd_work *work, __le32 err) { struct smb2_hdr *rsp_hdr; - if (work->next_smb2_rcv_hdr_off) - rsp_hdr = ksmbd_resp_buf_next(work); - else - rsp_hdr = smb2_get_msg(work->response_buf); + rsp_hdr = smb2_get_msg(work->response_buf); rsp_hdr->Status = err; + + work->iov_idx = 0; + work->iov_cnt = 0; + work->next_smb2_rcv_hdr_off = 0; smb2_set_err_rsp(work); } @@ -6151,12 +6152,12 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) memcpy(aux_payload_buf, rpc_resp->payload, rpc_resp->payload_sz); nbytes = rpc_resp->payload_sz; - kvfree(rpc_resp); err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); if (err) goto out; + kvfree(rpc_resp); } else { err = ksmbd_iov_pin_rsp(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer)); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index c4b80ab7df74..c91eac6514dd 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -106,7 +106,7 @@ int ksmbd_query_inode_status(struct inode *inode) ci = __ksmbd_inode_lookup(inode); if (ci) { ret = KSMBD_INODE_STATUS_OK; - if (ci->m_flags & S_DEL_PENDING) + if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)) ret = KSMBD_INODE_STATUS_PENDING_DELETE; atomic_dec(&ci->m_count); } @@ -116,7 +116,7 @@ int ksmbd_query_inode_status(struct inode *inode) bool ksmbd_inode_pending_delete(struct ksmbd_file *fp) { - return (fp->f_ci->m_flags & S_DEL_PENDING); + return (fp->f_ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)); } void ksmbd_set_inode_pending_delete(struct ksmbd_file *fp) @@ -603,6 +603,9 @@ err_out: void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, unsigned int state) { + if (!fp) + return; + write_lock(&ft->lock); fp->f_state = state; write_unlock(&ft->lock); diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index a6164fdf9435..5a756e6790b5 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -111,4 +111,4 @@ extern const struct address_space_operations squashfs_symlink_aops; extern const struct inode_operations squashfs_symlink_inode_ops; /* xattr.c */ -extern const struct xattr_handler *squashfs_xattr_handlers[]; +extern const struct xattr_handler * const squashfs_xattr_handlers[]; diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c index e1e3f3dd5a06..ce6608cabd49 100644 --- a/fs/squashfs/xattr.c +++ b/fs/squashfs/xattr.c @@ -262,7 +262,7 @@ static const struct xattr_handler *squashfs_xattr_handler(int type) } } -const struct xattr_handler *squashfs_xattr_handlers[] = { +const struct xattr_handler * const squashfs_xattr_handlers[] = { &squashfs_xattr_user_handler, &squashfs_xattr_trusted_handler, &squashfs_xattr_security_handler, diff --git a/fs/super.c b/fs/super.c index 2d762ce67f6e..c7b452e12e4c 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1419,32 +1419,48 @@ EXPORT_SYMBOL(sget_dev); #ifdef CONFIG_BLOCK /* - * Lock a super block that the callers holds a reference to. + * Lock the superblock that is holder of the bdev. Returns the superblock + * pointer if we successfully locked the superblock and it is alive. Otherwise + * we return NULL and just unlock bdev->bd_holder_lock. * - * The caller needs to ensure that the super_block isn't being freed while - * calling this function, e.g. by holding a lock over the call to this function - * and the place that clears the pointer to the superblock used by this function - * before freeing the superblock. + * The function must be called with bdev->bd_holder_lock and releases it. */ -static bool super_lock_shared_active(struct super_block *sb) +static struct super_block *bdev_super_lock_shared(struct block_device *bdev) + __releases(&bdev->bd_holder_lock) { - bool born = super_lock_shared(sb); + struct super_block *sb = bdev->bd_holder; + bool born; + + lockdep_assert_held(&bdev->bd_holder_lock); + lockdep_assert_not_held(&sb->s_umount); + lockdep_assert_not_held(&bdev->bd_disk->open_mutex); + + /* Make sure sb doesn't go away from under us */ + spin_lock(&sb_lock); + sb->s_count++; + spin_unlock(&sb_lock); + mutex_unlock(&bdev->bd_holder_lock); + born = super_lock_shared(sb); if (!born || !sb->s_root || !(sb->s_flags & SB_ACTIVE)) { super_unlock_shared(sb); - return false; + put_super(sb); + return NULL; } - return true; + /* + * The superblock is active and we hold s_umount, we can drop our + * temporary reference now. + */ + put_super(sb); + return sb; } static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise) { - struct super_block *sb = bdev->bd_holder; - - /* bd_holder_lock ensures that the sb isn't freed */ - lockdep_assert_held(&bdev->bd_holder_lock); + struct super_block *sb; - if (!super_lock_shared_active(sb)) + sb = bdev_super_lock_shared(bdev); + if (!sb) return; if (!surprise) @@ -1459,11 +1475,10 @@ static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise) static void fs_bdev_sync(struct block_device *bdev) { - struct super_block *sb = bdev->bd_holder; - - lockdep_assert_held(&bdev->bd_holder_lock); + struct super_block *sb; - if (!super_lock_shared_active(sb)) + sb = bdev_super_lock_shared(bdev); + if (!sb) return; sync_filesystem(sb); super_unlock_shared(sb); @@ -1479,14 +1494,16 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc) { blk_mode_t mode = sb_open_mode(sb_flags); + struct bdev_handle *bdev_handle; struct block_device *bdev; - bdev = blkdev_get_by_dev(sb->s_dev, mode, sb, &fs_holder_ops); - if (IS_ERR(bdev)) { + bdev_handle = bdev_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops); + if (IS_ERR(bdev_handle)) { if (fc) errorf(fc, "%s: Can't open blockdev", fc->source); - return PTR_ERR(bdev); + return PTR_ERR(bdev_handle); } + bdev = bdev_handle->bdev; /* * This really should be in blkdev_get_by_dev, but right now can't due @@ -1494,7 +1511,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, * writable from userspace even for a read-only block device. */ if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { - blkdev_put(bdev, sb); + bdev_release(bdev_handle); return -EACCES; } @@ -1510,10 +1527,11 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, mutex_unlock(&bdev->bd_fsfreeze_mutex); if (fc) warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); - blkdev_put(bdev, sb); + bdev_release(bdev_handle); return -EBUSY; } spin_lock(&sb_lock); + sb->s_bdev_handle = bdev_handle; sb->s_bdev = bdev; sb->s_bdi = bdi_get(bdev->bd_disk->bdi); if (bdev_stable_writes(bdev)) @@ -1646,7 +1664,7 @@ void kill_block_super(struct super_block *sb) generic_shutdown_super(sb); if (bdev) { sync_blockdev(bdev); - blkdev_put(bdev, sb); + bdev_release(sb->s_bdev_handle); } } diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index ebb3ad6b5e7e..62633816d7d0 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -2043,7 +2043,7 @@ ssize_t ubifs_xattr_get(struct inode *host, const char *name, void *buf, size_t size); #ifdef CONFIG_UBIFS_FS_XATTR -extern const struct xattr_handler *ubifs_xattr_handlers[]; +extern const struct xattr_handler * const ubifs_xattr_handlers[]; ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size); void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum); int ubifs_purge_xattrs(struct inode *host); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 406c82eab513..0847db521984 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -735,7 +735,7 @@ static const struct xattr_handler ubifs_security_xattr_handler = { }; #endif -const struct xattr_handler *ubifs_xattr_handlers[] = { +const struct xattr_handler * const ubifs_xattr_handlers[] = { &ubifs_user_xattr_handler, &ubifs_trusted_xattr_handler, #ifdef CONFIG_UBIFS_FS_SECURITY diff --git a/fs/xattr.c b/fs/xattr.c index efd4736bc94b..09d927603433 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -56,7 +56,7 @@ strcmp_prefix(const char *a, const char *a_prefix) static const struct xattr_handler * xattr_resolve_name(struct inode *inode, const char **name) { - const struct xattr_handler **handlers = inode->i_sb->s_xattr; + const struct xattr_handler * const *handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { @@ -162,7 +162,7 @@ xattr_permission(struct mnt_idmap *idmap, struct inode *inode, int xattr_supports_user_prefix(struct inode *inode) { - const struct xattr_handler **handlers = inode->i_sb->s_xattr; + const struct xattr_handler * const *handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { @@ -999,7 +999,7 @@ int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { - const struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr; + const struct xattr_handler *handler, * const *handlers = dentry->d_sb->s_xattr; ssize_t remaining_size = buffer_size; int err = 0; diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index e9cc481b4ddf..f9f4d694640d 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -1001,6 +1001,12 @@ xfs_ag_shrink_space( error = -ENOSPC; goto resv_init_out; } + + /* Update perag geometry */ + pag->block_count -= delta; + __xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min, + &pag->agino_max); + xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH); xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH); return 0; diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c index d98e8e77c684..090c3ead43fd 100644 --- a/fs/xfs/scrub/xfile.c +++ b/fs/xfs/scrub/xfile.c @@ -10,7 +10,6 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_format.h" #include "scrub/xfile.h" #include "scrub/xfarray.h" #include "scrub/scrub.h" diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index c1ece4a08ff4..003e157241da 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1945,8 +1945,6 @@ void xfs_free_buftarg( struct xfs_buftarg *btp) { - struct block_device *bdev = btp->bt_bdev; - unregister_shrinker(&btp->bt_shrinker); ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0); percpu_counter_destroy(&btp->bt_io_count); @@ -1954,8 +1952,8 @@ xfs_free_buftarg( fs_put_dax(btp->bt_daxdev, btp->bt_mount); /* the main block device is closed by kill_block_super */ - if (bdev != btp->bt_mount->m_super->s_bdev) - blkdev_put(bdev, btp->bt_mount->m_super); + if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev) + bdev_release(btp->bt_bdev_handle); kmem_free(btp); } @@ -1990,16 +1988,15 @@ xfs_setsize_buftarg( */ STATIC int xfs_setsize_buftarg_early( - xfs_buftarg_t *btp, - struct block_device *bdev) + xfs_buftarg_t *btp) { - return xfs_setsize_buftarg(btp, bdev_logical_block_size(bdev)); + return xfs_setsize_buftarg(btp, bdev_logical_block_size(btp->bt_bdev)); } struct xfs_buftarg * xfs_alloc_buftarg( struct xfs_mount *mp, - struct block_device *bdev) + struct bdev_handle *bdev_handle) { xfs_buftarg_t *btp; const struct dax_holder_operations *ops = NULL; @@ -2010,9 +2007,10 @@ xfs_alloc_buftarg( btp = kmem_zalloc(sizeof(*btp), KM_NOFS); btp->bt_mount = mp; - btp->bt_dev = bdev->bd_dev; - btp->bt_bdev = bdev; - btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off, + btp->bt_bdev_handle = bdev_handle; + btp->bt_dev = bdev_handle->bdev->bd_dev; + btp->bt_bdev = bdev_handle->bdev; + btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off, mp, ops); /* @@ -2022,7 +2020,7 @@ xfs_alloc_buftarg( ratelimit_state_init(&btp->bt_ioerror_rl, 30 * HZ, DEFAULT_RATELIMIT_BURST); - if (xfs_setsize_buftarg_early(btp, bdev)) + if (xfs_setsize_buftarg_early(btp)) goto error_free; if (list_lru_init(&btp->bt_lru)) diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index df8f47953bb4..ada9d310b7d3 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -98,6 +98,7 @@ typedef unsigned int xfs_buf_flags_t; */ typedef struct xfs_buftarg { dev_t bt_dev; + struct bdev_handle *bt_bdev_handle; struct block_device *bt_bdev; struct dax_device *bt_daxdev; u64 bt_dax_part_off; @@ -364,7 +365,7 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset) * Handling of buftargs. */ struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *mp, - struct block_device *bdev); + struct bdev_handle *bdev_handle); extern void xfs_free_buftarg(struct xfs_buftarg *); extern void xfs_buftarg_wait(struct xfs_buftarg *); extern void xfs_buftarg_drain(struct xfs_buftarg *); diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 746814815b1d..9ecfdcdc752f 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -62,7 +62,8 @@ xfs_extent_busy_insert_list( rb_link_node(&new->rb_node, parent, rbp); rb_insert_color(&new->rb_node, &pag->pagb_tree); - list_add(&new->list, busy_list); + /* always process discard lists in fifo order */ + list_add_tail(&new->list, busy_list); spin_unlock(&pag->pagb_lock); } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 687eff5d9e16..fdfda4fba12b 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -584,6 +584,11 @@ xfs_vn_getattr( } } + if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) { + stat->change_cookie = inode_query_iversion(inode); + stat->result_mask |= STATX_CHANGE_COOKIE; + } + /* * Note: If you add another clause to set an attribute flag, please * update attributes_mask below. diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index 4a9bbd3fe120..a7daa522e00f 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -126,8 +126,8 @@ xfs_dax_notify_ddev_failure( struct xfs_rmap_irec ri_low = { }; struct xfs_rmap_irec ri_high; struct xfs_agf *agf; - xfs_agblock_t agend; struct xfs_perag *pag; + xfs_agblock_t range_agend; pag = xfs_perag_get(mp, agno); error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); @@ -148,10 +148,10 @@ xfs_dax_notify_ddev_failure( ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno); agf = agf_bp->b_addr; - agend = min(be32_to_cpu(agf->agf_length), + range_agend = min(be32_to_cpu(agf->agf_length) - 1, ri_high.rm_startblock); notify.startblock = ri_low.rm_startblock; - notify.blockcount = agend - ri_low.rm_startblock; + notify.blockcount = range_agend + 1 - ri_low.rm_startblock; error = xfs_rmap_query_range(cur, &ri_low, &ri_high, xfs_dax_failure_fn, ¬ify); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 819a3568b28f..f0ae07828153 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -361,14 +361,15 @@ STATIC int xfs_blkdev_get( xfs_mount_t *mp, const char *name, - struct block_device **bdevp) + struct bdev_handle **handlep) { int error = 0; - *bdevp = blkdev_get_by_path(name, BLK_OPEN_READ | BLK_OPEN_WRITE, - mp->m_super, &fs_holder_ops); - if (IS_ERR(*bdevp)) { - error = PTR_ERR(*bdevp); + *handlep = bdev_open_by_path(name, BLK_OPEN_READ | BLK_OPEN_WRITE, + mp->m_super, &fs_holder_ops); + if (IS_ERR(*handlep)) { + error = PTR_ERR(*handlep); + *handlep = NULL; xfs_warn(mp, "Invalid device [%s], error=%d", name, error); } @@ -433,7 +434,7 @@ xfs_open_devices( { struct super_block *sb = mp->m_super; struct block_device *ddev = sb->s_bdev; - struct block_device *logdev = NULL, *rtdev = NULL; + struct bdev_handle *logdev_handle = NULL, *rtdev_handle = NULL; int error; /* @@ -446,17 +447,19 @@ xfs_open_devices( * Open real time and log devices - order is important. */ if (mp->m_logname) { - error = xfs_blkdev_get(mp, mp->m_logname, &logdev); + error = xfs_blkdev_get(mp, mp->m_logname, &logdev_handle); if (error) goto out_relock; } if (mp->m_rtname) { - error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev); + error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev_handle); if (error) goto out_close_logdev; - if (rtdev == ddev || rtdev == logdev) { + if (rtdev_handle->bdev == ddev || + (logdev_handle && + rtdev_handle->bdev == logdev_handle->bdev)) { xfs_warn(mp, "Cannot mount filesystem with identical rtdev and ddev/logdev."); error = -EINVAL; @@ -468,22 +471,25 @@ xfs_open_devices( * Setup xfs_mount buffer target pointers */ error = -ENOMEM; - mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev); + mp->m_ddev_targp = xfs_alloc_buftarg(mp, sb->s_bdev_handle); if (!mp->m_ddev_targp) goto out_close_rtdev; - if (rtdev) { - mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev); + if (rtdev_handle) { + mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev_handle); if (!mp->m_rtdev_targp) goto out_free_ddev_targ; } - if (logdev && logdev != ddev) { - mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev); + if (logdev_handle && logdev_handle->bdev != ddev) { + mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev_handle); if (!mp->m_logdev_targp) goto out_free_rtdev_targ; } else { mp->m_logdev_targp = mp->m_ddev_targp; + /* Handle won't be used, drop it */ + if (logdev_handle) + bdev_release(logdev_handle); } error = 0; @@ -497,11 +503,11 @@ out_relock: out_free_ddev_targ: xfs_free_buftarg(mp->m_ddev_targp); out_close_rtdev: - if (rtdev) - blkdev_put(rtdev, sb); + if (rtdev_handle) + bdev_release(rtdev_handle); out_close_logdev: - if (logdev && logdev != ddev) - blkdev_put(logdev, sb); + if (logdev_handle) + bdev_release(logdev_handle); goto out_relock; } diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index a3975f325f4e..987843f84d03 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -186,7 +186,7 @@ static const struct xattr_handler xfs_xattr_security_handler = { .set = xfs_xattr_set, }; -const struct xattr_handler *xfs_xattr_handlers[] = { +const struct xattr_handler * const xfs_xattr_handlers[] = { &xfs_xattr_user_handler, &xfs_xattr_trusted_handler, &xfs_xattr_security_handler, diff --git a/fs/xfs/xfs_xattr.h b/fs/xfs/xfs_xattr.h index 2b09133b1b9b..cec766cad26c 100644 --- a/fs/xfs/xfs_xattr.h +++ b/fs/xfs/xfs_xattr.h @@ -8,6 +8,6 @@ int xfs_attr_change(struct xfs_da_args *args); -extern const struct xattr_handler *xfs_xattr_handlers[]; +extern const struct xattr_handler * const xfs_xattr_handlers[]; #endif /* __XFS_XATTR_H__ */ |